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
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
|
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2000-2006 Silicon Graphics, Inc.
* All Rights Reserved.
*/
#include "xfs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
#include "xfs_bmap.h"
#include "xfs_alloc.h"
#include "xfs_fsops.h"
#include "xfs_trans.h"
#include "xfs_buf_item.h"
#include "xfs_log.h"
#include "xfs_log_priv.h"
#include "xfs_dir2.h"
#include "xfs_extfree_item.h"
#include "xfs_mru_cache.h"
#include "xfs_inode_item.h"
#include "xfs_icache.h"
#include "xfs_trace.h"
#include "xfs_icreate_item.h"
#include "xfs_filestream.h"
#include "xfs_quota.h"
#include "xfs_sysfs.h"
#include "xfs_ondisk.h"
#include "xfs_rmap_item.h"
#include "xfs_refcount_item.h"
#include "xfs_bmap_item.h"
#include "xfs_reflink.h"
#include "xfs_pwork.h"
#include "xfs_ag.h"
#include "xfs_defer.h"
#include "xfs_attr_item.h"
#include "xfs_xattr.h"
#include "xfs_iunlink_item.h"
#include "xfs_dahash_test.h"
#include "xfs_rtbitmap.h"
#include "scrub/stats.h"
#include <linux/magic.h>
#include <linux/fs_context.h>
#include <linux/fs_parser.h>
static const struct super_operations xfs_super_operations;
static struct dentry *xfs_debugfs; /* top-level xfs debugfs dir */
static struct kset *xfs_kset; /* top-level xfs sysfs dir */
#ifdef DEBUG
static struct xfs_kobj xfs_dbg_kobj; /* global debug sysfs attrs */
#endif
enum xfs_dax_mode {
XFS_DAX_INODE = 0,
XFS_DAX_ALWAYS = 1,
XFS_DAX_NEVER = 2,
};
static void
xfs_mount_set_dax_mode(
struct xfs_mount *mp,
enum xfs_dax_mode mode)
{
switch (mode) {
case XFS_DAX_INODE:
mp->m_features &= ~(XFS_FEAT_DAX_ALWAYS | XFS_FEAT_DAX_NEVER);
break;
case XFS_DAX_ALWAYS:
mp->m_features |= XFS_FEAT_DAX_ALWAYS;
mp->m_features &= ~XFS_FEAT_DAX_NEVER;
break;
case XFS_DAX_NEVER:
mp->m_features |= XFS_FEAT_DAX_NEVER;
mp->m_features &= ~XFS_FEAT_DAX_ALWAYS;
break;
}
}
static const struct constant_table dax_param_enums[] = {
{"inode", XFS_DAX_INODE },
{"always", XFS_DAX_ALWAYS },
{"never", XFS_DAX_NEVER },
{}
};
/*
* Table driven mount option parser.
*/
enum {
Opt_logbufs, Opt_logbsize, Opt_logdev, Opt_rtdev,
Opt_wsync, Opt_noalign, Opt_swalloc, Opt_sunit, Opt_swidth, Opt_nouuid,
Opt_grpid, Opt_nogrpid, Opt_bsdgroups, Opt_sysvgroups,
Opt_allocsize, Opt_norecovery, Opt_inode64, Opt_inode32, Opt_ikeep,
Opt_noikeep, Opt_largeio, Opt_nolargeio, Opt_attr2, Opt_noattr2,
Opt_filestreams, Opt_quota, Opt_noquota, Opt_usrquota, Opt_grpquota,
Opt_prjquota, Opt_uquota, Opt_gquota, Opt_pquota,
Opt_uqnoenforce, Opt_gqnoenforce, Opt_pqnoenforce, Opt_qnoenforce,
Opt_discard, Opt_nodiscard, Opt_dax, Opt_dax_enum,
};
static const struct fs_parameter_spec xfs_fs_parameters[] = {
fsparam_u32("logbufs", Opt_logbufs),
fsparam_string("logbsize", Opt_logbsize),
fsparam_string("logdev", Opt_logdev),
fsparam_string("rtdev", Opt_rtdev),
fsparam_flag("wsync", Opt_wsync),
fsparam_flag("noalign", Opt_noalign),
fsparam_flag("swalloc", Opt_swalloc),
fsparam_u32("sunit", Opt_sunit),
fsparam_u32("swidth", Opt_swidth),
fsparam_flag("nouuid", Opt_nouuid),
fsparam_flag("grpid", Opt_grpid),
fsparam_flag("nogrpid", Opt_nogrpid),
fsparam_flag("bsdgroups", Opt_bsdgroups),
fsparam_flag("sysvgroups", Opt_sysvgroups),
fsparam_string("allocsize", Opt_allocsize),
fsparam_flag("norecovery", Opt_norecovery),
fsparam_flag("inode64", Opt_inode64),
fsparam_flag("inode32", Opt_inode32),
fsparam_flag("ikeep", Opt_ikeep),
fsparam_flag("noikeep", Opt_noikeep),
fsparam_flag("largeio", Opt_largeio),
fsparam_flag("nolargeio", Opt_nolargeio),
fsparam_flag("attr2", Opt_attr2),
fsparam_flag("noattr2", Opt_noattr2),
fsparam_flag("filestreams", Opt_filestreams),
fsparam_flag("quota", Opt_quota),
fsparam_flag("noquota", Opt_noquota),
fsparam_flag("usrquota", Opt_usrquota),
fsparam_flag("grpquota", Opt_grpquota),
fsparam_flag("prjquota", Opt_prjquota),
fsparam_flag("uquota", Opt_uquota),
fsparam_flag("gquota", Opt_gquota),
fsparam_flag("pquota", Opt_pquota),
fsparam_flag("uqnoenforce", Opt_uqnoenforce),
fsparam_flag("gqnoenforce", Opt_gqnoenforce),
fsparam_flag("pqnoenforce", Opt_pqnoenforce),
fsparam_flag("qnoenforce", Opt_qnoenforce),
fsparam_flag("discard", Opt_discard),
fsparam_flag("nodiscard", Opt_nodiscard),
fsparam_flag("dax", Opt_dax),
fsparam_enum("dax", Opt_dax_enum, dax_param_enums),
{}
};
struct proc_xfs_info {
uint64_t flag;
char *str;
};
static int
xfs_fs_show_options(
struct seq_file *m,
struct dentry *root)
{
static struct proc_xfs_info xfs_info_set[] = {
/* the few simple ones we can get from the mount struct */
{ XFS_FEAT_IKEEP, ",ikeep" },
{ XFS_FEAT_WSYNC, ",wsync" },
{ XFS_FEAT_NOALIGN, ",noalign" },
{ XFS_FEAT_SWALLOC, ",swalloc" },
{ XFS_FEAT_NOUUID, ",nouuid" },
{ XFS_FEAT_NORECOVERY, ",norecovery" },
{ XFS_FEAT_ATTR2, ",attr2" },
{ XFS_FEAT_FILESTREAMS, ",filestreams" },
{ XFS_FEAT_GRPID, ",grpid" },
{ XFS_FEAT_DISCARD, ",discard" },
{ XFS_FEAT_LARGE_IOSIZE, ",largeio" },
{ XFS_FEAT_DAX_ALWAYS, ",dax=always" },
{ XFS_FEAT_DAX_NEVER, ",dax=never" },
{ 0, NULL }
};
struct xfs_mount *mp = XFS_M(root->d_sb);
struct proc_xfs_info *xfs_infop;
for (xfs_infop = xfs_info_set; xfs_infop->flag; xfs_infop++) {
if (mp->m_features & xfs_infop->flag)
seq_puts(m, xfs_infop->str);
}
seq_printf(m, ",inode%d", xfs_has_small_inums(mp) ? 32 : 64);
if (xfs_has_allocsize(mp))
seq_printf(m, ",allocsize=%dk",
(1 << mp->m_allocsize_log) >> 10);
if (mp->m_logbufs > 0)
seq_printf(m, ",logbufs=%d", mp->m_logbufs);
if (mp->m_logbsize > 0)
seq_printf(m, ",logbsize=%dk", mp->m_logbsize >> 10);
if (mp->m_logname)
seq_show_option(m, "logdev", mp->m_logname);
if (mp->m_rtname)
seq_show_option(m, "rtdev", mp->m_rtname);
if (mp->m_dalign > 0)
seq_printf(m, ",sunit=%d",
(int)XFS_FSB_TO_BB(mp, mp->m_dalign));
if (mp->m_swidth > 0)
seq_printf(m, ",swidth=%d",
(int)XFS_FSB_TO_BB(mp, mp->m_swidth));
if (mp->m_qflags & XFS_UQUOTA_ENFD)
seq_puts(m, ",usrquota");
else if (mp->m_qflags & XFS_UQUOTA_ACCT)
seq_puts(m, ",uqnoenforce");
if (mp->m_qflags & XFS_PQUOTA_ENFD)
seq_puts(m, ",prjquota");
else if (mp->m_qflags & XFS_PQUOTA_ACCT)
seq_puts(m, ",pqnoenforce");
if (mp->m_qflags & XFS_GQUOTA_ENFD)
seq_puts(m, ",grpquota");
else if (mp->m_qflags & XFS_GQUOTA_ACCT)
seq_puts(m, ",gqnoenforce");
if (!(mp->m_qflags & XFS_ALL_QUOTA_ACCT))
seq_puts(m, ",noquota");
return 0;
}
static bool
xfs_set_inode_alloc_perag(
struct xfs_perag *pag,
xfs_ino_t ino,
xfs_agnumber_t max_metadata)
{
if (!xfs_is_inode32(pag->pag_mount)) {
set_bit(XFS_AGSTATE_ALLOWS_INODES, &pag->pag_opstate);
clear_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate);
return false;
}
if (ino > XFS_MAXINUMBER_32) {
clear_bit(XFS_AGSTATE_ALLOWS_INODES, &pag->pag_opstate);
clear_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate);
return false;
}
set_bit(XFS_AGSTATE_ALLOWS_INODES, &pag->pag_opstate);
if (pag->pag_agno < max_metadata)
set_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate);
else
clear_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate);
return true;
}
/*
* Set parameters for inode allocation heuristics, taking into account
* filesystem size and inode32/inode64 mount options; i.e. specifically
* whether or not XFS_FEAT_SMALL_INUMS is set.
*
* Inode allocation patterns are altered only if inode32 is requested
* (XFS_FEAT_SMALL_INUMS), and the filesystem is sufficiently large.
* If altered, XFS_OPSTATE_INODE32 is set as well.
*
* An agcount independent of that in the mount structure is provided
* because in the growfs case, mp->m_sb.sb_agcount is not yet updated
* to the potentially higher ag count.
*
* Returns the maximum AG index which may contain inodes.
*/
xfs_agnumber_t
xfs_set_inode_alloc(
struct xfs_mount *mp,
xfs_agnumber_t agcount)
{
xfs_agnumber_t index;
xfs_agnumber_t maxagi = 0;
xfs_sb_t *sbp = &mp->m_sb;
xfs_agnumber_t max_metadata;
xfs_agino_t agino;
xfs_ino_t ino;
/*
* Calculate how much should be reserved for inodes to meet
* the max inode percentage. Used only for inode32.
*/
if (M_IGEO(mp)->maxicount) {
uint64_t icount;
icount = sbp->sb_dblocks * sbp->sb_imax_pct;
do_div(icount, 100);
icount += sbp->sb_agblocks - 1;
do_div(icount, sbp->sb_agblocks);
max_metadata = icount;
} else {
max_metadata = agcount;
}
/* Get the last possible inode in the filesystem */
agino = XFS_AGB_TO_AGINO(mp, sbp->sb_agblocks - 1);
ino = XFS_AGINO_TO_INO(mp, agcount - 1, agino);
/*
* If user asked for no more than 32-bit inodes, and the fs is
* sufficiently large, set XFS_OPSTATE_INODE32 if we must alter
* the allocator to accommodate the request.
*/
if (xfs_has_small_inums(mp) && ino > XFS_MAXINUMBER_32)
set_bit(XFS_OPSTATE_INODE32, &mp->m_opstate);
else
clear_bit(XFS_OPSTATE_INODE32, &mp->m_opstate);
for (index = 0; index < agcount; index++) {
struct xfs_perag *pag;
ino = XFS_AGINO_TO_INO(mp, index, agino);
pag = xfs_perag_get(mp, index);
if (xfs_set_inode_alloc_perag(pag, ino, max_metadata))
maxagi++;
xfs_perag_put(pag);
}
return xfs_is_inode32(mp) ? maxagi : agcount;
}
static int
xfs_setup_dax_always(
struct xfs_mount *mp)
{
if (!mp->m_ddev_targp->bt_daxdev &&
(!mp->m_rtdev_targp || !mp->m_rtdev_targp->bt_daxdev)) {
xfs_alert(mp,
"DAX unsupported by block device. Turning off DAX.");
goto disable_dax;
}
if (mp->m_super->s_blocksize != PAGE_SIZE) {
xfs_alert(mp,
"DAX not supported for blocksize. Turning off DAX.");
goto disable_dax;
}
if (xfs_has_reflink(mp) &&
bdev_is_partition(mp->m_ddev_targp->bt_bdev)) {
xfs_alert(mp,
"DAX and reflink cannot work with multi-partitions!");
return -EINVAL;
}
xfs_warn(mp, "DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
return 0;
disable_dax:
xfs_mount_set_dax_mode(mp, XFS_DAX_NEVER);
return 0;
}
STATIC int
xfs_blkdev_get(
xfs_mount_t *mp,
const char *name,
struct bdev_handle **handlep)
{
int error = 0;
*handlep = bdev_open_by_path(name,
BLK_OPEN_READ | BLK_OPEN_WRITE | BLK_OPEN_RESTRICT_WRITES,
mp->m_super, &fs_holder_ops);
if (IS_ERR(*handlep)) {
error = PTR_ERR(*handlep);
*handlep = NULL;
xfs_warn(mp, "Invalid device [%s], error=%d", name, error);
}
return error;
}
STATIC void
xfs_shutdown_devices(
struct xfs_mount *mp)
{
/*
* Udev is triggered whenever anyone closes a block device or unmounts
* a file systemm on a block device.
* The default udev rules invoke blkid to read the fs super and create
* symlinks to the bdev under /dev/disk. For this, it uses buffered
* reads through the page cache.
*
* xfs_db also uses buffered reads to examine metadata. There is no
* coordination between xfs_db and udev, which means that they can run
* concurrently. Note there is no coordination between the kernel and
* blkid either.
*
* On a system with 64k pages, the page cache can cache the superblock
* and the root inode (and hence the root directory) with the same 64k
* page. If udev spawns blkid after the mkfs and the system is busy
* enough that it is still running when xfs_db starts up, they'll both
* read from the same page in the pagecache.
*
* The unmount writes updated inode metadata to disk directly. The XFS
* buffer cache does not use the bdev pagecache, so it needs to
* invalidate that pagecache on unmount. If the above scenario occurs,
* the pagecache no longer reflects what's on disk, xfs_db reads the
* stale metadata, and fails to find /a. Most of the time this succeeds
* because closing a bdev invalidates the page cache, but when processes
* race, everyone loses.
*/
if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) {
blkdev_issue_flush(mp->m_logdev_targp->bt_bdev);
invalidate_bdev(mp->m_logdev_targp->bt_bdev);
}
if (mp->m_rtdev_targp) {
blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev);
invalidate_bdev(mp->m_rtdev_targp->bt_bdev);
}
blkdev_issue_flush(mp->m_ddev_targp->bt_bdev);
invalidate_bdev(mp->m_ddev_targp->bt_bdev);
}
/*
* The file system configurations are:
* (1) device (partition) with data and internal log
* (2) logical volume with data and log subvolumes.
* (3) logical volume with data, log, and realtime subvolumes.
*
* We only have to handle opening the log and realtime volumes here if
* they are present. The data subvolume has already been opened by
* get_sb_bdev() and is stored in sb->s_bdev.
*/
STATIC int
xfs_open_devices(
struct xfs_mount *mp)
{
struct super_block *sb = mp->m_super;
struct block_device *ddev = sb->s_bdev;
struct bdev_handle *logdev_handle = NULL, *rtdev_handle = NULL;
int error;
/*
* Open real time and log devices - order is important.
*/
if (mp->m_logname) {
error = xfs_blkdev_get(mp, mp->m_logname, &logdev_handle);
if (error)
return error;
}
if (mp->m_rtname) {
error = xfs_blkdev_get(mp, mp->m_rtname, &rtdev_handle);
if (error)
goto out_close_logdev;
if (rtdev_handle->bdev == ddev ||
(logdev_handle &&
rtdev_handle->bdev == logdev_handle->bdev)) {
xfs_warn(mp,
"Cannot mount filesystem with identical rtdev and ddev/logdev.");
error = -EINVAL;
goto out_close_rtdev;
}
}
/*
* Setup xfs_mount buffer target pointers
*/
error = -ENOMEM;
mp->m_ddev_targp = xfs_alloc_buftarg(mp, sb->s_bdev_handle);
if (!mp->m_ddev_targp)
goto out_close_rtdev;
if (rtdev_handle) {
mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev_handle);
if (!mp->m_rtdev_targp)
goto out_free_ddev_targ;
}
if (logdev_handle && logdev_handle->bdev != ddev) {
mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev_handle);
if (!mp->m_logdev_targp)
goto out_free_rtdev_targ;
} else {
mp->m_logdev_targp = mp->m_ddev_targp;
/* Handle won't be used, drop it */
if (logdev_handle)
bdev_release(logdev_handle);
}
return 0;
out_free_rtdev_targ:
if (mp->m_rtdev_targp)
xfs_free_buftarg(mp->m_rtdev_targp);
out_free_ddev_targ:
xfs_free_buftarg(mp->m_ddev_targp);
out_close_rtdev:
if (rtdev_handle)
bdev_release(rtdev_handle);
out_close_logdev:
if (logdev_handle)
bdev_release(logdev_handle);
return error;
}
/*
* Setup xfs_mount buffer target pointers based on superblock
*/
STATIC int
xfs_setup_devices(
struct xfs_mount *mp)
{
int error;
error = xfs_setsize_buftarg(mp->m_ddev_targp, mp->m_sb.sb_sectsize);
if (error)
return error;
if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) {
unsigned int log_sector_size = BBSIZE;
if (xfs_has_sector(mp))
log_sector_size = mp->m_sb.sb_logsectsize;
error = xfs_setsize_buftarg(mp->m_logdev_targp,
log_sector_size);
if (error)
return error;
}
if (mp->m_rtdev_targp) {
error = xfs_setsize_buftarg(mp->m_rtdev_targp,
mp->m_sb.sb_sectsize);
if (error)
return error;
}
return 0;
}
STATIC int
xfs_init_mount_workqueues(
struct xfs_mount *mp)
{
mp->m_buf_workqueue = alloc_workqueue("xfs-buf/%s",
XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM),
1, mp->m_super->s_id);
if (!mp->m_buf_workqueue)
goto out;
mp->m_unwritten_workqueue = alloc_workqueue("xfs-conv/%s",
XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM),
0, mp->m_super->s_id);
if (!mp->m_unwritten_workqueue)
goto out_destroy_buf;
mp->m_reclaim_workqueue = alloc_workqueue("xfs-reclaim/%s",
XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM),
0, mp->m_super->s_id);
if (!mp->m_reclaim_workqueue)
goto out_destroy_unwritten;
mp->m_blockgc_wq = alloc_workqueue("xfs-blockgc/%s",
XFS_WQFLAGS(WQ_UNBOUND | WQ_FREEZABLE | WQ_MEM_RECLAIM),
0, mp->m_super->s_id);
if (!mp->m_blockgc_wq)
goto out_destroy_reclaim;
mp->m_inodegc_wq = alloc_workqueue("xfs-inodegc/%s",
XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM),
1, mp->m_super->s_id);
if (!mp->m_inodegc_wq)
goto out_destroy_blockgc;
mp->m_sync_workqueue = alloc_workqueue("xfs-sync/%s",
XFS_WQFLAGS(WQ_FREEZABLE), 0, mp->m_super->s_id);
if (!mp->m_sync_workqueue)
goto out_destroy_inodegc;
return 0;
out_destroy_inodegc:
destroy_workqueue(mp->m_inodegc_wq);
out_destroy_blockgc:
destroy_workqueue(mp->m_blockgc_wq);
out_destroy_reclaim:
destroy_workqueue(mp->m_reclaim_workqueue);
out_destroy_unwritten:
destroy_workqueue(mp->m_unwritten_workqueue);
out_destroy_buf:
destroy_workqueue(mp->m_buf_workqueue);
out:
return -ENOMEM;
}
STATIC void
xfs_destroy_mount_workqueues(
struct xfs_mount *mp)
{
destroy_workqueue(mp->m_sync_workqueue);
destroy_workqueue(mp->m_blockgc_wq);
destroy_workqueue(mp->m_inodegc_wq);
destroy_workqueue(mp->m_reclaim_workqueue);
destroy_workqueue(mp->m_unwritten_workqueue);
destroy_workqueue(mp->m_buf_workqueue);
}
static void
xfs_flush_inodes_worker(
struct work_struct *work)
{
struct xfs_mount *mp = container_of(work, struct xfs_mount,
m_flush_inodes_work);
struct super_block *sb = mp->m_super;
if (down_read_trylock(&sb->s_umount)) {
sync_inodes_sb(sb);
up_read(&sb->s_umount);
}
}
/*
* Flush all dirty data to disk. Must not be called while holding an XFS_ILOCK
* or a page lock. We use sync_inodes_sb() here to ensure we block while waiting
* for IO to complete so that we effectively throttle multiple callers to the
* rate at which IO is completing.
*/
void
xfs_flush_inodes(
struct xfs_mount *mp)
{
/*
* If flush_work() returns true then that means we waited for a flush
* which was already in progress. Don't bother running another scan.
*/
if (flush_work(&mp->m_flush_inodes_work))
return;
queue_work(mp->m_sync_workqueue, &mp->m_flush_inodes_work);
flush_work(&mp->m_flush_inodes_work);
}
/* Catch misguided souls that try to use this interface on XFS */
STATIC struct inode *
xfs_fs_alloc_inode(
struct super_block *sb)
{
BUG();
return NULL;
}
/*
* Now that the generic code is guaranteed not to be accessing
* the linux inode, we can inactivate and reclaim the inode.
*/
STATIC void
xfs_fs_destroy_inode(
struct inode *inode)
{
struct xfs_inode *ip = XFS_I(inode);
trace_xfs_destroy_inode(ip);
ASSERT(!rwsem_is_locked(&inode->i_rwsem));
XFS_STATS_INC(ip->i_mount, vn_rele);
XFS_STATS_INC(ip->i_mount, vn_remove);
xfs_inode_mark_reclaimable(ip);
}
static void
xfs_fs_dirty_inode(
struct inode *inode,
int flags)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
if (!(inode->i_sb->s_flags & SB_LAZYTIME))
return;
/*
* Only do the timestamp update if the inode is dirty (I_DIRTY_SYNC)
* and has dirty timestamp (I_DIRTY_TIME). I_DIRTY_TIME can be passed
* in flags possibly together with I_DIRTY_SYNC.
*/
if ((flags & ~I_DIRTY_TIME) != I_DIRTY_SYNC || !(flags & I_DIRTY_TIME))
return;
if (xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp))
return;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_log_inode(tp, ip, XFS_ILOG_TIMESTAMP);
xfs_trans_commit(tp);
}
/*
* Slab object creation initialisation for the XFS inode.
* This covers only the idempotent fields in the XFS inode;
* all other fields need to be initialised on allocation
* from the slab. This avoids the need to repeatedly initialise
* fields in the xfs inode that left in the initialise state
* when freeing the inode.
*/
STATIC void
xfs_fs_inode_init_once(
void *inode)
{
struct xfs_inode *ip = inode;
memset(ip, 0, sizeof(struct xfs_inode));
/* vfs inode */
inode_init_once(VFS_I(ip));
/* xfs inode */
atomic_set(&ip->i_pincount, 0);
spin_lock_init(&ip->i_flags_lock);
mrlock_init(&ip->i_lock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER,
"xfsino", ip->i_ino);
}
/*
* We do an unlocked check for XFS_IDONTCACHE here because we are already
* serialised against cache hits here via the inode->i_lock and igrab() in
* xfs_iget_cache_hit(). Hence a lookup that might clear this flag will not be
* racing with us, and it avoids needing to grab a spinlock here for every inode
* we drop the final reference on.
*/
STATIC int
xfs_fs_drop_inode(
struct inode *inode)
{
struct xfs_inode *ip = XFS_I(inode);
/*
* If this unlinked inode is in the middle of recovery, don't
* drop the inode just yet; log recovery will take care of
* that. See the comment for this inode flag.
*/
if (ip->i_flags & XFS_IRECOVERY) {
ASSERT(xlog_recovery_needed(ip->i_mount->m_log));
return 0;
}
return generic_drop_inode(inode);
}
static void
xfs_mount_free(
struct xfs_mount *mp)
{
if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
xfs_free_buftarg(mp->m_logdev_targp);
if (mp->m_rtdev_targp)
xfs_free_buftarg(mp->m_rtdev_targp);
if (mp->m_ddev_targp)
xfs_free_buftarg(mp->m_ddev_targp);
debugfs_remove(mp->m_debugfs);
kfree(mp->m_rtname);
kfree(mp->m_logname);
kmem_free(mp);
}
STATIC int
xfs_fs_sync_fs(
struct super_block *sb,
int wait)
{
struct xfs_mount *mp = XFS_M(sb);
int error;
trace_xfs_fs_sync_fs(mp, __return_address);
/*
* Doing anything during the async pass would be counterproductive.
*/
if (!wait)
return 0;
error = xfs_log_force(mp, XFS_LOG_SYNC);
if (error)
return error;
if (laptop_mode) {
/*
* The disk must be active because we're syncing.
* We schedule log work now (now that the disk is
* active) instead of later (when it might not be).
*/
flush_delayed_work(&mp->m_log->l_work);
}
/*
* If we are called with page faults frozen out, it means we are about
* to freeze the transaction subsystem. Take the opportunity to shut
* down inodegc because once SB_FREEZE_FS is set it's too late to
* prevent inactivation races with freeze. The fs doesn't get called
* again by the freezing process until after SB_FREEZE_FS has been set,
* so it's now or never. Same logic applies to speculative allocation
* garbage collection.
*
* We don't care if this is a normal syncfs call that does this or
* freeze that does this - we can run this multiple times without issue
* and we won't race with a restart because a restart can only occur
* when the state is either SB_FREEZE_FS or SB_FREEZE_COMPLETE.
*/
if (sb->s_writers.frozen == SB_FREEZE_PAGEFAULT) {
xfs_inodegc_stop(mp);
xfs_blockgc_stop(mp);
}
return 0;
}
STATIC int
xfs_fs_statfs(
struct dentry *dentry,
struct kstatfs *statp)
{
struct xfs_mount *mp = XFS_M(dentry->d_sb);
xfs_sb_t *sbp = &mp->m_sb;
struct xfs_inode *ip = XFS_I(d_inode(dentry));
uint64_t fakeinos, id;
uint64_t icount;
uint64_t ifree;
uint64_t fdblocks;
xfs_extlen_t lsize;
int64_t ffree;
/*
* Expedite background inodegc but don't wait. We do not want to block
* here waiting hours for a billion extent file to be truncated.
*/
xfs_inodegc_push(mp);
statp->f_type = XFS_SUPER_MAGIC;
statp->f_namelen = MAXNAMELEN - 1;
id = huge_encode_dev(mp->m_ddev_targp->bt_dev);
statp->f_fsid = u64_to_fsid(id);
icount = percpu_counter_sum(&mp->m_icount);
ifree = percpu_counter_sum(&mp->m_ifree);
fdblocks = percpu_counter_sum(&mp->m_fdblocks);
spin_lock(&mp->m_sb_lock);
statp->f_bsize = sbp->sb_blocksize;
lsize = sbp->sb_logstart ? sbp->sb_logblocks : 0;
statp->f_blocks = sbp->sb_dblocks - lsize;
spin_unlock(&mp->m_sb_lock);
/* make sure statp->f_bfree does not underflow */
statp->f_bfree = max_t(int64_t, 0,
fdblocks - xfs_fdblocks_unavailable(mp));
statp->f_bavail = statp->f_bfree;
fakeinos = XFS_FSB_TO_INO(mp, statp->f_bfree);
statp->f_files = min(icount + fakeinos, (uint64_t)XFS_MAXINUMBER);
if (M_IGEO(mp)->maxicount)
statp->f_files = min_t(typeof(statp->f_files),
statp->f_files,
M_IGEO(mp)->maxicount);
/* If sb_icount overshot maxicount, report actual allocation */
statp->f_files = max_t(typeof(statp->f_files),
statp->f_files,
sbp->sb_icount);
/* make sure statp->f_ffree does not underflow */
ffree = statp->f_files - (icount - ifree);
statp->f_ffree = max_t(int64_t, ffree, 0);
if ((ip->i_diflags & XFS_DIFLAG_PROJINHERIT) &&
((mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))) ==
(XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))
xfs_qm_statvfs(ip, statp);
if (XFS_IS_REALTIME_MOUNT(mp) &&
(ip->i_diflags & (XFS_DIFLAG_RTINHERIT | XFS_DIFLAG_REALTIME))) {
s64 freertx;
statp->f_blocks = sbp->sb_rblocks;
freertx = percpu_counter_sum_positive(&mp->m_frextents);
statp->f_bavail = statp->f_bfree = xfs_rtx_to_rtb(mp, freertx);
}
return 0;
}
STATIC void
xfs_save_resvblks(struct xfs_mount *mp)
{
mp->m_resblks_save = mp->m_resblks;
xfs_reserve_blocks(mp, 0);
}
STATIC void
xfs_restore_resvblks(struct xfs_mount *mp)
{
uint64_t resblks;
if (mp->m_resblks_save) {
resblks = mp->m_resblks_save;
mp->m_resblks_save = 0;
} else
resblks = xfs_default_resblks(mp);
xfs_reserve_blocks(mp, resblks);
}
/*
* Second stage of a freeze. The data is already frozen so we only
* need to take care of the metadata. Once that's done sync the superblock
* to the log to dirty it in case of a crash while frozen. This ensures that we
* will recover the unlinked inode lists on the next mount.
*/
STATIC int
xfs_fs_freeze(
struct super_block *sb)
{
struct xfs_mount *mp = XFS_M(sb);
unsigned int flags;
int ret;
/*
* The filesystem is now frozen far enough that memory reclaim
* cannot safely operate on the filesystem. Hence we need to
* set a GFP_NOFS context here to avoid recursion deadlocks.
*/
flags = memalloc_nofs_save();
xfs_save_resvblks(mp);
ret = xfs_log_quiesce(mp);
memalloc_nofs_restore(flags);
/*
* For read-write filesystems, we need to restart the inodegc on error
* because we stopped it at SB_FREEZE_PAGEFAULT level and a thaw is not
* going to be run to restart it now. We are at SB_FREEZE_FS level
* here, so we can restart safely without racing with a stop in
* xfs_fs_sync_fs().
*/
if (ret && !xfs_is_readonly(mp)) {
xfs_blockgc_start(mp);
xfs_inodegc_start(mp);
}
return ret;
}
STATIC int
xfs_fs_unfreeze(
struct super_block *sb)
{
struct xfs_mount *mp = XFS_M(sb);
xfs_restore_resvblks(mp);
xfs_log_work_queue(mp);
/*
* Don't reactivate the inodegc worker on a readonly filesystem because
* inodes are sent directly to reclaim. Don't reactivate the blockgc
* worker because there are no speculative preallocations on a readonly
* filesystem.
*/
if (!xfs_is_readonly(mp)) {
xfs_blockgc_start(mp);
xfs_inodegc_start(mp);
}
return 0;
}
/*
* This function fills in xfs_mount_t fields based on mount args.
* Note: the superblock _has_ now been read in.
*/
STATIC int
xfs_finish_flags(
struct xfs_mount *mp)
{
/* Fail a mount where the logbuf is smaller than the log stripe */
if (xfs_has_logv2(mp)) {
if (mp->m_logbsize <= 0 &&
mp->m_sb.sb_logsunit > XLOG_BIG_RECORD_BSIZE) {
mp->m_logbsize = mp->m_sb.sb_logsunit;
} else if (mp->m_logbsize > 0 &&
mp->m_logbsize < mp->m_sb.sb_logsunit) {
xfs_warn(mp,
"logbuf size must be greater than or equal to log stripe size");
return -EINVAL;
}
} else {
/* Fail a mount if the logbuf is larger than 32K */
if (mp->m_logbsize > XLOG_BIG_RECORD_BSIZE) {
xfs_warn(mp,
"logbuf size for version 1 logs must be 16K or 32K");
return -EINVAL;
}
}
/*
* V5 filesystems always use attr2 format for attributes.
*/
if (xfs_has_crc(mp) && xfs_has_noattr2(mp)) {
xfs_warn(mp, "Cannot mount a V5 filesystem as noattr2. "
"attr2 is always enabled for V5 filesystems.");
return -EINVAL;
}
/*
* prohibit r/w mounts of read-only filesystems
*/
if ((mp->m_sb.sb_flags & XFS_SBF_READONLY) && !xfs_is_readonly(mp)) {
xfs_warn(mp,
"cannot mount a read-only filesystem as read-write");
return -EROFS;
}
if ((mp->m_qflags & XFS_GQUOTA_ACCT) &&
(mp->m_qflags & XFS_PQUOTA_ACCT) &&
!xfs_has_pquotino(mp)) {
xfs_warn(mp,
"Super block does not support project and group quota together");
return -EINVAL;
}
return 0;
}
static int
xfs_init_percpu_counters(
struct xfs_mount *mp)
{
int error;
error = percpu_counter_init(&mp->m_icount, 0, GFP_KERNEL);
if (error)
return -ENOMEM;
error = percpu_counter_init(&mp->m_ifree, 0, GFP_KERNEL);
if (error)
goto free_icount;
error = percpu_counter_init(&mp->m_fdblocks, 0, GFP_KERNEL);
if (error)
goto free_ifree;
error = percpu_counter_init(&mp->m_delalloc_blks, 0, GFP_KERNEL);
if (error)
goto free_fdblocks;
error = percpu_counter_init(&mp->m_frextents, 0, GFP_KERNEL);
if (error)
goto free_delalloc;
return 0;
free_delalloc:
percpu_counter_destroy(&mp->m_delalloc_blks);
free_fdblocks:
percpu_counter_destroy(&mp->m_fdblocks);
free_ifree:
percpu_counter_destroy(&mp->m_ifree);
free_icount:
percpu_counter_destroy(&mp->m_icount);
return -ENOMEM;
}
void
xfs_reinit_percpu_counters(
struct xfs_mount *mp)
{
percpu_counter_set(&mp->m_icount, mp->m_sb.sb_icount);
percpu_counter_set(&mp->m_ifree, mp->m_sb.sb_ifree);
percpu_counter_set(&mp->m_fdblocks, mp->m_sb.sb_fdblocks);
percpu_counter_set(&mp->m_frextents, mp->m_sb.sb_frextents);
}
static void
xfs_destroy_percpu_counters(
struct xfs_mount *mp)
{
percpu_counter_destroy(&mp->m_icount);
percpu_counter_destroy(&mp->m_ifree);
percpu_counter_destroy(&mp->m_fdblocks);
ASSERT(xfs_is_shutdown(mp) ||
percpu_counter_sum(&mp->m_delalloc_blks) == 0);
percpu_counter_destroy(&mp->m_delalloc_blks);
percpu_counter_destroy(&mp->m_frextents);
}
static int
xfs_inodegc_init_percpu(
struct xfs_mount *mp)
{
struct xfs_inodegc *gc;
int cpu;
mp->m_inodegc = alloc_percpu(struct xfs_inodegc);
if (!mp->m_inodegc)
return -ENOMEM;
for_each_possible_cpu(cpu) {
gc = per_cpu_ptr(mp->m_inodegc, cpu);
gc->cpu = cpu;
gc->mp = mp;
init_llist_head(&gc->list);
gc->items = 0;
gc->error = 0;
INIT_DELAYED_WORK(&gc->work, xfs_inodegc_worker);
}
return 0;
}
static void
xfs_inodegc_free_percpu(
struct xfs_mount *mp)
{
if (!mp->m_inodegc)
return;
free_percpu(mp->m_inodegc);
}
static void
xfs_fs_put_super(
struct super_block *sb)
{
struct xfs_mount *mp = XFS_M(sb);
xfs_notice(mp, "Unmounting Filesystem %pU", &mp->m_sb.sb_uuid);
xfs_filestream_unmount(mp);
xfs_unmountfs(mp);
xfs_freesb(mp);
xchk_mount_stats_free(mp);
free_percpu(mp->m_stats.xs_stats);
xfs_inodegc_free_percpu(mp);
xfs_destroy_percpu_counters(mp);
xfs_destroy_mount_workqueues(mp);
xfs_shutdown_devices(mp);
}
static long
xfs_fs_nr_cached_objects(
struct super_block *sb,
struct shrink_control *sc)
{
/* Paranoia: catch incorrect calls during mount setup or teardown */
if (WARN_ON_ONCE(!sb->s_fs_info))
return 0;
return xfs_reclaim_inodes_count(XFS_M(sb));
}
static long
xfs_fs_free_cached_objects(
struct super_block *sb,
struct shrink_control *sc)
{
return xfs_reclaim_inodes_nr(XFS_M(sb), sc->nr_to_scan);
}
static void
xfs_fs_shutdown(
struct super_block *sb)
{
xfs_force_shutdown(XFS_M(sb), SHUTDOWN_DEVICE_REMOVED);
}
static const struct super_operations xfs_super_operations = {
.alloc_inode = xfs_fs_alloc_inode,
.destroy_inode = xfs_fs_destroy_inode,
.dirty_inode = xfs_fs_dirty_inode,
.drop_inode = xfs_fs_drop_inode,
.put_super = xfs_fs_put_super,
.sync_fs = xfs_fs_sync_fs,
.freeze_fs = xfs_fs_freeze,
.unfreeze_fs = xfs_fs_unfreeze,
.statfs = xfs_fs_statfs,
.show_options = xfs_fs_show_options,
.nr_cached_objects = xfs_fs_nr_cached_objects,
.free_cached_objects = xfs_fs_free_cached_objects,
.shutdown = xfs_fs_shutdown,
};
static int
suffix_kstrtoint(
const char *s,
unsigned int base,
int *res)
{
int last, shift_left_factor = 0, _res;
char *value;
int ret = 0;
value = kstrdup(s, GFP_KERNEL);
if (!value)
return -ENOMEM;
last = strlen(value) - 1;
if (value[last] == 'K' || value[last] == 'k') {
shift_left_factor = 10;
value[last] = '\0';
}
if (value[last] == 'M' || value[last] == 'm') {
shift_left_factor = 20;
value[last] = '\0';
}
if (value[last] == 'G' || value[last] == 'g') {
shift_left_factor = 30;
value[last] = '\0';
}
if (kstrtoint(value, base, &_res))
ret = -EINVAL;
kfree(value);
*res = _res << shift_left_factor;
return ret;
}
static inline void
xfs_fs_warn_deprecated(
struct fs_context *fc,
struct fs_parameter *param,
uint64_t flag,
bool value)
{
/* Don't print the warning if reconfiguring and current mount point
* already had the flag set
*/
if ((fc->purpose & FS_CONTEXT_FOR_RECONFIGURE) &&
!!(XFS_M(fc->root->d_sb)->m_features & flag) == value)
return;
xfs_warn(fc->s_fs_info, "%s mount option is deprecated.", param->key);
}
/*
* Set mount state from a mount option.
*
* NOTE: mp->m_super is NULL here!
*/
static int
xfs_fs_parse_param(
struct fs_context *fc,
struct fs_parameter *param)
{
struct xfs_mount *parsing_mp = fc->s_fs_info;
struct fs_parse_result result;
int size = 0;
int opt;
opt = fs_parse(fc, xfs_fs_parameters, param, &result);
if (opt < 0)
return opt;
switch (opt) {
case Opt_logbufs:
parsing_mp->m_logbufs = result.uint_32;
return 0;
case Opt_logbsize:
if (suffix_kstrtoint(param->string, 10, &parsing_mp->m_logbsize))
return -EINVAL;
return 0;
case Opt_logdev:
kfree(parsing_mp->m_logname);
parsing_mp->m_logname = kstrdup(param->string, GFP_KERNEL);
if (!parsing_mp->m_logname)
return -ENOMEM;
return 0;
case Opt_rtdev:
kfree(parsing_mp->m_rtname);
parsing_mp->m_rtname = kstrdup(param->string, GFP_KERNEL);
if (!parsing_mp->m_rtname)
return -ENOMEM;
return 0;
case Opt_allocsize:
if (suffix_kstrtoint(param->string, 10, &size))
return -EINVAL;
parsing_mp->m_allocsize_log = ffs(size) - 1;
parsing_mp->m_features |= XFS_FEAT_ALLOCSIZE;
return 0;
case Opt_grpid:
case Opt_bsdgroups:
parsing_mp->m_features |= XFS_FEAT_GRPID;
return 0;
case Opt_nogrpid:
case Opt_sysvgroups:
parsing_mp->m_features &= ~XFS_FEAT_GRPID;
return 0;
case Opt_wsync:
parsing_mp->m_features |= XFS_FEAT_WSYNC;
return 0;
case Opt_norecovery:
parsing_mp->m_features |= XFS_FEAT_NORECOVERY;
return 0;
case Opt_noalign:
parsing_mp->m_features |= XFS_FEAT_NOALIGN;
return 0;
case Opt_swalloc:
parsing_mp->m_features |= XFS_FEAT_SWALLOC;
return 0;
case Opt_sunit:
parsing_mp->m_dalign = result.uint_32;
return 0;
case Opt_swidth:
parsing_mp->m_swidth = result.uint_32;
return 0;
case Opt_inode32:
parsing_mp->m_features |= XFS_FEAT_SMALL_INUMS;
return 0;
case Opt_inode64:
parsing_mp->m_features &= ~XFS_FEAT_SMALL_INUMS;
return 0;
case Opt_nouuid:
parsing_mp->m_features |= XFS_FEAT_NOUUID;
return 0;
case Opt_largeio:
parsing_mp->m_features |= XFS_FEAT_LARGE_IOSIZE;
return 0;
case Opt_nolargeio:
parsing_mp->m_features &= ~XFS_FEAT_LARGE_IOSIZE;
return 0;
case Opt_filestreams:
parsing_mp->m_features |= XFS_FEAT_FILESTREAMS;
return 0;
case Opt_noquota:
parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ACCT;
parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ENFD;
return 0;
case Opt_quota:
case Opt_uquota:
case Opt_usrquota:
parsing_mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ENFD);
return 0;
case Opt_qnoenforce:
case Opt_uqnoenforce:
parsing_mp->m_qflags |= XFS_UQUOTA_ACCT;
parsing_mp->m_qflags &= ~XFS_UQUOTA_ENFD;
return 0;
case Opt_pquota:
case Opt_prjquota:
parsing_mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ENFD);
return 0;
case Opt_pqnoenforce:
parsing_mp->m_qflags |= XFS_PQUOTA_ACCT;
parsing_mp->m_qflags &= ~XFS_PQUOTA_ENFD;
return 0;
case Opt_gquota:
case Opt_grpquota:
parsing_mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ENFD);
return 0;
case Opt_gqnoenforce:
parsing_mp->m_qflags |= XFS_GQUOTA_ACCT;
parsing_mp->m_qflags &= ~XFS_GQUOTA_ENFD;
return 0;
case Opt_discard:
parsing_mp->m_features |= XFS_FEAT_DISCARD;
return 0;
case Opt_nodiscard:
parsing_mp->m_features &= ~XFS_FEAT_DISCARD;
return 0;
#ifdef CONFIG_FS_DAX
case Opt_dax:
xfs_mount_set_dax_mode(parsing_mp, XFS_DAX_ALWAYS);
return 0;
case Opt_dax_enum:
xfs_mount_set_dax_mode(parsing_mp, result.uint_32);
return 0;
#endif
/* Following mount options will be removed in September 2025 */
case Opt_ikeep:
xfs_fs_warn_deprecated(fc, param, XFS_FEAT_IKEEP, true);
parsing_mp->m_features |= XFS_FEAT_IKEEP;
return 0;
case Opt_noikeep:
xfs_fs_warn_deprecated(fc, param, XFS_FEAT_IKEEP, false);
parsing_mp->m_features &= ~XFS_FEAT_IKEEP;
return 0;
case Opt_attr2:
xfs_fs_warn_deprecated(fc, param, XFS_FEAT_ATTR2, true);
parsing_mp->m_features |= XFS_FEAT_ATTR2;
return 0;
case Opt_noattr2:
xfs_fs_warn_deprecated(fc, param, XFS_FEAT_NOATTR2, true);
parsing_mp->m_features |= XFS_FEAT_NOATTR2;
return 0;
default:
xfs_warn(parsing_mp, "unknown mount option [%s].", param->key);
return -EINVAL;
}
return 0;
}
static int
xfs_fs_validate_params(
struct xfs_mount *mp)
{
/* No recovery flag requires a read-only mount */
if (xfs_has_norecovery(mp) && !xfs_is_readonly(mp)) {
xfs_warn(mp, "no-recovery mounts must be read-only.");
return -EINVAL;
}
/*
* We have not read the superblock at this point, so only the attr2
* mount option can set the attr2 feature by this stage.
*/
if (xfs_has_attr2(mp) && xfs_has_noattr2(mp)) {
xfs_warn(mp, "attr2 and noattr2 cannot both be specified.");
return -EINVAL;
}
if (xfs_has_noalign(mp) && (mp->m_dalign || mp->m_swidth)) {
xfs_warn(mp,
"sunit and swidth options incompatible with the noalign option");
return -EINVAL;
}
if (!IS_ENABLED(CONFIG_XFS_QUOTA) && mp->m_qflags != 0) {
xfs_warn(mp, "quota support not available in this kernel.");
return -EINVAL;
}
if ((mp->m_dalign && !mp->m_swidth) ||
(!mp->m_dalign && mp->m_swidth)) {
xfs_warn(mp, "sunit and swidth must be specified together");
return -EINVAL;
}
if (mp->m_dalign && (mp->m_swidth % mp->m_dalign != 0)) {
xfs_warn(mp,
"stripe width (%d) must be a multiple of the stripe unit (%d)",
mp->m_swidth, mp->m_dalign);
return -EINVAL;
}
if (mp->m_logbufs != -1 &&
mp->m_logbufs != 0 &&
(mp->m_logbufs < XLOG_MIN_ICLOGS ||
mp->m_logbufs > XLOG_MAX_ICLOGS)) {
xfs_warn(mp, "invalid logbufs value: %d [not %d-%d]",
mp->m_logbufs, XLOG_MIN_ICLOGS, XLOG_MAX_ICLOGS);
return -EINVAL;
}
if (mp->m_logbsize != -1 &&
mp->m_logbsize != 0 &&
(mp->m_logbsize < XLOG_MIN_RECORD_BSIZE ||
mp->m_logbsize > XLOG_MAX_RECORD_BSIZE ||
!is_power_of_2(mp->m_logbsize))) {
xfs_warn(mp,
"invalid logbufsize: %d [not 16k,32k,64k,128k or 256k]",
mp->m_logbsize);
return -EINVAL;
}
if (xfs_has_allocsize(mp) &&
(mp->m_allocsize_log > XFS_MAX_IO_LOG ||
mp->m_allocsize_log < XFS_MIN_IO_LOG)) {
xfs_warn(mp, "invalid log iosize: %d [not %d-%d]",
mp->m_allocsize_log, XFS_MIN_IO_LOG, XFS_MAX_IO_LOG);
return -EINVAL;
}
return 0;
}
struct dentry *
xfs_debugfs_mkdir(
const char *name,
struct dentry *parent)
{
struct dentry *child;
/* Apparently we're expected to ignore error returns?? */
child = debugfs_create_dir(name, parent);
if (IS_ERR(child))
return NULL;
return child;
}
static int
xfs_fs_fill_super(
struct super_block *sb,
struct fs_context *fc)
{
struct xfs_mount *mp = sb->s_fs_info;
struct inode *root;
int flags = 0, error;
mp->m_super = sb;
/*
* Copy VFS mount flags from the context now that all parameter parsing
* is guaranteed to have been completed by either the old mount API or
* the newer fsopen/fsconfig API.
*/
if (fc->sb_flags & SB_RDONLY)
set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate);
if (fc->sb_flags & SB_DIRSYNC)
mp->m_features |= XFS_FEAT_DIRSYNC;
if (fc->sb_flags & SB_SYNCHRONOUS)
mp->m_features |= XFS_FEAT_WSYNC;
error = xfs_fs_validate_params(mp);
if (error)
return error;
sb_min_blocksize(sb, BBSIZE);
sb->s_xattr = xfs_xattr_handlers;
sb->s_export_op = &xfs_export_operations;
#ifdef CONFIG_XFS_QUOTA
sb->s_qcop = &xfs_quotactl_operations;
sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ;
#endif
sb->s_op = &xfs_super_operations;
/*
* Delay mount work if the debug hook is set. This is debug
* instrumention to coordinate simulation of xfs mount failures with
* VFS superblock operations
*/
if (xfs_globals.mount_delay) {
xfs_notice(mp, "Delaying mount for %d seconds.",
xfs_globals.mount_delay);
msleep(xfs_globals.mount_delay * 1000);
}
if (fc->sb_flags & SB_SILENT)
flags |= XFS_MFSI_QUIET;
error = xfs_open_devices(mp);
if (error)
return error;
if (xfs_debugfs) {
mp->m_debugfs = xfs_debugfs_mkdir(mp->m_super->s_id,
xfs_debugfs);
} else {
mp->m_debugfs = NULL;
}
error = xfs_init_mount_workqueues(mp);
if (error)
goto out_shutdown_devices;
error = xfs_init_percpu_counters(mp);
if (error)
goto out_destroy_workqueues;
error = xfs_inodegc_init_percpu(mp);
if (error)
goto out_destroy_counters;
/* Allocate stats memory before we do operations that might use it */
mp->m_stats.xs_stats = alloc_percpu(struct xfsstats);
if (!mp->m_stats.xs_stats) {
error = -ENOMEM;
goto out_destroy_inodegc;
}
error = xchk_mount_stats_alloc(mp);
if (error)
goto out_free_stats;
error = xfs_readsb(mp, flags);
if (error)
goto out_free_scrub_stats;
error = xfs_finish_flags(mp);
if (error)
goto out_free_sb;
error = xfs_setup_devices(mp);
if (error)
goto out_free_sb;
/* V4 support is undergoing deprecation. */
if (!xfs_has_crc(mp)) {
#ifdef CONFIG_XFS_SUPPORT_V4
xfs_warn_once(mp,
"Deprecated V4 format (crc=0) will not be supported after September 2030.");
#else
xfs_warn(mp,
"Deprecated V4 format (crc=0) not supported by kernel.");
error = -EINVAL;
goto out_free_sb;
#endif
}
/* ASCII case insensitivity is undergoing deprecation. */
if (xfs_has_asciici(mp)) {
#ifdef CONFIG_XFS_SUPPORT_ASCII_CI
xfs_warn_once(mp,
"Deprecated ASCII case-insensitivity feature (ascii-ci=1) will not be supported after September 2030.");
#else
xfs_warn(mp,
"Deprecated ASCII case-insensitivity feature (ascii-ci=1) not supported by kernel.");
error = -EINVAL;
goto out_free_sb;
#endif
}
/* Filesystem claims it needs repair, so refuse the mount. */
if (xfs_has_needsrepair(mp)) {
xfs_warn(mp, "Filesystem needs repair. Please run xfs_repair.");
error = -EFSCORRUPTED;
goto out_free_sb;
}
/*
* Don't touch the filesystem if a user tool thinks it owns the primary
* superblock. mkfs doesn't clear the flag from secondary supers, so
* we don't check them at all.
*/
if (mp->m_sb.sb_inprogress) {
xfs_warn(mp, "Offline file system operation in progress!");
error = -EFSCORRUPTED;
goto out_free_sb;
}
/*
* Until this is fixed only page-sized or smaller data blocks work.
*/
if (mp->m_sb.sb_blocksize > PAGE_SIZE) {
xfs_warn(mp,
"File system with blocksize %d bytes. "
"Only pagesize (%ld) or less will currently work.",
mp->m_sb.sb_blocksize, PAGE_SIZE);
error = -ENOSYS;
goto out_free_sb;
}
/* Ensure this filesystem fits in the page cache limits */
if (xfs_sb_validate_fsb_count(&mp->m_sb, mp->m_sb.sb_dblocks) ||
xfs_sb_validate_fsb_count(&mp->m_sb, mp->m_sb.sb_rblocks)) {
xfs_warn(mp,
"file system too large to be mounted on this system.");
error = -EFBIG;
goto out_free_sb;
}
/*
* XFS block mappings use 54 bits to store the logical block offset.
* This should suffice to handle the maximum file size that the VFS
* supports (currently 2^63 bytes on 64-bit and ULONG_MAX << PAGE_SHIFT
* bytes on 32-bit), but as XFS and VFS have gotten the s_maxbytes
* calculation wrong on 32-bit kernels in the past, we'll add a WARN_ON
* to check this assertion.
*
* Avoid integer overflow by comparing the maximum bmbt offset to the
* maximum pagecache offset in units of fs blocks.
*/
if (!xfs_verify_fileoff(mp, XFS_B_TO_FSBT(mp, MAX_LFS_FILESIZE))) {
xfs_warn(mp,
"MAX_LFS_FILESIZE block offset (%llu) exceeds extent map maximum (%llu)!",
XFS_B_TO_FSBT(mp, MAX_LFS_FILESIZE),
XFS_MAX_FILEOFF);
error = -EINVAL;
goto out_free_sb;
}
error = xfs_filestream_mount(mp);
if (error)
goto out_free_sb;
/*
* we must configure the block size in the superblock before we run the
* full mount process as the mount process can lookup and cache inodes.
*/
sb->s_magic = XFS_SUPER_MAGIC;
sb->s_blocksize = mp->m_sb.sb_blocksize;
sb->s_blocksize_bits = ffs(sb->s_blocksize) - 1;
sb->s_maxbytes = MAX_LFS_FILESIZE;
sb->s_max_links = XFS_MAXLINK;
sb->s_time_gran = 1;
if (xfs_has_bigtime(mp)) {
sb->s_time_min = xfs_bigtime_to_unix(XFS_BIGTIME_TIME_MIN);
sb->s_time_max = xfs_bigtime_to_unix(XFS_BIGTIME_TIME_MAX);
} else {
sb->s_time_min = XFS_LEGACY_TIME_MIN;
sb->s_time_max = XFS_LEGACY_TIME_MAX;
}
trace_xfs_inode_timestamp_range(mp, sb->s_time_min, sb->s_time_max);
sb->s_iflags |= SB_I_CGROUPWB;
set_posix_acl_flag(sb);
/* version 5 superblocks support inode version counters. */
if (xfs_has_crc(mp))
sb->s_flags |= SB_I_VERSION;
if (xfs_has_dax_always(mp)) {
error = xfs_setup_dax_always(mp);
if (error)
goto out_filestream_unmount;
}
if (xfs_has_discard(mp) && !bdev_max_discard_sectors(sb->s_bdev)) {
xfs_warn(mp,
"mounting with \"discard\" option, but the device does not support discard");
mp->m_features &= ~XFS_FEAT_DISCARD;
}
if (xfs_has_reflink(mp)) {
if (mp->m_sb.sb_rblocks) {
xfs_alert(mp,
"reflink not compatible with realtime device!");
error = -EINVAL;
goto out_filestream_unmount;
}
if (xfs_globals.always_cow) {
xfs_info(mp, "using DEBUG-only always_cow mode.");
mp->m_always_cow = true;
}
}
if (xfs_has_rmapbt(mp) && mp->m_sb.sb_rblocks) {
xfs_alert(mp,
"reverse mapping btree not compatible with realtime device!");
error = -EINVAL;
goto out_filestream_unmount;
}
error = xfs_mountfs(mp);
if (error)
goto out_filestream_unmount;
root = igrab(VFS_I(mp->m_rootip));
if (!root) {
error = -ENOENT;
goto out_unmount;
}
sb->s_root = d_make_root(root);
if (!sb->s_root) {
error = -ENOMEM;
goto out_unmount;
}
return 0;
out_filestream_unmount:
xfs_filestream_unmount(mp);
out_free_sb:
xfs_freesb(mp);
out_free_scrub_stats:
xchk_mount_stats_free(mp);
out_free_stats:
free_percpu(mp->m_stats.xs_stats);
out_destroy_inodegc:
xfs_inodegc_free_percpu(mp);
out_destroy_counters:
xfs_destroy_percpu_counters(mp);
out_destroy_workqueues:
xfs_destroy_mount_workqueues(mp);
out_shutdown_devices:
xfs_shutdown_devices(mp);
return error;
out_unmount:
xfs_filestream_unmount(mp);
xfs_unmountfs(mp);
goto out_free_sb;
}
static int
xfs_fs_get_tree(
struct fs_context *fc)
{
return get_tree_bdev(fc, xfs_fs_fill_super);
}
static int
xfs_remount_rw(
struct xfs_mount *mp)
{
struct xfs_sb *sbp = &mp->m_sb;
int error;
if (xfs_has_norecovery(mp)) {
xfs_warn(mp,
"ro->rw transition prohibited on norecovery mount");
return -EINVAL;
}
if (xfs_sb_is_v5(sbp) &&
xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
xfs_warn(mp,
"ro->rw transition prohibited on unknown (0x%x) ro-compat filesystem",
(sbp->sb_features_ro_compat &
XFS_SB_FEAT_RO_COMPAT_UNKNOWN));
return -EINVAL;
}
clear_bit(XFS_OPSTATE_READONLY, &mp->m_opstate);
/*
* If this is the first remount to writeable state we might have some
* superblock changes to update.
*/
if (mp->m_update_sb) {
error = xfs_sync_sb(mp, false);
if (error) {
xfs_warn(mp, "failed to write sb changes");
return error;
}
mp->m_update_sb = false;
}
/*
* Fill out the reserve pool if it is empty. Use the stashed value if
* it is non-zero, otherwise go with the default.
*/
xfs_restore_resvblks(mp);
xfs_log_work_queue(mp);
xfs_blockgc_start(mp);
/* Create the per-AG metadata reservation pool .*/
error = xfs_fs_reserve_ag_blocks(mp);
if (error && error != -ENOSPC)
return error;
/* Re-enable the background inode inactivation worker. */
xfs_inodegc_start(mp);
return 0;
}
static int
xfs_remount_ro(
struct xfs_mount *mp)
{
struct xfs_icwalk icw = {
.icw_flags = XFS_ICWALK_FLAG_SYNC,
};
int error;
/* Flush all the dirty data to disk. */
error = sync_filesystem(mp->m_super);
if (error)
return error;
/*
* Cancel background eofb scanning so it cannot race with the final
* log force+buftarg wait and deadlock the remount.
*/
xfs_blockgc_stop(mp);
/*
* Clear out all remaining COW staging extents and speculative post-EOF
* preallocations so that we don't leave inodes requiring inactivation
* cleanups during reclaim on a read-only mount. We must process every
* cached inode, so this requires a synchronous cache scan.
*/
error = xfs_blockgc_free_space(mp, &icw);
if (error) {
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
return error;
}
/*
* Stop the inodegc background worker. xfs_fs_reconfigure already
* flushed all pending inodegc work when it sync'd the filesystem.
* The VFS holds s_umount, so we know that inodes cannot enter
* xfs_fs_destroy_inode during a remount operation. In readonly mode
* we send inodes straight to reclaim, so no inodes will be queued.
*/
xfs_inodegc_stop(mp);
/* Free the per-AG metadata reservation pool. */
error = xfs_fs_unreserve_ag_blocks(mp);
if (error) {
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
return error;
}
/*
* Before we sync the metadata, we need to free up the reserve block
* pool so that the used block count in the superblock on disk is
* correct at the end of the remount. Stash the current* reserve pool
* size so that if we get remounted rw, we can return it to the same
* size.
*/
xfs_save_resvblks(mp);
xfs_log_clean(mp);
set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate);
return 0;
}
/*
* Logically we would return an error here to prevent users from believing
* they might have changed mount options using remount which can't be changed.
*
* But unfortunately mount(8) adds all options from mtab and fstab to the mount
* arguments in some cases so we can't blindly reject options, but have to
* check for each specified option if it actually differs from the currently
* set option and only reject it if that's the case.
*
* Until that is implemented we return success for every remount request, and
* silently ignore all options that we can't actually change.
*/
static int
xfs_fs_reconfigure(
struct fs_context *fc)
{
struct xfs_mount *mp = XFS_M(fc->root->d_sb);
struct xfs_mount *new_mp = fc->s_fs_info;
int flags = fc->sb_flags;
int error;
/* version 5 superblocks always support version counters. */
if (xfs_has_crc(mp))
fc->sb_flags |= SB_I_VERSION;
error = xfs_fs_validate_params(new_mp);
if (error)
return error;
/* inode32 -> inode64 */
if (xfs_has_small_inums(mp) && !xfs_has_small_inums(new_mp)) {
mp->m_features &= ~XFS_FEAT_SMALL_INUMS;
mp->m_maxagi = xfs_set_inode_alloc(mp, mp->m_sb.sb_agcount);
}
/* inode64 -> inode32 */
if (!xfs_has_small_inums(mp) && xfs_has_small_inums(new_mp)) {
mp->m_features |= XFS_FEAT_SMALL_INUMS;
mp->m_maxagi = xfs_set_inode_alloc(mp, mp->m_sb.sb_agcount);
}
/* ro -> rw */
if (xfs_is_readonly(mp) && !(flags & SB_RDONLY)) {
error = xfs_remount_rw(mp);
if (error)
return error;
}
/* rw -> ro */
if (!xfs_is_readonly(mp) && (flags & SB_RDONLY)) {
error = xfs_remount_ro(mp);
if (error)
return error;
}
return 0;
}
static void
xfs_fs_free(
struct fs_context *fc)
{
struct xfs_mount *mp = fc->s_fs_info;
/*
* mp is stored in the fs_context when it is initialized.
* mp is transferred to the superblock on a successful mount,
* but if an error occurs before the transfer we have to free
* it here.
*/
if (mp)
xfs_mount_free(mp);
}
static const struct fs_context_operations xfs_context_ops = {
.parse_param = xfs_fs_parse_param,
.get_tree = xfs_fs_get_tree,
.reconfigure = xfs_fs_reconfigure,
.free = xfs_fs_free,
};
/*
* WARNING: do not initialise any parameters in this function that depend on
* mount option parsing having already been performed as this can be called from
* fsopen() before any parameters have been set.
*/
static int xfs_init_fs_context(
struct fs_context *fc)
{
struct xfs_mount *mp;
mp = kzalloc(sizeof(struct xfs_mount), GFP_KERNEL | __GFP_NOFAIL);
if (!mp)
return -ENOMEM;
spin_lock_init(&mp->m_sb_lock);
INIT_RADIX_TREE(&mp->m_perag_tree, GFP_ATOMIC);
spin_lock_init(&mp->m_perag_lock);
mutex_init(&mp->m_growlock);
INIT_WORK(&mp->m_flush_inodes_work, xfs_flush_inodes_worker);
INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker);
mp->m_kobj.kobject.kset = xfs_kset;
/*
* We don't create the finobt per-ag space reservation until after log
* recovery, so we must set this to true so that an ifree transaction
* started during log recovery will not depend on space reservations
* for finobt expansion.
*/
mp->m_finobt_nores = true;
/*
* These can be overridden by the mount option parsing.
*/
mp->m_logbufs = -1;
mp->m_logbsize = -1;
mp->m_allocsize_log = 16; /* 64k */
fc->s_fs_info = mp;
fc->ops = &xfs_context_ops;
return 0;
}
static void
xfs_kill_sb(
struct super_block *sb)
{
kill_block_super(sb);
xfs_mount_free(XFS_M(sb));
}
static struct file_system_type xfs_fs_type = {
.owner = THIS_MODULE,
.name = "xfs",
.init_fs_context = xfs_init_fs_context,
.parameters = xfs_fs_parameters,
.kill_sb = xfs_kill_sb,
.fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP,
};
MODULE_ALIAS_FS("xfs");
STATIC int __init
xfs_init_caches(void)
{
int error;
xfs_buf_cache = kmem_cache_create("xfs_buf", sizeof(struct xfs_buf), 0,
SLAB_HWCACHE_ALIGN |
SLAB_RECLAIM_ACCOUNT |
SLAB_MEM_SPREAD,
NULL);
if (!xfs_buf_cache)
goto out;
xfs_log_ticket_cache = kmem_cache_create("xfs_log_ticket",
sizeof(struct xlog_ticket),
0, 0, NULL);
if (!xfs_log_ticket_cache)
goto out_destroy_buf_cache;
error = xfs_btree_init_cur_caches();
if (error)
goto out_destroy_log_ticket_cache;
error = xfs_defer_init_item_caches();
if (error)
goto out_destroy_btree_cur_cache;
xfs_da_state_cache = kmem_cache_create("xfs_da_state",
sizeof(struct xfs_da_state),
0, 0, NULL);
if (!xfs_da_state_cache)
goto out_destroy_defer_item_cache;
xfs_ifork_cache = kmem_cache_create("xfs_ifork",
sizeof(struct xfs_ifork),
0, 0, NULL);
if (!xfs_ifork_cache)
goto out_destroy_da_state_cache;
xfs_trans_cache = kmem_cache_create("xfs_trans",
sizeof(struct xfs_trans),
0, 0, NULL);
if (!xfs_trans_cache)
goto out_destroy_ifork_cache;
/*
* The size of the cache-allocated buf log item is the maximum
* size possible under XFS. This wastes a little bit of memory,
* but it is much faster.
*/
xfs_buf_item_cache = kmem_cache_create("xfs_buf_item",
sizeof(struct xfs_buf_log_item),
0, 0, NULL);
if (!xfs_buf_item_cache)
goto out_destroy_trans_cache;
xfs_efd_cache = kmem_cache_create("xfs_efd_item",
xfs_efd_log_item_sizeof(XFS_EFD_MAX_FAST_EXTENTS),
0, 0, NULL);
if (!xfs_efd_cache)
goto out_destroy_buf_item_cache;
xfs_efi_cache = kmem_cache_create("xfs_efi_item",
xfs_efi_log_item_sizeof(XFS_EFI_MAX_FAST_EXTENTS),
0, 0, NULL);
if (!xfs_efi_cache)
goto out_destroy_efd_cache;
xfs_inode_cache = kmem_cache_create("xfs_inode",
sizeof(struct xfs_inode), 0,
(SLAB_HWCACHE_ALIGN |
SLAB_RECLAIM_ACCOUNT |
SLAB_MEM_SPREAD | SLAB_ACCOUNT),
xfs_fs_inode_init_once);
if (!xfs_inode_cache)
goto out_destroy_efi_cache;
xfs_ili_cache = kmem_cache_create("xfs_ili",
sizeof(struct xfs_inode_log_item), 0,
SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD,
NULL);
if (!xfs_ili_cache)
goto out_destroy_inode_cache;
xfs_icreate_cache = kmem_cache_create("xfs_icr",
sizeof(struct xfs_icreate_item),
0, 0, NULL);
if (!xfs_icreate_cache)
goto out_destroy_ili_cache;
xfs_rud_cache = kmem_cache_create("xfs_rud_item",
sizeof(struct xfs_rud_log_item),
0, 0, NULL);
if (!xfs_rud_cache)
goto out_destroy_icreate_cache;
xfs_rui_cache = kmem_cache_create("xfs_rui_item",
xfs_rui_log_item_sizeof(XFS_RUI_MAX_FAST_EXTENTS),
0, 0, NULL);
if (!xfs_rui_cache)
goto out_destroy_rud_cache;
xfs_cud_cache = kmem_cache_create("xfs_cud_item",
sizeof(struct xfs_cud_log_item),
0, 0, NULL);
if (!xfs_cud_cache)
goto out_destroy_rui_cache;
xfs_cui_cache = kmem_cache_create("xfs_cui_item",
xfs_cui_log_item_sizeof(XFS_CUI_MAX_FAST_EXTENTS),
0, 0, NULL);
if (!xfs_cui_cache)
goto out_destroy_cud_cache;
xfs_bud_cache = kmem_cache_create("xfs_bud_item",
sizeof(struct xfs_bud_log_item),
0, 0, NULL);
if (!xfs_bud_cache)
goto out_destroy_cui_cache;
xfs_bui_cache = kmem_cache_create("xfs_bui_item",
xfs_bui_log_item_sizeof(XFS_BUI_MAX_FAST_EXTENTS),
0, 0, NULL);
if (!xfs_bui_cache)
goto out_destroy_bud_cache;
xfs_attrd_cache = kmem_cache_create("xfs_attrd_item",
sizeof(struct xfs_attrd_log_item),
0, 0, NULL);
if (!xfs_attrd_cache)
goto out_destroy_bui_cache;
xfs_attri_cache = kmem_cache_create("xfs_attri_item",
sizeof(struct xfs_attri_log_item),
0, 0, NULL);
if (!xfs_attri_cache)
goto out_destroy_attrd_cache;
xfs_iunlink_cache = kmem_cache_create("xfs_iul_item",
sizeof(struct xfs_iunlink_item),
0, 0, NULL);
if (!xfs_iunlink_cache)
goto out_destroy_attri_cache;
return 0;
out_destroy_attri_cache:
kmem_cache_destroy(xfs_attri_cache);
out_destroy_attrd_cache:
kmem_cache_destroy(xfs_attrd_cache);
out_destroy_bui_cache:
kmem_cache_destroy(xfs_bui_cache);
out_destroy_bud_cache:
kmem_cache_destroy(xfs_bud_cache);
out_destroy_cui_cache:
kmem_cache_destroy(xfs_cui_cache);
out_destroy_cud_cache:
kmem_cache_destroy(xfs_cud_cache);
out_destroy_rui_cache:
kmem_cache_destroy(xfs_rui_cache);
out_destroy_rud_cache:
kmem_cache_destroy(xfs_rud_cache);
out_destroy_icreate_cache:
kmem_cache_destroy(xfs_icreate_cache);
out_destroy_ili_cache:
kmem_cache_destroy(xfs_ili_cache);
out_destroy_inode_cache:
kmem_cache_destroy(xfs_inode_cache);
out_destroy_efi_cache:
kmem_cache_destroy(xfs_efi_cache);
out_destroy_efd_cache:
kmem_cache_destroy(xfs_efd_cache);
out_destroy_buf_item_cache:
kmem_cache_destroy(xfs_buf_item_cache);
out_destroy_trans_cache:
kmem_cache_destroy(xfs_trans_cache);
out_destroy_ifork_cache:
kmem_cache_destroy(xfs_ifork_cache);
out_destroy_da_state_cache:
kmem_cache_destroy(xfs_da_state_cache);
out_destroy_defer_item_cache:
xfs_defer_destroy_item_caches();
out_destroy_btree_cur_cache:
xfs_btree_destroy_cur_caches();
out_destroy_log_ticket_cache:
kmem_cache_destroy(xfs_log_ticket_cache);
out_destroy_buf_cache:
kmem_cache_destroy(xfs_buf_cache);
out:
return -ENOMEM;
}
STATIC void
xfs_destroy_caches(void)
{
/*
* Make sure all delayed rcu free are flushed before we
* destroy caches.
*/
rcu_barrier();
kmem_cache_destroy(xfs_iunlink_cache);
kmem_cache_destroy(xfs_attri_cache);
kmem_cache_destroy(xfs_attrd_cache);
kmem_cache_destroy(xfs_bui_cache);
kmem_cache_destroy(xfs_bud_cache);
kmem_cache_destroy(xfs_cui_cache);
kmem_cache_destroy(xfs_cud_cache);
kmem_cache_destroy(xfs_rui_cache);
kmem_cache_destroy(xfs_rud_cache);
kmem_cache_destroy(xfs_icreate_cache);
kmem_cache_destroy(xfs_ili_cache);
kmem_cache_destroy(xfs_inode_cache);
kmem_cache_destroy(xfs_efi_cache);
kmem_cache_destroy(xfs_efd_cache);
kmem_cache_destroy(xfs_buf_item_cache);
kmem_cache_destroy(xfs_trans_cache);
kmem_cache_destroy(xfs_ifork_cache);
kmem_cache_destroy(xfs_da_state_cache);
xfs_defer_destroy_item_caches();
xfs_btree_destroy_cur_caches();
kmem_cache_destroy(xfs_log_ticket_cache);
kmem_cache_destroy(xfs_buf_cache);
}
STATIC int __init
xfs_init_workqueues(void)
{
/*
* The allocation workqueue can be used in memory reclaim situations
* (writepage path), and parallelism is only limited by the number of
* AGs in all the filesystems mounted. Hence use the default large
* max_active value for this workqueue.
*/
xfs_alloc_wq = alloc_workqueue("xfsalloc",
XFS_WQFLAGS(WQ_MEM_RECLAIM | WQ_FREEZABLE), 0);
if (!xfs_alloc_wq)
return -ENOMEM;
xfs_discard_wq = alloc_workqueue("xfsdiscard", XFS_WQFLAGS(WQ_UNBOUND),
0);
if (!xfs_discard_wq)
goto out_free_alloc_wq;
return 0;
out_free_alloc_wq:
destroy_workqueue(xfs_alloc_wq);
return -ENOMEM;
}
STATIC void
xfs_destroy_workqueues(void)
{
destroy_workqueue(xfs_discard_wq);
destroy_workqueue(xfs_alloc_wq);
}
STATIC int __init
init_xfs_fs(void)
{
int error;
xfs_check_ondisk_structs();
error = xfs_dahash_test();
if (error)
return error;
printk(KERN_INFO XFS_VERSION_STRING " with "
XFS_BUILD_OPTIONS " enabled\n");
xfs_dir_startup();
error = xfs_init_caches();
if (error)
goto out;
error = xfs_init_workqueues();
if (error)
goto out_destroy_caches;
error = xfs_mru_cache_init();
if (error)
goto out_destroy_wq;
error = xfs_init_procfs();
if (error)
goto out_mru_cache_uninit;
error = xfs_sysctl_register();
if (error)
goto out_cleanup_procfs;
xfs_debugfs = xfs_debugfs_mkdir("xfs", NULL);
xfs_kset = kset_create_and_add("xfs", NULL, fs_kobj);
if (!xfs_kset) {
error = -ENOMEM;
goto out_debugfs_unregister;
}
xfsstats.xs_kobj.kobject.kset = xfs_kset;
xfsstats.xs_stats = alloc_percpu(struct xfsstats);
if (!xfsstats.xs_stats) {
error = -ENOMEM;
goto out_kset_unregister;
}
error = xfs_sysfs_init(&xfsstats.xs_kobj, &xfs_stats_ktype, NULL,
"stats");
if (error)
goto out_free_stats;
error = xchk_global_stats_setup(xfs_debugfs);
if (error)
goto out_remove_stats_kobj;
#ifdef DEBUG
xfs_dbg_kobj.kobject.kset = xfs_kset;
error = xfs_sysfs_init(&xfs_dbg_kobj, &xfs_dbg_ktype, NULL, "debug");
if (error)
goto out_remove_scrub_stats;
#endif
error = xfs_qm_init();
if (error)
goto out_remove_dbg_kobj;
error = register_filesystem(&xfs_fs_type);
if (error)
goto out_qm_exit;
return 0;
out_qm_exit:
xfs_qm_exit();
out_remove_dbg_kobj:
#ifdef DEBUG
xfs_sysfs_del(&xfs_dbg_kobj);
out_remove_scrub_stats:
#endif
xchk_global_stats_teardown();
out_remove_stats_kobj:
xfs_sysfs_del(&xfsstats.xs_kobj);
out_free_stats:
free_percpu(xfsstats.xs_stats);
out_kset_unregister:
kset_unregister(xfs_kset);
out_debugfs_unregister:
debugfs_remove(xfs_debugfs);
xfs_sysctl_unregister();
out_cleanup_procfs:
xfs_cleanup_procfs();
out_mru_cache_uninit:
xfs_mru_cache_uninit();
out_destroy_wq:
xfs_destroy_workqueues();
out_destroy_caches:
xfs_destroy_caches();
out:
return error;
}
STATIC void __exit
exit_xfs_fs(void)
{
xfs_qm_exit();
unregister_filesystem(&xfs_fs_type);
#ifdef DEBUG
xfs_sysfs_del(&xfs_dbg_kobj);
#endif
xchk_global_stats_teardown();
xfs_sysfs_del(&xfsstats.xs_kobj);
free_percpu(xfsstats.xs_stats);
kset_unregister(xfs_kset);
debugfs_remove(xfs_debugfs);
xfs_sysctl_unregister();
xfs_cleanup_procfs();
xfs_mru_cache_uninit();
xfs_destroy_workqueues();
xfs_destroy_caches();
xfs_uuid_table_free();
}
module_init(init_xfs_fs);
module_exit(exit_xfs_fs);
MODULE_AUTHOR("Silicon Graphics, Inc.");
MODULE_DESCRIPTION(XFS_VERSION_STRING " with " XFS_BUILD_OPTIONS " enabled");
MODULE_LICENSE("GPL");
|