summaryrefslogtreecommitdiff
path: root/fs/quota/dquot.c
blob: 8c40c07797ad3d8c64a05ae799f746edceebea4f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
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
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
/*
 * Implementation of the diskquota system for the LINUX operating system. QUOTA
 * is implemented using the BSD system call interface as the means of
 * communication with the user level. This file contains the generic routines
 * called by the different filesystems on allocation of an inode or block.
 * These routines take care of the administration needed to have a consistent
 * diskquota tracking system. The ideas of both user and group quotas are based
 * on the Melbourne quota system as used on BSD derived systems. The internal
 * implementation is based on one of the several variants of the LINUX
 * inode-subsystem with added complexity of the diskquota system.
 * 
 * Author:	Marco van Wieringen <mvw@planets.elm.net>
 *
 * Fixes:   Dmitry Gorodchanin <pgmdsg@ibi.com>, 11 Feb 96
 *
 *		Revised list management to avoid races
 *		-- Bill Hawes, <whawes@star.net>, 9/98
 *
 *		Fixed races in dquot_transfer(), dqget() and dquot_alloc_...().
 *		As the consequence the locking was moved from dquot_decr_...(),
 *		dquot_incr_...() to calling functions.
 *		invalidate_dquots() now writes modified dquots.
 *		Serialized quota_off() and quota_on() for mount point.
 *		Fixed a few bugs in grow_dquots().
 *		Fixed deadlock in write_dquot() - we no longer account quotas on
 *		quota files
 *		remove_dquot_ref() moved to inode.c - it now traverses through inodes
 *		add_dquot_ref() restarts after blocking
 *		Added check for bogus uid and fixed check for group in quotactl.
 *		Jan Kara, <jack@suse.cz>, sponsored by SuSE CR, 10-11/99
 *
 *		Used struct list_head instead of own list struct
 *		Invalidation of referenced dquots is no longer possible
 *		Improved free_dquots list management
 *		Quota and i_blocks are now updated in one place to avoid races
 *		Warnings are now delayed so we won't block in critical section
 *		Write updated not to require dquot lock
 *		Jan Kara, <jack@suse.cz>, 9/2000
 *
 *		Added dynamic quota structure allocation
 *		Jan Kara <jack@suse.cz> 12/2000
 *
 *		Rewritten quota interface. Implemented new quota format and
 *		formats registering.
 *		Jan Kara, <jack@suse.cz>, 2001,2002
 *
 *		New SMP locking.
 *		Jan Kara, <jack@suse.cz>, 10/2002
 *
 *		Added journalled quota support, fix lock inversion problems
 *		Jan Kara, <jack@suse.cz>, 2003,2004
 *
 * (C) Copyright 1994 - 1997 Marco van Wieringen 
 */

#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/mm.h>
#include <linux/time.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/fcntl.h>
#include <linux/stat.h>
#include <linux/tty.h>
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/sysctl.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/security.h>
#include <linux/kmod.h>
#include <linux/namei.h>
#include <linux/buffer_head.h>
#include <linux/capability.h>
#include <linux/quotaops.h>
#include <linux/writeback.h> /* for inode_lock, oddly enough.. */

#include <asm/uaccess.h>

/*
 * There are three quota SMP locks. dq_list_lock protects all lists with quotas
 * and quota formats, dqstats structure containing statistics about the lists
 * dq_data_lock protects data from dq_dqb and also mem_dqinfo structures and
 * also guards consistency of dquot->dq_dqb with inode->i_blocks, i_bytes.
 * i_blocks and i_bytes updates itself are guarded by i_lock acquired directly
 * in inode_add_bytes() and inode_sub_bytes(). dq_state_lock protects
 * modifications of quota state (on quotaon and quotaoff) and readers who care
 * about latest values take it as well.
 *
 * The spinlock ordering is hence: dq_data_lock > dq_list_lock > i_lock,
 *   dq_list_lock > dq_state_lock
 *
 * Note that some things (eg. sb pointer, type, id) doesn't change during
 * the life of the dquot structure and so needn't to be protected by a lock
 *
 * Any operation working on dquots via inode pointers must hold dqptr_sem.  If
 * operation is just reading pointers from inode (or not using them at all) the
 * read lock is enough. If pointers are altered function must hold write lock.
 * Special care needs to be taken about S_NOQUOTA inode flag (marking that
 * inode is a quota file). Functions adding pointers from inode to dquots have
 * to check this flag under dqptr_sem and then (if S_NOQUOTA is not set) they
 * have to do all pointer modifications before dropping dqptr_sem. This makes
 * sure they cannot race with quotaon which first sets S_NOQUOTA flag and
 * then drops all pointers to dquots from an inode.
 *
 * Each dquot has its dq_lock mutex. Locked dquots might not be referenced
 * from inodes (dquot_alloc_space() and such don't check the dq_lock).
 * Currently dquot is locked only when it is being read to memory (or space for
 * it is being allocated) on the first dqget() and when it is being released on
 * the last dqput(). The allocation and release oparations are serialized by
 * the dq_lock and by checking the use count in dquot_release().  Write
 * operations on dquots don't hold dq_lock as they copy data under dq_data_lock
 * spinlock to internal buffers before writing.
 *
 * Lock ordering (including related VFS locks) is the following:
 *   i_mutex > dqonoff_sem > journal_lock > dqptr_sem > dquot->dq_lock >
 *   dqio_mutex
 * The lock ordering of dqptr_sem imposed by quota code is only dqonoff_sem >
 * dqptr_sem. But filesystem has to count with the fact that functions such as
 * dquot_alloc_space() acquire dqptr_sem and they usually have to be called
 * from inside a transaction to keep filesystem consistency after a crash. Also
 * filesystems usually want to do some IO on dquot from ->mark_dirty which is
 * called with dqptr_sem held.
 * i_mutex on quota files is special (it's below dqio_mutex)
 */

static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dq_list_lock);
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dq_state_lock);
__cacheline_aligned_in_smp DEFINE_SPINLOCK(dq_data_lock);
EXPORT_SYMBOL(dq_data_lock);

static char *quotatypes[] = INITQFNAMES;
static struct quota_format_type *quota_formats;	/* List of registered formats */
static struct quota_module_name module_names[] = INIT_QUOTA_MODULE_NAMES;

/* SLAB cache for dquot structures */
static struct kmem_cache *dquot_cachep;

int register_quota_format(struct quota_format_type *fmt)
{
	spin_lock(&dq_list_lock);
	fmt->qf_next = quota_formats;
	quota_formats = fmt;
	spin_unlock(&dq_list_lock);
	return 0;
}
EXPORT_SYMBOL(register_quota_format);

void unregister_quota_format(struct quota_format_type *fmt)
{
	struct quota_format_type **actqf;

	spin_lock(&dq_list_lock);
	for (actqf = &quota_formats; *actqf && *actqf != fmt;
	     actqf = &(*actqf)->qf_next)
		;
	if (*actqf)
		*actqf = (*actqf)->qf_next;
	spin_unlock(&dq_list_lock);
}
EXPORT_SYMBOL(unregister_quota_format);

static struct quota_format_type *find_quota_format(int id)
{
	struct quota_format_type *actqf;

	spin_lock(&dq_list_lock);
	for (actqf = quota_formats; actqf && actqf->qf_fmt_id != id;
	     actqf = actqf->qf_next)
		;
	if (!actqf || !try_module_get(actqf->qf_owner)) {
		int qm;

		spin_unlock(&dq_list_lock);
		
		for (qm = 0; module_names[qm].qm_fmt_id &&
			     module_names[qm].qm_fmt_id != id; qm++)
			;
		if (!module_names[qm].qm_fmt_id ||
		    request_module(module_names[qm].qm_mod_name))
			return NULL;

		spin_lock(&dq_list_lock);
		for (actqf = quota_formats; actqf && actqf->qf_fmt_id != id;
		     actqf = actqf->qf_next)
			;
		if (actqf && !try_module_get(actqf->qf_owner))
			actqf = NULL;
	}
	spin_unlock(&dq_list_lock);
	return actqf;
}

static void put_quota_format(struct quota_format_type *fmt)
{
	module_put(fmt->qf_owner);
}

/*
 * Dquot List Management:
 * The quota code uses three lists for dquot management: the inuse_list,
 * free_dquots, and dquot_hash[] array. A single dquot structure may be
 * on all three lists, depending on its current state.
 *
 * All dquots are placed to the end of inuse_list when first created, and this
 * list is used for invalidate operation, which must look at every dquot.
 *
 * Unused dquots (dq_count == 0) are added to the free_dquots list when freed,
 * and this list is searched whenever we need an available dquot.  Dquots are
 * removed from the list as soon as they are used again, and
 * dqstats.free_dquots gives the number of dquots on the list. When
 * dquot is invalidated it's completely released from memory.
 *
 * Dquots with a specific identity (device, type and id) are placed on
 * one of the dquot_hash[] hash chains. The provides an efficient search
 * mechanism to locate a specific dquot.
 */

static LIST_HEAD(inuse_list);
static LIST_HEAD(free_dquots);
static unsigned int dq_hash_bits, dq_hash_mask;
static struct hlist_head *dquot_hash;

struct dqstats dqstats;
EXPORT_SYMBOL(dqstats);

static qsize_t inode_get_rsv_space(struct inode *inode);
static void __dquot_initialize(struct inode *inode, int type);

static inline unsigned int
hashfn(const struct super_block *sb, unsigned int id, int type)
{
	unsigned long tmp;

	tmp = (((unsigned long)sb>>L1_CACHE_SHIFT) ^ id) * (MAXQUOTAS - type);
	return (tmp + (tmp >> dq_hash_bits)) & dq_hash_mask;
}

/*
 * Following list functions expect dq_list_lock to be held
 */
static inline void insert_dquot_hash(struct dquot *dquot)
{
	struct hlist_head *head;
	head = dquot_hash + hashfn(dquot->dq_sb, dquot->dq_id, dquot->dq_type);
	hlist_add_head(&dquot->dq_hash, head);
}

static inline void remove_dquot_hash(struct dquot *dquot)
{
	hlist_del_init(&dquot->dq_hash);
}

static struct dquot *find_dquot(unsigned int hashent, struct super_block *sb,
				unsigned int id, int type)
{
	struct hlist_node *node;
	struct dquot *dquot;

	hlist_for_each (node, dquot_hash+hashent) {
		dquot = hlist_entry(node, struct dquot, dq_hash);
		if (dquot->dq_sb == sb && dquot->dq_id == id &&
		    dquot->dq_type == type)
			return dquot;
	}
	return NULL;
}

/* Add a dquot to the tail of the free list */
static inline void put_dquot_last(struct dquot *dquot)
{
	list_add_tail(&dquot->dq_free, &free_dquots);
	dqstats.free_dquots++;
}

static inline void remove_free_dquot(struct dquot *dquot)
{
	if (list_empty(&dquot->dq_free))
		return;
	list_del_init(&dquot->dq_free);
	dqstats.free_dquots--;
}

static inline void put_inuse(struct dquot *dquot)
{
	/* We add to the back of inuse list so we don't have to restart
	 * when traversing this list and we block */
	list_add_tail(&dquot->dq_inuse, &inuse_list);
	dqstats.allocated_dquots++;
}

static inline void remove_inuse(struct dquot *dquot)
{
	dqstats.allocated_dquots--;
	list_del(&dquot->dq_inuse);
}
/*
 * End of list functions needing dq_list_lock
 */

static void wait_on_dquot(struct dquot *dquot)
{
	mutex_lock(&dquot->dq_lock);
	mutex_unlock(&dquot->dq_lock);
}

static inline int dquot_dirty(struct dquot *dquot)
{
	return test_bit(DQ_MOD_B, &dquot->dq_flags);
}

static inline int mark_dquot_dirty(struct dquot *dquot)
{
	return dquot->dq_sb->dq_op->mark_dirty(dquot);
}

int dquot_mark_dquot_dirty(struct dquot *dquot)
{
	spin_lock(&dq_list_lock);
	if (!test_and_set_bit(DQ_MOD_B, &dquot->dq_flags))
		list_add(&dquot->dq_dirty, &sb_dqopt(dquot->dq_sb)->
				info[dquot->dq_type].dqi_dirty_list);
	spin_unlock(&dq_list_lock);
	return 0;
}
EXPORT_SYMBOL(dquot_mark_dquot_dirty);

/* Dirtify all the dquots - this can block when journalling */
static inline int mark_all_dquot_dirty(struct dquot * const *dquot)
{
	int ret, err, cnt;

	ret = err = 0;
	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
		if (dquot[cnt])
			/* Even in case of error we have to continue */
			ret = mark_dquot_dirty(dquot[cnt]);
		if (!err)
			err = ret;
	}
	return err;
}

static inline void dqput_all(struct dquot **dquot)
{
	unsigned int cnt;

	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
		dqput(dquot[cnt]);
}

/* This function needs dq_list_lock */
static inline int clear_dquot_dirty(struct dquot *dquot)
{
	if (!test_and_clear_bit(DQ_MOD_B, &dquot->dq_flags))
		return 0;
	list_del_init(&dquot->dq_dirty);
	return 1;
}

void mark_info_dirty(struct super_block *sb, int type)
{
	set_bit(DQF_INFO_DIRTY_B, &sb_dqopt(sb)->info[type].dqi_flags);
}
EXPORT_SYMBOL(mark_info_dirty);

/*
 *	Read dquot from disk and alloc space for it
 */

int dquot_acquire(struct dquot *dquot)
{
	int ret = 0, ret2 = 0;
	struct quota_info *dqopt = sb_dqopt(dquot->dq_sb);

	mutex_lock(&dquot->dq_lock);
	mutex_lock(&dqopt->dqio_mutex);
	if (!test_bit(DQ_READ_B, &dquot->dq_flags))
		ret = dqopt->ops[dquot->dq_type]->read_dqblk(dquot);
	if (ret < 0)
		goto out_iolock;
	set_bit(DQ_READ_B, &dquot->dq_flags);
	/* Instantiate dquot if needed */
	if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags) && !dquot->dq_off) {
		ret = dqopt->ops[dquot->dq_type]->commit_dqblk(dquot);
		/* Write the info if needed */
		if (info_dirty(&dqopt->info[dquot->dq_type])) {
			ret2 = dqopt->ops[dquot->dq_type]->write_file_info(
						dquot->dq_sb, dquot->dq_type);
		}
		if (ret < 0)
			goto out_iolock;
		if (ret2 < 0) {
			ret = ret2;
			goto out_iolock;
		}
	}
	set_bit(DQ_ACTIVE_B, &dquot->dq_flags);
out_iolock:
	mutex_unlock(&dqopt->dqio_mutex);
	mutex_unlock(&dquot->dq_lock);
	return ret;
}
EXPORT_SYMBOL(dquot_acquire);

/*
 *	Write dquot to disk
 */
int dquot_commit(struct dquot *dquot)
{
	int ret = 0, ret2 = 0;
	struct quota_info *dqopt = sb_dqopt(dquot->dq_sb);

	mutex_lock(&dqopt->dqio_mutex);
	spin_lock(&dq_list_lock);
	if (!clear_dquot_dirty(dquot)) {
		spin_unlock(&dq_list_lock);
		goto out_sem;
	}
	spin_unlock(&dq_list_lock);
	/* Inactive dquot can be only if there was error during read/init
	 * => we have better not writing it */
	if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) {
		ret = dqopt->ops[dquot->dq_type]->commit_dqblk(dquot);
		if (info_dirty(&dqopt->info[dquot->dq_type])) {
			ret2 = dqopt->ops[dquot->dq_type]->write_file_info(
						dquot->dq_sb, dquot->dq_type);
		}
		if (ret >= 0)
			ret = ret2;
	}
out_sem:
	mutex_unlock(&dqopt->dqio_mutex);
	return ret;
}
EXPORT_SYMBOL(dquot_commit);

/*
 *	Release dquot
 */
int dquot_release(struct dquot *dquot)
{
	int ret = 0, ret2 = 0;
	struct quota_info *dqopt = sb_dqopt(dquot->dq_sb);

	mutex_lock(&dquot->dq_lock);
	/* Check whether we are not racing with some other dqget() */
	if (atomic_read(&dquot->dq_count) > 1)
		goto out_dqlock;
	mutex_lock(&dqopt->dqio_mutex);
	if (dqopt->ops[dquot->dq_type]->release_dqblk) {
		ret = dqopt->ops[dquot->dq_type]->release_dqblk(dquot);
		/* Write the info */
		if (info_dirty(&dqopt->info[dquot->dq_type])) {
			ret2 = dqopt->ops[dquot->dq_type]->write_file_info(
						dquot->dq_sb, dquot->dq_type);
		}
		if (ret >= 0)
			ret = ret2;
	}
	clear_bit(DQ_ACTIVE_B, &dquot->dq_flags);
	mutex_unlock(&dqopt->dqio_mutex);
out_dqlock:
	mutex_unlock(&dquot->dq_lock);
	return ret;
}
EXPORT_SYMBOL(dquot_release);

void dquot_destroy(struct dquot *dquot)
{
	kmem_cache_free(dquot_cachep, dquot);
}
EXPORT_SYMBOL(dquot_destroy);

static inline void do_destroy_dquot(struct dquot *dquot)
{
	dquot->dq_sb->dq_op->destroy_dquot(dquot);
}

/* Invalidate all dquots on the list. Note that this function is called after
 * quota is disabled and pointers from inodes removed so there cannot be new
 * quota users. There can still be some users of quotas due to inodes being
 * just deleted or pruned by prune_icache() (those are not attached to any
 * list) or parallel quotactl call. We have to wait for such users.
 */
static void invalidate_dquots(struct super_block *sb, int type)
{
	struct dquot *dquot, *tmp;

restart:
	spin_lock(&dq_list_lock);
	list_for_each_entry_safe(dquot, tmp, &inuse_list, dq_inuse) {
		if (dquot->dq_sb != sb)
			continue;
		if (dquot->dq_type != type)
			continue;
		/* Wait for dquot users */
		if (atomic_read(&dquot->dq_count)) {
			DEFINE_WAIT(wait);

			atomic_inc(&dquot->dq_count);
			prepare_to_wait(&dquot->dq_wait_unused, &wait,
					TASK_UNINTERRUPTIBLE);
			spin_unlock(&dq_list_lock);
			/* Once dqput() wakes us up, we know it's time to free
			 * the dquot.
			 * IMPORTANT: we rely on the fact that there is always
			 * at most one process waiting for dquot to free.
			 * Otherwise dq_count would be > 1 and we would never
			 * wake up.
			 */
			if (atomic_read(&dquot->dq_count) > 1)
				schedule();
			finish_wait(&dquot->dq_wait_unused, &wait);
			dqput(dquot);
			/* At this moment dquot() need not exist (it could be
			 * reclaimed by prune_dqcache(). Hence we must
			 * restart. */
			goto restart;
		}
		/*
		 * Quota now has no users and it has been written on last
		 * dqput()
		 */
		remove_dquot_hash(dquot);
		remove_free_dquot(dquot);
		remove_inuse(dquot);
		do_destroy_dquot(dquot);
	}
	spin_unlock(&dq_list_lock);
}

/* Call callback for every active dquot on given filesystem */
int dquot_scan_active(struct super_block *sb,
		      int (*fn)(struct dquot *dquot, unsigned long priv),
		      unsigned long priv)
{
	struct dquot *dquot, *old_dquot = NULL;
	int ret = 0;

	mutex_lock(&sb_dqopt(sb)->dqonoff_mutex);
	spin_lock(&dq_list_lock);
	list_for_each_entry(dquot, &inuse_list, dq_inuse) {
		if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags))
			continue;
		if (dquot->dq_sb != sb)
			continue;
		/* Now we have active dquot so we can just increase use count */
		atomic_inc(&dquot->dq_count);
		dqstats.lookups++;
		spin_unlock(&dq_list_lock);
		dqput(old_dquot);
		old_dquot = dquot;
		ret = fn(dquot, priv);
		if (ret < 0)
			goto out;
		spin_lock(&dq_list_lock);
		/* We are safe to continue now because our dquot could not
		 * be moved out of the inuse list while we hold the reference */
	}
	spin_unlock(&dq_list_lock);
out:
	dqput(old_dquot);
	mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex);
	return ret;
}
EXPORT_SYMBOL(dquot_scan_active);

int vfs_quota_sync(struct super_block *sb, int type, int wait)
{
	struct list_head *dirty;
	struct dquot *dquot;
	struct quota_info *dqopt = sb_dqopt(sb);
	int cnt;

	mutex_lock(&dqopt->dqonoff_mutex);
	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
		if (type != -1 && cnt != type)
			continue;
		if (!sb_has_quota_active(sb, cnt))
			continue;
		spin_lock(&dq_list_lock);
		dirty = &dqopt->info[cnt].dqi_dirty_list;
		while (!list_empty(dirty)) {
			dquot = list_first_entry(dirty, struct dquot,
						 dq_dirty);
			/* Dirty and inactive can be only bad dquot... */
			if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) {
				clear_dquot_dirty(dquot);
				continue;
			}
			/* Now we have active dquot from which someone is
 			 * holding reference so we can safely just increase
			 * use count */
			atomic_inc(&dquot->dq_count);
			dqstats.lookups++;
			spin_unlock(&dq_list_lock);
			sb->dq_op->write_dquot(dquot);
			dqput(dquot);
			spin_lock(&dq_list_lock);
		}
		spin_unlock(&dq_list_lock);
	}

	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
		if ((cnt == type || type == -1) && sb_has_quota_active(sb, cnt)
		    && info_dirty(&dqopt->info[cnt]))
			sb->dq_op->write_info(sb, cnt);
	spin_lock(&dq_list_lock);
	dqstats.syncs++;
	spin_unlock(&dq_list_lock);
	mutex_unlock(&dqopt->dqonoff_mutex);

	if (!wait || (sb_dqopt(sb)->flags & DQUOT_QUOTA_SYS_FILE))
		return 0;

	/* This is not very clever (and fast) but currently I don't know about
	 * any other simple way of getting quota data to disk and we must get
	 * them there for userspace to be visible... */
	if (sb->s_op->sync_fs)
		sb->s_op->sync_fs(sb, 1);
	sync_blockdev(sb->s_bdev);

	/*
	 * Now when everything is written we can discard the pagecache so
	 * that userspace sees the changes.
	 */
	mutex_lock(&sb_dqopt(sb)->dqonoff_mutex);
	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
		if (type != -1 && cnt != type)
			continue;
		if (!sb_has_quota_active(sb, cnt))
			continue;
		mutex_lock_nested(&sb_dqopt(sb)->files[cnt]->i_mutex,
				  I_MUTEX_QUOTA);
		truncate_inode_pages(&sb_dqopt(sb)->files[cnt]->i_data, 0);
		mutex_unlock(&sb_dqopt(sb)->files[cnt]->i_mutex);
	}
	mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex);

	return 0;
}
EXPORT_SYMBOL(vfs_quota_sync);

/* Free unused dquots from cache */
static void prune_dqcache(int count)
{
	struct list_head *head;
	struct dquot *dquot;

	head = free_dquots.prev;
	while (head != &free_dquots && count) {
		dquot = list_entry(head, struct dquot, dq_free);
		remove_dquot_hash(dquot);
		remove_free_dquot(dquot);
		remove_inuse(dquot);
		do_destroy_dquot(dquot);
		count--;
		head = free_dquots.prev;
	}
}

/*
 * This is called from kswapd when we think we need some
 * more memory
 */

static int shrink_dqcache_memory(int nr, gfp_t gfp_mask)
{
	if (nr) {
		spin_lock(&dq_list_lock);
		prune_dqcache(nr);
		spin_unlock(&dq_list_lock);
	}
	return (dqstats.free_dquots / 100) * sysctl_vfs_cache_pressure;
}

static struct shrinker dqcache_shrinker = {
	.shrink = shrink_dqcache_memory,
	.seeks = DEFAULT_SEEKS,
};

/*
 * Put reference to dquot
 * NOTE: If you change this function please check whether dqput_blocks() works right...
 */
void dqput(struct dquot *dquot)
{
	int ret;

	if (!dquot)
		return;
#ifdef CONFIG_QUOTA_DEBUG
	if (!atomic_read(&dquot->dq_count)) {
		printk("VFS: dqput: trying to free free dquot\n");
		printk("VFS: device %s, dquot of %s %d\n",
			dquot->dq_sb->s_id,
			quotatypes[dquot->dq_type],
			dquot->dq_id);
		BUG();
	}
#endif
	
	spin_lock(&dq_list_lock);
	dqstats.drops++;
	spin_unlock(&dq_list_lock);
we_slept:
	spin_lock(&dq_list_lock);
	if (atomic_read(&dquot->dq_count) > 1) {
		/* We have more than one user... nothing to do */
		atomic_dec(&dquot->dq_count);
		/* Releasing dquot during quotaoff phase? */
		if (!sb_has_quota_active(dquot->dq_sb, dquot->dq_type) &&
		    atomic_read(&dquot->dq_count) == 1)
			wake_up(&dquot->dq_wait_unused);
		spin_unlock(&dq_list_lock);
		return;
	}
	/* Need to release dquot? */
	if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags) && dquot_dirty(dquot)) {
		spin_unlock(&dq_list_lock);
		/* Commit dquot before releasing */
		ret = dquot->dq_sb->dq_op->write_dquot(dquot);
		if (ret < 0) {
			printk(KERN_ERR "VFS: cannot write quota structure on "
				"device %s (error %d). Quota may get out of "
				"sync!\n", dquot->dq_sb->s_id, ret);
			/*
			 * We clear dirty bit anyway, so that we avoid
			 * infinite loop here
			 */
			spin_lock(&dq_list_lock);
			clear_dquot_dirty(dquot);
			spin_unlock(&dq_list_lock);
		}
		goto we_slept;
	}
	/* Clear flag in case dquot was inactive (something bad happened) */
	clear_dquot_dirty(dquot);
	if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) {
		spin_unlock(&dq_list_lock);
		dquot->dq_sb->dq_op->release_dquot(dquot);
		goto we_slept;
	}
	atomic_dec(&dquot->dq_count);
#ifdef CONFIG_QUOTA_DEBUG
	/* sanity check */
	BUG_ON(!list_empty(&dquot->dq_free));
#endif
	put_dquot_last(dquot);
	spin_unlock(&dq_list_lock);
}
EXPORT_SYMBOL(dqput);

struct dquot *dquot_alloc(struct super_block *sb, int type)
{
	return kmem_cache_zalloc(dquot_cachep, GFP_NOFS);
}
EXPORT_SYMBOL(dquot_alloc);

static struct dquot *get_empty_dquot(struct super_block *sb, int type)
{
	struct dquot *dquot;

	dquot = sb->dq_op->alloc_dquot(sb, type);
	if(!dquot)
		return NULL;

	mutex_init(&dquot->dq_lock);
	INIT_LIST_HEAD(&dquot->dq_free);
	INIT_LIST_HEAD(&dquot->dq_inuse);
	INIT_HLIST_NODE(&dquot->dq_hash);
	INIT_LIST_HEAD(&dquot->dq_dirty);
	init_waitqueue_head(&dquot->dq_wait_unused);
	dquot->dq_sb = sb;
	dquot->dq_type = type;
	atomic_set(&dquot->dq_count, 1);

	return dquot;
}

/*
 * Get reference to dquot
 *
 * Locking is slightly tricky here. We are guarded from parallel quotaoff()
 * destroying our dquot by:
 *   a) checking for quota flags under dq_list_lock and
 *   b) getting a reference to dquot before we release dq_list_lock
 */
struct dquot *dqget(struct super_block *sb, unsigned int id, int type)
{
	unsigned int hashent = hashfn(sb, id, type);
	struct dquot *dquot = NULL, *empty = NULL;

        if (!sb_has_quota_active(sb, type))
		return NULL;
we_slept:
	spin_lock(&dq_list_lock);
	spin_lock(&dq_state_lock);
	if (!sb_has_quota_active(sb, type)) {
		spin_unlock(&dq_state_lock);
		spin_unlock(&dq_list_lock);
		goto out;
	}
	spin_unlock(&dq_state_lock);

	dquot = find_dquot(hashent, sb, id, type);
	if (!dquot) {
		if (!empty) {
			spin_unlock(&dq_list_lock);
			empty = get_empty_dquot(sb, type);
			if (!empty)
				schedule();	/* Try to wait for a moment... */
			goto we_slept;
		}
		dquot = empty;
		empty = NULL;
		dquot->dq_id = id;
		/* all dquots go on the inuse_list */
		put_inuse(dquot);
		/* hash it first so it can be found */
		insert_dquot_hash(dquot);
		dqstats.lookups++;
		spin_unlock(&dq_list_lock);
	} else {
		if (!atomic_read(&dquot->dq_count))
			remove_free_dquot(dquot);
		atomic_inc(&dquot->dq_count);
		dqstats.cache_hits++;
		dqstats.lookups++;
		spin_unlock(&dq_list_lock);
	}
	/* Wait for dq_lock - after this we know that either dquot_release() is
	 * already finished or it will be canceled due to dq_count > 1 test */
	wait_on_dquot(dquot);
	/* Read the dquot / allocate space in quota file */
	if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags) &&
	    sb->dq_op->acquire_dquot(dquot) < 0) {
		dqput(dquot);
		dquot = NULL;
		goto out;
	}
#ifdef CONFIG_QUOTA_DEBUG
	BUG_ON(!dquot->dq_sb);	/* Has somebody invalidated entry under us? */
#endif
out:
	if (empty)
		do_destroy_dquot(empty);

	return dquot;
}
EXPORT_SYMBOL(dqget);

static int dqinit_needed(struct inode *inode, int type)
{
	int cnt;

	if (IS_NOQUOTA(inode))
		return 0;
	if (type != -1)
		return !inode->i_dquot[type];
	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
		if (!inode->i_dquot[cnt])
			return 1;
	return 0;
}

/* This routine is guarded by dqonoff_mutex mutex */
static void add_dquot_ref(struct super_block *sb, int type)
{
	struct inode *inode, *old_inode = NULL;
#ifdef CONFIG_QUOTA_DEBUG
	int reserved = 0;
#endif

	spin_lock(&inode_lock);
	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
		if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
			continue;
#ifdef CONFIG_QUOTA_DEBUG
		if (unlikely(inode_get_rsv_space(inode) > 0))
			reserved = 1;
#endif
		if (!atomic_read(&inode->i_writecount))
			continue;
		if (!dqinit_needed(inode, type))
			continue;

		__iget(inode);
		spin_unlock(&inode_lock);

		iput(old_inode);
		__dquot_initialize(inode, type);
		/* We hold a reference to 'inode' so it couldn't have been
		 * removed from s_inodes list while we dropped the inode_lock.
		 * We cannot iput the inode now as we can be holding the last
		 * reference and we cannot iput it under inode_lock. So we
		 * keep the reference and iput it later. */
		old_inode = inode;
		spin_lock(&inode_lock);
	}
	spin_unlock(&inode_lock);
	iput(old_inode);

#ifdef CONFIG_QUOTA_DEBUG
	if (reserved) {
		printk(KERN_WARNING "VFS (%s): Writes happened before quota"
			" was turned on thus quota information is probably "
			"inconsistent. Please run quotacheck(8).\n", sb->s_id);
	}
#endif
}

/*
 * Return 0 if dqput() won't block.
 * (note that 1 doesn't necessarily mean blocking)
 */
static inline int dqput_blocks(struct dquot *dquot)
{
	if (atomic_read(&dquot->dq_count) <= 1)
		return 1;
	return 0;
}

/*
 * Remove references to dquots from inode and add dquot to list for freeing
 * if we have the last referece to dquot
 * We can't race with anybody because we hold dqptr_sem for writing...
 */
static int remove_inode_dquot_ref(struct inode *inode, int type,
				  struct list_head *tofree_head)
{
	struct dquot *dquot = inode->i_dquot[type];

	inode->i_dquot[type] = NULL;
	if (dquot) {
		if (dqput_blocks(dquot)) {
#ifdef CONFIG_QUOTA_DEBUG
			if (atomic_read(&dquot->dq_count) != 1)
				printk(KERN_WARNING "VFS: Adding dquot with dq_count %d to dispose list.\n", atomic_read(&dquot->dq_count));
#endif
			spin_lock(&dq_list_lock);
			/* As dquot must have currently users it can't be on
			 * the free list... */
			list_add(&dquot->dq_free, tofree_head);
			spin_unlock(&dq_list_lock);
			return 1;
		}
		else
			dqput(dquot);   /* We have guaranteed we won't block */
	}
	return 0;
}

/*
 * Free list of dquots
 * Dquots are removed from inodes and no new references can be got so we are
 * the only ones holding reference
 */
static void put_dquot_list(struct list_head *tofree_head)
{
	struct list_head *act_head;
	struct dquot *dquot;

	act_head = tofree_head->next;
	while (act_head != tofree_head) {
		dquot = list_entry(act_head, struct dquot, dq_free);
		act_head = act_head->next;
		/* Remove dquot from the list so we won't have problems... */
		list_del_init(&dquot->dq_free);
		dqput(dquot);
	}
}

static void remove_dquot_ref(struct super_block *sb, int type,
		struct list_head *tofree_head)
{
	struct inode *inode;

	spin_lock(&inode_lock);
	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
		/*
		 *  We have to scan also I_NEW inodes because they can already
		 *  have quota pointer initialized. Luckily, we need to touch
		 *  only quota pointers and these have separate locking
		 *  (dqptr_sem).
		 */
		if (!IS_NOQUOTA(inode))
			remove_inode_dquot_ref(inode, type, tofree_head);
	}
	spin_unlock(&inode_lock);
}

/* Gather all references from inodes and drop them */
static void drop_dquot_ref(struct super_block *sb, int type)
{
	LIST_HEAD(tofree_head);

	if (sb->dq_op) {
		down_write(&sb_dqopt(sb)->dqptr_sem);
		remove_dquot_ref(sb, type, &tofree_head);
		up_write(&sb_dqopt(sb)->dqptr_sem);
		put_dquot_list(&tofree_head);
	}
}

static inline void dquot_incr_inodes(struct dquot *dquot, qsize_t number)
{
	dquot->dq_dqb.dqb_curinodes += number;
}

static inline void dquot_incr_space(struct dquot *dquot, qsize_t number)
{
	dquot->dq_dqb.dqb_curspace += number;
}

static inline void dquot_resv_space(struct dquot *dquot, qsize_t number)
{
	dquot->dq_dqb.dqb_rsvspace += number;
}

/*
 * Claim reserved quota space
 */
static void dquot_claim_reserved_space(struct dquot *dquot, qsize_t number)
{
	if (dquot->dq_dqb.dqb_rsvspace < number) {
		WARN_ON_ONCE(1);
		number = dquot->dq_dqb.dqb_rsvspace;
	}
	dquot->dq_dqb.dqb_curspace += number;
	dquot->dq_dqb.dqb_rsvspace -= number;
}

static inline
void dquot_free_reserved_space(struct dquot *dquot, qsize_t number)
{
	if (dquot->dq_dqb.dqb_rsvspace >= number)
		dquot->dq_dqb.dqb_rsvspace -= number;
	else {
		WARN_ON_ONCE(1);
		dquot->dq_dqb.dqb_rsvspace = 0;
	}
}

static void dquot_decr_inodes(struct dquot *dquot, qsize_t number)
{
	if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NEGATIVE_USAGE ||
	    dquot->dq_dqb.dqb_curinodes >= number)
		dquot->dq_dqb.dqb_curinodes -= number;
	else
		dquot->dq_dqb.dqb_curinodes = 0;
	if (dquot->dq_dqb.dqb_curinodes <= dquot->dq_dqb.dqb_isoftlimit)
		dquot->dq_dqb.dqb_itime = (time_t) 0;
	clear_bit(DQ_INODES_B, &dquot->dq_flags);
}

static void dquot_decr_space(struct dquot *dquot, qsize_t number)
{
	if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NEGATIVE_USAGE ||
	    dquot->dq_dqb.dqb_curspace >= number)
		dquot->dq_dqb.dqb_curspace -= number;
	else
		dquot->dq_dqb.dqb_curspace = 0;
	if (dquot->dq_dqb.dqb_curspace <= dquot->dq_dqb.dqb_bsoftlimit)
		dquot->dq_dqb.dqb_btime = (time_t) 0;
	clear_bit(DQ_BLKS_B, &dquot->dq_flags);
}

static int warning_issued(struct dquot *dquot, const int warntype)
{
	int flag = (warntype == QUOTA_NL_BHARDWARN ||
		warntype == QUOTA_NL_BSOFTLONGWARN) ? DQ_BLKS_B :
		((warntype == QUOTA_NL_IHARDWARN ||
		warntype == QUOTA_NL_ISOFTLONGWARN) ? DQ_INODES_B : 0);

	if (!flag)
		return 0;
	return test_and_set_bit(flag, &dquot->dq_flags);
}

#ifdef CONFIG_PRINT_QUOTA_WARNING
static int flag_print_warnings = 1;

static int need_print_warning(struct dquot *dquot)
{
	if (!flag_print_warnings)
		return 0;

	switch (dquot->dq_type) {
		case USRQUOTA:
			return current_fsuid() == dquot->dq_id;
		case GRPQUOTA:
			return in_group_p(dquot->dq_id);
	}
	return 0;
}

/* Print warning to user which exceeded quota */
static void print_warning(struct dquot *dquot, const int warntype)
{
	char *msg = NULL;
	struct tty_struct *tty;

	if (warntype == QUOTA_NL_IHARDBELOW ||
	    warntype == QUOTA_NL_ISOFTBELOW ||
	    warntype == QUOTA_NL_BHARDBELOW ||
	    warntype == QUOTA_NL_BSOFTBELOW || !need_print_warning(dquot))
		return;

	tty = get_current_tty();
	if (!tty)
		return;
	tty_write_message(tty, dquot->dq_sb->s_id);
	if (warntype == QUOTA_NL_ISOFTWARN || warntype == QUOTA_NL_BSOFTWARN)
		tty_write_message(tty, ": warning, ");
	else
		tty_write_message(tty, ": write failed, ");
	tty_write_message(tty, quotatypes[dquot->dq_type]);
	switch (warntype) {
		case QUOTA_NL_IHARDWARN:
			msg = " file limit reached.\r\n";
			break;
		case QUOTA_NL_ISOFTLONGWARN:
			msg = " file quota exceeded too long.\r\n";
			break;
		case QUOTA_NL_ISOFTWARN:
			msg = " file quota exceeded.\r\n";
			break;
		case QUOTA_NL_BHARDWARN:
			msg = " block limit reached.\r\n";
			break;
		case QUOTA_NL_BSOFTLONGWARN:
			msg = " block quota exceeded too long.\r\n";
			break;
		case QUOTA_NL_BSOFTWARN:
			msg = " block quota exceeded.\r\n";
			break;
	}
	tty_write_message(tty, msg);
	tty_kref_put(tty);
}
#endif

/*
 * Write warnings to the console and send warning messages over netlink.
 *
 * Note that this function can sleep.
 */
static void flush_warnings(struct dquot *const *dquots, char *warntype)
{
	struct dquot *dq;
	int i;

	for (i = 0; i < MAXQUOTAS; i++) {
		dq = dquots[i];
		if (dq && warntype[i] != QUOTA_NL_NOWARN &&
		    !warning_issued(dq, warntype[i])) {
#ifdef CONFIG_PRINT_QUOTA_WARNING
			print_warning(dq, warntype[i]);
#endif
			quota_send_warning(dq->dq_type, dq->dq_id,
					   dq->dq_sb->s_dev, warntype[i]);
		}
	}
}

static int ignore_hardlimit(struct dquot *dquot)
{
	struct mem_dqinfo *info = &sb_dqopt(dquot->dq_sb)->info[dquot->dq_type];

	return capable(CAP_SYS_RESOURCE) &&
	       (info->dqi_format->qf_fmt_id != QFMT_VFS_OLD ||
		!(info->dqi_flags & V1_DQF_RSQUASH));
}

/* needs dq_data_lock */
static int check_idq(struct dquot *dquot, qsize_t inodes, char *warntype)
{
	qsize_t newinodes = dquot->dq_dqb.dqb_curinodes + inodes;

	*warntype = QUOTA_NL_NOWARN;
	if (!sb_has_quota_limits_enabled(dquot->dq_sb, dquot->dq_type) ||
	    test_bit(DQ_FAKE_B, &dquot->dq_flags))
		return 0;

	if (dquot->dq_dqb.dqb_ihardlimit &&
	    newinodes > dquot->dq_dqb.dqb_ihardlimit &&
            !ignore_hardlimit(dquot)) {
		*warntype = QUOTA_NL_IHARDWARN;
		return -EDQUOT;
	}

	if (dquot->dq_dqb.dqb_isoftlimit &&
	    newinodes > dquot->dq_dqb.dqb_isoftlimit &&
	    dquot->dq_dqb.dqb_itime &&
	    get_seconds() >= dquot->dq_dqb.dqb_itime &&
            !ignore_hardlimit(dquot)) {
		*warntype = QUOTA_NL_ISOFTLONGWARN;
		return -EDQUOT;
	}

	if (dquot->dq_dqb.dqb_isoftlimit &&
	    newinodes > dquot->dq_dqb.dqb_isoftlimit &&
	    dquot->dq_dqb.dqb_itime == 0) {
		*warntype = QUOTA_NL_ISOFTWARN;
		dquot->dq_dqb.dqb_itime = get_seconds() +
		    sb_dqopt(dquot->dq_sb)->info[dquot->dq_type].dqi_igrace;
	}

	return 0;
}

/* needs dq_data_lock */
static int check_bdq(struct dquot *dquot, qsize_t space, int prealloc, char *warntype)
{
	qsize_t tspace;
	struct super_block *sb = dquot->dq_sb;

	*warntype = QUOTA_NL_NOWARN;
	if (!sb_has_quota_limits_enabled(sb, dquot->dq_type) ||
	    test_bit(DQ_FAKE_B, &dquot->dq_flags))
		return 0;

	tspace = dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace
		+ space;

	if (dquot->dq_dqb.dqb_bhardlimit &&
	    tspace > dquot->dq_dqb.dqb_bhardlimit &&
            !ignore_hardlimit(dquot)) {
		if (!prealloc)
			*warntype = QUOTA_NL_BHARDWARN;
		return -EDQUOT;
	}

	if (dquot->dq_dqb.dqb_bsoftlimit &&
	    tspace > dquot->dq_dqb.dqb_bsoftlimit &&
	    dquot->dq_dqb.dqb_btime &&
	    get_seconds() >= dquot->dq_dqb.dqb_btime &&
            !ignore_hardlimit(dquot)) {
		if (!prealloc)
			*warntype = QUOTA_NL_BSOFTLONGWARN;
		return -EDQUOT;
	}

	if (dquot->dq_dqb.dqb_bsoftlimit &&
	    tspace > dquot->dq_dqb.dqb_bsoftlimit &&
	    dquot->dq_dqb.dqb_btime == 0) {
		if (!prealloc) {
			*warntype = QUOTA_NL_BSOFTWARN;
			dquot->dq_dqb.dqb_btime = get_seconds() +
			    sb_dqopt(sb)->info[dquot->dq_type].dqi_bgrace;
		}
		else
			/*
			 * We don't allow preallocation to exceed softlimit so exceeding will
			 * be always printed
			 */
			return -EDQUOT;
	}

	return 0;
}

static int info_idq_free(struct dquot *dquot, qsize_t inodes)
{
	qsize_t newinodes;

	if (test_bit(DQ_FAKE_B, &dquot->dq_flags) ||
	    dquot->dq_dqb.dqb_curinodes <= dquot->dq_dqb.dqb_isoftlimit ||
	    !sb_has_quota_limits_enabled(dquot->dq_sb, dquot->dq_type))
		return QUOTA_NL_NOWARN;

	newinodes = dquot->dq_dqb.dqb_curinodes - inodes;
	if (newinodes <= dquot->dq_dqb.dqb_isoftlimit)
		return QUOTA_NL_ISOFTBELOW;
	if (dquot->dq_dqb.dqb_curinodes >= dquot->dq_dqb.dqb_ihardlimit &&
	    newinodes < dquot->dq_dqb.dqb_ihardlimit)
		return QUOTA_NL_IHARDBELOW;
	return QUOTA_NL_NOWARN;
}

static int info_bdq_free(struct dquot *dquot, qsize_t space)
{
	if (test_bit(DQ_FAKE_B, &dquot->dq_flags) ||
	    dquot->dq_dqb.dqb_curspace <= dquot->dq_dqb.dqb_bsoftlimit)
		return QUOTA_NL_NOWARN;

	if (dquot->dq_dqb.dqb_curspace - space <= dquot->dq_dqb.dqb_bsoftlimit)
		return QUOTA_NL_BSOFTBELOW;
	if (dquot->dq_dqb.dqb_curspace >= dquot->dq_dqb.dqb_bhardlimit &&
	    dquot->dq_dqb.dqb_curspace - space < dquot->dq_dqb.dqb_bhardlimit)
		return QUOTA_NL_BHARDBELOW;
	return QUOTA_NL_NOWARN;
}

/*
 * Initialize quota pointers in inode
 *
 * We do things in a bit complicated way but by that we avoid calling
 * dqget() and thus filesystem callbacks under dqptr_sem.
 *
 * It is better to call this function outside of any transaction as it
 * might need a lot of space in journal for dquot structure allocation.
 */
static void __dquot_initialize(struct inode *inode, int type)
{
	unsigned int id = 0;
	int cnt;
	struct dquot *got[MAXQUOTAS];
	struct super_block *sb = inode->i_sb;
	qsize_t rsv;

	/* First test before acquiring mutex - solves deadlocks when we
         * re-enter the quota code and are already holding the mutex */
	if (!sb_any_quota_active(inode->i_sb) || IS_NOQUOTA(inode))
		return;

	/* First get references to structures we might need. */
	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
		got[cnt] = NULL;
		if (type != -1 && cnt != type)
			continue;
		switch (cnt) {
		case USRQUOTA:
			id = inode->i_uid;
			break;
		case GRPQUOTA:
			id = inode->i_gid;
			break;
		}
		got[cnt] = dqget(sb, id, cnt);
	}

	down_write(&sb_dqopt(sb)->dqptr_sem);
	if (IS_NOQUOTA(inode))
		goto out_err;
	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
		if (type != -1 && cnt != type)
			continue;
		/* Avoid races with quotaoff() */
		if (!sb_has_quota_active(sb, cnt))
			continue;
		if (!inode->i_dquot[cnt]) {
			inode->i_dquot[cnt] = got[cnt];
			got[cnt] = NULL;
			/*
			 * Make quota reservation system happy if someone
			 * did a write before quota was turned on
			 */
			rsv = inode_get_rsv_space(inode);
			if (unlikely(rsv))
				dquot_resv_space(inode->i_dquot[cnt], rsv);
		}
	}
out_err:
	up_write(&sb_dqopt(sb)->dqptr_sem);
	/* Drop unused references */
	dqput_all(got);
}

void dquot_initialize(struct inode *inode)
{
	__dquot_initialize(inode, -1);
}
EXPORT_SYMBOL(dquot_initialize);

/*
 * 	Release all quotas referenced by inode
 */
static void __dquot_drop(struct inode *inode)
{
	int cnt;
	struct dquot *put[MAXQUOTAS];

	down_write(&sb_dqopt(inode->i_sb)->dqptr_sem);
	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
		put[cnt] = inode->i_dquot[cnt];
		inode->i_dquot[cnt] = NULL;
	}
	up_write(&sb_dqopt(inode->i_sb)->dqptr_sem);
	dqput_all(put);
}

void dquot_drop(struct inode *inode)
{
	int cnt;

	if (IS_NOQUOTA(inode))
		return;

	/*
	 * Test before calling to rule out calls from proc and such
	 * where we are not allowed to block. Note that this is
	 * actually reliable test even without the lock - the caller
	 * must assure that nobody can come after the DQUOT_DROP and
	 * add quota pointers back anyway.
	 */
	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
		if (inode->i_dquot[cnt])
			break;
	}

	if (cnt < MAXQUOTAS)
		__dquot_drop(inode);
}
EXPORT_SYMBOL(dquot_drop);

/*
 * inode_reserved_space is managed internally by quota, and protected by
 * i_lock similar to i_blocks+i_bytes.
 */
static qsize_t *inode_reserved_space(struct inode * inode)
{
	/* Filesystem must explicitly define it's own method in order to use
	 * quota reservation interface */
	BUG_ON(!inode->i_sb->dq_op->get_reserved_space);
	return inode->i_sb->dq_op->get_reserved_space(inode);
}

void inode_add_rsv_space(struct inode *inode, qsize_t number)
{
	spin_lock(&inode->i_lock);
	*inode_reserved_space(inode) += number;
	spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL(inode_add_rsv_space);

void inode_claim_rsv_space(struct inode *inode, qsize_t number)
{
	spin_lock(&inode->i_lock);
	*inode_reserved_space(inode) -= number;
	__inode_add_bytes(inode, number);
	spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL(inode_claim_rsv_space);

void inode_sub_rsv_space(struct inode *inode, qsize_t number)
{
	spin_lock(&inode->i_lock);
	*inode_reserved_space(inode) -= number;
	spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL(inode_sub_rsv_space);

static qsize_t inode_get_rsv_space(struct inode *inode)
{
	qsize_t ret;

	if (!inode->i_sb->dq_op->get_reserved_space)
		return 0;
	spin_lock(&inode->i_lock);
	ret = *inode_reserved_space(inode);
	spin_unlock(&inode->i_lock);
	return ret;
}

static void inode_incr_space(struct inode *inode, qsize_t number,
				int reserve)
{
	if (reserve)
		inode_add_rsv_space(inode, number);
	else
		inode_add_bytes(inode, number);
}

static void inode_decr_space(struct inode *inode, qsize_t number, int reserve)
{
	if (reserve)
		inode_sub_rsv_space(inode, number);
	else
		inode_sub_bytes(inode, number);
}

/*
 * This functions updates i_blocks+i_bytes fields and quota information
 * (together with appropriate checks).
 *
 * NOTE: We absolutely rely on the fact that caller dirties the inode
 * (usually helpers in quotaops.h care about this) and holds a handle for
 * the current transaction so that dquot write and inode write go into the
 * same transaction.
 */

/*
 * This operation can block, but only after everything is updated
 */
int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags)
{
	int cnt, ret = 0;
	char warntype[MAXQUOTAS];
	int warn = flags & DQUOT_SPACE_WARN;
	int reserve = flags & DQUOT_SPACE_RESERVE;

	/*
	 * First test before acquiring mutex - solves deadlocks when we
	 * re-enter the quota code and are already holding the mutex
	 */
	if (!sb_any_quota_active(inode->i_sb) || IS_NOQUOTA(inode)) {
		inode_incr_space(inode, number, reserve);
		goto out;
	}

	down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
		warntype[cnt] = QUOTA_NL_NOWARN;

	spin_lock(&dq_data_lock);
	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
		if (!inode->i_dquot[cnt])
			continue;
		ret = check_bdq(inode->i_dquot[cnt], number, !warn,
				warntype+cnt);
		if (ret) {
			spin_unlock(&dq_data_lock);
			goto out_flush_warn;
		}
	}
	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
		if (!inode->i_dquot[cnt])
			continue;
		if (reserve)
			dquot_resv_space(inode->i_dquot[cnt], number);
		else
			dquot_incr_space(inode->i_dquot[cnt], number);
	}
	inode_incr_space(inode, number, reserve);
	spin_unlock(&dq_data_lock);

	if (reserve)
		goto out_flush_warn;
	mark_all_dquot_dirty(inode->i_dquot);
out_flush_warn:
	flush_warnings(inode->i_dquot, warntype);
	up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
out:
	return ret;
}
EXPORT_SYMBOL(__dquot_alloc_space);

/*
 * This operation can block, but only after everything is updated
 */
int dquot_alloc_inode(const struct inode *inode)
{
	int cnt, ret = 0;
	char warntype[MAXQUOTAS];

	/* First test before acquiring mutex - solves deadlocks when we
         * re-enter the quota code and are already holding the mutex */
	if (!sb_any_quota_active(inode->i_sb) || IS_NOQUOTA(inode))
		return 0;
	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
		warntype[cnt] = QUOTA_NL_NOWARN;
	down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
	spin_lock(&dq_data_lock);
	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
		if (!inode->i_dquot[cnt])
			continue;
		ret = check_idq(inode->i_dquot[cnt], 1, warntype + cnt);
		if (ret)
			goto warn_put_all;
	}

	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
		if (!inode->i_dquot[cnt])
			continue;
		dquot_incr_inodes(inode->i_dquot[cnt], 1);
	}

warn_put_all:
	spin_unlock(&dq_data_lock);
	if (ret == 0)
		mark_all_dquot_dirty(inode->i_dquot);
	flush_warnings(inode->i_dquot, warntype);
	up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
	return ret;
}
EXPORT_SYMBOL(dquot_alloc_inode);

/*
 * Convert in-memory reserved quotas to real consumed quotas
 */
int dquot_claim_space_nodirty(struct inode *inode, qsize_t number)
{
	int cnt;

	if (!sb_any_quota_active(inode->i_sb) || IS_NOQUOTA(inode)) {
		inode_claim_rsv_space(inode, number);
		return 0;
	}

	down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
	spin_lock(&dq_data_lock);
	/* Claim reserved quotas to allocated quotas */
	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
		if (inode->i_dquot[cnt])
			dquot_claim_reserved_space(inode->i_dquot[cnt],
							number);
	}
	/* Update inode bytes */
	inode_claim_rsv_space(inode, number);
	spin_unlock(&dq_data_lock);
	mark_all_dquot_dirty(inode->i_dquot);
	up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
	return 0;
}
EXPORT_SYMBOL(dquot_claim_space_nodirty);

/*
 * This operation can block, but only after everything is updated
 */
void __dquot_free_space(struct inode *inode, qsize_t number, int flags)
{
	unsigned int cnt;
	char warntype[MAXQUOTAS];
	int reserve = flags & DQUOT_SPACE_RESERVE;

	/* First test before acquiring mutex - solves deadlocks when we
         * re-enter the quota code and are already holding the mutex */
	if (!sb_any_quota_active(inode->i_sb) || IS_NOQUOTA(inode)) {
		inode_decr_space(inode, number, reserve);
		return;
	}

	down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
	spin_lock(&dq_data_lock);
	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
		if (!inode->i_dquot[cnt])
			continue;
		warntype[cnt] = info_bdq_free(inode->i_dquot[cnt], number);
		if (reserve)
			dquot_free_reserved_space(inode->i_dquot[cnt], number);
		else
			dquot_decr_space(inode->i_dquot[cnt], number);
	}
	inode_decr_space(inode, number, reserve);
	spin_unlock(&dq_data_lock);

	if (reserve)
		goto out_unlock;
	mark_all_dquot_dirty(inode->i_dquot);
out_unlock:
	flush_warnings(inode->i_dquot, warntype);
	up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
}
EXPORT_SYMBOL(__dquot_free_space);

/*
 * This operation can block, but only after everything is updated
 */
void dquot_free_inode(const struct inode *inode)
{
	unsigned int cnt;
	char warntype[MAXQUOTAS];

	/* First test before acquiring mutex - solves deadlocks when we
         * re-enter the quota code and are already holding the mutex */
	if (!sb_any_quota_active(inode->i_sb) || IS_NOQUOTA(inode))
		return;

	down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
	spin_lock(&dq_data_lock);
	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
		if (!inode->i_dquot[cnt])
			continue;
		warntype[cnt] = info_idq_free(inode->i_dquot[cnt], 1);
		dquot_decr_inodes(inode->i_dquot[cnt], 1);
	}
	spin_unlock(&dq_data_lock);
	mark_all_dquot_dirty(inode->i_dquot);
	flush_warnings(inode->i_dquot, warntype);
	up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
}
EXPORT_SYMBOL(dquot_free_inode);

/*
 * Transfer the number of inode and blocks from one diskquota to an other.
 *
 * This operation can block, but only after everything is updated
 * A transaction must be started when entering this function.
 */
static int __dquot_transfer(struct inode *inode, qid_t *chid, unsigned long mask)
{
	qsize_t space, cur_space;
	qsize_t rsv_space = 0;
	struct dquot *transfer_from[MAXQUOTAS];
	struct dquot *transfer_to[MAXQUOTAS];
	int cnt, ret = 0;
	char warntype_to[MAXQUOTAS];
	char warntype_from_inodes[MAXQUOTAS], warntype_from_space[MAXQUOTAS];

	/* First test before acquiring mutex - solves deadlocks when we
         * re-enter the quota code and are already holding the mutex */
	if (IS_NOQUOTA(inode))
		return 0;
	/* Initialize the arrays */
	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
		transfer_from[cnt] = NULL;
		transfer_to[cnt] = NULL;
		warntype_to[cnt] = QUOTA_NL_NOWARN;
	}
	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
		if (mask & (1 << cnt))
			transfer_to[cnt] = dqget(inode->i_sb, chid[cnt], cnt);
	}
	down_write(&sb_dqopt(inode->i_sb)->dqptr_sem);
	if (IS_NOQUOTA(inode)) {	/* File without quota accounting? */
		up_write(&sb_dqopt(inode->i_sb)->dqptr_sem);
		goto put_all;
	}
	spin_lock(&dq_data_lock);
	cur_space = inode_get_bytes(inode);
	rsv_space = inode_get_rsv_space(inode);
	space = cur_space + rsv_space;
	/* Build the transfer_from list and check the limits */
	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
		if (!transfer_to[cnt])
			continue;
		transfer_from[cnt] = inode->i_dquot[cnt];
		ret = check_idq(transfer_to[cnt], 1, warntype_to + cnt);
		if (ret)
			goto over_quota;
		ret = check_bdq(transfer_to[cnt], space, 0, warntype_to + cnt);
		if (ret)
			goto over_quota;
	}

	/*
	 * Finally perform the needed transfer from transfer_from to transfer_to
	 */
	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
		/*
		 * Skip changes for same uid or gid or for turned off quota-type.
		 */
		if (!transfer_to[cnt])
			continue;

		/* Due to IO error we might not have transfer_from[] structure */
		if (transfer_from[cnt]) {
			warntype_from_inodes[cnt] =
				info_idq_free(transfer_from[cnt], 1);
			warntype_from_space[cnt] =
				info_bdq_free(transfer_from[cnt], space);
			dquot_decr_inodes(transfer_from[cnt], 1);
			dquot_decr_space(transfer_from[cnt], cur_space);
			dquot_free_reserved_space(transfer_from[cnt],
						  rsv_space);
		}

		dquot_incr_inodes(transfer_to[cnt], 1);
		dquot_incr_space(transfer_to[cnt], cur_space);
		dquot_resv_space(transfer_to[cnt], rsv_space);

		inode->i_dquot[cnt] = transfer_to[cnt];
	}
	spin_unlock(&dq_data_lock);
	up_write(&sb_dqopt(inode->i_sb)->dqptr_sem);

	mark_all_dquot_dirty(transfer_from);
	mark_all_dquot_dirty(transfer_to);
	/* The reference we got is transferred to the inode */
	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
		transfer_to[cnt] = NULL;
warn_put_all:
	flush_warnings(transfer_to, warntype_to);
	flush_warnings(transfer_from, warntype_from_inodes);
	flush_warnings(transfer_from, warntype_from_space);
put_all:
	dqput_all(transfer_from);
	dqput_all(transfer_to);
	return ret;
over_quota:
	spin_unlock(&dq_data_lock);
	up_write(&sb_dqopt(inode->i_sb)->dqptr_sem);
	/* Clear dquot pointers we don't want to dqput() */
	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
		transfer_from[cnt] = NULL;
	goto warn_put_all;
}

/* Wrapper for transferring ownership of an inode for uid/gid only
 * Called from FSXXX_setattr()
 */
int dquot_transfer(struct inode *inode, struct iattr *iattr)
{
	qid_t chid[MAXQUOTAS];
	unsigned long mask = 0;

	if (iattr->ia_valid & ATTR_UID && iattr->ia_uid != inode->i_uid) {
		mask |= 1 << USRQUOTA;
		chid[USRQUOTA] = iattr->ia_uid;
	}
	if (iattr->ia_valid & ATTR_GID && iattr->ia_gid != inode->i_gid) {
		mask |= 1 << GRPQUOTA;
		chid[GRPQUOTA] = iattr->ia_gid;
	}
	if (sb_any_quota_active(inode->i_sb) && !IS_NOQUOTA(inode)) {
		dquot_initialize(inode);
		return __dquot_transfer(inode, chid, mask);
	}
	return 0;
}
EXPORT_SYMBOL(dquot_transfer);

/*
 * Write info of quota file to disk
 */
int dquot_commit_info(struct super_block *sb, int type)
{
	int ret;
	struct quota_info *dqopt = sb_dqopt(sb);

	mutex_lock(&dqopt->dqio_mutex);
	ret = dqopt->ops[type]->write_file_info(sb, type);
	mutex_unlock(&dqopt->dqio_mutex);
	return ret;
}
EXPORT_SYMBOL(dquot_commit_info);

/*
 * Definitions of diskquota operations.
 */
const struct dquot_operations dquot_operations = {
	.write_dquot	= dquot_commit,
	.acquire_dquot	= dquot_acquire,
	.release_dquot	= dquot_release,
	.mark_dirty	= dquot_mark_dquot_dirty,
	.write_info	= dquot_commit_info,
	.alloc_dquot	= dquot_alloc,
	.destroy_dquot	= dquot_destroy,
};

/*
 * Generic helper for ->open on filesystems supporting disk quotas.
 */
int dquot_file_open(struct inode *inode, struct file *file)
{
	int error;

	error = generic_file_open(inode, file);
	if (!error && (file->f_mode & FMODE_WRITE))
		dquot_initialize(inode);
	return error;
}
EXPORT_SYMBOL(dquot_file_open);

/*
 * Turn quota off on a device. type == -1 ==> quotaoff for all types (umount)
 */
int vfs_quota_disable(struct super_block *sb, int type, unsigned int flags)
{
	int cnt, ret = 0;
	struct quota_info *dqopt = sb_dqopt(sb);
	struct inode *toputinode[MAXQUOTAS];

	/* Cannot turn off usage accounting without turning off limits, or
	 * suspend quotas and simultaneously turn quotas off. */
	if ((flags & DQUOT_USAGE_ENABLED && !(flags & DQUOT_LIMITS_ENABLED))
	    || (flags & DQUOT_SUSPENDED && flags & (DQUOT_LIMITS_ENABLED |
	    DQUOT_USAGE_ENABLED)))
		return -EINVAL;

	/* We need to serialize quota_off() for device */
	mutex_lock(&dqopt->dqonoff_mutex);

	/*
	 * Skip everything if there's nothing to do. We have to do this because
	 * sometimes we are called when fill_super() failed and calling
	 * sync_fs() in such cases does no good.
	 */
	if (!sb_any_quota_loaded(sb)) {
		mutex_unlock(&dqopt->dqonoff_mutex);
		return 0;
	}
	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
		toputinode[cnt] = NULL;
		if (type != -1 && cnt != type)
			continue;
		if (!sb_has_quota_loaded(sb, cnt))
			continue;

		if (flags & DQUOT_SUSPENDED) {
			spin_lock(&dq_state_lock);
			dqopt->flags |=
				dquot_state_flag(DQUOT_SUSPENDED, cnt);
			spin_unlock(&dq_state_lock);
		} else {
			spin_lock(&dq_state_lock);
			dqopt->flags &= ~dquot_state_flag(flags, cnt);
			/* Turning off suspended quotas? */
			if (!sb_has_quota_loaded(sb, cnt) &&
			    sb_has_quota_suspended(sb, cnt)) {
				dqopt->flags &=	~dquot_state_flag(
							DQUOT_SUSPENDED, cnt);
				spin_unlock(&dq_state_lock);
				iput(dqopt->files[cnt]);
				dqopt->files[cnt] = NULL;
				continue;
			}
			spin_unlock(&dq_state_lock);
		}

		/* We still have to keep quota loaded? */
		if (sb_has_quota_loaded(sb, cnt) && !(flags & DQUOT_SUSPENDED))
			continue;

		/* Note: these are blocking operations */
		drop_dquot_ref(sb, cnt);
		invalidate_dquots(sb, cnt);
		/*
		 * Now all dquots should be invalidated, all writes done so we
		 * should be only users of the info. No locks needed.
		 */
		if (info_dirty(&dqopt->info[cnt]))
			sb->dq_op->write_info(sb, cnt);
		if (dqopt->ops[cnt]->free_file_info)
			dqopt->ops[cnt]->free_file_info(sb, cnt);
		put_quota_format(dqopt->info[cnt].dqi_format);

		toputinode[cnt] = dqopt->files[cnt];
		if (!sb_has_quota_loaded(sb, cnt))
			dqopt->files[cnt] = NULL;
		dqopt->info[cnt].dqi_flags = 0;
		dqopt->info[cnt].dqi_igrace = 0;
		dqopt->info[cnt].dqi_bgrace = 0;
		dqopt->ops[cnt] = NULL;
	}
	mutex_unlock(&dqopt->dqonoff_mutex);

	/* Skip syncing and setting flags if quota files are hidden */
	if (dqopt->flags & DQUOT_QUOTA_SYS_FILE)
		goto put_inodes;

	/* Sync the superblock so that buffers with quota data are written to
	 * disk (and so userspace sees correct data afterwards). */
	if (sb->s_op->sync_fs)
		sb->s_op->sync_fs(sb, 1);
	sync_blockdev(sb->s_bdev);
	/* Now the quota files are just ordinary files and we can set the
	 * inode flags back. Moreover we discard the pagecache so that
	 * userspace sees the writes we did bypassing the pagecache. We
	 * must also discard the blockdev buffers so that we see the
	 * changes done by userspace on the next quotaon() */
	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
		if (toputinode[cnt]) {
			mutex_lock(&dqopt->dqonoff_mutex);
			/* If quota was reenabled in the meantime, we have
			 * nothing to do */
			if (!sb_has_quota_loaded(sb, cnt)) {
				mutex_lock_nested(&toputinode[cnt]->i_mutex,
						  I_MUTEX_QUOTA);
				toputinode[cnt]->i_flags &= ~(S_IMMUTABLE |
				  S_NOATIME | S_NOQUOTA);
				truncate_inode_pages(&toputinode[cnt]->i_data,
						     0);
				mutex_unlock(&toputinode[cnt]->i_mutex);
				mark_inode_dirty(toputinode[cnt]);
			}
			mutex_unlock(&dqopt->dqonoff_mutex);
		}
	if (sb->s_bdev)
		invalidate_bdev(sb->s_bdev);
put_inodes:
	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
		if (toputinode[cnt]) {
			/* On remount RO, we keep the inode pointer so that we
			 * can reenable quota on the subsequent remount RW. We
			 * have to check 'flags' variable and not use sb_has_
			 * function because another quotaon / quotaoff could
			 * change global state before we got here. We refuse
			 * to suspend quotas when there is pending delete on
			 * the quota file... */
			if (!(flags & DQUOT_SUSPENDED))
				iput(toputinode[cnt]);
			else if (!toputinode[cnt]->i_nlink)
				ret = -EBUSY;
		}
	return ret;
}
EXPORT_SYMBOL(vfs_quota_disable);

int vfs_quota_off(struct super_block *sb, int type, int remount)
{
	return vfs_quota_disable(sb, type, remount ? DQUOT_SUSPENDED :
				 (DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED));
}
EXPORT_SYMBOL(vfs_quota_off);
/*
 *	Turn quotas on on a device
 */

/*
 * Helper function to turn quotas on when we already have the inode of
 * quota file and no quota information is loaded.
 */
static int vfs_load_quota_inode(struct inode *inode, int type, int format_id,
	unsigned int flags)
{
	struct quota_format_type *fmt = find_quota_format(format_id);
	struct super_block *sb = inode->i_sb;
	struct quota_info *dqopt = sb_dqopt(sb);
	int error;
	int oldflags = -1;

	if (!fmt)
		return -ESRCH;
	if (!S_ISREG(inode->i_mode)) {
		error = -EACCES;
		goto out_fmt;
	}
	if (IS_RDONLY(inode)) {
		error = -EROFS;
		goto out_fmt;
	}
	if (!sb->s_op->quota_write || !sb->s_op->quota_read) {
		error = -EINVAL;
		goto out_fmt;
	}
	/* Usage always has to be set... */
	if (!(flags & DQUOT_USAGE_ENABLED)) {
		error = -EINVAL;
		goto out_fmt;
	}

	if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) {
		/* As we bypass the pagecache we must now flush all the
		 * dirty data and invalidate caches so that kernel sees
		 * changes from userspace. It is not enough to just flush
		 * the quota file since if blocksize < pagesize, invalidation
		 * of the cache could fail because of other unrelated dirty
		 * data */
		sync_filesystem(sb);
		invalidate_bdev(sb->s_bdev);
	}
	mutex_lock(&dqopt->dqonoff_mutex);
	if (sb_has_quota_loaded(sb, type)) {
		error = -EBUSY;
		goto out_lock;
	}

	if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) {
		/* We don't want quota and atime on quota files (deadlocks
		 * possible) Also nobody should write to the file - we use
		 * special IO operations which ignore the immutable bit. */
		mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
		oldflags = inode->i_flags & (S_NOATIME | S_IMMUTABLE |
					     S_NOQUOTA);
		inode->i_flags |= S_NOQUOTA | S_NOATIME | S_IMMUTABLE;
		mutex_unlock(&inode->i_mutex);
		/*
		 * When S_NOQUOTA is set, remove dquot references as no more
		 * references can be added
		 */
		__dquot_drop(inode);
	}

	error = -EIO;
	dqopt->files[type] = igrab(inode);
	if (!dqopt->files[type])
		goto out_lock;
	error = -EINVAL;
	if (!fmt->qf_ops->check_quota_file(sb, type))
		goto out_file_init;

	dqopt->ops[type] = fmt->qf_ops;
	dqopt->info[type].dqi_format = fmt;
	dqopt->info[type].dqi_fmt_id = format_id;
	INIT_LIST_HEAD(&dqopt->info[type].dqi_dirty_list);
	mutex_lock(&dqopt->dqio_mutex);
	error = dqopt->ops[type]->read_file_info(sb, type);
	if (error < 0) {
		mutex_unlock(&dqopt->dqio_mutex);
		goto out_file_init;
	}
	mutex_unlock(&dqopt->dqio_mutex);
	spin_lock(&dq_state_lock);
	dqopt->flags |= dquot_state_flag(flags, type);
	spin_unlock(&dq_state_lock);

	add_dquot_ref(sb, type);
	mutex_unlock(&dqopt->dqonoff_mutex);

	return 0;

out_file_init:
	dqopt->files[type] = NULL;
	iput(inode);
out_lock:
	if (oldflags != -1) {
		mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
		/* Set the flags back (in the case of accidental quotaon()
		 * on a wrong file we don't want to mess up the flags) */
		inode->i_flags &= ~(S_NOATIME | S_NOQUOTA | S_IMMUTABLE);
		inode->i_flags |= oldflags;
		mutex_unlock(&inode->i_mutex);
	}
	mutex_unlock(&dqopt->dqonoff_mutex);
out_fmt:
	put_quota_format(fmt);

	return error; 
}

/* Reenable quotas on remount RW */
static int vfs_quota_on_remount(struct super_block *sb, int type)
{
	struct quota_info *dqopt = sb_dqopt(sb);
	struct inode *inode;
	int ret;
	unsigned int flags;

	mutex_lock(&dqopt->dqonoff_mutex);
	if (!sb_has_quota_suspended(sb, type)) {
		mutex_unlock(&dqopt->dqonoff_mutex);
		return 0;
	}
	inode = dqopt->files[type];
	dqopt->files[type] = NULL;
	spin_lock(&dq_state_lock);
	flags = dqopt->flags & dquot_state_flag(DQUOT_USAGE_ENABLED |
						DQUOT_LIMITS_ENABLED, type);
	dqopt->flags &= ~dquot_state_flag(DQUOT_STATE_FLAGS, type);
	spin_unlock(&dq_state_lock);
	mutex_unlock(&dqopt->dqonoff_mutex);

	flags = dquot_generic_flag(flags, type);
	ret = vfs_load_quota_inode(inode, type, dqopt->info[type].dqi_fmt_id,
				   flags);
	iput(inode);

	return ret;
}

int vfs_quota_on_path(struct super_block *sb, int type, int format_id,
		      struct path *path)
{
	int error = security_quota_on(path->dentry);
	if (error)
		return error;
	/* Quota file not on the same filesystem? */
	if (path->mnt->mnt_sb != sb)
		error = -EXDEV;
	else
		error = vfs_load_quota_inode(path->dentry->d_inode, type,
					     format_id, DQUOT_USAGE_ENABLED |
					     DQUOT_LIMITS_ENABLED);
	return error;
}
EXPORT_SYMBOL(vfs_quota_on_path);

int vfs_quota_on(struct super_block *sb, int type, int format_id, char *name,
		 int remount)
{
	struct path path;
	int error;

	if (remount)
		return vfs_quota_on_remount(sb, type);

	error = kern_path(name, LOOKUP_FOLLOW, &path);
	if (!error) {
		error = vfs_quota_on_path(sb, type, format_id, &path);
		path_put(&path);
	}
	return error;
}
EXPORT_SYMBOL(vfs_quota_on);

/*
 * More powerful function for turning on quotas allowing setting
 * of individual quota flags
 */
int vfs_quota_enable(struct inode *inode, int type, int format_id,
		unsigned int flags)
{
	int ret = 0;
	struct super_block *sb = inode->i_sb;
	struct quota_info *dqopt = sb_dqopt(sb);

	/* Just unsuspend quotas? */
	if (flags & DQUOT_SUSPENDED)
		return vfs_quota_on_remount(sb, type);
	if (!flags)
		return 0;
	/* Just updating flags needed? */
	if (sb_has_quota_loaded(sb, type)) {
		mutex_lock(&dqopt->dqonoff_mutex);
		/* Now do a reliable test... */
		if (!sb_has_quota_loaded(sb, type)) {
			mutex_unlock(&dqopt->dqonoff_mutex);
			goto load_quota;
		}
		if (flags & DQUOT_USAGE_ENABLED &&
		    sb_has_quota_usage_enabled(sb, type)) {
			ret = -EBUSY;
			goto out_lock;
		}
		if (flags & DQUOT_LIMITS_ENABLED &&
		    sb_has_quota_limits_enabled(sb, type)) {
			ret = -EBUSY;
			goto out_lock;
		}
		spin_lock(&dq_state_lock);
		sb_dqopt(sb)->flags |= dquot_state_flag(flags, type);
		spin_unlock(&dq_state_lock);
out_lock:
		mutex_unlock(&dqopt->dqonoff_mutex);
		return ret;
	}

load_quota:
	return vfs_load_quota_inode(inode, type, format_id, flags);
}
EXPORT_SYMBOL(vfs_quota_enable);

/*
 * This function is used when filesystem needs to initialize quotas
 * during mount time.
 */
int vfs_quota_on_mount(struct super_block *sb, char *qf_name,
		int format_id, int type)
{
	struct dentry *dentry;
	int error;

	mutex_lock(&sb->s_root->d_inode->i_mutex);
	dentry = lookup_one_len(qf_name, sb->s_root, strlen(qf_name));
	mutex_unlock(&sb->s_root->d_inode->i_mutex);
	if (IS_ERR(dentry))
		return PTR_ERR(dentry);

	if (!dentry->d_inode) {
		error = -ENOENT;
		goto out;
	}

	error = security_quota_on(dentry);
	if (!error)
		error = vfs_load_quota_inode(dentry->d_inode, type, format_id,
				DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);

out:
	dput(dentry);
	return error;
}
EXPORT_SYMBOL(vfs_quota_on_mount);

/* Wrapper to turn on quotas when remounting rw */
int vfs_dq_quota_on_remount(struct super_block *sb)
{
	int cnt;
	int ret = 0, err;

	if (!sb->s_qcop || !sb->s_qcop->quota_on)
		return -ENOSYS;
	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
		err = sb->s_qcop->quota_on(sb, cnt, 0, NULL, 1);
		if (err < 0 && !ret)
			ret = err;
	}
	return ret;
}
EXPORT_SYMBOL(vfs_dq_quota_on_remount);

static inline qsize_t qbtos(qsize_t blocks)
{
	return blocks << QIF_DQBLKSIZE_BITS;
}

static inline qsize_t stoqb(qsize_t space)
{
	return (space + QIF_DQBLKSIZE - 1) >> QIF_DQBLKSIZE_BITS;
}

/* Generic routine for getting common part of quota structure */
static void do_get_dqblk(struct dquot *dquot, struct if_dqblk *di)
{
	struct mem_dqblk *dm = &dquot->dq_dqb;

	spin_lock(&dq_data_lock);
	di->dqb_bhardlimit = stoqb(dm->dqb_bhardlimit);
	di->dqb_bsoftlimit = stoqb(dm->dqb_bsoftlimit);
	di->dqb_curspace = dm->dqb_curspace + dm->dqb_rsvspace;
	di->dqb_ihardlimit = dm->dqb_ihardlimit;
	di->dqb_isoftlimit = dm->dqb_isoftlimit;
	di->dqb_curinodes = dm->dqb_curinodes;
	di->dqb_btime = dm->dqb_btime;
	di->dqb_itime = dm->dqb_itime;
	di->dqb_valid = QIF_ALL;
	spin_unlock(&dq_data_lock);
}

int vfs_get_dqblk(struct super_block *sb, int type, qid_t id,
		  struct if_dqblk *di)
{
	struct dquot *dquot;

	dquot = dqget(sb, id, type);
	if (!dquot)
		return -ESRCH;
	do_get_dqblk(dquot, di);
	dqput(dquot);

	return 0;
}
EXPORT_SYMBOL(vfs_get_dqblk);

/* Generic routine for setting common part of quota structure */
static int do_set_dqblk(struct dquot *dquot, struct if_dqblk *di)
{
	struct mem_dqblk *dm = &dquot->dq_dqb;
	int check_blim = 0, check_ilim = 0;
	struct mem_dqinfo *dqi = &sb_dqopt(dquot->dq_sb)->info[dquot->dq_type];

	if ((di->dqb_valid & QIF_BLIMITS &&
	     (di->dqb_bhardlimit > dqi->dqi_maxblimit ||
	      di->dqb_bsoftlimit > dqi->dqi_maxblimit)) ||
	    (di->dqb_valid & QIF_ILIMITS &&
	     (di->dqb_ihardlimit > dqi->dqi_maxilimit ||
	      di->dqb_isoftlimit > dqi->dqi_maxilimit)))
		return -ERANGE;

	spin_lock(&dq_data_lock);
	if (di->dqb_valid & QIF_SPACE) {
		dm->dqb_curspace = di->dqb_curspace - dm->dqb_rsvspace;
		check_blim = 1;
		set_bit(DQ_LASTSET_B + QIF_SPACE_B, &dquot->dq_flags);
	}
	if (di->dqb_valid & QIF_BLIMITS) {
		dm->dqb_bsoftlimit = qbtos(di->dqb_bsoftlimit);
		dm->dqb_bhardlimit = qbtos(di->dqb_bhardlimit);
		check_blim = 1;
		set_bit(DQ_LASTSET_B + QIF_BLIMITS_B, &dquot->dq_flags);
	}
	if (di->dqb_valid & QIF_INODES) {
		dm->dqb_curinodes = di->dqb_curinodes;
		check_ilim = 1;
		set_bit(DQ_LASTSET_B + QIF_INODES_B, &dquot->dq_flags);
	}
	if (di->dqb_valid & QIF_ILIMITS) {
		dm->dqb_isoftlimit = di->dqb_isoftlimit;
		dm->dqb_ihardlimit = di->dqb_ihardlimit;
		check_ilim = 1;
		set_bit(DQ_LASTSET_B + QIF_ILIMITS_B, &dquot->dq_flags);
	}
	if (di->dqb_valid & QIF_BTIME) {
		dm->dqb_btime = di->dqb_btime;
		check_blim = 1;
		set_bit(DQ_LASTSET_B + QIF_BTIME_B, &dquot->dq_flags);
	}
	if (di->dqb_valid & QIF_ITIME) {
		dm->dqb_itime = di->dqb_itime;
		check_ilim = 1;
		set_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags);
	}

	if (check_blim) {
		if (!dm->dqb_bsoftlimit ||
		    dm->dqb_curspace < dm->dqb_bsoftlimit) {
			dm->dqb_btime = 0;
			clear_bit(DQ_BLKS_B, &dquot->dq_flags);
		} else if (!(di->dqb_valid & QIF_BTIME))
			/* Set grace only if user hasn't provided his own... */
			dm->dqb_btime = get_seconds() + dqi->dqi_bgrace;
	}
	if (check_ilim) {
		if (!dm->dqb_isoftlimit ||
		    dm->dqb_curinodes < dm->dqb_isoftlimit) {
			dm->dqb_itime = 0;
			clear_bit(DQ_INODES_B, &dquot->dq_flags);
		} else if (!(di->dqb_valid & QIF_ITIME))
			/* Set grace only if user hasn't provided his own... */
			dm->dqb_itime = get_seconds() + dqi->dqi_igrace;
	}
	if (dm->dqb_bhardlimit || dm->dqb_bsoftlimit || dm->dqb_ihardlimit ||
	    dm->dqb_isoftlimit)
		clear_bit(DQ_FAKE_B, &dquot->dq_flags);
	else
		set_bit(DQ_FAKE_B, &dquot->dq_flags);
	spin_unlock(&dq_data_lock);
	mark_dquot_dirty(dquot);

	return 0;
}

int vfs_set_dqblk(struct super_block *sb, int type, qid_t id,
		  struct if_dqblk *di)
{
	struct dquot *dquot;
	int rc;

	dquot = dqget(sb, id, type);
	if (!dquot) {
		rc = -ESRCH;
		goto out;
	}
	rc = do_set_dqblk(dquot, di);
	dqput(dquot);
out:
	return rc;
}
EXPORT_SYMBOL(vfs_set_dqblk);

/* Generic routine for getting common part of quota file information */
int vfs_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii)
{
	struct mem_dqinfo *mi;
  
	mutex_lock(&sb_dqopt(sb)->dqonoff_mutex);
	if (!sb_has_quota_active(sb, type)) {
		mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex);
		return -ESRCH;
	}
	mi = sb_dqopt(sb)->info + type;
	spin_lock(&dq_data_lock);
	ii->dqi_bgrace = mi->dqi_bgrace;
	ii->dqi_igrace = mi->dqi_igrace;
	ii->dqi_flags = mi->dqi_flags & DQF_MASK;
	ii->dqi_valid = IIF_ALL;
	spin_unlock(&dq_data_lock);
	mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex);
	return 0;
}
EXPORT_SYMBOL(vfs_get_dqinfo);

/* Generic routine for setting common part of quota file information */
int vfs_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii)
{
	struct mem_dqinfo *mi;
	int err = 0;

	mutex_lock(&sb_dqopt(sb)->dqonoff_mutex);
	if (!sb_has_quota_active(sb, type)) {
		err = -ESRCH;
		goto out;
	}
	mi = sb_dqopt(sb)->info + type;
	spin_lock(&dq_data_lock);
	if (ii->dqi_valid & IIF_BGRACE)
		mi->dqi_bgrace = ii->dqi_bgrace;
	if (ii->dqi_valid & IIF_IGRACE)
		mi->dqi_igrace = ii->dqi_igrace;
	if (ii->dqi_valid & IIF_FLAGS)
		mi->dqi_flags = (mi->dqi_flags & ~DQF_MASK) |
				(ii->dqi_flags & DQF_MASK);
	spin_unlock(&dq_data_lock);
	mark_info_dirty(sb, type);
	/* Force write to disk */
	sb->dq_op->write_info(sb, type);
out:
	mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex);
	return err;
}
EXPORT_SYMBOL(vfs_set_dqinfo);

const struct quotactl_ops vfs_quotactl_ops = {
	.quota_on	= vfs_quota_on,
	.quota_off	= vfs_quota_off,
	.quota_sync	= vfs_quota_sync,
	.get_info	= vfs_get_dqinfo,
	.set_info	= vfs_set_dqinfo,
	.get_dqblk	= vfs_get_dqblk,
	.set_dqblk	= vfs_set_dqblk
};

static ctl_table fs_dqstats_table[] = {
	{
		.procname	= "lookups",
		.data		= &dqstats.lookups,
		.maxlen		= sizeof(int),
		.mode		= 0444,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "drops",
		.data		= &dqstats.drops,
		.maxlen		= sizeof(int),
		.mode		= 0444,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "reads",
		.data		= &dqstats.reads,
		.maxlen		= sizeof(int),
		.mode		= 0444,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "writes",
		.data		= &dqstats.writes,
		.maxlen		= sizeof(int),
		.mode		= 0444,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "cache_hits",
		.data		= &dqstats.cache_hits,
		.maxlen		= sizeof(int),
		.mode		= 0444,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "allocated_dquots",
		.data		= &dqstats.allocated_dquots,
		.maxlen		= sizeof(int),
		.mode		= 0444,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "free_dquots",
		.data		= &dqstats.free_dquots,
		.maxlen		= sizeof(int),
		.mode		= 0444,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "syncs",
		.data		= &dqstats.syncs,
		.maxlen		= sizeof(int),
		.mode		= 0444,
		.proc_handler	= proc_dointvec,
	},
#ifdef CONFIG_PRINT_QUOTA_WARNING
	{
		.procname	= "warnings",
		.data		= &flag_print_warnings,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
	{ },
};

static ctl_table fs_table[] = {
	{
		.procname	= "quota",
		.mode		= 0555,
		.child		= fs_dqstats_table,
	},
	{ },
};

static ctl_table sys_table[] = {
	{
		.procname	= "fs",
		.mode		= 0555,
		.child		= fs_table,
	},
	{ },
};

static int __init dquot_init(void)
{
	int i;
	unsigned long nr_hash, order;

	printk(KERN_NOTICE "VFS: Disk quotas %s\n", __DQUOT_VERSION__);

	register_sysctl_table(sys_table);

	dquot_cachep = kmem_cache_create("dquot",
			sizeof(struct dquot), sizeof(unsigned long) * 4,
			(SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
				SLAB_MEM_SPREAD|SLAB_PANIC),
			NULL);

	order = 0;
	dquot_hash = (struct hlist_head *)__get_free_pages(GFP_ATOMIC, order);
	if (!dquot_hash)
		panic("Cannot create dquot hash table");

	/* Find power-of-two hlist_heads which can fit into allocation */
	nr_hash = (1UL << order) * PAGE_SIZE / sizeof(struct hlist_head);
	dq_hash_bits = 0;
	do {
		dq_hash_bits++;
	} while (nr_hash >> dq_hash_bits);
	dq_hash_bits--;

	nr_hash = 1UL << dq_hash_bits;
	dq_hash_mask = nr_hash - 1;
	for (i = 0; i < nr_hash; i++)
		INIT_HLIST_HEAD(dquot_hash + i);

	printk("Dquot-cache hash table entries: %ld (order %ld, %ld bytes)\n",
			nr_hash, order, (PAGE_SIZE << order));

	register_shrinker(&dqcache_shrinker);

	return 0;
}
module_init(dquot_init);