summaryrefslogtreecommitdiffstats
path: root/fs/inode.c
blob: 86bfaca724dbdb9f0bded8076b03741ad2eddc58 (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
/*
 * (C) 1997 Linus Torvalds
 * (C) 1999 Andrea Arcangeli <andrea@suse.de> (dynamic inode allocation)
 */
#include <linux/export.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/backing-dev.h>
#include <linux/hash.h>
#include <linux/swap.h>
#include <linux/security.h>
#include <linux/cdev.h>
#include <linux/bootmem.h>
#include <linux/fsnotify.h>
#include <linux/mount.h>
#include <linux/posix_acl.h>
#include <linux/prefetch.h>
#include <linux/buffer_head.h> /* for inode_has_buffers */
#include <linux/ratelimit.h>
#include <linux/list_lru.h>
#include "internal.h"

/*
 * Inode locking rules:
 *
 * inode->i_lock protects:
 *   inode->i_state, inode->i_hash, __iget()
 * Inode LRU list locks protect:
 *   inode->i_sb->s_inode_lru, inode->i_lru
 * inode_sb_list_lock protects:
 *   sb->s_inodes, inode->i_sb_list
 * bdi->wb.list_lock protects:
 *   bdi->wb.b_{dirty,io,more_io}, inode->i_wb_list
 * inode_hash_lock protects:
 *   inode_hashtable, inode->i_hash
 *
 * Lock ordering:
 *
 * inode_sb_list_lock
 *   inode->i_lock
 *     Inode LRU list locks
 *
 * bdi->wb.list_lock
 *   inode->i_lock
 *
 * inode_hash_lock
 *   inode_sb_list_lock
 *   inode->i_lock
 *
 * iunique_lock
 *   inode_hash_lock
 */

static unsigned int i_hash_mask __read_mostly;
static unsigned int i_hash_shift __read_mostly;
static struct hlist_head *inode_hashtable __read_mostly;
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock);

__cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_sb_list_lock);

/*
 * Empty aops. Can be used for the cases where the user does not
 * define any of the address_space operations.
 */
const struct address_space_operations empty_aops = {
};
EXPORT_SYMBOL(empty_aops);

/*
 * Statistics gathering..
 */
struct inodes_stat_t inodes_stat;

static DEFINE_PER_CPU(unsigned long, nr_inodes);
static DEFINE_PER_CPU(unsigned long, nr_unused);

static struct kmem_cache *inode_cachep __read_mostly;

static long get_nr_inodes(void)
{
	int i;
	long sum = 0;
	for_each_possible_cpu(i)
		sum += per_cpu(nr_inodes, i);
	return sum < 0 ? 0 : sum;
}

static inline long get_nr_inodes_unused(void)
{
	int i;
	long sum = 0;
	for_each_possible_cpu(i)
		sum += per_cpu(nr_unused, i);
	return sum < 0 ? 0 : sum;
}

long get_nr_dirty_inodes(void)
{
	/* not actually dirty inodes, but a wild approximation */
	long nr_dirty = get_nr_inodes() - get_nr_inodes_unused();
	return nr_dirty > 0 ? nr_dirty : 0;
}

/*
 * Handle nr_inode sysctl
 */
#ifdef CONFIG_SYSCTL
int proc_nr_inodes(struct ctl_table *table, int write,
		   void __user *buffer, size_t *lenp, loff_t *ppos)
{
	inodes_stat.nr_inodes = get_nr_inodes();
	inodes_stat.nr_unused = get_nr_inodes_unused();
	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
#endif

static int no_open(struct inode *inode, struct file *file)
{
	return -ENXIO;
}

/**
 * inode_init_always - perform inode structure intialisation
 * @sb: superblock inode belongs to
 * @inode: inode to initialise
 *
 * These are initializations that need to be done on every inode
 * allocation as the fields are not initialised by slab allocation.
 */
int inode_init_always(struct super_block *sb, struct inode *inode)
{
	static const struct inode_operations empty_iops;
	static const struct file_operations no_open_fops = {.open = no_open};
	struct address_space *const mapping = &inode->i_data;

	inode->i_sb = sb;
	inode->i_blkbits = sb->s_blocksize_bits;
	inode->i_flags = 0;
	atomic_set(&inode->i_count, 1);
	inode->i_op = &empty_iops;
	inode->i_fop = &no_open_fops;
	inode->__i_nlink = 1;
	inode->i_opflags = 0;
	i_uid_write(inode, 0);
	i_gid_write(inode, 0);
	atomic_set(&inode->i_writecount, 0);
	inode->i_size = 0;
	inode->i_blocks = 0;
	inode->i_bytes = 0;
	inode->i_generation = 0;
	inode->i_pipe = NULL;
	inode->i_bdev = NULL;
	inode->i_cdev = NULL;
	inode->i_rdev = 0;
	inode->dirtied_when = 0;

	if (security_inode_alloc(inode))
		goto out;
	spin_lock_init(&inode->i_lock);
	lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key);

	mutex_init(&inode->i_mutex);
	lockdep_set_class(&inode->i_mutex, &sb->s_type->i_mutex_key);

	atomic_set(&inode->i_dio_count, 0);

	mapping->a_ops = &empty_aops;
	mapping->host = inode;
	mapping->flags = 0;
	atomic_set(&mapping->i_mmap_writable, 0);
	mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
	mapping->private_data = NULL;
	mapping->writeback_index = 0;
	inode->i_private = NULL;
	inode->i_mapping = mapping;
	INIT_HLIST_HEAD(&inode->i_dentry);	/* buggered by rcu freeing */
#ifdef CONFIG_FS_POSIX_ACL
	inode->i_acl = inode->i_default_acl = ACL_NOT_CACHED;
#endif

#ifdef CONFIG_FSNOTIFY
	inode->i_fsnotify_mask = 0;
#endif
	inode->i_flctx = NULL;
	this_cpu_inc(nr_inodes);

	return 0;
out:
	return -ENOMEM;
}
EXPORT_SYMBOL(inode_init_always);

static struct inode *alloc_inode(struct super_block *sb)
{
	struct inode *inode;

	if (sb->s_op->alloc_inode)
		inode = sb->s_op->alloc_inode(sb);
	else
		inode = kmem_cache_alloc(inode_cachep, GFP_KERNEL);

	if (!inode)
		return NULL;

	if (unlikely(inode_init_always(sb, inode))) {
		if (inode->i_sb->s_op->destroy_inode)
			inode->i_sb->s_op->destroy_inode(inode);
		else
			kmem_cache_free(inode_cachep, inode);
		return NULL;
	}

	return inode;
}

void free_inode_nonrcu(struct inode *inode)
{
	kmem_cache_free(inode_cachep, inode);
}
EXPORT_SYMBOL(free_inode_nonrcu);

void __destroy_inode(struct inode *inode)
{
	BUG_ON(inode_has_buffers(inode));
	security_inode_free(inode);
	fsnotify_inode_delete(inode);
	locks_free_lock_context(inode->i_flctx);
	if (!inode->i_nlink) {
		WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0);
		atomic_long_dec(&inode->i_sb->s_remove_count);
	}

#ifdef CONFIG_FS_POSIX_ACL
	if (inode->i_acl && inode->i_acl != ACL_NOT_CACHED)
		posix_acl_release(inode->i_acl);
	if (inode->i_default_acl && inode->i_default_acl != ACL_NOT_CACHED)
		posix_acl_release(inode->i_default_acl);
#endif
	this_cpu_dec(nr_inodes);
}
EXPORT_SYMBOL(__destroy_inode);

static void i_callback(struct rcu_head *head)
{
	struct inode *inode = container_of(head, struct inode, i_rcu);
	kmem_cache_free(inode_cachep, inode);
}

static void destroy_inode(struct inode *inode)
{
	BUG_ON(!list_empty(&inode->i_lru));
	__destroy_inode(inode);
	if (inode->i_sb->s_op->destroy_inode)
		inode->i_sb->s_op->destroy_inode(inode);
	else
		call_rcu(&inode->i_rcu, i_callback);
}

/**
 * drop_nlink - directly drop an inode's link count
 * @inode: inode
 *
 * This is a low-level filesystem helper to replace any
 * direct filesystem manipulation of i_nlink.  In cases
 * where we are attempting to track writes to the
 * filesystem, a decrement to zero means an imminent
 * write when the file is truncated and actually unlinked
 * on the filesystem.
 */
void drop_nlink(struct inode *inode)
{
	WARN_ON(inode->i_nlink == 0);
	inode->__i_nlink--;
	if (!inode->i_nlink)
		atomic_long_inc(&inode->i_sb->s_remove_count);
}
EXPORT_SYMBOL(drop_nlink);

/**
 * clear_nlink - directly zero an inode's link count
 * @inode: inode
 *
 * This is a low-level filesystem helper to replace any
 * direct filesystem manipulation of i_nlink.  See
 * drop_nlink() for why we care about i_nlink hitting zero.
 */
void clear_nlink(struct inode *inode)
{
	if (inode->i_nlink) {
		inode->__i_nlink = 0;
		atomic_long_inc(&inode->i_sb->s_remove_count);
	}
}
EXPORT_SYMBOL(clear_nlink);

/**
 * set_nlink - directly set an inode's link count
 * @inode: inode
 * @nlink: new nlink (should be non-zero)
 *
 * This is a low-level filesystem helper to replace any
 * direct filesystem manipulation of i_nlink.
 */
void set_nlink(struct inode *inode, unsigned int nlink)
{
	if (!nlink) {
		clear_nlink(inode);
	} else {
		/* Yes, some filesystems do change nlink from zero to one */
		if (inode->i_nlink == 0)
			atomic_long_dec(&inode->i_sb->s_remove_count);

		inode->__i_nlink = nlink;
	}
}
EXPORT_SYMBOL(set_nlink);

/**
 * inc_nlink - directly increment an inode's link count
 * @inode: inode
 *
 * This is a low-level filesystem helper to replace any
 * direct filesystem manipulation of i_nlink.  Currently,
 * it is only here for parity with dec_nlink().
 */
void inc_nlink(struct inode *inode)
{
	if (unlikely(inode->i_nlink == 0)) {
		WARN_ON(!(inode->i_state & I_LINKABLE));
		atomic_long_dec(&inode->i_sb->s_remove_count);
	}

	inode->__i_nlink++;
}
EXPORT_SYMBOL(inc_nlink);

void address_space_init_once(struct address_space *mapping)
{
	memset(mapping, 0, sizeof(*mapping));
	INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC);
	spin_lock_init(&mapping->tree_lock);
	init_rwsem(&mapping->i_mmap_rwsem);
	INIT_LIST_HEAD(&mapping->private_list);
	spin_lock_init(&mapping->private_lock);
	mapping->i_mmap = RB_ROOT;
}
EXPORT_SYMBOL(address_space_init_once);

/*
 * These are initializations that only need to be done
 * once, because the fields are idempotent across use
 * of the inode, so let the slab aware of that.
 */
void inode_init_once(struct inode *inode)
{
	memset(inode, 0, sizeof(*inode));
	INIT_HLIST_NODE(&inode->i_hash);
	INIT_LIST_HEAD(&inode->i_devices);
	INIT_LIST_HEAD(&inode->i_wb_list);
	INIT_LIST_HEAD(&inode->i_lru);
	address_space_init_once(&inode->i_data);
	i_size_ordered_init(inode);
#ifdef CONFIG_FSNOTIFY
	INIT_HLIST_HEAD(&inode->i_fsnotify_marks);
#endif
}
EXPORT_SYMBOL(inode_init_once);

static void init_once(void *foo)
{
	struct inode *inode = (struct inode *) foo;

	inode_init_once(inode);
}

/*
 * inode->i_lock must be held
 */
void __iget(struct inode *inode)
{
	atomic_inc(&inode->i_count);
}

/*
 * get additional reference to inode; caller must already hold one.
 */
void ihold(struct inode *inode)
{
	WARN_ON(atomic_inc_return(&inode->i_count) < 2);
}
EXPORT_SYMBOL(ihold);

static void inode_lru_list_add(struct inode *inode)
{
	if (list_lru_add(&inode->i_sb->s_inode_lru, &inode->i_lru))
		this_cpu_inc(nr_unused);
}

/*
 * Add inode to LRU if needed (inode is unused and clean).
 *
 * Needs inode->i_lock held.
 */
void inode_add_lru(struct inode *inode)
{
	if (!(inode->i_state & (I_DIRTY | I_SYNC | I_FREEING | I_WILL_FREE)) &&
	    !atomic_read(&inode->i_count) && inode->i_sb->s_flags & MS_ACTIVE)
		inode_lru_list_add(inode);
}


static void inode_lru_list_del(struct inode *inode)
{

	if (list_lru_del(&inode->i_sb->s_inode_lru, &inode->i_lru))
		this_cpu_dec(nr_unused);
}

/**
 * inode_sb_list_add - add inode to the superblock list of inodes
 * @inode: inode to add
 */
void inode_sb_list_add(struct inode *inode)
{
	spin_lock(&inode_sb_list_lock);
	list_add(&inode->i_sb_list, &inode->i_sb->s_inodes);
	spin_unlock(&inode_sb_list_lock);
}
EXPORT_SYMBOL_GPL(inode_sb_list_add);

static inline void inode_sb_list_del(struct inode *inode)
{
	if (!list_empty(&inode->i_sb_list)) {
		spin_lock(&inode_sb_list_lock);
		list_del_init(&inode->i_sb_list);
		spin_unlock(&inode_sb_list_lock);
	}
}

static unsigned long hash(struct super_block *sb, unsigned long hashval)
{
	unsigned long tmp;

	tmp = (hashval * (unsigned long)sb) ^ (GOLDEN_RATIO_PRIME + hashval) /
			L1_CACHE_BYTES;
	tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> i_hash_shift);
	return tmp & i_hash_mask;
}

/**
 *	__insert_inode_hash - hash an inode
 *	@inode: unhashed inode
 *	@hashval: unsigned long value used to locate this object in the
 *		inode_hashtable.
 *
 *	Add an inode to the inode hash for this superblock.
 */
void __insert_inode_hash(struct inode *inode, unsigned long hashval)
{
	struct hlist_head *b = inode_hashtable + hash(inode->i_sb, hashval);

	spin_lock(&inode_hash_lock);
	spin_lock(&inode->i_lock);
	hlist_add_head(&inode->i_hash, b);
	spin_unlock(&inode->i_lock);
	spin_unlock(&inode_hash_lock);
}
EXPORT_SYMBOL(__insert_inode_hash);

/**
 *	__remove_inode_hash - remove an inode from the hash
 *	@inode: inode to unhash
 *
 *	Remove an inode from the superblock.
 */
void __remove_inode_hash(struct inode *inode)
{
	spin_lock(&inode_hash_lock);
	spin_lock(&inode->i_lock);
	hlist_del_init(&inode->i_hash);
	spin_unlock(&inode->i_lock);
	spin_unlock(&inode_hash_lock);
}
EXPORT_SYMBOL(__remove_inode_hash);

void clear_inode(struct inode *inode)
{
	might_sleep();
	/*
	 * We have to cycle tree_lock here because reclaim can be still in the
	 * process of removing the last page (in __delete_from_page_cache())
	 * and we must not free mapping under it.
	 */
	spin_lock_irq(&inode->i_data.tree_lock);
	BUG_ON(inode->i_data.nrpages);
	BUG_ON(inode->i_data.nrshadows);
	spin_unlock_irq(&inode->i_data.tree_lock);
	BUG_ON(!list_empty(&inode->i_data.private_list));
	BUG_ON(!(inode->i_state & I_FREEING));
	BUG_ON(inode->i_state & I_CLEAR);
	/* don't need i_lock here, no concurrent mods to i_state */
	inode->i_state = I_FREEING | I_CLEAR;
}
EXPORT_SYMBOL(clear_inode);

/*
 * Free the inode passed in, removing it from the lists it is still connected
 * to. We remove any pages still attached to the inode and wait for any IO that
 * is still in progress before finally destroying the inode.
 *
 * An inode must already be marked I_FREEING so that we avoid the inode being
 * moved back onto lists if we race with other code that manipulates the lists
 * (e.g. writeback_single_inode). The caller is responsible for setting this.
 *
 * An inode must already be removed from the LRU list before being evicted from
 * the cache. This should occur atomically with setting the I_FREEING state
 * flag, so no inodes here should ever be on the LRU when being evicted.
 */
static void evict(struct inode *inode)
{
	const struct super_operations *op = inode->i_sb->s_op;

	BUG_ON(!(inode->i_state & I_FREEING));
	BUG_ON(!list_empty(&inode->i_lru));

	if (!list_empty(&inode->i_wb_list))
		inode_wb_list_del(inode);

	inode_sb_list_del(inode);

	/*
	 * Wait for flusher thread to be done with the inode so that filesystem
	 * does not start destroying it while writeback is still running. Since
	 * the inode has I_FREEING set, flusher thread won't start new work on
	 * the inode.  We just have to wait for running writeback to finish.
	 */
	inode_wait_for_writeback(inode);

	if (op->evict_inode) {
		op->evict_inode(inode);
	} else {
		truncate_inode_pages_final(&inode->i_data);
		clear_inode(inode);
	}
	if (S_ISBLK(inode->i_mode) && inode->i_bdev)
		bd_forget(inode);
	if (S_ISCHR(inode->i_mode) && inode->i_cdev)
		cd_forget(inode);

	remove_inode_hash(inode);

	spin_lock(&inode->i_lock);
	wake_up_bit(&inode->i_state, __I_NEW);
	BUG_ON(inode->i_state != (I_FREEING | I_CLEAR));
	spin_unlock(&inode->i_lock);

	destroy_inode(inode);
}

/*
 * dispose_list - dispose of the contents of a local list
 * @head: the head of the list to free
 *
 * Dispose-list gets a local list with local inodes in it, so it doesn't
 * need to worry about list corruption and SMP locks.
 */
static void dispose_list(struct list_head *head)
{
	while (!list_empty(head)) {
		struct inode *inode;

		inode = list_first_entry(head, struct inode, i_lru);
		list_del_init(&inode->i_lru);

		evict(inode);
	}
}

/**
 * evict_inodes	- evict all evictable inodes for a superblock
 * @sb:		superblock to operate on
 *
 * Make sure that no inodes with zero refcount are retained.  This is
 * called by superblock shutdown after having MS_ACTIVE flag removed,
 * so any inode reaching zero refcount during or after that call will
 * be immediately evicted.
 */
void evict_inodes(struct super_block *sb)
{
	struct inode *inode, *next;
	LIST_HEAD(dispose);

	spin_lock(&inode_sb_list_lock);
	list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
		if (atomic_read(&inode->i_count))
			continue;

		spin_lock(&inode->i_lock);
		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
			spin_unlock(&inode->i_lock);
			continue;
		}

		inode->i_state |= I_FREEING;
		inode_lru_list_del(inode);
		spin_unlock(&inode->i_lock);
		list_add(&inode->i_lru, &dispose);
	}
	spin_unlock(&inode_sb_list_lock);

	dispose_list(&dispose);
}

/**
 * invalidate_inodes	- attempt to free all inodes on a superblock
 * @sb:		superblock to operate on
 * @kill_dirty: flag to guide handling of dirty inodes
 *
 * Attempts to free all inodes for a given superblock.  If there were any
 * busy inodes return a non-zero value, else zero.
 * If @kill_dirty is set, discard dirty inodes too, otherwise treat
 * them as busy.
 */
int invalidate_inodes(struct super_block *sb, bool kill_dirty)
{
	int busy = 0;
	struct inode *inode, *next;
	LIST_HEAD(dispose);

	spin_lock(&inode_sb_list_lock);
	list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
		spin_lock(&inode->i_lock);
		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
			spin_unlock(&inode->i_lock);
			continue;
		}
		if (inode->i_state & I_DIRTY && !kill_dirty) {
			spin_unlock(&inode->i_lock);
			busy = 1;
			continue;
		}
		if (atomic_read(&inode->i_count)) {
			spin_unlock(&inode->i_lock);
			busy = 1;
			continue;
		}

		inode->i_state |= I_FREEING;
		inode_lru_list_del(inode);
		spin_unlock(&inode->i_lock);
		list_add(&inode->i_lru, &dispose);
	}
	spin_unlock(&inode_sb_list_lock);

	dispose_list(&dispose);

	return busy;
}

/*
 * Isolate the inode from the LRU in preparation for freeing it.
 *
 * Any inodes which are pinned purely because of attached pagecache have their
 * pagecache removed.  If the inode has metadata buffers attached to
 * mapping->private_list then try to remove them.
 *
 * If the inode has the I_REFERENCED flag set, then it means that it has been
 * used recently - the flag is set in iput_final(). When we encounter such an
 * inode, clear the flag and move it to the back of the LRU so it gets another
 * pass through the LRU before it gets reclaimed. This is necessary because of
 * the fact we are doing lazy LRU updates to minimise lock contention so the
 * LRU does not have strict ordering. Hence we don't want to reclaim inodes
 * with this flag set because they are the inodes that are out of order.
 */
static enum lru_status inode_lru_isolate(struct list_head *item,
		struct list_lru_one *lru, spinlock_t *lru_lock, void *arg)
{
	struct list_head *freeable = arg;
	struct inode	*inode = container_of(item, struct inode, i_lru);

	/*
	 * we are inverting the lru lock/inode->i_lock here, so use a trylock.
	 * If we fail to get the lock, just skip it.
	 */
	if (!spin_trylock(&inode->i_lock))
		return LRU_SKIP;

	/*
	 * Referenced or dirty inodes are still in use. Give them another pass
	 * through the LRU as we canot reclaim them now.
	 */
	if (atomic_read(&inode->i_count) ||
	    (inode->i_state & ~I_REFERENCED)) {
		list_lru_isolate(lru, &inode->i_lru);
		spin_unlock(&inode->i_lock);
		this_cpu_dec(nr_unused);
		return LRU_REMOVED;
	}

	/* recently referenced inodes get one more pass */
	if (inode->i_state & I_REFERENCED) {
		inode->i_state &= ~I_REFERENCED;
		spin_unlock(&inode->i_lock);
		return LRU_ROTATE;
	}

	if (inode_has_buffers(inode) || inode->i_data.nrpages) {
		__iget(inode);
		spin_unlock(&inode->i_lock);
		spin_unlock(lru_lock);
		if (remove_inode_buffers(inode)) {
			unsigned long reap;
			reap = invalidate_mapping_pages(&inode->i_data, 0, -1);
			if (current_is_kswapd())
				__count_vm_events(KSWAPD_INODESTEAL, reap);
			else
				__count_vm_events(PGINODESTEAL, reap);
			if (current->reclaim_state)
				current->reclaim_state->reclaimed_slab += reap;
		}
		iput(inode);
		spin_lock(lru_lock);
		return LRU_RETRY;
	}

	WARN_ON(inode->i_state & I_NEW);
	inode->i_state |= I_FREEING;
	list_lru_isolate_move(lru, &inode->i_lru, freeable);
	spin_unlock(&inode->i_lock);

	this_cpu_dec(nr_unused);
	return LRU_REMOVED;
}

/*
 * Walk the superblock inode LRU for freeable inodes and attempt to free them.
 * This is called from the superblock shrinker function with a number of inodes
 * to trim from the LRU. Inodes to be freed are moved to a temporary list and
 * then are freed outside inode_lock by dispose_list().
 */
long prune_icache_sb(struct super_block *sb, struct shrink_control *sc)
{
	LIST_HEAD(freeable);
	long freed;

	freed = list_lru_shrink_walk(&sb->s_inode_lru, sc,
				     inode_lru_isolate, &freeable);
	dispose_list(&freeable);
	return freed;
}

static void __wait_on_freeing_inode(struct inode *inode);
/*
 * Called with the inode lock held.
 */
static struct inode *find_inode(struct super_block *sb,
				struct hlist_head *head,
				int (*test)(struct inode *, void *),
				void *data)
{
	struct inode *inode = NULL;

repeat:
	hlist_for_each_entry(inode, head, i_hash) {
		if (inode->i_sb != sb)
			continue;
		if (!test(inode, data))
			continue;
		spin_lock(&inode->i_lock);
		if (inode->i_state & (I_FREEING|I_WILL_FREE)) {
			__wait_on_freeing_inode(inode);
			goto repeat;
		}
		__iget(inode);
		spin_unlock(&inode->i_lock);
		return inode;
	}
	return NULL;
}

/*
 * find_inode_fast is the fast path version of find_inode, see the comment at
 * iget_locked for details.
 */
static struct inode *find_inode_fast(struct super_block *sb,
				struct hlist_head *head, unsigned long ino)
{
	struct inode *inode = NULL;

repeat:
	hlist_for_each_entry(inode, head, i_hash) {
		if (inode->i_ino != ino)
			continue;
		if (inode->i_sb != sb)
			continue;
		spin_lock(&inode->i_lock);
		if (inode->i_state & (I_FREEING|I_WILL_FREE)) {
			__wait_on_freeing_inode(inode);
			goto repeat;
		}
		__iget(inode);
		spin_unlock(&inode->i_lock);
		return inode;
	}
	return NULL;
}

/*
 * Each cpu owns a range of LAST_INO_BATCH numbers.
 * 'shared_last_ino' is dirtied only once out of LAST_INO_BATCH allocations,
 * to renew the exhausted range.
 *
 * This does not significantly increase overflow rate because every CPU can
 * consume at most LAST_INO_BATCH-1 unused inode numbers. So there is
 * NR_CPUS*(LAST_INO_BATCH-1) wastage. At 4096 and 1024, this is ~0.1% of the
 * 2^32 range, and is a worst-case. Even a 50% wastage would only increase
 * overflow rate by 2x, which does not seem too significant.
 *
 * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW
 * error if st_ino won't fit in target struct field. Use 32bit counter
 * here to attempt to avoid that.
 */
#define LAST_INO_BATCH 1024
static DEFINE_PER_CPU(unsigned int, last_ino);

unsigned int get_next_ino(void)
{
	unsigned int *p = &get_cpu_var(last_ino);
	unsigned int res = *p;

#ifdef CONFIG_SMP
	if (unlikely((res & (LAST_INO_BATCH-1)) == 0)) {
		static atomic_t shared_last_ino;
		int next = atomic_add_return(LAST_INO_BATCH, &shared_last_ino);

		res = next - LAST_INO_BATCH;
	}
#endif

	*p = ++res;
	put_cpu_var(last_ino);
	return res;
}
EXPORT_SYMBOL(get_next_ino);

/**
 *	new_inode_pseudo 	- obtain an inode
 *	@sb: superblock
 *
 *	Allocates a new inode for given superblock.
 *	Inode wont be chained in superblock s_inodes list
 *	This means :
 *	- fs can't be unmount
 *	- quotas, fsnotify, writeback can't work
 */
struct inode *new_inode_pseudo(struct super_block *sb)
{
	struct inode *inode = alloc_inode(sb);

	if (inode) {
		spin_lock(&inode->i_lock);
		inode->i_state = 0;
		spin_unlock(&inode->i_lock);
		INIT_LIST_HEAD(&inode->i_sb_list);
	}
	return inode;
}

/**
 *	new_inode 	- obtain an inode
 *	@sb: superblock
 *
 *	Allocates a new inode for given superblock. The default gfp_mask
 *	for allocations related to inode->i_mapping is GFP_HIGHUSER_MOVABLE.
 *	If HIGHMEM pages are unsuitable or it is known that pages allocated
 *	for the page cache are not reclaimable or migratable,
 *	mapping_set_gfp_mask() must be called with suitable flags on the
 *	newly created inode's mapping
 *
 */
struct inode *new_inode(struct super_block *sb)
{
	struct inode *inode;

	spin_lock_prefetch(&inode_sb_list_lock);

	inode = new_inode_pseudo(sb);
	if (inode)
		inode_sb_list_add(inode);
	return inode;
}
EXPORT_SYMBOL(new_inode);

#ifdef CONFIG_DEBUG_LOCK_ALLOC
void lockdep_annotate_inode_mutex_key(struct inode *inode)
{
	if (S_ISDIR(inode->i_mode)) {
		struct file_system_type *type = inode->i_sb->s_type;

		/* Set new key only if filesystem hasn't already changed it */
		if (lockdep_match_class(&inode->i_mutex, &type->i_mutex_key)) {
			/*
			 * ensure nobody is actually holding i_mutex
			 */
			mutex_destroy(&inode->i_mutex);
			mutex_init(&inode->i_mutex);
			lockdep_set_class(&inode->i_mutex,
					  &type->i_mutex_dir_key);
		}
	}
}
EXPORT_SYMBOL(lockdep_annotate_inode_mutex_key);
#endif

/**
 * unlock_new_inode - clear the I_NEW state and wake up any waiters
 * @inode:	new inode to unlock
 *
 * Called when the inode is fully initialised to clear the new state of the
 * inode and wake up anyone waiting for the inode to finish initialisation.
 */
void unlock_new_inode(struct inode *inode)
{
	lockdep_annotate_inode_mutex_key(inode);
	spin_lock(&inode->i_lock);
	WARN_ON(!(inode->i_state & I_NEW));
	inode->i_state &= ~I_NEW;
	smp_mb();
	wake_up_bit(&inode->i_state, __I_NEW);
	spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL(unlock_new_inode);

/**
 * lock_two_nondirectories - take two i_mutexes on non-directory objects
 *
 * Lock any non-NULL argument that is not a directory.
 * Zero, one or two objects may be locked by this function.
 *
 * @inode1: first inode to lock
 * @inode2: second inode to lock
 */
void lock_two_nondirectories(struct inode *inode1, struct inode *inode2)
{
	if (inode1 > inode2)
		swap(inode1, inode2);

	if (inode1 && !S_ISDIR(inode1->i_mode))
		mutex_lock(&inode1->i_mutex);
	if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1)
		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_NONDIR2);
}
EXPORT_SYMBOL(lock_two_nondirectories);

/**
 * unlock_two_nondirectories - release locks from lock_two_nondirectories()
 * @inode1: first inode to unlock
 * @inode2: second inode to unlock
 */
void unlock_two_nondirectories(struct inode *inode1, struct inode *inode2)
{
	if (inode1 && !S_ISDIR(inode1->i_mode))
		mutex_unlock(&inode1->i_mutex);
	if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1)
		mutex_unlock(&inode2->i_mutex);
}
EXPORT_SYMBOL(unlock_two_nondirectories);

/**
 * iget5_locked - obtain an inode from a mounted file system
 * @sb:		super block of file system
 * @hashval:	hash value (usually inode number) to get
 * @test:	callback used for comparisons between inodes
 * @set:	callback used to initialize a new struct inode
 * @data:	opaque data pointer to pass to @test and @set
 *
 * Search for the inode specified by @hashval and @data in the inode cache,
 * and if present it is return it with an increased reference count. This is
 * a generalized version of iget_locked() for file systems where the inode
 * number is not sufficient for unique identification of an inode.
 *
 * If the inode is not in cache, allocate a new inode and return it locked,
 * hashed, and with the I_NEW flag set. The file system gets to fill it in
 * before unlocking it via unlock_new_inode().
 *
 * Note both @test and @set are called with the inode_hash_lock held, so can't
 * sleep.
 */
struct inode *iget5_locked(struct super_block *sb, unsigned long hashval,
		int (*test)(struct inode *, void *),
		int (*set)(struct inode *, void *), void *data)
{
	struct hlist_head *head = inode_hashtable + hash(sb, hashval);
	struct inode *inode;

	spin_lock(&inode_hash_lock);
	inode = find_inode(sb, head, test, data);
	spin_unlock(&inode_hash_lock);

	if (inode) {
		wait_on_inode(inode);
		return inode;
	}

	inode = alloc_inode(sb);
	if (inode) {
		struct inode *old;

		spin_lock(&inode_hash_lock);
		/* We released the lock, so.. */
		old = find_inode(sb, head, test, data);
		if (!old) {
			if (set(inode, data))
				goto set_failed;

			spin_lock(&inode->i_lock);
			inode->i_state = I_NEW;
			hlist_add_head(&inode->i_hash, head);
			spin_unlock(&inode->i_lock);
			inode_sb_list_add(inode);
			spin_unlock(&inode_hash_lock);

			/* Return the locked inode with I_NEW set, the
			 * caller is responsible for filling in the contents
			 */
			return inode;
		}

		/*
		 * Uhhuh, somebody else created the same inode under
		 * us. Use the old inode instead of the one we just
		 * allocated.
		 */
		spin_unlock(&inode_hash_lock);
		destroy_inode(inode);
		inode = old;
		wait_on_inode(inode);
	}
	return inode;

set_failed:
	spin_unlock(&inode_hash_lock);
	destroy_inode(inode);
	return NULL;
}
EXPORT_SYMBOL(iget5_locked);

/**
 * iget_locked - obtain an inode from a mounted file system
 * @sb:		super block of file system
 * @ino:	inode number to get
 *
 * Search for the inode specified by @ino in the inode cache and if present
 * return it with an increased reference count. This is for file systems
 * where the inode number is sufficient for unique identification of an inode.
 *
 * If the inode is not in cache, allocate a new inode and return it locked,
 * hashed, and with the I_NEW flag set.  The file system gets to fill it in
 * before unlocking it via unlock_new_inode().
 */
struct inode *iget_locked(struct super_block *sb, unsigned long ino)
{
	struct hlist_head *head = inode_hashtable + hash(sb, ino);
	struct inode *inode;

	spin_lock(&inode_hash_lock);
	inode = find_inode_fast(sb, head, ino);
	spin_unlock(&inode_hash_lock);
	if (inode) {
		wait_on_inode(inode);
		return inode;
	}

	inode = alloc_inode(sb);
	if (inode) {
		struct inode *old;

		spin_lock(&inode_hash_lock);
		/* We released the lock, so.. */
		old = find_inode_fast(sb, head, ino);
		if (!old) {
			inode->i_ino = ino;
			spin_lock(&inode->i_lock);
			inode->i_state = I_NEW;
			hlist_add_head(&inode->i_hash, head);
			spin_unlock(&inode->i_lock);
			inode_sb_list_add(inode);
			spin_unlock(&inode_hash_lock);

			/* Return the locked inode with I_NEW set, the
			 * caller is responsible for filling in the contents
			 */
			return inode;
		}

		/*
		 * Uhhuh, somebody else created the same inode under
		 * us. Use the old inode instead of the one we just
		 * allocated.
		 */
		spin_unlock(&inode_hash_lock);
		destroy_inode(inode);
		inode = old;
		wait_on_inode(inode);
	}
	return inode;
}
EXPORT_SYMBOL(iget_locked);

/*
 * search the inode cache for a matching inode number.
 * If we find one, then the inode number we are trying to
 * allocate is not unique and so we should not use it.
 *
 * Returns 1 if the inode number is unique, 0 if it is not.
 */
static int test_inode_iunique(struct super_block *sb, unsigned long ino)
{
	struct hlist_head *b = inode_hashtable + hash(sb, ino);
	struct inode *inode;

	spin_lock(&inode_hash_lock);
	hlist_for_each_entry(inode, b, i_hash) {
		if (inode->i_ino == ino && inode->i_sb == sb) {
			spin_unlock(&inode_hash_lock);
			return 0;
		}
	}
	spin_unlock(&inode_hash_lock);

	return 1;
}

/**
 *	iunique - get a unique inode number
 *	@sb: superblock
 *	@max_reserved: highest reserved inode number
 *
 *	Obtain an inode number that is unique on the system for a given
 *	superblock. This is used by file systems that have no natural
 *	permanent inode numbering system. An inode number is returned that
 *	is higher than the reserved limit but unique.
 *
 *	BUGS:
 *	With a large number of inodes live on the file system this function
 *	currently becomes quite slow.
 */
ino_t iunique(struct super_block *sb, ino_t max_reserved)
{
	/*
	 * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW
	 * error if st_ino won't fit in target struct field. Use 32bit counter
	 * here to attempt to avoid that.
	 */
	static DEFINE_SPINLOCK(iunique_lock);
	static unsigned int counter;
	ino_t res;

	spin_lock(&iunique_lock);
	do {
		if (counter <= max_reserved)
			counter = max_reserved + 1;
		res = counter++;
	} while (!test_inode_iunique(sb, res));
	spin_unlock(&iunique_lock);

	return res;
}
EXPORT_SYMBOL(iunique);

struct inode *igrab(struct inode *inode)
{
	spin_lock(&inode->i_lock);
	if (!(inode->i_state & (I_FREEING|I_WILL_FREE))) {
		__iget(inode);
		spin_unlock(&inode->i_lock);
	} else {
		spin_unlock(&inode->i_lock);
		/*
		 * Handle the case where s_op->clear_inode is not been
		 * called yet, and somebody is calling igrab
		 * while the inode is getting freed.
		 */
		inode = NULL;
	}
	return inode;
}
EXPORT_SYMBOL(igrab);

/**
 * ilookup5_nowait - search for an inode in the inode cache
 * @sb:		super block of file system to search
 * @hashval:	hash value (usually inode number) to search for
 * @test:	callback used for comparisons between inodes
 * @data:	opaque data pointer to pass to @test
 *
 * Search for the inode specified by @hashval and @data in the inode cache.
 * If the inode is in the cache, the inode is returned with an incremented
 * reference count.
 *
 * Note: I_NEW is not waited upon so you have to be very careful what you do
 * with the returned inode.  You probably should be using ilookup5() instead.
 *
 * Note2: @test is called with the inode_hash_lock held, so can't sleep.
 */
struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval,
		int (*test)(struct inode *, void *), void *data)
{
	struct hlist_head *head = inode_hashtable + hash(sb, hashval);
	struct inode *inode;

	spin_lock(&inode_hash_lock);
	inode = find_inode(sb, head, test, data);
	spin_unlock(&inode_hash_lock);

	return inode;
}
EXPORT_SYMBOL(ilookup5_nowait);

/**
 * ilookup5 - search for an inode in the inode cache
 * @sb:		super block of file system to search
 * @hashval:	hash value (usually inode number) to search for
 * @test:	callback used for comparisons between inodes
 * @data:	opaque data pointer to pass to @test
 *
 * Search for the inode specified by @hashval and @data in the inode cache,
 * and if the inode is in the cache, return the inode with an incremented
 * reference count.  Waits on I_NEW before returning the inode.
 * returned with an incremented reference count.
 *
 * This is a generalized version of ilookup() for file systems where the
 * inode number is not sufficient for unique identification of an inode.
 *
 * Note: @test is called with the inode_hash_lock held, so can't sleep.
 */
struct inode *ilookup5(struct super_block *sb, unsigned long hashval,
		int (*test)(struct inode *, void *), void *data)
{
	struct inode *inode = ilookup5_nowait(sb, hashval, test, data);

	if (inode)
		wait_on_inode(inode);
	return inode;
}
EXPORT_SYMBOL(ilookup5);

/**
 * ilookup - search for an inode in the inode cache
 * @sb:		super block of file system to search
 * @ino:	inode number to search for
 *
 * Search for the inode @ino in the inode cache, and if the inode is in the
 * cache, the inode is returned with an incremented reference count.
 */
struct inode *ilookup(struct super_block *sb, unsigned long ino)
{
	struct hlist_head *head = inode_hashtable + hash(sb, ino);
	struct inode *inode;

	spin_lock(&inode_hash_lock);
	inode = find_inode_fast(sb, head, ino);
	spin_unlock(&inode_hash_lock);

	if (inode)
		wait_on_inode(inode);
	return inode;
}
EXPORT_SYMBOL(ilookup);

int insert_inode_locked(struct inode *inode)
{
	struct super_block *sb = inode->i_sb;
	ino_t ino = inode->i_ino;
	struct hlist_head *head = inode_hashtable + hash(sb, ino);

	while (1) {
		struct inode *old = NULL;
		spin_lock(&inode_hash_lock);
		hlist_for_each_entry(old, head, i_hash) {
			if (old->i_ino != ino)
				continue;
			if (old->i_sb != sb)
				continue;
			spin_lock(&old->i_lock);
			if (old->i_state & (I_FREEING|I_WILL_FREE)) {
				spin_unlock(&old->i_lock);
				continue;
			}
			break;
		}
		if (likely(!old)) {
			spin_lock(&inode->i_lock);
			inode->i_state |= I_NEW;
			hlist_add_head(&inode->i_hash, head);
			spin_unlock(&inode->i_lock);
			spin_unlock(&inode_hash_lock);
			return 0;
		}
		__iget(old);
		spin_unlock(&old->i_lock);
		spin_unlock(&inode_hash_lock);
		wait_on_inode(old);
		if (unlikely(!inode_unhashed(old))) {
			iput(old);
			return -EBUSY;
		}
		iput(old);
	}
}
EXPORT_SYMBOL(insert_inode_locked);

int insert_inode_locked4(struct inode *inode, unsigned long hashval,
		int (*test)(struct inode *, void *), void *data)
{
	struct super_block *sb = inode->i_sb;
	struct hlist_head *head = inode_hashtable + hash(sb, hashval);

	while (1) {
		struct inode *old = NULL;

		spin_lock(&inode_hash_lock);
		hlist_for_each_entry(old, head, i_hash) {
			if (old->i_sb != sb)
				continue;
			if (!test(old, data))
				continue;
			spin_lock(&old->i_lock);
			if (old->i_state & (I_FREEING|I_WILL_FREE)) {
				spin_unlock(&old->i_lock);
				continue;
			}
			break;
		}
		if (likely(!old)) {
			spin_lock(&inode->i_lock);
			inode->i_state |= I_NEW;
			hlist_add_head(&inode->i_hash, head);
			spin_unlock(&inode->i_lock);
			spin_unlock(&inode_hash_lock);
			return 0;
		}
		__iget(old);
		spin_unlock(&old->i_lock);
		spin_unlock(&inode_hash_lock);
		wait_on_inode(old);
		if (unlikely(!inode_unhashed(old))) {
			iput(old);
			return -EBUSY;
		}
		iput(old);
	}
}
EXPORT_SYMBOL(insert_inode_locked4);


int generic_delete_inode(struct inode *inode)
{
	return 1;
}
EXPORT_SYMBOL(generic_delete_inode);

/*
 * Called when we're dropping the last reference
 * to an inode.
 *
 * Call the FS "drop_inode()" function, defaulting to
 * the legacy UNIX filesystem behaviour.  If it tells
 * us to evict inode, do so.  Otherwise, retain inode
 * in cache if fs is alive, sync and evict if fs is
 * shutting down.
 */
static void iput_final(struct inode *inode)
{
	struct super_block *sb = inode->i_sb;
	const struct super_operations *op = inode->i_sb->s_op;
	int drop;

	WARN_ON(inode->i_state & I_NEW);

	if (op->drop_inode)
		drop = op->drop_inode(inode);
	else
		drop = generic_drop_inode(inode);

	if (!drop && (sb->s_flags & MS_ACTIVE)) {
		inode->i_state |= I_REFERENCED;
		inode_add_lru(inode);
		spin_unlock(&inode->i_lock);
		return;
	}

	if (!drop) {
		inode->i_state |= I_WILL_FREE;
		spin_unlock(&inode->i_lock);
		write_inode_now(inode, 1);
		spin_lock(&inode->i_lock);
		WARN_ON(inode->i_state & I_NEW);
		inode->i_state &= ~I_WILL_FREE;
	}

	inode->i_state |= I_FREEING;
	if (!list_empty(&inode->i_lru))
		inode_lru_list_del(inode);
	spin_unlock(&inode->i_lock);

	evict(inode);
}

/**
 *	iput	- put an inode
 *	@inode: inode to put
 *
 *	Puts an inode, dropping its usage count. If the inode use count hits
 *	zero, the inode is then freed and may also be destroyed.
 *
 *	Consequently, iput() can sleep.
 */
void iput(struct inode *inode)
{
	if (inode) {
		BUG_ON(inode->i_state & I_CLEAR);

		if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock))
			iput_final(inode);
	}
}
EXPORT_SYMBOL(iput);

/**
 *	bmap	- find a block number in a file
 *	@inode: inode of file
 *	@block: block to find
 *
 *	Returns the block number on the device holding the inode that
 *	is the disk block number for the block of the file requested.
 *	That is, asked for block 4 of inode 1 the function will return the
 *	disk block relative to the disk start that holds that block of the
 *	file.
 */
sector_t bmap(struct inode *inode, sector_t block)
{
	sector_t res = 0;
	if (inode->i_mapping->a_ops->bmap)
		res = inode->i_mapping->a_ops->bmap(inode->i_mapping, block);
	return res;
}
EXPORT_SYMBOL(bmap);

/*
 * With relative atime, only update atime if the previous atime is
 * earlier than either the ctime or mtime or if at least a day has
 * passed since the last atime update.
 */
static int relatime_need_update(struct vfsmount *mnt, struct inode *inode,
			     struct timespec now)
{

	if (!(mnt->mnt_flags & MNT_RELATIME))
		return 1;
	/*
	 * Is mtime younger than atime? If yes, update atime:
	 */
	if (timespec_compare(&inode->i_mtime, &inode->i_atime) >= 0)
		return 1;
	/*
	 * Is ctime younger than atime? If yes, update atime:
	 */
	if (timespec_compare(&inode->i_ctime, &inode->i_atime) >= 0)
		return 1;

	/*
	 * Is the previous atime value older than a day? If yes,
	 * update atime:
	 */
	if ((long)(now.tv_sec - inode->i_atime.tv_sec) >= 24*60*60)
		return 1;
	/*
	 * Good, we can skip the atime update:
	 */
	return 0;
}

/*
 * This does the actual work of updating an inodes time or version.  Must have
 * had called mnt_want_write() before calling this.
 */
static int update_time(struct inode *inode, struct timespec *time, int flags)
{
	if (inode->i_op->update_time)
		return inode->i_op->update_time(inode, time, flags);

	if (flags & S_ATIME)
		inode->i_atime = *time;
	if (flags & S_VERSION)
		inode_inc_iversion(inode);
	if (flags & S_CTIME)
		inode->i_ctime = *time;
	if (flags & S_MTIME)
		inode->i_mtime = *time;
	mark_inode_dirty_sync(inode);
	return 0;
}

/**
 *	touch_atime	-	update the access time
 *	@path: the &struct path to update
 *
 *	Update the accessed time on an inode and mark it for writeback.
 *	This function automatically handles read only file systems and media,
 *	as well as the "noatime" flag and inode specific "noatime" markers.
 */
void touch_atime(const struct path *path)
{
	struct vfsmount *mnt = path->mnt;
	struct inode *inode = path->dentry->d_inode;
	struct timespec now;

	if (inode->i_flags & S_NOATIME)
		return;
	if (IS_NOATIME(inode))
		return;
	if ((inode->i_sb->s_flags & MS_NODIRATIME) && S_ISDIR(inode->i_mode))
		return;

	if (mnt->mnt_flags & MNT_NOATIME)
		return;
	if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode))
		return;

	now = current_fs_time(inode->i_sb);

	if (!relatime_need_update(mnt, inode, now))
		return;

	if (timespec_equal(&inode->i_atime, &now))
		return;

	if (!sb_start_write_trylock(inode->i_sb))
		return;

	if (__mnt_want_write(mnt))
		goto skip_update;
	/*
	 * File systems can error out when updating inodes if they need to
	 * allocate new space to modify an inode (such is the case for
	 * Btrfs), but since we touch atime while walking down the path we
	 * really don't care if we failed to update the atime of the file,
	 * so just ignore the return value.
	 * We may also fail on filesystems that have the ability to make parts
	 * of the fs read only, e.g. subvolumes in Btrfs.
	 */
	update_time(inode, &now, S_ATIME);
	__mnt_drop_write(mnt);
skip_update:
	sb_end_write(inode->i_sb);
}
EXPORT_SYMBOL(touch_atime);

/*
 * The logic we want is
 *
 *	if suid or (sgid and xgrp)
 *		remove privs
 */
int should_remove_suid(struct dentry *dentry)
{
	umode_t mode = dentry->d_inode->i_mode;
	int kill = 0;

	/* suid always must be killed */
	if (unlikely(mode & S_ISUID))
		kill = ATTR_KILL_SUID;

	/*
	 * sgid without any exec bits is just a mandatory locking mark; leave
	 * it alone.  If some exec bits are set, it's a real sgid; kill it.
	 */
	if (unlikely((mode & S_ISGID) && (mode & S_IXGRP)))
		kill |= ATTR_KILL_SGID;

	if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode)))
		return kill;

	return 0;
}
EXPORT_SYMBOL(should_remove_suid);

static int __remove_suid(struct dentry *dentry, int kill)
{
	struct iattr newattrs;

	newattrs.ia_valid = ATTR_FORCE | kill;
	/*
	 * Note we call this on write, so notify_change will not
	 * encounter any conflicting delegations:
	 */
	return notify_change(dentry, &newattrs, NULL);
}

int file_remove_suid(struct file *file)
{
	struct dentry *dentry = file->f_path.dentry;
	struct inode *inode = dentry->d_inode;
	int killsuid;
	int killpriv;
	int error = 0;

	/* Fast path for nothing security related */
	if (IS_NOSEC(inode))
		return 0;

	killsuid = should_remove_suid(dentry);
	killpriv = security_inode_need_killpriv(dentry);

	if (killpriv < 0)
		return killpriv;
	if (killpriv)
		error = security_inode_killpriv(dentry);
	if (!error && killsuid)
		error = __remove_suid(dentry, killsuid);
	if (!error && (inode->i_sb->s_flags & MS_NOSEC))
		inode->i_flags |= S_NOSEC;

	return error;
}
EXPORT_SYMBOL(file_remove_suid);

/**
 *	file_update_time	-	update mtime and ctime time
 *	@file: file accessed
 *
 *	Update the mtime and ctime members of an inode and mark the inode
 *	for writeback.  Note that this function is meant exclusively for
 *	usage in the file write path of filesystems, and filesystems may
 *	choose to explicitly ignore update via this function with the
 *	S_NOCMTIME inode flag, e.g. for network filesystem where these
 *	timestamps are handled by the server.  This can return an error for
 *	file systems who need to allocate space in order to update an inode.
 */

int file_update_time(struct file *file)
{
	struct inode *inode = file_inode(file);
	struct timespec now;
	int sync_it = 0;
	int ret;

	/* First try to exhaust all avenues to not sync */
	if (IS_NOCMTIME(inode))
		return 0;

	now = current_fs_time(inode->i_sb);
	if (!timespec_equal(&inode->i_mtime, &now))
		sync_it = S_MTIME;

	if (!timespec_equal(&inode->i_ctime, &now))
		sync_it |= S_CTIME;

	if (IS_I_VERSION(inode))
		sync_it |= S_VERSION;

	if (!sync_it)
		return 0;

	/* Finally allowed to write? Takes lock. */
	if (__mnt_want_write_file(file))
		return 0;

	ret = update_time(inode, &now, sync_it);
	__mnt_drop_write_file(file);

	return ret;
}
EXPORT_SYMBOL(file_update_time);

int inode_needs_sync(struct inode *inode)
{
	if (IS_SYNC(inode))
		return 1;
	if (S_ISDIR(inode->i_mode) && IS_DIRSYNC(inode))
		return 1;
	return 0;
}
EXPORT_SYMBOL(inode_needs_sync);

/*
 * If we try to find an inode in the inode hash while it is being
 * deleted, we have to wait until the filesystem completes its
 * deletion before reporting that it isn't found.  This function waits
 * until the deletion _might_ have completed.  Callers are responsible
 * to recheck inode state.
 *
 * It doesn't matter if I_NEW is not set initially, a call to
 * wake_up_bit(&inode->i_state, __I_NEW) after removing from the hash list
 * will DTRT.
 */
static void __wait_on_freeing_inode(struct inode *inode)
{
	wait_queue_head_t *wq;
	DEFINE_WAIT_BIT(wait, &inode->i_state, __I_NEW);
	wq = bit_waitqueue(&inode->i_state, __I_NEW);
	prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
	spin_unlock(&inode->i_lock);
	spin_unlock(&inode_hash_lock);
	schedule();
	finish_wait(wq, &wait.wait);
	spin_lock(&inode_hash_lock);
}

static __initdata unsigned long ihash_entries;
static int __init set_ihash_entries(char *str)
{
	if (!str)
		return 0;
	ihash_entries = simple_strtoul(str, &str, 0);
	return 1;
}
__setup("ihash_entries=", set_ihash_entries);

/*
 * Initialize the waitqueues and inode hash table.
 */
void __init inode_init_early(void)
{
	unsigned int loop;

	/* If hashes are distributed across NUMA nodes, defer
	 * hash allocation until vmalloc space is available.
	 */
	if (hashdist)
		return;

	inode_hashtable =
		alloc_large_system_hash("Inode-cache",
					sizeof(struct hlist_head),
					ihash_entries,
					14,
					HASH_EARLY,
					&i_hash_shift,
					&i_hash_mask,
					0,
					0);

	for (loop = 0; loop < (1U << i_hash_shift); loop++)
		INIT_HLIST_HEAD(&inode_hashtable[loop]);
}

void __init inode_init(void)
{
	unsigned int loop;

	/* inode slab cache */
	inode_cachep = kmem_cache_create("inode_cache",
					 sizeof(struct inode),
					 0,
					 (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|
					 SLAB_MEM_SPREAD),
					 init_once);

	/* Hash may have been set up in inode_init_early */
	if (!hashdist)
		return;

	inode_hashtable =
		alloc_large_system_hash("Inode-cache",
					sizeof(struct hlist_head),
					ihash_entries,
					14,
					0,
					&i_hash_shift,
					&i_hash_mask,
					0,
					0);

	for (loop = 0; loop < (1U << i_hash_shift); loop++)
		INIT_HLIST_HEAD(&inode_hashtable[loop]);
}

void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev)
{
	inode->i_mode = mode;
	if (S_ISCHR(mode)) {
		inode->i_fop = &def_chr_fops;
		inode->i_rdev = rdev;
	} else if (S_ISBLK(mode)) {
		inode->i_fop = &def_blk_fops;
		inode->i_rdev = rdev;
	} else if (S_ISFIFO(mode))
		inode->i_fop = &pipefifo_fops;
	else if (S_ISSOCK(mode))
		;	/* leave it no_open_fops */
	else
		printk(KERN_DEBUG "init_special_inode: bogus i_mode (%o) for"
				  " inode %s:%lu\n", mode, inode->i_sb->s_id,
				  inode->i_ino);
}
EXPORT_SYMBOL(init_special_inode);

/**
 * inode_init_owner - Init uid,gid,mode for new inode according to posix standards
 * @inode: New inode
 * @dir: Directory inode
 * @mode: mode of the new inode
 */
void inode_init_owner(struct inode *inode, const struct inode *dir,
			umode_t mode)
{
	inode->i_uid = current_fsuid();
	if (dir && dir->i_mode & S_ISGID) {
		inode->i_gid = dir->i_gid;
		if (S_ISDIR(mode))
			mode |= S_ISGID;
	} else
		inode->i_gid = current_fsgid();
	inode->i_mode = mode;
}
EXPORT_SYMBOL(inode_init_owner);

/**
 * inode_owner_or_capable - check current task permissions to inode
 * @inode: inode being checked
 *
 * Return true if current either has CAP_FOWNER in a namespace with the
 * inode owner uid mapped, or owns the file.
 */
bool inode_owner_or_capable(const struct inode *inode)
{
	struct user_namespace *ns;

	if (uid_eq(current_fsuid(), inode->i_uid))
		return true;

	ns = current_user_ns();
	if (ns_capable(ns, CAP_FOWNER) && kuid_has_mapping(ns, inode->i_uid))
		return true;
	return false;
}
EXPORT_SYMBOL(inode_owner_or_capable);

/*
 * Direct i/o helper functions
 */
static void __inode_dio_wait(struct inode *inode)
{
	wait_queue_head_t *wq = bit_waitqueue(&inode->i_state, __I_DIO_WAKEUP);
	DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP);

	do {
		prepare_to_wait(wq, &q.wait, TASK_UNINTERRUPTIBLE);
		if (atomic_read(&inode->i_dio_count))
			schedule();
	} while (atomic_read(&inode->i_dio_count));
	finish_wait(wq, &q.wait);
}

/**
 * inode_dio_wait - wait for outstanding DIO requests to finish
 * @inode: inode to wait for
 *
 * Waits for all pending direct I/O requests to finish so that we can
 * proceed with a truncate or equivalent operation.
 *
 * Must be called under a lock that serializes taking new references
 * to i_dio_count, usually by inode->i_mutex.
 */
void inode_dio_wait(struct inode *inode)
{
	if (atomic_read(&inode->i_dio_count))
		__inode_dio_wait(inode);
}
EXPORT_SYMBOL(inode_dio_wait);

/*
 * inode_dio_done - signal finish of a direct I/O requests
 * @inode: inode the direct I/O happens on
 *
 * This is called once we've finished processing a direct I/O request,
 * and is used to wake up callers waiting for direct I/O to be quiesced.
 */
void inode_dio_done(struct inode *inode)
{
	if (atomic_dec_and_test(&inode->i_dio_count))
		wake_up_bit(&inode->i_state, __I_DIO_WAKEUP);
}
EXPORT_SYMBOL(inode_dio_done);

/*
 * inode_set_flags - atomically set some inode flags
 *
 * Note: the caller should be holding i_mutex, or else be sure that
 * they have exclusive access to the inode structure (i.e., while the
 * inode is being instantiated).  The reason for the cmpxchg() loop
 * --- which wouldn't be necessary if all code paths which modify
 * i_flags actually followed this rule, is that there is at least one
 * code path which doesn't today --- for example,
 * __generic_file_aio_write() calls file_remove_suid() without holding
 * i_mutex --- so we use cmpxchg() out of an abundance of caution.
 *
 * In the long run, i_mutex is overkill, and we should probably look
 * at using the i_lock spinlock to protect i_flags, and then make sure
 * it is so documented in include/linux/fs.h and that all code follows
 * the locking convention!!
 */
void inode_set_flags(struct inode *inode, unsigned int flags,
		     unsigned int mask)
{
	unsigned int old_flags, new_flags;

	WARN_ON_ONCE(flags & ~mask);
	do {
		old_flags = ACCESS_ONCE(inode->i_flags);
		new_flags = (old_flags & ~mask) | flags;
	} while (unlikely(cmpxchg(&inode->i_flags, old_flags,
				  new_flags) != old_flags));
}
EXPORT_SYMBOL(inode_set_flags);
OpenPOWER on IntegriCloud