summaryrefslogtreecommitdiff
path: root/fs/gfs2/inode.c
blob: a7d611b93f0fca912ce716736df2524cad7b40be (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
/*
 * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
 * Copyright (C) 2004-2011 Red Hat, Inc.  All rights reserved.
 *
 * This copyrighted material is made available to anyone wishing to use,
 * modify, copy, or redistribute it subject to the terms and conditions
 * of the GNU General Public License version 2.
 */

#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/namei.h>
#include <linux/mm.h>
#include <linux/xattr.h>
#include <linux/posix_acl.h>
#include <linux/gfs2_ondisk.h>
#include <linux/crc32.h>
#include <linux/fiemap.h>
#include <linux/security.h>
#include <asm/uaccess.h>

#include "gfs2.h"
#include "incore.h"
#include "acl.h"
#include "bmap.h"
#include "dir.h"
#include "xattr.h"
#include "glock.h"
#include "inode.h"
#include "meta_io.h"
#include "quota.h"
#include "rgrp.h"
#include "trans.h"
#include "util.h"
#include "super.h"
#include "glops.h"

struct gfs2_skip_data {
	u64 no_addr;
	int skipped;
	int non_block;
};

static int iget_test(struct inode *inode, void *opaque)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_skip_data *data = opaque;

	if (ip->i_no_addr == data->no_addr) {
		if (data->non_block &&
		    inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE)) {
			data->skipped = 1;
			return 0;
		}
		return 1;
	}
	return 0;
}

static int iget_set(struct inode *inode, void *opaque)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_skip_data *data = opaque;

	if (data->skipped)
		return -ENOENT;
	inode->i_ino = (unsigned long)(data->no_addr);
	ip->i_no_addr = data->no_addr;
	return 0;
}

struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr, int non_block)
{
	unsigned long hash = (unsigned long)no_addr;
	struct gfs2_skip_data data;

	data.no_addr = no_addr;
	data.skipped = 0;
	data.non_block = non_block;
	return ilookup5(sb, hash, iget_test, &data);
}

static struct inode *gfs2_iget(struct super_block *sb, u64 no_addr,
			       int non_block)
{
	struct gfs2_skip_data data;
	unsigned long hash = (unsigned long)no_addr;

	data.no_addr = no_addr;
	data.skipped = 0;
	data.non_block = non_block;
	return iget5_locked(sb, hash, iget_test, iget_set, &data);
}

/**
 * gfs2_set_iop - Sets inode operations
 * @inode: The inode with correct i_mode filled in
 *
 * GFS2 lookup code fills in vfs inode contents based on info obtained
 * from directory entry inside gfs2_inode_lookup().
 */

static void gfs2_set_iop(struct inode *inode)
{
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	umode_t mode = inode->i_mode;

	if (S_ISREG(mode)) {
		inode->i_op = &gfs2_file_iops;
		if (gfs2_localflocks(sdp))
			inode->i_fop = &gfs2_file_fops_nolock;
		else
			inode->i_fop = &gfs2_file_fops;
	} else if (S_ISDIR(mode)) {
		inode->i_op = &gfs2_dir_iops;
		if (gfs2_localflocks(sdp))
			inode->i_fop = &gfs2_dir_fops_nolock;
		else
			inode->i_fop = &gfs2_dir_fops;
	} else if (S_ISLNK(mode)) {
		inode->i_op = &gfs2_symlink_iops;
	} else {
		inode->i_op = &gfs2_file_iops;
		init_special_inode(inode, inode->i_mode, inode->i_rdev);
	}
}

/**
 * gfs2_inode_lookup - Lookup an inode
 * @sb: The super block
 * @no_addr: The inode number
 * @type: The type of the inode
 * non_block: Can we block on inodes that are being freed?
 *
 * Returns: A VFS inode, or an error
 */

struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
				u64 no_addr, u64 no_formal_ino, int non_block)
{
	struct inode *inode;
	struct gfs2_inode *ip;
	struct gfs2_glock *io_gl = NULL;
	int error;

	inode = gfs2_iget(sb, no_addr, non_block);
	ip = GFS2_I(inode);

	if (!inode)
		return ERR_PTR(-ENOBUFS);

	if (inode->i_state & I_NEW) {
		struct gfs2_sbd *sdp = GFS2_SB(inode);
		ip->i_no_formal_ino = no_formal_ino;

		error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl);
		if (unlikely(error))
			goto fail;
		ip->i_gl->gl_object = ip;

		error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
		if (unlikely(error))
			goto fail_put;

		set_bit(GIF_INVALID, &ip->i_flags);
		error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
		if (unlikely(error))
			goto fail_iopen;

		ip->i_iopen_gh.gh_gl->gl_object = ip;
		gfs2_glock_put(io_gl);
		io_gl = NULL;

		if (type == DT_UNKNOWN) {
			/* Inode glock must be locked already */
			error = gfs2_inode_refresh(GFS2_I(inode));
			if (error)
				goto fail_refresh;
		} else {
			inode->i_mode = DT2IF(type);
		}

		gfs2_set_iop(inode);
		unlock_new_inode(inode);
	}

	return inode;

fail_refresh:
	ip->i_iopen_gh.gh_gl->gl_object = NULL;
	gfs2_glock_dq_uninit(&ip->i_iopen_gh);
fail_iopen:
	if (io_gl)
		gfs2_glock_put(io_gl);
fail_put:
	ip->i_gl->gl_object = NULL;
	gfs2_glock_put(ip->i_gl);
fail:
	iget_failed(inode);
	return ERR_PTR(error);
}

struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr,
				  u64 *no_formal_ino, unsigned int blktype)
{
	struct super_block *sb = sdp->sd_vfs;
	struct gfs2_holder i_gh;
	struct inode *inode = NULL;
	int error;

	/* Must not read in block until block type is verified */
	error = gfs2_glock_nq_num(sdp, no_addr, &gfs2_inode_glops,
				  LM_ST_EXCLUSIVE, GL_SKIP, &i_gh);
	if (error)
		return ERR_PTR(error);

	error = gfs2_check_blk_type(sdp, no_addr, blktype);
	if (error)
		goto fail;

	inode = gfs2_inode_lookup(sb, DT_UNKNOWN, no_addr, 0, 1);
	if (IS_ERR(inode))
		goto fail;

	/* Two extra checks for NFS only */
	if (no_formal_ino) {
		error = -ESTALE;
		if (GFS2_I(inode)->i_no_formal_ino != *no_formal_ino)
			goto fail_iput;

		error = -EIO;
		if (GFS2_I(inode)->i_diskflags & GFS2_DIF_SYSTEM)
			goto fail_iput;

		error = 0;
	}

fail:
	gfs2_glock_dq_uninit(&i_gh);
	return error ? ERR_PTR(error) : inode;
fail_iput:
	iput(inode);
	goto fail;
}


struct inode *gfs2_lookup_simple(struct inode *dip, const char *name)
{
	struct qstr qstr;
	struct inode *inode;
	gfs2_str2qstr(&qstr, name);
	inode = gfs2_lookupi(dip, &qstr, 1);
	/* gfs2_lookupi has inconsistent callers: vfs
	 * related routines expect NULL for no entry found,
	 * gfs2_lookup_simple callers expect ENOENT
	 * and do not check for NULL.
	 */
	if (inode == NULL)
		return ERR_PTR(-ENOENT);
	else
		return inode;
}


/**
 * gfs2_lookupi - Look up a filename in a directory and return its inode
 * @d_gh: An initialized holder for the directory glock
 * @name: The name of the inode to look for
 * @is_root: If 1, ignore the caller's permissions
 * @i_gh: An uninitialized holder for the new inode glock
 *
 * This can be called via the VFS filldir function when NFS is doing
 * a readdirplus and the inode which its intending to stat isn't
 * already in cache. In this case we must not take the directory glock
 * again, since the readdir call will have already taken that lock.
 *
 * Returns: errno
 */

struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
			   int is_root)
{
	struct super_block *sb = dir->i_sb;
	struct gfs2_inode *dip = GFS2_I(dir);
	struct gfs2_holder d_gh;
	int error = 0;
	struct inode *inode = NULL;
	int unlock = 0;

	if (!name->len || name->len > GFS2_FNAMESIZE)
		return ERR_PTR(-ENAMETOOLONG);

	if ((name->len == 1 && memcmp(name->name, ".", 1) == 0) ||
	    (name->len == 2 && memcmp(name->name, "..", 2) == 0 &&
	     dir == sb->s_root->d_inode)) {
		igrab(dir);
		return dir;
	}

	if (gfs2_glock_is_locked_by_me(dip->i_gl) == NULL) {
		error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
		if (error)
			return ERR_PTR(error);
		unlock = 1;
	}

	if (!is_root) {
		error = gfs2_permission(dir, MAY_EXEC);
		if (error)
			goto out;
	}

	inode = gfs2_dir_search(dir, name);
	if (IS_ERR(inode))
		error = PTR_ERR(inode);
out:
	if (unlock)
		gfs2_glock_dq_uninit(&d_gh);
	if (error == -ENOENT)
		return NULL;
	return inode ? inode : ERR_PTR(error);
}

/**
 * create_ok - OK to create a new on-disk inode here?
 * @dip:  Directory in which dinode is to be created
 * @name:  Name of new dinode
 * @mode:
 *
 * Returns: errno
 */

static int create_ok(struct gfs2_inode *dip, const struct qstr *name,
		     umode_t mode)
{
	int error;

	error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC);
	if (error)
		return error;

	/*  Don't create entries in an unlinked directory  */
	if (!dip->i_inode.i_nlink)
		return -ENOENT;

	error = gfs2_dir_check(&dip->i_inode, name, NULL);
	switch (error) {
	case -ENOENT:
		error = 0;
		break;
	case 0:
		return -EEXIST;
	default:
		return error;
	}

	if (dip->i_entries == (u32)-1)
		return -EFBIG;
	if (S_ISDIR(mode) && dip->i_inode.i_nlink == (u32)-1)
		return -EMLINK;

	return 0;
}

static void munge_mode_uid_gid(struct gfs2_inode *dip, umode_t *mode,
			       unsigned int *uid, unsigned int *gid)
{
	if (GFS2_SB(&dip->i_inode)->sd_args.ar_suiddir &&
	    (dip->i_inode.i_mode & S_ISUID) && dip->i_inode.i_uid) {
		if (S_ISDIR(*mode))
			*mode |= S_ISUID;
		else if (dip->i_inode.i_uid != current_fsuid())
			*mode &= ~07111;
		*uid = dip->i_inode.i_uid;
	} else
		*uid = current_fsuid();

	if (dip->i_inode.i_mode & S_ISGID) {
		if (S_ISDIR(*mode))
			*mode |= S_ISGID;
		*gid = dip->i_inode.i_gid;
	} else
		*gid = current_fsgid();
}

static int alloc_dinode(struct gfs2_inode *dip, u64 *no_addr, u64 *generation)
{
	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
	int error;
	int dblocks = 1;

	error = gfs2_rindex_update(sdp);
	if (error)
		fs_warn(sdp, "rindex update returns %d\n", error);

	error = gfs2_inplace_reserve(dip, RES_DINODE);
	if (error)
		goto out;

	error = gfs2_trans_begin(sdp, RES_RG_BIT + RES_STATFS, 0);
	if (error)
		goto out_ipreserv;

	error = gfs2_alloc_blocks(dip, no_addr, &dblocks, 1, generation);

	gfs2_trans_end(sdp);

out_ipreserv:
	gfs2_inplace_release(dip);
out:
	return error;
}

static void gfs2_init_dir(struct buffer_head *dibh,
			  const struct gfs2_inode *parent)
{
	struct gfs2_dinode *di = (struct gfs2_dinode *)dibh->b_data;
	struct gfs2_dirent *dent = (struct gfs2_dirent *)(di+1);

	gfs2_qstr2dirent(&gfs2_qdot, GFS2_DIRENT_SIZE(gfs2_qdot.len), dent);
	dent->de_inum = di->di_num; /* already GFS2 endian */
	dent->de_type = cpu_to_be16(DT_DIR);

	dent = (struct gfs2_dirent *)((char*)dent + GFS2_DIRENT_SIZE(1));
	gfs2_qstr2dirent(&gfs2_qdotdot, dibh->b_size - GFS2_DIRENT_SIZE(1) - sizeof(struct gfs2_dinode), dent);
	gfs2_inum_out(parent, dent);
	dent->de_type = cpu_to_be16(DT_DIR);
	
}

/**
 * init_dinode - Fill in a new dinode structure
 * @dip: The directory this inode is being created in
 * @gl: The glock covering the new inode
 * @inum: The inode number
 * @mode: The file permissions
 * @uid: The uid of the new inode
 * @gid: The gid of the new inode
 * @generation: The generation number of the new inode
 * @dev: The device number (if a device node)
 * @symname: The symlink destination (if a symlink)
 * @size: The inode size (ignored for directories)
 * @bhp: The buffer head (returned to caller)
 *
 */

static void init_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
			const struct gfs2_inum_host *inum, umode_t mode,
			unsigned int uid, unsigned int gid,
			const u64 *generation, dev_t dev, const char *symname,
			unsigned size, struct buffer_head **bhp)
{
	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
	struct gfs2_dinode *di;
	struct buffer_head *dibh;
	struct timespec tv = CURRENT_TIME;

	dibh = gfs2_meta_new(gl, inum->no_addr);
	gfs2_trans_add_bh(gl, dibh, 1);
	gfs2_metatype_set(dibh, GFS2_METATYPE_DI, GFS2_FORMAT_DI);
	gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
	di = (struct gfs2_dinode *)dibh->b_data;

	di->di_num.no_formal_ino = cpu_to_be64(inum->no_formal_ino);
	di->di_num.no_addr = cpu_to_be64(inum->no_addr);
	di->di_mode = cpu_to_be32(mode);
	di->di_uid = cpu_to_be32(uid);
	di->di_gid = cpu_to_be32(gid);
	di->di_nlink = 0;
	di->di_size = cpu_to_be64(size);
	di->di_blocks = cpu_to_be64(1);
	di->di_atime = di->di_mtime = di->di_ctime = cpu_to_be64(tv.tv_sec);
	di->di_major = cpu_to_be32(MAJOR(dev));
	di->di_minor = cpu_to_be32(MINOR(dev));
	di->di_goal_meta = di->di_goal_data = cpu_to_be64(inum->no_addr);
	di->di_generation = cpu_to_be64(*generation);
	di->di_flags = 0;
	di->__pad1 = 0;
	di->di_payload_format = cpu_to_be32(S_ISDIR(mode) ? GFS2_FORMAT_DE : 0);
	di->di_height = 0;
	di->__pad2 = 0;
	di->__pad3 = 0;
	di->di_depth = 0;
	di->di_entries = 0;
	memset(&di->__pad4, 0, sizeof(di->__pad4));
	di->di_eattr = 0;
	di->di_atime_nsec = cpu_to_be32(tv.tv_nsec);
	di->di_mtime_nsec = cpu_to_be32(tv.tv_nsec);
	di->di_ctime_nsec = cpu_to_be32(tv.tv_nsec);
	memset(&di->di_reserved, 0, sizeof(di->di_reserved));

	switch(mode & S_IFMT) {	
	case S_IFREG:
		if ((dip->i_diskflags & GFS2_DIF_INHERIT_JDATA) ||
		    gfs2_tune_get(sdp, gt_new_files_jdata))
			di->di_flags |= cpu_to_be32(GFS2_DIF_JDATA);
		break;
	case S_IFDIR:
		di->di_flags |= cpu_to_be32(dip->i_diskflags &
					    GFS2_DIF_INHERIT_JDATA);
		di->di_flags |= cpu_to_be32(GFS2_DIF_JDATA);
		di->di_size = cpu_to_be64(sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode));
		di->di_entries = cpu_to_be32(2);
		gfs2_init_dir(dibh, dip);
		break;
	case S_IFLNK:
		memcpy(dibh->b_data + sizeof(struct gfs2_dinode), symname, size);
		break;
	}

	set_buffer_uptodate(dibh);

	*bhp = dibh;
}

static int make_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
		       umode_t mode, const struct gfs2_inum_host *inum,
		       const u64 *generation, dev_t dev, const char *symname,
		       unsigned int size, struct buffer_head **bhp)
{
	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
	unsigned int uid, gid;
	int error;

	munge_mode_uid_gid(dip, &mode, &uid, &gid);
	if (!gfs2_qadata_get(dip))
		return -ENOMEM;

	error = gfs2_quota_lock(dip, uid, gid);
	if (error)
		goto out;

	error = gfs2_quota_check(dip, uid, gid);
	if (error)
		goto out_quota;

	error = gfs2_trans_begin(sdp, RES_DINODE + RES_QUOTA, 0);
	if (error)
		goto out_quota;

	init_dinode(dip, gl, inum, mode, uid, gid, generation, dev, symname, size, bhp);
	gfs2_quota_change(dip, +1, uid, gid);
	gfs2_trans_end(sdp);

out_quota:
	gfs2_quota_unlock(dip);
out:
	gfs2_qadata_put(dip);
	return error;
}

static int link_dinode(struct gfs2_inode *dip, const struct qstr *name,
		       struct gfs2_inode *ip)
{
	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
	struct gfs2_qadata *qa;
	int alloc_required;
	struct buffer_head *dibh;
	int error;

	qa = gfs2_qadata_get(dip);
	if (!qa)
		return -ENOMEM;

	error = gfs2_quota_lock(dip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
	if (error)
		goto fail;

	error = alloc_required = gfs2_diradd_alloc_required(&dip->i_inode, name);
	if (alloc_required < 0)
		goto fail_quota_locks;
	if (alloc_required) {
		error = gfs2_quota_check(dip, dip->i_inode.i_uid, dip->i_inode.i_gid);
		if (error)
			goto fail_quota_locks;

		error = gfs2_inplace_reserve(dip, sdp->sd_max_dirres);
		if (error)
			goto fail_quota_locks;

		error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
					 dip->i_rgd->rd_length +
					 2 * RES_DINODE +
					 RES_STATFS + RES_QUOTA, 0);
		if (error)
			goto fail_ipreserv;
	} else {
		error = gfs2_trans_begin(sdp, RES_LEAF + 2 * RES_DINODE, 0);
		if (error)
			goto fail_quota_locks;
	}

	error = gfs2_dir_add(&dip->i_inode, name, ip);
	if (error)
		goto fail_end_trans;

	error = gfs2_meta_inode_buffer(ip, &dibh);
	if (error)
		goto fail_end_trans;
	set_nlink(&ip->i_inode, S_ISDIR(ip->i_inode.i_mode) ? 2 : 1);
	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
	gfs2_dinode_out(ip, dibh->b_data);
	brelse(dibh);
	return 0;

fail_end_trans:
	gfs2_trans_end(sdp);

fail_ipreserv:
	gfs2_inplace_release(dip);

fail_quota_locks:
	gfs2_quota_unlock(dip);

fail:
	gfs2_qadata_put(dip);
	return error;
}

static int gfs2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
		    void *fs_info)
{
	const struct xattr *xattr;
	int err = 0;

	for (xattr = xattr_array; xattr->name != NULL; xattr++) {
		err = __gfs2_xattr_set(inode, xattr->name, xattr->value,
				       xattr->value_len, 0,
				       GFS2_EATYPE_SECURITY);
		if (err < 0)
			break;
	}
	return err;
}

static int gfs2_security_init(struct gfs2_inode *dip, struct gfs2_inode *ip,
			      const struct qstr *qstr)
{
	return security_inode_init_security(&ip->i_inode, &dip->i_inode, qstr,
					    &gfs2_initxattrs, NULL);
}

/**
 * gfs2_create_inode - Create a new inode
 * @dir: The parent directory
 * @dentry: The new dentry
 * @mode: The permissions on the new inode
 * @dev: For device nodes, this is the device number
 * @symname: For symlinks, this is the link destination
 * @size: The initial size of the inode (ignored for directories)
 *
 * Returns: 0 on success, or error code
 */

static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
			     umode_t mode, dev_t dev, const char *symname,
			     unsigned int size, int excl)
{
	const struct qstr *name = &dentry->d_name;
	struct gfs2_holder ghs[2];
	struct inode *inode = NULL;
	struct gfs2_inode *dip = GFS2_I(dir);
	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
	struct gfs2_inum_host inum = { .no_addr = 0, .no_formal_ino = 0 };
	int error;
	u64 generation;
	struct buffer_head *bh = NULL;

	if (!name->len || name->len > GFS2_FNAMESIZE)
		return -ENAMETOOLONG;

	error = gfs2_glock_nq_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
	if (error)
		goto fail;

	error = create_ok(dip, name, mode);
	if ((error == -EEXIST) && S_ISREG(mode) && !excl) {
		inode = gfs2_lookupi(dir, &dentry->d_name, 0);
		gfs2_glock_dq_uninit(ghs);
		d_instantiate(dentry, inode);
		return IS_ERR(inode) ? PTR_ERR(inode) : 0;
	}
	if (error)
		goto fail_gunlock;

	error = alloc_dinode(dip, &inum.no_addr, &generation);
	if (error)
		goto fail_gunlock;
	inum.no_formal_ino = generation;

	error = gfs2_glock_nq_num(sdp, inum.no_addr, &gfs2_inode_glops,
				  LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1);
	if (error)
		goto fail_gunlock;

	error = make_dinode(dip, ghs[1].gh_gl, mode, &inum, &generation, dev, symname, size, &bh);
	if (error)
		goto fail_gunlock2;

	inode = gfs2_inode_lookup(dir->i_sb, IF2DT(mode), inum.no_addr,
				  inum.no_formal_ino, 0);
	if (IS_ERR(inode))
		goto fail_gunlock2;

	error = gfs2_inode_refresh(GFS2_I(inode));
	if (error)
		goto fail_gunlock2;

	error = gfs2_acl_create(dip, inode);
	if (error)
		goto fail_gunlock2;

	error = gfs2_security_init(dip, GFS2_I(inode), name);
	if (error)
		goto fail_gunlock2;

	error = link_dinode(dip, name, GFS2_I(inode));
	if (error)
		goto fail_gunlock2;

	if (bh)
		brelse(bh);

	gfs2_trans_end(sdp);
	/* Check if we reserved space in the rgrp. Function link_dinode may
	   not, depending on whether alloc is required. */
	if (dip->i_res)
		gfs2_inplace_release(dip);
	gfs2_quota_unlock(dip);
	gfs2_qadata_put(dip);
	mark_inode_dirty(inode);
	gfs2_glock_dq_uninit_m(2, ghs);
	d_instantiate(dentry, inode);
	return 0;

fail_gunlock2:
	gfs2_glock_dq_uninit(ghs + 1);
fail_gunlock:
	gfs2_glock_dq_uninit(ghs);
	if (inode && !IS_ERR(inode)) {
		set_bit(GIF_ALLOC_FAILED, &GFS2_I(inode)->i_flags);
		iput(inode);
	}
fail:
	if (bh)
		brelse(bh);
	return error;
}

/**
 * gfs2_create - Create a file
 * @dir: The directory in which to create the file
 * @dentry: The dentry of the new file
 * @mode: The mode of the new file
 *
 * Returns: errno
 */

static int gfs2_create(struct inode *dir, struct dentry *dentry,
		       umode_t mode, struct nameidata *nd)
{
	int excl = 0;
	if (nd && (nd->flags & LOOKUP_EXCL))
		excl = 1;
	return gfs2_create_inode(dir, dentry, S_IFREG | mode, 0, NULL, 0, excl);
}

/**
 * gfs2_lookup - Look up a filename in a directory and return its inode
 * @dir: The directory inode
 * @dentry: The dentry of the new inode
 * @nd: passed from Linux VFS, ignored by us
 *
 * Called by the VFS layer. Lock dir and call gfs2_lookupi()
 *
 * Returns: errno
 */

static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry,
				  struct nameidata *nd)
{
	struct inode *inode = gfs2_lookupi(dir, &dentry->d_name, 0);
	if (inode && !IS_ERR(inode)) {
		struct gfs2_glock *gl = GFS2_I(inode)->i_gl;
		struct gfs2_holder gh;
		int error;
		error = gfs2_glock_nq_init(gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
		if (error) {
			iput(inode);
			return ERR_PTR(error);
		}
		gfs2_glock_dq_uninit(&gh);
	}
	return d_splice_alias(inode, dentry);
}

/**
 * gfs2_link - Link to a file
 * @old_dentry: The inode to link
 * @dir: Add link to this directory
 * @dentry: The name of the link
 *
 * Link the inode in "old_dentry" into the directory "dir" with the
 * name in "dentry".
 *
 * Returns: errno
 */

static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
		     struct dentry *dentry)
{
	struct gfs2_inode *dip = GFS2_I(dir);
	struct gfs2_sbd *sdp = GFS2_SB(dir);
	struct inode *inode = old_dentry->d_inode;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_holder ghs[2];
	struct buffer_head *dibh;
	int alloc_required;
	int error;

	if (S_ISDIR(inode->i_mode))
		return -EPERM;

	gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + 1);

	error = gfs2_glock_nq(ghs); /* parent */
	if (error)
		goto out_parent;

	error = gfs2_glock_nq(ghs + 1); /* child */
	if (error)
		goto out_child;

	error = -ENOENT;
	if (inode->i_nlink == 0)
		goto out_gunlock;

	error = gfs2_permission(dir, MAY_WRITE | MAY_EXEC);
	if (error)
		goto out_gunlock;

	error = gfs2_dir_check(dir, &dentry->d_name, NULL);
	switch (error) {
	case -ENOENT:
		break;
	case 0:
		error = -EEXIST;
	default:
		goto out_gunlock;
	}

	error = -EINVAL;
	if (!dip->i_inode.i_nlink)
		goto out_gunlock;
	error = -EFBIG;
	if (dip->i_entries == (u32)-1)
		goto out_gunlock;
	error = -EPERM;
	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
		goto out_gunlock;
	error = -EINVAL;
	if (!ip->i_inode.i_nlink)
		goto out_gunlock;
	error = -EMLINK;
	if (ip->i_inode.i_nlink == (u32)-1)
		goto out_gunlock;

	alloc_required = error = gfs2_diradd_alloc_required(dir, &dentry->d_name);
	if (error < 0)
		goto out_gunlock;
	error = 0;

	if (alloc_required) {
		struct gfs2_qadata *qa = gfs2_qadata_get(dip);

		if (!qa) {
			error = -ENOMEM;
			goto out_gunlock;
		}

		error = gfs2_quota_lock_check(dip);
		if (error)
			goto out_alloc;

		error = gfs2_inplace_reserve(dip, sdp->sd_max_dirres);
		if (error)
			goto out_gunlock_q;

		error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
					 gfs2_rg_blocks(dip) +
					 2 * RES_DINODE + RES_STATFS +
					 RES_QUOTA, 0);
		if (error)
			goto out_ipres;
	} else {
		error = gfs2_trans_begin(sdp, 2 * RES_DINODE + RES_LEAF, 0);
		if (error)
			goto out_ipres;
	}

	error = gfs2_meta_inode_buffer(ip, &dibh);
	if (error)
		goto out_end_trans;

	error = gfs2_dir_add(dir, &dentry->d_name, ip);
	if (error)
		goto out_brelse;

	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
	inc_nlink(&ip->i_inode);
	ip->i_inode.i_ctime = CURRENT_TIME;
	ihold(inode);
	d_instantiate(dentry, inode);
	mark_inode_dirty(inode);

out_brelse:
	brelse(dibh);
out_end_trans:
	gfs2_trans_end(sdp);
out_ipres:
	if (alloc_required)
		gfs2_inplace_release(dip);
out_gunlock_q:
	if (alloc_required)
		gfs2_quota_unlock(dip);
out_alloc:
	if (alloc_required)
		gfs2_qadata_put(dip);
out_gunlock:
	gfs2_glock_dq(ghs + 1);
out_child:
	gfs2_glock_dq(ghs);
out_parent:
	gfs2_holder_uninit(ghs);
	gfs2_holder_uninit(ghs + 1);
	return error;
}

/*
 * gfs2_unlink_ok - check to see that a inode is still in a directory
 * @dip: the directory
 * @name: the name of the file
 * @ip: the inode
 *
 * Assumes that the lock on (at least) @dip is held.
 *
 * Returns: 0 if the parent/child relationship is correct, errno if it isn't
 */

static int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
			  const struct gfs2_inode *ip)
{
	int error;

	if (IS_IMMUTABLE(&ip->i_inode) || IS_APPEND(&ip->i_inode))
		return -EPERM;

	if ((dip->i_inode.i_mode & S_ISVTX) &&
	    dip->i_inode.i_uid != current_fsuid() &&
	    ip->i_inode.i_uid != current_fsuid() && !capable(CAP_FOWNER))
		return -EPERM;

	if (IS_APPEND(&dip->i_inode))
		return -EPERM;

	error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC);
	if (error)
		return error;

	error = gfs2_dir_check(&dip->i_inode, name, ip);
	if (error)
		return error;

	return 0;
}

/**
 * gfs2_unlink_inode - Removes an inode from its parent dir and unlinks it
 * @dip: The parent directory
 * @name: The name of the entry in the parent directory
 * @bh: The inode buffer for the inode to be removed
 * @inode: The inode to be removed
 *
 * Called with all the locks and in a transaction. This will only be
 * called for a directory after it has been checked to ensure it is empty.
 *
 * Returns: 0 on success, or an error
 */

static int gfs2_unlink_inode(struct gfs2_inode *dip,
			     const struct dentry *dentry,
			     struct buffer_head *bh)
{
	struct inode *inode = dentry->d_inode;
	struct gfs2_inode *ip = GFS2_I(inode);
	int error;

	error = gfs2_dir_del(dip, dentry);
	if (error)
		return error;

	ip->i_entries = 0;
	inode->i_ctime = CURRENT_TIME;
	if (S_ISDIR(inode->i_mode))
		clear_nlink(inode);
	else
		drop_nlink(inode);
	mark_inode_dirty(inode);
	if (inode->i_nlink == 0)
		gfs2_unlink_di(inode);
	return 0;
}


/**
 * gfs2_unlink - Unlink an inode (this does rmdir as well)
 * @dir: The inode of the directory containing the inode to unlink
 * @dentry: The file itself
 *
 * This routine uses the type of the inode as a flag to figure out
 * whether this is an unlink or an rmdir.
 *
 * Returns: errno
 */

static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
{
	struct gfs2_inode *dip = GFS2_I(dir);
	struct gfs2_sbd *sdp = GFS2_SB(dir);
	struct inode *inode = dentry->d_inode;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct buffer_head *bh;
	struct gfs2_holder ghs[3];
	struct gfs2_rgrpd *rgd;
	int error = -EROFS;

	gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
	gfs2_holder_init(ip->i_gl,  LM_ST_EXCLUSIVE, 0, ghs + 1);

	rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr);
	if (!rgd)
		goto out_inodes;
	gfs2_holder_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + 2);


	error = gfs2_glock_nq(ghs); /* parent */
	if (error)
		goto out_parent;

	error = gfs2_glock_nq(ghs + 1); /* child */
	if (error)
		goto out_child;

	error = -ENOENT;
	if (inode->i_nlink == 0)
		goto out_rgrp;

	if (S_ISDIR(inode->i_mode)) {
		error = -ENOTEMPTY;
		if (ip->i_entries > 2 || inode->i_nlink > 2)
			goto out_rgrp;
	}

	error = gfs2_glock_nq(ghs + 2); /* rgrp */
	if (error)
		goto out_rgrp;

	error = gfs2_unlink_ok(dip, &dentry->d_name, ip);
	if (error)
		goto out_gunlock;

	error = gfs2_trans_begin(sdp, 2*RES_DINODE + 3*RES_LEAF + RES_RG_BIT, 0);
	if (error)
		goto out_gunlock;

	error = gfs2_meta_inode_buffer(ip, &bh);
	if (error)
		goto out_end_trans;

	error = gfs2_unlink_inode(dip, dentry, bh);
	brelse(bh);

out_end_trans:
	gfs2_trans_end(sdp);
out_gunlock:
	gfs2_glock_dq(ghs + 2);
out_rgrp:
	gfs2_glock_dq(ghs + 1);
out_child:
	gfs2_glock_dq(ghs);
out_parent:
	gfs2_holder_uninit(ghs + 2);
out_inodes:
	gfs2_holder_uninit(ghs + 1);
	gfs2_holder_uninit(ghs);
	return error;
}

/**
 * gfs2_symlink - Create a symlink
 * @dir: The directory to create the symlink in
 * @dentry: The dentry to put the symlink in
 * @symname: The thing which the link points to
 *
 * Returns: errno
 */

static int gfs2_symlink(struct inode *dir, struct dentry *dentry,
			const char *symname)
{
	struct gfs2_sbd *sdp = GFS2_SB(dir);
	unsigned int size;

	size = strlen(symname);
	if (size > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode) - 1)
		return -ENAMETOOLONG;

	return gfs2_create_inode(dir, dentry, S_IFLNK | S_IRWXUGO, 0, symname, size, 0);
}

/**
 * gfs2_mkdir - Make a directory
 * @dir: The parent directory of the new one
 * @dentry: The dentry of the new directory
 * @mode: The mode of the new directory
 *
 * Returns: errno
 */

static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
	return gfs2_create_inode(dir, dentry, S_IFDIR | mode, 0, NULL, 0, 0);
}

/**
 * gfs2_mknod - Make a special file
 * @dir: The directory in which the special file will reside
 * @dentry: The dentry of the special file
 * @mode: The mode of the special file
 * @dev: The device specification of the special file
 *
 */

static int gfs2_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
		      dev_t dev)
{
	return gfs2_create_inode(dir, dentry, mode, dev, NULL, 0, 0);
}

/*
 * gfs2_ok_to_move - check if it's ok to move a directory to another directory
 * @this: move this
 * @to: to here
 *
 * Follow @to back to the root and make sure we don't encounter @this
 * Assumes we already hold the rename lock.
 *
 * Returns: errno
 */

static int gfs2_ok_to_move(struct gfs2_inode *this, struct gfs2_inode *to)
{
	struct inode *dir = &to->i_inode;
	struct super_block *sb = dir->i_sb;
	struct inode *tmp;
	int error = 0;

	igrab(dir);

	for (;;) {
		if (dir == &this->i_inode) {
			error = -EINVAL;
			break;
		}
		if (dir == sb->s_root->d_inode) {
			error = 0;
			break;
		}

		tmp = gfs2_lookupi(dir, &gfs2_qdotdot, 1);
		if (IS_ERR(tmp)) {
			error = PTR_ERR(tmp);
			break;
		}

		iput(dir);
		dir = tmp;
	}

	iput(dir);

	return error;
}

/**
 * gfs2_rename - Rename a file
 * @odir: Parent directory of old file name
 * @odentry: The old dentry of the file
 * @ndir: Parent directory of new file name
 * @ndentry: The new dentry of the file
 *
 * Returns: errno
 */

static int gfs2_rename(struct inode *odir, struct dentry *odentry,
		       struct inode *ndir, struct dentry *ndentry)
{
	struct gfs2_inode *odip = GFS2_I(odir);
	struct gfs2_inode *ndip = GFS2_I(ndir);
	struct gfs2_inode *ip = GFS2_I(odentry->d_inode);
	struct gfs2_inode *nip = NULL;
	struct gfs2_sbd *sdp = GFS2_SB(odir);
	struct gfs2_holder ghs[5], r_gh = { .gh_gl = NULL, };
	struct gfs2_rgrpd *nrgd;
	unsigned int num_gh;
	int dir_rename = 0;
	int alloc_required = 0;
	unsigned int x;
	int error;

	if (ndentry->d_inode) {
		nip = GFS2_I(ndentry->d_inode);
		if (ip == nip)
			return 0;
	}

	if (odip != ndip) {
		error = gfs2_glock_nq_init(sdp->sd_rename_gl, LM_ST_EXCLUSIVE,
					   0, &r_gh);
		if (error)
			goto out;

		if (S_ISDIR(ip->i_inode.i_mode)) {
			dir_rename = 1;
			/* don't move a dirctory into it's subdir */
			error = gfs2_ok_to_move(ip, ndip);
			if (error)
				goto out_gunlock_r;
		}
	}

	num_gh = 1;
	gfs2_holder_init(odip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
	if (odip != ndip) {
		gfs2_holder_init(ndip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh);
		num_gh++;
	}
	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh);
	num_gh++;

	if (nip) {
		gfs2_holder_init(nip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh);
		num_gh++;
		/* grab the resource lock for unlink flag twiddling 
		 * this is the case of the target file already existing
		 * so we unlink before doing the rename
		 */
		nrgd = gfs2_blk2rgrpd(sdp, nip->i_no_addr);
		if (nrgd)
			gfs2_holder_init(nrgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh++);
	}

	for (x = 0; x < num_gh; x++) {
		error = gfs2_glock_nq(ghs + x);
		if (error)
			goto out_gunlock;
	}

	error = -ENOENT;
	if (ip->i_inode.i_nlink == 0)
		goto out_gunlock;

	/* Check out the old directory */

	error = gfs2_unlink_ok(odip, &odentry->d_name, ip);
	if (error)
		goto out_gunlock;

	/* Check out the new directory */

	if (nip) {
		error = gfs2_unlink_ok(ndip, &ndentry->d_name, nip);
		if (error)
			goto out_gunlock;

		if (nip->i_inode.i_nlink == 0) {
			error = -EAGAIN;
			goto out_gunlock;
		}

		if (S_ISDIR(nip->i_inode.i_mode)) {
			if (nip->i_entries < 2) {
				gfs2_consist_inode(nip);
				error = -EIO;
				goto out_gunlock;
			}
			if (nip->i_entries > 2) {
				error = -ENOTEMPTY;
				goto out_gunlock;
			}
		}
	} else {
		error = gfs2_permission(ndir, MAY_WRITE | MAY_EXEC);
		if (error)
			goto out_gunlock;

		error = gfs2_dir_check(ndir, &ndentry->d_name, NULL);
		switch (error) {
		case -ENOENT:
			error = 0;
			break;
		case 0:
			error = -EEXIST;
		default:
			goto out_gunlock;
		};

		if (odip != ndip) {
			if (!ndip->i_inode.i_nlink) {
				error = -ENOENT;
				goto out_gunlock;
			}
			if (ndip->i_entries == (u32)-1) {
				error = -EFBIG;
				goto out_gunlock;
			}
			if (S_ISDIR(ip->i_inode.i_mode) &&
			    ndip->i_inode.i_nlink == (u32)-1) {
				error = -EMLINK;
				goto out_gunlock;
			}
		}
	}

	/* Check out the dir to be renamed */

	if (dir_rename) {
		error = gfs2_permission(odentry->d_inode, MAY_WRITE);
		if (error)
			goto out_gunlock;
	}

	if (nip == NULL)
		alloc_required = gfs2_diradd_alloc_required(ndir, &ndentry->d_name);
	error = alloc_required;
	if (error < 0)
		goto out_gunlock;
	error = 0;

	if (alloc_required) {
		struct gfs2_qadata *qa = gfs2_qadata_get(ndip);

		if (!qa) {
			error = -ENOMEM;
			goto out_gunlock;
		}

		error = gfs2_quota_lock_check(ndip);
		if (error)
			goto out_alloc;

		error = gfs2_inplace_reserve(ndip, sdp->sd_max_dirres);
		if (error)
			goto out_gunlock_q;

		error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
					 gfs2_rg_blocks(ndip) +
					 4 * RES_DINODE + 4 * RES_LEAF +
					 RES_STATFS + RES_QUOTA + 4, 0);
		if (error)
			goto out_ipreserv;
	} else {
		error = gfs2_trans_begin(sdp, 4 * RES_DINODE +
					 5 * RES_LEAF + 4, 0);
		if (error)
			goto out_gunlock;
	}

	/* Remove the target file, if it exists */

	if (nip) {
		struct buffer_head *bh;
		error = gfs2_meta_inode_buffer(nip, &bh);
		if (error)
			goto out_end_trans;
		error = gfs2_unlink_inode(ndip, ndentry, bh);
		brelse(bh);
	}

	if (dir_rename) {
		error = gfs2_dir_mvino(ip, &gfs2_qdotdot, ndip, DT_DIR);
		if (error)
			goto out_end_trans;
	} else {
		struct buffer_head *dibh;
		error = gfs2_meta_inode_buffer(ip, &dibh);
		if (error)
			goto out_end_trans;
		ip->i_inode.i_ctime = CURRENT_TIME;
		gfs2_trans_add_bh(ip->i_gl, dibh, 1);
		gfs2_dinode_out(ip, dibh->b_data);
		brelse(dibh);
	}

	error = gfs2_dir_del(odip, odentry);
	if (error)
		goto out_end_trans;

	error = gfs2_dir_add(ndir, &ndentry->d_name, ip);
	if (error)
		goto out_end_trans;

out_end_trans:
	gfs2_trans_end(sdp);
out_ipreserv:
	if (alloc_required)
		gfs2_inplace_release(ndip);
out_gunlock_q:
	if (alloc_required)
		gfs2_quota_unlock(ndip);
out_alloc:
	if (alloc_required)
		gfs2_qadata_put(ndip);
out_gunlock:
	while (x--) {
		gfs2_glock_dq(ghs + x);
		gfs2_holder_uninit(ghs + x);
	}
out_gunlock_r:
	if (r_gh.gh_gl)
		gfs2_glock_dq_uninit(&r_gh);
out:
	return error;
}

/**
 * gfs2_follow_link - Follow a symbolic link
 * @dentry: The dentry of the link
 * @nd: Data that we pass to vfs_follow_link()
 *
 * This can handle symlinks of any size.
 *
 * Returns: 0 on success or error code
 */

static void *gfs2_follow_link(struct dentry *dentry, struct nameidata *nd)
{
	struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
	struct gfs2_holder i_gh;
	struct buffer_head *dibh;
	unsigned int size;
	char *buf;
	int error;

	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh);
	error = gfs2_glock_nq(&i_gh);
	if (error) {
		gfs2_holder_uninit(&i_gh);
		nd_set_link(nd, ERR_PTR(error));
		return NULL;
	}

	size = (unsigned int)i_size_read(&ip->i_inode);
	if (size == 0) {
		gfs2_consist_inode(ip);
		buf = ERR_PTR(-EIO);
		goto out;
	}

	error = gfs2_meta_inode_buffer(ip, &dibh);
	if (error) {
		buf = ERR_PTR(error);
		goto out;
	}

	buf = kzalloc(size + 1, GFP_NOFS);
	if (!buf)
		buf = ERR_PTR(-ENOMEM);
	else
		memcpy(buf, dibh->b_data + sizeof(struct gfs2_dinode), size);
	brelse(dibh);
out:
	gfs2_glock_dq_uninit(&i_gh);
	nd_set_link(nd, buf);
	return NULL;
}

static void gfs2_put_link(struct dentry *dentry, struct nameidata *nd, void *p)
{
	char *s = nd_get_link(nd);
	if (!IS_ERR(s))
		kfree(s);
}

/**
 * gfs2_permission -
 * @inode: The inode
 * @mask: The mask to be tested
 * @flags: Indicates whether this is an RCU path walk or not
 *
 * This may be called from the VFS directly, or from within GFS2 with the
 * inode locked, so we look to see if the glock is already locked and only
 * lock the glock if its not already been done.
 *
 * Returns: errno
 */

int gfs2_permission(struct inode *inode, int mask)
{
	struct gfs2_inode *ip;
	struct gfs2_holder i_gh;
	int error;
	int unlock = 0;


	ip = GFS2_I(inode);
	if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) {
		if (mask & MAY_NOT_BLOCK)
			return -ECHILD;
		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
		if (error)
			return error;
		unlock = 1;
	}

	if ((mask & MAY_WRITE) && IS_IMMUTABLE(inode))
		error = -EACCES;
	else
		error = generic_permission(inode, mask);
	if (unlock)
		gfs2_glock_dq_uninit(&i_gh);

	return error;
}

static int __gfs2_setattr_simple(struct inode *inode, struct iattr *attr)
{
	setattr_copy(inode, attr);
	mark_inode_dirty(inode);
	return 0;
}

/**
 * gfs2_setattr_simple -
 * @ip:
 * @attr:
 *
 * Returns: errno
 */

int gfs2_setattr_simple(struct inode *inode, struct iattr *attr)
{
	int error;

	if (current->journal_info)
		return __gfs2_setattr_simple(inode, attr);

	error = gfs2_trans_begin(GFS2_SB(inode), RES_DINODE, 0);
	if (error)
		return error;

	error = __gfs2_setattr_simple(inode, attr);
	gfs2_trans_end(GFS2_SB(inode));
	return error;
}

static int setattr_chown(struct inode *inode, struct iattr *attr)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	u32 ouid, ogid, nuid, ngid;
	int error;

	ouid = inode->i_uid;
	ogid = inode->i_gid;
	nuid = attr->ia_uid;
	ngid = attr->ia_gid;

	if (!(attr->ia_valid & ATTR_UID) || ouid == nuid)
		ouid = nuid = NO_QUOTA_CHANGE;
	if (!(attr->ia_valid & ATTR_GID) || ogid == ngid)
		ogid = ngid = NO_QUOTA_CHANGE;

	if (!gfs2_qadata_get(ip))
		return -ENOMEM;

	error = gfs2_quota_lock(ip, nuid, ngid);
	if (error)
		goto out_alloc;

	if (ouid != NO_QUOTA_CHANGE || ogid != NO_QUOTA_CHANGE) {
		error = gfs2_quota_check(ip, nuid, ngid);
		if (error)
			goto out_gunlock_q;
	}

	error = gfs2_trans_begin(sdp, RES_DINODE + 2 * RES_QUOTA, 0);
	if (error)
		goto out_gunlock_q;

	error = gfs2_setattr_simple(inode, attr);
	if (error)
		goto out_end_trans;

	if (ouid != NO_QUOTA_CHANGE || ogid != NO_QUOTA_CHANGE) {
		u64 blocks = gfs2_get_inode_blocks(&ip->i_inode);
		gfs2_quota_change(ip, -blocks, ouid, ogid);
		gfs2_quota_change(ip, blocks, nuid, ngid);
	}

out_end_trans:
	gfs2_trans_end(sdp);
out_gunlock_q:
	gfs2_quota_unlock(ip);
out_alloc:
	gfs2_qadata_put(ip);
	return error;
}

/**
 * gfs2_setattr - Change attributes on an inode
 * @dentry: The dentry which is changing
 * @attr: The structure describing the change
 *
 * The VFS layer wants to change one or more of an inodes attributes.  Write
 * that change out to disk.
 *
 * Returns: errno
 */

static int gfs2_setattr(struct dentry *dentry, struct iattr *attr)
{
	struct inode *inode = dentry->d_inode;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_holder i_gh;
	int error;

	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh);
	if (error)
		return error;

	error = -EPERM;
	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
		goto out;

	error = inode_change_ok(inode, attr);
	if (error)
		goto out;

	if (attr->ia_valid & ATTR_SIZE)
		error = gfs2_setattr_size(inode, attr->ia_size);
	else if (attr->ia_valid & (ATTR_UID | ATTR_GID))
		error = setattr_chown(inode, attr);
	else if ((attr->ia_valid & ATTR_MODE) && IS_POSIXACL(inode))
		error = gfs2_acl_chmod(ip, attr);
	else
		error = gfs2_setattr_simple(inode, attr);

out:
	if (!error)
		mark_inode_dirty(inode);
	gfs2_glock_dq_uninit(&i_gh);
	return error;
}

/**
 * gfs2_getattr - Read out an inode's attributes
 * @mnt: The vfsmount the inode is being accessed from
 * @dentry: The dentry to stat
 * @stat: The inode's stats
 *
 * This may be called from the VFS directly, or from within GFS2 with the
 * inode locked, so we look to see if the glock is already locked and only
 * lock the glock if its not already been done. Note that its the NFS
 * readdirplus operation which causes this to be called (from filldir)
 * with the glock already held.
 *
 * Returns: errno
 */

static int gfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
			struct kstat *stat)
{
	struct inode *inode = dentry->d_inode;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_holder gh;
	int error;
	int unlock = 0;

	if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) {
		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
		if (error)
			return error;
		unlock = 1;
	}

	generic_fillattr(inode, stat);
	if (unlock)
		gfs2_glock_dq_uninit(&gh);

	return 0;
}

static int gfs2_setxattr(struct dentry *dentry, const char *name,
			 const void *data, size_t size, int flags)
{
	struct inode *inode = dentry->d_inode;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_holder gh;
	int ret;

	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
	ret = gfs2_glock_nq(&gh);
	if (ret == 0) {
		ret = generic_setxattr(dentry, name, data, size, flags);
		gfs2_glock_dq(&gh);
	}
	gfs2_holder_uninit(&gh);
	return ret;
}

static ssize_t gfs2_getxattr(struct dentry *dentry, const char *name,
			     void *data, size_t size)
{
	struct inode *inode = dentry->d_inode;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_holder gh;
	int ret;

	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
	ret = gfs2_glock_nq(&gh);
	if (ret == 0) {
		ret = generic_getxattr(dentry, name, data, size);
		gfs2_glock_dq(&gh);
	}
	gfs2_holder_uninit(&gh);
	return ret;
}

static int gfs2_removexattr(struct dentry *dentry, const char *name)
{
	struct inode *inode = dentry->d_inode;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_holder gh;
	int ret;

	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
	ret = gfs2_glock_nq(&gh);
	if (ret == 0) {
		ret = generic_removexattr(dentry, name);
		gfs2_glock_dq(&gh);
	}
	gfs2_holder_uninit(&gh);
	return ret;
}

static int gfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
		       u64 start, u64 len)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_holder gh;
	int ret;

	ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
	if (ret)
		return ret;

	mutex_lock(&inode->i_mutex);

	ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
	if (ret)
		goto out;

	if (gfs2_is_stuffed(ip)) {
		u64 phys = ip->i_no_addr << inode->i_blkbits;
		u64 size = i_size_read(inode);
		u32 flags = FIEMAP_EXTENT_LAST|FIEMAP_EXTENT_NOT_ALIGNED|
			    FIEMAP_EXTENT_DATA_INLINE;
		phys += sizeof(struct gfs2_dinode);
		phys += start;
		if (start + len > size)
			len = size - start;
		if (start < size)
			ret = fiemap_fill_next_extent(fieinfo, start, phys,
						      len, flags);
		if (ret == 1)
			ret = 0;
	} else {
		ret = __generic_block_fiemap(inode, fieinfo, start, len,
					     gfs2_block_map);
	}

	gfs2_glock_dq_uninit(&gh);
out:
	mutex_unlock(&inode->i_mutex);
	return ret;
}

const struct inode_operations gfs2_file_iops = {
	.permission = gfs2_permission,
	.setattr = gfs2_setattr,
	.getattr = gfs2_getattr,
	.setxattr = gfs2_setxattr,
	.getxattr = gfs2_getxattr,
	.listxattr = gfs2_listxattr,
	.removexattr = gfs2_removexattr,
	.fiemap = gfs2_fiemap,
	.get_acl = gfs2_get_acl,
};

const struct inode_operations gfs2_dir_iops = {
	.create = gfs2_create,
	.lookup = gfs2_lookup,
	.link = gfs2_link,
	.unlink = gfs2_unlink,
	.symlink = gfs2_symlink,
	.mkdir = gfs2_mkdir,
	.rmdir = gfs2_unlink,
	.mknod = gfs2_mknod,
	.rename = gfs2_rename,
	.permission = gfs2_permission,
	.setattr = gfs2_setattr,
	.getattr = gfs2_getattr,
	.setxattr = gfs2_setxattr,
	.getxattr = gfs2_getxattr,
	.listxattr = gfs2_listxattr,
	.removexattr = gfs2_removexattr,
	.fiemap = gfs2_fiemap,
	.get_acl = gfs2_get_acl,
};

const struct inode_operations gfs2_symlink_iops = {
	.readlink = generic_readlink,
	.follow_link = gfs2_follow_link,
	.put_link = gfs2_put_link,
	.permission = gfs2_permission,
	.setattr = gfs2_setattr,
	.getattr = gfs2_getattr,
	.setxattr = gfs2_setxattr,
	.getxattr = gfs2_getxattr,
	.listxattr = gfs2_listxattr,
	.removexattr = gfs2_removexattr,
	.fiemap = gfs2_fiemap,
	.get_acl = gfs2_get_acl,
};