aboutsummaryrefslogtreecommitdiffstats
blob: 7841d71421aab1d4e1d751a12c91540e7e6c347a (plain) (blame)
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
/*
 *  linux/fs/ext2/inode.c
 *
 * Copyright (C) 1992, 1993, 1994, 1995
 * Remy Card (card@masi.ibp.fr)
 * Laboratoire MASI - Institut Blaise Pascal
 * Universite Pierre et Marie Curie (Paris VI)
 *
 *  from
 *
 *  linux/fs/minix/inode.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  Goal-directed block allocation by Stephen Tweedie
 * 	(sct@dcs.ed.ac.uk), 1993, 1998
 *  Big-endian to little-endian byte-swapping/bitmaps by
 *        David S. Miller (davem@caip.rutgers.edu), 1995
 *  64-bit file support on 64-bit platforms by Jakub Jelinek
 * 	(jj@sunsite.ms.mff.cuni.cz)
 *
 *  Assorted race fixes, rewrite of ext2_get_block() by Al Viro, 2000
 */

#include <linux/time.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
#include <linux/dax.h>
#include <linux/quotaops.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h>
#include <linux/mpage.h>
#include <linux/fiemap.h>
#include <linux/namei.h>
#include <linux/uio.h>
#include "ext2.h"
#include "acl.h"
#include "xattr.h"

static int __ext2_write_inode(struct inode *inode, int do_sync);

/*
 * Test whether an inode is a fast symlink.
 */
static inline int ext2_inode_is_fast_symlink(struct inode *inode)
{
	int ea_blocks = EXT2_I(inode)->i_file_acl ?
		(inode->i_sb->s_blocksize >> 9) : 0;

	return (S_ISLNK(inode->i_mode) &&
		inode->i_blocks - ea_blocks == 0);
}

static void ext2_truncate_blocks(struct inode *inode, loff_t offset);

static void ext2_write_failed(struct address_space *mapping, loff_t to)
{
	struct inode *inode = mapping->host;

	if (to > inode->i_size) {
		truncate_pagecache(inode, inode->i_size);
		ext2_truncate_blocks(inode, inode->i_size);
	}
}

/*
 * Called at the last iput() if i_nlink is zero.
 */
void ext2_evict_inode(struct inode * inode)
{
	struct ext2_block_alloc_info *rsv;
	int want_delete = 0;

	if (!inode->i_nlink && !is_bad_inode(inode)) {
		want_delete = 1;
		dquot_initialize(inode);
	} else {
		dquot_drop(inode);
	}

	truncate_inode_pages_final(&inode->i_data);

	if (want_delete) {
		sb_start_intwrite(inode->i_sb);
		/* set dtime */
		EXT2_I(inode)->i_dtime	= get_seconds();
		mark_inode_dirty(inode);
		__ext2_write_inode(inode, inode_needs_sync(inode));
		/* truncate to 0 */
		inode->i_size = 0;
		if (inode->i_blocks)
			ext2_truncate_blocks(inode, 0);
		ext2_xattr_delete_inode(inode);
	}

	invalidate_inode_buffers(inode);
	clear_inode(inode);

	ext2_discard_reservation(inode);
	rsv = EXT2_I(inode)->i_block_alloc_info;
	EXT2_I(inode)->i_block_alloc_info = NULL;
	if (unlikely(rsv))
		kfree(rsv);

	if (want_delete) {
		ext2_free_inode(inode);
		sb_end_intwrite(inode->i_sb);
	}
}

typedef struct {
	__le32	*p;
	__le32	key;
	struct buffer_head *bh;
} Indirect;

static inline void add_chain(Indirect *p, struct buffer_head *bh, __le32 *v)
{
	p->key = *(p->p = v);
	p->bh = bh;
}

static inline int verify_chain(Indirect *from, Indirect *to)
{
	while (from <= to && from->key == *from->p)
		from++;
	return (from > to);
}

/**
 *	ext2_block_to_path - parse the block number into array of offsets
 *	@inode: inode in question (we are only interested in its superblock)
 *	@i_block: block number to be parsed
 *	@offsets: array to store the offsets in
 *      @boundary: set this non-zero if the referred-to block is likely to be
 *             followed (on disk) by an indirect block.
 *	To store the locations of file's data ext2 uses a data structure common
 *	for UNIX filesystems - tree of pointers anchored in the inode, with
 *	data blocks at leaves and indirect blocks in intermediate nodes.
 *	This function translates the block number into path in that tree -
 *	return value is the path length and @offsets[n] is the offset of
 *	pointer to (n+1)th node in the nth one. If @block is out of range
 *	(negative or too large) warning is printed and zero returned.
 *
 *	Note: function doesn't find node addresses, so no IO is needed. All
 *	we need to know is the capacity of indirect blocks (taken from the
 *	inode->i_sb).
 */

/*
 * Portability note: the last comparison (check that we fit into triple
 * indirect block) is spelled differently, because otherwise on an
 * architecture with 32-bit longs and 8Kb pages we might get into trouble
 * if our filesystem had 8Kb blocks. We might use long long, but that would
 * kill us on x86. Oh, well, at least the sign propagation does not matter -
 * i_block would have to be negative in the very beginning, so we would not
 * get there at all.
 */

static int ext2_block_to_path(struct inode *inode,
			long i_block, int offsets[4], int *boundary)
{
	int ptrs = EXT2_ADDR_PER_BLOCK(inode->i_sb);
	int ptrs_bits = EXT2_ADDR_PER_BLOCK_BITS(inode->i_sb);
	const long direct_blocks = EXT2_NDIR_BLOCKS,
		indirect_blocks = ptrs,
		double_blocks = (1 << (ptrs_bits * 2));
	int n = 0;
	int final = 0;

	if (i_block < 0) {
		ext2_msg(inode->i_sb, KERN_WARNING,
			"warning: %s: block < 0", __func__);
	} else if (i_block < direct_blocks) {
		offsets[n++] = i_block;
		final = direct_blocks;
	} else if ( (i_block -= direct_blocks) < indirect_blocks) {
		offsets[n++] = EXT2_IND_BLOCK;
		offsets[n++] = i_block;
		final = ptrs;
	} else if ((i_block -= indirect_blocks) < double_blocks) {
		offsets[n++] = EXT2_DIND_BLOCK;
		offsets[n++] = i_block >> ptrs_bits;
		offsets[n++] = i_block & (ptrs - 1);
		final = ptrs;
	} else if (((i_block -= double_blocks) >> (ptrs_bits * 2)) < ptrs) {
		offsets[n++] = EXT2_TIND_BLOCK;
		offsets[n++] = i_block >> (ptrs_bits * 2);
		offsets[n++] = (i_block >> ptrs_bits) & (ptrs - 1);
		offsets[n++] = i_block & (ptrs - 1);
		final = ptrs;
	} else {
		ext2_msg(inode->i_sb, KERN_WARNING,
			"warning: %s: block is too big", __func__);
	}
	if (boundary)
		*boundary = final - 1 - (i_block & (ptrs - 1));

	return n;
}

/**
 *	ext2_get_branch - read the chain of indirect blocks leading to data
 *	@inode: inode in question
 *	@depth: depth of the chain (1 - direct pointer, etc.)
 *	@offsets: offsets of pointers in inode/indirect blocks
 *	@chain: place to store the result
 *	@err: here we store the error value
 *
 *	Function fills the array of triples <key, p, bh> and returns %NULL
 *	if everything went OK or the pointer to the last filled triple
 *	(incomplete one) otherwise. Upon the return chain[i].key contains
 *	the number of (i+1)-th block in the chain (as it is stored in memory,
 *	i.e. little-endian 32-bit), chain[i].p contains the address of that
 *	number (it points into struct inode for i==0 and into the bh->b_data
 *	for i>0) and chain[i].bh points to the buffer_head of i-th indirect
 *	block for i>0 and NULL for i==0. In other words, it holds the block
 *	numbers of the chain, addresses they were taken from (and where we can
 *	verify that chain did not change) and buffer_heads hosting these
 *	numbers.
 *
 *	Function stops when it stumbles upon zero pointer (absent block)
 *		(pointer to last triple returned, *@err == 0)
 *	or when it gets an IO error reading an indirect block
 *		(ditto, *@err == -EIO)
 *	or when it notices that chain had been changed while it was reading
 *		(ditto, *@err == -EAGAIN)
 *	or when it reads all @depth-1 indirect blocks successfully and finds
 *	the whole chain, all way to the data (returns %NULL, *err == 0).
 */
static Indirect *ext2_get_branch(struct inode *inode,
				 int depth,
				 int *offsets,
				 Indirect chain[4],
				 int *err)
{
	struct super_block *sb = inode->i_sb;
	Indirect *p = chain;
	struct buffer_head *bh;

	*err = 0;
	/* i_data is not going away, no lock needed */
	add_chain (chain, NULL, EXT2_I(inode)->i_data + *offsets);
	if (!p->key)
		goto no_block;
	while (--depth) {
		bh = sb_bread(sb, le32_to_cpu(p->key));
		if (!bh)
			goto failure;
		read_lock(&EXT2_I(inode)->i_meta_lock);
		if (!verify_chain(chain, p))
			goto changed;
		add_chain(++p, bh, (__le32*)bh->b_data + *++offsets);
		read_unlock(&EXT2_I(inode)->i_meta_lock);
		if (!p->key)
			goto no_block;
	}
	return NULL;

changed:
	read_unlock(&EXT2_I(inode)->i_meta_lock);
	brelse(bh);
	*err = -EAGAIN;
	goto no_block;
failure:
	*err = -EIO;
no_block:
	return p;
}

/**
 *	ext2_find_near - find a place for allocation with sufficient locality
 *	@inode: owner
 *	@ind: descriptor of indirect block.
 *
 *	This function returns the preferred place for block allocation.
 *	It is used when heuristic for sequential allocation fails.
 *	Rules are:
 *	  + if there is a block to the left of our position - allocate near it.
 *	  + if pointer will live in indirect block - allocate near that block.
 *	  + if pointer will live in inode - allocate in the same cylinder group.
 *
 * In the latter case we colour the starting block by the callers PID to
 * prevent it from clashing with concurrent allocations for a different inode
 * in the same block group.   The PID is used here so that functionally related
 * files will be close-by on-disk.
 *
 *	Caller must make sure that @ind is valid and will stay that way.
 */

static ext2_fsblk_t ext2_find_near(struct inode *inode, Indirect *ind)
{
	struct ext2_inode_info *ei = EXT2_I(inode);
	__le32 *start = ind->bh ? (__le32 *) ind->bh->b_data : ei->i_data;
	__le32 *p;
	ext2_fsblk_t bg_start;
	ext2_fsblk_t colour;

	/* Try to find previous block */
	for (p = ind->p - 1; p >= start; p--)
		if (*p)
			return le32_to_cpu(*p);

	/* No such thing, so let's try location of indirect block */
	if (ind->bh)
		return ind->bh->b_blocknr;

	/*
	 * It is going to be referred from inode itself? OK, just put it into
	 * the same cylinder group then.
	 */
	bg_start = ext2_group_first_block_no(inode->i_sb, ei->i_block_group);
	colour = (current->pid % 16) *
			(EXT2_BLOCKS_PER_GROUP(inode->i_sb) / 16);
	return bg_start + colour;
}

/**
 *	ext2_find_goal - find a preferred place for allocation.
 *	@inode: owner
 *	@block:  block we want
 *	@partial: pointer to the last triple within a chain
 *
 *	Returns preferred place for a block (the goal).
 */

static inline ext2_fsblk_t ext2_find_goal(struct inode *inode, long block,
					  Indirect *partial)
{
	struct ext2_block_alloc_info *block_i;

	block_i = EXT2_I(inode)->i_block_alloc_info;

	/*
	 * try the heuristic for sequential allocation,
	 * failing that at least try to get decent locality.
	 */
	if (block_i && (block == block_i->last_alloc_logical_block + 1)
		&& (block_i->last_alloc_physical_block != 0)) {
		return block_i->last_alloc_physical_block + 1;
	}

	return ext2_find_near(inode, partial);
}

/**
 *	ext2_blks_to_allocate: Look up the block map and count the number
 *	of direct blocks need to be allocated for the given branch.
 *
 * 	@branch: chain of indirect blocks
 *	@k: number of blocks need for indirect blocks
 *	@blks: number of data blocks to be mapped.
 *	@blocks_to_boundary:  the offset in the indirect block
 *
 *	return the total number of blocks to be allocate, including the
 *	direct and indirect blocks.
 */
static int
ext2_blks_to_allocate(Indirect * branch, int k, unsigned long blks,
		int blocks_to_boundary)
{
	unsigned long count = 0;

	/*
	 * Simple case, [t,d]Indirect block(s) has not allocated yet
	 * then it's clear blocks on that path have not allocated
	 */
	if (k > 0) {
		/* right now don't hanel cross boundary allocation */
		if (blks < blocks_to_boundary + 1)
			count += blks;
		else
			count += blocks_to_boundary + 1;
		return count;
	}

	count++;
	while (count < blks && count <= blocks_to_boundary
		&& le32_to_cpu(*(branch[0].p + count)) == 0) {
		count++;
	}
	return count;
}

/**
 *	ext2_alloc_blocks: multiple allocate blocks needed for a branch
 *	@indirect_blks: the number of blocks need to allocate for indirect
 *			blocks
 *
 *	@new_blocks: on return it will store the new block numbers for
 *	the indirect blocks(if needed) and the first direct block,
 *	@blks:	on return it will store the total number of allocated
 *		direct blocks
 */
static int ext2_alloc_blocks(struct inode *inode,
			ext2_fsblk_t goal, int indirect_blks, int blks,
			ext2_fsblk_t new_blocks[4], int *err)
{
	int target, i;
	unsigned long count = 0;
	int index = 0;
	ext2_fsblk_t current_block = 0;
	int ret = 0;

	/*
	 * Here we try to allocate the requested multiple blocks at once,
	 * on a best-effort basis.
	 * To build a branch, we should allocate blocks for
	 * the indirect blocks(if not allocated yet), and at least
	 * the first direct block of this branch.  That's the
	 * minimum number of blocks need to allocate(required)
	 */
	target = blks + indirect_blks;

	while (1) {
		count = target;
		/* allocating blocks for indirect blocks and direct blocks */
		current_block = ext2_new_blocks(inode,goal,&count,err);
		if (*err)
			goto failed_out;

		target -= count;
		/* allocate blocks for indirect blocks */
		while (index < indirect_blks && count) {
			new_blocks[index++] = current_block++;
			count--;
		}

		if (count > 0)
			break;
	}

	/* save the new block number for the first direct block */
	new_blocks[index] = current_block;

	/* total number of blocks allocated for direct blocks */
	ret = count;
	*err = 0;
	return ret;
failed_out:
	for (i = 0; i <index; i++)
		ext2_free_blocks(inode, new_blocks[i], 1);
	if (index)
		mark_inode_dirty(inode);
	return ret;
}

/**
 *	ext2_alloc_branch - allocate and set up a chain of blocks.
 *	@inode: owner
 *	@num: depth of the chain (number of blocks to allocate)
 *	@offsets: offsets (in the blocks) to store the pointers to next.
 *	@branch: place to store the chain in.
 *
 *	This function allocates @num blocks, zeroes out all but the last one,
 *	links them into chain and (if we are synchronous) writes them to disk.
 *	In other words, it prepares a branch that can be spliced onto the
 *	inode. It stores the information about that chain in the branch[], in
 *	the same format as ext2_get_branch() would do. We are calling it after
 *	we had read the existing part of chain and partial points to the last
 *	triple of that (one with zero ->key). Upon the exit we have the same
 *	picture as after the successful ext2_get_block(), except that in one
 *	place chain is disconnected - *branch->p is still zero (we did not
 *	set the last link), but branch->key contains the number that should
 *	be placed into *branch->p to fill that gap.
 *
 *	If allocation fails we free all blocks we've allocated (and forget
 *	their buffer_heads) and return the error value the from failed
 *	ext2_alloc_block() (normally -ENOSPC). Otherwise we set the chain
 *	as described above and return 0.
 */

static int ext2_alloc_branch(struct inode *inode,
			int indirect_blks, int *blks, ext2_fsblk_t goal,
			int *offsets, Indirect *branch)
{
	int blocksize = inode->i_sb->s_blocksize;
	int i, n = 0;
	int err = 0;
	struct buffer_head *bh;
	int num;
	ext2_fsblk_t new_blocks[4];
	ext2_fsblk_t current_block;

	num = ext2_alloc_blocks(inode, goal, indirect_blks,
				*blks, new_blocks, &err);
	if (err)
		return err;

	branch[0].key = cpu_to_le32(new_blocks[0]);
	/*
	 * metadata blocks and data blocks are allocated.
	 */
	for (n = 1; n <= indirect_blks;  n++) {
		/*
		 * Get buffer_head for parent block, zero it out
		 * and set the pointer to new one, then send
		 * parent to disk.
		 */
		bh = sb_getblk(inode->i_sb, new_blocks[n-1]);
		if (unlikely(!bh)) {
			err = -ENOMEM;
			goto failed;
		}
		branch[n].bh = bh;
		lock_buffer(bh);
		memset(bh->b_data, 0, blocksize);
		branch[n].p = (__le32 *) bh->b_data + offsets[n];
		branch[n].key = cpu_to_le32(new_blocks[n]);
		*branch[n].p = branch[n].key;
		if ( n == indirect_blks) {
			current_block = new_blocks[n];
			/*
			 * End of chain, update the last new metablock of
			 * the chain to point to the new allocated
			 * data blocks numbers
			 */
			for (i=1; i < num; i++)
				*(branch[n].p + i) = cpu_to_le32(++current_block);
		}
		set_buffer_uptodate(bh);
		unlock_buffer(bh);
		mark_buffer_dirty_inode(bh, inode);
		/* We used to sync bh here if IS_SYNC(inode).
		 * But we now rely upon generic_write_sync()
		 * and b_inode_buffers.  But not for directories.
		 */
		if (S_ISDIR(inode->i_mode) && IS_DIRSYNC(inode))
			sync_dirty_buffer(bh);
	}
	*blks = num;
	return err;

failed:
	for (i = 1; i < n; i++)
		bforget(branch[i].bh);
	for (i = 0; i < indirect_blks; i++)
		ext2_free_blocks(inode, new_blocks[i], 1);
	ext2_free_blocks(inode, new_blocks[i], num);
	return err;
}

/**
 * ext2_splice_branch - splice the allocated branch onto inode.
 * @inode: owner
 * @block: (logical) number of block we are adding
 * @where: location of missing link
 * @num:   number of indirect blocks we are adding
 * @blks:  number of direct blocks we are adding
 *
 * This function fills the missing link and does all housekeeping needed in
 * inode (->i_blocks, etc.). In case of success we end up with the full
 * chain to new block and return 0.
 */
static void ext2_splice_branch(struct inode *inode,
			long block, Indirect *where, int num, int blks)
{
	int i;
	struct ext2_block_alloc_info *block_i;
	ext2_fsblk_t current_block;

	block_i = EXT2_I(inode)->i_block_alloc_info;

	/* XXX LOCKING probably should have i_meta_lock ?*/
	/* That's it */

	*where->p = where->key;

	/*
	 * Update the host buffer_head or inode to point to more just allocated
	 * direct blocks blocks
	 */
	if (num == 0 && blks > 1) {
		current_block = le32_to_cpu(where->key) + 1;
		for (i = 1; i < blks; i++)
			*(where->p + i ) = cpu_to_le32(current_block++);
	}

	/*
	 * update the most recently allocated logical & physical block
	 * in i_block_alloc_info, to assist find the proper goal block for next
	 * allocation
	 */
	if (block_i) {
		block_i->last_alloc_logical_block = block + blks - 1;
		block_i->last_alloc_physical_block =
				le32_to_cpu(where[num].key) + blks - 1;
	}

	/* We are done with atomic stuff, now do the rest of housekeeping */

	/* had we spliced it onto indirect block? */
	if (where->bh)
		mark_buffer_dirty_inode(where->bh, inode);

	inode->i_ctime = CURRENT_TIME_SEC;
	mark_inode_dirty(inode);
}

/*
 * Allocation strategy is simple: if we have to allocate something, we will
 * have to go the whole way to leaf. So let's do it before attaching anything
 * to tree, set linkage between the newborn blocks, write them if sync is
 * required, recheck the path, free and repeat if check fails, otherwise
 * set the last missing link (that will protect us from any truncate-generated
 * removals - all blocks on the path are immune now) and possibly force the
 * write on the parent block.
 * That has a nice additional property: no special recovery from the failed
 * allocations is needed - we simply release blocks and do not touch anything
 * reachable from inode.
 *
 * `handle' can be NULL if create == 0.
 *
 * return > 0, # of blocks mapped or allocated.
 * return = 0, if plain lookup failed.
 * return < 0, error case.
 */
static int ext2_get_blocks(struct inode *inode,
			   sector_t iblock, unsigned long maxblocks,
			   struct buffer_head *bh_result,
			   int create)
{
	int err = -EIO;
	int offsets[4];
	Indirect chain[4];
	Indirect *partial;
	ext2_fsblk_t goal;
	int indirect_blks;
	int blocks_to_boundary = 0;
	int depth;
	struct ext2_inode_info *ei = EXT2_I(inode);
	int count = 0;
	ext2_fsblk_t first_block = 0;

	BUG_ON(maxblocks == 0);

	depth = ext2_block_to_path(inode,iblock,offsets,&blocks_to_boundary);

	if (depth == 0)
		return (err);

	partial = ext2_get_branch(inode, depth, offsets, chain, &err);
	/* Simplest case - block found, no allocation needed */
	if (!partial) {
		first_block = le32_to_cpu(chain[depth - 1].key);
		clear_buffer_new(bh_result); /* What's this do? */
		count++;
		/*map more blocks*/
		while (count < maxblocks && count <= blocks_to_boundary) {
			ext2_fsblk_t blk;

			if (!verify_chain(chain, chain + depth - 1)) {
				/*
				 * Indirect block might be removed by
				 * truncate while we were reading it.
				 * Handling of that case: forget what we've
				 * got now, go to reread.
				 */
				err = -EAGAIN;
				count = 0;
				break;
			}
			blk = le32_to_cpu(*(chain[depth-1].p + count));
			if (blk == first_block + count)
				count++;
			else
				break;
		}
		if (err != -EAGAIN)
			goto got_it;
	}

	/* Next simple case - plain lookup or failed read of indirect block */
	if (!create || err == -EIO)
		goto cleanup;

	mutex_lock(&ei->truncate_mutex);
	/*
	 * If the indirect block is missing while we are reading
	 * the chain(ext2_get_branch() returns -EAGAIN err), or
	 * if the chain has been changed after we grab the semaphore,
	 * (either because another process truncated this branch, or
	 * another get_block allocated this branch) re-grab the chain to see if
	 * the request block has been allocated or not.
	 *
	 * Since we already block the truncate/other get_block
	 * at this point, we will have the current copy of the chain when we
	 * splice the branch into the tree.
	 */
	if (err == -EAGAIN || !verify_chain(chain, partial)) {
		while (partial > chain) {
			brelse(partial->bh);
			partial--;
		}
		partial = ext2_get_branch(inode, depth, offsets, chain, &err);
		if (!partial) {
			count++;
			mutex_unlock(&ei->truncate_mutex);
			if (err)
				goto cleanup;
			clear_buffer_new(bh_result);
			goto got_it;
		}
	}

	/*
	 * Okay, we need to do block allocation.  Lazily initialize the block
	 * allocation info here if necessary
	*/
	if (S_ISREG(inode->i_mode) && (!ei->i_block_alloc_info))
		ext2_init_block_alloc_info(inode);

	goal = ext2_find_goal(inode, iblock, partial);

	/* the number of blocks need to allocate for [d,t]indirect blocks */
	indirect_blks = (chain + depth) - partial - 1;
	/*
	 * Next look up the indirect map to count the totoal number of
	 * direct blocks to allocate for this branch.
	 */
	count = ext2_blks_to_allocate(partial, indirect_blks,
					maxblocks, blocks_to_boundary);
	/*
	 * XXX ???? Block out ext2_truncate while we alter the tree
	 */
	err = ext2_alloc_branch(inode, indirect_blks, &count, goal,
				offsets + (partial - chain), partial);

	if (err) {
		mutex_unlock(&ei->truncate_mutex);
		goto cleanup;
	}

	if (IS_DAX(inode)) {
		/*
		 * block must be initialised before we put it in the tree
		 * so that it's not found by another thread before it's
		 * initialised
		 */
		err = dax_clear_blocks(inode, le32_to_cpu(chain[depth-1].key),
						1 << inode->i_blkbits);
		if (err) {
			mutex_unlock(&ei->truncate_mutex);
			goto cleanup;
		}
	}

	ext2_splice_branch(inode, iblock, partial, indirect_blks, count);
	mutex_unlock(&ei->truncate_mutex);
	set_buffer_new(bh_result);
got_it:
	map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
	if (count > blocks_to_boundary)
		set_buffer_boundary(bh_result);
	err = count;
	/* Clean up and exit */
	partial = chain + depth - 1;	/* the whole chain */
cleanup:
	while (partial > chain) {
		brelse(partial->bh);
		partial--;
	}
	return err;
}

int ext2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create)
{
	unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
	int ret = ext2_get_blocks(inode, iblock, max_blocks,
			      bh_result, create);
	if (ret > 0) {
		bh_result->b_size = (ret << inode->i_blkbits);
		ret = 0;
	}
	return ret;

}

int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
		u64 start, u64 len)
{
	return generic_block_fiemap(inode, fieinfo, start, len,
				    ext2_get_block);
}

static int ext2_writepage(struct page *page, struct writeback_control *wbc)
{
	return block_write_full_page(page, ext2_get_block, wbc);
}

static int ext2_readpage(struct file *file, struct page *page)
{
	return mpage_readpage(page, ext2_get_block);
}

static int
ext2_readpages(struct file *file, struct address_space *mapping,
		struct list_head *pages, unsigned nr_pages)
{
	return mpage_readpages(mapping, pages, nr_pages, ext2_get_block);
}

static int
ext2_write_begin(struct file *file, struct address_space *mapping,
		loff_t pos, unsigned len, unsigned flags,
		struct page **pagep, void **fsdata)
{
	int ret;

	ret = block_write_begin(mapping, pos, len, flags, pagep,
				ext2_get_block);
	if (ret < 0)
		ext2_write_failed(mapping, pos + len);
	return ret;
}

static int ext2_write_end(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned copied,
			struct page *page, void *fsdata)
{
	int ret;

	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
	if (ret < len)
		ext2_write_failed(mapping, pos + len);
	return ret;
}

static int
ext2_nobh_write_begin(struct file *file, struct address_space *mapping,
		loff_t pos, unsigned len, unsigned flags,
		struct page **pagep, void **fsdata)
{
	int ret;

	ret = nobh_write_begin(mapping, pos, len, flags, pagep, fsdata,
			       ext2_get_block);
	if (ret < 0)
		ext2_write_failed(mapping, pos + len);
	return ret;
}

static int ext2_nobh_writepage(struct page *page,
			struct writeback_control *wbc)
{
	return nobh_writepage(page, ext2_get_block, wbc);
}

static sector_t ext2_bmap(struct address_space *mapping, sector_t block)
{
	return generic_block_bmap(mapping,block,ext2_get_block);
}

static ssize_t
ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
{
	struct file *file = iocb->ki_filp;
	struct address_space *mapping = file->f_mapping;
	struct inode *inode = mapping->host;
	size_t count = iov_iter_count(iter);
	ssize_t ret;

	if (IS_DAX(inode))
		ret = dax_do_io(iocb, inode, iter, offset, ext2_get_block, NULL,
				DIO_LOCKING);
	else
		ret = blockdev_direct_IO(iocb, inode, iter, offset,
					 ext2_get_block);
	if (ret < 0 && iov_iter_rw(iter) == WRITE)
		ext2_write_failed(mapping, offset + count);
	return ret;
}

static int
ext2_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
	return mpage_writepages(mapping, wbc, ext2_get_block);
}

const struct address_space_operations ext2_aops = {
	.readpage		= ext2_readpage,
	.readpages		= ext2_readpages,
	.writepage		= ext2_writepage,
	.write_begin		= ext2_write_begin,
	.write_end		= ext2_write_end,
	.bmap			= ext2_bmap,
	.direct_IO		= ext2_direct_IO,
	.writepages		= ext2_writepages,
	.migratepage		= buffer_migrate_page,
	.is_partially_uptodate	= block_is_partially_uptodate,
	.error_remove_page	= generic_error_remove_page,
};

const struct address_space_operations ext2_nobh_aops = {
	.readpage		= ext2_readpage,
	.readpages		= ext2_readpages,
	.writepage		= ext2_nobh_writepage,
	.write_begin		= ext2_nobh_write_begin,
	.write_end		= nobh_write_end,
	.bmap			= ext2_bmap,
	.direct_IO		= ext2_direct_IO,
	.writepages		= ext2_writepages,
	.migratepage		= buffer_migrate_page,
	.error_remove_page	= generic_error_remove_page,
};

/*
 * Probably it should be a library function... search for first non-zero word
 * or memcmp with zero_page, whatever is better for particular architecture.
 * Linus?
 */
static inline int all_zeroes(__le32 *p, __le32 *q)
{
	while (p < q)
		if (*p++)
			return 0;
	return 1;
}

/**
 *	ext2_find_shared - find the indirect blocks for partial truncation.
 *	@inode:	  inode in question
 *	@depth:	  depth of the affected branch
 *	@offsets: offsets of pointers in that branch (see ext2_block_to_path)
 *	@chain:	  place to store the pointers to partial indirect blocks
 *	@top:	  place to the (detached) top of branch
 *
 *	This is a helper function used by ext2_truncate().
 *
 *	When we do truncate() we may have to clean the ends of several indirect
 *	blocks but leave the blocks themselves alive. Block is partially
 *	truncated if some data below the new i_size is referred from it (and
 *	it is on the path to the first completely truncated data block, indeed).
 *	We have to free the top of that path along with everything to the right
 *	of the path. Since no allocation past the truncation point is possible
 *	until ext2_truncate() finishes, we may safely do the latter, but top
 *	of branch may require special attention - pageout below the truncation
 *	point might try to populate it.
 *
 *	We atomically detach the top of branch from the tree, store the block
 *	number of its root in *@top, pointers to buffer_heads of partially
 *	truncated blocks - in @chain[].bh and pointers to their last elements
 *	that should not be removed - in @chain[].p. Return value is the pointer
 *	to last filled element of @chain.
 *
 *	The work left to caller to do the actual freeing of subtrees:
 *		a) free the subtree starting from *@top
 *		b) free the subtrees whose roots are stored in
 *			(@chain[i].p+1 .. end of @chain[i].bh->b_data)
 *		c) free the subtrees growing from the inode past the @chain[0].p
 *			(no partially truncated stuff there).
 */

static Indirect *ext2_find_shared(struct inode *inode,
				int depth,
				int offsets[4],
				Indirect chain[4],
				__le32 *top)
{
	Indirect *partial, *p;
	int k, err;

	*top = 0;
	for (k = depth; k > 1 && !offsets[k-1]; k--)
		;
	partial = ext2_get_branch(inode, k, offsets, chain, &err);
	if (!partial)
		partial = chain + k-1;
	/*
	 * If the branch acquired continuation since we've looked at it -
	 * fine, it should all survive and (new) top doesn't belong to us.
	 */
	write_lock(&EXT2_I(inode)->i_meta_lock);
	if (!partial->key && *partial->p) {
		write_unlock(&EXT2_I(inode)->i_meta_lock);
		goto no_top;
	}
	for (p=partial; p>chain && all_zeroes((__le32*)p->bh->b_data,p->p); p--)
		;
	/*
	 * OK, we've found the last block that must survive. The rest of our
	 * branch should be detached before unlocking. However, if that rest
	 * of branch is all ours and does not grow immediately from the inode
	 * it's easier to cheat and just decrement partial->p.
	 */
	if (p == chain + k - 1 && p > chain) {
		p->p--;
	} else {
		*top = *p->p;
		*p->p = 0;
	}
	write_unlock(&EXT2_I(inode)->i_meta_lock);

	while(partial > p)
	{
		brelse(partial->bh);
		partial--;
	}
no_top:
	return partial;
}

/**
 *	ext2_free_data - free a list of data blocks
 *	@inode:	inode we are dealing with
 *	@p:	array of block numbers
 *	@q:	points immediately past the end of array
 *
 *	We are freeing all blocks referred from that array (numbers are
 *	stored as little-endian 32-bit) and updating @inode->i_blocks
 *	appropriately.
 */
static inline void ext2_free_data(struct inode *inode, __le32 *p, __le32 *q)
{
	unsigned long block_to_free = 0, count = 0;
	unsigned long nr;

	for ( ; p < q ; p++) {
		nr = le32_to_cpu(*p);
		if (nr) {
			*p = 0;
			/* accumulate blocks to free if they're contiguous */
			if (count == 0)
				goto free_this;
			else if (block_to_free == nr - count)
				count++;
			else {
				ext2_free_blocks (inode, block_to_free, count);
				mark_inode_dirty(inode);
			free_this:
				block_to_free = nr;
				count = 1;
			}
		}
	}
	if (count > 0) {
		ext2_free_blocks (inode, block_to_free, count);
		mark_inode_dirty(inode);
	}
}

/**
 *	ext2_free_branches - free an array of branches
 *	@inode:	inode we are dealing with
 *	@p:	array of block numbers
 *	@q:	pointer immediately past the end of array
 *	@depth:	depth of the branches to free
 *
 *	We are freeing all blocks referred from these branches (numbers are
 *	stored as little-endian 32-bit) and updating @inode->i_blocks
 *	appropriately.
 */
static void ext2_free_branches(struct inode *inode, __le32 *p, __le32 *q, int depth)
{
	struct buffer_head * bh;
	unsigned long nr;

	if (depth--) {
		int addr_per_block = EXT2_ADDR_PER_BLOCK(inode->i_sb);
		for ( ; p < q ; p++) {
			nr = le32_to_cpu(*p);
			if (!nr)
				continue;
			*p = 0;
			bh = sb_bread(inode->i_sb, nr);
			/*
			 * A read failure? Report error and clear slot
			 * (should be rare).
			 */ 
			if (!bh) {
				ext2_error(inode->i_sb, "ext2_free_branches",
					"Read failure, inode=%ld, block=%ld",
					inode->i_ino, nr);
				continue;
			}
			ext2_free_branches(inode,
					   (__le32*)bh->b_data,
					   (__le32*)bh->b_data + addr_per_block,
					   depth);
			bforget(bh);
			ext2_free_blocks(inode, nr, 1);
			mark_inode_dirty(inode);
		}
	} else
		ext2_free_data(inode, p, q);
}

static void __ext2_truncate_blocks(struct inode *inode, loff_t offset)
{
	__le32 *i_data = EXT2_I(inode)->i_data;
	struct ext2_inode_info *ei = EXT2_I(inode);
	int addr_per_block = EXT2_ADDR_PER_BLOCK(inode->i_sb);
	int offsets[4];
	Indirect chain[4];
	Indirect *partial;
	__le32 nr = 0;
	int n;
	long iblock;
	unsigned blocksize;
	blocksize = inode->i_sb->s_blocksize;
	iblock = (offset + blocksize-1) >> EXT2_BLOCK_SIZE_BITS(inode->i_sb);

	n = ext2_block_to_path(inode, iblock, offsets, NULL);
	if (n == 0)
		return;

	/*
	 * From here we block out all ext2_get_block() callers who want to
	 * modify the block allocation tree.
	 */
	mutex_lock(&ei->truncate_mutex);

	if (n == 1) {
		ext2_free_data(inode, i_data+offsets[0],
					i_data + EXT2_NDIR_BLOCKS);
		goto do_indirects;
	}

	partial = ext2_find_shared(inode, n, offsets, chain, &nr);
	/* Kill the top of shared branch (already detached) */
	if (nr) {
		if (partial == chain)
			mark_inode_dirty(inode);
		else
			mark_buffer_dirty_inode(partial->bh, inode);
		ext2_free_branches(inode, &nr, &nr+1, (chain+n-1) - partial);
	}
	/* Clear the ends of indirect blocks on the shared branch */
	while (partial > chain) {
		ext2_free_branches(inode,
				   partial->p + 1,
				   (__le32*)partial->bh->b_data+addr_per_block,
				   (chain+n-1) - partial);
		mark_buffer_dirty_inode(partial->bh, inode);
		brelse (partial->bh);
		partial--;
	}
do_indirects:
	/* Kill the remaining (whole) subtrees */
	switch (offsets[0]) {
		default:
			nr = i_data[EXT2_IND_BLOCK];
			if (nr) {
				i_data[EXT2_IND_BLOCK] = 0;
				mark_inode_dirty(inode);
				ext2_free_branches(inode, &nr, &nr+1, 1);
			}
		case EXT2_IND_BLOCK:
			nr = i_data[EXT2_DIND_BLOCK];
			if (nr) {
				i_data[EXT2_DIND_BLOCK] = 0;
				mark_inode_dirty(inode);
				ext2_free_branches(inode, &nr, &nr+1, 2);
			}
		case EXT2_DIND_BLOCK:
			nr = i_data[EXT2_TIND_BLOCK];
			if (nr) {
				i_data[EXT2_TIND_BLOCK] = 0;
				mark_inode_dirty(inode);
				ext2_free_branches(inode, &nr, &nr+1, 3);
			}
		case EXT2_TIND_BLOCK:
			;
	}

	ext2_discard_reservation(inode);

	mutex_unlock(&ei->truncate_mutex);
}

static void ext2_truncate_blocks(struct inode *inode, loff_t offset)
{
	/*
	 * XXX: it seems like a bug here that we don't allow
	 * IS_APPEND inode to have blocks-past-i_size trimmed off.
	 * review and fix this.
	 *
	 * Also would be nice to be able to handle IO errors and such,
	 * but that's probably too much to ask.
	 */
	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
	    S_ISLNK(inode->i_mode)))
		return;
	if (ext2_inode_is_fast_symlink(inode))
		return;
	if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
		return;
	__ext2_truncate_blocks(inode, offset);
}

static int ext2_setsize(struct inode *inode, loff_t newsize)
{
	int error;

	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
	    S_ISLNK(inode->i_mode)))
		return -EINVAL;
	if (ext2_inode_is_fast_symlink(inode))
		return -EINVAL;
	if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
		return -EPERM;

	inode_dio_wait(inode);

	if (IS_DAX(inode))
		error = dax_truncate_page(inode, newsize, ext2_get_block);
	else if (test_opt(inode->i_sb, NOBH))
		error = nobh_truncate_page(inode->i_mapping,
				newsize, ext2_get_block);
	else
		error = block_truncate_page(inode->i_mapping,
				newsize, ext2_get_block);
	if (error)
		return error;

	truncate_setsize(inode, newsize);
	__ext2_truncate_blocks(inode, newsize);

	inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC;
	if (inode_needs_sync(inode)) {
		sync_mapping_buffers(inode->i_mapping);
		sync_inode_metadata(inode, 1);
	} else {
		mark_inode_dirty(inode);
	}

	return 0;
}

static struct ext2_inode *ext2_get_inode(struct super_block *sb, ino_t ino,
					struct buffer_head **p)
{
	struct buffer_head * bh;
	unsigned long block_group;
	unsigned long block;
	unsigned long offset;
	struct ext2_group_desc * gdp;

	*p = NULL;
	if ((ino != EXT2_ROOT_INO && ino < EXT2_FIRST_INO(sb)) ||
	    ino > le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count))
		goto Einval;

	block_group = (ino - 1) / EXT2_INODES_PER_GROUP(sb);
	gdp = ext2_get_group_desc(sb, block_group, NULL);
	if (!gdp)
		goto Egdp;
	/*
	 * Figure out the offset within the block group inode table
	 */
	offset = ((ino - 1) % EXT2_INODES_PER_GROUP(sb)) * EXT2_INODE_SIZE(sb);
	block = le32_to_cpu(gdp->bg_inode_table) +
		(offset >> EXT2_BLOCK_SIZE_BITS(sb));
	if (!(bh = sb_bread(sb, block)))
		goto Eio;

	*p = bh;
	offset &= (EXT2_BLOCK_SIZE(sb) - 1);
	return (struct ext2_inode *) (bh->b_data + offset);

Einval:
	ext2_error(sb, "ext2_get_inode", "bad inode number: %lu",
		   (unsigned long) ino);
	return ERR_PTR(-EINVAL);
Eio:
	ext2_error(sb, "ext2_get_inode",
		   "unable to read inode block - inode=%lu, block=%lu",
		   (unsigned long) ino, block);
Egdp:
	return ERR_PTR(-EIO);
}

void ext2_set_inode_flags(struct inode *inode)
{
	unsigned int flags = EXT2_I(inode)->i_flags;

	inode->i_flags &= ~(S_SYNC | S_APPEND | S_IMMUTABLE | S_NOATIME |
				S_DIRSYNC | S_DAX);
	if (flags & EXT2_SYNC_FL)
		inode->i_flags |= S_SYNC;
	if (flags & EXT2_APPEND_FL)
		inode->i_flags |= S_APPEND;
	if (flags & EXT2_IMMUTABLE_FL)
		inode->i_flags |= S_IMMUTABLE;
	if (flags & EXT2_NOATIME_FL)
		inode->i_flags |= S_NOATIME;
	if (flags & EXT2_DIRSYNC_FL)
		inode->i_flags |= S_DIRSYNC;
	if (test_opt(inode->i_sb, DAX))
		inode->i_flags |= S_DAX;
}

/* Propagate flags from i_flags to EXT2_I(inode)->i_flags */
void ext2_get_inode_flags(struct ext2_inode_info *ei)
{
	unsigned int flags = ei->vfs_inode.i_flags;

	ei->i_flags &= ~(EXT2_SYNC_FL|EXT2_APPEND_FL|
			EXT2_IMMUTABLE_FL|EXT2_NOATIME_FL|EXT2_DIRSYNC_FL);
	if (flags & S_SYNC)
		ei->i_flags |= EXT2_SYNC_FL;
	if (flags & S_APPEND)
		ei->i_flags |= EXT2_APPEND_FL;
	if (flags & S_IMMUTABLE)
		ei->i_flags |= EXT2_IMMUTABLE_FL;
	if (flags & S_NOATIME)
		ei->i_flags |= EXT2_NOATIME_FL;
	if (flags & S_DIRSYNC)
		ei->i_flags |= EXT2_DIRSYNC_FL;
}

struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
{
	struct ext2_inode_info *ei;
	struct buffer_head * bh;
	struct ext2_inode *raw_inode;
	struct inode *inode;
	long ret = -EIO;
	int n;
	uid_t i_uid;
	gid_t i_gid;

	inode = iget_locked(sb, ino);
	if (!inode)
		return ERR_PTR(-ENOMEM);
	if (!(inode->i_state & I_NEW))
		return inode;

	ei = EXT2_I(inode);
	ei->i_block_alloc_info = NULL;

	raw_inode = ext2_get_inode(inode->i_sb, ino, &bh);
	if (IS_ERR(raw_inode)) {
		ret = PTR_ERR(raw_inode);
 		goto bad_inode;
	}

	inode->i_mode = le16_to_cpu(raw_inode->i_mode);
	i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
	i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low);
	if (!(test_opt (inode->i_sb, NO_UID32))) {
		i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
		i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
	}
	i_uid_write(inode, i_uid);
	i_gid_write(inode, i_gid);
	set_nlink(inode, le16_to_cpu(raw_inode->i_links_count));
	inode->i_size = le32_to_cpu(raw_inode->i_size);
	inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime);
	inode->i_ctime.tv_sec = (signed)le32_to_cpu(raw_inode->i_ctime);
	inode->i_mtime.tv_sec = (signed)le32_to_cpu(raw_inode->i_mtime);
	inode->i_atime.tv_nsec = inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec = 0;
	ei->i_dtime = le32_to_cpu(raw_inode->i_dtime);
	/* We now have enough fields to check if the inode was active or not.
	 * This is needed because nfsd might try to access dead inodes
	 * the test is that same one that e2fsck uses
	 * NeilBrown 1999oct15
	 */
	if (inode->i_nlink == 0 && (inode->i_mode == 0 || ei->i_dtime)) {
		/* this inode is deleted */
		brelse (bh);
		ret = -ESTALE;
		goto bad_inode;
	}
	inode->i_blocks = le32_to_cpu(raw_inode->i_blocks);
	ei->i_flags = le32_to_cpu(raw_inode->i_flags);
	ei->i_faddr = le32_to_cpu(raw_inode->i_faddr);
	ei->i_frag_no = raw_inode->i_frag;
	ei->i_frag_size = raw_inode->i_fsize;
	ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl);
	ei->i_dir_acl = 0;
	if (S_ISREG(inode->i_mode))
		inode->i_size |= ((__u64)le32_to_cpu(raw_inode->i_size_high)) << 32;
	else
		ei->i_dir_acl = le32_to_cpu(raw_inode->i_dir_acl);
	ei->i_dtime = 0;
	inode->i_generation = le32_to_cpu(raw_inode->i_generation);
	ei->i_state = 0;
	ei->i_block_group = (ino - 1) / EXT2_INODES_PER_GROUP(inode->i_sb);
	ei->i_dir_start_lookup = 0;

	/*
	 * NOTE! The in-memory inode i_data array is in little-endian order
	 * even on big-endian machines: we do NOT byteswap the block numbers!
	 */
	for (n = 0; n < EXT2_N_BLOCKS; n++)
		ei->i_data[n] = raw_inode->i_block[n];

	if (S_ISREG(inode->i_mode)) {
		inode->i_op = &ext2_file_inode_operations;
		if (test_opt(inode->i_sb, NOBH)) {
			inode->i_mapping->a_ops = &ext2_nobh_aops;
			inode->i_fop = &ext2_file_operations;
		} else {
			inode->i_mapping->a_ops = &ext2_aops;
			inode->i_fop = &ext2_file_operations;
		}
	} else if (S_ISDIR(inode->i_mode)) {
		inode->i_op = &ext2_dir_inode_operations;
		inode->i_fop = &ext2_dir_operations;
		if (test_opt(inode->i_sb, NOBH))
			inode->i_mapping->a_ops = &ext2_nobh_aops;
		else
			inode->i_mapping->a_ops = &ext2_aops;
	} else if (S_ISLNK(inode->i_mode)) {
		if (ext2_inode_is_fast_symlink(inode)) {
			inode->i_op = &ext2_fast_symlink_inode_operations;
			nd_terminate_link(ei->i_data, inode->i_size,
				sizeof(ei->i_data) - 1);
		} else {
			inode->i_op = &ext2_symlink_inode_operations;
			if (test_opt(inode->i_sb, NOBH))
				inode->i_mapping->a_ops = &ext2_nobh_aops;
			else
				inode->i_mapping->a_ops = &ext2_aops;
		}
	} else {
		inode->i_op = &ext2_special_inode_operations;
		if (raw_inode->i_block[0])
			init_special_inode(inode, inode->i_mode,
			   old_decode_dev(le32_to_cpu(raw_inode->i_block[0])));
		else 
			init_special_inode(inode, inode->i_mode,
			   new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
	}
	brelse (bh);
	ext2_set_inode_flags(inode);
	unlock_new_inode(inode);
	return inode;
	
bad_inode:
	iget_failed(inode);
	return ERR_PTR(ret);
}

static int __ext2_write_inode(struct inode *inode, int do_sync)
{
	struct ext2_inode_info *ei = EXT2_I(inode);
	struct super_block *sb = inode->i_sb;
	ino_t ino = inode->i_ino;
	uid_t uid = i_uid_read(inode);
	gid_t gid = i_gid_read(inode);
	struct buffer_head * bh;
	struct ext2_inode * raw_inode = ext2_get_inode(sb, ino, &bh);
	int n;
	int err = 0;

	if (IS_ERR(raw_inode))
 		return -EIO;

	/* For fields not not tracking in the in-memory inode,
	 * initialise them to zero for new inodes. */
	if (ei->i_state & EXT2_STATE_NEW)
		memset(raw_inode, 0, EXT2_SB(sb)->s_inode_size);

	ext2_get_inode_flags(ei);
	raw_inode->i_mode = cpu_to_le16(inode->i_mode);
	if (!(test_opt(sb, NO_UID32))) {
		raw_inode->i_uid_low = cpu_to_le16(low_16_bits(uid));
		raw_inode->i_gid_low = cpu_to_le16(low_16_bits(gid));
/*
 * Fix up interoperability with old kernels. Otherwise, old inodes get
 * re-used with the upper 16 bits of the uid/gid intact
 */
		if (!ei->i_dtime) {
			raw_inode->i_uid_high = cpu_to_le16(high_16_bits(uid));
			raw_inode->i_gid_high = cpu_to_le16(high_16_bits(gid));
		} else {
			raw_inode->i_uid_high = 0;
			raw_inode->i_gid_high = 0;
		}
	} else {
		raw_inode->i_uid_low = cpu_to_le16(fs_high2lowuid(uid));
		raw_inode->i_gid_low = cpu_to_le16(fs_high2lowgid(gid));
		raw_inode->i_uid_high = 0;
		raw_inode->i_gid_high = 0;
	}
	raw_inode->i_links_count = cpu_to_le16(inode->i_nlink);
	raw_inode->i_size = cpu_to_le32(inode->i_size);
	raw_inode->i_atime = cpu_to_le32(inode->i_atime.tv_sec);
	raw_inode->i_ctime = cpu_to_le32(inode->i_ctime.tv_sec);
	raw_inode->i_mtime = cpu_to_le32(inode->i_mtime.tv_sec);

	raw_inode->i_blocks = cpu_to_le32(inode->i_blocks);
	raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
	raw_inode->i_flags = cpu_to_le32(ei->i_flags);
	raw_inode->i_faddr = cpu_to_le32(ei->i_faddr);
	raw_inode->i_frag = ei->i_frag_no;
	raw_inode->i_fsize = ei->i_frag_size;
	raw_inode->i_file_acl = cpu_to_le32(ei->i_file_acl);
	if (!S_ISREG(inode->i_mode))
		raw_inode->i_dir_acl = cpu_to_le32(ei->i_dir_acl);
	else {
		raw_inode->i_size_high = cpu_to_le32(inode->i_size >> 32);
		if (inode->i_size > 0x7fffffffULL) {
			if (!EXT2_HAS_RO_COMPAT_FEATURE(sb,
					EXT2_FEATURE_RO_COMPAT_LARGE_FILE) ||
			    EXT2_SB(sb)->s_es->s_rev_level ==
					cpu_to_le32(EXT2_GOOD_OLD_REV)) {
			       /* If this is the first large file
				* created, add a flag to the superblock.
				*/
				spin_lock(&EXT2_SB(sb)->s_lock);
				ext2_update_dynamic_rev(sb);
				EXT2_SET_RO_COMPAT_FEATURE(sb,
					EXT2_FEATURE_RO_COMPAT_LARGE_FILE);
				spin_unlock(&EXT2_SB(sb)->s_lock);
				ext2_write_super(sb);
			}
		}
	}
	
	raw_inode->i_generation = cpu_to_le32(inode->i_generation);
	if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
		if (old_valid_dev(inode->i_rdev)) {
			raw_inode->i_block[0] =
				cpu_to_le32(old_encode_dev(inode->i_rdev));
			raw_inode->i_block[1] = 0;
		} else {
			raw_inode->i_block[0] = 0;
			raw_inode->i_block[1] =
				cpu_to_le32(new_encode_dev(inode->i_rdev));
			raw_inode->i_block[2] = 0;
		}
	} else for (n = 0; n < EXT2_N_BLOCKS; n++)
		raw_inode->i_block[n] = ei->i_data[n];
	mark_buffer_dirty(bh);
	if (do_sync) {
		sync_dirty_buffer(bh);
		if (buffer_req(bh) && !buffer_uptodate(bh)) {
			printk ("IO error syncing ext2 inode [%s:%08lx]\n",
				sb->s_id, (unsigned long) ino);
			err = -EIO;
		}
	}
	ei->i_state &= ~EXT2_STATE_NEW;
	brelse (bh);
	return err;
}

int ext2_write_inode(struct inode *inode, struct writeback_control *wbc)
{
	return __ext2_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL);
}

int ext2_setattr(struct dentry *dentry, struct iattr *iattr)
{
	struct inode *inode = d_inode(dentry);
	int error;

	error = setattr_prepare(dentry, iattr);
	if (error)
		return error;

	if (is_quota_modification(inode, iattr))
		dquot_initialize(inode);
	if ((iattr->ia_valid & ATTR_UID && !uid_eq(iattr->ia_uid, inode->i_uid)) ||
	    (iattr->ia_valid & ATTR_GID && !gid_eq(iattr->ia_gid, inode->i_gid))) {
		error = dquot_transfer(inode, iattr);
		if (error)
			return error;
	}
	if (iattr->ia_valid & ATTR_SIZE && iattr->ia_size != inode->i_size) {
		error = ext2_setsize(inode, iattr->ia_size);
		if (error)
			return error;
	}
	setattr_copy(inode, iattr);
	if (iattr->ia_valid & ATTR_MODE)
		error = posix_acl_chmod(inode, inode->i_mode);
	mark_inode_dirty(inode);

	return error;
}