summaryrefslogtreecommitdiff
path: root/fs/ext4/ialloc.c
blob: fb897ec183c8451e81ee9c780044629f86b819bd (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
/*
 *  linux/fs/ext4/ialloc.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)
 *
 *  BSD ufs-inspired inode and directory allocation by
 *  Stephen Tweedie (sct@redhat.com), 1993
 *  Big-endian to little-endian byte-swapping/bitmaps by
 *        David S. Miller (davem@caip.rutgers.edu), 1995
 */

#include <linux/time.h>
#include <linux/fs.h>
#include <linux/jbd2.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/quotaops.h>
#include <linux/buffer_head.h>
#include <linux/random.h>
#include <linux/bitops.h>
#include <linux/blkdev.h>
#include <asm/byteorder.h>

#include "ext4.h"
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"

#include <trace/events/ext4.h>

/*
 * ialloc.c contains the inodes allocation and deallocation routines
 */

/*
 * The free inodes are managed by bitmaps.  A file system contains several
 * blocks groups.  Each group contains 1 bitmap block for blocks, 1 bitmap
 * block for inodes, N blocks for the inode table and data blocks.
 *
 * The file system contains group descriptors which are located after the
 * super block.  Each descriptor contains the number of the bitmap block and
 * the free blocks count in the block.
 */

/*
 * To avoid calling the atomic setbit hundreds or thousands of times, we only
 * need to use it within a single byte (to ensure we get endianness right).
 * We can use memset for the rest of the bitmap as there are no other users.
 */
void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap)
{
	int i;

	if (start_bit >= end_bit)
		return;

	ext4_debug("mark end bits +%d through +%d used\n", start_bit, end_bit);
	for (i = start_bit; i < ((start_bit + 7) & ~7UL); i++)
		ext4_set_bit(i, bitmap);
	if (i < end_bit)
		memset(bitmap + (i >> 3), 0xff, (end_bit - i) >> 3);
}

/* Initializes an uninitialized inode bitmap */
static unsigned ext4_init_inode_bitmap(struct super_block *sb,
				       struct buffer_head *bh,
				       ext4_group_t block_group,
				       struct ext4_group_desc *gdp)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);

	J_ASSERT_BH(bh, buffer_locked(bh));

	/* If checksum is bad mark all blocks and inodes use to prevent
	 * allocation, essentially implementing a per-group read-only flag. */
	if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
		ext4_error(sb, "Checksum bad for group %u", block_group);
		ext4_free_group_clusters_set(sb, gdp, 0);
		ext4_free_inodes_set(sb, gdp, 0);
		ext4_itable_unused_set(sb, gdp, 0);
		memset(bh->b_data, 0xff, sb->s_blocksize);
		ext4_inode_bitmap_csum_set(sb, block_group, gdp, bh,
					   EXT4_INODES_PER_GROUP(sb) / 8);
		return 0;
	}

	memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8);
	ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8,
			bh->b_data);
	ext4_inode_bitmap_csum_set(sb, block_group, gdp, bh,
				   EXT4_INODES_PER_GROUP(sb) / 8);
	gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp);

	return EXT4_INODES_PER_GROUP(sb);
}

void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate)
{
	if (uptodate) {
		set_buffer_uptodate(bh);
		set_bitmap_uptodate(bh);
	}
	unlock_buffer(bh);
	put_bh(bh);
}

/*
 * Read the inode allocation bitmap for a given block_group, reading
 * into the specified slot in the superblock's bitmap cache.
 *
 * Return buffer_head of bitmap on success or NULL.
 */
static struct buffer_head *
ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
{
	struct ext4_group_desc *desc;
	struct buffer_head *bh = NULL;
	ext4_fsblk_t bitmap_blk;

	desc = ext4_get_group_desc(sb, block_group, NULL);
	if (!desc)
		return NULL;

	bitmap_blk = ext4_inode_bitmap(sb, desc);
	bh = sb_getblk(sb, bitmap_blk);
	if (unlikely(!bh)) {
		ext4_error(sb, "Cannot read inode bitmap - "
			    "block_group = %u, inode_bitmap = %llu",
			    block_group, bitmap_blk);
		return NULL;
	}
	if (bitmap_uptodate(bh))
		goto verify;

	lock_buffer(bh);
	if (bitmap_uptodate(bh)) {
		unlock_buffer(bh);
		goto verify;
	}

	ext4_lock_group(sb, block_group);
	if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
		ext4_init_inode_bitmap(sb, bh, block_group, desc);
		set_bitmap_uptodate(bh);
		set_buffer_uptodate(bh);
		set_buffer_verified(bh);
		ext4_unlock_group(sb, block_group);
		unlock_buffer(bh);
		return bh;
	}
	ext4_unlock_group(sb, block_group);

	if (buffer_uptodate(bh)) {
		/*
		 * if not uninit if bh is uptodate,
		 * bitmap is also uptodate
		 */
		set_bitmap_uptodate(bh);
		unlock_buffer(bh);
		goto verify;
	}
	/*
	 * submit the buffer_head for reading
	 */
	trace_ext4_load_inode_bitmap(sb, block_group);
	bh->b_end_io = ext4_end_bitmap_read;
	get_bh(bh);
	submit_bh(READ, bh);
	wait_on_buffer(bh);
	if (!buffer_uptodate(bh)) {
		put_bh(bh);
		ext4_error(sb, "Cannot read inode bitmap - "
			   "block_group = %u, inode_bitmap = %llu",
			   block_group, bitmap_blk);
		return NULL;
	}

verify:
	ext4_lock_group(sb, block_group);
	if (!buffer_verified(bh) &&
	    !ext4_inode_bitmap_csum_verify(sb, block_group, desc, bh,
					   EXT4_INODES_PER_GROUP(sb) / 8)) {
		ext4_unlock_group(sb, block_group);
		put_bh(bh);
		ext4_error(sb, "Corrupt inode bitmap - block_group = %u, "
			   "inode_bitmap = %llu", block_group, bitmap_blk);
		return NULL;
	}
	ext4_unlock_group(sb, block_group);
	set_buffer_verified(bh);
	return bh;
}

/*
 * NOTE! When we get the inode, we're the only people
 * that have access to it, and as such there are no
 * race conditions we have to worry about. The inode
 * is not on the hash-lists, and it cannot be reached
 * through the filesystem because the directory entry
 * has been deleted earlier.
 *
 * HOWEVER: we must make sure that we get no aliases,
 * which means that we have to call "clear_inode()"
 * _before_ we mark the inode not in use in the inode
 * bitmaps. Otherwise a newly created file might use
 * the same inode number (not actually the same pointer
 * though), and then we'd have two inodes sharing the
 * same inode number and space on the harddisk.
 */
void ext4_free_inode(handle_t *handle, struct inode *inode)
{
	struct super_block *sb = inode->i_sb;
	int is_directory;
	unsigned long ino;
	struct buffer_head *bitmap_bh = NULL;
	struct buffer_head *bh2;
	ext4_group_t block_group;
	unsigned long bit;
	struct ext4_group_desc *gdp;
	struct ext4_super_block *es;
	struct ext4_sb_info *sbi;
	int fatal = 0, err, count, cleared;

	if (!sb) {
		printk(KERN_ERR "EXT4-fs: %s:%d: inode on "
		       "nonexistent device\n", __func__, __LINE__);
		return;
	}
	if (atomic_read(&inode->i_count) > 1) {
		ext4_msg(sb, KERN_ERR, "%s:%d: inode #%lu: count=%d",
			 __func__, __LINE__, inode->i_ino,
			 atomic_read(&inode->i_count));
		return;
	}
	if (inode->i_nlink) {
		ext4_msg(sb, KERN_ERR, "%s:%d: inode #%lu: nlink=%d\n",
			 __func__, __LINE__, inode->i_ino, inode->i_nlink);
		return;
	}
	sbi = EXT4_SB(sb);

	ino = inode->i_ino;
	ext4_debug("freeing inode %lu\n", ino);
	trace_ext4_free_inode(inode);

	/*
	 * Note: we must free any quota before locking the superblock,
	 * as writing the quota to disk may need the lock as well.
	 */
	dquot_initialize(inode);
	ext4_xattr_delete_inode(handle, inode);
	dquot_free_inode(inode);
	dquot_drop(inode);

	is_directory = S_ISDIR(inode->i_mode);

	/* Do this BEFORE marking the inode not in use or returning an error */
	ext4_clear_inode(inode);

	es = EXT4_SB(sb)->s_es;
	if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
		ext4_error(sb, "reserved or nonexistent inode %lu", ino);
		goto error_return;
	}
	block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
	bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
	bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
	if (!bitmap_bh)
		goto error_return;

	BUFFER_TRACE(bitmap_bh, "get_write_access");
	fatal = ext4_journal_get_write_access(handle, bitmap_bh);
	if (fatal)
		goto error_return;

	fatal = -ESRCH;
	gdp = ext4_get_group_desc(sb, block_group, &bh2);
	if (gdp) {
		BUFFER_TRACE(bh2, "get_write_access");
		fatal = ext4_journal_get_write_access(handle, bh2);
	}
	ext4_lock_group(sb, block_group);
	cleared = ext4_test_and_clear_bit(bit, bitmap_bh->b_data);
	if (fatal || !cleared) {
		ext4_unlock_group(sb, block_group);
		goto out;
	}

	count = ext4_free_inodes_count(sb, gdp) + 1;
	ext4_free_inodes_set(sb, gdp, count);
	if (is_directory) {
		count = ext4_used_dirs_count(sb, gdp) - 1;
		ext4_used_dirs_set(sb, gdp, count);
		percpu_counter_dec(&sbi->s_dirs_counter);
	}
	ext4_inode_bitmap_csum_set(sb, block_group, gdp, bitmap_bh,
				   EXT4_INODES_PER_GROUP(sb) / 8);
	gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp);
	ext4_unlock_group(sb, block_group);

	percpu_counter_inc(&sbi->s_freeinodes_counter);
	if (sbi->s_log_groups_per_flex) {
		ext4_group_t f = ext4_flex_group(sbi, block_group);

		atomic_inc(&sbi->s_flex_groups[f].free_inodes);
		if (is_directory)
			atomic_dec(&sbi->s_flex_groups[f].used_dirs);
	}
	BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata");
	fatal = ext4_handle_dirty_metadata(handle, NULL, bh2);
out:
	if (cleared) {
		BUFFER_TRACE(bitmap_bh, "call ext4_handle_dirty_metadata");
		err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
		if (!fatal)
			fatal = err;
		ext4_mark_super_dirty(sb);
	} else
		ext4_error(sb, "bit already cleared for inode %lu", ino);

error_return:
	brelse(bitmap_bh);
	ext4_std_error(sb, fatal);
}

struct orlov_stats {
	__u32 free_inodes;
	__u32 free_clusters;
	__u32 used_dirs;
};

/*
 * Helper function for Orlov's allocator; returns critical information
 * for a particular block group or flex_bg.  If flex_size is 1, then g
 * is a block group number; otherwise it is flex_bg number.
 */
static void get_orlov_stats(struct super_block *sb, ext4_group_t g,
			    int flex_size, struct orlov_stats *stats)
{
	struct ext4_group_desc *desc;
	struct flex_groups *flex_group = EXT4_SB(sb)->s_flex_groups;

	if (flex_size > 1) {
		stats->free_inodes = atomic_read(&flex_group[g].free_inodes);
		stats->free_clusters = atomic_read(&flex_group[g].free_clusters);
		stats->used_dirs = atomic_read(&flex_group[g].used_dirs);
		return;
	}

	desc = ext4_get_group_desc(sb, g, NULL);
	if (desc) {
		stats->free_inodes = ext4_free_inodes_count(sb, desc);
		stats->free_clusters = ext4_free_group_clusters(sb, desc);
		stats->used_dirs = ext4_used_dirs_count(sb, desc);
	} else {
		stats->free_inodes = 0;
		stats->free_clusters = 0;
		stats->used_dirs = 0;
	}
}

/*
 * Orlov's allocator for directories.
 *
 * We always try to spread first-level directories.
 *
 * If there are blockgroups with both free inodes and free blocks counts
 * not worse than average we return one with smallest directory count.
 * Otherwise we simply return a random group.
 *
 * For the rest rules look so:
 *
 * It's OK to put directory into a group unless
 * it has too many directories already (max_dirs) or
 * it has too few free inodes left (min_inodes) or
 * it has too few free blocks left (min_blocks) or
 * Parent's group is preferred, if it doesn't satisfy these
 * conditions we search cyclically through the rest. If none
 * of the groups look good we just look for a group with more
 * free inodes than average (starting at parent's group).
 */

static int find_group_orlov(struct super_block *sb, struct inode *parent,
			    ext4_group_t *group, umode_t mode,
			    const struct qstr *qstr)
{
	ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	ext4_group_t real_ngroups = ext4_get_groups_count(sb);
	int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
	unsigned int freei, avefreei, grp_free;
	ext4_fsblk_t freeb, avefreec;
	unsigned int ndirs;
	int max_dirs, min_inodes;
	ext4_grpblk_t min_clusters;
	ext4_group_t i, grp, g, ngroups;
	struct ext4_group_desc *desc;
	struct orlov_stats stats;
	int flex_size = ext4_flex_bg_size(sbi);
	struct dx_hash_info hinfo;

	ngroups = real_ngroups;
	if (flex_size > 1) {
		ngroups = (real_ngroups + flex_size - 1) >>
			sbi->s_log_groups_per_flex;
		parent_group >>= sbi->s_log_groups_per_flex;
	}

	freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
	avefreei = freei / ngroups;
	freeb = EXT4_C2B(sbi,
		percpu_counter_read_positive(&sbi->s_freeclusters_counter));
	avefreec = freeb;
	do_div(avefreec, ngroups);
	ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);

	if (S_ISDIR(mode) &&
	    ((parent == sb->s_root->d_inode) ||
	     (ext4_test_inode_flag(parent, EXT4_INODE_TOPDIR)))) {
		int best_ndir = inodes_per_group;
		int ret = -1;

		if (qstr) {
			hinfo.hash_version = DX_HASH_HALF_MD4;
			hinfo.seed = sbi->s_hash_seed;
			ext4fs_dirhash(qstr->name, qstr->len, &hinfo);
			grp = hinfo.hash;
		} else
			get_random_bytes(&grp, sizeof(grp));
		parent_group = (unsigned)grp % ngroups;
		for (i = 0; i < ngroups; i++) {
			g = (parent_group + i) % ngroups;
			get_orlov_stats(sb, g, flex_size, &stats);
			if (!stats.free_inodes)
				continue;
			if (stats.used_dirs >= best_ndir)
				continue;
			if (stats.free_inodes < avefreei)
				continue;
			if (stats.free_clusters < avefreec)
				continue;
			grp = g;
			ret = 0;
			best_ndir = stats.used_dirs;
		}
		if (ret)
			goto fallback;
	found_flex_bg:
		if (flex_size == 1) {
			*group = grp;
			return 0;
		}

		/*
		 * We pack inodes at the beginning of the flexgroup's
		 * inode tables.  Block allocation decisions will do
		 * something similar, although regular files will
		 * start at 2nd block group of the flexgroup.  See
		 * ext4_ext_find_goal() and ext4_find_near().
		 */
		grp *= flex_size;
		for (i = 0; i < flex_size; i++) {
			if (grp+i >= real_ngroups)
				break;
			desc = ext4_get_group_desc(sb, grp+i, NULL);
			if (desc && ext4_free_inodes_count(sb, desc)) {
				*group = grp+i;
				return 0;
			}
		}
		goto fallback;
	}

	max_dirs = ndirs / ngroups + inodes_per_group / 16;
	min_inodes = avefreei - inodes_per_group*flex_size / 4;
	if (min_inodes < 1)
		min_inodes = 1;
	min_clusters = avefreec - EXT4_CLUSTERS_PER_GROUP(sb)*flex_size / 4;

	/*
	 * Start looking in the flex group where we last allocated an
	 * inode for this parent directory
	 */
	if (EXT4_I(parent)->i_last_alloc_group != ~0) {
		parent_group = EXT4_I(parent)->i_last_alloc_group;
		if (flex_size > 1)
			parent_group >>= sbi->s_log_groups_per_flex;
	}

	for (i = 0; i < ngroups; i++) {
		grp = (parent_group + i) % ngroups;
		get_orlov_stats(sb, grp, flex_size, &stats);
		if (stats.used_dirs >= max_dirs)
			continue;
		if (stats.free_inodes < min_inodes)
			continue;
		if (stats.free_clusters < min_clusters)
			continue;
		goto found_flex_bg;
	}

fallback:
	ngroups = real_ngroups;
	avefreei = freei / ngroups;
fallback_retry:
	parent_group = EXT4_I(parent)->i_block_group;
	for (i = 0; i < ngroups; i++) {
		grp = (parent_group + i) % ngroups;
		desc = ext4_get_group_desc(sb, grp, NULL);
		grp_free = ext4_free_inodes_count(sb, desc);
		if (desc && grp_free && grp_free >= avefreei) {
			*group = grp;
			return 0;
		}
	}

	if (avefreei) {
		/*
		 * The free-inodes counter is approximate, and for really small
		 * filesystems the above test can fail to find any blockgroups
		 */
		avefreei = 0;
		goto fallback_retry;
	}

	return -1;
}

static int find_group_other(struct super_block *sb, struct inode *parent,
			    ext4_group_t *group, umode_t mode)
{
	ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
	ext4_group_t i, last, ngroups = ext4_get_groups_count(sb);
	struct ext4_group_desc *desc;
	int flex_size = ext4_flex_bg_size(EXT4_SB(sb));

	/*
	 * Try to place the inode is the same flex group as its
	 * parent.  If we can't find space, use the Orlov algorithm to
	 * find another flex group, and store that information in the
	 * parent directory's inode information so that use that flex
	 * group for future allocations.
	 */
	if (flex_size > 1) {
		int retry = 0;

	try_again:
		parent_group &= ~(flex_size-1);
		last = parent_group + flex_size;
		if (last > ngroups)
			last = ngroups;
		for  (i = parent_group; i < last; i++) {
			desc = ext4_get_group_desc(sb, i, NULL);
			if (desc && ext4_free_inodes_count(sb, desc)) {
				*group = i;
				return 0;
			}
		}
		if (!retry && EXT4_I(parent)->i_last_alloc_group != ~0) {
			retry = 1;
			parent_group = EXT4_I(parent)->i_last_alloc_group;
			goto try_again;
		}
		/*
		 * If this didn't work, use the Orlov search algorithm
		 * to find a new flex group; we pass in the mode to
		 * avoid the topdir algorithms.
		 */
		*group = parent_group + flex_size;
		if (*group > ngroups)
			*group = 0;
		return find_group_orlov(sb, parent, group, mode, NULL);
	}

	/*
	 * Try to place the inode in its parent directory
	 */
	*group = parent_group;
	desc = ext4_get_group_desc(sb, *group, NULL);
	if (desc && ext4_free_inodes_count(sb, desc) &&
	    ext4_free_group_clusters(sb, desc))
		return 0;

	/*
	 * We're going to place this inode in a different blockgroup from its
	 * parent.  We want to cause files in a common directory to all land in
	 * the same blockgroup.  But we want files which are in a different
	 * directory which shares a blockgroup with our parent to land in a
	 * different blockgroup.
	 *
	 * So add our directory's i_ino into the starting point for the hash.
	 */
	*group = (*group + parent->i_ino) % ngroups;

	/*
	 * Use a quadratic hash to find a group with a free inode and some free
	 * blocks.
	 */
	for (i = 1; i < ngroups; i <<= 1) {
		*group += i;
		if (*group >= ngroups)
			*group -= ngroups;
		desc = ext4_get_group_desc(sb, *group, NULL);
		if (desc && ext4_free_inodes_count(sb, desc) &&
		    ext4_free_group_clusters(sb, desc))
			return 0;
	}

	/*
	 * That failed: try linear search for a free inode, even if that group
	 * has no free blocks.
	 */
	*group = parent_group;
	for (i = 0; i < ngroups; i++) {
		if (++*group >= ngroups)
			*group = 0;
		desc = ext4_get_group_desc(sb, *group, NULL);
		if (desc && ext4_free_inodes_count(sb, desc))
			return 0;
	}

	return -1;
}

/*
 * There are two policies for allocating an inode.  If the new inode is
 * a directory, then a forward search is made for a block group with both
 * free space and a low directory-to-inode ratio; if that fails, then of
 * the groups with above-average free space, that group with the fewest
 * directories already is chosen.
 *
 * For other inodes, search forward from the parent directory's block
 * group to find a free inode.
 */
struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, umode_t mode,
			     const struct qstr *qstr, __u32 goal, uid_t *owner)
{
	struct super_block *sb;
	struct buffer_head *inode_bitmap_bh = NULL;
	struct buffer_head *group_desc_bh;
	ext4_group_t ngroups, group = 0;
	unsigned long ino = 0;
	struct inode *inode;
	struct ext4_group_desc *gdp = NULL;
	struct ext4_inode_info *ei;
	struct ext4_sb_info *sbi;
	int ret2, err = 0;
	struct inode *ret;
	ext4_group_t i;
	ext4_group_t flex_group;

	/* Cannot create files in a deleted directory */
	if (!dir || !dir->i_nlink)
		return ERR_PTR(-EPERM);

	sb = dir->i_sb;
	ngroups = ext4_get_groups_count(sb);
	trace_ext4_request_inode(dir, mode);
	inode = new_inode(sb);
	if (!inode)
		return ERR_PTR(-ENOMEM);
	ei = EXT4_I(inode);
	sbi = EXT4_SB(sb);

	if (!goal)
		goal = sbi->s_inode_goal;

	if (goal && goal <= le32_to_cpu(sbi->s_es->s_inodes_count)) {
		group = (goal - 1) / EXT4_INODES_PER_GROUP(sb);
		ino = (goal - 1) % EXT4_INODES_PER_GROUP(sb);
		ret2 = 0;
		goto got_group;
	}

	if (S_ISDIR(mode))
		ret2 = find_group_orlov(sb, dir, &group, mode, qstr);
	else
		ret2 = find_group_other(sb, dir, &group, mode);

got_group:
	EXT4_I(dir)->i_last_alloc_group = group;
	err = -ENOSPC;
	if (ret2 == -1)
		goto out;

	/*
	 * Normally we will only go through one pass of this loop,
	 * unless we get unlucky and it turns out the group we selected
	 * had its last inode grabbed by someone else.
	 */
	for (i = 0; i < ngroups; i++, ino = 0) {
		err = -EIO;

		gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
		if (!gdp)
			goto fail;

		brelse(inode_bitmap_bh);
		inode_bitmap_bh = ext4_read_inode_bitmap(sb, group);
		if (!inode_bitmap_bh)
			goto fail;

repeat_in_this_group:
		ino = ext4_find_next_zero_bit((unsigned long *)
					      inode_bitmap_bh->b_data,
					      EXT4_INODES_PER_GROUP(sb), ino);
		if (ino >= EXT4_INODES_PER_GROUP(sb)) {
			if (++group == ngroups)
				group = 0;
			continue;
		}
		if (group == 0 && (ino+1) < EXT4_FIRST_INO(sb)) {
			ext4_error(sb, "reserved inode found cleared - "
				   "inode=%lu", ino + 1);
			continue;
		}
		ext4_lock_group(sb, group);
		ret2 = ext4_test_and_set_bit(ino, inode_bitmap_bh->b_data);
		ext4_unlock_group(sb, group);
		ino++;		/* the inode bitmap is zero-based */
		if (!ret2)
			goto got; /* we grabbed the inode! */
		if (ino < EXT4_INODES_PER_GROUP(sb))
			goto repeat_in_this_group;
	}
	err = -ENOSPC;
	goto out;

got:
	/* We may have to initialize the block bitmap if it isn't already */
	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM) &&
	    gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
		struct buffer_head *block_bitmap_bh;

		block_bitmap_bh = ext4_read_block_bitmap(sb, group);
		BUFFER_TRACE(block_bitmap_bh, "get block bitmap access");
		err = ext4_journal_get_write_access(handle, block_bitmap_bh);
		if (err) {
			brelse(block_bitmap_bh);
			goto fail;
		}

		BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap");
		err = ext4_handle_dirty_metadata(handle, NULL, block_bitmap_bh);
		brelse(block_bitmap_bh);

		/* recheck and clear flag under lock if we still need to */
		ext4_lock_group(sb, group);
		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
			ext4_free_group_clusters_set(sb, gdp,
				ext4_free_clusters_after_init(sb, group, gdp));
			gdp->bg_checksum = ext4_group_desc_csum(sbi, group,
								gdp);
		}
		ext4_unlock_group(sb, group);

		if (err)
			goto fail;
	}

	BUFFER_TRACE(inode_bitmap_bh, "get_write_access");
	err = ext4_journal_get_write_access(handle, inode_bitmap_bh);
	if (err)
		goto fail;

	BUFFER_TRACE(group_desc_bh, "get_write_access");
	err = ext4_journal_get_write_access(handle, group_desc_bh);
	if (err)
		goto fail;

	/* Update the relevant bg descriptor fields */
	if (ext4_has_group_desc_csum(sb)) {
		int free;
		struct ext4_group_info *grp = ext4_get_group_info(sb, group);

		down_read(&grp->alloc_sem); /* protect vs itable lazyinit */
		ext4_lock_group(sb, group); /* while we modify the bg desc */
		free = EXT4_INODES_PER_GROUP(sb) -
			ext4_itable_unused_count(sb, gdp);
		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT);
			free = 0;
		}
		/*
		 * Check the relative inode number against the last used
		 * relative inode number in this group. if it is greater
		 * we need to update the bg_itable_unused count
		 */
		if (ino > free)
			ext4_itable_unused_set(sb, gdp,
					(EXT4_INODES_PER_GROUP(sb) - ino));
		up_read(&grp->alloc_sem);
	}
	ext4_free_inodes_set(sb, gdp, ext4_free_inodes_count(sb, gdp) - 1);
	if (S_ISDIR(mode)) {
		ext4_used_dirs_set(sb, gdp, ext4_used_dirs_count(sb, gdp) + 1);
		if (sbi->s_log_groups_per_flex) {
			ext4_group_t f = ext4_flex_group(sbi, group);

			atomic_inc(&sbi->s_flex_groups[f].used_dirs);
		}
	}
	if (ext4_has_group_desc_csum(sb)) {
		ext4_inode_bitmap_csum_set(sb, group, gdp, inode_bitmap_bh,
					   EXT4_INODES_PER_GROUP(sb) / 8);
		gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
		ext4_unlock_group(sb, group);
	}

	BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata");
	err = ext4_handle_dirty_metadata(handle, NULL, inode_bitmap_bh);
	if (err)
		goto fail;

	BUFFER_TRACE(group_desc_bh, "call ext4_handle_dirty_metadata");
	err = ext4_handle_dirty_metadata(handle, NULL, group_desc_bh);
	if (err)
		goto fail;

	percpu_counter_dec(&sbi->s_freeinodes_counter);
	if (S_ISDIR(mode))
		percpu_counter_inc(&sbi->s_dirs_counter);
	ext4_mark_super_dirty(sb);

	if (sbi->s_log_groups_per_flex) {
		flex_group = ext4_flex_group(sbi, group);
		atomic_dec(&sbi->s_flex_groups[flex_group].free_inodes);
	}
	if (owner) {
		inode->i_mode = mode;
		inode->i_uid = owner[0];
		inode->i_gid = owner[1];
	} else if (test_opt(sb, GRPID)) {
		inode->i_mode = mode;
		inode->i_uid = current_fsuid();
		inode->i_gid = dir->i_gid;
	} else
		inode_init_owner(inode, dir, mode);

	inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb);
	/* This is the optimal IO size (for stat), not the fs block size */
	inode->i_blocks = 0;
	inode->i_mtime = inode->i_atime = inode->i_ctime = ei->i_crtime =
						       ext4_current_time(inode);

	memset(ei->i_data, 0, sizeof(ei->i_data));
	ei->i_dir_start_lookup = 0;
	ei->i_disksize = 0;

	/* Don't inherit extent flag from directory, amongst others. */
	ei->i_flags =
		ext4_mask_flags(mode, EXT4_I(dir)->i_flags & EXT4_FL_INHERITED);
	ei->i_file_acl = 0;
	ei->i_dtime = 0;
	ei->i_block_group = group;
	ei->i_last_alloc_group = ~0;

	ext4_set_inode_flags(inode);
	if (IS_DIRSYNC(inode))
		ext4_handle_sync(handle);
	if (insert_inode_locked(inode) < 0) {
		/*
		 * Likely a bitmap corruption causing inode to be allocated
		 * twice.
		 */
		err = -EIO;
		goto fail;
	}
	spin_lock(&sbi->s_next_gen_lock);
	inode->i_generation = sbi->s_next_generation++;
	spin_unlock(&sbi->s_next_gen_lock);

	/* Precompute checksum seed for inode metadata */
	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
			EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
		__u32 csum;
		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
		__le32 inum = cpu_to_le32(inode->i_ino);
		__le32 gen = cpu_to_le32(inode->i_generation);
		csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&inum,
				   sizeof(inum));
		ei->i_csum_seed = ext4_chksum(sbi, csum, (__u8 *)&gen,
					      sizeof(gen));
	}

	ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */
	ext4_set_inode_state(inode, EXT4_STATE_NEW);

	ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize;

	ret = inode;
	dquot_initialize(inode);
	err = dquot_alloc_inode(inode);
	if (err)
		goto fail_drop;

	err = ext4_init_acl(handle, inode, dir);
	if (err)
		goto fail_free_drop;

	err = ext4_init_security(handle, inode, dir, qstr);
	if (err)
		goto fail_free_drop;

	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
		/* set extent flag only for directory, file and normal symlink*/
		if (S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode)) {
			ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS);
			ext4_ext_tree_init(handle, inode);
		}
	}

	if (ext4_handle_valid(handle)) {
		ei->i_sync_tid = handle->h_transaction->t_tid;
		ei->i_datasync_tid = handle->h_transaction->t_tid;
	}

	err = ext4_mark_inode_dirty(handle, inode);
	if (err) {
		ext4_std_error(sb, err);
		goto fail_free_drop;
	}

	ext4_debug("allocating inode %lu\n", inode->i_ino);
	trace_ext4_allocate_inode(inode, dir, mode);
	goto really_out;
fail:
	ext4_std_error(sb, err);
out:
	iput(inode);
	ret = ERR_PTR(err);
really_out:
	brelse(inode_bitmap_bh);
	return ret;

fail_free_drop:
	dquot_free_inode(inode);

fail_drop:
	dquot_drop(inode);
	inode->i_flags |= S_NOQUOTA;
	clear_nlink(inode);
	unlock_new_inode(inode);
	iput(inode);
	brelse(inode_bitmap_bh);
	return ERR_PTR(err);
}

/* Verify that we are loading a valid orphan from disk */
struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
{
	unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count);
	ext4_group_t block_group;
	int bit;
	struct buffer_head *bitmap_bh;
	struct inode *inode = NULL;
	long err = -EIO;

	/* Error cases - e2fsck has already cleaned up for us */
	if (ino > max_ino) {
		ext4_warning(sb, "bad orphan ino %lu!  e2fsck was run?", ino);
		goto error;
	}

	block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
	bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
	bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
	if (!bitmap_bh) {
		ext4_warning(sb, "inode bitmap error for orphan %lu", ino);
		goto error;
	}

	/* Having the inode bit set should be a 100% indicator that this
	 * is a valid orphan (no e2fsck run on fs).  Orphans also include
	 * inodes that were being truncated, so we can't check i_nlink==0.
	 */
	if (!ext4_test_bit(bit, bitmap_bh->b_data))
		goto bad_orphan;

	inode = ext4_iget(sb, ino);
	if (IS_ERR(inode))
		goto iget_failed;

	/*
	 * If the orphans has i_nlinks > 0 then it should be able to be
	 * truncated, otherwise it won't be removed from the orphan list
	 * during processing and an infinite loop will result.
	 */
	if (inode->i_nlink && !ext4_can_truncate(inode))
		goto bad_orphan;

	if (NEXT_ORPHAN(inode) > max_ino)
		goto bad_orphan;
	brelse(bitmap_bh);
	return inode;

iget_failed:
	err = PTR_ERR(inode);
	inode = NULL;
bad_orphan:
	ext4_warning(sb, "bad orphan inode %lu!  e2fsck was run?", ino);
	printk(KERN_NOTICE "ext4_test_bit(bit=%d, block=%llu) = %d\n",
	       bit, (unsigned long long)bitmap_bh->b_blocknr,
	       ext4_test_bit(bit, bitmap_bh->b_data));
	printk(KERN_NOTICE "inode=%p\n", inode);
	if (inode) {
		printk(KERN_NOTICE "is_bad_inode(inode)=%d\n",
		       is_bad_inode(inode));
		printk(KERN_NOTICE "NEXT_ORPHAN(inode)=%u\n",
		       NEXT_ORPHAN(inode));
		printk(KERN_NOTICE "max_ino=%lu\n", max_ino);
		printk(KERN_NOTICE "i_nlink=%u\n", inode->i_nlink);
		/* Avoid freeing blocks if we got a bad deleted inode */
		if (inode->i_nlink == 0)
			inode->i_blocks = 0;
		iput(inode);
	}
	brelse(bitmap_bh);
error:
	return ERR_PTR(err);
}

unsigned long ext4_count_free_inodes(struct super_block *sb)
{
	unsigned long desc_count;
	struct ext4_group_desc *gdp;
	ext4_group_t i, ngroups = ext4_get_groups_count(sb);
#ifdef EXT4FS_DEBUG
	struct ext4_super_block *es;
	unsigned long bitmap_count, x;
	struct buffer_head *bitmap_bh = NULL;

	es = EXT4_SB(sb)->s_es;
	desc_count = 0;
	bitmap_count = 0;
	gdp = NULL;
	for (i = 0; i < ngroups; i++) {
		gdp = ext4_get_group_desc(sb, i, NULL);
		if (!gdp)
			continue;
		desc_count += ext4_free_inodes_count(sb, gdp);
		brelse(bitmap_bh);
		bitmap_bh = ext4_read_inode_bitmap(sb, i);
		if (!bitmap_bh)
			continue;

		x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8);
		printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n",
			(unsigned long) i, ext4_free_inodes_count(sb, gdp), x);
		bitmap_count += x;
	}
	brelse(bitmap_bh);
	printk(KERN_DEBUG "ext4_count_free_inodes: "
	       "stored = %u, computed = %lu, %lu\n",
	       le32_to_cpu(es->s_free_inodes_count), desc_count, bitmap_count);
	return desc_count;
#else
	desc_count = 0;
	for (i = 0; i < ngroups; i++) {
		gdp = ext4_get_group_desc(sb, i, NULL);
		if (!gdp)
			continue;
		desc_count += ext4_free_inodes_count(sb, gdp);
		cond_resched();
	}
	return desc_count;
#endif
}

/* Called at mount-time, super-block is locked */
unsigned long ext4_count_dirs(struct super_block * sb)
{
	unsigned long count = 0;
	ext4_group_t i, ngroups = ext4_get_groups_count(sb);

	for (i = 0; i < ngroups; i++) {
		struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL);
		if (!gdp)
			continue;
		count += ext4_used_dirs_count(sb, gdp);
	}
	return count;
}

/*
 * Zeroes not yet zeroed inode table - just write zeroes through the whole
 * inode table. Must be called without any spinlock held. The only place
 * where it is called from on active part of filesystem is ext4lazyinit
 * thread, so we do not need any special locks, however we have to prevent
 * inode allocation from the current group, so we take alloc_sem lock, to
 * block ext4_new_inode() until we are finished.
 */
int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
				 int barrier)
{
	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct ext4_group_desc *gdp = NULL;
	struct buffer_head *group_desc_bh;
	handle_t *handle;
	ext4_fsblk_t blk;
	int num, ret = 0, used_blks = 0;

	/* This should not happen, but just to be sure check this */
	if (sb->s_flags & MS_RDONLY) {
		ret = 1;
		goto out;
	}

	gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
	if (!gdp)
		goto out;

	/*
	 * We do not need to lock this, because we are the only one
	 * handling this flag.
	 */
	if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))
		goto out;

	handle = ext4_journal_start_sb(sb, 1);
	if (IS_ERR(handle)) {
		ret = PTR_ERR(handle);
		goto out;
	}

	down_write(&grp->alloc_sem);
	/*
	 * If inode bitmap was already initialized there may be some
	 * used inodes so we need to skip blocks with used inodes in
	 * inode table.
	 */
	if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)))
		used_blks = DIV_ROUND_UP((EXT4_INODES_PER_GROUP(sb) -
			    ext4_itable_unused_count(sb, gdp)),
			    sbi->s_inodes_per_block);

	if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group)) {
		ext4_error(sb, "Something is wrong with group %u: "
			   "used itable blocks: %d; "
			   "itable unused count: %u",
			   group, used_blks,
			   ext4_itable_unused_count(sb, gdp));
		ret = 1;
		goto err_out;
	}

	blk = ext4_inode_table(sb, gdp) + used_blks;
	num = sbi->s_itb_per_group - used_blks;

	BUFFER_TRACE(group_desc_bh, "get_write_access");
	ret = ext4_journal_get_write_access(handle,
					    group_desc_bh);
	if (ret)
		goto err_out;

	/*
	 * Skip zeroout if the inode table is full. But we set the ZEROED
	 * flag anyway, because obviously, when it is full it does not need
	 * further zeroing.
	 */
	if (unlikely(num == 0))
		goto skip_zeroout;

	ext4_debug("going to zero out inode table in group %d\n",
		   group);
	ret = sb_issue_zeroout(sb, blk, num, GFP_NOFS);
	if (ret < 0)
		goto err_out;
	if (barrier)
		blkdev_issue_flush(sb->s_bdev, GFP_NOFS, NULL);

skip_zeroout:
	ext4_lock_group(sb, group);
	gdp->bg_flags |= cpu_to_le16(EXT4_BG_INODE_ZEROED);
	gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
	ext4_unlock_group(sb, group);

	BUFFER_TRACE(group_desc_bh,
		     "call ext4_handle_dirty_metadata");
	ret = ext4_handle_dirty_metadata(handle, NULL,
					 group_desc_bh);

err_out:
	up_write(&grp->alloc_sem);
	ext4_journal_stop(handle);
out:
	return ret;
}