summaryrefslogtreecommitdiff
path: root/fs/ext4/balloc.c
blob: 9dc6e74b265c80e7b92a847d61c95a84fa9e2fcd (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
// SPDX-License-Identifier: GPL-2.0
/*
 *  linux/fs/ext4/balloc.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)
 *
 *  Enhanced block 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/capability.h>
#include <linux/fs.h>
#include <linux/quotaops.h>
#include <linux/buffer_head.h>
#include "ext4.h"
#include "ext4_jbd2.h"
#include "mballoc.h"

#include <trace/events/ext4.h>

static unsigned ext4_num_base_meta_clusters(struct super_block *sb,
					    ext4_group_t block_group);
/*
 * balloc.c contains the blocks allocation and deallocation routines
 */

/*
 * Calculate block group number for a given block number
 */
ext4_group_t ext4_get_group_number(struct super_block *sb,
				   ext4_fsblk_t block)
{
	ext4_group_t group;

	if (test_opt2(sb, STD_GROUP_SIZE))
		group = (block -
			 le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) >>
			(EXT4_BLOCK_SIZE_BITS(sb) + EXT4_CLUSTER_BITS(sb) + 3);
	else
		ext4_get_group_no_and_offset(sb, block, &group, NULL);
	return group;
}

/*
 * Calculate the block group number and offset into the block/cluster
 * allocation bitmap, given a block number
 */
void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
		ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp)
{
	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
	ext4_grpblk_t offset;

	blocknr = blocknr - le32_to_cpu(es->s_first_data_block);
	offset = do_div(blocknr, EXT4_BLOCKS_PER_GROUP(sb)) >>
		EXT4_SB(sb)->s_cluster_bits;
	if (offsetp)
		*offsetp = offset;
	if (blockgrpp)
		*blockgrpp = blocknr;

}

/*
 * Check whether the 'block' lives within the 'block_group'. Returns 1 if so
 * and 0 otherwise.
 */
static inline int ext4_block_in_group(struct super_block *sb,
				      ext4_fsblk_t block,
				      ext4_group_t block_group)
{
	ext4_group_t actual_group;

	actual_group = ext4_get_group_number(sb, block);
	return (actual_group == block_group) ? 1 : 0;
}

/* Return the number of clusters used for file system metadata; this
 * represents the overhead needed by the file system.
 */
static unsigned ext4_num_overhead_clusters(struct super_block *sb,
					   ext4_group_t block_group,
					   struct ext4_group_desc *gdp)
{
	unsigned num_clusters;
	int block_cluster = -1, inode_cluster = -1, itbl_cluster = -1, i, c;
	ext4_fsblk_t start = ext4_group_first_block_no(sb, block_group);
	ext4_fsblk_t itbl_blk;
	struct ext4_sb_info *sbi = EXT4_SB(sb);

	/* This is the number of clusters used by the superblock,
	 * block group descriptors, and reserved block group
	 * descriptor blocks */
	num_clusters = ext4_num_base_meta_clusters(sb, block_group);

	/*
	 * For the allocation bitmaps and inode table, we first need
	 * to check to see if the block is in the block group.  If it
	 * is, then check to see if the cluster is already accounted
	 * for in the clusters used for the base metadata cluster, or
	 * if we can increment the base metadata cluster to include
	 * that block.  Otherwise, we will have to track the cluster
	 * used for the allocation bitmap or inode table explicitly.
	 * Normally all of these blocks are contiguous, so the special
	 * case handling shouldn't be necessary except for *very*
	 * unusual file system layouts.
	 */
	if (ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp), block_group)) {
		block_cluster = EXT4_B2C(sbi,
					 ext4_block_bitmap(sb, gdp) - start);
		if (block_cluster < num_clusters)
			block_cluster = -1;
		else if (block_cluster == num_clusters) {
			num_clusters++;
			block_cluster = -1;
		}
	}

	if (ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp), block_group)) {
		inode_cluster = EXT4_B2C(sbi,
					 ext4_inode_bitmap(sb, gdp) - start);
		if (inode_cluster < num_clusters)
			inode_cluster = -1;
		else if (inode_cluster == num_clusters) {
			num_clusters++;
			inode_cluster = -1;
		}
	}

	itbl_blk = ext4_inode_table(sb, gdp);
	for (i = 0; i < sbi->s_itb_per_group; i++) {
		if (ext4_block_in_group(sb, itbl_blk + i, block_group)) {
			c = EXT4_B2C(sbi, itbl_blk + i - start);
			if ((c < num_clusters) || (c == inode_cluster) ||
			    (c == block_cluster) || (c == itbl_cluster))
				continue;
			if (c == num_clusters) {
				num_clusters++;
				continue;
			}
			num_clusters++;
			itbl_cluster = c;
		}
	}

	if (block_cluster != -1)
		num_clusters++;
	if (inode_cluster != -1)
		num_clusters++;

	return num_clusters;
}

static unsigned int num_clusters_in_group(struct super_block *sb,
					  ext4_group_t block_group)
{
	unsigned int blocks;

	if (block_group == ext4_get_groups_count(sb) - 1) {
		/*
		 * Even though mke2fs always initializes the first and
		 * last group, just in case some other tool was used,
		 * we need to make sure we calculate the right free
		 * blocks.
		 */
		blocks = ext4_blocks_count(EXT4_SB(sb)->s_es) -
			ext4_group_first_block_no(sb, block_group);
	} else
		blocks = EXT4_BLOCKS_PER_GROUP(sb);
	return EXT4_NUM_B2C(EXT4_SB(sb), blocks);
}

/* Initializes an uninitialized block bitmap */
static int ext4_init_block_bitmap(struct super_block *sb,
				   struct buffer_head *bh,
				   ext4_group_t block_group,
				   struct ext4_group_desc *gdp)
{
	unsigned int bit, bit_max;
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	ext4_fsblk_t start, tmp;

	ASSERT(buffer_locked(bh));

	/* If checksum is bad mark all blocks used to prevent allocation
	 * essentially implementing a per-group read-only flag. */
	if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
		ext4_mark_group_bitmap_corrupted(sb, block_group,
					EXT4_GROUP_INFO_BBITMAP_CORRUPT |
					EXT4_GROUP_INFO_IBITMAP_CORRUPT);
		return -EFSBADCRC;
	}
	memset(bh->b_data, 0, sb->s_blocksize);

	bit_max = ext4_num_base_meta_clusters(sb, block_group);
	if ((bit_max >> 3) >= bh->b_size)
		return -EFSCORRUPTED;

	for (bit = 0; bit < bit_max; bit++)
		ext4_set_bit(bit, bh->b_data);

	start = ext4_group_first_block_no(sb, block_group);

	/* Set bits for block and inode bitmaps, and inode table */
	tmp = ext4_block_bitmap(sb, gdp);
	if (ext4_block_in_group(sb, tmp, block_group))
		ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);

	tmp = ext4_inode_bitmap(sb, gdp);
	if (ext4_block_in_group(sb, tmp, block_group))
		ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);

	tmp = ext4_inode_table(sb, gdp);
	for (; tmp < ext4_inode_table(sb, gdp) +
		     sbi->s_itb_per_group; tmp++) {
		if (ext4_block_in_group(sb, tmp, block_group))
			ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
	}

	/*
	 * Also if the number of blocks within the group is less than
	 * the blocksize * 8 ( which is the size of bitmap ), set rest
	 * of the block bitmap to 1
	 */
	ext4_mark_bitmap_end(num_clusters_in_group(sb, block_group),
			     sb->s_blocksize * 8, bh->b_data);
	return 0;
}

/* Return the number of free blocks in a block group.  It is used when
 * the block bitmap is uninitialized, so we can't just count the bits
 * in the bitmap. */
unsigned ext4_free_clusters_after_init(struct super_block *sb,
				       ext4_group_t block_group,
				       struct ext4_group_desc *gdp)
{
	return num_clusters_in_group(sb, block_group) -
		ext4_num_overhead_clusters(sb, block_group, gdp);
}

/*
 * The free blocks 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.  The descriptors are loaded in memory
 * when a file system is mounted (see ext4_fill_super).
 */

/**
 * ext4_get_group_desc() -- load group descriptor from disk
 * @sb:			super block
 * @block_group:	given block group
 * @bh:			pointer to the buffer head to store the block
 *			group descriptor
 */
struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
					     ext4_group_t block_group,
					     struct buffer_head **bh)
{
	unsigned int group_desc;
	unsigned int offset;
	ext4_group_t ngroups = ext4_get_groups_count(sb);
	struct ext4_group_desc *desc;
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct buffer_head *bh_p;

	if (block_group >= ngroups) {
		ext4_error(sb, "block_group >= groups_count - block_group = %u,"
			   " groups_count = %u", block_group, ngroups);

		return NULL;
	}

	group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb);
	offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1);
	bh_p = sbi_array_rcu_deref(sbi, s_group_desc, group_desc);
	/*
	 * sbi_array_rcu_deref returns with rcu unlocked, this is ok since
	 * the pointer being dereferenced won't be dereferenced again. By
	 * looking at the usage in add_new_gdb() the value isn't modified,
	 * just the pointer, and so it remains valid.
	 */
	if (!bh_p) {
		ext4_error(sb, "Group descriptor not loaded - "
			   "block_group = %u, group_desc = %u, desc = %u",
			   block_group, group_desc, offset);
		return NULL;
	}

	desc = (struct ext4_group_desc *)(
		(__u8 *)bh_p->b_data +
		offset * EXT4_DESC_SIZE(sb));
	if (bh)
		*bh = bh_p;
	return desc;
}

/*
 * Return the block number which was discovered to be invalid, or 0 if
 * the block bitmap is valid.
 */
static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
					    struct ext4_group_desc *desc,
					    ext4_group_t block_group,
					    struct buffer_head *bh)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	ext4_grpblk_t offset;
	ext4_grpblk_t next_zero_bit;
	ext4_grpblk_t max_bit = EXT4_CLUSTERS_PER_GROUP(sb);
	ext4_fsblk_t blk;
	ext4_fsblk_t group_first_block;

	if (ext4_has_feature_flex_bg(sb)) {
		/* with FLEX_BG, the inode/block bitmaps and itable
		 * blocks may not be in the group at all
		 * so the bitmap validation will be skipped for those groups
		 * or it has to also read the block group where the bitmaps
		 * are located to verify they are set.
		 */
		return 0;
	}
	group_first_block = ext4_group_first_block_no(sb, block_group);

	/* check whether block bitmap block number is set */
	blk = ext4_block_bitmap(sb, desc);
	offset = blk - group_first_block;
	if (offset < 0 || EXT4_B2C(sbi, offset) >= max_bit ||
	    !ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data))
		/* bad block bitmap */
		return blk;

	/* check whether the inode bitmap block number is set */
	blk = ext4_inode_bitmap(sb, desc);
	offset = blk - group_first_block;
	if (offset < 0 || EXT4_B2C(sbi, offset) >= max_bit ||
	    !ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data))
		/* bad block bitmap */
		return blk;

	/* check whether the inode table block number is set */
	blk = ext4_inode_table(sb, desc);
	offset = blk - group_first_block;
	if (offset < 0 || EXT4_B2C(sbi, offset) >= max_bit ||
	    EXT4_B2C(sbi, offset + sbi->s_itb_per_group) >= max_bit)
		return blk;
	next_zero_bit = ext4_find_next_zero_bit(bh->b_data,
			EXT4_B2C(sbi, offset + sbi->s_itb_per_group),
			EXT4_B2C(sbi, offset));
	if (next_zero_bit <
	    EXT4_B2C(sbi, offset + sbi->s_itb_per_group))
		/* bad bitmap for inode tables */
		return blk;
	return 0;
}

static int ext4_validate_block_bitmap(struct super_block *sb,
				      struct ext4_group_desc *desc,
				      ext4_group_t block_group,
				      struct buffer_head *bh)
{
	ext4_fsblk_t	blk;
	struct ext4_group_info *grp;

	if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)
		return 0;

	grp = ext4_get_group_info(sb, block_group);

	if (buffer_verified(bh))
		return 0;
	if (EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
		return -EFSCORRUPTED;

	ext4_lock_group(sb, block_group);
	if (buffer_verified(bh))
		goto verified;
	if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group,
						    desc, bh) ||
		     ext4_simulate_fail(sb, EXT4_SIM_BBITMAP_CRC))) {
		ext4_unlock_group(sb, block_group);
		ext4_error(sb, "bg %u: bad block bitmap checksum", block_group);
		ext4_mark_group_bitmap_corrupted(sb, block_group,
					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
		return -EFSBADCRC;
	}
	blk = ext4_valid_block_bitmap(sb, desc, block_group, bh);
	if (unlikely(blk != 0)) {
		ext4_unlock_group(sb, block_group);
		ext4_error(sb, "bg %u: block %llu: invalid block bitmap",
			   block_group, blk);
		ext4_mark_group_bitmap_corrupted(sb, block_group,
					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
		return -EFSCORRUPTED;
	}
	set_buffer_verified(bh);
verified:
	ext4_unlock_group(sb, block_group);
	return 0;
}

/**
 * ext4_read_block_bitmap_nowait()
 * @sb:			super block
 * @block_group:	given block group
 *
 * Read the bitmap for a given block_group,and validate the
 * bits for block/inode/inode tables are set in the bitmaps
 *
 * Return buffer_head on success or an ERR_PTR in case of failure.
 */
struct buffer_head *
ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group,
			      bool ignore_locked)
{
	struct ext4_group_desc *desc;
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	struct buffer_head *bh;
	ext4_fsblk_t bitmap_blk;
	int err;

	desc = ext4_get_group_desc(sb, block_group, NULL);
	if (!desc)
		return ERR_PTR(-EFSCORRUPTED);
	bitmap_blk = ext4_block_bitmap(sb, desc);
	if ((bitmap_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||
	    (bitmap_blk >= ext4_blocks_count(sbi->s_es))) {
		ext4_error(sb, "Invalid block bitmap block %llu in "
			   "block_group %u", bitmap_blk, block_group);
		ext4_mark_group_bitmap_corrupted(sb, block_group,
					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
		return ERR_PTR(-EFSCORRUPTED);
	}
	bh = sb_getblk(sb, bitmap_blk);
	if (unlikely(!bh)) {
		ext4_warning(sb, "Cannot get buffer for block bitmap - "
			     "block_group = %u, block_bitmap = %llu",
			     block_group, bitmap_blk);
		return ERR_PTR(-ENOMEM);
	}

	if (ignore_locked && buffer_locked(bh)) {
		/* buffer under IO already, return if called for prefetching */
		put_bh(bh);
		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 (ext4_has_group_desc_csum(sb) &&
	    (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
		if (block_group == 0) {
			ext4_unlock_group(sb, block_group);
			unlock_buffer(bh);
			ext4_error(sb, "Block bitmap for bg 0 marked "
				   "uninitialized");
			err = -EFSCORRUPTED;
			goto out;
		}
		err = ext4_init_block_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);
		if (err) {
			ext4_error(sb, "Failed to init block bitmap for group "
				   "%u: %d", block_group, err);
			goto out;
		}
		goto verify;
	}
	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
	 */
	set_buffer_new(bh);
	trace_ext4_read_block_bitmap_load(sb, block_group, ignore_locked);
	ext4_read_bh_nowait(bh, REQ_META | REQ_PRIO |
			    (ignore_locked ? REQ_RAHEAD : 0),
			    ext4_end_bitmap_read);
	return bh;
verify:
	err = ext4_validate_block_bitmap(sb, desc, block_group, bh);
	if (err)
		goto out;
	return bh;
out:
	put_bh(bh);
	return ERR_PTR(err);
}

/* Returns 0 on success, -errno on error */
int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group,
			   struct buffer_head *bh)
{
	struct ext4_group_desc *desc;

	if (!buffer_new(bh))
		return 0;
	desc = ext4_get_group_desc(sb, block_group, NULL);
	if (!desc)
		return -EFSCORRUPTED;
	wait_on_buffer(bh);
	ext4_simulate_fail_bh(sb, bh, EXT4_SIM_BBITMAP_EIO);
	if (!buffer_uptodate(bh)) {
		ext4_error_err(sb, EIO, "Cannot read block bitmap - "
			       "block_group = %u, block_bitmap = %llu",
			       block_group, (unsigned long long) bh->b_blocknr);
		ext4_mark_group_bitmap_corrupted(sb, block_group,
					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
		return -EIO;
	}
	clear_buffer_new(bh);
	/* Panic or remount fs read-only if block bitmap is invalid */
	return ext4_validate_block_bitmap(sb, desc, block_group, bh);
}

struct buffer_head *
ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
{
	struct buffer_head *bh;
	int err;

	bh = ext4_read_block_bitmap_nowait(sb, block_group, false);
	if (IS_ERR(bh))
		return bh;
	err = ext4_wait_block_bitmap(sb, block_group, bh);
	if (err) {
		put_bh(bh);
		return ERR_PTR(err);
	}
	return bh;
}

/**
 * ext4_has_free_clusters()
 * @sbi:	in-core super block structure.
 * @nclusters:	number of needed blocks
 * @flags:	flags from ext4_mb_new_blocks()
 *
 * Check if filesystem has nclusters free & available for allocation.
 * On success return 1, return 0 on failure.
 */
static int ext4_has_free_clusters(struct ext4_sb_info *sbi,
				  s64 nclusters, unsigned int flags)
{
	s64 free_clusters, dirty_clusters, rsv, resv_clusters;
	struct percpu_counter *fcc = &sbi->s_freeclusters_counter;
	struct percpu_counter *dcc = &sbi->s_dirtyclusters_counter;

	free_clusters  = percpu_counter_read_positive(fcc);
	dirty_clusters = percpu_counter_read_positive(dcc);
	resv_clusters = atomic64_read(&sbi->s_resv_clusters);

	/*
	 * r_blocks_count should always be multiple of the cluster ratio so
	 * we are safe to do a plane bit shift only.
	 */
	rsv = (ext4_r_blocks_count(sbi->s_es) >> sbi->s_cluster_bits) +
	      resv_clusters;

	if (free_clusters - (nclusters + rsv + dirty_clusters) <
					EXT4_FREECLUSTERS_WATERMARK) {
		free_clusters  = percpu_counter_sum_positive(fcc);
		dirty_clusters = percpu_counter_sum_positive(dcc);
	}
	/* Check whether we have space after accounting for current
	 * dirty clusters & root reserved clusters.
	 */
	if (free_clusters >= (rsv + nclusters + dirty_clusters))
		return 1;

	/* Hm, nope.  Are (enough) root reserved clusters available? */
	if (uid_eq(sbi->s_resuid, current_fsuid()) ||
	    (!gid_eq(sbi->s_resgid, GLOBAL_ROOT_GID) && in_group_p(sbi->s_resgid)) ||
	    capable(CAP_SYS_RESOURCE) ||
	    (flags & EXT4_MB_USE_ROOT_BLOCKS)) {

		if (free_clusters >= (nclusters + dirty_clusters +
				      resv_clusters))
			return 1;
	}
	/* No free blocks. Let's see if we can dip into reserved pool */
	if (flags & EXT4_MB_USE_RESERVED) {
		if (free_clusters >= (nclusters + dirty_clusters))
			return 1;
	}

	return 0;
}

int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
			     s64 nclusters, unsigned int flags)
{
	if (ext4_has_free_clusters(sbi, nclusters, flags)) {
		percpu_counter_add(&sbi->s_dirtyclusters_counter, nclusters);
		return 0;
	} else
		return -ENOSPC;
}

/**
 * ext4_should_retry_alloc() - check if a block allocation should be retried
 * @sb:			superblock
 * @retries:		number of retry attempts made so far
 *
 * ext4_should_retry_alloc() is called when ENOSPC is returned while
 * attempting to allocate blocks.  If there's an indication that a pending
 * journal transaction might free some space and allow another attempt to
 * succeed, this function will wait for the current or committing transaction
 * to complete and then return TRUE.
 */
int ext4_should_retry_alloc(struct super_block *sb, int *retries)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);

	if (!sbi->s_journal)
		return 0;

	if (++(*retries) > 3) {
		percpu_counter_inc(&sbi->s_sra_exceeded_retry_limit);
		return 0;
	}

	/*
	 * if there's no indication that blocks are about to be freed it's
	 * possible we just missed a transaction commit that did so
	 */
	smp_mb();
	if (sbi->s_mb_free_pending == 0)
		return ext4_has_free_clusters(sbi, 1, 0);

	/*
	 * it's possible we've just missed a transaction commit here,
	 * so ignore the returned status
	 */
	jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id);
	(void) jbd2_journal_force_commit_nested(sbi->s_journal);
	return 1;
}

/*
 * ext4_new_meta_blocks() -- allocate block for meta data (indexing) blocks
 *
 * @handle:             handle to this transaction
 * @inode:              file inode
 * @goal:               given target block(filesystem wide)
 * @count:		pointer to total number of clusters needed
 * @errp:               error code
 *
 * Return 1st allocated block number on success, *count stores total account
 * error stores in errp pointer
 */
ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
				  ext4_fsblk_t goal, unsigned int flags,
				  unsigned long *count, int *errp)
{
	struct ext4_allocation_request ar;
	ext4_fsblk_t ret;

	memset(&ar, 0, sizeof(ar));
	/* Fill with neighbour allocated blocks */
	ar.inode = inode;
	ar.goal = goal;
	ar.len = count ? *count : 1;
	ar.flags = flags;

	ret = ext4_mb_new_blocks(handle, &ar, errp);
	if (count)
		*count = ar.len;
	/*
	 * Account for the allocated meta blocks.  We will never
	 * fail EDQUOT for metdata, but we do account for it.
	 */
	if (!(*errp) && (flags & EXT4_MB_DELALLOC_RESERVED)) {
		dquot_alloc_block_nofail(inode,
				EXT4_C2B(EXT4_SB(inode->i_sb), ar.len));
	}
	return ret;
}

/**
 * ext4_count_free_clusters() -- count filesystem free clusters
 * @sb:		superblock
 *
 * Adds up the number of free clusters from each block group.
 */
ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb)
{
	ext4_fsblk_t desc_count;
	struct ext4_group_desc *gdp;
	ext4_group_t i;
	ext4_group_t ngroups = ext4_get_groups_count(sb);
	struct ext4_group_info *grp;
#ifdef EXT4FS_DEBUG
	struct ext4_super_block *es;
	ext4_fsblk_t bitmap_count;
	unsigned int 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;
		grp = NULL;
		if (EXT4_SB(sb)->s_group_info)
			grp = ext4_get_group_info(sb, i);
		if (!grp || !EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
			desc_count += ext4_free_group_clusters(sb, gdp);
		brelse(bitmap_bh);
		bitmap_bh = ext4_read_block_bitmap(sb, i);
		if (IS_ERR(bitmap_bh)) {
			bitmap_bh = NULL;
			continue;
		}

		x = ext4_count_free(bitmap_bh->b_data,
				    EXT4_CLUSTERS_PER_GROUP(sb) / 8);
		printk(KERN_DEBUG "group %u: stored = %d, counted = %u\n",
			i, ext4_free_group_clusters(sb, gdp), x);
		bitmap_count += x;
	}
	brelse(bitmap_bh);
	printk(KERN_DEBUG "ext4_count_free_clusters: stored = %llu"
	       ", computed = %llu, %llu\n",
	       EXT4_NUM_B2C(EXT4_SB(sb), ext4_free_blocks_count(es)),
	       desc_count, bitmap_count);
	return bitmap_count;
#else
	desc_count = 0;
	for (i = 0; i < ngroups; i++) {
		gdp = ext4_get_group_desc(sb, i, NULL);
		if (!gdp)
			continue;
		grp = NULL;
		if (EXT4_SB(sb)->s_group_info)
			grp = ext4_get_group_info(sb, i);
		if (!grp || !EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
			desc_count += ext4_free_group_clusters(sb, gdp);
	}

	return desc_count;
#endif
}

static inline int test_root(ext4_group_t a, int b)
{
	while (1) {
		if (a < b)
			return 0;
		if (a == b)
			return 1;
		if ((a % b) != 0)
			return 0;
		a = a / b;
	}
}

/**
 *	ext4_bg_has_super - number of blocks used by the superblock in group
 *	@sb: superblock for filesystem
 *	@group: group number to check
 *
 *	Return the number of blocks used by the superblock (primary or backup)
 *	in this group.  Currently this will be only 0 or 1.
 */
int ext4_bg_has_super(struct super_block *sb, ext4_group_t group)
{
	struct ext4_super_block *es = EXT4_SB(sb)->s_es;

	if (group == 0)
		return 1;
	if (ext4_has_feature_sparse_super2(sb)) {
		if (group == le32_to_cpu(es->s_backup_bgs[0]) ||
		    group == le32_to_cpu(es->s_backup_bgs[1]))
			return 1;
		return 0;
	}
	if ((group <= 1) || !ext4_has_feature_sparse_super(sb))
		return 1;
	if (!(group & 1))
		return 0;
	if (test_root(group, 3) || (test_root(group, 5)) ||
	    test_root(group, 7))
		return 1;

	return 0;
}

static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb,
					ext4_group_t group)
{
	unsigned long metagroup = group / EXT4_DESC_PER_BLOCK(sb);
	ext4_group_t first = metagroup * EXT4_DESC_PER_BLOCK(sb);
	ext4_group_t last = first + EXT4_DESC_PER_BLOCK(sb) - 1;

	if (group == first || group == first + 1 || group == last)
		return 1;
	return 0;
}

static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb,
					ext4_group_t group)
{
	if (!ext4_bg_has_super(sb, group))
		return 0;

	if (ext4_has_feature_meta_bg(sb))
		return le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg);
	else
		return EXT4_SB(sb)->s_gdb_count;
}

/**
 *	ext4_bg_num_gdb - number of blocks used by the group table in group
 *	@sb: superblock for filesystem
 *	@group: group number to check
 *
 *	Return the number of blocks used by the group descriptor table
 *	(primary or backup) in this group.  In the future there may be a
 *	different number of descriptor blocks in each group.
 */
unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group)
{
	unsigned long first_meta_bg =
			le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg);
	unsigned long metagroup = group / EXT4_DESC_PER_BLOCK(sb);

	if (!ext4_has_feature_meta_bg(sb) || metagroup < first_meta_bg)
		return ext4_bg_num_gdb_nometa(sb, group);

	return ext4_bg_num_gdb_meta(sb,group);

}

/*
 * This function returns the number of file system metadata clusters at
 * the beginning of a block group, including the reserved gdt blocks.
 */
static unsigned ext4_num_base_meta_clusters(struct super_block *sb,
				     ext4_group_t block_group)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	unsigned num;

	/* Check for superblock and gdt backups in this group */
	num = ext4_bg_has_super(sb, block_group);

	if (!ext4_has_feature_meta_bg(sb) ||
	    block_group < le32_to_cpu(sbi->s_es->s_first_meta_bg) *
			  sbi->s_desc_per_block) {
		if (num) {
			num += ext4_bg_num_gdb(sb, block_group);
			num += le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks);
		}
	} else { /* For META_BG_BLOCK_GROUPS */
		num += ext4_bg_num_gdb(sb, block_group);
	}
	return EXT4_NUM_B2C(sbi, num);
}
/**
 *	ext4_inode_to_goal_block - return a hint for block allocation
 *	@inode: inode for block allocation
 *
 *	Return the ideal location to start allocating blocks for a
 *	newly created inode.
 */
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *inode)
{
	struct ext4_inode_info *ei = EXT4_I(inode);
	ext4_group_t block_group;
	ext4_grpblk_t colour;
	int flex_size = ext4_flex_bg_size(EXT4_SB(inode->i_sb));
	ext4_fsblk_t bg_start;
	ext4_fsblk_t last_block;

	block_group = ei->i_block_group;
	if (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) {
		/*
		 * If there are at least EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME
		 * block groups per flexgroup, reserve the first block
		 * group for directories and special files.  Regular
		 * files will start at the second block group.  This
		 * tends to speed up directory access and improves
		 * fsck times.
		 */
		block_group &= ~(flex_size-1);
		if (S_ISREG(inode->i_mode))
			block_group++;
	}
	bg_start = ext4_group_first_block_no(inode->i_sb, block_group);
	last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1;

	/*
	 * If we are doing delayed allocation, we don't need take
	 * colour into account.
	 */
	if (test_opt(inode->i_sb, DELALLOC))
		return bg_start;

	if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block)
		colour = (task_pid_nr(current) % 16) *
			(EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
	else
		colour = (task_pid_nr(current) % 16) *
			((last_block - bg_start) / 16);
	return bg_start + colour;
}