forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
balloc.c
2042 lines (1853 loc) · 59.2 KB
/
balloc.c
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
/*
* linux/fs/ext4/balloc.c
*
* Copyright (C) 1992, 1993, 1994, 1995
* Remy Card ([email protected])
* Laboratoire MASI - Institut Blaise Pascal
* Universite Pierre et Marie Curie (Paris VI)
*
* Enhanced block allocation by Stephen Tweedie ([email protected]), 1993
* Big-endian to little-endian byte-swapping/bitmaps by
* David S. Miller ([email protected]), 1995
*/
#include <linux/time.h>
#include <linux/capability.h>
#include <linux/fs.h>
#include <linux/jbd2.h>
#include <linux/ext4_fs.h>
#include <linux/ext4_jbd2.h>
#include <linux/quotaops.h>
#include <linux/buffer_head.h>
#include "group.h"
/*
* balloc.c contains the blocks allocation and deallocation routines
*/
/*
* Calculate the block group number and offset, 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));
if (offsetp)
*offsetp = offset;
if (blockgrpp)
*blockgrpp = blocknr;
}
/* Initializes an uninitialized block bitmap if given, and returns the
* number of blocks free in the group. */
unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
ext4_group_t block_group, struct ext4_group_desc *gdp)
{
unsigned long start;
int bit, bit_max;
unsigned free_blocks, group_blocks;
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (bh) {
J_ASSERT_BH(bh, 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(sbi, block_group, gdp)) {
ext4_error(sb, __FUNCTION__,
"Checksum bad for group %lu\n", block_group);
gdp->bg_free_blocks_count = 0;
gdp->bg_free_inodes_count = 0;
gdp->bg_itable_unused = 0;
memset(bh->b_data, 0xff, sb->s_blocksize);
return 0;
}
memset(bh->b_data, 0, sb->s_blocksize);
}
/* Check for superblock and gdt backups in this group */
bit_max = ext4_bg_has_super(sb, block_group);
if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) ||
block_group < le32_to_cpu(sbi->s_es->s_first_meta_bg) *
sbi->s_desc_per_block) {
if (bit_max) {
bit_max += ext4_bg_num_gdb(sb, block_group);
bit_max +=
le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks);
}
} else { /* For META_BG_BLOCK_GROUPS */
int group_rel = (block_group -
le32_to_cpu(sbi->s_es->s_first_meta_bg)) %
EXT4_DESC_PER_BLOCK(sb);
if (group_rel == 0 || group_rel == 1 ||
(group_rel == EXT4_DESC_PER_BLOCK(sb) - 1))
bit_max += 1;
}
if (block_group == sbi->s_groups_count - 1) {
/*
* Even though mke2fs always initialize first and last group
* if some other tool enabled the EXT4_BG_BLOCK_UNINIT we need
* to make sure we calculate the right free blocks
*/
group_blocks = ext4_blocks_count(sbi->s_es) -
le32_to_cpu(sbi->s_es->s_first_data_block) -
(EXT4_BLOCKS_PER_GROUP(sb) * (sbi->s_groups_count -1));
} else {
group_blocks = EXT4_BLOCKS_PER_GROUP(sb);
}
free_blocks = group_blocks - bit_max;
if (bh) {
for (bit = 0; bit < bit_max; bit++)
ext4_set_bit(bit, bh->b_data);
start = block_group * EXT4_BLOCKS_PER_GROUP(sb) +
le32_to_cpu(sbi->s_es->s_first_data_block);
/* Set bits for block and inode bitmaps, and inode table */
ext4_set_bit(ext4_block_bitmap(sb, gdp) - start, bh->b_data);
ext4_set_bit(ext4_inode_bitmap(sb, gdp) - start, bh->b_data);
for (bit = (ext4_inode_table(sb, gdp) - start),
bit_max = bit + sbi->s_itb_per_group; bit < bit_max; bit++)
ext4_set_bit(bit, 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
*/
mark_bitmap_end(group_blocks, sb->s_blocksize * 8, bh->b_data);
}
return free_blocks - sbi->s_itb_per_group - 2;
}
/*
* 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).
*/
#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1)
/**
* 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 long group_desc;
unsigned long offset;
struct ext4_group_desc * desc;
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (block_group >= sbi->s_groups_count) {
ext4_error (sb, "ext4_get_group_desc",
"block_group >= groups_count - "
"block_group = %lu, groups_count = %lu",
block_group, sbi->s_groups_count);
return NULL;
}
smp_rmb();
group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb);
offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1);
if (!sbi->s_group_desc[group_desc]) {
ext4_error (sb, "ext4_get_group_desc",
"Group descriptor not loaded - "
"block_group = %lu, group_desc = %lu, desc = %lu",
block_group, group_desc, offset);
return NULL;
}
desc = (struct ext4_group_desc *)(
(__u8 *)sbi->s_group_desc[group_desc]->b_data +
offset * EXT4_DESC_SIZE(sb));
if (bh)
*bh = sbi->s_group_desc[group_desc];
return desc;
}
static int ext4_valid_block_bitmap(struct super_block *sb,
struct ext4_group_desc *desc,
unsigned int block_group,
struct buffer_head *bh)
{
ext4_grpblk_t offset;
ext4_grpblk_t next_zero_bit;
ext4_fsblk_t bitmap_blk;
ext4_fsblk_t group_first_block;
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
/* 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 1;
}
group_first_block = ext4_group_first_block_no(sb, block_group);
/* check whether block bitmap block number is set */
bitmap_blk = ext4_block_bitmap(sb, desc);
offset = bitmap_blk - group_first_block;
if (!ext4_test_bit(offset, bh->b_data))
/* bad block bitmap */
goto err_out;
/* check whether the inode bitmap block number is set */
bitmap_blk = ext4_inode_bitmap(sb, desc);
offset = bitmap_blk - group_first_block;
if (!ext4_test_bit(offset, bh->b_data))
/* bad block bitmap */
goto err_out;
/* check whether the inode table block number is set */
bitmap_blk = ext4_inode_table(sb, desc);
offset = bitmap_blk - group_first_block;
next_zero_bit = ext4_find_next_zero_bit(bh->b_data,
offset + EXT4_SB(sb)->s_itb_per_group,
offset);
if (next_zero_bit >= offset + EXT4_SB(sb)->s_itb_per_group)
/* good bitmap for inode tables */
return 1;
err_out:
ext4_error(sb, __FUNCTION__,
"Invalid block bitmap - "
"block_group = %d, block = %llu",
block_group, bitmap_blk);
return 0;
}
/**
* read_block_bitmap()
* @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 NULL in case of failure.
*/
struct buffer_head *
read_block_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_block_bitmap(sb, desc);
bh = sb_getblk(sb, bitmap_blk);
if (unlikely(!bh)) {
ext4_error(sb, __FUNCTION__,
"Cannot read block bitmap - "
"block_group = %d, block_bitmap = %llu",
(int)block_group, (unsigned long long)bitmap_blk);
return NULL;
}
if (bh_uptodate_or_lock(bh))
return bh;
if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
ext4_init_block_bitmap(sb, bh, block_group, desc);
set_buffer_uptodate(bh);
unlock_buffer(bh);
return bh;
}
if (bh_submit_read(bh) < 0) {
put_bh(bh);
ext4_error(sb, __FUNCTION__,
"Cannot read block bitmap - "
"block_group = %d, block_bitmap = %llu",
(int)block_group, (unsigned long long)bitmap_blk);
return NULL;
}
if (!ext4_valid_block_bitmap(sb, desc, block_group, bh)) {
put_bh(bh);
return NULL;
}
return bh;
}
/*
* The reservation window structure operations
* --------------------------------------------
* Operations include:
* dump, find, add, remove, is_empty, find_next_reservable_window, etc.
*
* We use a red-black tree to represent per-filesystem reservation
* windows.
*
*/
/**
* __rsv_window_dump() -- Dump the filesystem block allocation reservation map
* @rb_root: root of per-filesystem reservation rb tree
* @verbose: verbose mode
* @fn: function which wishes to dump the reservation map
*
* If verbose is turned on, it will print the whole block reservation
* windows(start, end). Otherwise, it will only print out the "bad" windows,
* those windows that overlap with their immediate neighbors.
*/
#if 1
static void __rsv_window_dump(struct rb_root *root, int verbose,
const char *fn)
{
struct rb_node *n;
struct ext4_reserve_window_node *rsv, *prev;
int bad;
restart:
n = rb_first(root);
bad = 0;
prev = NULL;
printk("Block Allocation Reservation Windows Map (%s):\n", fn);
while (n) {
rsv = rb_entry(n, struct ext4_reserve_window_node, rsv_node);
if (verbose)
printk("reservation window 0x%p "
"start: %llu, end: %llu\n",
rsv, rsv->rsv_start, rsv->rsv_end);
if (rsv->rsv_start && rsv->rsv_start >= rsv->rsv_end) {
printk("Bad reservation %p (start >= end)\n",
rsv);
bad = 1;
}
if (prev && prev->rsv_end >= rsv->rsv_start) {
printk("Bad reservation %p (prev->end >= start)\n",
rsv);
bad = 1;
}
if (bad) {
if (!verbose) {
printk("Restarting reservation walk in verbose mode\n");
verbose = 1;
goto restart;
}
}
n = rb_next(n);
prev = rsv;
}
printk("Window map complete.\n");
if (bad)
BUG();
}
#define rsv_window_dump(root, verbose) \
__rsv_window_dump((root), (verbose), __FUNCTION__)
#else
#define rsv_window_dump(root, verbose) do {} while (0)
#endif
/**
* goal_in_my_reservation()
* @rsv: inode's reservation window
* @grp_goal: given goal block relative to the allocation block group
* @group: the current allocation block group
* @sb: filesystem super block
*
* Test if the given goal block (group relative) is within the file's
* own block reservation window range.
*
* If the reservation window is outside the goal allocation group, return 0;
* grp_goal (given goal block) could be -1, which means no specific
* goal block. In this case, always return 1.
* If the goal block is within the reservation window, return 1;
* otherwise, return 0;
*/
static int
goal_in_my_reservation(struct ext4_reserve_window *rsv, ext4_grpblk_t grp_goal,
ext4_group_t group, struct super_block *sb)
{
ext4_fsblk_t group_first_block, group_last_block;
group_first_block = ext4_group_first_block_no(sb, group);
group_last_block = group_first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1);
if ((rsv->_rsv_start > group_last_block) ||
(rsv->_rsv_end < group_first_block))
return 0;
if ((grp_goal >= 0) && ((grp_goal + group_first_block < rsv->_rsv_start)
|| (grp_goal + group_first_block > rsv->_rsv_end)))
return 0;
return 1;
}
/**
* search_reserve_window()
* @rb_root: root of reservation tree
* @goal: target allocation block
*
* Find the reserved window which includes the goal, or the previous one
* if the goal is not in any window.
* Returns NULL if there are no windows or if all windows start after the goal.
*/
static struct ext4_reserve_window_node *
search_reserve_window(struct rb_root *root, ext4_fsblk_t goal)
{
struct rb_node *n = root->rb_node;
struct ext4_reserve_window_node *rsv;
if (!n)
return NULL;
do {
rsv = rb_entry(n, struct ext4_reserve_window_node, rsv_node);
if (goal < rsv->rsv_start)
n = n->rb_left;
else if (goal > rsv->rsv_end)
n = n->rb_right;
else
return rsv;
} while (n);
/*
* We've fallen off the end of the tree: the goal wasn't inside
* any particular node. OK, the previous node must be to one
* side of the interval containing the goal. If it's the RHS,
* we need to back up one.
*/
if (rsv->rsv_start > goal) {
n = rb_prev(&rsv->rsv_node);
rsv = rb_entry(n, struct ext4_reserve_window_node, rsv_node);
}
return rsv;
}
/**
* ext4_rsv_window_add() -- Insert a window to the block reservation rb tree.
* @sb: super block
* @rsv: reservation window to add
*
* Must be called with rsv_lock hold.
*/
void ext4_rsv_window_add(struct super_block *sb,
struct ext4_reserve_window_node *rsv)
{
struct rb_root *root = &EXT4_SB(sb)->s_rsv_window_root;
struct rb_node *node = &rsv->rsv_node;
ext4_fsblk_t start = rsv->rsv_start;
struct rb_node ** p = &root->rb_node;
struct rb_node * parent = NULL;
struct ext4_reserve_window_node *this;
while (*p)
{
parent = *p;
this = rb_entry(parent, struct ext4_reserve_window_node, rsv_node);
if (start < this->rsv_start)
p = &(*p)->rb_left;
else if (start > this->rsv_end)
p = &(*p)->rb_right;
else {
rsv_window_dump(root, 1);
BUG();
}
}
rb_link_node(node, parent, p);
rb_insert_color(node, root);
}
/**
* ext4_rsv_window_remove() -- unlink a window from the reservation rb tree
* @sb: super block
* @rsv: reservation window to remove
*
* Mark the block reservation window as not allocated, and unlink it
* from the filesystem reservation window rb tree. Must be called with
* rsv_lock hold.
*/
static void rsv_window_remove(struct super_block *sb,
struct ext4_reserve_window_node *rsv)
{
rsv->rsv_start = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
rsv->rsv_end = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
rsv->rsv_alloc_hit = 0;
rb_erase(&rsv->rsv_node, &EXT4_SB(sb)->s_rsv_window_root);
}
/*
* rsv_is_empty() -- Check if the reservation window is allocated.
* @rsv: given reservation window to check
*
* returns 1 if the end block is EXT4_RESERVE_WINDOW_NOT_ALLOCATED.
*/
static inline int rsv_is_empty(struct ext4_reserve_window *rsv)
{
/* a valid reservation end block could not be 0 */
return rsv->_rsv_end == EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
}
/**
* ext4_init_block_alloc_info()
* @inode: file inode structure
*
* Allocate and initialize the reservation window structure, and
* link the window to the ext4 inode structure at last
*
* The reservation window structure is only dynamically allocated
* and linked to ext4 inode the first time the open file
* needs a new block. So, before every ext4_new_block(s) call, for
* regular files, we should check whether the reservation window
* structure exists or not. In the latter case, this function is called.
* Fail to do so will result in block reservation being turned off for that
* open file.
*
* This function is called from ext4_get_blocks_handle(), also called
* when setting the reservation window size through ioctl before the file
* is open for write (needs block allocation).
*
* Needs down_write(i_data_sem) protection prior to call this function.
*/
void ext4_init_block_alloc_info(struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_block_alloc_info *block_i = ei->i_block_alloc_info;
struct super_block *sb = inode->i_sb;
block_i = kmalloc(sizeof(*block_i), GFP_NOFS);
if (block_i) {
struct ext4_reserve_window_node *rsv = &block_i->rsv_window_node;
rsv->rsv_start = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
rsv->rsv_end = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
/*
* if filesystem is mounted with NORESERVATION, the goal
* reservation window size is set to zero to indicate
* block reservation is off
*/
if (!test_opt(sb, RESERVATION))
rsv->rsv_goal_size = 0;
else
rsv->rsv_goal_size = EXT4_DEFAULT_RESERVE_BLOCKS;
rsv->rsv_alloc_hit = 0;
block_i->last_alloc_logical_block = 0;
block_i->last_alloc_physical_block = 0;
}
ei->i_block_alloc_info = block_i;
}
/**
* ext4_discard_reservation()
* @inode: inode
*
* Discard(free) block reservation window on last file close, or truncate
* or at last iput().
*
* It is being called in three cases:
* ext4_release_file(): last writer close the file
* ext4_clear_inode(): last iput(), when nobody link to this file.
* ext4_truncate(): when the block indirect map is about to change.
*
*/
void ext4_discard_reservation(struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_block_alloc_info *block_i = ei->i_block_alloc_info;
struct ext4_reserve_window_node *rsv;
spinlock_t *rsv_lock = &EXT4_SB(inode->i_sb)->s_rsv_window_lock;
ext4_mb_discard_inode_preallocations(inode);
if (!block_i)
return;
rsv = &block_i->rsv_window_node;
if (!rsv_is_empty(&rsv->rsv_window)) {
spin_lock(rsv_lock);
if (!rsv_is_empty(&rsv->rsv_window))
rsv_window_remove(inode->i_sb, rsv);
spin_unlock(rsv_lock);
}
}
/**
* ext4_free_blocks_sb() -- Free given blocks and update quota
* @handle: handle to this transaction
* @sb: super block
* @block: start physcial block to free
* @count: number of blocks to free
* @pdquot_freed_blocks: pointer to quota
*/
void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
ext4_fsblk_t block, unsigned long count,
unsigned long *pdquot_freed_blocks)
{
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *gd_bh;
ext4_group_t block_group;
ext4_grpblk_t bit;
unsigned long i;
unsigned long overflow;
struct ext4_group_desc * desc;
struct ext4_super_block * es;
struct ext4_sb_info *sbi;
int err = 0, ret;
ext4_grpblk_t group_freed;
*pdquot_freed_blocks = 0;
sbi = EXT4_SB(sb);
es = sbi->s_es;
if (block < le32_to_cpu(es->s_first_data_block) ||
block + count < block ||
block + count > ext4_blocks_count(es)) {
ext4_error (sb, "ext4_free_blocks",
"Freeing blocks not in datazone - "
"block = %llu, count = %lu", block, count);
goto error_return;
}
ext4_debug ("freeing block(s) %llu-%llu\n", block, block + count - 1);
do_more:
overflow = 0;
ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
/*
* Check to see if we are freeing blocks across a group
* boundary.
*/
if (bit + count > EXT4_BLOCKS_PER_GROUP(sb)) {
overflow = bit + count - EXT4_BLOCKS_PER_GROUP(sb);
count -= overflow;
}
brelse(bitmap_bh);
bitmap_bh = read_block_bitmap(sb, block_group);
if (!bitmap_bh)
goto error_return;
desc = ext4_get_group_desc (sb, block_group, &gd_bh);
if (!desc)
goto error_return;
if (in_range(ext4_block_bitmap(sb, desc), block, count) ||
in_range(ext4_inode_bitmap(sb, desc), block, count) ||
in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
in_range(block + count - 1, ext4_inode_table(sb, desc),
sbi->s_itb_per_group)) {
ext4_error (sb, "ext4_free_blocks",
"Freeing blocks in system zones - "
"Block = %llu, count = %lu",
block, count);
goto error_return;
}
/*
* We are about to start releasing blocks in the bitmap,
* so we need undo access.
*/
/* @@@ check errors */
BUFFER_TRACE(bitmap_bh, "getting undo access");
err = ext4_journal_get_undo_access(handle, bitmap_bh);
if (err)
goto error_return;
/*
* We are about to modify some metadata. Call the journal APIs
* to unshare ->b_data if a currently-committing transaction is
* using it
*/
BUFFER_TRACE(gd_bh, "get_write_access");
err = ext4_journal_get_write_access(handle, gd_bh);
if (err)
goto error_return;
jbd_lock_bh_state(bitmap_bh);
for (i = 0, group_freed = 0; i < count; i++) {
/*
* An HJ special. This is expensive...
*/
#ifdef CONFIG_JBD2_DEBUG
jbd_unlock_bh_state(bitmap_bh);
{
struct buffer_head *debug_bh;
debug_bh = sb_find_get_block(sb, block + i);
if (debug_bh) {
BUFFER_TRACE(debug_bh, "Deleted!");
if (!bh2jh(bitmap_bh)->b_committed_data)
BUFFER_TRACE(debug_bh,
"No commited data in bitmap");
BUFFER_TRACE2(debug_bh, bitmap_bh, "bitmap");
__brelse(debug_bh);
}
}
jbd_lock_bh_state(bitmap_bh);
#endif
if (need_resched()) {
jbd_unlock_bh_state(bitmap_bh);
cond_resched();
jbd_lock_bh_state(bitmap_bh);
}
/* @@@ This prevents newly-allocated data from being
* freed and then reallocated within the same
* transaction.
*
* Ideally we would want to allow that to happen, but to
* do so requires making jbd2_journal_forget() capable of
* revoking the queued write of a data block, which
* implies blocking on the journal lock. *forget()
* cannot block due to truncate races.
*
* Eventually we can fix this by making jbd2_journal_forget()
* return a status indicating whether or not it was able
* to revoke the buffer. On successful revoke, it is
* safe not to set the allocation bit in the committed
* bitmap, because we know that there is no outstanding
* activity on the buffer any more and so it is safe to
* reallocate it.
*/
BUFFER_TRACE(bitmap_bh, "set in b_committed_data");
J_ASSERT_BH(bitmap_bh,
bh2jh(bitmap_bh)->b_committed_data != NULL);
ext4_set_bit_atomic(sb_bgl_lock(sbi, block_group), bit + i,
bh2jh(bitmap_bh)->b_committed_data);
/*
* We clear the bit in the bitmap after setting the committed
* data bit, because this is the reverse order to that which
* the allocator uses.
*/
BUFFER_TRACE(bitmap_bh, "clear bit");
if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
bit + i, bitmap_bh->b_data)) {
jbd_unlock_bh_state(bitmap_bh);
ext4_error(sb, __FUNCTION__,
"bit already cleared for block %llu",
(ext4_fsblk_t)(block + i));
jbd_lock_bh_state(bitmap_bh);
BUFFER_TRACE(bitmap_bh, "bit already cleared");
} else {
group_freed++;
}
}
jbd_unlock_bh_state(bitmap_bh);
spin_lock(sb_bgl_lock(sbi, block_group));
desc->bg_free_blocks_count =
cpu_to_le16(le16_to_cpu(desc->bg_free_blocks_count) +
group_freed);
desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
spin_unlock(sb_bgl_lock(sbi, block_group));
percpu_counter_add(&sbi->s_freeblocks_counter, count);
/* We dirtied the bitmap block */
BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
err = ext4_journal_dirty_metadata(handle, bitmap_bh);
/* And the group descriptor block */
BUFFER_TRACE(gd_bh, "dirtied group descriptor block");
ret = ext4_journal_dirty_metadata(handle, gd_bh);
if (!err) err = ret;
*pdquot_freed_blocks += group_freed;
if (overflow && !err) {
block += count;
count = overflow;
goto do_more;
}
sb->s_dirt = 1;
error_return:
brelse(bitmap_bh);
ext4_std_error(sb, err);
return;
}
/**
* ext4_free_blocks() -- Free given blocks and update quota
* @handle: handle for this transaction
* @inode: inode
* @block: start physical block to free
* @count: number of blocks to count
* @metadata: Are these metadata blocks
*/
void ext4_free_blocks(handle_t *handle, struct inode *inode,
ext4_fsblk_t block, unsigned long count,
int metadata)
{
struct super_block * sb;
unsigned long dquot_freed_blocks;
/* this isn't the right place to decide whether block is metadata
* inode.c/extents.c knows better, but for safety ... */
if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode) ||
ext4_should_journal_data(inode))
metadata = 1;
sb = inode->i_sb;
if (!test_opt(sb, MBALLOC) || !EXT4_SB(sb)->s_group_info)
ext4_free_blocks_sb(handle, sb, block, count,
&dquot_freed_blocks);
else
ext4_mb_free_blocks(handle, inode, block, count,
metadata, &dquot_freed_blocks);
if (dquot_freed_blocks)
DQUOT_FREE_BLOCK(inode, dquot_freed_blocks);
return;
}
/**
* ext4_test_allocatable()
* @nr: given allocation block group
* @bh: bufferhead contains the bitmap of the given block group
*
* For ext4 allocations, we must not reuse any blocks which are
* allocated in the bitmap buffer's "last committed data" copy. This
* prevents deletes from freeing up the page for reuse until we have
* committed the delete transaction.
*
* If we didn't do this, then deleting something and reallocating it as
* data would allow the old block to be overwritten before the
* transaction committed (because we force data to disk before commit).
* This would lead to corruption if we crashed between overwriting the
* data and committing the delete.
*
* @@@ We may want to make this allocation behaviour conditional on
* data-writes at some point, and disable it for metadata allocations or
* sync-data inodes.
*/
static int ext4_test_allocatable(ext4_grpblk_t nr, struct buffer_head *bh)
{
int ret;
struct journal_head *jh = bh2jh(bh);
if (ext4_test_bit(nr, bh->b_data))
return 0;
jbd_lock_bh_state(bh);
if (!jh->b_committed_data)
ret = 1;
else
ret = !ext4_test_bit(nr, jh->b_committed_data);
jbd_unlock_bh_state(bh);
return ret;
}
/**
* bitmap_search_next_usable_block()
* @start: the starting block (group relative) of the search
* @bh: bufferhead contains the block group bitmap
* @maxblocks: the ending block (group relative) of the reservation
*
* The bitmap search --- search forward alternately through the actual
* bitmap on disk and the last-committed copy in journal, until we find a
* bit free in both bitmaps.
*/
static ext4_grpblk_t
bitmap_search_next_usable_block(ext4_grpblk_t start, struct buffer_head *bh,
ext4_grpblk_t maxblocks)
{
ext4_grpblk_t next;
struct journal_head *jh = bh2jh(bh);
while (start < maxblocks) {
next = ext4_find_next_zero_bit(bh->b_data, maxblocks, start);
if (next >= maxblocks)
return -1;
if (ext4_test_allocatable(next, bh))
return next;
jbd_lock_bh_state(bh);
if (jh->b_committed_data)
start = ext4_find_next_zero_bit(jh->b_committed_data,
maxblocks, next);
jbd_unlock_bh_state(bh);
}
return -1;
}
/**
* find_next_usable_block()
* @start: the starting block (group relative) to find next
* allocatable block in bitmap.
* @bh: bufferhead contains the block group bitmap
* @maxblocks: the ending block (group relative) for the search
*
* Find an allocatable block in a bitmap. We honor both the bitmap and
* its last-committed copy (if that exists), and perform the "most
* appropriate allocation" algorithm of looking for a free block near
* the initial goal; then for a free byte somewhere in the bitmap; then
* for any free bit in the bitmap.
*/
static ext4_grpblk_t
find_next_usable_block(ext4_grpblk_t start, struct buffer_head *bh,
ext4_grpblk_t maxblocks)
{
ext4_grpblk_t here, next;
char *p, *r;
if (start > 0) {
/*
* The goal was occupied; search forward for a free
* block within the next XX blocks.
*
* end_goal is more or less random, but it has to be
* less than EXT4_BLOCKS_PER_GROUP. Aligning up to the
* next 64-bit boundary is simple..
*/
ext4_grpblk_t end_goal = (start + 63) & ~63;
if (end_goal > maxblocks)
end_goal = maxblocks;
here = ext4_find_next_zero_bit(bh->b_data, end_goal, start);
if (here < end_goal && ext4_test_allocatable(here, bh))
return here;
ext4_debug("Bit not found near goal\n");
}
here = start;
if (here < 0)
here = 0;
p = ((char *)bh->b_data) + (here >> 3);
r = memscan(p, 0, ((maxblocks + 7) >> 3) - (here >> 3));
next = (r - ((char *)bh->b_data)) << 3;
if (next < maxblocks && next >= start && ext4_test_allocatable(next, bh))
return next;
/*
* The bitmap search --- search forward alternately through the actual
* bitmap and the last-committed copy until we find a bit free in
* both
*/
here = bitmap_search_next_usable_block(here, bh, maxblocks);
return here;
}
/**
* claim_block()
* @block: the free block (group relative) to allocate
* @bh: the bufferhead containts the block group bitmap
*
* We think we can allocate this block in this bitmap. Try to set the bit.
* If that succeeds then check that nobody has allocated and then freed the
* block since we saw that is was not marked in b_committed_data. If it _was_
* allocated and freed then clear the bit in the bitmap again and return
* zero (failure).
*/
static inline int
claim_block(spinlock_t *lock, ext4_grpblk_t block, struct buffer_head *bh)
{
struct journal_head *jh = bh2jh(bh);
int ret;
if (ext4_set_bit_atomic(lock, block, bh->b_data))
return 0;
jbd_lock_bh_state(bh);
if (jh->b_committed_data && ext4_test_bit(block,jh->b_committed_data)) {
ext4_clear_bit_atomic(lock, block, bh->b_data);
ret = 0;
} else {
ret = 1;
}
jbd_unlock_bh_state(bh);
return ret;
}
/**
* ext4_try_to_allocate()
* @sb: superblock
* @handle: handle to this transaction
* @group: given allocation block group
* @bitmap_bh: bufferhead holds the block bitmap
* @grp_goal: given target block within the group
* @count: target number of blocks to allocate
* @my_rsv: reservation window
*
* Attempt to allocate blocks within a give range. Set the range of allocation
* first, then find the first free bit(s) from the bitmap (within the range),
* and at last, allocate the blocks by claiming the found free bit as allocated.
*
* To set the range of this allocation:
* if there is a reservation window, only try to allocate block(s) from the
* file's own reservation window;
* Otherwise, the allocation range starts from the give goal block, ends at
* the block group's last block.
*
* If we failed to allocate the desired block then we may end up crossing to a
* new bitmap. In that case we must release write access to the old one via
* ext4_journal_release_buffer(), else we'll run out of credits.
*/
static ext4_grpblk_t
ext4_try_to_allocate(struct super_block *sb, handle_t *handle,