forked from analogdevicesinc/linux
-
Notifications
You must be signed in to change notification settings - Fork 3
/
balloc.c
1536 lines (1392 loc) · 44.5 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/ext2/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 "ext2.h"
#include <linux/quotaops.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/buffer_head.h>
#include <linux/capability.h>
/*
* balloc.c contains the blocks allocation and deallocation routines
*/
/*
* 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 ext2_fill_super).
*/
#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1)
struct ext2_group_desc * ext2_get_group_desc(struct super_block * sb,
unsigned int block_group,
struct buffer_head ** bh)
{
unsigned long group_desc;
unsigned long offset;
struct ext2_group_desc * desc;
struct ext2_sb_info *sbi = EXT2_SB(sb);
if (block_group >= sbi->s_groups_count) {
ext2_error (sb, "ext2_get_group_desc",
"block_group >= groups_count - "
"block_group = %d, groups_count = %lu",
block_group, sbi->s_groups_count);
return NULL;
}
group_desc = block_group >> EXT2_DESC_PER_BLOCK_BITS(sb);
offset = block_group & (EXT2_DESC_PER_BLOCK(sb) - 1);
if (!sbi->s_group_desc[group_desc]) {
ext2_error (sb, "ext2_get_group_desc",
"Group descriptor not loaded - "
"block_group = %d, group_desc = %lu, desc = %lu",
block_group, group_desc, offset);
return NULL;
}
desc = (struct ext2_group_desc *) sbi->s_group_desc[group_desc]->b_data;
if (bh)
*bh = sbi->s_group_desc[group_desc];
return desc + offset;
}
static int ext2_valid_block_bitmap(struct super_block *sb,
struct ext2_group_desc *desc,
unsigned int block_group,
struct buffer_head *bh)
{
ext2_grpblk_t offset;
ext2_grpblk_t next_zero_bit;
ext2_fsblk_t bitmap_blk;
ext2_fsblk_t group_first_block;
group_first_block = ext2_group_first_block_no(sb, block_group);
/* check whether block bitmap block number is set */
bitmap_blk = le32_to_cpu(desc->bg_block_bitmap);
offset = bitmap_blk - group_first_block;
if (!ext2_test_bit(offset, bh->b_data))
/* bad block bitmap */
goto err_out;
/* check whether the inode bitmap block number is set */
bitmap_blk = le32_to_cpu(desc->bg_inode_bitmap);
offset = bitmap_blk - group_first_block;
if (!ext2_test_bit(offset, bh->b_data))
/* bad block bitmap */
goto err_out;
/* check whether the inode table block number is set */
bitmap_blk = le32_to_cpu(desc->bg_inode_table);
offset = bitmap_blk - group_first_block;
next_zero_bit = ext2_find_next_zero_bit(bh->b_data,
offset + EXT2_SB(sb)->s_itb_per_group,
offset);
if (next_zero_bit >= offset + EXT2_SB(sb)->s_itb_per_group)
/* good bitmap for inode tables */
return 1;
err_out:
ext2_error(sb, __func__,
"Invalid block bitmap - "
"block_group = %d, block = %lu",
block_group, bitmap_blk);
return 0;
}
/*
* 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.
*/
static struct buffer_head *
read_block_bitmap(struct super_block *sb, unsigned int block_group)
{
struct ext2_group_desc * desc;
struct buffer_head * bh = NULL;
ext2_fsblk_t bitmap_blk;
desc = ext2_get_group_desc(sb, block_group, NULL);
if (!desc)
return NULL;
bitmap_blk = le32_to_cpu(desc->bg_block_bitmap);
bh = sb_getblk(sb, bitmap_blk);
if (unlikely(!bh)) {
ext2_error(sb, __func__,
"Cannot read block bitmap - "
"block_group = %d, block_bitmap = %u",
block_group, le32_to_cpu(desc->bg_block_bitmap));
return NULL;
}
if (likely(bh_uptodate_or_lock(bh)))
return bh;
if (bh_submit_read(bh) < 0) {
brelse(bh);
ext2_error(sb, __func__,
"Cannot read block bitmap - "
"block_group = %d, block_bitmap = %u",
block_group, le32_to_cpu(desc->bg_block_bitmap));
return NULL;
}
ext2_valid_block_bitmap(sb, desc, block_group, bh);
/*
* file system mounted not to panic on error, continue with corrupt
* bitmap
*/
return bh;
}
static void group_adjust_blocks(struct super_block *sb, int group_no,
struct ext2_group_desc *desc, struct buffer_head *bh, int count)
{
if (count) {
struct ext2_sb_info *sbi = EXT2_SB(sb);
unsigned free_blocks;
spin_lock(sb_bgl_lock(sbi, group_no));
free_blocks = le16_to_cpu(desc->bg_free_blocks_count);
desc->bg_free_blocks_count = cpu_to_le16(free_blocks + count);
spin_unlock(sb_bgl_lock(sbi, group_no));
mark_buffer_dirty(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 ext2_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 ext2_reserve_window_node, rsv_node);
if (verbose)
printk("reservation window 0x%p "
"start: %lu, end: %lu\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");
BUG_ON(bad);
}
#define rsv_window_dump(root, verbose) \
__rsv_window_dump((root), (verbose), __func__)
#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 ext2_reserve_window *rsv, ext2_grpblk_t grp_goal,
unsigned int group, struct super_block * sb)
{
ext2_fsblk_t group_first_block, group_last_block;
group_first_block = ext2_group_first_block_no(sb, group);
group_last_block = group_first_block + EXT2_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 ext2_reserve_window_node *
search_reserve_window(struct rb_root *root, ext2_fsblk_t goal)
{
struct rb_node *n = root->rb_node;
struct ext2_reserve_window_node *rsv;
if (!n)
return NULL;
do {
rsv = rb_entry(n, struct ext2_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 ext2_reserve_window_node, rsv_node);
}
return rsv;
}
/*
* ext2_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 held.
*/
void ext2_rsv_window_add(struct super_block *sb,
struct ext2_reserve_window_node *rsv)
{
struct rb_root *root = &EXT2_SB(sb)->s_rsv_window_root;
struct rb_node *node = &rsv->rsv_node;
ext2_fsblk_t start = rsv->rsv_start;
struct rb_node ** p = &root->rb_node;
struct rb_node * parent = NULL;
struct ext2_reserve_window_node *this;
while (*p)
{
parent = *p;
this = rb_entry(parent, struct ext2_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);
}
/**
* 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 held.
*/
static void rsv_window_remove(struct super_block *sb,
struct ext2_reserve_window_node *rsv)
{
rsv->rsv_start = EXT2_RESERVE_WINDOW_NOT_ALLOCATED;
rsv->rsv_end = EXT2_RESERVE_WINDOW_NOT_ALLOCATED;
rsv->rsv_alloc_hit = 0;
rb_erase(&rsv->rsv_node, &EXT2_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 EXT2_RESERVE_WINDOW_NOT_ALLOCATED.
*/
static inline int rsv_is_empty(struct ext2_reserve_window *rsv)
{
/* a valid reservation end block could not be 0 */
return (rsv->_rsv_end == EXT2_RESERVE_WINDOW_NOT_ALLOCATED);
}
/**
* ext2_init_block_alloc_info()
* @inode: file inode structure
*
* Allocate and initialize the reservation window structure, and
* link the window to the ext2 inode structure at last
*
* The reservation window structure is only dynamically allocated
* and linked to ext2 inode the first time the open file
* needs a new block. So, before every ext2_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 ext2_get_blocks_handle(), also called
* when setting the reservation window size through ioctl before the file
* is open for write (needs block allocation).
*
* Needs truncate_mutex protection prior to calling this function.
*/
void ext2_init_block_alloc_info(struct inode *inode)
{
struct ext2_inode_info *ei = EXT2_I(inode);
struct ext2_block_alloc_info *block_i;
struct super_block *sb = inode->i_sb;
block_i = kmalloc(sizeof(*block_i), GFP_NOFS);
if (block_i) {
struct ext2_reserve_window_node *rsv = &block_i->rsv_window_node;
rsv->rsv_start = EXT2_RESERVE_WINDOW_NOT_ALLOCATED;
rsv->rsv_end = EXT2_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 = EXT2_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;
}
/**
* ext2_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:
* ext2_release_file(): last writer closes the file
* ext2_clear_inode(): last iput(), when nobody links to this file.
* ext2_truncate(): when the block indirect map is about to change.
*/
void ext2_discard_reservation(struct inode *inode)
{
struct ext2_inode_info *ei = EXT2_I(inode);
struct ext2_block_alloc_info *block_i = ei->i_block_alloc_info;
struct ext2_reserve_window_node *rsv;
spinlock_t *rsv_lock = &EXT2_SB(inode->i_sb)->s_rsv_window_lock;
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);
}
}
/**
* ext2_free_blocks() -- Free given blocks and update quota and i_blocks
* @inode: inode
* @block: start physical block to free
* @count: number of blocks to free
*/
void ext2_free_blocks (struct inode * inode, unsigned long block,
unsigned long count)
{
struct buffer_head *bitmap_bh = NULL;
struct buffer_head * bh2;
unsigned long block_group;
unsigned long bit;
unsigned long i;
unsigned long overflow;
struct super_block * sb = inode->i_sb;
struct ext2_sb_info * sbi = EXT2_SB(sb);
struct ext2_group_desc * desc;
struct ext2_super_block * es = sbi->s_es;
unsigned freed = 0, group_freed;
if (block < le32_to_cpu(es->s_first_data_block) ||
block + count < block ||
block + count > le32_to_cpu(es->s_blocks_count)) {
ext2_error (sb, "ext2_free_blocks",
"Freeing blocks not in datazone - "
"block = %lu, count = %lu", block, count);
goto error_return;
}
ext2_debug ("freeing block(s) %lu-%lu\n", block, block + count - 1);
do_more:
overflow = 0;
block_group = (block - le32_to_cpu(es->s_first_data_block)) /
EXT2_BLOCKS_PER_GROUP(sb);
bit = (block - le32_to_cpu(es->s_first_data_block)) %
EXT2_BLOCKS_PER_GROUP(sb);
/*
* Check to see if we are freeing blocks across a group
* boundary.
*/
if (bit + count > EXT2_BLOCKS_PER_GROUP(sb)) {
overflow = bit + count - EXT2_BLOCKS_PER_GROUP(sb);
count -= overflow;
}
brelse(bitmap_bh);
bitmap_bh = read_block_bitmap(sb, block_group);
if (!bitmap_bh)
goto error_return;
desc = ext2_get_group_desc (sb, block_group, &bh2);
if (!desc)
goto error_return;
if (in_range (le32_to_cpu(desc->bg_block_bitmap), block, count) ||
in_range (le32_to_cpu(desc->bg_inode_bitmap), block, count) ||
in_range (block, le32_to_cpu(desc->bg_inode_table),
sbi->s_itb_per_group) ||
in_range (block + count - 1, le32_to_cpu(desc->bg_inode_table),
sbi->s_itb_per_group)) {
ext2_error (sb, "ext2_free_blocks",
"Freeing blocks in system zones - "
"Block = %lu, count = %lu",
block, count);
goto error_return;
}
for (i = 0, group_freed = 0; i < count; i++) {
if (!ext2_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
bit + i, bitmap_bh->b_data)) {
ext2_error(sb, __func__,
"bit already cleared for block %lu", block + i);
} else {
group_freed++;
}
}
mark_buffer_dirty(bitmap_bh);
if (sb->s_flags & MS_SYNCHRONOUS)
sync_dirty_buffer(bitmap_bh);
group_adjust_blocks(sb, block_group, desc, bh2, group_freed);
freed += group_freed;
if (overflow) {
block += count;
count = overflow;
goto do_more;
}
error_return:
brelse(bitmap_bh);
if (freed) {
percpu_counter_add(&sbi->s_freeblocks_counter, freed);
dquot_free_block_nodirty(inode, freed);
mark_inode_dirty(inode);
}
}
/**
* 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 through the actual bitmap on disk until
* we find a bit free.
*/
static ext2_grpblk_t
bitmap_search_next_usable_block(ext2_grpblk_t start, struct buffer_head *bh,
ext2_grpblk_t maxblocks)
{
ext2_grpblk_t next;
next = ext2_find_next_zero_bit(bh->b_data, maxblocks, start);
if (next >= maxblocks)
return -1;
return next;
}
/**
* 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 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 ext2_grpblk_t
find_next_usable_block(int start, struct buffer_head *bh, int maxblocks)
{
ext2_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 EXT2_BLOCKS_PER_GROUP. Aligning up to the
* next 64-bit boundary is simple..
*/
ext2_grpblk_t end_goal = (start + 63) & ~63;
if (end_goal > maxblocks)
end_goal = maxblocks;
here = ext2_find_next_zero_bit(bh->b_data, end_goal, start);
if (here < end_goal)
return here;
ext2_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 >= here)
return next;
here = bitmap_search_next_usable_block(here, bh, maxblocks);
return here;
}
/**
* ext2_try_to_allocate()
* @sb: superblock
* @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.
*/
static int
ext2_try_to_allocate(struct super_block *sb, int group,
struct buffer_head *bitmap_bh, ext2_grpblk_t grp_goal,
unsigned long *count,
struct ext2_reserve_window *my_rsv)
{
ext2_fsblk_t group_first_block;
ext2_grpblk_t start, end;
unsigned long num = 0;
/* we do allocation within the reservation window if we have a window */
if (my_rsv) {
group_first_block = ext2_group_first_block_no(sb, group);
if (my_rsv->_rsv_start >= group_first_block)
start = my_rsv->_rsv_start - group_first_block;
else
/* reservation window cross group boundary */
start = 0;
end = my_rsv->_rsv_end - group_first_block + 1;
if (end > EXT2_BLOCKS_PER_GROUP(sb))
/* reservation window crosses group boundary */
end = EXT2_BLOCKS_PER_GROUP(sb);
if ((start <= grp_goal) && (grp_goal < end))
start = grp_goal;
else
grp_goal = -1;
} else {
if (grp_goal > 0)
start = grp_goal;
else
start = 0;
end = EXT2_BLOCKS_PER_GROUP(sb);
}
BUG_ON(start > EXT2_BLOCKS_PER_GROUP(sb));
repeat:
if (grp_goal < 0) {
grp_goal = find_next_usable_block(start, bitmap_bh, end);
if (grp_goal < 0)
goto fail_access;
if (!my_rsv) {
int i;
for (i = 0; i < 7 && grp_goal > start &&
!ext2_test_bit(grp_goal - 1,
bitmap_bh->b_data);
i++, grp_goal--)
;
}
}
start = grp_goal;
if (ext2_set_bit_atomic(sb_bgl_lock(EXT2_SB(sb), group), grp_goal,
bitmap_bh->b_data)) {
/*
* The block was allocated by another thread, or it was
* allocated and then freed by another thread
*/
start++;
grp_goal++;
if (start >= end)
goto fail_access;
goto repeat;
}
num++;
grp_goal++;
while (num < *count && grp_goal < end
&& !ext2_set_bit_atomic(sb_bgl_lock(EXT2_SB(sb), group),
grp_goal, bitmap_bh->b_data)) {
num++;
grp_goal++;
}
*count = num;
return grp_goal - num;
fail_access:
*count = num;
return -1;
}
/**
* find_next_reservable_window():
* find a reservable space within the given range.
* It does not allocate the reservation window for now:
* alloc_new_reservation() will do the work later.
*
* @search_head: the head of the searching list;
* This is not necessarily the list head of the whole filesystem
*
* We have both head and start_block to assist the search
* for the reservable space. The list starts from head,
* but we will shift to the place where start_block is,
* then start from there, when looking for a reservable space.
*
* @size: the target new reservation window size
*
* @group_first_block: the first block we consider to start
* the real search from
*
* @last_block:
* the maximum block number that our goal reservable space
* could start from. This is normally the last block in this
* group. The search will end when we found the start of next
* possible reservable space is out of this boundary.
* This could handle the cross boundary reservation window
* request.
*
* basically we search from the given range, rather than the whole
* reservation double linked list, (start_block, last_block)
* to find a free region that is of my size and has not
* been reserved.
*
*/
static int find_next_reservable_window(
struct ext2_reserve_window_node *search_head,
struct ext2_reserve_window_node *my_rsv,
struct super_block * sb,
ext2_fsblk_t start_block,
ext2_fsblk_t last_block)
{
struct rb_node *next;
struct ext2_reserve_window_node *rsv, *prev;
ext2_fsblk_t cur;
int size = my_rsv->rsv_goal_size;
/* TODO: make the start of the reservation window byte-aligned */
/* cur = *start_block & ~7;*/
cur = start_block;
rsv = search_head;
if (!rsv)
return -1;
while (1) {
if (cur <= rsv->rsv_end)
cur = rsv->rsv_end + 1;
/* TODO?
* in the case we could not find a reservable space
* that is what is expected, during the re-search, we could
* remember what's the largest reservable space we could have
* and return that one.
*
* For now it will fail if we could not find the reservable
* space with expected-size (or more)...
*/
if (cur > last_block)
return -1; /* fail */
prev = rsv;
next = rb_next(&rsv->rsv_node);
rsv = rb_entry(next,struct ext2_reserve_window_node,rsv_node);
/*
* Reached the last reservation, we can just append to the
* previous one.
*/
if (!next)
break;
if (cur + size <= rsv->rsv_start) {
/*
* Found a reserveable space big enough. We could
* have a reservation across the group boundary here
*/
break;
}
}
/*
* we come here either :
* when we reach the end of the whole list,
* and there is empty reservable space after last entry in the list.
* append it to the end of the list.
*
* or we found one reservable space in the middle of the list,
* return the reservation window that we could append to.
* succeed.
*/
if ((prev != my_rsv) && (!rsv_is_empty(&my_rsv->rsv_window)))
rsv_window_remove(sb, my_rsv);
/*
* Let's book the whole available window for now. We will check the
* disk bitmap later and then, if there are free blocks then we adjust
* the window size if it's larger than requested.
* Otherwise, we will remove this node from the tree next time
* call find_next_reservable_window.
*/
my_rsv->rsv_start = cur;
my_rsv->rsv_end = cur + size - 1;
my_rsv->rsv_alloc_hit = 0;
if (prev != my_rsv)
ext2_rsv_window_add(sb, my_rsv);
return 0;
}
/**
* alloc_new_reservation()--allocate a new reservation window
*
* To make a new reservation, we search part of the filesystem
* reservation list (the list that inside the group). We try to
* allocate a new reservation window near the allocation goal,
* or the beginning of the group, if there is no goal.
*
* We first find a reservable space after the goal, then from
* there, we check the bitmap for the first free block after
* it. If there is no free block until the end of group, then the
* whole group is full, we failed. Otherwise, check if the free
* block is inside the expected reservable space, if so, we
* succeed.
* If the first free block is outside the reservable space, then
* start from the first free block, we search for next available
* space, and go on.
*
* on succeed, a new reservation will be found and inserted into the list
* It contains at least one free block, and it does not overlap with other
* reservation windows.
*
* failed: we failed to find a reservation window in this group
*
* @rsv: the reservation
*
* @grp_goal: The goal (group-relative). It is where the search for a
* free reservable space should start from.
* if we have a goal(goal >0 ), then start from there,
* no goal(goal = -1), we start from the first block
* of the group.
*
* @sb: the super block
* @group: the group we are trying to allocate in
* @bitmap_bh: the block group block bitmap
*
*/
static int alloc_new_reservation(struct ext2_reserve_window_node *my_rsv,
ext2_grpblk_t grp_goal, struct super_block *sb,
unsigned int group, struct buffer_head *bitmap_bh)
{
struct ext2_reserve_window_node *search_head;
ext2_fsblk_t group_first_block, group_end_block, start_block;
ext2_grpblk_t first_free_block;
struct rb_root *fs_rsv_root = &EXT2_SB(sb)->s_rsv_window_root;
unsigned long size;
int ret;
spinlock_t *rsv_lock = &EXT2_SB(sb)->s_rsv_window_lock;
group_first_block = ext2_group_first_block_no(sb, group);
group_end_block = group_first_block + (EXT2_BLOCKS_PER_GROUP(sb) - 1);
if (grp_goal < 0)
start_block = group_first_block;
else
start_block = grp_goal + group_first_block;
size = my_rsv->rsv_goal_size;
if (!rsv_is_empty(&my_rsv->rsv_window)) {
/*
* if the old reservation is cross group boundary
* and if the goal is inside the old reservation window,
* we will come here when we just failed to allocate from
* the first part of the window. We still have another part
* that belongs to the next group. In this case, there is no
* point to discard our window and try to allocate a new one
* in this group(which will fail). we should
* keep the reservation window, just simply move on.
*
* Maybe we could shift the start block of the reservation
* window to the first block of next group.
*/
if ((my_rsv->rsv_start <= group_end_block) &&
(my_rsv->rsv_end > group_end_block) &&
(start_block >= my_rsv->rsv_start))
return -1;
if ((my_rsv->rsv_alloc_hit >
(my_rsv->rsv_end - my_rsv->rsv_start + 1) / 2)) {
/*
* if the previously allocation hit ratio is
* greater than 1/2, then we double the size of
* the reservation window the next time,
* otherwise we keep the same size window
*/
size = size * 2;
if (size > EXT2_MAX_RESERVE_BLOCKS)
size = EXT2_MAX_RESERVE_BLOCKS;
my_rsv->rsv_goal_size= size;
}
}
spin_lock(rsv_lock);
/*
* shift the search start to the window near the goal block
*/
search_head = search_reserve_window(fs_rsv_root, start_block);
/*
* find_next_reservable_window() simply finds a reservable window
* inside the given range(start_block, group_end_block).
*
* To make sure the reservation window has a free bit inside it, we
* need to check the bitmap after we found a reservable window.
*/
retry:
ret = find_next_reservable_window(search_head, my_rsv, sb,
start_block, group_end_block);
if (ret == -1) {
if (!rsv_is_empty(&my_rsv->rsv_window))
rsv_window_remove(sb, my_rsv);
spin_unlock(rsv_lock);
return -1;
}
/*
* On success, find_next_reservable_window() returns the
* reservation window where there is a reservable space after it.
* Before we reserve this reservable space, we need
* to make sure there is at least a free block inside this region.
*
* Search the first free bit on the block bitmap. Search starts from
* the start block of the reservable space we just found.
*/
spin_unlock(rsv_lock);
first_free_block = bitmap_search_next_usable_block(
my_rsv->rsv_start - group_first_block,
bitmap_bh, group_end_block - group_first_block + 1);
if (first_free_block < 0) {
/*
* no free block left on the bitmap, no point
* to reserve the space. return failed.
*/
spin_lock(rsv_lock);
if (!rsv_is_empty(&my_rsv->rsv_window))
rsv_window_remove(sb, my_rsv);