-
Notifications
You must be signed in to change notification settings - Fork 14
/
Copy pathsuballoc.c
1852 lines (1600 loc) · 48.9 KB
/
suballoc.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
/* -*- mode: c; c-basic-offset: 8; -*-
* vim: noexpandtab sw=8 ts=8 sts=0:
*
* suballoc.c
*
* metadata alloc and free
* Inspired by ext3 block groups.
*
* Copyright (C) 2002, 2004 Oracle. All rights reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* You should have received a copy of the GNU General Public
* License along with this program; if not, write to the
* Free Software Foundation, Inc., 59 Temple Place - Suite 330,
* Boston, MA 021110-1307, USA.
*/
#include <linux/fs.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/highmem.h>
#define MLOG_MASK_PREFIX ML_DISK_ALLOC
#include <cluster/masklog.h>
#include "ocfs2.h"
#include "alloc.h"
#include "dlmglue.h"
#include "inode.h"
#include "journal.h"
#include "localalloc.h"
#include "suballoc.h"
#include "super.h"
#include "sysfile.h"
#include "uptodate.h"
#include "buffer_head_io.h"
static inline void ocfs2_debug_bg(struct ocfs2_group_desc *bg);
static inline void ocfs2_debug_suballoc_inode(struct ocfs2_dinode *fe);
static inline u16 ocfs2_find_victim_chain(struct ocfs2_chain_list *cl);
static int ocfs2_block_group_fill(struct ocfs2_journal_handle *handle,
struct inode *alloc_inode,
struct buffer_head *bg_bh,
u64 group_blkno,
u16 my_chain,
struct ocfs2_chain_list *cl);
static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
struct inode *alloc_inode,
struct buffer_head *bh);
static int ocfs2_reserve_suballoc_bits(struct ocfs2_super *osb,
struct ocfs2_alloc_context *ac);
static int ocfs2_cluster_group_search(struct inode *inode,
struct buffer_head *group_bh,
u32 bits_wanted, u32 min_bits,
u16 *bit_off, u16 *bits_found);
static int ocfs2_block_group_search(struct inode *inode,
struct buffer_head *group_bh,
u32 bits_wanted, u32 min_bits,
u16 *bit_off, u16 *bits_found);
static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
struct ocfs2_alloc_context *ac,
u32 bits_wanted,
u32 min_bits,
u16 *bit_off,
unsigned int *num_bits,
u64 *bg_blkno);
static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh,
int nr);
static inline int ocfs2_block_group_set_bits(struct ocfs2_journal_handle *handle,
struct inode *alloc_inode,
struct ocfs2_group_desc *bg,
struct buffer_head *group_bh,
unsigned int bit_off,
unsigned int num_bits);
static inline int ocfs2_block_group_clear_bits(struct ocfs2_journal_handle *handle,
struct inode *alloc_inode,
struct ocfs2_group_desc *bg,
struct buffer_head *group_bh,
unsigned int bit_off,
unsigned int num_bits);
static int ocfs2_relink_block_group(struct ocfs2_journal_handle *handle,
struct inode *alloc_inode,
struct buffer_head *fe_bh,
struct buffer_head *bg_bh,
struct buffer_head *prev_bg_bh,
u16 chain);
static inline int ocfs2_block_group_reasonably_empty(struct ocfs2_group_desc *bg,
u32 wanted);
static int ocfs2_free_suballoc_bits(struct ocfs2_journal_handle *handle,
struct inode *alloc_inode,
struct buffer_head *alloc_bh,
unsigned int start_bit,
u64 bg_blkno,
unsigned int count);
static inline u64 ocfs2_which_suballoc_group(u64 block,
unsigned int bit);
static inline u32 ocfs2_desc_bitmap_to_cluster_off(struct inode *inode,
u64 bg_blkno,
u16 bg_bit_off);
static inline u64 ocfs2_which_cluster_group(struct inode *inode,
u32 cluster);
static inline void ocfs2_block_to_cluster_group(struct inode *inode,
u64 data_blkno,
u64 *bg_blkno,
u16 *bg_bit_off);
void ocfs2_free_alloc_context(struct ocfs2_alloc_context *ac)
{
if (ac->ac_inode)
iput(ac->ac_inode);
if (ac->ac_bh)
brelse(ac->ac_bh);
kfree(ac);
}
static u32 ocfs2_bits_per_group(struct ocfs2_chain_list *cl)
{
return (u32)le16_to_cpu(cl->cl_cpg) * (u32)le16_to_cpu(cl->cl_bpc);
}
/* somewhat more expensive than our other checks, so use sparingly. */
static int ocfs2_check_group_descriptor(struct super_block *sb,
struct ocfs2_dinode *di,
struct ocfs2_group_desc *gd)
{
unsigned int max_bits;
if (!OCFS2_IS_VALID_GROUP_DESC(gd)) {
OCFS2_RO_ON_INVALID_GROUP_DESC(sb, gd);
return -EIO;
}
if (di->i_blkno != gd->bg_parent_dinode) {
ocfs2_error(sb, "Group descriptor # %llu has bad parent "
"pointer (%llu, expected %llu)",
(unsigned long long)le64_to_cpu(gd->bg_blkno),
(unsigned long long)le64_to_cpu(gd->bg_parent_dinode),
(unsigned long long)le64_to_cpu(di->i_blkno));
return -EIO;
}
max_bits = le16_to_cpu(di->id2.i_chain.cl_cpg) * le16_to_cpu(di->id2.i_chain.cl_bpc);
if (le16_to_cpu(gd->bg_bits) > max_bits) {
ocfs2_error(sb, "Group descriptor # %llu has bit count of %u",
(unsigned long long)le64_to_cpu(gd->bg_blkno),
le16_to_cpu(gd->bg_bits));
return -EIO;
}
if (le16_to_cpu(gd->bg_chain) >=
le16_to_cpu(di->id2.i_chain.cl_next_free_rec)) {
ocfs2_error(sb, "Group descriptor # %llu has bad chain %u",
(unsigned long long)le64_to_cpu(gd->bg_blkno),
le16_to_cpu(gd->bg_chain));
return -EIO;
}
if (le16_to_cpu(gd->bg_free_bits_count) > le16_to_cpu(gd->bg_bits)) {
ocfs2_error(sb, "Group descriptor # %llu has bit count %u but "
"claims that %u are free",
(unsigned long long)le64_to_cpu(gd->bg_blkno),
le16_to_cpu(gd->bg_bits),
le16_to_cpu(gd->bg_free_bits_count));
return -EIO;
}
if (le16_to_cpu(gd->bg_bits) > (8 * le16_to_cpu(gd->bg_size))) {
ocfs2_error(sb, "Group descriptor # %llu has bit count %u but "
"max bitmap bits of %u",
(unsigned long long)le64_to_cpu(gd->bg_blkno),
le16_to_cpu(gd->bg_bits),
8 * le16_to_cpu(gd->bg_size));
return -EIO;
}
return 0;
}
static int ocfs2_block_group_fill(struct ocfs2_journal_handle *handle,
struct inode *alloc_inode,
struct buffer_head *bg_bh,
u64 group_blkno,
u16 my_chain,
struct ocfs2_chain_list *cl)
{
int status = 0;
struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data;
struct super_block * sb = alloc_inode->i_sb;
mlog_entry_void();
if (((unsigned long long) bg_bh->b_blocknr) != group_blkno) {
ocfs2_error(alloc_inode->i_sb, "group block (%llu) != "
"b_blocknr (%llu)",
(unsigned long long)group_blkno,
(unsigned long long) bg_bh->b_blocknr);
status = -EIO;
goto bail;
}
status = ocfs2_journal_access(handle,
alloc_inode,
bg_bh,
OCFS2_JOURNAL_ACCESS_CREATE);
if (status < 0) {
mlog_errno(status);
goto bail;
}
memset(bg, 0, sb->s_blocksize);
strcpy(bg->bg_signature, OCFS2_GROUP_DESC_SIGNATURE);
bg->bg_generation = cpu_to_le32(OCFS2_SB(sb)->fs_generation);
bg->bg_size = cpu_to_le16(ocfs2_group_bitmap_size(sb));
bg->bg_bits = cpu_to_le16(ocfs2_bits_per_group(cl));
bg->bg_chain = cpu_to_le16(my_chain);
bg->bg_next_group = cl->cl_recs[my_chain].c_blkno;
bg->bg_parent_dinode = cpu_to_le64(OCFS2_I(alloc_inode)->ip_blkno);
bg->bg_blkno = cpu_to_le64(group_blkno);
/* set the 1st bit in the bitmap to account for the descriptor block */
ocfs2_set_bit(0, (unsigned long *)bg->bg_bitmap);
bg->bg_free_bits_count = cpu_to_le16(le16_to_cpu(bg->bg_bits) - 1);
status = ocfs2_journal_dirty(handle, bg_bh);
if (status < 0)
mlog_errno(status);
/* There is no need to zero out or otherwise initialize the
* other blocks in a group - All valid FS metadata in a block
* group stores the superblock fs_generation value at
* allocation time. */
bail:
mlog_exit(status);
return status;
}
static inline u16 ocfs2_find_smallest_chain(struct ocfs2_chain_list *cl)
{
u16 curr, best;
best = curr = 0;
while (curr < le16_to_cpu(cl->cl_count)) {
if (le32_to_cpu(cl->cl_recs[best].c_total) >
le32_to_cpu(cl->cl_recs[curr].c_total))
best = curr;
curr++;
}
return best;
}
/*
* We expect the block group allocator to already be locked.
*/
static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
struct inode *alloc_inode,
struct buffer_head *bh)
{
int status, credits;
struct ocfs2_dinode *fe = (struct ocfs2_dinode *) bh->b_data;
struct ocfs2_chain_list *cl;
struct ocfs2_alloc_context *ac = NULL;
struct ocfs2_journal_handle *handle = NULL;
u32 bit_off, num_bits;
u16 alloc_rec;
u64 bg_blkno;
struct buffer_head *bg_bh = NULL;
struct ocfs2_group_desc *bg;
BUG_ON(ocfs2_is_cluster_bitmap(alloc_inode));
mlog_entry_void();
handle = ocfs2_alloc_handle(osb);
if (!handle) {
status = -ENOMEM;
mlog_errno(status);
goto bail;
}
cl = &fe->id2.i_chain;
status = ocfs2_reserve_clusters(osb,
handle,
le16_to_cpu(cl->cl_cpg),
&ac);
if (status < 0) {
if (status != -ENOSPC)
mlog_errno(status);
goto bail;
}
credits = ocfs2_calc_group_alloc_credits(osb->sb,
le16_to_cpu(cl->cl_cpg));
handle = ocfs2_start_trans(osb, handle, credits);
if (IS_ERR(handle)) {
status = PTR_ERR(handle);
handle = NULL;
mlog_errno(status);
goto bail;
}
status = ocfs2_claim_clusters(osb,
handle,
ac,
le16_to_cpu(cl->cl_cpg),
&bit_off,
&num_bits);
if (status < 0) {
if (status != -ENOSPC)
mlog_errno(status);
goto bail;
}
alloc_rec = ocfs2_find_smallest_chain(cl);
/* setup the group */
bg_blkno = ocfs2_clusters_to_blocks(osb->sb, bit_off);
mlog(0, "new descriptor, record %u, at block %llu\n",
alloc_rec, (unsigned long long)bg_blkno);
bg_bh = sb_getblk(osb->sb, bg_blkno);
if (!bg_bh) {
status = -EIO;
mlog_errno(status);
goto bail;
}
ocfs2_set_new_buffer_uptodate(alloc_inode, bg_bh);
status = ocfs2_block_group_fill(handle,
alloc_inode,
bg_bh,
bg_blkno,
alloc_rec,
cl);
if (status < 0) {
mlog_errno(status);
goto bail;
}
bg = (struct ocfs2_group_desc *) bg_bh->b_data;
status = ocfs2_journal_access(handle, alloc_inode,
bh, OCFS2_JOURNAL_ACCESS_WRITE);
if (status < 0) {
mlog_errno(status);
goto bail;
}
le32_add_cpu(&cl->cl_recs[alloc_rec].c_free,
le16_to_cpu(bg->bg_free_bits_count));
le32_add_cpu(&cl->cl_recs[alloc_rec].c_total, le16_to_cpu(bg->bg_bits));
cl->cl_recs[alloc_rec].c_blkno = cpu_to_le64(bg_blkno);
if (le16_to_cpu(cl->cl_next_free_rec) < le16_to_cpu(cl->cl_count))
le16_add_cpu(&cl->cl_next_free_rec, 1);
le32_add_cpu(&fe->id1.bitmap1.i_used, le16_to_cpu(bg->bg_bits) -
le16_to_cpu(bg->bg_free_bits_count));
le32_add_cpu(&fe->id1.bitmap1.i_total, le16_to_cpu(bg->bg_bits));
le32_add_cpu(&fe->i_clusters, le16_to_cpu(cl->cl_cpg));
status = ocfs2_journal_dirty(handle, bh);
if (status < 0) {
mlog_errno(status);
goto bail;
}
spin_lock(&OCFS2_I(alloc_inode)->ip_lock);
OCFS2_I(alloc_inode)->ip_clusters = le32_to_cpu(fe->i_clusters);
fe->i_size = cpu_to_le64(ocfs2_clusters_to_bytes(alloc_inode->i_sb,
le32_to_cpu(fe->i_clusters)));
spin_unlock(&OCFS2_I(alloc_inode)->ip_lock);
i_size_write(alloc_inode, le64_to_cpu(fe->i_size));
alloc_inode->i_blocks =
ocfs2_align_bytes_to_sectors(i_size_read(alloc_inode));
status = 0;
bail:
if (handle)
ocfs2_commit_trans(handle);
if (ac)
ocfs2_free_alloc_context(ac);
if (bg_bh)
brelse(bg_bh);
mlog_exit(status);
return status;
}
static int ocfs2_reserve_suballoc_bits(struct ocfs2_super *osb,
struct ocfs2_alloc_context *ac)
{
int status;
u32 bits_wanted = ac->ac_bits_wanted;
struct inode *alloc_inode = ac->ac_inode;
struct buffer_head *bh = NULL;
struct ocfs2_journal_handle *handle = ac->ac_handle;
struct ocfs2_dinode *fe;
u32 free_bits;
mlog_entry_void();
BUG_ON(handle->flags & OCFS2_HANDLE_STARTED);
ocfs2_handle_add_inode(handle, alloc_inode);
status = ocfs2_meta_lock(alloc_inode, handle, &bh, 1);
if (status < 0) {
mlog_errno(status);
goto bail;
}
fe = (struct ocfs2_dinode *) bh->b_data;
if (!OCFS2_IS_VALID_DINODE(fe)) {
OCFS2_RO_ON_INVALID_DINODE(alloc_inode->i_sb, fe);
status = -EIO;
goto bail;
}
if (!(fe->i_flags & cpu_to_le32(OCFS2_CHAIN_FL))) {
ocfs2_error(alloc_inode->i_sb, "Invalid chain allocator %llu",
(unsigned long long)le64_to_cpu(fe->i_blkno));
status = -EIO;
goto bail;
}
free_bits = le32_to_cpu(fe->id1.bitmap1.i_total) -
le32_to_cpu(fe->id1.bitmap1.i_used);
if (bits_wanted > free_bits) {
/* cluster bitmap never grows */
if (ocfs2_is_cluster_bitmap(alloc_inode)) {
mlog(0, "Disk Full: wanted=%u, free_bits=%u\n",
bits_wanted, free_bits);
status = -ENOSPC;
goto bail;
}
status = ocfs2_block_group_alloc(osb, alloc_inode, bh);
if (status < 0) {
if (status != -ENOSPC)
mlog_errno(status);
goto bail;
}
atomic_inc(&osb->alloc_stats.bg_extends);
/* You should never ask for this much metadata */
BUG_ON(bits_wanted >
(le32_to_cpu(fe->id1.bitmap1.i_total)
- le32_to_cpu(fe->id1.bitmap1.i_used)));
}
get_bh(bh);
ac->ac_bh = bh;
bail:
if (bh)
brelse(bh);
mlog_exit(status);
return status;
}
int ocfs2_reserve_new_metadata(struct ocfs2_super *osb,
struct ocfs2_journal_handle *handle,
struct ocfs2_dinode *fe,
struct ocfs2_alloc_context **ac)
{
int status;
struct inode *alloc_inode = NULL;
*ac = kcalloc(1, sizeof(struct ocfs2_alloc_context), GFP_KERNEL);
if (!(*ac)) {
status = -ENOMEM;
mlog_errno(status);
goto bail;
}
(*ac)->ac_bits_wanted = ocfs2_extend_meta_needed(fe);
(*ac)->ac_handle = handle;
(*ac)->ac_which = OCFS2_AC_USE_META;
#ifndef OCFS2_USE_ALL_METADATA_SUBALLOCATORS
alloc_inode = ocfs2_get_system_file_inode(osb,
EXTENT_ALLOC_SYSTEM_INODE,
0);
#else
alloc_inode = ocfs2_get_system_file_inode(osb,
EXTENT_ALLOC_SYSTEM_INODE,
osb->slot_num);
#endif
if (!alloc_inode) {
status = -ENOMEM;
mlog_errno(status);
goto bail;
}
(*ac)->ac_inode = igrab(alloc_inode);
(*ac)->ac_group_search = ocfs2_block_group_search;
status = ocfs2_reserve_suballoc_bits(osb, (*ac));
if (status < 0) {
if (status != -ENOSPC)
mlog_errno(status);
goto bail;
}
status = 0;
bail:
if ((status < 0) && *ac) {
ocfs2_free_alloc_context(*ac);
*ac = NULL;
}
if (alloc_inode)
iput(alloc_inode);
mlog_exit(status);
return status;
}
int ocfs2_reserve_new_inode(struct ocfs2_super *osb,
struct ocfs2_journal_handle *handle,
struct ocfs2_alloc_context **ac)
{
int status;
struct inode *alloc_inode = NULL;
*ac = kcalloc(1, sizeof(struct ocfs2_alloc_context), GFP_KERNEL);
if (!(*ac)) {
status = -ENOMEM;
mlog_errno(status);
goto bail;
}
(*ac)->ac_bits_wanted = 1;
(*ac)->ac_handle = handle;
(*ac)->ac_which = OCFS2_AC_USE_INODE;
alloc_inode = ocfs2_get_system_file_inode(osb,
INODE_ALLOC_SYSTEM_INODE,
osb->slot_num);
if (!alloc_inode) {
status = -ENOMEM;
mlog_errno(status);
goto bail;
}
(*ac)->ac_inode = igrab(alloc_inode);
(*ac)->ac_group_search = ocfs2_block_group_search;
status = ocfs2_reserve_suballoc_bits(osb, *ac);
if (status < 0) {
if (status != -ENOSPC)
mlog_errno(status);
goto bail;
}
status = 0;
bail:
if ((status < 0) && *ac) {
ocfs2_free_alloc_context(*ac);
*ac = NULL;
}
if (alloc_inode)
iput(alloc_inode);
mlog_exit(status);
return status;
}
/* local alloc code has to do the same thing, so rather than do this
* twice.. */
int ocfs2_reserve_cluster_bitmap_bits(struct ocfs2_super *osb,
struct ocfs2_alloc_context *ac)
{
int status;
ac->ac_inode = ocfs2_get_system_file_inode(osb,
GLOBAL_BITMAP_SYSTEM_INODE,
OCFS2_INVALID_SLOT);
if (!ac->ac_inode) {
status = -EINVAL;
mlog(ML_ERROR, "Could not get bitmap inode!\n");
goto bail;
}
ac->ac_which = OCFS2_AC_USE_MAIN;
ac->ac_group_search = ocfs2_cluster_group_search;
status = ocfs2_reserve_suballoc_bits(osb, ac);
if (status < 0 && status != -ENOSPC)
mlog_errno(status);
bail:
return status;
}
/* Callers don't need to care which bitmap (local alloc or main) to
* use so we figure it out for them, but unfortunately this clutters
* things a bit. */
int ocfs2_reserve_clusters(struct ocfs2_super *osb,
struct ocfs2_journal_handle *handle,
u32 bits_wanted,
struct ocfs2_alloc_context **ac)
{
int status;
mlog_entry_void();
BUG_ON(!handle);
*ac = kcalloc(1, sizeof(struct ocfs2_alloc_context), GFP_KERNEL);
if (!(*ac)) {
status = -ENOMEM;
mlog_errno(status);
goto bail;
}
(*ac)->ac_bits_wanted = bits_wanted;
(*ac)->ac_handle = handle;
status = -ENOSPC;
if (ocfs2_alloc_should_use_local(osb, bits_wanted)) {
status = ocfs2_reserve_local_alloc_bits(osb,
handle,
bits_wanted,
*ac);
if ((status < 0) && (status != -ENOSPC)) {
mlog_errno(status);
goto bail;
} else if (status == -ENOSPC) {
/* reserve_local_bits will return enospc with
* the local alloc inode still locked, so we
* can change this safely here. */
mlog(0, "Disabling local alloc\n");
/* We set to OCFS2_LA_DISABLED so that umount
* can clean up what's left of the local
* allocation */
osb->local_alloc_state = OCFS2_LA_DISABLED;
}
}
if (status == -ENOSPC) {
status = ocfs2_reserve_cluster_bitmap_bits(osb, *ac);
if (status < 0) {
if (status != -ENOSPC)
mlog_errno(status);
goto bail;
}
}
status = 0;
bail:
if ((status < 0) && *ac) {
ocfs2_free_alloc_context(*ac);
*ac = NULL;
}
mlog_exit(status);
return status;
}
/*
* More or less lifted from ext3. I'll leave their description below:
*
* "For ext3 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."
*
* Note: OCFS2 already does this differently for metadata vs data
* allocations, as those bitmaps are seperate and undo access is never
* called on a metadata group descriptor.
*/
static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh,
int nr)
{
struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data;
if (ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap))
return 0;
if (!buffer_jbd(bg_bh) || !bh2jh(bg_bh)->b_committed_data)
return 1;
bg = (struct ocfs2_group_desc *) bh2jh(bg_bh)->b_committed_data;
return !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap);
}
static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
struct buffer_head *bg_bh,
unsigned int bits_wanted,
unsigned int total_bits,
u16 *bit_off,
u16 *bits_found)
{
void *bitmap;
u16 best_offset, best_size;
int offset, start, found, status = 0;
struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data;
if (!OCFS2_IS_VALID_GROUP_DESC(bg)) {
OCFS2_RO_ON_INVALID_GROUP_DESC(osb->sb, bg);
return -EIO;
}
found = start = best_offset = best_size = 0;
bitmap = bg->bg_bitmap;
while((offset = ocfs2_find_next_zero_bit(bitmap, total_bits, start)) != -1) {
if (offset == total_bits)
break;
if (!ocfs2_test_bg_bit_allocatable(bg_bh, offset)) {
/* We found a zero, but we can't use it as it
* hasn't been put to disk yet! */
found = 0;
start = offset + 1;
} else if (offset == start) {
/* we found a zero */
found++;
/* move start to the next bit to test */
start++;
} else {
/* got a zero after some ones */
found = 1;
start = offset + 1;
}
if (found > best_size) {
best_size = found;
best_offset = start - found;
}
/* we got everything we needed */
if (found == bits_wanted) {
/* mlog(0, "Found it all!\n"); */
break;
}
}
/* XXX: I think the first clause is equivalent to the second
* - jlbec */
if (found == bits_wanted) {
*bit_off = start - found;
*bits_found = found;
} else if (best_size) {
*bit_off = best_offset;
*bits_found = best_size;
} else {
status = -ENOSPC;
/* No error log here -- see the comment above
* ocfs2_test_bg_bit_allocatable */
}
return status;
}
static inline int ocfs2_block_group_set_bits(struct ocfs2_journal_handle *handle,
struct inode *alloc_inode,
struct ocfs2_group_desc *bg,
struct buffer_head *group_bh,
unsigned int bit_off,
unsigned int num_bits)
{
int status;
void *bitmap = bg->bg_bitmap;
int journal_type = OCFS2_JOURNAL_ACCESS_WRITE;
mlog_entry_void();
if (!OCFS2_IS_VALID_GROUP_DESC(bg)) {
OCFS2_RO_ON_INVALID_GROUP_DESC(alloc_inode->i_sb, bg);
status = -EIO;
goto bail;
}
BUG_ON(le16_to_cpu(bg->bg_free_bits_count) < num_bits);
mlog(0, "block_group_set_bits: off = %u, num = %u\n", bit_off,
num_bits);
if (ocfs2_is_cluster_bitmap(alloc_inode))
journal_type = OCFS2_JOURNAL_ACCESS_UNDO;
status = ocfs2_journal_access(handle,
alloc_inode,
group_bh,
journal_type);
if (status < 0) {
mlog_errno(status);
goto bail;
}
le16_add_cpu(&bg->bg_free_bits_count, -num_bits);
while(num_bits--)
ocfs2_set_bit(bit_off++, bitmap);
status = ocfs2_journal_dirty(handle,
group_bh);
if (status < 0) {
mlog_errno(status);
goto bail;
}
bail:
mlog_exit(status);
return status;
}
/* find the one with the most empty bits */
static inline u16 ocfs2_find_victim_chain(struct ocfs2_chain_list *cl)
{
u16 curr, best;
BUG_ON(!cl->cl_next_free_rec);
best = curr = 0;
while (curr < le16_to_cpu(cl->cl_next_free_rec)) {
if (le32_to_cpu(cl->cl_recs[curr].c_free) >
le32_to_cpu(cl->cl_recs[best].c_free))
best = curr;
curr++;
}
BUG_ON(best >= le16_to_cpu(cl->cl_next_free_rec));
return best;
}
static int ocfs2_relink_block_group(struct ocfs2_journal_handle *handle,
struct inode *alloc_inode,
struct buffer_head *fe_bh,
struct buffer_head *bg_bh,
struct buffer_head *prev_bg_bh,
u16 chain)
{
int status;
/* there is a really tiny chance the journal calls could fail,
* but we wouldn't want inconsistent blocks in *any* case. */
u64 fe_ptr, bg_ptr, prev_bg_ptr;
struct ocfs2_dinode *fe = (struct ocfs2_dinode *) fe_bh->b_data;
struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data;
struct ocfs2_group_desc *prev_bg = (struct ocfs2_group_desc *) prev_bg_bh->b_data;
if (!OCFS2_IS_VALID_DINODE(fe)) {
OCFS2_RO_ON_INVALID_DINODE(alloc_inode->i_sb, fe);
status = -EIO;
goto out;
}
if (!OCFS2_IS_VALID_GROUP_DESC(bg)) {
OCFS2_RO_ON_INVALID_GROUP_DESC(alloc_inode->i_sb, bg);
status = -EIO;
goto out;
}
if (!OCFS2_IS_VALID_GROUP_DESC(prev_bg)) {
OCFS2_RO_ON_INVALID_GROUP_DESC(alloc_inode->i_sb, prev_bg);
status = -EIO;
goto out;
}
mlog(0, "Suballoc %llu, chain %u, move group %llu to top, prev = %llu\n",
(unsigned long long)fe->i_blkno, chain,
(unsigned long long)bg->bg_blkno,
(unsigned long long)prev_bg->bg_blkno);
fe_ptr = le64_to_cpu(fe->id2.i_chain.cl_recs[chain].c_blkno);
bg_ptr = le64_to_cpu(bg->bg_next_group);
prev_bg_ptr = le64_to_cpu(prev_bg->bg_next_group);
status = ocfs2_journal_access(handle, alloc_inode, prev_bg_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (status < 0) {
mlog_errno(status);
goto out_rollback;
}
prev_bg->bg_next_group = bg->bg_next_group;
status = ocfs2_journal_dirty(handle, prev_bg_bh);
if (status < 0) {
mlog_errno(status);
goto out_rollback;
}
status = ocfs2_journal_access(handle, alloc_inode, bg_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (status < 0) {
mlog_errno(status);
goto out_rollback;
}
bg->bg_next_group = fe->id2.i_chain.cl_recs[chain].c_blkno;
status = ocfs2_journal_dirty(handle, bg_bh);
if (status < 0) {
mlog_errno(status);
goto out_rollback;
}
status = ocfs2_journal_access(handle, alloc_inode, fe_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (status < 0) {
mlog_errno(status);
goto out_rollback;
}
fe->id2.i_chain.cl_recs[chain].c_blkno = bg->bg_blkno;
status = ocfs2_journal_dirty(handle, fe_bh);
if (status < 0) {
mlog_errno(status);
goto out_rollback;
}
status = 0;
out_rollback:
if (status < 0) {
fe->id2.i_chain.cl_recs[chain].c_blkno = cpu_to_le64(fe_ptr);
bg->bg_next_group = cpu_to_le64(bg_ptr);
prev_bg->bg_next_group = cpu_to_le64(prev_bg_ptr);
}
out:
mlog_exit(status);
return status;
}
static inline int ocfs2_block_group_reasonably_empty(struct ocfs2_group_desc *bg,
u32 wanted)
{
return le16_to_cpu(bg->bg_free_bits_count) > wanted;
}
/* return 0 on success, -ENOSPC to keep searching and any other < 0
* value on error. */
static int ocfs2_cluster_group_search(struct inode *inode,
struct buffer_head *group_bh,
u32 bits_wanted, u32 min_bits,
u16 *bit_off, u16 *bits_found)
{
int search = -ENOSPC;
int ret;
struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *) group_bh->b_data;
u16 tmp_off, tmp_found;
unsigned int max_bits, gd_cluster_off;
BUG_ON(!ocfs2_is_cluster_bitmap(inode));
if (gd->bg_free_bits_count) {
max_bits = le16_to_cpu(gd->bg_bits);
/* Tail groups in cluster bitmaps which aren't cpg
* aligned are prone to partial extention by a failed
* fs resize. If the file system resize never got to
* update the dinode cluster count, then we don't want
* to trust any clusters past it, regardless of what
* the group descriptor says. */
gd_cluster_off = ocfs2_blocks_to_clusters(inode->i_sb,
le64_to_cpu(gd->bg_blkno));
if ((gd_cluster_off + max_bits) >
OCFS2_I(inode)->ip_clusters) {
max_bits = OCFS2_I(inode)->ip_clusters - gd_cluster_off;
mlog(0, "Desc %llu, bg_bits %u, clusters %u, use %u\n",
(unsigned long long)le64_to_cpu(gd->bg_blkno),
le16_to_cpu(gd->bg_bits),
OCFS2_I(inode)->ip_clusters, max_bits);
}
ret = ocfs2_block_group_find_clear_bits(OCFS2_SB(inode->i_sb),
group_bh, bits_wanted,
max_bits,
&tmp_off, &tmp_found);
if (ret)
return ret;
/* ocfs2_block_group_find_clear_bits() might
* return success, but we still want to return
* -ENOSPC unless it found the minimum number
* of bits. */
if (min_bits <= tmp_found) {
*bit_off = tmp_off;
*bits_found = tmp_found;
search = 0; /* success */