forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathresize.c
1770 lines (1538 loc) · 50.8 KB
/
resize.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/resize.c
*
* Support for resizing an ext4 filesystem while it is mounted.
*
* Copyright (C) 2001, 2002 Andreas Dilger <adilger@clusterfs.com>
*
* This could probably be made into a module, because it is not often in use.
*/
#define EXT4FS_DEBUG
#include <linux/errno.h>
#include <linux/slab.h>
#include "ext4_jbd2.h"
int ext4_resize_begin(struct super_block *sb)
{
int ret = 0;
if (!capable(CAP_SYS_RESOURCE))
return -EPERM;
/*
* We are not allowed to do online-resizing on a filesystem mounted
* with error, because it can destroy the filesystem easily.
*/
if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
ext4_warning(sb, "There are errors in the filesystem, "
"so online resizing is not allowed\n");
return -EPERM;
}
if (test_and_set_bit_lock(EXT4_RESIZING, &EXT4_SB(sb)->s_resize_flags))
ret = -EBUSY;
return ret;
}
void ext4_resize_end(struct super_block *sb)
{
clear_bit_unlock(EXT4_RESIZING, &EXT4_SB(sb)->s_resize_flags);
smp_mb__after_clear_bit();
}
#define outside(b, first, last) ((b) < (first) || (b) >= (last))
#define inside(b, first, last) ((b) >= (first) && (b) < (last))
static int verify_group_input(struct super_block *sb,
struct ext4_new_group_data *input)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
ext4_fsblk_t start = ext4_blocks_count(es);
ext4_fsblk_t end = start + input->blocks_count;
ext4_group_t group = input->group;
ext4_fsblk_t itend = input->inode_table + sbi->s_itb_per_group;
unsigned overhead = ext4_bg_has_super(sb, group) ?
(1 + ext4_bg_num_gdb(sb, group) +
le16_to_cpu(es->s_reserved_gdt_blocks)) : 0;
ext4_fsblk_t metaend = start + overhead;
struct buffer_head *bh = NULL;
ext4_grpblk_t free_blocks_count, offset;
int err = -EINVAL;
input->free_blocks_count = free_blocks_count =
input->blocks_count - 2 - overhead - sbi->s_itb_per_group;
if (test_opt(sb, DEBUG))
printk(KERN_DEBUG "EXT4-fs: adding %s group %u: %u blocks "
"(%d free, %u reserved)\n",
ext4_bg_has_super(sb, input->group) ? "normal" :
"no-super", input->group, input->blocks_count,
free_blocks_count, input->reserved_blocks);
ext4_get_group_no_and_offset(sb, start, NULL, &offset);
if (group != sbi->s_groups_count)
ext4_warning(sb, "Cannot add at group %u (only %u groups)",
input->group, sbi->s_groups_count);
else if (offset != 0)
ext4_warning(sb, "Last group not full");
else if (input->reserved_blocks > input->blocks_count / 5)
ext4_warning(sb, "Reserved blocks too high (%u)",
input->reserved_blocks);
else if (free_blocks_count < 0)
ext4_warning(sb, "Bad blocks count %u",
input->blocks_count);
else if (!(bh = sb_bread(sb, end - 1)))
ext4_warning(sb, "Cannot read last block (%llu)",
end - 1);
else if (outside(input->block_bitmap, start, end))
ext4_warning(sb, "Block bitmap not in group (block %llu)",
(unsigned long long)input->block_bitmap);
else if (outside(input->inode_bitmap, start, end))
ext4_warning(sb, "Inode bitmap not in group (block %llu)",
(unsigned long long)input->inode_bitmap);
else if (outside(input->inode_table, start, end) ||
outside(itend - 1, start, end))
ext4_warning(sb, "Inode table not in group (blocks %llu-%llu)",
(unsigned long long)input->inode_table, itend - 1);
else if (input->inode_bitmap == input->block_bitmap)
ext4_warning(sb, "Block bitmap same as inode bitmap (%llu)",
(unsigned long long)input->block_bitmap);
else if (inside(input->block_bitmap, input->inode_table, itend))
ext4_warning(sb, "Block bitmap (%llu) in inode table "
"(%llu-%llu)",
(unsigned long long)input->block_bitmap,
(unsigned long long)input->inode_table, itend - 1);
else if (inside(input->inode_bitmap, input->inode_table, itend))
ext4_warning(sb, "Inode bitmap (%llu) in inode table "
"(%llu-%llu)",
(unsigned long long)input->inode_bitmap,
(unsigned long long)input->inode_table, itend - 1);
else if (inside(input->block_bitmap, start, metaend))
ext4_warning(sb, "Block bitmap (%llu) in GDT table (%llu-%llu)",
(unsigned long long)input->block_bitmap,
start, metaend - 1);
else if (inside(input->inode_bitmap, start, metaend))
ext4_warning(sb, "Inode bitmap (%llu) in GDT table (%llu-%llu)",
(unsigned long long)input->inode_bitmap,
start, metaend - 1);
else if (inside(input->inode_table, start, metaend) ||
inside(itend - 1, start, metaend))
ext4_warning(sb, "Inode table (%llu-%llu) overlaps GDT table "
"(%llu-%llu)",
(unsigned long long)input->inode_table,
itend - 1, start, metaend - 1);
else
err = 0;
brelse(bh);
return err;
}
/*
* ext4_new_flex_group_data is used by 64bit-resize interface to add a flex
* group each time.
*/
struct ext4_new_flex_group_data {
struct ext4_new_group_data *groups; /* new_group_data for groups
in the flex group */
__u16 *bg_flags; /* block group flags of groups
in @groups */
ext4_group_t count; /* number of groups in @groups
*/
};
/*
* alloc_flex_gd() allocates a ext4_new_flex_group_data with size of
* @flexbg_size.
*
* Returns NULL on failure otherwise address of the allocated structure.
*/
static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size)
{
struct ext4_new_flex_group_data *flex_gd;
flex_gd = kmalloc(sizeof(*flex_gd), GFP_NOFS);
if (flex_gd == NULL)
goto out3;
if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_flex_group_data))
goto out2;
flex_gd->count = flexbg_size;
flex_gd->groups = kmalloc(sizeof(struct ext4_new_group_data) *
flexbg_size, GFP_NOFS);
if (flex_gd->groups == NULL)
goto out2;
flex_gd->bg_flags = kmalloc(flexbg_size * sizeof(__u16), GFP_NOFS);
if (flex_gd->bg_flags == NULL)
goto out1;
return flex_gd;
out1:
kfree(flex_gd->groups);
out2:
kfree(flex_gd);
out3:
return NULL;
}
static void free_flex_gd(struct ext4_new_flex_group_data *flex_gd)
{
kfree(flex_gd->bg_flags);
kfree(flex_gd->groups);
kfree(flex_gd);
}
/*
* ext4_alloc_group_tables() allocates block bitmaps, inode bitmaps
* and inode tables for a flex group.
*
* This function is used by 64bit-resize. Note that this function allocates
* group tables from the 1st group of groups contained by @flexgd, which may
* be a partial of a flex group.
*
* @sb: super block of fs to which the groups belongs
*
* Returns 0 on a successful allocation of the metadata blocks in the
* block group.
*/
static int ext4_alloc_group_tables(struct super_block *sb,
struct ext4_new_flex_group_data *flex_gd,
int flexbg_size)
{
struct ext4_new_group_data *group_data = flex_gd->groups;
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
ext4_fsblk_t start_blk;
ext4_fsblk_t last_blk;
ext4_group_t src_group;
ext4_group_t bb_index = 0;
ext4_group_t ib_index = 0;
ext4_group_t it_index = 0;
ext4_group_t group;
ext4_group_t last_group;
unsigned overhead;
BUG_ON(flex_gd->count == 0 || group_data == NULL);
src_group = group_data[0].group;
last_group = src_group + flex_gd->count - 1;
BUG_ON((flexbg_size > 1) && ((src_group & ~(flexbg_size - 1)) !=
(last_group & ~(flexbg_size - 1))));
next_group:
group = group_data[0].group;
if (src_group >= group_data[0].group + flex_gd->count)
return -ENOSPC;
start_blk = ext4_group_first_block_no(sb, src_group);
last_blk = start_blk + group_data[src_group - group].blocks_count;
overhead = ext4_bg_has_super(sb, src_group) ?
(1 + ext4_bg_num_gdb(sb, src_group) +
le16_to_cpu(es->s_reserved_gdt_blocks)) : 0;
start_blk += overhead;
/* We collect contiguous blocks as much as possible. */
src_group++;
for (; src_group <= last_group; src_group++)
if (!ext4_bg_has_super(sb, src_group))
last_blk += group_data[src_group - group].blocks_count;
else
break;
/* Allocate block bitmaps */
for (; bb_index < flex_gd->count; bb_index++) {
if (start_blk >= last_blk)
goto next_group;
group_data[bb_index].block_bitmap = start_blk++;
ext4_get_group_no_and_offset(sb, start_blk - 1, &group, NULL);
group -= group_data[0].group;
group_data[group].free_blocks_count--;
if (flexbg_size > 1)
flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
}
/* Allocate inode bitmaps */
for (; ib_index < flex_gd->count; ib_index++) {
if (start_blk >= last_blk)
goto next_group;
group_data[ib_index].inode_bitmap = start_blk++;
ext4_get_group_no_and_offset(sb, start_blk - 1, &group, NULL);
group -= group_data[0].group;
group_data[group].free_blocks_count--;
if (flexbg_size > 1)
flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
}
/* Allocate inode tables */
for (; it_index < flex_gd->count; it_index++) {
if (start_blk + EXT4_SB(sb)->s_itb_per_group > last_blk)
goto next_group;
group_data[it_index].inode_table = start_blk;
ext4_get_group_no_and_offset(sb, start_blk, &group, NULL);
group -= group_data[0].group;
group_data[group].free_blocks_count -=
EXT4_SB(sb)->s_itb_per_group;
if (flexbg_size > 1)
flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
start_blk += EXT4_SB(sb)->s_itb_per_group;
}
if (test_opt(sb, DEBUG)) {
int i;
group = group_data[0].group;
printk(KERN_DEBUG "EXT4-fs: adding a flex group with "
"%d groups, flexbg size is %d:\n", flex_gd->count,
flexbg_size);
for (i = 0; i < flex_gd->count; i++) {
printk(KERN_DEBUG "adding %s group %u: %u "
"blocks (%d free)\n",
ext4_bg_has_super(sb, group + i) ? "normal" :
"no-super", group + i,
group_data[i].blocks_count,
group_data[i].free_blocks_count);
}
}
return 0;
}
static struct buffer_head *bclean(handle_t *handle, struct super_block *sb,
ext4_fsblk_t blk)
{
struct buffer_head *bh;
int err;
bh = sb_getblk(sb, blk);
if (!bh)
return ERR_PTR(-EIO);
if ((err = ext4_journal_get_write_access(handle, bh))) {
brelse(bh);
bh = ERR_PTR(err);
} else {
memset(bh->b_data, 0, sb->s_blocksize);
set_buffer_uptodate(bh);
}
return bh;
}
/*
* If we have fewer than thresh credits, extend by EXT4_MAX_TRANS_DATA.
* If that fails, restart the transaction & regain write access for the
* buffer head which is used for block_bitmap modifications.
*/
static int extend_or_restart_transaction(handle_t *handle, int thresh)
{
int err;
if (ext4_handle_has_enough_credits(handle, thresh))
return 0;
err = ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA);
if (err < 0)
return err;
if (err) {
err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA);
if (err)
return err;
}
return 0;
}
/*
* set_flexbg_block_bitmap() mark @count blocks starting from @block used.
*
* Helper function for ext4_setup_new_group_blocks() which set .
*
* @sb: super block
* @handle: journal handle
* @flex_gd: flex group data
*/
static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle,
struct ext4_new_flex_group_data *flex_gd,
ext4_fsblk_t block, ext4_group_t count)
{
ext4_group_t count2;
ext4_debug("mark blocks [%llu/%u] used\n", block, count);
for (count2 = count; count > 0; count -= count2, block += count2) {
ext4_fsblk_t start;
struct buffer_head *bh;
ext4_group_t group;
int err;
ext4_get_group_no_and_offset(sb, block, &group, NULL);
start = ext4_group_first_block_no(sb, group);
group -= flex_gd->groups[0].group;
count2 = sb->s_blocksize * 8 - (block - start);
if (count2 > count)
count2 = count;
if (flex_gd->bg_flags[group] & EXT4_BG_BLOCK_UNINIT) {
BUG_ON(flex_gd->count > 1);
continue;
}
err = extend_or_restart_transaction(handle, 1);
if (err)
return err;
bh = sb_getblk(sb, flex_gd->groups[group].block_bitmap);
if (!bh)
return -EIO;
err = ext4_journal_get_write_access(handle, bh);
if (err)
return err;
ext4_debug("mark block bitmap %#04llx (+%llu/%u)\n", block,
block - start, count2);
ext4_set_bits(bh->b_data, block - start, count2);
err = ext4_handle_dirty_metadata(handle, NULL, bh);
if (unlikely(err))
return err;
brelse(bh);
}
return 0;
}
/*
* Set up the block and inode bitmaps, and the inode table for the new groups.
* This doesn't need to be part of the main transaction, since we are only
* changing blocks outside the actual filesystem. We still do journaling to
* ensure the recovery is correct in case of a failure just after resize.
* If any part of this fails, we simply abort the resize.
*
* setup_new_flex_group_blocks handles a flex group as follow:
* 1. copy super block and GDT, and initialize group tables if necessary.
* In this step, we only set bits in blocks bitmaps for blocks taken by
* super block and GDT.
* 2. allocate group tables in block bitmaps, that is, set bits in block
* bitmap for blocks taken by group tables.
*/
static int setup_new_flex_group_blocks(struct super_block *sb,
struct ext4_new_flex_group_data *flex_gd)
{
int group_table_count[] = {1, 1, EXT4_SB(sb)->s_itb_per_group};
ext4_fsblk_t start;
ext4_fsblk_t block;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
struct ext4_new_group_data *group_data = flex_gd->groups;
__u16 *bg_flags = flex_gd->bg_flags;
handle_t *handle;
ext4_group_t group, count;
struct buffer_head *bh = NULL;
int reserved_gdb, i, j, err = 0, err2;
BUG_ON(!flex_gd->count || !group_data ||
group_data[0].group != sbi->s_groups_count);
reserved_gdb = le16_to_cpu(es->s_reserved_gdt_blocks);
/* This transaction may be extended/restarted along the way */
handle = ext4_journal_start_sb(sb, EXT4_MAX_TRANS_DATA);
if (IS_ERR(handle))
return PTR_ERR(handle);
group = group_data[0].group;
for (i = 0; i < flex_gd->count; i++, group++) {
unsigned long gdblocks;
gdblocks = ext4_bg_num_gdb(sb, group);
start = ext4_group_first_block_no(sb, group);
if (!ext4_bg_has_super(sb, group))
goto handle_itb;
/* Copy all of the GDT blocks into the backup in this group */
for (j = 0, block = start + 1; j < gdblocks; j++, block++) {
struct buffer_head *gdb;
ext4_debug("update backup group %#04llx\n", block);
err = extend_or_restart_transaction(handle, 1);
if (err)
goto out;
gdb = sb_getblk(sb, block);
if (!gdb) {
err = -EIO;
goto out;
}
err = ext4_journal_get_write_access(handle, gdb);
if (err) {
brelse(gdb);
goto out;
}
memcpy(gdb->b_data, sbi->s_group_desc[j]->b_data,
gdb->b_size);
set_buffer_uptodate(gdb);
err = ext4_handle_dirty_metadata(handle, NULL, gdb);
if (unlikely(err)) {
brelse(gdb);
goto out;
}
brelse(gdb);
}
/* Zero out all of the reserved backup group descriptor
* table blocks
*/
if (ext4_bg_has_super(sb, group)) {
err = sb_issue_zeroout(sb, gdblocks + start + 1,
reserved_gdb, GFP_NOFS);
if (err)
goto out;
}
handle_itb:
/* Initialize group tables of the grop @group */
if (!(bg_flags[i] & EXT4_BG_INODE_ZEROED))
goto handle_bb;
/* Zero out all of the inode table blocks */
block = group_data[i].inode_table;
ext4_debug("clear inode table blocks %#04llx -> %#04lx\n",
block, sbi->s_itb_per_group);
err = sb_issue_zeroout(sb, block, sbi->s_itb_per_group,
GFP_NOFS);
if (err)
goto out;
handle_bb:
if (bg_flags[i] & EXT4_BG_BLOCK_UNINIT)
goto handle_ib;
/* Initialize block bitmap of the @group */
block = group_data[i].block_bitmap;
err = extend_or_restart_transaction(handle, 1);
if (err)
goto out;
bh = bclean(handle, sb, block);
if (IS_ERR(bh)) {
err = PTR_ERR(bh);
goto out;
}
if (ext4_bg_has_super(sb, group)) {
ext4_debug("mark backup superblock %#04llx (+0)\n",
start);
ext4_set_bits(bh->b_data, 0, gdblocks + reserved_gdb +
1);
}
ext4_mark_bitmap_end(group_data[i].blocks_count,
sb->s_blocksize * 8, bh->b_data);
err = ext4_handle_dirty_metadata(handle, NULL, bh);
if (err)
goto out;
brelse(bh);
handle_ib:
if (bg_flags[i] & EXT4_BG_INODE_UNINIT)
continue;
/* Initialize inode bitmap of the @group */
block = group_data[i].inode_bitmap;
err = extend_or_restart_transaction(handle, 1);
if (err)
goto out;
/* Mark unused entries in inode bitmap used */
bh = bclean(handle, sb, block);
if (IS_ERR(bh)) {
err = PTR_ERR(bh);
goto out;
}
ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb),
sb->s_blocksize * 8, bh->b_data);
err = ext4_handle_dirty_metadata(handle, NULL, bh);
if (err)
goto out;
brelse(bh);
}
bh = NULL;
/* Mark group tables in block bitmap */
for (j = 0; j < GROUP_TABLE_COUNT; j++) {
count = group_table_count[j];
start = (&group_data[0].block_bitmap)[j];
block = start;
for (i = 1; i < flex_gd->count; i++) {
block += group_table_count[j];
if (block == (&group_data[i].block_bitmap)[j]) {
count += group_table_count[j];
continue;
}
err = set_flexbg_block_bitmap(sb, handle,
flex_gd, start, count);
if (err)
goto out;
count = group_table_count[j];
start = group_data[i].block_bitmap;
block = start;
}
if (count) {
err = set_flexbg_block_bitmap(sb, handle,
flex_gd, start, count);
if (err)
goto out;
}
}
out:
brelse(bh);
err2 = ext4_journal_stop(handle);
if (err2 && !err)
err = err2;
return err;
}
/*
* Iterate through the groups which hold BACKUP superblock/GDT copies in an
* ext4 filesystem. The counters should be initialized to 1, 5, and 7 before
* calling this for the first time. In a sparse filesystem it will be the
* sequence of powers of 3, 5, and 7: 1, 3, 5, 7, 9, 25, 27, 49, 81, ...
* For a non-sparse filesystem it will be every group: 1, 2, 3, 4, ...
*/
static unsigned ext4_list_backups(struct super_block *sb, unsigned *three,
unsigned *five, unsigned *seven)
{
unsigned *min = three;
int mult = 3;
unsigned ret;
if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER)) {
ret = *min;
*min += 1;
return ret;
}
if (*five < *min) {
min = five;
mult = 5;
}
if (*seven < *min) {
min = seven;
mult = 7;
}
ret = *min;
*min *= mult;
return ret;
}
/*
* Check that all of the backup GDT blocks are held in the primary GDT block.
* It is assumed that they are stored in group order. Returns the number of
* groups in current filesystem that have BACKUPS, or -ve error code.
*/
static int verify_reserved_gdb(struct super_block *sb,
ext4_group_t end,
struct buffer_head *primary)
{
const ext4_fsblk_t blk = primary->b_blocknr;
unsigned three = 1;
unsigned five = 5;
unsigned seven = 7;
unsigned grp;
__le32 *p = (__le32 *)primary->b_data;
int gdbackups = 0;
while ((grp = ext4_list_backups(sb, &three, &five, &seven)) < end) {
if (le32_to_cpu(*p++) !=
grp * EXT4_BLOCKS_PER_GROUP(sb) + blk){
ext4_warning(sb, "reserved GDT %llu"
" missing grp %d (%llu)",
blk, grp,
grp *
(ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) +
blk);
return -EINVAL;
}
if (++gdbackups > EXT4_ADDR_PER_BLOCK(sb))
return -EFBIG;
}
return gdbackups;
}
/*
* Called when we need to bring a reserved group descriptor table block into
* use from the resize inode. The primary copy of the new GDT block currently
* is an indirect block (under the double indirect block in the resize inode).
* The new backup GDT blocks will be stored as leaf blocks in this indirect
* block, in group order. Even though we know all the block numbers we need,
* we check to ensure that the resize inode has actually reserved these blocks.
*
* Don't need to update the block bitmaps because the blocks are still in use.
*
* We get all of the error cases out of the way, so that we are sure to not
* fail once we start modifying the data on disk, because JBD has no rollback.
*/
static int add_new_gdb(handle_t *handle, struct inode *inode,
ext4_group_t group)
{
struct super_block *sb = inode->i_sb;
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
unsigned long gdb_num = group / EXT4_DESC_PER_BLOCK(sb);
ext4_fsblk_t gdblock = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + gdb_num;
struct buffer_head **o_group_desc, **n_group_desc;
struct buffer_head *dind;
struct buffer_head *gdb_bh;
int gdbackups;
struct ext4_iloc iloc;
__le32 *data;
int err;
if (test_opt(sb, DEBUG))
printk(KERN_DEBUG
"EXT4-fs: ext4_add_new_gdb: adding group block %lu\n",
gdb_num);
/*
* If we are not using the primary superblock/GDT copy don't resize,
* because the user tools have no way of handling this. Probably a
* bad time to do it anyways.
*/
if (EXT4_SB(sb)->s_sbh->b_blocknr !=
le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) {
ext4_warning(sb, "won't resize using backup superblock at %llu",
(unsigned long long)EXT4_SB(sb)->s_sbh->b_blocknr);
return -EPERM;
}
gdb_bh = sb_bread(sb, gdblock);
if (!gdb_bh)
return -EIO;
gdbackups = verify_reserved_gdb(sb, group, gdb_bh);
if (gdbackups < 0) {
err = gdbackups;
goto exit_bh;
}
data = EXT4_I(inode)->i_data + EXT4_DIND_BLOCK;
dind = sb_bread(sb, le32_to_cpu(*data));
if (!dind) {
err = -EIO;
goto exit_bh;
}
data = (__le32 *)dind->b_data;
if (le32_to_cpu(data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)]) != gdblock) {
ext4_warning(sb, "new group %u GDT block %llu not reserved",
group, gdblock);
err = -EINVAL;
goto exit_dind;
}
err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
if (unlikely(err))
goto exit_dind;
err = ext4_journal_get_write_access(handle, gdb_bh);
if (unlikely(err))
goto exit_sbh;
err = ext4_journal_get_write_access(handle, dind);
if (unlikely(err))
ext4_std_error(sb, err);
/* ext4_reserve_inode_write() gets a reference on the iloc */
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (unlikely(err))
goto exit_dindj;
n_group_desc = ext4_kvmalloc((gdb_num + 1) *
sizeof(struct buffer_head *),
GFP_NOFS);
if (!n_group_desc) {
err = -ENOMEM;
ext4_warning(sb, "not enough memory for %lu groups",
gdb_num + 1);
goto exit_inode;
}
/*
* Finally, we have all of the possible failures behind us...
*
* Remove new GDT block from inode double-indirect block and clear out
* the new GDT block for use (which also "frees" the backup GDT blocks
* from the reserved inode). We don't need to change the bitmaps for
* these blocks, because they are marked as in-use from being in the
* reserved inode, and will become GDT blocks (primary and backup).
*/
data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)] = 0;
err = ext4_handle_dirty_metadata(handle, NULL, dind);
if (unlikely(err)) {
ext4_std_error(sb, err);
goto exit_inode;
}
inode->i_blocks -= (gdbackups + 1) * sb->s_blocksize >> 9;
ext4_mark_iloc_dirty(handle, inode, &iloc);
memset(gdb_bh->b_data, 0, sb->s_blocksize);
err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh);
if (unlikely(err)) {
ext4_std_error(sb, err);
goto exit_inode;
}
brelse(dind);
o_group_desc = EXT4_SB(sb)->s_group_desc;
memcpy(n_group_desc, o_group_desc,
EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *));
n_group_desc[gdb_num] = gdb_bh;
EXT4_SB(sb)->s_group_desc = n_group_desc;
EXT4_SB(sb)->s_gdb_count++;
ext4_kvfree(o_group_desc);
le16_add_cpu(&es->s_reserved_gdt_blocks, -1);
err = ext4_handle_dirty_super(handle, sb);
if (err)
ext4_std_error(sb, err);
return err;
exit_inode:
ext4_kvfree(n_group_desc);
/* ext4_handle_release_buffer(handle, iloc.bh); */
brelse(iloc.bh);
exit_dindj:
/* ext4_handle_release_buffer(handle, dind); */
exit_sbh:
/* ext4_handle_release_buffer(handle, EXT4_SB(sb)->s_sbh); */
exit_dind:
brelse(dind);
exit_bh:
brelse(gdb_bh);
ext4_debug("leaving with error %d\n", err);
return err;
}
/*
* Called when we are adding a new group which has a backup copy of each of
* the GDT blocks (i.e. sparse group) and there are reserved GDT blocks.
* We need to add these reserved backup GDT blocks to the resize inode, so
* that they are kept for future resizing and not allocated to files.
*
* Each reserved backup GDT block will go into a different indirect block.
* The indirect blocks are actually the primary reserved GDT blocks,
* so we know in advance what their block numbers are. We only get the
* double-indirect block to verify it is pointing to the primary reserved
* GDT blocks so we don't overwrite a data block by accident. The reserved
* backup GDT blocks are stored in their reserved primary GDT block.
*/
static int reserve_backup_gdb(handle_t *handle, struct inode *inode,
ext4_group_t group)
{
struct super_block *sb = inode->i_sb;
int reserved_gdb =le16_to_cpu(EXT4_SB(sb)->s_es->s_reserved_gdt_blocks);
struct buffer_head **primary;
struct buffer_head *dind;
struct ext4_iloc iloc;
ext4_fsblk_t blk;
__le32 *data, *end;
int gdbackups = 0;
int res, i;
int err;
primary = kmalloc(reserved_gdb * sizeof(*primary), GFP_NOFS);
if (!primary)
return -ENOMEM;
data = EXT4_I(inode)->i_data + EXT4_DIND_BLOCK;
dind = sb_bread(sb, le32_to_cpu(*data));
if (!dind) {
err = -EIO;
goto exit_free;
}
blk = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + EXT4_SB(sb)->s_gdb_count;
data = (__le32 *)dind->b_data + (EXT4_SB(sb)->s_gdb_count %
EXT4_ADDR_PER_BLOCK(sb));
end = (__le32 *)dind->b_data + EXT4_ADDR_PER_BLOCK(sb);
/* Get each reserved primary GDT block and verify it holds backups */
for (res = 0; res < reserved_gdb; res++, blk++) {
if (le32_to_cpu(*data) != blk) {
ext4_warning(sb, "reserved block %llu"
" not at offset %ld",
blk,
(long)(data - (__le32 *)dind->b_data));
err = -EINVAL;
goto exit_bh;
}
primary[res] = sb_bread(sb, blk);
if (!primary[res]) {
err = -EIO;
goto exit_bh;
}
gdbackups = verify_reserved_gdb(sb, group, primary[res]);
if (gdbackups < 0) {
brelse(primary[res]);
err = gdbackups;
goto exit_bh;
}
if (++data >= end)
data = (__le32 *)dind->b_data;
}
for (i = 0; i < reserved_gdb; i++) {
if ((err = ext4_journal_get_write_access(handle, primary[i]))) {
/*
int j;
for (j = 0; j < i; j++)
ext4_handle_release_buffer(handle, primary[j]);
*/
goto exit_bh;
}
}
if ((err = ext4_reserve_inode_write(handle, inode, &iloc)))
goto exit_bh;
/*
* Finally we can add each of the reserved backup GDT blocks from
* the new group to its reserved primary GDT block.
*/
blk = group * EXT4_BLOCKS_PER_GROUP(sb);
for (i = 0; i < reserved_gdb; i++) {
int err2;
data = (__le32 *)primary[i]->b_data;
/* printk("reserving backup %lu[%u] = %lu\n",
primary[i]->b_blocknr, gdbackups,
blk + primary[i]->b_blocknr); */
data[gdbackups] = cpu_to_le32(blk + primary[i]->b_blocknr);
err2 = ext4_handle_dirty_metadata(handle, NULL, primary[i]);
if (!err)
err = err2;
}
inode->i_blocks += reserved_gdb * sb->s_blocksize >> 9;
ext4_mark_iloc_dirty(handle, inode, &iloc);
exit_bh:
while (--res >= 0)
brelse(primary[res]);
brelse(dind);
exit_free:
kfree(primary);
return err;
}
/*
* Update the backup copies of the ext4 metadata. These don't need to be part
* of the main resize transaction, because e2fsck will re-write them if there
* is a problem (basically only OOM will cause a problem). However, we
* _should_ update the backups if possible, in case the primary gets trashed
* for some reason and we need to run e2fsck from a backup superblock. The
* important part is that the new block and inode counts are in the backup
* superblocks, and the location of the new group metadata in the GDT backups.
*
* We do not need take the s_resize_lock for this, because these
* blocks are not otherwise touched by the filesystem code when it is
* mounted. We don't need to worry about last changing from
* sbi->s_groups_count, because the worst that can happen is that we
* do not copy the full number of backups at this time. The resize
* which changed s_groups_count will backup again.
*/
static void update_backups(struct super_block *sb,
int blk_off, char *data, int size)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
const ext4_group_t last = sbi->s_groups_count;
const int bpg = EXT4_BLOCKS_PER_GROUP(sb);
unsigned three = 1;
unsigned five = 5;
unsigned seven = 7;
ext4_group_t group;
int rest = sb->s_blocksize - size;
handle_t *handle;
int err = 0, err2;
handle = ext4_journal_start_sb(sb, EXT4_MAX_TRANS_DATA);
if (IS_ERR(handle)) {
group = 1;
err = PTR_ERR(handle);
goto exit_err;
}
ext4_superblock_csum_set(sb, (struct ext4_super_block *)data);
while ((group = ext4_list_backups(sb, &three, &five, &seven)) < last) {
struct buffer_head *bh;
/* Out of journal space, and can't get more - abort - so sad */
if (ext4_handle_valid(handle) &&
handle->h_buffer_credits == 0 &&
ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA) &&
(err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA)))
break;
bh = sb_getblk(sb, group * bpg + blk_off);
if (!bh) {
err = -EIO;
break;
}
ext4_debug("update metadata backup %#04lx\n",
(unsigned long)bh->b_blocknr);