Blame view

fs/ext4/resize.c 49 KB
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1
  /*
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
2
   *  linux/fs/ext4/resize.c
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
3
   *
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
4
   * Support for resizing an ext4 filesystem while it is mounted.
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
5
6
7
8
9
   *
   * Copyright (C) 2001, 2002 Andreas Dilger <adilger@clusterfs.com>
   *
   * This could probably be made into a module, because it is not often in use.
   */
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
10
  #define EXT4FS_DEBUG
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
11

ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
12
13
  #include <linux/errno.h>
  #include <linux/slab.h>
3dcf54515   Christoph Hellwig   ext4: move header...
14
  #include "ext4_jbd2.h"
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
15

8f82f840e   Yongqiang Yang   ext4: prevent par...
16
17
18
19
20
21
  int ext4_resize_begin(struct super_block *sb)
  {
  	int ret = 0;
  
  	if (!capable(CAP_SYS_RESOURCE))
  		return -EPERM;
ce723c31b   Yongqiang Yang   ext4: prevent a f...
22
23
24
25
26
27
28
29
30
31
  	/*
  	 * 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
  ");
  		return -EPERM;
  	}
8f82f840e   Yongqiang Yang   ext4: prevent par...
32
33
34
35
36
37
38
39
40
41
42
  	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();
  }
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
43
44
45
46
  #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,
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
47
  			      struct ext4_new_group_data *input)
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
48
  {
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
49
50
  	struct ext4_sb_info *sbi = EXT4_SB(sb);
  	struct ext4_super_block *es = sbi->s_es;
bd81d8eec   Laurent Vivier   [PATCH] ext4: 64b...
51
  	ext4_fsblk_t start = ext4_blocks_count(es);
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
52
  	ext4_fsblk_t end = start + input->blocks_count;
fd2d42912   Avantika Mathur   ext4: add ext4_gr...
53
  	ext4_group_t group = input->group;
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
54
55
56
  	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) +
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
57
  		 le16_to_cpu(es->s_reserved_gdt_blocks)) : 0;
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
58
  	ext4_fsblk_t metaend = start + overhead;
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
59
  	struct buffer_head *bh = NULL;
3a5b2ecdd   Mingming Cao   [PATCH] ext4: swi...
60
  	ext4_grpblk_t free_blocks_count, offset;
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
61
62
63
64
65
66
  	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))
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
67
  		printk(KERN_DEBUG "EXT4-fs: adding %s group %u: %u blocks "
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
68
69
  		       "(%d free, %u reserved)
  ",
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
70
  		       ext4_bg_has_super(sb, input->group) ? "normal" :
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
71
72
  		       "no-super", input->group, input->blocks_count,
  		       free_blocks_count, input->reserved_blocks);
3a5b2ecdd   Mingming Cao   [PATCH] ext4: swi...
73
  	ext4_get_group_no_and_offset(sb, start, NULL, &offset);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
74
  	if (group != sbi->s_groups_count)
12062dddd   Eric Sandeen   ext4: move __func...
75
  		ext4_warning(sb, "Cannot add at group %u (only %u groups)",
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
76
  			     input->group, sbi->s_groups_count);
3a5b2ecdd   Mingming Cao   [PATCH] ext4: swi...
77
  	else if (offset != 0)
12062dddd   Eric Sandeen   ext4: move __func...
78
  			ext4_warning(sb, "Last group not full");
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
79
  	else if (input->reserved_blocks > input->blocks_count / 5)
12062dddd   Eric Sandeen   ext4: move __func...
80
  		ext4_warning(sb, "Reserved blocks too high (%u)",
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
81
82
  			     input->reserved_blocks);
  	else if (free_blocks_count < 0)
12062dddd   Eric Sandeen   ext4: move __func...
83
  		ext4_warning(sb, "Bad blocks count %u",
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
84
85
  			     input->blocks_count);
  	else if (!(bh = sb_bread(sb, end - 1)))
12062dddd   Eric Sandeen   ext4: move __func...
86
  		ext4_warning(sb, "Cannot read last block (%llu)",
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
87
88
  			     end - 1);
  	else if (outside(input->block_bitmap, start, end))
12062dddd   Eric Sandeen   ext4: move __func...
89
  		ext4_warning(sb, "Block bitmap not in group (block %llu)",
1939e49a0   Randy Dunlap   [PATCH] ext4: fix...
90
  			     (unsigned long long)input->block_bitmap);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
91
  	else if (outside(input->inode_bitmap, start, end))
12062dddd   Eric Sandeen   ext4: move __func...
92
  		ext4_warning(sb, "Inode bitmap not in group (block %llu)",
1939e49a0   Randy Dunlap   [PATCH] ext4: fix...
93
  			     (unsigned long long)input->inode_bitmap);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
94
  	else if (outside(input->inode_table, start, end) ||
2b2d6d019   Theodore Ts'o   ext4: Cleanup whi...
95
  		 outside(itend - 1, start, end))
12062dddd   Eric Sandeen   ext4: move __func...
96
  		ext4_warning(sb, "Inode table not in group (blocks %llu-%llu)",
1939e49a0   Randy Dunlap   [PATCH] ext4: fix...
97
  			     (unsigned long long)input->inode_table, itend - 1);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
98
  	else if (input->inode_bitmap == input->block_bitmap)
12062dddd   Eric Sandeen   ext4: move __func...
99
  		ext4_warning(sb, "Block bitmap same as inode bitmap (%llu)",
1939e49a0   Randy Dunlap   [PATCH] ext4: fix...
100
  			     (unsigned long long)input->block_bitmap);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
101
  	else if (inside(input->block_bitmap, input->inode_table, itend))
12062dddd   Eric Sandeen   ext4: move __func...
102
103
  		ext4_warning(sb, "Block bitmap (%llu) in inode table "
  			     "(%llu-%llu)",
1939e49a0   Randy Dunlap   [PATCH] ext4: fix...
104
105
  			     (unsigned long long)input->block_bitmap,
  			     (unsigned long long)input->inode_table, itend - 1);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
106
  	else if (inside(input->inode_bitmap, input->inode_table, itend))
12062dddd   Eric Sandeen   ext4: move __func...
107
108
  		ext4_warning(sb, "Inode bitmap (%llu) in inode table "
  			     "(%llu-%llu)",
1939e49a0   Randy Dunlap   [PATCH] ext4: fix...
109
110
  			     (unsigned long long)input->inode_bitmap,
  			     (unsigned long long)input->inode_table, itend - 1);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
111
  	else if (inside(input->block_bitmap, start, metaend))
12062dddd   Eric Sandeen   ext4: move __func...
112
  		ext4_warning(sb, "Block bitmap (%llu) in GDT table (%llu-%llu)",
1939e49a0   Randy Dunlap   [PATCH] ext4: fix...
113
114
  			     (unsigned long long)input->block_bitmap,
  			     start, metaend - 1);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
115
  	else if (inside(input->inode_bitmap, start, metaend))
12062dddd   Eric Sandeen   ext4: move __func...
116
  		ext4_warning(sb, "Inode bitmap (%llu) in GDT table (%llu-%llu)",
1939e49a0   Randy Dunlap   [PATCH] ext4: fix...
117
118
  			     (unsigned long long)input->inode_bitmap,
  			     start, metaend - 1);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
119
  	else if (inside(input->inode_table, start, metaend) ||
2b2d6d019   Theodore Ts'o   ext4: Cleanup whi...
120
  		 inside(itend - 1, start, metaend))
12062dddd   Eric Sandeen   ext4: move __func...
121
122
  		ext4_warning(sb, "Inode table (%llu-%llu) overlaps GDT table "
  			     "(%llu-%llu)",
1939e49a0   Randy Dunlap   [PATCH] ext4: fix...
123
124
  			     (unsigned long long)input->inode_table,
  			     itend - 1, start, metaend - 1);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
125
126
127
128
129
130
  	else
  		err = 0;
  	brelse(bh);
  
  	return err;
  }
28c7bac00   Yongqiang Yang   ext4: add a struc...
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
  /*
   * 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;
  
  	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);
  }
3fbea4b36   Yongqiang Yang   ext4: add a new f...
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
  /*
   * 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
   */
  static void 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;
  	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;
  
  	BUG_ON(src_group >= group_data[0].group + flex_gd->count);
  	/* 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:
  ", flex_gd->count,
  		       flexbg_size);
  
  		for (i = 0; i < flex_gd->count; i++) {
  			printk(KERN_DEBUG "adding %s group %u: %u "
  			       "blocks (%d free)
  ",
  			       ext4_bg_has_super(sb, group + i) ? "normal" :
  			       "no-super", group + i,
  			       group_data[i].blocks_count,
  			       group_data[i].free_blocks_count);
  		}
  	}
  }
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
297
  static struct buffer_head *bclean(handle_t *handle, struct super_block *sb,
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
298
  				  ext4_fsblk_t blk)
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
299
300
301
302
303
304
305
  {
  	struct buffer_head *bh;
  	int err;
  
  	bh = sb_getblk(sb, blk);
  	if (!bh)
  		return ERR_PTR(-EIO);
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
306
  	if ((err = ext4_journal_get_write_access(handle, bh))) {
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
307
308
309
  		brelse(bh);
  		bh = ERR_PTR(err);
  	} else {
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
310
311
  		memset(bh->b_data, 0, sb->s_blocksize);
  		set_buffer_uptodate(bh);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
312
313
314
315
316
317
  	}
  
  	return bh;
  }
  
  /*
149041070   Eric Sandeen   ext4: lighten up ...
318
319
320
321
   * 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.
   */
6d40bc5a7   Yongqiang Yang   ext4: simplify jo...
322
  static int extend_or_restart_transaction(handle_t *handle, int thresh)
149041070   Eric Sandeen   ext4: lighten up ...
323
324
  {
  	int err;
0390131ba   Frank Mayhar   ext4: Allow ext4 ...
325
  	if (ext4_handle_has_enough_credits(handle, thresh))
149041070   Eric Sandeen   ext4: lighten up ...
326
327
328
329
330
331
  		return 0;
  
  	err = ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA);
  	if (err < 0)
  		return err;
  	if (err) {
6d40bc5a7   Yongqiang Yang   ext4: simplify jo...
332
333
  		err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA);
  		if (err)
149041070   Eric Sandeen   ext4: lighten up ...
334
  			return err;
2b2d6d019   Theodore Ts'o   ext4: Cleanup whi...
335
  	}
149041070   Eric Sandeen   ext4: lighten up ...
336
337
338
339
340
  
  	return 0;
  }
  
  /*
33afdcc54   Yongqiang Yang   ext4: add a funct...
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
   * 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
  ", 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)
  ", 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);
  
  		/* 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
  ", 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;
  		}
  
  		/* 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
  ",
  			   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)
  ",
  				   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;
  }
  
  /*
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
596
   * Iterate through the groups which hold BACKUP superblock/GDT copies in an
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
597
   * ext4 filesystem.  The counters should be initialized to 1, 5, and 7 before
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
598
599
600
601
   * 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, ...
   */
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
602
  static unsigned ext4_list_backups(struct super_block *sb, unsigned *three,
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
603
604
605
606
607
  				  unsigned *five, unsigned *seven)
  {
  	unsigned *min = three;
  	int mult = 3;
  	unsigned ret;
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
608
609
  	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
  					EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER)) {
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
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
  		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,
c72df9f92   Yongqiang Yang   ext4: pass verify...
636
  			       ext4_group_t end,
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
637
638
  			       struct buffer_head *primary)
  {
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
639
  	const ext4_fsblk_t blk = primary->b_blocknr;
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
640
641
642
643
644
645
  	unsigned three = 1;
  	unsigned five = 5;
  	unsigned seven = 7;
  	unsigned grp;
  	__le32 *p = (__le32 *)primary->b_data;
  	int gdbackups = 0;
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
646
  	while ((grp = ext4_list_backups(sb, &three, &five, &seven)) < end) {
bd81d8eec   Laurent Vivier   [PATCH] ext4: 64b...
647
648
  		if (le32_to_cpu(*p++) !=
  		    grp * EXT4_BLOCKS_PER_GROUP(sb) + blk){
12062dddd   Eric Sandeen   ext4: move __func...
649
  			ext4_warning(sb, "reserved GDT %llu"
2ae021076   Mingming Cao   [PATCH] ext4: blk...
650
  				     " missing grp %d (%llu)",
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
651
  				     blk, grp,
bd81d8eec   Laurent Vivier   [PATCH] ext4: 64b...
652
653
654
  				     grp *
  				     (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) +
  				     blk);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
655
656
  			return -EINVAL;
  		}
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
657
  		if (++gdbackups > EXT4_ADDR_PER_BLOCK(sb))
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
  			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,
2f9197101   Yongqiang Yang   ext4: simplify pa...
678
  		       ext4_group_t group)
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
679
680
  {
  	struct super_block *sb = inode->i_sb;
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
681
  	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
2f9197101   Yongqiang Yang   ext4: simplify pa...
682
  	unsigned long gdb_num = group / EXT4_DESC_PER_BLOCK(sb);
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
683
  	ext4_fsblk_t gdblock = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + gdb_num;
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
684
685
  	struct buffer_head **o_group_desc, **n_group_desc;
  	struct buffer_head *dind;
2f9197101   Yongqiang Yang   ext4: simplify pa...
686
  	struct buffer_head *gdb_bh;
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
687
  	int gdbackups;
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
688
  	struct ext4_iloc iloc;
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
689
690
691
692
693
  	__le32 *data;
  	int err;
  
  	if (test_opt(sb, DEBUG))
  		printk(KERN_DEBUG
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
694
695
  		       "EXT4-fs: ext4_add_new_gdb: adding group block %lu
  ",
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
696
  		       gdb_num);
af5bc92dd   Theodore Ts'o   ext4: Fix whitesp...
697
698
  	/*
  	 * If we are not using the primary superblock/GDT copy don't resize,
2b2d6d019   Theodore Ts'o   ext4: Cleanup whi...
699
700
701
           * because the user tools have no way of handling this.  Probably a
           * bad time to do it anyways.
           */
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
702
703
  	if (EXT4_SB(sb)->s_sbh->b_blocknr !=
  	    le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) {
12062dddd   Eric Sandeen   ext4: move __func...
704
  		ext4_warning(sb, "won't resize using backup superblock at %llu",
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
705
  			(unsigned long long)EXT4_SB(sb)->s_sbh->b_blocknr);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
706
707
  		return -EPERM;
  	}
2f9197101   Yongqiang Yang   ext4: simplify pa...
708
709
  	gdb_bh = sb_bread(sb, gdblock);
  	if (!gdb_bh)
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
710
  		return -EIO;
c72df9f92   Yongqiang Yang   ext4: pass verify...
711
  	gdbackups = verify_reserved_gdb(sb, group, gdb_bh);
2f9197101   Yongqiang Yang   ext4: simplify pa...
712
  	if (gdbackups < 0) {
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
713
714
715
  		err = gdbackups;
  		goto exit_bh;
  	}
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
716
  	data = EXT4_I(inode)->i_data + EXT4_DIND_BLOCK;
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
717
718
719
720
721
722
723
  	dind = sb_bread(sb, le32_to_cpu(*data));
  	if (!dind) {
  		err = -EIO;
  		goto exit_bh;
  	}
  
  	data = (__le32 *)dind->b_data;
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
724
  	if (le32_to_cpu(data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)]) != gdblock) {
12062dddd   Eric Sandeen   ext4: move __func...
725
  		ext4_warning(sb, "new group %u GDT block %llu not reserved",
2f9197101   Yongqiang Yang   ext4: simplify pa...
726
  			     group, gdblock);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
727
728
729
  		err = -EINVAL;
  		goto exit_dind;
  	}
b40971426   Theodore Ts'o   ext4: add error c...
730
731
  	err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
  	if (unlikely(err))
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
732
  		goto exit_dind;
2f9197101   Yongqiang Yang   ext4: simplify pa...
733
  	err = ext4_journal_get_write_access(handle, gdb_bh);
b40971426   Theodore Ts'o   ext4: add error c...
734
  	if (unlikely(err))
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
735
  		goto exit_sbh;
b40971426   Theodore Ts'o   ext4: add error c...
736
737
738
  	err = ext4_journal_get_write_access(handle, dind);
  	if (unlikely(err))
  		ext4_std_error(sb, err);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
739

617ba13b3   Mingming Cao   [PATCH] ext4: ren...
740
  	/* ext4_reserve_inode_write() gets a reference on the iloc */
b40971426   Theodore Ts'o   ext4: add error c...
741
742
  	err = ext4_reserve_inode_write(handle, inode, &iloc);
  	if (unlikely(err))
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
743
  		goto exit_dindj;
f18a5f21c   Theodore Ts'o   ext4: use ext4_kv...
744
745
746
  	n_group_desc = ext4_kvmalloc((gdb_num + 1) *
  				     sizeof(struct buffer_head *),
  				     GFP_NOFS);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
747
748
  	if (!n_group_desc) {
  		err = -ENOMEM;
f18a5f21c   Theodore Ts'o   ext4: use ext4_kv...
749
750
  		ext4_warning(sb, "not enough memory for %lu groups",
  			     gdb_num + 1);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
751
752
753
754
755
756
757
758
759
760
761
762
  		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).
  	 */
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
763
  	data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)] = 0;
b40971426   Theodore Ts'o   ext4: add error c...
764
765
766
767
768
  	err = ext4_handle_dirty_metadata(handle, NULL, dind);
  	if (unlikely(err)) {
  		ext4_std_error(sb, err);
  		goto exit_inode;
  	}
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
769
  	inode->i_blocks -= (gdbackups + 1) * sb->s_blocksize >> 9;
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
770
  	ext4_mark_iloc_dirty(handle, inode, &iloc);
2f9197101   Yongqiang Yang   ext4: simplify pa...
771
772
  	memset(gdb_bh->b_data, 0, sb->s_blocksize);
  	err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh);
b40971426   Theodore Ts'o   ext4: add error c...
773
774
775
776
777
  	if (unlikely(err)) {
  		ext4_std_error(sb, err);
  		goto exit_inode;
  	}
  	brelse(dind);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
778

617ba13b3   Mingming Cao   [PATCH] ext4: ren...
779
  	o_group_desc = EXT4_SB(sb)->s_group_desc;
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
780
  	memcpy(n_group_desc, o_group_desc,
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
781
  	       EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *));
2f9197101   Yongqiang Yang   ext4: simplify pa...
782
  	n_group_desc[gdb_num] = gdb_bh;
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
783
784
  	EXT4_SB(sb)->s_group_desc = n_group_desc;
  	EXT4_SB(sb)->s_gdb_count++;
f18a5f21c   Theodore Ts'o   ext4: use ext4_kv...
785
  	ext4_kvfree(o_group_desc);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
786

e8546d061   Marcin Slusarz   ext4: le*_add_cpu...
787
  	le16_add_cpu(&es->s_reserved_gdt_blocks, -1);
b40971426   Theodore Ts'o   ext4: add error c...
788
789
790
  	err = ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
  	if (err)
  		ext4_std_error(sb, err);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
791

b40971426   Theodore Ts'o   ext4: add error c...
792
  	return err;
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
793
794
  
  exit_inode:
f18a5f21c   Theodore Ts'o   ext4: use ext4_kv...
795
  	ext4_kvfree(n_group_desc);
537a03103   Amir Goldstein   ext4: unify the e...
796
  	/* ext4_handle_release_buffer(handle, iloc.bh); */
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
797
798
  	brelse(iloc.bh);
  exit_dindj:
537a03103   Amir Goldstein   ext4: unify the e...
799
  	/* ext4_handle_release_buffer(handle, dind); */
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
800
  exit_sbh:
537a03103   Amir Goldstein   ext4: unify the e...
801
  	/* ext4_handle_release_buffer(handle, EXT4_SB(sb)->s_sbh); */
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
802
803
804
  exit_dind:
  	brelse(dind);
  exit_bh:
2f9197101   Yongqiang Yang   ext4: simplify pa...
805
  	brelse(gdb_bh);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
806

617ba13b3   Mingming Cao   [PATCH] ext4: ren...
807
808
  	ext4_debug("leaving with error %d
  ", err);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
  	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,
668f4dc55   Yongqiang Yang   ext4: simplify pa...
826
  			      ext4_group_t group)
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
827
828
  {
  	struct super_block *sb = inode->i_sb;
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
829
  	int reserved_gdb =le16_to_cpu(EXT4_SB(sb)->s_es->s_reserved_gdt_blocks);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
830
831
  	struct buffer_head **primary;
  	struct buffer_head *dind;
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
832
833
  	struct ext4_iloc iloc;
  	ext4_fsblk_t blk;
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
834
835
836
837
  	__le32 *data, *end;
  	int gdbackups = 0;
  	int res, i;
  	int err;
216553c4b   Josef Bacik   ext4: fix wrong g...
838
  	primary = kmalloc(reserved_gdb * sizeof(*primary), GFP_NOFS);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
839
840
  	if (!primary)
  		return -ENOMEM;
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
841
  	data = EXT4_I(inode)->i_data + EXT4_DIND_BLOCK;
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
842
843
844
845
846
  	dind = sb_bread(sb, le32_to_cpu(*data));
  	if (!dind) {
  		err = -EIO;
  		goto exit_free;
  	}
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
847
  	blk = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + EXT4_SB(sb)->s_gdb_count;
944600930   Josef Bacik   ext4: fix online ...
848
849
  	data = (__le32 *)dind->b_data + (EXT4_SB(sb)->s_gdb_count %
  					 EXT4_ADDR_PER_BLOCK(sb));
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
850
  	end = (__le32 *)dind->b_data + EXT4_ADDR_PER_BLOCK(sb);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
851
852
853
854
  
  	/* 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) {
12062dddd   Eric Sandeen   ext4: move __func...
855
  			ext4_warning(sb, "reserved block %llu"
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
856
857
858
859
860
861
862
863
864
865
866
  				     " 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;
  		}
c72df9f92   Yongqiang Yang   ext4: pass verify...
867
868
  		gdbackups = verify_reserved_gdb(sb, group, primary[res]);
  		if (gdbackups < 0) {
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
869
870
871
872
873
874
875
876
877
  			brelse(primary[res]);
  			err = gdbackups;
  			goto exit_bh;
  		}
  		if (++data >= end)
  			data = (__le32 *)dind->b_data;
  	}
  
  	for (i = 0; i < reserved_gdb; i++) {
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
878
  		if ((err = ext4_journal_get_write_access(handle, primary[i]))) {
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
879
880
881
  			/*
  			int j;
  			for (j = 0; j < i; j++)
537a03103   Amir Goldstein   ext4: unify the e...
882
  				ext4_handle_release_buffer(handle, primary[j]);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
883
884
885
886
  			 */
  			goto exit_bh;
  		}
  	}
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
887
  	if ((err = ext4_reserve_inode_write(handle, inode, &iloc)))
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
888
889
890
891
892
893
  		goto exit_bh;
  
  	/*
  	 * Finally we can add each of the reserved backup GDT blocks from
  	 * the new group to its reserved primary GDT block.
  	 */
668f4dc55   Yongqiang Yang   ext4: simplify pa...
894
  	blk = group * EXT4_BLOCKS_PER_GROUP(sb);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
895
896
897
898
899
900
901
902
  	for (i = 0; i < reserved_gdb; i++) {
  		int err2;
  		data = (__le32 *)primary[i]->b_data;
  		/* printk("reserving backup %lu[%u] = %lu
  ",
  		       primary[i]->b_blocknr, gdbackups,
  		       blk + primary[i]->b_blocknr); */
  		data[gdbackups] = cpu_to_le32(blk + primary[i]->b_blocknr);
0390131ba   Frank Mayhar   ext4: Allow ext4 ...
903
  		err2 = ext4_handle_dirty_metadata(handle, NULL, primary[i]);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
904
905
906
907
  		if (!err)
  			err = err2;
  	}
  	inode->i_blocks += reserved_gdb * sb->s_blocksize >> 9;
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
908
  	ext4_mark_iloc_dirty(handle, inode, &iloc);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
909
910
911
912
913
914
915
916
917
918
919
920
921
  
  exit_bh:
  	while (--res >= 0)
  		brelse(primary[res]);
  	brelse(dind);
  
  exit_free:
  	kfree(primary);
  
  	return err;
  }
  
  /*
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
922
   * Update the backup copies of the ext4 metadata.  These don't need to be part
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
923
924
925
926
927
928
929
   * 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.
   *
32ed5058c   Theodore Ts'o   ext4: Replace loc...
930
931
932
933
934
935
   * 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.
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
936
937
938
939
   */
  static void update_backups(struct super_block *sb,
  			   int blk_off, char *data, int size)
  {
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
940
  	struct ext4_sb_info *sbi = EXT4_SB(sb);
fd2d42912   Avantika Mathur   ext4: add ext4_gr...
941
  	const ext4_group_t last = sbi->s_groups_count;
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
942
  	const int bpg = EXT4_BLOCKS_PER_GROUP(sb);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
943
944
945
  	unsigned three = 1;
  	unsigned five = 5;
  	unsigned seven = 7;
fd2d42912   Avantika Mathur   ext4: add ext4_gr...
946
  	ext4_group_t group;
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
947
948
949
  	int rest = sb->s_blocksize - size;
  	handle_t *handle;
  	int err = 0, err2;
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
950
  	handle = ext4_journal_start_sb(sb, EXT4_MAX_TRANS_DATA);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
951
952
953
954
955
  	if (IS_ERR(handle)) {
  		group = 1;
  		err = PTR_ERR(handle);
  		goto exit_err;
  	}
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
956
  	while ((group = ext4_list_backups(sb, &three, &five, &seven)) < last) {
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
957
958
959
  		struct buffer_head *bh;
  
  		/* Out of journal space, and can't get more - abort - so sad */
0390131ba   Frank Mayhar   ext4: Allow ext4 ...
960
961
  		if (ext4_handle_valid(handle) &&
  		    handle->h_buffer_credits == 0 &&
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
962
963
  		    ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA) &&
  		    (err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA)))
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
964
965
966
967
968
969
970
  			break;
  
  		bh = sb_getblk(sb, group * bpg + blk_off);
  		if (!bh) {
  			err = -EIO;
  			break;
  		}
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
971
972
  		ext4_debug("update metadata backup %#04lx
  ",
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
973
  			  (unsigned long)bh->b_blocknr);
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
974
  		if ((err = ext4_journal_get_write_access(handle, bh)))
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
975
976
977
978
979
980
981
  			break;
  		lock_buffer(bh);
  		memcpy(bh->b_data, data, size);
  		if (rest)
  			memset(bh->b_data + size, 0, rest);
  		set_buffer_uptodate(bh);
  		unlock_buffer(bh);
b40971426   Theodore Ts'o   ext4: add error c...
982
983
984
  		err = ext4_handle_dirty_metadata(handle, NULL, bh);
  		if (unlikely(err))
  			ext4_std_error(sb, err);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
985
986
  		brelse(bh);
  	}
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
987
  	if ((err2 = ext4_journal_stop(handle)) && !err)
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
  		err = err2;
  
  	/*
  	 * Ugh! Need to have e2fsck write the backup copies.  It is too
  	 * late to revert the resize, we shouldn't fail just because of
  	 * the backup copies (they are only needed in case of corruption).
  	 *
  	 * However, if we got here we have a journal problem too, so we
  	 * can't really start a transaction to mark the superblock.
  	 * Chicken out and just set the flag on the hope it will be written
  	 * to disk, and if not - we will simply wait until next fsck.
  	 */
  exit_err:
  	if (err) {
12062dddd   Eric Sandeen   ext4: move __func...
1002
  		ext4_warning(sb, "can't update backup for group %u (err %d), "
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1003
  			     "forcing fsck on next reboot", group, err);
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
1004
1005
  		sbi->s_mount_state &= ~EXT4_VALID_FS;
  		sbi->s_es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1006
1007
1008
  		mark_buffer_dirty(sbi->s_sbh);
  	}
  }
bb08c1e7d   Yongqiang Yang   ext4: add a funct...
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
  /*
   * ext4_add_new_descs() adds @count group descriptor of groups
   * starting at @group
   *
   * @handle: journal handle
   * @sb: super block
   * @group: the group no. of the first group desc to be added
   * @resize_inode: the resize inode
   * @count: number of group descriptors to be added
   */
  static int ext4_add_new_descs(handle_t *handle, struct super_block *sb,
  			      ext4_group_t group, struct inode *resize_inode,
  			      ext4_group_t count)
  {
  	struct ext4_sb_info *sbi = EXT4_SB(sb);
  	struct ext4_super_block *es = sbi->s_es;
  	struct buffer_head *gdb_bh;
  	int i, gdb_off, gdb_num, err = 0;
  
  	for (i = 0; i < count; i++, group++) {
  		int reserved_gdb = ext4_bg_has_super(sb, group) ?
  			le16_to_cpu(es->s_reserved_gdt_blocks) : 0;
  
  		gdb_off = group % EXT4_DESC_PER_BLOCK(sb);
  		gdb_num = group / EXT4_DESC_PER_BLOCK(sb);
  
  		/*
  		 * We will only either add reserved group blocks to a backup group
  		 * or remove reserved blocks for the first group in a new group block.
  		 * Doing both would be mean more complex code, and sane people don't
  		 * use non-sparse filesystems anymore.  This is already checked above.
  		 */
  		if (gdb_off) {
  			gdb_bh = sbi->s_group_desc[gdb_num];
  			err = ext4_journal_get_write_access(handle, gdb_bh);
  
  			if (!err && reserved_gdb && ext4_bg_num_gdb(sb, group))
  				err = reserve_backup_gdb(handle, resize_inode, group);
  		} else
  			err = add_new_gdb(handle, resize_inode, group);
  		if (err)
  			break;
  	}
  	return err;
  }
083f5b24c   Yongqiang Yang   ext4: add a funct...
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
  /*
   * ext4_setup_new_descs() will set up the group descriptor descriptors of a flex bg
   */
  static int ext4_setup_new_descs(handle_t *handle, struct super_block *sb,
  				struct ext4_new_flex_group_data *flex_gd)
  {
  	struct ext4_new_group_data	*group_data = flex_gd->groups;
  	struct ext4_group_desc		*gdp;
  	struct ext4_sb_info		*sbi = EXT4_SB(sb);
  	struct buffer_head		*gdb_bh;
  	ext4_group_t			group;
  	__u16				*bg_flags = flex_gd->bg_flags;
  	int				i, gdb_off, gdb_num, err = 0;
  	
  
  	for (i = 0; i < flex_gd->count; i++, group_data++, bg_flags++) {
  		group = group_data->group;
  
  		gdb_off = group % EXT4_DESC_PER_BLOCK(sb);
  		gdb_num = group / EXT4_DESC_PER_BLOCK(sb);
  
  		/*
  		 * get_write_access() has been called on gdb_bh by ext4_add_new_desc().
  		 */
  		gdb_bh = sbi->s_group_desc[gdb_num];
  		/* Update group descriptor block for new group */
  		gdp = (struct ext4_group_desc *)((char *)gdb_bh->b_data +
  						 gdb_off * EXT4_DESC_SIZE(sb));
  
  		memset(gdp, 0, EXT4_DESC_SIZE(sb));
  		ext4_block_bitmap_set(sb, gdp, group_data->block_bitmap);
  		ext4_inode_bitmap_set(sb, gdp, group_data->inode_bitmap);
  		ext4_inode_table_set(sb, gdp, group_data->inode_table);
  		ext4_free_group_clusters_set(sb, gdp,
  					     EXT4_B2C(sbi, group_data->free_blocks_count));
  		ext4_free_inodes_set(sb, gdp, EXT4_INODES_PER_GROUP(sb));
  		gdp->bg_flags = cpu_to_le16(*bg_flags);
  		gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
  
  		err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh);
  		if (unlikely(err)) {
  			ext4_std_error(sb, err);
  			break;
  		}
  
  		/*
  		 * We can allocate memory for mb_alloc based on the new group
  		 * descriptor
  		 */
  		err = ext4_mb_add_groupinfo(sb, group, gdp);
  		if (err)
  			break;
  	}
  	return err;
  }
2e10e2f2e   Yongqiang Yang   ext4: add a funct...
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
  /*
   * ext4_update_super() updates the super block so that the newly added
   * groups can be seen by the filesystem.
   *
   * @sb: super block
   * @flex_gd: new added groups
   */
  static void ext4_update_super(struct super_block *sb,
  			     struct ext4_new_flex_group_data *flex_gd)
  {
  	ext4_fsblk_t blocks_count = 0;
  	ext4_fsblk_t free_blocks = 0;
  	ext4_fsblk_t reserved_blocks = 0;
  	struct ext4_new_group_data *group_data = flex_gd->groups;
  	struct ext4_sb_info *sbi = EXT4_SB(sb);
  	struct ext4_super_block *es = sbi->s_es;
  	int i;
  
  	BUG_ON(flex_gd->count == 0 || group_data == NULL);
  	/*
  	 * Make the new blocks and inodes valid next.  We do this before
  	 * increasing the group count so that once the group is enabled,
  	 * all of its blocks and inodes are already valid.
  	 *
  	 * We always allocate group-by-group, then block-by-block or
  	 * inode-by-inode within a group, so enabling these
  	 * blocks/inodes before the group is live won't actually let us
  	 * allocate the new space yet.
  	 */
  	for (i = 0; i < flex_gd->count; i++) {
  		blocks_count += group_data[i].blocks_count;
  		free_blocks += group_data[i].free_blocks_count;
  	}
  
  	reserved_blocks = ext4_r_blocks_count(es) * 100;
  	do_div(reserved_blocks, ext4_blocks_count(es));
  	reserved_blocks *= blocks_count;
  	do_div(reserved_blocks, 100);
  
  	ext4_blocks_count_set(es, ext4_blocks_count(es) + blocks_count);
  	le32_add_cpu(&es->s_inodes_count, EXT4_INODES_PER_GROUP(sb) *
  		     flex_gd->count);
  
  	/*
  	 * We need to protect s_groups_count against other CPUs seeing
  	 * inconsistent state in the superblock.
  	 *
  	 * The precise rules we use are:
  	 *
  	 * * Writers must perform a smp_wmb() after updating all
  	 *   dependent data and before modifying the groups count
  	 *
  	 * * Readers must perform an smp_rmb() after reading the groups
  	 *   count and before reading any dependent data.
  	 *
  	 * NB. These rules can be relaxed when checking the group count
  	 * while freeing data, as we can only allocate from a block
  	 * group after serialising against the group count, and we can
  	 * only then free after serialising in turn against that
  	 * allocation.
  	 */
  	smp_wmb();
  
  	/* Update the global fs size fields */
  	sbi->s_groups_count += flex_gd->count;
  
  	/* Update the reserved block counts only once the new group is
  	 * active. */
  	ext4_r_blocks_count_set(es, ext4_r_blocks_count(es) +
  				reserved_blocks);
  
  	/* Update the free space counts */
  	percpu_counter_add(&sbi->s_freeclusters_counter,
  			   EXT4_B2C(sbi, free_blocks));
  	percpu_counter_add(&sbi->s_freeinodes_counter,
  			   EXT4_INODES_PER_GROUP(sb) * flex_gd->count);
  
  	if (EXT4_HAS_INCOMPAT_FEATURE(sb,
  				      EXT4_FEATURE_INCOMPAT_FLEX_BG) &&
  	    sbi->s_log_groups_per_flex) {
  		ext4_group_t flex_group;
  		flex_group = ext4_flex_group(sbi, group_data[0].group);
  		atomic_add(EXT4_B2C(sbi, free_blocks),
  			   &sbi->s_flex_groups[flex_group].free_clusters);
  		atomic_add(EXT4_INODES_PER_GROUP(sb) * flex_gd->count,
  			   &sbi->s_flex_groups[flex_group].free_inodes);
  	}
  
  	if (test_opt(sb, DEBUG))
  		printk(KERN_DEBUG "EXT4-fs: added group %u:"
  		       "%llu blocks(%llu free %llu reserved)
  ", flex_gd->count,
  		       blocks_count, free_blocks, reserved_blocks);
  }
4bac1f8ce   Yongqiang Yang   ext4: add a new f...
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
  /* Add a flex group to an fs. Ensure we handle all possible error conditions
   * _before_ we start modifying the filesystem, because we cannot abort the
   * transaction and not have it write the data to disk.
   */
  static int ext4_flex_group_add(struct super_block *sb,
  			       struct inode *resize_inode,
  			       struct ext4_new_flex_group_data *flex_gd)
  {
  	struct ext4_sb_info *sbi = EXT4_SB(sb);
  	struct ext4_super_block *es = sbi->s_es;
  	ext4_fsblk_t o_blocks_count;
  	ext4_grpblk_t last;
  	ext4_group_t group;
  	handle_t *handle;
  	unsigned reserved_gdb;
  	int err = 0, err2 = 0, credit;
  
  	BUG_ON(!flex_gd->count || !flex_gd->groups || !flex_gd->bg_flags);
  
  	reserved_gdb = le16_to_cpu(es->s_reserved_gdt_blocks);
  	o_blocks_count = ext4_blocks_count(es);
  	ext4_get_group_no_and_offset(sb, o_blocks_count, &group, &last);
  	BUG_ON(last);
  
  	err = setup_new_flex_group_blocks(sb, flex_gd);
  	if (err)
  		goto exit;
  	/*
  	 * We will always be modifying at least the superblock and  GDT
  	 * block.  If we are adding a group past the last current GDT block,
  	 * we will also modify the inode and the dindirect block.  If we
  	 * are adding a group with superblock/GDT backups  we will also
  	 * modify each of the reserved GDT dindirect blocks.
  	 */
  	credit = flex_gd->count * 4 + reserved_gdb;
  	handle = ext4_journal_start_sb(sb, credit);
  	if (IS_ERR(handle)) {
  		err = PTR_ERR(handle);
  		goto exit;
  	}
  
  	err = ext4_journal_get_write_access(handle, sbi->s_sbh);
  	if (err)
  		goto exit_journal;
  
  	group = flex_gd->groups[0].group;
  	BUG_ON(group != EXT4_SB(sb)->s_groups_count);
  	err = ext4_add_new_descs(handle, sb, group,
  				resize_inode, flex_gd->count);
  	if (err)
  		goto exit_journal;
  
  	err = ext4_setup_new_descs(handle, sb, flex_gd);
  	if (err)
  		goto exit_journal;
  
  	ext4_update_super(sb, flex_gd);
  
  	err = ext4_handle_dirty_super(handle, sb);
  
  exit_journal:
  	err2 = ext4_journal_stop(handle);
  	if (!err)
  		err = err2;
  
  	if (!err) {
  		int i;
  		update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es,
  			       sizeof(struct ext4_super_block));
  		for (i = 0; i < flex_gd->count; i++, group++) {
  			struct buffer_head *gdb_bh;
  			int gdb_num;
  			gdb_num = group / EXT4_BLOCKS_PER_GROUP(sb);
  			gdb_bh = sbi->s_group_desc[gdb_num];
  			update_backups(sb, gdb_bh->b_blocknr, gdb_bh->b_data,
  				       gdb_bh->b_size);
  		}
  	}
  exit:
  	return err;
  }
19c5246d2   Yongqiang Yang   ext4: add new onl...
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
  static int ext4_setup_next_flex_gd(struct super_block *sb,
  				    struct ext4_new_flex_group_data *flex_gd,
  				    ext4_fsblk_t n_blocks_count,
  				    unsigned long flexbg_size)
  {
  	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
  	struct ext4_new_group_data *group_data = flex_gd->groups;
  	ext4_fsblk_t o_blocks_count;
  	ext4_group_t n_group;
  	ext4_group_t group;
  	ext4_group_t last_group;
  	ext4_grpblk_t last;
  	ext4_grpblk_t blocks_per_group;
  	unsigned long i;
  
  	blocks_per_group = EXT4_BLOCKS_PER_GROUP(sb);
  
  	o_blocks_count = ext4_blocks_count(es);
  
  	if (o_blocks_count == n_blocks_count)
  		return 0;
  
  	ext4_get_group_no_and_offset(sb, o_blocks_count, &group, &last);
  	BUG_ON(last);
  	ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &last);
  
  	last_group = group | (flexbg_size - 1);
  	if (last_group > n_group)
  		last_group = n_group;
  
  	flex_gd->count = last_group - group + 1;
  
  	for (i = 0; i < flex_gd->count; i++) {
  		int overhead;
  
  		group_data[i].group = group + i;
  		group_data[i].blocks_count = blocks_per_group;
  		overhead = ext4_bg_has_super(sb, group + i) ?
  			   (1 + ext4_bg_num_gdb(sb, group + i) +
  			    le16_to_cpu(es->s_reserved_gdt_blocks)) : 0;
  		group_data[i].free_blocks_count = blocks_per_group - overhead;
  		if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
  					       EXT4_FEATURE_RO_COMPAT_GDT_CSUM))
  			flex_gd->bg_flags[i] = EXT4_BG_BLOCK_UNINIT |
  					       EXT4_BG_INODE_UNINIT;
  		else
  			flex_gd->bg_flags[i] = EXT4_BG_INODE_ZEROED;
  	}
  
  	if (last_group == n_group &&
  	    EXT4_HAS_RO_COMPAT_FEATURE(sb,
  				       EXT4_FEATURE_RO_COMPAT_GDT_CSUM))
  		/* We need to initialize block bitmap of last group. */
  		flex_gd->bg_flags[i - 1] &= ~EXT4_BG_BLOCK_UNINIT;
  
  	if ((last_group == n_group) && (last != blocks_per_group - 1)) {
  		group_data[i - 1].blocks_count = last + 1;
  		group_data[i - 1].free_blocks_count -= blocks_per_group-
  					last - 1;
  	}
  
  	return 1;
  }
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
  /* Add group descriptor data to an existing or new group descriptor block.
   * Ensure we handle all possible error conditions _before_ we start modifying
   * the filesystem, because we cannot abort the transaction and not have it
   * write the data to disk.
   *
   * If we are on a GDT block boundary, we need to get the reserved GDT block.
   * Otherwise, we may need to add backup GDT blocks for a sparse group.
   *
   * We only need to hold the superblock lock while we are actually adding
   * in the new group's counts to the superblock.  Prior to that we have
   * not really "added" the group at all.  We re-check that we are still
   * adding in the last group in case things have changed since verifying.
   */
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
1360
  int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1361
  {
61f296cc4   Yongqiang Yang   ext4: let ext4_gr...
1362
  	struct ext4_new_flex_group_data flex_gd;
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
1363
1364
1365
  	struct ext4_sb_info *sbi = EXT4_SB(sb);
  	struct ext4_super_block *es = sbi->s_es;
  	int reserved_gdb = ext4_bg_has_super(sb, input->group) ?
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1366
  		le16_to_cpu(es->s_reserved_gdt_blocks) : 0;
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1367
  	struct inode *inode = NULL;
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1368
  	int gdb_off, gdb_num;
61f296cc4   Yongqiang Yang   ext4: let ext4_gr...
1369
1370
  	int err;
  	__u16 bg_flags = 0;
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1371

617ba13b3   Mingming Cao   [PATCH] ext4: ren...
1372
1373
  	gdb_num = input->group / EXT4_DESC_PER_BLOCK(sb);
  	gdb_off = input->group % EXT4_DESC_PER_BLOCK(sb);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1374

617ba13b3   Mingming Cao   [PATCH] ext4: ren...
1375
1376
  	if (gdb_off == 0 && !EXT4_HAS_RO_COMPAT_FEATURE(sb,
  					EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER)) {
12062dddd   Eric Sandeen   ext4: move __func...
1377
  		ext4_warning(sb, "Can't resize non-sparse filesystem further");
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1378
1379
  		return -EPERM;
  	}
bd81d8eec   Laurent Vivier   [PATCH] ext4: 64b...
1380
1381
  	if (ext4_blocks_count(es) + input->blocks_count <
  	    ext4_blocks_count(es)) {
12062dddd   Eric Sandeen   ext4: move __func...
1382
  		ext4_warning(sb, "blocks_count overflow");
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1383
1384
  		return -EINVAL;
  	}
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
1385
  	if (le32_to_cpu(es->s_inodes_count) + EXT4_INODES_PER_GROUP(sb) <
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1386
  	    le32_to_cpu(es->s_inodes_count)) {
12062dddd   Eric Sandeen   ext4: move __func...
1387
  		ext4_warning(sb, "inodes_count overflow");
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1388
1389
1390
1391
  		return -EINVAL;
  	}
  
  	if (reserved_gdb || gdb_off == 0) {
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
1392
  		if (!EXT4_HAS_COMPAT_FEATURE(sb,
37609fd5a   Josef Bacik   ext4: don't try t...
1393
1394
  					     EXT4_FEATURE_COMPAT_RESIZE_INODE)
  		    || !le16_to_cpu(es->s_reserved_gdt_blocks)) {
12062dddd   Eric Sandeen   ext4: move __func...
1395
  			ext4_warning(sb,
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1396
1397
1398
  				     "No reserved GDT blocks, can't resize");
  			return -EPERM;
  		}
1d1fe1ee0   David Howells   iget: stop EXT4 f...
1399
1400
  		inode = ext4_iget(sb, EXT4_RESIZE_INO);
  		if (IS_ERR(inode)) {
12062dddd   Eric Sandeen   ext4: move __func...
1401
  			ext4_warning(sb, "Error opening resize inode");
1d1fe1ee0   David Howells   iget: stop EXT4 f...
1402
  			return PTR_ERR(inode);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1403
1404
  		}
  	}
920313a72   Aneesh Kumar K.V   ext4: Use EXT4_GR...
1405

61f296cc4   Yongqiang Yang   ext4: let ext4_gr...
1406
  	err = verify_group_input(sb, input);
08c3a8133   Aneesh Kumar K.V   ext4: Clarify the...
1407
  	if (err)
61f296cc4   Yongqiang Yang   ext4: let ext4_gr...
1408
  		goto out;
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1409

61f296cc4   Yongqiang Yang   ext4: let ext4_gr...
1410
1411
1412
1413
1414
  	flex_gd.count = 1;
  	flex_gd.groups = input;
  	flex_gd.bg_flags = &bg_flags;
  	err = ext4_flex_group_add(sb, inode, &flex_gd);
  out:
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1415
1416
  	iput(inode);
  	return err;
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
1417
  } /* ext4_group_add */
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1418

2b2d6d019   Theodore Ts'o   ext4: Cleanup whi...
1419
  /*
18e314384   Yongqiang Yang   ext4: add a funct...
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
   * extend a group without checking assuming that checking has been done.
   */
  static int ext4_group_extend_no_check(struct super_block *sb,
  				      ext4_fsblk_t o_blocks_count, ext4_grpblk_t add)
  {
  	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
  	handle_t *handle;
  	int err = 0, err2;
  
  	/* We will update the superblock, one block bitmap, and
  	 * one group descriptor via ext4_group_add_blocks().
  	 */
  	handle = ext4_journal_start_sb(sb, 3);
  	if (IS_ERR(handle)) {
  		err = PTR_ERR(handle);
  		ext4_warning(sb, "error %d on journal start", err);
  		return err;
  	}
  
  	err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
  	if (err) {
  		ext4_warning(sb, "error %d on journal write access", err);
  		goto errout;
  	}
  
  	ext4_blocks_count_set(es, o_blocks_count + add);
  	ext4_debug("freeing blocks %llu through %llu
  ", o_blocks_count,
  		   o_blocks_count + add);
  	/* We add the blocks to the bitmap and set the group need init bit */
  	err = ext4_group_add_blocks(handle, sb, o_blocks_count, add);
  	if (err)
  		goto errout;
  	ext4_handle_dirty_super(handle, sb);
  	ext4_debug("freed blocks %llu through %llu
  ", o_blocks_count,
  		   o_blocks_count + add);
  errout:
  	err2 = ext4_journal_stop(handle);
  	if (err2 && !err)
  		err = err2;
  
  	if (!err) {
  		if (test_opt(sb, DEBUG))
  			printk(KERN_DEBUG "EXT4-fs: extended group to %llu "
  			       "blocks
  ", ext4_blocks_count(es));
  		update_backups(sb, EXT4_SB(sb)->s_sbh->b_blocknr, (char *)es,
  			       sizeof(struct ext4_super_block));
  	}
  	return err;
  }
  
  /*
2b2d6d019   Theodore Ts'o   ext4: Cleanup whi...
1474
   * Extend the filesystem to the new number of blocks specified.  This entry
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1475
1476
1477
1478
   * point is only used to extend the current filesystem to the end of the last
   * existing group.  It can be accessed via ioctl, or by "remount,resize=<size>"
   * for emergencies (because it has no dependencies on reserved blocks).
   *
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
1479
   * If we _really_ wanted, we could use default values to call ext4_group_add()
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1480
1481
1482
   * allow the "remount" trick to work for arbitrary resizing, assuming enough
   * GDT blocks are reserved to grow to the desired size.
   */
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
1483
1484
  int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
  		      ext4_fsblk_t n_blocks_count)
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1485
  {
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
1486
  	ext4_fsblk_t o_blocks_count;
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
1487
1488
  	ext4_grpblk_t last;
  	ext4_grpblk_t add;
af5bc92dd   Theodore Ts'o   ext4: Fix whitesp...
1489
  	struct buffer_head *bh;
d89651c8e   Yongqiang Yang   ext4: let ext4_gr...
1490
  	int err;
5f21b0e64   Frederic Bohe   ext4: fix online ...
1491
  	ext4_group_t group;
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1492

bd81d8eec   Laurent Vivier   [PATCH] ext4: 64b...
1493
  	o_blocks_count = ext4_blocks_count(es);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1494
1495
  
  	if (test_opt(sb, DEBUG))
2b79b09d1   Yongqiang Yang   ext4: fix a typo ...
1496
1497
  		printk(KERN_DEBUG "EXT4-fs: extending last group from %llu to %llu blocks
  ",
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1498
1499
1500
1501
1502
1503
  		       o_blocks_count, n_blocks_count);
  
  	if (n_blocks_count == 0 || n_blocks_count == o_blocks_count)
  		return 0;
  
  	if (n_blocks_count > (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) {
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
1504
  		printk(KERN_ERR "EXT4-fs: filesystem on %s:"
2ae021076   Mingming Cao   [PATCH] ext4: blk...
1505
1506
  			" too large to resize to %llu blocks safely
  ",
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1507
1508
  			sb->s_id, n_blocks_count);
  		if (sizeof(sector_t) < 8)
12062dddd   Eric Sandeen   ext4: move __func...
1509
  			ext4_warning(sb, "CONFIG_LBDAF not enabled");
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1510
1511
1512
1513
  		return -EINVAL;
  	}
  
  	if (n_blocks_count < o_blocks_count) {
12062dddd   Eric Sandeen   ext4: move __func...
1514
  		ext4_warning(sb, "can't shrink FS - resize aborted");
8f82f840e   Yongqiang Yang   ext4: prevent par...
1515
  		return -EINVAL;
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1516
1517
1518
  	}
  
  	/* Handle the remaining blocks in the last group only. */
5f21b0e64   Frederic Bohe   ext4: fix online ...
1519
  	ext4_get_group_no_and_offset(sb, o_blocks_count, &group, &last);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1520
1521
  
  	if (last == 0) {
12062dddd   Eric Sandeen   ext4: move __func...
1522
  		ext4_warning(sb, "need to use ext2online to resize further");
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1523
1524
  		return -EPERM;
  	}
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
1525
  	add = EXT4_BLOCKS_PER_GROUP(sb) - last;
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1526
1527
  
  	if (o_blocks_count + add < o_blocks_count) {
12062dddd   Eric Sandeen   ext4: move __func...
1528
  		ext4_warning(sb, "blocks_count overflow");
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1529
1530
1531
1532
1533
1534
1535
  		return -EINVAL;
  	}
  
  	if (o_blocks_count + add > n_blocks_count)
  		add = n_blocks_count - o_blocks_count;
  
  	if (o_blocks_count + add < n_blocks_count)
12062dddd   Eric Sandeen   ext4: move __func...
1536
  		ext4_warning(sb, "will only finish group (%llu blocks, %u new)",
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1537
1538
1539
  			     o_blocks_count + add, add);
  
  	/* See if the device is actually as big as what was requested */
2b2d6d019   Theodore Ts'o   ext4: Cleanup whi...
1540
  	bh = sb_bread(sb, o_blocks_count + add - 1);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1541
  	if (!bh) {
12062dddd   Eric Sandeen   ext4: move __func...
1542
  		ext4_warning(sb, "can't read last block, resize aborted");
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1543
1544
1545
  		return -ENOSPC;
  	}
  	brelse(bh);
d89651c8e   Yongqiang Yang   ext4: let ext4_gr...
1546
  	err = ext4_group_extend_no_check(sb, o_blocks_count, add);
ac27a0ec1   Dave Kleikamp   [PATCH] ext4: ini...
1547
  	return err;
617ba13b3   Mingming Cao   [PATCH] ext4: ren...
1548
  } /* ext4_group_extend */
19c5246d2   Yongqiang Yang   ext4: add new onl...
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
  
  /*
   * ext4_resize_fs() resizes a fs to new size specified by @n_blocks_count
   *
   * @sb: super block of the fs to be resized
   * @n_blocks_count: the number of blocks resides in the resized fs
   */
  int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
  {
  	struct ext4_new_flex_group_data *flex_gd = NULL;
  	struct ext4_sb_info *sbi = EXT4_SB(sb);
  	struct ext4_super_block *es = sbi->s_es;
  	struct buffer_head *bh;
  	struct inode *resize_inode;
  	ext4_fsblk_t o_blocks_count;
  	ext4_group_t o_group;
  	ext4_group_t n_group;
  	ext4_grpblk_t offset;
  	unsigned long n_desc_blocks;
  	unsigned long o_desc_blocks;
  	unsigned long desc_blocks;
  	int err = 0, flexbg_size = 1;
  
  	o_blocks_count = ext4_blocks_count(es);
  
  	if (test_opt(sb, DEBUG))
  		printk(KERN_DEBUG "EXT4-fs: resizing filesystem from %llu "
  		       "upto %llu blocks
  ", o_blocks_count, n_blocks_count);
  
  	if (n_blocks_count < o_blocks_count) {
  		/* On-line shrinking not supported */
  		ext4_warning(sb, "can't shrink FS - resize aborted");
  		return -EINVAL;
  	}
  
  	if (n_blocks_count == o_blocks_count)
  		/* Nothing need to do */
  		return 0;
  
  	ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &offset);
  	ext4_get_group_no_and_offset(sb, o_blocks_count, &o_group, &offset);
  
  	n_desc_blocks = (n_group + EXT4_DESC_PER_BLOCK(sb)) /
  			EXT4_DESC_PER_BLOCK(sb);
  	o_desc_blocks = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
  			EXT4_DESC_PER_BLOCK(sb);
  	desc_blocks = n_desc_blocks - o_desc_blocks;
  
  	if (desc_blocks &&
  	    (!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_RESIZE_INODE) ||
  	     le16_to_cpu(es->s_reserved_gdt_blocks) < desc_blocks)) {
  		ext4_warning(sb, "No reserved GDT blocks, can't resize");
  		return -EPERM;
  	}
  
  	resize_inode = ext4_iget(sb, EXT4_RESIZE_INO);
  	if (IS_ERR(resize_inode)) {
  		ext4_warning(sb, "Error opening resize inode");
  		return PTR_ERR(resize_inode);
  	}
  
  	/* See if the device is actually as big as what was requested */
  	bh = sb_bread(sb, n_blocks_count - 1);
  	if (!bh) {
  		ext4_warning(sb, "can't read last block, resize aborted");
  		return -ENOSPC;
  	}
  	brelse(bh);
  
  	if (offset != 0) {
  		/* extend the last group */
  		ext4_grpblk_t add;
  		add = EXT4_BLOCKS_PER_GROUP(sb) - offset;
  		err = ext4_group_extend_no_check(sb, o_blocks_count, add);
  		if (err)
  			goto out;
  	}
  
  	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG) &&
  	    es->s_log_groups_per_flex)
  		flexbg_size = 1 << es->s_log_groups_per_flex;
  
  	o_blocks_count = ext4_blocks_count(es);
  	if (o_blocks_count == n_blocks_count)
  		goto out;
  
  	flex_gd = alloc_flex_gd(flexbg_size);
  	if (flex_gd == NULL) {
  		err = -ENOMEM;
  		goto out;
  	}
  
  	/* Add flex groups. Note that a regular group is a
  	 * flex group with 1 group.
  	 */
  	while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count,
  					      flexbg_size)) {
  		ext4_alloc_group_tables(sb, flex_gd, flexbg_size);
  		err = ext4_flex_group_add(sb, resize_inode, flex_gd);
  		if (unlikely(err))
  			break;
  	}
  
  out:
  	if (flex_gd)
  		free_flex_gd(flex_gd);
  
  	iput(resize_inode);
  	if (test_opt(sb, DEBUG))
  		printk(KERN_DEBUG "EXT4-fs: resized filesystem from %llu "
  		       "upto %llu blocks
  ", o_blocks_count, n_blocks_count);
  	return err;
  }