summaryrefslogtreecommitdiff
path: root/fs/ext3/resize.c
blob: 8aac5334680d18603b987cd1afb759d1b59cf574 (plain)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
/*
 *  linux/fs/ext3/resize.c
 *
 * Support for resizing an ext3 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.
 */

#include <linux/config.h>

#define EXT3FS_DEBUG

#include <linux/sched.h>
#include <linux/smp_lock.h>
#include <linux/ext3_jbd.h>

#include <linux/errno.h>
#include <linux/slab.h>


#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 ext3_new_group_data *input)
{
	struct ext3_sb_info *sbi = EXT3_SB(sb);
	struct ext3_super_block *es = sbi->s_es;
	unsigned start = le32_to_cpu(es->s_blocks_count);
	unsigned end = start + input->blocks_count;
	unsigned group = input->group;
	unsigned itend = input->inode_table + sbi->s_itb_per_group;
	unsigned overhead = ext3_bg_has_super(sb, group) ?
		(1 + ext3_bg_num_gdb(sb, group) +
		 le16_to_cpu(es->s_reserved_gdt_blocks)) : 0;
	unsigned metaend = start + overhead;
	struct buffer_head *bh = NULL;
	int free_blocks_count;
	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 "EXT3-fs: adding %s group %u: %u blocks "
		       "(%d free, %u reserved)\n",
		       ext3_bg_has_super(sb, input->group) ? "normal" :
		       "no-super", input->group, input->blocks_count,
		       free_blocks_count, input->reserved_blocks);

	if (group != sbi->s_groups_count)
		ext3_warning(sb, __FUNCTION__,
			     "Cannot add at group %u (only %lu groups)",
			     input->group, sbi->s_groups_count);
	else if ((start - le32_to_cpu(es->s_first_data_block)) %
		 EXT3_BLOCKS_PER_GROUP(sb))
		ext3_warning(sb, __FUNCTION__, "Last group not full");
	else if (input->reserved_blocks > input->blocks_count / 5)
		ext3_warning(sb, __FUNCTION__, "Reserved blocks too high (%u)",
			     input->reserved_blocks);
	else if (free_blocks_count < 0)
		ext3_warning(sb, __FUNCTION__, "Bad blocks count %u",
			     input->blocks_count);
	else if (!(bh = sb_bread(sb, end - 1)))
		ext3_warning(sb, __FUNCTION__, "Cannot read last block (%u)",
			     end - 1);
	else if (outside(input->block_bitmap, start, end))
		ext3_warning(sb, __FUNCTION__,
			     "Block bitmap not in group (block %u)",
			     input->block_bitmap);
	else if (outside(input->inode_bitmap, start, end))
		ext3_warning(sb, __FUNCTION__,
			     "Inode bitmap not in group (block %u)",
			     input->inode_bitmap);
	else if (outside(input->inode_table, start, end) ||
	         outside(itend - 1, start, end))
		ext3_warning(sb, __FUNCTION__,
			     "Inode table not in group (blocks %u-%u)",
			     input->inode_table, itend - 1);
	else if (input->inode_bitmap == input->block_bitmap)
		ext3_warning(sb, __FUNCTION__,
			     "Block bitmap same as inode bitmap (%u)",
			     input->block_bitmap);
	else if (inside(input->block_bitmap, input->inode_table, itend))
		ext3_warning(sb, __FUNCTION__,
			     "Block bitmap (%u) in inode table (%u-%u)",
			     input->block_bitmap, input->inode_table, itend-1);
	else if (inside(input->inode_bitmap, input->inode_table, itend))
		ext3_warning(sb, __FUNCTION__,
			     "Inode bitmap (%u) in inode table (%u-%u)",
			     input->inode_bitmap, input->inode_table, itend-1);
	else if (inside(input->block_bitmap, start, metaend))
		ext3_warning(sb, __FUNCTION__,
			     "Block bitmap (%u) in GDT table (%u-%u)",
			     input->block_bitmap, start, metaend - 1);
	else if (inside(input->inode_bitmap, start, metaend))
		ext3_warning(sb, __FUNCTION__,
			     "Inode bitmap (%u) in GDT table (%u-%u)",
			     input->inode_bitmap, start, metaend - 1);
	else if (inside(input->inode_table, start, metaend) ||
	         inside(itend - 1, start, metaend))
		ext3_warning(sb, __FUNCTION__,
			     "Inode table (%u-%u) overlaps GDT table (%u-%u)",
			     input->inode_table, itend - 1, start, metaend - 1);
	else
		err = 0;
	brelse(bh);

	return err;
}

static struct buffer_head *bclean(handle_t *handle, struct super_block *sb,
				  unsigned long blk)
{
	struct buffer_head *bh;
	int err;

	bh = sb_getblk(sb, blk);
	if (!bh)
		return ERR_PTR(-EIO);
	if ((err = ext3_journal_get_write_access(handle, bh))) {
		brelse(bh);
		bh = ERR_PTR(err);
	} else {
		lock_buffer(bh);
		memset(bh->b_data, 0, sb->s_blocksize);
		set_buffer_uptodate(bh);
		unlock_buffer(bh);
	}

	return bh;
}

/*
 * To avoid calling the atomic setbit hundreds or thousands of times, we only
 * need to use it within a single byte (to ensure we get endianness right).
 * We can use memset for the rest of the bitmap as there are no other users.
 */
static void mark_bitmap_end(int start_bit, int end_bit, char *bitmap)
{
	int i;

	if (start_bit >= end_bit)
		return;

	ext3_debug("mark end bits +%d through +%d used\n", start_bit, end_bit);
	for (i = start_bit; i < ((start_bit + 7) & ~7UL); i++)
		ext3_set_bit(i, bitmap);
	if (i < end_bit)
		memset(bitmap + (i >> 3), 0xff, (end_bit - i) >> 3);
}

/*
 * Set up the block and inode bitmaps, and the inode table for the new group.
 * 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.
 */
static int setup_new_group_blocks(struct super_block *sb,
				  struct ext3_new_group_data *input)
{
	struct ext3_sb_info *sbi = EXT3_SB(sb);
	unsigned long start = input->group * sbi->s_blocks_per_group +
		le32_to_cpu(sbi->s_es->s_first_data_block);
	int reserved_gdb = ext3_bg_has_super(sb, input->group) ?
		le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) : 0;
	unsigned long gdblocks = ext3_bg_num_gdb(sb, input->group);
	struct buffer_head *bh;
	handle_t *handle;
	unsigned long block;
	int bit;
	int i;
	int err = 0, err2;

	handle = ext3_journal_start_sb(sb, reserved_gdb + gdblocks +
				       2 + sbi->s_itb_per_group);
	if (IS_ERR(handle))
		return PTR_ERR(handle);

	lock_super(sb);
	if (input->group != sbi->s_groups_count) {
		err = -EBUSY;
		goto exit_journal;
	}

	if (IS_ERR(bh = bclean(handle, sb, input->block_bitmap))) {
		err = PTR_ERR(bh);
		goto exit_journal;
	}

	if (ext3_bg_has_super(sb, input->group)) {
		ext3_debug("mark backup superblock %#04lx (+0)\n", start);
		ext3_set_bit(0, bh->b_data);
	}

	/* Copy all of the GDT blocks into the backup in this group */
	for (i = 0, bit = 1, block = start + 1;
	     i < gdblocks; i++, block++, bit++) {
		struct buffer_head *gdb;

		ext3_debug("update backup group %#04lx (+%d)\n", block, bit);

		gdb = sb_getblk(sb, block);
		if (!gdb) {
			err = -EIO;
			goto exit_bh;
		}
		if ((err = ext3_journal_get_write_access(handle, gdb))) {
			brelse(gdb);
			goto exit_bh;
		}
		lock_buffer(bh);
		memcpy(gdb->b_data, sbi->s_group_desc[i]->b_data, bh->b_size);
		set_buffer_uptodate(gdb);
		unlock_buffer(bh);
		ext3_journal_dirty_metadata(handle, gdb);
		ext3_set_bit(bit, bh->b_data);
		brelse(gdb);
	}

	/* Zero out all of the reserved backup group descriptor table blocks */
	for (i = 0, bit = gdblocks + 1, block = start + bit;
	     i < reserved_gdb; i++, block++, bit++) {
		struct buffer_head *gdb;

		ext3_debug("clear reserved block %#04lx (+%d)\n", block, bit);

		if (IS_ERR(gdb = bclean(handle, sb, block))) {
			err = PTR_ERR(bh);
			goto exit_bh;
		}
		ext3_journal_dirty_metadata(handle, gdb);
		ext3_set_bit(bit, bh->b_data);
		brelse(gdb);
	}
	ext3_debug("mark block bitmap %#04x (+%ld)\n", input->block_bitmap,
		   input->block_bitmap - start);
	ext3_set_bit(input->block_bitmap - start, bh->b_data);
	ext3_debug("mark inode bitmap %#04x (+%ld)\n", input->inode_bitmap,
		   input->inode_bitmap - start);
	ext3_set_bit(input->inode_bitmap - start, bh->b_data);

	/* Zero out all of the inode table blocks */
	for (i = 0, block = input->inode_table, bit = block - start;
	     i < sbi->s_itb_per_group; i++, bit++, block++) {
		struct buffer_head *it;

		ext3_debug("clear inode block %#04lx (+%d)\n", block, bit);
		if (IS_ERR(it = bclean(handle, sb, block))) {
			err = PTR_ERR(it);
			goto exit_bh;
		}
		ext3_journal_dirty_metadata(handle, it);
		brelse(it);
		ext3_set_bit(bit, bh->b_data);
	}
	mark_bitmap_end(input->blocks_count, EXT3_BLOCKS_PER_GROUP(sb),
			bh->b_data);
	ext3_journal_dirty_metadata(handle, bh);
	brelse(bh);

	/* Mark unused entries in inode bitmap used */
	ext3_debug("clear inode bitmap %#04x (+%ld)\n",
		   input->inode_bitmap, input->inode_bitmap - start);
	if (IS_ERR(bh = bclean(handle, sb, input->inode_bitmap))) {
		err = PTR_ERR(bh);
		goto exit_journal;
	}

	mark_bitmap_end(EXT3_INODES_PER_GROUP(sb), EXT3_BLOCKS_PER_GROUP(sb),
			bh->b_data);
	ext3_journal_dirty_metadata(handle, bh);
exit_bh:
	brelse(bh);

exit_journal:
	unlock_super(sb);
	if ((err2 = ext3_journal_stop(handle)) && !err)
		err = err2;

	return err;
}

/*
 * Iterate through the groups which hold BACKUP superblock/GDT copies in an
 * ext3 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 ext3_list_backups(struct super_block *sb, unsigned *three,
				  unsigned *five, unsigned *seven)
{
	unsigned *min = three;
	int mult = 3;
	unsigned ret;

	if (!EXT3_HAS_RO_COMPAT_FEATURE(sb,
					EXT3_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,
			       struct buffer_head *primary)
{
	const unsigned long blk = primary->b_blocknr;
	const unsigned long end = EXT3_SB(sb)->s_groups_count;
	unsigned three = 1;
	unsigned five = 5;
	unsigned seven = 7;
	unsigned grp;
	__u32 *p = (__u32 *)primary->b_data;
	int gdbackups = 0;

	while ((grp = ext3_list_backups(sb, &three, &five, &seven)) < end) {
		if (le32_to_cpu(*p++) != grp * EXT3_BLOCKS_PER_GROUP(sb) + blk){
			ext3_warning(sb, __FUNCTION__,
				     "reserved GDT %ld missing grp %d (%ld)",
				     blk, grp,
				     grp * EXT3_BLOCKS_PER_GROUP(sb) + blk);
			return -EINVAL;
		}
		if (++gdbackups > EXT3_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,
		       struct ext3_new_group_data *input,
		       struct buffer_head **primary)
{
	struct super_block *sb = inode->i_sb;
	struct ext3_super_block *es = EXT3_SB(sb)->s_es;
	unsigned long gdb_num = input->group / EXT3_DESC_PER_BLOCK(sb);
	unsigned long gdblock = EXT3_SB(sb)->s_sbh->b_blocknr + 1 + gdb_num;
	struct buffer_head **o_group_desc, **n_group_desc;
	struct buffer_head *dind;
	int gdbackups;
	struct ext3_iloc iloc;
	__u32 *data;
	int err;

	if (test_opt(sb, DEBUG))
		printk(KERN_DEBUG
		       "EXT3-fs: ext3_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 (EXT3_SB(sb)->s_sbh->b_blocknr !=
	    le32_to_cpu(EXT3_SB(sb)->s_es->s_first_data_block)) {
		ext3_warning(sb, __FUNCTION__,
			"won't resize using backup superblock at %llu",
			(unsigned long long)EXT3_SB(sb)->s_sbh->b_blocknr);
		return -EPERM;
	}

	*primary = sb_bread(sb, gdblock);
	if (!*primary)
		return -EIO;

	if ((gdbackups = verify_reserved_gdb(sb, *primary)) < 0) {
		err = gdbackups;
		goto exit_bh;
	}

	data = EXT3_I(inode)->i_data + EXT3_DIND_BLOCK;
	dind = sb_bread(sb, le32_to_cpu(*data));
	if (!dind) {
		err = -EIO;
		goto exit_bh;
	}

	data = (__u32 *)dind->b_data;
	if (le32_to_cpu(data[gdb_num % EXT3_ADDR_PER_BLOCK(sb)]) != gdblock) {
		ext3_warning(sb, __FUNCTION__,
			     "new group %u GDT block %lu not reserved",
			     input->group, gdblock);
		err = -EINVAL;
		goto exit_dind;
	}

	if ((err = ext3_journal_get_write_access(handle, EXT3_SB(sb)->s_sbh)))
		goto exit_dind;

	if ((err = ext3_journal_get_write_access(handle, *primary)))
		goto exit_sbh;

	if ((err = ext3_journal_get_write_access(handle, dind)))
		goto exit_primary;

	/* ext3_reserve_inode_write() gets a reference on the iloc */
	if ((err = ext3_reserve_inode_write(handle, inode, &iloc)))
		goto exit_dindj;

	n_group_desc = (struct buffer_head **)kmalloc((gdb_num + 1) *
				sizeof(struct buffer_head *), GFP_KERNEL);
	if (!n_group_desc) {
		err = -ENOMEM;
		ext3_warning (sb, __FUNCTION__,
			      "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 % EXT3_ADDR_PER_BLOCK(sb)] = 0;
	ext3_journal_dirty_metadata(handle, dind);
	brelse(dind);
	inode->i_blocks -= (gdbackups + 1) * sb->s_blocksize >> 9;
	ext3_mark_iloc_dirty(handle, inode, &iloc);
	memset((*primary)->b_data, 0, sb->s_blocksize);
	ext3_journal_dirty_metadata(handle, *primary);

	o_group_desc = EXT3_SB(sb)->s_group_desc;
	memcpy(n_group_desc, o_group_desc,
	       EXT3_SB(sb)->s_gdb_count * sizeof(struct buffer_head *));
	n_group_desc[gdb_num] = *primary;
	EXT3_SB(sb)->s_group_desc = n_group_desc;
	EXT3_SB(sb)->s_gdb_count++;
	kfree(o_group_desc);

	es->s_reserved_gdt_blocks =
		cpu_to_le16(le16_to_cpu(es->s_reserved_gdt_blocks) - 1);
	ext3_journal_dirty_metadata(handle, EXT3_SB(sb)->s_sbh);

	return 0;

exit_inode:
	//ext3_journal_release_buffer(handle, iloc.bh);
	brelse(iloc.bh);
exit_dindj:
	//ext3_journal_release_buffer(handle, dind);
exit_primary:
	//ext3_journal_release_buffer(handle, *primary);
exit_sbh:
	//ext3_journal_release_buffer(handle, *primary);
exit_dind:
	brelse(dind);
exit_bh:
	brelse(*primary);

	ext3_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,
			      struct ext3_new_group_data *input)
{
	struct super_block *sb = inode->i_sb;
	int reserved_gdb =le16_to_cpu(EXT3_SB(sb)->s_es->s_reserved_gdt_blocks);
	struct buffer_head **primary;
	struct buffer_head *dind;
	struct ext3_iloc iloc;
	unsigned long blk;
	__u32 *data, *end;
	int gdbackups = 0;
	int res, i;
	int err;

	primary = kmalloc(reserved_gdb * sizeof(*primary), GFP_KERNEL);
	if (!primary)
		return -ENOMEM;

	data = EXT3_I(inode)->i_data + EXT3_DIND_BLOCK;
	dind = sb_bread(sb, le32_to_cpu(*data));
	if (!dind) {
		err = -EIO;
		goto exit_free;
	}

	blk = EXT3_SB(sb)->s_sbh->b_blocknr + 1 + EXT3_SB(sb)->s_gdb_count;
	data = (__u32 *)dind->b_data + EXT3_SB(sb)->s_gdb_count;
	end = (__u32 *)dind->b_data + EXT3_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) {
			ext3_warning(sb, __FUNCTION__,
				     "reserved block %lu not at offset %ld",
				     blk, (long)(data - (__u32 *)dind->b_data));
			err = -EINVAL;
			goto exit_bh;
		}
		primary[res] = sb_bread(sb, blk);
		if (!primary[res]) {
			err = -EIO;
			goto exit_bh;
		}
		if ((gdbackups = verify_reserved_gdb(sb, primary[res])) < 0) {
			brelse(primary[res]);
			err = gdbackups;
			goto exit_bh;
		}
		if (++data >= end)
			data = (__u32 *)dind->b_data;
	}

	for (i = 0; i < reserved_gdb; i++) {
		if ((err = ext3_journal_get_write_access(handle, primary[i]))) {
			/*
			int j;
			for (j = 0; j < i; j++)
				ext3_journal_release_buffer(handle, primary[j]);
			 */
			goto exit_bh;
		}
	}

	if ((err = ext3_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 = input->group * EXT3_BLOCKS_PER_GROUP(sb);
	for (i = 0; i < reserved_gdb; i++) {
		int err2;
		data = (__u32 *)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 = ext3_journal_dirty_metadata(handle, primary[i]);
		if (!err)
			err = err2;
	}
	inode->i_blocks += reserved_gdb * sb->s_blocksize >> 9;
	ext3_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 ext3 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 lock_super() 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 ext3_sb_info *sbi = EXT3_SB(sb);
	const unsigned long last = sbi->s_groups_count;
	const int bpg = EXT3_BLOCKS_PER_GROUP(sb);
	unsigned three = 1;
	unsigned five = 5;
	unsigned seven = 7;
	unsigned group;
	int rest = sb->s_blocksize - size;
	handle_t *handle;
	int err = 0, err2;

	handle = ext3_journal_start_sb(sb, EXT3_MAX_TRANS_DATA);
	if (IS_ERR(handle)) {
		group = 1;
		err = PTR_ERR(handle);
		goto exit_err;
	}

	while ((group = ext3_list_backups(sb, &three, &five, &seven)) < last) {
		struct buffer_head *bh;

		/* Out of journal space, and can't get more - abort - so sad */
		if (handle->h_buffer_credits == 0 &&
		    ext3_journal_extend(handle, EXT3_MAX_TRANS_DATA) &&
		    (err = ext3_journal_restart(handle, EXT3_MAX_TRANS_DATA)))
			break;

		bh = sb_getblk(sb, group * bpg + blk_off);
		if (!bh) {
			err = -EIO;
			break;
		}
		ext3_debug("update metadata backup %#04lx\n",
			  (unsigned long)bh->b_blocknr);
		if ((err = ext3_journal_get_write_access(handle, bh)))
			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);
		ext3_journal_dirty_metadata(handle, bh);
		brelse(bh);
	}
	if ((err2 = ext3_journal_stop(handle)) && !err)
		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) {
		ext3_warning(sb, __FUNCTION__,
			     "can't update backup for group %d (err %d), "
			     "forcing fsck on next reboot", group, err);
		sbi->s_mount_state &= ~EXT3_VALID_FS;
		sbi->s_es->s_state &= ~cpu_to_le16(EXT3_VALID_FS);
		mark_buffer_dirty(sbi->s_sbh);
	}
}

/* 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.
 */
int ext3_group_add(struct super_block *sb, struct ext3_new_group_data *input)
{
	struct ext3_sb_info *sbi = EXT3_SB(sb);
	struct ext3_super_block *es = sbi->s_es;
	int reserved_gdb = ext3_bg_has_super(sb, input->group) ?
		le16_to_cpu(es->s_reserved_gdt_blocks) : 0;
	struct buffer_head *primary = NULL;
	struct ext3_group_desc *gdp;
	struct inode *inode = NULL;
	handle_t *handle;
	int gdb_off, gdb_num;
	int err, err2;

	gdb_num = input->group / EXT3_DESC_PER_BLOCK(sb);
	gdb_off = input->group % EXT3_DESC_PER_BLOCK(sb);

	if (gdb_off == 0 && !EXT3_HAS_RO_COMPAT_FEATURE(sb,
					EXT3_FEATURE_RO_COMPAT_SPARSE_SUPER)) {
		ext3_warning(sb, __FUNCTION__,
			     "Can't resize non-sparse filesystem further");
		return -EPERM;
	}

	if (reserved_gdb || gdb_off == 0) {
		if (!EXT3_HAS_COMPAT_FEATURE(sb,
					     EXT3_FEATURE_COMPAT_RESIZE_INODE)){
			ext3_warning(sb, __FUNCTION__,
				     "No reserved GDT blocks, can't resize");
			return -EPERM;
		}
		inode = iget(sb, EXT3_RESIZE_INO);
		if (!inode || is_bad_inode(inode)) {
			ext3_warning(sb, __FUNCTION__,
				     "Error opening resize inode");
			iput(inode);
			return -ENOENT;
		}
	}

	if ((err = verify_group_input(sb, input)))
		goto exit_put;

	if ((err = setup_new_group_blocks(sb, input)))
		goto exit_put;

	/*
	 * We will always be modifying at least the superblock and a 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.
	 */
	handle = ext3_journal_start_sb(sb,
				       ext3_bg_has_super(sb, input->group) ?
				       3 + reserved_gdb : 4);
	if (IS_ERR(handle)) {
		err = PTR_ERR(handle);
		goto exit_put;
	}

	lock_super(sb);
	if (input->group != sbi->s_groups_count) {
		ext3_warning(sb, __FUNCTION__,
			     "multiple resizers run on filesystem!");
		unlock_super(sb);
		err = -EBUSY;
		goto exit_journal;
	}

	if ((err = ext3_journal_get_write_access(handle, sbi->s_sbh)))
		goto exit_journal;

	/*
	 * 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) {
		primary = sbi->s_group_desc[gdb_num];
		if ((err = ext3_journal_get_write_access(handle, primary)))
			goto exit_journal;

		if (reserved_gdb && ext3_bg_num_gdb(sb, input->group) &&
		    (err = reserve_backup_gdb(handle, inode, input)))
			goto exit_journal;
	} else if ((err = add_new_gdb(handle, inode, input, &primary)))
		goto exit_journal;

	/*
	 * OK, now we've set up the new group.  Time to make it active.
	 *
	 * Current kernels don't lock all allocations via lock_super(),
	 * so we have to be safe wrt. concurrent accesses the group
	 * data.  So we need to be careful to set all of the relevant
	 * group descriptor data etc. *before* we enable the group.
	 *
	 * The key field here is sbi->s_groups_count: as long as
	 * that retains its old value, nobody is going to access the new
	 * group.
	 *
	 * So first we update all the descriptor metadata for the new
	 * group; then we update the total disk blocks count; then we
	 * update the groups count to enable the group; then finally we
	 * update the free space counts so that the system can start
	 * using the new disk blocks.
	 */

	/* Update group descriptor block for new group */
	gdp = (struct ext3_group_desc *)primary->b_data + gdb_off;

	gdp->bg_block_bitmap = cpu_to_le32(input->block_bitmap);
	gdp->bg_inode_bitmap = cpu_to_le32(input->inode_bitmap);
	gdp->bg_inode_table = cpu_to_le32(input->inode_table);
	gdp->bg_free_blocks_count = cpu_to_le16(input->free_blocks_count);
	gdp->bg_free_inodes_count = cpu_to_le16(EXT3_INODES_PER_GROUP(sb));

	/*
	 * 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.
	 */
	es->s_blocks_count = cpu_to_le32(le32_to_cpu(es->s_blocks_count) +
		input->blocks_count);
	es->s_inodes_count = cpu_to_le32(le32_to_cpu(es->s_inodes_count) +
		EXT3_INODES_PER_GROUP(sb));

	/*
	 * We need to protect s_groups_count against other CPUs seeing
	 * inconsistent state in the superblock.
	 *
	 * The precise rules we use are:
	 *
	 * * Writers of s_groups_count *must* hold lock_super
	 * AND
	 * * Writers must perform a smp_wmb() after updating all dependent
	 *   data and before modifying the groups count
	 *
	 * * Readers must hold lock_super() over the access
	 * OR
	 * * 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++;

	ext3_journal_dirty_metadata(handle, primary);

	/* Update the reserved block counts only once the new group is
	 * active. */
	es->s_r_blocks_count = cpu_to_le32(le32_to_cpu(es->s_r_blocks_count) +
		input->reserved_blocks);

	/* Update the free space counts */
	percpu_counter_mod(&sbi->s_freeblocks_counter,
			   input->free_blocks_count);
	percpu_counter_mod(&sbi->s_freeinodes_counter,
			   EXT3_INODES_PER_GROUP(sb));

	ext3_journal_dirty_metadata(handle, sbi->s_sbh);
	sb->s_dirt = 1;

exit_journal:
	unlock_super(sb);
	if ((err2 = ext3_journal_stop(handle)) && !err)
		err = err2;
	if (!err) {
		update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es,
			       sizeof(struct ext3_super_block));
		update_backups(sb, primary->b_blocknr, primary->b_data,
			       primary->b_size);
	}
exit_put:
	iput(inode);
	return err;
} /* ext3_group_add */

/* Extend the filesystem to the new number of blocks specified.  This entry
 * 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).
 *
 * If we _really_ wanted, we could use default values to call ext3_group_add()
 * allow the "remount" trick to work for arbitrary resizing, assuming enough
 * GDT blocks are reserved to grow to the desired size.
 */
int ext3_group_extend(struct super_block *sb, struct ext3_super_block *es,
		      unsigned long n_blocks_count)
{
	unsigned long o_blocks_count;
	unsigned long o_groups_count;
	unsigned long last;
	int add;
	struct buffer_head * bh;
	handle_t *handle;
	int err, freed_blocks;

	/* We don't need to worry about locking wrt other resizers just
	 * yet: we're going to revalidate es->s_blocks_count after
	 * taking lock_super() below. */
	o_blocks_count = le32_to_cpu(es->s_blocks_count);
	o_groups_count = EXT3_SB(sb)->s_groups_count;

	if (test_opt(sb, DEBUG))
		printk(KERN_DEBUG "EXT3-fs: extending last group from %lu to %lu blocks\n",
		       o_blocks_count, n_blocks_count);

	if (n_blocks_count == 0 || n_blocks_count == o_blocks_count)
		return 0;

	if (n_blocks_count < o_blocks_count) {
		ext3_warning(sb, __FUNCTION__,
			     "can't shrink FS - resize aborted");
		return -EBUSY;
	}

	/* Handle the remaining blocks in the last group only. */
	last = (o_blocks_count - le32_to_cpu(es->s_first_data_block)) %
		EXT3_BLOCKS_PER_GROUP(sb);

	if (last == 0) {
		ext3_warning(sb, __FUNCTION__,
			     "need to use ext2online to resize further");
		return -EPERM;
	}

	add = EXT3_BLOCKS_PER_GROUP(sb) - last;

	if (o_blocks_count + add > n_blocks_count)
		add = n_blocks_count - o_blocks_count;

	if (o_blocks_count + add < n_blocks_count)
		ext3_warning(sb, __FUNCTION__,
			     "will only finish group (%lu blocks, %u new)",
			     o_blocks_count + add, add);

	/* See if the device is actually as big as what was requested */
	bh = sb_bread(sb, o_blocks_count + add -1);
	if (!bh) {
		ext3_warning(sb, __FUNCTION__,
			     "can't read last block, resize aborted");
		return -ENOSPC;
	}
	brelse(bh);

	/* We will update the superblock, one block bitmap, and
	 * one group descriptor via ext3_free_blocks().
	 */
	handle = ext3_journal_start_sb(sb, 3);
	if (IS_ERR(handle)) {
		err = PTR_ERR(handle);
		ext3_warning(sb, __FUNCTION__, "error %d on journal start",err);
		goto exit_put;
	}

	lock_super(sb);
	if (o_blocks_count != le32_to_cpu(es->s_blocks_count)) {
		ext3_warning(sb, __FUNCTION__,
			     "multiple resizers run on filesystem!");
		unlock_super(sb);
		err = -EBUSY;
		goto exit_put;
	}

	if ((err = ext3_journal_get_write_access(handle,
						 EXT3_SB(sb)->s_sbh))) {
		ext3_warning(sb, __FUNCTION__,
			     "error %d on journal write access", err);
		unlock_super(sb);
		ext3_journal_stop(handle);
		goto exit_put;
	}
	es->s_blocks_count = cpu_to_le32(o_blocks_count + add);
	ext3_journal_dirty_metadata(handle, EXT3_SB(sb)->s_sbh);
	sb->s_dirt = 1;
	unlock_super(sb);
	ext3_debug("freeing blocks %ld through %ld\n", o_blocks_count,
		   o_blocks_count + add);
	ext3_free_blocks_sb(handle, sb, o_blocks_count, add, &freed_blocks);
	ext3_debug("freed blocks %ld through %ld\n", o_blocks_count,
		   o_blocks_count + add);
	if ((err = ext3_journal_stop(handle)))
		goto exit_put;
	if (test_opt(sb, DEBUG))
		printk(KERN_DEBUG "EXT3-fs: extended group to %u blocks\n",
		       le32_to_cpu(es->s_blocks_count));
	update_backups(sb, EXT3_SB(sb)->s_sbh->b_blocknr, (char *)es,
		       sizeof(struct ext3_super_block));
exit_put:
	return err;
} /* ext3_group_extend */