aboutsummaryrefslogtreecommitdiff
path: root/fs/xfs/scrub/agheader_repair.c
blob: f7568a4b5fe58f5aecef931c3928d3c9ec0564fd (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
// SPDX-License-Identifier: GPL-2.0+
/*
 * Copyright (C) 2018 Oracle.  All Rights Reserved.
 * Author: Darrick J. Wong <darrick.wong@oracle.com>
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_btree.h"
#include "xfs_bit.h"
#include "xfs_log_format.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_inode.h"
#include "xfs_alloc.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc.h"
#include "xfs_ialloc_btree.h"
#include "xfs_rmap.h"
#include "xfs_rmap_btree.h"
#include "xfs_refcount.h"
#include "xfs_refcount_btree.h"
#include "scrub/xfs_scrub.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/trace.h"
#include "scrub/repair.h"
#include "scrub/bitmap.h"

/* Superblock */

/* Repair the superblock. */
int
xrep_superblock(
	struct xfs_scrub	*sc)
{
	struct xfs_mount	*mp = sc->mp;
	struct xfs_buf		*bp;
	xfs_agnumber_t		agno;
	int			error;

	/* Don't try to repair AG 0's sb; let xfs_repair deal with it. */
	agno = sc->sm->sm_agno;
	if (agno == 0)
		return -EOPNOTSUPP;

	error = xfs_sb_get_secondary(mp, sc->tp, agno, &bp);
	if (error)
		return error;

	/* Copy AG 0's superblock to this one. */
	xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
	xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb);

	/* Write this to disk. */
	xfs_trans_buf_set_type(sc->tp, bp, XFS_BLFT_SB_BUF);
	xfs_trans_log_buf(sc->tp, bp, 0, BBTOB(bp->b_length) - 1);
	return error;
}

/* AGF */

struct xrep_agf_allocbt {
	struct xfs_scrub	*sc;
	xfs_agblock_t		freeblks;
	xfs_agblock_t		longest;
};

/* Record free space shape information. */
STATIC int
xrep_agf_walk_allocbt(
	struct xfs_btree_cur		*cur,
	struct xfs_alloc_rec_incore	*rec,
	void				*priv)
{
	struct xrep_agf_allocbt		*raa = priv;
	int				error = 0;

	if (xchk_should_terminate(raa->sc, &error))
		return error;

	raa->freeblks += rec->ar_blockcount;
	if (rec->ar_blockcount > raa->longest)
		raa->longest = rec->ar_blockcount;
	return error;
}

/* Does this AGFL block look sane? */
STATIC int
xrep_agf_check_agfl_block(
	struct xfs_mount	*mp,
	xfs_agblock_t		agbno,
	void			*priv)
{
	struct xfs_scrub	*sc = priv;

	if (!xfs_verify_agbno(mp, sc->sa.agno, agbno))
		return -EFSCORRUPTED;
	return 0;
}

/*
 * Offset within the xrep_find_ag_btree array for each btree type.  Avoid the
 * XFS_BTNUM_ names here to avoid creating a sparse array.
 */
enum {
	XREP_AGF_BNOBT = 0,
	XREP_AGF_CNTBT,
	XREP_AGF_RMAPBT,
	XREP_AGF_REFCOUNTBT,
	XREP_AGF_END,
	XREP_AGF_MAX
};

/* Check a btree root candidate. */
static inline bool
xrep_check_btree_root(
	struct xfs_scrub		*sc,
	struct xrep_find_ag_btree	*fab)
{
	struct xfs_mount		*mp = sc->mp;
	xfs_agnumber_t			agno = sc->sm->sm_agno;

	return xfs_verify_agbno(mp, agno, fab->root) &&
	       fab->height <= XFS_BTREE_MAXLEVELS;
}

/*
 * Given the btree roots described by *fab, find the roots, check them for
 * sanity, and pass the root data back out via *fab.
 *
 * This is /also/ a chicken and egg problem because we have to use the rmapbt
 * (rooted in the AGF) to find the btrees rooted in the AGF.  We also have no
 * idea if the btrees make any sense.  If we hit obvious corruptions in those
 * btrees we'll bail out.
 */
STATIC int
xrep_agf_find_btrees(
	struct xfs_scrub		*sc,
	struct xfs_buf			*agf_bp,
	struct xrep_find_ag_btree	*fab,
	struct xfs_buf			*agfl_bp)
{
	struct xfs_agf			*old_agf = XFS_BUF_TO_AGF(agf_bp);
	int				error;

	/* Go find the root data. */
	error = xrep_find_ag_btree_roots(sc, agf_bp, fab, agfl_bp);
	if (error)
		return error;

	/* We must find the bnobt, cntbt, and rmapbt roots. */
	if (!xrep_check_btree_root(sc, &fab[XREP_AGF_BNOBT]) ||
	    !xrep_check_btree_root(sc, &fab[XREP_AGF_CNTBT]) ||
	    !xrep_check_btree_root(sc, &fab[XREP_AGF_RMAPBT]))
		return -EFSCORRUPTED;

	/*
	 * We relied on the rmapbt to reconstruct the AGF.  If we get a
	 * different root then something's seriously wrong.
	 */
	if (fab[XREP_AGF_RMAPBT].root !=
	    be32_to_cpu(old_agf->agf_roots[XFS_BTNUM_RMAPi]))
		return -EFSCORRUPTED;

	/* We must find the refcountbt root if that feature is enabled. */
	if (xfs_sb_version_hasreflink(&sc->mp->m_sb) &&
	    !xrep_check_btree_root(sc, &fab[XREP_AGF_REFCOUNTBT]))
		return -EFSCORRUPTED;

	return 0;
}

/*
 * Reinitialize the AGF header, making an in-core copy of the old contents so
 * that we know which in-core state needs to be reinitialized.
 */
STATIC void
xrep_agf_init_header(
	struct xfs_scrub	*sc,
	struct xfs_buf		*agf_bp,
	struct xfs_agf		*old_agf)
{
	struct xfs_mount	*mp = sc->mp;
	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agf_bp);

	memcpy(old_agf, agf, sizeof(*old_agf));
	memset(agf, 0, BBTOB(agf_bp->b_length));
	agf->agf_magicnum = cpu_to_be32(XFS_AGF_MAGIC);
	agf->agf_versionnum = cpu_to_be32(XFS_AGF_VERSION);
	agf->agf_seqno = cpu_to_be32(sc->sa.agno);
	agf->agf_length = cpu_to_be32(xfs_ag_block_count(mp, sc->sa.agno));
	agf->agf_flfirst = old_agf->agf_flfirst;
	agf->agf_fllast = old_agf->agf_fllast;
	agf->agf_flcount = old_agf->agf_flcount;
	if (xfs_sb_version_hascrc(&mp->m_sb))
		uuid_copy(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid);

	/* Mark the incore AGF data stale until we're done fixing things. */
	ASSERT(sc->sa.pag->pagf_init);
	sc->sa.pag->pagf_init = 0;
}

/* Set btree root information in an AGF. */
STATIC void
xrep_agf_set_roots(
	struct xfs_scrub		*sc,
	struct xfs_agf			*agf,
	struct xrep_find_ag_btree	*fab)
{
	agf->agf_roots[XFS_BTNUM_BNOi] =
			cpu_to_be32(fab[XREP_AGF_BNOBT].root);
	agf->agf_levels[XFS_BTNUM_BNOi] =
			cpu_to_be32(fab[XREP_AGF_BNOBT].height);

	agf->agf_roots[XFS_BTNUM_CNTi] =
			cpu_to_be32(fab[XREP_AGF_CNTBT].root);
	agf->agf_levels[XFS_BTNUM_CNTi] =
			cpu_to_be32(fab[XREP_AGF_CNTBT].height);

	agf->agf_roots[XFS_BTNUM_RMAPi] =
			cpu_to_be32(fab[XREP_AGF_RMAPBT].root);
	agf->agf_levels[XFS_BTNUM_RMAPi] =
			cpu_to_be32(fab[XREP_AGF_RMAPBT].height);

	if (xfs_sb_version_hasreflink(&sc->mp->m_sb)) {
		agf->agf_refcount_root =
				cpu_to_be32(fab[XREP_AGF_REFCOUNTBT].root);
		agf->agf_refcount_level =
				cpu_to_be32(fab[XREP_AGF_REFCOUNTBT].height);
	}
}

/* Update all AGF fields which derive from btree contents. */
STATIC int
xrep_agf_calc_from_btrees(
	struct xfs_scrub	*sc,
	struct xfs_buf		*agf_bp)
{
	struct xrep_agf_allocbt	raa = { .sc = sc };
	struct xfs_btree_cur	*cur = NULL;
	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agf_bp);
	struct xfs_mount	*mp = sc->mp;
	xfs_agblock_t		btreeblks;
	xfs_agblock_t		blocks;
	int			error;

	/* Update the AGF counters from the bnobt. */
	cur = xfs_allocbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno,
			XFS_BTNUM_BNO);
	error = xfs_alloc_query_all(cur, xrep_agf_walk_allocbt, &raa);
	if (error)
		goto err;
	error = xfs_btree_count_blocks(cur, &blocks);
	if (error)
		goto err;
	xfs_btree_del_cursor(cur, error);
	btreeblks = blocks - 1;
	agf->agf_freeblks = cpu_to_be32(raa.freeblks);
	agf->agf_longest = cpu_to_be32(raa.longest);

	/* Update the AGF counters from the cntbt. */
	cur = xfs_allocbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno,
			XFS_BTNUM_CNT);
	error = xfs_btree_count_blocks(cur, &blocks);
	if (error)
		goto err;
	xfs_btree_del_cursor(cur, error);
	btreeblks += blocks - 1;

	/* Update the AGF counters from the rmapbt. */
	cur = xfs_rmapbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno);
	error = xfs_btree_count_blocks(cur, &blocks);
	if (error)
		goto err;
	xfs_btree_del_cursor(cur, error);
	agf->agf_rmap_blocks = cpu_to_be32(blocks);
	btreeblks += blocks - 1;

	agf->agf_btreeblks = cpu_to_be32(btreeblks);

	/* Update the AGF counters from the refcountbt. */
	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
		cur = xfs_refcountbt_init_cursor(mp, sc->tp, agf_bp,
				sc->sa.agno);
		error = xfs_btree_count_blocks(cur, &blocks);
		if (error)
			goto err;
		xfs_btree_del_cursor(cur, error);
		agf->agf_refcount_blocks = cpu_to_be32(blocks);
	}

	return 0;
err:
	xfs_btree_del_cursor(cur, error);
	return error;
}

/* Commit the new AGF and reinitialize the incore state. */
STATIC int
xrep_agf_commit_new(
	struct xfs_scrub	*sc,
	struct xfs_buf		*agf_bp)
{
	struct xfs_perag	*pag;
	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agf_bp);

	/* Trigger fdblocks recalculation */
	xfs_force_summary_recalc(sc->mp);

	/* Write this to disk. */
	xfs_trans_buf_set_type(sc->tp, agf_bp, XFS_BLFT_AGF_BUF);
	xfs_trans_log_buf(sc->tp, agf_bp, 0, BBTOB(agf_bp->b_length) - 1);

	/* Now reinitialize the in-core counters we changed. */
	pag = sc->sa.pag;
	pag->pagf_btreeblks = be32_to_cpu(agf->agf_btreeblks);
	pag->pagf_freeblks = be32_to_cpu(agf->agf_freeblks);
	pag->pagf_longest = be32_to_cpu(agf->agf_longest);
	pag->pagf_levels[XFS_BTNUM_BNOi] =
			be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNOi]);
	pag->pagf_levels[XFS_BTNUM_CNTi] =
			be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNTi]);
	pag->pagf_levels[XFS_BTNUM_RMAPi] =
			be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAPi]);
	pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level);
	pag->pagf_init = 1;

	return 0;
}

/* Repair the AGF. v5 filesystems only. */
int
xrep_agf(
	struct xfs_scrub		*sc)
{
	struct xrep_find_ag_btree	fab[XREP_AGF_MAX] = {
		[XREP_AGF_BNOBT] = {
			.rmap_owner = XFS_RMAP_OWN_AG,
			.buf_ops = &xfs_allocbt_buf_ops,
			.magic = XFS_ABTB_CRC_MAGIC,
		},
		[XREP_AGF_CNTBT] = {
			.rmap_owner = XFS_RMAP_OWN_AG,
			.buf_ops = &xfs_allocbt_buf_ops,
			.magic = XFS_ABTC_CRC_MAGIC,
		},
		[XREP_AGF_RMAPBT] = {
			.rmap_owner = XFS_RMAP_OWN_AG,
			.buf_ops = &xfs_rmapbt_buf_ops,
			.magic = XFS_RMAP_CRC_MAGIC,
		},
		[XREP_AGF_REFCOUNTBT] = {
			.rmap_owner = XFS_RMAP_OWN_REFC,
			.buf_ops = &xfs_refcountbt_buf_ops,
			.magic = XFS_REFC_CRC_MAGIC,
		},
		[XREP_AGF_END] = {
			.buf_ops = NULL,
		},
	};
	struct xfs_agf			old_agf;
	struct xfs_mount		*mp = sc->mp;
	struct xfs_buf			*agf_bp;
	struct xfs_buf			*agfl_bp;
	struct xfs_agf			*agf;
	int				error;

	/* We require the rmapbt to rebuild anything. */
	if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
		return -EOPNOTSUPP;

	xchk_perag_get(sc->mp, &sc->sa);
	/*
	 * Make sure we have the AGF buffer, as scrub might have decided it
	 * was corrupt after xfs_alloc_read_agf failed with -EFSCORRUPTED.
	 */
	error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
			XFS_AG_DADDR(mp, sc->sa.agno, XFS_AGF_DADDR(mp)),
			XFS_FSS_TO_BB(mp, 1), 0, &agf_bp, NULL);
	if (error)
		return error;
	agf_bp->b_ops = &xfs_agf_buf_ops;
	agf = XFS_BUF_TO_AGF(agf_bp);

	/*
	 * Load the AGFL so that we can screen out OWN_AG blocks that are on
	 * the AGFL now; these blocks might have once been part of the
	 * bno/cnt/rmap btrees but are not now.  This is a chicken and egg
	 * problem: the AGF is corrupt, so we have to trust the AGFL contents
	 * because we can't do any serious cross-referencing with any of the
	 * btrees rooted in the AGF.  If the AGFL contents are obviously bad
	 * then we'll bail out.
	 */
	error = xfs_alloc_read_agfl(mp, sc->tp, sc->sa.agno, &agfl_bp);
	if (error)
		return error;

	/*
	 * Spot-check the AGFL blocks; if they're obviously corrupt then
	 * there's nothing we can do but bail out.
	 */
	error = xfs_agfl_walk(sc->mp, XFS_BUF_TO_AGF(agf_bp), agfl_bp,
			xrep_agf_check_agfl_block, sc);
	if (error)
		return error;

	/*
	 * Find the AGF btree roots.  This is also a chicken-and-egg situation;
	 * see the function for more details.
	 */
	error = xrep_agf_find_btrees(sc, agf_bp, fab, agfl_bp);
	if (error)
		return error;

	/* Start rewriting the header and implant the btrees we found. */
	xrep_agf_init_header(sc, agf_bp, &old_agf);
	xrep_agf_set_roots(sc, agf, fab);
	error = xrep_agf_calc_from_btrees(sc, agf_bp);
	if (error)
		goto out_revert;

	/* Commit the changes and reinitialize incore state. */
	return xrep_agf_commit_new(sc, agf_bp);

out_revert:
	/* Mark the incore AGF state stale and revert the AGF. */
	sc->sa.pag->pagf_init = 0;
	memcpy(agf, &old_agf, sizeof(old_agf));
	return error;
}

/* AGFL */

struct xrep_agfl {
	/* Bitmap of other OWN_AG metadata blocks. */
	struct xfs_bitmap	agmetablocks;

	/* Bitmap of free space. */
	struct xfs_bitmap	*freesp;

	struct xfs_scrub	*sc;
};

/* Record all OWN_AG (free space btree) information from the rmap data. */
STATIC int
xrep_agfl_walk_rmap(
	struct xfs_btree_cur	*cur,
	struct xfs_rmap_irec	*rec,
	void			*priv)
{
	struct xrep_agfl	*ra = priv;
	xfs_fsblock_t		fsb;
	int			error = 0;

	if (xchk_should_terminate(ra->sc, &error))
		return error;

	/* Record all the OWN_AG blocks. */
	if (rec->rm_owner == XFS_RMAP_OWN_AG) {
		fsb = XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_private.a.agno,
				rec->rm_startblock);
		error = xfs_bitmap_set(ra->freesp, fsb, rec->rm_blockcount);
		if (error)
			return error;
	}

	return xfs_bitmap_set_btcur_path(&ra->agmetablocks, cur);
}

/*
 * Map out all the non-AGFL OWN_AG space in this AG so that we can deduce
 * which blocks belong to the AGFL.
 *
 * Compute the set of old AGFL blocks by subtracting from the list of OWN_AG
 * blocks the list of blocks owned by all other OWN_AG metadata (bnobt, cntbt,
 * rmapbt).  These are the old AGFL blocks, so return that list and the number
 * of blocks we're actually going to put back on the AGFL.
 */
STATIC int
xrep_agfl_collect_blocks(
	struct xfs_scrub	*sc,
	struct xfs_buf		*agf_bp,
	struct xfs_bitmap	*agfl_extents,
	xfs_agblock_t		*flcount)
{
	struct xrep_agfl	ra;
	struct xfs_mount	*mp = sc->mp;
	struct xfs_btree_cur	*cur;
	struct xfs_bitmap_range	*br;
	struct xfs_bitmap_range	*n;
	int			error;

	ra.sc = sc;
	ra.freesp = agfl_extents;
	xfs_bitmap_init(&ra.agmetablocks);

	/* Find all space used by the free space btrees & rmapbt. */
	cur = xfs_rmapbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno);
	error = xfs_rmap_query_all(cur, xrep_agfl_walk_rmap, &ra);
	if (error)
		goto err;
	xfs_btree_del_cursor(cur, error);

	/* Find all blocks currently being used by the bnobt. */
	cur = xfs_allocbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno,
			XFS_BTNUM_BNO);
	error = xfs_bitmap_set_btblocks(&ra.agmetablocks, cur);
	if (error)
		goto err;
	xfs_btree_del_cursor(cur, error);

	/* Find all blocks currently being used by the cntbt. */
	cur = xfs_allocbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno,
			XFS_BTNUM_CNT);
	error = xfs_bitmap_set_btblocks(&ra.agmetablocks, cur);
	if (error)
		goto err;

	xfs_btree_del_cursor(cur, error);

	/*
	 * Drop the freesp meta blocks that are in use by btrees.
	 * The remaining blocks /should/ be AGFL blocks.
	 */
	error = xfs_bitmap_disunion(agfl_extents, &ra.agmetablocks);
	xfs_bitmap_destroy(&ra.agmetablocks);
	if (error)
		return error;

	/*
	 * Calculate the new AGFL size.  If we found more blocks than fit in
	 * the AGFL we'll free them later.
	 */
	*flcount = 0;
	for_each_xfs_bitmap_extent(br, n, agfl_extents) {
		*flcount += br->len;
		if (*flcount > xfs_agfl_size(mp))
			break;
	}
	if (*flcount > xfs_agfl_size(mp))
		*flcount = xfs_agfl_size(mp);
	return 0;

err:
	xfs_bitmap_destroy(&ra.agmetablocks);
	xfs_btree_del_cursor(cur, error);
	return error;
}

/* Update the AGF and reset the in-core state. */
STATIC void
xrep_agfl_update_agf(
	struct xfs_scrub	*sc,
	struct xfs_buf		*agf_bp,
	xfs_agblock_t		flcount)
{
	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agf_bp);

	ASSERT(flcount <= xfs_agfl_size(sc->mp));

	/* Trigger fdblocks recalculation */
	xfs_force_summary_recalc(sc->mp);

	/* Update the AGF counters. */
	if (sc->sa.pag->pagf_init)
		sc->sa.pag->pagf_flcount = flcount;
	agf->agf_flfirst = cpu_to_be32(0);
	agf->agf_flcount = cpu_to_be32(flcount);
	agf->agf_fllast = cpu_to_be32(flcount - 1);

	xfs_alloc_log_agf(sc->tp, agf_bp,
			XFS_AGF_FLFIRST | XFS_AGF_FLLAST | XFS_AGF_FLCOUNT);
}

/* Write out a totally new AGFL. */
STATIC void
xrep_agfl_init_header(
	struct xfs_scrub	*sc,
	struct xfs_buf		*agfl_bp,
	struct xfs_bitmap	*agfl_extents,
	xfs_agblock_t		flcount)
{
	struct xfs_mount	*mp = sc->mp;
	__be32			*agfl_bno;
	struct xfs_bitmap_range	*br;
	struct xfs_bitmap_range	*n;
	struct xfs_agfl		*agfl;
	xfs_agblock_t		agbno;
	unsigned int		fl_off;

	ASSERT(flcount <= xfs_agfl_size(mp));

	/*
	 * Start rewriting the header by setting the bno[] array to
	 * NULLAGBLOCK, then setting AGFL header fields.
	 */
	agfl = XFS_BUF_TO_AGFL(agfl_bp);
	memset(agfl, 0xFF, BBTOB(agfl_bp->b_length));
	agfl->agfl_magicnum = cpu_to_be32(XFS_AGFL_MAGIC);
	agfl->agfl_seqno = cpu_to_be32(sc->sa.agno);
	uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_meta_uuid);

	/*
	 * Fill the AGFL with the remaining blocks.  If agfl_extents has more
	 * blocks than fit in the AGFL, they will be freed in a subsequent
	 * step.
	 */
	fl_off = 0;
	agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, agfl_bp);
	for_each_xfs_bitmap_extent(br, n, agfl_extents) {
		agbno = XFS_FSB_TO_AGBNO(mp, br->start);

		trace_xrep_agfl_insert(mp, sc->sa.agno, agbno, br->len);

		while (br->len > 0 && fl_off < flcount) {
			agfl_bno[fl_off] = cpu_to_be32(agbno);
			fl_off++;
			agbno++;

			/*
			 * We've now used br->start by putting it in the AGFL,
			 * so bump br so that we don't reap the block later.
			 */
			br->start++;
			br->len--;
		}

		if (br->len)
			break;
		list_del(&br->list);
		kmem_free(br);
	}

	/* Write new AGFL to disk. */
	xfs_trans_buf_set_type(sc->tp, agfl_bp, XFS_BLFT_AGFL_BUF);
	xfs_trans_log_buf(sc->tp, agfl_bp, 0, BBTOB(agfl_bp->b_length) - 1);
}

/* Repair the AGFL. */
int
xrep_agfl(
	struct xfs_scrub	*sc)
{
	struct xfs_owner_info	oinfo;
	struct xfs_bitmap	agfl_extents;
	struct xfs_mount	*mp = sc->mp;
	struct xfs_buf		*agf_bp;
	struct xfs_buf		*agfl_bp;
	xfs_agblock_t		flcount;
	int			error;

	/* We require the rmapbt to rebuild anything. */
	if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
		return -EOPNOTSUPP;

	xchk_perag_get(sc->mp, &sc->sa);
	xfs_bitmap_init(&agfl_extents);

	/*
	 * Read the AGF so that we can query the rmapbt.  We hope that there's
	 * nothing wrong with the AGF, but all the AG header repair functions
	 * have this chicken-and-egg problem.
	 */
	error = xfs_alloc_read_agf(mp, sc->tp, sc->sa.agno, 0, &agf_bp);
	if (error)
		return error;
	if (!agf_bp)
		return -ENOMEM;

	/*
	 * Make sure we have the AGFL buffer, as scrub might have decided it
	 * was corrupt after xfs_alloc_read_agfl failed with -EFSCORRUPTED.
	 */
	error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
			XFS_AG_DADDR(mp, sc->sa.agno, XFS_AGFL_DADDR(mp)),
			XFS_FSS_TO_BB(mp, 1), 0, &agfl_bp, NULL);
	if (error)
		return error;
	agfl_bp->b_ops = &xfs_agfl_buf_ops;

	/* Gather all the extents we're going to put on the new AGFL. */
	error = xrep_agfl_collect_blocks(sc, agf_bp, &agfl_extents, &flcount);
	if (error)
		goto err;

	/*
	 * Update AGF and AGFL.  We reset the global free block counter when
	 * we adjust the AGF flcount (which can fail) so avoid updating any
	 * buffers until we know that part works.
	 */
	xrep_agfl_update_agf(sc, agf_bp, flcount);
	xrep_agfl_init_header(sc, agfl_bp, &agfl_extents, flcount);

	/*
	 * Ok, the AGFL should be ready to go now.  Roll the transaction to
	 * make the new AGFL permanent before we start using it to return
	 * freespace overflow to the freespace btrees.
	 */
	sc->sa.agf_bp = agf_bp;
	sc->sa.agfl_bp = agfl_bp;
	error = xrep_roll_ag_trans(sc);
	if (error)
		goto err;

	/* Dump any AGFL overflow. */
	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_AG);
	return xrep_reap_extents(sc, &agfl_extents, &oinfo, XFS_AG_RESV_AGFL);
err:
	xfs_bitmap_destroy(&agfl_extents);
	return error;
}

/* AGI */

/*
 * Offset within the xrep_find_ag_btree array for each btree type.  Avoid the
 * XFS_BTNUM_ names here to avoid creating a sparse array.
 */
enum {
	XREP_AGI_INOBT = 0,
	XREP_AGI_FINOBT,
	XREP_AGI_END,
	XREP_AGI_MAX
};

/*
 * Given the inode btree roots described by *fab, find the roots, check them
 * for sanity, and pass the root data back out via *fab.
 */
STATIC int
xrep_agi_find_btrees(
	struct xfs_scrub		*sc,
	struct xrep_find_ag_btree	*fab)
{
	struct xfs_buf			*agf_bp;
	struct xfs_mount		*mp = sc->mp;
	int				error;

	/* Read the AGF. */
	error = xfs_alloc_read_agf(mp, sc->tp, sc->sa.agno, 0, &agf_bp);
	if (error)
		return error;
	if (!agf_bp)
		return -ENOMEM;

	/* Find the btree roots. */
	error = xrep_find_ag_btree_roots(sc, agf_bp, fab, NULL);
	if (error)
		return error;

	/* We must find the inobt root. */
	if (!xrep_check_btree_root(sc, &fab[XREP_AGI_INOBT]))
		return -EFSCORRUPTED;

	/* We must find the finobt root if that feature is enabled. */
	if (xfs_sb_version_hasfinobt(&mp->m_sb) &&
	    !xrep_check_btree_root(sc, &fab[XREP_AGI_FINOBT]))
		return -EFSCORRUPTED;

	return 0;
}

/*
 * Reinitialize the AGI header, making an in-core copy of the old contents so
 * that we know which in-core state needs to be reinitialized.
 */
STATIC void
xrep_agi_init_header(
	struct xfs_scrub	*sc,
	struct xfs_buf		*agi_bp,
	struct xfs_agi		*old_agi)
{
	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agi_bp);
	struct xfs_mount	*mp = sc->mp;

	memcpy(old_agi, agi, sizeof(*old_agi));
	memset(agi, 0, BBTOB(agi_bp->b_length));
	agi->agi_magicnum = cpu_to_be32(XFS_AGI_MAGIC);
	agi->agi_versionnum = cpu_to_be32(XFS_AGI_VERSION);
	agi->agi_seqno = cpu_to_be32(sc->sa.agno);
	agi->agi_length = cpu_to_be32(xfs_ag_block_count(mp, sc->sa.agno));
	agi->agi_newino = cpu_to_be32(NULLAGINO);
	agi->agi_dirino = cpu_to_be32(NULLAGINO);
	if (xfs_sb_version_hascrc(&mp->m_sb))
		uuid_copy(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid);

	/* We don't know how to fix the unlinked list yet. */
	memcpy(&agi->agi_unlinked, &old_agi->agi_unlinked,
			sizeof(agi->agi_unlinked));

	/* Mark the incore AGF data stale until we're done fixing things. */
	ASSERT(sc->sa.pag->pagi_init);
	sc->sa.pag->pagi_init = 0;
}

/* Set btree root information in an AGI. */
STATIC void
xrep_agi_set_roots(
	struct xfs_scrub		*sc,
	struct xfs_agi			*agi,
	struct xrep_find_ag_btree	*fab)
{
	agi->agi_root = cpu_to_be32(fab[XREP_AGI_INOBT].root);
	agi->agi_level = cpu_to_be32(fab[XREP_AGI_INOBT].height);

	if (xfs_sb_version_hasfinobt(&sc->mp->m_sb)) {
		agi->agi_free_root = cpu_to_be32(fab[XREP_AGI_FINOBT].root);
		agi->agi_free_level = cpu_to_be32(fab[XREP_AGI_FINOBT].height);
	}
}

/* Update the AGI counters. */
STATIC int
xrep_agi_calc_from_btrees(
	struct xfs_scrub	*sc,
	struct xfs_buf		*agi_bp)
{
	struct xfs_btree_cur	*cur;
	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agi_bp);
	struct xfs_mount	*mp = sc->mp;
	xfs_agino_t		count;
	xfs_agino_t		freecount;
	int			error;

	cur = xfs_inobt_init_cursor(mp, sc->tp, agi_bp, sc->sa.agno,
			XFS_BTNUM_INO);
	error = xfs_ialloc_count_inodes(cur, &count, &freecount);
	if (error)
		goto err;
	xfs_btree_del_cursor(cur, error);

	agi->agi_count = cpu_to_be32(count);
	agi->agi_freecount = cpu_to_be32(freecount);
	return 0;
err:
	xfs_btree_del_cursor(cur, error);
	return error;
}

/* Trigger reinitialization of the in-core data. */
STATIC int
xrep_agi_commit_new(
	struct xfs_scrub	*sc,
	struct xfs_buf		*agi_bp)
{
	struct xfs_perag	*pag;
	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agi_bp);

	/* Trigger inode count recalculation */
	xfs_force_summary_recalc(sc->mp);

	/* Write this to disk. */
	xfs_trans_buf_set_type(sc->tp, agi_bp, XFS_BLFT_AGI_BUF);
	xfs_trans_log_buf(sc->tp, agi_bp, 0, BBTOB(agi_bp->b_length) - 1);

	/* Now reinitialize the in-core counters if necessary. */
	pag = sc->sa.pag;
	pag->pagi_count = be32_to_cpu(agi->agi_count);
	pag->pagi_freecount = be32_to_cpu(agi->agi_freecount);
	pag->pagi_init = 1;

	return 0;
}

/* Repair the AGI. */
int
xrep_agi(
	struct xfs_scrub		*sc)
{
	struct xrep_find_ag_btree	fab[XREP_AGI_MAX] = {
		[XREP_AGI_INOBT] = {
			.rmap_owner = XFS_RMAP_OWN_INOBT,
			.buf_ops = &xfs_inobt_buf_ops,
			.magic = XFS_IBT_CRC_MAGIC,
		},
		[XREP_AGI_FINOBT] = {
			.rmap_owner = XFS_RMAP_OWN_INOBT,
			.buf_ops = &xfs_inobt_buf_ops,
			.magic = XFS_FIBT_CRC_MAGIC,
		},
		[XREP_AGI_END] = {
			.buf_ops = NULL
		},
	};
	struct xfs_agi			old_agi;
	struct xfs_mount		*mp = sc->mp;
	struct xfs_buf			*agi_bp;
	struct xfs_agi			*agi;
	int				error;

	/* We require the rmapbt to rebuild anything. */
	if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
		return -EOPNOTSUPP;

	xchk_perag_get(sc->mp, &sc->sa);
	/*
	 * Make sure we have the AGI buffer, as scrub might have decided it
	 * was corrupt after xfs_ialloc_read_agi failed with -EFSCORRUPTED.
	 */
	error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
			XFS_AG_DADDR(mp, sc->sa.agno, XFS_AGI_DADDR(mp)),
			XFS_FSS_TO_BB(mp, 1), 0, &agi_bp, NULL);
	if (error)
		return error;
	agi_bp->b_ops = &xfs_agi_buf_ops;
	agi = XFS_BUF_TO_AGI(agi_bp);

	/* Find the AGI btree roots. */
	error = xrep_agi_find_btrees(sc, fab);
	if (error)
		return error;

	/* Start rewriting the header and implant the btrees we found. */
	xrep_agi_init_header(sc, agi_bp, &old_agi);
	xrep_agi_set_roots(sc, agi, fab);
	error = xrep_agi_calc_from_btrees(sc, agi_bp);
	if (error)
		goto out_revert;

	/* Reinitialize in-core state. */
	return xrep_agi_commit_new(sc, agi_bp);

out_revert:
	/* Mark the incore AGI state stale and revert the AGI. */
	sc->sa.pag->pagi_init = 0;
	memcpy(agi, &old_agi, sizeof(old_agi));
	return error;
}