summaryrefslogtreecommitdiffstats
path: root/fs/xfs/scrub/common.c
blob: aa874607618a22e0dbc763f5e540994619231057 (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
// SPDX-License-Identifier: GPL-2.0+
/*
 * Copyright (C) 2017 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_btree.h"
#include "xfs_log_format.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_inode.h"
#include "xfs_icache.h"
#include "xfs_alloc.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc.h"
#include "xfs_ialloc_btree.h"
#include "xfs_refcount_btree.h"
#include "xfs_rmap.h"
#include "xfs_rmap_btree.h"
#include "xfs_log.h"
#include "xfs_trans_priv.h"
#include "xfs_attr.h"
#include "xfs_reflink.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/trace.h"
#include "scrub/repair.h"
#include "scrub/health.h"

/* Common code for the metadata scrubbers. */

/*
 * Handling operational errors.
 *
 * The *_process_error() family of functions are used to process error return
 * codes from functions called as part of a scrub operation.
 *
 * If there's no error, we return true to tell the caller that it's ok
 * to move on to the next check in its list.
 *
 * For non-verifier errors (e.g. ENOMEM) we return false to tell the
 * caller that something bad happened, and we preserve *error so that
 * the caller can return the *error up the stack to userspace.
 *
 * Verifier errors (EFSBADCRC/EFSCORRUPTED) are recorded by setting
 * OFLAG_CORRUPT in sm_flags and the *error is cleared.  In other words,
 * we track verifier errors (and failed scrub checks) via OFLAG_CORRUPT,
 * not via return codes.  We return false to tell the caller that
 * something bad happened.  Since the error has been cleared, the caller
 * will (presumably) return that zero and scrubbing will move on to
 * whatever's next.
 *
 * ftrace can be used to record the precise metadata location and the
 * approximate code location of the failed operation.
 */

/* Check for operational errors. */
static bool
__xchk_process_error(
	struct xfs_scrub	*sc,
	xfs_agnumber_t		agno,
	xfs_agblock_t		bno,
	int			*error,
	__u32			errflag,
	void			*ret_ip)
{
	switch (*error) {
	case 0:
		return true;
	case -EDEADLOCK:
		/* Used to restart an op with deadlock avoidance. */
		trace_xchk_deadlock_retry(sc->ip, sc->sm, *error);
		break;
	case -EFSBADCRC:
	case -EFSCORRUPTED:
		/* Note the badness but don't abort. */
		sc->sm->sm_flags |= errflag;
		*error = 0;
		/* fall through */
	default:
		trace_xchk_op_error(sc, agno, bno, *error,
				ret_ip);
		break;
	}
	return false;
}

bool
xchk_process_error(
	struct xfs_scrub	*sc,
	xfs_agnumber_t		agno,
	xfs_agblock_t		bno,
	int			*error)
{
	return __xchk_process_error(sc, agno, bno, error,
			XFS_SCRUB_OFLAG_CORRUPT, __return_address);
}

bool
xchk_xref_process_error(
	struct xfs_scrub	*sc,
	xfs_agnumber_t		agno,
	xfs_agblock_t		bno,
	int			*error)
{
	return __xchk_process_error(sc, agno, bno, error,
			XFS_SCRUB_OFLAG_XFAIL, __return_address);
}

/* Check for operational errors for a file offset. */
static bool
__xchk_fblock_process_error(
	struct xfs_scrub	*sc,
	int			whichfork,
	xfs_fileoff_t		offset,
	int			*error,
	__u32			errflag,
	void			*ret_ip)
{
	switch (*error) {
	case 0:
		return true;
	case -EDEADLOCK:
		/* Used to restart an op with deadlock avoidance. */
		trace_xchk_deadlock_retry(sc->ip, sc->sm, *error);
		break;
	case -EFSBADCRC:
	case -EFSCORRUPTED:
		/* Note the badness but don't abort. */
		sc->sm->sm_flags |= errflag;
		*error = 0;
		/* fall through */
	default:
		trace_xchk_file_op_error(sc, whichfork, offset, *error,
				ret_ip);
		break;
	}
	return false;
}

bool
xchk_fblock_process_error(
	struct xfs_scrub	*sc,
	int			whichfork,
	xfs_fileoff_t		offset,
	int			*error)
{
	return __xchk_fblock_process_error(sc, whichfork, offset, error,
			XFS_SCRUB_OFLAG_CORRUPT, __return_address);
}

bool
xchk_fblock_xref_process_error(
	struct xfs_scrub	*sc,
	int			whichfork,
	xfs_fileoff_t		offset,
	int			*error)
{
	return __xchk_fblock_process_error(sc, whichfork, offset, error,
			XFS_SCRUB_OFLAG_XFAIL, __return_address);
}

/*
 * Handling scrub corruption/optimization/warning checks.
 *
 * The *_set_{corrupt,preen,warning}() family of functions are used to
 * record the presence of metadata that is incorrect (corrupt), could be
 * optimized somehow (preen), or should be flagged for administrative
 * review but is not incorrect (warn).
 *
 * ftrace can be used to record the precise metadata location and
 * approximate code location of the failed check.
 */

/* Record a block which could be optimized. */
void
xchk_block_set_preen(
	struct xfs_scrub	*sc,
	struct xfs_buf		*bp)
{
	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_PREEN;
	trace_xchk_block_preen(sc, bp->b_bn, __return_address);
}

/*
 * Record an inode which could be optimized.  The trace data will
 * include the block given by bp if bp is given; otherwise it will use
 * the block location of the inode record itself.
 */
void
xchk_ino_set_preen(
	struct xfs_scrub	*sc,
	xfs_ino_t		ino)
{
	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_PREEN;
	trace_xchk_ino_preen(sc, ino, __return_address);
}

/* Record something being wrong with the filesystem primary superblock. */
void
xchk_set_corrupt(
	struct xfs_scrub	*sc)
{
	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
	trace_xchk_fs_error(sc, 0, __return_address);
}

/* Record a corrupt block. */
void
xchk_block_set_corrupt(
	struct xfs_scrub	*sc,
	struct xfs_buf		*bp)
{
	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
	trace_xchk_block_error(sc, bp->b_bn, __return_address);
}

/* Record a corruption while cross-referencing. */
void
xchk_block_xref_set_corrupt(
	struct xfs_scrub	*sc,
	struct xfs_buf		*bp)
{
	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
	trace_xchk_block_error(sc, bp->b_bn, __return_address);
}

/*
 * Record a corrupt inode.  The trace data will include the block given
 * by bp if bp is given; otherwise it will use the block location of the
 * inode record itself.
 */
void
xchk_ino_set_corrupt(
	struct xfs_scrub	*sc,
	xfs_ino_t		ino)
{
	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
	trace_xchk_ino_error(sc, ino, __return_address);
}

/* Record a corruption while cross-referencing with an inode. */
void
xchk_ino_xref_set_corrupt(
	struct xfs_scrub	*sc,
	xfs_ino_t		ino)
{
	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
	trace_xchk_ino_error(sc, ino, __return_address);
}

/* Record corruption in a block indexed by a file fork. */
void
xchk_fblock_set_corrupt(
	struct xfs_scrub	*sc,
	int			whichfork,
	xfs_fileoff_t		offset)
{
	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
	trace_xchk_fblock_error(sc, whichfork, offset, __return_address);
}

/* Record a corruption while cross-referencing a fork block. */
void
xchk_fblock_xref_set_corrupt(
	struct xfs_scrub	*sc,
	int			whichfork,
	xfs_fileoff_t		offset)
{
	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
	trace_xchk_fblock_error(sc, whichfork, offset, __return_address);
}

/*
 * Warn about inodes that need administrative review but is not
 * incorrect.
 */
void
xchk_ino_set_warning(
	struct xfs_scrub	*sc,
	xfs_ino_t		ino)
{
	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_WARNING;
	trace_xchk_ino_warning(sc, ino, __return_address);
}

/* Warn about a block indexed by a file fork that needs review. */
void
xchk_fblock_set_warning(
	struct xfs_scrub	*sc,
	int			whichfork,
	xfs_fileoff_t		offset)
{
	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_WARNING;
	trace_xchk_fblock_warning(sc, whichfork, offset, __return_address);
}

/* Signal an incomplete scrub. */
void
xchk_set_incomplete(
	struct xfs_scrub	*sc)
{
	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_INCOMPLETE;
	trace_xchk_incomplete(sc, __return_address);
}

/*
 * rmap scrubbing -- compute the number of blocks with a given owner,
 * at least according to the reverse mapping data.
 */

struct xchk_rmap_ownedby_info {
	const struct xfs_owner_info	*oinfo;
	xfs_filblks_t			*blocks;
};

STATIC int
xchk_count_rmap_ownedby_irec(
	struct xfs_btree_cur		*cur,
	struct xfs_rmap_irec		*rec,
	void				*priv)
{
	struct xchk_rmap_ownedby_info	*sroi = priv;
	bool				irec_attr;
	bool				oinfo_attr;

	irec_attr = rec->rm_flags & XFS_RMAP_ATTR_FORK;
	oinfo_attr = sroi->oinfo->oi_flags & XFS_OWNER_INFO_ATTR_FORK;

	if (rec->rm_owner != sroi->oinfo->oi_owner)
		return 0;

	if (XFS_RMAP_NON_INODE_OWNER(rec->rm_owner) || irec_attr == oinfo_attr)
		(*sroi->blocks) += rec->rm_blockcount;

	return 0;
}

/*
 * Calculate the number of blocks the rmap thinks are owned by something.
 * The caller should pass us an rmapbt cursor.
 */
int
xchk_count_rmap_ownedby_ag(
	struct xfs_scrub		*sc,
	struct xfs_btree_cur		*cur,
	const struct xfs_owner_info	*oinfo,
	xfs_filblks_t			*blocks)
{
	struct xchk_rmap_ownedby_info	sroi = {
		.oinfo			= oinfo,
		.blocks			= blocks,
	};

	*blocks = 0;
	return xfs_rmap_query_all(cur, xchk_count_rmap_ownedby_irec,
			&sroi);
}

/*
 * AG scrubbing
 *
 * These helpers facilitate locking an allocation group's header
 * buffers, setting up cursors for all btrees that are present, and
 * cleaning everything up once we're through.
 */

/* Decide if we want to return an AG header read failure. */
static inline bool
want_ag_read_header_failure(
	struct xfs_scrub	*sc,
	unsigned int		type)
{
	/* Return all AG header read failures when scanning btrees. */
	if (sc->sm->sm_type != XFS_SCRUB_TYPE_AGF &&
	    sc->sm->sm_type != XFS_SCRUB_TYPE_AGFL &&
	    sc->sm->sm_type != XFS_SCRUB_TYPE_AGI)
		return true;
	/*
	 * If we're scanning a given type of AG header, we only want to
	 * see read failures from that specific header.  We'd like the
	 * other headers to cross-check them, but this isn't required.
	 */
	if (sc->sm->sm_type == type)
		return true;
	return false;
}

/*
 * Grab all the headers for an AG.
 *
 * The headers should be released by xchk_ag_free, but as a fail
 * safe we attach all the buffers we grab to the scrub transaction so
 * they'll all be freed when we cancel it.
 */
int
xchk_ag_read_headers(
	struct xfs_scrub	*sc,
	xfs_agnumber_t		agno,
	struct xchk_ag		*sa)
{
	struct xfs_mount	*mp = sc->mp;
	int			error;

	sa->agno = agno;

	error = xfs_ialloc_read_agi(mp, sc->tp, agno, &sa->agi_bp);
	if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGI))
		goto out;

	error = xfs_alloc_read_agf(mp, sc->tp, agno, 0, &sa->agf_bp);
	if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGF))
		goto out;

	error = xfs_alloc_read_agfl(mp, sc->tp, agno, &sa->agfl_bp);
	if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGFL))
		goto out;
	error = 0;
out:
	return error;
}

/* Release all the AG btree cursors. */
void
xchk_ag_btcur_free(
	struct xchk_ag		*sa)
{
	if (sa->refc_cur)
		xfs_btree_del_cursor(sa->refc_cur, XFS_BTREE_ERROR);
	if (sa->rmap_cur)
		xfs_btree_del_cursor(sa->rmap_cur, XFS_BTREE_ERROR);
	if (sa->fino_cur)
		xfs_btree_del_cursor(sa->fino_cur, XFS_BTREE_ERROR);
	if (sa->ino_cur)
		xfs_btree_del_cursor(sa->ino_cur, XFS_BTREE_ERROR);
	if (sa->cnt_cur)
		xfs_btree_del_cursor(sa->cnt_cur, XFS_BTREE_ERROR);
	if (sa->bno_cur)
		xfs_btree_del_cursor(sa->bno_cur, XFS_BTREE_ERROR);

	sa->refc_cur = NULL;
	sa->rmap_cur = NULL;
	sa->fino_cur = NULL;
	sa->ino_cur = NULL;
	sa->bno_cur = NULL;
	sa->cnt_cur = NULL;
}

/* Initialize all the btree cursors for an AG. */
void
xchk_ag_btcur_init(
	struct xfs_scrub	*sc,
	struct xchk_ag		*sa)
{
	struct xfs_mount	*mp = sc->mp;
	xfs_agnumber_t		agno = sa->agno;

	xchk_perag_get(sc->mp, sa);
	if (sa->agf_bp &&
	    xchk_ag_btree_healthy_enough(sc, sa->pag, XFS_BTNUM_BNO)) {
		/* Set up a bnobt cursor for cross-referencing. */
		sa->bno_cur = xfs_allocbt_init_cursor(mp, sc->tp, sa->agf_bp,
				agno, XFS_BTNUM_BNO);
	}

	if (sa->agf_bp &&
	    xchk_ag_btree_healthy_enough(sc, sa->pag, XFS_BTNUM_CNT)) {
		/* Set up a cntbt cursor for cross-referencing. */
		sa->cnt_cur = xfs_allocbt_init_cursor(mp, sc->tp, sa->agf_bp,
				agno, XFS_BTNUM_CNT);
	}

	/* Set up a inobt cursor for cross-referencing. */
	if (sa->agi_bp &&
	    xchk_ag_btree_healthy_enough(sc, sa->pag, XFS_BTNUM_INO)) {
		sa->ino_cur = xfs_inobt_init_cursor(mp, sc->tp, sa->agi_bp,
					agno, XFS_BTNUM_INO);
	}

	/* Set up a finobt cursor for cross-referencing. */
	if (sa->agi_bp && xfs_sb_version_hasfinobt(&mp->m_sb) &&
	    xchk_ag_btree_healthy_enough(sc, sa->pag, XFS_BTNUM_FINO)) {
		sa->fino_cur = xfs_inobt_init_cursor(mp, sc->tp, sa->agi_bp,
				agno, XFS_BTNUM_FINO);
	}

	/* Set up a rmapbt cursor for cross-referencing. */
	if (sa->agf_bp && xfs_sb_version_hasrmapbt(&mp->m_sb) &&
	    xchk_ag_btree_healthy_enough(sc, sa->pag, XFS_BTNUM_RMAP)) {
		sa->rmap_cur = xfs_rmapbt_init_cursor(mp, sc->tp, sa->agf_bp,
				agno);
	}

	/* Set up a refcountbt cursor for cross-referencing. */
	if (sa->agf_bp && xfs_sb_version_hasreflink(&mp->m_sb) &&
	    xchk_ag_btree_healthy_enough(sc, sa->pag, XFS_BTNUM_REFC)) {
		sa->refc_cur = xfs_refcountbt_init_cursor(mp, sc->tp,
				sa->agf_bp, agno);
	}
}

/* Release the AG header context and btree cursors. */
void
xchk_ag_free(
	struct xfs_scrub	*sc,
	struct xchk_ag		*sa)
{
	xchk_ag_btcur_free(sa);
	if (sa->agfl_bp) {
		xfs_trans_brelse(sc->tp, sa->agfl_bp);
		sa->agfl_bp = NULL;
	}
	if (sa->agf_bp) {
		xfs_trans_brelse(sc->tp, sa->agf_bp);
		sa->agf_bp = NULL;
	}
	if (sa->agi_bp) {
		xfs_trans_brelse(sc->tp, sa->agi_bp);
		sa->agi_bp = NULL;
	}
	if (sa->pag) {
		xfs_perag_put(sa->pag);
		sa->pag = NULL;
	}
	sa->agno = NULLAGNUMBER;
}

/*
 * For scrub, grab the AGI and the AGF headers, in that order.  Locking
 * order requires us to get the AGI before the AGF.  We use the
 * transaction to avoid deadlocking on crosslinked metadata buffers;
 * either the caller passes one in (bmap scrub) or we have to create a
 * transaction ourselves.
 */
int
xchk_ag_init(
	struct xfs_scrub	*sc,
	xfs_agnumber_t		agno,
	struct xchk_ag		*sa)
{
	int			error;

	error = xchk_ag_read_headers(sc, agno, sa);
	if (error)
		return error;

	xchk_ag_btcur_init(sc, sa);
	return 0;
}

/*
 * Grab the per-ag structure if we haven't already gotten it.  Teardown of the
 * xchk_ag will release it for us.
 */
void
xchk_perag_get(
	struct xfs_mount	*mp,
	struct xchk_ag		*sa)
{
	if (!sa->pag)
		sa->pag = xfs_perag_get(mp, sa->agno);
}

/* Per-scrubber setup functions */

/*
 * Grab an empty transaction so that we can re-grab locked buffers if
 * one of our btrees turns out to be cyclic.
 *
 * If we're going to repair something, we need to ask for the largest possible
 * log reservation so that we can handle the worst case scenario for metadata
 * updates while rebuilding a metadata item.  We also need to reserve as many
 * blocks in the head transaction as we think we're going to need to rebuild
 * the metadata object.
 */
int
xchk_trans_alloc(
	struct xfs_scrub	*sc,
	uint			resblks)
{
	if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)
		return xfs_trans_alloc(sc->mp, &M_RES(sc->mp)->tr_itruncate,
				resblks, 0, 0, &sc->tp);

	return xfs_trans_alloc_empty(sc->mp, &sc->tp);
}

/* Set us up with a transaction and an empty context. */
int
xchk_setup_fs(
	struct xfs_scrub	*sc)
{
	uint			resblks;

	resblks = xrep_calc_ag_resblks(sc);
	return xchk_trans_alloc(sc, resblks);
}

/* Set us up with AG headers and btree cursors. */
int
xchk_setup_ag_btree(
	struct xfs_scrub	*sc,
	bool			force_log)
{
	struct xfs_mount	*mp = sc->mp;
	int			error;

	/*
	 * If the caller asks us to checkpont the log, do so.  This
	 * expensive operation should be performed infrequently and only
	 * as a last resort.  Any caller that sets force_log should
	 * document why they need to do so.
	 */
	if (force_log) {
		error = xchk_checkpoint_log(mp);
		if (error)
			return error;
	}

	error = xchk_setup_fs(sc);
	if (error)
		return error;

	return xchk_ag_init(sc, sc->sm->sm_agno, &sc->sa);
}

/* Push everything out of the log onto disk. */
int
xchk_checkpoint_log(
	struct xfs_mount	*mp)
{
	int			error;

	error = xfs_log_force(mp, XFS_LOG_SYNC);
	if (error)
		return error;
	xfs_ail_push_all_sync(mp->m_ail);
	return 0;
}

/*
 * Given an inode and the scrub control structure, grab either the
 * inode referenced in the control structure or the inode passed in.
 * The inode is not locked.
 */
int
xchk_get_inode(
	struct xfs_scrub	*sc)
{
	struct xfs_imap		imap;
	struct xfs_mount	*mp = sc->mp;
	struct xfs_inode	*ip_in = XFS_I(file_inode(sc->file));
	struct xfs_inode	*ip = NULL;
	int			error;

	/* We want to scan the inode we already had opened. */
	if (sc->sm->sm_ino == 0 || sc->sm->sm_ino == ip_in->i_ino) {
		sc->ip = ip_in;
		return 0;
	}

	/* Look up the inode, see if the generation number matches. */
	if (xfs_internal_inum(mp, sc->sm->sm_ino))
		return -ENOENT;
	error = xfs_iget(mp, NULL, sc->sm->sm_ino,
			XFS_IGET_UNTRUSTED | XFS_IGET_DONTCACHE, 0, &ip);
	switch (error) {
	case -ENOENT:
		/* Inode doesn't exist, just bail out. */
		return error;
	case 0:
		/* Got an inode, continue. */
		break;
	case -EINVAL:
		/*
		 * -EINVAL with IGET_UNTRUSTED could mean one of several
		 * things: userspace gave us an inode number that doesn't
		 * correspond to fs space, or doesn't have an inobt entry;
		 * or it could simply mean that the inode buffer failed the
		 * read verifiers.
		 *
		 * Try just the inode mapping lookup -- if it succeeds, then
		 * the inode buffer verifier failed and something needs fixing.
		 * Otherwise, we really couldn't find it so tell userspace
		 * that it no longer exists.
		 */
		error = xfs_imap(sc->mp, sc->tp, sc->sm->sm_ino, &imap,
				XFS_IGET_UNTRUSTED | XFS_IGET_DONTCACHE);
		if (error)
			return -ENOENT;
		error = -EFSCORRUPTED;
		/* fall through */
	default:
		trace_xchk_op_error(sc,
				XFS_INO_TO_AGNO(mp, sc->sm->sm_ino),
				XFS_INO_TO_AGBNO(mp, sc->sm->sm_ino),
				error, __return_address);
		return error;
	}
	if (VFS_I(ip)->i_generation != sc->sm->sm_gen) {
		xfs_irele(ip);
		return -ENOENT;
	}

	sc->ip = ip;
	return 0;
}

/* Set us up to scrub a file's contents. */
int
xchk_setup_inode_contents(
	struct xfs_scrub	*sc,
	unsigned int		resblks)
{
	int			error;

	error = xchk_get_inode(sc);
	if (error)
		return error;

	/* Got the inode, lock it and we're ready to go. */
	sc->ilock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
	xfs_ilock(sc->ip, sc->ilock_flags);
	error = xchk_trans_alloc(sc, resblks);
	if (error)
		goto out;
	sc->ilock_flags |= XFS_ILOCK_EXCL;
	xfs_ilock(sc->ip, XFS_ILOCK_EXCL);

out:
	/* scrub teardown will unlock and release the inode for us */
	return error;
}

/*
 * Predicate that decides if we need to evaluate the cross-reference check.
 * If there was an error accessing the cross-reference btree, just delete
 * the cursor and skip the check.
 */
bool
xchk_should_check_xref(
	struct xfs_scrub	*sc,
	int			*error,
	struct xfs_btree_cur	**curpp)
{
	/* No point in xref if we already know we're corrupt. */
	if (xchk_skip_xref(sc->sm))
		return false;

	if (*error == 0)
		return true;

	if (curpp) {
		/* If we've already given up on xref, just bail out. */
		if (!*curpp)
			return false;

		/* xref error, delete cursor and bail out. */
		xfs_btree_del_cursor(*curpp, XFS_BTREE_ERROR);
		*curpp = NULL;
	}

	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XFAIL;
	trace_xchk_xref_error(sc, *error, __return_address);

	/*
	 * Errors encountered during cross-referencing with another
	 * data structure should not cause this scrubber to abort.
	 */
	*error = 0;
	return false;
}

/* Run the structure verifiers on in-memory buffers to detect bad memory. */
void
xchk_buffer_recheck(
	struct xfs_scrub	*sc,
	struct xfs_buf		*bp)
{
	xfs_failaddr_t		fa;

	if (bp->b_ops == NULL) {
		xchk_block_set_corrupt(sc, bp);
		return;
	}
	if (bp->b_ops->verify_struct == NULL) {
		xchk_set_incomplete(sc);
		return;
	}
	fa = bp->b_ops->verify_struct(bp);
	if (!fa)
		return;
	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
	trace_xchk_block_error(sc, bp->b_bn, fa);
}

/*
 * Scrub the attr/data forks of a metadata inode.  The metadata inode must be
 * pointed to by sc->ip and the ILOCK must be held.
 */
int
xchk_metadata_inode_forks(
	struct xfs_scrub	*sc)
{
	__u32			smtype;
	bool			shared;
	int			error;

	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
		return 0;

	/* Metadata inodes don't live on the rt device. */
	if (sc->ip->i_diflags & XFS_DIFLAG_REALTIME) {
		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
		return 0;
	}

	/* They should never participate in reflink. */
	if (xfs_is_reflink_inode(sc->ip)) {
		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
		return 0;
	}

	/* They also should never have extended attributes. */
	if (xfs_inode_hasattr(sc->ip)) {
		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
		return 0;
	}

	/* Invoke the data fork scrubber. */
	smtype = sc->sm->sm_type;
	sc->sm->sm_type = XFS_SCRUB_TYPE_BMBTD;
	error = xchk_bmap_data(sc);
	sc->sm->sm_type = smtype;
	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
		return error;

	/* Look for incorrect shared blocks. */
	if (xfs_sb_version_hasreflink(&sc->mp->m_sb)) {
		error = xfs_reflink_inode_has_shared_extents(sc->tp, sc->ip,
				&shared);
		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0,
				&error))
			return error;
		if (shared)
			xchk_ino_set_corrupt(sc, sc->ip->i_ino);
	}

	return error;
}

/*
 * Try to lock an inode in violation of the usual locking order rules.  For
 * example, trying to get the IOLOCK while in transaction context, or just
 * plain breaking AG-order or inode-order inode locking rules.  Either way,
 * the only way to avoid an ABBA deadlock is to use trylock and back off if
 * we can't.
 */
int
xchk_ilock_inverted(
	struct xfs_inode	*ip,
	uint			lock_mode)
{
	int			i;

	for (i = 0; i < 20; i++) {
		if (xfs_ilock_nowait(ip, lock_mode))
			return 0;
		delay(1);
	}
	return -EDEADLOCK;
}

/* Pause background reaping of resources. */
void
xchk_stop_reaping(
	struct xfs_scrub	*sc)
{
	sc->flags |= XCHK_REAPING_DISABLED;
	xfs_blockgc_stop(sc->mp);
}

/* Restart background reaping of resources. */
void
xchk_start_reaping(
	struct xfs_scrub	*sc)
{
	xfs_blockgc_start(sc->mp);
	sc->flags &= ~XCHK_REAPING_DISABLED;
}