summaryrefslogtreecommitdiffstats
path: root/fs/xfs/scrub/btree.c
blob: 1935b9ce1885c9437545bcf0404c78883f569ceb (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright (C) 2017-2023 Oracle.  All Rights Reserved.
 * Author: Darrick J. Wong <djwong@kernel.org>
 */
#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_inode.h"
#include "xfs_btree.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/btree.h"
#include "scrub/trace.h"

/* btree scrubbing */

/*
 * Check for btree operation errors.  See the section about handling
 * operational errors in common.c.
 */
static bool
__xchk_btree_process_error(
	struct xfs_scrub	*sc,
	struct xfs_btree_cur	*cur,
	int			level,
	int			*error,
	__u32			errflag,
	void			*ret_ip)
{
	if (*error == 0)
		return true;

	switch (*error) {
	case -EDEADLOCK:
	case -ECHRNG:
		/* 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;
		fallthrough;
	default:
		if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
			trace_xchk_ifork_btree_op_error(sc, cur, level,
					*error, ret_ip);
		else
			trace_xchk_btree_op_error(sc, cur, level,
					*error, ret_ip);
		break;
	}
	return false;
}

bool
xchk_btree_process_error(
	struct xfs_scrub	*sc,
	struct xfs_btree_cur	*cur,
	int			level,
	int			*error)
{
	return __xchk_btree_process_error(sc, cur, level, error,
			XFS_SCRUB_OFLAG_CORRUPT, __return_address);
}

bool
xchk_btree_xref_process_error(
	struct xfs_scrub	*sc,
	struct xfs_btree_cur	*cur,
	int			level,
	int			*error)
{
	return __xchk_btree_process_error(sc, cur, level, error,
			XFS_SCRUB_OFLAG_XFAIL, __return_address);
}

/* Record btree block corruption. */
static void
__xchk_btree_set_corrupt(
	struct xfs_scrub	*sc,
	struct xfs_btree_cur	*cur,
	int			level,
	__u32			errflag,
	void			*ret_ip)
{
	sc->sm->sm_flags |= errflag;

	if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
		trace_xchk_ifork_btree_error(sc, cur, level,
				ret_ip);
	else
		trace_xchk_btree_error(sc, cur, level,
				ret_ip);
}

void
xchk_btree_set_corrupt(
	struct xfs_scrub	*sc,
	struct xfs_btree_cur	*cur,
	int			level)
{
	__xchk_btree_set_corrupt(sc, cur, level, XFS_SCRUB_OFLAG_CORRUPT,
			__return_address);
}

void
xchk_btree_xref_set_corrupt(
	struct xfs_scrub	*sc,
	struct xfs_btree_cur	*cur,
	int			level)
{
	__xchk_btree_set_corrupt(sc, cur, level, XFS_SCRUB_OFLAG_XCORRUPT,
			__return_address);
}

void
xchk_btree_set_preen(
	struct xfs_scrub	*sc,
	struct xfs_btree_cur	*cur,
	int			level)
{
	__xchk_btree_set_corrupt(sc, cur, level, XFS_SCRUB_OFLAG_PREEN,
			__return_address);
}

/*
 * Make sure this record is in order and doesn't stray outside of the parent
 * keys.
 */
STATIC void
xchk_btree_rec(
	struct xchk_btree	*bs)
{
	struct xfs_btree_cur	*cur = bs->cur;
	union xfs_btree_rec	*rec;
	union xfs_btree_key	key;
	union xfs_btree_key	hkey;
	union xfs_btree_key	*keyp;
	struct xfs_btree_block	*block;
	struct xfs_btree_block	*keyblock;
	struct xfs_buf		*bp;

	block = xfs_btree_get_block(cur, 0, &bp);
	rec = xfs_btree_rec_addr(cur, cur->bc_levels[0].ptr, block);

	trace_xchk_btree_rec(bs->sc, cur, 0);

	/* Are all records across all record blocks in order? */
	if (bs->lastrec_valid &&
	    !cur->bc_ops->recs_inorder(cur, &bs->lastrec, rec))
		xchk_btree_set_corrupt(bs->sc, cur, 0);
	memcpy(&bs->lastrec, rec, cur->bc_ops->rec_len);
	bs->lastrec_valid = true;

	if (cur->bc_nlevels == 1)
		return;

	/* Is low_key(rec) at least as large as the parent low key? */
	cur->bc_ops->init_key_from_rec(&key, rec);
	keyblock = xfs_btree_get_block(cur, 1, &bp);
	keyp = xfs_btree_key_addr(cur, cur->bc_levels[1].ptr, keyblock);
	if (xfs_btree_keycmp_lt(cur, &key, keyp))
		xchk_btree_set_corrupt(bs->sc, cur, 1);

	if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING))
		return;

	/* Is high_key(rec) no larger than the parent high key? */
	cur->bc_ops->init_high_key_from_rec(&hkey, rec);
	keyp = xfs_btree_high_key_addr(cur, cur->bc_levels[1].ptr, keyblock);
	if (xfs_btree_keycmp_lt(cur, keyp, &hkey))
		xchk_btree_set_corrupt(bs->sc, cur, 1);
}

/*
 * Make sure this key is in order and doesn't stray outside of the parent
 * keys.
 */
STATIC void
xchk_btree_key(
	struct xchk_btree	*bs,
	int			level)
{
	struct xfs_btree_cur	*cur = bs->cur;
	union xfs_btree_key	*key;
	union xfs_btree_key	*keyp;
	struct xfs_btree_block	*block;
	struct xfs_btree_block	*keyblock;
	struct xfs_buf		*bp;

	block = xfs_btree_get_block(cur, level, &bp);
	key = xfs_btree_key_addr(cur, cur->bc_levels[level].ptr, block);

	trace_xchk_btree_key(bs->sc, cur, level);

	/* Are all low keys across all node blocks in order? */
	if (bs->lastkey[level - 1].valid &&
	    !cur->bc_ops->keys_inorder(cur, &bs->lastkey[level - 1].key, key))
		xchk_btree_set_corrupt(bs->sc, cur, level);
	memcpy(&bs->lastkey[level - 1].key, key, cur->bc_ops->key_len);
	bs->lastkey[level - 1].valid = true;

	if (level + 1 >= cur->bc_nlevels)
		return;

	/* Is this block's low key at least as large as the parent low key? */
	keyblock = xfs_btree_get_block(cur, level + 1, &bp);
	keyp = xfs_btree_key_addr(cur, cur->bc_levels[level + 1].ptr, keyblock);
	if (xfs_btree_keycmp_lt(cur, key, keyp))
		xchk_btree_set_corrupt(bs->sc, cur, level);

	if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING))
		return;

	/* Is this block's high key no larger than the parent high key? */
	key = xfs_btree_high_key_addr(cur, cur->bc_levels[level].ptr, block);
	keyp = xfs_btree_high_key_addr(cur, cur->bc_levels[level + 1].ptr,
			keyblock);
	if (xfs_btree_keycmp_lt(cur, keyp, key))
		xchk_btree_set_corrupt(bs->sc, cur, level);
}

/*
 * Check a btree pointer.  Returns true if it's ok to use this pointer.
 * Callers do not need to set the corrupt flag.
 */
static bool
xchk_btree_ptr_ok(
	struct xchk_btree	*bs,
	int			level,
	union xfs_btree_ptr	*ptr)
{
	bool			res;

	/* A btree rooted in an inode has no block pointer to the root. */
	if ((bs->cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) &&
	    level == bs->cur->bc_nlevels)
		return true;

	/* Otherwise, check the pointers. */
	if (bs->cur->bc_flags & XFS_BTREE_LONG_PTRS)
		res = xfs_btree_check_lptr(bs->cur, be64_to_cpu(ptr->l), level);
	else
		res = xfs_btree_check_sptr(bs->cur, be32_to_cpu(ptr->s), level);
	if (!res)
		xchk_btree_set_corrupt(bs->sc, bs->cur, level);

	return res;
}

/* Check that a btree block's sibling matches what we expect it. */
STATIC int
xchk_btree_block_check_sibling(
	struct xchk_btree	*bs,
	int			level,
	int			direction,
	union xfs_btree_ptr	*sibling)
{
	struct xfs_btree_cur	*cur = bs->cur;
	struct xfs_btree_block	*pblock;
	struct xfs_buf		*pbp;
	struct xfs_btree_cur	*ncur = NULL;
	union xfs_btree_ptr	*pp;
	int			success;
	int			error;

	error = xfs_btree_dup_cursor(cur, &ncur);
	if (!xchk_btree_process_error(bs->sc, cur, level + 1, &error) ||
	    !ncur)
		return error;

	/*
	 * If the pointer is null, we shouldn't be able to move the upper
	 * level pointer anywhere.
	 */
	if (xfs_btree_ptr_is_null(cur, sibling)) {
		if (direction > 0)
			error = xfs_btree_increment(ncur, level + 1, &success);
		else
			error = xfs_btree_decrement(ncur, level + 1, &success);
		if (error == 0 && success)
			xchk_btree_set_corrupt(bs->sc, cur, level);
		error = 0;
		goto out;
	}

	/* Increment upper level pointer. */
	if (direction > 0)
		error = xfs_btree_increment(ncur, level + 1, &success);
	else
		error = xfs_btree_decrement(ncur, level + 1, &success);
	if (!xchk_btree_process_error(bs->sc, cur, level + 1, &error))
		goto out;
	if (!success) {
		xchk_btree_set_corrupt(bs->sc, cur, level + 1);
		goto out;
	}

	/* Compare upper level pointer to sibling pointer. */
	pblock = xfs_btree_get_block(ncur, level + 1, &pbp);
	pp = xfs_btree_ptr_addr(ncur, ncur->bc_levels[level + 1].ptr, pblock);
	if (!xchk_btree_ptr_ok(bs, level + 1, pp))
		goto out;
	if (pbp)
		xchk_buffer_recheck(bs->sc, pbp);

	if (xfs_btree_diff_two_ptrs(cur, pp, sibling))
		xchk_btree_set_corrupt(bs->sc, cur, level);
out:
	xfs_btree_del_cursor(ncur, XFS_BTREE_ERROR);
	return error;
}

/* Check the siblings of a btree block. */
STATIC int
xchk_btree_block_check_siblings(
	struct xchk_btree	*bs,
	struct xfs_btree_block	*block)
{
	struct xfs_btree_cur	*cur = bs->cur;
	union xfs_btree_ptr	leftsib;
	union xfs_btree_ptr	rightsib;
	int			level;
	int			error = 0;

	xfs_btree_get_sibling(cur, block, &leftsib, XFS_BB_LEFTSIB);
	xfs_btree_get_sibling(cur, block, &rightsib, XFS_BB_RIGHTSIB);
	level = xfs_btree_get_level(block);

	/* Root block should never have siblings. */
	if (level == cur->bc_nlevels - 1) {
		if (!xfs_btree_ptr_is_null(cur, &leftsib) ||
		    !xfs_btree_ptr_is_null(cur, &rightsib))
			xchk_btree_set_corrupt(bs->sc, cur, level);
		goto out;
	}

	/*
	 * Does the left & right sibling pointers match the adjacent
	 * parent level pointers?
	 * (These function absorbs error codes for us.)
	 */
	error = xchk_btree_block_check_sibling(bs, level, -1, &leftsib);
	if (error)
		return error;
	error = xchk_btree_block_check_sibling(bs, level, 1, &rightsib);
	if (error)
		return error;
out:
	return error;
}

struct check_owner {
	struct list_head	list;
	xfs_daddr_t		daddr;
	int			level;
};

/*
 * Make sure this btree block isn't in the free list and that there's
 * an rmap record for it.
 */
STATIC int
xchk_btree_check_block_owner(
	struct xchk_btree	*bs,
	int			level,
	xfs_daddr_t		daddr)
{
	xfs_agnumber_t		agno;
	xfs_agblock_t		agbno;
	xfs_btnum_t		btnum;
	bool			init_sa;
	int			error = 0;

	if (!bs->cur)
		return 0;

	btnum = bs->cur->bc_btnum;
	agno = xfs_daddr_to_agno(bs->cur->bc_mp, daddr);
	agbno = xfs_daddr_to_agbno(bs->cur->bc_mp, daddr);

	init_sa = bs->cur->bc_flags & XFS_BTREE_LONG_PTRS;
	if (init_sa) {
		error = xchk_ag_init_existing(bs->sc, agno, &bs->sc->sa);
		if (!xchk_btree_xref_process_error(bs->sc, bs->cur,
				level, &error))
			goto out_free;
	}

	xchk_xref_is_used_space(bs->sc, agbno, 1);
	/*
	 * The bnobt scrubber aliases bs->cur to bs->sc->sa.bno_cur, so we
	 * have to nullify it (to shut down further block owner checks) if
	 * self-xref encounters problems.
	 */
	if (!bs->sc->sa.bno_cur && btnum == XFS_BTNUM_BNO)
		bs->cur = NULL;

	xchk_xref_is_only_owned_by(bs->sc, agbno, 1, bs->oinfo);
	if (!bs->sc->sa.rmap_cur && btnum == XFS_BTNUM_RMAP)
		bs->cur = NULL;

out_free:
	if (init_sa)
		xchk_ag_free(bs->sc, &bs->sc->sa);

	return error;
}

/* Check the owner of a btree block. */
STATIC int
xchk_btree_check_owner(
	struct xchk_btree	*bs,
	int			level,
	struct xfs_buf		*bp)
{
	struct xfs_btree_cur	*cur = bs->cur;

	/*
	 * In theory, xfs_btree_get_block should only give us a null buffer
	 * pointer for the root of a root-in-inode btree type, but we need
	 * to check defensively here in case the cursor state is also screwed
	 * up.
	 */
	if (bp == NULL) {
		if (!(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE))
			xchk_btree_set_corrupt(bs->sc, bs->cur, level);
		return 0;
	}

	/*
	 * We want to cross-reference each btree block with the bnobt
	 * and the rmapbt.  We cannot cross-reference the bnobt or
	 * rmapbt while scanning the bnobt or rmapbt, respectively,
	 * because we cannot alter the cursor and we'd prefer not to
	 * duplicate cursors.  Therefore, save the buffer daddr for
	 * later scanning.
	 */
	if (cur->bc_btnum == XFS_BTNUM_BNO || cur->bc_btnum == XFS_BTNUM_RMAP) {
		struct check_owner	*co;

		co = kmalloc(sizeof(struct check_owner), XCHK_GFP_FLAGS);
		if (!co)
			return -ENOMEM;

		INIT_LIST_HEAD(&co->list);
		co->level = level;
		co->daddr = xfs_buf_daddr(bp);
		list_add_tail(&co->list, &bs->to_check);
		return 0;
	}

	return xchk_btree_check_block_owner(bs, level, xfs_buf_daddr(bp));
}

/* Decide if we want to check minrecs of a btree block in the inode root. */
static inline bool
xchk_btree_check_iroot_minrecs(
	struct xchk_btree	*bs)
{
	/*
	 * xfs_bmap_add_attrfork_btree had an implementation bug wherein it
	 * would miscalculate the space required for the data fork bmbt root
	 * when adding an attr fork, and promote the iroot contents to an
	 * external block unnecessarily.  This went unnoticed for many years
	 * until scrub found filesystems in this state.  Inode rooted btrees are
	 * not supposed to have immediate child blocks that are small enough
	 * that the contents could fit in the inode root, but we can't fail
	 * existing filesystems, so instead we disable the check for data fork
	 * bmap btrees when there's an attr fork.
	 */
	if (bs->cur->bc_btnum == XFS_BTNUM_BMAP &&
	    bs->cur->bc_ino.whichfork == XFS_DATA_FORK &&
	    xfs_inode_has_attr_fork(bs->sc->ip))
		return false;

	return true;
}

/*
 * Check that this btree block has at least minrecs records or is one of the
 * special blocks that don't require that.
 */
STATIC void
xchk_btree_check_minrecs(
	struct xchk_btree	*bs,
	int			level,
	struct xfs_btree_block	*block)
{
	struct xfs_btree_cur	*cur = bs->cur;
	unsigned int		root_level = cur->bc_nlevels - 1;
	unsigned int		numrecs = be16_to_cpu(block->bb_numrecs);

	/* More records than minrecs means the block is ok. */
	if (numrecs >= cur->bc_ops->get_minrecs(cur, level))
		return;

	/*
	 * For btrees rooted in the inode, it's possible that the root block
	 * contents spilled into a regular ondisk block because there wasn't
	 * enough space in the inode root.  The number of records in that
	 * child block might be less than the standard minrecs, but that's ok
	 * provided that there's only one direct child of the root.
	 */
	if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) &&
	    level == cur->bc_nlevels - 2) {
		struct xfs_btree_block	*root_block;
		struct xfs_buf		*root_bp;
		int			root_maxrecs;

		root_block = xfs_btree_get_block(cur, root_level, &root_bp);
		root_maxrecs = cur->bc_ops->get_dmaxrecs(cur, root_level);
		if (xchk_btree_check_iroot_minrecs(bs) &&
		    (be16_to_cpu(root_block->bb_numrecs) != 1 ||
		     numrecs <= root_maxrecs))
			xchk_btree_set_corrupt(bs->sc, cur, level);
		return;
	}

	/*
	 * Otherwise, only the root level is allowed to have fewer than minrecs
	 * records or keyptrs.
	 */
	if (level < root_level)
		xchk_btree_set_corrupt(bs->sc, cur, level);
}

/*
 * If this btree block has a parent, make sure that the parent's keys capture
 * the keyspace contained in this block.
 */
STATIC void
xchk_btree_block_check_keys(
	struct xchk_btree	*bs,
	int			level,
	struct xfs_btree_block	*block)
{
	union xfs_btree_key	block_key;
	union xfs_btree_key	*block_high_key;
	union xfs_btree_key	*parent_low_key, *parent_high_key;
	struct xfs_btree_cur	*cur = bs->cur;
	struct xfs_btree_block	*parent_block;
	struct xfs_buf		*bp;

	if (level == cur->bc_nlevels - 1)
		return;

	xfs_btree_get_keys(cur, block, &block_key);

	/* Make sure the low key of this block matches the parent. */
	parent_block = xfs_btree_get_block(cur, level + 1, &bp);
	parent_low_key = xfs_btree_key_addr(cur, cur->bc_levels[level + 1].ptr,
			parent_block);
	if (xfs_btree_keycmp_ne(cur, &block_key, parent_low_key)) {
		xchk_btree_set_corrupt(bs->sc, bs->cur, level);
		return;
	}

	if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING))
		return;

	/* Make sure the high key of this block matches the parent. */
	parent_high_key = xfs_btree_high_key_addr(cur,
			cur->bc_levels[level + 1].ptr, parent_block);
	block_high_key = xfs_btree_high_key_from_key(cur, &block_key);
	if (xfs_btree_keycmp_ne(cur, block_high_key, parent_high_key))
		xchk_btree_set_corrupt(bs->sc, bs->cur, level);
}

/*
 * Grab and scrub a btree block given a btree pointer.  Returns block
 * and buffer pointers (if applicable) if they're ok to use.
 */
STATIC int
xchk_btree_get_block(
	struct xchk_btree	*bs,
	int			level,
	union xfs_btree_ptr	*pp,
	struct xfs_btree_block	**pblock,
	struct xfs_buf		**pbp)
{
	xfs_failaddr_t		failed_at;
	int			error;

	*pblock = NULL;
	*pbp = NULL;

	error = xfs_btree_lookup_get_block(bs->cur, level, pp, pblock);
	if (!xchk_btree_process_error(bs->sc, bs->cur, level, &error) ||
	    !*pblock)
		return error;

	xfs_btree_get_block(bs->cur, level, pbp);
	if (bs->cur->bc_flags & XFS_BTREE_LONG_PTRS)
		failed_at = __xfs_btree_check_lblock(bs->cur, *pblock,
				level, *pbp);
	else
		failed_at = __xfs_btree_check_sblock(bs->cur, *pblock,
				 level, *pbp);
	if (failed_at) {
		xchk_btree_set_corrupt(bs->sc, bs->cur, level);
		return 0;
	}
	if (*pbp)
		xchk_buffer_recheck(bs->sc, *pbp);

	xchk_btree_check_minrecs(bs, level, *pblock);

	/*
	 * Check the block's owner; this function absorbs error codes
	 * for us.
	 */
	error = xchk_btree_check_owner(bs, level, *pbp);
	if (error)
		return error;

	/*
	 * Check the block's siblings; this function absorbs error codes
	 * for us.
	 */
	error = xchk_btree_block_check_siblings(bs, *pblock);
	if (error)
		return error;

	xchk_btree_block_check_keys(bs, level, *pblock);
	return 0;
}

/*
 * Check that the low and high keys of this block match the keys stored
 * in the parent block.
 */
STATIC void
xchk_btree_block_keys(
	struct xchk_btree	*bs,
	int			level,
	struct xfs_btree_block	*block)
{
	union xfs_btree_key	block_keys;
	struct xfs_btree_cur	*cur = bs->cur;
	union xfs_btree_key	*high_bk;
	union xfs_btree_key	*parent_keys;
	union xfs_btree_key	*high_pk;
	struct xfs_btree_block	*parent_block;
	struct xfs_buf		*bp;

	if (level >= cur->bc_nlevels - 1)
		return;

	/* Calculate the keys for this block. */
	xfs_btree_get_keys(cur, block, &block_keys);

	/* Obtain the parent's copy of the keys for this block. */
	parent_block = xfs_btree_get_block(cur, level + 1, &bp);
	parent_keys = xfs_btree_key_addr(cur, cur->bc_levels[level + 1].ptr,
			parent_block);

	if (xfs_btree_keycmp_ne(cur, &block_keys, parent_keys))
		xchk_btree_set_corrupt(bs->sc, cur, 1);

	if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING))
		return;

	/* Get high keys */
	high_bk = xfs_btree_high_key_from_key(cur, &block_keys);
	high_pk = xfs_btree_high_key_addr(cur, cur->bc_levels[level + 1].ptr,
			parent_block);

	if (xfs_btree_keycmp_ne(cur, high_bk, high_pk))
		xchk_btree_set_corrupt(bs->sc, cur, 1);
}

/*
 * Visit all nodes and leaves of a btree.  Check that all pointers and
 * records are in order, that the keys reflect the records, and use a callback
 * so that the caller can verify individual records.
 */
int
xchk_btree(
	struct xfs_scrub		*sc,
	struct xfs_btree_cur		*cur,
	xchk_btree_rec_fn		scrub_fn,
	const struct xfs_owner_info	*oinfo,
	void				*private)
{
	union xfs_btree_ptr		ptr;
	struct xchk_btree		*bs;
	union xfs_btree_ptr		*pp;
	union xfs_btree_rec		*recp;
	struct xfs_btree_block		*block;
	struct xfs_buf			*bp;
	struct check_owner		*co;
	struct check_owner		*n;
	size_t				cur_sz;
	int				level;
	int				error = 0;

	/*
	 * Allocate the btree scrub context from the heap, because this
	 * structure can get rather large.  Don't let a caller feed us a
	 * totally absurd size.
	 */
	cur_sz = xchk_btree_sizeof(cur->bc_nlevels);
	if (cur_sz > PAGE_SIZE) {
		xchk_btree_set_corrupt(sc, cur, 0);
		return 0;
	}
	bs = kzalloc(cur_sz, XCHK_GFP_FLAGS);
	if (!bs)
		return -ENOMEM;
	bs->cur = cur;
	bs->scrub_rec = scrub_fn;
	bs->oinfo = oinfo;
	bs->private = private;
	bs->sc = sc;

	/* Initialize scrub state */
	INIT_LIST_HEAD(&bs->to_check);

	/*
	 * Load the root of the btree.  The helper function absorbs
	 * error codes for us.
	 */
	level = cur->bc_nlevels - 1;
	cur->bc_ops->init_ptr_from_cur(cur, &ptr);
	if (!xchk_btree_ptr_ok(bs, cur->bc_nlevels, &ptr))
		goto out;
	error = xchk_btree_get_block(bs, level, &ptr, &block, &bp);
	if (error || !block)
		goto out;

	cur->bc_levels[level].ptr = 1;

	while (level < cur->bc_nlevels) {
		block = xfs_btree_get_block(cur, level, &bp);

		if (level == 0) {
			/* End of leaf, pop back towards the root. */
			if (cur->bc_levels[level].ptr >
			    be16_to_cpu(block->bb_numrecs)) {
				xchk_btree_block_keys(bs, level, block);
				if (level < cur->bc_nlevels - 1)
					cur->bc_levels[level + 1].ptr++;
				level++;
				continue;
			}

			/* Records in order for scrub? */
			xchk_btree_rec(bs);

			/* Call out to the record checker. */
			recp = xfs_btree_rec_addr(cur, cur->bc_levels[0].ptr,
					block);
			error = bs->scrub_rec(bs, recp);
			if (error)
				break;
			if (xchk_should_terminate(sc, &error) ||
			    (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
				break;

			cur->bc_levels[level].ptr++;
			continue;
		}

		/* End of node, pop back towards the root. */
		if (cur->bc_levels[level].ptr >
					be16_to_cpu(block->bb_numrecs)) {
			xchk_btree_block_keys(bs, level, block);
			if (level < cur->bc_nlevels - 1)
				cur->bc_levels[level + 1].ptr++;
			level++;
			continue;
		}

		/* Keys in order for scrub? */
		xchk_btree_key(bs, level);

		/* Drill another level deeper. */
		pp = xfs_btree_ptr_addr(cur, cur->bc_levels[level].ptr, block);
		if (!xchk_btree_ptr_ok(bs, level, pp)) {
			cur->bc_levels[level].ptr++;
			continue;
		}
		level--;
		error = xchk_btree_get_block(bs, level, pp, &block, &bp);
		if (error || !block)
			goto out;

		cur->bc_levels[level].ptr = 1;
	}

out:
	/* Process deferred owner checks on btree blocks. */
	list_for_each_entry_safe(co, n, &bs->to_check, list) {
		if (!error && bs->cur)
			error = xchk_btree_check_block_owner(bs, co->level,
					co->daddr);
		list_del(&co->list);
		kfree(co);
	}
	kfree(bs);

	return error;
}