summaryrefslogtreecommitdiff
path: root/fs/xfs/scrub/common.c
blob: 9aa79665c6080538c72a24ece5166cbff9d8086c (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
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
// 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_btree.h"
#include "xfs_log_format.h"
#include "xfs_trans.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_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_attr.h"
#include "xfs_reflink.h"
#include "xfs_ag.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:
	case -ECHRNG:
		/* Used to restart an op with deadlock avoidance. */
		trace_xchk_deadlock_retry(
				sc->ip ? sc->ip : XFS_I(file_inode(sc->file)),
				sc->sm, *error);
		break;
	case -EFSBADCRC:
	case -EFSCORRUPTED:
		/* Note the badness but don't abort. */
		sc->sm->sm_flags |= errflag;
		*error = 0;
		fallthrough;
	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:
	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:
		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, xfs_buf_daddr(bp), __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, xfs_buf_daddr(bp), __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, xfs_buf_daddr(bp), __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,
	const 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 the AG header buffers for the attached perag structure.
 *
 * 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.
 */
static inline int
xchk_perag_read_headers(
	struct xfs_scrub	*sc,
	struct xchk_ag		*sa)
{
	int			error;

	error = xfs_ialloc_read_agi(sa->pag, sc->tp, &sa->agi_bp);
	if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGI))
		return error;

	error = xfs_alloc_read_agf(sa->pag, sc->tp, 0, &sa->agf_bp);
	if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGF))
		return error;

	return 0;
}

/*
 * Grab the AG headers for the attached perag structure and wait for pending
 * intents to drain.
 */
static int
xchk_perag_drain_and_lock(
	struct xfs_scrub	*sc)
{
	struct xchk_ag		*sa = &sc->sa;
	int			error = 0;

	ASSERT(sa->pag != NULL);
	ASSERT(sa->agi_bp == NULL);
	ASSERT(sa->agf_bp == NULL);

	do {
		if (xchk_should_terminate(sc, &error))
			return error;

		error = xchk_perag_read_headers(sc, sa);
		if (error)
			return error;

		/*
		 * If we've grabbed an inode for scrubbing then we assume that
		 * holding its ILOCK will suffice to coordinate with any intent
		 * chains involving this inode.
		 */
		if (sc->ip)
			return 0;

		/*
		 * Decide if this AG is quiet enough for all metadata to be
		 * consistent with each other.  XFS allows the AG header buffer
		 * locks to cycle across transaction rolls while processing
		 * chains of deferred ops, which means that there could be
		 * other threads in the middle of processing a chain of
		 * deferred ops.  For regular operations we are careful about
		 * ordering operations to prevent collisions between threads
		 * (which is why we don't need a per-AG lock), but scrub and
		 * repair have to serialize against chained operations.
		 *
		 * We just locked all the AG headers buffers; now take a look
		 * to see if there are any intents in progress.  If there are,
		 * drop the AG headers and wait for the intents to drain.
		 * Since we hold all the AG header locks for the duration of
		 * the scrub, this is the only time we have to sample the
		 * intents counter; any threads increasing it after this point
		 * can't possibly be in the middle of a chain of AG metadata
		 * updates.
		 *
		 * Obviously, this should be slanted against scrub and in favor
		 * of runtime threads.
		 */
		if (!xfs_perag_intent_busy(sa->pag))
			return 0;

		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 (!(sc->flags & XCHK_FSGATES_DRAIN))
			return -ECHRNG;
		error = xfs_perag_intent_drain(sa->pag);
		if (error == -ERESTARTSYS)
			error = -EINTR;
	} while (!error);

	return error;
}

/*
 * Grab the per-AG structure, grab all AG header buffers, and wait until there
 * aren't any pending intents.  Returns -ENOENT if we can't grab the perag
 * structure.
 */
int
xchk_ag_read_headers(
	struct xfs_scrub	*sc,
	xfs_agnumber_t		agno,
	struct xchk_ag		*sa)
{
	struct xfs_mount	*mp = sc->mp;

	ASSERT(!sa->pag);
	sa->pag = xfs_perag_get(mp, agno);
	if (!sa->pag)
		return -ENOENT;

	return xchk_perag_drain_and_lock(sc);
}

/* 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;

	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,
				sa->pag, 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,
				sa->pag, 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(sa->pag, sc->tp, sa->agi_bp,
				XFS_BTNUM_INO);
	}

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

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

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

/* 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->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;
	}
}

/*
 * For scrub, grab the perag structure, 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.  Returns ENOENT if the perag struct cannot be grabbed.
 */
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;
}

/* Per-scrubber setup functions */

void
xchk_trans_cancel(
	struct xfs_scrub	*sc)
{
	xfs_trans_cancel(sc->tp);
	sc->tp = NULL;
}

/*
 * 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;
}

/* Verify that an inode is allocated ondisk, then return its cached inode. */
int
xchk_iget(
	struct xfs_scrub	*sc,
	xfs_ino_t		inum,
	struct xfs_inode	**ipp)
{
	return xfs_iget(sc->mp, sc->tp, inum, XFS_IGET_UNTRUSTED, 0, ipp);
}

/*
 * Try to grab an inode in a manner that avoids races with physical inode
 * allocation.  If we can't, return the locked AGI buffer so that the caller
 * can single-step the loading process to see where things went wrong.
 * Callers must have a valid scrub transaction.
 *
 * If the iget succeeds, return 0, a NULL AGI, and the inode.
 *
 * If the iget fails, return the error, the locked AGI, and a NULL inode.  This
 * can include -EINVAL and -ENOENT for invalid inode numbers or inodes that are
 * no longer allocated; or any other corruption or runtime error.
 *
 * If the AGI read fails, return the error, a NULL AGI, and NULL inode.
 *
 * If a fatal signal is pending, return -EINTR, a NULL AGI, and a NULL inode.
 */
int
xchk_iget_agi(
	struct xfs_scrub	*sc,
	xfs_ino_t		inum,
	struct xfs_buf		**agi_bpp,
	struct xfs_inode	**ipp)
{
	struct xfs_mount	*mp = sc->mp;
	struct xfs_trans	*tp = sc->tp;
	struct xfs_perag	*pag;
	int			error;

	ASSERT(sc->tp != NULL);

again:
	*agi_bpp = NULL;
	*ipp = NULL;
	error = 0;

	if (xchk_should_terminate(sc, &error))
		return error;

	/*
	 * Attach the AGI buffer to the scrub transaction to avoid deadlocks
	 * in the iget cache miss path.
	 */
	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, inum));
	error = xfs_ialloc_read_agi(pag, tp, agi_bpp);
	xfs_perag_put(pag);
	if (error)
		return error;

	error = xfs_iget(mp, tp, inum,
			XFS_IGET_NORETRY | XFS_IGET_UNTRUSTED, 0, ipp);
	if (error == -EAGAIN) {
		/*
		 * The inode may be in core but temporarily unavailable and may
		 * require the AGI buffer before it can be returned.  Drop the
		 * AGI buffer and retry the lookup.
		 *
		 * Incore lookup will fail with EAGAIN on a cache hit if the
		 * inode is queued to the inactivation list.  The inactivation
		 * worker may remove the inode from the unlinked list and hence
		 * needs the AGI.
		 *
		 * Hence xchk_iget_agi() needs to drop the AGI lock on EAGAIN
		 * to allow inodegc to make progress and move the inode to
		 * IRECLAIMABLE state where xfs_iget will be able to return it
		 * again if it can lock the inode.
		 */
		xfs_trans_brelse(tp, *agi_bpp);
		delay(1);
		goto again;
	}
	if (error)
		return error;

	/* We got the inode, so we can release the AGI. */
	ASSERT(*ipp != NULL);
	xfs_trans_brelse(tp, *agi_bpp);
	*agi_bpp = NULL;
	return 0;
}

/* Install an inode that we opened by handle for scrubbing. */
int
xchk_install_handle_inode(
	struct xfs_scrub	*sc,
	struct xfs_inode	*ip)
{
	if (VFS_I(ip)->i_generation != sc->sm->sm_gen) {
		xchk_irele(sc, ip);
		return -ENOENT;
	}

	sc->ip = ip;
	return 0;
}

/*
 * In preparation to scrub metadata structures that hang off of an inode,
 * grab either the inode referenced in the scrub control structure or the
 * inode passed in.  If the inumber does not reference an allocated inode
 * record, the function returns ENOENT to end the scrub early.  The inode
 * is not locked.
 */
int
xchk_iget_for_scrubbing(
	struct xfs_scrub	*sc)
{
	struct xfs_imap		imap;
	struct xfs_mount	*mp = sc->mp;
	struct xfs_perag	*pag;
	struct xfs_buf		*agi_bp;
	struct xfs_inode	*ip_in = XFS_I(file_inode(sc->file));
	struct xfs_inode	*ip = NULL;
	xfs_agnumber_t		agno = XFS_INO_TO_AGNO(mp, sc->sm->sm_ino);
	int			error;

	ASSERT(sc->tp == NULL);

	/* 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;
	}

	/* Reject internal metadata files and obviously bad inode numbers. */
	if (xfs_internal_inum(mp, sc->sm->sm_ino))
		return -ENOENT;
	if (!xfs_verify_ino(sc->mp, sc->sm->sm_ino))
		return -ENOENT;

	/* Try a regular untrusted iget. */
	error = xchk_iget(sc, sc->sm->sm_ino, &ip);
	if (!error)
		return xchk_install_handle_inode(sc, ip);
	if (error == -ENOENT)
		return error;
	if (error != -EINVAL)
		goto out_error;

	/*
	 * EINVAL with IGET_UNTRUSTED probably means one of several things:
	 * userspace gave us an inode number that doesn't correspond to fs
	 * space; the inode btree lacks a record for this inode; or there is a
	 * record, and it says this inode is free.
	 *
	 * We want to look up this inode in the inobt to distinguish two
	 * scenarios: (1) the inobt says the inode is free, in which case
	 * there's nothing to do; and (2) the inobt says the inode is
	 * allocated, but loading it failed due to corruption.
	 *
	 * Allocate a transaction and grab the AGI to prevent inobt activity
	 * in this AG.  Retry the iget in case someone allocated a new inode
	 * after the first iget failed.
	 */
	error = xchk_trans_alloc(sc, 0);
	if (error)
		goto out_error;

	error = xchk_iget_agi(sc, sc->sm->sm_ino, &agi_bp, &ip);
	if (error == 0) {
		/* Actually got the inode, so install it. */
		xchk_trans_cancel(sc);
		return xchk_install_handle_inode(sc, ip);
	}
	if (error == -ENOENT)
		goto out_gone;
	if (error != -EINVAL)
		goto out_cancel;

	/* Ensure that we have protected against inode allocation/freeing. */
	if (agi_bp == NULL) {
		ASSERT(agi_bp != NULL);
		error = -ECANCELED;
		goto out_cancel;
	}

	/*
	 * Untrusted iget failed a second time.  Let's try an inobt lookup.
	 * If the inobt thinks this the inode neither can exist inside the
	 * filesystem nor is allocated, return ENOENT to signal that the check
	 * can be skipped.
	 *
	 * If the lookup returns corruption, we'll mark this inode corrupt and
	 * exit to userspace.  There's little chance of fixing anything until
	 * the inobt is straightened out, but there's nothing we can do here.
	 *
	 * If the lookup encounters any other error, exit to userspace.
	 *
	 * If the lookup succeeds, something else must be very wrong in the fs
	 * such that setting up the incore inode failed in some strange way.
	 * Treat those as corruptions.
	 */
	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, sc->sm->sm_ino));
	if (!pag) {
		error = -EFSCORRUPTED;
		goto out_cancel;
	}

	error = xfs_imap(pag, sc->tp, sc->sm->sm_ino, &imap,
			XFS_IGET_UNTRUSTED);
	xfs_perag_put(pag);
	if (error == -EINVAL || error == -ENOENT)
		goto out_gone;
	if (!error)
		error = -EFSCORRUPTED;

out_cancel:
	xchk_trans_cancel(sc);
out_error:
	trace_xchk_op_error(sc, agno, XFS_INO_TO_AGBNO(mp, sc->sm->sm_ino),
			error, __return_address);
	return error;
out_gone:
	/* The file is gone, so there's nothing to check. */
	xchk_trans_cancel(sc);
	return -ENOENT;
}

/* Release an inode, possibly dropping it in the process. */
void
xchk_irele(
	struct xfs_scrub	*sc,
	struct xfs_inode	*ip)
{
	if (current->journal_info != NULL) {
		ASSERT(current->journal_info == sc->tp);

		/*
		 * If we are in a transaction, we /cannot/ drop the inode
		 * ourselves, because the VFS will trigger writeback, which
		 * can require a transaction.  Clear DONTCACHE to force the
		 * inode to the LRU, where someone else can take care of
		 * dropping it.
		 *
		 * Note that when we grabbed our reference to the inode, it
		 * could have had an active ref and DONTCACHE set if a sysadmin
		 * is trying to coerce a change in file access mode.  icache
		 * hits do not clear DONTCACHE, so we must do it here.
		 */
		spin_lock(&VFS_I(ip)->i_lock);
		VFS_I(ip)->i_state &= ~I_DONTCACHE;
		spin_unlock(&VFS_I(ip)->i_lock);
	} else if (atomic_read(&VFS_I(ip)->i_count) == 1) {
		/*
		 * If this is the last reference to the inode and the caller
		 * permits it, set DONTCACHE to avoid thrashing.
		 */
		d_mark_dontcache(VFS_I(ip));
	}

	xfs_irele(ip);
}

/*
 * Set us up to scrub metadata mapped by a file's fork.  Callers must not use
 * this to operate on user-accessible regular file data because the MMAPLOCK is
 * not taken.
 */
int
xchk_setup_inode_contents(
	struct xfs_scrub	*sc,
	unsigned int		resblks)
{
	int			error;

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

	/* Lock the inode so the VFS cannot touch this file. */
	sc->ilock_flags = XFS_IOLOCK_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, xfs_buf_daddr(bp), fa);
}

static inline int
xchk_metadata_inode_subtype(
	struct xfs_scrub	*sc,
	unsigned int		scrub_type)
{
	__u32			smtype = sc->sm->sm_type;
	int			error;

	sc->sm->sm_type = scrub_type;

	switch (scrub_type) {
	case XFS_SCRUB_TYPE_INODE:
		error = xchk_inode(sc);
		break;
	case XFS_SCRUB_TYPE_BMBTD:
		error = xchk_bmap_data(sc);
		break;
	default:
		ASSERT(0);
		error = -EFSCORRUPTED;
		break;
	}

	sc->sm->sm_type = smtype;
	return error;
}

/*
 * 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)
{
	bool			shared;
	int			error;

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

	/* Check the inode record. */
	error = xchk_metadata_inode_subtype(sc, XFS_SCRUB_TYPE_INODE);
	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
		return error;

	/* 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. */
	error = xchk_metadata_inode_subtype(sc, XFS_SCRUB_TYPE_BMBTD);
	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
		return error;

	/* Look for incorrect shared blocks. */
	if (xfs_has_reflink(sc->mp)) {
		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 0;
}

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

/* Restart background reaping of resources. */
void
xchk_start_reaping(
	struct xfs_scrub	*sc)
{
	/*
	 * Readonly filesystems do not perform inactivation or speculative
	 * preallocation, so there's no need to restart the workers.
	 */
	if (!xfs_is_readonly(sc->mp)) {
		xfs_inodegc_start(sc->mp);
		xfs_blockgc_start(sc->mp);
	}
	sc->flags &= ~XCHK_REAPING_DISABLED;
}

/*
 * Enable filesystem hooks (i.e. runtime code patching) before starting a scrub
 * operation.  Callers must not hold any locks that intersect with the CPU
 * hotplug lock (e.g. writeback locks) because code patching must halt the CPUs
 * to change kernel code.
 */
void
xchk_fsgates_enable(
	struct xfs_scrub	*sc,
	unsigned int		scrub_fsgates)
{
	ASSERT(!(scrub_fsgates & ~XCHK_FSGATES_ALL));
	ASSERT(!(sc->flags & scrub_fsgates));

	trace_xchk_fsgates_enable(sc, scrub_fsgates);

	if (scrub_fsgates & XCHK_FSGATES_DRAIN)
		xfs_drain_wait_enable();

	sc->flags |= scrub_fsgates;
}