summaryrefslogtreecommitdiffstats
path: root/fs/xfs/scrub/inode_repair.c
blob: 0ca62d59f84ad1089146ffc67581a1225de7e5ae (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
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright (C) 2018-2023 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_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_icache.h"
#include "xfs_inode_buf.h"
#include "xfs_inode_fork.h"
#include "xfs_ialloc.h"
#include "xfs_da_format.h"
#include "xfs_reflink.h"
#include "xfs_alloc.h"
#include "xfs_rmap.h"
#include "xfs_rmap_btree.h"
#include "xfs_bmap.h"
#include "xfs_bmap_btree.h"
#include "xfs_bmap_util.h"
#include "xfs_dir2.h"
#include "xfs_dir2_priv.h"
#include "xfs_quota_defs.h"
#include "xfs_quota.h"
#include "xfs_ag.h"
#include "xfs_rtbitmap.h"
#include "xfs_attr_leaf.h"
#include "xfs_log_priv.h"
#include "xfs_health.h"
#include "scrub/xfs_scrub.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/btree.h"
#include "scrub/trace.h"
#include "scrub/repair.h"

/*
 * Inode Record Repair
 * ===================
 *
 * Roughly speaking, inode problems can be classified based on whether or not
 * they trip the dinode verifiers.  If those trip, then we won't be able to
 * xfs_iget ourselves the inode.
 *
 * Therefore, the xrep_dinode_* functions fix anything that will cause the
 * inode buffer verifier or the dinode verifier.  The xrep_inode_* functions
 * fix things on live incore inodes.  The inode repair functions make decisions
 * with security and usability implications when reviving a file:
 *
 * - Files with zero di_mode or a garbage di_mode are converted to regular file
 *   that only root can read.  This file may not actually contain user data,
 *   if the file was not previously a regular file.  Setuid and setgid bits
 *   are cleared.
 *
 * - Zero-size directories can be truncated to look empty.  It is necessary to
 *   run the bmapbtd and directory repair functions to fully rebuild the
 *   directory.
 *
 * - Zero-size symbolic link targets can be truncated to '?'.  It is necessary
 *   to run the bmapbtd and symlink repair functions to salvage the symlink.
 *
 * - Invalid extent size hints will be removed.
 *
 * - Quotacheck will be scheduled if we repaired an inode that was so badly
 *   damaged that the ondisk inode had to be rebuilt.
 *
 * - Invalid user, group, or project IDs (aka -1U) will be reset to zero.
 *   Setuid and setgid bits are cleared.
 *
 * - Data and attr forks are reset to extents format with zero extents if the
 *   fork data is inconsistent.  It is necessary to run the bmapbtd or bmapbta
 *   repair functions to recover the space mapping.
 *
 * - ACLs will not be recovered if the attr fork is zapped or the extended
 *   attribute structure itself requires salvaging.
 *
 * - If the attr fork is zapped, the user and group ids are reset to root and
 *   the setuid and setgid bits are removed.
 */

/*
 * All the information we need to repair the ondisk inode if we can't iget the
 * incore inode.  We don't allocate this buffer unless we're going to perform
 * a repair to the ondisk inode cluster buffer.
 */
struct xrep_inode {
	/* Inode mapping that we saved from the initial lookup attempt. */
	struct xfs_imap		imap;

	struct xfs_scrub	*sc;

	/* Blocks in use on the data device by data extents or bmbt blocks. */
	xfs_rfsblock_t		data_blocks;

	/* Blocks in use on the rt device. */
	xfs_rfsblock_t		rt_blocks;

	/* Blocks in use by the attr fork. */
	xfs_rfsblock_t		attr_blocks;

	/* Number of data device extents for the data fork. */
	xfs_extnum_t		data_extents;

	/*
	 * Number of realtime device extents for the data fork.  If
	 * data_extents and rt_extents indicate that the data fork has extents
	 * on both devices, we'll just back away slowly.
	 */
	xfs_extnum_t		rt_extents;

	/* Number of (data device) extents for the attr fork. */
	xfs_aextnum_t		attr_extents;

	/* Sick state to set after zapping parts of the inode. */
	unsigned int		ino_sick_mask;

	/* Must we remove all access from this file? */
	bool			zap_acls;
};

/*
 * Setup function for inode repair.  @imap contains the ondisk inode mapping
 * information so that we can correct the ondisk inode cluster buffer if
 * necessary to make iget work.
 */
int
xrep_setup_inode(
	struct xfs_scrub	*sc,
	const struct xfs_imap	*imap)
{
	struct xrep_inode	*ri;

	sc->buf = kzalloc(sizeof(struct xrep_inode), XCHK_GFP_FLAGS);
	if (!sc->buf)
		return -ENOMEM;

	ri = sc->buf;
	memcpy(&ri->imap, imap, sizeof(struct xfs_imap));
	ri->sc = sc;
	return 0;
}

/*
 * Make sure this ondisk inode can pass the inode buffer verifier.  This is
 * not the same as the dinode verifier.
 */
STATIC void
xrep_dinode_buf_core(
	struct xfs_scrub	*sc,
	struct xfs_buf		*bp,
	unsigned int		ioffset)
{
	struct xfs_dinode	*dip = xfs_buf_offset(bp, ioffset);
	struct xfs_trans	*tp = sc->tp;
	struct xfs_mount	*mp = sc->mp;
	xfs_agino_t		agino;
	bool			crc_ok = false;
	bool			magic_ok = false;
	bool			unlinked_ok = false;

	agino = be32_to_cpu(dip->di_next_unlinked);

	if (xfs_verify_agino_or_null(bp->b_pag, agino))
		unlinked_ok = true;

	if (dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
	    xfs_dinode_good_version(mp, dip->di_version))
		magic_ok = true;

	if (xfs_verify_cksum((char *)dip, mp->m_sb.sb_inodesize,
			XFS_DINODE_CRC_OFF))
		crc_ok = true;

	if (magic_ok && unlinked_ok && crc_ok)
		return;

	if (!magic_ok) {
		dip->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
		dip->di_version = 3;
	}
	if (!unlinked_ok)
		dip->di_next_unlinked = cpu_to_be32(NULLAGINO);
	xfs_dinode_calc_crc(mp, dip);
	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DINO_BUF);
	xfs_trans_log_buf(tp, bp, ioffset,
				  ioffset + sizeof(struct xfs_dinode) - 1);
}

/* Make sure this inode cluster buffer can pass the inode buffer verifier. */
STATIC void
xrep_dinode_buf(
	struct xfs_scrub	*sc,
	struct xfs_buf		*bp)
{
	struct xfs_mount	*mp = sc->mp;
	int			i;
	int			ni;

	ni = XFS_BB_TO_FSB(mp, bp->b_length) * mp->m_sb.sb_inopblock;
	for (i = 0; i < ni; i++)
		xrep_dinode_buf_core(sc, bp, i << mp->m_sb.sb_inodelog);
}

/* Reinitialize things that never change in an inode. */
STATIC void
xrep_dinode_header(
	struct xfs_scrub	*sc,
	struct xfs_dinode	*dip)
{
	trace_xrep_dinode_header(sc, dip);

	dip->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
	if (!xfs_dinode_good_version(sc->mp, dip->di_version))
		dip->di_version = 3;
	dip->di_ino = cpu_to_be64(sc->sm->sm_ino);
	uuid_copy(&dip->di_uuid, &sc->mp->m_sb.sb_meta_uuid);
	dip->di_gen = cpu_to_be32(sc->sm->sm_gen);
}

/* Turn di_mode into /something/ recognizable. */
STATIC void
xrep_dinode_mode(
	struct xrep_inode	*ri,
	struct xfs_dinode	*dip)
{
	struct xfs_scrub	*sc = ri->sc;
	uint16_t		mode = be16_to_cpu(dip->di_mode);

	trace_xrep_dinode_mode(sc, dip);

	if (mode == 0 || xfs_mode_to_ftype(mode) != XFS_DIR3_FT_UNKNOWN)
		return;

	/* bad mode, so we set it to a file that only root can read */
	mode = S_IFREG;
	dip->di_mode = cpu_to_be16(mode);
	dip->di_uid = 0;
	dip->di_gid = 0;
	ri->zap_acls = true;
}

/* Fix any conflicting flags that the verifiers complain about. */
STATIC void
xrep_dinode_flags(
	struct xfs_scrub	*sc,
	struct xfs_dinode	*dip,
	bool			isrt)
{
	struct xfs_mount	*mp = sc->mp;
	uint64_t		flags2 = be64_to_cpu(dip->di_flags2);
	uint16_t		flags = be16_to_cpu(dip->di_flags);
	uint16_t		mode = be16_to_cpu(dip->di_mode);

	trace_xrep_dinode_flags(sc, dip);

	if (isrt)
		flags |= XFS_DIFLAG_REALTIME;
	else
		flags &= ~XFS_DIFLAG_REALTIME;

	/*
	 * For regular files on a reflink filesystem, set the REFLINK flag to
	 * protect shared extents.  A later stage will actually check those
	 * extents and clear the flag if possible.
	 */
	if (xfs_has_reflink(mp) && S_ISREG(mode))
		flags2 |= XFS_DIFLAG2_REFLINK;
	else
		flags2 &= ~(XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE);
	if (flags & XFS_DIFLAG_REALTIME)
		flags2 &= ~XFS_DIFLAG2_REFLINK;
	if (!xfs_has_bigtime(mp))
		flags2 &= ~XFS_DIFLAG2_BIGTIME;
	if (!xfs_has_large_extent_counts(mp))
		flags2 &= ~XFS_DIFLAG2_NREXT64;
	if (flags2 & XFS_DIFLAG2_NREXT64)
		dip->di_nrext64_pad = 0;
	else if (dip->di_version >= 3)
		dip->di_v3_pad = 0;
	dip->di_flags = cpu_to_be16(flags);
	dip->di_flags2 = cpu_to_be64(flags2);
}

/*
 * Blow out symlink; now it points nowhere.  We don't have to worry about
 * incore state because this inode is failing the verifiers.
 */
STATIC void
xrep_dinode_zap_symlink(
	struct xrep_inode	*ri,
	struct xfs_dinode	*dip)
{
	struct xfs_scrub	*sc = ri->sc;
	char			*p;

	trace_xrep_dinode_zap_symlink(sc, dip);

	dip->di_format = XFS_DINODE_FMT_LOCAL;
	dip->di_size = cpu_to_be64(1);
	p = XFS_DFORK_PTR(dip, XFS_DATA_FORK);
	*p = '?';
	ri->ino_sick_mask |= XFS_SICK_INO_SYMLINK_ZAPPED;
}

/*
 * Blow out dir, make the parent point to the root.  In the future repair will
 * reconstruct this directory for us.  Note that there's no in-core directory
 * inode because the sf verifier tripped, so we don't have to worry about the
 * dentry cache.
 */
STATIC void
xrep_dinode_zap_dir(
	struct xrep_inode	*ri,
	struct xfs_dinode	*dip)
{
	struct xfs_scrub	*sc = ri->sc;
	struct xfs_mount	*mp = sc->mp;
	struct xfs_dir2_sf_hdr	*sfp;
	int			i8count;

	trace_xrep_dinode_zap_dir(sc, dip);

	dip->di_format = XFS_DINODE_FMT_LOCAL;
	i8count = mp->m_sb.sb_rootino > XFS_DIR2_MAX_SHORT_INUM;
	sfp = XFS_DFORK_PTR(dip, XFS_DATA_FORK);
	sfp->count = 0;
	sfp->i8count = i8count;
	xfs_dir2_sf_put_parent_ino(sfp, mp->m_sb.sb_rootino);
	dip->di_size = cpu_to_be64(xfs_dir2_sf_hdr_size(i8count));
	ri->ino_sick_mask |= XFS_SICK_INO_DIR_ZAPPED;
}

/* Make sure we don't have a garbage file size. */
STATIC void
xrep_dinode_size(
	struct xrep_inode	*ri,
	struct xfs_dinode	*dip)
{
	struct xfs_scrub	*sc = ri->sc;
	uint64_t		size = be64_to_cpu(dip->di_size);
	uint16_t		mode = be16_to_cpu(dip->di_mode);

	trace_xrep_dinode_size(sc, dip);

	switch (mode & S_IFMT) {
	case S_IFIFO:
	case S_IFCHR:
	case S_IFBLK:
	case S_IFSOCK:
		/* di_size can't be nonzero for special files */
		dip->di_size = 0;
		break;
	case S_IFREG:
		/* Regular files can't be larger than 2^63-1 bytes. */
		dip->di_size = cpu_to_be64(size & ~(1ULL << 63));
		break;
	case S_IFLNK:
		/*
		 * Truncate ridiculously oversized symlinks.  If the size is
		 * zero, reset it to point to the current directory.  Both of
		 * these conditions trigger dinode verifier errors, so there
		 * is no in-core state to reset.
		 */
		if (size > XFS_SYMLINK_MAXLEN)
			dip->di_size = cpu_to_be64(XFS_SYMLINK_MAXLEN);
		else if (size == 0)
			xrep_dinode_zap_symlink(ri, dip);
		break;
	case S_IFDIR:
		/*
		 * Directories can't have a size larger than 32G.  If the size
		 * is zero, reset it to an empty directory.  Both of these
		 * conditions trigger dinode verifier errors, so there is no
		 * in-core state to reset.
		 */
		if (size > XFS_DIR2_SPACE_SIZE)
			dip->di_size = cpu_to_be64(XFS_DIR2_SPACE_SIZE);
		else if (size == 0)
			xrep_dinode_zap_dir(ri, dip);
		break;
	}
}

/* Fix extent size hints. */
STATIC void
xrep_dinode_extsize_hints(
	struct xfs_scrub	*sc,
	struct xfs_dinode	*dip)
{
	struct xfs_mount	*mp = sc->mp;
	uint64_t		flags2 = be64_to_cpu(dip->di_flags2);
	uint16_t		flags = be16_to_cpu(dip->di_flags);
	uint16_t		mode = be16_to_cpu(dip->di_mode);

	xfs_failaddr_t		fa;

	trace_xrep_dinode_extsize_hints(sc, dip);

	fa = xfs_inode_validate_extsize(mp, be32_to_cpu(dip->di_extsize),
			mode, flags);
	if (fa) {
		dip->di_extsize = 0;
		dip->di_flags &= ~cpu_to_be16(XFS_DIFLAG_EXTSIZE |
					      XFS_DIFLAG_EXTSZINHERIT);
	}

	if (dip->di_version < 3)
		return;

	fa = xfs_inode_validate_cowextsize(mp, be32_to_cpu(dip->di_cowextsize),
			mode, flags, flags2);
	if (fa) {
		dip->di_cowextsize = 0;
		dip->di_flags2 &= ~cpu_to_be64(XFS_DIFLAG2_COWEXTSIZE);
	}
}

/* Count extents and blocks for an inode given an rmap. */
STATIC int
xrep_dinode_walk_rmap(
	struct xfs_btree_cur		*cur,
	const struct xfs_rmap_irec	*rec,
	void				*priv)
{
	struct xrep_inode		*ri = priv;
	int				error = 0;

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

	/* We only care about this inode. */
	if (rec->rm_owner != ri->sc->sm->sm_ino)
		return 0;

	if (rec->rm_flags & XFS_RMAP_ATTR_FORK) {
		ri->attr_blocks += rec->rm_blockcount;
		if (!(rec->rm_flags & XFS_RMAP_BMBT_BLOCK))
			ri->attr_extents++;

		return 0;
	}

	ri->data_blocks += rec->rm_blockcount;
	if (!(rec->rm_flags & XFS_RMAP_BMBT_BLOCK))
		ri->data_extents++;

	return 0;
}

/* Count extents and blocks for an inode from all AG rmap data. */
STATIC int
xrep_dinode_count_ag_rmaps(
	struct xrep_inode	*ri,
	struct xfs_perag	*pag)
{
	struct xfs_btree_cur	*cur;
	struct xfs_buf		*agf;
	int			error;

	error = xfs_alloc_read_agf(pag, ri->sc->tp, 0, &agf);
	if (error)
		return error;

	cur = xfs_rmapbt_init_cursor(ri->sc->mp, ri->sc->tp, agf, pag);
	error = xfs_rmap_query_all(cur, xrep_dinode_walk_rmap, ri);
	xfs_btree_del_cursor(cur, error);
	xfs_trans_brelse(ri->sc->tp, agf);
	return error;
}

/* Count extents and blocks for a given inode from all rmap data. */
STATIC int
xrep_dinode_count_rmaps(
	struct xrep_inode	*ri)
{
	struct xfs_perag	*pag;
	xfs_agnumber_t		agno;
	int			error;

	if (!xfs_has_rmapbt(ri->sc->mp) || xfs_has_realtime(ri->sc->mp))
		return -EOPNOTSUPP;

	for_each_perag(ri->sc->mp, agno, pag) {
		error = xrep_dinode_count_ag_rmaps(ri, pag);
		if (error) {
			xfs_perag_rele(pag);
			return error;
		}
	}

	/* Can't have extents on both the rt and the data device. */
	if (ri->data_extents && ri->rt_extents)
		return -EFSCORRUPTED;

	trace_xrep_dinode_count_rmaps(ri->sc,
			ri->data_blocks, ri->rt_blocks, ri->attr_blocks,
			ri->data_extents, ri->rt_extents, ri->attr_extents);
	return 0;
}

/* Return true if this extents-format ifork looks like garbage. */
STATIC bool
xrep_dinode_bad_extents_fork(
	struct xfs_scrub	*sc,
	struct xfs_dinode	*dip,
	unsigned int		dfork_size,
	int			whichfork)
{
	struct xfs_bmbt_irec	new;
	struct xfs_bmbt_rec	*dp;
	xfs_extnum_t		nex;
	bool			isrt;
	unsigned int		i;

	nex = xfs_dfork_nextents(dip, whichfork);
	if (nex > dfork_size / sizeof(struct xfs_bmbt_rec))
		return true;

	dp = XFS_DFORK_PTR(dip, whichfork);

	isrt = dip->di_flags & cpu_to_be16(XFS_DIFLAG_REALTIME);
	for (i = 0; i < nex; i++, dp++) {
		xfs_failaddr_t	fa;

		xfs_bmbt_disk_get_all(dp, &new);
		fa = xfs_bmap_validate_extent_raw(sc->mp, isrt, whichfork,
				&new);
		if (fa)
			return true;
	}

	return false;
}

/* Return true if this btree-format ifork looks like garbage. */
STATIC bool
xrep_dinode_bad_bmbt_fork(
	struct xfs_scrub	*sc,
	struct xfs_dinode	*dip,
	unsigned int		dfork_size,
	int			whichfork)
{
	struct xfs_bmdr_block	*dfp;
	xfs_extnum_t		nex;
	unsigned int		i;
	unsigned int		dmxr;
	unsigned int		nrecs;
	unsigned int		level;

	nex = xfs_dfork_nextents(dip, whichfork);
	if (nex <= dfork_size / sizeof(struct xfs_bmbt_rec))
		return true;

	if (dfork_size < sizeof(struct xfs_bmdr_block))
		return true;

	dfp = XFS_DFORK_PTR(dip, whichfork);
	nrecs = be16_to_cpu(dfp->bb_numrecs);
	level = be16_to_cpu(dfp->bb_level);

	if (nrecs == 0 || XFS_BMDR_SPACE_CALC(nrecs) > dfork_size)
		return true;
	if (level == 0 || level >= XFS_BM_MAXLEVELS(sc->mp, whichfork))
		return true;

	dmxr = xfs_bmdr_maxrecs(dfork_size, 0);
	for (i = 1; i <= nrecs; i++) {
		struct xfs_bmbt_key	*fkp;
		xfs_bmbt_ptr_t		*fpp;
		xfs_fileoff_t		fileoff;
		xfs_fsblock_t		fsbno;

		fkp = XFS_BMDR_KEY_ADDR(dfp, i);
		fileoff = be64_to_cpu(fkp->br_startoff);
		if (!xfs_verify_fileoff(sc->mp, fileoff))
			return true;

		fpp = XFS_BMDR_PTR_ADDR(dfp, i, dmxr);
		fsbno = be64_to_cpu(*fpp);
		if (!xfs_verify_fsbno(sc->mp, fsbno))
			return true;
	}

	return false;
}

/*
 * Check the data fork for things that will fail the ifork verifiers or the
 * ifork formatters.
 */
STATIC bool
xrep_dinode_check_dfork(
	struct xfs_scrub	*sc,
	struct xfs_dinode	*dip,
	uint16_t		mode)
{
	void			*dfork_ptr;
	int64_t			data_size;
	unsigned int		fmt;
	unsigned int		dfork_size;

	/*
	 * Verifier functions take signed int64_t, so check for bogus negative
	 * values first.
	 */
	data_size = be64_to_cpu(dip->di_size);
	if (data_size < 0)
		return true;

	fmt = XFS_DFORK_FORMAT(dip, XFS_DATA_FORK);
	switch (mode & S_IFMT) {
	case S_IFIFO:
	case S_IFCHR:
	case S_IFBLK:
	case S_IFSOCK:
		if (fmt != XFS_DINODE_FMT_DEV)
			return true;
		break;
	case S_IFREG:
		if (fmt == XFS_DINODE_FMT_LOCAL)
			return true;
		fallthrough;
	case S_IFLNK:
	case S_IFDIR:
		switch (fmt) {
		case XFS_DINODE_FMT_LOCAL:
		case XFS_DINODE_FMT_EXTENTS:
		case XFS_DINODE_FMT_BTREE:
			break;
		default:
			return true;
		}
		break;
	default:
		return true;
	}

	dfork_size = XFS_DFORK_SIZE(dip, sc->mp, XFS_DATA_FORK);
	dfork_ptr = XFS_DFORK_PTR(dip, XFS_DATA_FORK);

	switch (fmt) {
	case XFS_DINODE_FMT_DEV:
		break;
	case XFS_DINODE_FMT_LOCAL:
		/* dir/symlink structure cannot be larger than the fork */
		if (data_size > dfork_size)
			return true;
		/* directory structure must pass verification. */
		if (S_ISDIR(mode) &&
		    xfs_dir2_sf_verify(sc->mp, dfork_ptr, data_size) != NULL)
			return true;
		/* symlink structure must pass verification. */
		if (S_ISLNK(mode) &&
		    xfs_symlink_shortform_verify(dfork_ptr, data_size) != NULL)
			return true;
		break;
	case XFS_DINODE_FMT_EXTENTS:
		if (xrep_dinode_bad_extents_fork(sc, dip, dfork_size,
				XFS_DATA_FORK))
			return true;
		break;
	case XFS_DINODE_FMT_BTREE:
		if (xrep_dinode_bad_bmbt_fork(sc, dip, dfork_size,
				XFS_DATA_FORK))
			return true;
		break;
	default:
		return true;
	}

	return false;
}

static void
xrep_dinode_set_data_nextents(
	struct xfs_dinode	*dip,
	xfs_extnum_t		nextents)
{
	if (xfs_dinode_has_large_extent_counts(dip))
		dip->di_big_nextents = cpu_to_be64(nextents);
	else
		dip->di_nextents = cpu_to_be32(nextents);
}

static void
xrep_dinode_set_attr_nextents(
	struct xfs_dinode	*dip,
	xfs_extnum_t		nextents)
{
	if (xfs_dinode_has_large_extent_counts(dip))
		dip->di_big_anextents = cpu_to_be32(nextents);
	else
		dip->di_anextents = cpu_to_be16(nextents);
}

/* Reset the data fork to something sane. */
STATIC void
xrep_dinode_zap_dfork(
	struct xrep_inode	*ri,
	struct xfs_dinode	*dip,
	uint16_t		mode)
{
	struct xfs_scrub	*sc = ri->sc;

	trace_xrep_dinode_zap_dfork(sc, dip);

	ri->ino_sick_mask |= XFS_SICK_INO_BMBTD_ZAPPED;

	xrep_dinode_set_data_nextents(dip, 0);
	ri->data_blocks = 0;
	ri->rt_blocks = 0;

	/* Special files always get reset to DEV */
	switch (mode & S_IFMT) {
	case S_IFIFO:
	case S_IFCHR:
	case S_IFBLK:
	case S_IFSOCK:
		dip->di_format = XFS_DINODE_FMT_DEV;
		dip->di_size = 0;
		return;
	}

	/*
	 * If we have data extents, reset to an empty map and hope the user
	 * will run the bmapbtd checker next.
	 */
	if (ri->data_extents || ri->rt_extents || S_ISREG(mode)) {
		dip->di_format = XFS_DINODE_FMT_EXTENTS;
		return;
	}

	/* Otherwise, reset the local format to the minimum. */
	switch (mode & S_IFMT) {
	case S_IFLNK:
		xrep_dinode_zap_symlink(ri, dip);
		break;
	case S_IFDIR:
		xrep_dinode_zap_dir(ri, dip);
		break;
	}
}

/*
 * Check the attr fork for things that will fail the ifork verifiers or the
 * ifork formatters.
 */
STATIC bool
xrep_dinode_check_afork(
	struct xfs_scrub		*sc,
	struct xfs_dinode		*dip)
{
	struct xfs_attr_sf_hdr		*afork_ptr;
	size_t				attr_size;
	unsigned int			afork_size;

	if (XFS_DFORK_BOFF(dip) == 0)
		return dip->di_aformat != XFS_DINODE_FMT_EXTENTS ||
		       xfs_dfork_attr_extents(dip) != 0;

	afork_size = XFS_DFORK_SIZE(dip, sc->mp, XFS_ATTR_FORK);
	afork_ptr = XFS_DFORK_PTR(dip, XFS_ATTR_FORK);

	switch (XFS_DFORK_FORMAT(dip, XFS_ATTR_FORK)) {
	case XFS_DINODE_FMT_LOCAL:
		/* Fork has to be large enough to extract the xattr size. */
		if (afork_size < sizeof(struct xfs_attr_sf_hdr))
			return true;

		/* xattr structure cannot be larger than the fork */
		attr_size = be16_to_cpu(afork_ptr->totsize);
		if (attr_size > afork_size)
			return true;

		/* xattr structure must pass verification. */
		return xfs_attr_shortform_verify(afork_ptr, attr_size) != NULL;
	case XFS_DINODE_FMT_EXTENTS:
		if (xrep_dinode_bad_extents_fork(sc, dip, afork_size,
					XFS_ATTR_FORK))
			return true;
		break;
	case XFS_DINODE_FMT_BTREE:
		if (xrep_dinode_bad_bmbt_fork(sc, dip, afork_size,
					XFS_ATTR_FORK))
			return true;
		break;
	default:
		return true;
	}

	return false;
}

/*
 * Reset the attr fork to empty.  Since the attr fork could have contained
 * ACLs, make the file readable only by root.
 */
STATIC void
xrep_dinode_zap_afork(
	struct xrep_inode	*ri,
	struct xfs_dinode	*dip,
	uint16_t		mode)
{
	struct xfs_scrub	*sc = ri->sc;

	trace_xrep_dinode_zap_afork(sc, dip);

	ri->ino_sick_mask |= XFS_SICK_INO_BMBTA_ZAPPED;

	dip->di_aformat = XFS_DINODE_FMT_EXTENTS;
	xrep_dinode_set_attr_nextents(dip, 0);
	ri->attr_blocks = 0;

	/*
	 * If the data fork is in btree format, removing the attr fork entirely
	 * might cause verifier failures if the next level down in the bmbt
	 * could now fit in the data fork area.
	 */
	if (dip->di_format != XFS_DINODE_FMT_BTREE)
		dip->di_forkoff = 0;
	dip->di_mode = cpu_to_be16(mode & ~0777);
	dip->di_uid = 0;
	dip->di_gid = 0;
}

/* Make sure the fork offset is a sensible value. */
STATIC void
xrep_dinode_ensure_forkoff(
	struct xrep_inode	*ri,
	struct xfs_dinode	*dip,
	uint16_t		mode)
{
	struct xfs_bmdr_block	*bmdr;
	struct xfs_scrub	*sc = ri->sc;
	xfs_extnum_t		attr_extents, data_extents;
	size_t			bmdr_minsz = XFS_BMDR_SPACE_CALC(1);
	unsigned int		lit_sz = XFS_LITINO(sc->mp);
	unsigned int		afork_min, dfork_min;

	trace_xrep_dinode_ensure_forkoff(sc, dip);

	/*
	 * Before calling this function, xrep_dinode_core ensured that both
	 * forks actually fit inside their respective literal areas.  If this
	 * was not the case, the fork was reset to FMT_EXTENTS with zero
	 * records.  If the rmapbt scan found attr or data fork blocks, this
	 * will be noted in the dinode_stats, and we must leave enough room
	 * for the bmap repair code to reconstruct the mapping structure.
	 *
	 * First, compute the minimum space required for the attr fork.
	 */
	switch (dip->di_aformat) {
	case XFS_DINODE_FMT_LOCAL:
		/*
		 * If we still have a shortform xattr structure at all, that
		 * means the attr fork area was exactly large enough to fit
		 * the sf structure.
		 */
		afork_min = XFS_DFORK_SIZE(dip, sc->mp, XFS_ATTR_FORK);
		break;
	case XFS_DINODE_FMT_EXTENTS:
		attr_extents = xfs_dfork_attr_extents(dip);
		if (attr_extents) {
			/*
			 * We must maintain sufficient space to hold the entire
			 * extent map array in the data fork.  Note that we
			 * previously zapped the fork if it had no chance of
			 * fitting in the inode.
			 */
			afork_min = sizeof(struct xfs_bmbt_rec) * attr_extents;
		} else if (ri->attr_extents > 0) {
			/*
			 * The attr fork thinks it has zero extents, but we
			 * found some xattr extents.  We need to leave enough
			 * empty space here so that the incore attr fork will
			 * get created (and hence trigger the attr fork bmap
			 * repairer).
			 */
			afork_min = bmdr_minsz;
		} else {
			/* No extents on disk or found in rmapbt. */
			afork_min = 0;
		}
		break;
	case XFS_DINODE_FMT_BTREE:
		/* Must have space for btree header and key/pointers. */
		bmdr = XFS_DFORK_PTR(dip, XFS_ATTR_FORK);
		afork_min = XFS_BMAP_BROOT_SPACE(sc->mp, bmdr);
		break;
	default:
		/* We should never see any other formats. */
		afork_min = 0;
		break;
	}

	/* Compute the minimum space required for the data fork. */
	switch (dip->di_format) {
	case XFS_DINODE_FMT_DEV:
		dfork_min = sizeof(__be32);
		break;
	case XFS_DINODE_FMT_UUID:
		dfork_min = sizeof(uuid_t);
		break;
	case XFS_DINODE_FMT_LOCAL:
		/*
		 * If we still have a shortform data fork at all, that means
		 * the data fork area was large enough to fit whatever was in
		 * there.
		 */
		dfork_min = be64_to_cpu(dip->di_size);
		break;
	case XFS_DINODE_FMT_EXTENTS:
		data_extents = xfs_dfork_data_extents(dip);
		if (data_extents) {
			/*
			 * We must maintain sufficient space to hold the entire
			 * extent map array in the data fork.  Note that we
			 * previously zapped the fork if it had no chance of
			 * fitting in the inode.
			 */
			dfork_min = sizeof(struct xfs_bmbt_rec) * data_extents;
		} else if (ri->data_extents > 0 || ri->rt_extents > 0) {
			/*
			 * The data fork thinks it has zero extents, but we
			 * found some data extents.  We need to leave enough
			 * empty space here so that the data fork bmap repair
			 * will recover the mappings.
			 */
			dfork_min = bmdr_minsz;
		} else {
			/* No extents on disk or found in rmapbt. */
			dfork_min = 0;
		}
		break;
	case XFS_DINODE_FMT_BTREE:
		/* Must have space for btree header and key/pointers. */
		bmdr = XFS_DFORK_PTR(dip, XFS_DATA_FORK);
		dfork_min = XFS_BMAP_BROOT_SPACE(sc->mp, bmdr);
		break;
	default:
		dfork_min = 0;
		break;
	}

	/*
	 * Round all values up to the nearest 8 bytes, because that is the
	 * precision of di_forkoff.
	 */
	afork_min = roundup(afork_min, 8);
	dfork_min = roundup(dfork_min, 8);
	bmdr_minsz = roundup(bmdr_minsz, 8);

	ASSERT(dfork_min <= lit_sz);
	ASSERT(afork_min <= lit_sz);

	/*
	 * If the data fork was zapped and we don't have enough space for the
	 * recovery fork, move the attr fork up.
	 */
	if (dip->di_format == XFS_DINODE_FMT_EXTENTS &&
	    xfs_dfork_data_extents(dip) == 0 &&
	    (ri->data_extents > 0 || ri->rt_extents > 0) &&
	    bmdr_minsz > XFS_DFORK_DSIZE(dip, sc->mp)) {
		if (bmdr_minsz + afork_min > lit_sz) {
			/*
			 * The attr for and the stub fork we need to recover
			 * the data fork won't both fit.  Zap the attr fork.
			 */
			xrep_dinode_zap_afork(ri, dip, mode);
			afork_min = bmdr_minsz;
		} else {
			void	*before, *after;

			/* Otherwise, just slide the attr fork up. */
			before = XFS_DFORK_APTR(dip);
			dip->di_forkoff = bmdr_minsz >> 3;
			after = XFS_DFORK_APTR(dip);
			memmove(after, before, XFS_DFORK_ASIZE(dip, sc->mp));
		}
	}

	/*
	 * If the attr fork was zapped and we don't have enough space for the
	 * recovery fork, move the attr fork down.
	 */
	if (dip->di_aformat == XFS_DINODE_FMT_EXTENTS &&
	    xfs_dfork_attr_extents(dip) == 0 &&
	    ri->attr_extents > 0 &&
	    bmdr_minsz > XFS_DFORK_ASIZE(dip, sc->mp)) {
		if (dip->di_format == XFS_DINODE_FMT_BTREE) {
			/*
			 * If the data fork is in btree format then we can't
			 * adjust forkoff because that runs the risk of
			 * violating the extents/btree format transition rules.
			 */
		} else if (bmdr_minsz + dfork_min > lit_sz) {
			/*
			 * If we can't move the attr fork, too bad, we lose the
			 * attr fork and leak its blocks.
			 */
			xrep_dinode_zap_afork(ri, dip, mode);
		} else {
			/*
			 * Otherwise, just slide the attr fork down.  The attr
			 * fork is empty, so we don't have any old contents to
			 * move here.
			 */
			dip->di_forkoff = (lit_sz - bmdr_minsz) >> 3;
		}
	}
}

/*
 * Zap the data/attr forks if we spot anything that isn't going to pass the
 * ifork verifiers or the ifork formatters, because we need to get the inode
 * into good enough shape that the higher level repair functions can run.
 */
STATIC void
xrep_dinode_zap_forks(
	struct xrep_inode	*ri,
	struct xfs_dinode	*dip)
{
	struct xfs_scrub	*sc = ri->sc;
	xfs_extnum_t		data_extents;
	xfs_extnum_t		attr_extents;
	xfs_filblks_t		nblocks;
	uint16_t		mode;
	bool			zap_datafork = false;
	bool			zap_attrfork = ri->zap_acls;

	trace_xrep_dinode_zap_forks(sc, dip);

	mode = be16_to_cpu(dip->di_mode);

	data_extents = xfs_dfork_data_extents(dip);
	attr_extents = xfs_dfork_attr_extents(dip);
	nblocks = be64_to_cpu(dip->di_nblocks);

	/* Inode counters don't make sense? */
	if (data_extents > nblocks)
		zap_datafork = true;
	if (attr_extents > nblocks)
		zap_attrfork = true;
	if (data_extents + attr_extents > nblocks)
		zap_datafork = zap_attrfork = true;

	if (!zap_datafork)
		zap_datafork = xrep_dinode_check_dfork(sc, dip, mode);
	if (!zap_attrfork)
		zap_attrfork = xrep_dinode_check_afork(sc, dip);

	/* Zap whatever's bad. */
	if (zap_attrfork)
		xrep_dinode_zap_afork(ri, dip, mode);
	if (zap_datafork)
		xrep_dinode_zap_dfork(ri, dip, mode);
	xrep_dinode_ensure_forkoff(ri, dip, mode);

	/*
	 * Zero di_nblocks if we don't have any extents at all to satisfy the
	 * buffer verifier.
	 */
	data_extents = xfs_dfork_data_extents(dip);
	attr_extents = xfs_dfork_attr_extents(dip);
	if (data_extents + attr_extents == 0)
		dip->di_nblocks = 0;
}

/* Inode didn't pass dinode verifiers, so fix the raw buffer and retry iget. */
STATIC int
xrep_dinode_core(
	struct xrep_inode	*ri)
{
	struct xfs_scrub	*sc = ri->sc;
	struct xfs_buf		*bp;
	struct xfs_dinode	*dip;
	xfs_ino_t		ino = sc->sm->sm_ino;
	int			error;
	int			iget_error;

	/* Figure out what this inode had mapped in both forks. */
	error = xrep_dinode_count_rmaps(ri);
	if (error)
		return error;

	/* Read the inode cluster buffer. */
	error = xfs_trans_read_buf(sc->mp, sc->tp, sc->mp->m_ddev_targp,
			ri->imap.im_blkno, ri->imap.im_len, XBF_UNMAPPED, &bp,
			NULL);
	if (error)
		return error;

	/* Make sure we can pass the inode buffer verifier. */
	xrep_dinode_buf(sc, bp);
	bp->b_ops = &xfs_inode_buf_ops;

	/* Fix everything the verifier will complain about. */
	dip = xfs_buf_offset(bp, ri->imap.im_boffset);
	xrep_dinode_header(sc, dip);
	xrep_dinode_mode(ri, dip);
	xrep_dinode_flags(sc, dip, ri->rt_extents > 0);
	xrep_dinode_size(ri, dip);
	xrep_dinode_extsize_hints(sc, dip);
	xrep_dinode_zap_forks(ri, dip);

	/* Write out the inode. */
	trace_xrep_dinode_fixed(sc, dip);
	xfs_dinode_calc_crc(sc->mp, dip);
	xfs_trans_buf_set_type(sc->tp, bp, XFS_BLFT_DINO_BUF);
	xfs_trans_log_buf(sc->tp, bp, ri->imap.im_boffset,
			ri->imap.im_boffset + sc->mp->m_sb.sb_inodesize - 1);

	/*
	 * In theory, we've fixed the ondisk inode record enough that we should
	 * be able to load the inode into the cache.  Try to iget that inode
	 * now while we hold the AGI and the inode cluster buffer and take the
	 * IOLOCK so that we can continue with repairs without anyone else
	 * accessing the inode.  If iget fails, we still need to commit the
	 * changes.
	 */
	iget_error = xchk_iget(sc, ino, &sc->ip);
	if (!iget_error)
		xchk_ilock(sc, XFS_IOLOCK_EXCL);

	/*
	 * Commit the inode cluster buffer updates and drop the AGI buffer that
	 * we've been holding since scrub setup.  From here on out, repairs
	 * deal only with the cached inode.
	 */
	error = xrep_trans_commit(sc);
	if (error)
		return error;

	if (iget_error)
		return iget_error;

	error = xchk_trans_alloc(sc, 0);
	if (error)
		return error;

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

	xchk_ilock(sc, XFS_ILOCK_EXCL);
	if (ri->ino_sick_mask)
		xfs_inode_mark_sick(sc->ip, ri->ino_sick_mask);
	return 0;
}

/* Fix everything xfs_dinode_verify cares about. */
STATIC int
xrep_dinode_problems(
	struct xrep_inode	*ri)
{
	struct xfs_scrub	*sc = ri->sc;
	int			error;

	error = xrep_dinode_core(ri);
	if (error)
		return error;

	/* We had to fix a totally busted inode, schedule quotacheck. */
	if (XFS_IS_UQUOTA_ON(sc->mp))
		xrep_force_quotacheck(sc, XFS_DQTYPE_USER);
	if (XFS_IS_GQUOTA_ON(sc->mp))
		xrep_force_quotacheck(sc, XFS_DQTYPE_GROUP);
	if (XFS_IS_PQUOTA_ON(sc->mp))
		xrep_force_quotacheck(sc, XFS_DQTYPE_PROJ);

	return 0;
}

/*
 * Fix problems that the verifiers don't care about.  In general these are
 * errors that don't cause problems elsewhere in the kernel that we can easily
 * detect, so we don't check them all that rigorously.
 */

/* Make sure block and extent counts are ok. */
STATIC int
xrep_inode_blockcounts(
	struct xfs_scrub	*sc)
{
	struct xfs_ifork	*ifp;
	xfs_filblks_t		count;
	xfs_filblks_t		acount;
	xfs_extnum_t		nextents;
	int			error;

	trace_xrep_inode_blockcounts(sc);

	/* Set data fork counters from the data fork mappings. */
	error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_DATA_FORK,
			&nextents, &count);
	if (error)
		return error;
	if (xfs_is_reflink_inode(sc->ip)) {
		/*
		 * data fork blockcount can exceed physical storage if a user
		 * reflinks the same block over and over again.
		 */
		;
	} else if (XFS_IS_REALTIME_INODE(sc->ip)) {
		if (count >= sc->mp->m_sb.sb_rblocks)
			return -EFSCORRUPTED;
	} else {
		if (count >= sc->mp->m_sb.sb_dblocks)
			return -EFSCORRUPTED;
	}
	error = xrep_ino_ensure_extent_count(sc, XFS_DATA_FORK, nextents);
	if (error)
		return error;
	sc->ip->i_df.if_nextents = nextents;

	/* Set attr fork counters from the attr fork mappings. */
	ifp = xfs_ifork_ptr(sc->ip, XFS_ATTR_FORK);
	if (ifp) {
		error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_ATTR_FORK,
				&nextents, &acount);
		if (error)
			return error;
		if (count >= sc->mp->m_sb.sb_dblocks)
			return -EFSCORRUPTED;
		error = xrep_ino_ensure_extent_count(sc, XFS_ATTR_FORK,
				nextents);
		if (error)
			return error;
		ifp->if_nextents = nextents;
	} else {
		acount = 0;
	}

	sc->ip->i_nblocks = count + acount;
	return 0;
}

/* Check for invalid uid/gid/prid. */
STATIC void
xrep_inode_ids(
	struct xfs_scrub	*sc)
{
	bool			dirty = false;

	trace_xrep_inode_ids(sc);

	if (!uid_valid(VFS_I(sc->ip)->i_uid)) {
		i_uid_write(VFS_I(sc->ip), 0);
		dirty = true;
		if (XFS_IS_UQUOTA_ON(sc->mp))
			xrep_force_quotacheck(sc, XFS_DQTYPE_USER);
	}

	if (!gid_valid(VFS_I(sc->ip)->i_gid)) {
		i_gid_write(VFS_I(sc->ip), 0);
		dirty = true;
		if (XFS_IS_GQUOTA_ON(sc->mp))
			xrep_force_quotacheck(sc, XFS_DQTYPE_GROUP);
	}

	if (sc->ip->i_projid == -1U) {
		sc->ip->i_projid = 0;
		dirty = true;
		if (XFS_IS_PQUOTA_ON(sc->mp))
			xrep_force_quotacheck(sc, XFS_DQTYPE_PROJ);
	}

	/* strip setuid/setgid if we touched any of the ids */
	if (dirty)
		VFS_I(sc->ip)->i_mode &= ~(S_ISUID | S_ISGID);
}

static inline void
xrep_clamp_timestamp(
	struct xfs_inode	*ip,
	struct timespec64	*ts)
{
	ts->tv_nsec = clamp_t(long, ts->tv_nsec, 0, NSEC_PER_SEC);
	*ts = timestamp_truncate(*ts, VFS_I(ip));
}

/* Nanosecond counters can't have more than 1 billion. */
STATIC void
xrep_inode_timestamps(
	struct xfs_inode	*ip)
{
	struct timespec64	tstamp;
	struct inode		*inode = VFS_I(ip);

	tstamp = inode_get_atime(inode);
	xrep_clamp_timestamp(ip, &tstamp);
	inode_set_atime_to_ts(inode, tstamp);

	tstamp = inode_get_mtime(inode);
	xrep_clamp_timestamp(ip, &tstamp);
	inode_set_mtime_to_ts(inode, tstamp);

	tstamp = inode_get_ctime(inode);
	xrep_clamp_timestamp(ip, &tstamp);
	inode_set_ctime_to_ts(inode, tstamp);

	xrep_clamp_timestamp(ip, &ip->i_crtime);
}

/* Fix inode flags that don't make sense together. */
STATIC void
xrep_inode_flags(
	struct xfs_scrub	*sc)
{
	uint16_t		mode;

	trace_xrep_inode_flags(sc);

	mode = VFS_I(sc->ip)->i_mode;

	/* Clear junk flags */
	if (sc->ip->i_diflags & ~XFS_DIFLAG_ANY)
		sc->ip->i_diflags &= ~XFS_DIFLAG_ANY;

	/* NEWRTBM only applies to realtime bitmaps */
	if (sc->ip->i_ino == sc->mp->m_sb.sb_rbmino)
		sc->ip->i_diflags |= XFS_DIFLAG_NEWRTBM;
	else
		sc->ip->i_diflags &= ~XFS_DIFLAG_NEWRTBM;

	/* These only make sense for directories. */
	if (!S_ISDIR(mode))
		sc->ip->i_diflags &= ~(XFS_DIFLAG_RTINHERIT |
					  XFS_DIFLAG_EXTSZINHERIT |
					  XFS_DIFLAG_PROJINHERIT |
					  XFS_DIFLAG_NOSYMLINKS);

	/* These only make sense for files. */
	if (!S_ISREG(mode))
		sc->ip->i_diflags &= ~(XFS_DIFLAG_REALTIME |
					  XFS_DIFLAG_EXTSIZE);

	/* These only make sense for non-rt files. */
	if (sc->ip->i_diflags & XFS_DIFLAG_REALTIME)
		sc->ip->i_diflags &= ~XFS_DIFLAG_FILESTREAM;

	/* Immutable and append only?  Drop the append. */
	if ((sc->ip->i_diflags & XFS_DIFLAG_IMMUTABLE) &&
	    (sc->ip->i_diflags & XFS_DIFLAG_APPEND))
		sc->ip->i_diflags &= ~XFS_DIFLAG_APPEND;

	/* Clear junk flags. */
	if (sc->ip->i_diflags2 & ~XFS_DIFLAG2_ANY)
		sc->ip->i_diflags2 &= ~XFS_DIFLAG2_ANY;

	/* No reflink flag unless we support it and it's a file. */
	if (!xfs_has_reflink(sc->mp) || !S_ISREG(mode))
		sc->ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;

	/* DAX only applies to files and dirs. */
	if (!(S_ISREG(mode) || S_ISDIR(mode)))
		sc->ip->i_diflags2 &= ~XFS_DIFLAG2_DAX;

	/* No reflink files on the realtime device. */
	if (sc->ip->i_diflags & XFS_DIFLAG_REALTIME)
		sc->ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
}

/*
 * Fix size problems with block/node format directories.  If we fail to find
 * the extent list, just bail out and let the bmapbtd repair functions clean
 * up that mess.
 */
STATIC void
xrep_inode_blockdir_size(
	struct xfs_scrub	*sc)
{
	struct xfs_iext_cursor	icur;
	struct xfs_bmbt_irec	got;
	struct xfs_ifork	*ifp;
	xfs_fileoff_t		off;
	int			error;

	trace_xrep_inode_blockdir_size(sc);

	error = xfs_iread_extents(sc->tp, sc->ip, XFS_DATA_FORK);
	if (error)
		return;

	/* Find the last block before 32G; this is the dir size. */
	ifp = xfs_ifork_ptr(sc->ip, XFS_DATA_FORK);
	off = XFS_B_TO_FSB(sc->mp, XFS_DIR2_SPACE_SIZE);
	if (!xfs_iext_lookup_extent_before(sc->ip, ifp, &off, &icur, &got)) {
		/* zero-extents directory? */
		return;
	}

	off = got.br_startoff + got.br_blockcount;
	sc->ip->i_disk_size = min_t(loff_t, XFS_DIR2_SPACE_SIZE,
			XFS_FSB_TO_B(sc->mp, off));
}

/* Fix size problems with short format directories. */
STATIC void
xrep_inode_sfdir_size(
	struct xfs_scrub	*sc)
{
	struct xfs_ifork	*ifp;

	trace_xrep_inode_sfdir_size(sc);

	ifp = xfs_ifork_ptr(sc->ip, XFS_DATA_FORK);
	sc->ip->i_disk_size = ifp->if_bytes;
}

/*
 * Fix any irregularities in a directory inode's size now that we can iterate
 * extent maps and access other regular inode data.
 */
STATIC void
xrep_inode_dir_size(
	struct xfs_scrub	*sc)
{
	trace_xrep_inode_dir_size(sc);

	switch (sc->ip->i_df.if_format) {
	case XFS_DINODE_FMT_EXTENTS:
	case XFS_DINODE_FMT_BTREE:
		xrep_inode_blockdir_size(sc);
		break;
	case XFS_DINODE_FMT_LOCAL:
		xrep_inode_sfdir_size(sc);
		break;
	}
}

/* Fix extent size hint problems. */
STATIC void
xrep_inode_extsize(
	struct xfs_scrub	*sc)
{
	/* Fix misaligned extent size hints on a directory. */
	if ((sc->ip->i_diflags & XFS_DIFLAG_RTINHERIT) &&
	    (sc->ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) &&
	    xfs_extlen_to_rtxmod(sc->mp, sc->ip->i_extsize) > 0) {
		sc->ip->i_extsize = 0;
		sc->ip->i_diflags &= ~XFS_DIFLAG_EXTSZINHERIT;
	}
}

/* Fix any irregularities in an inode that the verifiers don't catch. */
STATIC int
xrep_inode_problems(
	struct xfs_scrub	*sc)
{
	int			error;

	error = xrep_inode_blockcounts(sc);
	if (error)
		return error;
	xrep_inode_timestamps(sc->ip);
	xrep_inode_flags(sc);
	xrep_inode_ids(sc);
	/*
	 * We can now do a better job fixing the size of a directory now that
	 * we can scan the data fork extents than we could in xrep_dinode_size.
	 */
	if (S_ISDIR(VFS_I(sc->ip)->i_mode))
		xrep_inode_dir_size(sc);
	xrep_inode_extsize(sc);

	trace_xrep_inode_fixed(sc);
	xfs_trans_log_inode(sc->tp, sc->ip, XFS_ILOG_CORE);
	return xrep_roll_trans(sc);
}

/* Repair an inode's fields. */
int
xrep_inode(
	struct xfs_scrub	*sc)
{
	int			error = 0;

	/*
	 * No inode?  That means we failed the _iget verifiers.  Repair all
	 * the things that the inode verifiers care about, then retry _iget.
	 */
	if (!sc->ip) {
		struct xrep_inode	*ri = sc->buf;

		ASSERT(ri != NULL);

		error = xrep_dinode_problems(ri);
		if (error)
			return error;

		/* By this point we had better have a working incore inode. */
		if (!sc->ip)
			return -EFSCORRUPTED;
	}

	xfs_trans_ijoin(sc->tp, sc->ip, 0);

	/* If we found corruption of any kind, try to fix it. */
	if ((sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) ||
	    (sc->sm->sm_flags & XFS_SCRUB_OFLAG_XCORRUPT)) {
		error = xrep_inode_problems(sc);
		if (error)
			return error;
	}

	/* See if we can clear the reflink flag. */
	if (xfs_is_reflink_inode(sc->ip)) {
		error = xfs_reflink_clear_inode_flag(sc->ip, &sc->tp);
		if (error)
			return error;
	}

	return xrep_defer_finish(sc);
}