summaryrefslogtreecommitdiff
path: root/fs/xfs/scrub/inode_repair.c
blob: 6806deba5b7cd4cbf3e4b2ee2ab47a5cb4489a74 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright (C) 2022 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_rmap.h"
#include "xfs_bmap.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 "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 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
 * _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.
 */

/*
 * 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;
};

/* Setup function for inode repair. */
int
xrep_setup_inode(
	struct xfs_scrub	*sc,
	struct xfs_imap		*imap)
{
	struct xrep_inode	*ri;

	/*
	 * The only information that needs to be passed between inode scrub and
	 * repair is the location of the ondisk metadata if iget fails.  The
	 * rest of struct xrep_inode is context data that we need to massage
	 * the ondisk inode to the point that iget will work, which means that
	 * we don't allocate anything at all if the incore inode is loaded.
	 */
	if (!imap)
		return 0;

	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 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;
	struct xfs_trans	*tp = sc->tp;
	struct xfs_perag	*pag;
	struct xfs_dinode	*dip;
	xfs_agnumber_t		agno;
	xfs_agino_t		agino;
	int			ioff;
	int			i;
	int			ni;
	bool			crc_ok;
	bool			magic_ok;
	bool			unlinked_ok;

	ni = XFS_BB_TO_FSB(mp, bp->b_length) * mp->m_sb.sb_inopblock;
	agno = xfs_daddr_to_agno(mp, xfs_buf_daddr(bp));
	pag = xfs_perag_get(mp, agno);
	for (i = 0; i < ni; i++) {
		ioff = i << mp->m_sb.sb_inodelog;
		dip = xfs_buf_offset(bp, ioff);
		agino = be32_to_cpu(dip->di_next_unlinked);

		unlinked_ok = magic_ok = crc_ok = false;

		if (xfs_verify_agino_or_null(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)
			continue;

		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, ioff, ioff + sizeof(*dip) - 1);
	}
	xfs_perag_put(pag);
}

/* 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 xfs_scrub	*sc,
	struct xfs_dinode	*dip)
{
	uint16_t		mode;

	trace_xrep_dinode_mode(sc, dip);

	mode = be16_to_cpu(dip->di_mode);
	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;
}

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

	trace_xrep_dinode_flags(sc, dip);

	mode = be16_to_cpu(dip->di_mode);
	flags = be16_to_cpu(dip->di_flags);
	flags2 = be64_to_cpu(dip->di_flags2);

	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 (flags2 & XFS_DIFLAG2_REFLINK)
		flags2 &= ~XFS_DIFLAG2_DAX;
	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 to the current dir.  We don't have to worry
 * about incore state because this inode is failing the verifiers.
 */
STATIC void
xrep_dinode_zap_symlink(
	struct xfs_scrub	*sc,
	struct xfs_dinode	*dip)
{
	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 = '.';
}

/*
 * Blow out dir, make it 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 xfs_scrub	*sc,
	struct xfs_dinode	*dip)
{
	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));
}

/* Make sure we don't have a garbage file size. */
STATIC void
xrep_dinode_size(
	struct xfs_scrub	*sc,
	struct xfs_dinode	*dip)
{
	uint64_t		size;
	uint16_t		mode;

	trace_xrep_dinode_size(sc, dip);

	mode = be16_to_cpu(dip->di_mode);
	size = be64_to_cpu(dip->di_size);
	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(sc, 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(sc, 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;
	uint16_t		flags;
	uint16_t		mode;
	xfs_failaddr_t		fa;

	trace_xrep_dinode_extsize_hints(sc, dip);

	mode = be16_to_cpu(dip->di_mode);
	flags = be16_to_cpu(dip->di_flags);
	flags2 = be64_to_cpu(dip->di_flags2);

	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);
	}
}

/* Inode didn't pass 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;
	bool			dontcare;
	int			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 absolutely sure this inode isn't in core, because we don't
	 * want to create a cache coherence problem.
	 */
	error = xfs_icache_inode_is_allocated(sc->mp, sc->tp, ino, &dontcare);
	if (error == 0) {
		ASSERT(0);
		return -EFSCORRUPTED;
	}

	/* 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(sc, dip);
	xrep_dinode_flags(sc, dip);
	xrep_dinode_size(sc, dip);
	xrep_dinode_extsize_hints(sc, 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);

	/*
	 * Now that we've finished rewriting anything in the ondisk metadata
	 * that would prevent iget from giving us an incore inode, commit the
	 * inode cluster buffer updates and drop the AGI buffer that we've been
	 * holding since scrub setup.
	 */
	error = xrep_trans_commit(sc);
	if (error)
		return error;

	/* Try again to load the inode. */
	error = xchk_iget(sc, ino, &sc->ip);
	if (error)
		return error;

	xchk_try_dqattach(sc);

	xchk_ilock(sc, XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL);
	error = xchk_trans_alloc(sc, 0);
	if (error)
		return error;

	xchk_ilock(sc, XFS_ILOCK_EXCL);
	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_REALTIME_INODE(sc->ip)) {
		if (count >= sc->mp->m_sb.sb_rblocks)
			return -EFSCORRUPTED;
	} else if (!xfs_has_reflink(sc->mp)) {
		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)
{
	trace_xrep_inode_ids(sc);

	if (i_uid_read(VFS_I(sc->ip)) == -1U) {
		i_uid_write(VFS_I(sc->ip), 0);
		VFS_I(sc->ip)->i_mode &= ~(S_ISUID | S_ISGID);
		if (XFS_IS_UQUOTA_ON(sc->mp))
			xrep_force_quotacheck(sc, XFS_DQTYPE_USER);
	}

	if (i_gid_read(VFS_I(sc->ip)) == -1U) {
		i_gid_write(VFS_I(sc->ip), 0);
		VFS_I(sc->ip)->i_mode &= ~(S_ISUID | S_ISGID);
		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;
		if (XFS_IS_PQUOTA_ON(sc->mp))
			xrep_force_quotacheck(sc, XFS_DQTYPE_PROJ);
	}
}

static inline void
xrep_clamp_nsec(
	struct timespec64	*ts)
{
	ts->tv_nsec = clamp_t(long, ts->tv_nsec, 0, NSEC_PER_SEC);
}

/* Nanosecond counters can't have more than 1 billion. */
STATIC void
xrep_inode_timestamps(
	struct xfs_inode	*ip)
{
	xrep_clamp_nsec(&VFS_I(ip)->i_atime);
	xrep_clamp_nsec(&VFS_I(ip)->i_mtime);
	xrep_clamp_nsec(&VFS_I(ip)->i_ctime);
	xrep_clamp_nsec(&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;

	/* No mixing reflink and DAX yet. */
	if (sc->ip->i_diflags2 & XFS_DIFLAG2_REFLINK)
		sc->ip->i_diflags2 &= ~XFS_DIFLAG2_DAX;
}

/*
 * 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);

	/* Find the last block before 32G; this is the dir size. */
	error = xfs_iread_extents(sc->tp, sc->ip, XFS_DATA_FORK);
	if (error)
		return;

	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 an inode's size now that we can iterate extent
 * maps and access other regular inode data.
 */
STATIC void
xrep_inode_size(
	struct xfs_scrub	*sc)
{
	trace_xrep_inode_size(sc);

	/*
	 * Currently we only support fixing size on extents or btree format
	 * directories.  Files can be any size and sizes for the other inode
	 * special types are fixed by xrep_dinode_size.
	 */
	if (!S_ISDIR(VFS_I(sc->ip)->i_mode))
		return;
	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) &&
	    sc->ip->i_extsize % sc->mp->m_sb.sb_rextsize > 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);
	xrep_inode_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))
		return xfs_reflink_clear_inode_flag(sc->ip, &sc->tp);

	return 0;
}