summaryrefslogtreecommitdiffstats
path: root/fs/xfs/libxfs/xfs_inode_buf.c
blob: 9bb9c73c1eb265bcb19b782cc75ccf1c458493fa (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2000-2006 Silicon Graphics, Inc.
 * All Rights Reserved.
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_inode.h"
#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_cksum.h"
#include "xfs_icache.h"
#include "xfs_trans.h"
#include "xfs_ialloc.h"
#include "xfs_dir2.h"

#include <linux/iversion.h>

/*
 * Check that none of the inode's in the buffer have a next
 * unlinked field of 0.
 */
#if defined(DEBUG)
void
xfs_inobp_check(
	xfs_mount_t	*mp,
	xfs_buf_t	*bp)
{
	int		i;
	xfs_dinode_t	*dip;

	for (i = 0; i < M_IGEO(mp)->inodes_per_cluster; i++) {
		dip = xfs_buf_offset(bp, i * mp->m_sb.sb_inodesize);
		if (!dip->di_next_unlinked)  {
			xfs_alert(mp,
	"Detected bogus zero next_unlinked field in inode %d buffer 0x%llx.",
				i, (long long)bp->b_bn);
		}
	}
}
#endif

bool
xfs_dinode_good_version(
	struct xfs_mount *mp,
	__u8		version)
{
	if (xfs_sb_version_hascrc(&mp->m_sb))
		return version == 3;

	return version == 1 || version == 2;
}

/*
 * If we are doing readahead on an inode buffer, we might be in log recovery
 * reading an inode allocation buffer that hasn't yet been replayed, and hence
 * has not had the inode cores stamped into it. Hence for readahead, the buffer
 * may be potentially invalid.
 *
 * If the readahead buffer is invalid, we need to mark it with an error and
 * clear the DONE status of the buffer so that a followup read will re-read it
 * from disk. We don't report the error otherwise to avoid warnings during log
 * recovery and we don't get unnecssary panics on debug kernels. We use EIO here
 * because all we want to do is say readahead failed; there is no-one to report
 * the error to, so this will distinguish it from a non-ra verifier failure.
 * Changes to this readahead error behavour also need to be reflected in
 * xfs_dquot_buf_readahead_verify().
 */
static void
xfs_inode_buf_verify(
	struct xfs_buf	*bp,
	bool		readahead)
{
	struct xfs_mount *mp = bp->b_mount;
	xfs_agnumber_t	agno;
	int		i;
	int		ni;

	/*
	 * Validate the magic number and version of every inode in the buffer
	 */
	agno = xfs_daddr_to_agno(mp, XFS_BUF_ADDR(bp));
	ni = XFS_BB_TO_FSB(mp, bp->b_length) * mp->m_sb.sb_inopblock;
	for (i = 0; i < ni; i++) {
		int		di_ok;
		xfs_dinode_t	*dip;
		xfs_agino_t	unlinked_ino;

		dip = xfs_buf_offset(bp, (i << mp->m_sb.sb_inodelog));
		unlinked_ino = be32_to_cpu(dip->di_next_unlinked);
		di_ok = xfs_verify_magic16(bp, dip->di_magic) &&
			xfs_dinode_good_version(mp, dip->di_version) &&
			xfs_verify_agino_or_null(mp, agno, unlinked_ino);
		if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
						XFS_ERRTAG_ITOBP_INOTOBP))) {
			if (readahead) {
				bp->b_flags &= ~XBF_DONE;
				xfs_buf_ioerror(bp, -EIO);
				return;
			}

#ifdef DEBUG
			xfs_alert(mp,
				"bad inode magic/vsn daddr %lld #%d (magic=%x)",
				(unsigned long long)bp->b_bn, i,
				be16_to_cpu(dip->di_magic));
#endif
			xfs_buf_verifier_error(bp, -EFSCORRUPTED,
					__func__, dip, sizeof(*dip),
					NULL);
			return;
		}
	}
}


static void
xfs_inode_buf_read_verify(
	struct xfs_buf	*bp)
{
	xfs_inode_buf_verify(bp, false);
}

static void
xfs_inode_buf_readahead_verify(
	struct xfs_buf	*bp)
{
	xfs_inode_buf_verify(bp, true);
}

static void
xfs_inode_buf_write_verify(
	struct xfs_buf	*bp)
{
	xfs_inode_buf_verify(bp, false);
}

const struct xfs_buf_ops xfs_inode_buf_ops = {
	.name = "xfs_inode",
	.magic16 = { cpu_to_be16(XFS_DINODE_MAGIC),
		     cpu_to_be16(XFS_DINODE_MAGIC) },
	.verify_read = xfs_inode_buf_read_verify,
	.verify_write = xfs_inode_buf_write_verify,
};

const struct xfs_buf_ops xfs_inode_buf_ra_ops = {
	.name = "xfs_inode_ra",
	.magic16 = { cpu_to_be16(XFS_DINODE_MAGIC),
		     cpu_to_be16(XFS_DINODE_MAGIC) },
	.verify_read = xfs_inode_buf_readahead_verify,
	.verify_write = xfs_inode_buf_write_verify,
};


/*
 * This routine is called to map an inode to the buffer containing the on-disk
 * version of the inode.  It returns a pointer to the buffer containing the
 * on-disk inode in the bpp parameter, and in the dipp parameter it returns a
 * pointer to the on-disk inode within that buffer.
 *
 * If a non-zero error is returned, then the contents of bpp and dipp are
 * undefined.
 */
int
xfs_imap_to_bp(
	struct xfs_mount	*mp,
	struct xfs_trans	*tp,
	struct xfs_imap		*imap,
	struct xfs_dinode       **dipp,
	struct xfs_buf		**bpp,
	uint			buf_flags,
	uint			iget_flags)
{
	struct xfs_buf		*bp;
	int			error;

	buf_flags |= XBF_UNMAPPED;
	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
				   (int)imap->im_len, buf_flags, &bp,
				   &xfs_inode_buf_ops);
	if (error) {
		if (error == -EAGAIN) {
			ASSERT(buf_flags & XBF_TRYLOCK);
			return error;
		}
		xfs_warn(mp, "%s: xfs_trans_read_buf() returned error %d.",
			__func__, error);
		return error;
	}

	*bpp = bp;
	*dipp = xfs_buf_offset(bp, imap->im_boffset);
	return 0;
}

void
xfs_inode_from_disk(
	struct xfs_inode	*ip,
	struct xfs_dinode	*from)
{
	struct xfs_icdinode	*to = &ip->i_d;
	struct inode		*inode = VFS_I(ip);


	/*
	 * Convert v1 inodes immediately to v2 inode format as this is the
	 * minimum inode version format we support in the rest of the code.
	 */
	to->di_version = from->di_version;
	if (to->di_version == 1) {
		set_nlink(inode, be16_to_cpu(from->di_onlink));
		to->di_projid_lo = 0;
		to->di_projid_hi = 0;
		to->di_version = 2;
	} else {
		set_nlink(inode, be32_to_cpu(from->di_nlink));
		to->di_projid_lo = be16_to_cpu(from->di_projid_lo);
		to->di_projid_hi = be16_to_cpu(from->di_projid_hi);
	}

	to->di_format = from->di_format;
	to->di_uid = be32_to_cpu(from->di_uid);
	to->di_gid = be32_to_cpu(from->di_gid);
	to->di_flushiter = be16_to_cpu(from->di_flushiter);

	/*
	 * Time is signed, so need to convert to signed 32 bit before
	 * storing in inode timestamp which may be 64 bit. Otherwise
	 * a time before epoch is converted to a time long after epoch
	 * on 64 bit systems.
	 */
	inode->i_atime.tv_sec = (int)be32_to_cpu(from->di_atime.t_sec);
	inode->i_atime.tv_nsec = (int)be32_to_cpu(from->di_atime.t_nsec);
	inode->i_mtime.tv_sec = (int)be32_to_cpu(from->di_mtime.t_sec);
	inode->i_mtime.tv_nsec = (int)be32_to_cpu(from->di_mtime.t_nsec);
	inode->i_ctime.tv_sec = (int)be32_to_cpu(from->di_ctime.t_sec);
	inode->i_ctime.tv_nsec = (int)be32_to_cpu(from->di_ctime.t_nsec);
	inode->i_generation = be32_to_cpu(from->di_gen);
	inode->i_mode = be16_to_cpu(from->di_mode);

	to->di_size = be64_to_cpu(from->di_size);
	to->di_nblocks = be64_to_cpu(from->di_nblocks);
	to->di_extsize = be32_to_cpu(from->di_extsize);
	to->di_nextents = be32_to_cpu(from->di_nextents);
	to->di_anextents = be16_to_cpu(from->di_anextents);
	to->di_forkoff = from->di_forkoff;
	to->di_aformat	= from->di_aformat;
	to->di_dmevmask	= be32_to_cpu(from->di_dmevmask);
	to->di_dmstate	= be16_to_cpu(from->di_dmstate);
	to->di_flags	= be16_to_cpu(from->di_flags);

	if (to->di_version == 3) {
		inode_set_iversion_queried(inode,
					   be64_to_cpu(from->di_changecount));
		to->di_crtime.t_sec = be32_to_cpu(from->di_crtime.t_sec);
		to->di_crtime.t_nsec = be32_to_cpu(from->di_crtime.t_nsec);
		to->di_flags2 = be64_to_cpu(from->di_flags2);
		to->di_cowextsize = be32_to_cpu(from->di_cowextsize);
	}
}

void
xfs_inode_to_disk(
	struct xfs_inode	*ip,
	struct xfs_dinode	*to,
	xfs_lsn_t		lsn)
{
	struct xfs_icdinode	*from = &ip->i_d;
	struct inode		*inode = VFS_I(ip);

	to->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
	to->di_onlink = 0;

	to->di_version = from->di_version;
	to->di_format = from->di_format;
	to->di_uid = cpu_to_be32(from->di_uid);
	to->di_gid = cpu_to_be32(from->di_gid);
	to->di_projid_lo = cpu_to_be16(from->di_projid_lo);
	to->di_projid_hi = cpu_to_be16(from->di_projid_hi);

	memset(to->di_pad, 0, sizeof(to->di_pad));
	to->di_atime.t_sec = cpu_to_be32(inode->i_atime.tv_sec);
	to->di_atime.t_nsec = cpu_to_be32(inode->i_atime.tv_nsec);
	to->di_mtime.t_sec = cpu_to_be32(inode->i_mtime.tv_sec);
	to->di_mtime.t_nsec = cpu_to_be32(inode->i_mtime.tv_nsec);
	to->di_ctime.t_sec = cpu_to_be32(inode->i_ctime.tv_sec);
	to->di_ctime.t_nsec = cpu_to_be32(inode->i_ctime.tv_nsec);
	to->di_nlink = cpu_to_be32(inode->i_nlink);
	to->di_gen = cpu_to_be32(inode->i_generation);
	to->di_mode = cpu_to_be16(inode->i_mode);

	to->di_size = cpu_to_be64(from->di_size);
	to->di_nblocks = cpu_to_be64(from->di_nblocks);
	to->di_extsize = cpu_to_be32(from->di_extsize);
	to->di_nextents = cpu_to_be32(from->di_nextents);
	to->di_anextents = cpu_to_be16(from->di_anextents);
	to->di_forkoff = from->di_forkoff;
	to->di_aformat = from->di_aformat;
	to->di_dmevmask = cpu_to_be32(from->di_dmevmask);
	to->di_dmstate = cpu_to_be16(from->di_dmstate);
	to->di_flags = cpu_to_be16(from->di_flags);

	if (from->di_version == 3) {
		to->di_changecount = cpu_to_be64(inode_peek_iversion(inode));
		to->di_crtime.t_sec = cpu_to_be32(from->di_crtime.t_sec);
		to->di_crtime.t_nsec = cpu_to_be32(from->di_crtime.t_nsec);
		to->di_flags2 = cpu_to_be64(from->di_flags2);
		to->di_cowextsize = cpu_to_be32(from->di_cowextsize);
		to->di_ino = cpu_to_be64(ip->i_ino);
		to->di_lsn = cpu_to_be64(lsn);
		memset(to->di_pad2, 0, sizeof(to->di_pad2));
		uuid_copy(&to->di_uuid, &ip->i_mount->m_sb.sb_meta_uuid);
		to->di_flushiter = 0;
	} else {
		to->di_flushiter = cpu_to_be16(from->di_flushiter);
	}
}

void
xfs_log_dinode_to_disk(
	struct xfs_log_dinode	*from,
	struct xfs_dinode	*to)
{
	to->di_magic = cpu_to_be16(from->di_magic);
	to->di_mode = cpu_to_be16(from->di_mode);
	to->di_version = from->di_version;
	to->di_format = from->di_format;
	to->di_onlink = 0;
	to->di_uid = cpu_to_be32(from->di_uid);
	to->di_gid = cpu_to_be32(from->di_gid);
	to->di_nlink = cpu_to_be32(from->di_nlink);
	to->di_projid_lo = cpu_to_be16(from->di_projid_lo);
	to->di_projid_hi = cpu_to_be16(from->di_projid_hi);
	memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));

	to->di_atime.t_sec = cpu_to_be32(from->di_atime.t_sec);
	to->di_atime.t_nsec = cpu_to_be32(from->di_atime.t_nsec);
	to->di_mtime.t_sec = cpu_to_be32(from->di_mtime.t_sec);
	to->di_mtime.t_nsec = cpu_to_be32(from->di_mtime.t_nsec);
	to->di_ctime.t_sec = cpu_to_be32(from->di_ctime.t_sec);
	to->di_ctime.t_nsec = cpu_to_be32(from->di_ctime.t_nsec);

	to->di_size = cpu_to_be64(from->di_size);
	to->di_nblocks = cpu_to_be64(from->di_nblocks);
	to->di_extsize = cpu_to_be32(from->di_extsize);
	to->di_nextents = cpu_to_be32(from->di_nextents);
	to->di_anextents = cpu_to_be16(from->di_anextents);
	to->di_forkoff = from->di_forkoff;
	to->di_aformat = from->di_aformat;
	to->di_dmevmask = cpu_to_be32(from->di_dmevmask);
	to->di_dmstate = cpu_to_be16(from->di_dmstate);
	to->di_flags = cpu_to_be16(from->di_flags);
	to->di_gen = cpu_to_be32(from->di_gen);

	if (from->di_version == 3) {
		to->di_changecount = cpu_to_be64(from->di_changecount);
		to->di_crtime.t_sec = cpu_to_be32(from->di_crtime.t_sec);
		to->di_crtime.t_nsec = cpu_to_be32(from->di_crtime.t_nsec);
		to->di_flags2 = cpu_to_be64(from->di_flags2);
		to->di_cowextsize = cpu_to_be32(from->di_cowextsize);
		to->di_ino = cpu_to_be64(from->di_ino);
		to->di_lsn = cpu_to_be64(from->di_lsn);
		memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
		uuid_copy(&to->di_uuid, &from->di_uuid);
		to->di_flushiter = 0;
	} else {
		to->di_flushiter = cpu_to_be16(from->di_flushiter);
	}
}

static xfs_failaddr_t
xfs_dinode_verify_fork(
	struct xfs_dinode	*dip,
	struct xfs_mount	*mp,
	int			whichfork)
{
	uint32_t		di_nextents = XFS_DFORK_NEXTENTS(dip, whichfork);

	switch (XFS_DFORK_FORMAT(dip, whichfork)) {
	case XFS_DINODE_FMT_LOCAL:
		/*
		 * no local regular files yet
		 */
		if (whichfork == XFS_DATA_FORK) {
			if (S_ISREG(be16_to_cpu(dip->di_mode)))
				return __this_address;
			if (be64_to_cpu(dip->di_size) >
					XFS_DFORK_SIZE(dip, mp, whichfork))
				return __this_address;
		}
		if (di_nextents)
			return __this_address;
		break;
	case XFS_DINODE_FMT_EXTENTS:
		if (di_nextents > XFS_DFORK_MAXEXT(dip, mp, whichfork))
			return __this_address;
		break;
	case XFS_DINODE_FMT_BTREE:
		if (whichfork == XFS_ATTR_FORK) {
			if (di_nextents > MAXAEXTNUM)
				return __this_address;
		} else if (di_nextents > MAXEXTNUM) {
			return __this_address;
		}
		break;
	default:
		return __this_address;
	}
	return NULL;
}

static xfs_failaddr_t
xfs_dinode_verify_forkoff(
	struct xfs_dinode	*dip,
	struct xfs_mount	*mp)
{
	if (!XFS_DFORK_Q(dip))
		return NULL;

	switch (dip->di_format)  {
	case XFS_DINODE_FMT_DEV:
		if (dip->di_forkoff != (roundup(sizeof(xfs_dev_t), 8) >> 3))
			return __this_address;
		break;
	case XFS_DINODE_FMT_LOCAL:	/* fall through ... */
	case XFS_DINODE_FMT_EXTENTS:    /* fall through ... */
	case XFS_DINODE_FMT_BTREE:
		if (dip->di_forkoff >= (XFS_LITINO(mp, dip->di_version) >> 3))
			return __this_address;
		break;
	default:
		return __this_address;
	}
	return NULL;
}

xfs_failaddr_t
xfs_dinode_verify(
	struct xfs_mount	*mp,
	xfs_ino_t		ino,
	struct xfs_dinode	*dip)
{
	xfs_failaddr_t		fa;
	uint16_t		mode;
	uint16_t		flags;
	uint64_t		flags2;
	uint64_t		di_size;

	if (dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC))
		return __this_address;

	/* Verify v3 integrity information first */
	if (dip->di_version >= 3) {
		if (!xfs_sb_version_hascrc(&mp->m_sb))
			return __this_address;
		if (!xfs_verify_cksum((char *)dip, mp->m_sb.sb_inodesize,
				      XFS_DINODE_CRC_OFF))
			return __this_address;
		if (be64_to_cpu(dip->di_ino) != ino)
			return __this_address;
		if (!uuid_equal(&dip->di_uuid, &mp->m_sb.sb_meta_uuid))
			return __this_address;
	}

	/* don't allow invalid i_size */
	di_size = be64_to_cpu(dip->di_size);
	if (di_size & (1ULL << 63))
		return __this_address;

	mode = be16_to_cpu(dip->di_mode);
	if (mode && xfs_mode_to_ftype(mode) == XFS_DIR3_FT_UNKNOWN)
		return __this_address;

	/* No zero-length symlinks/dirs. */
	if ((S_ISLNK(mode) || S_ISDIR(mode)) && di_size == 0)
		return __this_address;

	/* Fork checks carried over from xfs_iformat_fork */
	if (mode &&
	    be32_to_cpu(dip->di_nextents) + be16_to_cpu(dip->di_anextents) >
			be64_to_cpu(dip->di_nblocks))
		return __this_address;

	if (mode && XFS_DFORK_BOFF(dip) > mp->m_sb.sb_inodesize)
		return __this_address;

	flags = be16_to_cpu(dip->di_flags);

	if (mode && (flags & XFS_DIFLAG_REALTIME) && !mp->m_rtdev_targp)
		return __this_address;

	/* check for illegal values of forkoff */
	fa = xfs_dinode_verify_forkoff(dip, mp);
	if (fa)
		return fa;

	/* Do we have appropriate data fork formats for the mode? */
	switch (mode & S_IFMT) {
	case S_IFIFO:
	case S_IFCHR:
	case S_IFBLK:
	case S_IFSOCK:
		if (dip->di_format != XFS_DINODE_FMT_DEV)
			return __this_address;
		break;
	case S_IFREG:
	case S_IFLNK:
	case S_IFDIR:
		fa = xfs_dinode_verify_fork(dip, mp, XFS_DATA_FORK);
		if (fa)
			return fa;
		break;
	case 0:
		/* Uninitialized inode ok. */
		break;
	default:
		return __this_address;
	}

	if (XFS_DFORK_Q(dip)) {
		fa = xfs_dinode_verify_fork(dip, mp, XFS_ATTR_FORK);
		if (fa)
			return fa;
	} else {
		/*
		 * If there is no fork offset, this may be a freshly-made inode
		 * in a new disk cluster, in which case di_aformat is zeroed.
		 * Otherwise, such an inode must be in EXTENTS format; this goes
		 * for freed inodes as well.
		 */
		switch (dip->di_aformat) {
		case 0:
		case XFS_DINODE_FMT_EXTENTS:
			break;
		default:
			return __this_address;
		}
		if (dip->di_anextents)
			return __this_address;
	}

	/* extent size hint validation */
	fa = xfs_inode_validate_extsize(mp, be32_to_cpu(dip->di_extsize),
			mode, flags);
	if (fa)
		return fa;

	/* only version 3 or greater inodes are extensively verified here */
	if (dip->di_version < 3)
		return NULL;

	flags2 = be64_to_cpu(dip->di_flags2);

	/* don't allow reflink/cowextsize if we don't have reflink */
	if ((flags2 & (XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE)) &&
	     !xfs_sb_version_hasreflink(&mp->m_sb))
		return __this_address;

	/* only regular files get reflink */
	if ((flags2 & XFS_DIFLAG2_REFLINK) && (mode & S_IFMT) != S_IFREG)
		return __this_address;

	/* don't let reflink and realtime mix */
	if ((flags2 & XFS_DIFLAG2_REFLINK) && (flags & XFS_DIFLAG_REALTIME))
		return __this_address;

	/* don't let reflink and dax mix */
	if ((flags2 & XFS_DIFLAG2_REFLINK) && (flags2 & XFS_DIFLAG2_DAX))
		return __this_address;

	/* COW extent size hint validation */
	fa = xfs_inode_validate_cowextsize(mp, be32_to_cpu(dip->di_cowextsize),
			mode, flags, flags2);
	if (fa)
		return fa;

	return NULL;
}

void
xfs_dinode_calc_crc(
	struct xfs_mount	*mp,
	struct xfs_dinode	*dip)
{
	uint32_t		crc;

	if (dip->di_version < 3)
		return;

	ASSERT(xfs_sb_version_hascrc(&mp->m_sb));
	crc = xfs_start_cksum_update((char *)dip, mp->m_sb.sb_inodesize,
			      XFS_DINODE_CRC_OFF);
	dip->di_crc = xfs_end_cksum(crc);
}

/*
 * Read the disk inode attributes into the in-core inode structure.
 *
 * For version 5 superblocks, if we are initialising a new inode and we are not
 * utilising the XFS_MOUNT_IKEEP inode cluster mode, we can simple build the new
 * inode core with a random generation number. If we are keeping inodes around,
 * we need to read the inode cluster to get the existing generation number off
 * disk. Further, if we are using version 4 superblocks (i.e. v1/v2 inode
 * format) then log recovery is dependent on the di_flushiter field being
 * initialised from the current on-disk value and hence we must also read the
 * inode off disk.
 */
int
xfs_iread(
	xfs_mount_t	*mp,
	xfs_trans_t	*tp,
	xfs_inode_t	*ip,
	uint		iget_flags)
{
	xfs_buf_t	*bp;
	xfs_dinode_t	*dip;
	xfs_failaddr_t	fa;
	int		error;

	/*
	 * Fill in the location information in the in-core inode.
	 */
	error = xfs_imap(mp, tp, ip->i_ino, &ip->i_imap, iget_flags);
	if (error)
		return error;

	/* shortcut IO on inode allocation if possible */
	if ((iget_flags & XFS_IGET_CREATE) &&
	    xfs_sb_version_hascrc(&mp->m_sb) &&
	    !(mp->m_flags & XFS_MOUNT_IKEEP)) {
		/* initialise the on-disk inode core */
		memset(&ip->i_d, 0, sizeof(ip->i_d));
		VFS_I(ip)->i_generation = prandom_u32();
		ip->i_d.di_version = 3;
		return 0;
	}

	/*
	 * Get pointers to the on-disk inode and the buffer containing it.
	 */
	error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &bp, 0, iget_flags);
	if (error)
		return error;

	/* even unallocated inodes are verified */
	fa = xfs_dinode_verify(mp, ip->i_ino, dip);
	if (fa) {
		xfs_inode_verifier_error(ip, -EFSCORRUPTED, "dinode", dip,
				sizeof(*dip), fa);
		error = -EFSCORRUPTED;
		goto out_brelse;
	}

	/*
	 * If the on-disk inode is already linked to a directory
	 * entry, copy all of the inode into the in-core inode.
	 * xfs_iformat_fork() handles copying in the inode format
	 * specific information.
	 * Otherwise, just get the truly permanent information.
	 */
	if (dip->di_mode) {
		xfs_inode_from_disk(ip, dip);
		error = xfs_iformat_fork(ip, dip);
		if (error)  {
#ifdef DEBUG
			xfs_alert(mp, "%s: xfs_iformat() returned error %d",
				__func__, error);
#endif /* DEBUG */
			goto out_brelse;
		}
	} else {
		/*
		 * Partial initialisation of the in-core inode. Just the bits
		 * that xfs_ialloc won't overwrite or relies on being correct.
		 */
		ip->i_d.di_version = dip->di_version;
		VFS_I(ip)->i_generation = be32_to_cpu(dip->di_gen);
		ip->i_d.di_flushiter = be16_to_cpu(dip->di_flushiter);

		/*
		 * Make sure to pull in the mode here as well in
		 * case the inode is released without being used.
		 * This ensures that xfs_inactive() will see that
		 * the inode is already free and not try to mess
		 * with the uninitialized part of it.
		 */
		VFS_I(ip)->i_mode = 0;
	}

	ASSERT(ip->i_d.di_version >= 2);
	ip->i_delayed_blks = 0;

	/*
	 * Mark the buffer containing the inode as something to keep
	 * around for a while.  This helps to keep recently accessed
	 * meta-data in-core longer.
	 */
	xfs_buf_set_ref(bp, XFS_INO_REF);

	/*
	 * Use xfs_trans_brelse() to release the buffer containing the on-disk
	 * inode, because it was acquired with xfs_trans_read_buf() in
	 * xfs_imap_to_bp() above.  If tp is NULL, this is just a normal
	 * brelse().  If we're within a transaction, then xfs_trans_brelse()
	 * will only release the buffer if it is not dirty within the
	 * transaction.  It will be OK to release the buffer in this case,
	 * because inodes on disk are never destroyed and we will be locking the
	 * new in-core inode before putting it in the cache where other
	 * processes can find it.  Thus we don't have to worry about the inode
	 * being changed just because we released the buffer.
	 */
 out_brelse:
	xfs_trans_brelse(tp, bp);
	return error;
}

/*
 * Validate di_extsize hint.
 *
 * The rules are documented at xfs_ioctl_setattr_check_extsize().
 * These functions must be kept in sync with each other.
 */
xfs_failaddr_t
xfs_inode_validate_extsize(
	struct xfs_mount		*mp,
	uint32_t			extsize,
	uint16_t			mode,
	uint16_t			flags)
{
	bool				rt_flag;
	bool				hint_flag;
	bool				inherit_flag;
	uint32_t			extsize_bytes;
	uint32_t			blocksize_bytes;

	rt_flag = (flags & XFS_DIFLAG_REALTIME);
	hint_flag = (flags & XFS_DIFLAG_EXTSIZE);
	inherit_flag = (flags & XFS_DIFLAG_EXTSZINHERIT);
	extsize_bytes = XFS_FSB_TO_B(mp, extsize);

	if (rt_flag)
		blocksize_bytes = mp->m_sb.sb_rextsize << mp->m_sb.sb_blocklog;
	else
		blocksize_bytes = mp->m_sb.sb_blocksize;

	if ((hint_flag || inherit_flag) && !(S_ISDIR(mode) || S_ISREG(mode)))
		return __this_address;

	if (hint_flag && !S_ISREG(mode))
		return __this_address;

	if (inherit_flag && !S_ISDIR(mode))
		return __this_address;

	if ((hint_flag || inherit_flag) && extsize == 0)
		return __this_address;

	/* free inodes get flags set to zero but extsize remains */
	if (mode && !(hint_flag || inherit_flag) && extsize != 0)
		return __this_address;

	if (extsize_bytes % blocksize_bytes)
		return __this_address;

	if (extsize > MAXEXTLEN)
		return __this_address;

	if (!rt_flag && extsize > mp->m_sb.sb_agblocks / 2)
		return __this_address;

	return NULL;
}

/*
 * Validate di_cowextsize hint.
 *
 * The rules are documented at xfs_ioctl_setattr_check_cowextsize().
 * These functions must be kept in sync with each other.
 */
xfs_failaddr_t
xfs_inode_validate_cowextsize(
	struct xfs_mount		*mp,
	uint32_t			cowextsize,
	uint16_t			mode,
	uint16_t			flags,
	uint64_t			flags2)
{
	bool				rt_flag;
	bool				hint_flag;
	uint32_t			cowextsize_bytes;

	rt_flag = (flags & XFS_DIFLAG_REALTIME);
	hint_flag = (flags2 & XFS_DIFLAG2_COWEXTSIZE);
	cowextsize_bytes = XFS_FSB_TO_B(mp, cowextsize);

	if (hint_flag && !xfs_sb_version_hasreflink(&mp->m_sb))
		return __this_address;

	if (hint_flag && !(S_ISDIR(mode) || S_ISREG(mode)))
		return __this_address;

	if (hint_flag && cowextsize == 0)
		return __this_address;

	/* free inodes get flags set to zero but cowextsize remains */
	if (mode && !hint_flag && cowextsize != 0)
		return __this_address;

	if (hint_flag && rt_flag)
		return __this_address;

	if (cowextsize_bytes % mp->m_sb.sb_blocksize)
		return __this_address;

	if (cowextsize > MAXEXTLEN)
		return __this_address;

	if (cowextsize > mp->m_sb.sb_agblocks / 2)
		return __this_address;

	return NULL;
}