summaryrefslogtreecommitdiff
path: root/fs/xfs/libxfs/xfs_dir2_data.c
blob: fdd803fecb8e266a009835cbd563ef5d04dbee6e (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
/*
 * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc.
 * Copyright (c) 2013 Red Hat, Inc.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_inode.h"
#include "xfs_dir2.h"
#include "xfs_dir2_priv.h"
#include "xfs_error.h"
#include "xfs_trans.h"
#include "xfs_buf_item.h"
#include "xfs_cksum.h"

/*
 * Check the consistency of the data block.
 * The input can also be a block-format directory.
 * Return 0 is the buffer is good, otherwise an error.
 */
int
__xfs_dir3_data_check(
	struct xfs_inode	*dp,		/* incore inode pointer */
	struct xfs_buf		*bp)		/* data block's buffer */
{
	xfs_dir2_dataptr_t	addr;		/* addr for leaf lookup */
	xfs_dir2_data_free_t	*bf;		/* bestfree table */
	xfs_dir2_block_tail_t	*btp=NULL;	/* block tail */
	int			count;		/* count of entries found */
	xfs_dir2_data_hdr_t	*hdr;		/* data block header */
	xfs_dir2_data_entry_t	*dep;		/* data entry */
	xfs_dir2_data_free_t	*dfp;		/* bestfree entry */
	xfs_dir2_data_unused_t	*dup;		/* unused entry */
	char			*endp;		/* end of useful data */
	int			freeseen;	/* mask of bestfrees seen */
	xfs_dahash_t		hash;		/* hash of current name */
	int			i;		/* leaf index */
	int			lastfree;	/* last entry was unused */
	xfs_dir2_leaf_entry_t	*lep=NULL;	/* block leaf entries */
	xfs_mount_t		*mp;		/* filesystem mount point */
	char			*p;		/* current data position */
	int			stale;		/* count of stale leaves */
	struct xfs_name		name;
	const struct xfs_dir_ops *ops;
	struct xfs_da_geometry	*geo;

	mp = bp->b_target->bt_mount;
	geo = mp->m_dir_geo;

	/*
	 * We can be passed a null dp here from a verifier, so we need to go the
	 * hard way to get them.
	 */
	ops = xfs_dir_get_ops(mp, dp);

	hdr = bp->b_addr;
	p = (char *)ops->data_entry_p(hdr);

	switch (hdr->magic) {
	case cpu_to_be32(XFS_DIR3_BLOCK_MAGIC):
	case cpu_to_be32(XFS_DIR2_BLOCK_MAGIC):
		btp = xfs_dir2_block_tail_p(geo, hdr);
		lep = xfs_dir2_block_leaf_p(btp);
		endp = (char *)lep;

		/*
		 * The number of leaf entries is limited by the size of the
		 * block and the amount of space used by the data entries.
		 * We don't know how much space is used by the data entries yet,
		 * so just ensure that the count falls somewhere inside the
		 * block right now.
		 */
		XFS_WANT_CORRUPTED_RETURN(be32_to_cpu(btp->count) <
			((char *)btp - p) / sizeof(struct xfs_dir2_leaf_entry));
		break;
	case cpu_to_be32(XFS_DIR3_DATA_MAGIC):
	case cpu_to_be32(XFS_DIR2_DATA_MAGIC):
		endp = (char *)hdr + geo->blksize;
		break;
	default:
		XFS_ERROR_REPORT("Bad Magic", XFS_ERRLEVEL_LOW, mp);
		return -EFSCORRUPTED;
	}

	/*
	 * Account for zero bestfree entries.
	 */
	bf = ops->data_bestfree_p(hdr);
	count = lastfree = freeseen = 0;
	if (!bf[0].length) {
		XFS_WANT_CORRUPTED_RETURN(!bf[0].offset);
		freeseen |= 1 << 0;
	}
	if (!bf[1].length) {
		XFS_WANT_CORRUPTED_RETURN(!bf[1].offset);
		freeseen |= 1 << 1;
	}
	if (!bf[2].length) {
		XFS_WANT_CORRUPTED_RETURN(!bf[2].offset);
		freeseen |= 1 << 2;
	}

	XFS_WANT_CORRUPTED_RETURN(be16_to_cpu(bf[0].length) >=
						be16_to_cpu(bf[1].length));
	XFS_WANT_CORRUPTED_RETURN(be16_to_cpu(bf[1].length) >=
						be16_to_cpu(bf[2].length));
	/*
	 * Loop over the data/unused entries.
	 */
	while (p < endp) {
		dup = (xfs_dir2_data_unused_t *)p;
		/*
		 * If it's unused, look for the space in the bestfree table.
		 * If we find it, account for that, else make sure it
		 * doesn't need to be there.
		 */
		if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
			XFS_WANT_CORRUPTED_RETURN(lastfree == 0);
			XFS_WANT_CORRUPTED_RETURN(
				be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup)) ==
					       (char *)dup - (char *)hdr);
			dfp = xfs_dir2_data_freefind(hdr, bf, dup);
			if (dfp) {
				i = (int)(dfp - bf);
				XFS_WANT_CORRUPTED_RETURN(
					(freeseen & (1 << i)) == 0);
				freeseen |= 1 << i;
			} else {
				XFS_WANT_CORRUPTED_RETURN(
					be16_to_cpu(dup->length) <=
						be16_to_cpu(bf[2].length));
			}
			p += be16_to_cpu(dup->length);
			lastfree = 1;
			continue;
		}
		/*
		 * It's a real entry.  Validate the fields.
		 * If this is a block directory then make sure it's
		 * in the leaf section of the block.
		 * The linear search is crude but this is DEBUG code.
		 */
		dep = (xfs_dir2_data_entry_t *)p;
		XFS_WANT_CORRUPTED_RETURN(dep->namelen != 0);
		XFS_WANT_CORRUPTED_RETURN(
			!xfs_dir_ino_validate(mp, be64_to_cpu(dep->inumber)));
		XFS_WANT_CORRUPTED_RETURN(
			be16_to_cpu(*ops->data_entry_tag_p(dep)) ==
					       (char *)dep - (char *)hdr);
		XFS_WANT_CORRUPTED_RETURN(
				ops->data_get_ftype(dep) < XFS_DIR3_FT_MAX);
		count++;
		lastfree = 0;
		if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
		    hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC)) {
			addr = xfs_dir2_db_off_to_dataptr(geo, geo->datablk,
						(xfs_dir2_data_aoff_t)
						((char *)dep - (char *)hdr));
			name.name = dep->name;
			name.len = dep->namelen;
			hash = mp->m_dirnameops->hashname(&name);
			for (i = 0; i < be32_to_cpu(btp->count); i++) {
				if (be32_to_cpu(lep[i].address) == addr &&
				    be32_to_cpu(lep[i].hashval) == hash)
					break;
			}
			XFS_WANT_CORRUPTED_RETURN(i < be32_to_cpu(btp->count));
		}
		p += ops->data_entsize(dep->namelen);
	}
	/*
	 * Need to have seen all the entries and all the bestfree slots.
	 */
	XFS_WANT_CORRUPTED_RETURN(freeseen == 7);
	if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
	    hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC)) {
		for (i = stale = 0; i < be32_to_cpu(btp->count); i++) {
			if (lep[i].address ==
			    cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
				stale++;
			if (i > 0)
				XFS_WANT_CORRUPTED_RETURN(
					be32_to_cpu(lep[i].hashval) >=
						be32_to_cpu(lep[i - 1].hashval));
		}
		XFS_WANT_CORRUPTED_RETURN(count ==
			be32_to_cpu(btp->count) - be32_to_cpu(btp->stale));
		XFS_WANT_CORRUPTED_RETURN(stale == be32_to_cpu(btp->stale));
	}
	return 0;
}

static bool
xfs_dir3_data_verify(
	struct xfs_buf		*bp)
{
	struct xfs_mount	*mp = bp->b_target->bt_mount;
	struct xfs_dir3_blk_hdr	*hdr3 = bp->b_addr;

	if (xfs_sb_version_hascrc(&mp->m_sb)) {
		if (hdr3->magic != cpu_to_be32(XFS_DIR3_DATA_MAGIC))
			return false;
		if (!uuid_equal(&hdr3->uuid, &mp->m_sb.sb_uuid))
			return false;
		if (be64_to_cpu(hdr3->blkno) != bp->b_bn)
			return false;
	} else {
		if (hdr3->magic != cpu_to_be32(XFS_DIR2_DATA_MAGIC))
			return false;
	}
	if (__xfs_dir3_data_check(NULL, bp))
		return false;
	return true;
}

/*
 * Readahead of the first block of the directory when it is opened is completely
 * oblivious to the format of the directory. Hence we can either get a block
 * format buffer or a data format buffer on readahead.
 */
static void
xfs_dir3_data_reada_verify(
	struct xfs_buf		*bp)
{
	struct xfs_dir2_data_hdr *hdr = bp->b_addr;

	switch (hdr->magic) {
	case cpu_to_be32(XFS_DIR2_BLOCK_MAGIC):
	case cpu_to_be32(XFS_DIR3_BLOCK_MAGIC):
		bp->b_ops = &xfs_dir3_block_buf_ops;
		bp->b_ops->verify_read(bp);
		return;
	case cpu_to_be32(XFS_DIR2_DATA_MAGIC):
	case cpu_to_be32(XFS_DIR3_DATA_MAGIC):
		xfs_dir3_data_verify(bp);
		return;
	default:
		xfs_buf_ioerror(bp, -EFSCORRUPTED);
		xfs_verifier_error(bp);
		break;
	}
}

static void
xfs_dir3_data_read_verify(
	struct xfs_buf	*bp)
{
	struct xfs_mount	*mp = bp->b_target->bt_mount;

	if (xfs_sb_version_hascrc(&mp->m_sb) &&
	     !xfs_buf_verify_cksum(bp, XFS_DIR3_DATA_CRC_OFF))
		 xfs_buf_ioerror(bp, -EFSBADCRC);
	else if (!xfs_dir3_data_verify(bp))
		xfs_buf_ioerror(bp, -EFSCORRUPTED);

	if (bp->b_error)
		xfs_verifier_error(bp);
}

static void
xfs_dir3_data_write_verify(
	struct xfs_buf	*bp)
{
	struct xfs_mount	*mp = bp->b_target->bt_mount;
	struct xfs_buf_log_item	*bip = bp->b_fspriv;
	struct xfs_dir3_blk_hdr	*hdr3 = bp->b_addr;

	if (!xfs_dir3_data_verify(bp)) {
		xfs_buf_ioerror(bp, -EFSCORRUPTED);
		xfs_verifier_error(bp);
		return;
	}

	if (!xfs_sb_version_hascrc(&mp->m_sb))
		return;

	if (bip)
		hdr3->lsn = cpu_to_be64(bip->bli_item.li_lsn);

	xfs_buf_update_cksum(bp, XFS_DIR3_DATA_CRC_OFF);
}

const struct xfs_buf_ops xfs_dir3_data_buf_ops = {
	.verify_read = xfs_dir3_data_read_verify,
	.verify_write = xfs_dir3_data_write_verify,
};

static const struct xfs_buf_ops xfs_dir3_data_reada_buf_ops = {
	.verify_read = xfs_dir3_data_reada_verify,
	.verify_write = xfs_dir3_data_write_verify,
};


int
xfs_dir3_data_read(
	struct xfs_trans	*tp,
	struct xfs_inode	*dp,
	xfs_dablk_t		bno,
	xfs_daddr_t		mapped_bno,
	struct xfs_buf		**bpp)
{
	int			err;

	err = xfs_da_read_buf(tp, dp, bno, mapped_bno, bpp,
				XFS_DATA_FORK, &xfs_dir3_data_buf_ops);
	if (!err && tp)
		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_DATA_BUF);
	return err;
}

int
xfs_dir3_data_readahead(
	struct xfs_inode	*dp,
	xfs_dablk_t		bno,
	xfs_daddr_t		mapped_bno)
{
	return xfs_da_reada_buf(dp, bno, mapped_bno,
				XFS_DATA_FORK, &xfs_dir3_data_reada_buf_ops);
}

/*
 * Given a data block and an unused entry from that block,
 * return the bestfree entry if any that corresponds to it.
 */
xfs_dir2_data_free_t *
xfs_dir2_data_freefind(
	struct xfs_dir2_data_hdr *hdr,		/* data block header */
	struct xfs_dir2_data_free *bf,		/* bestfree table pointer */
	struct xfs_dir2_data_unused *dup)	/* unused space */
{
	xfs_dir2_data_free_t	*dfp;		/* bestfree entry */
	xfs_dir2_data_aoff_t	off;		/* offset value needed */
#ifdef DEBUG
	int			matched;	/* matched the value */
	int			seenzero;	/* saw a 0 bestfree entry */
#endif

	off = (xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr);

#ifdef DEBUG
	/*
	 * Validate some consistency in the bestfree table.
	 * Check order, non-overlapping entries, and if we find the
	 * one we're looking for it has to be exact.
	 */
	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
	for (dfp = &bf[0], seenzero = matched = 0;
	     dfp < &bf[XFS_DIR2_DATA_FD_COUNT];
	     dfp++) {
		if (!dfp->offset) {
			ASSERT(!dfp->length);
			seenzero = 1;
			continue;
		}
		ASSERT(seenzero == 0);
		if (be16_to_cpu(dfp->offset) == off) {
			matched = 1;
			ASSERT(dfp->length == dup->length);
		} else if (off < be16_to_cpu(dfp->offset))
			ASSERT(off + be16_to_cpu(dup->length) <= be16_to_cpu(dfp->offset));
		else
			ASSERT(be16_to_cpu(dfp->offset) + be16_to_cpu(dfp->length) <= off);
		ASSERT(matched || be16_to_cpu(dfp->length) >= be16_to_cpu(dup->length));
		if (dfp > &bf[0])
			ASSERT(be16_to_cpu(dfp[-1].length) >= be16_to_cpu(dfp[0].length));
	}
#endif
	/*
	 * If this is smaller than the smallest bestfree entry,
	 * it can't be there since they're sorted.
	 */
	if (be16_to_cpu(dup->length) <
	    be16_to_cpu(bf[XFS_DIR2_DATA_FD_COUNT - 1].length))
		return NULL;
	/*
	 * Look at the three bestfree entries for our guy.
	 */
	for (dfp = &bf[0]; dfp < &bf[XFS_DIR2_DATA_FD_COUNT]; dfp++) {
		if (!dfp->offset)
			return NULL;
		if (be16_to_cpu(dfp->offset) == off)
			return dfp;
	}
	/*
	 * Didn't find it.  This only happens if there are duplicate lengths.
	 */
	return NULL;
}

/*
 * Insert an unused-space entry into the bestfree table.
 */
xfs_dir2_data_free_t *				/* entry inserted */
xfs_dir2_data_freeinsert(
	struct xfs_dir2_data_hdr *hdr,		/* data block pointer */
	struct xfs_dir2_data_free *dfp,		/* bestfree table pointer */
	struct xfs_dir2_data_unused *dup,	/* unused space */
	int			*loghead)	/* log the data header (out) */
{
	xfs_dir2_data_free_t	new;		/* new bestfree entry */

	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));

	new.length = dup->length;
	new.offset = cpu_to_be16((char *)dup - (char *)hdr);

	/*
	 * Insert at position 0, 1, or 2; or not at all.
	 */
	if (be16_to_cpu(new.length) > be16_to_cpu(dfp[0].length)) {
		dfp[2] = dfp[1];
		dfp[1] = dfp[0];
		dfp[0] = new;
		*loghead = 1;
		return &dfp[0];
	}
	if (be16_to_cpu(new.length) > be16_to_cpu(dfp[1].length)) {
		dfp[2] = dfp[1];
		dfp[1] = new;
		*loghead = 1;
		return &dfp[1];
	}
	if (be16_to_cpu(new.length) > be16_to_cpu(dfp[2].length)) {
		dfp[2] = new;
		*loghead = 1;
		return &dfp[2];
	}
	return NULL;
}

/*
 * Remove a bestfree entry from the table.
 */
STATIC void
xfs_dir2_data_freeremove(
	struct xfs_dir2_data_hdr *hdr,		/* data block header */
	struct xfs_dir2_data_free *bf,		/* bestfree table pointer */
	struct xfs_dir2_data_free *dfp,		/* bestfree entry pointer */
	int			*loghead)	/* out: log data header */
{

	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));

	/*
	 * It's the first entry, slide the next 2 up.
	 */
	if (dfp == &bf[0]) {
		bf[0] = bf[1];
		bf[1] = bf[2];
	}
	/*
	 * It's the second entry, slide the 3rd entry up.
	 */
	else if (dfp == &bf[1])
		bf[1] = bf[2];
	/*
	 * Must be the last entry.
	 */
	else
		ASSERT(dfp == &bf[2]);
	/*
	 * Clear the 3rd entry, must be zero now.
	 */
	bf[2].length = 0;
	bf[2].offset = 0;
	*loghead = 1;
}

/*
 * Given a data block, reconstruct its bestfree map.
 */
void
xfs_dir2_data_freescan(
	struct xfs_inode	*dp,
	struct xfs_dir2_data_hdr *hdr,
	int			*loghead)
{
	xfs_dir2_block_tail_t	*btp;		/* block tail */
	xfs_dir2_data_entry_t	*dep;		/* active data entry */
	xfs_dir2_data_unused_t	*dup;		/* unused data entry */
	struct xfs_dir2_data_free *bf;
	char			*endp;		/* end of block's data */
	char			*p;		/* current entry pointer */
	struct xfs_da_geometry	*geo = dp->i_mount->m_dir_geo;

	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));

	/*
	 * Start by clearing the table.
	 */
	bf = dp->d_ops->data_bestfree_p(hdr);
	memset(bf, 0, sizeof(*bf) * XFS_DIR2_DATA_FD_COUNT);
	*loghead = 1;
	/*
	 * Set up pointers.
	 */
	p = (char *)dp->d_ops->data_entry_p(hdr);
	if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
	    hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC)) {
		btp = xfs_dir2_block_tail_p(geo, hdr);
		endp = (char *)xfs_dir2_block_leaf_p(btp);
	} else
		endp = (char *)hdr + geo->blksize;
	/*
	 * Loop over the block's entries.
	 */
	while (p < endp) {
		dup = (xfs_dir2_data_unused_t *)p;
		/*
		 * If it's a free entry, insert it.
		 */
		if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
			ASSERT((char *)dup - (char *)hdr ==
			       be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup)));
			xfs_dir2_data_freeinsert(hdr, bf, dup, loghead);
			p += be16_to_cpu(dup->length);
		}
		/*
		 * For active entries, check their tags and skip them.
		 */
		else {
			dep = (xfs_dir2_data_entry_t *)p;
			ASSERT((char *)dep - (char *)hdr ==
			       be16_to_cpu(*dp->d_ops->data_entry_tag_p(dep)));
			p += dp->d_ops->data_entsize(dep->namelen);
		}
	}
}

/*
 * Initialize a data block at the given block number in the directory.
 * Give back the buffer for the created block.
 */
int						/* error */
xfs_dir3_data_init(
	xfs_da_args_t		*args,		/* directory operation args */
	xfs_dir2_db_t		blkno,		/* logical dir block number */
	struct xfs_buf		**bpp)		/* output block buffer */
{
	struct xfs_buf		*bp;		/* block buffer */
	xfs_dir2_data_hdr_t	*hdr;		/* data block header */
	xfs_inode_t		*dp;		/* incore directory inode */
	xfs_dir2_data_unused_t	*dup;		/* unused entry pointer */
	struct xfs_dir2_data_free *bf;
	int			error;		/* error return value */
	int			i;		/* bestfree index */
	xfs_mount_t		*mp;		/* filesystem mount point */
	xfs_trans_t		*tp;		/* transaction pointer */
	int                     t;              /* temp */

	dp = args->dp;
	mp = dp->i_mount;
	tp = args->trans;
	/*
	 * Get the buffer set up for the block.
	 */
	error = xfs_da_get_buf(tp, dp, xfs_dir2_db_to_da(args->geo, blkno),
			       -1, &bp, XFS_DATA_FORK);
	if (error)
		return error;
	bp->b_ops = &xfs_dir3_data_buf_ops;
	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DIR_DATA_BUF);

	/*
	 * Initialize the header.
	 */
	hdr = bp->b_addr;
	if (xfs_sb_version_hascrc(&mp->m_sb)) {
		struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;

		memset(hdr3, 0, sizeof(*hdr3));
		hdr3->magic = cpu_to_be32(XFS_DIR3_DATA_MAGIC);
		hdr3->blkno = cpu_to_be64(bp->b_bn);
		hdr3->owner = cpu_to_be64(dp->i_ino);
		uuid_copy(&hdr3->uuid, &mp->m_sb.sb_uuid);

	} else
		hdr->magic = cpu_to_be32(XFS_DIR2_DATA_MAGIC);

	bf = dp->d_ops->data_bestfree_p(hdr);
	bf[0].offset = cpu_to_be16(dp->d_ops->data_entry_offset);
	for (i = 1; i < XFS_DIR2_DATA_FD_COUNT; i++) {
		bf[i].length = 0;
		bf[i].offset = 0;
	}

	/*
	 * Set up an unused entry for the block's body.
	 */
	dup = dp->d_ops->data_unused_p(hdr);
	dup->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG);

	t = args->geo->blksize - (uint)dp->d_ops->data_entry_offset;
	bf[0].length = cpu_to_be16(t);
	dup->length = cpu_to_be16(t);
	*xfs_dir2_data_unused_tag_p(dup) = cpu_to_be16((char *)dup - (char *)hdr);
	/*
	 * Log it and return it.
	 */
	xfs_dir2_data_log_header(args, bp);
	xfs_dir2_data_log_unused(args, bp, dup);
	*bpp = bp;
	return 0;
}

/*
 * Log an active data entry from the block.
 */
void
xfs_dir2_data_log_entry(
	struct xfs_da_args	*args,
	struct xfs_buf		*bp,
	xfs_dir2_data_entry_t	*dep)		/* data entry pointer */
{
	struct xfs_dir2_data_hdr *hdr = bp->b_addr;

	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));

	xfs_trans_log_buf(args->trans, bp, (uint)((char *)dep - (char *)hdr),
		(uint)((char *)(args->dp->d_ops->data_entry_tag_p(dep) + 1) -
		       (char *)hdr - 1));
}

/*
 * Log a data block header.
 */
void
xfs_dir2_data_log_header(
	struct xfs_da_args	*args,
	struct xfs_buf		*bp)
{
#ifdef DEBUG
	struct xfs_dir2_data_hdr *hdr = bp->b_addr;

	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
#endif

	xfs_trans_log_buf(args->trans, bp, 0,
			  args->dp->d_ops->data_entry_offset - 1);
}

/*
 * Log a data unused entry.
 */
void
xfs_dir2_data_log_unused(
	struct xfs_da_args	*args,
	struct xfs_buf		*bp,
	xfs_dir2_data_unused_t	*dup)		/* data unused pointer */
{
	xfs_dir2_data_hdr_t	*hdr = bp->b_addr;

	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));

	/*
	 * Log the first part of the unused entry.
	 */
	xfs_trans_log_buf(args->trans, bp, (uint)((char *)dup - (char *)hdr),
		(uint)((char *)&dup->length + sizeof(dup->length) -
		       1 - (char *)hdr));
	/*
	 * Log the end (tag) of the unused entry.
	 */
	xfs_trans_log_buf(args->trans, bp,
		(uint)((char *)xfs_dir2_data_unused_tag_p(dup) - (char *)hdr),
		(uint)((char *)xfs_dir2_data_unused_tag_p(dup) - (char *)hdr +
		       sizeof(xfs_dir2_data_off_t) - 1));
}

/*
 * Make a byte range in the data block unused.
 * Its current contents are unimportant.
 */
void
xfs_dir2_data_make_free(
	struct xfs_da_args	*args,
	struct xfs_buf		*bp,
	xfs_dir2_data_aoff_t	offset,		/* starting byte offset */
	xfs_dir2_data_aoff_t	len,		/* length in bytes */
	int			*needlogp,	/* out: log header */
	int			*needscanp)	/* out: regen bestfree */
{
	xfs_dir2_data_hdr_t	*hdr;		/* data block pointer */
	xfs_dir2_data_free_t	*dfp;		/* bestfree pointer */
	char			*endptr;	/* end of data area */
	int			needscan;	/* need to regen bestfree */
	xfs_dir2_data_unused_t	*newdup;	/* new unused entry */
	xfs_dir2_data_unused_t	*postdup;	/* unused entry after us */
	xfs_dir2_data_unused_t	*prevdup;	/* unused entry before us */
	struct xfs_dir2_data_free *bf;

	hdr = bp->b_addr;

	/*
	 * Figure out where the end of the data area is.
	 */
	if (hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
	    hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC))
		endptr = (char *)hdr + args->geo->blksize;
	else {
		xfs_dir2_block_tail_t	*btp;	/* block tail */

		ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
			hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
		btp = xfs_dir2_block_tail_p(args->geo, hdr);
		endptr = (char *)xfs_dir2_block_leaf_p(btp);
	}
	/*
	 * If this isn't the start of the block, then back up to
	 * the previous entry and see if it's free.
	 */
	if (offset > args->dp->d_ops->data_entry_offset) {
		__be16			*tagp;	/* tag just before us */

		tagp = (__be16 *)((char *)hdr + offset) - 1;
		prevdup = (xfs_dir2_data_unused_t *)((char *)hdr + be16_to_cpu(*tagp));
		if (be16_to_cpu(prevdup->freetag) != XFS_DIR2_DATA_FREE_TAG)
			prevdup = NULL;
	} else
		prevdup = NULL;
	/*
	 * If this isn't the end of the block, see if the entry after
	 * us is free.
	 */
	if ((char *)hdr + offset + len < endptr) {
		postdup =
			(xfs_dir2_data_unused_t *)((char *)hdr + offset + len);
		if (be16_to_cpu(postdup->freetag) != XFS_DIR2_DATA_FREE_TAG)
			postdup = NULL;
	} else
		postdup = NULL;
	ASSERT(*needscanp == 0);
	needscan = 0;
	/*
	 * Previous and following entries are both free,
	 * merge everything into a single free entry.
	 */
	bf = args->dp->d_ops->data_bestfree_p(hdr);
	if (prevdup && postdup) {
		xfs_dir2_data_free_t	*dfp2;	/* another bestfree pointer */

		/*
		 * See if prevdup and/or postdup are in bestfree table.
		 */
		dfp = xfs_dir2_data_freefind(hdr, bf, prevdup);
		dfp2 = xfs_dir2_data_freefind(hdr, bf, postdup);
		/*
		 * We need a rescan unless there are exactly 2 free entries
		 * namely our two.  Then we know what's happening, otherwise
		 * since the third bestfree is there, there might be more
		 * entries.
		 */
		needscan = (bf[2].length != 0);
		/*
		 * Fix up the new big freespace.
		 */
		be16_add_cpu(&prevdup->length, len + be16_to_cpu(postdup->length));
		*xfs_dir2_data_unused_tag_p(prevdup) =
			cpu_to_be16((char *)prevdup - (char *)hdr);
		xfs_dir2_data_log_unused(args, bp, prevdup);
		if (!needscan) {
			/*
			 * Has to be the case that entries 0 and 1 are
			 * dfp and dfp2 (don't know which is which), and
			 * entry 2 is empty.
			 * Remove entry 1 first then entry 0.
			 */
			ASSERT(dfp && dfp2);
			if (dfp == &bf[1]) {
				dfp = &bf[0];
				ASSERT(dfp2 == dfp);
				dfp2 = &bf[1];
			}
			xfs_dir2_data_freeremove(hdr, bf, dfp2, needlogp);
			xfs_dir2_data_freeremove(hdr, bf, dfp, needlogp);
			/*
			 * Now insert the new entry.
			 */
			dfp = xfs_dir2_data_freeinsert(hdr, bf, prevdup,
						       needlogp);
			ASSERT(dfp == &bf[0]);
			ASSERT(dfp->length == prevdup->length);
			ASSERT(!dfp[1].length);
			ASSERT(!dfp[2].length);
		}
	}
	/*
	 * The entry before us is free, merge with it.
	 */
	else if (prevdup) {
		dfp = xfs_dir2_data_freefind(hdr, bf, prevdup);
		be16_add_cpu(&prevdup->length, len);
		*xfs_dir2_data_unused_tag_p(prevdup) =
			cpu_to_be16((char *)prevdup - (char *)hdr);
		xfs_dir2_data_log_unused(args, bp, prevdup);
		/*
		 * If the previous entry was in the table, the new entry
		 * is longer, so it will be in the table too.  Remove
		 * the old one and add the new one.
		 */
		if (dfp) {
			xfs_dir2_data_freeremove(hdr, bf, dfp, needlogp);
			xfs_dir2_data_freeinsert(hdr, bf, prevdup, needlogp);
		}
		/*
		 * Otherwise we need a scan if the new entry is big enough.
		 */
		else {
			needscan = be16_to_cpu(prevdup->length) >
				   be16_to_cpu(bf[2].length);
		}
	}
	/*
	 * The following entry is free, merge with it.
	 */
	else if (postdup) {
		dfp = xfs_dir2_data_freefind(hdr, bf, postdup);
		newdup = (xfs_dir2_data_unused_t *)((char *)hdr + offset);
		newdup->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG);
		newdup->length = cpu_to_be16(len + be16_to_cpu(postdup->length));
		*xfs_dir2_data_unused_tag_p(newdup) =
			cpu_to_be16((char *)newdup - (char *)hdr);
		xfs_dir2_data_log_unused(args, bp, newdup);
		/*
		 * If the following entry was in the table, the new entry
		 * is longer, so it will be in the table too.  Remove
		 * the old one and add the new one.
		 */
		if (dfp) {
			xfs_dir2_data_freeremove(hdr, bf, dfp, needlogp);
			xfs_dir2_data_freeinsert(hdr, bf, newdup, needlogp);
		}
		/*
		 * Otherwise we need a scan if the new entry is big enough.
		 */
		else {
			needscan = be16_to_cpu(newdup->length) >
				   be16_to_cpu(bf[2].length);
		}
	}
	/*
	 * Neither neighbor is free.  Make a new entry.
	 */
	else {
		newdup = (xfs_dir2_data_unused_t *)((char *)hdr + offset);
		newdup->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG);
		newdup->length = cpu_to_be16(len);
		*xfs_dir2_data_unused_tag_p(newdup) =
			cpu_to_be16((char *)newdup - (char *)hdr);
		xfs_dir2_data_log_unused(args, bp, newdup);
		xfs_dir2_data_freeinsert(hdr, bf, newdup, needlogp);
	}
	*needscanp = needscan;
}

/*
 * Take a byte range out of an existing unused space and make it un-free.
 */
void
xfs_dir2_data_use_free(
	struct xfs_da_args	*args,
	struct xfs_buf		*bp,
	xfs_dir2_data_unused_t	*dup,		/* unused entry */
	xfs_dir2_data_aoff_t	offset,		/* starting offset to use */
	xfs_dir2_data_aoff_t	len,		/* length to use */
	int			*needlogp,	/* out: need to log header */
	int			*needscanp)	/* out: need regen bestfree */
{
	xfs_dir2_data_hdr_t	*hdr;		/* data block header */
	xfs_dir2_data_free_t	*dfp;		/* bestfree pointer */
	int			matchback;	/* matches end of freespace */
	int			matchfront;	/* matches start of freespace */
	int			needscan;	/* need to regen bestfree */
	xfs_dir2_data_unused_t	*newdup;	/* new unused entry */
	xfs_dir2_data_unused_t	*newdup2;	/* another new unused entry */
	int			oldlen;		/* old unused entry's length */
	struct xfs_dir2_data_free *bf;

	hdr = bp->b_addr;
	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
	ASSERT(be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG);
	ASSERT(offset >= (char *)dup - (char *)hdr);
	ASSERT(offset + len <= (char *)dup + be16_to_cpu(dup->length) - (char *)hdr);
	ASSERT((char *)dup - (char *)hdr == be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup)));
	/*
	 * Look up the entry in the bestfree table.
	 */
	oldlen = be16_to_cpu(dup->length);
	bf = args->dp->d_ops->data_bestfree_p(hdr);
	dfp = xfs_dir2_data_freefind(hdr, bf, dup);
	ASSERT(dfp || oldlen <= be16_to_cpu(bf[2].length));
	/*
	 * Check for alignment with front and back of the entry.
	 */
	matchfront = (char *)dup - (char *)hdr == offset;
	matchback = (char *)dup + oldlen - (char *)hdr == offset + len;
	ASSERT(*needscanp == 0);
	needscan = 0;
	/*
	 * If we matched it exactly we just need to get rid of it from
	 * the bestfree table.
	 */
	if (matchfront && matchback) {
		if (dfp) {
			needscan = (bf[2].offset != 0);
			if (!needscan)
				xfs_dir2_data_freeremove(hdr, bf, dfp,
							 needlogp);
		}
	}
	/*
	 * We match the first part of the entry.
	 * Make a new entry with the remaining freespace.
	 */
	else if (matchfront) {
		newdup = (xfs_dir2_data_unused_t *)((char *)hdr + offset + len);
		newdup->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG);
		newdup->length = cpu_to_be16(oldlen - len);
		*xfs_dir2_data_unused_tag_p(newdup) =
			cpu_to_be16((char *)newdup - (char *)hdr);
		xfs_dir2_data_log_unused(args, bp, newdup);
		/*
		 * If it was in the table, remove it and add the new one.
		 */
		if (dfp) {
			xfs_dir2_data_freeremove(hdr, bf, dfp, needlogp);
			dfp = xfs_dir2_data_freeinsert(hdr, bf, newdup,
						       needlogp);
			ASSERT(dfp != NULL);
			ASSERT(dfp->length == newdup->length);
			ASSERT(be16_to_cpu(dfp->offset) == (char *)newdup - (char *)hdr);
			/*
			 * If we got inserted at the last slot,
			 * that means we don't know if there was a better
			 * choice for the last slot, or not.  Rescan.
			 */
			needscan = dfp == &bf[2];
		}
	}
	/*
	 * We match the last part of the entry.
	 * Trim the allocated space off the tail of the entry.
	 */
	else if (matchback) {
		newdup = dup;
		newdup->length = cpu_to_be16(((char *)hdr + offset) - (char *)newdup);
		*xfs_dir2_data_unused_tag_p(newdup) =
			cpu_to_be16((char *)newdup - (char *)hdr);
		xfs_dir2_data_log_unused(args, bp, newdup);
		/*
		 * If it was in the table, remove it and add the new one.
		 */
		if (dfp) {
			xfs_dir2_data_freeremove(hdr, bf, dfp, needlogp);
			dfp = xfs_dir2_data_freeinsert(hdr, bf, newdup,
						       needlogp);
			ASSERT(dfp != NULL);
			ASSERT(dfp->length == newdup->length);
			ASSERT(be16_to_cpu(dfp->offset) == (char *)newdup - (char *)hdr);
			/*
			 * If we got inserted at the last slot,
			 * that means we don't know if there was a better
			 * choice for the last slot, or not.  Rescan.
			 */
			needscan = dfp == &bf[2];
		}
	}
	/*
	 * Poking out the middle of an entry.
	 * Make two new entries.
	 */
	else {
		newdup = dup;
		newdup->length = cpu_to_be16(((char *)hdr + offset) - (char *)newdup);
		*xfs_dir2_data_unused_tag_p(newdup) =
			cpu_to_be16((char *)newdup - (char *)hdr);
		xfs_dir2_data_log_unused(args, bp, newdup);
		newdup2 = (xfs_dir2_data_unused_t *)((char *)hdr + offset + len);
		newdup2->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG);
		newdup2->length = cpu_to_be16(oldlen - len - be16_to_cpu(newdup->length));
		*xfs_dir2_data_unused_tag_p(newdup2) =
			cpu_to_be16((char *)newdup2 - (char *)hdr);
		xfs_dir2_data_log_unused(args, bp, newdup2);
		/*
		 * If the old entry was in the table, we need to scan
		 * if the 3rd entry was valid, since these entries
		 * are smaller than the old one.
		 * If we don't need to scan that means there were 1 or 2
		 * entries in the table, and removing the old and adding
		 * the 2 new will work.
		 */
		if (dfp) {
			needscan = (bf[2].length != 0);
			if (!needscan) {
				xfs_dir2_data_freeremove(hdr, bf, dfp,
							 needlogp);
				xfs_dir2_data_freeinsert(hdr, bf, newdup,
							 needlogp);
				xfs_dir2_data_freeinsert(hdr, bf, newdup2,
							 needlogp);
			}
		}
	}
	*needscanp = needscan;
}