aboutsummaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_dir2_block.c
blob: d2e445f92ffb0fa189aff66c20ff3397e704f730 (plain) (blame)
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
/*
 * Copyright (c) 2000-2003,2005 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_types.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_da_btree.h"
#include "xfs_bmap_btree.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_inode_item.h"
#include "xfs_buf_item.h"
#include "xfs_dir2.h"
#include "xfs_dir2_format.h"
#include "xfs_dir2_priv.h"
#include "xfs_error.h"
#include "xfs_trace.h"
#include "xfs_cksum.h"

/*
 * Local function prototypes.
 */
static void xfs_dir2_block_log_leaf(xfs_trans_t *tp, struct xfs_buf *bp,
				    int first, int last);
static void xfs_dir2_block_log_tail(xfs_trans_t *tp, struct xfs_buf *bp);
static int xfs_dir2_block_lookup_int(xfs_da_args_t *args, struct xfs_buf **bpp,
				     int *entno);
static int xfs_dir2_block_sort(const void *a, const void *b);

static xfs_dahash_t xfs_dir_hash_dot, xfs_dir_hash_dotdot;

/*
 * One-time startup routine called from xfs_init().
 */
void
xfs_dir_startup(void)
{
	xfs_dir_hash_dot = xfs_da_hashname((unsigned char *)".", 1);
	xfs_dir_hash_dotdot = xfs_da_hashname((unsigned char *)"..", 2);
}

static bool
xfs_dir3_block_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_BLOCK_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_BLOCK_MAGIC))
			return false;
	}
	if (__xfs_dir3_data_check(NULL, bp))
		return false;
	return true;
}

static void
xfs_dir3_block_read_verify(
	struct xfs_buf	*bp)
{
	struct xfs_mount	*mp = bp->b_target->bt_mount;

	if ((xfs_sb_version_hascrc(&mp->m_sb) &&
	     !xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
					  XFS_DIR3_DATA_CRC_OFF)) ||
	    !xfs_dir3_block_verify(bp)) {
		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
		xfs_buf_ioerror(bp, EFSCORRUPTED);
	}
}

static void
xfs_dir3_block_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_block_verify(bp)) {
		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
		xfs_buf_ioerror(bp, EFSCORRUPTED);
		return;
	}

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

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

	xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length), XFS_DIR3_DATA_CRC_OFF);
}

const struct xfs_buf_ops xfs_dir3_block_buf_ops = {
	.verify_read = xfs_dir3_block_read_verify,
	.verify_write = xfs_dir3_block_write_verify,
};

static int
xfs_dir3_block_read(
	struct xfs_trans	*tp,
	struct xfs_inode	*dp,
	struct xfs_buf		**bpp)
{
	struct xfs_mount	*mp = dp->i_mount;

	return xfs_da_read_buf(tp, dp, mp->m_dirdatablk, -1, bpp,
				XFS_DATA_FORK, &xfs_dir3_block_buf_ops);
}

static void
xfs_dir3_block_init(
	struct xfs_mount	*mp,
	struct xfs_buf		*bp,
	struct xfs_inode	*dp)
{
	struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;

	bp->b_ops = &xfs_dir3_block_buf_ops;

	if (xfs_sb_version_hascrc(&mp->m_sb)) {
		memset(hdr3, 0, sizeof(*hdr3));
		hdr3->magic = cpu_to_be32(XFS_DIR3_BLOCK_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);
		return;

	}
	hdr3->magic = cpu_to_be32(XFS_DIR2_BLOCK_MAGIC);
}

static void
xfs_dir2_block_need_space(
	struct xfs_dir2_data_hdr	*hdr,
	struct xfs_dir2_block_tail	*btp,
	struct xfs_dir2_leaf_entry	*blp,
	__be16				**tagpp,
	struct xfs_dir2_data_unused	**dupp,
	struct xfs_dir2_data_unused	**enddupp,
	int				*compact,
	int				len)
{
	struct xfs_dir2_data_free	*bf;
	__be16				*tagp = NULL;
	struct xfs_dir2_data_unused	*dup = NULL;
	struct xfs_dir2_data_unused	*enddup = NULL;

	*compact = 0;
	bf = xfs_dir3_data_bestfree_p(hdr);

	/*
	 * If there are stale entries we'll use one for the leaf.
	 */
	if (btp->stale) {
		if (be16_to_cpu(bf[0].length) >= len) {
			/*
			 * The biggest entry enough to avoid compaction.
			 */
			dup = (xfs_dir2_data_unused_t *)
			      ((char *)hdr + be16_to_cpu(bf[0].offset));
			goto out;
		}

		/*
		 * Will need to compact to make this work.
		 * Tag just before the first leaf entry.
		 */
		*compact = 1;
		tagp = (__be16 *)blp - 1;

		/* Data object just before the first leaf entry.  */
		dup = (xfs_dir2_data_unused_t *)((char *)hdr + be16_to_cpu(*tagp));

		/*
		 * If it's not free then the data will go where the
		 * leaf data starts now, if it works at all.
		 */
		if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
			if (be16_to_cpu(dup->length) + (be32_to_cpu(btp->stale) - 1) *
			    (uint)sizeof(*blp) < len)
				dup = NULL;
		} else if ((be32_to_cpu(btp->stale) - 1) * (uint)sizeof(*blp) < len)
			dup = NULL;
		else
			dup = (xfs_dir2_data_unused_t *)blp;
		goto out;
	}

	/*
	 * no stale entries, so just use free space.
	 * Tag just before the first leaf entry.
	 */
	tagp = (__be16 *)blp - 1;

	/* Data object just before the first leaf entry.  */
	enddup = (xfs_dir2_data_unused_t *)((char *)hdr + be16_to_cpu(*tagp));

	/*
	 * If it's not free then can't do this add without cleaning up:
	 * the space before the first leaf entry needs to be free so it
	 * can be expanded to hold the pointer to the new entry.
	 */
	if (be16_to_cpu(enddup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
		/*
		 * Check out the biggest freespace and see if it's the same one.
		 */
		dup = (xfs_dir2_data_unused_t *)
		      ((char *)hdr + be16_to_cpu(bf[0].offset));
		if (dup != enddup) {
			/*
			 * Not the same free entry, just check its length.
			 */
			if (be16_to_cpu(dup->length) < len)
				dup = NULL;
			goto out;
		}

		/*
		 * It is the biggest freespace, can it hold the leaf too?
		 */
		if (be16_to_cpu(dup->length) < len + (uint)sizeof(*blp)) {
			/*
			 * Yes, use the second-largest entry instead if it works.
			 */
			if (be16_to_cpu(bf[1].length) >= len)
				dup = (xfs_dir2_data_unused_t *)
				      ((char *)hdr + be16_to_cpu(bf[1].offset));
			else
				dup = NULL;
		}
	}
out:
	*tagpp = tagp;
	*dupp = dup;
	*enddupp = enddup;
}

/*
 * compact the leaf entries.
 * Leave the highest-numbered stale entry stale.
 * XXX should be the one closest to mid but mid is not yet computed.
 */
static void
xfs_dir2_block_compact(
	struct xfs_trans		*tp,
	struct xfs_buf			*bp,
	struct xfs_dir2_data_hdr	*hdr,
	struct xfs_dir2_block_tail	*btp,
	struct xfs_dir2_leaf_entry	*blp,
	int				*needlog,
	int				*lfloghigh,
	int				*lfloglow)
{
	int			fromidx;	/* source leaf index */
	int			toidx;		/* target leaf index */
	int			needscan = 0;
	int			highstale;	/* high stale index */

	fromidx = toidx = be32_to_cpu(btp->count) - 1;
	highstale = *lfloghigh = -1;
	for (; fromidx >= 0; fromidx--) {
		if (blp[fromidx].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR)) {
			if (highstale == -1)
				highstale = toidx;
			else {
				if (*lfloghigh == -1)
					*lfloghigh = toidx;
				continue;
			}
		}
		if (fromidx < toidx)
			blp[toidx] = blp[fromidx];
		toidx--;
	}
	*lfloglow = toidx + 1 - (be32_to_cpu(btp->stale) - 1);
	*lfloghigh -= be32_to_cpu(btp->stale) - 1;
	be32_add_cpu(&btp->count, -(be32_to_cpu(btp->stale) - 1));
	xfs_dir2_data_make_free(tp, bp,
		(xfs_dir2_data_aoff_t)((char *)blp - (char *)hdr),
		(xfs_dir2_data_aoff_t)((be32_to_cpu(btp->stale) - 1) * sizeof(*blp)),
		needlog, &needscan);
	blp += be32_to_cpu(btp->stale) - 1;
	btp->stale = cpu_to_be32(1);
	/*
	 * If we now need to rebuild the bestfree map, do so.
	 * This needs to happen before the next call to use_free.
	 */
	if (needscan)
		xfs_dir2_data_freescan(tp->t_mountp, hdr, needlog);
}

/*
 * Add an entry to a block directory.
 */
int						/* error */
xfs_dir2_block_addname(
	xfs_da_args_t		*args)		/* directory op arguments */
{
	xfs_dir2_data_hdr_t	*hdr;		/* block header */
	xfs_dir2_leaf_entry_t	*blp;		/* block leaf entries */
	struct xfs_buf		*bp;		/* buffer for block */
	xfs_dir2_block_tail_t	*btp;		/* block tail */
	int			compact;	/* need to compact leaf ents */
	xfs_dir2_data_entry_t	*dep;		/* block data entry */
	xfs_inode_t		*dp;		/* directory inode */
	xfs_dir2_data_unused_t	*dup;		/* block unused entry */
	int			error;		/* error return value */
	xfs_dir2_data_unused_t	*enddup=NULL;	/* unused at end of data */
	xfs_dahash_t		hash;		/* hash value of found entry */
	int			high;		/* high index for binary srch */
	int			highstale;	/* high stale index */
	int			lfloghigh=0;	/* last final leaf to log */
	int			lfloglow=0;	/* first final leaf to log */
	int			len;		/* length of the new entry */
	int			low;		/* low index for binary srch */
	int			lowstale;	/* low stale index */
	int			mid=0;		/* midpoint for binary srch */
	xfs_mount_t		*mp;		/* filesystem mount point */
	int			needlog;	/* need to log header */
	int			needscan;	/* need to rescan freespace */
	__be16			*tagp;		/* pointer to tag value */
	xfs_trans_t		*tp;		/* transaction structure */

	trace_xfs_dir2_block_addname(args);

	dp = args->dp;
	tp = args->trans;
	mp = dp->i_mount;

	/* Read the (one and only) directory block into bp. */
	error = xfs_dir3_block_read(tp, dp, &bp);
	if (error)
		return error;

	len = xfs_dir2_data_entsize(args->namelen);

	/*
	 * Set up pointers to parts of the block.
	 */
	hdr = bp->b_addr;
	btp = xfs_dir2_block_tail_p(mp, hdr);
	blp = xfs_dir2_block_leaf_p(btp);

	/*
	 * Find out if we can reuse stale entries or whether we need extra
	 * space for entry and new leaf.
	 */
	xfs_dir2_block_need_space(hdr, btp, blp, &tagp, &dup,
				  &enddup, &compact, len);

	/*
	 * Done everything we need for a space check now.
	 */
	if (args->op_flags & XFS_DA_OP_JUSTCHECK) {
		xfs_trans_brelse(tp, bp);
		if (!dup)
			return XFS_ERROR(ENOSPC);
		return 0;
	}

	/*
	 * If we don't have space for the new entry & leaf ...
	 */
	if (!dup) {
		/* Don't have a space reservation: return no-space.  */
		if (args->total == 0)
			return XFS_ERROR(ENOSPC);
		/*
		 * Convert to the next larger format.
		 * Then add the new entry in that format.
		 */
		error = xfs_dir2_block_to_leaf(args, bp);
		if (error)
			return error;
		return xfs_dir2_leaf_addname(args);
	}

	needlog = needscan = 0;

	/*
	 * If need to compact the leaf entries, do it now.
	 */
	if (compact) {
		xfs_dir2_block_compact(tp, bp, hdr, btp, blp, &needlog,
				      &lfloghigh, &lfloglow);
		/* recalculate blp post-compaction */
		blp = xfs_dir2_block_leaf_p(btp);
	} else if (btp->stale) {
		/*
		 * Set leaf logging boundaries to impossible state.
		 * For the no-stale case they're set explicitly.
		 */
		lfloglow = be32_to_cpu(btp->count);
		lfloghigh = -1;
	}

	/*
	 * Find the slot that's first lower than our hash value, -1 if none.
	 */
	for (low = 0, high = be32_to_cpu(btp->count) - 1; low <= high; ) {
		mid = (low + high) >> 1;
		if ((hash = be32_to_cpu(blp[mid].hashval)) == args->hashval)
			break;
		if (hash < args->hashval)
			low = mid + 1;
		else
			high = mid - 1;
	}
	while (mid >= 0 && be32_to_cpu(blp[mid].hashval) >= args->hashval) {
		mid--;
	}
	/*
	 * No stale entries, will use enddup space to hold new leaf.
	 */
	if (!btp->stale) {
		/*
		 * Mark the space needed for the new leaf entry, now in use.
		 */
		xfs_dir2_data_use_free(tp, bp, enddup,
			(xfs_dir2_data_aoff_t)
			((char *)enddup - (char *)hdr + be16_to_cpu(enddup->length) -
			 sizeof(*blp)),
			(xfs_dir2_data_aoff_t)sizeof(*blp),
			&needlog, &needscan);
		/*
		 * Update the tail (entry count).
		 */
		be32_add_cpu(&btp->count, 1);
		/*
		 * If we now need to rebuild the bestfree map, do so.
		 * This needs to happen before the next call to use_free.
		 */
		if (needscan) {
			xfs_dir2_data_freescan(mp, hdr, &needlog);
			needscan = 0;
		}
		/*
		 * Adjust pointer to the first leaf entry, we're about to move
		 * the table up one to open up space for the new leaf entry.
		 * Then adjust our index to match.
		 */
		blp--;
		mid++;
		if (mid)
			memmove(blp, &blp[1], mid * sizeof(*blp));
		lfloglow = 0;
		lfloghigh = mid;
	}
	/*
	 * Use a stale leaf for our new entry.
	 */
	else {
		for (lowstale = mid;
		     lowstale >= 0 &&
			blp[lowstale].address !=
			cpu_to_be32(XFS_DIR2_NULL_DATAPTR);
		     lowstale--)
			continue;
		for (highstale = mid + 1;
		     highstale < be32_to_cpu(btp->count) &&
			blp[highstale].address !=
			cpu_to_be32(XFS_DIR2_NULL_DATAPTR) &&
			(lowstale < 0 || mid - lowstale > highstale - mid);
		     highstale++)
			continue;
		/*
		 * Move entries toward the low-numbered stale entry.
		 */
		if (lowstale >= 0 &&
		    (highstale == be32_to_cpu(btp->count) ||
		     mid - lowstale <= highstale - mid)) {
			if (mid - lowstale)
				memmove(&blp[lowstale], &blp[lowstale + 1],
					(mid - lowstale) * sizeof(*blp));
			lfloglow = MIN(lowstale, lfloglow);
			lfloghigh = MAX(mid, lfloghigh);
		}
		/*
		 * Move entries toward the high-numbered stale entry.
		 */
		else {
			ASSERT(highstale < be32_to_cpu(btp->count));
			mid++;
			if (highstale - mid)
				memmove(&blp[mid + 1], &blp[mid],
					(highstale - mid) * sizeof(*blp));
			lfloglow = MIN(mid, lfloglow);
			lfloghigh = MAX(highstale, lfloghigh);
		}
		be32_add_cpu(&btp->stale, -1);
	}
	/*
	 * Point to the new data entry.
	 */
	dep = (xfs_dir2_data_entry_t *)dup;
	/*
	 * Fill in the leaf entry.
	 */
	blp[mid].hashval = cpu_to_be32(args->hashval);
	blp[mid].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
				(char *)dep - (char *)hdr));
	xfs_dir2_block_log_leaf(tp, bp, lfloglow, lfloghigh);
	/*
	 * Mark space for the data entry used.
	 */
	xfs_dir2_data_use_free(tp, bp, dup,
		(xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr),
		(xfs_dir2_data_aoff_t)len, &needlog, &needscan);
	/*
	 * Create the new data entry.
	 */
	dep->inumber = cpu_to_be64(args->inumber);
	dep->namelen = args->namelen;
	memcpy(dep->name, args->name, args->namelen);
	tagp = xfs_dir2_data_entry_tag_p(dep);
	*tagp = cpu_to_be16((char *)dep - (char *)hdr);
	/*
	 * Clean up the bestfree array and log the header, tail, and entry.
	 */
	if (needscan)
		xfs_dir2_data_freescan(mp, hdr, &needlog);
	if (needlog)
		xfs_dir2_data_log_header(tp, bp);
	xfs_dir2_block_log_tail(tp, bp);
	xfs_dir2_data_log_entry(tp, bp, dep);
	xfs_dir3_data_check(dp, bp);
	return 0;
}

/*
 * Readdir for block directories.
 */
int						/* error */
xfs_dir2_block_getdents(
	xfs_inode_t		*dp,		/* incore inode */
	void			*dirent,
	xfs_off_t		*offset,
	filldir_t		filldir)
{
	xfs_dir2_data_hdr_t	*hdr;		/* block header */
	struct xfs_buf		*bp;		/* buffer for block */
	xfs_dir2_block_tail_t	*btp;		/* block tail */
	xfs_dir2_data_entry_t	*dep;		/* block data entry */
	xfs_dir2_data_unused_t	*dup;		/* block unused entry */
	char			*endptr;	/* end of the data entries */
	int			error;		/* error return value */
	xfs_mount_t		*mp;		/* filesystem mount point */
	char			*ptr;		/* current data entry */
	int			wantoff;	/* starting block offset */
	xfs_off_t		cook;

	mp = dp->i_mount;
	/*
	 * If the block number in the offset is out of range, we're done.
	 */
	if (xfs_dir2_dataptr_to_db(mp, *offset) > mp->m_dirdatablk)
		return 0;

	error = xfs_dir3_block_read(NULL, dp, &bp);
	if (error)
		return error;

	/*
	 * Extract the byte offset we start at from the seek pointer.
	 * We'll skip entries before this.
	 */
	wantoff = xfs_dir2_dataptr_to_off(mp, *offset);
	hdr = bp->b_addr;
	xfs_dir3_data_check(dp, bp);
	/*
	 * Set up values for the loop.
	 */
	btp = xfs_dir2_block_tail_p(mp, hdr);
	ptr = (char *)xfs_dir3_data_entry_p(hdr);
	endptr = (char *)xfs_dir2_block_leaf_p(btp);

	/*
	 * Loop over the data portion of the block.
	 * Each object is a real entry (dep) or an unused one (dup).
	 */
	while (ptr < endptr) {
		dup = (xfs_dir2_data_unused_t *)ptr;
		/*
		 * Unused, skip it.
		 */
		if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
			ptr += be16_to_cpu(dup->length);
			continue;
		}

		dep = (xfs_dir2_data_entry_t *)ptr;

		/*
		 * Bump pointer for the next iteration.
		 */
		ptr += xfs_dir2_data_entsize(dep->namelen);
		/*
		 * The entry is before the desired starting point, skip it.
		 */
		if ((char *)dep - (char *)hdr < wantoff)
			continue;

		cook = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk,
					    (char *)dep - (char *)hdr);

		/*
		 * If it didn't fit, set the final offset to here & return.
		 */
		if (filldir(dirent, (char *)dep->name, dep->namelen,
			    cook & 0x7fffffff, be64_to_cpu(dep->inumber),
			    DT_UNKNOWN)) {
			*offset = cook & 0x7fffffff;
			xfs_trans_brelse(NULL, bp);
			return 0;
		}
	}

	/*
	 * Reached the end of the block.
	 * Set the offset to a non-existent block 1 and return.
	 */
	*offset = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk + 1, 0) &
			0x7fffffff;
	xfs_trans_brelse(NULL, bp);
	return 0;
}

/*
 * Log leaf entries from the block.
 */
static void
xfs_dir2_block_log_leaf(
	xfs_trans_t		*tp,		/* transaction structure */
	struct xfs_buf		*bp,		/* block buffer */
	int			first,		/* index of first logged leaf */
	int			last)		/* index of last logged leaf */
{
	xfs_dir2_data_hdr_t	*hdr = bp->b_addr;
	xfs_dir2_leaf_entry_t	*blp;
	xfs_dir2_block_tail_t	*btp;

	btp = xfs_dir2_block_tail_p(tp->t_mountp, hdr);
	blp = xfs_dir2_block_leaf_p(btp);
	xfs_trans_log_buf(tp, bp, (uint)((char *)&blp[first] - (char *)hdr),
		(uint)((char *)&blp[last + 1] - (char *)hdr - 1));
}

/*
 * Log the block tail.
 */
static void
xfs_dir2_block_log_tail(
	xfs_trans_t		*tp,		/* transaction structure */
	struct xfs_buf		*bp)		/* block buffer */
{
	xfs_dir2_data_hdr_t	*hdr = bp->b_addr;
	xfs_dir2_block_tail_t	*btp;

	btp = xfs_dir2_block_tail_p(tp->t_mountp, hdr);
	xfs_trans_log_buf(tp, bp, (uint)((char *)btp - (char *)hdr),
		(uint)((char *)(btp + 1) - (char *)hdr - 1));
}

/*
 * Look up an entry in the block.  This is the external routine,
 * xfs_dir2_block_lookup_int does the real work.
 */
int						/* error */
xfs_dir2_block_lookup(
	xfs_da_args_t		*args)		/* dir lookup arguments */
{
	xfs_dir2_data_hdr_t	*hdr;		/* block header */
	xfs_dir2_leaf_entry_t	*blp;		/* block leaf entries */
	struct xfs_buf		*bp;		/* block buffer */
	xfs_dir2_block_tail_t	*btp;		/* block tail */
	xfs_dir2_data_entry_t	*dep;		/* block data entry */
	xfs_inode_t		*dp;		/* incore inode */
	int			ent;		/* entry index */
	int			error;		/* error return value */
	xfs_mount_t		*mp;		/* filesystem mount point */

	trace_xfs_dir2_block_lookup(args);

	/*
	 * Get the buffer, look up the entry.
	 * If not found (ENOENT) then return, have no buffer.
	 */
	if ((error = xfs_dir2_block_lookup_int(args, &bp, &ent)))
		return error;
	dp = args->dp;
	mp = dp->i_mount;
	hdr = bp->b_addr;
	xfs_dir3_data_check(dp, bp);
	btp = xfs_dir2_block_tail_p(mp, hdr);
	blp = xfs_dir2_block_leaf_p(btp);
	/*
	 * Get the offset from the leaf entry, to point to the data.
	 */
	dep = (xfs_dir2_data_entry_t *)((char *)hdr +
		xfs_dir2_dataptr_to_off(mp, be32_to_cpu(blp[ent].address)));
	/*
	 * Fill in inode number, CI name if appropriate, release the block.
	 */
	args->inumber = be64_to_cpu(dep->inumber);
	error = xfs_dir_cilookup_result(args, dep->name, dep->namelen);
	xfs_trans_brelse(args->trans, bp);
	return XFS_ERROR(error);
}

/*
 * Internal block lookup routine.
 */
static int					/* error */
xfs_dir2_block_lookup_int(
	xfs_da_args_t		*args,		/* dir lookup arguments */
	struct xfs_buf		**bpp,		/* returned block buffer */
	int			*entno)		/* returned entry number */
{
	xfs_dir2_dataptr_t	addr;		/* data entry address */
	xfs_dir2_data_hdr_t	*hdr;		/* block header */
	xfs_dir2_leaf_entry_t	*blp;		/* block leaf entries */
	struct xfs_buf		*bp;		/* block buffer */
	xfs_dir2_block_tail_t	*btp;		/* block tail */
	xfs_dir2_data_entry_t	*dep;		/* block data entry */
	xfs_inode_t		*dp;		/* incore inode */
	int			error;		/* error return value */
	xfs_dahash_t		hash;		/* found hash value */
	int			high;		/* binary search high index */
	int			low;		/* binary search low index */
	int			mid;		/* binary search current idx */
	xfs_mount_t		*mp;		/* filesystem mount point */
	xfs_trans_t		*tp;		/* transaction pointer */
	enum xfs_dacmp		cmp;		/* comparison result */

	dp = args->dp;
	tp = args->trans;
	mp = dp->i_mount;

	error = xfs_dir3_block_read(tp, dp, &bp);
	if (error)
		return error;

	hdr = bp->b_addr;
	xfs_dir3_data_check(dp, bp);
	btp = xfs_dir2_block_tail_p(mp, hdr);
	blp = xfs_dir2_block_leaf_p(btp);
	/*
	 * Loop doing a binary search for our hash value.
	 * Find our entry, ENOENT if it's not there.
	 */
	for (low = 0, high = be32_to_cpu(btp->count) - 1; ; ) {
		ASSERT(low <= high);
		mid = (low + high) >> 1;
		if ((hash = be32_to_cpu(blp[mid].hashval)) == args->hashval)
			break;
		if (hash < args->hashval)
			low = mid + 1;
		else
			high = mid - 1;
		if (low > high) {
			ASSERT(args->op_flags & XFS_DA_OP_OKNOENT);
			xfs_trans_brelse(tp, bp);
			return XFS_ERROR(ENOENT);
		}
	}
	/*
	 * Back up to the first one with the right hash value.
	 */
	while (mid > 0 && be32_to_cpu(blp[mid - 1].hashval) == args->hashval) {
		mid--;
	}
	/*
	 * Now loop forward through all the entries with the
	 * right hash value looking for our name.
	 */
	do {
		if ((addr = be32_to_cpu(blp[mid].address)) == XFS_DIR2_NULL_DATAPTR)
			continue;
		/*
		 * Get pointer to the entry from the leaf.
		 */
		dep = (xfs_dir2_data_entry_t *)
			((char *)hdr + xfs_dir2_dataptr_to_off(mp, addr));
		/*
		 * Compare name and if it's an exact match, return the index
		 * and buffer. If it's the first case-insensitive match, store
		 * the index and buffer and continue looking for an exact match.
		 */
		cmp = mp->m_dirnameops->compname(args, dep->name, dep->namelen);
		if (cmp != XFS_CMP_DIFFERENT && cmp != args->cmpresult) {
			args->cmpresult = cmp;
			*bpp = bp;
			*entno = mid;
			if (cmp == XFS_CMP_EXACT)
				return 0;
		}
	} while (++mid < be32_to_cpu(btp->count) &&
			be32_to_cpu(blp[mid].hashval) == hash);

	ASSERT(args->op_flags & XFS_DA_OP_OKNOENT);
	/*
	 * Here, we can only be doing a lookup (not a rename or replace).
	 * If a case-insensitive match was found earlier, return success.
	 */
	if (args->cmpresult == XFS_CMP_CASE)
		return 0;
	/*
	 * No match, release the buffer and return ENOENT.
	 */
	xfs_trans_brelse(tp, bp);
	return XFS_ERROR(ENOENT);
}

/*
 * Remove an entry from a block format directory.
 * If that makes the block small enough to fit in shortform, transform it.
 */
int						/* error */
xfs_dir2_block_removename(
	xfs_da_args_t		*args)		/* directory operation args */
{
	xfs_dir2_data_hdr_t	*hdr;		/* block header */
	xfs_dir2_leaf_entry_t	*blp;		/* block leaf pointer */
	struct xfs_buf		*bp;		/* block buffer */
	xfs_dir2_block_tail_t	*btp;		/* block tail */
	xfs_dir2_data_entry_t	*dep;		/* block data entry */
	xfs_inode_t		*dp;		/* incore inode */
	int			ent;		/* block leaf entry index */
	int			error;		/* error return value */
	xfs_mount_t		*mp;		/* filesystem mount point */
	int			needlog;	/* need to log block header */
	int			needscan;	/* need to fixup bestfree */
	xfs_dir2_sf_hdr_t	sfh;		/* shortform header */
	int			size;		/* shortform size */
	xfs_trans_t		*tp;		/* transaction pointer */

	trace_xfs_dir2_block_removename(args);

	/*
	 * Look up the entry in the block.  Gets the buffer and entry index.
	 * It will always be there, the vnodeops level does a lookup first.
	 */
	if ((error = xfs_dir2_block_lookup_int(args, &bp, &ent))) {
		return error;
	}
	dp = args->dp;
	tp = args->trans;
	mp = dp->i_mount;
	hdr = bp->b_addr;
	btp = xfs_dir2_block_tail_p(mp, hdr);
	blp = xfs_dir2_block_leaf_p(btp);
	/*
	 * Point to the data entry using the leaf entry.
	 */
	dep = (xfs_dir2_data_entry_t *)
	      ((char *)hdr + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(blp[ent].address)));
	/*
	 * Mark the data entry's space free.
	 */
	needlog = needscan = 0;
	xfs_dir2_data_make_free(tp, bp,
		(xfs_dir2_data_aoff_t)((char *)dep - (char *)hdr),
		xfs_dir2_data_entsize(dep->namelen), &needlog, &needscan);
	/*
	 * Fix up the block tail.
	 */
	be32_add_cpu(&btp->stale, 1);
	xfs_dir2_block_log_tail(tp, bp);
	/*
	 * Remove the leaf entry by marking it stale.
	 */
	blp[ent].address = cpu_to_be32(XFS_DIR2_NULL_DATAPTR);
	xfs_dir2_block_log_leaf(tp, bp, ent, ent);
	/*
	 * Fix up bestfree, log the header if necessary.
	 */
	if (needscan)
		xfs_dir2_data_freescan(mp, hdr, &needlog);
	if (needlog)
		xfs_dir2_data_log_header(tp, bp);
	xfs_dir3_data_check(dp, bp);
	/*
	 * See if the size as a shortform is good enough.
	 */
	size = xfs_dir2_block_sfsize(dp, hdr, &sfh);
	if (size > XFS_IFORK_DSIZE(dp))
		return 0;

	/*
	 * If it works, do the conversion.
	 */
	return xfs_dir2_block_to_sf(args, bp, size, &sfh);
}

/*
 * Replace an entry in a V2 block directory.
 * Change the inode number to the new value.
 */
int						/* error */
xfs_dir2_block_replace(
	xfs_da_args_t		*args)		/* directory operation args */
{
	xfs_dir2_data_hdr_t	*hdr;		/* block header */
	xfs_dir2_leaf_entry_t	*blp;		/* block leaf entries */
	struct xfs_buf		*bp;		/* block buffer */
	xfs_dir2_block_tail_t	*btp;		/* block tail */
	xfs_dir2_data_entry_t	*dep;		/* block data entry */
	xfs_inode_t		*dp;		/* incore inode */
	int			ent;		/* leaf entry index */
	int			error;		/* error return value */
	xfs_mount_t		*mp;		/* filesystem mount point */

	trace_xfs_dir2_block_replace(args);

	/*
	 * Lookup the entry in the directory.  Get buffer and entry index.
	 * This will always succeed since the caller has already done a lookup.
	 */
	if ((error = xfs_dir2_block_lookup_int(args, &bp, &ent))) {
		return error;
	}
	dp = args->dp;
	mp = dp->i_mount;
	hdr = bp->b_addr;
	btp = xfs_dir2_block_tail_p(mp, hdr);
	blp = xfs_dir2_block_leaf_p(btp);
	/*
	 * Point to the data entry we need to change.
	 */
	dep = (xfs_dir2_data_entry_t *)
	      ((char *)hdr + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(blp[ent].address)));
	ASSERT(be64_to_cpu(dep->inumber) != args->inumber);
	/*
	 * Change the inode number to the new value.
	 */
	dep->inumber = cpu_to_be64(args->inumber);
	xfs_dir2_data_log_entry(args->trans, bp, dep);
	xfs_dir3_data_check(dp, bp);
	return 0;
}

/*
 * Qsort comparison routine for the block leaf entries.
 */
static int					/* sort order */
xfs_dir2_block_sort(
	const void			*a,	/* first leaf entry */
	const void			*b)	/* second leaf entry */
{
	const xfs_dir2_leaf_entry_t	*la;	/* first leaf entry */
	const xfs_dir2_leaf_entry_t	*lb;	/* second leaf entry */

	la = a;
	lb = b;
	return be32_to_cpu(la->hashval) < be32_to_cpu(lb->hashval) ? -1 :
		(be32_to_cpu(la->hashval) > be32_to_cpu(lb->hashval) ? 1 : 0);
}

/*
 * Convert a V2 leaf directory to a V2 block directory if possible.
 */
int						/* error */
xfs_dir2_leaf_to_block(
	xfs_da_args_t		*args,		/* operation arguments */
	struct xfs_buf		*lbp,		/* leaf buffer */
	struct xfs_buf		*dbp)		/* data buffer */
{
	__be16			*bestsp;	/* leaf bests table */
	xfs_dir2_data_hdr_t	*hdr;		/* block header */
	xfs_dir2_block_tail_t	*btp;		/* block tail */
	xfs_inode_t		*dp;		/* incore directory inode */
	xfs_dir2_data_unused_t	*dup;		/* unused data entry */
	int			error;		/* error return value */
	int			from;		/* leaf from index */
	xfs_dir2_leaf_t		*leaf;		/* leaf structure */
	xfs_dir2_leaf_entry_t	*lep;		/* leaf entry */
	xfs_dir2_leaf_tail_t	*ltp;		/* leaf tail structure */
	xfs_mount_t		*mp;		/* file system mount point */
	int			needlog;	/* need to log data header */
	int			needscan;	/* need to scan for bestfree */
	xfs_dir2_sf_hdr_t	sfh;		/* shortform header */
	int			size;		/* bytes used */
	__be16			*tagp;		/* end of entry (tag) */
	int			to;		/* block/leaf to index */
	xfs_trans_t		*tp;		/* transaction pointer */
	struct xfs_dir2_leaf_entry *ents;
	struct xfs_dir3_icleaf_hdr leafhdr;

	trace_xfs_dir2_leaf_to_block(args);

	dp = args->dp;
	tp = args->trans;
	mp = dp->i_mount;
	leaf = lbp->b_addr;
	xfs_dir3_leaf_hdr_from_disk(&leafhdr, leaf);
	ents = xfs_dir3_leaf_ents_p(leaf);
	ltp = xfs_dir2_leaf_tail_p(mp, leaf);

	ASSERT(leafhdr.magic == XFS_DIR2_LEAF1_MAGIC ||
	       leafhdr.magic == XFS_DIR3_LEAF1_MAGIC);
	/*
	 * If there are data blocks other than the first one, take this
	 * opportunity to remove trailing empty data blocks that may have
	 * been left behind during no-space-reservation operations.
	 * These will show up in the leaf bests table.
	 */
	while (dp->i_d.di_size > mp->m_dirblksize) {
		int hdrsz;

		hdrsz = xfs_dir3_data_hdr_size(xfs_sb_version_hascrc(&mp->m_sb));
		bestsp = xfs_dir2_leaf_bests_p(ltp);
		if (be16_to_cpu(bestsp[be32_to_cpu(ltp->bestcount) - 1]) ==
					    mp->m_dirblksize - hdrsz) {
			if ((error =
			    xfs_dir2_leaf_trim_data(args, lbp,
				    (xfs_dir2_db_t)(be32_to_cpu(ltp->bestcount) - 1))))
				return error;
		} else
			return 0;
	}
	/*
	 * Read the data block if we don't already have it, give up if it fails.
	 */
	if (!dbp) {
		error = xfs_dir3_data_read(tp, dp, mp->m_dirdatablk, -1, &dbp);
		if (error)
			return error;
	}
	hdr = dbp->b_addr;
	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
	       hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC));

	/*
	 * Size of the "leaf" area in the block.
	 */
	size = (uint)sizeof(xfs_dir2_block_tail_t) +
	       (uint)sizeof(*lep) * (leafhdr.count - leafhdr.stale);
	/*
	 * Look at the last data entry.
	 */
	tagp = (__be16 *)((char *)hdr + mp->m_dirblksize) - 1;
	dup = (xfs_dir2_data_unused_t *)((char *)hdr + be16_to_cpu(*tagp));
	/*
	 * If it's not free or is too short we can't do it.
	 */
	if (be16_to_cpu(dup->freetag) != XFS_DIR2_DATA_FREE_TAG ||
	    be16_to_cpu(dup->length) < size)
		return 0;

	/*
	 * Start converting it to block form.
	 */
	xfs_dir3_block_init(mp, dbp, dp);

	needlog = 1;
	needscan = 0;
	/*
	 * Use up the space at the end of the block (blp/btp).
	 */
	xfs_dir2_data_use_free(tp, dbp, dup, mp->m_dirblksize - size, size,
		&needlog, &needscan);
	/*
	 * Initialize the block tail.
	 */
	btp = xfs_dir2_block_tail_p(mp, hdr);
	btp->count = cpu_to_be32(leafhdr.count - leafhdr.stale);
	btp->stale = 0;
	xfs_dir2_block_log_tail(tp, dbp);
	/*
	 * Initialize the block leaf area.  We compact out stale entries.
	 */
	lep = xfs_dir2_block_leaf_p(btp);
	for (from = to = 0; from < leafhdr.count; from++) {
		if (ents[from].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
			continue;
		lep[to++] = ents[from];
	}
	ASSERT(to == be32_to_cpu(btp->count));
	xfs_dir2_block_log_leaf(tp, dbp, 0, be32_to_cpu(btp->count) - 1);
	/*
	 * Scan the bestfree if we need it and log the data block header.
	 */
	if (needscan)
		xfs_dir2_data_freescan(mp, hdr, &needlog);
	if (needlog)
		xfs_dir2_data_log_header(tp, dbp);
	/*
	 * Pitch the old leaf block.
	 */
	error = xfs_da_shrink_inode(args, mp->m_dirleafblk, lbp);
	if (error)
		return error;

	/*
	 * Now see if the resulting block can be shrunken to shortform.
	 */
	size = xfs_dir2_block_sfsize(dp, hdr, &sfh);
	if (size > XFS_IFORK_DSIZE(dp))
		return 0;

	return xfs_dir2_block_to_sf(args, dbp, size, &sfh);
}

/*
 * Convert the shortform directory to block form.
 */
int						/* error */
xfs_dir2_sf_to_block(
	xfs_da_args_t		*args)		/* operation arguments */
{
	xfs_dir2_db_t		blkno;		/* dir-relative block # (0) */
	xfs_dir2_data_hdr_t	*hdr;		/* block header */
	xfs_dir2_leaf_entry_t	*blp;		/* block leaf entries */
	struct xfs_buf		*bp;		/* block buffer */
	xfs_dir2_block_tail_t	*btp;		/* block tail pointer */
	xfs_dir2_data_entry_t	*dep;		/* data entry pointer */
	xfs_inode_t		*dp;		/* incore directory inode */
	int			dummy;		/* trash */
	xfs_dir2_data_unused_t	*dup;		/* unused entry pointer */
	int			endoffset;	/* end of data objects */
	int			error;		/* error return value */
	int			i;		/* index */
	xfs_mount_t		*mp;		/* filesystem mount point */
	int			needlog;	/* need to log block header */
	int			needscan;	/* need to scan block freespc */
	int			newoffset;	/* offset from current entry */
	int			offset;		/* target block offset */
	xfs_dir2_sf_entry_t	*sfep;		/* sf entry pointer */
	xfs_dir2_sf_hdr_t	*oldsfp;	/* old shortform header  */
	xfs_dir2_sf_hdr_t	*sfp;		/* shortform header  */
	__be16			*tagp;		/* end of data entry */
	xfs_trans_t		*tp;		/* transaction pointer */
	struct xfs_name		name;

	trace_xfs_dir2_sf_to_block(args);

	dp = args->dp;
	tp = args->trans;
	mp = dp->i_mount;
	ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
	/*
	 * Bomb out if the shortform directory is way too short.
	 */
	if (dp->i_d.di_size < offsetof(xfs_dir2_sf_hdr_t, parent)) {
		ASSERT(XFS_FORCED_SHUTDOWN(mp));
		return XFS_ERROR(EIO);
	}

	oldsfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;

	ASSERT(dp->i_df.if_bytes == dp->i_d.di_size);
	ASSERT(dp->i_df.if_u1.if_data != NULL);
	ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(oldsfp->i8count));

	/*
	 * Copy the directory into a temporary buffer.
	 * Then pitch the incore inode data so we can make extents.
	 */
	sfp = kmem_alloc(dp->i_df.if_bytes, KM_SLEEP);
	memcpy(sfp, oldsfp, dp->i_df.if_bytes);

	xfs_idata_realloc(dp, -dp->i_df.if_bytes, XFS_DATA_FORK);
	dp->i_d.di_size = 0;
	xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);

	/*
	 * Add block 0 to the inode.
	 */
	error = xfs_dir2_grow_inode(args, XFS_DIR2_DATA_SPACE, &blkno);
	if (error) {
		kmem_free(sfp);
		return error;
	}
	/*
	 * Initialize the data block, then convert it to block format.
	 */
	error = xfs_dir3_data_init(args, blkno, &bp);
	if (error) {
		kmem_free(sfp);
		return error;
	}
	xfs_dir3_block_init(mp, bp, dp);
	hdr = bp->b_addr;

	/*
	 * Compute size of block "tail" area.
	 */
	i = (uint)sizeof(*btp) +
	    (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t);
	/*
	 * The whole thing is initialized to free by the init routine.
	 * Say we're using the leaf and tail area.
	 */
	dup = xfs_dir3_data_unused_p(hdr);
	needlog = needscan = 0;
	xfs_dir2_data_use_free(tp, bp, dup, mp->m_dirblksize - i, i, &needlog,
		&needscan);
	ASSERT(needscan == 0);
	/*
	 * Fill in the tail.
	 */
	btp = xfs_dir2_block_tail_p(mp, hdr);
	btp->count = cpu_to_be32(sfp->count + 2);	/* ., .. */
	btp->stale = 0;
	blp = xfs_dir2_block_leaf_p(btp);
	endoffset = (uint)((char *)blp - (char *)hdr);
	/*
	 * Remove the freespace, we'll manage it.
	 */
	xfs_dir2_data_use_free(tp, bp, dup,
		(xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr),
		be16_to_cpu(dup->length), &needlog, &needscan);
	/*
	 * Create entry for .
	 */
	dep = xfs_dir3_data_dot_entry_p(hdr);
	dep->inumber = cpu_to_be64(dp->i_ino);
	dep->namelen = 1;
	dep->name[0] = '.';
	tagp = xfs_dir2_data_entry_tag_p(dep);
	*tagp = cpu_to_be16((char *)dep - (char *)hdr);
	xfs_dir2_data_log_entry(tp, bp, dep);
	blp[0].hashval = cpu_to_be32(xfs_dir_hash_dot);
	blp[0].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
				(char *)dep - (char *)hdr));
	/*
	 * Create entry for ..
	 */
	dep = xfs_dir3_data_dotdot_entry_p(hdr);
	dep->inumber = cpu_to_be64(xfs_dir2_sf_get_parent_ino(sfp));
	dep->namelen = 2;
	dep->name[0] = dep->name[1] = '.';
	tagp = xfs_dir2_data_entry_tag_p(dep);
	*tagp = cpu_to_be16((char *)dep - (char *)hdr);
	xfs_dir2_data_log_entry(tp, bp, dep);
	blp[1].hashval = cpu_to_be32(xfs_dir_hash_dotdot);
	blp[1].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
				(char *)dep - (char *)hdr));
	offset = xfs_dir3_data_first_offset(hdr);
	/*
	 * Loop over existing entries, stuff them in.
	 */
	i = 0;
	if (!sfp->count)
		sfep = NULL;
	else
		sfep = xfs_dir2_sf_firstentry(sfp);
	/*
	 * Need to preserve the existing offset values in the sf directory.
	 * Insert holes (unused entries) where necessary.
	 */
	while (offset < endoffset) {
		/*
		 * sfep is null when we reach the end of the list.
		 */
		if (sfep == NULL)
			newoffset = endoffset;
		else
			newoffset = xfs_dir2_sf_get_offset(sfep);
		/*
		 * There should be a hole here, make one.
		 */
		if (offset < newoffset) {
			dup = (xfs_dir2_data_unused_t *)((char *)hdr + offset);
			dup->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG);
			dup->length = cpu_to_be16(newoffset - offset);
			*xfs_dir2_data_unused_tag_p(dup) = cpu_to_be16(
				((char *)dup - (char *)hdr));
			xfs_dir2_data_log_unused(tp, bp, dup);
			xfs_dir2_data_freeinsert(hdr, dup, &dummy);
			offset += be16_to_cpu(dup->length);
			continue;
		}
		/*
		 * Copy a real entry.
		 */
		dep = (xfs_dir2_data_entry_t *)((char *)hdr + newoffset);
		dep->inumber = cpu_to_be64(xfs_dir2_sfe_get_ino(sfp, sfep));
		dep->namelen = sfep->namelen;
		memcpy(dep->name, sfep->name, dep->namelen);
		tagp = xfs_dir2_data_entry_tag_p(dep);
		*tagp = cpu_to_be16((char *)dep - (char *)hdr);
		xfs_dir2_data_log_entry(tp, bp, dep);
		name.name = sfep->name;
		name.len = sfep->namelen;
		blp[2 + i].hashval = cpu_to_be32(mp->m_dirnameops->
							hashname(&name));
		blp[2 + i].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
						 (char *)dep - (char *)hdr));
		offset = (int)((char *)(tagp + 1) - (char *)hdr);
		if (++i == sfp->count)
			sfep = NULL;
		else
			sfep = xfs_dir2_sf_nextentry(sfp, sfep);
	}
	/* Done with the temporary buffer */
	kmem_free(sfp);
	/*
	 * Sort the leaf entries by hash value.
	 */
	xfs_sort(blp, be32_to_cpu(btp->count), sizeof(*blp), xfs_dir2_block_sort);
	/*
	 * Log the leaf entry area and tail.
	 * Already logged the header in data_init, ignore needlog.
	 */
	ASSERT(needscan == 0);
	xfs_dir2_block_log_leaf(tp, bp, 0, be32_to_cpu(btp->count) - 1);
	xfs_dir2_block_log_tail(tp, bp);
	xfs_dir3_data_check(dp, bp);
	return 0;
}