forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathxfs_dir2_node.c
1999 lines (1940 loc) · 56.5 KB
/
xfs_dir2_node.c
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
/*
* Copyright (c) 2000-2005 Silicon Graphics, 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_inum.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_dir2.h"
#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_da_btree.h"
#include "xfs_bmap_btree.h"
#include "xfs_dir2_sf.h"
#include "xfs_attr_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_bmap.h"
#include "xfs_dir2_data.h"
#include "xfs_dir2_leaf.h"
#include "xfs_dir2_block.h"
#include "xfs_dir2_node.h"
#include "xfs_dir2_trace.h"
#include "xfs_error.h"
/*
* Function declarations.
*/
static void xfs_dir2_free_log_header(xfs_trans_t *tp, xfs_dabuf_t *bp);
static int xfs_dir2_leafn_add(xfs_dabuf_t *bp, xfs_da_args_t *args, int index);
#ifdef DEBUG
static void xfs_dir2_leafn_check(xfs_inode_t *dp, xfs_dabuf_t *bp);
#else
#define xfs_dir2_leafn_check(dp, bp)
#endif
static void xfs_dir2_leafn_moveents(xfs_da_args_t *args, xfs_dabuf_t *bp_s,
int start_s, xfs_dabuf_t *bp_d, int start_d,
int count);
static void xfs_dir2_leafn_rebalance(xfs_da_state_t *state,
xfs_da_state_blk_t *blk1,
xfs_da_state_blk_t *blk2);
static int xfs_dir2_leafn_remove(xfs_da_args_t *args, xfs_dabuf_t *bp,
int index, xfs_da_state_blk_t *dblk,
int *rval);
static int xfs_dir2_node_addname_int(xfs_da_args_t *args,
xfs_da_state_blk_t *fblk);
/*
* Log entries from a freespace block.
*/
void
xfs_dir2_free_log_bests(
xfs_trans_t *tp, /* transaction pointer */
xfs_dabuf_t *bp, /* freespace buffer */
int first, /* first entry to log */
int last) /* last entry to log */
{
xfs_dir2_free_t *free; /* freespace structure */
free = bp->data;
ASSERT(be32_to_cpu(free->hdr.magic) == XFS_DIR2_FREE_MAGIC);
xfs_da_log_buf(tp, bp,
(uint)((char *)&free->bests[first] - (char *)free),
(uint)((char *)&free->bests[last] - (char *)free +
sizeof(free->bests[0]) - 1));
}
/*
* Log header from a freespace block.
*/
static void
xfs_dir2_free_log_header(
xfs_trans_t *tp, /* transaction pointer */
xfs_dabuf_t *bp) /* freespace buffer */
{
xfs_dir2_free_t *free; /* freespace structure */
free = bp->data;
ASSERT(be32_to_cpu(free->hdr.magic) == XFS_DIR2_FREE_MAGIC);
xfs_da_log_buf(tp, bp, (uint)((char *)&free->hdr - (char *)free),
(uint)(sizeof(xfs_dir2_free_hdr_t) - 1));
}
/*
* Convert a leaf-format directory to a node-format directory.
* We need to change the magic number of the leaf block, and copy
* the freespace table out of the leaf block into its own block.
*/
int /* error */
xfs_dir2_leaf_to_node(
xfs_da_args_t *args, /* operation arguments */
xfs_dabuf_t *lbp) /* leaf buffer */
{
xfs_inode_t *dp; /* incore directory inode */
int error; /* error return value */
xfs_dabuf_t *fbp; /* freespace buffer */
xfs_dir2_db_t fdb; /* freespace block number */
xfs_dir2_free_t *free; /* freespace structure */
__be16 *from; /* pointer to freespace entry */
int i; /* leaf freespace index */
xfs_dir2_leaf_t *leaf; /* leaf structure */
xfs_dir2_leaf_tail_t *ltp; /* leaf tail structure */
xfs_mount_t *mp; /* filesystem mount point */
int n; /* count of live freespc ents */
xfs_dir2_data_off_t off; /* freespace entry value */
__be16 *to; /* pointer to freespace entry */
xfs_trans_t *tp; /* transaction pointer */
xfs_dir2_trace_args_b("leaf_to_node", args, lbp);
dp = args->dp;
mp = dp->i_mount;
tp = args->trans;
/*
* Add a freespace block to the directory.
*/
if ((error = xfs_dir2_grow_inode(args, XFS_DIR2_FREE_SPACE, &fdb))) {
return error;
}
ASSERT(fdb == XFS_DIR2_FREE_FIRSTDB(mp));
/*
* Get the buffer for the new freespace block.
*/
if ((error = xfs_da_get_buf(tp, dp, XFS_DIR2_DB_TO_DA(mp, fdb), -1, &fbp,
XFS_DATA_FORK))) {
return error;
}
ASSERT(fbp != NULL);
free = fbp->data;
leaf = lbp->data;
ltp = XFS_DIR2_LEAF_TAIL_P(mp, leaf);
/*
* Initialize the freespace block header.
*/
free->hdr.magic = cpu_to_be32(XFS_DIR2_FREE_MAGIC);
free->hdr.firstdb = 0;
ASSERT(be32_to_cpu(ltp->bestcount) <= (uint)dp->i_d.di_size / mp->m_dirblksize);
free->hdr.nvalid = ltp->bestcount;
/*
* Copy freespace entries from the leaf block to the new block.
* Count active entries.
*/
for (i = n = 0, from = XFS_DIR2_LEAF_BESTS_P(ltp), to = free->bests;
i < be32_to_cpu(ltp->bestcount); i++, from++, to++) {
if ((off = be16_to_cpu(*from)) != NULLDATAOFF)
n++;
*to = cpu_to_be16(off);
}
free->hdr.nused = cpu_to_be32(n);
leaf->hdr.info.magic = cpu_to_be16(XFS_DIR2_LEAFN_MAGIC);
/*
* Log everything.
*/
xfs_dir2_leaf_log_header(tp, lbp);
xfs_dir2_free_log_header(tp, fbp);
xfs_dir2_free_log_bests(tp, fbp, 0, be32_to_cpu(free->hdr.nvalid) - 1);
xfs_da_buf_done(fbp);
xfs_dir2_leafn_check(dp, lbp);
return 0;
}
/*
* Add a leaf entry to a leaf block in a node-form directory.
* The other work necessary is done from the caller.
*/
static int /* error */
xfs_dir2_leafn_add(
xfs_dabuf_t *bp, /* leaf buffer */
xfs_da_args_t *args, /* operation arguments */
int index) /* insertion pt for new entry */
{
int compact; /* compacting stale leaves */
xfs_inode_t *dp; /* incore directory inode */
int highstale; /* next stale entry */
xfs_dir2_leaf_t *leaf; /* leaf structure */
xfs_dir2_leaf_entry_t *lep; /* leaf entry */
int lfloghigh; /* high leaf entry logging */
int lfloglow; /* low leaf entry logging */
int lowstale; /* previous stale entry */
xfs_mount_t *mp; /* filesystem mount point */
xfs_trans_t *tp; /* transaction pointer */
xfs_dir2_trace_args_sb("leafn_add", args, index, bp);
dp = args->dp;
mp = dp->i_mount;
tp = args->trans;
leaf = bp->data;
/*
* Quick check just to make sure we are not going to index
* into other peoples memory
*/
if (index < 0)
return XFS_ERROR(EFSCORRUPTED);
/*
* If there are already the maximum number of leaf entries in
* the block, if there are no stale entries it won't fit.
* Caller will do a split. If there are stale entries we'll do
* a compact.
*/
if (be16_to_cpu(leaf->hdr.count) == XFS_DIR2_MAX_LEAF_ENTS(mp)) {
if (!leaf->hdr.stale)
return XFS_ERROR(ENOSPC);
compact = be16_to_cpu(leaf->hdr.stale) > 1;
} else
compact = 0;
ASSERT(index == 0 || be32_to_cpu(leaf->ents[index - 1].hashval) <= args->hashval);
ASSERT(index == be16_to_cpu(leaf->hdr.count) ||
be32_to_cpu(leaf->ents[index].hashval) >= args->hashval);
if (args->justcheck)
return 0;
/*
* Compact out all but one stale leaf entry. Leaves behind
* the entry closest to index.
*/
if (compact) {
xfs_dir2_leaf_compact_x1(bp, &index, &lowstale, &highstale,
&lfloglow, &lfloghigh);
}
/*
* Set impossible logging indices for this case.
*/
else if (leaf->hdr.stale) {
lfloglow = be16_to_cpu(leaf->hdr.count);
lfloghigh = -1;
}
/*
* No stale entries, just insert a space for the new entry.
*/
if (!leaf->hdr.stale) {
lep = &leaf->ents[index];
if (index < be16_to_cpu(leaf->hdr.count))
memmove(lep + 1, lep,
(be16_to_cpu(leaf->hdr.count) - index) * sizeof(*lep));
lfloglow = index;
lfloghigh = be16_to_cpu(leaf->hdr.count);
be16_add(&leaf->hdr.count, 1);
}
/*
* There are stale entries. We'll use one for the new entry.
*/
else {
/*
* If we didn't do a compact then we need to figure out
* which stale entry will be used.
*/
if (compact == 0) {
/*
* Find first stale entry before our insertion point.
*/
for (lowstale = index - 1;
lowstale >= 0 &&
be32_to_cpu(leaf->ents[lowstale].address) !=
XFS_DIR2_NULL_DATAPTR;
lowstale--)
continue;
/*
* Find next stale entry after insertion point.
* Stop looking if the answer would be worse than
* lowstale already found.
*/
for (highstale = index;
highstale < be16_to_cpu(leaf->hdr.count) &&
be32_to_cpu(leaf->ents[highstale].address) !=
XFS_DIR2_NULL_DATAPTR &&
(lowstale < 0 ||
index - lowstale - 1 >= highstale - index);
highstale++)
continue;
}
/*
* Using the low stale entry.
* Shift entries up toward the stale slot.
*/
if (lowstale >= 0 &&
(highstale == be16_to_cpu(leaf->hdr.count) ||
index - lowstale - 1 < highstale - index)) {
ASSERT(be32_to_cpu(leaf->ents[lowstale].address) ==
XFS_DIR2_NULL_DATAPTR);
ASSERT(index - lowstale - 1 >= 0);
if (index - lowstale - 1 > 0)
memmove(&leaf->ents[lowstale],
&leaf->ents[lowstale + 1],
(index - lowstale - 1) * sizeof(*lep));
lep = &leaf->ents[index - 1];
lfloglow = MIN(lowstale, lfloglow);
lfloghigh = MAX(index - 1, lfloghigh);
}
/*
* Using the high stale entry.
* Shift entries down toward the stale slot.
*/
else {
ASSERT(be32_to_cpu(leaf->ents[highstale].address) ==
XFS_DIR2_NULL_DATAPTR);
ASSERT(highstale - index >= 0);
if (highstale - index > 0)
memmove(&leaf->ents[index + 1],
&leaf->ents[index],
(highstale - index) * sizeof(*lep));
lep = &leaf->ents[index];
lfloglow = MIN(index, lfloglow);
lfloghigh = MAX(highstale, lfloghigh);
}
be16_add(&leaf->hdr.stale, -1);
}
/*
* Insert the new entry, log everything.
*/
lep->hashval = cpu_to_be32(args->hashval);
lep->address = cpu_to_be32(XFS_DIR2_DB_OFF_TO_DATAPTR(mp,
args->blkno, args->index));
xfs_dir2_leaf_log_header(tp, bp);
xfs_dir2_leaf_log_ents(tp, bp, lfloglow, lfloghigh);
xfs_dir2_leafn_check(dp, bp);
return 0;
}
#ifdef DEBUG
/*
* Check internal consistency of a leafn block.
*/
void
xfs_dir2_leafn_check(
xfs_inode_t *dp, /* incore directory inode */
xfs_dabuf_t *bp) /* leaf buffer */
{
int i; /* leaf index */
xfs_dir2_leaf_t *leaf; /* leaf structure */
xfs_mount_t *mp; /* filesystem mount point */
int stale; /* count of stale leaves */
leaf = bp->data;
mp = dp->i_mount;
ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC);
ASSERT(be16_to_cpu(leaf->hdr.count) <= XFS_DIR2_MAX_LEAF_ENTS(mp));
for (i = stale = 0; i < be16_to_cpu(leaf->hdr.count); i++) {
if (i + 1 < be16_to_cpu(leaf->hdr.count)) {
ASSERT(be32_to_cpu(leaf->ents[i].hashval) <=
be32_to_cpu(leaf->ents[i + 1].hashval));
}
if (be32_to_cpu(leaf->ents[i].address) == XFS_DIR2_NULL_DATAPTR)
stale++;
}
ASSERT(be16_to_cpu(leaf->hdr.stale) == stale);
}
#endif /* DEBUG */
/*
* Return the last hash value in the leaf.
* Stale entries are ok.
*/
xfs_dahash_t /* hash value */
xfs_dir2_leafn_lasthash(
xfs_dabuf_t *bp, /* leaf buffer */
int *count) /* count of entries in leaf */
{
xfs_dir2_leaf_t *leaf; /* leaf structure */
leaf = bp->data;
ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC);
if (count)
*count = be16_to_cpu(leaf->hdr.count);
if (!leaf->hdr.count)
return 0;
return be32_to_cpu(leaf->ents[be16_to_cpu(leaf->hdr.count) - 1].hashval);
}
/*
* Look up a leaf entry in a node-format leaf block.
* If this is an addname then the extrablk in state is a freespace block,
* otherwise it's a data block.
*/
int
xfs_dir2_leafn_lookup_int(
xfs_dabuf_t *bp, /* leaf buffer */
xfs_da_args_t *args, /* operation arguments */
int *indexp, /* out: leaf entry index */
xfs_da_state_t *state) /* state to fill in */
{
xfs_dabuf_t *curbp; /* current data/free buffer */
xfs_dir2_db_t curdb; /* current data block number */
xfs_dir2_db_t curfdb; /* current free block number */
xfs_dir2_data_entry_t *dep; /* data block entry */
xfs_inode_t *dp; /* incore directory inode */
int error; /* error return value */
int fi; /* free entry index */
xfs_dir2_free_t *free=NULL; /* free block structure */
int index; /* leaf entry index */
xfs_dir2_leaf_t *leaf; /* leaf structure */
int length=0; /* length of new data entry */
xfs_dir2_leaf_entry_t *lep; /* leaf entry */
xfs_mount_t *mp; /* filesystem mount point */
xfs_dir2_db_t newdb; /* new data block number */
xfs_dir2_db_t newfdb; /* new free block number */
xfs_trans_t *tp; /* transaction pointer */
dp = args->dp;
tp = args->trans;
mp = dp->i_mount;
leaf = bp->data;
ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC);
#ifdef __KERNEL__
ASSERT(be16_to_cpu(leaf->hdr.count) > 0);
#endif
xfs_dir2_leafn_check(dp, bp);
/*
* Look up the hash value in the leaf entries.
*/
index = xfs_dir2_leaf_search_hash(args, bp);
/*
* Do we have a buffer coming in?
*/
if (state->extravalid)
curbp = state->extrablk.bp;
else
curbp = NULL;
/*
* For addname, it's a free block buffer, get the block number.
*/
if (args->addname) {
curfdb = curbp ? state->extrablk.blkno : -1;
curdb = -1;
length = XFS_DIR2_DATA_ENTSIZE(args->namelen);
if ((free = (curbp ? curbp->data : NULL)))
ASSERT(be32_to_cpu(free->hdr.magic) == XFS_DIR2_FREE_MAGIC);
}
/*
* For others, it's a data block buffer, get the block number.
*/
else {
curfdb = -1;
curdb = curbp ? state->extrablk.blkno : -1;
}
/*
* Loop over leaf entries with the right hash value.
*/
for (lep = &leaf->ents[index];
index < be16_to_cpu(leaf->hdr.count) && be32_to_cpu(lep->hashval) == args->hashval;
lep++, index++) {
/*
* Skip stale leaf entries.
*/
if (be32_to_cpu(lep->address) == XFS_DIR2_NULL_DATAPTR)
continue;
/*
* Pull the data block number from the entry.
*/
newdb = XFS_DIR2_DATAPTR_TO_DB(mp, be32_to_cpu(lep->address));
/*
* For addname, we're looking for a place to put the new entry.
* We want to use a data block with an entry of equal
* hash value to ours if there is one with room.
*/
if (args->addname) {
/*
* If this block isn't the data block we already have
* in hand, take a look at it.
*/
if (newdb != curdb) {
curdb = newdb;
/*
* Convert the data block to the free block
* holding its freespace information.
*/
newfdb = XFS_DIR2_DB_TO_FDB(mp, newdb);
/*
* If it's not the one we have in hand,
* read it in.
*/
if (newfdb != curfdb) {
/*
* If we had one before, drop it.
*/
if (curbp)
xfs_da_brelse(tp, curbp);
/*
* Read the free block.
*/
if ((error = xfs_da_read_buf(tp, dp,
XFS_DIR2_DB_TO_DA(mp,
newfdb),
-1, &curbp,
XFS_DATA_FORK))) {
return error;
}
free = curbp->data;
ASSERT(be32_to_cpu(free->hdr.magic) ==
XFS_DIR2_FREE_MAGIC);
ASSERT((be32_to_cpu(free->hdr.firstdb) %
XFS_DIR2_MAX_FREE_BESTS(mp)) ==
0);
ASSERT(be32_to_cpu(free->hdr.firstdb) <= curdb);
ASSERT(curdb <
be32_to_cpu(free->hdr.firstdb) +
be32_to_cpu(free->hdr.nvalid));
}
/*
* Get the index for our entry.
*/
fi = XFS_DIR2_DB_TO_FDINDEX(mp, curdb);
/*
* If it has room, return it.
*/
if (unlikely(be16_to_cpu(free->bests[fi]) == NULLDATAOFF)) {
XFS_ERROR_REPORT("xfs_dir2_leafn_lookup_int",
XFS_ERRLEVEL_LOW, mp);
if (curfdb != newfdb)
xfs_da_brelse(tp, curbp);
return XFS_ERROR(EFSCORRUPTED);
}
curfdb = newfdb;
if (be16_to_cpu(free->bests[fi]) >= length) {
*indexp = index;
state->extravalid = 1;
state->extrablk.bp = curbp;
state->extrablk.blkno = curfdb;
state->extrablk.index = fi;
state->extrablk.magic =
XFS_DIR2_FREE_MAGIC;
ASSERT(args->oknoent);
return XFS_ERROR(ENOENT);
}
}
}
/*
* Not adding a new entry, so we really want to find
* the name given to us.
*/
else {
/*
* If it's a different data block, go get it.
*/
if (newdb != curdb) {
/*
* If we had a block before, drop it.
*/
if (curbp)
xfs_da_brelse(tp, curbp);
/*
* Read the data block.
*/
if ((error =
xfs_da_read_buf(tp, dp,
XFS_DIR2_DB_TO_DA(mp, newdb), -1,
&curbp, XFS_DATA_FORK))) {
return error;
}
xfs_dir2_data_check(dp, curbp);
curdb = newdb;
}
/*
* Point to the data entry.
*/
dep = (xfs_dir2_data_entry_t *)
((char *)curbp->data +
XFS_DIR2_DATAPTR_TO_OFF(mp, be32_to_cpu(lep->address)));
/*
* Compare the entry, return it if it matches.
*/
if (dep->namelen == args->namelen &&
dep->name[0] == args->name[0] &&
memcmp(dep->name, args->name, args->namelen) == 0) {
args->inumber = be64_to_cpu(dep->inumber);
*indexp = index;
state->extravalid = 1;
state->extrablk.bp = curbp;
state->extrablk.blkno = curdb;
state->extrablk.index =
(int)((char *)dep -
(char *)curbp->data);
state->extrablk.magic = XFS_DIR2_DATA_MAGIC;
return XFS_ERROR(EEXIST);
}
}
}
/*
* Didn't find a match.
* If we are holding a buffer, give it back in case our caller
* finds it useful.
*/
if ((state->extravalid = (curbp != NULL))) {
state->extrablk.bp = curbp;
state->extrablk.index = -1;
/*
* For addname, giving back a free block.
*/
if (args->addname) {
state->extrablk.blkno = curfdb;
state->extrablk.magic = XFS_DIR2_FREE_MAGIC;
}
/*
* For other callers, giving back a data block.
*/
else {
state->extrablk.blkno = curdb;
state->extrablk.magic = XFS_DIR2_DATA_MAGIC;
}
}
/*
* Return the final index, that will be the insertion point.
*/
*indexp = index;
ASSERT(index == be16_to_cpu(leaf->hdr.count) || args->oknoent);
return XFS_ERROR(ENOENT);
}
/*
* Move count leaf entries from source to destination leaf.
* Log entries and headers. Stale entries are preserved.
*/
static void
xfs_dir2_leafn_moveents(
xfs_da_args_t *args, /* operation arguments */
xfs_dabuf_t *bp_s, /* source leaf buffer */
int start_s, /* source leaf index */
xfs_dabuf_t *bp_d, /* destination leaf buffer */
int start_d, /* destination leaf index */
int count) /* count of leaves to copy */
{
xfs_dir2_leaf_t *leaf_d; /* destination leaf structure */
xfs_dir2_leaf_t *leaf_s; /* source leaf structure */
int stale; /* count stale leaves copied */
xfs_trans_t *tp; /* transaction pointer */
xfs_dir2_trace_args_bibii("leafn_moveents", args, bp_s, start_s, bp_d,
start_d, count);
/*
* Silently return if nothing to do.
*/
if (count == 0) {
return;
}
tp = args->trans;
leaf_s = bp_s->data;
leaf_d = bp_d->data;
/*
* If the destination index is not the end of the current
* destination leaf entries, open up a hole in the destination
* to hold the new entries.
*/
if (start_d < be16_to_cpu(leaf_d->hdr.count)) {
memmove(&leaf_d->ents[start_d + count], &leaf_d->ents[start_d],
(be16_to_cpu(leaf_d->hdr.count) - start_d) *
sizeof(xfs_dir2_leaf_entry_t));
xfs_dir2_leaf_log_ents(tp, bp_d, start_d + count,
count + be16_to_cpu(leaf_d->hdr.count) - 1);
}
/*
* If the source has stale leaves, count the ones in the copy range
* so we can update the header correctly.
*/
if (leaf_s->hdr.stale) {
int i; /* temp leaf index */
for (i = start_s, stale = 0; i < start_s + count; i++) {
if (be32_to_cpu(leaf_s->ents[i].address) == XFS_DIR2_NULL_DATAPTR)
stale++;
}
} else
stale = 0;
/*
* Copy the leaf entries from source to destination.
*/
memcpy(&leaf_d->ents[start_d], &leaf_s->ents[start_s],
count * sizeof(xfs_dir2_leaf_entry_t));
xfs_dir2_leaf_log_ents(tp, bp_d, start_d, start_d + count - 1);
/*
* If there are source entries after the ones we copied,
* delete the ones we copied by sliding the next ones down.
*/
if (start_s + count < be16_to_cpu(leaf_s->hdr.count)) {
memmove(&leaf_s->ents[start_s], &leaf_s->ents[start_s + count],
count * sizeof(xfs_dir2_leaf_entry_t));
xfs_dir2_leaf_log_ents(tp, bp_s, start_s, start_s + count - 1);
}
/*
* Update the headers and log them.
*/
be16_add(&leaf_s->hdr.count, -(count));
be16_add(&leaf_s->hdr.stale, -(stale));
be16_add(&leaf_d->hdr.count, count);
be16_add(&leaf_d->hdr.stale, stale);
xfs_dir2_leaf_log_header(tp, bp_s);
xfs_dir2_leaf_log_header(tp, bp_d);
xfs_dir2_leafn_check(args->dp, bp_s);
xfs_dir2_leafn_check(args->dp, bp_d);
}
/*
* Determine the sort order of two leaf blocks.
* Returns 1 if both are valid and leaf2 should be before leaf1, else 0.
*/
int /* sort order */
xfs_dir2_leafn_order(
xfs_dabuf_t *leaf1_bp, /* leaf1 buffer */
xfs_dabuf_t *leaf2_bp) /* leaf2 buffer */
{
xfs_dir2_leaf_t *leaf1; /* leaf1 structure */
xfs_dir2_leaf_t *leaf2; /* leaf2 structure */
leaf1 = leaf1_bp->data;
leaf2 = leaf2_bp->data;
ASSERT(be16_to_cpu(leaf1->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC);
ASSERT(be16_to_cpu(leaf2->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC);
if (be16_to_cpu(leaf1->hdr.count) > 0 &&
be16_to_cpu(leaf2->hdr.count) > 0 &&
(be32_to_cpu(leaf2->ents[0].hashval) < be32_to_cpu(leaf1->ents[0].hashval) ||
be32_to_cpu(leaf2->ents[be16_to_cpu(leaf2->hdr.count) - 1].hashval) <
be32_to_cpu(leaf1->ents[be16_to_cpu(leaf1->hdr.count) - 1].hashval)))
return 1;
return 0;
}
/*
* Rebalance leaf entries between two leaf blocks.
* This is actually only called when the second block is new,
* though the code deals with the general case.
* A new entry will be inserted in one of the blocks, and that
* entry is taken into account when balancing.
*/
static void
xfs_dir2_leafn_rebalance(
xfs_da_state_t *state, /* btree cursor */
xfs_da_state_blk_t *blk1, /* first btree block */
xfs_da_state_blk_t *blk2) /* second btree block */
{
xfs_da_args_t *args; /* operation arguments */
int count; /* count (& direction) leaves */
int isleft; /* new goes in left leaf */
xfs_dir2_leaf_t *leaf1; /* first leaf structure */
xfs_dir2_leaf_t *leaf2; /* second leaf structure */
int mid; /* midpoint leaf index */
#ifdef DEBUG
int oldstale; /* old count of stale leaves */
#endif
int oldsum; /* old total leaf count */
int swap; /* swapped leaf blocks */
args = state->args;
/*
* If the block order is wrong, swap the arguments.
*/
if ((swap = xfs_dir2_leafn_order(blk1->bp, blk2->bp))) {
xfs_da_state_blk_t *tmp; /* temp for block swap */
tmp = blk1;
blk1 = blk2;
blk2 = tmp;
}
leaf1 = blk1->bp->data;
leaf2 = blk2->bp->data;
oldsum = be16_to_cpu(leaf1->hdr.count) + be16_to_cpu(leaf2->hdr.count);
#ifdef DEBUG
oldstale = be16_to_cpu(leaf1->hdr.stale) + be16_to_cpu(leaf2->hdr.stale);
#endif
mid = oldsum >> 1;
/*
* If the old leaf count was odd then the new one will be even,
* so we need to divide the new count evenly.
*/
if (oldsum & 1) {
xfs_dahash_t midhash; /* middle entry hash value */
if (mid >= be16_to_cpu(leaf1->hdr.count))
midhash = be32_to_cpu(leaf2->ents[mid - be16_to_cpu(leaf1->hdr.count)].hashval);
else
midhash = be32_to_cpu(leaf1->ents[mid].hashval);
isleft = args->hashval <= midhash;
}
/*
* If the old count is even then the new count is odd, so there's
* no preferred side for the new entry.
* Pick the left one.
*/
else
isleft = 1;
/*
* Calculate moved entry count. Positive means left-to-right,
* negative means right-to-left. Then move the entries.
*/
count = be16_to_cpu(leaf1->hdr.count) - mid + (isleft == 0);
if (count > 0)
xfs_dir2_leafn_moveents(args, blk1->bp,
be16_to_cpu(leaf1->hdr.count) - count, blk2->bp, 0, count);
else if (count < 0)
xfs_dir2_leafn_moveents(args, blk2->bp, 0, blk1->bp,
be16_to_cpu(leaf1->hdr.count), count);
ASSERT(be16_to_cpu(leaf1->hdr.count) + be16_to_cpu(leaf2->hdr.count) == oldsum);
ASSERT(be16_to_cpu(leaf1->hdr.stale) + be16_to_cpu(leaf2->hdr.stale) == oldstale);
/*
* Mark whether we're inserting into the old or new leaf.
*/
if (be16_to_cpu(leaf1->hdr.count) < be16_to_cpu(leaf2->hdr.count))
state->inleaf = swap;
else if (be16_to_cpu(leaf1->hdr.count) > be16_to_cpu(leaf2->hdr.count))
state->inleaf = !swap;
else
state->inleaf =
swap ^ (blk1->index <= be16_to_cpu(leaf1->hdr.count));
/*
* Adjust the expected index for insertion.
*/
if (!state->inleaf)
blk2->index = blk1->index - be16_to_cpu(leaf1->hdr.count);
/*
* Finally sanity check just to make sure we are not returning a negative index
*/
if(blk2->index < 0) {
state->inleaf = 1;
blk2->index = 0;
cmn_err(CE_ALERT,
"xfs_dir2_leafn_rebalance: picked the wrong leaf? reverting original leaf: "
"blk1->index %d\n",
blk1->index);
}
}
/*
* Remove an entry from a node directory.
* This removes the leaf entry and the data entry,
* and updates the free block if necessary.
*/
static int /* error */
xfs_dir2_leafn_remove(
xfs_da_args_t *args, /* operation arguments */
xfs_dabuf_t *bp, /* leaf buffer */
int index, /* leaf entry index */
xfs_da_state_blk_t *dblk, /* data block */
int *rval) /* resulting block needs join */
{
xfs_dir2_data_t *data; /* data block structure */
xfs_dir2_db_t db; /* data block number */
xfs_dabuf_t *dbp; /* data block buffer */
xfs_dir2_data_entry_t *dep; /* data block entry */
xfs_inode_t *dp; /* incore directory inode */
xfs_dir2_leaf_t *leaf; /* leaf structure */
xfs_dir2_leaf_entry_t *lep; /* leaf entry */
int longest; /* longest data free entry */
int off; /* data block entry offset */
xfs_mount_t *mp; /* filesystem mount point */
int needlog; /* need to log data header */
int needscan; /* need to rescan data frees */
xfs_trans_t *tp; /* transaction pointer */
xfs_dir2_trace_args_sb("leafn_remove", args, index, bp);
dp = args->dp;
tp = args->trans;
mp = dp->i_mount;
leaf = bp->data;
ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC);
/*
* Point to the entry we're removing.
*/
lep = &leaf->ents[index];
/*
* Extract the data block and offset from the entry.
*/
db = XFS_DIR2_DATAPTR_TO_DB(mp, be32_to_cpu(lep->address));
ASSERT(dblk->blkno == db);
off = XFS_DIR2_DATAPTR_TO_OFF(mp, be32_to_cpu(lep->address));
ASSERT(dblk->index == off);
/*
* Kill the leaf entry by marking it stale.
* Log the leaf block changes.
*/
be16_add(&leaf->hdr.stale, 1);
xfs_dir2_leaf_log_header(tp, bp);
lep->address = cpu_to_be32(XFS_DIR2_NULL_DATAPTR);
xfs_dir2_leaf_log_ents(tp, bp, index, index);
/*
* Make the data entry free. Keep track of the longest freespace
* in the data block in case it changes.
*/
dbp = dblk->bp;
data = dbp->data;
dep = (xfs_dir2_data_entry_t *)((char *)data + off);
longest = be16_to_cpu(data->hdr.bestfree[0].length);
needlog = needscan = 0;
xfs_dir2_data_make_free(tp, dbp, off,
XFS_DIR2_DATA_ENTSIZE(dep->namelen), &needlog, &needscan);
/*
* Rescan the data block freespaces for bestfree.
* Log the data block header if needed.
*/
if (needscan)
xfs_dir2_data_freescan(mp, data, &needlog, NULL);
if (needlog)
xfs_dir2_data_log_header(tp, dbp);
xfs_dir2_data_check(dp, dbp);
/*
* If the longest data block freespace changes, need to update
* the corresponding freeblock entry.
*/
if (longest < be16_to_cpu(data->hdr.bestfree[0].length)) {
int error; /* error return value */
xfs_dabuf_t *fbp; /* freeblock buffer */
xfs_dir2_db_t fdb; /* freeblock block number */
int findex; /* index in freeblock entries */
xfs_dir2_free_t *free; /* freeblock structure */
int logfree; /* need to log free entry */
/*
* Convert the data block number to a free block,
* read in the free block.
*/
fdb = XFS_DIR2_DB_TO_FDB(mp, db);
if ((error = xfs_da_read_buf(tp, dp, XFS_DIR2_DB_TO_DA(mp, fdb),
-1, &fbp, XFS_DATA_FORK))) {
return error;
}
free = fbp->data;
ASSERT(be32_to_cpu(free->hdr.magic) == XFS_DIR2_FREE_MAGIC);
ASSERT(be32_to_cpu(free->hdr.firstdb) ==
XFS_DIR2_MAX_FREE_BESTS(mp) *
(fdb - XFS_DIR2_FREE_FIRSTDB(mp)));
/*
* Calculate which entry we need to fix.
*/
findex = XFS_DIR2_DB_TO_FDINDEX(mp, db);
longest = be16_to_cpu(data->hdr.bestfree[0].length);
/*
* If the data block is now empty we can get rid of it
* (usually).
*/
if (longest == mp->m_dirblksize - (uint)sizeof(data->hdr)) {
/*
* Try to punch out the data block.
*/
error = xfs_dir2_shrink_inode(args, db, dbp);
if (error == 0) {
dblk->bp = NULL;
data = NULL;
}
/*
* We can get ENOSPC if there's no space reservation.
* In this case just drop the buffer and some one else
* will eventually get rid of the empty block.
*/
else if (error == ENOSPC && args->total == 0)
xfs_da_buf_done(dbp);
else
return error;
}
/*
* If we got rid of the data block, we can eliminate that entry
* in the free block.
*/
if (data == NULL) {
/*
* One less used entry in the free table.
*/
be32_add(&free->hdr.nused, -1);
xfs_dir2_free_log_header(tp, fbp);
/*
* If this was the last entry in the table, we can
* trim the table size back. There might be other
* entries at the end referring to non-existent
* data blocks, get those too.
*/
if (findex == be32_to_cpu(free->hdr.nvalid) - 1) {
int i; /* free entry index */
for (i = findex - 1;
i >= 0 && be16_to_cpu(free->bests[i]) == NULLDATAOFF;
i--)
continue;
free->hdr.nvalid = cpu_to_be32(i + 1);
logfree = 0;
}
/*
* Not the last entry, just punch it out.
*/
else {
free->bests[findex] = cpu_to_be16(NULLDATAOFF);
logfree = 1;
}
/*
* If there are no useful entries left in the block,
* get rid of the block if we can.