forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathxfs_dir2_leaf.c
1881 lines (1824 loc) · 53 KB
/
xfs_dir2_leaf.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) 2000-2003,2005 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_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_dir2.h"
#include "xfs_mount.h"
#include "xfs_da_btree.h"
#include "xfs_bmap_btree.h"
#include "xfs_dir2_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_error.h"
#include "xfs_trace.h"
/*
* Local function declarations.
*/
#ifdef DEBUG
static void xfs_dir2_leaf_check(xfs_inode_t *dp, xfs_dabuf_t *bp);
#else
#define xfs_dir2_leaf_check(dp, bp)
#endif
static int xfs_dir2_leaf_lookup_int(xfs_da_args_t *args, xfs_dabuf_t **lbpp,
int *indexp, xfs_dabuf_t **dbpp);
static void xfs_dir2_leaf_log_bests(struct xfs_trans *tp, struct xfs_dabuf *bp,
int first, int last);
static void xfs_dir2_leaf_log_tail(struct xfs_trans *tp, struct xfs_dabuf *bp);
/*
* Convert a block form directory to a leaf form directory.
*/
int /* error */
xfs_dir2_block_to_leaf(
xfs_da_args_t *args, /* operation arguments */
xfs_dabuf_t *dbp) /* input block's buffer */
{
__be16 *bestsp; /* leaf's bestsp entries */
xfs_dablk_t blkno; /* leaf block's bno */
xfs_dir2_block_t *block; /* block structure */
xfs_dir2_leaf_entry_t *blp; /* block's leaf entries */
xfs_dir2_block_tail_t *btp; /* block's tail */
xfs_inode_t *dp; /* incore directory inode */
int error; /* error return code */
xfs_dabuf_t *lbp; /* leaf block's buffer */
xfs_dir2_db_t ldb; /* leaf block's bno */
xfs_dir2_leaf_t *leaf; /* leaf structure */
xfs_dir2_leaf_tail_t *ltp; /* leaf's tail */
xfs_mount_t *mp; /* filesystem mount point */
int needlog; /* need to log block header */
int needscan; /* need to rescan bestfree */
xfs_trans_t *tp; /* transaction pointer */
trace_xfs_dir2_block_to_leaf(args);
dp = args->dp;
mp = dp->i_mount;
tp = args->trans;
/*
* Add the leaf block to the inode.
* This interface will only put blocks in the leaf/node range.
* Since that's empty now, we'll get the root (block 0 in range).
*/
if ((error = xfs_da_grow_inode(args, &blkno))) {
return error;
}
ldb = xfs_dir2_da_to_db(mp, blkno);
ASSERT(ldb == XFS_DIR2_LEAF_FIRSTDB(mp));
/*
* Initialize the leaf block, get a buffer for it.
*/
if ((error = xfs_dir2_leaf_init(args, ldb, &lbp, XFS_DIR2_LEAF1_MAGIC))) {
return error;
}
ASSERT(lbp != NULL);
leaf = lbp->data;
block = dbp->data;
xfs_dir2_data_check(dp, dbp);
btp = xfs_dir2_block_tail_p(mp, block);
blp = xfs_dir2_block_leaf_p(btp);
/*
* Set the counts in the leaf header.
*/
leaf->hdr.count = cpu_to_be16(be32_to_cpu(btp->count));
leaf->hdr.stale = cpu_to_be16(be32_to_cpu(btp->stale));
/*
* Could compact these but I think we always do the conversion
* after squeezing out stale entries.
*/
memcpy(leaf->ents, blp, be32_to_cpu(btp->count) * sizeof(xfs_dir2_leaf_entry_t));
xfs_dir2_leaf_log_ents(tp, lbp, 0, be16_to_cpu(leaf->hdr.count) - 1);
needscan = 0;
needlog = 1;
/*
* Make the space formerly occupied by the leaf entries and block
* tail be free.
*/
xfs_dir2_data_make_free(tp, dbp,
(xfs_dir2_data_aoff_t)((char *)blp - (char *)block),
(xfs_dir2_data_aoff_t)((char *)block + mp->m_dirblksize -
(char *)blp),
&needlog, &needscan);
/*
* Fix up the block header, make it a data block.
*/
block->hdr.magic = cpu_to_be32(XFS_DIR2_DATA_MAGIC);
if (needscan)
xfs_dir2_data_freescan(mp, (xfs_dir2_data_t *)block, &needlog);
/*
* Set up leaf tail and bests table.
*/
ltp = xfs_dir2_leaf_tail_p(mp, leaf);
ltp->bestcount = cpu_to_be32(1);
bestsp = xfs_dir2_leaf_bests_p(ltp);
bestsp[0] = block->hdr.bestfree[0].length;
/*
* Log the data header and leaf bests table.
*/
if (needlog)
xfs_dir2_data_log_header(tp, dbp);
xfs_dir2_leaf_check(dp, lbp);
xfs_dir2_data_check(dp, dbp);
xfs_dir2_leaf_log_bests(tp, lbp, 0, 0);
xfs_da_buf_done(lbp);
return 0;
}
/*
* Add an entry to a leaf form directory.
*/
int /* error */
xfs_dir2_leaf_addname(
xfs_da_args_t *args) /* operation arguments */
{
__be16 *bestsp; /* freespace table in leaf */
int compact; /* need to compact leaves */
xfs_dir2_data_t *data; /* data block structure */
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_data_unused_t *dup; /* data unused entry */
int error; /* error return value */
int grown; /* allocated new data block */
int highstale; /* index of next stale leaf */
int i; /* temporary, index */
int index; /* leaf table position */
xfs_dabuf_t *lbp; /* leaf's buffer */
xfs_dir2_leaf_t *leaf; /* leaf structure */
int length; /* length of new entry */
xfs_dir2_leaf_entry_t *lep; /* leaf entry table pointer */
int lfloglow; /* low leaf logging index */
int lfloghigh; /* high leaf logging index */
int lowstale; /* index of prev stale leaf */
xfs_dir2_leaf_tail_t *ltp; /* leaf tail pointer */
xfs_mount_t *mp; /* filesystem mount point */
int needbytes; /* leaf block bytes needed */
int needlog; /* need to log data header */
int needscan; /* need to rescan data free */
__be16 *tagp; /* end of data entry */
xfs_trans_t *tp; /* transaction pointer */
xfs_dir2_db_t use_block; /* data block number */
trace_xfs_dir2_leaf_addname(args);
dp = args->dp;
tp = args->trans;
mp = dp->i_mount;
/*
* Read the leaf block.
*/
error = xfs_da_read_buf(tp, dp, mp->m_dirleafblk, -1, &lbp,
XFS_DATA_FORK);
if (error) {
return error;
}
ASSERT(lbp != NULL);
/*
* Look up the entry by hash value and name.
* We know it's not there, our caller has already done a lookup.
* So the index is of the entry to insert in front of.
* But if there are dup hash values the index is of the first of those.
*/
index = xfs_dir2_leaf_search_hash(args, lbp);
leaf = lbp->data;
ltp = xfs_dir2_leaf_tail_p(mp, leaf);
bestsp = xfs_dir2_leaf_bests_p(ltp);
length = xfs_dir2_data_entsize(args->namelen);
/*
* See if there are any entries with the same hash value
* and space in their block for the new entry.
* This is good because it puts multiple same-hash value entries
* in a data block, improving the lookup of those entries.
*/
for (use_block = -1, lep = &leaf->ents[index];
index < be16_to_cpu(leaf->hdr.count) && be32_to_cpu(lep->hashval) == args->hashval;
index++, lep++) {
if (be32_to_cpu(lep->address) == XFS_DIR2_NULL_DATAPTR)
continue;
i = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address));
ASSERT(i < be32_to_cpu(ltp->bestcount));
ASSERT(be16_to_cpu(bestsp[i]) != NULLDATAOFF);
if (be16_to_cpu(bestsp[i]) >= length) {
use_block = i;
break;
}
}
/*
* Didn't find a block yet, linear search all the data blocks.
*/
if (use_block == -1) {
for (i = 0; i < be32_to_cpu(ltp->bestcount); i++) {
/*
* Remember a block we see that's missing.
*/
if (be16_to_cpu(bestsp[i]) == NULLDATAOFF && use_block == -1)
use_block = i;
else if (be16_to_cpu(bestsp[i]) >= length) {
use_block = i;
break;
}
}
}
/*
* How many bytes do we need in the leaf block?
*/
needbytes =
(leaf->hdr.stale ? 0 : (uint)sizeof(leaf->ents[0])) +
(use_block != -1 ? 0 : (uint)sizeof(leaf->bests[0]));
/*
* Now kill use_block if it refers to a missing block, so we
* can use it as an indication of allocation needed.
*/
if (use_block != -1 && be16_to_cpu(bestsp[use_block]) == NULLDATAOFF)
use_block = -1;
/*
* If we don't have enough free bytes but we can make enough
* by compacting out stale entries, we'll do that.
*/
if ((char *)bestsp - (char *)&leaf->ents[be16_to_cpu(leaf->hdr.count)] <
needbytes && be16_to_cpu(leaf->hdr.stale) > 1) {
compact = 1;
}
/*
* Otherwise if we don't have enough free bytes we need to
* convert to node form.
*/
else if ((char *)bestsp - (char *)&leaf->ents[be16_to_cpu(
leaf->hdr.count)] < needbytes) {
/*
* Just checking or no space reservation, give up.
*/
if ((args->op_flags & XFS_DA_OP_JUSTCHECK) ||
args->total == 0) {
xfs_da_brelse(tp, lbp);
return XFS_ERROR(ENOSPC);
}
/*
* Convert to node form.
*/
error = xfs_dir2_leaf_to_node(args, lbp);
xfs_da_buf_done(lbp);
if (error)
return error;
/*
* Then add the new entry.
*/
return xfs_dir2_node_addname(args);
}
/*
* Otherwise it will fit without compaction.
*/
else
compact = 0;
/*
* If just checking, then it will fit unless we needed to allocate
* a new data block.
*/
if (args->op_flags & XFS_DA_OP_JUSTCHECK) {
xfs_da_brelse(tp, lbp);
return use_block == -1 ? XFS_ERROR(ENOSPC) : 0;
}
/*
* If no allocations are allowed, return now before we've
* changed anything.
*/
if (args->total == 0 && use_block == -1) {
xfs_da_brelse(tp, lbp);
return XFS_ERROR(ENOSPC);
}
/*
* Need to compact the leaf entries, removing stale ones.
* Leave one stale entry behind - the one closest to our
* insertion index - and we'll shift that one to our insertion
* point later.
*/
if (compact) {
xfs_dir2_leaf_compact_x1(lbp, &index, &lowstale, &highstale,
&lfloglow, &lfloghigh);
}
/*
* There are stale entries, so we'll need log-low and log-high
* impossibly bad values later.
*/
else if (be16_to_cpu(leaf->hdr.stale)) {
lfloglow = be16_to_cpu(leaf->hdr.count);
lfloghigh = -1;
}
/*
* If there was no data block space found, we need to allocate
* a new one.
*/
if (use_block == -1) {
/*
* Add the new data block.
*/
if ((error = xfs_dir2_grow_inode(args, XFS_DIR2_DATA_SPACE,
&use_block))) {
xfs_da_brelse(tp, lbp);
return error;
}
/*
* Initialize the block.
*/
if ((error = xfs_dir2_data_init(args, use_block, &dbp))) {
xfs_da_brelse(tp, lbp);
return error;
}
/*
* If we're adding a new data block on the end we need to
* extend the bests table. Copy it up one entry.
*/
if (use_block >= be32_to_cpu(ltp->bestcount)) {
bestsp--;
memmove(&bestsp[0], &bestsp[1],
be32_to_cpu(ltp->bestcount) * sizeof(bestsp[0]));
be32_add_cpu(<p->bestcount, 1);
xfs_dir2_leaf_log_tail(tp, lbp);
xfs_dir2_leaf_log_bests(tp, lbp, 0, be32_to_cpu(ltp->bestcount) - 1);
}
/*
* If we're filling in a previously empty block just log it.
*/
else
xfs_dir2_leaf_log_bests(tp, lbp, use_block, use_block);
data = dbp->data;
bestsp[use_block] = data->hdr.bestfree[0].length;
grown = 1;
}
/*
* Already had space in some data block.
* Just read that one in.
*/
else {
if ((error =
xfs_da_read_buf(tp, dp, xfs_dir2_db_to_da(mp, use_block),
-1, &dbp, XFS_DATA_FORK))) {
xfs_da_brelse(tp, lbp);
return error;
}
data = dbp->data;
grown = 0;
}
xfs_dir2_data_check(dp, dbp);
/*
* Point to the biggest freespace in our data block.
*/
dup = (xfs_dir2_data_unused_t *)
((char *)data + be16_to_cpu(data->hdr.bestfree[0].offset));
ASSERT(be16_to_cpu(dup->length) >= length);
needscan = needlog = 0;
/*
* Mark the initial part of our freespace in use for the new entry.
*/
xfs_dir2_data_use_free(tp, dbp, dup,
(xfs_dir2_data_aoff_t)((char *)dup - (char *)data), length,
&needlog, &needscan);
/*
* Initialize our new entry (at last).
*/
dep = (xfs_dir2_data_entry_t *)dup;
dep->inumber = cpu_to_be64(args->inumber);
dep->namelen = args->namelen;
memcpy(dep->name, args->name, dep->namelen);
tagp = xfs_dir2_data_entry_tag_p(dep);
*tagp = cpu_to_be16((char *)dep - (char *)data);
/*
* Need to scan fix up the bestfree table.
*/
if (needscan)
xfs_dir2_data_freescan(mp, data, &needlog);
/*
* Need to log the data block's header.
*/
if (needlog)
xfs_dir2_data_log_header(tp, dbp);
xfs_dir2_data_log_entry(tp, dbp, dep);
/*
* If the bests table needs to be changed, do it.
* Log the change unless we've already done that.
*/
if (be16_to_cpu(bestsp[use_block]) != be16_to_cpu(data->hdr.bestfree[0].length)) {
bestsp[use_block] = data->hdr.bestfree[0].length;
if (!grown)
xfs_dir2_leaf_log_bests(tp, lbp, use_block, use_block);
}
/*
* Now we need to make room to insert the leaf entry.
* If there are no stale entries, we just insert a hole at index.
*/
if (!leaf->hdr.stale) {
/*
* lep is still good as the index leaf entry.
*/
if (index < be16_to_cpu(leaf->hdr.count))
memmove(lep + 1, lep,
(be16_to_cpu(leaf->hdr.count) - index) * sizeof(*lep));
/*
* Record low and high logging indices for the leaf.
*/
lfloglow = index;
lfloghigh = be16_to_cpu(leaf->hdr.count);
be16_add_cpu(&leaf->hdr.count, 1);
}
/*
* There are stale entries.
* We will use one of them for the new entry.
* It's probably not at the right location, so we'll have to
* shift some up or down first.
*/
else {
/*
* If we didn't compact before, we need to find the nearest
* stale entries before and after our insertion point.
*/
if (compact == 0) {
/*
* Find the first stale entry before the insertion
* point, if any.
*/
for (lowstale = index - 1;
lowstale >= 0 &&
be32_to_cpu(leaf->ents[lowstale].address) !=
XFS_DIR2_NULL_DATAPTR;
lowstale--)
continue;
/*
* Find the next stale entry at or after the insertion
* point, if any. Stop if we go so far that the
* lowstale entry would be better.
*/
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;
}
/*
* If the low one is better, use it.
*/
if (lowstale >= 0 &&
(highstale == be16_to_cpu(leaf->hdr.count) ||
index - lowstale - 1 < highstale - index)) {
ASSERT(index - lowstale - 1 >= 0);
ASSERT(be32_to_cpu(leaf->ents[lowstale].address) ==
XFS_DIR2_NULL_DATAPTR);
/*
* Copy entries up to cover the stale entry
* and make room for the new entry.
*/
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);
}
/*
* The high one is better, so use that one.
*/
else {
ASSERT(highstale - index >= 0);
ASSERT(be32_to_cpu(leaf->ents[highstale].address) ==
XFS_DIR2_NULL_DATAPTR);
/*
* Copy entries down to cover the stale entry
* and make room for the new entry.
*/
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_cpu(&leaf->hdr.stale, -1);
}
/*
* Fill in the new leaf entry.
*/
lep->hashval = cpu_to_be32(args->hashval);
lep->address = cpu_to_be32(xfs_dir2_db_off_to_dataptr(mp, use_block,
be16_to_cpu(*tagp)));
/*
* Log the leaf fields and give up the buffers.
*/
xfs_dir2_leaf_log_header(tp, lbp);
xfs_dir2_leaf_log_ents(tp, lbp, lfloglow, lfloghigh);
xfs_dir2_leaf_check(dp, lbp);
xfs_da_buf_done(lbp);
xfs_dir2_data_check(dp, dbp);
xfs_da_buf_done(dbp);
return 0;
}
#ifdef DEBUG
/*
* Check the internal consistency of a leaf1 block.
* Pop an assert if something is wrong.
*/
STATIC void
xfs_dir2_leaf_check(
xfs_inode_t *dp, /* incore directory inode */
xfs_dabuf_t *bp) /* leaf's buffer */
{
int i; /* leaf index */
xfs_dir2_leaf_t *leaf; /* leaf structure */
xfs_dir2_leaf_tail_t *ltp; /* leaf tail pointer */
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_LEAF1_MAGIC);
/*
* This value is not restrictive enough.
* Should factor in the size of the bests table as well.
* We can deduce a value for that from di_size.
*/
ASSERT(be16_to_cpu(leaf->hdr.count) <= xfs_dir2_max_leaf_ents(mp));
ltp = xfs_dir2_leaf_tail_p(mp, leaf);
/*
* Leaves and bests don't overlap.
*/
ASSERT((char *)&leaf->ents[be16_to_cpu(leaf->hdr.count)] <=
(char *)xfs_dir2_leaf_bests_p(ltp));
/*
* Check hash value order, count stale entries.
*/
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 */
/*
* Compact out any stale entries in the leaf.
* Log the header and changed leaf entries, if any.
*/
void
xfs_dir2_leaf_compact(
xfs_da_args_t *args, /* operation arguments */
xfs_dabuf_t *bp) /* leaf buffer */
{
int from; /* source leaf index */
xfs_dir2_leaf_t *leaf; /* leaf structure */
int loglow; /* first leaf entry to log */
int to; /* target leaf index */
leaf = bp->data;
if (!leaf->hdr.stale) {
return;
}
/*
* Compress out the stale entries in place.
*/
for (from = to = 0, loglow = -1; from < be16_to_cpu(leaf->hdr.count); from++) {
if (be32_to_cpu(leaf->ents[from].address) == XFS_DIR2_NULL_DATAPTR)
continue;
/*
* Only actually copy the entries that are different.
*/
if (from > to) {
if (loglow == -1)
loglow = to;
leaf->ents[to] = leaf->ents[from];
}
to++;
}
/*
* Update and log the header, log the leaf entries.
*/
ASSERT(be16_to_cpu(leaf->hdr.stale) == from - to);
be16_add_cpu(&leaf->hdr.count, -(be16_to_cpu(leaf->hdr.stale)));
leaf->hdr.stale = 0;
xfs_dir2_leaf_log_header(args->trans, bp);
if (loglow != -1)
xfs_dir2_leaf_log_ents(args->trans, bp, loglow, to - 1);
}
/*
* Compact the leaf entries, removing stale ones.
* Leave one stale entry behind - the one closest to our
* insertion index - and the caller will shift that one to our insertion
* point later.
* Return new insertion index, where the remaining stale entry is,
* and leaf logging indices.
*/
void
xfs_dir2_leaf_compact_x1(
xfs_dabuf_t *bp, /* leaf buffer */
int *indexp, /* insertion index */
int *lowstalep, /* out: stale entry before us */
int *highstalep, /* out: stale entry after us */
int *lowlogp, /* out: low log index */
int *highlogp) /* out: high log index */
{
int from; /* source copy index */
int highstale; /* stale entry at/after index */
int index; /* insertion index */
int keepstale; /* source index of kept stale */
xfs_dir2_leaf_t *leaf; /* leaf structure */
int lowstale; /* stale entry before index */
int newindex=0; /* new insertion index */
int to; /* destination copy index */
leaf = bp->data;
ASSERT(be16_to_cpu(leaf->hdr.stale) > 1);
index = *indexp;
/*
* Find the first stale entry before our index, if any.
*/
for (lowstale = index - 1;
lowstale >= 0 &&
be32_to_cpu(leaf->ents[lowstale].address) != XFS_DIR2_NULL_DATAPTR;
lowstale--)
continue;
/*
* Find the first stale entry at or after our index, if any.
* Stop if the answer would be worse than lowstale.
*/
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 > highstale - index);
highstale++)
continue;
/*
* Pick the better of lowstale and highstale.
*/
if (lowstale >= 0 &&
(highstale == be16_to_cpu(leaf->hdr.count) ||
index - lowstale <= highstale - index))
keepstale = lowstale;
else
keepstale = highstale;
/*
* Copy the entries in place, removing all the stale entries
* except keepstale.
*/
for (from = to = 0; from < be16_to_cpu(leaf->hdr.count); from++) {
/*
* Notice the new value of index.
*/
if (index == from)
newindex = to;
if (from != keepstale &&
be32_to_cpu(leaf->ents[from].address) == XFS_DIR2_NULL_DATAPTR) {
if (from == to)
*lowlogp = to;
continue;
}
/*
* Record the new keepstale value for the insertion.
*/
if (from == keepstale)
lowstale = highstale = to;
/*
* Copy only the entries that have moved.
*/
if (from > to)
leaf->ents[to] = leaf->ents[from];
to++;
}
ASSERT(from > to);
/*
* If the insertion point was past the last entry,
* set the new insertion point accordingly.
*/
if (index == from)
newindex = to;
*indexp = newindex;
/*
* Adjust the leaf header values.
*/
be16_add_cpu(&leaf->hdr.count, -(from - to));
leaf->hdr.stale = cpu_to_be16(1);
/*
* Remember the low/high stale value only in the "right"
* direction.
*/
if (lowstale >= newindex)
lowstale = -1;
else
highstale = be16_to_cpu(leaf->hdr.count);
*highlogp = be16_to_cpu(leaf->hdr.count) - 1;
*lowstalep = lowstale;
*highstalep = highstale;
}
/*
* Getdents (readdir) for leaf and node directories.
* This reads the data blocks only, so is the same for both forms.
*/
int /* error */
xfs_dir2_leaf_getdents(
xfs_inode_t *dp, /* incore directory inode */
void *dirent,
size_t bufsize,
xfs_off_t *offset,
filldir_t filldir)
{
xfs_dabuf_t *bp; /* data block buffer */
int byteoff; /* offset in current block */
xfs_dir2_db_t curdb; /* db for current block */
xfs_dir2_off_t curoff; /* current overall offset */
xfs_dir2_data_t *data; /* data block structure */
xfs_dir2_data_entry_t *dep; /* data entry */
xfs_dir2_data_unused_t *dup; /* unused entry */
int error = 0; /* error return value */
int i; /* temporary loop index */
int j; /* temporary loop index */
int length; /* temporary length value */
xfs_bmbt_irec_t *map; /* map vector for blocks */
xfs_extlen_t map_blocks; /* number of fsbs in map */
xfs_dablk_t map_off; /* last mapped file offset */
int map_size; /* total entries in *map */
int map_valid; /* valid entries in *map */
xfs_mount_t *mp; /* filesystem mount point */
xfs_dir2_off_t newoff; /* new curoff after new blk */
int nmap; /* mappings to ask xfs_bmapi */
char *ptr = NULL; /* pointer to current data */
int ra_current; /* number of read-ahead blks */
int ra_index; /* *map index for read-ahead */
int ra_offset; /* map entry offset for ra */
int ra_want; /* readahead count wanted */
/*
* If the offset is at or past the largest allowed value,
* give up right away.
*/
if (*offset >= XFS_DIR2_MAX_DATAPTR)
return 0;
mp = dp->i_mount;
/*
* Set up to bmap a number of blocks based on the caller's
* buffer size, the directory block size, and the filesystem
* block size.
*/
map_size = howmany(bufsize + mp->m_dirblksize, mp->m_sb.sb_blocksize);
map = kmem_alloc(map_size * sizeof(*map), KM_SLEEP);
map_valid = ra_index = ra_offset = ra_current = map_blocks = 0;
bp = NULL;
/*
* Inside the loop we keep the main offset value as a byte offset
* in the directory file.
*/
curoff = xfs_dir2_dataptr_to_byte(mp, *offset);
/*
* Force this conversion through db so we truncate the offset
* down to get the start of the data block.
*/
map_off = xfs_dir2_db_to_da(mp, xfs_dir2_byte_to_db(mp, curoff));
/*
* Loop over directory entries until we reach the end offset.
* Get more blocks and readahead as necessary.
*/
while (curoff < XFS_DIR2_LEAF_OFFSET) {
/*
* If we have no buffer, or we're off the end of the
* current buffer, need to get another one.
*/
if (!bp || ptr >= (char *)bp->data + mp->m_dirblksize) {
/*
* If we have a buffer, we need to release it and
* take it out of the mapping.
*/
if (bp) {
xfs_da_brelse(NULL, bp);
bp = NULL;
map_blocks -= mp->m_dirblkfsbs;
/*
* Loop to get rid of the extents for the
* directory block.
*/
for (i = mp->m_dirblkfsbs; i > 0; ) {
j = MIN((int)map->br_blockcount, i);
map->br_blockcount -= j;
map->br_startblock += j;
map->br_startoff += j;
/*
* If mapping is done, pitch it from
* the table.
*/
if (!map->br_blockcount && --map_valid)
memmove(&map[0], &map[1],
sizeof(map[0]) *
map_valid);
i -= j;
}
}
/*
* Recalculate the readahead blocks wanted.
*/
ra_want = howmany(bufsize + mp->m_dirblksize,
mp->m_sb.sb_blocksize) - 1;
ASSERT(ra_want >= 0);
/*
* If we don't have as many as we want, and we haven't
* run out of data blocks, get some more mappings.
*/
if (1 + ra_want > map_blocks &&
map_off <
xfs_dir2_byte_to_da(mp, XFS_DIR2_LEAF_OFFSET)) {
/*
* Get more bmaps, fill in after the ones
* we already have in the table.
*/
nmap = map_size - map_valid;
error = xfs_bmapi(NULL, dp,
map_off,
xfs_dir2_byte_to_da(mp,
XFS_DIR2_LEAF_OFFSET) - map_off,
XFS_BMAPI_METADATA, NULL, 0,
&map[map_valid], &nmap, NULL);
/*
* Don't know if we should ignore this or
* try to return an error.
* The trouble with returning errors
* is that readdir will just stop without
* actually passing the error through.
*/
if (error)
break; /* XXX */
/*
* If we got all the mappings we asked for,
* set the final map offset based on the
* last bmap value received.
* Otherwise, we've reached the end.
*/
if (nmap == map_size - map_valid)
map_off =
map[map_valid + nmap - 1].br_startoff +
map[map_valid + nmap - 1].br_blockcount;
else
map_off =
xfs_dir2_byte_to_da(mp,
XFS_DIR2_LEAF_OFFSET);
/*
* Look for holes in the mapping, and
* eliminate them. Count up the valid blocks.
*/
for (i = map_valid; i < map_valid + nmap; ) {
if (map[i].br_startblock ==
HOLESTARTBLOCK) {
nmap--;
length = map_valid + nmap - i;
if (length)
memmove(&map[i],
&map[i + 1],
sizeof(map[i]) *
length);
} else {
map_blocks +=
map[i].br_blockcount;
i++;
}
}
map_valid += nmap;
}
/*
* No valid mappings, so no more data blocks.
*/
if (!map_valid) {
curoff = xfs_dir2_da_to_byte(mp, map_off);
break;
}
/*
* Read the directory block starting at the first
* mapping.
*/
curdb = xfs_dir2_da_to_db(mp, map->br_startoff);
error = xfs_da_read_buf(NULL, dp, map->br_startoff,
map->br_blockcount >= mp->m_dirblkfsbs ?
XFS_FSB_TO_DADDR(mp, map->br_startblock) :
-1,
&bp, XFS_DATA_FORK);
/*
* Should just skip over the data block instead
* of giving up.
*/
if (error)
break; /* XXX */
/*
* Adjust the current amount of read-ahead: we just
* read a block that was previously ra.
*/
if (ra_current)
ra_current -= mp->m_dirblkfsbs;
/*
* Do we need more readahead?
*/
for (ra_index = ra_offset = i = 0;
ra_want > ra_current && i < map_blocks;
i += mp->m_dirblkfsbs) {
ASSERT(ra_index < map_valid);
/*
* Read-ahead a contiguous directory block.
*/
if (i > ra_current &&
map[ra_index].br_blockcount >=
mp->m_dirblkfsbs) {
xfs_buf_readahead(mp->m_ddev_targp,
XFS_FSB_TO_DADDR(mp,
map[ra_index].br_startblock +
ra_offset),
(int)BTOBB(mp->m_dirblksize));
ra_current = i;
}
/*
* Read-ahead a non-contiguous directory block.
* This doesn't use our mapping, but this
* is a very rare case.
*/
else if (i > ra_current) {
(void)xfs_da_reada_buf(NULL, dp,
map[ra_index].br_startoff +
ra_offset, XFS_DATA_FORK);
ra_current = i;
}
/*
* Advance offset through the mapping table.
*/
for (j = 0; j < mp->m_dirblkfsbs; j++) {
/*
* The rest of this extent but not
* more than a dir block.
*/
length = MIN(mp->m_dirblkfsbs,
(int)(map[ra_index].br_blockcount -
ra_offset));
j += length;
ra_offset += length;
/*
* Advance to the next mapping if
* this one is used up.
*/
if (ra_offset ==
map[ra_index].br_blockcount) {