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
|
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2017 Christoph Hellwig.
*/
#include "xfs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_bit.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_trace.h"
/*
* In-core extent record layout:
*
* +-------+----------------------------+
* | 00:53 | all 54 bits of startoff |
* | 54:63 | low 10 bits of startblock |
* +-------+----------------------------+
* | 00:20 | all 21 bits of length |
* | 21 | unwritten extent bit |
* | 22:63 | high 42 bits of startblock |
* +-------+----------------------------+
*/
#define XFS_IEXT_STARTOFF_MASK xfs_mask64lo(BMBT_STARTOFF_BITLEN)
#define XFS_IEXT_LENGTH_MASK xfs_mask64lo(BMBT_BLOCKCOUNT_BITLEN)
#define XFS_IEXT_STARTBLOCK_MASK xfs_mask64lo(BMBT_STARTBLOCK_BITLEN)
struct xfs_iext_rec {
uint64_t lo;
uint64_t hi;
};
/*
* Given that the length can't be a zero, only an empty hi value indicates an
* unused record.
*/
static bool xfs_iext_rec_is_empty(struct xfs_iext_rec *rec)
{
return rec->hi == 0;
}
static inline void xfs_iext_rec_clear(struct xfs_iext_rec *rec)
{
rec->lo = 0;
rec->hi = 0;
}
static void
xfs_iext_set(
struct xfs_iext_rec *rec,
struct xfs_bmbt_irec *irec)
{
ASSERT((irec->br_startoff & ~XFS_IEXT_STARTOFF_MASK) == 0);
ASSERT((irec->br_blockcount & ~XFS_IEXT_LENGTH_MASK) == 0);
ASSERT((irec->br_startblock & ~XFS_IEXT_STARTBLOCK_MASK) == 0);
rec->lo = irec->br_startoff & XFS_IEXT_STARTOFF_MASK;
rec->hi = irec->br_blockcount & XFS_IEXT_LENGTH_MASK;
rec->lo |= (irec->br_startblock << 54);
rec->hi |= ((irec->br_startblock & ~xfs_mask64lo(10)) << (22 - 10));
if (irec->br_state == XFS_EXT_UNWRITTEN)
rec->hi |= (1 << 21);
}
static void
xfs_iext_get(
struct xfs_bmbt_irec *irec,
struct xfs_iext_rec *rec)
{
irec->br_startoff = rec->lo & XFS_IEXT_STARTOFF_MASK;
irec->br_blockcount = rec->hi & XFS_IEXT_LENGTH_MASK;
irec->br_startblock = rec->lo >> 54;
irec->br_startblock |= (rec->hi & xfs_mask64hi(42)) >> (22 - 10);
if (rec->hi & (1 << 21))
irec->br_state = XFS_EXT_UNWRITTEN;
else
irec->br_state = XFS_EXT_NORM;
}
enum {
NODE_SIZE = 256,
KEYS_PER_NODE = NODE_SIZE / (sizeof(uint64_t) + sizeof(void *)),
RECS_PER_LEAF = (NODE_SIZE - (2 * sizeof(struct xfs_iext_leaf *))) /
sizeof(struct xfs_iext_rec),
};
/*
* In-core extent btree block layout:
*
* There are two types of blocks in the btree: leaf and inner (non-leaf) blocks.
*
* The leaf blocks are made up by %KEYS_PER_NODE extent records, which each
* contain the startoffset, blockcount, startblock and unwritten extent flag.
* See above for the exact format, followed by pointers to the previous and next
* leaf blocks (if there are any).
*
* The inner (non-leaf) blocks first contain KEYS_PER_NODE lookup keys, followed
* by an equal number of pointers to the btree blocks at the next lower level.
*
* +-------+-------+-------+-------+-------+----------+----------+
* Leaf: | rec 1 | rec 2 | rec 3 | rec 4 | rec N | prev-ptr | next-ptr |
* +-------+-------+-------+-------+-------+----------+----------+
*
* +-------+-------+-------+-------+-------+-------+------+-------+
* Inner: | key 1 | key 2 | key 3 | key N | ptr 1 | ptr 2 | ptr3 | ptr N |
* +-------+-------+-------+-------+-------+-------+------+-------+
*/
struct xfs_iext_node {
uint64_t keys[KEYS_PER_NODE];
#define XFS_IEXT_KEY_INVALID (1ULL << 63)
void *ptrs[KEYS_PER_NODE];
};
struct xfs_iext_leaf {
struct xfs_iext_rec recs[RECS_PER_LEAF];
struct xfs_iext_leaf *prev;
struct xfs_iext_leaf *next;
};
inline xfs_extnum_t xfs_iext_count(struct xfs_ifork *ifp)
{
return ifp->if_bytes / sizeof(struct xfs_iext_rec);
}
static inline int xfs_iext_max_recs(struct xfs_ifork *ifp)
{
if (ifp->if_height == 1)
return xfs_iext_count(ifp);
return RECS_PER_LEAF;
}
static inline struct xfs_iext_rec *cur_rec(struct xfs_iext_cursor *cur)
{
return &cur->leaf->recs[cur->pos];
}
static inline bool xfs_iext_valid(struct xfs_ifork *ifp,
struct xfs_iext_cursor *cur)
{
if (!cur->leaf)
return false;
if (cur->pos < 0 || cur->pos >= xfs_iext_max_recs(ifp))
return false;
if (xfs_iext_rec_is_empty(cur_rec(cur)))
return false;
return true;
}
static void *
xfs_iext_find_first_leaf(
struct xfs_ifork *ifp)
{
struct xfs_iext_node *node = ifp->if_data;
int height;
if (!ifp->if_height)
return NULL;
for (height = ifp->if_height; height > 1; height--) {
node = node->ptrs[0];
ASSERT(node);
}
return node;
}
static void *
xfs_iext_find_last_leaf(
struct xfs_ifork *ifp)
{
struct xfs_iext_node *node = ifp->if_data;
int height, i;
if (!ifp->if_height)
return NULL;
for (height = ifp->if_height; height > 1; height--) {
for (i = 1; i < KEYS_PER_NODE; i++)
if (!node->ptrs[i])
break;
node = node->ptrs[i - 1];
ASSERT(node);
}
return node;
}
void
xfs_iext_first(
struct xfs_ifork *ifp,
struct xfs_iext_cursor *cur)
{
cur->pos = 0;
cur->leaf = xfs_iext_find_first_leaf(ifp);
}
void
xfs_iext_last(
struct xfs_ifork *ifp,
struct xfs_iext_cursor *cur)
{
int i;
cur->leaf = xfs_iext_find_last_leaf(ifp);
if (!cur->leaf) {
cur->pos = 0;
return;
}
for (i = 1; i < xfs_iext_max_recs(ifp); i++) {
if (xfs_iext_rec_is_empty(&cur->leaf->recs[i]))
break;
}
cur->pos = i - 1;
}
void
xfs_iext_next(
struct xfs_ifork *ifp,
struct xfs_iext_cursor *cur)
{
if (!cur->leaf) {
ASSERT(cur->pos <= 0 || cur->pos >= RECS_PER_LEAF);
xfs_iext_first(ifp, cur);
return;
}
ASSERT(cur->pos >= 0);
ASSERT(cur->pos < xfs_iext_max_recs(ifp));
cur->pos++;
if (ifp->if_height > 1 && !xfs_iext_valid(ifp, cur) &&
cur->leaf->next) {
cur->leaf = cur->leaf->next;
cur->pos = 0;
}
}
void
xfs_iext_prev(
struct xfs_ifork *ifp,
struct xfs_iext_cursor *cur)
{
if (!cur->leaf) {
ASSERT(cur->pos <= 0 || cur->pos >= RECS_PER_LEAF);
xfs_iext_last(ifp, cur);
return;
}
ASSERT(cur->pos >= 0);
ASSERT(cur->pos <= RECS_PER_LEAF);
recurse:
do {
cur->pos--;
if (xfs_iext_valid(ifp, cur))
return;
} while (cur->pos > 0);
if (ifp->if_height > 1 && cur->leaf->prev) {
cur->leaf = cur->leaf->prev;
cur->pos = RECS_PER_LEAF;
goto recurse;
}
}
static inline int
xfs_iext_key_cmp(
struct xfs_iext_node *node,
int n,
xfs_fileoff_t offset)
{
if (node->keys[n] > offset)
return 1;
if (node->keys[n] < offset)
return -1;
return 0;
}
static inline int
xfs_iext_rec_cmp(
struct xfs_iext_rec *rec,
xfs_fileoff_t offset)
{
uint64_t rec_offset = rec->lo & XFS_IEXT_STARTOFF_MASK;
uint32_t rec_len = rec->hi & XFS_IEXT_LENGTH_MASK;
if (rec_offset > offset)
return 1;
if (rec_offset + rec_len <= offset)
return -1;
return 0;
}
static void *
xfs_iext_find_level(
struct xfs_ifork *ifp,
xfs_fileoff_t offset,
int level)
{
struct xfs_iext_node *node = ifp->if_data;
int height, i;
if (!ifp->if_height)
return NULL;
for (height = ifp->if_height; height > level; height--) {
for (i = 1; i < KEYS_PER_NODE; i++)
if (xfs_iext_key_cmp(node, i, offset) > 0)
break;
node = node->ptrs[i - 1];
if (!node)
break;
}
return node;
}
static int
xfs_iext_node_pos(
struct xfs_iext_node *node,
xfs_fileoff_t offset)
{
int i;
for (i = 1; i < KEYS_PER_NODE; i++) {
if (xfs_iext_key_cmp(node, i, offset) > 0)
break;
}
return i - 1;
}
static int
xfs_iext_node_insert_pos(
struct xfs_iext_node *node,
xfs_fileoff_t offset)
{
int i;
for (i = 0; i < KEYS_PER_NODE; i++) {
if (xfs_iext_key_cmp(node, i, offset) > 0)
return i;
}
return KEYS_PER_NODE;
}
static int
xfs_iext_node_nr_entries(
struct xfs_iext_node *node,
int start)
{
int i;
for (i = start; i < KEYS_PER_NODE; i++) {
if (node->keys[i] == XFS_IEXT_KEY_INVALID)
break;
}
return i;
}
static int
xfs_iext_leaf_nr_entries(
struct xfs_ifork *ifp,
struct xfs_iext_leaf *leaf,
int start)
{
int i;
for (i = start; i < xfs_iext_max_recs(ifp); i++) {
if (xfs_iext_rec_is_empty(&leaf->recs[i]))
break;
}
return i;
}
static inline uint64_t
xfs_iext_leaf_key(
struct xfs_iext_leaf *leaf,
int n)
{
return leaf->recs[n].lo & XFS_IEXT_STARTOFF_MASK;
}
static void
xfs_iext_grow(
struct xfs_ifork *ifp)
{
struct xfs_iext_node *node = kzalloc(NODE_SIZE,
GFP_NOFS | __GFP_NOFAIL);
int i;
if (ifp->if_height == 1) {
struct xfs_iext_leaf *prev = ifp->if_data;
node->keys[0] = xfs_iext_leaf_key(prev, 0);
node->ptrs[0] = prev;
} else {
struct xfs_iext_node *prev = ifp->if_data;
ASSERT(ifp->if_height > 1);
node->keys[0] = prev->keys[0];
node->ptrs[0] = prev;
}
for (i = 1; i < KEYS_PER_NODE; i++)
node->keys[i] = XFS_IEXT_KEY_INVALID;
ifp->if_data = node;
ifp->if_height++;
}
static void
xfs_iext_update_node(
struct xfs_ifork *ifp,
xfs_fileoff_t old_offset,
xfs_fileoff_t new_offset,
int level,
void *ptr)
{
struct xfs_iext_node *node = ifp->if_data;
int height, i;
for (height = ifp->if_height; height > level; height--) {
for (i = 0; i < KEYS_PER_NODE; i++) {
if (i > 0 && xfs_iext_key_cmp(node, i, old_offset) > 0)
break;
if (node->keys[i] == old_offset)
node->keys[i] = new_offset;
}
node = node->ptrs[i - 1];
ASSERT(node);
}
ASSERT(node == ptr);
}
static struct xfs_iext_node *
xfs_iext_split_node(
struct xfs_iext_node **nodep,
int *pos,
int *nr_entries)
{
struct xfs_iext_node *node = *nodep;
struct xfs_iext_node *new = kzalloc(NODE_SIZE,
GFP_NOFS | __GFP_NOFAIL);
const int nr_move = KEYS_PER_NODE / 2;
int nr_keep = nr_move + (KEYS_PER_NODE & 1);
int i = 0;
/* for sequential append operations just spill over into the new node */
if (*pos == KEYS_PER_NODE) {
*nodep = new;
*pos = 0;
*nr_entries = 0;
goto done;
}
for (i = 0; i < nr_move; i++) {
new->keys[i] = node->keys[nr_keep + i];
new->ptrs[i] = node->ptrs[nr_keep + i];
node->keys[nr_keep + i] = XFS_IEXT_KEY_INVALID;
node->ptrs[nr_keep + i] = NULL;
}
if (*pos >= nr_keep) {
*nodep = new;
*pos -= nr_keep;
*nr_entries = nr_move;
} else {
*nr_entries = nr_keep;
}
done:
for (; i < KEYS_PER_NODE; i++)
new->keys[i] = XFS_IEXT_KEY_INVALID;
return new;
}
static void
xfs_iext_insert_node(
struct xfs_ifork *ifp,
uint64_t offset,
void *ptr,
int level)
{
struct xfs_iext_node *node, *new;
int i, pos, nr_entries;
again:
if (ifp->if_height < level)
xfs_iext_grow(ifp);
new = NULL;
node = xfs_iext_find_level(ifp, offset, level);
pos = xfs_iext_node_insert_pos(node, offset);
nr_entries = xfs_iext_node_nr_entries(node, pos);
ASSERT(pos >= nr_entries || xfs_iext_key_cmp(node, pos, offset) != 0);
ASSERT(nr_entries <= KEYS_PER_NODE);
if (nr_entries == KEYS_PER_NODE)
new = xfs_iext_split_node(&node, &pos, &nr_entries);
/*
* Update the pointers in higher levels if the first entry changes
* in an existing node.
*/
if (node != new && pos == 0 && nr_entries > 0)
xfs_iext_update_node(ifp, node->keys[0], offset, level, node);
for (i = nr_entries; i > pos; i--) {
node->keys[i] = node->keys[i - 1];
node->ptrs[i] = node->ptrs[i - 1];
}
node->keys[pos] = offset;
node->ptrs[pos] = ptr;
if (new) {
offset = new->keys[0];
ptr = new;
level++;
goto again;
}
}
static struct xfs_iext_leaf *
xfs_iext_split_leaf(
struct xfs_iext_cursor *cur,
int *nr_entries)
{
struct xfs_iext_leaf *leaf = cur->leaf;
struct xfs_iext_leaf *new = kzalloc(NODE_SIZE,
GFP_NOFS | __GFP_NOFAIL);
const int nr_move = RECS_PER_LEAF / 2;
int nr_keep = nr_move + (RECS_PER_LEAF & 1);
int i;
/* for sequential append operations just spill over into the new node */
if (cur->pos == RECS_PER_LEAF) {
cur->leaf = new;
cur->pos = 0;
*nr_entries = 0;
goto done;
}
for (i = 0; i < nr_move; i++) {
new->recs[i] = leaf->recs[nr_keep + i];
xfs_iext_rec_clear(&leaf->recs[nr_keep + i]);
}
if (cur->pos >= nr_keep) {
cur->leaf = new;
cur->pos -= nr_keep;
*nr_entries = nr_move;
} else {
*nr_entries = nr_keep;
}
done:
if (leaf->next)
leaf->next->prev = new;
new->next = leaf->next;
new->prev = leaf;
leaf->next = new;
return new;
}
static void
xfs_iext_alloc_root(
struct xfs_ifork *ifp,
struct xfs_iext_cursor *cur)
{
ASSERT(ifp->if_bytes == 0);
ifp->if_data = kzalloc(sizeof(struct xfs_iext_rec),
GFP_NOFS | __GFP_NOFAIL);
ifp->if_height = 1;
/* now that we have a node step into it */
cur->leaf = ifp->if_data;
cur->pos = 0;
}
static void
xfs_iext_realloc_root(
struct xfs_ifork *ifp,
struct xfs_iext_cursor *cur)
{
int64_t new_size = ifp->if_bytes + sizeof(struct xfs_iext_rec);
void *new;
/* account for the prev/next pointers */
if (new_size / sizeof(struct xfs_iext_rec) == RECS_PER_LEAF)
new_size = NODE_SIZE;
new = krealloc(ifp->if_data, new_size, GFP_NOFS | __GFP_NOFAIL);
memset(new + ifp->if_bytes, 0, new_size - ifp->if_bytes);
ifp->if_data = new;
cur->leaf = new;
}
/*
* Increment the sequence counter on extent tree changes. If we are on a COW
* fork, this allows the writeback code to skip looking for a COW extent if the
* COW fork hasn't changed. We use WRITE_ONCE here to ensure the update to the
* sequence counter is seen before the modifications to the extent tree itself
* take effect.
*/
static inline void xfs_iext_inc_seq(struct xfs_ifork *ifp)
{
WRITE_ONCE(ifp->if_seq, READ_ONCE(ifp->if_seq) + 1);
}
void
xfs_iext_insert_raw(
struct xfs_ifork *ifp,
struct xfs_iext_cursor *cur,
struct xfs_bmbt_irec *irec)
{
xfs_fileoff_t offset = irec->br_startoff;
struct xfs_iext_leaf *new = NULL;
int nr_entries, i;
xfs_iext_inc_seq(ifp);
if (ifp->if_height == 0)
xfs_iext_alloc_root(ifp, cur);
else if (ifp->if_height == 1)
xfs_iext_realloc_root(ifp, cur);
nr_entries = xfs_iext_leaf_nr_entries(ifp, cur->leaf, cur->pos);
ASSERT(nr_entries <= RECS_PER_LEAF);
ASSERT(cur->pos >= nr_entries ||
xfs_iext_rec_cmp(cur_rec(cur), irec->br_startoff) != 0);
if (nr_entries == RECS_PER_LEAF)
new = xfs_iext_split_leaf(cur, &nr_entries);
/*
* Update the pointers in higher levels if the first entry changes
* in an existing node.
*/
if (cur->leaf != new && cur->pos == 0 && nr_entries > 0) {
xfs_iext_update_node(ifp, xfs_iext_leaf_key(cur->leaf, 0),
offset, 1, cur->leaf);
}
for (i = nr_entries; i > cur->pos; i--)
cur->leaf->recs[i] = cur->leaf->recs[i - 1];
xfs_iext_set(cur_rec(cur), irec);
ifp->if_bytes += sizeof(struct xfs_iext_rec);
if (new)
xfs_iext_insert_node(ifp, xfs_iext_leaf_key(new, 0), new, 2);
}
void
xfs_iext_insert(
struct xfs_inode *ip,
struct xfs_iext_cursor *cur,
struct xfs_bmbt_irec *irec,
int state)
{
struct xfs_ifork *ifp = xfs_iext_state_to_fork(ip, state);
xfs_iext_insert_raw(ifp, cur, irec);
trace_xfs_iext_insert(ip, cur, state, _RET_IP_);
}
static struct xfs_iext_node *
xfs_iext_rebalance_node(
struct xfs_iext_node *parent,
int *pos,
struct xfs_iext_node *node,
int nr_entries)
{
/*
* If the neighbouring nodes are completely full, or have different
* parents, we might never be able to merge our node, and will only
* delete it once the number of entries hits zero.
*/
if (nr_entries == 0)
return node;
if (*pos > 0) {
struct xfs_iext_node *prev = parent->ptrs[*pos - 1];
int nr_prev = xfs_iext_node_nr_entries(prev, 0), i;
if (nr_prev + nr_entries <= KEYS_PER_NODE) {
for (i = 0; i < nr_entries; i++) {
prev->keys[nr_prev + i] = node->keys[i];
prev->ptrs[nr_prev + i] = node->ptrs[i];
}
return node;
}
}
if (*pos + 1 < xfs_iext_node_nr_entries(parent, *pos)) {
struct xfs_iext_node *next = parent->ptrs[*pos + 1];
int nr_next = xfs_iext_node_nr_entries(next, 0), i;
if (nr_entries + nr_next <= KEYS_PER_NODE) {
/*
* Merge the next node into this node so that we don't
* have to do an additional update of the keys in the
* higher levels.
*/
for (i = 0; i < nr_next; i++) {
node->keys[nr_entries + i] = next->keys[i];
node->ptrs[nr_entries + i] = next->ptrs[i];
}
++*pos;
return next;
}
}
return NULL;
}
static void
xfs_iext_remove_node(
struct xfs_ifork *ifp,
xfs_fileoff_t offset,
void *victim)
{
struct xfs_iext_node *node, *parent;
int level = 2, pos, nr_entries, i;
ASSERT(level <= ifp->if_height);
node = xfs_iext_find_level(ifp, offset, level);
pos = xfs_iext_node_pos(node, offset);
again:
ASSERT(node->ptrs[pos]);
ASSERT(node->ptrs[pos] == victim);
kmem_free(victim);
nr_entries = xfs_iext_node_nr_entries(node, pos) - 1;
offset = node->keys[0];
for (i = pos; i < nr_entries; i++) {
node->keys[i] = node->keys[i + 1];
node->ptrs[i] = node->ptrs[i + 1];
}
node->keys[nr_entries] = XFS_IEXT_KEY_INVALID;
node->ptrs[nr_entries] = NULL;
if (pos == 0 && nr_entries > 0) {
xfs_iext_update_node(ifp, offset, node->keys[0], level, node);
offset = node->keys[0];
}
if (nr_entries >= KEYS_PER_NODE / 2)
return;
if (level < ifp->if_height) {
/*
* If we aren't at the root yet try to find a neighbour node to
* merge with (or delete the node if it is empty), and then
* recurse up to the next level.
*/
level++;
parent = xfs_iext_find_level(ifp, offset, level);
pos = xfs_iext_node_pos(parent, offset);
ASSERT(pos != KEYS_PER_NODE);
ASSERT(parent->ptrs[pos] == node);
node = xfs_iext_rebalance_node(parent, &pos, node, nr_entries);
if (node) {
victim = node;
node = parent;
goto again;
}
} else if (nr_entries == 1) {
/*
* If we are at the root and only one entry is left we can just
* free this node and update the root pointer.
*/
ASSERT(node == ifp->if_data);
ifp->if_data = node->ptrs[0];
ifp->if_height--;
kmem_free(node);
}
}
static void
xfs_iext_rebalance_leaf(
struct xfs_ifork *ifp,
struct xfs_iext_cursor *cur,
struct xfs_iext_leaf *leaf,
xfs_fileoff_t offset,
int nr_entries)
{
/*
* If the neighbouring nodes are completely full we might never be able
* to merge our node, and will only delete it once the number of
* entries hits zero.
*/
if (nr_entries == 0)
goto remove_node;
if (leaf->prev) {
int nr_prev = xfs_iext_leaf_nr_entries(ifp, leaf->prev, 0), i;
if (nr_prev + nr_entries <= RECS_PER_LEAF) {
for (i = 0; i < nr_entries; i++)
leaf->prev->recs[nr_prev + i] = leaf->recs[i];
if (cur->leaf == leaf) {
cur->leaf = leaf->prev;
cur->pos += nr_prev;
}
goto remove_node;
}
}
if (leaf->next) {
int nr_next = xfs_iext_leaf_nr_entries(ifp, leaf->next, 0), i;
if (nr_entries + nr_next <= RECS_PER_LEAF) {
/*
* Merge the next node into this node so that we don't
* have to do an additional update of the keys in the
* higher levels.
*/
for (i = 0; i < nr_next; i++) {
leaf->recs[nr_entries + i] =
leaf->next->recs[i];
}
if (cur->leaf == leaf->next) {
cur->leaf = leaf;
cur->pos += nr_entries;
}
offset = xfs_iext_leaf_key(leaf->next, 0);
leaf = leaf->next;
goto remove_node;
}
}
return;
remove_node:
if (leaf->prev)
leaf->prev->next = leaf->next;
if (leaf->next)
leaf->next->prev = leaf->prev;
xfs_iext_remove_node(ifp, offset, leaf);
}
static void
xfs_iext_free_last_leaf(
struct xfs_ifork *ifp)
{
ifp->if_height--;
kmem_free(ifp->if_data);
ifp->if_data = NULL;
}
void
xfs_iext_remove(
struct xfs_inode *ip,
struct xfs_iext_cursor *cur,
int state)
{
struct xfs_ifork *ifp = xfs_iext_state_to_fork(ip, state);
struct xfs_iext_leaf *leaf = cur->leaf;
xfs_fileoff_t offset = xfs_iext_leaf_key(leaf, 0);
int i, nr_entries;
trace_xfs_iext_remove(ip, cur, state, _RET_IP_);
ASSERT(ifp->if_height > 0);
ASSERT(ifp->if_data != NULL);
ASSERT(xfs_iext_valid(ifp, cur));
xfs_iext_inc_seq(ifp);
nr_entries = xfs_iext_leaf_nr_entries(ifp, leaf, cur->pos) - 1;
for (i = cur->pos; i < nr_entries; i++)
leaf->recs[i] = leaf->recs[i + 1];
xfs_iext_rec_clear(&leaf->recs[nr_entries]);
ifp->if_bytes -= sizeof(struct xfs_iext_rec);
if (cur->pos == 0 && nr_entries > 0) {
xfs_iext_update_node(ifp, offset, xfs_iext_leaf_key(leaf, 0), 1,
leaf);
offset = xfs_iext_leaf_key(leaf, 0);
} else if (cur->pos == nr_entries) {
if (ifp->if_height > 1 && leaf->next)
cur->leaf = leaf->next;
else
cur->leaf = NULL;
cur->pos = 0;
}
if (nr_entries >= RECS_PER_LEAF / 2)
return;
if (ifp->if_height > 1)
xfs_iext_rebalance_leaf(ifp, cur, leaf, offset, nr_entries);
else if (nr_entries == 0)
xfs_iext_free_last_leaf(ifp);
}
/*
* Lookup the extent covering bno.
*
* If there is an extent covering bno return the extent index, and store the
* expanded extent structure in *gotp, and the extent cursor in *cur.
* If there is no extent covering bno, but there is an extent after it (e.g.
* it lies in a hole) return that extent in *gotp and its cursor in *cur
* instead.
* If bno is beyond the last extent return false, and return an invalid
* cursor value.
*/
bool
xfs_iext_lookup_extent(
struct xfs_inode *ip,
struct xfs_ifork *ifp,
xfs_fileoff_t offset,
struct xfs_iext_cursor *cur,
struct xfs_bmbt_irec *gotp)
{
XFS_STATS_INC(ip->i_mount, xs_look_exlist);
cur->leaf = xfs_iext_find_level(ifp, offset, 1);
if (!cur->leaf) {
cur->pos = 0;
return false;
}
for (cur->pos = 0; cur->pos < xfs_iext_max_recs(ifp); cur->pos++) {
struct xfs_iext_rec *rec = cur_rec(cur);
if (xfs_iext_rec_is_empty(rec))
break;
if (xfs_iext_rec_cmp(rec, offset) >= 0)
goto found;
}
/* Try looking in the next node for an entry > offset */
if (ifp->if_height == 1 || !cur->leaf->next)
return false;
cur->leaf = cur->leaf->next;
cur->pos = 0;
if (!xfs_iext_valid(ifp, cur))
return false;
found:
xfs_iext_get(gotp, cur_rec(cur));
return true;
}
/*
* Returns the last extent before end, and if this extent doesn't cover
* end, update end to the end of the extent.
*/
bool
xfs_iext_lookup_extent_before(
struct xfs_inode *ip,
struct xfs_ifork *ifp,
xfs_fileoff_t *end,
struct xfs_iext_cursor *cur,
struct xfs_bmbt_irec *gotp)
{
/* could be optimized to not even look up the next on a match.. */
if (xfs_iext_lookup_extent(ip, ifp, *end - 1, cur, gotp) &&
gotp->br_startoff <= *end - 1)
return true;
if (!xfs_iext_prev_extent(ifp, cur, gotp))
return false;
*end = gotp->br_startoff + gotp->br_blockcount;
return true;
}
void
xfs_iext_update_extent(
struct xfs_inode *ip,
int state,
struct xfs_iext_cursor *cur,
struct xfs_bmbt_irec *new)
{
struct xfs_ifork *ifp = xfs_iext_state_to_fork(ip, state);
xfs_iext_inc_seq(ifp);
if (cur->pos == 0) {
struct xfs_bmbt_irec old;
xfs_iext_get(&old, cur_rec(cur));
if (new->br_startoff != old.br_startoff) {
xfs_iext_update_node(ifp, old.br_startoff,
new->br_startoff, 1, cur->leaf);
}
}
trace_xfs_bmap_pre_update(ip, cur, state, _RET_IP_);
xfs_iext_set(cur_rec(cur), new);
trace_xfs_bmap_post_update(ip, cur, state, _RET_IP_);
}
/*
* Return true if the cursor points at an extent and return the extent structure
* in gotp. Else return false.
*/
bool
xfs_iext_get_extent(
struct xfs_ifork *ifp,
struct xfs_iext_cursor *cur,
struct xfs_bmbt_irec *gotp)
{
if (!xfs_iext_valid(ifp, cur))
return false;
xfs_iext_get(gotp, cur_rec(cur));
return true;
}
/*
* This is a recursive function, because of that we need to be extremely
* careful with stack usage.
*/
static void
xfs_iext_destroy_node(
struct xfs_iext_node *node,
int level)
{
int i;
if (level > 1) {
for (i = 0; i < KEYS_PER_NODE; i++) {
if (node->keys[i] == XFS_IEXT_KEY_INVALID)
break;
xfs_iext_destroy_node(node->ptrs[i], level - 1);
}
}
kmem_free(node);
}
void
xfs_iext_destroy(
struct xfs_ifork *ifp)
{
xfs_iext_destroy_node(ifp->if_data, ifp->if_height);
ifp->if_bytes = 0;
ifp->if_height = 0;
ifp->if_data = NULL;
}
|