forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathmove_extent.c
1541 lines (1382 loc) · 44.7 KB
/
move_extent.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) 2008,2009 NEC Software Tohoku, Ltd.
* Written by Takashi Sato <[email protected]>
* Akira Fujita <[email protected]>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of version 2.1 of the GNU Lesser General Public License
* as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will 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.
*/
#include <linux/fs.h>
#include <linux/quotaops.h>
#include <linux/slab.h>
#include "ext4_jbd2.h"
#include "ext4.h"
#include "ext4_extents.h"
/**
* get_ext_path - Find an extent path for designated logical block number.
*
* @inode: an inode which is searched
* @lblock: logical block number to find an extent path
* @path: pointer to an extent path pointer (for output)
*
* ext4_ext_find_extent wrapper. Return 0 on success, or a negative error value
* on failure.
*/
static inline int
get_ext_path(struct inode *inode, ext4_lblk_t lblock,
struct ext4_ext_path **orig_path)
{
int ret = 0;
struct ext4_ext_path *path;
path = ext4_ext_find_extent(inode, lblock, *orig_path, EXT4_EX_NOCACHE);
if (IS_ERR(path))
ret = PTR_ERR(path);
else if (path[ext_depth(inode)].p_ext == NULL)
ret = -ENODATA;
else
*orig_path = path;
return ret;
}
/**
* copy_extent_status - Copy the extent's initialization status
*
* @src: an extent for getting initialize status
* @dest: an extent to be set the status
*/
static void
copy_extent_status(struct ext4_extent *src, struct ext4_extent *dest)
{
if (ext4_ext_is_uninitialized(src))
ext4_ext_mark_uninitialized(dest);
else
dest->ee_len = cpu_to_le16(ext4_ext_get_actual_len(dest));
}
/**
* mext_next_extent - Search for the next extent and set it to "extent"
*
* @inode: inode which is searched
* @path: this will obtain data for the next extent
* @extent: pointer to the next extent we have just gotten
*
* Search the next extent in the array of ext4_ext_path structure (@path)
* and set it to ext4_extent structure (@extent). In addition, the member of
* @path (->p_ext) also points the next extent. Return 0 on success, 1 if
* ext4_ext_path structure refers to the last extent, or a negative error
* value on failure.
*/
static int
mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
struct ext4_extent **extent)
{
struct ext4_extent_header *eh;
int ppos, leaf_ppos = path->p_depth;
ppos = leaf_ppos;
if (EXT_LAST_EXTENT(path[ppos].p_hdr) > path[ppos].p_ext) {
/* leaf block */
*extent = ++path[ppos].p_ext;
path[ppos].p_block = ext4_ext_pblock(path[ppos].p_ext);
return 0;
}
while (--ppos >= 0) {
if (EXT_LAST_INDEX(path[ppos].p_hdr) >
path[ppos].p_idx) {
int cur_ppos = ppos;
/* index block */
path[ppos].p_idx++;
path[ppos].p_block = ext4_idx_pblock(path[ppos].p_idx);
if (path[ppos+1].p_bh)
brelse(path[ppos+1].p_bh);
path[ppos+1].p_bh =
sb_bread(inode->i_sb, path[ppos].p_block);
if (!path[ppos+1].p_bh)
return -EIO;
path[ppos+1].p_hdr =
ext_block_hdr(path[ppos+1].p_bh);
/* Halfway index block */
while (++cur_ppos < leaf_ppos) {
path[cur_ppos].p_idx =
EXT_FIRST_INDEX(path[cur_ppos].p_hdr);
path[cur_ppos].p_block =
ext4_idx_pblock(path[cur_ppos].p_idx);
if (path[cur_ppos+1].p_bh)
brelse(path[cur_ppos+1].p_bh);
path[cur_ppos+1].p_bh = sb_bread(inode->i_sb,
path[cur_ppos].p_block);
if (!path[cur_ppos+1].p_bh)
return -EIO;
path[cur_ppos+1].p_hdr =
ext_block_hdr(path[cur_ppos+1].p_bh);
}
path[leaf_ppos].p_ext = *extent = NULL;
eh = path[leaf_ppos].p_hdr;
if (le16_to_cpu(eh->eh_entries) == 0)
/* empty leaf is found */
return -ENODATA;
/* leaf block */
path[leaf_ppos].p_ext = *extent =
EXT_FIRST_EXTENT(path[leaf_ppos].p_hdr);
path[leaf_ppos].p_block =
ext4_ext_pblock(path[leaf_ppos].p_ext);
return 0;
}
}
/* We found the last extent */
return 1;
}
/**
* ext4_double_down_write_data_sem - Acquire two inodes' write lock
* of i_data_sem
*
* Acquire write lock of i_data_sem of the two inodes
*/
void
ext4_double_down_write_data_sem(struct inode *first, struct inode *second)
{
if (first < second) {
down_write(&EXT4_I(first)->i_data_sem);
down_write_nested(&EXT4_I(second)->i_data_sem, SINGLE_DEPTH_NESTING);
} else {
down_write(&EXT4_I(second)->i_data_sem);
down_write_nested(&EXT4_I(first)->i_data_sem, SINGLE_DEPTH_NESTING);
}
}
/**
* ext4_double_up_write_data_sem - Release two inodes' write lock of i_data_sem
*
* @orig_inode: original inode structure to be released its lock first
* @donor_inode: donor inode structure to be released its lock second
* Release write lock of i_data_sem of two inodes (orig and donor).
*/
void
ext4_double_up_write_data_sem(struct inode *orig_inode,
struct inode *donor_inode)
{
up_write(&EXT4_I(orig_inode)->i_data_sem);
up_write(&EXT4_I(donor_inode)->i_data_sem);
}
/**
* mext_insert_across_blocks - Insert extents across leaf block
*
* @handle: journal handle
* @orig_inode: original inode
* @o_start: first original extent to be changed
* @o_end: last original extent to be changed
* @start_ext: first new extent to be inserted
* @new_ext: middle of new extent to be inserted
* @end_ext: last new extent to be inserted
*
* Allocate a new leaf block and insert extents into it. Return 0 on success,
* or a negative error value on failure.
*/
static int
mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode,
struct ext4_extent *o_start, struct ext4_extent *o_end,
struct ext4_extent *start_ext, struct ext4_extent *new_ext,
struct ext4_extent *end_ext)
{
struct ext4_ext_path *orig_path = NULL;
ext4_lblk_t eblock = 0;
int new_flag = 0;
int end_flag = 0;
int err = 0;
if (start_ext->ee_len && new_ext->ee_len && end_ext->ee_len) {
if (o_start == o_end) {
/* start_ext new_ext end_ext
* donor |---------|-----------|--------|
* orig |------------------------------|
*/
end_flag = 1;
} else {
/* start_ext new_ext end_ext
* donor |---------|----------|---------|
* orig |---------------|--------------|
*/
o_end->ee_block = end_ext->ee_block;
o_end->ee_len = end_ext->ee_len;
ext4_ext_store_pblock(o_end, ext4_ext_pblock(end_ext));
}
o_start->ee_len = start_ext->ee_len;
eblock = le32_to_cpu(start_ext->ee_block);
new_flag = 1;
} else if (start_ext->ee_len && new_ext->ee_len &&
!end_ext->ee_len && o_start == o_end) {
/* start_ext new_ext
* donor |--------------|---------------|
* orig |------------------------------|
*/
o_start->ee_len = start_ext->ee_len;
eblock = le32_to_cpu(start_ext->ee_block);
new_flag = 1;
} else if (!start_ext->ee_len && new_ext->ee_len &&
end_ext->ee_len && o_start == o_end) {
/* new_ext end_ext
* donor |--------------|---------------|
* orig |------------------------------|
*/
o_end->ee_block = end_ext->ee_block;
o_end->ee_len = end_ext->ee_len;
ext4_ext_store_pblock(o_end, ext4_ext_pblock(end_ext));
/*
* Set 0 to the extent block if new_ext was
* the first block.
*/
if (new_ext->ee_block)
eblock = le32_to_cpu(new_ext->ee_block);
new_flag = 1;
} else {
ext4_debug("ext4 move extent: Unexpected insert case\n");
return -EIO;
}
if (new_flag) {
err = get_ext_path(orig_inode, eblock, &orig_path);
if (err)
goto out;
if (ext4_ext_insert_extent(handle, orig_inode,
orig_path, new_ext, 0))
goto out;
}
if (end_flag) {
err = get_ext_path(orig_inode,
le32_to_cpu(end_ext->ee_block) - 1, &orig_path);
if (err)
goto out;
if (ext4_ext_insert_extent(handle, orig_inode,
orig_path, end_ext, 0))
goto out;
}
out:
if (orig_path) {
ext4_ext_drop_refs(orig_path);
kfree(orig_path);
}
return err;
}
/**
* mext_insert_inside_block - Insert new extent to the extent block
*
* @o_start: first original extent to be moved
* @o_end: last original extent to be moved
* @start_ext: first new extent to be inserted
* @new_ext: middle of new extent to be inserted
* @end_ext: last new extent to be inserted
* @eh: extent header of target leaf block
* @range_to_move: used to decide how to insert extent
*
* Insert extents into the leaf block. The extent (@o_start) is overwritten
* by inserted extents.
*/
static void
mext_insert_inside_block(struct ext4_extent *o_start,
struct ext4_extent *o_end,
struct ext4_extent *start_ext,
struct ext4_extent *new_ext,
struct ext4_extent *end_ext,
struct ext4_extent_header *eh,
int range_to_move)
{
int i = 0;
unsigned long len;
/* Move the existing extents */
if (range_to_move && o_end < EXT_LAST_EXTENT(eh)) {
len = (unsigned long)(EXT_LAST_EXTENT(eh) + 1) -
(unsigned long)(o_end + 1);
memmove(o_end + 1 + range_to_move, o_end + 1, len);
}
/* Insert start entry */
if (start_ext->ee_len)
o_start[i++].ee_len = start_ext->ee_len;
/* Insert new entry */
if (new_ext->ee_len) {
o_start[i] = *new_ext;
ext4_ext_store_pblock(&o_start[i++], ext4_ext_pblock(new_ext));
}
/* Insert end entry */
if (end_ext->ee_len)
o_start[i] = *end_ext;
/* Increment the total entries counter on the extent block */
le16_add_cpu(&eh->eh_entries, range_to_move);
}
/**
* mext_insert_extents - Insert new extent
*
* @handle: journal handle
* @orig_inode: original inode
* @orig_path: path indicates first extent to be changed
* @o_start: first original extent to be changed
* @o_end: last original extent to be changed
* @start_ext: first new extent to be inserted
* @new_ext: middle of new extent to be inserted
* @end_ext: last new extent to be inserted
*
* Call the function to insert extents. If we cannot add more extents into
* the leaf block, we call mext_insert_across_blocks() to create a
* new leaf block. Otherwise call mext_insert_inside_block(). Return 0
* on success, or a negative error value on failure.
*/
static int
mext_insert_extents(handle_t *handle, struct inode *orig_inode,
struct ext4_ext_path *orig_path,
struct ext4_extent *o_start,
struct ext4_extent *o_end,
struct ext4_extent *start_ext,
struct ext4_extent *new_ext,
struct ext4_extent *end_ext)
{
struct ext4_extent_header *eh;
unsigned long need_slots, slots_range;
int range_to_move, depth, ret;
/*
* The extents need to be inserted
* start_extent + new_extent + end_extent.
*/
need_slots = (start_ext->ee_len ? 1 : 0) + (end_ext->ee_len ? 1 : 0) +
(new_ext->ee_len ? 1 : 0);
/* The number of slots between start and end */
slots_range = ((unsigned long)(o_end + 1) - (unsigned long)o_start + 1)
/ sizeof(struct ext4_extent);
/* Range to move the end of extent */
range_to_move = need_slots - slots_range;
depth = orig_path->p_depth;
orig_path += depth;
eh = orig_path->p_hdr;
if (depth) {
/* Register to journal */
ret = ext4_journal_get_write_access(handle, orig_path->p_bh);
if (ret)
return ret;
}
/* Expansion */
if (range_to_move > 0 &&
(range_to_move > le16_to_cpu(eh->eh_max)
- le16_to_cpu(eh->eh_entries))) {
ret = mext_insert_across_blocks(handle, orig_inode, o_start,
o_end, start_ext, new_ext, end_ext);
if (ret < 0)
return ret;
} else
mext_insert_inside_block(o_start, o_end, start_ext, new_ext,
end_ext, eh, range_to_move);
return ext4_ext_dirty(handle, orig_inode, orig_path);
}
/**
* mext_leaf_block - Move one leaf extent block into the inode.
*
* @handle: journal handle
* @orig_inode: original inode
* @orig_path: path indicates first extent to be changed
* @dext: donor extent
* @from: start offset on the target file
*
* In order to insert extents into the leaf block, we must divide the extent
* in the leaf block into three extents. The one is located to be inserted
* extents, and the others are located around it.
*
* Therefore, this function creates structures to save extents of the leaf
* block, and inserts extents by calling mext_insert_extents() with
* created extents. Return 0 on success, or a negative error value on failure.
*/
static int
mext_leaf_block(handle_t *handle, struct inode *orig_inode,
struct ext4_ext_path *orig_path, struct ext4_extent *dext,
ext4_lblk_t *from)
{
struct ext4_extent *oext, *o_start, *o_end, *prev_ext;
struct ext4_extent new_ext, start_ext, end_ext;
ext4_lblk_t new_ext_end;
int oext_alen, new_ext_alen, end_ext_alen;
int depth = ext_depth(orig_inode);
int ret;
start_ext.ee_block = end_ext.ee_block = 0;
o_start = o_end = oext = orig_path[depth].p_ext;
oext_alen = ext4_ext_get_actual_len(oext);
start_ext.ee_len = end_ext.ee_len = 0;
new_ext.ee_block = cpu_to_le32(*from);
ext4_ext_store_pblock(&new_ext, ext4_ext_pblock(dext));
new_ext.ee_len = dext->ee_len;
new_ext_alen = ext4_ext_get_actual_len(&new_ext);
new_ext_end = le32_to_cpu(new_ext.ee_block) + new_ext_alen - 1;
/*
* Case: original extent is first
* oext |--------|
* new_ext |--|
* start_ext |--|
*/
if (le32_to_cpu(oext->ee_block) < le32_to_cpu(new_ext.ee_block) &&
le32_to_cpu(new_ext.ee_block) <
le32_to_cpu(oext->ee_block) + oext_alen) {
start_ext.ee_len = cpu_to_le16(le32_to_cpu(new_ext.ee_block) -
le32_to_cpu(oext->ee_block));
start_ext.ee_block = oext->ee_block;
copy_extent_status(oext, &start_ext);
} else if (oext > EXT_FIRST_EXTENT(orig_path[depth].p_hdr)) {
prev_ext = oext - 1;
/*
* We can merge new_ext into previous extent,
* if these are contiguous and same extent type.
*/
if (ext4_can_extents_be_merged(orig_inode, prev_ext,
&new_ext)) {
o_start = prev_ext;
start_ext.ee_len = cpu_to_le16(
ext4_ext_get_actual_len(prev_ext) +
new_ext_alen);
start_ext.ee_block = oext->ee_block;
copy_extent_status(prev_ext, &start_ext);
new_ext.ee_len = 0;
}
}
/*
* Case: new_ext_end must be less than oext
* oext |-----------|
* new_ext |-------|
*/
if (le32_to_cpu(oext->ee_block) + oext_alen - 1 < new_ext_end) {
EXT4_ERROR_INODE(orig_inode,
"new_ext_end(%u) should be less than or equal to "
"oext->ee_block(%u) + oext_alen(%d) - 1",
new_ext_end, le32_to_cpu(oext->ee_block),
oext_alen);
ret = -EIO;
goto out;
}
/*
* Case: new_ext is smaller than original extent
* oext |---------------|
* new_ext |-----------|
* end_ext |---|
*/
if (le32_to_cpu(oext->ee_block) <= new_ext_end &&
new_ext_end < le32_to_cpu(oext->ee_block) + oext_alen - 1) {
end_ext.ee_len =
cpu_to_le16(le32_to_cpu(oext->ee_block) +
oext_alen - 1 - new_ext_end);
copy_extent_status(oext, &end_ext);
end_ext_alen = ext4_ext_get_actual_len(&end_ext);
ext4_ext_store_pblock(&end_ext,
(ext4_ext_pblock(o_end) + oext_alen - end_ext_alen));
end_ext.ee_block =
cpu_to_le32(le32_to_cpu(o_end->ee_block) +
oext_alen - end_ext_alen);
}
ret = mext_insert_extents(handle, orig_inode, orig_path, o_start,
o_end, &start_ext, &new_ext, &end_ext);
out:
return ret;
}
/**
* mext_calc_swap_extents - Calculate extents for extent swapping.
*
* @tmp_dext: the extent that will belong to the original inode
* @tmp_oext: the extent that will belong to the donor inode
* @orig_off: block offset of original inode
* @donor_off: block offset of donor inode
* @max_count: the maximum length of extents
*
* Return 0 on success, or a negative error value on failure.
*/
static int
mext_calc_swap_extents(struct ext4_extent *tmp_dext,
struct ext4_extent *tmp_oext,
ext4_lblk_t orig_off, ext4_lblk_t donor_off,
ext4_lblk_t max_count)
{
ext4_lblk_t diff, orig_diff;
struct ext4_extent dext_old, oext_old;
BUG_ON(orig_off != donor_off);
/* original and donor extents have to cover the same block offset */
if (orig_off < le32_to_cpu(tmp_oext->ee_block) ||
le32_to_cpu(tmp_oext->ee_block) +
ext4_ext_get_actual_len(tmp_oext) - 1 < orig_off)
return -ENODATA;
if (orig_off < le32_to_cpu(tmp_dext->ee_block) ||
le32_to_cpu(tmp_dext->ee_block) +
ext4_ext_get_actual_len(tmp_dext) - 1 < orig_off)
return -ENODATA;
dext_old = *tmp_dext;
oext_old = *tmp_oext;
/* When tmp_dext is too large, pick up the target range. */
diff = donor_off - le32_to_cpu(tmp_dext->ee_block);
ext4_ext_store_pblock(tmp_dext, ext4_ext_pblock(tmp_dext) + diff);
le32_add_cpu(&tmp_dext->ee_block, diff);
le16_add_cpu(&tmp_dext->ee_len, -diff);
if (max_count < ext4_ext_get_actual_len(tmp_dext))
tmp_dext->ee_len = cpu_to_le16(max_count);
orig_diff = orig_off - le32_to_cpu(tmp_oext->ee_block);
ext4_ext_store_pblock(tmp_oext, ext4_ext_pblock(tmp_oext) + orig_diff);
/* Adjust extent length if donor extent is larger than orig */
if (ext4_ext_get_actual_len(tmp_dext) >
ext4_ext_get_actual_len(tmp_oext) - orig_diff)
tmp_dext->ee_len = cpu_to_le16(le16_to_cpu(tmp_oext->ee_len) -
orig_diff);
tmp_oext->ee_len = cpu_to_le16(ext4_ext_get_actual_len(tmp_dext));
copy_extent_status(&oext_old, tmp_dext);
copy_extent_status(&dext_old, tmp_oext);
return 0;
}
/**
* mext_check_coverage - Check that all extents in range has the same type
*
* @inode: inode in question
* @from: block offset of inode
* @count: block count to be checked
* @uninit: extents expected to be uninitialized
* @err: pointer to save error value
*
* Return 1 if all extents in range has expected type, and zero otherwise.
*/
static int
mext_check_coverage(struct inode *inode, ext4_lblk_t from, ext4_lblk_t count,
int uninit, int *err)
{
struct ext4_ext_path *path = NULL;
struct ext4_extent *ext;
int ret = 0;
ext4_lblk_t last = from + count;
while (from < last) {
*err = get_ext_path(inode, from, &path);
if (*err)
goto out;
ext = path[ext_depth(inode)].p_ext;
if (uninit != ext4_ext_is_uninitialized(ext))
goto out;
from += ext4_ext_get_actual_len(ext);
ext4_ext_drop_refs(path);
}
ret = 1;
out:
if (path) {
ext4_ext_drop_refs(path);
kfree(path);
}
return ret;
}
/**
* mext_replace_branches - Replace original extents with new extents
*
* @handle: journal handle
* @orig_inode: original inode
* @donor_inode: donor inode
* @from: block offset of orig_inode
* @count: block count to be replaced
* @err: pointer to save return value
*
* Replace original inode extents and donor inode extents page by page.
* We implement this replacement in the following three steps:
* 1. Save the block information of original and donor inodes into
* dummy extents.
* 2. Change the block information of original inode to point at the
* donor inode blocks.
* 3. Change the block information of donor inode to point at the saved
* original inode blocks in the dummy extents.
*
* Return replaced block count.
*/
static int
mext_replace_branches(handle_t *handle, struct inode *orig_inode,
struct inode *donor_inode, ext4_lblk_t from,
ext4_lblk_t count, int *err)
{
struct ext4_ext_path *orig_path = NULL;
struct ext4_ext_path *donor_path = NULL;
struct ext4_extent *oext, *dext;
struct ext4_extent tmp_dext, tmp_oext;
ext4_lblk_t orig_off = from, donor_off = from;
int depth;
int replaced_count = 0;
int dext_alen;
*err = ext4_es_remove_extent(orig_inode, from, count);
if (*err)
goto out;
*err = ext4_es_remove_extent(donor_inode, from, count);
if (*err)
goto out;
/* Get the original extent for the block "orig_off" */
*err = get_ext_path(orig_inode, orig_off, &orig_path);
if (*err)
goto out;
/* Get the donor extent for the head */
*err = get_ext_path(donor_inode, donor_off, &donor_path);
if (*err)
goto out;
depth = ext_depth(orig_inode);
oext = orig_path[depth].p_ext;
tmp_oext = *oext;
depth = ext_depth(donor_inode);
dext = donor_path[depth].p_ext;
if (unlikely(!dext))
goto missing_donor_extent;
tmp_dext = *dext;
*err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
donor_off, count);
if (*err)
goto out;
/* Loop for the donor extents */
while (1) {
/* The extent for donor must be found. */
if (unlikely(!dext)) {
missing_donor_extent:
EXT4_ERROR_INODE(donor_inode,
"The extent for donor must be found");
*err = -EIO;
goto out;
} else if (donor_off != le32_to_cpu(tmp_dext.ee_block)) {
EXT4_ERROR_INODE(donor_inode,
"Donor offset(%u) and the first block of donor "
"extent(%u) should be equal",
donor_off,
le32_to_cpu(tmp_dext.ee_block));
*err = -EIO;
goto out;
}
/* Set donor extent to orig extent */
*err = mext_leaf_block(handle, orig_inode,
orig_path, &tmp_dext, &orig_off);
if (*err)
goto out;
/* Set orig extent to donor extent */
*err = mext_leaf_block(handle, donor_inode,
donor_path, &tmp_oext, &donor_off);
if (*err)
goto out;
dext_alen = ext4_ext_get_actual_len(&tmp_dext);
replaced_count += dext_alen;
donor_off += dext_alen;
orig_off += dext_alen;
BUG_ON(replaced_count > count);
/* Already moved the expected blocks */
if (replaced_count >= count)
break;
if (orig_path)
ext4_ext_drop_refs(orig_path);
*err = get_ext_path(orig_inode, orig_off, &orig_path);
if (*err)
goto out;
depth = ext_depth(orig_inode);
oext = orig_path[depth].p_ext;
tmp_oext = *oext;
if (donor_path)
ext4_ext_drop_refs(donor_path);
*err = get_ext_path(donor_inode, donor_off, &donor_path);
if (*err)
goto out;
depth = ext_depth(donor_inode);
dext = donor_path[depth].p_ext;
tmp_dext = *dext;
*err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
donor_off, count - replaced_count);
if (*err)
goto out;
}
out:
if (orig_path) {
ext4_ext_drop_refs(orig_path);
kfree(orig_path);
}
if (donor_path) {
ext4_ext_drop_refs(donor_path);
kfree(donor_path);
}
return replaced_count;
}
/**
* mext_page_double_lock - Grab and lock pages on both @inode1 and @inode2
*
* @inode1: the inode structure
* @inode2: the inode structure
* @index: page index
* @page: result page vector
*
* Grab two locked pages for inode's by inode order
*/
static int
mext_page_double_lock(struct inode *inode1, struct inode *inode2,
pgoff_t index, struct page *page[2])
{
struct address_space *mapping[2];
unsigned fl = AOP_FLAG_NOFS;
BUG_ON(!inode1 || !inode2);
if (inode1 < inode2) {
mapping[0] = inode1->i_mapping;
mapping[1] = inode2->i_mapping;
} else {
mapping[0] = inode2->i_mapping;
mapping[1] = inode1->i_mapping;
}
page[0] = grab_cache_page_write_begin(mapping[0], index, fl);
if (!page[0])
return -ENOMEM;
page[1] = grab_cache_page_write_begin(mapping[1], index, fl);
if (!page[1]) {
unlock_page(page[0]);
page_cache_release(page[0]);
return -ENOMEM;
}
/*
* grab_cache_page_write_begin() may not wait on page's writeback if
* BDI not demand that. But it is reasonable to be very conservative
* here and explicitly wait on page's writeback
*/
wait_on_page_writeback(page[0]);
wait_on_page_writeback(page[1]);
if (inode1 > inode2) {
struct page *tmp;
tmp = page[0];
page[0] = page[1];
page[1] = tmp;
}
return 0;
}
/* Force page buffers uptodate w/o dropping page's lock */
static int
mext_page_mkuptodate(struct page *page, unsigned from, unsigned to)
{
struct inode *inode = page->mapping->host;
sector_t block;
struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE];
unsigned int blocksize, block_start, block_end;
int i, err, nr = 0, partial = 0;
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
if (PageUptodate(page))
return 0;
blocksize = 1 << inode->i_blkbits;
if (!page_has_buffers(page))
create_empty_buffers(page, blocksize, 0);
head = page_buffers(page);
block = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
for (bh = head, block_start = 0; bh != head || !block_start;
block++, block_start = block_end, bh = bh->b_this_page) {
block_end = block_start + blocksize;
if (block_end <= from || block_start >= to) {
if (!buffer_uptodate(bh))
partial = 1;
continue;
}
if (buffer_uptodate(bh))
continue;
if (!buffer_mapped(bh)) {
err = ext4_get_block(inode, block, bh, 0);
if (err) {
SetPageError(page);
return err;
}
if (!buffer_mapped(bh)) {
zero_user(page, block_start, blocksize);
if (!err)
set_buffer_uptodate(bh);
continue;
}
}
BUG_ON(nr >= MAX_BUF_PER_PAGE);
arr[nr++] = bh;
}
/* No io required */
if (!nr)
goto out;
for (i = 0; i < nr; i++) {
bh = arr[i];
if (!bh_uptodate_or_lock(bh)) {
err = bh_submit_read(bh);
if (err)
return err;
}
}
out:
if (!partial)
SetPageUptodate(page);
return 0;
}
/**
* move_extent_per_page - Move extent data per page
*
* @o_filp: file structure of original file
* @donor_inode: donor inode
* @orig_page_offset: page index on original file
* @data_offset_in_page: block index where data swapping starts
* @block_len_in_page: the number of blocks to be swapped
* @uninit: orig extent is uninitialized or not
* @err: pointer to save return value
*
* Save the data in original inode blocks and replace original inode extents
* with donor inode extents by calling mext_replace_branches().
* Finally, write out the saved data in new original inode blocks. Return
* replaced block count.
*/
static int
move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
pgoff_t orig_page_offset, int data_offset_in_page,
int block_len_in_page, int uninit, int *err)
{
struct inode *orig_inode = file_inode(o_filp);
struct page *pagep[2] = {NULL, NULL};
handle_t *handle;
ext4_lblk_t orig_blk_offset;
unsigned long blocksize = orig_inode->i_sb->s_blocksize;
unsigned int w_flags = 0;
unsigned int tmp_data_size, data_size, replaced_size;
int err2, jblocks, retries = 0;
int replaced_count = 0;
int from = data_offset_in_page << orig_inode->i_blkbits;
int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
/*
* It needs twice the amount of ordinary journal buffers because
* inode and donor_inode may change each different metadata blocks.
*/
again:
*err = 0;
jblocks = ext4_writepage_trans_blocks(orig_inode) * 2;
handle = ext4_journal_start(orig_inode, EXT4_HT_MOVE_EXTENTS, jblocks);
if (IS_ERR(handle)) {
*err = PTR_ERR(handle);
return 0;
}
if (segment_eq(get_fs(), KERNEL_DS))
w_flags |= AOP_FLAG_UNINTERRUPTIBLE;
orig_blk_offset = orig_page_offset * blocks_per_page +
data_offset_in_page;
/* Calculate data_size */
if ((orig_blk_offset + block_len_in_page - 1) ==
((orig_inode->i_size - 1) >> orig_inode->i_blkbits)) {
/* Replace the last block */
tmp_data_size = orig_inode->i_size & (blocksize - 1);
/*
* If data_size equal zero, it shows data_size is multiples of
* blocksize. So we set appropriate value.
*/
if (tmp_data_size == 0)
tmp_data_size = blocksize;
data_size = tmp_data_size +
((block_len_in_page - 1) << orig_inode->i_blkbits);
} else
data_size = block_len_in_page << orig_inode->i_blkbits;
replaced_size = data_size;
*err = mext_page_double_lock(orig_inode, donor_inode, orig_page_offset,
pagep);
if (unlikely(*err < 0))
goto stop_journal;
/*
* If orig extent was uninitialized it can become initialized
* at any time after i_data_sem was dropped, in order to
* serialize with delalloc we have recheck extent while we
* hold page's lock, if it is still the case data copy is not
* necessary, just swap data blocks between orig and donor.
*/
if (uninit) {
ext4_double_down_write_data_sem(orig_inode, donor_inode);
/* If any of extents in range became initialized we have to
* fallback to data copying */
uninit = mext_check_coverage(orig_inode, orig_blk_offset,
block_len_in_page, 1, err);
if (*err)
goto drop_data_sem;
uninit &= mext_check_coverage(donor_inode, orig_blk_offset,
block_len_in_page, 1, err);
if (*err)
goto drop_data_sem;
if (!uninit) {
ext4_double_up_write_data_sem(orig_inode, donor_inode);
goto data_copy;
}
if ((page_has_private(pagep[0]) &&
!try_to_release_page(pagep[0], 0)) ||
(page_has_private(pagep[1]) &&
!try_to_release_page(pagep[1], 0))) {
*err = -EBUSY;
goto drop_data_sem;
}
replaced_count = mext_replace_branches(handle, orig_inode,
donor_inode, orig_blk_offset,
block_len_in_page, err);
drop_data_sem: