forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathmove_extents.c
1147 lines (965 loc) · 27.2 KB
/
move_extents.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
/* -*- mode: c; c-basic-offset: 8; -*-
* vim: noexpandtab sw=8 ts=8 sts=0:
*
* move_extents.c
*
* Copyright (C) 2011 Oracle. 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 version 2 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/types.h>
#include <linux/mount.h>
#include <linux/swap.h>
#include <cluster/masklog.h>
#include "ocfs2.h"
#include "ocfs2_ioctl.h"
#include "alloc.h"
#include "aops.h"
#include "dlmglue.h"
#include "extent_map.h"
#include "inode.h"
#include "journal.h"
#include "suballoc.h"
#include "uptodate.h"
#include "super.h"
#include "dir.h"
#include "buffer_head_io.h"
#include "sysfile.h"
#include "refcounttree.h"
#include "move_extents.h"
struct ocfs2_move_extents_context {
struct inode *inode;
struct file *file;
int auto_defrag;
int partial;
int credits;
u32 new_phys_cpos;
u32 clusters_moved;
u64 refcount_loc;
struct ocfs2_move_extents *range;
struct ocfs2_extent_tree et;
struct ocfs2_alloc_context *meta_ac;
struct ocfs2_alloc_context *data_ac;
struct ocfs2_cached_dealloc_ctxt dealloc;
};
static int __ocfs2_move_extent(handle_t *handle,
struct ocfs2_move_extents_context *context,
u32 cpos, u32 len, u32 p_cpos, u32 new_p_cpos,
int ext_flags)
{
int ret = 0, index;
struct inode *inode = context->inode;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
struct ocfs2_extent_rec *rec, replace_rec;
struct ocfs2_path *path = NULL;
struct ocfs2_extent_list *el;
u64 ino = ocfs2_metadata_cache_owner(context->et.et_ci);
u64 old_blkno = ocfs2_clusters_to_blocks(inode->i_sb, p_cpos);
ret = ocfs2_duplicate_clusters_by_page(handle, inode, cpos,
p_cpos, new_p_cpos, len);
if (ret) {
mlog_errno(ret);
goto out;
}
memset(&replace_rec, 0, sizeof(replace_rec));
replace_rec.e_cpos = cpu_to_le32(cpos);
replace_rec.e_leaf_clusters = cpu_to_le16(len);
replace_rec.e_blkno = cpu_to_le64(ocfs2_clusters_to_blocks(inode->i_sb,
new_p_cpos));
path = ocfs2_new_path_from_et(&context->et);
if (!path) {
ret = -ENOMEM;
mlog_errno(ret);
goto out;
}
ret = ocfs2_find_path(INODE_CACHE(inode), path, cpos);
if (ret) {
mlog_errno(ret);
goto out;
}
el = path_leaf_el(path);
index = ocfs2_search_extent_list(el, cpos);
if (index == -1 || index >= le16_to_cpu(el->l_next_free_rec)) {
ocfs2_error(inode->i_sb,
"Inode %llu has an extent at cpos %u which can no "
"longer be found.\n",
(unsigned long long)ino, cpos);
ret = -EROFS;
goto out;
}
rec = &el->l_recs[index];
BUG_ON(ext_flags != rec->e_flags);
/*
* after moving/defraging to new location, the extent is not going
* to be refcounted anymore.
*/
replace_rec.e_flags = ext_flags & ~OCFS2_EXT_REFCOUNTED;
ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode),
context->et.et_root_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
goto out;
}
ret = ocfs2_split_extent(handle, &context->et, path, index,
&replace_rec, context->meta_ac,
&context->dealloc);
if (ret) {
mlog_errno(ret);
goto out;
}
ocfs2_journal_dirty(handle, context->et.et_root_bh);
context->new_phys_cpos = new_p_cpos;
/*
* need I to append truncate log for old clusters?
*/
if (old_blkno) {
if (ext_flags & OCFS2_EXT_REFCOUNTED)
ret = ocfs2_decrease_refcount(inode, handle,
ocfs2_blocks_to_clusters(osb->sb,
old_blkno),
len, context->meta_ac,
&context->dealloc, 1);
else
ret = ocfs2_truncate_log_append(osb, handle,
old_blkno, len);
}
out:
ocfs2_free_path(path);
return ret;
}
/*
* lock allocators, and reserving appropriate number of bits for
* meta blocks and data clusters.
*
* in some cases, we don't need to reserve clusters, just let data_ac
* be NULL.
*/
static int ocfs2_lock_allocators_move_extents(struct inode *inode,
struct ocfs2_extent_tree *et,
u32 clusters_to_move,
u32 extents_to_split,
struct ocfs2_alloc_context **meta_ac,
struct ocfs2_alloc_context **data_ac,
int extra_blocks,
int *credits)
{
int ret, num_free_extents;
unsigned int max_recs_needed = 2 * extents_to_split + clusters_to_move;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
num_free_extents = ocfs2_num_free_extents(osb, et);
if (num_free_extents < 0) {
ret = num_free_extents;
mlog_errno(ret);
goto out;
}
if (!num_free_extents ||
(ocfs2_sparse_alloc(osb) && num_free_extents < max_recs_needed))
extra_blocks += ocfs2_extend_meta_needed(et->et_root_el);
ret = ocfs2_reserve_new_metadata_blocks(osb, extra_blocks, meta_ac);
if (ret) {
mlog_errno(ret);
goto out;
}
if (data_ac) {
ret = ocfs2_reserve_clusters(osb, clusters_to_move, data_ac);
if (ret) {
mlog_errno(ret);
goto out;
}
}
*credits += ocfs2_calc_extend_credits(osb->sb, et->et_root_el,
clusters_to_move + 2);
mlog(0, "reserve metadata_blocks: %d, data_clusters: %u, credits: %d\n",
extra_blocks, clusters_to_move, *credits);
out:
if (ret) {
if (*meta_ac) {
ocfs2_free_alloc_context(*meta_ac);
*meta_ac = NULL;
}
}
return ret;
}
/*
* Using one journal handle to guarantee the data consistency in case
* crash happens anywhere.
*
* XXX: defrag can end up with finishing partial extent as requested,
* due to not enough contiguous clusters can be found in allocator.
*/
static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context,
u32 cpos, u32 phys_cpos, u32 *len, int ext_flags)
{
int ret, credits = 0, extra_blocks = 0, partial = context->partial;
handle_t *handle;
struct inode *inode = context->inode;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
struct inode *tl_inode = osb->osb_tl_inode;
struct ocfs2_refcount_tree *ref_tree = NULL;
u32 new_phys_cpos, new_len;
u64 phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos);
if ((ext_flags & OCFS2_EXT_REFCOUNTED) && *len) {
BUG_ON(!(OCFS2_I(inode)->ip_dyn_features &
OCFS2_HAS_REFCOUNT_FL));
BUG_ON(!context->refcount_loc);
ret = ocfs2_lock_refcount_tree(osb, context->refcount_loc, 1,
&ref_tree, NULL);
if (ret) {
mlog_errno(ret);
return ret;
}
ret = ocfs2_prepare_refcount_change_for_del(inode,
context->refcount_loc,
phys_blkno,
*len,
&credits,
&extra_blocks);
if (ret) {
mlog_errno(ret);
goto out;
}
}
ret = ocfs2_lock_allocators_move_extents(inode, &context->et, *len, 1,
&context->meta_ac,
&context->data_ac,
extra_blocks, &credits);
if (ret) {
mlog_errno(ret);
goto out;
}
/*
* should be using allocation reservation strategy there?
*
* if (context->data_ac)
* context->data_ac->ac_resv = &OCFS2_I(inode)->ip_la_data_resv;
*/
mutex_lock(&tl_inode->i_mutex);
if (ocfs2_truncate_log_needs_flush(osb)) {
ret = __ocfs2_flush_truncate_log(osb);
if (ret < 0) {
mlog_errno(ret);
goto out_unlock_mutex;
}
}
handle = ocfs2_start_trans(osb, credits);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
mlog_errno(ret);
goto out_unlock_mutex;
}
ret = __ocfs2_claim_clusters(handle, context->data_ac, 1, *len,
&new_phys_cpos, &new_len);
if (ret) {
mlog_errno(ret);
goto out_commit;
}
/*
* allowing partial extent moving is kind of 'pros and cons', it makes
* whole defragmentation less likely to fail, on the contrary, the bad
* thing is it may make the fs even more fragmented after moving, let
* userspace make a good decision here.
*/
if (new_len != *len) {
mlog(0, "len_claimed: %u, len: %u\n", new_len, *len);
if (!partial) {
context->range->me_flags &= ~OCFS2_MOVE_EXT_FL_COMPLETE;
ret = -ENOSPC;
goto out_commit;
}
}
mlog(0, "cpos: %u, phys_cpos: %u, new_phys_cpos: %u\n", cpos,
phys_cpos, new_phys_cpos);
ret = __ocfs2_move_extent(handle, context, cpos, new_len, phys_cpos,
new_phys_cpos, ext_flags);
if (ret)
mlog_errno(ret);
if (partial && (new_len != *len))
*len = new_len;
/*
* Here we should write the new page out first if we are
* in write-back mode.
*/
ret = ocfs2_cow_sync_writeback(inode->i_sb, context->inode, cpos, *len);
if (ret)
mlog_errno(ret);
out_commit:
ocfs2_commit_trans(osb, handle);
out_unlock_mutex:
mutex_unlock(&tl_inode->i_mutex);
if (context->data_ac) {
ocfs2_free_alloc_context(context->data_ac);
context->data_ac = NULL;
}
if (context->meta_ac) {
ocfs2_free_alloc_context(context->meta_ac);
context->meta_ac = NULL;
}
out:
if (ref_tree)
ocfs2_unlock_refcount_tree(osb, ref_tree, 1);
return ret;
}
/*
* find the victim alloc group, where #blkno fits.
*/
static int ocfs2_find_victim_alloc_group(struct inode *inode,
u64 vict_blkno,
int type, int slot,
int *vict_bit,
struct buffer_head **ret_bh)
{
int ret, i, bits_per_unit = 0;
u64 blkno;
char namebuf[40];
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
struct buffer_head *ac_bh = NULL, *gd_bh = NULL;
struct ocfs2_chain_list *cl;
struct ocfs2_chain_rec *rec;
struct ocfs2_dinode *ac_dinode;
struct ocfs2_group_desc *bg;
ocfs2_sprintf_system_inode_name(namebuf, sizeof(namebuf), type, slot);
ret = ocfs2_lookup_ino_from_name(osb->sys_root_inode, namebuf,
strlen(namebuf), &blkno);
if (ret) {
ret = -ENOENT;
goto out;
}
ret = ocfs2_read_blocks_sync(osb, blkno, 1, &ac_bh);
if (ret) {
mlog_errno(ret);
goto out;
}
ac_dinode = (struct ocfs2_dinode *)ac_bh->b_data;
cl = &(ac_dinode->id2.i_chain);
rec = &(cl->cl_recs[0]);
if (type == GLOBAL_BITMAP_SYSTEM_INODE)
bits_per_unit = osb->s_clustersize_bits -
inode->i_sb->s_blocksize_bits;
/*
* 'vict_blkno' was out of the valid range.
*/
if ((vict_blkno < le64_to_cpu(rec->c_blkno)) ||
(vict_blkno >= (le32_to_cpu(ac_dinode->id1.bitmap1.i_total) <<
bits_per_unit))) {
ret = -EINVAL;
goto out;
}
for (i = 0; i < le16_to_cpu(cl->cl_next_free_rec); i++) {
rec = &(cl->cl_recs[i]);
if (!rec)
continue;
bg = NULL;
do {
if (!bg)
blkno = le64_to_cpu(rec->c_blkno);
else
blkno = le64_to_cpu(bg->bg_next_group);
if (gd_bh) {
brelse(gd_bh);
gd_bh = NULL;
}
ret = ocfs2_read_blocks_sync(osb, blkno, 1, &gd_bh);
if (ret) {
mlog_errno(ret);
goto out;
}
bg = (struct ocfs2_group_desc *)gd_bh->b_data;
if (vict_blkno < (le64_to_cpu(bg->bg_blkno) +
le16_to_cpu(bg->bg_bits))) {
*ret_bh = gd_bh;
*vict_bit = (vict_blkno - blkno) >>
bits_per_unit;
mlog(0, "find the victim group: #%llu, "
"total_bits: %u, vict_bit: %u\n",
blkno, le16_to_cpu(bg->bg_bits),
*vict_bit);
goto out;
}
} while (le64_to_cpu(bg->bg_next_group));
}
ret = -EINVAL;
out:
brelse(ac_bh);
/*
* caller has to release the gd_bh properly.
*/
return ret;
}
/*
* XXX: helper to validate and adjust moving goal.
*/
static int ocfs2_validate_and_adjust_move_goal(struct inode *inode,
struct ocfs2_move_extents *range)
{
int ret, goal_bit = 0;
struct buffer_head *gd_bh = NULL;
struct ocfs2_group_desc *bg;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
int c_to_b = 1 << (osb->s_clustersize_bits -
inode->i_sb->s_blocksize_bits);
/*
* make goal become cluster aligned.
*/
range->me_goal = ocfs2_block_to_cluster_start(inode->i_sb,
range->me_goal);
/*
* validate goal sits within global_bitmap, and return the victim
* group desc
*/
ret = ocfs2_find_victim_alloc_group(inode, range->me_goal,
GLOBAL_BITMAP_SYSTEM_INODE,
OCFS2_INVALID_SLOT,
&goal_bit, &gd_bh);
if (ret)
goto out;
bg = (struct ocfs2_group_desc *)gd_bh->b_data;
/*
* moving goal is not allowd to start with a group desc blok(#0 blk)
* let's compromise to the latter cluster.
*/
if (range->me_goal == le64_to_cpu(bg->bg_blkno))
range->me_goal += c_to_b;
/*
* movement is not gonna cross two groups.
*/
if ((le16_to_cpu(bg->bg_bits) - goal_bit) * osb->s_clustersize <
range->me_len) {
ret = -EINVAL;
goto out;
}
/*
* more exact validations/adjustments will be performed later during
* moving operation for each extent range.
*/
mlog(0, "extents get ready to be moved to #%llu block\n",
range->me_goal);
out:
brelse(gd_bh);
return ret;
}
static void ocfs2_probe_alloc_group(struct inode *inode, struct buffer_head *bh,
int *goal_bit, u32 move_len, u32 max_hop,
u32 *phys_cpos)
{
int i, used, last_free_bits = 0, base_bit = *goal_bit;
struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *)bh->b_data;
u32 base_cpos = ocfs2_blocks_to_clusters(inode->i_sb,
le64_to_cpu(gd->bg_blkno));
for (i = base_bit; i < le16_to_cpu(gd->bg_bits); i++) {
used = ocfs2_test_bit(i, (unsigned long *)gd->bg_bitmap);
if (used) {
/*
* we even tried searching the free chunk by jumping
* a 'max_hop' distance, but still failed.
*/
if ((i - base_bit) > max_hop) {
*phys_cpos = 0;
break;
}
if (last_free_bits)
last_free_bits = 0;
continue;
} else
last_free_bits++;
if (last_free_bits == move_len) {
*goal_bit = i;
*phys_cpos = base_cpos + i;
break;
}
}
mlog(0, "found phys_cpos: %u to fit the wanted moving.\n", *phys_cpos);
}
static int ocfs2_alloc_dinode_update_counts(struct inode *inode,
handle_t *handle,
struct buffer_head *di_bh,
u32 num_bits,
u16 chain)
{
int ret;
u32 tmp_used;
struct ocfs2_dinode *di = (struct ocfs2_dinode *) di_bh->b_data;
struct ocfs2_chain_list *cl =
(struct ocfs2_chain_list *) &di->id2.i_chain;
ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret < 0) {
mlog_errno(ret);
goto out;
}
tmp_used = le32_to_cpu(di->id1.bitmap1.i_used);
di->id1.bitmap1.i_used = cpu_to_le32(num_bits + tmp_used);
le32_add_cpu(&cl->cl_recs[chain].c_free, -num_bits);
ocfs2_journal_dirty(handle, di_bh);
out:
return ret;
}
static inline int ocfs2_block_group_set_bits(handle_t *handle,
struct inode *alloc_inode,
struct ocfs2_group_desc *bg,
struct buffer_head *group_bh,
unsigned int bit_off,
unsigned int num_bits)
{
int status;
void *bitmap = bg->bg_bitmap;
int journal_type = OCFS2_JOURNAL_ACCESS_WRITE;
/* All callers get the descriptor via
* ocfs2_read_group_descriptor(). Any corruption is a code bug. */
BUG_ON(!OCFS2_IS_VALID_GROUP_DESC(bg));
BUG_ON(le16_to_cpu(bg->bg_free_bits_count) < num_bits);
mlog(0, "block_group_set_bits: off = %u, num = %u\n", bit_off,
num_bits);
if (ocfs2_is_cluster_bitmap(alloc_inode))
journal_type = OCFS2_JOURNAL_ACCESS_UNDO;
status = ocfs2_journal_access_gd(handle,
INODE_CACHE(alloc_inode),
group_bh,
journal_type);
if (status < 0) {
mlog_errno(status);
goto bail;
}
le16_add_cpu(&bg->bg_free_bits_count, -num_bits);
if (le16_to_cpu(bg->bg_free_bits_count) > le16_to_cpu(bg->bg_bits)) {
ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit"
" count %u but claims %u are freed. num_bits %d",
(unsigned long long)le64_to_cpu(bg->bg_blkno),
le16_to_cpu(bg->bg_bits),
le16_to_cpu(bg->bg_free_bits_count), num_bits);
return -EROFS;
}
while (num_bits--)
ocfs2_set_bit(bit_off++, bitmap);
ocfs2_journal_dirty(handle, group_bh);
bail:
return status;
}
static int ocfs2_move_extent(struct ocfs2_move_extents_context *context,
u32 cpos, u32 phys_cpos, u32 *new_phys_cpos,
u32 len, int ext_flags)
{
int ret, credits = 0, extra_blocks = 0, goal_bit = 0;
handle_t *handle;
struct inode *inode = context->inode;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
struct inode *tl_inode = osb->osb_tl_inode;
struct inode *gb_inode = NULL;
struct buffer_head *gb_bh = NULL;
struct buffer_head *gd_bh = NULL;
struct ocfs2_group_desc *gd;
struct ocfs2_refcount_tree *ref_tree = NULL;
u32 move_max_hop = ocfs2_blocks_to_clusters(inode->i_sb,
context->range->me_threshold);
u64 phys_blkno, new_phys_blkno;
phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos);
if ((ext_flags & OCFS2_EXT_REFCOUNTED) && len) {
BUG_ON(!(OCFS2_I(inode)->ip_dyn_features &
OCFS2_HAS_REFCOUNT_FL));
BUG_ON(!context->refcount_loc);
ret = ocfs2_lock_refcount_tree(osb, context->refcount_loc, 1,
&ref_tree, NULL);
if (ret) {
mlog_errno(ret);
return ret;
}
ret = ocfs2_prepare_refcount_change_for_del(inode,
context->refcount_loc,
phys_blkno,
len,
&credits,
&extra_blocks);
if (ret) {
mlog_errno(ret);
goto out;
}
}
ret = ocfs2_lock_allocators_move_extents(inode, &context->et, len, 1,
&context->meta_ac,
NULL, extra_blocks, &credits);
if (ret) {
mlog_errno(ret);
goto out;
}
/*
* need to count 2 extra credits for global_bitmap inode and
* group descriptor.
*/
credits += OCFS2_INODE_UPDATE_CREDITS + 1;
/*
* ocfs2_move_extent() didn't reserve any clusters in lock_allocators()
* logic, while we still need to lock the global_bitmap.
*/
gb_inode = ocfs2_get_system_file_inode(osb, GLOBAL_BITMAP_SYSTEM_INODE,
OCFS2_INVALID_SLOT);
if (!gb_inode) {
mlog(ML_ERROR, "unable to get global_bitmap inode\n");
ret = -EIO;
goto out;
}
mutex_lock(&gb_inode->i_mutex);
ret = ocfs2_inode_lock(gb_inode, &gb_bh, 1);
if (ret) {
mlog_errno(ret);
goto out_unlock_gb_mutex;
}
mutex_lock(&tl_inode->i_mutex);
handle = ocfs2_start_trans(osb, credits);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
mlog_errno(ret);
goto out_unlock_tl_inode;
}
new_phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, *new_phys_cpos);
ret = ocfs2_find_victim_alloc_group(inode, new_phys_blkno,
GLOBAL_BITMAP_SYSTEM_INODE,
OCFS2_INVALID_SLOT,
&goal_bit, &gd_bh);
if (ret) {
mlog_errno(ret);
goto out_commit;
}
/*
* probe the victim cluster group to find a proper
* region to fit wanted movement, it even will perfrom
* a best-effort attempt by compromising to a threshold
* around the goal.
*/
ocfs2_probe_alloc_group(inode, gd_bh, &goal_bit, len, move_max_hop,
new_phys_cpos);
if (!*new_phys_cpos) {
ret = -ENOSPC;
goto out_commit;
}
ret = __ocfs2_move_extent(handle, context, cpos, len, phys_cpos,
*new_phys_cpos, ext_flags);
if (ret) {
mlog_errno(ret);
goto out_commit;
}
gd = (struct ocfs2_group_desc *)gd_bh->b_data;
ret = ocfs2_alloc_dinode_update_counts(gb_inode, handle, gb_bh, len,
le16_to_cpu(gd->bg_chain));
if (ret) {
mlog_errno(ret);
goto out_commit;
}
ret = ocfs2_block_group_set_bits(handle, gb_inode, gd, gd_bh,
goal_bit, len);
if (ret)
mlog_errno(ret);
/*
* Here we should write the new page out first if we are
* in write-back mode.
*/
ret = ocfs2_cow_sync_writeback(inode->i_sb, context->inode, cpos, len);
if (ret)
mlog_errno(ret);
out_commit:
ocfs2_commit_trans(osb, handle);
brelse(gd_bh);
out_unlock_tl_inode:
mutex_unlock(&tl_inode->i_mutex);
ocfs2_inode_unlock(gb_inode, 1);
out_unlock_gb_mutex:
mutex_unlock(&gb_inode->i_mutex);
brelse(gb_bh);
iput(gb_inode);
out:
if (context->meta_ac) {
ocfs2_free_alloc_context(context->meta_ac);
context->meta_ac = NULL;
}
if (ref_tree)
ocfs2_unlock_refcount_tree(osb, ref_tree, 1);
return ret;
}
/*
* Helper to calculate the defraging length in one run according to threshold.
*/
static void ocfs2_calc_extent_defrag_len(u32 *alloc_size, u32 *len_defraged,
u32 threshold, int *skip)
{
if ((*alloc_size + *len_defraged) < threshold) {
/*
* proceed defragmentation until we meet the thresh
*/
*len_defraged += *alloc_size;
} else if (*len_defraged == 0) {
/*
* XXX: skip a large extent.
*/
*skip = 1;
} else {
/*
* split this extent to coalesce with former pieces as
* to reach the threshold.
*
* we're done here with one cycle of defragmentation
* in a size of 'thresh', resetting 'len_defraged'
* forces a new defragmentation.
*/
*alloc_size = threshold - *len_defraged;
*len_defraged = 0;
}
}
static int __ocfs2_move_extents_range(struct buffer_head *di_bh,
struct ocfs2_move_extents_context *context)
{
int ret = 0, flags, do_defrag, skip = 0;
u32 cpos, phys_cpos, move_start, len_to_move, alloc_size;
u32 len_defraged = 0, defrag_thresh = 0, new_phys_cpos = 0;
struct inode *inode = context->inode;
struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
struct ocfs2_move_extents *range = context->range;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
if ((i_size_read(inode) == 0) || (range->me_len == 0))
return 0;
if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
return 0;
context->refcount_loc = le64_to_cpu(di->i_refcount_loc);
ocfs2_init_dinode_extent_tree(&context->et, INODE_CACHE(inode), di_bh);
ocfs2_init_dealloc_ctxt(&context->dealloc);
/*
* TO-DO XXX:
*
* - xattr extents.
*/
do_defrag = context->auto_defrag;
/*
* extents moving happens in unit of clusters, for the sake
* of simplicity, we may ignore two clusters where 'byte_start'
* and 'byte_start + len' were within.
*/
move_start = ocfs2_clusters_for_bytes(osb->sb, range->me_start);
len_to_move = (range->me_start + range->me_len) >>
osb->s_clustersize_bits;
if (len_to_move >= move_start)
len_to_move -= move_start;
else
len_to_move = 0;
if (do_defrag) {
defrag_thresh = range->me_threshold >> osb->s_clustersize_bits;
if (defrag_thresh <= 1)
goto done;
} else
new_phys_cpos = ocfs2_blocks_to_clusters(inode->i_sb,
range->me_goal);
mlog(0, "Inode: %llu, start: %llu, len: %llu, cstart: %u, clen: %u, "
"thresh: %u\n",
(unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)range->me_start,
(unsigned long long)range->me_len,
move_start, len_to_move, defrag_thresh);
cpos = move_start;
while (len_to_move) {
ret = ocfs2_get_clusters(inode, cpos, &phys_cpos, &alloc_size,
&flags);
if (ret) {
mlog_errno(ret);
goto out;
}
if (alloc_size > len_to_move)
alloc_size = len_to_move;
/*
* XXX: how to deal with a hole:
*
* - skip the hole of course
* - force a new defragmentation
*/
if (!phys_cpos) {
if (do_defrag)
len_defraged = 0;
goto next;
}
if (do_defrag) {
ocfs2_calc_extent_defrag_len(&alloc_size, &len_defraged,
defrag_thresh, &skip);
/*
* skip large extents
*/
if (skip) {
skip = 0;
goto next;
}
mlog(0, "#Defrag: cpos: %u, phys_cpos: %u, "
"alloc_size: %u, len_defraged: %u\n",
cpos, phys_cpos, alloc_size, len_defraged);
ret = ocfs2_defrag_extent(context, cpos, phys_cpos,
&alloc_size, flags);
} else {
ret = ocfs2_move_extent(context, cpos, phys_cpos,
&new_phys_cpos, alloc_size,
flags);
new_phys_cpos += alloc_size;
}
if (ret < 0) {
mlog_errno(ret);
goto out;
}
context->clusters_moved += alloc_size;
next:
cpos += alloc_size;
len_to_move -= alloc_size;
}
done:
range->me_flags |= OCFS2_MOVE_EXT_FL_COMPLETE;
out:
range->me_moved_len = ocfs2_clusters_to_bytes(osb->sb,
context->clusters_moved);
range->me_new_offset = ocfs2_clusters_to_bytes(osb->sb,
context->new_phys_cpos);
ocfs2_schedule_truncate_log_flush(osb, 1);
ocfs2_run_deallocs(osb, &context->dealloc);
return ret;
}
static int ocfs2_move_extents(struct ocfs2_move_extents_context *context)
{
int status;
handle_t *handle;
struct inode *inode = context->inode;
struct ocfs2_dinode *di;
struct buffer_head *di_bh = NULL;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
if (!inode)
return -ENOENT;
if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb))
return -EROFS;
mutex_lock(&inode->i_mutex);
/*
* This prevents concurrent writes from other nodes
*/
status = ocfs2_rw_lock(inode, 1);
if (status) {
mlog_errno(status);
goto out;
}
status = ocfs2_inode_lock(inode, &di_bh, 1);
if (status) {
mlog_errno(status);