-
Notifications
You must be signed in to change notification settings - Fork 2
/
segment.c
2836 lines (2453 loc) · 74.4 KB
/
segment.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
// SPDX-License-Identifier: GPL-2.0+
/*
* segment.c - NILFS segment constructor.
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
* Written by Ryusuke Konishi.
*
*/
#include <linux/pagemap.h>
#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <linux/bitops.h>
#include <linux/bio.h>
#include <linux/completion.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <linux/crc32.h>
#include <linux/pagevec.h>
#include <linux/slab.h>
#include <linux/sched/signal.h>
#include "nilfs.h"
#include "btnode.h"
#include "page.h"
#include "segment.h"
#include "sufile.h"
#include "cpfile.h"
#include "ifile.h"
#include "segbuf.h"
/*
* Segment constructor
*/
#define SC_N_INODEVEC 16 /* Size of locally allocated inode vector */
#define SC_MAX_SEGDELTA 64 /*
* Upper limit of the number of segments
* appended in collection retry loop
*/
/* Construction mode */
enum {
SC_LSEG_SR = 1, /* Make a logical segment having a super root */
SC_LSEG_DSYNC, /*
* Flush data blocks of a given file and make
* a logical segment without a super root.
*/
SC_FLUSH_FILE, /*
* Flush data files, leads to segment writes without
* creating a checkpoint.
*/
SC_FLUSH_DAT, /*
* Flush DAT file. This also creates segments
* without a checkpoint.
*/
};
/* Stage numbers of dirty block collection */
enum {
NILFS_ST_INIT = 0,
NILFS_ST_GC, /* Collecting dirty blocks for GC */
NILFS_ST_FILE,
NILFS_ST_IFILE,
NILFS_ST_CPFILE,
NILFS_ST_SUFILE,
NILFS_ST_DAT,
NILFS_ST_SR, /* Super root */
NILFS_ST_DSYNC, /* Data sync blocks */
NILFS_ST_DONE,
};
#define CREATE_TRACE_POINTS
#include <trace/events/nilfs2.h>
/*
* nilfs_sc_cstage_inc(), nilfs_sc_cstage_set(), nilfs_sc_cstage_get() are
* wrapper functions of stage count (nilfs_sc_info->sc_stage.scnt). Users of
* the variable must use them because transition of stage count must involve
* trace events (trace_nilfs2_collection_stage_transition).
*
* nilfs_sc_cstage_get() isn't required for the above purpose because it doesn't
* produce tracepoint events. It is provided just for making the intention
* clear.
*/
static inline void nilfs_sc_cstage_inc(struct nilfs_sc_info *sci)
{
sci->sc_stage.scnt++;
trace_nilfs2_collection_stage_transition(sci);
}
static inline void nilfs_sc_cstage_set(struct nilfs_sc_info *sci, int next_scnt)
{
sci->sc_stage.scnt = next_scnt;
trace_nilfs2_collection_stage_transition(sci);
}
static inline int nilfs_sc_cstage_get(struct nilfs_sc_info *sci)
{
return sci->sc_stage.scnt;
}
/* State flags of collection */
#define NILFS_CF_NODE 0x0001 /* Collecting node blocks */
#define NILFS_CF_IFILE_STARTED 0x0002 /* IFILE stage has started */
#define NILFS_CF_SUFREED 0x0004 /* segment usages has been freed */
#define NILFS_CF_HISTORY_MASK (NILFS_CF_IFILE_STARTED | NILFS_CF_SUFREED)
/* Operations depending on the construction mode and file type */
struct nilfs_sc_operations {
int (*collect_data)(struct nilfs_sc_info *, struct buffer_head *,
struct inode *);
int (*collect_node)(struct nilfs_sc_info *, struct buffer_head *,
struct inode *);
int (*collect_bmap)(struct nilfs_sc_info *, struct buffer_head *,
struct inode *);
void (*write_data_binfo)(struct nilfs_sc_info *,
struct nilfs_segsum_pointer *,
union nilfs_binfo *);
void (*write_node_binfo)(struct nilfs_sc_info *,
struct nilfs_segsum_pointer *,
union nilfs_binfo *);
};
/*
* Other definitions
*/
static void nilfs_segctor_start_timer(struct nilfs_sc_info *);
static void nilfs_segctor_do_flush(struct nilfs_sc_info *, int);
static void nilfs_segctor_do_immediate_flush(struct nilfs_sc_info *);
static void nilfs_dispose_list(struct the_nilfs *, struct list_head *, int);
#define nilfs_cnt32_gt(a, b) \
(typecheck(__u32, a) && typecheck(__u32, b) && \
((__s32)(b) - (__s32)(a) < 0))
#define nilfs_cnt32_ge(a, b) \
(typecheck(__u32, a) && typecheck(__u32, b) && \
((__s32)(a) - (__s32)(b) >= 0))
#define nilfs_cnt32_lt(a, b) nilfs_cnt32_gt(b, a)
#define nilfs_cnt32_le(a, b) nilfs_cnt32_ge(b, a)
static int nilfs_prepare_segment_lock(struct super_block *sb,
struct nilfs_transaction_info *ti)
{
struct nilfs_transaction_info *cur_ti = current->journal_info;
void *save = NULL;
if (cur_ti) {
if (cur_ti->ti_magic == NILFS_TI_MAGIC)
return ++cur_ti->ti_count;
/*
* If journal_info field is occupied by other FS,
* it is saved and will be restored on
* nilfs_transaction_commit().
*/
nilfs_warn(sb, "journal info from a different FS");
save = current->journal_info;
}
if (!ti) {
ti = kmem_cache_alloc(nilfs_transaction_cachep, GFP_NOFS);
if (!ti)
return -ENOMEM;
ti->ti_flags = NILFS_TI_DYNAMIC_ALLOC;
} else {
ti->ti_flags = 0;
}
ti->ti_count = 0;
ti->ti_save = save;
ti->ti_magic = NILFS_TI_MAGIC;
current->journal_info = ti;
return 0;
}
/**
* nilfs_transaction_begin - start indivisible file operations.
* @sb: super block
* @ti: nilfs_transaction_info
* @vacancy_check: flags for vacancy rate checks
*
* nilfs_transaction_begin() acquires a reader/writer semaphore, called
* the segment semaphore, to make a segment construction and write tasks
* exclusive. The function is used with nilfs_transaction_commit() in pairs.
* The region enclosed by these two functions can be nested. To avoid a
* deadlock, the semaphore is only acquired or released in the outermost call.
*
* This function allocates a nilfs_transaction_info struct to keep context
* information on it. It is initialized and hooked onto the current task in
* the outermost call. If a pre-allocated struct is given to @ti, it is used
* instead; otherwise a new struct is assigned from a slab.
*
* When @vacancy_check flag is set, this function will check the amount of
* free space, and will wait for the GC to reclaim disk space if low capacity.
*
* Return Value: On success, 0 is returned. On error, one of the following
* negative error code is returned.
*
* %-ENOMEM - Insufficient memory available.
*
* %-ENOSPC - No space left on device
*/
int nilfs_transaction_begin(struct super_block *sb,
struct nilfs_transaction_info *ti,
int vacancy_check)
{
struct the_nilfs *nilfs;
int ret = nilfs_prepare_segment_lock(sb, ti);
struct nilfs_transaction_info *trace_ti;
if (unlikely(ret < 0))
return ret;
if (ret > 0) {
trace_ti = current->journal_info;
trace_nilfs2_transaction_transition(sb, trace_ti,
trace_ti->ti_count, trace_ti->ti_flags,
TRACE_NILFS2_TRANSACTION_BEGIN);
return 0;
}
sb_start_intwrite(sb);
nilfs = sb->s_fs_info;
down_read(&nilfs->ns_segctor_sem);
if (vacancy_check && nilfs_near_disk_full(nilfs)) {
up_read(&nilfs->ns_segctor_sem);
ret = -ENOSPC;
goto failed;
}
trace_ti = current->journal_info;
trace_nilfs2_transaction_transition(sb, trace_ti, trace_ti->ti_count,
trace_ti->ti_flags,
TRACE_NILFS2_TRANSACTION_BEGIN);
return 0;
failed:
ti = current->journal_info;
current->journal_info = ti->ti_save;
if (ti->ti_flags & NILFS_TI_DYNAMIC_ALLOC)
kmem_cache_free(nilfs_transaction_cachep, ti);
sb_end_intwrite(sb);
return ret;
}
/**
* nilfs_transaction_commit - commit indivisible file operations.
* @sb: super block
*
* nilfs_transaction_commit() releases the read semaphore which is
* acquired by nilfs_transaction_begin(). This is only performed
* in outermost call of this function. If a commit flag is set,
* nilfs_transaction_commit() sets a timer to start the segment
* constructor. If a sync flag is set, it starts construction
* directly.
*/
int nilfs_transaction_commit(struct super_block *sb)
{
struct nilfs_transaction_info *ti = current->journal_info;
struct the_nilfs *nilfs = sb->s_fs_info;
int err = 0;
BUG_ON(ti == NULL || ti->ti_magic != NILFS_TI_MAGIC);
ti->ti_flags |= NILFS_TI_COMMIT;
if (ti->ti_count > 0) {
ti->ti_count--;
trace_nilfs2_transaction_transition(sb, ti, ti->ti_count,
ti->ti_flags, TRACE_NILFS2_TRANSACTION_COMMIT);
return 0;
}
if (nilfs->ns_writer) {
struct nilfs_sc_info *sci = nilfs->ns_writer;
if (ti->ti_flags & NILFS_TI_COMMIT)
nilfs_segctor_start_timer(sci);
if (atomic_read(&nilfs->ns_ndirtyblks) > sci->sc_watermark)
nilfs_segctor_do_flush(sci, 0);
}
up_read(&nilfs->ns_segctor_sem);
trace_nilfs2_transaction_transition(sb, ti, ti->ti_count,
ti->ti_flags, TRACE_NILFS2_TRANSACTION_COMMIT);
current->journal_info = ti->ti_save;
if (ti->ti_flags & NILFS_TI_SYNC)
err = nilfs_construct_segment(sb);
if (ti->ti_flags & NILFS_TI_DYNAMIC_ALLOC)
kmem_cache_free(nilfs_transaction_cachep, ti);
sb_end_intwrite(sb);
return err;
}
void nilfs_transaction_abort(struct super_block *sb)
{
struct nilfs_transaction_info *ti = current->journal_info;
struct the_nilfs *nilfs = sb->s_fs_info;
BUG_ON(ti == NULL || ti->ti_magic != NILFS_TI_MAGIC);
if (ti->ti_count > 0) {
ti->ti_count--;
trace_nilfs2_transaction_transition(sb, ti, ti->ti_count,
ti->ti_flags, TRACE_NILFS2_TRANSACTION_ABORT);
return;
}
up_read(&nilfs->ns_segctor_sem);
trace_nilfs2_transaction_transition(sb, ti, ti->ti_count,
ti->ti_flags, TRACE_NILFS2_TRANSACTION_ABORT);
current->journal_info = ti->ti_save;
if (ti->ti_flags & NILFS_TI_DYNAMIC_ALLOC)
kmem_cache_free(nilfs_transaction_cachep, ti);
sb_end_intwrite(sb);
}
void nilfs_relax_pressure_in_lock(struct super_block *sb)
{
struct the_nilfs *nilfs = sb->s_fs_info;
struct nilfs_sc_info *sci = nilfs->ns_writer;
if (sb_rdonly(sb) || unlikely(!sci) || !sci->sc_flush_request)
return;
set_bit(NILFS_SC_PRIOR_FLUSH, &sci->sc_flags);
up_read(&nilfs->ns_segctor_sem);
down_write(&nilfs->ns_segctor_sem);
if (sci->sc_flush_request &&
test_bit(NILFS_SC_PRIOR_FLUSH, &sci->sc_flags)) {
struct nilfs_transaction_info *ti = current->journal_info;
ti->ti_flags |= NILFS_TI_WRITER;
nilfs_segctor_do_immediate_flush(sci);
ti->ti_flags &= ~NILFS_TI_WRITER;
}
downgrade_write(&nilfs->ns_segctor_sem);
}
static void nilfs_transaction_lock(struct super_block *sb,
struct nilfs_transaction_info *ti,
int gcflag)
{
struct nilfs_transaction_info *cur_ti = current->journal_info;
struct the_nilfs *nilfs = sb->s_fs_info;
struct nilfs_sc_info *sci = nilfs->ns_writer;
WARN_ON(cur_ti);
ti->ti_flags = NILFS_TI_WRITER;
ti->ti_count = 0;
ti->ti_save = cur_ti;
ti->ti_magic = NILFS_TI_MAGIC;
current->journal_info = ti;
for (;;) {
trace_nilfs2_transaction_transition(sb, ti, ti->ti_count,
ti->ti_flags, TRACE_NILFS2_TRANSACTION_TRYLOCK);
down_write(&nilfs->ns_segctor_sem);
if (!test_bit(NILFS_SC_PRIOR_FLUSH, &sci->sc_flags))
break;
nilfs_segctor_do_immediate_flush(sci);
up_write(&nilfs->ns_segctor_sem);
cond_resched();
}
if (gcflag)
ti->ti_flags |= NILFS_TI_GC;
trace_nilfs2_transaction_transition(sb, ti, ti->ti_count,
ti->ti_flags, TRACE_NILFS2_TRANSACTION_LOCK);
}
static void nilfs_transaction_unlock(struct super_block *sb)
{
struct nilfs_transaction_info *ti = current->journal_info;
struct the_nilfs *nilfs = sb->s_fs_info;
BUG_ON(ti == NULL || ti->ti_magic != NILFS_TI_MAGIC);
BUG_ON(ti->ti_count > 0);
up_write(&nilfs->ns_segctor_sem);
current->journal_info = ti->ti_save;
trace_nilfs2_transaction_transition(sb, ti, ti->ti_count,
ti->ti_flags, TRACE_NILFS2_TRANSACTION_UNLOCK);
}
static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci,
struct nilfs_segsum_pointer *ssp,
unsigned int bytes)
{
struct nilfs_segment_buffer *segbuf = sci->sc_curseg;
unsigned int blocksize = sci->sc_super->s_blocksize;
void *p;
if (unlikely(ssp->offset + bytes > blocksize)) {
ssp->offset = 0;
BUG_ON(NILFS_SEGBUF_BH_IS_LAST(ssp->bh,
&segbuf->sb_segsum_buffers));
ssp->bh = NILFS_SEGBUF_NEXT_BH(ssp->bh);
}
p = ssp->bh->b_data + ssp->offset;
ssp->offset += bytes;
return p;
}
/**
* nilfs_segctor_reset_segment_buffer - reset the current segment buffer
* @sci: nilfs_sc_info
*/
static int nilfs_segctor_reset_segment_buffer(struct nilfs_sc_info *sci)
{
struct nilfs_segment_buffer *segbuf = sci->sc_curseg;
struct buffer_head *sumbh;
unsigned int sumbytes;
unsigned int flags = 0;
int err;
if (nilfs_doing_gc())
flags = NILFS_SS_GC;
err = nilfs_segbuf_reset(segbuf, flags, sci->sc_seg_ctime, sci->sc_cno);
if (unlikely(err))
return err;
sumbh = NILFS_SEGBUF_FIRST_BH(&segbuf->sb_segsum_buffers);
sumbytes = segbuf->sb_sum.sumbytes;
sci->sc_finfo_ptr.bh = sumbh; sci->sc_finfo_ptr.offset = sumbytes;
sci->sc_binfo_ptr.bh = sumbh; sci->sc_binfo_ptr.offset = sumbytes;
sci->sc_blk_cnt = sci->sc_datablk_cnt = 0;
return 0;
}
static int nilfs_segctor_feed_segment(struct nilfs_sc_info *sci)
{
sci->sc_nblk_this_inc += sci->sc_curseg->sb_sum.nblocks;
if (NILFS_SEGBUF_IS_LAST(sci->sc_curseg, &sci->sc_segbufs))
return -E2BIG; /*
* The current segment is filled up
* (internal code)
*/
sci->sc_curseg = NILFS_NEXT_SEGBUF(sci->sc_curseg);
return nilfs_segctor_reset_segment_buffer(sci);
}
static int nilfs_segctor_add_super_root(struct nilfs_sc_info *sci)
{
struct nilfs_segment_buffer *segbuf = sci->sc_curseg;
int err;
if (segbuf->sb_sum.nblocks >= segbuf->sb_rest_blocks) {
err = nilfs_segctor_feed_segment(sci);
if (err)
return err;
segbuf = sci->sc_curseg;
}
err = nilfs_segbuf_extend_payload(segbuf, &segbuf->sb_super_root);
if (likely(!err))
segbuf->sb_sum.flags |= NILFS_SS_SR;
return err;
}
/*
* Functions for making segment summary and payloads
*/
static int nilfs_segctor_segsum_block_required(
struct nilfs_sc_info *sci, const struct nilfs_segsum_pointer *ssp,
unsigned int binfo_size)
{
unsigned int blocksize = sci->sc_super->s_blocksize;
/* Size of finfo and binfo is enough small against blocksize */
return ssp->offset + binfo_size +
(!sci->sc_blk_cnt ? sizeof(struct nilfs_finfo) : 0) >
blocksize;
}
static void nilfs_segctor_begin_finfo(struct nilfs_sc_info *sci,
struct inode *inode)
{
sci->sc_curseg->sb_sum.nfinfo++;
sci->sc_binfo_ptr = sci->sc_finfo_ptr;
nilfs_segctor_map_segsum_entry(
sci, &sci->sc_binfo_ptr, sizeof(struct nilfs_finfo));
if (NILFS_I(inode)->i_root &&
!test_bit(NILFS_SC_HAVE_DELTA, &sci->sc_flags))
set_bit(NILFS_SC_HAVE_DELTA, &sci->sc_flags);
/* skip finfo */
}
static void nilfs_segctor_end_finfo(struct nilfs_sc_info *sci,
struct inode *inode)
{
struct nilfs_finfo *finfo;
struct nilfs_inode_info *ii;
struct nilfs_segment_buffer *segbuf;
__u64 cno;
if (sci->sc_blk_cnt == 0)
return;
ii = NILFS_I(inode);
if (test_bit(NILFS_I_GCINODE, &ii->i_state))
cno = ii->i_cno;
else if (NILFS_ROOT_METADATA_FILE(inode->i_ino))
cno = 0;
else
cno = sci->sc_cno;
finfo = nilfs_segctor_map_segsum_entry(sci, &sci->sc_finfo_ptr,
sizeof(*finfo));
finfo->fi_ino = cpu_to_le64(inode->i_ino);
finfo->fi_nblocks = cpu_to_le32(sci->sc_blk_cnt);
finfo->fi_ndatablk = cpu_to_le32(sci->sc_datablk_cnt);
finfo->fi_cno = cpu_to_le64(cno);
segbuf = sci->sc_curseg;
segbuf->sb_sum.sumbytes = sci->sc_binfo_ptr.offset +
sci->sc_super->s_blocksize * (segbuf->sb_sum.nsumblk - 1);
sci->sc_finfo_ptr = sci->sc_binfo_ptr;
sci->sc_blk_cnt = sci->sc_datablk_cnt = 0;
}
static int nilfs_segctor_add_file_block(struct nilfs_sc_info *sci,
struct buffer_head *bh,
struct inode *inode,
unsigned int binfo_size)
{
struct nilfs_segment_buffer *segbuf;
int required, err = 0;
retry:
segbuf = sci->sc_curseg;
required = nilfs_segctor_segsum_block_required(
sci, &sci->sc_binfo_ptr, binfo_size);
if (segbuf->sb_sum.nblocks + required + 1 > segbuf->sb_rest_blocks) {
nilfs_segctor_end_finfo(sci, inode);
err = nilfs_segctor_feed_segment(sci);
if (err)
return err;
goto retry;
}
if (unlikely(required)) {
err = nilfs_segbuf_extend_segsum(segbuf);
if (unlikely(err))
goto failed;
}
if (sci->sc_blk_cnt == 0)
nilfs_segctor_begin_finfo(sci, inode);
nilfs_segctor_map_segsum_entry(sci, &sci->sc_binfo_ptr, binfo_size);
/* Substitution to vblocknr is delayed until update_blocknr() */
nilfs_segbuf_add_file_buffer(segbuf, bh);
sci->sc_blk_cnt++;
failed:
return err;
}
/*
* Callback functions that enumerate, mark, and collect dirty blocks
*/
static int nilfs_collect_file_data(struct nilfs_sc_info *sci,
struct buffer_head *bh, struct inode *inode)
{
int err;
err = nilfs_bmap_propagate(NILFS_I(inode)->i_bmap, bh);
if (err < 0)
return err;
err = nilfs_segctor_add_file_block(sci, bh, inode,
sizeof(struct nilfs_binfo_v));
if (!err)
sci->sc_datablk_cnt++;
return err;
}
static int nilfs_collect_file_node(struct nilfs_sc_info *sci,
struct buffer_head *bh,
struct inode *inode)
{
return nilfs_bmap_propagate(NILFS_I(inode)->i_bmap, bh);
}
static int nilfs_collect_file_bmap(struct nilfs_sc_info *sci,
struct buffer_head *bh,
struct inode *inode)
{
WARN_ON(!buffer_dirty(bh));
return nilfs_segctor_add_file_block(sci, bh, inode, sizeof(__le64));
}
static void nilfs_write_file_data_binfo(struct nilfs_sc_info *sci,
struct nilfs_segsum_pointer *ssp,
union nilfs_binfo *binfo)
{
struct nilfs_binfo_v *binfo_v = nilfs_segctor_map_segsum_entry(
sci, ssp, sizeof(*binfo_v));
*binfo_v = binfo->bi_v;
}
static void nilfs_write_file_node_binfo(struct nilfs_sc_info *sci,
struct nilfs_segsum_pointer *ssp,
union nilfs_binfo *binfo)
{
__le64 *vblocknr = nilfs_segctor_map_segsum_entry(
sci, ssp, sizeof(*vblocknr));
*vblocknr = binfo->bi_v.bi_vblocknr;
}
static const struct nilfs_sc_operations nilfs_sc_file_ops = {
.collect_data = nilfs_collect_file_data,
.collect_node = nilfs_collect_file_node,
.collect_bmap = nilfs_collect_file_bmap,
.write_data_binfo = nilfs_write_file_data_binfo,
.write_node_binfo = nilfs_write_file_node_binfo,
};
static int nilfs_collect_dat_data(struct nilfs_sc_info *sci,
struct buffer_head *bh, struct inode *inode)
{
int err;
err = nilfs_bmap_propagate(NILFS_I(inode)->i_bmap, bh);
if (err < 0)
return err;
err = nilfs_segctor_add_file_block(sci, bh, inode, sizeof(__le64));
if (!err)
sci->sc_datablk_cnt++;
return err;
}
static int nilfs_collect_dat_bmap(struct nilfs_sc_info *sci,
struct buffer_head *bh, struct inode *inode)
{
WARN_ON(!buffer_dirty(bh));
return nilfs_segctor_add_file_block(sci, bh, inode,
sizeof(struct nilfs_binfo_dat));
}
static void nilfs_write_dat_data_binfo(struct nilfs_sc_info *sci,
struct nilfs_segsum_pointer *ssp,
union nilfs_binfo *binfo)
{
__le64 *blkoff = nilfs_segctor_map_segsum_entry(sci, ssp,
sizeof(*blkoff));
*blkoff = binfo->bi_dat.bi_blkoff;
}
static void nilfs_write_dat_node_binfo(struct nilfs_sc_info *sci,
struct nilfs_segsum_pointer *ssp,
union nilfs_binfo *binfo)
{
struct nilfs_binfo_dat *binfo_dat =
nilfs_segctor_map_segsum_entry(sci, ssp, sizeof(*binfo_dat));
*binfo_dat = binfo->bi_dat;
}
static const struct nilfs_sc_operations nilfs_sc_dat_ops = {
.collect_data = nilfs_collect_dat_data,
.collect_node = nilfs_collect_file_node,
.collect_bmap = nilfs_collect_dat_bmap,
.write_data_binfo = nilfs_write_dat_data_binfo,
.write_node_binfo = nilfs_write_dat_node_binfo,
};
static const struct nilfs_sc_operations nilfs_sc_dsync_ops = {
.collect_data = nilfs_collect_file_data,
.collect_node = NULL,
.collect_bmap = NULL,
.write_data_binfo = nilfs_write_file_data_binfo,
.write_node_binfo = NULL,
};
static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode,
struct list_head *listp,
size_t nlimit,
loff_t start, loff_t end)
{
struct address_space *mapping = inode->i_mapping;
struct pagevec pvec;
pgoff_t index = 0, last = ULONG_MAX;
size_t ndirties = 0;
int i;
if (unlikely(start != 0 || end != LLONG_MAX)) {
/*
* A valid range is given for sync-ing data pages. The
* range is rounded to per-page; extra dirty buffers
* may be included if blocksize < pagesize.
*/
index = start >> PAGE_SHIFT;
last = end >> PAGE_SHIFT;
}
pagevec_init(&pvec);
repeat:
if (unlikely(index > last) ||
!pagevec_lookup_range_tag(&pvec, mapping, &index, last,
PAGECACHE_TAG_DIRTY))
return ndirties;
for (i = 0; i < pagevec_count(&pvec); i++) {
struct buffer_head *bh, *head;
struct page *page = pvec.pages[i];
lock_page(page);
if (!page_has_buffers(page))
create_empty_buffers(page, i_blocksize(inode), 0);
unlock_page(page);
bh = head = page_buffers(page);
do {
if (!buffer_dirty(bh) || buffer_async_write(bh))
continue;
get_bh(bh);
list_add_tail(&bh->b_assoc_buffers, listp);
ndirties++;
if (unlikely(ndirties >= nlimit)) {
pagevec_release(&pvec);
cond_resched();
return ndirties;
}
} while (bh = bh->b_this_page, bh != head);
}
pagevec_release(&pvec);
cond_resched();
goto repeat;
}
static void nilfs_lookup_dirty_node_buffers(struct inode *inode,
struct list_head *listp)
{
struct nilfs_inode_info *ii = NILFS_I(inode);
struct inode *btnc_inode = ii->i_assoc_inode;
struct pagevec pvec;
struct buffer_head *bh, *head;
unsigned int i;
pgoff_t index = 0;
if (!btnc_inode)
return;
pagevec_init(&pvec);
while (pagevec_lookup_tag(&pvec, btnc_inode->i_mapping, &index,
PAGECACHE_TAG_DIRTY)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
bh = head = page_buffers(pvec.pages[i]);
do {
if (buffer_dirty(bh) &&
!buffer_async_write(bh)) {
get_bh(bh);
list_add_tail(&bh->b_assoc_buffers,
listp);
}
bh = bh->b_this_page;
} while (bh != head);
}
pagevec_release(&pvec);
cond_resched();
}
}
static void nilfs_dispose_list(struct the_nilfs *nilfs,
struct list_head *head, int force)
{
struct nilfs_inode_info *ii, *n;
struct nilfs_inode_info *ivec[SC_N_INODEVEC], **pii;
unsigned int nv = 0;
while (!list_empty(head)) {
spin_lock(&nilfs->ns_inode_lock);
list_for_each_entry_safe(ii, n, head, i_dirty) {
list_del_init(&ii->i_dirty);
if (force) {
if (unlikely(ii->i_bh)) {
brelse(ii->i_bh);
ii->i_bh = NULL;
}
} else if (test_bit(NILFS_I_DIRTY, &ii->i_state)) {
set_bit(NILFS_I_QUEUED, &ii->i_state);
list_add_tail(&ii->i_dirty,
&nilfs->ns_dirty_files);
continue;
}
ivec[nv++] = ii;
if (nv == SC_N_INODEVEC)
break;
}
spin_unlock(&nilfs->ns_inode_lock);
for (pii = ivec; nv > 0; pii++, nv--)
iput(&(*pii)->vfs_inode);
}
}
static void nilfs_iput_work_func(struct work_struct *work)
{
struct nilfs_sc_info *sci = container_of(work, struct nilfs_sc_info,
sc_iput_work);
struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 0);
}
static int nilfs_test_metadata_dirty(struct the_nilfs *nilfs,
struct nilfs_root *root)
{
int ret = 0;
if (nilfs_mdt_fetch_dirty(root->ifile))
ret++;
if (nilfs_mdt_fetch_dirty(nilfs->ns_cpfile))
ret++;
if (nilfs_mdt_fetch_dirty(nilfs->ns_sufile))
ret++;
if ((ret || nilfs_doing_gc()) && nilfs_mdt_fetch_dirty(nilfs->ns_dat))
ret++;
return ret;
}
static int nilfs_segctor_clean(struct nilfs_sc_info *sci)
{
return list_empty(&sci->sc_dirty_files) &&
!test_bit(NILFS_SC_DIRTY, &sci->sc_flags) &&
sci->sc_nfreesegs == 0 &&
(!nilfs_doing_gc() || list_empty(&sci->sc_gc_inodes));
}
static int nilfs_segctor_confirm(struct nilfs_sc_info *sci)
{
struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
int ret = 0;
if (nilfs_test_metadata_dirty(nilfs, sci->sc_root))
set_bit(NILFS_SC_DIRTY, &sci->sc_flags);
spin_lock(&nilfs->ns_inode_lock);
if (list_empty(&nilfs->ns_dirty_files) && nilfs_segctor_clean(sci))
ret++;
spin_unlock(&nilfs->ns_inode_lock);
return ret;
}
static void nilfs_segctor_clear_metadata_dirty(struct nilfs_sc_info *sci)
{
struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
nilfs_mdt_clear_dirty(sci->sc_root->ifile);
nilfs_mdt_clear_dirty(nilfs->ns_cpfile);
nilfs_mdt_clear_dirty(nilfs->ns_sufile);
nilfs_mdt_clear_dirty(nilfs->ns_dat);
}
static int nilfs_segctor_create_checkpoint(struct nilfs_sc_info *sci)
{
struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
struct buffer_head *bh_cp;
struct nilfs_checkpoint *raw_cp;
int err;
/* XXX: this interface will be changed */
err = nilfs_cpfile_get_checkpoint(nilfs->ns_cpfile, nilfs->ns_cno, 1,
&raw_cp, &bh_cp);
if (likely(!err)) {
/*
* The following code is duplicated with cpfile. But, it is
* needed to collect the checkpoint even if it was not newly
* created.
*/
mark_buffer_dirty(bh_cp);
nilfs_mdt_mark_dirty(nilfs->ns_cpfile);
nilfs_cpfile_put_checkpoint(
nilfs->ns_cpfile, nilfs->ns_cno, bh_cp);
} else if (err == -EINVAL || err == -ENOENT) {
nilfs_error(sci->sc_super,
"checkpoint creation failed due to metadata corruption.");
err = -EIO;
}
return err;
}
static int nilfs_segctor_fill_in_checkpoint(struct nilfs_sc_info *sci)
{
struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
struct buffer_head *bh_cp;
struct nilfs_checkpoint *raw_cp;
int err;
err = nilfs_cpfile_get_checkpoint(nilfs->ns_cpfile, nilfs->ns_cno, 0,
&raw_cp, &bh_cp);
if (unlikely(err)) {
if (err == -EINVAL || err == -ENOENT) {
nilfs_error(sci->sc_super,
"checkpoint finalization failed due to metadata corruption.");
err = -EIO;
}
goto failed_ibh;
}
raw_cp->cp_snapshot_list.ssl_next = 0;
raw_cp->cp_snapshot_list.ssl_prev = 0;
raw_cp->cp_inodes_count =
cpu_to_le64(atomic64_read(&sci->sc_root->inodes_count));
raw_cp->cp_blocks_count =
cpu_to_le64(atomic64_read(&sci->sc_root->blocks_count));
raw_cp->cp_nblk_inc =
cpu_to_le64(sci->sc_nblk_inc + sci->sc_nblk_this_inc);
raw_cp->cp_create = cpu_to_le64(sci->sc_seg_ctime);
raw_cp->cp_cno = cpu_to_le64(nilfs->ns_cno);
if (test_bit(NILFS_SC_HAVE_DELTA, &sci->sc_flags))
nilfs_checkpoint_clear_minor(raw_cp);
else
nilfs_checkpoint_set_minor(raw_cp);
nilfs_write_inode_common(sci->sc_root->ifile,
&raw_cp->cp_ifile_inode, 1);
nilfs_cpfile_put_checkpoint(nilfs->ns_cpfile, nilfs->ns_cno, bh_cp);
return 0;
failed_ibh:
return err;
}
static void nilfs_fill_in_file_bmap(struct inode *ifile,
struct nilfs_inode_info *ii)
{
struct buffer_head *ibh;
struct nilfs_inode *raw_inode;
if (test_bit(NILFS_I_BMAP, &ii->i_state)) {
ibh = ii->i_bh;
BUG_ON(!ibh);
raw_inode = nilfs_ifile_map_inode(ifile, ii->vfs_inode.i_ino,
ibh);
nilfs_bmap_write(ii->i_bmap, raw_inode);
nilfs_ifile_unmap_inode(ifile, ii->vfs_inode.i_ino, ibh);
}
}
static void nilfs_segctor_fill_in_file_bmap(struct nilfs_sc_info *sci)
{
struct nilfs_inode_info *ii;
list_for_each_entry(ii, &sci->sc_dirty_files, i_dirty) {
nilfs_fill_in_file_bmap(sci->sc_root->ifile, ii);
set_bit(NILFS_I_COLLECTED, &ii->i_state);
}
}
static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci,
struct the_nilfs *nilfs)
{
struct buffer_head *bh_sr;
struct nilfs_super_root *raw_sr;
unsigned int isz, srsz;
bh_sr = NILFS_LAST_SEGBUF(&sci->sc_segbufs)->sb_super_root;
raw_sr = (struct nilfs_super_root *)bh_sr->b_data;
isz = nilfs->ns_inode_size;
srsz = NILFS_SR_BYTES(isz);
raw_sr->sr_bytes = cpu_to_le16(srsz);
raw_sr->sr_nongc_ctime
= cpu_to_le64(nilfs_doing_gc() ?
nilfs->ns_nongc_ctime : sci->sc_seg_ctime);
raw_sr->sr_flags = 0;
nilfs_write_inode_common(nilfs->ns_dat, (void *)raw_sr +
NILFS_SR_DAT_OFFSET(isz), 1);
nilfs_write_inode_common(nilfs->ns_cpfile, (void *)raw_sr +
NILFS_SR_CPFILE_OFFSET(isz), 1);
nilfs_write_inode_common(nilfs->ns_sufile, (void *)raw_sr +
NILFS_SR_SUFILE_OFFSET(isz), 1);
memset((void *)raw_sr + srsz, 0, nilfs->ns_blocksize - srsz);
}
static void nilfs_redirty_inodes(struct list_head *head)
{
struct nilfs_inode_info *ii;
list_for_each_entry(ii, head, i_dirty) {
if (test_bit(NILFS_I_COLLECTED, &ii->i_state))
clear_bit(NILFS_I_COLLECTED, &ii->i_state);
}
}
static void nilfs_drop_collected_inodes(struct list_head *head)
{
struct nilfs_inode_info *ii;