forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
data.c
4164 lines (3519 loc) · 100 KB
/
data.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
/*
* fs/f2fs/data.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/buffer_head.h>
#include <linux/sched/mm.h>
#include <linux/mpage.h>
#include <linux/writeback.h>
#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/bio.h>
#include <linux/blk-crypto.h>
#include <linux/swap.h>
#include <linux/prefetch.h>
#include <linux/uio.h>
#include <linux/sched/signal.h>
#include <linux/fiemap.h>
#include <linux/iomap.h>
#include "f2fs.h"
#include "node.h"
#include "segment.h"
#include "iostat.h"
#include <trace/events/f2fs.h>
#define NUM_PREALLOC_POST_READ_CTXS 128
static struct kmem_cache *bio_post_read_ctx_cache;
static struct kmem_cache *bio_entry_slab;
static mempool_t *bio_post_read_ctx_pool;
static struct bio_set f2fs_bioset;
#define F2FS_BIO_POOL_SIZE NR_CURSEG_TYPE
int __init f2fs_init_bioset(void)
{
if (bioset_init(&f2fs_bioset, F2FS_BIO_POOL_SIZE,
0, BIOSET_NEED_BVECS))
return -ENOMEM;
return 0;
}
void f2fs_destroy_bioset(void)
{
bioset_exit(&f2fs_bioset);
}
static bool __is_cp_guaranteed(struct page *page)
{
struct address_space *mapping = page->mapping;
struct inode *inode;
struct f2fs_sb_info *sbi;
if (!mapping)
return false;
inode = mapping->host;
sbi = F2FS_I_SB(inode);
if (inode->i_ino == F2FS_META_INO(sbi) ||
inode->i_ino == F2FS_NODE_INO(sbi) ||
S_ISDIR(inode->i_mode))
return true;
if (f2fs_is_compressed_page(page))
return false;
if ((S_ISREG(inode->i_mode) && IS_NOQUOTA(inode)) ||
page_private_gcing(page))
return true;
return false;
}
static enum count_type __read_io_type(struct page *page)
{
struct address_space *mapping = page_file_mapping(page);
if (mapping) {
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (inode->i_ino == F2FS_META_INO(sbi))
return F2FS_RD_META;
if (inode->i_ino == F2FS_NODE_INO(sbi))
return F2FS_RD_NODE;
}
return F2FS_RD_DATA;
}
/* postprocessing steps for read bios */
enum bio_post_read_step {
#ifdef CONFIG_FS_ENCRYPTION
STEP_DECRYPT = 1 << 0,
#else
STEP_DECRYPT = 0, /* compile out the decryption-related code */
#endif
#ifdef CONFIG_F2FS_FS_COMPRESSION
STEP_DECOMPRESS = 1 << 1,
#else
STEP_DECOMPRESS = 0, /* compile out the decompression-related code */
#endif
#ifdef CONFIG_FS_VERITY
STEP_VERITY = 1 << 2,
#else
STEP_VERITY = 0, /* compile out the verity-related code */
#endif
};
struct bio_post_read_ctx {
struct bio *bio;
struct f2fs_sb_info *sbi;
struct work_struct work;
unsigned int enabled_steps;
block_t fs_blkaddr;
};
static void f2fs_finish_read_bio(struct bio *bio)
{
struct bio_vec *bv;
struct bvec_iter_all iter_all;
/*
* Update and unlock the bio's pagecache pages, and put the
* decompression context for any compressed pages.
*/
bio_for_each_segment_all(bv, bio, iter_all) {
struct page *page = bv->bv_page;
if (f2fs_is_compressed_page(page)) {
if (bio->bi_status)
f2fs_end_read_compressed_page(page, true, 0);
f2fs_put_page_dic(page);
continue;
}
/* PG_error was set if decryption or verity failed. */
if (bio->bi_status || PageError(page)) {
ClearPageUptodate(page);
/* will re-read again later */
ClearPageError(page);
} else {
SetPageUptodate(page);
}
dec_page_count(F2FS_P_SB(page), __read_io_type(page));
unlock_page(page);
}
if (bio->bi_private)
mempool_free(bio->bi_private, bio_post_read_ctx_pool);
bio_put(bio);
}
static void f2fs_verify_bio(struct work_struct *work)
{
struct bio_post_read_ctx *ctx =
container_of(work, struct bio_post_read_ctx, work);
struct bio *bio = ctx->bio;
bool may_have_compressed_pages = (ctx->enabled_steps & STEP_DECOMPRESS);
/*
* fsverity_verify_bio() may call readahead() again, and while verity
* will be disabled for this, decryption and/or decompression may still
* be needed, resulting in another bio_post_read_ctx being allocated.
* So to prevent deadlocks we need to release the current ctx to the
* mempool first. This assumes that verity is the last post-read step.
*/
mempool_free(ctx, bio_post_read_ctx_pool);
bio->bi_private = NULL;
/*
* Verify the bio's pages with fs-verity. Exclude compressed pages,
* as those were handled separately by f2fs_end_read_compressed_page().
*/
if (may_have_compressed_pages) {
struct bio_vec *bv;
struct bvec_iter_all iter_all;
bio_for_each_segment_all(bv, bio, iter_all) {
struct page *page = bv->bv_page;
if (!f2fs_is_compressed_page(page) &&
!PageError(page) && !fsverity_verify_page(page))
SetPageError(page);
}
} else {
fsverity_verify_bio(bio);
}
f2fs_finish_read_bio(bio);
}
/*
* If the bio's data needs to be verified with fs-verity, then enqueue the
* verity work for the bio. Otherwise finish the bio now.
*
* Note that to avoid deadlocks, the verity work can't be done on the
* decryption/decompression workqueue. This is because verifying the data pages
* can involve reading verity metadata pages from the file, and these verity
* metadata pages may be encrypted and/or compressed.
*/
static void f2fs_verify_and_finish_bio(struct bio *bio)
{
struct bio_post_read_ctx *ctx = bio->bi_private;
if (ctx && (ctx->enabled_steps & STEP_VERITY)) {
INIT_WORK(&ctx->work, f2fs_verify_bio);
fsverity_enqueue_verify_work(&ctx->work);
} else {
f2fs_finish_read_bio(bio);
}
}
/*
* Handle STEP_DECOMPRESS by decompressing any compressed clusters whose last
* remaining page was read by @ctx->bio.
*
* Note that a bio may span clusters (even a mix of compressed and uncompressed
* clusters) or be for just part of a cluster. STEP_DECOMPRESS just indicates
* that the bio includes at least one compressed page. The actual decompression
* is done on a per-cluster basis, not a per-bio basis.
*/
static void f2fs_handle_step_decompress(struct bio_post_read_ctx *ctx)
{
struct bio_vec *bv;
struct bvec_iter_all iter_all;
bool all_compressed = true;
block_t blkaddr = ctx->fs_blkaddr;
bio_for_each_segment_all(bv, ctx->bio, iter_all) {
struct page *page = bv->bv_page;
/* PG_error was set if decryption failed. */
if (f2fs_is_compressed_page(page))
f2fs_end_read_compressed_page(page, PageError(page),
blkaddr);
else
all_compressed = false;
blkaddr++;
}
/*
* Optimization: if all the bio's pages are compressed, then scheduling
* the per-bio verity work is unnecessary, as verity will be fully
* handled at the compression cluster level.
*/
if (all_compressed)
ctx->enabled_steps &= ~STEP_VERITY;
}
static void f2fs_post_read_work(struct work_struct *work)
{
struct bio_post_read_ctx *ctx =
container_of(work, struct bio_post_read_ctx, work);
if (ctx->enabled_steps & STEP_DECRYPT)
fscrypt_decrypt_bio(ctx->bio);
if (ctx->enabled_steps & STEP_DECOMPRESS)
f2fs_handle_step_decompress(ctx);
f2fs_verify_and_finish_bio(ctx->bio);
}
static void f2fs_read_end_io(struct bio *bio)
{
struct f2fs_sb_info *sbi = F2FS_P_SB(bio_first_page_all(bio));
struct bio_post_read_ctx *ctx;
iostat_update_and_unbind_ctx(bio, 0);
ctx = bio->bi_private;
if (time_to_inject(sbi, FAULT_READ_IO)) {
f2fs_show_injection_info(sbi, FAULT_READ_IO);
bio->bi_status = BLK_STS_IOERR;
}
if (bio->bi_status) {
f2fs_finish_read_bio(bio);
return;
}
if (ctx && (ctx->enabled_steps & (STEP_DECRYPT | STEP_DECOMPRESS))) {
INIT_WORK(&ctx->work, f2fs_post_read_work);
queue_work(ctx->sbi->post_read_wq, &ctx->work);
} else {
f2fs_verify_and_finish_bio(bio);
}
}
static void f2fs_write_end_io(struct bio *bio)
{
struct f2fs_sb_info *sbi;
struct bio_vec *bvec;
struct bvec_iter_all iter_all;
iostat_update_and_unbind_ctx(bio, 1);
sbi = bio->bi_private;
if (time_to_inject(sbi, FAULT_WRITE_IO)) {
f2fs_show_injection_info(sbi, FAULT_WRITE_IO);
bio->bi_status = BLK_STS_IOERR;
}
bio_for_each_segment_all(bvec, bio, iter_all) {
struct page *page = bvec->bv_page;
enum count_type type = WB_DATA_TYPE(page);
if (page_private_dummy(page)) {
clear_page_private_dummy(page);
unlock_page(page);
mempool_free(page, sbi->write_io_dummy);
if (unlikely(bio->bi_status))
f2fs_stop_checkpoint(sbi, true);
continue;
}
fscrypt_finalize_bounce_page(&page);
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (f2fs_is_compressed_page(page)) {
f2fs_compress_write_end_io(bio, page);
continue;
}
#endif
if (unlikely(bio->bi_status)) {
mapping_set_error(page->mapping, -EIO);
if (type == F2FS_WB_CP_DATA)
f2fs_stop_checkpoint(sbi, true);
}
f2fs_bug_on(sbi, page->mapping == NODE_MAPPING(sbi) &&
page->index != nid_of_node(page));
dec_page_count(sbi, type);
if (f2fs_in_warm_node_list(sbi, page))
f2fs_del_fsync_node_entry(sbi, page);
clear_page_private_gcing(page);
end_page_writeback(page);
}
if (!get_pages(sbi, F2FS_WB_CP_DATA) &&
wq_has_sleeper(&sbi->cp_wait))
wake_up(&sbi->cp_wait);
bio_put(bio);
}
struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
block_t blk_addr, sector_t *sector)
{
struct block_device *bdev = sbi->sb->s_bdev;
int i;
if (f2fs_is_multi_device(sbi)) {
for (i = 0; i < sbi->s_ndevs; i++) {
if (FDEV(i).start_blk <= blk_addr &&
FDEV(i).end_blk >= blk_addr) {
blk_addr -= FDEV(i).start_blk;
bdev = FDEV(i).bdev;
break;
}
}
}
if (sector)
*sector = SECTOR_FROM_BLOCK(blk_addr);
return bdev;
}
int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr)
{
int i;
if (!f2fs_is_multi_device(sbi))
return 0;
for (i = 0; i < sbi->s_ndevs; i++)
if (FDEV(i).start_blk <= blkaddr && FDEV(i).end_blk >= blkaddr)
return i;
return 0;
}
static unsigned int f2fs_io_flags(struct f2fs_io_info *fio)
{
unsigned int temp_mask = (1 << NR_TEMP_TYPE) - 1;
unsigned int fua_flag, meta_flag, io_flag;
unsigned int op_flags = 0;
if (fio->op != REQ_OP_WRITE)
return 0;
if (fio->type == DATA)
io_flag = fio->sbi->data_io_flag;
else if (fio->type == NODE)
io_flag = fio->sbi->node_io_flag;
else
return 0;
fua_flag = io_flag & temp_mask;
meta_flag = (io_flag >> NR_TEMP_TYPE) & temp_mask;
/*
* data/node io flag bits per temp:
* REQ_META | REQ_FUA |
* 5 | 4 | 3 | 2 | 1 | 0 |
* Cold | Warm | Hot | Cold | Warm | Hot |
*/
if ((1 << fio->temp) & meta_flag)
op_flags |= REQ_META;
if ((1 << fio->temp) & fua_flag)
op_flags |= REQ_FUA;
return op_flags;
}
static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages)
{
struct f2fs_sb_info *sbi = fio->sbi;
struct block_device *bdev;
sector_t sector;
struct bio *bio;
bdev = f2fs_target_device(sbi, fio->new_blkaddr, §or);
bio = bio_alloc_bioset(bdev, npages,
fio->op | fio->op_flags | f2fs_io_flags(fio),
GFP_NOIO, &f2fs_bioset);
bio->bi_iter.bi_sector = sector;
if (is_read_io(fio->op)) {
bio->bi_end_io = f2fs_read_end_io;
bio->bi_private = NULL;
} else {
bio->bi_end_io = f2fs_write_end_io;
bio->bi_private = sbi;
}
iostat_alloc_and_bind_ctx(sbi, bio, NULL);
if (fio->io_wbc)
wbc_init_bio(fio->io_wbc, bio);
return bio;
}
static void f2fs_set_bio_crypt_ctx(struct bio *bio, const struct inode *inode,
pgoff_t first_idx,
const struct f2fs_io_info *fio,
gfp_t gfp_mask)
{
/*
* The f2fs garbage collector sets ->encrypted_page when it wants to
* read/write raw data without encryption.
*/
if (!fio || !fio->encrypted_page)
fscrypt_set_bio_crypt_ctx(bio, inode, first_idx, gfp_mask);
}
static bool f2fs_crypt_mergeable_bio(struct bio *bio, const struct inode *inode,
pgoff_t next_idx,
const struct f2fs_io_info *fio)
{
/*
* The f2fs garbage collector sets ->encrypted_page when it wants to
* read/write raw data without encryption.
*/
if (fio && fio->encrypted_page)
return !bio_has_crypt_ctx(bio);
return fscrypt_mergeable_bio(bio, inode, next_idx);
}
static inline void __submit_bio(struct f2fs_sb_info *sbi,
struct bio *bio, enum page_type type)
{
if (!is_read_io(bio_op(bio))) {
unsigned int start;
if (type != DATA && type != NODE)
goto submit_io;
if (f2fs_lfs_mode(sbi) && current->plug)
blk_finish_plug(current->plug);
if (!F2FS_IO_ALIGNED(sbi))
goto submit_io;
start = bio->bi_iter.bi_size >> F2FS_BLKSIZE_BITS;
start %= F2FS_IO_SIZE(sbi);
if (start == 0)
goto submit_io;
/* fill dummy pages */
for (; start < F2FS_IO_SIZE(sbi); start++) {
struct page *page =
mempool_alloc(sbi->write_io_dummy,
GFP_NOIO | __GFP_NOFAIL);
f2fs_bug_on(sbi, !page);
lock_page(page);
zero_user_segment(page, 0, PAGE_SIZE);
set_page_private_dummy(page);
if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE)
f2fs_bug_on(sbi, 1);
}
/*
* In the NODE case, we lose next block address chain. So, we
* need to do checkpoint in f2fs_sync_file.
*/
if (type == NODE)
set_sbi_flag(sbi, SBI_NEED_CP);
}
submit_io:
if (is_read_io(bio_op(bio)))
trace_f2fs_submit_read_bio(sbi->sb, type, bio);
else
trace_f2fs_submit_write_bio(sbi->sb, type, bio);
iostat_update_submit_ctx(bio, type);
submit_bio(bio);
}
void f2fs_submit_bio(struct f2fs_sb_info *sbi,
struct bio *bio, enum page_type type)
{
__submit_bio(sbi, bio, type);
}
static void __submit_merged_bio(struct f2fs_bio_info *io)
{
struct f2fs_io_info *fio = &io->fio;
if (!io->bio)
return;
if (is_read_io(fio->op))
trace_f2fs_prepare_read_bio(io->sbi->sb, fio->type, io->bio);
else
trace_f2fs_prepare_write_bio(io->sbi->sb, fio->type, io->bio);
__submit_bio(io->sbi, io->bio, fio->type);
io->bio = NULL;
}
static bool __has_merged_page(struct bio *bio, struct inode *inode,
struct page *page, nid_t ino)
{
struct bio_vec *bvec;
struct bvec_iter_all iter_all;
if (!bio)
return false;
if (!inode && !page && !ino)
return true;
bio_for_each_segment_all(bvec, bio, iter_all) {
struct page *target = bvec->bv_page;
if (fscrypt_is_bounce_page(target)) {
target = fscrypt_pagecache_page(target);
if (IS_ERR(target))
continue;
}
if (f2fs_is_compressed_page(target)) {
target = f2fs_compress_control_page(target);
if (IS_ERR(target))
continue;
}
if (inode && inode == target->mapping->host)
return true;
if (page && page == target)
return true;
if (ino && ino == ino_of_node(target))
return true;
}
return false;
}
int f2fs_init_write_merge_io(struct f2fs_sb_info *sbi)
{
int i;
for (i = 0; i < NR_PAGE_TYPE; i++) {
int n = (i == META) ? 1 : NR_TEMP_TYPE;
int j;
sbi->write_io[i] = f2fs_kmalloc(sbi,
array_size(n, sizeof(struct f2fs_bio_info)),
GFP_KERNEL);
if (!sbi->write_io[i])
return -ENOMEM;
for (j = HOT; j < n; j++) {
init_f2fs_rwsem(&sbi->write_io[i][j].io_rwsem);
sbi->write_io[i][j].sbi = sbi;
sbi->write_io[i][j].bio = NULL;
spin_lock_init(&sbi->write_io[i][j].io_lock);
INIT_LIST_HEAD(&sbi->write_io[i][j].io_list);
INIT_LIST_HEAD(&sbi->write_io[i][j].bio_list);
init_f2fs_rwsem(&sbi->write_io[i][j].bio_list_lock);
}
}
return 0;
}
static void __f2fs_submit_merged_write(struct f2fs_sb_info *sbi,
enum page_type type, enum temp_type temp)
{
enum page_type btype = PAGE_TYPE_OF_BIO(type);
struct f2fs_bio_info *io = sbi->write_io[btype] + temp;
f2fs_down_write(&io->io_rwsem);
/* change META to META_FLUSH in the checkpoint procedure */
if (type >= META_FLUSH) {
io->fio.type = META_FLUSH;
io->bio->bi_opf |= REQ_META | REQ_PRIO | REQ_SYNC;
if (!test_opt(sbi, NOBARRIER))
io->bio->bi_opf |= REQ_PREFLUSH | REQ_FUA;
}
__submit_merged_bio(io);
f2fs_up_write(&io->io_rwsem);
}
static void __submit_merged_write_cond(struct f2fs_sb_info *sbi,
struct inode *inode, struct page *page,
nid_t ino, enum page_type type, bool force)
{
enum temp_type temp;
bool ret = true;
for (temp = HOT; temp < NR_TEMP_TYPE; temp++) {
if (!force) {
enum page_type btype = PAGE_TYPE_OF_BIO(type);
struct f2fs_bio_info *io = sbi->write_io[btype] + temp;
f2fs_down_read(&io->io_rwsem);
ret = __has_merged_page(io->bio, inode, page, ino);
f2fs_up_read(&io->io_rwsem);
}
if (ret)
__f2fs_submit_merged_write(sbi, type, temp);
/* TODO: use HOT temp only for meta pages now. */
if (type >= META)
break;
}
}
void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type)
{
__submit_merged_write_cond(sbi, NULL, NULL, 0, type, true);
}
void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
struct inode *inode, struct page *page,
nid_t ino, enum page_type type)
{
__submit_merged_write_cond(sbi, inode, page, ino, type, false);
}
void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi)
{
f2fs_submit_merged_write(sbi, DATA);
f2fs_submit_merged_write(sbi, NODE);
f2fs_submit_merged_write(sbi, META);
}
/*
* Fill the locked page with data located in the block address.
* A caller needs to unlock the page on failure.
*/
int f2fs_submit_page_bio(struct f2fs_io_info *fio)
{
struct bio *bio;
struct page *page = fio->encrypted_page ?
fio->encrypted_page : fio->page;
if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
fio->is_por ? META_POR : (__is_meta_io(fio) ?
META_GENERIC : DATA_GENERIC_ENHANCE)))
return -EFSCORRUPTED;
trace_f2fs_submit_page_bio(page, fio);
/* Allocate a new bio */
bio = __bio_alloc(fio, 1);
f2fs_set_bio_crypt_ctx(bio, fio->page->mapping->host,
fio->page->index, fio, GFP_NOIO);
if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
bio_put(bio);
return -EFAULT;
}
if (fio->io_wbc && !is_read_io(fio->op))
wbc_account_cgroup_owner(fio->io_wbc, page, PAGE_SIZE);
inc_page_count(fio->sbi, is_read_io(fio->op) ?
__read_io_type(page): WB_DATA_TYPE(fio->page));
__submit_bio(fio->sbi, bio, fio->type);
return 0;
}
static bool page_is_mergeable(struct f2fs_sb_info *sbi, struct bio *bio,
block_t last_blkaddr, block_t cur_blkaddr)
{
if (unlikely(sbi->max_io_bytes &&
bio->bi_iter.bi_size >= sbi->max_io_bytes))
return false;
if (last_blkaddr + 1 != cur_blkaddr)
return false;
return bio->bi_bdev == f2fs_target_device(sbi, cur_blkaddr, NULL);
}
static bool io_type_is_mergeable(struct f2fs_bio_info *io,
struct f2fs_io_info *fio)
{
if (io->fio.op != fio->op)
return false;
return io->fio.op_flags == fio->op_flags;
}
static bool io_is_mergeable(struct f2fs_sb_info *sbi, struct bio *bio,
struct f2fs_bio_info *io,
struct f2fs_io_info *fio,
block_t last_blkaddr,
block_t cur_blkaddr)
{
if (F2FS_IO_ALIGNED(sbi) && (fio->type == DATA || fio->type == NODE)) {
unsigned int filled_blocks =
F2FS_BYTES_TO_BLK(bio->bi_iter.bi_size);
unsigned int io_size = F2FS_IO_SIZE(sbi);
unsigned int left_vecs = bio->bi_max_vecs - bio->bi_vcnt;
/* IOs in bio is aligned and left space of vectors is not enough */
if (!(filled_blocks % io_size) && left_vecs < io_size)
return false;
}
if (!page_is_mergeable(sbi, bio, last_blkaddr, cur_blkaddr))
return false;
return io_type_is_mergeable(io, fio);
}
static void add_bio_entry(struct f2fs_sb_info *sbi, struct bio *bio,
struct page *page, enum temp_type temp)
{
struct f2fs_bio_info *io = sbi->write_io[DATA] + temp;
struct bio_entry *be;
be = f2fs_kmem_cache_alloc(bio_entry_slab, GFP_NOFS, true, NULL);
be->bio = bio;
bio_get(bio);
if (bio_add_page(bio, page, PAGE_SIZE, 0) != PAGE_SIZE)
f2fs_bug_on(sbi, 1);
f2fs_down_write(&io->bio_list_lock);
list_add_tail(&be->list, &io->bio_list);
f2fs_up_write(&io->bio_list_lock);
}
static void del_bio_entry(struct bio_entry *be)
{
list_del(&be->list);
kmem_cache_free(bio_entry_slab, be);
}
static int add_ipu_page(struct f2fs_io_info *fio, struct bio **bio,
struct page *page)
{
struct f2fs_sb_info *sbi = fio->sbi;
enum temp_type temp;
bool found = false;
int ret = -EAGAIN;
for (temp = HOT; temp < NR_TEMP_TYPE && !found; temp++) {
struct f2fs_bio_info *io = sbi->write_io[DATA] + temp;
struct list_head *head = &io->bio_list;
struct bio_entry *be;
f2fs_down_write(&io->bio_list_lock);
list_for_each_entry(be, head, list) {
if (be->bio != *bio)
continue;
found = true;
f2fs_bug_on(sbi, !page_is_mergeable(sbi, *bio,
*fio->last_block,
fio->new_blkaddr));
if (f2fs_crypt_mergeable_bio(*bio,
fio->page->mapping->host,
fio->page->index, fio) &&
bio_add_page(*bio, page, PAGE_SIZE, 0) ==
PAGE_SIZE) {
ret = 0;
break;
}
/* page can't be merged into bio; submit the bio */
del_bio_entry(be);
__submit_bio(sbi, *bio, DATA);
break;
}
f2fs_up_write(&io->bio_list_lock);
}
if (ret) {
bio_put(*bio);
*bio = NULL;
}
return ret;
}
void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi,
struct bio **bio, struct page *page)
{
enum temp_type temp;
bool found = false;
struct bio *target = bio ? *bio : NULL;
for (temp = HOT; temp < NR_TEMP_TYPE && !found; temp++) {
struct f2fs_bio_info *io = sbi->write_io[DATA] + temp;
struct list_head *head = &io->bio_list;
struct bio_entry *be;
if (list_empty(head))
continue;
f2fs_down_read(&io->bio_list_lock);
list_for_each_entry(be, head, list) {
if (target)
found = (target == be->bio);
else
found = __has_merged_page(be->bio, NULL,
page, 0);
if (found)
break;
}
f2fs_up_read(&io->bio_list_lock);
if (!found)
continue;
found = false;
f2fs_down_write(&io->bio_list_lock);
list_for_each_entry(be, head, list) {
if (target)
found = (target == be->bio);
else
found = __has_merged_page(be->bio, NULL,
page, 0);
if (found) {
target = be->bio;
del_bio_entry(be);
break;
}
}
f2fs_up_write(&io->bio_list_lock);
}
if (found)
__submit_bio(sbi, target, DATA);
if (bio && *bio) {
bio_put(*bio);
*bio = NULL;
}
}
int f2fs_merge_page_bio(struct f2fs_io_info *fio)
{
struct bio *bio = *fio->bio;
struct page *page = fio->encrypted_page ?
fio->encrypted_page : fio->page;
if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
__is_meta_io(fio) ? META_GENERIC : DATA_GENERIC))
return -EFSCORRUPTED;
trace_f2fs_submit_page_bio(page, fio);
if (bio && !page_is_mergeable(fio->sbi, bio, *fio->last_block,
fio->new_blkaddr))
f2fs_submit_merged_ipu_write(fio->sbi, &bio, NULL);
alloc_new:
if (!bio) {
bio = __bio_alloc(fio, BIO_MAX_VECS);
f2fs_set_bio_crypt_ctx(bio, fio->page->mapping->host,
fio->page->index, fio, GFP_NOIO);
add_bio_entry(fio->sbi, bio, page, fio->temp);
} else {
if (add_ipu_page(fio, &bio, page))
goto alloc_new;
}
if (fio->io_wbc)
wbc_account_cgroup_owner(fio->io_wbc, page, PAGE_SIZE);
inc_page_count(fio->sbi, WB_DATA_TYPE(page));
*fio->last_block = fio->new_blkaddr;
*fio->bio = bio;
return 0;
}
void f2fs_submit_page_write(struct f2fs_io_info *fio)
{
struct f2fs_sb_info *sbi = fio->sbi;
enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
struct f2fs_bio_info *io = sbi->write_io[btype] + fio->temp;
struct page *bio_page;
f2fs_bug_on(sbi, is_read_io(fio->op));
f2fs_down_write(&io->io_rwsem);
next:
if (fio->in_list) {
spin_lock(&io->io_lock);
if (list_empty(&io->io_list)) {
spin_unlock(&io->io_lock);
goto out;
}
fio = list_first_entry(&io->io_list,
struct f2fs_io_info, list);
list_del(&fio->list);
spin_unlock(&io->io_lock);
}
verify_fio_blkaddr(fio);
if (fio->encrypted_page)
bio_page = fio->encrypted_page;
else if (fio->compressed_page)
bio_page = fio->compressed_page;
else
bio_page = fio->page;
/* set submitted = true as a return value */
fio->submitted = true;
inc_page_count(sbi, WB_DATA_TYPE(bio_page));
if (io->bio &&
(!io_is_mergeable(sbi, io->bio, io, fio, io->last_block_in_bio,
fio->new_blkaddr) ||
!f2fs_crypt_mergeable_bio(io->bio, fio->page->mapping->host,
bio_page->index, fio)))
__submit_merged_bio(io);
alloc_new:
if (io->bio == NULL) {
if (F2FS_IO_ALIGNED(sbi) &&
(fio->type == DATA || fio->type == NODE) &&
fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) {
dec_page_count(sbi, WB_DATA_TYPE(bio_page));
fio->retry = true;
goto skip;
}
io->bio = __bio_alloc(fio, BIO_MAX_VECS);
f2fs_set_bio_crypt_ctx(io->bio, fio->page->mapping->host,
bio_page->index, fio, GFP_NOIO);
io->fio = *fio;
}
if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) < PAGE_SIZE) {
__submit_merged_bio(io);
goto alloc_new;
}
if (fio->io_wbc)
wbc_account_cgroup_owner(fio->io_wbc, bio_page, PAGE_SIZE);
io->last_block_in_bio = fio->new_blkaddr;
trace_f2fs_submit_page_write(fio->page, fio);
skip:
if (fio->in_list)
goto next;
out:
if (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) ||
!f2fs_is_checkpoint_ready(sbi))
__submit_merged_bio(io);
f2fs_up_write(&io->io_rwsem);
}