forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathnode.c
3432 lines (2885 loc) · 81.5 KB
/
node.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/node.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/mpage.h>
#include <linux/sched/mm.h>
#include <linux/blkdev.h>
#include <linux/pagevec.h>
#include <linux/swap.h>
#include "f2fs.h"
#include "node.h"
#include "segment.h"
#include "xattr.h"
#include "iostat.h"
#include <trace/events/f2fs.h>
#define on_f2fs_build_free_nids(nmi) mutex_is_locked(&(nm_i)->build_lock)
static struct kmem_cache *nat_entry_slab;
static struct kmem_cache *free_nid_slab;
static struct kmem_cache *nat_entry_set_slab;
static struct kmem_cache *fsync_node_entry_slab;
/*
* Check whether the given nid is within node id range.
*/
int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid)
{
if (unlikely(nid < F2FS_ROOT_INO(sbi) || nid >= NM_I(sbi)->max_nid)) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_warn(sbi, "%s: out-of-range nid=%x, run fsck to fix.",
__func__, nid);
f2fs_handle_error(sbi, ERROR_CORRUPTED_INODE);
return -EFSCORRUPTED;
}
return 0;
}
bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct sysinfo val;
unsigned long avail_ram;
unsigned long mem_size = 0;
bool res = false;
if (!nm_i)
return true;
si_meminfo(&val);
/* only uses low memory */
avail_ram = val.totalram - val.totalhigh;
/*
* give 25%, 25%, 50%, 50%, 50% memory for each components respectively
*/
if (type == FREE_NIDS) {
mem_size = (nm_i->nid_cnt[FREE_NID] *
sizeof(struct free_nid)) >> PAGE_SHIFT;
res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
} else if (type == NAT_ENTRIES) {
mem_size = (nm_i->nat_cnt[TOTAL_NAT] *
sizeof(struct nat_entry)) >> PAGE_SHIFT;
res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
if (excess_cached_nats(sbi))
res = false;
} else if (type == DIRTY_DENTS) {
if (sbi->sb->s_bdi->wb.dirty_exceeded)
return false;
mem_size = get_pages(sbi, F2FS_DIRTY_DENTS);
res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
} else if (type == INO_ENTRIES) {
int i;
for (i = 0; i < MAX_INO_ENTRY; i++)
mem_size += sbi->im[i].ino_num *
sizeof(struct ino_entry);
mem_size >>= PAGE_SHIFT;
res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
} else if (type == EXTENT_CACHE) {
mem_size = (atomic_read(&sbi->total_ext_tree) *
sizeof(struct extent_tree) +
atomic_read(&sbi->total_ext_node) *
sizeof(struct extent_node)) >> PAGE_SHIFT;
res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
} else if (type == DISCARD_CACHE) {
mem_size = (atomic_read(&dcc->discard_cmd_cnt) *
sizeof(struct discard_cmd)) >> PAGE_SHIFT;
res = mem_size < (avail_ram * nm_i->ram_thresh / 100);
} else if (type == COMPRESS_PAGE) {
#ifdef CONFIG_F2FS_FS_COMPRESSION
unsigned long free_ram = val.freeram;
/*
* free memory is lower than watermark or cached page count
* exceed threshold, deny caching compress page.
*/
res = (free_ram > avail_ram * sbi->compress_watermark / 100) &&
(COMPRESS_MAPPING(sbi)->nrpages <
free_ram * sbi->compress_percent / 100);
#else
res = false;
#endif
} else {
if (!sbi->sb->s_bdi->wb.dirty_exceeded)
return true;
}
return res;
}
static void clear_node_page_dirty(struct page *page)
{
if (PageDirty(page)) {
f2fs_clear_page_cache_dirty_tag(page);
clear_page_dirty_for_io(page);
dec_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES);
}
ClearPageUptodate(page);
}
static struct page *get_current_nat_page(struct f2fs_sb_info *sbi, nid_t nid)
{
return f2fs_get_meta_page_retry(sbi, current_nat_addr(sbi, nid));
}
static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid)
{
struct page *src_page;
struct page *dst_page;
pgoff_t dst_off;
void *src_addr;
void *dst_addr;
struct f2fs_nm_info *nm_i = NM_I(sbi);
dst_off = next_nat_addr(sbi, current_nat_addr(sbi, nid));
/* get current nat block page with lock */
src_page = get_current_nat_page(sbi, nid);
if (IS_ERR(src_page))
return src_page;
dst_page = f2fs_grab_meta_page(sbi, dst_off);
f2fs_bug_on(sbi, PageDirty(src_page));
src_addr = page_address(src_page);
dst_addr = page_address(dst_page);
memcpy(dst_addr, src_addr, PAGE_SIZE);
set_page_dirty(dst_page);
f2fs_put_page(src_page, 1);
set_to_next_nat(nm_i, nid);
return dst_page;
}
static struct nat_entry *__alloc_nat_entry(struct f2fs_sb_info *sbi,
nid_t nid, bool no_fail)
{
struct nat_entry *new;
new = f2fs_kmem_cache_alloc(nat_entry_slab,
GFP_F2FS_ZERO, no_fail, sbi);
if (new) {
nat_set_nid(new, nid);
nat_reset_flag(new);
}
return new;
}
static void __free_nat_entry(struct nat_entry *e)
{
kmem_cache_free(nat_entry_slab, e);
}
/* must be locked by nat_tree_lock */
static struct nat_entry *__init_nat_entry(struct f2fs_nm_info *nm_i,
struct nat_entry *ne, struct f2fs_nat_entry *raw_ne, bool no_fail)
{
if (no_fail)
f2fs_radix_tree_insert(&nm_i->nat_root, nat_get_nid(ne), ne);
else if (radix_tree_insert(&nm_i->nat_root, nat_get_nid(ne), ne))
return NULL;
if (raw_ne)
node_info_from_raw_nat(&ne->ni, raw_ne);
spin_lock(&nm_i->nat_list_lock);
list_add_tail(&ne->list, &nm_i->nat_entries);
spin_unlock(&nm_i->nat_list_lock);
nm_i->nat_cnt[TOTAL_NAT]++;
nm_i->nat_cnt[RECLAIMABLE_NAT]++;
return ne;
}
static struct nat_entry *__lookup_nat_cache(struct f2fs_nm_info *nm_i, nid_t n)
{
struct nat_entry *ne;
ne = radix_tree_lookup(&nm_i->nat_root, n);
/* for recent accessed nat entry, move it to tail of lru list */
if (ne && !get_nat_flag(ne, IS_DIRTY)) {
spin_lock(&nm_i->nat_list_lock);
if (!list_empty(&ne->list))
list_move_tail(&ne->list, &nm_i->nat_entries);
spin_unlock(&nm_i->nat_list_lock);
}
return ne;
}
static unsigned int __gang_lookup_nat_cache(struct f2fs_nm_info *nm_i,
nid_t start, unsigned int nr, struct nat_entry **ep)
{
return radix_tree_gang_lookup(&nm_i->nat_root, (void **)ep, start, nr);
}
static void __del_from_nat_cache(struct f2fs_nm_info *nm_i, struct nat_entry *e)
{
radix_tree_delete(&nm_i->nat_root, nat_get_nid(e));
nm_i->nat_cnt[TOTAL_NAT]--;
nm_i->nat_cnt[RECLAIMABLE_NAT]--;
__free_nat_entry(e);
}
static struct nat_entry_set *__grab_nat_entry_set(struct f2fs_nm_info *nm_i,
struct nat_entry *ne)
{
nid_t set = NAT_BLOCK_OFFSET(ne->ni.nid);
struct nat_entry_set *head;
head = radix_tree_lookup(&nm_i->nat_set_root, set);
if (!head) {
head = f2fs_kmem_cache_alloc(nat_entry_set_slab,
GFP_NOFS, true, NULL);
INIT_LIST_HEAD(&head->entry_list);
INIT_LIST_HEAD(&head->set_list);
head->set = set;
head->entry_cnt = 0;
f2fs_radix_tree_insert(&nm_i->nat_set_root, set, head);
}
return head;
}
static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i,
struct nat_entry *ne)
{
struct nat_entry_set *head;
bool new_ne = nat_get_blkaddr(ne) == NEW_ADDR;
if (!new_ne)
head = __grab_nat_entry_set(nm_i, ne);
/*
* update entry_cnt in below condition:
* 1. update NEW_ADDR to valid block address;
* 2. update old block address to new one;
*/
if (!new_ne && (get_nat_flag(ne, IS_PREALLOC) ||
!get_nat_flag(ne, IS_DIRTY)))
head->entry_cnt++;
set_nat_flag(ne, IS_PREALLOC, new_ne);
if (get_nat_flag(ne, IS_DIRTY))
goto refresh_list;
nm_i->nat_cnt[DIRTY_NAT]++;
nm_i->nat_cnt[RECLAIMABLE_NAT]--;
set_nat_flag(ne, IS_DIRTY, true);
refresh_list:
spin_lock(&nm_i->nat_list_lock);
if (new_ne)
list_del_init(&ne->list);
else
list_move_tail(&ne->list, &head->entry_list);
spin_unlock(&nm_i->nat_list_lock);
}
static void __clear_nat_cache_dirty(struct f2fs_nm_info *nm_i,
struct nat_entry_set *set, struct nat_entry *ne)
{
spin_lock(&nm_i->nat_list_lock);
list_move_tail(&ne->list, &nm_i->nat_entries);
spin_unlock(&nm_i->nat_list_lock);
set_nat_flag(ne, IS_DIRTY, false);
set->entry_cnt--;
nm_i->nat_cnt[DIRTY_NAT]--;
nm_i->nat_cnt[RECLAIMABLE_NAT]++;
}
static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i,
nid_t start, unsigned int nr, struct nat_entry_set **ep)
{
return radix_tree_gang_lookup(&nm_i->nat_set_root, (void **)ep,
start, nr);
}
bool f2fs_in_warm_node_list(struct f2fs_sb_info *sbi, struct page *page)
{
return NODE_MAPPING(sbi) == page->mapping &&
IS_DNODE(page) && is_cold_node(page);
}
void f2fs_init_fsync_node_info(struct f2fs_sb_info *sbi)
{
spin_lock_init(&sbi->fsync_node_lock);
INIT_LIST_HEAD(&sbi->fsync_node_list);
sbi->fsync_seg_id = 0;
sbi->fsync_node_num = 0;
}
static unsigned int f2fs_add_fsync_node_entry(struct f2fs_sb_info *sbi,
struct page *page)
{
struct fsync_node_entry *fn;
unsigned long flags;
unsigned int seq_id;
fn = f2fs_kmem_cache_alloc(fsync_node_entry_slab,
GFP_NOFS, true, NULL);
get_page(page);
fn->page = page;
INIT_LIST_HEAD(&fn->list);
spin_lock_irqsave(&sbi->fsync_node_lock, flags);
list_add_tail(&fn->list, &sbi->fsync_node_list);
fn->seq_id = sbi->fsync_seg_id++;
seq_id = fn->seq_id;
sbi->fsync_node_num++;
spin_unlock_irqrestore(&sbi->fsync_node_lock, flags);
return seq_id;
}
void f2fs_del_fsync_node_entry(struct f2fs_sb_info *sbi, struct page *page)
{
struct fsync_node_entry *fn;
unsigned long flags;
spin_lock_irqsave(&sbi->fsync_node_lock, flags);
list_for_each_entry(fn, &sbi->fsync_node_list, list) {
if (fn->page == page) {
list_del(&fn->list);
sbi->fsync_node_num--;
spin_unlock_irqrestore(&sbi->fsync_node_lock, flags);
kmem_cache_free(fsync_node_entry_slab, fn);
put_page(page);
return;
}
}
spin_unlock_irqrestore(&sbi->fsync_node_lock, flags);
f2fs_bug_on(sbi, 1);
}
void f2fs_reset_fsync_node_info(struct f2fs_sb_info *sbi)
{
unsigned long flags;
spin_lock_irqsave(&sbi->fsync_node_lock, flags);
sbi->fsync_seg_id = 0;
spin_unlock_irqrestore(&sbi->fsync_node_lock, flags);
}
int f2fs_need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
bool need = false;
f2fs_down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
if (e) {
if (!get_nat_flag(e, IS_CHECKPOINTED) &&
!get_nat_flag(e, HAS_FSYNCED_INODE))
need = true;
}
f2fs_up_read(&nm_i->nat_tree_lock);
return need;
}
bool f2fs_is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
bool is_cp = true;
f2fs_down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
if (e && !get_nat_flag(e, IS_CHECKPOINTED))
is_cp = false;
f2fs_up_read(&nm_i->nat_tree_lock);
return is_cp;
}
bool f2fs_need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
bool need_update = true;
f2fs_down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, ino);
if (e && get_nat_flag(e, HAS_LAST_FSYNC) &&
(get_nat_flag(e, IS_CHECKPOINTED) ||
get_nat_flag(e, HAS_FSYNCED_INODE)))
need_update = false;
f2fs_up_read(&nm_i->nat_tree_lock);
return need_update;
}
/* must be locked by nat_tree_lock */
static void cache_nat_entry(struct f2fs_sb_info *sbi, nid_t nid,
struct f2fs_nat_entry *ne)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *new, *e;
/* Let's mitigate lock contention of nat_tree_lock during checkpoint */
if (f2fs_rwsem_is_locked(&sbi->cp_global_sem))
return;
new = __alloc_nat_entry(sbi, nid, false);
if (!new)
return;
f2fs_down_write(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
if (!e)
e = __init_nat_entry(nm_i, new, ne, false);
else
f2fs_bug_on(sbi, nat_get_ino(e) != le32_to_cpu(ne->ino) ||
nat_get_blkaddr(e) !=
le32_to_cpu(ne->block_addr) ||
nat_get_version(e) != ne->version);
f2fs_up_write(&nm_i->nat_tree_lock);
if (e != new)
__free_nat_entry(new);
}
static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
block_t new_blkaddr, bool fsync_done)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
struct nat_entry *new = __alloc_nat_entry(sbi, ni->nid, true);
f2fs_down_write(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, ni->nid);
if (!e) {
e = __init_nat_entry(nm_i, new, NULL, true);
copy_node_info(&e->ni, ni);
f2fs_bug_on(sbi, ni->blk_addr == NEW_ADDR);
} else if (new_blkaddr == NEW_ADDR) {
/*
* when nid is reallocated,
* previous nat entry can be remained in nat cache.
* So, reinitialize it with new information.
*/
copy_node_info(&e->ni, ni);
f2fs_bug_on(sbi, ni->blk_addr != NULL_ADDR);
}
/* let's free early to reduce memory consumption */
if (e != new)
__free_nat_entry(new);
/* sanity check */
f2fs_bug_on(sbi, nat_get_blkaddr(e) != ni->blk_addr);
f2fs_bug_on(sbi, nat_get_blkaddr(e) == NULL_ADDR &&
new_blkaddr == NULL_ADDR);
f2fs_bug_on(sbi, nat_get_blkaddr(e) == NEW_ADDR &&
new_blkaddr == NEW_ADDR);
f2fs_bug_on(sbi, __is_valid_data_blkaddr(nat_get_blkaddr(e)) &&
new_blkaddr == NEW_ADDR);
/* increment version no as node is removed */
if (nat_get_blkaddr(e) != NEW_ADDR && new_blkaddr == NULL_ADDR) {
unsigned char version = nat_get_version(e);
nat_set_version(e, inc_node_version(version));
}
/* change address */
nat_set_blkaddr(e, new_blkaddr);
if (!__is_valid_data_blkaddr(new_blkaddr))
set_nat_flag(e, IS_CHECKPOINTED, false);
__set_nat_cache_dirty(nm_i, e);
/* update fsync_mark if its inode nat entry is still alive */
if (ni->nid != ni->ino)
e = __lookup_nat_cache(nm_i, ni->ino);
if (e) {
if (fsync_done && ni->nid == ni->ino)
set_nat_flag(e, HAS_FSYNCED_INODE, true);
set_nat_flag(e, HAS_LAST_FSYNC, fsync_done);
}
f2fs_up_write(&nm_i->nat_tree_lock);
}
int f2fs_try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
int nr = nr_shrink;
if (!f2fs_down_write_trylock(&nm_i->nat_tree_lock))
return 0;
spin_lock(&nm_i->nat_list_lock);
while (nr_shrink) {
struct nat_entry *ne;
if (list_empty(&nm_i->nat_entries))
break;
ne = list_first_entry(&nm_i->nat_entries,
struct nat_entry, list);
list_del(&ne->list);
spin_unlock(&nm_i->nat_list_lock);
__del_from_nat_cache(nm_i, ne);
nr_shrink--;
spin_lock(&nm_i->nat_list_lock);
}
spin_unlock(&nm_i->nat_list_lock);
f2fs_up_write(&nm_i->nat_tree_lock);
return nr - nr_shrink;
}
int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
struct node_info *ni, bool checkpoint_context)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
struct f2fs_journal *journal = curseg->journal;
nid_t start_nid = START_NID(nid);
struct f2fs_nat_block *nat_blk;
struct page *page = NULL;
struct f2fs_nat_entry ne;
struct nat_entry *e;
pgoff_t index;
block_t blkaddr;
int i;
ni->nid = nid;
retry:
/* Check nat cache */
f2fs_down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
if (e) {
ni->ino = nat_get_ino(e);
ni->blk_addr = nat_get_blkaddr(e);
ni->version = nat_get_version(e);
f2fs_up_read(&nm_i->nat_tree_lock);
return 0;
}
/*
* Check current segment summary by trying to grab journal_rwsem first.
* This sem is on the critical path on the checkpoint requiring the above
* nat_tree_lock. Therefore, we should retry, if we failed to grab here
* while not bothering checkpoint.
*/
if (!f2fs_rwsem_is_locked(&sbi->cp_global_sem) || checkpoint_context) {
down_read(&curseg->journal_rwsem);
} else if (f2fs_rwsem_is_contended(&nm_i->nat_tree_lock) ||
!down_read_trylock(&curseg->journal_rwsem)) {
f2fs_up_read(&nm_i->nat_tree_lock);
goto retry;
}
i = f2fs_lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 0);
if (i >= 0) {
ne = nat_in_journal(journal, i);
node_info_from_raw_nat(ni, &ne);
}
up_read(&curseg->journal_rwsem);
if (i >= 0) {
f2fs_up_read(&nm_i->nat_tree_lock);
goto cache;
}
/* Fill node_info from nat page */
index = current_nat_addr(sbi, nid);
f2fs_up_read(&nm_i->nat_tree_lock);
page = f2fs_get_meta_page(sbi, index);
if (IS_ERR(page))
return PTR_ERR(page);
nat_blk = (struct f2fs_nat_block *)page_address(page);
ne = nat_blk->entries[nid - start_nid];
node_info_from_raw_nat(ni, &ne);
f2fs_put_page(page, 1);
cache:
blkaddr = le32_to_cpu(ne.block_addr);
if (__is_valid_data_blkaddr(blkaddr) &&
!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE))
return -EFAULT;
/* cache nat entry */
cache_nat_entry(sbi, nid, &ne);
return 0;
}
/*
* readahead MAX_RA_NODE number of node pages.
*/
static void f2fs_ra_node_pages(struct page *parent, int start, int n)
{
struct f2fs_sb_info *sbi = F2FS_P_SB(parent);
struct blk_plug plug;
int i, end;
nid_t nid;
blk_start_plug(&plug);
/* Then, try readahead for siblings of the desired node */
end = start + n;
end = min(end, NIDS_PER_BLOCK);
for (i = start; i < end; i++) {
nid = get_nid(parent, i, false);
f2fs_ra_node_page(sbi, nid);
}
blk_finish_plug(&plug);
}
pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs)
{
const long direct_index = ADDRS_PER_INODE(dn->inode);
const long direct_blks = ADDRS_PER_BLOCK(dn->inode);
const long indirect_blks = ADDRS_PER_BLOCK(dn->inode) * NIDS_PER_BLOCK;
unsigned int skipped_unit = ADDRS_PER_BLOCK(dn->inode);
int cur_level = dn->cur_level;
int max_level = dn->max_level;
pgoff_t base = 0;
if (!dn->max_level)
return pgofs + 1;
while (max_level-- > cur_level)
skipped_unit *= NIDS_PER_BLOCK;
switch (dn->max_level) {
case 3:
base += 2 * indirect_blks;
fallthrough;
case 2:
base += 2 * direct_blks;
fallthrough;
case 1:
base += direct_index;
break;
default:
f2fs_bug_on(F2FS_I_SB(dn->inode), 1);
}
return ((pgofs - base) / skipped_unit + 1) * skipped_unit + base;
}
/*
* The maximum depth is four.
* Offset[0] will have raw inode offset.
*/
static int get_node_path(struct inode *inode, long block,
int offset[4], unsigned int noffset[4])
{
const long direct_index = ADDRS_PER_INODE(inode);
const long direct_blks = ADDRS_PER_BLOCK(inode);
const long dptrs_per_blk = NIDS_PER_BLOCK;
const long indirect_blks = ADDRS_PER_BLOCK(inode) * NIDS_PER_BLOCK;
const long dindirect_blks = indirect_blks * NIDS_PER_BLOCK;
int n = 0;
int level = 0;
noffset[0] = 0;
if (block < direct_index) {
offset[n] = block;
goto got;
}
block -= direct_index;
if (block < direct_blks) {
offset[n++] = NODE_DIR1_BLOCK;
noffset[n] = 1;
offset[n] = block;
level = 1;
goto got;
}
block -= direct_blks;
if (block < direct_blks) {
offset[n++] = NODE_DIR2_BLOCK;
noffset[n] = 2;
offset[n] = block;
level = 1;
goto got;
}
block -= direct_blks;
if (block < indirect_blks) {
offset[n++] = NODE_IND1_BLOCK;
noffset[n] = 3;
offset[n++] = block / direct_blks;
noffset[n] = 4 + offset[n - 1];
offset[n] = block % direct_blks;
level = 2;
goto got;
}
block -= indirect_blks;
if (block < indirect_blks) {
offset[n++] = NODE_IND2_BLOCK;
noffset[n] = 4 + dptrs_per_blk;
offset[n++] = block / direct_blks;
noffset[n] = 5 + dptrs_per_blk + offset[n - 1];
offset[n] = block % direct_blks;
level = 2;
goto got;
}
block -= indirect_blks;
if (block < dindirect_blks) {
offset[n++] = NODE_DIND_BLOCK;
noffset[n] = 5 + (dptrs_per_blk * 2);
offset[n++] = block / indirect_blks;
noffset[n] = 6 + (dptrs_per_blk * 2) +
offset[n - 1] * (dptrs_per_blk + 1);
offset[n++] = (block / direct_blks) % dptrs_per_blk;
noffset[n] = 7 + (dptrs_per_blk * 2) +
offset[n - 2] * (dptrs_per_blk + 1) +
offset[n - 1];
offset[n] = block % direct_blks;
level = 3;
goto got;
} else {
return -E2BIG;
}
got:
return level;
}
/*
* Caller should call f2fs_put_dnode(dn).
* Also, it should grab and release a rwsem by calling f2fs_lock_op() and
* f2fs_unlock_op() only if mode is set with ALLOC_NODE.
*/
int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct page *npage[4];
struct page *parent = NULL;
int offset[4];
unsigned int noffset[4];
nid_t nids[4];
int level, i = 0;
int err = 0;
level = get_node_path(dn->inode, index, offset, noffset);
if (level < 0)
return level;
nids[0] = dn->inode->i_ino;
npage[0] = dn->inode_page;
if (!npage[0]) {
npage[0] = f2fs_get_node_page(sbi, nids[0]);
if (IS_ERR(npage[0]))
return PTR_ERR(npage[0]);
}
/* if inline_data is set, should not report any block indices */
if (f2fs_has_inline_data(dn->inode) && index) {
err = -ENOENT;
f2fs_put_page(npage[0], 1);
goto release_out;
}
parent = npage[0];
if (level != 0)
nids[1] = get_nid(parent, offset[0], true);
dn->inode_page = npage[0];
dn->inode_page_locked = true;
/* get indirect or direct nodes */
for (i = 1; i <= level; i++) {
bool done = false;
if (!nids[i] && mode == ALLOC_NODE) {
/* alloc new node */
if (!f2fs_alloc_nid(sbi, &(nids[i]))) {
err = -ENOSPC;
goto release_pages;
}
dn->nid = nids[i];
npage[i] = f2fs_new_node_page(dn, noffset[i]);
if (IS_ERR(npage[i])) {
f2fs_alloc_nid_failed(sbi, nids[i]);
err = PTR_ERR(npage[i]);
goto release_pages;
}
set_nid(parent, offset[i - 1], nids[i], i == 1);
f2fs_alloc_nid_done(sbi, nids[i]);
done = true;
} else if (mode == LOOKUP_NODE_RA && i == level && level > 1) {
npage[i] = f2fs_get_node_page_ra(parent, offset[i - 1]);
if (IS_ERR(npage[i])) {
err = PTR_ERR(npage[i]);
goto release_pages;
}
done = true;
}
if (i == 1) {
dn->inode_page_locked = false;
unlock_page(parent);
} else {
f2fs_put_page(parent, 1);
}
if (!done) {
npage[i] = f2fs_get_node_page(sbi, nids[i]);
if (IS_ERR(npage[i])) {
err = PTR_ERR(npage[i]);
f2fs_put_page(npage[0], 0);
goto release_out;
}
}
if (i < level) {
parent = npage[i];
nids[i + 1] = get_nid(parent, offset[i], false);
}
}
dn->nid = nids[level];
dn->ofs_in_node = offset[level];
dn->node_page = npage[level];
dn->data_blkaddr = f2fs_data_blkaddr(dn);
if (is_inode_flag_set(dn->inode, FI_COMPRESSED_FILE) &&
f2fs_sb_has_readonly(sbi)) {
unsigned int c_len = f2fs_cluster_blocks_are_contiguous(dn);
block_t blkaddr;
if (!c_len)
goto out;
blkaddr = f2fs_data_blkaddr(dn);
if (blkaddr == COMPRESS_ADDR)
blkaddr = data_blkaddr(dn->inode, dn->node_page,
dn->ofs_in_node + 1);
f2fs_update_extent_tree_range_compressed(dn->inode,
index, blkaddr,
F2FS_I(dn->inode)->i_cluster_size,
c_len);
}
out:
return 0;
release_pages:
f2fs_put_page(parent, 1);
if (i > 1)
f2fs_put_page(npage[0], 0);
release_out:
dn->inode_page = NULL;
dn->node_page = NULL;
if (err == -ENOENT) {
dn->cur_level = i;
dn->max_level = level;
dn->ofs_in_node = offset[level];
}
return err;
}
static int truncate_node(struct dnode_of_data *dn)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct node_info ni;
int err;
pgoff_t index;
err = f2fs_get_node_info(sbi, dn->nid, &ni, false);
if (err)
return err;
/* Deallocate node address */
f2fs_invalidate_blocks(sbi, ni.blk_addr);
dec_valid_node_count(sbi, dn->inode, dn->nid == dn->inode->i_ino);
set_node_addr(sbi, &ni, NULL_ADDR, false);
if (dn->nid == dn->inode->i_ino) {
f2fs_remove_orphan_inode(sbi, dn->nid);
dec_valid_inode_count(sbi);
f2fs_inode_synced(dn->inode);
}
clear_node_page_dirty(dn->node_page);
set_sbi_flag(sbi, SBI_IS_DIRTY);
index = dn->node_page->index;
f2fs_put_page(dn->node_page, 1);
invalidate_mapping_pages(NODE_MAPPING(sbi),
index, index);
dn->node_page = NULL;
trace_f2fs_truncate_node(dn->inode, dn->nid, ni.blk_addr);
return 0;
}
static int truncate_dnode(struct dnode_of_data *dn)
{
struct page *page;
int err;
if (dn->nid == 0)
return 1;
/* get direct node */
page = f2fs_get_node_page(F2FS_I_SB(dn->inode), dn->nid);
if (PTR_ERR(page) == -ENOENT)
return 1;
else if (IS_ERR(page))
return PTR_ERR(page);
/* Make dnode_of_data for parameter */
dn->node_page = page;
dn->ofs_in_node = 0;
f2fs_truncate_data_blocks(dn);
err = truncate_node(dn);
if (err)
return err;
return 1;
}
static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs,
int ofs, int depth)
{
struct dnode_of_data rdn = *dn;
struct page *page;
struct f2fs_node *rn;
nid_t child_nid;
unsigned int child_nofs;
int freed = 0;
int i, ret;
if (dn->nid == 0)
return NIDS_PER_BLOCK + 1;
trace_f2fs_truncate_nodes_enter(dn->inode, dn->nid, dn->data_blkaddr);
page = f2fs_get_node_page(F2FS_I_SB(dn->inode), dn->nid);
if (IS_ERR(page)) {
trace_f2fs_truncate_nodes_exit(dn->inode, PTR_ERR(page));
return PTR_ERR(page);
}
f2fs_ra_node_pages(page, ofs, NIDS_PER_BLOCK);
rn = F2FS_NODE(page);
if (depth < 3) {
for (i = ofs; i < NIDS_PER_BLOCK; i++, freed++) {
child_nid = le32_to_cpu(rn->in.nid[i]);
if (child_nid == 0)
continue;
rdn.nid = child_nid;
ret = truncate_dnode(&rdn);
if (ret < 0)
goto out_err;
if (set_nid(page, i, 0, false))
dn->node_changed = true;
}
} else {
child_nofs = nofs + ofs * (NIDS_PER_BLOCK + 1) + 1;
for (i = ofs; i < NIDS_PER_BLOCK; i++) {
child_nid = le32_to_cpu(rn->in.nid[i]);
if (child_nid == 0) {
child_nofs += NIDS_PER_BLOCK + 1;
continue;
}
rdn.nid = child_nid;
ret = truncate_nodes(&rdn, child_nofs, 0, depth - 1);
if (ret == (NIDS_PER_BLOCK + 1)) {
if (set_nid(page, i, 0, false))
dn->node_changed = true;
child_nofs += ret;
} else if (ret < 0 && ret != -ENOENT) {
goto out_err;