forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
zdata.c
1894 lines (1589 loc) · 48.4 KB
/
zdata.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-only
/*
* Copyright (C) 2018 HUAWEI, Inc.
* https://www.huawei.com/
* Copyright (C) 2022 Alibaba Cloud
*/
#include "compress.h"
#include <linux/psi.h>
#include <linux/cpuhotplug.h>
#include <trace/events/erofs.h>
#define Z_EROFS_PCLUSTER_MAX_PAGES (Z_EROFS_PCLUSTER_MAX_SIZE / PAGE_SIZE)
#define Z_EROFS_INLINE_BVECS 2
/*
* let's leave a type here in case of introducing
* another tagged pointer later.
*/
typedef void *z_erofs_next_pcluster_t;
struct z_erofs_bvec {
struct page *page;
int offset;
unsigned int end;
};
#define __Z_EROFS_BVSET(name, total) \
struct name { \
/* point to the next page which contains the following bvecs */ \
struct page *nextpage; \
struct z_erofs_bvec bvec[total]; \
}
__Z_EROFS_BVSET(z_erofs_bvset,);
__Z_EROFS_BVSET(z_erofs_bvset_inline, Z_EROFS_INLINE_BVECS);
/*
* Structure fields follow one of the following exclusion rules.
*
* I: Modifiable by initialization/destruction paths and read-only
* for everyone else;
*
* L: Field should be protected by the pcluster lock;
*
* A: Field should be accessed / updated in atomic for parallelized code.
*/
struct z_erofs_pcluster {
struct erofs_workgroup obj;
struct mutex lock;
/* A: point to next chained pcluster or TAILs */
z_erofs_next_pcluster_t next;
/* L: the maximum decompression size of this round */
unsigned int length;
/* L: total number of bvecs */
unsigned int vcnt;
/* I: page offset of start position of decompression */
unsigned short pageofs_out;
/* I: page offset of inline compressed data */
unsigned short pageofs_in;
union {
/* L: inline a certain number of bvec for bootstrap */
struct z_erofs_bvset_inline bvset;
/* I: can be used to free the pcluster by RCU. */
struct rcu_head rcu;
};
union {
/* I: physical cluster size in pages */
unsigned short pclusterpages;
/* I: tailpacking inline compressed size */
unsigned short tailpacking_size;
};
/* I: compression algorithm format */
unsigned char algorithmformat;
/* L: whether partial decompression or not */
bool partial;
/* L: indicate several pageofs_outs or not */
bool multibases;
/* A: compressed bvecs (can be cached or inplaced pages) */
struct z_erofs_bvec compressed_bvecs[];
};
/* the end of a chain of pclusters */
#define Z_EROFS_PCLUSTER_TAIL ((void *) 0x700 + POISON_POINTER_DELTA)
#define Z_EROFS_PCLUSTER_NIL (NULL)
struct z_erofs_decompressqueue {
struct super_block *sb;
atomic_t pending_bios;
z_erofs_next_pcluster_t head;
union {
struct completion done;
struct work_struct work;
struct kthread_work kthread_work;
} u;
bool eio, sync;
};
static inline bool z_erofs_is_inline_pcluster(struct z_erofs_pcluster *pcl)
{
return !pcl->obj.index;
}
static inline unsigned int z_erofs_pclusterpages(struct z_erofs_pcluster *pcl)
{
if (z_erofs_is_inline_pcluster(pcl))
return 1;
return pcl->pclusterpages;
}
/*
* bit 30: I/O error occurred on this page
* bit 0 - 29: remaining parts to complete this page
*/
#define Z_EROFS_PAGE_EIO (1 << 30)
static inline void z_erofs_onlinepage_init(struct page *page)
{
union {
atomic_t o;
unsigned long v;
} u = { .o = ATOMIC_INIT(1) };
set_page_private(page, u.v);
smp_wmb();
SetPagePrivate(page);
}
static inline void z_erofs_onlinepage_split(struct page *page)
{
atomic_inc((atomic_t *)&page->private);
}
static void z_erofs_onlinepage_endio(struct page *page, int err)
{
int orig, v;
DBG_BUGON(!PagePrivate(page));
do {
orig = atomic_read((atomic_t *)&page->private);
v = (orig - 1) | (err ? Z_EROFS_PAGE_EIO : 0);
} while (atomic_cmpxchg((atomic_t *)&page->private, orig, v) != orig);
if (!(v & ~Z_EROFS_PAGE_EIO)) {
set_page_private(page, 0);
ClearPagePrivate(page);
if (!(v & Z_EROFS_PAGE_EIO))
SetPageUptodate(page);
unlock_page(page);
}
}
#define Z_EROFS_ONSTACK_PAGES 32
/*
* since pclustersize is variable for big pcluster feature, introduce slab
* pools implementation for different pcluster sizes.
*/
struct z_erofs_pcluster_slab {
struct kmem_cache *slab;
unsigned int maxpages;
char name[48];
};
#define _PCLP(n) { .maxpages = n }
static struct z_erofs_pcluster_slab pcluster_pool[] __read_mostly = {
_PCLP(1), _PCLP(4), _PCLP(16), _PCLP(64), _PCLP(128),
_PCLP(Z_EROFS_PCLUSTER_MAX_PAGES)
};
struct z_erofs_bvec_iter {
struct page *bvpage;
struct z_erofs_bvset *bvset;
unsigned int nr, cur;
};
static struct page *z_erofs_bvec_iter_end(struct z_erofs_bvec_iter *iter)
{
if (iter->bvpage)
kunmap_local(iter->bvset);
return iter->bvpage;
}
static struct page *z_erofs_bvset_flip(struct z_erofs_bvec_iter *iter)
{
unsigned long base = (unsigned long)((struct z_erofs_bvset *)0)->bvec;
/* have to access nextpage in advance, otherwise it will be unmapped */
struct page *nextpage = iter->bvset->nextpage;
struct page *oldpage;
DBG_BUGON(!nextpage);
oldpage = z_erofs_bvec_iter_end(iter);
iter->bvpage = nextpage;
iter->bvset = kmap_local_page(nextpage);
iter->nr = (PAGE_SIZE - base) / sizeof(struct z_erofs_bvec);
iter->cur = 0;
return oldpage;
}
static void z_erofs_bvec_iter_begin(struct z_erofs_bvec_iter *iter,
struct z_erofs_bvset_inline *bvset,
unsigned int bootstrap_nr,
unsigned int cur)
{
*iter = (struct z_erofs_bvec_iter) {
.nr = bootstrap_nr,
.bvset = (struct z_erofs_bvset *)bvset,
};
while (cur > iter->nr) {
cur -= iter->nr;
z_erofs_bvset_flip(iter);
}
iter->cur = cur;
}
static int z_erofs_bvec_enqueue(struct z_erofs_bvec_iter *iter,
struct z_erofs_bvec *bvec,
struct page **candidate_bvpage,
struct page **pagepool)
{
if (iter->cur >= iter->nr) {
struct page *nextpage = *candidate_bvpage;
if (!nextpage) {
nextpage = erofs_allocpage(pagepool, GFP_NOFS);
if (!nextpage)
return -ENOMEM;
set_page_private(nextpage, Z_EROFS_SHORTLIVED_PAGE);
}
DBG_BUGON(iter->bvset->nextpage);
iter->bvset->nextpage = nextpage;
z_erofs_bvset_flip(iter);
iter->bvset->nextpage = NULL;
*candidate_bvpage = NULL;
}
iter->bvset->bvec[iter->cur++] = *bvec;
return 0;
}
static void z_erofs_bvec_dequeue(struct z_erofs_bvec_iter *iter,
struct z_erofs_bvec *bvec,
struct page **old_bvpage)
{
if (iter->cur == iter->nr)
*old_bvpage = z_erofs_bvset_flip(iter);
else
*old_bvpage = NULL;
*bvec = iter->bvset->bvec[iter->cur++];
}
static void z_erofs_destroy_pcluster_pool(void)
{
int i;
for (i = 0; i < ARRAY_SIZE(pcluster_pool); ++i) {
if (!pcluster_pool[i].slab)
continue;
kmem_cache_destroy(pcluster_pool[i].slab);
pcluster_pool[i].slab = NULL;
}
}
static int z_erofs_create_pcluster_pool(void)
{
struct z_erofs_pcluster_slab *pcs;
struct z_erofs_pcluster *a;
unsigned int size;
for (pcs = pcluster_pool;
pcs < pcluster_pool + ARRAY_SIZE(pcluster_pool); ++pcs) {
size = struct_size(a, compressed_bvecs, pcs->maxpages);
sprintf(pcs->name, "erofs_pcluster-%u", pcs->maxpages);
pcs->slab = kmem_cache_create(pcs->name, size, 0,
SLAB_RECLAIM_ACCOUNT, NULL);
if (pcs->slab)
continue;
z_erofs_destroy_pcluster_pool();
return -ENOMEM;
}
return 0;
}
static struct z_erofs_pcluster *z_erofs_alloc_pcluster(unsigned int nrpages)
{
int i;
for (i = 0; i < ARRAY_SIZE(pcluster_pool); ++i) {
struct z_erofs_pcluster_slab *pcs = pcluster_pool + i;
struct z_erofs_pcluster *pcl;
if (nrpages > pcs->maxpages)
continue;
pcl = kmem_cache_zalloc(pcs->slab, GFP_NOFS);
if (!pcl)
return ERR_PTR(-ENOMEM);
pcl->pclusterpages = nrpages;
return pcl;
}
return ERR_PTR(-EINVAL);
}
static void z_erofs_free_pcluster(struct z_erofs_pcluster *pcl)
{
unsigned int pclusterpages = z_erofs_pclusterpages(pcl);
int i;
for (i = 0; i < ARRAY_SIZE(pcluster_pool); ++i) {
struct z_erofs_pcluster_slab *pcs = pcluster_pool + i;
if (pclusterpages > pcs->maxpages)
continue;
kmem_cache_free(pcs->slab, pcl);
return;
}
DBG_BUGON(1);
}
static struct workqueue_struct *z_erofs_workqueue __read_mostly;
#ifdef CONFIG_EROFS_FS_PCPU_KTHREAD
static struct kthread_worker __rcu **z_erofs_pcpu_workers;
static void erofs_destroy_percpu_workers(void)
{
struct kthread_worker *worker;
unsigned int cpu;
for_each_possible_cpu(cpu) {
worker = rcu_dereference_protected(
z_erofs_pcpu_workers[cpu], 1);
rcu_assign_pointer(z_erofs_pcpu_workers[cpu], NULL);
if (worker)
kthread_destroy_worker(worker);
}
kfree(z_erofs_pcpu_workers);
}
static struct kthread_worker *erofs_init_percpu_worker(int cpu)
{
struct kthread_worker *worker =
kthread_create_worker_on_cpu(cpu, 0, "erofs_worker/%u", cpu);
if (IS_ERR(worker))
return worker;
if (IS_ENABLED(CONFIG_EROFS_FS_PCPU_KTHREAD_HIPRI))
sched_set_fifo_low(worker->task);
return worker;
}
static int erofs_init_percpu_workers(void)
{
struct kthread_worker *worker;
unsigned int cpu;
z_erofs_pcpu_workers = kcalloc(num_possible_cpus(),
sizeof(struct kthread_worker *), GFP_ATOMIC);
if (!z_erofs_pcpu_workers)
return -ENOMEM;
for_each_online_cpu(cpu) { /* could miss cpu{off,on}line? */
worker = erofs_init_percpu_worker(cpu);
if (!IS_ERR(worker))
rcu_assign_pointer(z_erofs_pcpu_workers[cpu], worker);
}
return 0;
}
#else
static inline void erofs_destroy_percpu_workers(void) {}
static inline int erofs_init_percpu_workers(void) { return 0; }
#endif
#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_EROFS_FS_PCPU_KTHREAD)
static DEFINE_SPINLOCK(z_erofs_pcpu_worker_lock);
static enum cpuhp_state erofs_cpuhp_state;
static int erofs_cpu_online(unsigned int cpu)
{
struct kthread_worker *worker, *old;
worker = erofs_init_percpu_worker(cpu);
if (IS_ERR(worker))
return PTR_ERR(worker);
spin_lock(&z_erofs_pcpu_worker_lock);
old = rcu_dereference_protected(z_erofs_pcpu_workers[cpu],
lockdep_is_held(&z_erofs_pcpu_worker_lock));
if (!old)
rcu_assign_pointer(z_erofs_pcpu_workers[cpu], worker);
spin_unlock(&z_erofs_pcpu_worker_lock);
if (old)
kthread_destroy_worker(worker);
return 0;
}
static int erofs_cpu_offline(unsigned int cpu)
{
struct kthread_worker *worker;
spin_lock(&z_erofs_pcpu_worker_lock);
worker = rcu_dereference_protected(z_erofs_pcpu_workers[cpu],
lockdep_is_held(&z_erofs_pcpu_worker_lock));
rcu_assign_pointer(z_erofs_pcpu_workers[cpu], NULL);
spin_unlock(&z_erofs_pcpu_worker_lock);
synchronize_rcu();
if (worker)
kthread_destroy_worker(worker);
return 0;
}
static int erofs_cpu_hotplug_init(void)
{
int state;
state = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
"fs/erofs:online", erofs_cpu_online, erofs_cpu_offline);
if (state < 0)
return state;
erofs_cpuhp_state = state;
return 0;
}
static void erofs_cpu_hotplug_destroy(void)
{
if (erofs_cpuhp_state)
cpuhp_remove_state_nocalls(erofs_cpuhp_state);
}
#else /* !CONFIG_HOTPLUG_CPU || !CONFIG_EROFS_FS_PCPU_KTHREAD */
static inline int erofs_cpu_hotplug_init(void) { return 0; }
static inline void erofs_cpu_hotplug_destroy(void) {}
#endif
void z_erofs_exit_zip_subsystem(void)
{
erofs_cpu_hotplug_destroy();
erofs_destroy_percpu_workers();
destroy_workqueue(z_erofs_workqueue);
z_erofs_destroy_pcluster_pool();
}
int __init z_erofs_init_zip_subsystem(void)
{
int err = z_erofs_create_pcluster_pool();
if (err)
goto out_error_pcluster_pool;
z_erofs_workqueue = alloc_workqueue("erofs_worker",
WQ_UNBOUND | WQ_HIGHPRI, num_possible_cpus());
if (!z_erofs_workqueue) {
err = -ENOMEM;
goto out_error_workqueue_init;
}
err = erofs_init_percpu_workers();
if (err)
goto out_error_pcpu_worker;
err = erofs_cpu_hotplug_init();
if (err < 0)
goto out_error_cpuhp_init;
return err;
out_error_cpuhp_init:
erofs_destroy_percpu_workers();
out_error_pcpu_worker:
destroy_workqueue(z_erofs_workqueue);
out_error_workqueue_init:
z_erofs_destroy_pcluster_pool();
out_error_pcluster_pool:
return err;
}
enum z_erofs_pclustermode {
Z_EROFS_PCLUSTER_INFLIGHT,
/*
* a weak form of Z_EROFS_PCLUSTER_FOLLOWED, the difference is that it
* could be dispatched into bypass queue later due to uptodated managed
* pages. All related online pages cannot be reused for inplace I/O (or
* bvpage) since it can be directly decoded without I/O submission.
*/
Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE,
/*
* The pcluster was just linked to a decompression chain by us. It can
* also be linked with the remaining pclusters, which means if the
* processing page is the tail page of a pcluster, this pcluster can
* safely use the whole page (since the previous pcluster is within the
* same chain) for in-place I/O, as illustrated below:
* ___________________________________________________
* | tail (partial) page | head (partial) page |
* | (of the current pcl) | (of the previous pcl) |
* |___PCLUSTER_FOLLOWED___|_____PCLUSTER_FOLLOWED_____|
*
* [ (*) the page above can be used as inplace I/O. ]
*/
Z_EROFS_PCLUSTER_FOLLOWED,
};
struct z_erofs_decompress_frontend {
struct inode *const inode;
struct erofs_map_blocks map;
struct z_erofs_bvec_iter biter;
struct page *pagepool;
struct page *candidate_bvpage;
struct z_erofs_pcluster *pcl;
z_erofs_next_pcluster_t owned_head;
enum z_erofs_pclustermode mode;
erofs_off_t headoffset;
/* a pointer used to pick up inplace I/O pages */
unsigned int icur;
};
#define DECOMPRESS_FRONTEND_INIT(__i) { \
.inode = __i, .owned_head = Z_EROFS_PCLUSTER_TAIL, \
.mode = Z_EROFS_PCLUSTER_FOLLOWED }
static bool z_erofs_should_alloc_cache(struct z_erofs_decompress_frontend *fe)
{
unsigned int cachestrategy = EROFS_I_SB(fe->inode)->opt.cache_strategy;
if (cachestrategy <= EROFS_ZIP_CACHE_DISABLED)
return false;
if (!(fe->map.m_flags & EROFS_MAP_FULL_MAPPED))
return true;
if (cachestrategy >= EROFS_ZIP_CACHE_READAROUND &&
fe->map.m_la < fe->headoffset)
return true;
return false;
}
static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe)
{
struct address_space *mc = MNGD_MAPPING(EROFS_I_SB(fe->inode));
struct z_erofs_pcluster *pcl = fe->pcl;
bool shouldalloc = z_erofs_should_alloc_cache(fe);
bool standalone = true;
/*
* optimistic allocation without direct reclaim since inplace I/O
* can be used if low memory otherwise.
*/
gfp_t gfp = (mapping_gfp_mask(mc) & ~__GFP_DIRECT_RECLAIM) |
__GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN;
unsigned int i;
if (fe->mode < Z_EROFS_PCLUSTER_FOLLOWED)
return;
for (i = 0; i < pcl->pclusterpages; ++i) {
struct page *page;
void *t; /* mark pages just found for debugging */
struct page *newpage = NULL;
/* the compressed page was loaded before */
if (READ_ONCE(pcl->compressed_bvecs[i].page))
continue;
page = find_get_page(mc, pcl->obj.index + i);
if (page) {
t = (void *)((unsigned long)page | 1);
} else {
/* I/O is needed, no possible to decompress directly */
standalone = false;
if (!shouldalloc)
continue;
/*
* try to use cached I/O if page allocation
* succeeds or fallback to in-place I/O instead
* to avoid any direct reclaim.
*/
newpage = erofs_allocpage(&fe->pagepool, gfp);
if (!newpage)
continue;
set_page_private(newpage, Z_EROFS_PREALLOCATED_PAGE);
t = (void *)((unsigned long)newpage | 1);
}
if (!cmpxchg_relaxed(&pcl->compressed_bvecs[i].page, NULL, t))
continue;
if (page)
put_page(page);
else if (newpage)
erofs_pagepool_add(&fe->pagepool, newpage);
}
/*
* don't do inplace I/O if all compressed pages are available in
* managed cache since it can be moved to the bypass queue instead.
*/
if (standalone)
fe->mode = Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE;
}
/* called by erofs_shrinker to get rid of all compressed_pages */
int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
struct erofs_workgroup *grp)
{
struct z_erofs_pcluster *const pcl =
container_of(grp, struct z_erofs_pcluster, obj);
int i;
DBG_BUGON(z_erofs_is_inline_pcluster(pcl));
/*
* refcount of workgroup is now freezed as 0,
* therefore no need to worry about available decompression users.
*/
for (i = 0; i < pcl->pclusterpages; ++i) {
struct page *page = pcl->compressed_bvecs[i].page;
if (!page)
continue;
/* block other users from reclaiming or migrating the page */
if (!trylock_page(page))
return -EBUSY;
if (!erofs_page_is_managed(sbi, page))
continue;
/* barrier is implied in the following 'unlock_page' */
WRITE_ONCE(pcl->compressed_bvecs[i].page, NULL);
detach_page_private(page);
unlock_page(page);
}
return 0;
}
static bool z_erofs_cache_release_folio(struct folio *folio, gfp_t gfp)
{
struct z_erofs_pcluster *pcl = folio_get_private(folio);
bool ret;
int i;
if (!folio_test_private(folio))
return true;
ret = false;
spin_lock(&pcl->obj.lockref.lock);
if (pcl->obj.lockref.count > 0)
goto out;
DBG_BUGON(z_erofs_is_inline_pcluster(pcl));
for (i = 0; i < pcl->pclusterpages; ++i) {
if (pcl->compressed_bvecs[i].page == &folio->page) {
WRITE_ONCE(pcl->compressed_bvecs[i].page, NULL);
ret = true;
break;
}
}
if (ret)
folio_detach_private(folio);
out:
spin_unlock(&pcl->obj.lockref.lock);
return ret;
}
/*
* It will be called only on inode eviction. In case that there are still some
* decompression requests in progress, wait with rescheduling for a bit here.
* An extra lock could be introduced instead but it seems unnecessary.
*/
static void z_erofs_cache_invalidate_folio(struct folio *folio,
size_t offset, size_t length)
{
const size_t stop = length + offset;
/* Check for potential overflow in debug mode */
DBG_BUGON(stop > folio_size(folio) || stop < length);
if (offset == 0 && stop == folio_size(folio))
while (!z_erofs_cache_release_folio(folio, GFP_NOFS))
cond_resched();
}
static const struct address_space_operations z_erofs_cache_aops = {
.release_folio = z_erofs_cache_release_folio,
.invalidate_folio = z_erofs_cache_invalidate_folio,
};
int erofs_init_managed_cache(struct super_block *sb)
{
struct inode *const inode = new_inode(sb);
if (!inode)
return -ENOMEM;
set_nlink(inode, 1);
inode->i_size = OFFSET_MAX;
inode->i_mapping->a_ops = &z_erofs_cache_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
EROFS_SB(sb)->managed_cache = inode;
return 0;
}
static bool z_erofs_try_inplace_io(struct z_erofs_decompress_frontend *fe,
struct z_erofs_bvec *bvec)
{
struct z_erofs_pcluster *const pcl = fe->pcl;
while (fe->icur > 0) {
if (!cmpxchg(&pcl->compressed_bvecs[--fe->icur].page,
NULL, bvec->page)) {
pcl->compressed_bvecs[fe->icur] = *bvec;
return true;
}
}
return false;
}
/* callers must be with pcluster lock held */
static int z_erofs_attach_page(struct z_erofs_decompress_frontend *fe,
struct z_erofs_bvec *bvec, bool exclusive)
{
int ret;
if (exclusive) {
/* give priority for inplaceio to use file pages first */
if (z_erofs_try_inplace_io(fe, bvec))
return 0;
/* otherwise, check if it can be used as a bvpage */
if (fe->mode >= Z_EROFS_PCLUSTER_FOLLOWED &&
!fe->candidate_bvpage)
fe->candidate_bvpage = bvec->page;
}
ret = z_erofs_bvec_enqueue(&fe->biter, bvec, &fe->candidate_bvpage,
&fe->pagepool);
fe->pcl->vcnt += (ret >= 0);
return ret;
}
static void z_erofs_try_to_claim_pcluster(struct z_erofs_decompress_frontend *f)
{
struct z_erofs_pcluster *pcl = f->pcl;
z_erofs_next_pcluster_t *owned_head = &f->owned_head;
/* type 1, nil pcluster (this pcluster doesn't belong to any chain.) */
if (cmpxchg(&pcl->next, Z_EROFS_PCLUSTER_NIL,
*owned_head) == Z_EROFS_PCLUSTER_NIL) {
*owned_head = &pcl->next;
/* so we can attach this pcluster to our submission chain. */
f->mode = Z_EROFS_PCLUSTER_FOLLOWED;
return;
}
/* type 2, it belongs to an ongoing chain */
f->mode = Z_EROFS_PCLUSTER_INFLIGHT;
}
static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe)
{
struct erofs_map_blocks *map = &fe->map;
bool ztailpacking = map->m_flags & EROFS_MAP_META;
struct z_erofs_pcluster *pcl;
struct erofs_workgroup *grp;
int err;
if (!(map->m_flags & EROFS_MAP_ENCODED) ||
(!ztailpacking && !(map->m_pa >> PAGE_SHIFT))) {
DBG_BUGON(1);
return -EFSCORRUPTED;
}
/* no available pcluster, let's allocate one */
pcl = z_erofs_alloc_pcluster(ztailpacking ? 1 :
map->m_plen >> PAGE_SHIFT);
if (IS_ERR(pcl))
return PTR_ERR(pcl);
spin_lock_init(&pcl->obj.lockref.lock);
pcl->algorithmformat = map->m_algorithmformat;
pcl->length = 0;
pcl->partial = true;
/* new pclusters should be claimed as type 1, primary and followed */
pcl->next = fe->owned_head;
pcl->pageofs_out = map->m_la & ~PAGE_MASK;
fe->mode = Z_EROFS_PCLUSTER_FOLLOWED;
/*
* lock all primary followed works before visible to others
* and mutex_trylock *never* fails for a new pcluster.
*/
mutex_init(&pcl->lock);
DBG_BUGON(!mutex_trylock(&pcl->lock));
if (ztailpacking) {
pcl->obj.index = 0; /* which indicates ztailpacking */
pcl->pageofs_in = erofs_blkoff(fe->inode->i_sb, map->m_pa);
pcl->tailpacking_size = map->m_plen;
} else {
pcl->obj.index = map->m_pa >> PAGE_SHIFT;
grp = erofs_insert_workgroup(fe->inode->i_sb, &pcl->obj);
if (IS_ERR(grp)) {
err = PTR_ERR(grp);
goto err_out;
}
if (grp != &pcl->obj) {
fe->pcl = container_of(grp,
struct z_erofs_pcluster, obj);
err = -EEXIST;
goto err_out;
}
}
fe->owned_head = &pcl->next;
fe->pcl = pcl;
return 0;
err_out:
mutex_unlock(&pcl->lock);
z_erofs_free_pcluster(pcl);
return err;
}
static int z_erofs_pcluster_begin(struct z_erofs_decompress_frontend *fe)
{
struct erofs_map_blocks *map = &fe->map;
struct super_block *sb = fe->inode->i_sb;
erofs_blk_t blknr = erofs_blknr(sb, map->m_pa);
struct erofs_workgroup *grp = NULL;
int ret;
DBG_BUGON(fe->pcl);
/* must be Z_EROFS_PCLUSTER_TAIL or pointed to previous pcluster */
DBG_BUGON(fe->owned_head == Z_EROFS_PCLUSTER_NIL);
if (!(map->m_flags & EROFS_MAP_META)) {
grp = erofs_find_workgroup(sb, blknr);
} else if ((map->m_pa & ~PAGE_MASK) + map->m_plen > PAGE_SIZE) {
DBG_BUGON(1);
return -EFSCORRUPTED;
}
if (grp) {
fe->pcl = container_of(grp, struct z_erofs_pcluster, obj);
ret = -EEXIST;
} else {
ret = z_erofs_register_pcluster(fe);
}
if (ret == -EEXIST) {
mutex_lock(&fe->pcl->lock);
z_erofs_try_to_claim_pcluster(fe);
} else if (ret) {
return ret;
}
z_erofs_bvec_iter_begin(&fe->biter, &fe->pcl->bvset,
Z_EROFS_INLINE_BVECS, fe->pcl->vcnt);
if (!z_erofs_is_inline_pcluster(fe->pcl)) {
/* bind cache first when cached decompression is preferred */
z_erofs_bind_cache(fe);
} else {
void *mptr;
mptr = erofs_read_metabuf(&map->buf, sb, blknr, EROFS_NO_KMAP);
if (IS_ERR(mptr)) {
ret = PTR_ERR(mptr);
erofs_err(sb, "failed to get inline data %d", ret);
return ret;
}
get_page(map->buf.page);
WRITE_ONCE(fe->pcl->compressed_bvecs[0].page, map->buf.page);
fe->mode = Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE;
}
/* file-backed inplace I/O pages are traversed in reverse order */
fe->icur = z_erofs_pclusterpages(fe->pcl);
return 0;
}
/*
* keep in mind that no referenced pclusters will be freed
* only after a RCU grace period.
*/
static void z_erofs_rcu_callback(struct rcu_head *head)
{
z_erofs_free_pcluster(container_of(head,
struct z_erofs_pcluster, rcu));
}
void erofs_workgroup_free_rcu(struct erofs_workgroup *grp)
{
struct z_erofs_pcluster *const pcl =
container_of(grp, struct z_erofs_pcluster, obj);
call_rcu(&pcl->rcu, z_erofs_rcu_callback);
}
static void z_erofs_pcluster_end(struct z_erofs_decompress_frontend *fe)
{
struct z_erofs_pcluster *pcl = fe->pcl;
if (!pcl)
return;
z_erofs_bvec_iter_end(&fe->biter);
mutex_unlock(&pcl->lock);
if (fe->candidate_bvpage)
fe->candidate_bvpage = NULL;
/*
* if all pending pages are added, don't hold its reference
* any longer if the pcluster isn't hosted by ourselves.
*/
if (fe->mode < Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE)
erofs_workgroup_put(&pcl->obj);
fe->pcl = NULL;
}
static int z_erofs_read_fragment(struct super_block *sb, struct page *page,
unsigned int cur, unsigned int end, erofs_off_t pos)
{
struct inode *packed_inode = EROFS_SB(sb)->packed_inode;
struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
unsigned int cnt;
u8 *src;
if (!packed_inode)
return -EFSCORRUPTED;
buf.inode = packed_inode;
for (; cur < end; cur += cnt, pos += cnt) {
cnt = min_t(unsigned int, end - cur,
sb->s_blocksize - erofs_blkoff(sb, pos));
src = erofs_bread(&buf, erofs_blknr(sb, pos), EROFS_KMAP);
if (IS_ERR(src)) {
erofs_put_metabuf(&buf);
return PTR_ERR(src);
}
memcpy_to_page(page, cur, src + erofs_blkoff(sb, pos), cnt);
}
erofs_put_metabuf(&buf);
return 0;
}
static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe,
struct page *page)
{
struct inode *const inode = fe->inode;
struct erofs_map_blocks *const map = &fe->map;
const loff_t offset = page_offset(page);
bool tight = true, exclusive;
unsigned int cur, end, len, split;
int err = 0;
z_erofs_onlinepage_init(page);
split = 0;
end = PAGE_SIZE;
repeat:
if (offset + end - 1 < map->m_la ||
offset + end - 1 >= map->m_la + map->m_llen) {
z_erofs_pcluster_end(fe);
map->m_la = offset + end - 1;
map->m_llen = 0;
err = z_erofs_map_blocks_iter(inode, map, 0);
if (err)
goto out;
}
cur = offset > map->m_la ? 0 : map->m_la - offset;
/* bump split parts first to avoid several separate cases */
++split;
if (!(map->m_flags & EROFS_MAP_MAPPED)) {
zero_user_segment(page, cur, end);
tight = false;