-
Notifications
You must be signed in to change notification settings - Fork 17
/
shmem.c
2691 lines (2418 loc) · 68.9 KB
/
shmem.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
/*
* Resizable virtual memory filesystem for Linux.
*
* Copyright (C) 2000 Linus Torvalds.
* 2000 Transmeta Corp.
* 2000-2001 Christoph Rohland
* 2000-2001 SAP AG
* 2002 Red Hat Inc.
* Copyright (C) 2002-2005 Hugh Dickins.
* Copyright (C) 2002-2005 VERITAS Software Corporation.
* Copyright (C) 2004 Andi Kleen, SuSE Labs
*
* Extended attribute support for tmpfs:
* Copyright (c) 2004, Luke Kenneth Casson Leighton <[email protected]>
* Copyright (c) 2004 Red Hat, Inc., James Morris <[email protected]>
*
* tiny-shmem:
* Copyright (c) 2004, 2008 Matt Mackall <[email protected]>
*
* This file is released under the GPL.
*/
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/vfs.h>
#include <linux/mount.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/swap.h>
#include <linux/ima.h>
static struct vfsmount *shm_mnt;
#ifdef CONFIG_SHMEM
/*
* This virtual memory filesystem is heavily based on the ramfs. It
* extends ramfs by the ability to use swap and honor resource limits
* which makes it a completely usable filesystem.
*/
#include <linux/xattr.h>
#include <linux/exportfs.h>
#include <linux/generic_acl.h>
#include <linux/mman.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/backing-dev.h>
#include <linux/shmem_fs.h>
#include <linux/writeback.h>
#include <linux/vfs.h>
#include <linux/blkdev.h>
#include <linux/security.h>
#include <linux/swapops.h>
#include <linux/mempolicy.h>
#include <linux/namei.h>
#include <linux/ctype.h>
#include <linux/migrate.h>
#include <linux/highmem.h>
#include <linux/seq_file.h>
#include <linux/magic.h>
#include <asm/uaccess.h>
#include <asm/div64.h>
#include <asm/pgtable.h>
/*
* The maximum size of a shmem/tmpfs file is limited by the maximum size of
* its triple-indirect swap vector - see illustration at shmem_swp_entry().
*
* With 4kB page size, maximum file size is just over 2TB on a 32-bit kernel,
* but one eighth of that on a 64-bit kernel. With 8kB page size, maximum
* file size is just over 4TB on a 64-bit kernel, but 16TB on a 32-bit kernel,
* MAX_LFS_FILESIZE being then more restrictive than swap vector layout.
*
* We use / and * instead of shifts in the definitions below, so that the swap
* vector can be tested with small even values (e.g. 20) for ENTRIES_PER_PAGE.
*/
#define ENTRIES_PER_PAGE (PAGE_CACHE_SIZE/sizeof(unsigned long))
#define ENTRIES_PER_PAGEPAGE ((unsigned long long)ENTRIES_PER_PAGE*ENTRIES_PER_PAGE)
#define SHMSWP_MAX_INDEX (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1))
#define SHMSWP_MAX_BYTES (SHMSWP_MAX_INDEX << PAGE_CACHE_SHIFT)
#define SHMEM_MAX_BYTES min_t(unsigned long long, SHMSWP_MAX_BYTES, MAX_LFS_FILESIZE)
#define SHMEM_MAX_INDEX ((unsigned long)((SHMEM_MAX_BYTES+1) >> PAGE_CACHE_SHIFT))
#define BLOCKS_PER_PAGE (PAGE_CACHE_SIZE/512)
#define VM_ACCT(size) (PAGE_CACHE_ALIGN(size) >> PAGE_SHIFT)
/* info->flags needs VM_flags to handle pagein/truncate races efficiently */
#define SHMEM_PAGEIN VM_READ
#define SHMEM_TRUNCATE VM_WRITE
/* Definition to limit shmem_truncate's steps between cond_rescheds */
#define LATENCY_LIMIT 64
/* Pretend that each entry is of this size in directory's i_size */
#define BOGO_DIRENT_SIZE 20
/* Flag allocation requirements to shmem_getpage and shmem_swp_alloc */
enum sgp_type {
SGP_READ, /* don't exceed i_size, don't allocate page */
SGP_CACHE, /* don't exceed i_size, may allocate page */
SGP_DIRTY, /* like SGP_CACHE, but set new page dirty */
SGP_WRITE, /* may exceed i_size, may allocate page */
};
#ifdef CONFIG_TMPFS
static unsigned long shmem_default_max_blocks(void)
{
return totalram_pages / 2;
}
static unsigned long shmem_default_max_inodes(void)
{
return min(totalram_pages - totalhigh_pages, totalram_pages / 2);
}
#endif
static int shmem_getpage(struct inode *inode, unsigned long idx,
struct page **pagep, enum sgp_type sgp, int *type);
static inline struct page *shmem_dir_alloc(gfp_t gfp_mask)
{
/*
* The above definition of ENTRIES_PER_PAGE, and the use of
* BLOCKS_PER_PAGE on indirect pages, assume PAGE_CACHE_SIZE:
* might be reconsidered if it ever diverges from PAGE_SIZE.
*
* Mobility flags are masked out as swap vectors cannot move
*/
return alloc_pages((gfp_mask & ~GFP_MOVABLE_MASK) | __GFP_ZERO,
PAGE_CACHE_SHIFT-PAGE_SHIFT);
}
static inline void shmem_dir_free(struct page *page)
{
__free_pages(page, PAGE_CACHE_SHIFT-PAGE_SHIFT);
}
static struct page **shmem_dir_map(struct page *page)
{
return (struct page **)kmap_atomic(page, KM_USER0);
}
static inline void shmem_dir_unmap(struct page **dir)
{
kunmap_atomic(dir, KM_USER0);
}
static swp_entry_t *shmem_swp_map(struct page *page)
{
return (swp_entry_t *)kmap_atomic(page, KM_USER1);
}
static inline void shmem_swp_balance_unmap(void)
{
/*
* When passing a pointer to an i_direct entry, to code which
* also handles indirect entries and so will shmem_swp_unmap,
* we must arrange for the preempt count to remain in balance.
* What kmap_atomic of a lowmem page does depends on config
* and architecture, so pretend to kmap_atomic some lowmem page.
*/
(void) kmap_atomic(ZERO_PAGE(0), KM_USER1);
}
static inline void shmem_swp_unmap(swp_entry_t *entry)
{
kunmap_atomic(entry, KM_USER1);
}
static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb)
{
return sb->s_fs_info;
}
/*
* shmem_file_setup pre-accounts the whole fixed size of a VM object,
* for shared memory and for shared anonymous (/dev/zero) mappings
* (unless MAP_NORESERVE and sysctl_overcommit_memory <= 1),
* consistent with the pre-accounting of private mappings ...
*/
static inline int shmem_acct_size(unsigned long flags, loff_t size)
{
return (flags & VM_NORESERVE) ?
0 : security_vm_enough_memory_kern(VM_ACCT(size));
}
static inline void shmem_unacct_size(unsigned long flags, loff_t size)
{
if (!(flags & VM_NORESERVE))
vm_unacct_memory(VM_ACCT(size));
}
/*
* ... whereas tmpfs objects are accounted incrementally as
* pages are allocated, in order to allow huge sparse files.
* shmem_getpage reports shmem_acct_block failure as -ENOSPC not -ENOMEM,
* so that a failure on a sparse tmpfs mapping will give SIGBUS not OOM.
*/
static inline int shmem_acct_block(unsigned long flags)
{
return (flags & VM_NORESERVE) ?
security_vm_enough_memory_kern(VM_ACCT(PAGE_CACHE_SIZE)) : 0;
}
static inline void shmem_unacct_blocks(unsigned long flags, long pages)
{
if (flags & VM_NORESERVE)
vm_unacct_memory(pages * VM_ACCT(PAGE_CACHE_SIZE));
}
static const struct super_operations shmem_ops;
static const struct address_space_operations shmem_aops;
static const struct file_operations shmem_file_operations;
static const struct inode_operations shmem_inode_operations;
static const struct inode_operations shmem_dir_inode_operations;
static const struct inode_operations shmem_special_inode_operations;
static struct vm_operations_struct shmem_vm_ops;
static struct backing_dev_info shmem_backing_dev_info __read_mostly = {
.ra_pages = 0, /* No readahead */
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
.unplug_io_fn = default_unplug_io_fn,
};
static LIST_HEAD(shmem_swaplist);
static DEFINE_MUTEX(shmem_swaplist_mutex);
static void shmem_free_blocks(struct inode *inode, long pages)
{
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
if (sbinfo->max_blocks) {
spin_lock(&sbinfo->stat_lock);
sbinfo->free_blocks += pages;
inode->i_blocks -= pages*BLOCKS_PER_PAGE;
spin_unlock(&sbinfo->stat_lock);
}
}
static int shmem_reserve_inode(struct super_block *sb)
{
struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
if (sbinfo->max_inodes) {
spin_lock(&sbinfo->stat_lock);
if (!sbinfo->free_inodes) {
spin_unlock(&sbinfo->stat_lock);
return -ENOSPC;
}
sbinfo->free_inodes--;
spin_unlock(&sbinfo->stat_lock);
}
return 0;
}
static void shmem_free_inode(struct super_block *sb)
{
struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
if (sbinfo->max_inodes) {
spin_lock(&sbinfo->stat_lock);
sbinfo->free_inodes++;
spin_unlock(&sbinfo->stat_lock);
}
}
/**
* shmem_recalc_inode - recalculate the size of an inode
* @inode: inode to recalc
*
* We have to calculate the free blocks since the mm can drop
* undirtied hole pages behind our back.
*
* But normally info->alloced == inode->i_mapping->nrpages + info->swapped
* So mm freed is info->alloced - (inode->i_mapping->nrpages + info->swapped)
*
* It has to be called with the spinlock held.
*/
static void shmem_recalc_inode(struct inode *inode)
{
struct shmem_inode_info *info = SHMEM_I(inode);
long freed;
freed = info->alloced - info->swapped - inode->i_mapping->nrpages;
if (freed > 0) {
info->alloced -= freed;
shmem_unacct_blocks(info->flags, freed);
shmem_free_blocks(inode, freed);
}
}
/**
* shmem_swp_entry - find the swap vector position in the info structure
* @info: info structure for the inode
* @index: index of the page to find
* @page: optional page to add to the structure. Has to be preset to
* all zeros
*
* If there is no space allocated yet it will return NULL when
* page is NULL, else it will use the page for the needed block,
* setting it to NULL on return to indicate that it has been used.
*
* The swap vector is organized the following way:
*
* There are SHMEM_NR_DIRECT entries directly stored in the
* shmem_inode_info structure. So small files do not need an addional
* allocation.
*
* For pages with index > SHMEM_NR_DIRECT there is the pointer
* i_indirect which points to a page which holds in the first half
* doubly indirect blocks, in the second half triple indirect blocks:
*
* For an artificial ENTRIES_PER_PAGE = 4 this would lead to the
* following layout (for SHMEM_NR_DIRECT == 16):
*
* i_indirect -> dir --> 16-19
* | +-> 20-23
* |
* +-->dir2 --> 24-27
* | +-> 28-31
* | +-> 32-35
* | +-> 36-39
* |
* +-->dir3 --> 40-43
* +-> 44-47
* +-> 48-51
* +-> 52-55
*/
static swp_entry_t *shmem_swp_entry(struct shmem_inode_info *info, unsigned long index, struct page **page)
{
unsigned long offset;
struct page **dir;
struct page *subdir;
if (index < SHMEM_NR_DIRECT) {
shmem_swp_balance_unmap();
return info->i_direct+index;
}
if (!info->i_indirect) {
if (page) {
info->i_indirect = *page;
*page = NULL;
}
return NULL; /* need another page */
}
index -= SHMEM_NR_DIRECT;
offset = index % ENTRIES_PER_PAGE;
index /= ENTRIES_PER_PAGE;
dir = shmem_dir_map(info->i_indirect);
if (index >= ENTRIES_PER_PAGE/2) {
index -= ENTRIES_PER_PAGE/2;
dir += ENTRIES_PER_PAGE/2 + index/ENTRIES_PER_PAGE;
index %= ENTRIES_PER_PAGE;
subdir = *dir;
if (!subdir) {
if (page) {
*dir = *page;
*page = NULL;
}
shmem_dir_unmap(dir);
return NULL; /* need another page */
}
shmem_dir_unmap(dir);
dir = shmem_dir_map(subdir);
}
dir += index;
subdir = *dir;
if (!subdir) {
if (!page || !(subdir = *page)) {
shmem_dir_unmap(dir);
return NULL; /* need a page */
}
*dir = subdir;
*page = NULL;
}
shmem_dir_unmap(dir);
return shmem_swp_map(subdir) + offset;
}
static void shmem_swp_set(struct shmem_inode_info *info, swp_entry_t *entry, unsigned long value)
{
long incdec = value? 1: -1;
entry->val = value;
info->swapped += incdec;
if ((unsigned long)(entry - info->i_direct) >= SHMEM_NR_DIRECT) {
struct page *page = kmap_atomic_to_page(entry);
set_page_private(page, page_private(page) + incdec);
}
}
/**
* shmem_swp_alloc - get the position of the swap entry for the page.
* @info: info structure for the inode
* @index: index of the page to find
* @sgp: check and recheck i_size? skip allocation?
*
* If the entry does not exist, allocate it.
*/
static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long index, enum sgp_type sgp)
{
struct inode *inode = &info->vfs_inode;
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
struct page *page = NULL;
swp_entry_t *entry;
if (sgp != SGP_WRITE &&
((loff_t) index << PAGE_CACHE_SHIFT) >= i_size_read(inode))
return ERR_PTR(-EINVAL);
while (!(entry = shmem_swp_entry(info, index, &page))) {
if (sgp == SGP_READ)
return shmem_swp_map(ZERO_PAGE(0));
/*
* Test free_blocks against 1 not 0, since we have 1 data
* page (and perhaps indirect index pages) yet to allocate:
* a waste to allocate index if we cannot allocate data.
*/
if (sbinfo->max_blocks) {
spin_lock(&sbinfo->stat_lock);
if (sbinfo->free_blocks <= 1) {
spin_unlock(&sbinfo->stat_lock);
return ERR_PTR(-ENOSPC);
}
sbinfo->free_blocks--;
inode->i_blocks += BLOCKS_PER_PAGE;
spin_unlock(&sbinfo->stat_lock);
}
spin_unlock(&info->lock);
page = shmem_dir_alloc(mapping_gfp_mask(inode->i_mapping));
if (page)
set_page_private(page, 0);
spin_lock(&info->lock);
if (!page) {
shmem_free_blocks(inode, 1);
return ERR_PTR(-ENOMEM);
}
if (sgp != SGP_WRITE &&
((loff_t) index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) {
entry = ERR_PTR(-EINVAL);
break;
}
if (info->next_index <= index)
info->next_index = index + 1;
}
if (page) {
/* another task gave its page, or truncated the file */
shmem_free_blocks(inode, 1);
shmem_dir_free(page);
}
if (info->next_index <= index && !IS_ERR(entry))
info->next_index = index + 1;
return entry;
}
/**
* shmem_free_swp - free some swap entries in a directory
* @dir: pointer to the directory
* @edir: pointer after last entry of the directory
* @punch_lock: pointer to spinlock when needed for the holepunch case
*/
static int shmem_free_swp(swp_entry_t *dir, swp_entry_t *edir,
spinlock_t *punch_lock)
{
spinlock_t *punch_unlock = NULL;
swp_entry_t *ptr;
int freed = 0;
for (ptr = dir; ptr < edir; ptr++) {
if (ptr->val) {
if (unlikely(punch_lock)) {
punch_unlock = punch_lock;
punch_lock = NULL;
spin_lock(punch_unlock);
if (!ptr->val)
continue;
}
free_swap_and_cache(*ptr);
*ptr = (swp_entry_t){0};
freed++;
}
}
if (punch_unlock)
spin_unlock(punch_unlock);
return freed;
}
static int shmem_map_and_free_swp(struct page *subdir, int offset,
int limit, struct page ***dir, spinlock_t *punch_lock)
{
swp_entry_t *ptr;
int freed = 0;
ptr = shmem_swp_map(subdir);
for (; offset < limit; offset += LATENCY_LIMIT) {
int size = limit - offset;
if (size > LATENCY_LIMIT)
size = LATENCY_LIMIT;
freed += shmem_free_swp(ptr+offset, ptr+offset+size,
punch_lock);
if (need_resched()) {
shmem_swp_unmap(ptr);
if (*dir) {
shmem_dir_unmap(*dir);
*dir = NULL;
}
cond_resched();
ptr = shmem_swp_map(subdir);
}
}
shmem_swp_unmap(ptr);
return freed;
}
static void shmem_free_pages(struct list_head *next)
{
struct page *page;
int freed = 0;
do {
page = container_of(next, struct page, lru);
next = next->next;
shmem_dir_free(page);
freed++;
if (freed >= LATENCY_LIMIT) {
cond_resched();
freed = 0;
}
} while (next);
}
static void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end)
{
struct shmem_inode_info *info = SHMEM_I(inode);
unsigned long idx;
unsigned long size;
unsigned long limit;
unsigned long stage;
unsigned long diroff;
struct page **dir;
struct page *topdir;
struct page *middir;
struct page *subdir;
swp_entry_t *ptr;
LIST_HEAD(pages_to_free);
long nr_pages_to_free = 0;
long nr_swaps_freed = 0;
int offset;
int freed;
int punch_hole;
spinlock_t *needs_lock;
spinlock_t *punch_lock;
unsigned long upper_limit;
inode->i_ctime = inode->i_mtime = CURRENT_TIME;
idx = (start + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
if (idx >= info->next_index)
return;
spin_lock(&info->lock);
info->flags |= SHMEM_TRUNCATE;
if (likely(end == (loff_t) -1)) {
limit = info->next_index;
upper_limit = SHMEM_MAX_INDEX;
info->next_index = idx;
needs_lock = NULL;
punch_hole = 0;
} else {
if (end + 1 >= inode->i_size) { /* we may free a little more */
limit = (inode->i_size + PAGE_CACHE_SIZE - 1) >>
PAGE_CACHE_SHIFT;
upper_limit = SHMEM_MAX_INDEX;
} else {
limit = (end + 1) >> PAGE_CACHE_SHIFT;
upper_limit = limit;
}
needs_lock = &info->lock;
punch_hole = 1;
}
topdir = info->i_indirect;
if (topdir && idx <= SHMEM_NR_DIRECT && !punch_hole) {
info->i_indirect = NULL;
nr_pages_to_free++;
list_add(&topdir->lru, &pages_to_free);
}
spin_unlock(&info->lock);
if (info->swapped && idx < SHMEM_NR_DIRECT) {
ptr = info->i_direct;
size = limit;
if (size > SHMEM_NR_DIRECT)
size = SHMEM_NR_DIRECT;
nr_swaps_freed = shmem_free_swp(ptr+idx, ptr+size, needs_lock);
}
/*
* If there are no indirect blocks or we are punching a hole
* below indirect blocks, nothing to be done.
*/
if (!topdir || limit <= SHMEM_NR_DIRECT)
goto done2;
/*
* The truncation case has already dropped info->lock, and we're safe
* because i_size and next_index have already been lowered, preventing
* access beyond. But in the punch_hole case, we still need to take
* the lock when updating the swap directory, because there might be
* racing accesses by shmem_getpage(SGP_CACHE), shmem_unuse_inode or
* shmem_writepage. However, whenever we find we can remove a whole
* directory page (not at the misaligned start or end of the range),
* we first NULLify its pointer in the level above, and then have no
* need to take the lock when updating its contents: needs_lock and
* punch_lock (either pointing to info->lock or NULL) manage this.
*/
upper_limit -= SHMEM_NR_DIRECT;
limit -= SHMEM_NR_DIRECT;
idx = (idx > SHMEM_NR_DIRECT)? (idx - SHMEM_NR_DIRECT): 0;
offset = idx % ENTRIES_PER_PAGE;
idx -= offset;
dir = shmem_dir_map(topdir);
stage = ENTRIES_PER_PAGEPAGE/2;
if (idx < ENTRIES_PER_PAGEPAGE/2) {
middir = topdir;
diroff = idx/ENTRIES_PER_PAGE;
} else {
dir += ENTRIES_PER_PAGE/2;
dir += (idx - ENTRIES_PER_PAGEPAGE/2)/ENTRIES_PER_PAGEPAGE;
while (stage <= idx)
stage += ENTRIES_PER_PAGEPAGE;
middir = *dir;
if (*dir) {
diroff = ((idx - ENTRIES_PER_PAGEPAGE/2) %
ENTRIES_PER_PAGEPAGE) / ENTRIES_PER_PAGE;
if (!diroff && !offset && upper_limit >= stage) {
if (needs_lock) {
spin_lock(needs_lock);
*dir = NULL;
spin_unlock(needs_lock);
needs_lock = NULL;
} else
*dir = NULL;
nr_pages_to_free++;
list_add(&middir->lru, &pages_to_free);
}
shmem_dir_unmap(dir);
dir = shmem_dir_map(middir);
} else {
diroff = 0;
offset = 0;
idx = stage;
}
}
for (; idx < limit; idx += ENTRIES_PER_PAGE, diroff++) {
if (unlikely(idx == stage)) {
shmem_dir_unmap(dir);
dir = shmem_dir_map(topdir) +
ENTRIES_PER_PAGE/2 + idx/ENTRIES_PER_PAGEPAGE;
while (!*dir) {
dir++;
idx += ENTRIES_PER_PAGEPAGE;
if (idx >= limit)
goto done1;
}
stage = idx + ENTRIES_PER_PAGEPAGE;
middir = *dir;
if (punch_hole)
needs_lock = &info->lock;
if (upper_limit >= stage) {
if (needs_lock) {
spin_lock(needs_lock);
*dir = NULL;
spin_unlock(needs_lock);
needs_lock = NULL;
} else
*dir = NULL;
nr_pages_to_free++;
list_add(&middir->lru, &pages_to_free);
}
shmem_dir_unmap(dir);
cond_resched();
dir = shmem_dir_map(middir);
diroff = 0;
}
punch_lock = needs_lock;
subdir = dir[diroff];
if (subdir && !offset && upper_limit-idx >= ENTRIES_PER_PAGE) {
if (needs_lock) {
spin_lock(needs_lock);
dir[diroff] = NULL;
spin_unlock(needs_lock);
punch_lock = NULL;
} else
dir[diroff] = NULL;
nr_pages_to_free++;
list_add(&subdir->lru, &pages_to_free);
}
if (subdir && page_private(subdir) /* has swap entries */) {
size = limit - idx;
if (size > ENTRIES_PER_PAGE)
size = ENTRIES_PER_PAGE;
freed = shmem_map_and_free_swp(subdir,
offset, size, &dir, punch_lock);
if (!dir)
dir = shmem_dir_map(middir);
nr_swaps_freed += freed;
if (offset || punch_lock) {
spin_lock(&info->lock);
set_page_private(subdir,
page_private(subdir) - freed);
spin_unlock(&info->lock);
} else
BUG_ON(page_private(subdir) != freed);
}
offset = 0;
}
done1:
shmem_dir_unmap(dir);
done2:
if (inode->i_mapping->nrpages && (info->flags & SHMEM_PAGEIN)) {
/*
* Call truncate_inode_pages again: racing shmem_unuse_inode
* may have swizzled a page in from swap since vmtruncate or
* generic_delete_inode did it, before we lowered next_index.
* Also, though shmem_getpage checks i_size before adding to
* cache, no recheck after: so fix the narrow window there too.
*
* Recalling truncate_inode_pages_range and unmap_mapping_range
* every time for punch_hole (which never got a chance to clear
* SHMEM_PAGEIN at the start of vmtruncate_range) is expensive,
* yet hardly ever necessary: try to optimize them out later.
*/
truncate_inode_pages_range(inode->i_mapping, start, end);
if (punch_hole)
unmap_mapping_range(inode->i_mapping, start,
end - start, 1);
}
spin_lock(&info->lock);
info->flags &= ~SHMEM_TRUNCATE;
info->swapped -= nr_swaps_freed;
if (nr_pages_to_free)
shmem_free_blocks(inode, nr_pages_to_free);
shmem_recalc_inode(inode);
spin_unlock(&info->lock);
/*
* Empty swap vector directory pages to be freed?
*/
if (!list_empty(&pages_to_free)) {
pages_to_free.prev->next = NULL;
shmem_free_pages(pages_to_free.next);
}
}
static void shmem_truncate(struct inode *inode)
{
shmem_truncate_range(inode, inode->i_size, (loff_t)-1);
}
static int shmem_notify_change(struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = dentry->d_inode;
struct page *page = NULL;
int error;
if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
if (attr->ia_size < inode->i_size) {
/*
* If truncating down to a partial page, then
* if that page is already allocated, hold it
* in memory until the truncation is over, so
* truncate_partial_page cannnot miss it were
* it assigned to swap.
*/
if (attr->ia_size & (PAGE_CACHE_SIZE-1)) {
(void) shmem_getpage(inode,
attr->ia_size>>PAGE_CACHE_SHIFT,
&page, SGP_READ, NULL);
if (page)
unlock_page(page);
}
/*
* Reset SHMEM_PAGEIN flag so that shmem_truncate can
* detect if any pages might have been added to cache
* after truncate_inode_pages. But we needn't bother
* if it's being fully truncated to zero-length: the
* nrpages check is efficient enough in that case.
*/
if (attr->ia_size) {
struct shmem_inode_info *info = SHMEM_I(inode);
spin_lock(&info->lock);
info->flags &= ~SHMEM_PAGEIN;
spin_unlock(&info->lock);
}
}
}
error = inode_change_ok(inode, attr);
if (!error)
error = inode_setattr(inode, attr);
#ifdef CONFIG_TMPFS_POSIX_ACL
if (!error && (attr->ia_valid & ATTR_MODE))
error = generic_acl_chmod(inode, &shmem_acl_ops);
#endif
if (page)
page_cache_release(page);
return error;
}
static void shmem_delete_inode(struct inode *inode)
{
struct shmem_inode_info *info = SHMEM_I(inode);
if (inode->i_op->truncate == shmem_truncate) {
truncate_inode_pages(inode->i_mapping, 0);
shmem_unacct_size(info->flags, inode->i_size);
inode->i_size = 0;
shmem_truncate(inode);
if (!list_empty(&info->swaplist)) {
mutex_lock(&shmem_swaplist_mutex);
list_del_init(&info->swaplist);
mutex_unlock(&shmem_swaplist_mutex);
}
}
BUG_ON(inode->i_blocks);
shmem_free_inode(inode->i_sb);
clear_inode(inode);
}
static inline int shmem_find_swp(swp_entry_t entry, swp_entry_t *dir, swp_entry_t *edir)
{
swp_entry_t *ptr;
for (ptr = dir; ptr < edir; ptr++) {
if (ptr->val == entry.val)
return ptr - dir;
}
return -1;
}
static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, struct page *page)
{
struct inode *inode;
unsigned long idx;
unsigned long size;
unsigned long limit;
unsigned long stage;
struct page **dir;
struct page *subdir;
swp_entry_t *ptr;
int offset;
int error;
idx = 0;
ptr = info->i_direct;
spin_lock(&info->lock);
if (!info->swapped) {
list_del_init(&info->swaplist);
goto lost2;
}
limit = info->next_index;
size = limit;
if (size > SHMEM_NR_DIRECT)
size = SHMEM_NR_DIRECT;
offset = shmem_find_swp(entry, ptr, ptr+size);
if (offset >= 0)
goto found;
if (!info->i_indirect)
goto lost2;
dir = shmem_dir_map(info->i_indirect);
stage = SHMEM_NR_DIRECT + ENTRIES_PER_PAGEPAGE/2;
for (idx = SHMEM_NR_DIRECT; idx < limit; idx += ENTRIES_PER_PAGE, dir++) {
if (unlikely(idx == stage)) {
shmem_dir_unmap(dir-1);
if (cond_resched_lock(&info->lock)) {
/* check it has not been truncated */
if (limit > info->next_index) {
limit = info->next_index;
if (idx >= limit)
goto lost2;
}
}
dir = shmem_dir_map(info->i_indirect) +
ENTRIES_PER_PAGE/2 + idx/ENTRIES_PER_PAGEPAGE;
while (!*dir) {
dir++;
idx += ENTRIES_PER_PAGEPAGE;
if (idx >= limit)
goto lost1;
}
stage = idx + ENTRIES_PER_PAGEPAGE;
subdir = *dir;
shmem_dir_unmap(dir);
dir = shmem_dir_map(subdir);
}
subdir = *dir;
if (subdir && page_private(subdir)) {
ptr = shmem_swp_map(subdir);
size = limit - idx;
if (size > ENTRIES_PER_PAGE)
size = ENTRIES_PER_PAGE;
offset = shmem_find_swp(entry, ptr, ptr+size);
shmem_swp_unmap(ptr);
if (offset >= 0) {
shmem_dir_unmap(dir);
goto found;
}
}
}
lost1:
shmem_dir_unmap(dir-1);
lost2:
spin_unlock(&info->lock);
return 0;
found:
idx += offset;
inode = igrab(&info->vfs_inode);
spin_unlock(&info->lock);
/*
* Move _head_ to start search for next from here.
* But be careful: shmem_delete_inode checks list_empty without taking
* mutex, and there's an instant in list_move_tail when info->swaplist
* would appear empty, if it were the only one on shmem_swaplist. We
* could avoid doing it if inode NULL; or use this minor optimization.
*/
if (shmem_swaplist.next != &info->swaplist)
list_move_tail(&shmem_swaplist, &info->swaplist);
mutex_unlock(&shmem_swaplist_mutex);
error = 1;
if (!inode)
goto out;
/*
* Charge page using GFP_KERNEL while we can wait.
* Charged back to the user(not to caller) when swap account is used.
* add_to_page_cache() will be called with GFP_NOWAIT.
*/
error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL);
if (error)
goto out;
error = radix_tree_preload(GFP_KERNEL);
if (error) {
mem_cgroup_uncharge_cache_page(page);
goto out;
}
error = 1;
spin_lock(&info->lock);
ptr = shmem_swp_entry(info, idx, NULL);
if (ptr && ptr->val == entry.val) {
error = add_to_page_cache_locked(page, inode->i_mapping,
idx, GFP_NOWAIT);
/* does mem_cgroup_uncharge_cache_page on error */
} else /* we must compensate for our precharge above */
mem_cgroup_uncharge_cache_page(page);
if (error == -EEXIST) {
struct page *filepage = find_get_page(inode->i_mapping, idx);
error = 1;
if (filepage) {
/*
* There might be a more uptodate page coming down
* from a stacked writepage: forget our swappage if so.
*/
if (PageUptodate(filepage))
error = 0;
page_cache_release(filepage);
}
}
if (!error) {
delete_from_swap_cache(page);
set_page_dirty(page);
info->flags |= SHMEM_PAGEIN;
shmem_swp_set(info, ptr, 0);
swap_free(entry);
error = 1; /* not an error, but entry was found */
}
if (ptr)
shmem_swp_unmap(ptr);
spin_unlock(&info->lock);
radix_tree_preload_end();
out:
unlock_page(page);
page_cache_release(page);
iput(inode); /* allows for NULL */
return error;