forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
swapfile.c
1879 lines (1691 loc) · 46 KB
/
swapfile.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
/*
* linux/mm/swapfile.c
*
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
* Swap reorganised 29.12.95, Stephen Tweedie
*/
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/mman.h>
#include <linux/slab.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/vmalloc.h>
#include <linux/pagemap.h>
#include <linux/namei.h>
#include <linux/shm.h>
#include <linux/blkdev.h>
#include <linux/writeback.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/rmap.h>
#include <linux/security.h>
#include <linux/backing-dev.h>
#include <linux/mutex.h>
#include <linux/capability.h>
#include <linux/syscalls.h>
#include <linux/memcontrol.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <linux/swapops.h>
static DEFINE_SPINLOCK(swap_lock);
static unsigned int nr_swapfiles;
long total_swap_pages;
static int swap_overflow;
static int least_priority;
static const char Bad_file[] = "Bad swap file entry ";
static const char Unused_file[] = "Unused swap file entry ";
static const char Bad_offset[] = "Bad swap offset entry ";
static const char Unused_offset[] = "Unused swap offset entry ";
static struct swap_list_t swap_list = {-1, -1};
static struct swap_info_struct swap_info[MAX_SWAPFILES];
static DEFINE_MUTEX(swapon_mutex);
/*
* We need this because the bdev->unplug_fn can sleep and we cannot
* hold swap_lock while calling the unplug_fn. And swap_lock
* cannot be turned into a mutex.
*/
static DECLARE_RWSEM(swap_unplug_sem);
void swap_unplug_io_fn(struct backing_dev_info *unused_bdi, struct page *page)
{
swp_entry_t entry;
down_read(&swap_unplug_sem);
entry.val = page_private(page);
if (PageSwapCache(page)) {
struct block_device *bdev = swap_info[swp_type(entry)].bdev;
struct backing_dev_info *bdi;
/*
* If the page is removed from swapcache from under us (with a
* racy try_to_unuse/swapoff) we need an additional reference
* count to avoid reading garbage from page_private(page) above.
* If the WARN_ON triggers during a swapoff it maybe the race
* condition and it's harmless. However if it triggers without
* swapoff it signals a problem.
*/
WARN_ON(page_count(page) <= 1);
bdi = bdev->bd_inode->i_mapping->backing_dev_info;
blk_run_backing_dev(bdi, page);
}
up_read(&swap_unplug_sem);
}
#define SWAPFILE_CLUSTER 256
#define LATENCY_LIMIT 256
static inline unsigned long scan_swap_map(struct swap_info_struct *si)
{
unsigned long offset, last_in_cluster;
int latency_ration = LATENCY_LIMIT;
/*
* We try to cluster swap pages by allocating them sequentially
* in swap. Once we've allocated SWAPFILE_CLUSTER pages this
* way, however, we resort to first-free allocation, starting
* a new cluster. This prevents us from scattering swap pages
* all over the entire swap partition, so that we reduce
* overall disk seek times between swap pages. -- sct
* But we do now try to find an empty cluster. -Andrea
*/
si->flags += SWP_SCANNING;
if (unlikely(!si->cluster_nr)) {
si->cluster_nr = SWAPFILE_CLUSTER - 1;
if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER)
goto lowest;
spin_unlock(&swap_lock);
offset = si->lowest_bit;
last_in_cluster = offset + SWAPFILE_CLUSTER - 1;
/* Locate the first empty (unaligned) cluster */
for (; last_in_cluster <= si->highest_bit; offset++) {
if (si->swap_map[offset])
last_in_cluster = offset + SWAPFILE_CLUSTER;
else if (offset == last_in_cluster) {
spin_lock(&swap_lock);
si->cluster_next = offset-SWAPFILE_CLUSTER+1;
goto cluster;
}
if (unlikely(--latency_ration < 0)) {
cond_resched();
latency_ration = LATENCY_LIMIT;
}
}
spin_lock(&swap_lock);
goto lowest;
}
si->cluster_nr--;
cluster:
offset = si->cluster_next;
if (offset > si->highest_bit)
lowest: offset = si->lowest_bit;
checks: if (!(si->flags & SWP_WRITEOK))
goto no_page;
if (!si->highest_bit)
goto no_page;
if (!si->swap_map[offset]) {
if (offset == si->lowest_bit)
si->lowest_bit++;
if (offset == si->highest_bit)
si->highest_bit--;
si->inuse_pages++;
if (si->inuse_pages == si->pages) {
si->lowest_bit = si->max;
si->highest_bit = 0;
}
si->swap_map[offset] = 1;
si->cluster_next = offset + 1;
si->flags -= SWP_SCANNING;
return offset;
}
spin_unlock(&swap_lock);
while (++offset <= si->highest_bit) {
if (!si->swap_map[offset]) {
spin_lock(&swap_lock);
goto checks;
}
if (unlikely(--latency_ration < 0)) {
cond_resched();
latency_ration = LATENCY_LIMIT;
}
}
spin_lock(&swap_lock);
goto lowest;
no_page:
si->flags -= SWP_SCANNING;
return 0;
}
swp_entry_t get_swap_page(void)
{
struct swap_info_struct *si;
pgoff_t offset;
int type, next;
int wrapped = 0;
spin_lock(&swap_lock);
if (nr_swap_pages <= 0)
goto noswap;
nr_swap_pages--;
for (type = swap_list.next; type >= 0 && wrapped < 2; type = next) {
si = swap_info + type;
next = si->next;
if (next < 0 ||
(!wrapped && si->prio != swap_info[next].prio)) {
next = swap_list.head;
wrapped++;
}
if (!si->highest_bit)
continue;
if (!(si->flags & SWP_WRITEOK))
continue;
swap_list.next = next;
offset = scan_swap_map(si);
if (offset) {
spin_unlock(&swap_lock);
return swp_entry(type, offset);
}
next = swap_list.next;
}
nr_swap_pages++;
noswap:
spin_unlock(&swap_lock);
return (swp_entry_t) {0};
}
swp_entry_t get_swap_page_of_type(int type)
{
struct swap_info_struct *si;
pgoff_t offset;
spin_lock(&swap_lock);
si = swap_info + type;
if (si->flags & SWP_WRITEOK) {
nr_swap_pages--;
offset = scan_swap_map(si);
if (offset) {
spin_unlock(&swap_lock);
return swp_entry(type, offset);
}
nr_swap_pages++;
}
spin_unlock(&swap_lock);
return (swp_entry_t) {0};
}
static struct swap_info_struct * swap_info_get(swp_entry_t entry)
{
struct swap_info_struct * p;
unsigned long offset, type;
if (!entry.val)
goto out;
type = swp_type(entry);
if (type >= nr_swapfiles)
goto bad_nofile;
p = & swap_info[type];
if (!(p->flags & SWP_USED))
goto bad_device;
offset = swp_offset(entry);
if (offset >= p->max)
goto bad_offset;
if (!p->swap_map[offset])
goto bad_free;
spin_lock(&swap_lock);
return p;
bad_free:
printk(KERN_ERR "swap_free: %s%08lx\n", Unused_offset, entry.val);
goto out;
bad_offset:
printk(KERN_ERR "swap_free: %s%08lx\n", Bad_offset, entry.val);
goto out;
bad_device:
printk(KERN_ERR "swap_free: %s%08lx\n", Unused_file, entry.val);
goto out;
bad_nofile:
printk(KERN_ERR "swap_free: %s%08lx\n", Bad_file, entry.val);
out:
return NULL;
}
static int swap_entry_free(struct swap_info_struct *p, unsigned long offset)
{
int count = p->swap_map[offset];
if (count < SWAP_MAP_MAX) {
count--;
p->swap_map[offset] = count;
if (!count) {
if (offset < p->lowest_bit)
p->lowest_bit = offset;
if (offset > p->highest_bit)
p->highest_bit = offset;
if (p->prio > swap_info[swap_list.next].prio)
swap_list.next = p - swap_info;
nr_swap_pages++;
p->inuse_pages--;
}
}
return count;
}
/*
* Caller has made sure that the swapdevice corresponding to entry
* is still around or has not been recycled.
*/
void swap_free(swp_entry_t entry)
{
struct swap_info_struct * p;
p = swap_info_get(entry);
if (p) {
swap_entry_free(p, swp_offset(entry));
spin_unlock(&swap_lock);
}
}
/*
* How many references to page are currently swapped out?
*/
static inline int page_swapcount(struct page *page)
{
int count = 0;
struct swap_info_struct *p;
swp_entry_t entry;
entry.val = page_private(page);
p = swap_info_get(entry);
if (p) {
/* Subtract the 1 for the swap cache itself */
count = p->swap_map[swp_offset(entry)] - 1;
spin_unlock(&swap_lock);
}
return count;
}
/*
* We can use this swap cache entry directly
* if there are no other references to it.
*/
int can_share_swap_page(struct page *page)
{
int count;
BUG_ON(!PageLocked(page));
count = page_mapcount(page);
if (count <= 1 && PageSwapCache(page))
count += page_swapcount(page);
return count == 1;
}
/*
* Work out if there are any other processes sharing this
* swap cache page. Free it if you can. Return success.
*/
static int remove_exclusive_swap_page_count(struct page *page, int count)
{
int retval;
struct swap_info_struct * p;
swp_entry_t entry;
BUG_ON(PagePrivate(page));
BUG_ON(!PageLocked(page));
if (!PageSwapCache(page))
return 0;
if (PageWriteback(page))
return 0;
if (page_count(page) != count) /* us + cache + ptes */
return 0;
entry.val = page_private(page);
p = swap_info_get(entry);
if (!p)
return 0;
/* Is the only swap cache user the cache itself? */
retval = 0;
if (p->swap_map[swp_offset(entry)] == 1) {
/* Recheck the page count with the swapcache lock held.. */
spin_lock_irq(&swapper_space.tree_lock);
if ((page_count(page) == count) && !PageWriteback(page)) {
__delete_from_swap_cache(page);
SetPageDirty(page);
retval = 1;
}
spin_unlock_irq(&swapper_space.tree_lock);
}
spin_unlock(&swap_lock);
if (retval) {
swap_free(entry);
page_cache_release(page);
}
return retval;
}
/*
* Most of the time the page should have two references: one for the
* process and one for the swap cache.
*/
int remove_exclusive_swap_page(struct page *page)
{
return remove_exclusive_swap_page_count(page, 2);
}
/*
* The pageout code holds an extra reference to the page. That raises
* the reference count to test for to 2 for a page that is only in the
* swap cache plus 1 for each process that maps the page.
*/
int remove_exclusive_swap_page_ref(struct page *page)
{
return remove_exclusive_swap_page_count(page, 2 + page_mapcount(page));
}
/*
* Free the swap entry like above, but also try to
* free the page cache entry if it is the last user.
*/
void free_swap_and_cache(swp_entry_t entry)
{
struct swap_info_struct * p;
struct page *page = NULL;
if (is_migration_entry(entry))
return;
p = swap_info_get(entry);
if (p) {
if (swap_entry_free(p, swp_offset(entry)) == 1) {
page = find_get_page(&swapper_space, entry.val);
if (page && !trylock_page(page)) {
page_cache_release(page);
page = NULL;
}
}
spin_unlock(&swap_lock);
}
if (page) {
int one_user;
BUG_ON(PagePrivate(page));
one_user = (page_count(page) == 2);
/* Only cache user (+us), or swap space full? Free it! */
/* Also recheck PageSwapCache after page is locked (above) */
if (PageSwapCache(page) && !PageWriteback(page) &&
(one_user || vm_swap_full())) {
delete_from_swap_cache(page);
SetPageDirty(page);
}
unlock_page(page);
page_cache_release(page);
}
}
#ifdef CONFIG_HIBERNATION
/*
* Find the swap type that corresponds to given device (if any).
*
* @offset - number of the PAGE_SIZE-sized block of the device, starting
* from 0, in which the swap header is expected to be located.
*
* This is needed for the suspend to disk (aka swsusp).
*/
int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p)
{
struct block_device *bdev = NULL;
int i;
if (device)
bdev = bdget(device);
spin_lock(&swap_lock);
for (i = 0; i < nr_swapfiles; i++) {
struct swap_info_struct *sis = swap_info + i;
if (!(sis->flags & SWP_WRITEOK))
continue;
if (!bdev) {
if (bdev_p)
*bdev_p = sis->bdev;
spin_unlock(&swap_lock);
return i;
}
if (bdev == sis->bdev) {
struct swap_extent *se;
se = list_entry(sis->extent_list.next,
struct swap_extent, list);
if (se->start_block == offset) {
if (bdev_p)
*bdev_p = sis->bdev;
spin_unlock(&swap_lock);
bdput(bdev);
return i;
}
}
}
spin_unlock(&swap_lock);
if (bdev)
bdput(bdev);
return -ENODEV;
}
/*
* Return either the total number of swap pages of given type, or the number
* of free pages of that type (depending on @free)
*
* This is needed for software suspend
*/
unsigned int count_swap_pages(int type, int free)
{
unsigned int n = 0;
if (type < nr_swapfiles) {
spin_lock(&swap_lock);
if (swap_info[type].flags & SWP_WRITEOK) {
n = swap_info[type].pages;
if (free)
n -= swap_info[type].inuse_pages;
}
spin_unlock(&swap_lock);
}
return n;
}
#endif
/*
* No need to decide whether this PTE shares the swap entry with others,
* just let do_wp_page work it out if a write is requested later - to
* force COW, vm_page_prot omits write permission from any private vma.
*/
static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, swp_entry_t entry, struct page *page)
{
spinlock_t *ptl;
pte_t *pte;
int ret = 1;
if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL))
ret = -ENOMEM;
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) {
if (ret > 0)
mem_cgroup_uncharge_page(page);
ret = 0;
goto out;
}
inc_mm_counter(vma->vm_mm, anon_rss);
get_page(page);
set_pte_at(vma->vm_mm, addr, pte,
pte_mkold(mk_pte(page, vma->vm_page_prot)));
page_add_anon_rmap(page, vma, addr);
swap_free(entry);
/*
* Move the page to the active list so it is not
* immediately swapped out again after swapon.
*/
activate_page(page);
out:
pte_unmap_unlock(pte, ptl);
return ret;
}
static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end,
swp_entry_t entry, struct page *page)
{
pte_t swp_pte = swp_entry_to_pte(entry);
pte_t *pte;
int ret = 0;
/*
* We don't actually need pte lock while scanning for swp_pte: since
* we hold page lock and mmap_sem, swp_pte cannot be inserted into the
* page table while we're scanning; though it could get zapped, and on
* some architectures (e.g. x86_32 with PAE) we might catch a glimpse
* of unmatched parts which look like swp_pte, so unuse_pte must
* recheck under pte lock. Scanning without pte lock lets it be
* preemptible whenever CONFIG_PREEMPT but not CONFIG_HIGHPTE.
*/
pte = pte_offset_map(pmd, addr);
do {
/*
* swapoff spends a _lot_ of time in this loop!
* Test inline before going to call unuse_pte.
*/
if (unlikely(pte_same(*pte, swp_pte))) {
pte_unmap(pte);
ret = unuse_pte(vma, pmd, addr, entry, page);
if (ret)
goto out;
pte = pte_offset_map(pmd, addr);
}
} while (pte++, addr += PAGE_SIZE, addr != end);
pte_unmap(pte - 1);
out:
return ret;
}
static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
unsigned long addr, unsigned long end,
swp_entry_t entry, struct page *page)
{
pmd_t *pmd;
unsigned long next;
int ret;
pmd = pmd_offset(pud, addr);
do {
next = pmd_addr_end(addr, end);
if (pmd_none_or_clear_bad(pmd))
continue;
ret = unuse_pte_range(vma, pmd, addr, next, entry, page);
if (ret)
return ret;
} while (pmd++, addr = next, addr != end);
return 0;
}
static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
unsigned long addr, unsigned long end,
swp_entry_t entry, struct page *page)
{
pud_t *pud;
unsigned long next;
int ret;
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
continue;
ret = unuse_pmd_range(vma, pud, addr, next, entry, page);
if (ret)
return ret;
} while (pud++, addr = next, addr != end);
return 0;
}
static int unuse_vma(struct vm_area_struct *vma,
swp_entry_t entry, struct page *page)
{
pgd_t *pgd;
unsigned long addr, end, next;
int ret;
if (page->mapping) {
addr = page_address_in_vma(page, vma);
if (addr == -EFAULT)
return 0;
else
end = addr + PAGE_SIZE;
} else {
addr = vma->vm_start;
end = vma->vm_end;
}
pgd = pgd_offset(vma->vm_mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
ret = unuse_pud_range(vma, pgd, addr, next, entry, page);
if (ret)
return ret;
} while (pgd++, addr = next, addr != end);
return 0;
}
static int unuse_mm(struct mm_struct *mm,
swp_entry_t entry, struct page *page)
{
struct vm_area_struct *vma;
int ret = 0;
if (!down_read_trylock(&mm->mmap_sem)) {
/*
* Activate page so shrink_inactive_list is unlikely to unmap
* its ptes while lock is dropped, so swapoff can make progress.
*/
activate_page(page);
unlock_page(page);
down_read(&mm->mmap_sem);
lock_page(page);
}
for (vma = mm->mmap; vma; vma = vma->vm_next) {
if (vma->anon_vma && (ret = unuse_vma(vma, entry, page)))
break;
}
up_read(&mm->mmap_sem);
return (ret < 0)? ret: 0;
}
/*
* Scan swap_map from current position to next entry still in use.
* Recycle to start on reaching the end, returning 0 when empty.
*/
static unsigned int find_next_to_unuse(struct swap_info_struct *si,
unsigned int prev)
{
unsigned int max = si->max;
unsigned int i = prev;
int count;
/*
* No need for swap_lock here: we're just looking
* for whether an entry is in use, not modifying it; false
* hits are okay, and sys_swapoff() has already prevented new
* allocations from this area (while holding swap_lock).
*/
for (;;) {
if (++i >= max) {
if (!prev) {
i = 0;
break;
}
/*
* No entries in use at top of swap_map,
* loop back to start and recheck there.
*/
max = prev + 1;
prev = 0;
i = 1;
}
count = si->swap_map[i];
if (count && count != SWAP_MAP_BAD)
break;
}
return i;
}
/*
* We completely avoid races by reading each swap page in advance,
* and then search for the process using it. All the necessary
* page table adjustments can then be made atomically.
*/
static int try_to_unuse(unsigned int type)
{
struct swap_info_struct * si = &swap_info[type];
struct mm_struct *start_mm;
unsigned short *swap_map;
unsigned short swcount;
struct page *page;
swp_entry_t entry;
unsigned int i = 0;
int retval = 0;
int reset_overflow = 0;
int shmem;
/*
* When searching mms for an entry, a good strategy is to
* start at the first mm we freed the previous entry from
* (though actually we don't notice whether we or coincidence
* freed the entry). Initialize this start_mm with a hold.
*
* A simpler strategy would be to start at the last mm we
* freed the previous entry from; but that would take less
* advantage of mmlist ordering, which clusters forked mms
* together, child after parent. If we race with dup_mmap(), we
* prefer to resolve parent before child, lest we miss entries
* duplicated after we scanned child: using last mm would invert
* that. Though it's only a serious concern when an overflowed
* swap count is reset from SWAP_MAP_MAX, preventing a rescan.
*/
start_mm = &init_mm;
atomic_inc(&init_mm.mm_users);
/*
* Keep on scanning until all entries have gone. Usually,
* one pass through swap_map is enough, but not necessarily:
* there are races when an instance of an entry might be missed.
*/
while ((i = find_next_to_unuse(si, i)) != 0) {
if (signal_pending(current)) {
retval = -EINTR;
break;
}
/*
* Get a page for the entry, using the existing swap
* cache page if there is one. Otherwise, get a clean
* page and read the swap into it.
*/
swap_map = &si->swap_map[i];
entry = swp_entry(type, i);
page = read_swap_cache_async(entry,
GFP_HIGHUSER_MOVABLE, NULL, 0);
if (!page) {
/*
* Either swap_duplicate() failed because entry
* has been freed independently, and will not be
* reused since sys_swapoff() already disabled
* allocation from here, or alloc_page() failed.
*/
if (!*swap_map)
continue;
retval = -ENOMEM;
break;
}
/*
* Don't hold on to start_mm if it looks like exiting.
*/
if (atomic_read(&start_mm->mm_users) == 1) {
mmput(start_mm);
start_mm = &init_mm;
atomic_inc(&init_mm.mm_users);
}
/*
* Wait for and lock page. When do_swap_page races with
* try_to_unuse, do_swap_page can handle the fault much
* faster than try_to_unuse can locate the entry. This
* apparently redundant "wait_on_page_locked" lets try_to_unuse
* defer to do_swap_page in such a case - in some tests,
* do_swap_page and try_to_unuse repeatedly compete.
*/
wait_on_page_locked(page);
wait_on_page_writeback(page);
lock_page(page);
wait_on_page_writeback(page);
/*
* Remove all references to entry.
* Whenever we reach init_mm, there's no address space
* to search, but use it as a reminder to search shmem.
*/
shmem = 0;
swcount = *swap_map;
if (swcount > 1) {
if (start_mm == &init_mm)
shmem = shmem_unuse(entry, page);
else
retval = unuse_mm(start_mm, entry, page);
}
if (*swap_map > 1) {
int set_start_mm = (*swap_map >= swcount);
struct list_head *p = &start_mm->mmlist;
struct mm_struct *new_start_mm = start_mm;
struct mm_struct *prev_mm = start_mm;
struct mm_struct *mm;
atomic_inc(&new_start_mm->mm_users);
atomic_inc(&prev_mm->mm_users);
spin_lock(&mmlist_lock);
while (*swap_map > 1 && !retval && !shmem &&
(p = p->next) != &start_mm->mmlist) {
mm = list_entry(p, struct mm_struct, mmlist);
if (!atomic_inc_not_zero(&mm->mm_users))
continue;
spin_unlock(&mmlist_lock);
mmput(prev_mm);
prev_mm = mm;
cond_resched();
swcount = *swap_map;
if (swcount <= 1)
;
else if (mm == &init_mm) {
set_start_mm = 1;
shmem = shmem_unuse(entry, page);
} else
retval = unuse_mm(mm, entry, page);
if (set_start_mm && *swap_map < swcount) {
mmput(new_start_mm);
atomic_inc(&mm->mm_users);
new_start_mm = mm;
set_start_mm = 0;
}
spin_lock(&mmlist_lock);
}
spin_unlock(&mmlist_lock);
mmput(prev_mm);
mmput(start_mm);
start_mm = new_start_mm;
}
if (shmem) {
/* page has already been unlocked and released */
if (shmem > 0)
continue;
retval = shmem;
break;
}
if (retval) {
unlock_page(page);
page_cache_release(page);
break;
}
/*
* How could swap count reach 0x7fff when the maximum
* pid is 0x7fff, and there's no way to repeat a swap
* page within an mm (except in shmem, where it's the
* shared object which takes the reference count)?
* We believe SWAP_MAP_MAX cannot occur in Linux 2.4.
*
* If that's wrong, then we should worry more about
* exit_mmap() and do_munmap() cases described above:
* we might be resetting SWAP_MAP_MAX too early here.
* We know "Undead"s can happen, they're okay, so don't
* report them; but do report if we reset SWAP_MAP_MAX.
*/
if (*swap_map == SWAP_MAP_MAX) {
spin_lock(&swap_lock);
*swap_map = 1;
spin_unlock(&swap_lock);
reset_overflow = 1;
}
/*
* If a reference remains (rare), we would like to leave
* the page in the swap cache; but try_to_unmap could
* then re-duplicate the entry once we drop page lock,
* so we might loop indefinitely; also, that page could
* not be swapped out to other storage meanwhile. So:
* delete from cache even if there's another reference,
* after ensuring that the data has been saved to disk -
* since if the reference remains (rarer), it will be
* read from disk into another page. Splitting into two
* pages would be incorrect if swap supported "shared
* private" pages, but they are handled by tmpfs files.
*/
if ((*swap_map > 1) && PageDirty(page) && PageSwapCache(page)) {
struct writeback_control wbc = {
.sync_mode = WB_SYNC_NONE,
};
swap_writepage(page, &wbc);
lock_page(page);
wait_on_page_writeback(page);
}
if (PageSwapCache(page))
delete_from_swap_cache(page);
/*
* So we could skip searching mms once swap count went
* to 1, we did not mark any present ptes as dirty: must
* mark page dirty so shrink_page_list will preserve it.
*/
SetPageDirty(page);
unlock_page(page);
page_cache_release(page);
/*
* Make sure that we aren't completely killing
* interactive performance.
*/
cond_resched();
}
mmput(start_mm);
if (reset_overflow) {
printk(KERN_WARNING "swapoff: cleared swap entry overflow\n");
swap_overflow = 0;
}
return retval;
}
/*
* After a successful try_to_unuse, if no swap is now in use, we know
* we can empty the mmlist. swap_lock must be held on entry and exit.
* Note that mmlist_lock nests inside swap_lock, and an mm must be
* added to the mmlist just after page_duplicate - before would be racy.
*/
static void drain_mmlist(void)
{
struct list_head *p, *next;
unsigned int i;
for (i = 0; i < nr_swapfiles; i++)
if (swap_info[i].inuse_pages)
return;
spin_lock(&mmlist_lock);
list_for_each_safe(p, next, &init_mm.mmlist)
list_del_init(p);
spin_unlock(&mmlist_lock);
}
/*
* Use this swapdev's extent info to locate the (PAGE_SIZE) block which
* corresponds to page offset `offset'.
*/
sector_t map_swap_page(struct swap_info_struct *sis, pgoff_t offset)
{
struct swap_extent *se = sis->curr_swap_extent;
struct swap_extent *start_se = se;
for ( ; ; ) {
struct list_head *lh;
if (se->start_page <= offset &&
offset < (se->start_page + se->nr_pages)) {
return se->start_block + (offset - se->start_page);
}
lh = se->list.next;
if (lh == &sis->extent_list)
lh = lh->next;
se = list_entry(lh, struct swap_extent, list);
sis->curr_swap_extent = se;