-
Notifications
You must be signed in to change notification settings - Fork 3
/
swapfile.c
1266 lines (1162 loc) · 31 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/slab.h>
#include <linux/smp_lock.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/swapctl.h>
#include <linux/blkdev.h> /* for blk_size */
#include <linux/vmalloc.h>
#include <linux/pagemap.h>
#include <linux/shm.h>
#include <asm/pgtable.h>
spinlock_t swaplock = SPIN_LOCK_UNLOCKED;
unsigned int nr_swapfiles;
int total_swap_pages;
static int swap_overflow;
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 ";
struct swap_list_t swap_list = {-1, -1};
struct swap_info_struct swap_info[MAX_SWAPFILES];
#define SWAPFILE_CLUSTER 256
static inline int scan_swap_map(struct swap_info_struct *si)
{
unsigned long offset;
/*
* 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 */
if (si->cluster_nr) {
while (si->cluster_next <= si->highest_bit) {
offset = si->cluster_next++;
if (si->swap_map[offset])
continue;
si->cluster_nr--;
goto got_page;
}
}
si->cluster_nr = SWAPFILE_CLUSTER;
/* try to find an empty (even not aligned) cluster. */
offset = si->lowest_bit;
check_next_cluster:
if (offset+SWAPFILE_CLUSTER-1 <= si->highest_bit)
{
int nr;
for (nr = offset; nr < offset+SWAPFILE_CLUSTER; nr++)
if (si->swap_map[nr])
{
offset = nr+1;
goto check_next_cluster;
}
/* We found a completly empty cluster, so start
* using it.
*/
goto got_page;
}
/* No luck, so now go finegrined as usual. -Andrea */
for (offset = si->lowest_bit; offset <= si->highest_bit ; offset++) {
if (si->swap_map[offset])
continue;
si->lowest_bit = offset+1;
got_page:
if (offset == si->lowest_bit)
si->lowest_bit++;
if (offset == si->highest_bit)
si->highest_bit--;
if (si->lowest_bit > si->highest_bit) {
si->lowest_bit = si->max;
si->highest_bit = 0;
}
si->swap_map[offset] = 1;
nr_swap_pages--;
si->cluster_next = offset+1;
return offset;
}
si->lowest_bit = si->max;
si->highest_bit = 0;
return 0;
}
swp_entry_t get_swap_page(void)
{
struct swap_info_struct * p;
unsigned long offset;
swp_entry_t entry;
int type, wrapped = 0;
entry.val = 0; /* Out of memory */
swap_list_lock();
type = swap_list.next;
if (type < 0)
goto out;
if (nr_swap_pages <= 0)
goto out;
while (1) {
p = &swap_info[type];
if ((p->flags & SWP_WRITEOK) == SWP_WRITEOK) {
swap_device_lock(p);
offset = scan_swap_map(p);
swap_device_unlock(p);
if (offset) {
entry = SWP_ENTRY(type,offset);
type = swap_info[type].next;
if (type < 0 ||
p->prio != swap_info[type].prio) {
swap_list.next = swap_list.head;
} else {
swap_list.next = type;
}
goto out;
}
}
type = p->next;
if (!wrapped) {
if (type < 0 || p->prio != swap_info[type].prio) {
type = swap_list.head;
wrapped = 1;
}
} else
if (type < 0)
goto out; /* out of swap space */
}
out:
swap_list_unlock();
return entry;
}
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;
swap_list_lock();
if (p->prio > swap_info[swap_list.next].prio)
swap_list.next = type;
swap_device_lock(p);
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 void swap_info_put(struct swap_info_struct * p)
{
swap_device_unlock(p);
swap_list_unlock();
}
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;
nr_swap_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));
swap_info_put(p);
}
}
/*
* Check if we're the only user of a swap page,
* when the page is locked.
*/
static int exclusive_swap_page(struct page *page)
{
int retval = 0;
struct swap_info_struct * p;
swp_entry_t entry;
entry.val = page->index;
p = swap_info_get(entry);
if (p) {
/* Is the only swap cache user the cache itself? */
if (p->swap_map[SWP_OFFSET(entry)] == 1) {
/* Recheck the page count with the pagecache lock held.. */
spin_lock(&pagecache_lock);
if (page_count(page) - !!page->buffers == 2)
retval = 1;
spin_unlock(&pagecache_lock);
}
swap_info_put(p);
}
return retval;
}
/*
* We can use this swap cache entry directly
* if there are no other references to it.
*
* Here "exclusive_swap_page()" does the real
* work, but we opportunistically check whether
* we need to get all the locks first..
*/
int can_share_swap_page(struct page *page)
{
int retval = 0;
if (!PageLocked(page))
BUG();
switch (page_count(page)) {
case 3:
if (!page->buffers)
break;
/* Fallthrough */
case 2:
if (!PageSwapCache(page))
break;
retval = exclusive_swap_page(page);
break;
case 1:
if (PageReserved(page))
break;
retval = 1;
}
return retval;
}
/*
* Work out if there are any other processes sharing this
* swap cache page. Free it if you can. Return success.
*/
int remove_exclusive_swap_page(struct page *page)
{
int retval;
struct swap_info_struct * p;
swp_entry_t entry;
if (!PageLocked(page))
BUG();
if (!PageSwapCache(page))
return 0;
if (page_count(page) - !!page->buffers != 2) /* 2: us + cache */
return 0;
entry.val = page->index;
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 pagecache lock held.. */
spin_lock(&pagecache_lock);
if (page_count(page) - !!page->buffers == 2) {
__delete_from_swap_cache(page);
SetPageDirty(page);
retval = 1;
}
spin_unlock(&pagecache_lock);
}
swap_info_put(p);
if (retval) {
block_flushpage(page, 0);
swap_free(entry);
page_cache_release(page);
}
return retval;
}
/*
* 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;
p = swap_info_get(entry);
if (p) {
if (swap_entry_free(p, SWP_OFFSET(entry)) == 1)
page = find_trylock_page(&swapper_space, entry.val);
swap_info_put(p);
}
if (page) {
page_cache_get(page);
/* Only cache user (+us), or swap space full? Free it! */
if (page_count(page) - !!page->buffers == 2 || vm_swap_full()) {
delete_from_swap_cache(page);
SetPageDirty(page);
}
UnlockPage(page);
page_cache_release(page);
}
}
/*
* The swap entry has been read in advance, and we return 1 to indicate
* that the page has been used or is no longer needed.
*
* Always set the resulting pte to be nowrite (the same as COW pages
* after one process has exited). We don't know just how many PTEs will
* share this swap entry, so be cautious and let do_wp_page work out
* what to do if a write is requested later.
*/
/* mmlist_lock and vma->vm_mm->page_table_lock are held */
static inline void unuse_pte(struct vm_area_struct * vma, unsigned long address,
pte_t *dir, swp_entry_t entry, struct page* page)
{
pte_t pte = *dir;
if (likely(pte_to_swp_entry(pte).val != entry.val))
return;
if (unlikely(pte_none(pte) || pte_present(pte)))
return;
get_page(page);
set_pte(dir, pte_mkold(mk_pte(page, vma->vm_page_prot)));
swap_free(entry);
++vma->vm_mm->rss;
}
/* mmlist_lock and vma->vm_mm->page_table_lock are held */
static inline void unuse_pmd(struct vm_area_struct * vma, pmd_t *dir,
unsigned long address, unsigned long size, unsigned long offset,
swp_entry_t entry, struct page* page)
{
pte_t * pte;
unsigned long end;
if (pmd_none(*dir))
return;
if (pmd_bad(*dir)) {
pmd_ERROR(*dir);
pmd_clear(dir);
return;
}
pte = pte_offset(dir, address);
offset += address & PMD_MASK;
address &= ~PMD_MASK;
end = address + size;
if (end > PMD_SIZE)
end = PMD_SIZE;
do {
unuse_pte(vma, offset+address-vma->vm_start, pte, entry, page);
address += PAGE_SIZE;
pte++;
} while (address && (address < end));
}
/* mmlist_lock and vma->vm_mm->page_table_lock are held */
static inline void unuse_pgd(struct vm_area_struct * vma, pgd_t *dir,
unsigned long address, unsigned long size,
swp_entry_t entry, struct page* page)
{
pmd_t * pmd;
unsigned long offset, end;
if (pgd_none(*dir))
return;
if (pgd_bad(*dir)) {
pgd_ERROR(*dir);
pgd_clear(dir);
return;
}
pmd = pmd_offset(dir, address);
offset = address & PGDIR_MASK;
address &= ~PGDIR_MASK;
end = address + size;
if (end > PGDIR_SIZE)
end = PGDIR_SIZE;
if (address >= end)
BUG();
do {
unuse_pmd(vma, pmd, address, end - address, offset, entry,
page);
address = (address + PMD_SIZE) & PMD_MASK;
pmd++;
} while (address && (address < end));
}
/* mmlist_lock and vma->vm_mm->page_table_lock are held */
static void unuse_vma(struct vm_area_struct * vma, pgd_t *pgdir,
swp_entry_t entry, struct page* page)
{
unsigned long start = vma->vm_start, end = vma->vm_end;
if (start >= end)
BUG();
do {
unuse_pgd(vma, pgdir, start, end - start, entry, page);
start = (start + PGDIR_SIZE) & PGDIR_MASK;
pgdir++;
} while (start && (start < end));
}
static void unuse_process(struct mm_struct * mm,
swp_entry_t entry, struct page* page)
{
struct vm_area_struct* vma;
/*
* Go through process' page directory.
*/
spin_lock(&mm->page_table_lock);
for (vma = mm->mmap; vma; vma = vma->vm_next) {
pgd_t * pgd = pgd_offset(mm, vma->vm_start);
unuse_vma(vma, pgd, entry, page);
}
spin_unlock(&mm->page_table_lock);
return;
}
/*
* Scan swap_map from current position to next entry still in use.
* Recycle to start on reaching the end, returning 0 when empty.
*/
static int find_next_to_unuse(struct swap_info_struct *si, int prev)
{
int max = si->max;
int i = prev;
int count;
/*
* No need for swap_device_lock(si) 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_list_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;
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 (now preserved by swap_out()),
* which clusters forked address spaces together, most recent
* child immediately after parent. If we race with dup_mmap(),
* we very much want to resolve parent before child, otherwise
* we may miss some entries: using last mm would invert that.
*/
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:
* mmput() removes mm from mmlist before exit_mmap() and its
* zap_page_range(). That's not too bad, those entries are
* on their way out, and handled faster there than here.
* do_munmap() behaves similarly, taking the range out of mm's
* vma list before zap_page_range(). But unfortunately, when
* unmapping a part of a vma, it takes the whole out first,
* then reinserts what's left after (might even reschedule if
* open() method called) - so swap entries may be invisible
* to swapoff for a while, then reappear - but that is rare.
*/
while ((i = find_next_to_unuse(si, i))) {
/*
* 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);
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" 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(page);
lock_page(page);
/*
* Remove all references to entry, without blocking.
* 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) {
flush_page_to_ram(page);
if (start_mm == &init_mm)
shmem = shmem_unuse(entry, page);
else
unuse_process(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 *mm;
spin_lock(&mmlist_lock);
while (*swap_map > 1 &&
(p = p->next) != &start_mm->mmlist) {
mm = list_entry(p, struct mm_struct, mmlist);
swcount = *swap_map;
if (mm == &init_mm) {
set_start_mm = 1;
spin_unlock(&mmlist_lock);
shmem = shmem_unuse(entry, page);
spin_lock(&mmlist_lock);
} else
unuse_process(mm, entry, page);
if (set_start_mm && *swap_map < swcount) {
new_start_mm = mm;
set_start_mm = 0;
}
}
atomic_inc(&new_start_mm->mm_users);
spin_unlock(&mmlist_lock);
mmput(start_mm);
start_mm = new_start_mm;
}
/*
* 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) {
swap_list_lock();
swap_device_lock(si);
nr_swap_pages++;
*swap_map = 1;
swap_device_unlock(si);
swap_list_unlock();
reset_overflow = 1;
}
/*
* If a reference remains (rare), we would like to leave
* the page in the swap cache; but try_to_swap_out 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.
*
* Note shmem_unuse already deleted swappage from cache,
* unless corresponding filepage found already in cache:
* in which case it left swappage in cache, lowered its
* swap count to pass quickly through the loops above,
* and now we must reincrement count to try again later.
*/
if ((*swap_map > 1) && PageDirty(page) && PageSwapCache(page)) {
rw_swap_page(WRITE, page);
lock_page(page);
}
if (PageSwapCache(page)) {
if (shmem)
swap_duplicate(entry);
else
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 try_to_swap_out will preserve it.
*/
SetPageDirty(page);
UnlockPage(page);
page_cache_release(page);
/*
* Make sure that we aren't completely killing
* interactive performance. Interruptible check on
* signal_pending() would be nice, but changes the spec?
*/
if (current->need_resched)
schedule();
}
mmput(start_mm);
if (reset_overflow) {
printk(KERN_WARNING "swapoff: cleared swap entry overflow\n");
swap_overflow = 0;
}
return retval;
}
asmlinkage long sys_swapoff(const char * specialfile)
{
struct swap_info_struct * p = NULL;
unsigned short *swap_map;
struct nameidata nd;
int i, type, prev;
int err;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
err = user_path_walk(specialfile, &nd);
if (err)
goto out;
lock_kernel();
prev = -1;
swap_list_lock();
for (type = swap_list.head; type >= 0; type = swap_info[type].next) {
p = swap_info + type;
if ((p->flags & SWP_WRITEOK) == SWP_WRITEOK) {
if (p->swap_file == nd.dentry)
break;
}
prev = type;
}
err = -EINVAL;
if (type < 0) {
swap_list_unlock();
goto out_dput;
}
if (prev < 0) {
swap_list.head = p->next;
} else {
swap_info[prev].next = p->next;
}
if (type == swap_list.next) {
/* just pick something that's safe... */
swap_list.next = swap_list.head;
}
nr_swap_pages -= p->pages;
total_swap_pages -= p->pages;
p->flags = SWP_USED;
swap_list_unlock();
unlock_kernel();
err = try_to_unuse(type);
lock_kernel();
if (err) {
/* re-insert swap space back into swap_list */
swap_list_lock();
for (prev = -1, i = swap_list.head; i >= 0; prev = i, i = swap_info[i].next)
if (p->prio >= swap_info[i].prio)
break;
p->next = i;
if (prev < 0)
swap_list.head = swap_list.next = p - swap_info;
else
swap_info[prev].next = p - swap_info;
nr_swap_pages += p->pages;
total_swap_pages += p->pages;
p->flags = SWP_WRITEOK;
swap_list_unlock();
goto out_dput;
}
if (p->swap_device)
blkdev_put(p->swap_file->d_inode->i_bdev, BDEV_SWAP);
path_release(&nd);
swap_list_lock();
swap_device_lock(p);
nd.mnt = p->swap_vfsmnt;
nd.dentry = p->swap_file;
p->swap_vfsmnt = NULL;
p->swap_file = NULL;
p->swap_device = 0;
p->max = 0;
swap_map = p->swap_map;
p->swap_map = NULL;
p->flags = 0;
swap_device_unlock(p);
swap_list_unlock();
vfree(swap_map);
err = 0;
out_dput:
unlock_kernel();
path_release(&nd);
out:
return err;
}
int get_swaparea_info(char *buf)
{
char * page = (char *) __get_free_page(GFP_KERNEL);
struct swap_info_struct *ptr = swap_info;
int i, j, len = 0, usedswap;
if (!page)
return -ENOMEM;
len += sprintf(buf, "Filename\t\t\tType\t\tSize\tUsed\tPriority\n");
for (i = 0 ; i < nr_swapfiles ; i++, ptr++) {
if ((ptr->flags & SWP_USED) && ptr->swap_map) {
char * path = d_path(ptr->swap_file, ptr->swap_vfsmnt,
page, PAGE_SIZE);
len += sprintf(buf + len, "%-31s ", path);
if (!ptr->swap_device)
len += sprintf(buf + len, "file\t\t");
else
len += sprintf(buf + len, "partition\t");
usedswap = 0;
for (j = 0; j < ptr->max; ++j)
switch (ptr->swap_map[j]) {
case SWAP_MAP_BAD:
case 0:
continue;
default:
usedswap++;
}
len += sprintf(buf + len, "%d\t%d\t%d\n", ptr->pages << (PAGE_SHIFT - 10),
usedswap << (PAGE_SHIFT - 10), ptr->prio);
}
}
free_page((unsigned long) page);
return len;
}
int is_swap_partition(kdev_t dev) {
struct swap_info_struct *ptr = swap_info;
int i;
for (i = 0 ; i < nr_swapfiles ; i++, ptr++) {
if (ptr->flags & SWP_USED)
if (ptr->swap_device == dev)
return 1;
}
return 0;
}
/*
* Written 01/25/92 by Simmule Turner, heavily changed by Linus.
*
* The swapon system call
*/
asmlinkage long sys_swapon(const char * specialfile, int swap_flags)
{
struct swap_info_struct * p;
struct nameidata nd;
struct inode * swap_inode;
unsigned int type;
int i, j, prev;
int error;
static int least_priority = 0;
union swap_header *swap_header = 0;
int swap_header_version;
int nr_good_pages = 0;
unsigned long maxpages = 1;
int swapfilesize;
struct block_device *bdev = NULL;
unsigned short *swap_map;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
lock_kernel();
swap_list_lock();
p = swap_info;
for (type = 0 ; type < nr_swapfiles ; type++,p++)
if (!(p->flags & SWP_USED))
break;
error = -EPERM;
if (type >= MAX_SWAPFILES) {
swap_list_unlock();
goto out;
}
if (type >= nr_swapfiles)
nr_swapfiles = type+1;
p->flags = SWP_USED;
p->swap_file = NULL;
p->swap_vfsmnt = NULL;
p->swap_device = 0;
p->swap_map = NULL;
p->lowest_bit = 0;
p->highest_bit = 0;
p->cluster_nr = 0;
p->sdev_lock = SPIN_LOCK_UNLOCKED;
p->next = -1;
if (swap_flags & SWAP_FLAG_PREFER) {
p->prio =
(swap_flags & SWAP_FLAG_PRIO_MASK)>>SWAP_FLAG_PRIO_SHIFT;
} else {
p->prio = --least_priority;
}
swap_list_unlock();
error = user_path_walk(specialfile, &nd);
if (error)
goto bad_swap_2;
p->swap_file = nd.dentry;
p->swap_vfsmnt = nd.mnt;
swap_inode = nd.dentry->d_inode;
error = -EINVAL;
if (S_ISBLK(swap_inode->i_mode)) {
kdev_t dev = swap_inode->i_rdev;
struct block_device_operations *bdops;
devfs_handle_t de;
if (is_mounted(dev)) {
error = -EBUSY;
goto bad_swap_2;
}
p->swap_device = dev;
set_blocksize(dev, PAGE_SIZE);
bd_acquire(swap_inode);
bdev = swap_inode->i_bdev;
de = devfs_get_handle_from_inode(swap_inode);
bdops = devfs_get_ops(de); /* Increments module use count */
if (bdops) bdev->bd_op = bdops;
error = blkdev_get(bdev, FMODE_READ|FMODE_WRITE, 0, BDEV_SWAP);
devfs_put_ops(de);/*Decrement module use count now we're safe*/
if (error)
goto bad_swap_2;
set_blocksize(dev, PAGE_SIZE);
error = -ENODEV;
if (!dev || (blk_size[MAJOR(dev)] &&
!blk_size[MAJOR(dev)][MINOR(dev)]))
goto bad_swap;
swapfilesize = 0;
if (blk_size[MAJOR(dev)])
swapfilesize = blk_size[MAJOR(dev)][MINOR(dev)]
>> (PAGE_SHIFT - 10);
} else if (S_ISREG(swap_inode->i_mode))
swapfilesize = swap_inode->i_size >> PAGE_SHIFT;
else
goto bad_swap;
error = -EBUSY;
for (i = 0 ; i < nr_swapfiles ; i++) {
struct swap_info_struct *q = &swap_info[i];
if (i == type || !q->swap_file)
continue;
if (swap_inode->i_mapping == q->swap_file->d_inode->i_mapping)
goto bad_swap;
}
swap_header = (void *) __get_free_page(GFP_USER);
if (!swap_header) {
printk("Unable to start swapping: out of memory :-)\n");
error = -ENOMEM;
goto bad_swap;
}
lock_page(virt_to_page(swap_header));
rw_swap_page_nolock(READ, SWP_ENTRY(type,0), (char *) swap_header);
if (!memcmp("SWAP-SPACE",swap_header->magic.magic,10))
swap_header_version = 1;
else if (!memcmp("SWAPSPACE2",swap_header->magic.magic,10))
swap_header_version = 2;
else {
printk("Unable to find swap-space signature\n");
error = -EINVAL;
goto bad_swap;
}
switch (swap_header_version) {
case 1:
memset(((char *) swap_header)+PAGE_SIZE-10,0,10);
j = 0;
p->lowest_bit = 0;
p->highest_bit = 0;
for (i = 1 ; i < 8*PAGE_SIZE ; i++) {
if (test_bit(i,(char *) swap_header)) {
if (!p->lowest_bit)