This repository was archived by the owner on Feb 9, 2023. It is now read-only.
forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 25
Expand file tree
/
Copy pathswapfile.c
More file actions
3740 lines (3281 loc) · 94.7 KB
/
swapfile.c
File metadata and controls
3740 lines (3281 loc) · 94.7 KB
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/sched/mm.h>
#include <linux/sched/task.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/shmem_fs.h>
#include <linux/blkdev.h>
#include <linux/random.h>
#include <linux/writeback.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/init.h>
#include <linux/ksm.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 <linux/poll.h>
#include <linux/oom.h>
#include <linux/frontswap.h>
#include <linux/swapfile.h>
#include <linux/export.h>
#include <linux/swap_slots.h>
#include <linux/sort.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <linux/swapops.h>
#include <linux/swap_cgroup.h>
static bool swap_count_continued(struct swap_info_struct *, pgoff_t,
unsigned char);
static void free_swap_count_continuations(struct swap_info_struct *);
static sector_t map_swap_entry(swp_entry_t, struct block_device**);
DEFINE_SPINLOCK(swap_lock);
static unsigned int nr_swapfiles;
atomic_long_t nr_swap_pages;
/*
* Some modules use swappable objects and may try to swap them out under
* memory pressure (via the shrinker). Before doing so, they may wish to
* check to see if any swap space is available.
*/
EXPORT_SYMBOL_GPL(nr_swap_pages);
/* protected with swap_lock. reading in vm_swap_full() doesn't need lock */
long total_swap_pages;
static int least_priority = -1;
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 ";
/*
* all active swap_info_structs
* protected with swap_lock, and ordered by priority.
*/
PLIST_HEAD(swap_active_head);
/*
* all available (active, not full) swap_info_structs
* protected with swap_avail_lock, ordered by priority.
* This is used by get_swap_page() instead of swap_active_head
* because swap_active_head includes all swap_info_structs,
* but get_swap_page() doesn't need to look at full ones.
* This uses its own lock instead of swap_lock because when a
* swap_info_struct changes between not-full/full, it needs to
* add/remove itself to/from this list, but the swap_info_struct->lock
* is held and the locking order requires swap_lock to be taken
* before any swap_info_struct->lock.
*/
struct plist_head *swap_avail_heads;
static DEFINE_SPINLOCK(swap_avail_lock);
struct swap_info_struct *swap_info[MAX_SWAPFILES];
static DEFINE_MUTEX(swapon_mutex);
static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait);
/* Activity counter to indicate that a swapon or swapoff has occurred */
static atomic_t proc_poll_event = ATOMIC_INIT(0);
atomic_t nr_rotate_swap = ATOMIC_INIT(0);
static inline unsigned char swap_count(unsigned char ent)
{
return ent & ~SWAP_HAS_CACHE; /* may include SWAP_HAS_CONT flag */
}
/* returns 1 if swap entry is freed */
static int
__try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset)
{
swp_entry_t entry = swp_entry(si->type, offset);
struct page *page;
int ret = 0;
page = find_get_page(swap_address_space(entry), swp_offset(entry));
if (!page)
return 0;
/*
* This function is called from scan_swap_map() and it's called
* by vmscan.c at reclaiming pages. So, we hold a lock on a page, here.
* We have to use trylock for avoiding deadlock. This is a special
* case and you should use try_to_free_swap() with explicit lock_page()
* in usual operations.
*/
if (trylock_page(page)) {
ret = try_to_free_swap(page);
unlock_page(page);
}
put_page(page);
return ret;
}
/*
* swapon tell device that all the old swap contents can be discarded,
* to allow the swap device to optimize its wear-levelling.
*/
static int discard_swap(struct swap_info_struct *si)
{
struct swap_extent *se;
sector_t start_block;
sector_t nr_blocks;
int err = 0;
/* Do not discard the swap header page! */
se = &si->first_swap_extent;
start_block = (se->start_block + 1) << (PAGE_SHIFT - 9);
nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9);
if (nr_blocks) {
err = blkdev_issue_discard(si->bdev, start_block,
nr_blocks, GFP_KERNEL, 0);
if (err)
return err;
cond_resched();
}
list_for_each_entry(se, &si->first_swap_extent.list, list) {
start_block = se->start_block << (PAGE_SHIFT - 9);
nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9);
err = blkdev_issue_discard(si->bdev, start_block,
nr_blocks, GFP_KERNEL, 0);
if (err)
break;
cond_resched();
}
return err; /* That will often be -EOPNOTSUPP */
}
/*
* swap allocation tell device that a cluster of swap can now be discarded,
* to allow the swap device to optimize its wear-levelling.
*/
static void discard_swap_cluster(struct swap_info_struct *si,
pgoff_t start_page, pgoff_t nr_pages)
{
struct swap_extent *se = si->curr_swap_extent;
int found_extent = 0;
while (nr_pages) {
if (se->start_page <= start_page &&
start_page < se->start_page + se->nr_pages) {
pgoff_t offset = start_page - se->start_page;
sector_t start_block = se->start_block + offset;
sector_t nr_blocks = se->nr_pages - offset;
if (nr_blocks > nr_pages)
nr_blocks = nr_pages;
start_page += nr_blocks;
nr_pages -= nr_blocks;
if (!found_extent++)
si->curr_swap_extent = se;
start_block <<= PAGE_SHIFT - 9;
nr_blocks <<= PAGE_SHIFT - 9;
if (blkdev_issue_discard(si->bdev, start_block,
nr_blocks, GFP_NOIO, 0))
break;
}
se = list_next_entry(se, list);
}
}
#ifdef CONFIG_THP_SWAP
#define SWAPFILE_CLUSTER HPAGE_PMD_NR
#else
#define SWAPFILE_CLUSTER 256
#endif
#define LATENCY_LIMIT 256
static inline void cluster_set_flag(struct swap_cluster_info *info,
unsigned int flag)
{
info->flags = flag;
}
static inline unsigned int cluster_count(struct swap_cluster_info *info)
{
return info->data;
}
static inline void cluster_set_count(struct swap_cluster_info *info,
unsigned int c)
{
info->data = c;
}
static inline void cluster_set_count_flag(struct swap_cluster_info *info,
unsigned int c, unsigned int f)
{
info->flags = f;
info->data = c;
}
static inline unsigned int cluster_next(struct swap_cluster_info *info)
{
return info->data;
}
static inline void cluster_set_next(struct swap_cluster_info *info,
unsigned int n)
{
info->data = n;
}
static inline void cluster_set_next_flag(struct swap_cluster_info *info,
unsigned int n, unsigned int f)
{
info->flags = f;
info->data = n;
}
static inline bool cluster_is_free(struct swap_cluster_info *info)
{
return info->flags & CLUSTER_FLAG_FREE;
}
static inline bool cluster_is_null(struct swap_cluster_info *info)
{
return info->flags & CLUSTER_FLAG_NEXT_NULL;
}
static inline void cluster_set_null(struct swap_cluster_info *info)
{
info->flags = CLUSTER_FLAG_NEXT_NULL;
info->data = 0;
}
static inline bool cluster_is_huge(struct swap_cluster_info *info)
{
return info->flags & CLUSTER_FLAG_HUGE;
}
static inline void cluster_clear_huge(struct swap_cluster_info *info)
{
info->flags &= ~CLUSTER_FLAG_HUGE;
}
static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si,
unsigned long offset)
{
struct swap_cluster_info *ci;
ci = si->cluster_info;
if (ci) {
ci += offset / SWAPFILE_CLUSTER;
spin_lock(&ci->lock);
}
return ci;
}
static inline void unlock_cluster(struct swap_cluster_info *ci)
{
if (ci)
spin_unlock(&ci->lock);
}
static inline struct swap_cluster_info *lock_cluster_or_swap_info(
struct swap_info_struct *si,
unsigned long offset)
{
struct swap_cluster_info *ci;
ci = lock_cluster(si, offset);
if (!ci)
spin_lock(&si->lock);
return ci;
}
static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si,
struct swap_cluster_info *ci)
{
if (ci)
unlock_cluster(ci);
else
spin_unlock(&si->lock);
}
static inline bool cluster_list_empty(struct swap_cluster_list *list)
{
return cluster_is_null(&list->head);
}
static inline unsigned int cluster_list_first(struct swap_cluster_list *list)
{
return cluster_next(&list->head);
}
static void cluster_list_init(struct swap_cluster_list *list)
{
cluster_set_null(&list->head);
cluster_set_null(&list->tail);
}
static void cluster_list_add_tail(struct swap_cluster_list *list,
struct swap_cluster_info *ci,
unsigned int idx)
{
if (cluster_list_empty(list)) {
cluster_set_next_flag(&list->head, idx, 0);
cluster_set_next_flag(&list->tail, idx, 0);
} else {
struct swap_cluster_info *ci_tail;
unsigned int tail = cluster_next(&list->tail);
/*
* Nested cluster lock, but both cluster locks are
* only acquired when we held swap_info_struct->lock
*/
ci_tail = ci + tail;
spin_lock_nested(&ci_tail->lock, SINGLE_DEPTH_NESTING);
cluster_set_next(ci_tail, idx);
spin_unlock(&ci_tail->lock);
cluster_set_next_flag(&list->tail, idx, 0);
}
}
static unsigned int cluster_list_del_first(struct swap_cluster_list *list,
struct swap_cluster_info *ci)
{
unsigned int idx;
idx = cluster_next(&list->head);
if (cluster_next(&list->tail) == idx) {
cluster_set_null(&list->head);
cluster_set_null(&list->tail);
} else
cluster_set_next_flag(&list->head,
cluster_next(&ci[idx]), 0);
return idx;
}
/* Add a cluster to discard list and schedule it to do discard */
static void swap_cluster_schedule_discard(struct swap_info_struct *si,
unsigned int idx)
{
/*
* If scan_swap_map() can't find a free cluster, it will check
* si->swap_map directly. To make sure the discarding cluster isn't
* taken by scan_swap_map(), mark the swap entries bad (occupied). It
* will be cleared after discard
*/
memset(si->swap_map + idx * SWAPFILE_CLUSTER,
SWAP_MAP_BAD, SWAPFILE_CLUSTER);
cluster_list_add_tail(&si->discard_clusters, si->cluster_info, idx);
schedule_work(&si->discard_work);
}
static void __free_cluster(struct swap_info_struct *si, unsigned long idx)
{
struct swap_cluster_info *ci = si->cluster_info;
cluster_set_flag(ci + idx, CLUSTER_FLAG_FREE);
cluster_list_add_tail(&si->free_clusters, ci, idx);
}
/*
* Doing discard actually. After a cluster discard is finished, the cluster
* will be added to free cluster list. caller should hold si->lock.
*/
static void swap_do_scheduled_discard(struct swap_info_struct *si)
{
struct swap_cluster_info *info, *ci;
unsigned int idx;
info = si->cluster_info;
while (!cluster_list_empty(&si->discard_clusters)) {
idx = cluster_list_del_first(&si->discard_clusters, info);
spin_unlock(&si->lock);
discard_swap_cluster(si, idx * SWAPFILE_CLUSTER,
SWAPFILE_CLUSTER);
spin_lock(&si->lock);
ci = lock_cluster(si, idx * SWAPFILE_CLUSTER);
__free_cluster(si, idx);
memset(si->swap_map + idx * SWAPFILE_CLUSTER,
0, SWAPFILE_CLUSTER);
unlock_cluster(ci);
}
}
static void swap_discard_work(struct work_struct *work)
{
struct swap_info_struct *si;
si = container_of(work, struct swap_info_struct, discard_work);
spin_lock(&si->lock);
swap_do_scheduled_discard(si);
spin_unlock(&si->lock);
}
static void alloc_cluster(struct swap_info_struct *si, unsigned long idx)
{
struct swap_cluster_info *ci = si->cluster_info;
VM_BUG_ON(cluster_list_first(&si->free_clusters) != idx);
cluster_list_del_first(&si->free_clusters, ci);
cluster_set_count_flag(ci + idx, 0, 0);
}
static void free_cluster(struct swap_info_struct *si, unsigned long idx)
{
struct swap_cluster_info *ci = si->cluster_info + idx;
VM_BUG_ON(cluster_count(ci) != 0);
/*
* If the swap is discardable, prepare discard the cluster
* instead of free it immediately. The cluster will be freed
* after discard.
*/
if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) ==
(SWP_WRITEOK | SWP_PAGE_DISCARD)) {
swap_cluster_schedule_discard(si, idx);
return;
}
__free_cluster(si, idx);
}
/*
* The cluster corresponding to page_nr will be used. The cluster will be
* removed from free cluster list and its usage counter will be increased.
*/
static void inc_cluster_info_page(struct swap_info_struct *p,
struct swap_cluster_info *cluster_info, unsigned long page_nr)
{
unsigned long idx = page_nr / SWAPFILE_CLUSTER;
if (!cluster_info)
return;
if (cluster_is_free(&cluster_info[idx]))
alloc_cluster(p, idx);
VM_BUG_ON(cluster_count(&cluster_info[idx]) >= SWAPFILE_CLUSTER);
cluster_set_count(&cluster_info[idx],
cluster_count(&cluster_info[idx]) + 1);
}
/*
* The cluster corresponding to page_nr decreases one usage. If the usage
* counter becomes 0, which means no page in the cluster is in using, we can
* optionally discard the cluster and add it to free cluster list.
*/
static void dec_cluster_info_page(struct swap_info_struct *p,
struct swap_cluster_info *cluster_info, unsigned long page_nr)
{
unsigned long idx = page_nr / SWAPFILE_CLUSTER;
if (!cluster_info)
return;
VM_BUG_ON(cluster_count(&cluster_info[idx]) == 0);
cluster_set_count(&cluster_info[idx],
cluster_count(&cluster_info[idx]) - 1);
if (cluster_count(&cluster_info[idx]) == 0)
free_cluster(p, idx);
}
/*
* It's possible scan_swap_map() uses a free cluster in the middle of free
* cluster list. Avoiding such abuse to avoid list corruption.
*/
static bool
scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si,
unsigned long offset)
{
struct percpu_cluster *percpu_cluster;
bool conflict;
offset /= SWAPFILE_CLUSTER;
conflict = !cluster_list_empty(&si->free_clusters) &&
offset != cluster_list_first(&si->free_clusters) &&
cluster_is_free(&si->cluster_info[offset]);
if (!conflict)
return false;
percpu_cluster = this_cpu_ptr(si->percpu_cluster);
cluster_set_null(&percpu_cluster->index);
return true;
}
/*
* Try to get a swap entry from current cpu's swap entry pool (a cluster). This
* might involve allocating a new cluster for current CPU too.
*/
static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si,
unsigned long *offset, unsigned long *scan_base)
{
struct percpu_cluster *cluster;
struct swap_cluster_info *ci;
bool found_free;
unsigned long tmp, max;
new_cluster:
cluster = this_cpu_ptr(si->percpu_cluster);
if (cluster_is_null(&cluster->index)) {
if (!cluster_list_empty(&si->free_clusters)) {
cluster->index = si->free_clusters.head;
cluster->next = cluster_next(&cluster->index) *
SWAPFILE_CLUSTER;
} else if (!cluster_list_empty(&si->discard_clusters)) {
/*
* we don't have free cluster but have some clusters in
* discarding, do discard now and reclaim them
*/
swap_do_scheduled_discard(si);
*scan_base = *offset = si->cluster_next;
goto new_cluster;
} else
return false;
}
found_free = false;
/*
* Other CPUs can use our cluster if they can't find a free cluster,
* check if there is still free entry in the cluster
*/
tmp = cluster->next;
max = min_t(unsigned long, si->max,
(cluster_next(&cluster->index) + 1) * SWAPFILE_CLUSTER);
if (tmp >= max) {
cluster_set_null(&cluster->index);
goto new_cluster;
}
ci = lock_cluster(si, tmp);
while (tmp < max) {
if (!si->swap_map[tmp]) {
found_free = true;
break;
}
tmp++;
}
unlock_cluster(ci);
if (!found_free) {
cluster_set_null(&cluster->index);
goto new_cluster;
}
cluster->next = tmp + 1;
*offset = tmp;
*scan_base = tmp;
return found_free;
}
static void __del_from_avail_list(struct swap_info_struct *p)
{
int nid;
for_each_node(nid)
plist_del(&p->avail_lists[nid], &swap_avail_heads[nid]);
}
static void del_from_avail_list(struct swap_info_struct *p)
{
spin_lock(&swap_avail_lock);
__del_from_avail_list(p);
spin_unlock(&swap_avail_lock);
}
static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset,
unsigned int nr_entries)
{
unsigned int end = offset + nr_entries - 1;
if (offset == si->lowest_bit)
si->lowest_bit += nr_entries;
if (end == si->highest_bit)
si->highest_bit -= nr_entries;
si->inuse_pages += nr_entries;
if (si->inuse_pages == si->pages) {
si->lowest_bit = si->max;
si->highest_bit = 0;
del_from_avail_list(si);
}
}
static void add_to_avail_list(struct swap_info_struct *p)
{
int nid;
spin_lock(&swap_avail_lock);
for_each_node(nid) {
WARN_ON(!plist_node_empty(&p->avail_lists[nid]));
plist_add(&p->avail_lists[nid], &swap_avail_heads[nid]);
}
spin_unlock(&swap_avail_lock);
}
static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
unsigned int nr_entries)
{
unsigned long end = offset + nr_entries - 1;
void (*swap_slot_free_notify)(struct block_device *, unsigned long);
if (offset < si->lowest_bit)
si->lowest_bit = offset;
if (end > si->highest_bit) {
bool was_full = !si->highest_bit;
si->highest_bit = end;
if (was_full && (si->flags & SWP_WRITEOK))
add_to_avail_list(si);
}
atomic_long_add(nr_entries, &nr_swap_pages);
si->inuse_pages -= nr_entries;
if (si->flags & SWP_BLKDEV)
swap_slot_free_notify =
si->bdev->bd_disk->fops->swap_slot_free_notify;
else
swap_slot_free_notify = NULL;
while (offset <= end) {
frontswap_invalidate_page(si->type, offset);
if (swap_slot_free_notify)
swap_slot_free_notify(si->bdev, offset);
offset++;
}
}
static int scan_swap_map_slots(struct swap_info_struct *si,
unsigned char usage, int nr,
swp_entry_t slots[])
{
struct swap_cluster_info *ci;
unsigned long offset;
unsigned long scan_base;
unsigned long last_in_cluster = 0;
int latency_ration = LATENCY_LIMIT;
int n_ret = 0;
if (nr > SWAP_BATCH)
nr = SWAP_BATCH;
/*
* 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
* And we let swap pages go all over an SSD partition. Hugh
*/
si->flags += SWP_SCANNING;
scan_base = offset = si->cluster_next;
/* SSD algorithm */
if (si->cluster_info) {
if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base))
goto checks;
else
goto scan;
}
if (unlikely(!si->cluster_nr--)) {
if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) {
si->cluster_nr = SWAPFILE_CLUSTER - 1;
goto checks;
}
spin_unlock(&si->lock);
/*
* If seek is expensive, start searching for new cluster from
* start of partition, to minimize the span of allocated swap.
* If seek is cheap, that is the SWP_SOLIDSTATE si->cluster_info
* case, just handled by scan_swap_map_try_ssd_cluster() above.
*/
scan_base = 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(&si->lock);
offset -= SWAPFILE_CLUSTER - 1;
si->cluster_next = offset;
si->cluster_nr = SWAPFILE_CLUSTER - 1;
goto checks;
}
if (unlikely(--latency_ration < 0)) {
cond_resched();
latency_ration = LATENCY_LIMIT;
}
}
offset = scan_base;
spin_lock(&si->lock);
si->cluster_nr = SWAPFILE_CLUSTER - 1;
}
checks:
if (si->cluster_info) {
while (scan_swap_map_ssd_cluster_conflict(si, offset)) {
/* take a break if we already got some slots */
if (n_ret)
goto done;
if (!scan_swap_map_try_ssd_cluster(si, &offset,
&scan_base))
goto scan;
}
}
if (!(si->flags & SWP_WRITEOK))
goto no_page;
if (!si->highest_bit)
goto no_page;
if (offset > si->highest_bit)
scan_base = offset = si->lowest_bit;
ci = lock_cluster(si, offset);
/* reuse swap entry of cache-only swap if not busy. */
if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {
int swap_was_freed;
unlock_cluster(ci);
spin_unlock(&si->lock);
swap_was_freed = __try_to_reclaim_swap(si, offset);
spin_lock(&si->lock);
/* entry was freed successfully, try to use this again */
if (swap_was_freed)
goto checks;
goto scan; /* check next one */
}
if (si->swap_map[offset]) {
unlock_cluster(ci);
if (!n_ret)
goto scan;
else
goto done;
}
si->swap_map[offset] = usage;
inc_cluster_info_page(si, si->cluster_info, offset);
unlock_cluster(ci);
swap_range_alloc(si, offset, 1);
si->cluster_next = offset + 1;
slots[n_ret++] = swp_entry(si->type, offset);
/* got enough slots or reach max slots? */
if ((n_ret == nr) || (offset >= si->highest_bit))
goto done;
/* search for next available slot */
/* time to take a break? */
if (unlikely(--latency_ration < 0)) {
if (n_ret)
goto done;
spin_unlock(&si->lock);
cond_resched();
spin_lock(&si->lock);
latency_ration = LATENCY_LIMIT;
}
/* try to get more slots in cluster */
if (si->cluster_info) {
if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base))
goto checks;
else
goto done;
}
/* non-ssd case */
++offset;
/* non-ssd case, still more slots in cluster? */
if (si->cluster_nr && !si->swap_map[offset]) {
--si->cluster_nr;
goto checks;
}
done:
si->flags -= SWP_SCANNING;
return n_ret;
scan:
spin_unlock(&si->lock);
while (++offset <= si->highest_bit) {
if (!si->swap_map[offset]) {
spin_lock(&si->lock);
goto checks;
}
if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {
spin_lock(&si->lock);
goto checks;
}
if (unlikely(--latency_ration < 0)) {
cond_resched();
latency_ration = LATENCY_LIMIT;
}
}
offset = si->lowest_bit;
while (offset < scan_base) {
if (!si->swap_map[offset]) {
spin_lock(&si->lock);
goto checks;
}
if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {
spin_lock(&si->lock);
goto checks;
}
if (unlikely(--latency_ration < 0)) {
cond_resched();
latency_ration = LATENCY_LIMIT;
}
offset++;
}
spin_lock(&si->lock);
no_page:
si->flags -= SWP_SCANNING;
return n_ret;
}
#ifdef CONFIG_THP_SWAP
static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot)
{
unsigned long idx;
struct swap_cluster_info *ci;
unsigned long offset, i;
unsigned char *map;
if (cluster_list_empty(&si->free_clusters))
return 0;
idx = cluster_list_first(&si->free_clusters);
offset = idx * SWAPFILE_CLUSTER;
ci = lock_cluster(si, offset);
alloc_cluster(si, idx);
cluster_set_count_flag(ci, SWAPFILE_CLUSTER, CLUSTER_FLAG_HUGE);
map = si->swap_map + offset;
for (i = 0; i < SWAPFILE_CLUSTER; i++)
map[i] = SWAP_HAS_CACHE;
unlock_cluster(ci);
swap_range_alloc(si, offset, SWAPFILE_CLUSTER);
*slot = swp_entry(si->type, offset);
return 1;
}
static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx)
{
unsigned long offset = idx * SWAPFILE_CLUSTER;
struct swap_cluster_info *ci;
ci = lock_cluster(si, offset);
cluster_set_count_flag(ci, 0, 0);
free_cluster(si, idx);
unlock_cluster(ci);
swap_range_free(si, offset, SWAPFILE_CLUSTER);
}
#else
static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot)
{
VM_WARN_ON_ONCE(1);
return 0;
}
#endif /* CONFIG_THP_SWAP */
static unsigned long scan_swap_map(struct swap_info_struct *si,
unsigned char usage)
{
swp_entry_t entry;
int n_ret;
n_ret = scan_swap_map_slots(si, usage, 1, &entry);
if (n_ret)
return swp_offset(entry);
else
return 0;
}
int get_swap_pages(int n_goal, bool cluster, swp_entry_t swp_entries[])
{
unsigned long nr_pages = cluster ? SWAPFILE_CLUSTER : 1;
struct swap_info_struct *si, *next;
long avail_pgs;
int n_ret = 0;
int node;
/* Only single cluster request supported */
WARN_ON_ONCE(n_goal > 1 && cluster);
avail_pgs = atomic_long_read(&nr_swap_pages) / nr_pages;
if (avail_pgs <= 0)
goto noswap;
if (n_goal > SWAP_BATCH)
n_goal = SWAP_BATCH;
if (n_goal > avail_pgs)
n_goal = avail_pgs;
atomic_long_sub(n_goal * nr_pages, &nr_swap_pages);
spin_lock(&swap_avail_lock);
start_over:
node = numa_node_id();
plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) {
/* requeue si to after same-priority siblings */
plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]);
spin_unlock(&swap_avail_lock);
spin_lock(&si->lock);
if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) {
spin_lock(&swap_avail_lock);
if (plist_node_empty(&si->avail_lists[node])) {
spin_unlock(&si->lock);
goto nextsi;
}
WARN(!si->highest_bit,
"swap_info %d in list but !highest_bit\n",
si->type);
WARN(!(si->flags & SWP_WRITEOK),
"swap_info %d in list but !SWP_WRITEOK\n",
si->type);
__del_from_avail_list(si);
spin_unlock(&si->lock);
goto nextsi;
}
if (cluster) {
if (!(si->flags & SWP_FILE))
n_ret = swap_alloc_cluster(si, swp_entries);
} else
n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
n_goal, swp_entries);
spin_unlock(&si->lock);
if (n_ret || cluster)
goto check_out;
pr_debug("scan_swap_map of si %d failed to find offset\n",
si->type);
spin_lock(&swap_avail_lock);
nextsi:
/*
* if we got here, it's likely that si was almost full before,
* and since scan_swap_map() can drop the si->lock, multiple
* callers probably all tried to get a page from the same si
* and it filled up before we could get one; or, the si filled
* up between us dropping swap_avail_lock and taking si->lock.
* Since we dropped the swap_avail_lock, the swap_avail_head
* list may have been modified; so if next is still in the
* swap_avail_head list then try it, otherwise start over
* if we have not gotten any slots.
*/
if (plist_node_empty(&next->avail_lists[node]))