aboutsummaryrefslogtreecommitdiff
path: root/mm/swap.c
blob: d1100b619e616e7f8a62e3c3db3eb19cb41b4caf (plain)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
/*
 *  linux/mm/swap.c
 *
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 */

/*
 * This file contains the default values for the operation of the
 * Linux VM subsystem. Fine-tuning documentation can be found in
 * Documentation/sysctl/vm.txt.
 * Started 18.12.91
 * Swap aging added 23.2.95, Stephen Tweedie.
 * Buffermem limits added 12.3.98, Rik van Riel.
 */

#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/init.h>
#include <linux/export.h>
#include <linux/mm_inline.h>
#include <linux/percpu_counter.h>
#include <linux/percpu.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/backing-dev.h>
#include <linux/memcontrol.h>
#include <linux/gfp.h>
#include <linux/uio.h>

#include "internal.h"

#define CREATE_TRACE_POINTS
#include <trace/events/pagemap.h>

/* How many pages do we try to swap or page in/out together? */
int page_cluster;

static DEFINE_PER_CPU(struct pagevec, lru_add_pvec);
static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs);
static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs);

/*
 * This path almost never happens for VM activity - pages are normally
 * freed via pagevecs.  But it gets used by networking.
 */
static void __page_cache_release(struct page *page)
{
	if (PageLRU(page)) {
		struct zone *zone = page_zone(page);
		struct lruvec *lruvec;
		unsigned long flags;

		spin_lock_irqsave(&zone->lru_lock, flags);
		lruvec = mem_cgroup_page_lruvec(page, zone);
		VM_BUG_ON(!PageLRU(page));
		__ClearPageLRU(page);
		del_page_from_lru_list(page, lruvec, page_off_lru(page));
		spin_unlock_irqrestore(&zone->lru_lock, flags);
	}
}

static void __put_single_page(struct page *page)
{
	__page_cache_release(page);
	free_hot_cold_page(page, 0);
}

static void __put_compound_page(struct page *page)
{
	compound_page_dtor *dtor;

	__page_cache_release(page);
	dtor = get_compound_page_dtor(page);
	(*dtor)(page);
}

static void put_compound_page(struct page *page)
{
	struct page *page_head;

	if (likely(!PageTail(page))) {
		if (put_page_testzero(page)) {
			/*
			 * By the time all refcounts have been released
			 * split_huge_page cannot run anymore from under us.
			 */
			if (PageHead(page))
				__put_compound_page(page);
			else
				__put_single_page(page);
		}
		return;
	}

	/* __split_huge_page_refcount can run under us */
	page_head = compound_trans_head(page);

	/*
	 * THP can not break up slab pages so avoid taking
	 * compound_lock() and skip the tail page refcounting (in
	 * _mapcount) too. Slab performs non-atomic bit ops on
	 * page->flags for better performance. In particular
	 * slab_unlock() in slub used to be a hot path. It is still
	 * hot on arches that do not support
	 * this_cpu_cmpxchg_double().
	 *
	 * If "page" is part of a slab or hugetlbfs page it cannot be
	 * splitted and the head page cannot change from under us. And
	 * if "page" is part of a THP page under splitting, if the
	 * head page pointed by the THP tail isn't a THP head anymore,
	 * we'll find PageTail clear after smp_rmb() and we'll treat
	 * it as a single page.
	 */
	if (!__compound_tail_refcounted(page_head)) {
		/*
		 * If "page" is a THP tail, we must read the tail page
		 * flags after the head page flags. The
		 * split_huge_page side enforces write memory barriers
		 * between clearing PageTail and before the head page
		 * can be freed and reallocated.
		 */
		smp_rmb();
		if (likely(PageTail(page))) {
			/*
			 * __split_huge_page_refcount cannot race
			 * here.
			 */
			VM_BUG_ON(!PageHead(page_head));
			VM_BUG_ON(page_mapcount(page) != 0);
			if (put_page_testzero(page_head)) {
				/*
				 * If this is the tail of a slab
				 * compound page, the tail pin must
				 * not be the last reference held on
				 * the page, because the PG_slab
				 * cannot be cleared before all tail
				 * pins (which skips the _mapcount
				 * tail refcounting) have been
				 * released. For hugetlbfs the tail
				 * pin may be the last reference on
				 * the page instead, because
				 * PageHeadHuge will not go away until
				 * the compound page enters the buddy
				 * allocator.
				 */
				VM_BUG_ON(PageSlab(page_head));
				__put_compound_page(page_head);
			}
			return;
		} else
			/*
			 * __split_huge_page_refcount run before us,
			 * "page" was a THP tail. The split page_head
			 * has been freed and reallocated as slab or
			 * hugetlbfs page of smaller order (only
			 * possible if reallocated as slab on x86).
			 */
			goto out_put_single;
	}

	if (likely(page != page_head && get_page_unless_zero(page_head))) {
		unsigned long flags;

		/*
		 * page_head wasn't a dangling pointer but it may not
		 * be a head page anymore by the time we obtain the
		 * lock. That is ok as long as it can't be freed from
		 * under us.
		 */
		flags = compound_lock_irqsave(page_head);
		if (unlikely(!PageTail(page))) {
			/* __split_huge_page_refcount run before us */
			compound_unlock_irqrestore(page_head, flags);
			if (put_page_testzero(page_head)) {
				/*
				 * The head page may have been freed
				 * and reallocated as a compound page
				 * of smaller order and then freed
				 * again.  All we know is that it
				 * cannot have become: a THP page, a
				 * compound page of higher order, a
				 * tail page.  That is because we
				 * still hold the refcount of the
				 * split THP tail and page_head was
				 * the THP head before the split.
				 */
				if (PageHead(page_head))
					__put_compound_page(page_head);
				else
					__put_single_page(page_head);
			}
out_put_single:
			if (put_page_testzero(page))
				__put_single_page(page);
			return;
		}
		VM_BUG_ON(page_head != page->first_page);
		/*
		 * We can release the refcount taken by
		 * get_page_unless_zero() now that
		 * __split_huge_page_refcount() is blocked on the
		 * compound_lock.
		 */
		if (put_page_testzero(page_head))
			VM_BUG_ON(1);
		/* __split_huge_page_refcount will wait now */
		VM_BUG_ON(page_mapcount(page) <= 0);
		atomic_dec(&page->_mapcount);
		VM_BUG_ON(atomic_read(&page_head->_count) <= 0);
		VM_BUG_ON(atomic_read(&page->_count) != 0);
		compound_unlock_irqrestore(page_head, flags);

		if (put_page_testzero(page_head)) {
			if (PageHead(page_head))
				__put_compound_page(page_head);
			else
				__put_single_page(page_head);
		}
	} else {
		/* page_head is a dangling pointer */
		VM_BUG_ON(PageTail(page));
		goto out_put_single;
	}
}

void put_page(struct page *page)
{
	if (unlikely(PageCompound(page)))
		put_compound_page(page);
	else if (put_page_testzero(page))
		__put_single_page(page);
}
EXPORT_SYMBOL(put_page);

/*
 * This function is exported but must not be called by anything other
 * than get_page(). It implements the slow path of get_page().
 */
bool __get_page_tail(struct page *page)
{
	/*
	 * This takes care of get_page() if run on a tail page
	 * returned by one of the get_user_pages/follow_page variants.
	 * get_user_pages/follow_page itself doesn't need the compound
	 * lock because it runs __get_page_tail_foll() under the
	 * proper PT lock that already serializes against
	 * split_huge_page().
	 */
	unsigned long flags;
	bool got;
	struct page *page_head = compound_trans_head(page);

	/* Ref to put_compound_page() comment. */
	if (!__compound_tail_refcounted(page_head)) {
		smp_rmb();
		if (likely(PageTail(page))) {
			/*
			 * This is a hugetlbfs page or a slab
			 * page. __split_huge_page_refcount
			 * cannot race here.
			 */
			VM_BUG_ON(!PageHead(page_head));
			__get_page_tail_foll(page, true);
			return true;
		} else {
			/*
			 * __split_huge_page_refcount run
			 * before us, "page" was a THP
			 * tail. The split page_head has been
			 * freed and reallocated as slab or
			 * hugetlbfs page of smaller order
			 * (only possible if reallocated as
			 * slab on x86).
			 */
			return false;
		}
	}

	got = false;
	if (likely(page != page_head && get_page_unless_zero(page_head))) {
		/*
		 * page_head wasn't a dangling pointer but it
		 * may not be a head page anymore by the time
		 * we obtain the lock. That is ok as long as it
		 * can't be freed from under us.
		 */
		flags = compound_lock_irqsave(page_head);
		/* here __split_huge_page_refcount won't run anymore */
		if (likely(PageTail(page))) {
			__get_page_tail_foll(page, false);
			got = true;
		}
		compound_unlock_irqrestore(page_head, flags);
		if (unlikely(!got))
			put_page(page_head);
	}
	return got;
}
EXPORT_SYMBOL(__get_page_tail);

/**
 * put_pages_list() - release a list of pages
 * @pages: list of pages threaded on page->lru
 *
 * Release a list of pages which are strung together on page.lru.  Currently
 * used by read_cache_pages() and related error recovery code.
 */
void put_pages_list(struct list_head *pages)
{
	while (!list_empty(pages)) {
		struct page *victim;

		victim = list_entry(pages->prev, struct page, lru);
		list_del(&victim->lru);
		page_cache_release(victim);
	}
}
EXPORT_SYMBOL(put_pages_list);

/*
 * get_kernel_pages() - pin kernel pages in memory
 * @kiov:	An array of struct kvec structures
 * @nr_segs:	number of segments to pin
 * @write:	pinning for read/write, currently ignored
 * @pages:	array that receives pointers to the pages pinned.
 *		Should be at least nr_segs long.
 *
 * Returns number of pages pinned. This may be fewer than the number
 * requested. If nr_pages is 0 or negative, returns 0. If no pages
 * were pinned, returns -errno. Each page returned must be released
 * with a put_page() call when it is finished with.
 */
int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write,
		struct page **pages)
{
	int seg;

	for (seg = 0; seg < nr_segs; seg++) {
		if (WARN_ON(kiov[seg].iov_len != PAGE_SIZE))
			return seg;

		pages[seg] = kmap_to_page(kiov[seg].iov_base);
		page_cache_get(pages[seg]);
	}

	return seg;
}
EXPORT_SYMBOL_GPL(get_kernel_pages);

/*
 * get_kernel_page() - pin a kernel page in memory
 * @start:	starting kernel address
 * @write:	pinning for read/write, currently ignored
 * @pages:	array that receives pointer to the page pinned.
 *		Must be at least nr_segs long.
 *
 * Returns 1 if page is pinned. If the page was not pinned, returns
 * -errno. The page returned must be released with a put_page() call
 * when it is finished with.
 */
int get_kernel_page(unsigned long start, int write, struct page **pages)
{
	const struct kvec kiov = {
		.iov_base = (void *)start,
		.iov_len = PAGE_SIZE
	};

	return get_kernel_pages(&kiov, 1, write, pages);
}
EXPORT_SYMBOL_GPL(get_kernel_page);

static void pagevec_lru_move_fn(struct pagevec *pvec,
	void (*move_fn)(struct page *page, struct lruvec *lruvec, void *arg),
	void *arg)
{
	int i;
	struct zone *zone = NULL;
	struct lruvec *lruvec;
	unsigned long flags = 0;

	for (i = 0; i < pagevec_count(pvec); i++) {
		struct page *page = pvec->pages[i];
		struct zone *pagezone = page_zone(page);

		if (pagezone != zone) {
			if (zone)
				spin_unlock_irqrestore(&zone->lru_lock, flags);
			zone = pagezone;
			spin_lock_irqsave(&zone->lru_lock, flags);
		}

		lruvec = mem_cgroup_page_lruvec(page, zone);
		(*move_fn)(page, lruvec, arg);
	}
	if (zone)
		spin_unlock_irqrestore(&zone->lru_lock, flags);
	release_pages(pvec->pages, pvec->nr, pvec->cold);
	pagevec_reinit(pvec);
}

static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec,
				 void *arg)
{
	int *pgmoved = arg;

	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
		enum lru_list lru = page_lru_base_type(page);
		list_move_tail(&page->lru, &lruvec->lists[lru]);
		(*pgmoved)++;
	}
}

/*
 * pagevec_move_tail() must be called with IRQ disabled.
 * Otherwise this may cause nasty races.
 */
static void pagevec_move_tail(struct pagevec *pvec)
{
	int pgmoved = 0;

	pagevec_lru_move_fn(pvec, pagevec_move_tail_fn, &pgmoved);
	__count_vm_events(PGROTATED, pgmoved);
}

/*
 * Writeback is about to end against a page which has been marked for immediate
 * reclaim.  If it still appears to be reclaimable, move it to the tail of the
 * inactive list.
 */
void rotate_reclaimable_page(struct page *page)
{
	if (!PageLocked(page) && !PageDirty(page) && !PageActive(page) &&
	    !PageUnevictable(page) && PageLRU(page)) {
		struct pagevec *pvec;
		unsigned long flags;

		page_cache_get(page);
		local_irq_save(flags);
		pvec = &__get_cpu_var(lru_rotate_pvecs);
		if (!pagevec_add(pvec, page))
			pagevec_move_tail(pvec);
		local_irq_restore(flags);
	}
}

static void update_page_reclaim_stat(struct lruvec *lruvec,
				     int file, int rotated)
{
	struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;

	reclaim_stat->recent_scanned[file]++;
	if (rotated)
		reclaim_stat->recent_rotated[file]++;
}

static void __activate_page(struct page *page, struct lruvec *lruvec,
			    void *arg)
{
	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
		int file = page_is_file_cache(page);
		int lru = page_lru_base_type(page);

		del_page_from_lru_list(page, lruvec, lru);
		SetPageActive(page);
		lru += LRU_ACTIVE;
		add_page_to_lru_list(page, lruvec, lru);
		trace_mm_lru_activate(page, page_to_pfn(page));

		__count_vm_event(PGACTIVATE);
		update_page_reclaim_stat(lruvec, file, 1);
	}
}

#ifdef CONFIG_SMP
static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs);

static void activate_page_drain(int cpu)
{
	struct pagevec *pvec = &per_cpu(activate_page_pvecs, cpu);

	if (pagevec_count(pvec))
		pagevec_lru_move_fn(pvec, __activate_page, NULL);
}

static bool need_activate_page_drain(int cpu)
{
	return pagevec_count(&per_cpu(activate_page_pvecs, cpu)) != 0;
}

void activate_page(struct page *page)
{
	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
		struct pagevec *pvec = &get_cpu_var(activate_page_pvecs);

		page_cache_get(page);
		if (!pagevec_add(pvec, page))
			pagevec_lru_move_fn(pvec, __activate_page, NULL);
		put_cpu_var(activate_page_pvecs);
	}
}

#else
static inline void activate_page_drain(int cpu)
{
}

static bool need_activate_page_drain(int cpu)
{
	return false;
}

void activate_page(struct page *page)
{
	struct zone *zone = page_zone(page);

	spin_lock_irq(&zone->lru_lock);
	__activate_page(page, mem_cgroup_page_lruvec(page, zone), NULL);
	spin_unlock_irq(&zone->lru_lock);
}
#endif

static void __lru_cache_activate_page(struct page *page)
{
	struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
	int i;

	/*
	 * Search backwards on the optimistic assumption that the page being
	 * activated has just been added to this pagevec. Note that only
	 * the local pagevec is examined as a !PageLRU page could be in the
	 * process of being released, reclaimed, migrated or on a remote
	 * pagevec that is currently being drained. Furthermore, marking
	 * a remote pagevec's page PageActive potentially hits a race where
	 * a page is marked PageActive just after it is added to the inactive
	 * list causing accounting errors and BUG_ON checks to trigger.
	 */
	for (i = pagevec_count(pvec) - 1; i >= 0; i--) {
		struct page *pagevec_page = pvec->pages[i];

		if (pagevec_page == page) {
			SetPageActive(page);
			break;
		}
	}

	put_cpu_var(lru_add_pvec);
}

/*
 * Mark a page as having seen activity.
 *
 * inactive,unreferenced	->	inactive,referenced
 * inactive,referenced		->	active,unreferenced
 * active,unreferenced		->	active,referenced
 */
void mark_page_accessed(struct page *page)
{
	if (!PageActive(page) && !PageUnevictable(page) &&
			PageReferenced(page)) {

		/*
		 * If the page is on the LRU, queue it for activation via
		 * activate_page_pvecs. Otherwise, assume the page is on a
		 * pagevec, mark it active and it'll be moved to the active
		 * LRU on the next drain.
		 */
		if (PageLRU(page))
			activate_page(page);
		else
			__lru_cache_activate_page(page);
		ClearPageReferenced(page);
	} else if (!PageReferenced(page)) {
		SetPageReferenced(page);
	}
}
EXPORT_SYMBOL(mark_page_accessed);

/*
 * Queue the page for addition to the LRU via pagevec. The decision on whether
 * to add the page to the [in]active [file|anon] list is deferred until the
 * pagevec is drained. This gives a chance for the caller of __lru_cache_add()
 * have the page added to the active list using mark_page_accessed().
 */
void __lru_cache_add(struct page *page)
{
	struct pagevec *pvec = &get_cpu_var(lru_add_pvec);

	page_cache_get(page);
	if (!pagevec_space(pvec))
		__pagevec_lru_add(pvec);
	pagevec_add(pvec, page);
	put_cpu_var(lru_add_pvec);
}
EXPORT_SYMBOL(__lru_cache_add);

/**
 * lru_cache_add - add a page to a page list
 * @page: the page to be added to the LRU.
 */
void lru_cache_add(struct page *page)
{
	VM_BUG_ON(PageActive(page) && PageUnevictable(page));
	VM_BUG_ON(PageLRU(page));
	__lru_cache_add(page);
}

/**
 * add_page_to_unevictable_list - add a page to the unevictable list
 * @page:  the page to be added to the unevictable list
 *
 * Add page directly to its zone's unevictable list.  To avoid races with
 * tasks that might be making the page evictable, through eg. munlock,
 * munmap or exit, while it's not on the lru, we want to add the page
 * while it's locked or otherwise "invisible" to other tasks.  This is
 * difficult to do when using the pagevec cache, so bypass that.
 */
void add_page_to_unevictable_list(struct page *page)
{
	struct zone *zone = page_zone(page);
	struct lruvec *lruvec;

	spin_lock_irq(&zone->lru_lock);
	lruvec = mem_cgroup_page_lruvec(page, zone);
	ClearPageActive(page);
	SetPageUnevictable(page);
	SetPageLRU(page);
	add_page_to_lru_list(page, lruvec, LRU_UNEVICTABLE);
	spin_unlock_irq(&zone->lru_lock);
}

/*
 * If the page can not be invalidated, it is moved to the
 * inactive list to speed up its reclaim.  It is moved to the
 * head of the list, rather than the tail, to give the flusher
 * threads some time to write it out, as this is much more
 * effective than the single-page writeout from reclaim.
 *
 * If the page isn't page_mapped and dirty/writeback, the page
 * could reclaim asap using PG_reclaim.
 *
 * 1. active, mapped page -> none
 * 2. active, dirty/writeback page -> inactive, head, PG_reclaim
 * 3. inactive, mapped page -> none
 * 4. inactive, dirty/writeback page -> inactive, head, PG_reclaim
 * 5. inactive, clean -> inactive, tail
 * 6. Others -> none
 *
 * In 4, why it moves inactive's head, the VM expects the page would
 * be write it out by flusher threads as this is much more effective
 * than the single-page writeout from reclaim.
 */
static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec,
			      void *arg)
{
	int lru, file;
	bool active;

	if (!PageLRU(page))
		return;

	if (PageUnevictable(page))
		return;

	/* Some processes are using the page */
	if (page_mapped(page))
		return;

	active = PageActive(page);
	file = page_is_file_cache(page);
	lru = page_lru_base_type(page);

	del_page_from_lru_list(page, lruvec, lru + active);
	ClearPageActive(page);
	ClearPageReferenced(page);
	add_page_to_lru_list(page, lruvec, lru);

	if (PageWriteback(page) || PageDirty(page)) {
		/*
		 * PG_reclaim could be raced with end_page_writeback
		 * It can make readahead confusing.  But race window
		 * is _really_ small and  it's non-critical problem.
		 */
		SetPageReclaim(page);
	} else {
		/*
		 * The page's writeback ends up during pagevec
		 * We moves tha page into tail of inactive.
		 */
		list_move_tail(&page->lru, &lruvec->lists[lru]);
		__count_vm_event(PGROTATED);
	}

	if (active)
		__count_vm_event(PGDEACTIVATE);
	update_page_reclaim_stat(lruvec, file, 0);
}

/*
 * Drain pages out of the cpu's pagevecs.
 * Either "cpu" is the current CPU, and preemption has already been
 * disabled; or "cpu" is being hot-unplugged, and is already dead.
 */
void lru_add_drain_cpu(int cpu)
{
	struct pagevec *pvec = &per_cpu(lru_add_pvec, cpu);

	if (pagevec_count(pvec))
		__pagevec_lru_add(pvec);

	pvec = &per_cpu(lru_rotate_pvecs, cpu);
	if (pagevec_count(pvec)) {
		unsigned long flags;

		/* No harm done if a racing interrupt already did this */
		local_irq_save(flags);
		pagevec_move_tail(pvec);
		local_irq_restore(flags);
	}

	pvec = &per_cpu(lru_deactivate_pvecs, cpu);
	if (pagevec_count(pvec))
		pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);

	activate_page_drain(cpu);
}

/**
 * deactivate_page - forcefully deactivate a page
 * @page: page to deactivate
 *
 * This function hints the VM that @page is a good reclaim candidate,
 * for example if its invalidation fails due to the page being dirty
 * or under writeback.
 */
void deactivate_page(struct page *page)
{
	/*
	 * In a workload with many unevictable page such as mprotect, unevictable
	 * page deactivation for accelerating reclaim is pointless.
	 */
	if (PageUnevictable(page))
		return;

	if (likely(get_page_unless_zero(page))) {
		struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs);

		if (!pagevec_add(pvec, page))
			pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
		put_cpu_var(lru_deactivate_pvecs);
	}
}

void lru_add_drain(void)
{
	lru_add_drain_cpu(get_cpu());
	put_cpu();
}

static void lru_add_drain_per_cpu(struct work_struct *dummy)
{
	lru_add_drain();
}

static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);

void lru_add_drain_all(void)
{
	static DEFINE_MUTEX(lock);
	static struct cpumask has_work;
	int cpu;

	mutex_lock(&lock);
	get_online_cpus();
	cpumask_clear(&has_work);

	for_each_online_cpu(cpu) {
		struct work_struct *work = &per_cpu(lru_add_drain_work, cpu);

		if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) ||
		    pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) ||
		    pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) ||
		    need_activate_page_drain(cpu)) {
			INIT_WORK(work, lru_add_drain_per_cpu);
			schedule_work_on(cpu, work);
			cpumask_set_cpu(cpu, &has_work);
		}
	}

	for_each_cpu(cpu, &has_work)
		flush_work(&per_cpu(lru_add_drain_work, cpu));

	put_online_cpus();
	mutex_unlock(&lock);
}

/*
 * Batched page_cache_release().  Decrement the reference count on all the
 * passed pages.  If it fell to zero then remove the page from the LRU and
 * free it.
 *
 * Avoid taking zone->lru_lock if possible, but if it is taken, retain it
 * for the remainder of the operation.
 *
 * The locking in this function is against shrink_inactive_list(): we recheck
 * the page count inside the lock to see whether shrink_inactive_list()
 * grabbed the page via the LRU.  If it did, give up: shrink_inactive_list()
 * will free it.
 */
void release_pages(struct page **pages, int nr, int cold)
{
	int i;
	LIST_HEAD(pages_to_free);
	struct zone *zone = NULL;
	struct lruvec *lruvec;
	unsigned long uninitialized_var(flags);

	for (i = 0; i < nr; i++) {
		struct page *page = pages[i];

		if (unlikely(PageCompound(page))) {
			if (zone) {
				spin_unlock_irqrestore(&zone->lru_lock, flags);
				zone = NULL;
			}
			put_compound_page(page);
			continue;
		}

		if (!put_page_testzero(page))
			continue;

		if (PageLRU(page)) {
			struct zone *pagezone = page_zone(page);

			if (pagezone != zone) {
				if (zone)
					spin_unlock_irqrestore(&zone->lru_lock,
									flags);
				zone = pagezone;
				spin_lock_irqsave(&zone->lru_lock, flags);
			}

			lruvec = mem_cgroup_page_lruvec(page, zone);
			VM_BUG_ON(!PageLRU(page));
			__ClearPageLRU(page);
			del_page_from_lru_list(page, lruvec, page_off_lru(page));
		}

		/* Clear Active bit in case of parallel mark_page_accessed */
		ClearPageActive(page);

		list_add(&page->lru, &pages_to_free);
	}
	if (zone)
		spin_unlock_irqrestore(&zone->lru_lock, flags);

	free_hot_cold_page_list(&pages_to_free, cold);
}
EXPORT_SYMBOL(release_pages);

/*
 * The pages which we're about to release may be in the deferred lru-addition
 * queues.  That would prevent them from really being freed right now.  That's
 * OK from a correctness point of view but is inefficient - those pages may be
 * cache-warm and we want to give them back to the page allocator ASAP.
 *
 * So __pagevec_release() will drain those queues here.  __pagevec_lru_add()
 * and __pagevec_lru_add_active() call release_pages() directly to avoid
 * mutual recursion.
 */
void __pagevec_release(struct pagevec *pvec)
{
	lru_add_drain();
	release_pages(pvec->pages, pagevec_count(pvec), pvec->cold);
	pagevec_reinit(pvec);
}
EXPORT_SYMBOL(__pagevec_release);

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/* used by __split_huge_page_refcount() */
void lru_add_page_tail(struct page *page, struct page *page_tail,
		       struct lruvec *lruvec, struct list_head *list)
{
	const int file = 0;

	VM_BUG_ON(!PageHead(page));
	VM_BUG_ON(PageCompound(page_tail));
	VM_BUG_ON(PageLRU(page_tail));
	VM_BUG_ON(NR_CPUS != 1 &&
		  !spin_is_locked(&lruvec_zone(lruvec)->lru_lock));

	if (!list)
		SetPageLRU(page_tail);

	if (likely(PageLRU(page)))
		list_add_tail(&page_tail->lru, &page->lru);
	else if (list) {
		/* page reclaim is reclaiming a huge page */
		get_page(page_tail);
		list_add_tail(&page_tail->lru, list);
	} else {
		struct list_head *list_head;
		/*
		 * Head page has not yet been counted, as an hpage,
		 * so we must account for each subpage individually.
		 *
		 * Use the standard add function to put page_tail on the list,
		 * but then correct its position so they all end up in order.
		 */
		add_page_to_lru_list(page_tail, lruvec, page_lru(page_tail));
		list_head = page_tail->lru.prev;
		list_move_tail(&page_tail->lru, list_head);
	}

	if (!PageUnevictable(page))
		update_page_reclaim_stat(lruvec, file, PageActive(page_tail));
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec,
				 void *arg)
{
	int file = page_is_file_cache(page);
	int active = PageActive(page);
	enum lru_list lru = page_lru(page);

	VM_BUG_ON(PageLRU(page));

	SetPageLRU(page);
	add_page_to_lru_list(page, lruvec, lru);
	update_page_reclaim_stat(lruvec, file, active);
	trace_mm_lru_insertion(page, page_to_pfn(page), lru, trace_pagemap_flags(page));
}

/*
 * Add the passed pages to the LRU, then drop the caller's refcount
 * on them.  Reinitialises the caller's pagevec.
 */
void __pagevec_lru_add(struct pagevec *pvec)
{
	pagevec_lru_move_fn(pvec, __pagevec_lru_add_fn, NULL);
}
EXPORT_SYMBOL(__pagevec_lru_add);

/**
 * pagevec_lookup - gang pagecache lookup
 * @pvec:	Where the resulting pages are placed
 * @mapping:	The address_space to search
 * @start:	The starting page index
 * @nr_pages:	The maximum number of pages
 *
 * pagevec_lookup() will search for and return a group of up to @nr_pages pages
 * in the mapping.  The pages are placed in @pvec.  pagevec_lookup() takes a
 * reference against the pages in @pvec.
 *
 * The search returns a group of mapping-contiguous pages with ascending
 * indexes.  There may be holes in the indices due to not-present pages.
 *
 * pagevec_lookup() returns the number of pages which were found.
 */
unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping,
		pgoff_t start, unsigned nr_pages)
{
	pvec->nr = find_get_pages(mapping, start, nr_pages, pvec->pages);
	return pagevec_count(pvec);
}
EXPORT_SYMBOL(pagevec_lookup);

unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping,
		pgoff_t *index, int tag, unsigned nr_pages)
{
	pvec->nr = find_get_pages_tag(mapping, index, tag,
					nr_pages, pvec->pages);
	return pagevec_count(pvec);
}
EXPORT_SYMBOL(pagevec_lookup_tag);

/*
 * Perform any setup for the swap system
 */
void __init swap_setup(void)
{
	unsigned long megs = totalram_pages >> (20 - PAGE_SHIFT);
#ifdef CONFIG_SWAP
	int i;

	if (bdi_init(swapper_spaces[0].backing_dev_info))
		panic("Failed to init swap bdi");
	for (i = 0; i < MAX_SWAPFILES; i++) {
		spin_lock_init(&swapper_spaces[i].tree_lock);
		INIT_LIST_HEAD(&swapper_spaces[i].i_mmap_nonlinear);
	}
#endif

	/* Use a smaller cluster for small-memory machines */
	if (megs < 16)
		page_cluster = 2;
	else
		page_cluster = 3;
	/*
	 * Right now other parts of the system means that we
	 * _really_ don't want to cluster much more
	 */
}