aboutsummaryrefslogtreecommitdiff
path: root/mm/compaction.c
blob: 9a3e351da29b797817d7311b1e70ad6618b7edbb (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
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
/*
 * linux/mm/compaction.c
 *
 * Memory compaction for the reduction of external fragmentation. Note that
 * this heavily depends upon page migration to do all the real heavy
 * lifting
 *
 * Copyright IBM Corp. 2007-2010 Mel Gorman <mel@csn.ul.ie>
 */
#include <linux/swap.h>
#include <linux/migrate.h>
#include <linux/compaction.h>
#include <linux/mm_inline.h>
#include <linux/backing-dev.h>
#include <linux/sysctl.h>
#include <linux/sysfs.h>
#include <linux/balloon_compaction.h>
#include <linux/page-isolation.h>
#include "internal.h"

#ifdef CONFIG_COMPACTION
static inline void count_compact_event(enum vm_event_item item)
{
	count_vm_event(item);
}

static inline void count_compact_events(enum vm_event_item item, long delta)
{
	count_vm_events(item, delta);
}
#else
#define count_compact_event(item) do { } while (0)
#define count_compact_events(item, delta) do { } while (0)
#endif

#if defined CONFIG_COMPACTION || defined CONFIG_CMA

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

static unsigned long release_freepages(struct list_head *freelist)
{
	struct page *page, *next;
	unsigned long count = 0;

	list_for_each_entry_safe(page, next, freelist, lru) {
		list_del(&page->lru);
		__free_page(page);
		count++;
	}

	return count;
}

static void map_pages(struct list_head *list)
{
	struct page *page;

	list_for_each_entry(page, list, lru) {
		arch_alloc_page(page, 0);
		kernel_map_pages(page, 1, 1);
	}
}

static inline bool migrate_async_suitable(int migratetype)
{
	return is_migrate_cma(migratetype) || migratetype == MIGRATE_MOVABLE;
}

#ifdef CONFIG_COMPACTION
/* Returns true if the pageblock should be scanned for pages to isolate. */
static inline bool isolation_suitable(struct compact_control *cc,
					struct page *page)
{
	if (cc->ignore_skip_hint)
		return true;

	return !get_pageblock_skip(page);
}

/*
 * This function is called to clear all cached information on pageblocks that
 * should be skipped for page isolation when the migrate and free page scanner
 * meet.
 */
static void __reset_isolation_suitable(struct zone *zone)
{
	unsigned long start_pfn = zone->zone_start_pfn;
	unsigned long end_pfn = zone_end_pfn(zone);
	unsigned long pfn;

	zone->compact_cached_migrate_pfn = start_pfn;
	zone->compact_cached_free_pfn = end_pfn;
	zone->compact_blockskip_flush = false;

	/* Walk the zone and mark every pageblock as suitable for isolation */
	for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
		struct page *page;

		cond_resched();

		if (!pfn_valid(pfn))
			continue;

		page = pfn_to_page(pfn);
		if (zone != page_zone(page))
			continue;

		clear_pageblock_skip(page);
	}
}

void reset_isolation_suitable(pg_data_t *pgdat)
{
	int zoneid;

	for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
		struct zone *zone = &pgdat->node_zones[zoneid];
		if (!populated_zone(zone))
			continue;

		/* Only flush if a full compaction finished recently */
		if (zone->compact_blockskip_flush)
			__reset_isolation_suitable(zone);
	}
}

/*
 * If no pages were isolated then mark this pageblock to be skipped in the
 * future. The information is later cleared by __reset_isolation_suitable().
 */
static void update_pageblock_skip(struct compact_control *cc,
			struct page *page, unsigned long nr_isolated,
			bool migrate_scanner)
{
	struct zone *zone = cc->zone;

	if (cc->ignore_skip_hint)
		return;

	if (!page)
		return;

	if (!nr_isolated) {
		unsigned long pfn = page_to_pfn(page);
		set_pageblock_skip(page);

		/* Update where compaction should restart */
		if (migrate_scanner) {
			if (!cc->finished_update_migrate &&
			    pfn > zone->compact_cached_migrate_pfn)
				zone->compact_cached_migrate_pfn = pfn;
		} else {
			if (!cc->finished_update_free &&
			    pfn < zone->compact_cached_free_pfn)
				zone->compact_cached_free_pfn = pfn;
		}
	}
}
#else
static inline bool isolation_suitable(struct compact_control *cc,
					struct page *page)
{
	return true;
}

static void update_pageblock_skip(struct compact_control *cc,
			struct page *page, unsigned long nr_isolated,
			bool migrate_scanner)
{
}
#endif /* CONFIG_COMPACTION */

static inline bool should_release_lock(spinlock_t *lock)
{
	return need_resched() || spin_is_contended(lock);
}

/*
 * Compaction requires the taking of some coarse locks that are potentially
 * very heavily contended. Check if the process needs to be scheduled or
 * if the lock is contended. For async compaction, back out in the event
 * if contention is severe. For sync compaction, schedule.
 *
 * Returns true if the lock is held.
 * Returns false if the lock is released and compaction should abort
 */
static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags,
				      bool locked, struct compact_control *cc)
{
	if (should_release_lock(lock)) {
		if (locked) {
			spin_unlock_irqrestore(lock, *flags);
			locked = false;
		}

		/* async aborts if taking too long or contended */
		if (!cc->sync) {
			cc->contended = true;
			return false;
		}

		cond_resched();
	}

	if (!locked)
		spin_lock_irqsave(lock, *flags);
	return true;
}

static inline bool compact_trylock_irqsave(spinlock_t *lock,
			unsigned long *flags, struct compact_control *cc)
{
	return compact_checklock_irqsave(lock, flags, false, cc);
}

/* Returns true if the page is within a block suitable for migration to */
static bool suitable_migration_target(struct page *page)
{
	int migratetype = get_pageblock_migratetype(page);

	/* Don't interfere with memory hot-remove or the min_free_kbytes blocks */
	if (migratetype == MIGRATE_RESERVE)
		return false;

	if (is_migrate_isolate(migratetype))
		return false;

	/* If the page is a large free page, then allow migration */
	if (PageBuddy(page) && page_order(page) >= pageblock_order)
		return true;

	/* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */
	if (migrate_async_suitable(migratetype))
		return true;

	/* Otherwise skip the block */
	return false;
}

/*
 * Isolate free pages onto a private freelist. Caller must hold zone->lock.
 * If @strict is true, will abort returning 0 on any invalid PFNs or non-free
 * pages inside of the pageblock (even though it may still end up isolating
 * some pages).
 */
static unsigned long isolate_freepages_block(struct compact_control *cc,
				unsigned long blockpfn,
				unsigned long end_pfn,
				struct list_head *freelist,
				bool strict)
{
	int nr_scanned = 0, total_isolated = 0;
	struct page *cursor, *valid_page = NULL;
	unsigned long nr_strict_required = end_pfn - blockpfn;
	unsigned long flags;
	bool locked = false;

	cursor = pfn_to_page(blockpfn);

	/* Isolate free pages. */
	for (; blockpfn < end_pfn; blockpfn++, cursor++) {
		int isolated, i;
		struct page *page = cursor;

		nr_scanned++;
		if (!pfn_valid_within(blockpfn))
			continue;
		if (!valid_page)
			valid_page = page;
		if (!PageBuddy(page))
			continue;

		/*
		 * The zone lock must be held to isolate freepages.
		 * Unfortunately this is a very coarse lock and can be
		 * heavily contended if there are parallel allocations
		 * or parallel compactions. For async compaction do not
		 * spin on the lock and we acquire the lock as late as
		 * possible.
		 */
		locked = compact_checklock_irqsave(&cc->zone->lock, &flags,
								locked, cc);
		if (!locked)
			break;

		/* Recheck this is a suitable migration target under lock */
		if (!strict && !suitable_migration_target(page))
			break;

		/* Recheck this is a buddy page under lock */
		if (!PageBuddy(page))
			continue;

		/* Found a free page, break it into order-0 pages */
		isolated = split_free_page(page);
		if (!isolated && strict)
			break;
		total_isolated += isolated;
		for (i = 0; i < isolated; i++) {
			list_add(&page->lru, freelist);
			page++;
		}

		/* If a page was split, advance to the end of it */
		if (isolated) {
			blockpfn += isolated - 1;
			cursor += isolated - 1;
		}
	}

	trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated);

	/*
	 * If strict isolation is requested by CMA then check that all the
	 * pages requested were isolated. If there were any failures, 0 is
	 * returned and CMA will fail.
	 */
	if (strict && nr_strict_required > total_isolated)
		total_isolated = 0;

	if (locked)
		spin_unlock_irqrestore(&cc->zone->lock, flags);

	/* Update the pageblock-skip if the whole pageblock was scanned */
	if (blockpfn == end_pfn)
		update_pageblock_skip(cc, valid_page, total_isolated, false);

	count_compact_events(COMPACTFREE_SCANNED, nr_scanned);
	if (total_isolated)
		count_compact_events(COMPACTISOLATED, total_isolated);
	return total_isolated;
}

/**
 * isolate_freepages_range() - isolate free pages.
 * @start_pfn: The first PFN to start isolating.
 * @end_pfn:   The one-past-last PFN.
 *
 * Non-free pages, invalid PFNs, or zone boundaries within the
 * [start_pfn, end_pfn) range are considered errors, cause function to
 * undo its actions and return zero.
 *
 * Otherwise, function returns one-past-the-last PFN of isolated page
 * (which may be greater then end_pfn if end fell in a middle of
 * a free page).
 */
unsigned long
isolate_freepages_range(struct compact_control *cc,
			unsigned long start_pfn, unsigned long end_pfn)
{
	unsigned long isolated, pfn, block_end_pfn;
	LIST_HEAD(freelist);

	for (pfn = start_pfn; pfn < end_pfn; pfn += isolated) {
		if (!pfn_valid(pfn) || cc->zone != page_zone(pfn_to_page(pfn)))
			break;

		/*
		 * On subsequent iterations ALIGN() is actually not needed,
		 * but we keep it that we not to complicate the code.
		 */
		block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
		block_end_pfn = min(block_end_pfn, end_pfn);

		isolated = isolate_freepages_block(cc, pfn, block_end_pfn,
						   &freelist, true);

		/*
		 * In strict mode, isolate_freepages_block() returns 0 if
		 * there are any holes in the block (ie. invalid PFNs or
		 * non-free pages).
		 */
		if (!isolated)
			break;

		/*
		 * If we managed to isolate pages, it is always (1 << n) *
		 * pageblock_nr_pages for some non-negative n.  (Max order
		 * page may span two pageblocks).
		 */
	}

	/* split_free_page does not map the pages */
	map_pages(&freelist);

	if (pfn < end_pfn) {
		/* Loop terminated early, cleanup. */
		release_freepages(&freelist);
		return 0;
	}

	/* We don't use freelists for anything. */
	return pfn;
}

/* Update the number of anon and file isolated pages in the zone */
static void acct_isolated(struct zone *zone, bool locked, struct compact_control *cc)
{
	struct page *page;
	unsigned int count[2] = { 0, };

	list_for_each_entry(page, &cc->migratepages, lru)
		count[!!page_is_file_cache(page)]++;

	/* If locked we can use the interrupt unsafe versions */
	if (locked) {
		__mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
		__mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
	} else {
		mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
		mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
	}
}

/* Similar to reclaim, but different enough that they don't share logic */
static bool too_many_isolated(struct zone *zone)
{
	unsigned long active, inactive, isolated;

	inactive = zone_page_state(zone, NR_INACTIVE_FILE) +
					zone_page_state(zone, NR_INACTIVE_ANON);
	active = zone_page_state(zone, NR_ACTIVE_FILE) +
					zone_page_state(zone, NR_ACTIVE_ANON);
	isolated = zone_page_state(zone, NR_ISOLATED_FILE) +
					zone_page_state(zone, NR_ISOLATED_ANON);

	return isolated > (inactive + active) / 2;
}

/**
 * isolate_migratepages_range() - isolate all migrate-able pages in range.
 * @zone:	Zone pages are in.
 * @cc:		Compaction control structure.
 * @low_pfn:	The first PFN of the range.
 * @end_pfn:	The one-past-the-last PFN of the range.
 * @unevictable: true if it allows to isolate unevictable pages
 *
 * Isolate all pages that can be migrated from the range specified by
 * [low_pfn, end_pfn).  Returns zero if there is a fatal signal
 * pending), otherwise PFN of the first page that was not scanned
 * (which may be both less, equal to or more then end_pfn).
 *
 * Assumes that cc->migratepages is empty and cc->nr_migratepages is
 * zero.
 *
 * Apart from cc->migratepages and cc->nr_migratetypes this function
 * does not modify any cc's fields, in particular it does not modify
 * (or read for that matter) cc->migrate_pfn.
 */
unsigned long
isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
		unsigned long low_pfn, unsigned long end_pfn, bool unevictable)
{
	unsigned long last_pageblock_nr = 0, pageblock_nr;
	unsigned long nr_scanned = 0, nr_isolated = 0;
	struct list_head *migratelist = &cc->migratepages;
	isolate_mode_t mode = 0;
	struct lruvec *lruvec;
	unsigned long flags;
	bool locked = false;
	struct page *page = NULL, *valid_page = NULL;

	/*
	 * Ensure that there are not too many pages isolated from the LRU
	 * list by either parallel reclaimers or compaction. If there are,
	 * delay for some time until fewer pages are isolated
	 */
	while (unlikely(too_many_isolated(zone))) {
		/* async migration should just abort */
		if (!cc->sync)
			return 0;

		congestion_wait(BLK_RW_ASYNC, HZ/10);

		if (fatal_signal_pending(current))
			return 0;
	}

	/* Time to isolate some pages for migration */
	cond_resched();
	for (; low_pfn < end_pfn; low_pfn++) {
		/* give a chance to irqs before checking need_resched() */
		if (locked && !((low_pfn+1) % SWAP_CLUSTER_MAX)) {
			if (should_release_lock(&zone->lru_lock)) {
				spin_unlock_irqrestore(&zone->lru_lock, flags);
				locked = false;
			}
		}

		/*
		 * migrate_pfn does not necessarily start aligned to a
		 * pageblock. Ensure that pfn_valid is called when moving
		 * into a new MAX_ORDER_NR_PAGES range in case of large
		 * memory holes within the zone
		 */
		if ((low_pfn & (MAX_ORDER_NR_PAGES - 1)) == 0) {
			if (!pfn_valid(low_pfn)) {
				low_pfn += MAX_ORDER_NR_PAGES - 1;
				continue;
			}
		}

		if (!pfn_valid_within(low_pfn))
			continue;
		nr_scanned++;

		/*
		 * Get the page and ensure the page is within the same zone.
		 * See the comment in isolate_freepages about overlapping
		 * nodes. It is deliberate that the new zone lock is not taken
		 * as memory compaction should not move pages between nodes.
		 */
		page = pfn_to_page(low_pfn);
		if (page_zone(page) != zone)
			continue;

		if (!valid_page)
			valid_page = page;

		/* If isolation recently failed, do not retry */
		pageblock_nr = low_pfn >> pageblock_order;
		if (!isolation_suitable(cc, page))
			goto next_pageblock;

		/* Skip if free */
		if (PageBuddy(page))
			continue;

		/*
		 * For async migration, also only scan in MOVABLE blocks. Async
		 * migration is optimistic to see if the minimum amount of work
		 * satisfies the allocation
		 */
		if (!cc->sync && last_pageblock_nr != pageblock_nr &&
		    !migrate_async_suitable(get_pageblock_migratetype(page))) {
			cc->finished_update_migrate = true;
			goto next_pageblock;
		}

		/*
		 * Check may be lockless but that's ok as we recheck later.
		 * It's possible to migrate LRU pages and balloon pages
		 * Skip any other type of page
		 */
		if (!PageLRU(page)) {
			if (unlikely(balloon_page_movable(page))) {
				if (locked && balloon_page_isolate(page)) {
					/* Successfully isolated */
					cc->finished_update_migrate = true;
					list_add(&page->lru, migratelist);
					cc->nr_migratepages++;
					nr_isolated++;
					goto check_compact_cluster;
				}
			}
			continue;
		}

		/*
		 * PageLRU is set. lru_lock normally excludes isolation
		 * splitting and collapsing (collapsing has already happened
		 * if PageLRU is set) but the lock is not necessarily taken
		 * here and it is wasteful to take it just to check transhuge.
		 * Check TransHuge without lock and skip the whole pageblock if
		 * it's either a transhuge or hugetlbfs page, as calling
		 * compound_order() without preventing THP from splitting the
		 * page underneath us may return surprising results.
		 */
		if (PageTransHuge(page)) {
			if (!locked)
				goto next_pageblock;
			low_pfn += (1 << compound_order(page)) - 1;
			continue;
		}

		/* Check if it is ok to still hold the lock */
		locked = compact_checklock_irqsave(&zone->lru_lock, &flags,
								locked, cc);
		if (!locked || fatal_signal_pending(current))
			break;

		/* Recheck PageLRU and PageTransHuge under lock */
		if (!PageLRU(page))
			continue;
		if (PageTransHuge(page)) {
			low_pfn += (1 << compound_order(page)) - 1;
			continue;
		}

		if (!cc->sync)
			mode |= ISOLATE_ASYNC_MIGRATE;

		if (unevictable)
			mode |= ISOLATE_UNEVICTABLE;

		lruvec = mem_cgroup_page_lruvec(page, zone);

		/* Try isolate the page */
		if (__isolate_lru_page(page, mode) != 0)
			continue;

		VM_BUG_ON(PageTransCompound(page));

		/* Successfully isolated */
		cc->finished_update_migrate = true;
		del_page_from_lru_list(page, lruvec, page_lru(page));
		list_add(&page->lru, migratelist);
		cc->nr_migratepages++;
		nr_isolated++;

check_compact_cluster:
		/* Avoid isolating too much */
		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) {
			++low_pfn;
			break;
		}

		continue;

next_pageblock:
		low_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages) - 1;
		last_pageblock_nr = pageblock_nr;
	}

	acct_isolated(zone, locked, cc);

	if (locked)
		spin_unlock_irqrestore(&zone->lru_lock, flags);

	/* Update the pageblock-skip if the whole pageblock was scanned */
	if (low_pfn == end_pfn)
		update_pageblock_skip(cc, valid_page, nr_isolated, true);

	trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);

	count_compact_events(COMPACTMIGRATE_SCANNED, nr_scanned);
	if (nr_isolated)
		count_compact_events(COMPACTISOLATED, nr_isolated);

	return low_pfn;
}

#endif /* CONFIG_COMPACTION || CONFIG_CMA */
#ifdef CONFIG_COMPACTION
/*
 * Based on information in the current compact_control, find blocks
 * suitable for isolating free pages from and then isolate them.
 */
static void isolate_freepages(struct zone *zone,
				struct compact_control *cc)
{
	struct page *page;
	unsigned long high_pfn, low_pfn, pfn, z_end_pfn, end_pfn;
	int nr_freepages = cc->nr_freepages;
	struct list_head *freelist = &cc->freepages;

	/*
	 * Initialise the free scanner. The starting point is where we last
	 * scanned from (or the end of the zone if starting). The low point
	 * is the end of the pageblock the migration scanner is using.
	 */
	pfn = cc->free_pfn;
	low_pfn = cc->migrate_pfn + pageblock_nr_pages;

	/*
	 * Take care that if the migration scanner is at the end of the zone
	 * that the free scanner does not accidentally move to the next zone
	 * in the next isolation cycle.
	 */
	high_pfn = min(low_pfn, pfn);

	z_end_pfn = zone_end_pfn(zone);

	/*
	 * Isolate free pages until enough are available to migrate the
	 * pages on cc->migratepages. We stop searching if the migrate
	 * and free page scanners meet or enough free pages are isolated.
	 */
	for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages;
					pfn -= pageblock_nr_pages) {
		unsigned long isolated;

		if (!pfn_valid(pfn))
			continue;

		/*
		 * Check for overlapping nodes/zones. It's possible on some
		 * configurations to have a setup like
		 * node0 node1 node0
		 * i.e. it's possible that all pages within a zones range of
		 * pages do not belong to a single zone.
		 */
		page = pfn_to_page(pfn);
		if (page_zone(page) != zone)
			continue;

		/* Check the block is suitable for migration */
		if (!suitable_migration_target(page))
			continue;

		/* If isolation recently failed, do not retry */
		if (!isolation_suitable(cc, page))
			continue;

		/* Found a block suitable for isolating free pages from */
		isolated = 0;

		/*
		 * As pfn may not start aligned, pfn+pageblock_nr_page
		 * may cross a MAX_ORDER_NR_PAGES boundary and miss
		 * a pfn_valid check. Ensure isolate_freepages_block()
		 * only scans within a pageblock
		 */
		end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
		end_pfn = min(end_pfn, z_end_pfn);
		isolated = isolate_freepages_block(cc, pfn, end_pfn,
						   freelist, false);
		nr_freepages += isolated;

		/*
		 * Record the highest PFN we isolated pages from. When next
		 * looking for free pages, the search will restart here as
		 * page migration may have returned some pages to the allocator
		 */
		if (isolated) {
			cc->finished_update_free = true;
			high_pfn = max(high_pfn, pfn);
		}
	}

	/* split_free_page does not map the pages */
	map_pages(freelist);

	cc->free_pfn = high_pfn;
	cc->nr_freepages = nr_freepages;
}

/*
 * This is a migrate-callback that "allocates" freepages by taking pages
 * from the isolated freelists in the block we are migrating to.
 */
static struct page *compaction_alloc(struct page *migratepage,
					unsigned long data,
					int **result)
{
	struct compact_control *cc = (struct compact_control *)data;
	struct page *freepage;

	/* Isolate free pages if necessary */
	if (list_empty(&cc->freepages)) {
		isolate_freepages(cc->zone, cc);

		if (list_empty(&cc->freepages))
			return NULL;
	}

	freepage = list_entry(cc->freepages.next, struct page, lru);
	list_del(&freepage->lru);
	cc->nr_freepages--;

	return freepage;
}

/*
 * We cannot control nr_migratepages and nr_freepages fully when migration is
 * running as migrate_pages() has no knowledge of compact_control. When
 * migration is complete, we count the number of pages on the lists by hand.
 */
static void update_nr_listpages(struct compact_control *cc)
{
	int nr_migratepages = 0;
	int nr_freepages = 0;
	struct page *page;

	list_for_each_entry(page, &cc->migratepages, lru)
		nr_migratepages++;
	list_for_each_entry(page, &cc->freepages, lru)
		nr_freepages++;

	cc->nr_migratepages = nr_migratepages;
	cc->nr_freepages = nr_freepages;
}

/* possible outcome of isolate_migratepages */
typedef enum {
	ISOLATE_ABORT,		/* Abort compaction now */
	ISOLATE_NONE,		/* No pages isolated, continue scanning */
	ISOLATE_SUCCESS,	/* Pages isolated, migrate */
} isolate_migrate_t;

/*
 * Isolate all pages that can be migrated from the block pointed to by
 * the migrate scanner within compact_control.
 */
static isolate_migrate_t isolate_migratepages(struct zone *zone,
					struct compact_control *cc)
{
	unsigned long low_pfn, end_pfn;

	/* Do not scan outside zone boundaries */
	low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn);

	/* Only scan within a pageblock boundary */
	end_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages);

	/* Do not cross the free scanner or scan within a memory hole */
	if (end_pfn > cc->free_pfn || !pfn_valid(low_pfn)) {
		cc->migrate_pfn = end_pfn;
		return ISOLATE_NONE;
	}

	/* Perform the isolation */
	low_pfn = isolate_migratepages_range(zone, cc, low_pfn, end_pfn, false);
	if (!low_pfn || cc->contended)
		return ISOLATE_ABORT;

	cc->migrate_pfn = low_pfn;

	return ISOLATE_SUCCESS;
}

static int compact_finished(struct zone *zone,
			    struct compact_control *cc)
{
	unsigned int order;
	unsigned long watermark;

	if (fatal_signal_pending(current))
		return COMPACT_PARTIAL;

	/* Compaction run completes if the migrate and free scanner meet */
	if (cc->free_pfn <= cc->migrate_pfn) {
		/*
		 * Mark that the PG_migrate_skip information should be cleared
		 * by kswapd when it goes to sleep. kswapd does not set the
		 * flag itself as the decision to be clear should be directly
		 * based on an allocation request.
		 */
		if (!current_is_kswapd())
			zone->compact_blockskip_flush = true;

		return COMPACT_COMPLETE;
	}

	/*
	 * order == -1 is expected when compacting via
	 * /proc/sys/vm/compact_memory
	 */
	if (cc->order == -1)
		return COMPACT_CONTINUE;

	/* Compaction run is not finished if the watermark is not met */
	watermark = low_wmark_pages(zone);
	watermark += (1 << cc->order);

	if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0))
		return COMPACT_CONTINUE;

	/* Direct compactor: Is a suitable page free? */
	for (order = cc->order; order < MAX_ORDER; order++) {
		struct free_area *area = &zone->free_area[order];

		/* Job done if page is free of the right migratetype */
		if (!list_empty(&area->free_list[cc->migratetype]))
			return COMPACT_PARTIAL;

		/* Job done if allocation would set block type */
		if (cc->order >= pageblock_order && area->nr_free)
			return COMPACT_PARTIAL;
	}

	return COMPACT_CONTINUE;
}

/*
 * compaction_suitable: Is this suitable to run compaction on this zone now?
 * Returns
 *   COMPACT_SKIPPED  - If there are too few free pages for compaction
 *   COMPACT_PARTIAL  - If the allocation would succeed without compaction
 *   COMPACT_CONTINUE - If compaction should run now
 */
unsigned long compaction_suitable(struct zone *zone, int order)
{
	int fragindex;
	unsigned long watermark;

	/*
	 * order == -1 is expected when compacting via
	 * /proc/sys/vm/compact_memory
	 */
	if (order == -1)
		return COMPACT_CONTINUE;

	/*
	 * Watermarks for order-0 must be met for compaction. Note the 2UL.
	 * This is because during migration, copies of pages need to be
	 * allocated and for a short time, the footprint is higher
	 */
	watermark = low_wmark_pages(zone) + (2UL << order);
	if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
		return COMPACT_SKIPPED;

	/*
	 * fragmentation index determines if allocation failures are due to
	 * low memory or external fragmentation
	 *
	 * index of -1000 implies allocations might succeed depending on
	 * watermarks
	 * index towards 0 implies failure is due to lack of memory
	 * index towards 1000 implies failure is due to fragmentation
	 *
	 * Only compact if a failure would be due to fragmentation.
	 */
	fragindex = fragmentation_index(zone, order);
	if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold)
		return COMPACT_SKIPPED;

	if (fragindex == -1000 && zone_watermark_ok(zone, order, watermark,
	    0, 0))
		return COMPACT_PARTIAL;

	return COMPACT_CONTINUE;
}

static int compact_zone(struct zone *zone, struct compact_control *cc)
{
	int ret;
	unsigned long start_pfn = zone->zone_start_pfn;
	unsigned long end_pfn = zone_end_pfn(zone);

	ret = compaction_suitable(zone, cc->order);
	switch (ret) {
	case COMPACT_PARTIAL:
	case COMPACT_SKIPPED:
		/* Compaction is likely to fail */
		return ret;
	case COMPACT_CONTINUE:
		/* Fall through to compaction */
		;
	}

	/*
	 * Setup to move all movable pages to the end of the zone. Used cached
	 * information on where the scanners should start but check that it
	 * is initialised by ensuring the values are within zone boundaries.
	 */
	cc->migrate_pfn = zone->compact_cached_migrate_pfn;
	cc->free_pfn = zone->compact_cached_free_pfn;
	if (cc->free_pfn < start_pfn || cc->free_pfn > end_pfn) {
		cc->free_pfn = end_pfn & ~(pageblock_nr_pages-1);
		zone->compact_cached_free_pfn = cc->free_pfn;
	}
	if (cc->migrate_pfn < start_pfn || cc->migrate_pfn > end_pfn) {
		cc->migrate_pfn = start_pfn;
		zone->compact_cached_migrate_pfn = cc->migrate_pfn;
	}

	/*
	 * Clear pageblock skip if there were failures recently and compaction
	 * is about to be retried after being deferred. kswapd does not do
	 * this reset as it'll reset the cached information when going to sleep.
	 */
	if (compaction_restarting(zone, cc->order) && !current_is_kswapd())
		__reset_isolation_suitable(zone);

	migrate_prep_local();

	while ((ret = compact_finished(zone, cc)) == COMPACT_CONTINUE) {
		unsigned long nr_migrate, nr_remaining;
		int err;

		switch (isolate_migratepages(zone, cc)) {
		case ISOLATE_ABORT:
			ret = COMPACT_PARTIAL;
			putback_movable_pages(&cc->migratepages);
			cc->nr_migratepages = 0;
			goto out;
		case ISOLATE_NONE:
			continue;
		case ISOLATE_SUCCESS:
			;
		}

		nr_migrate = cc->nr_migratepages;
		err = migrate_pages(&cc->migratepages, compaction_alloc,
				(unsigned long)cc,
				cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC,
				MR_COMPACTION);
		update_nr_listpages(cc);
		nr_remaining = cc->nr_migratepages;

		trace_mm_compaction_migratepages(nr_migrate - nr_remaining,
						nr_remaining);

		/* Release isolated pages not migrated */
		if (err) {
			putback_movable_pages(&cc->migratepages);
			cc->nr_migratepages = 0;
			if (err == -ENOMEM) {
				ret = COMPACT_PARTIAL;
				goto out;
			}
		}
	}

out:
	/* Release free pages and check accounting */
	cc->nr_freepages -= release_freepages(&cc->freepages);
	VM_BUG_ON(cc->nr_freepages != 0);

	return ret;
}

static unsigned long compact_zone_order(struct zone *zone,
				 int order, gfp_t gfp_mask,
				 bool sync, bool *contended)
{
	unsigned long ret;
	struct compact_control cc = {
		.nr_freepages = 0,
		.nr_migratepages = 0,
		.order = order,
		.migratetype = allocflags_to_migratetype(gfp_mask),
		.zone = zone,
		.sync = sync,
	};
	INIT_LIST_HEAD(&cc.freepages);
	INIT_LIST_HEAD(&cc.migratepages);

	ret = compact_zone(zone, &cc);

	VM_BUG_ON(!list_empty(&cc.freepages));
	VM_BUG_ON(!list_empty(&cc.migratepages));

	*contended = cc.contended;
	return ret;
}

int sysctl_extfrag_threshold = 500;

/**
 * try_to_compact_pages - Direct compact to satisfy a high-order allocation
 * @zonelist: The zonelist used for the current allocation
 * @order: The order of the current allocation
 * @gfp_mask: The GFP mask of the current allocation
 * @nodemask: The allowed nodes to allocate from
 * @sync: Whether migration is synchronous or not
 * @contended: Return value that is true if compaction was aborted due to lock contention
 * @page: Optionally capture a free page of the requested order during compaction
 *
 * This is the main entry point for direct page compaction.
 */
unsigned long try_to_compact_pages(struct zonelist *zonelist,
			int order, gfp_t gfp_mask, nodemask_t *nodemask,
			bool sync, bool *contended)
{
	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
	int may_enter_fs = gfp_mask & __GFP_FS;
	int may_perform_io = gfp_mask & __GFP_IO;
	struct zoneref *z;
	struct zone *zone;
	int rc = COMPACT_SKIPPED;
	int alloc_flags = 0;

	/* Check if the GFP flags allow compaction */
	if (!order || !may_enter_fs || !may_perform_io)
		return rc;

	count_compact_event(COMPACTSTALL);

#ifdef CONFIG_CMA
	if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
		alloc_flags |= ALLOC_CMA;
#endif
	/* Compact each zone in the list */
	for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
								nodemask) {
		int status;

		status = compact_zone_order(zone, order, gfp_mask, sync,
						contended);
		rc = max(status, rc);

		/* If a normal allocation would succeed, stop compacting */
		if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0,
				      alloc_flags))
			break;
	}

	return rc;
}


/* Compact all zones within a node */
static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
{
	int zoneid;
	struct zone *zone;

	for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {

		zone = &pgdat->node_zones[zoneid];
		if (!populated_zone(zone))
			continue;

		cc->nr_freepages = 0;
		cc->nr_migratepages = 0;
		cc->zone = zone;
		INIT_LIST_HEAD(&cc->freepages);
		INIT_LIST_HEAD(&cc->migratepages);

		if (cc->order == -1 || !compaction_deferred(zone, cc->order))
			compact_zone(zone, cc);

		if (cc->order > 0) {
			int ok = zone_watermark_ok(zone, cc->order,
						low_wmark_pages(zone), 0, 0);
			if (ok && cc->order >= zone->compact_order_failed)
				zone->compact_order_failed = cc->order + 1;
			/* Currently async compaction is never deferred. */
			else if (!ok && cc->sync)
				defer_compaction(zone, cc->order);
		}

		VM_BUG_ON(!list_empty(&cc->freepages));
		VM_BUG_ON(!list_empty(&cc->migratepages));
	}
}

void compact_pgdat(pg_data_t *pgdat, int order)
{
	struct compact_control cc = {
		.order = order,
		.sync = false,
	};

	__compact_pgdat(pgdat, &cc);
}

static void compact_node(int nid)
{
	struct compact_control cc = {
		.order = -1,
		.sync = true,
	};

	__compact_pgdat(NODE_DATA(nid), &cc);
}

/* Compact all nodes in the system */
static void compact_nodes(void)
{
	int nid;

	/* Flush pending updates to the LRU lists */
	lru_add_drain_all();

	for_each_online_node(nid)
		compact_node(nid);
}

/* The written value is actually unused, all memory is compacted */
int sysctl_compact_memory;

/* This is the entry point for compacting all nodes via /proc/sys/vm */
int sysctl_compaction_handler(struct ctl_table *table, int write,
			void __user *buffer, size_t *length, loff_t *ppos)
{
	if (write)
		compact_nodes();

	return 0;
}

int sysctl_extfrag_handler(struct ctl_table *table, int write,
			void __user *buffer, size_t *length, loff_t *ppos)
{
	proc_dointvec_minmax(table, write, buffer, length, ppos);

	return 0;
}

#if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
ssize_t sysfs_compact_node(struct device *dev,
			struct device_attribute *attr,
			const char *buf, size_t count)
{
	int nid = dev->id;

	if (nid >= 0 && nid < nr_node_ids && node_online(nid)) {
		/* Flush pending updates to the LRU lists */
		lru_add_drain_all();

		compact_node(nid);
	}

	return count;
}
static DEVICE_ATTR(compact, S_IWUSR, NULL, sysfs_compact_node);

int compaction_register_node(struct node *node)
{
	return device_create_file(&node->dev, &dev_attr_compact);
}

void compaction_unregister_node(struct node *node)
{
	return device_remove_file(&node->dev, &dev_attr_compact);
}
#endif /* CONFIG_SYSFS && CONFIG_NUMA */

#endif /* CONFIG_COMPACTION */