forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
compaction.c
2063 lines (1735 loc) · 56.2 KB
/
compaction.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* linux/mm/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 <[email protected]>
*/
#include <linux/cpu.h>
#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/page-isolation.h>
#include <linux/kasan.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/page_owner.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>
#define block_start_pfn(pfn, order) round_down(pfn, 1UL << (order))
#define block_end_pfn(pfn, order) ALIGN((pfn) + 1, 1UL << (order))
#define pageblock_start_pfn(pfn) block_start_pfn(pfn, pageblock_order)
#define pageblock_end_pfn(pfn) block_end_pfn(pfn, pageblock_order)
static unsigned long release_freepages(struct list_head *freelist)
{
struct page *page, *next;
unsigned long high_pfn = 0;
list_for_each_entry_safe(page, next, freelist, lru) {
unsigned long pfn = page_to_pfn(page);
list_del(&page->lru);
__free_page(page);
if (pfn > high_pfn)
high_pfn = pfn;
}
return high_pfn;
}
static void map_pages(struct list_head *list)
{
unsigned int i, order, nr_pages;
struct page *page, *next;
LIST_HEAD(tmp_list);
list_for_each_entry_safe(page, next, list, lru) {
list_del(&page->lru);
order = page_private(page);
nr_pages = 1 << order;
post_alloc_hook(page, order, __GFP_MOVABLE);
if (order)
split_page(page, order);
for (i = 0; i < nr_pages; i++) {
list_add(&page->lru, &tmp_list);
page++;
}
}
list_splice(&tmp_list, list);
}
static inline bool migrate_async_suitable(int migratetype)
{
return is_migrate_cma(migratetype) || migratetype == MIGRATE_MOVABLE;
}
#ifdef CONFIG_COMPACTION
int PageMovable(struct page *page)
{
struct address_space *mapping;
VM_BUG_ON_PAGE(!PageLocked(page), page);
if (!__PageMovable(page))
return 0;
mapping = page_mapping(page);
if (mapping && mapping->a_ops && mapping->a_ops->isolate_page)
return 1;
return 0;
}
EXPORT_SYMBOL(PageMovable);
void __SetPageMovable(struct page *page, struct address_space *mapping)
{
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE((unsigned long)mapping & PAGE_MAPPING_MOVABLE, page);
page->mapping = (void *)((unsigned long)mapping | PAGE_MAPPING_MOVABLE);
}
EXPORT_SYMBOL(__SetPageMovable);
void __ClearPageMovable(struct page *page)
{
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(!PageMovable(page), page);
/*
* Clear registered address_space val with keeping PAGE_MAPPING_MOVABLE
* flag so that VM can catch up released page by driver after isolation.
* With it, VM migration doesn't try to put it back.
*/
page->mapping = (void *)((unsigned long)page->mapping &
PAGE_MAPPING_MOVABLE);
}
EXPORT_SYMBOL(__ClearPageMovable);
/* Do not skip compaction more than 64 times */
#define COMPACT_MAX_DEFER_SHIFT 6
/*
* Compaction is deferred when compaction fails to result in a page
* allocation success. 1 << compact_defer_limit compactions are skipped up
* to a limit of 1 << COMPACT_MAX_DEFER_SHIFT
*/
void defer_compaction(struct zone *zone, int order)
{
zone->compact_considered = 0;
zone->compact_defer_shift++;
if (order < zone->compact_order_failed)
zone->compact_order_failed = order;
if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT)
zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT;
trace_mm_compaction_defer_compaction(zone, order);
}
/* Returns true if compaction should be skipped this time */
bool compaction_deferred(struct zone *zone, int order)
{
unsigned long defer_limit = 1UL << zone->compact_defer_shift;
if (order < zone->compact_order_failed)
return false;
/* Avoid possible overflow */
if (++zone->compact_considered > defer_limit)
zone->compact_considered = defer_limit;
if (zone->compact_considered >= defer_limit)
return false;
trace_mm_compaction_deferred(zone, order);
return true;
}
/*
* Update defer tracking counters after successful compaction of given order,
* which means an allocation either succeeded (alloc_success == true) or is
* expected to succeed.
*/
void compaction_defer_reset(struct zone *zone, int order,
bool alloc_success)
{
if (alloc_success) {
zone->compact_considered = 0;
zone->compact_defer_shift = 0;
}
if (order >= zone->compact_order_failed)
zone->compact_order_failed = order + 1;
trace_mm_compaction_defer_reset(zone, order);
}
/* Returns true if restarting compaction after many failures */
bool compaction_restarting(struct zone *zone, int order)
{
if (order < zone->compact_order_failed)
return false;
return zone->compact_defer_shift == COMPACT_MAX_DEFER_SHIFT &&
zone->compact_considered >= 1UL << zone->compact_defer_shift;
}
/* 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);
}
static void reset_cached_positions(struct zone *zone)
{
zone->compact_cached_migrate_pfn[0] = zone->zone_start_pfn;
zone->compact_cached_migrate_pfn[1] = zone->zone_start_pfn;
zone->compact_cached_free_pfn =
pageblock_start_pfn(zone_end_pfn(zone) - 1);
}
/*
* 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_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);
}
reset_cached_positions(zone);
}
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;
unsigned long pfn;
if (cc->ignore_skip_hint)
return;
if (!page)
return;
if (nr_isolated)
return;
set_pageblock_skip(page);
pfn = page_to_pfn(page);
/* Update where async and sync compaction should restart */
if (migrate_scanner) {
if (pfn > zone->compact_cached_migrate_pfn[0])
zone->compact_cached_migrate_pfn[0] = pfn;
if (cc->mode != MIGRATE_ASYNC &&
pfn > zone->compact_cached_migrate_pfn[1])
zone->compact_cached_migrate_pfn[1] = pfn;
} else {
if (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 */
/*
* Compaction requires the taking of some coarse locks that are potentially
* very heavily contended. For async compaction, back out if the lock cannot
* be taken immediately. For sync compaction, spin on the lock if needed.
*
* Returns true if the lock is held
* Returns false if the lock is not held and compaction should abort
*/
static bool compact_trylock_irqsave(spinlock_t *lock, unsigned long *flags,
struct compact_control *cc)
{
if (cc->mode == MIGRATE_ASYNC) {
if (!spin_trylock_irqsave(lock, *flags)) {
cc->contended = true;
return false;
}
} else {
spin_lock_irqsave(lock, *flags);
}
return true;
}
/*
* Compaction requires the taking of some coarse locks that are potentially
* very heavily contended. The lock should be periodically unlocked to avoid
* having disabled IRQs for a long time, even when there is nobody waiting on
* the lock. It might also be that allowing the IRQs will result in
* need_resched() becoming true. If scheduling is needed, async compaction
* aborts. Sync compaction schedules.
* Either compaction type will also abort if a fatal signal is pending.
* In either case if the lock was locked, it is dropped and not regained.
*
* Returns true if compaction should abort due to fatal signal pending, or
* async compaction due to need_resched()
* Returns false when compaction can continue (sync compaction might have
* scheduled)
*/
static bool compact_unlock_should_abort(spinlock_t *lock,
unsigned long flags, bool *locked, struct compact_control *cc)
{
if (*locked) {
spin_unlock_irqrestore(lock, flags);
*locked = false;
}
if (fatal_signal_pending(current)) {
cc->contended = true;
return true;
}
if (need_resched()) {
if (cc->mode == MIGRATE_ASYNC) {
cc->contended = true;
return true;
}
cond_resched();
}
return false;
}
/*
* Aside from avoiding lock contention, compaction also periodically checks
* need_resched() and either schedules in sync compaction or aborts async
* compaction. This is similar to what compact_unlock_should_abort() does, but
* is used where no lock is concerned.
*
* Returns false when no scheduling was needed, or sync compaction scheduled.
* Returns true when async compaction should abort.
*/
static inline bool compact_should_abort(struct compact_control *cc)
{
/* async compaction aborts if contended */
if (need_resched()) {
if (cc->mode == MIGRATE_ASYNC) {
cc->contended = true;
return true;
}
cond_resched();
}
return false;
}
/*
* Isolate free pages onto a private freelist. 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 *start_pfn,
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 flags = 0;
bool locked = false;
unsigned long blockpfn = *start_pfn;
unsigned int order;
cursor = pfn_to_page(blockpfn);
/* Isolate free pages. */
for (; blockpfn < end_pfn; blockpfn++, cursor++) {
int isolated;
struct page *page = cursor;
/*
* Periodically drop the lock (if held) regardless of its
* contention, to give chance to IRQs. Abort if fatal signal
* pending or async compaction detects need_resched()
*/
if (!(blockpfn % SWAP_CLUSTER_MAX)
&& compact_unlock_should_abort(&cc->zone->lock, flags,
&locked, cc))
break;
nr_scanned++;
if (!pfn_valid_within(blockpfn))
goto isolate_fail;
if (!valid_page)
valid_page = page;
/*
* For compound pages such as THP and hugetlbfs, we can save
* potentially a lot of iterations if we skip them at once.
* The check is racy, but we can consider only valid values
* and the only danger is skipping too much.
*/
if (PageCompound(page)) {
unsigned int comp_order = compound_order(page);
if (likely(comp_order < MAX_ORDER)) {
blockpfn += (1UL << comp_order) - 1;
cursor += (1UL << comp_order) - 1;
}
goto isolate_fail;
}
if (!PageBuddy(page))
goto isolate_fail;
/*
* If we already hold the lock, we can skip some rechecking.
* Note that if we hold the lock now, checked_pageblock was
* already set in some previous iteration (or strict is true),
* so it is correct to skip the suitable migration target
* recheck as well.
*/
if (!locked) {
/*
* 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_trylock_irqsave(&cc->zone->lock,
&flags, cc);
if (!locked)
break;
/* Recheck this is a buddy page under lock */
if (!PageBuddy(page))
goto isolate_fail;
}
/* Found a free page, will break it into order-0 pages */
order = page_order(page);
isolated = __isolate_free_page(page, order);
if (!isolated)
break;
set_page_private(page, order);
total_isolated += isolated;
cc->nr_freepages += isolated;
list_add_tail(&page->lru, freelist);
if (!strict && cc->nr_migratepages <= cc->nr_freepages) {
blockpfn += isolated;
break;
}
/* Advance to the end of split page */
blockpfn += isolated - 1;
cursor += isolated - 1;
continue;
isolate_fail:
if (strict)
break;
else
continue;
}
if (locked)
spin_unlock_irqrestore(&cc->zone->lock, flags);
/*
* There is a tiny chance that we have read bogus compound_order(),
* so be careful to not go outside of the pageblock.
*/
if (unlikely(blockpfn > end_pfn))
blockpfn = end_pfn;
trace_mm_compaction_isolate_freepages(*start_pfn, blockpfn,
nr_scanned, total_isolated);
/* Record how far we have got within the block */
*start_pfn = blockpfn;
/*
* 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 && blockpfn < end_pfn)
total_isolated = 0;
/* 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_start_pfn, block_end_pfn;
LIST_HEAD(freelist);
pfn = start_pfn;
block_start_pfn = pageblock_start_pfn(pfn);
if (block_start_pfn < cc->zone->zone_start_pfn)
block_start_pfn = cc->zone->zone_start_pfn;
block_end_pfn = pageblock_end_pfn(pfn);
for (; pfn < end_pfn; pfn += isolated,
block_start_pfn = block_end_pfn,
block_end_pfn += pageblock_nr_pages) {
/* Protect pfn from changing by isolate_freepages_block */
unsigned long isolate_start_pfn = pfn;
block_end_pfn = min(block_end_pfn, end_pfn);
/*
* pfn could pass the block_end_pfn if isolated freepage
* is more than pageblock order. In this case, we adjust
* scanning range to right one.
*/
if (pfn >= block_end_pfn) {
block_start_pfn = pageblock_start_pfn(pfn);
block_end_pfn = pageblock_end_pfn(pfn);
block_end_pfn = min(block_end_pfn, end_pfn);
}
if (!pageblock_pfn_to_page(block_start_pfn,
block_end_pfn, cc->zone))
break;
isolated = isolate_freepages_block(cc, &isolate_start_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).
*/
}
/* __isolate_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;
}
/* 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 = node_page_state(zone->zone_pgdat, NR_INACTIVE_FILE) +
node_page_state(zone->zone_pgdat, NR_INACTIVE_ANON);
active = node_page_state(zone->zone_pgdat, NR_ACTIVE_FILE) +
node_page_state(zone->zone_pgdat, NR_ACTIVE_ANON);
isolated = node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE) +
node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON);
return isolated > (inactive + active) / 2;
}
/**
* isolate_migratepages_block() - isolate all migrate-able pages within
* a single pageblock
* @cc: Compaction control structure.
* @low_pfn: The first PFN to isolate
* @end_pfn: The one-past-the-last PFN to isolate, within same pageblock
* @isolate_mode: Isolation mode to be used.
*
* Isolate all pages that can be migrated from the range specified by
* [low_pfn, end_pfn). The range is expected to be within same pageblock.
* 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
* than end_pfn).
*
* The pages are isolated on cc->migratepages list (not required to be empty),
* and cc->nr_migratepages is updated accordingly. The cc->migrate_pfn field
* is neither read nor updated.
*/
static unsigned long
isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
unsigned long end_pfn, isolate_mode_t isolate_mode)
{
struct zone *zone = cc->zone;
unsigned long nr_scanned = 0, nr_isolated = 0;
struct lruvec *lruvec;
unsigned long flags = 0;
bool locked = false;
struct page *page = NULL, *valid_page = NULL;
unsigned long start_pfn = low_pfn;
bool skip_on_failure = false;
unsigned long next_skip_pfn = 0;
/*
* 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->mode == MIGRATE_ASYNC)
return 0;
congestion_wait(BLK_RW_ASYNC, HZ/10);
if (fatal_signal_pending(current))
return 0;
}
if (compact_should_abort(cc))
return 0;
if (cc->direct_compaction && (cc->mode == MIGRATE_ASYNC)) {
skip_on_failure = true;
next_skip_pfn = block_end_pfn(low_pfn, cc->order);
}
/* Time to isolate some pages for migration */
for (; low_pfn < end_pfn; low_pfn++) {
if (skip_on_failure && low_pfn >= next_skip_pfn) {
/*
* We have isolated all migration candidates in the
* previous order-aligned block, and did not skip it due
* to failure. We should migrate the pages now and
* hopefully succeed compaction.
*/
if (nr_isolated)
break;
/*
* We failed to isolate in the previous order-aligned
* block. Set the new boundary to the end of the
* current block. Note we can't simply increase
* next_skip_pfn by 1 << order, as low_pfn might have
* been incremented by a higher number due to skipping
* a compound or a high-order buddy page in the
* previous loop iteration.
*/
next_skip_pfn = block_end_pfn(low_pfn, cc->order);
}
/*
* Periodically drop the lock (if held) regardless of its
* contention, to give chance to IRQs. Abort async compaction
* if contended.
*/
if (!(low_pfn % SWAP_CLUSTER_MAX)
&& compact_unlock_should_abort(zone_lru_lock(zone), flags,
&locked, cc))
break;
if (!pfn_valid_within(low_pfn))
goto isolate_fail;
nr_scanned++;
page = pfn_to_page(low_pfn);
if (!valid_page)
valid_page = page;
/*
* Skip if free. We read page order here without zone lock
* which is generally unsafe, but the race window is small and
* the worst thing that can happen is that we skip some
* potential isolation targets.
*/
if (PageBuddy(page)) {
unsigned long freepage_order = page_order_unsafe(page);
/*
* Without lock, we cannot be sure that what we got is
* a valid page order. Consider only values in the
* valid order range to prevent low_pfn overflow.
*/
if (freepage_order > 0 && freepage_order < MAX_ORDER)
low_pfn += (1UL << freepage_order) - 1;
continue;
}
/*
* Regardless of being on LRU, compound pages such as THP and
* hugetlbfs are not to be compacted. We can potentially save
* a lot of iterations if we skip them at once. The check is
* racy, but we can consider only valid values and the only
* danger is skipping too much.
*/
if (PageCompound(page)) {
unsigned int comp_order = compound_order(page);
if (likely(comp_order < MAX_ORDER))
low_pfn += (1UL << comp_order) - 1;
goto isolate_fail;
}
/*
* Check may be lockless but that's ok as we recheck later.
* It's possible to migrate LRU and non-lru movable pages.
* Skip any other type of page
*/
if (!PageLRU(page)) {
/*
* __PageMovable can return false positive so we need
* to verify it under page_lock.
*/
if (unlikely(__PageMovable(page)) &&
!PageIsolated(page)) {
if (locked) {
spin_unlock_irqrestore(zone_lru_lock(zone),
flags);
locked = false;
}
if (isolate_movable_page(page, isolate_mode))
goto isolate_success;
}
goto isolate_fail;
}
/*
* Migration will fail if an anonymous page is pinned in memory,
* so avoid taking lru_lock and isolating it unnecessarily in an
* admittedly racy check.
*/
if (!page_mapping(page) &&
page_count(page) > page_mapcount(page))
goto isolate_fail;
/* If we already hold the lock, we can skip some rechecking */
if (!locked) {
locked = compact_trylock_irqsave(zone_lru_lock(zone),
&flags, cc);
if (!locked)
break;
/* Recheck PageLRU and PageCompound under lock */
if (!PageLRU(page))
goto isolate_fail;
/*
* Page become compound since the non-locked check,
* and it's on LRU. It can only be a THP so the order
* is safe to read and it's 0 for tail pages.
*/
if (unlikely(PageCompound(page))) {
low_pfn += (1UL << compound_order(page)) - 1;
goto isolate_fail;
}
}
lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
/* Try isolate the page */
if (__isolate_lru_page(page, isolate_mode) != 0)
goto isolate_fail;
VM_BUG_ON_PAGE(PageCompound(page), page);
/* Successfully isolated */
del_page_from_lru_list(page, lruvec, page_lru(page));
inc_node_page_state(page,
NR_ISOLATED_ANON + page_is_file_cache(page));
isolate_success:
list_add(&page->lru, &cc->migratepages);
cc->nr_migratepages++;
nr_isolated++;
/*
* Record where we could have freed pages by migration and not
* yet flushed them to buddy allocator.
* - this is the lowest page that was isolated and likely be
* then freed by migration.
*/
if (!cc->last_migrated_pfn)
cc->last_migrated_pfn = low_pfn;
/* Avoid isolating too much */
if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) {
++low_pfn;
break;
}
continue;
isolate_fail:
if (!skip_on_failure)
continue;
/*
* We have isolated some pages, but then failed. Release them
* instead of migrating, as we cannot form the cc->order buddy
* page anyway.
*/
if (nr_isolated) {
if (locked) {
spin_unlock_irqrestore(zone_lru_lock(zone), flags);
locked = false;
}
putback_movable_pages(&cc->migratepages);
cc->nr_migratepages = 0;
cc->last_migrated_pfn = 0;
nr_isolated = 0;
}
if (low_pfn < next_skip_pfn) {
low_pfn = next_skip_pfn - 1;
/*
* The check near the loop beginning would have updated
* next_skip_pfn too, but this is a bit simpler.
*/
next_skip_pfn += 1UL << cc->order;
}
}
/*
* The PageBuddy() check could have potentially brought us outside
* the range to be scanned.
*/
if (unlikely(low_pfn > end_pfn))
low_pfn = end_pfn;
if (locked)
spin_unlock_irqrestore(zone_lru_lock(zone), flags);
/*
* Update the pageblock-skip information and cached scanner pfn,
* if the whole pageblock was scanned without isolating any page.
*/
if (low_pfn == end_pfn)
update_pageblock_skip(cc, valid_page, nr_isolated, true);
trace_mm_compaction_isolate_migratepages(start_pfn, low_pfn,
nr_scanned, nr_isolated);
count_compact_events(COMPACTMIGRATE_SCANNED, nr_scanned);
if (nr_isolated)
count_compact_events(COMPACTISOLATED, nr_isolated);
return low_pfn;
}
/**
* isolate_migratepages_range() - isolate migrate-able pages in a PFN range
* @cc: Compaction control structure.
* @start_pfn: The first PFN to start isolating.
* @end_pfn: The one-past-last PFN.
*
* Returns zero if isolation fails fatally due to e.g. pending signal.
* Otherwise, function returns one-past-the-last PFN of isolated page
* (which may be greater than end_pfn if end fell in a middle of a THP page).
*/
unsigned long
isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
unsigned long end_pfn)
{
unsigned long pfn, block_start_pfn, block_end_pfn;
/* Scan block by block. First and last block may be incomplete */
pfn = start_pfn;
block_start_pfn = pageblock_start_pfn(pfn);
if (block_start_pfn < cc->zone->zone_start_pfn)
block_start_pfn = cc->zone->zone_start_pfn;
block_end_pfn = pageblock_end_pfn(pfn);
for (; pfn < end_pfn; pfn = block_end_pfn,
block_start_pfn = block_end_pfn,
block_end_pfn += pageblock_nr_pages) {
block_end_pfn = min(block_end_pfn, end_pfn);
if (!pageblock_pfn_to_page(block_start_pfn,
block_end_pfn, cc->zone))
continue;
pfn = isolate_migratepages_block(cc, pfn, block_end_pfn,
ISOLATE_UNEVICTABLE);
if (!pfn)
break;
if (cc->nr_migratepages == COMPACT_CLUSTER_MAX)
break;
}
return pfn;
}
#endif /* CONFIG_COMPACTION || CONFIG_CMA */
#ifdef CONFIG_COMPACTION
/* Returns true if the page is within a block suitable for migration to */
static bool suitable_migration_target(struct compact_control *cc,
struct page *page)
{
if (cc->ignore_block_suitable)
return true;
/* If the page is a large free page, then disallow migration */
if (PageBuddy(page)) {
/*
* We are checking page_order without zone->lock taken. But
* the only small danger is that we skip a potentially suitable
* pageblock, so it's not worth to check order for valid range.
*/
if (page_order_unsafe(page) >= pageblock_order)
return false;
}