summaryrefslogtreecommitdiffstats
path: root/mm/migrate.c
blob: 880bd592d38ea47af36f5f9b64323e8814d09f24 (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
/*
 * Memory Migration functionality - linux/mm/migration.c
 *
 * Copyright (C) 2006 Silicon Graphics, Inc., Christoph Lameter
 *
 * Page migration was first developed in the context of the memory hotplug
 * project. The main authors of the migration code are:
 *
 * IWAMOTO Toshihiro <iwamoto@valinux.co.jp>
 * Hirokazu Takahashi <taka@valinux.co.jp>
 * Dave Hansen <haveblue@us.ibm.com>
 * Christoph Lameter
 */

#include <linux/migrate.h>
#include <linux/module.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pagemap.h>
#include <linux/buffer_head.h>
#include <linux/mm_inline.h>
#include <linux/nsproxy.h>
#include <linux/pagevec.h>
#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/topology.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/writeback.h>
#include <linux/mempolicy.h>
#include <linux/vmalloc.h>
#include <linux/security.h>
#include <linux/memcontrol.h>
#include <linux/syscalls.h>

#include "internal.h"

#define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))

/*
 * migrate_prep() needs to be called before we start compiling a list of pages
 * to be migrated using isolate_lru_page().
 */
int migrate_prep(void)
{
	/*
	 * Clear the LRU lists so pages can be isolated.
	 * Note that pages may be moved off the LRU after we have
	 * drained them. Those pages will fail to migrate like other
	 * pages that may be busy.
	 */
	lru_add_drain_all();

	return 0;
}

/*
 * Add isolated pages on the list back to the LRU under page lock
 * to avoid leaking evictable pages back onto unevictable list.
 *
 * returns the number of pages put back.
 */
int putback_lru_pages(struct list_head *l)
{
	struct page *page;
	struct page *page2;
	int count = 0;

	list_for_each_entry_safe(page, page2, l, lru) {
		list_del(&page->lru);
		dec_zone_page_state(page, NR_ISOLATED_ANON +
				page_is_file_cache(page));
		putback_lru_page(page);
		count++;
	}
	return count;
}

/*
 * Restore a potential migration pte to a working pte entry
 */
static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
				 unsigned long addr, void *old)
{
	struct mm_struct *mm = vma->vm_mm;
	swp_entry_t entry;
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
	pte_t *ptep, pte;
 	spinlock_t *ptl;

 	pgd = pgd_offset(mm, addr);
	if (!pgd_present(*pgd))
		goto out;

	pud = pud_offset(pgd, addr);
	if (!pud_present(*pud))
		goto out;

	pmd = pmd_offset(pud, addr);
	if (!pmd_present(*pmd))
		goto out;

	ptep = pte_offset_map(pmd, addr);

	if (!is_swap_pte(*ptep)) {
		pte_unmap(ptep);
		goto out;
 	}

 	ptl = pte_lockptr(mm, pmd);
 	spin_lock(ptl);
	pte = *ptep;
	if (!is_swap_pte(pte))
		goto unlock;

	entry = pte_to_swp_entry(pte);

	if (!is_migration_entry(entry) ||
	    migration_entry_to_page(entry) != old)
		goto unlock;

	get_page(new);
	pte = pte_mkold(mk_pte(new, vma->vm_page_prot));
	if (is_write_migration_entry(entry))
		pte = pte_mkwrite(pte);
	flush_cache_page(vma, addr, pte_pfn(pte));
	set_pte_at(mm, addr, ptep, pte);

	if (PageAnon(new))
		page_add_anon_rmap(new, vma, addr);
	else
		page_add_file_rmap(new);

	/* No need to invalidate - it was non-present before */
	update_mmu_cache(vma, addr, pte);
unlock:
	pte_unmap_unlock(ptep, ptl);
out:
	return SWAP_AGAIN;
}

/*
 * Get rid of all migration entries and replace them by
 * references to the indicated page.
 */
static void remove_migration_ptes(struct page *old, struct page *new)
{
	rmap_walk(new, remove_migration_pte, old);
}

/*
 * Something used the pte of a page under migration. We need to
 * get to the page and wait until migration is finished.
 * When we return from this function the fault will be retried.
 *
 * This function is called from do_swap_page().
 */
void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
				unsigned long address)
{
	pte_t *ptep, pte;
	spinlock_t *ptl;
	swp_entry_t entry;
	struct page *page;

	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
	pte = *ptep;
	if (!is_swap_pte(pte))
		goto out;

	entry = pte_to_swp_entry(pte);
	if (!is_migration_entry(entry))
		goto out;

	page = migration_entry_to_page(entry);

	/*
	 * Once radix-tree replacement of page migration started, page_count
	 * *must* be zero. And, we don't want to call wait_on_page_locked()
	 * against a page without get_page().
	 * So, we use get_page_unless_zero(), here. Even failed, page fault
	 * will occur again.
	 */
	if (!get_page_unless_zero(page))
		goto out;
	pte_unmap_unlock(ptep, ptl);
	wait_on_page_locked(page);
	put_page(page);
	return;
out:
	pte_unmap_unlock(ptep, ptl);
}

/*
 * Replace the page in the mapping.
 *
 * The number of remaining references must be:
 * 1 for anonymous pages without a mapping
 * 2 for pages with a mapping
 * 3 for pages with a mapping and PagePrivate/PagePrivate2 set.
 */
static int migrate_page_move_mapping(struct address_space *mapping,
		struct page *newpage, struct page *page)
{
	int expected_count;
	void **pslot;

	if (!mapping) {
		/* Anonymous page without mapping */
		if (page_count(page) != 1)
			return -EAGAIN;
		return 0;
	}

	spin_lock_irq(&mapping->tree_lock);

	pslot = radix_tree_lookup_slot(&mapping->page_tree,
 					page_index(page));

	expected_count = 2 + page_has_private(page);
	if (page_count(page) != expected_count ||
			(struct page *)radix_tree_deref_slot(pslot) != page) {
		spin_unlock_irq(&mapping->tree_lock);
		return -EAGAIN;
	}

	if (!page_freeze_refs(page, expected_count)) {
		spin_unlock_irq(&mapping->tree_lock);
		return -EAGAIN;
	}

	/*
	 * Now we know that no one else is looking at the page.
	 */
	get_page(newpage);	/* add cache reference */
	if (PageSwapCache(page)) {
		SetPageSwapCache(newpage);
		set_page_private(newpage, page_private(page));
	}

	radix_tree_replace_slot(pslot, newpage);

	page_unfreeze_refs(page, expected_count);
	/*
	 * Drop cache reference from old page.
	 * We know this isn't the last reference.
	 */
	__put_page(page);

	/*
	 * If moved to a different zone then also account
	 * the page for that zone. Other VM counters will be
	 * taken care of when we establish references to the
	 * new page and drop references to the old page.
	 *
	 * Note that anonymous pages are accounted for
	 * via NR_FILE_PAGES and NR_ANON_PAGES if they
	 * are mapped to swap space.
	 */
	__dec_zone_page_state(page, NR_FILE_PAGES);
	__inc_zone_page_state(newpage, NR_FILE_PAGES);
	if (PageSwapBacked(page)) {
		__dec_zone_page_state(page, NR_SHMEM);
		__inc_zone_page_state(newpage, NR_SHMEM);
	}
	spin_unlock_irq(&mapping->tree_lock);

	return 0;
}

/*
 * Copy the page to its new location
 */
static void migrate_page_copy(struct page *newpage, struct page *page)
{
	int anon;

	copy_highpage(newpage, page);

	if (PageError(page))
		SetPageError(newpage);
	if (PageReferenced(page))
		SetPageReferenced(newpage);
	if (PageUptodate(page))
		SetPageUptodate(newpage);
	if (TestClearPageActive(page)) {
		VM_BUG_ON(PageUnevictable(page));
		SetPageActive(newpage);
	} else if (TestClearPageUnevictable(page))
		SetPageUnevictable(newpage);
	if (PageChecked(page))
		SetPageChecked(newpage);
	if (PageMappedToDisk(page))
		SetPageMappedToDisk(newpage);

	if (PageDirty(page)) {
		clear_page_dirty_for_io(page);
		/*
		 * Want to mark the page and the radix tree as dirty, and
		 * redo the accounting that clear_page_dirty_for_io undid,
		 * but we can't use set_page_dirty because that function
		 * is actually a signal that all of the page has become dirty.
		 * Wheras only part of our page may be dirty.
		 */
		__set_page_dirty_nobuffers(newpage);
 	}

	mlock_migrate_page(newpage, page);
	ksm_migrate_page(newpage, page);

	ClearPageSwapCache(page);
	ClearPagePrivate(page);
	set_page_private(page, 0);
	/* page->mapping contains a flag for PageAnon() */
	anon = PageAnon(page);
	page->mapping = NULL;

	/*
	 * If any waiters have accumulated on the new page then
	 * wake them up.
	 */
	if (PageWriteback(newpage))
		end_page_writeback(newpage);
}

/************************************************************
 *                    Migration functions
 ***********************************************************/

/* Always fail migration. Used for mappings that are not movable */
int fail_migrate_page(struct address_space *mapping,
			struct page *newpage, struct page *page)
{
	return -EIO;
}
EXPORT_SYMBOL(fail_migrate_page);

/*
 * Common logic to directly migrate a single page suitable for
 * pages that do not use PagePrivate/PagePrivate2.
 *
 * Pages are locked upon entry and exit.
 */
int migrate_page(struct address_space *mapping,
		struct page *newpage, struct page *page)
{
	int rc;

	BUG_ON(PageWriteback(page));	/* Writeback must be complete */

	rc = migrate_page_move_mapping(mapping, newpage, page);

	if (rc)
		return rc;

	migrate_page_copy(newpage, page);
	return 0;
}
EXPORT_SYMBOL(migrate_page);

#ifdef CONFIG_BLOCK
/*
 * Migration function for pages with buffers. This function can only be used
 * if the underlying filesystem guarantees that no other references to "page"
 * exist.
 */
int buffer_migrate_page(struct address_space *mapping,
		struct page *newpage, struct page *page)
{
	struct buffer_head *bh, *head;
	int rc;

	if (!page_has_buffers(page))
		return migrate_page(mapping, newpage, page);

	head = page_buffers(page);

	rc = migrate_page_move_mapping(mapping, newpage, page);

	if (rc)
		return rc;

	bh = head;
	do {
		get_bh(bh);
		lock_buffer(bh);
		bh = bh->b_this_page;

	} while (bh != head);

	ClearPagePrivate(page);
	set_page_private(newpage, page_private(page));
	set_page_private(page, 0);
	put_page(page);
	get_page(newpage);

	bh = head;
	do {
		set_bh_page(bh, newpage, bh_offset(bh));
		bh = bh->b_this_page;

	} while (bh != head);

	SetPagePrivate(newpage);

	migrate_page_copy(newpage, page);

	bh = head;
	do {
		unlock_buffer(bh);
 		put_bh(bh);
		bh = bh->b_this_page;

	} while (bh != head);

	return 0;
}
EXPORT_SYMBOL(buffer_migrate_page);
#endif

/*
 * Writeback a page to clean the dirty state
 */
static int writeout(struct address_space *mapping, struct page *page)
{
	struct writeback_control wbc = {
		.sync_mode = WB_SYNC_NONE,
		.nr_to_write = 1,
		.range_start = 0,
		.range_end = LLONG_MAX,
		.nonblocking = 1,
		.for_reclaim = 1
	};
	int rc;

	if (!mapping->a_ops->writepage)
		/* No write method for the address space */
		return -EINVAL;

	if (!clear_page_dirty_for_io(page))
		/* Someone else already triggered a write */
		return -EAGAIN;

	/*
	 * A dirty page may imply that the underlying filesystem has
	 * the page on some queue. So the page must be clean for
	 * migration. Writeout may mean we loose the lock and the
	 * page state is no longer what we checked for earlier.
	 * At this point we know that the migration attempt cannot
	 * be successful.
	 */
	remove_migration_ptes(page, page);

	rc = mapping->a_ops->writepage(page, &wbc);

	if (rc != AOP_WRITEPAGE_ACTIVATE)
		/* unlocked. Relock */
		lock_page(page);

	return (rc < 0) ? -EIO : -EAGAIN;
}

/*
 * Default handling if a filesystem does not provide a migration function.
 */
static int fallback_migrate_page(struct address_space *mapping,
	struct page *newpage, struct page *page)
{
	if (PageDirty(page))
		return writeout(mapping, page);

	/*
	 * Buffers may be managed in a filesystem specific way.
	 * We must have no buffers or drop them.
	 */
	if (page_has_private(page) &&
	    !try_to_release_page(page, GFP_KERNEL))
		return -EAGAIN;

	return migrate_page(mapping, newpage, page);
}

/*
 * Move a page to a newly allocated page
 * The page is locked and all ptes have been successfully removed.
 *
 * The new page will have replaced the old page if this function
 * is successful.
 *
 * Return value:
 *   < 0 - error code
 *  == 0 - success
 */
static int move_to_new_page(struct page *newpage, struct page *page)
{
	struct address_space *mapping;
	int rc;

	/*
	 * Block others from accessing the page when we get around to
	 * establishing additional references. We are the only one
	 * holding a reference to the new page at this point.
	 */
	if (!trylock_page(newpage))
		BUG();

	/* Prepare mapping for the new page.*/
	newpage->index = page->index;
	newpage->mapping = page->mapping;
	if (PageSwapBacked(page))
		SetPageSwapBacked(newpage);

	mapping = page_mapping(page);
	if (!mapping)
		rc = migrate_page(mapping, newpage, page);
	else if (mapping->a_ops->migratepage)
		/*
		 * Most pages have a mapping and most filesystems
		 * should provide a migration function. Anonymous
		 * pages are part of swap space which also has its
		 * own migration function. This is the most common
		 * path for page migration.
		 */
		rc = mapping->a_ops->migratepage(mapping,
						newpage, page);
	else
		rc = fallback_migrate_page(mapping, newpage, page);

	if (!rc)
		remove_migration_ptes(page, newpage);
	else
		newpage->mapping = NULL;

	unlock_page(newpage);

	return rc;
}

/*
 * Obtain the lock on page, remove all ptes and migrate the page
 * to the newly allocated page in newpage.
 */
static int unmap_and_move(new_page_t get_new_page, unsigned long private,
			struct page *page, int force, int offlining)
{
	int rc = 0;
	int *result = NULL;
	struct page *newpage = get_new_page(page, private, &result);
	int rcu_locked = 0;
	int charge = 0;
	struct mem_cgroup *mem = NULL;

	if (!newpage)
		return -ENOMEM;

	if (page_count(page) == 1) {
		/* page was freed from under us. So we are done. */
		goto move_newpage;
	}

	/* prepare cgroup just returns 0 or -ENOMEM */
	rc = -EAGAIN;

	if (!trylock_page(page)) {
		if (!force)
			goto move_newpage;
		lock_page(page);
	}

	/*
	 * Only memory hotplug's offline_pages() caller has locked out KSM,
	 * and can safely migrate a KSM page.  The other cases have skipped
	 * PageKsm along with PageReserved - but it is only now when we have
	 * the page lock that we can be certain it will not go KSM beneath us
	 * (KSM will not upgrade a page from PageAnon to PageKsm when it sees
	 * its pagecount raised, but only here do we take the page lock which
	 * serializes that).
	 */
	if (PageKsm(page) && !offlining) {
		rc = -EBUSY;
		goto unlock;
	}

	/* charge against new page */
	charge = mem_cgroup_prepare_migration(page, &mem);
	if (charge == -ENOMEM) {
		rc = -ENOMEM;
		goto unlock;
	}
	BUG_ON(charge);

	if (PageWriteback(page)) {
		if (!force)
			goto uncharge;
		wait_on_page_writeback(page);
	}
	/*
	 * By try_to_unmap(), page->mapcount goes down to 0 here. In this case,
	 * we cannot notice that anon_vma is freed while we migrates a page.
	 * This rcu_read_lock() delays freeing anon_vma pointer until the end
	 * of migration. File cache pages are no problem because of page_lock()
	 * File Caches may use write_page() or lock_page() in migration, then,
	 * just care Anon page here.
	 */
	if (PageAnon(page)) {
		rcu_read_lock();
		rcu_locked = 1;
	}

	/*
	 * Corner case handling:
	 * 1. When a new swap-cache page is read into, it is added to the LRU
	 * and treated as swapcache but it has no rmap yet.
	 * Calling try_to_unmap() against a page->mapping==NULL page will
	 * trigger a BUG.  So handle it here.
	 * 2. An orphaned page (see truncate_complete_page) might have
	 * fs-private metadata. The page can be picked up due to memory
	 * offlining.  Everywhere else except page reclaim, the page is
	 * invisible to the vm, so the page can not be migrated.  So try to
	 * free the metadata, so the page can be freed.
	 */
	if (!page->mapping) {
		if (!PageAnon(page) && page_has_private(page)) {
			/*
			 * Go direct to try_to_free_buffers() here because
			 * a) that's what try_to_release_page() would do anyway
			 * b) we may be under rcu_read_lock() here, so we can't
			 *    use GFP_KERNEL which is what try_to_release_page()
			 *    needs to be effective.
			 */
			try_to_free_buffers(page);
			goto rcu_unlock;
		}
		goto skip_unmap;
	}

	/* Establish migration ptes or remove ptes */
	try_to_unmap(page, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);

skip_unmap:
	if (!page_mapped(page))
		rc = move_to_new_page(newpage, page);

	if (rc)
		remove_migration_ptes(page, page);
rcu_unlock:
	if (rcu_locked)
		rcu_read_unlock();
uncharge:
	if (!charge)
		mem_cgroup_end_migration(mem, page, newpage);
unlock:
	unlock_page(page);

	if (rc != -EAGAIN) {
 		/*
 		 * A page that has been migrated has all references
 		 * removed and will be freed. A page that has not been
 		 * migrated will have kepts its references and be
 		 * restored.
 		 */
 		list_del(&page->lru);
		dec_zone_page_state(page, NR_ISOLATED_ANON +
				page_is_file_cache(page));
		putback_lru_page(page);
	}

move_newpage:

	/*
	 * Move the new page to the LRU. If migration was not successful
	 * then this will free the page.
	 */
	putback_lru_page(newpage);

	if (result) {
		if (rc)
			*result = rc;
		else
			*result = page_to_nid(newpage);
	}
	return rc;
}

/*
 * migrate_pages
 *
 * The function takes one list of pages to migrate and a function
 * that determines from the page to be migrated and the private data
 * the target of the move and allocates the page.
 *
 * The function returns after 10 attempts or if no pages
 * are movable anymore because to has become empty
 * or no retryable pages exist anymore. All pages will be
 * returned to the LRU or freed.
 *
 * Return: Number of pages not migrated or error code.
 */
int migrate_pages(struct list_head *from,
		new_page_t get_new_page, unsigned long private, int offlining)
{
	int retry = 1;
	int nr_failed = 0;
	int pass = 0;
	struct page *page;
	struct page *page2;
	int swapwrite = current->flags & PF_SWAPWRITE;
	int rc;

	if (!swapwrite)
		current->flags |= PF_SWAPWRITE;

	for(pass = 0; pass < 10 && retry; pass++) {
		retry = 0;

		list_for_each_entry_safe(page, page2, from, lru) {
			cond_resched();

			rc = unmap_and_move(get_new_page, private,
						page, pass > 2, offlining);

			switch(rc) {
			case -ENOMEM:
				goto out;
			case -EAGAIN:
				retry++;
				break;
			case 0:
				break;
			default:
				/* Permanent failure */
				nr_failed++;
				break;
			}
		}
	}
	rc = 0;
out:
	if (!swapwrite)
		current->flags &= ~PF_SWAPWRITE;

	putback_lru_pages(from);

	if (rc)
		return rc;

	return nr_failed + retry;
}

#ifdef CONFIG_NUMA
/*
 * Move a list of individual pages
 */
struct page_to_node {
	unsigned long addr;
	struct page *page;
	int node;
	int status;
};

static struct page *new_page_node(struct page *p, unsigned long private,
		int **result)
{
	struct page_to_node *pm = (struct page_to_node *)private;

	while (pm->node != MAX_NUMNODES && pm->page != p)
		pm++;

	if (pm->node == MAX_NUMNODES)
		return NULL;

	*result = &pm->status;

	return alloc_pages_exact_node(pm->node,
				GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0);
}

/*
 * Move a set of pages as indicated in the pm array. The addr
 * field must be set to the virtual address of the page to be moved
 * and the node number must contain a valid target node.
 * The pm array ends with node = MAX_NUMNODES.
 */
static int do_move_page_to_node_array(struct mm_struct *mm,
				      struct page_to_node *pm,
				      int migrate_all)
{
	int err;
	struct page_to_node *pp;
	LIST_HEAD(pagelist);

	down_read(&mm->mmap_sem);

	/*
	 * Build a list of pages to migrate
	 */
	for (pp = pm; pp->node != MAX_NUMNODES; pp++) {
		struct vm_area_struct *vma;
		struct page *page;

		err = -EFAULT;
		vma = find_vma(mm, pp->addr);
		if (!vma || !vma_migratable(vma))
			goto set_status;

		page = follow_page(vma, pp->addr, FOLL_GET);

		err = PTR_ERR(page);
		if (IS_ERR(page))
			goto set_status;

		err = -ENOENT;
		if (!page)
			goto set_status;

		/* Use PageReserved to check for zero page */
		if (PageReserved(page) || PageKsm(page))
			goto put_and_set;

		pp->page = page;
		err = page_to_nid(page);

		if (err == pp->node)
			/*
			 * Node already in the right place
			 */
			goto put_and_set;

		err = -EACCES;
		if (page_mapcount(page) > 1 &&
				!migrate_all)
			goto put_and_set;

		err = isolate_lru_page(page);
		if (!err) {
			list_add_tail(&page->lru, &pagelist);
			inc_zone_page_state(page, NR_ISOLATED_ANON +
					    page_is_file_cache(page));
		}
put_and_set:
		/*
		 * Either remove the duplicate refcount from
		 * isolate_lru_page() or drop the page ref if it was
		 * not isolated.
		 */
		put_page(page);
set_status:
		pp->status = err;
	}

	err = 0;
	if (!list_empty(&pagelist))
		err = migrate_pages(&pagelist, new_page_node,
				(unsigned long)pm, 0);

	up_read(&mm->mmap_sem);
	return err;
}

/*
 * Migrate an array of page address onto an array of nodes and fill
 * the corresponding array of status.
 */
static int do_pages_move(struct mm_struct *mm, struct task_struct *task,
			 unsigned long nr_pages,
			 const void __user * __user *pages,
			 const int __user *nodes,
			 int __user *status, int flags)
{
	struct page_to_node *pm;
	nodemask_t task_nodes;
	unsigned long chunk_nr_pages;
	unsigned long chunk_start;
	int err;

	task_nodes = cpuset_mems_allowed(task);

	err = -ENOMEM;
	pm = (struct page_to_node *)__get_free_page(GFP_KERNEL);
	if (!pm)
		goto out;

	migrate_prep();

	/*
	 * Store a chunk of page_to_node array in a page,
	 * but keep the last one as a marker
	 */
	chunk_nr_pages = (PAGE_SIZE / sizeof(struct page_to_node)) - 1;

	for (chunk_start = 0;
	     chunk_start < nr_pages;
	     chunk_start += chunk_nr_pages) {
		int j;

		if (chunk_start + chunk_nr_pages > nr_pages)
			chunk_nr_pages = nr_pages - chunk_start;

		/* fill the chunk pm with addrs and nodes from user-space */
		for (j = 0; j < chunk_nr_pages; j++) {
			const void __user *p;
			int node;

			err = -EFAULT;
			if (get_user(p, pages + j + chunk_start))
				goto out_pm;
			pm[j].addr = (unsigned long) p;

			if (get_user(node, nodes + j + chunk_start))
				goto out_pm;

			err = -ENODEV;
			if (node < 0 || node >= MAX_NUMNODES)
				goto out_pm;

			if (!node_state(node, N_HIGH_MEMORY))
				goto out_pm;

			err = -EACCES;
			if (!node_isset(node, task_nodes))
				goto out_pm;

			pm[j].node = node;
		}

		/* End marker for this chunk */
		pm[chunk_nr_pages].node = MAX_NUMNODES;

		/* Migrate this chunk */
		err = do_move_page_to_node_array(mm, pm,
						 flags & MPOL_MF_MOVE_ALL);
		if (err < 0)
			goto out_pm;

		/* Return status information */
		for (j = 0; j < chunk_nr_pages; j++)
			if (put_user(pm[j].status, status + j + chunk_start)) {
				err = -EFAULT;
				goto out_pm;
			}
	}
	err = 0;

out_pm:
	free_page((unsigned long)pm);
out:
	return err;
}

/*
 * Determine the nodes of an array of pages and store it in an array of status.
 */
static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages,
				const void __user **pages, int *status)
{
	unsigned long i;

	down_read(&mm->mmap_sem);

	for (i = 0; i < nr_pages; i++) {
		unsigned long addr = (unsigned long)(*pages);
		struct vm_area_struct *vma;
		struct page *page;
		int err = -EFAULT;

		vma = find_vma(mm, addr);
		if (!vma)
			goto set_status;

		page = follow_page(vma, addr, 0);

		err = PTR_ERR(page);
		if (IS_ERR(page))
			goto set_status;

		err = -ENOENT;
		/* Use PageReserved to check for zero page */
		if (!page || PageReserved(page) || PageKsm(page))
			goto set_status;

		err = page_to_nid(page);
set_status:
		*status = err;

		pages++;
		status++;
	}

	up_read(&mm->mmap_sem);
}

/*
 * Determine the nodes of a user array of pages and store it in
 * a user array of status.
 */
static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages,
			 const void __user * __user *pages,
			 int __user *status)
{
#define DO_PAGES_STAT_CHUNK_NR 16
	const void __user *chunk_pages[DO_PAGES_STAT_CHUNK_NR];
	int chunk_status[DO_PAGES_STAT_CHUNK_NR];

	while (nr_pages) {
		unsigned long chunk_nr;

		chunk_nr = nr_pages;
		if (chunk_nr > DO_PAGES_STAT_CHUNK_NR)
			chunk_nr = DO_PAGES_STAT_CHUNK_NR;

		if (copy_from_user(chunk_pages, pages, chunk_nr * sizeof(*chunk_pages)))
			break;

		do_pages_stat_array(mm, chunk_nr, chunk_pages, chunk_status);

		if (copy_to_user(status, chunk_status, chunk_nr * sizeof(*status)))
			break;

		pages += chunk_nr;
		status += chunk_nr;
		nr_pages -= chunk_nr;
	}
	return nr_pages ? -EFAULT : 0;
}

/*
 * Move a list of pages in the address space of the currently executing
 * process.
 */
SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
		const void __user * __user *, pages,
		const int __user *, nodes,
		int __user *, status, int, flags)
{
	const struct cred *cred = current_cred(), *tcred;
	struct task_struct *task;
	struct mm_struct *mm;
	int err;

	/* Check flags */
	if (flags & ~(MPOL_MF_MOVE|MPOL_MF_MOVE_ALL))
		return -EINVAL;

	if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE))
		return -EPERM;

	/* Find the mm_struct */
	read_lock(&tasklist_lock);
	task = pid ? find_task_by_vpid(pid) : current;
	if (!task) {
		read_unlock(&tasklist_lock);
		return -ESRCH;
	}
	mm = get_task_mm(task);
	read_unlock(&tasklist_lock);

	if (!mm)
		return -EINVAL;

	/*
	 * Check if this process has the right to modify the specified
	 * process. The right exists if the process has administrative
	 * capabilities, superuser privileges or the same
	 * userid as the target process.
	 */
	rcu_read_lock();
	tcred = __task_cred(task);
	if (cred->euid != tcred->suid && cred->euid != tcred->uid &&
	    cred->uid  != tcred->suid && cred->uid  != tcred->uid &&
	    !capable(CAP_SYS_NICE)) {
		rcu_read_unlock();
		err = -EPERM;
		goto out;
	}
	rcu_read_unlock();

 	err = security_task_movememory(task);
 	if (err)
		goto out;

	if (nodes) {
		err = do_pages_move(mm, task, nr_pages, pages, nodes, status,
				    flags);
	} else {
		err = do_pages_stat(mm, nr_pages, pages, status);
	}

out:
	mmput(mm);
	return err;
}

/*
 * Call migration functions in the vma_ops that may prepare
 * memory in a vm for migration. migration functions may perform
 * the migration for vmas that do not have an underlying page struct.
 */
int migrate_vmas(struct mm_struct *mm, const nodemask_t *to,
	const nodemask_t *from, unsigned long flags)
{
 	struct vm_area_struct *vma;
 	int err = 0;

	for (vma = mm->mmap; vma && !err; vma = vma->vm_next) {
 		if (vma->vm_ops && vma->vm_ops->migrate) {
 			err = vma->vm_ops->migrate(vma, to, from, flags);
 			if (err)
 				break;
 		}
 	}
 	return err;
}
#endif