aboutsummaryrefslogtreecommitdiff
path: root/mm/migrate.c
blob: cd4fd10c4ec3aebbea946ce3a2c862cf29688a40 (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
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
/*
 * 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/export.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 <linux/hugetlb.h>
#include <linux/hugetlb_cgroup.h>
#include <linux/gfp.h>
#include <linux/balloon_compaction.h>
#include <linux/mmu_notifier.h>

#include <asm/tlbflush.h>

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

#include "internal.h"

/*
 * migrate_prep() needs to be called before we start compiling a list of pages
 * to be migrated using isolate_lru_page(). If scheduling work on other CPUs is
 * undesirable, use migrate_prep_local()
 */
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;
}

/* Do the necessary work of migrate_prep but not if it involves other CPUs */
int migrate_prep_local(void)
{
	lru_add_drain();

	return 0;
}

/*
 * Put previously isolated pages back onto the appropriate lists
 * from where they were once taken off for compaction/migration.
 *
 * This function shall be used whenever the isolated pageset has been
 * built from lru, balloon, hugetlbfs page. See isolate_migratepages_range()
 * and isolate_huge_page().
 */
void putback_movable_pages(struct list_head *l)
{
	struct page *page;
	struct page *page2;

	list_for_each_entry_safe(page, page2, l, lru) {
		if (unlikely(PageHuge(page))) {
			putback_active_hugepage(page);
			continue;
		}
		list_del(&page->lru);
		dec_zone_page_state(page, NR_ISOLATED_ANON +
				page_is_file_cache(page));
		if (unlikely(isolated_balloon_page(page)))
			balloon_page_putback(page);
		else
			putback_lru_page(page);
	}
}

/*
 * 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;
 	pmd_t *pmd;
	pte_t *ptep, pte;
 	spinlock_t *ptl;

	if (unlikely(PageHuge(new))) {
		ptep = huge_pte_offset(mm, addr);
		if (!ptep)
			goto out;
		ptl = huge_pte_lockptr(hstate_vma(vma), mm, ptep);
	} else {
		pmd = mm_find_pmd(mm, addr);
		if (!pmd)
			goto out;

		ptep = pte_offset_map(pmd, addr);

		/*
		 * Peek to check is_swap_pte() before taking ptlock?  No, we
		 * can race mremap's move_ptes(), which skips anon_vma lock.
		 */

		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 (pte_swp_soft_dirty(*ptep))
		pte = pte_mksoft_dirty(pte);

	/* Recheck VMA as permissions can change since migration started  */
	if (is_write_migration_entry(entry))
		pte = maybe_mkwrite(pte, vma);

#ifdef CONFIG_HUGETLB_PAGE
	if (PageHuge(new)) {
		pte = pte_mkhuge(pte);
		pte = arch_make_huge_pte(pte, vma, new, 0);
	}
#endif
	flush_dcache_page(new);
	set_pte_at(mm, addr, ptep, pte);

	if (PageHuge(new)) {
		if (PageAnon(new))
			hugepage_add_anon_rmap(new, vma, addr);
		else
			page_dup_rmap(new);
	} else 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, ptep);
unlock:
	pte_unmap_unlock(ptep, ptl);
out:
	return SWAP_AGAIN;
}

/*
 * Congratulations to trinity for discovering this bug.
 * mm/fremap.c's remap_file_pages() accepts any range within a single vma to
 * convert that vma to VM_NONLINEAR; and generic_file_remap_pages() will then
 * replace the specified range by file ptes throughout (maybe populated after).
 * If page migration finds a page within that range, while it's still located
 * by vma_interval_tree rather than lost to i_mmap_nonlinear list, no problem:
 * zap_pte() clears the temporary migration entry before mmap_sem is dropped.
 * But if the migrating page is in a part of the vma outside the range to be
 * remapped, then it will not be cleared, and remove_migration_ptes() needs to
 * deal with it.  Fortunately, this part of the vma is of course still linear,
 * so we just need to use linear location on the nonlinear list.
 */
static int remove_linear_migration_ptes_from_nonlinear(struct page *page,
		struct address_space *mapping, void *arg)
{
	struct vm_area_struct *vma;
	/* hugetlbfs does not support remap_pages, so no huge pgoff worries */
	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
	unsigned long addr;

	list_for_each_entry(vma,
		&mapping->i_mmap_nonlinear, shared.nonlinear) {

		addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
		if (addr >= vma->vm_start && addr < vma->vm_end)
			remove_migration_pte(page, vma, addr, arg);
	}
	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)
{
	struct rmap_walk_control rwc = {
		.rmap_one = remove_migration_pte,
		.arg = old,
		.file_nonlinear = remove_linear_migration_ptes_from_nonlinear,
	};

	rmap_walk(new, &rwc);
}

/*
 * 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.
 */
void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
				spinlock_t *ptl)
{
	pte_t pte;
	swp_entry_t entry;
	struct page *page;

	spin_lock(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);
}

void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
				unsigned long address)
{
	spinlock_t *ptl = pte_lockptr(mm, pmd);
	pte_t *ptep = pte_offset_map(pmd, address);
	__migration_entry_wait(mm, ptep, ptl);
}

void migration_entry_wait_huge(struct vm_area_struct *vma,
		struct mm_struct *mm, pte_t *pte)
{
	spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), mm, pte);
	__migration_entry_wait(mm, pte, ptl);
}

#ifdef CONFIG_BLOCK
/* Returns true if all buffers are successfully locked */
static bool buffer_migrate_lock_buffers(struct buffer_head *head,
							enum migrate_mode mode)
{
	struct buffer_head *bh = head;

	/* Simple case, sync compaction */
	if (mode != MIGRATE_ASYNC) {
		do {
			get_bh(bh);
			lock_buffer(bh);
			bh = bh->b_this_page;

		} while (bh != head);

		return true;
	}

	/* async case, we cannot block on lock_buffer so use trylock_buffer */
	do {
		get_bh(bh);
		if (!trylock_buffer(bh)) {
			/*
			 * We failed to lock the buffer and cannot stall in
			 * async migration. Release the taken locks
			 */
			struct buffer_head *failed_bh = bh;
			put_bh(failed_bh);
			bh = head;
			while (bh != failed_bh) {
				unlock_buffer(bh);
				put_bh(bh);
				bh = bh->b_this_page;
			}
			return false;
		}

		bh = bh->b_this_page;
	} while (bh != head);
	return true;
}
#else
static inline bool buffer_migrate_lock_buffers(struct buffer_head *head,
							enum migrate_mode mode)
{
	return true;
}
#endif /* CONFIG_BLOCK */

/*
 * 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.
 */
int migrate_page_move_mapping(struct address_space *mapping,
		struct page *newpage, struct page *page,
		struct buffer_head *head, enum migrate_mode mode,
		int extra_count)
{
	int expected_count = 1 + extra_count;
	void **pslot;

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

	spin_lock_irq(&mapping->tree_lock);

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

	expected_count += 1 + page_has_private(page);
	if (page_count(page) != expected_count ||
		radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) {
		spin_unlock_irq(&mapping->tree_lock);
		return -EAGAIN;
	}

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

	/*
	 * In the async migration case of moving a page with buffers, lock the
	 * buffers using trylock before the mapping is moved. If the mapping
	 * was moved, we later failed to lock the buffers and could not move
	 * the mapping back due to an elevated page count, we would have to
	 * block waiting on other references to be dropped.
	 */
	if (mode == MIGRATE_ASYNC && head &&
			!buffer_migrate_lock_buffers(head, mode)) {
		page_unfreeze_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);

	/*
	 * Drop cache reference from old page by unfreezing
	 * to one less reference.
	 * We know this isn't the last reference.
	 */
	page_unfreeze_refs(page, expected_count - 1);

	/*
	 * 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 (!PageSwapCache(page) && PageSwapBacked(page)) {
		__dec_zone_page_state(page, NR_SHMEM);
		__inc_zone_page_state(newpage, NR_SHMEM);
	}
	spin_unlock_irq(&mapping->tree_lock);

	return MIGRATEPAGE_SUCCESS;
}

/*
 * The expected number of remaining references is the same as that
 * of migrate_page_move_mapping().
 */
int migrate_huge_page_move_mapping(struct address_space *mapping,
				   struct page *newpage, struct page *page)
{
	int expected_count;
	void **pslot;

	if (!mapping) {
		if (page_count(page) != 1)
			return -EAGAIN;
		return MIGRATEPAGE_SUCCESS;
	}

	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 ||
		radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) {
		spin_unlock_irq(&mapping->tree_lock);
		return -EAGAIN;
	}

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

	get_page(newpage);

	radix_tree_replace_slot(pslot, newpage);

	page_unfreeze_refs(page, expected_count - 1);

	spin_unlock_irq(&mapping->tree_lock);
	return MIGRATEPAGE_SUCCESS;
}

/*
 * Gigantic pages are so large that we do not guarantee that page++ pointer
 * arithmetic will work across the entire page.  We need something more
 * specialized.
 */
static void __copy_gigantic_page(struct page *dst, struct page *src,
				int nr_pages)
{
	int i;
	struct page *dst_base = dst;
	struct page *src_base = src;

	for (i = 0; i < nr_pages; ) {
		cond_resched();
		copy_highpage(dst, src);

		i++;
		dst = mem_map_next(dst, dst_base, i);
		src = mem_map_next(src, src_base, i);
	}
}

static void copy_huge_page(struct page *dst, struct page *src)
{
	int i;
	int nr_pages;

	if (PageHuge(src)) {
		/* hugetlbfs page */
		struct hstate *h = page_hstate(src);
		nr_pages = pages_per_huge_page(h);

		if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) {
			__copy_gigantic_page(dst, src, nr_pages);
			return;
		}
	} else {
		/* thp page */
		BUG_ON(!PageTransHuge(src));
		nr_pages = hpage_nr_pages(src);
	}

	for (i = 0; i < nr_pages; i++) {
		cond_resched();
		copy_highpage(dst + i, src + i);
	}
}

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

	if (PageHuge(page) || PageTransHuge(page))
		copy_huge_page(newpage, page);
	else
		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_PAGE(PageUnevictable(page), 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.
		 * Whereas only part of our page may be dirty.
		 */
		if (PageSwapBacked(page))
			SetPageDirty(newpage);
		else
			__set_page_dirty_nobuffers(newpage);
 	}

	/*
	 * Copy NUMA information to the new page, to prevent over-eager
	 * future migrations of this same page.
	 */
	cpupid = page_cpupid_xchg_last(page, -1);
	page_cpupid_xchg_last(newpage, cpupid);

	mlock_migrate_page(newpage, page);
	ksm_migrate_page(newpage, page);
	/*
	 * Please do not reorder this without considering how mm/ksm.c's
	 * get_ksm_page() depends upon ksm_migrate_page() and PageSwapCache().
	 */
	ClearPageSwapCache(page);
	ClearPagePrivate(page);
	set_page_private(page, 0);

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

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

/*
 * 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,
		enum migrate_mode mode)
{
	int rc;

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

	rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, 0);

	if (rc != MIGRATEPAGE_SUCCESS)
		return rc;

	migrate_page_copy(newpage, page);
	return MIGRATEPAGE_SUCCESS;
}
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, enum migrate_mode mode)
{
	struct buffer_head *bh, *head;
	int rc;

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

	head = page_buffers(page);

	rc = migrate_page_move_mapping(mapping, newpage, page, head, mode, 0);

	if (rc != MIGRATEPAGE_SUCCESS)
		return rc;

	/*
	 * In the async case, migrate_page_move_mapping locked the buffers
	 * with an IRQ-safe spinlock held. In the sync case, the buffers
	 * need to be locked now
	 */
	if (mode != MIGRATE_ASYNC)
		BUG_ON(!buffer_migrate_lock_buffers(head, mode));

	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 MIGRATEPAGE_SUCCESS;
}
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,
		.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, enum migrate_mode mode)
{
	if (PageDirty(page)) {
		/* Only writeback pages in full synchronous migration */
		if (mode != MIGRATE_SYNC)
			return -EBUSY;
		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, mode);
}

/*
 * 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
 *  MIGRATEPAGE_SUCCESS - success
 */
static int move_to_new_page(struct page *newpage, struct page *page,
				int remap_swapcache, enum migrate_mode mode)
{
	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, mode);
	else if (mapping->a_ops->migratepage)
		/*
		 * Most pages have a mapping and most filesystems provide a
		 * migratepage callback. Anonymous pages are part of swap
		 * space which also has its own migratepage callback. This
		 * is the most common path for page migration.
		 */
		rc = mapping->a_ops->migratepage(mapping,
						newpage, page, mode);
	else
		rc = fallback_migrate_page(mapping, newpage, page, mode);

	if (rc != MIGRATEPAGE_SUCCESS) {
		newpage->mapping = NULL;
	} else {
		mem_cgroup_migrate(page, newpage, false);
		if (remap_swapcache)
			remove_migration_ptes(page, newpage);
		page->mapping = NULL;
	}

	unlock_page(newpage);

	return rc;
}

static int __unmap_and_move(struct page *page, struct page *newpage,
				int force, enum migrate_mode mode)
{
	int rc = -EAGAIN;
	int remap_swapcache = 1;
	struct anon_vma *anon_vma = NULL;

	if (!trylock_page(page)) {
		if (!force || mode == MIGRATE_ASYNC)
			goto out;

		/*
		 * It's not safe for direct compaction to call lock_page.
		 * For example, during page readahead pages are added locked
		 * to the LRU. Later, when the IO completes the pages are
		 * marked uptodate and unlocked. However, the queueing
		 * could be merging multiple pages for one bio (e.g.
		 * mpage_readpages). If an allocation happens for the
		 * second or third page, the process can end up locking
		 * the same page twice and deadlocking. Rather than
		 * trying to be clever about what pages can be locked,
		 * avoid the use of lock_page for direct compaction
		 * altogether.
		 */
		if (current->flags & PF_MEMALLOC)
			goto out;

		lock_page(page);
	}

	if (PageWriteback(page)) {
		/*
		 * Only in the case of a full synchronous migration is it
		 * necessary to wait for PageWriteback. In the async case,
		 * the retry loop is too short and in the sync-light case,
		 * the overhead of stalling is too much
		 */
		if (mode != MIGRATE_SYNC) {
			rc = -EBUSY;
			goto out_unlock;
		}
		if (!force)
			goto out_unlock;
		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 get_anon_vma() 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) && !PageKsm(page)) {
		/*
		 * Only page_lock_anon_vma_read() understands the subtleties of
		 * getting a hold on an anon_vma from outside one of its mms.
		 */
		anon_vma = page_get_anon_vma(page);
		if (anon_vma) {
			/*
			 * Anon page
			 */
		} else if (PageSwapCache(page)) {
			/*
			 * We cannot be sure that the anon_vma of an unmapped
			 * swapcache page is safe to use because we don't
			 * know in advance if the VMA that this page belonged
			 * to still exists. If the VMA and others sharing the
			 * data have been freed, then the anon_vma could
			 * already be invalid.
			 *
			 * To avoid this possibility, swapcache pages get
			 * migrated but are not remapped when migration
			 * completes
			 */
			remap_swapcache = 0;
		} else {
			goto out_unlock;
		}
	}

	if (unlikely(isolated_balloon_page(page))) {
		/*
		 * A ballooned page does not need any special attention from
		 * physical to virtual reverse mapping procedures.
		 * Skip any attempt to unmap PTEs or to remap swap cache,
		 * in order to avoid burning cycles at rmap level, and perform
		 * the page migration right away (proteced by page lock).
		 */
		rc = balloon_page_migrate(newpage, page, mode);
		goto out_unlock;
	}

	/*
	 * 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) {
		VM_BUG_ON_PAGE(PageAnon(page), page);
		if (page_has_private(page)) {
			try_to_free_buffers(page);
			goto out_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, remap_swapcache, mode);

	if (rc && remap_swapcache)
		remove_migration_ptes(page, page);

	/* Drop an anon_vma reference if we took one */
	if (anon_vma)
		put_anon_vma(anon_vma);

out_unlock:
	unlock_page(page);
out:
	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, free_page_t put_new_page,
			unsigned long private, struct page *page, int force,
			enum migrate_mode mode)
{
	int rc = 0;
	int *result = NULL;
	struct page *newpage = get_new_page(page, private, &result);

	if (!newpage)
		return -ENOMEM;

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

	if (unlikely(PageTransHuge(page)))
		if (unlikely(split_huge_page(page)))
			goto out;

	rc = __unmap_and_move(page, newpage, force, mode);

out:
	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);
	}

	/*
	 * If migration was not successful and there's a freeing callback, use
	 * it.  Otherwise, putback_lru_page() will drop the reference grabbed
	 * during isolation.
	 */
	if (rc != MIGRATEPAGE_SUCCESS && put_new_page) {
		ClearPageSwapBacked(newpage);
		put_new_page(newpage, private);
	} else if (unlikely(__is_movable_balloon_page(newpage))) {
		/* drop our reference, page already in the balloon */
		put_page(newpage);
	} else
		putback_lru_page(newpage);

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

/*
 * Counterpart of unmap_and_move_page() for hugepage migration.
 *
 * This function doesn't wait the completion of hugepage I/O
 * because there is no race between I/O and migration for hugepage.
 * Note that currently hugepage I/O occurs only in direct I/O
 * where no lock is held and PG_writeback is irrelevant,
 * and writeback status of all subpages are counted in the reference
 * count of the head page (i.e. if all subpages of a 2MB hugepage are
 * under direct I/O, the reference of the head page is 512 and a bit more.)
 * This means that when we try to migrate hugepage whose subpages are
 * doing direct I/O, some references remain after try_to_unmap() and
 * hugepage migration fails without data corruption.
 *
 * There is also no race when direct I/O is issued on the page under migration,
 * because then pte is replaced with migration swap entry and direct I/O code
 * will wait in the page fault for migration to complete.
 */
static int unmap_and_move_huge_page(new_page_t get_new_page,
				free_page_t put_new_page, unsigned long private,
				struct page *hpage, int force,
				enum migrate_mode mode)
{
	int rc = 0;
	int *result = NULL;
	struct page *new_hpage;
	struct anon_vma *anon_vma = NULL;

	/*
	 * Movability of hugepages depends on architectures and hugepage size.
	 * This check is necessary because some callers of hugepage migration
	 * like soft offline and memory hotremove don't walk through page
	 * tables or check whether the hugepage is pmd-based or not before
	 * kicking migration.
	 */
	if (!hugepage_migration_supported(page_hstate(hpage))) {
		putback_active_hugepage(hpage);
		return -ENOSYS;
	}

	new_hpage = get_new_page(hpage, private, &result);
	if (!new_hpage)
		return -ENOMEM;

	rc = -EAGAIN;

	if (!trylock_page(hpage)) {
		if (!force || mode != MIGRATE_SYNC)
			goto out;
		lock_page(hpage);
	}

	if (PageAnon(hpage))
		anon_vma = page_get_anon_vma(hpage);

	try_to_unmap(hpage, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);

	if (!page_mapped(hpage))
		rc = move_to_new_page(new_hpage, hpage, 1, mode);

	if (rc != MIGRATEPAGE_SUCCESS)
		remove_migration_ptes(hpage, hpage);

	if (anon_vma)
		put_anon_vma(anon_vma);

	if (rc == MIGRATEPAGE_SUCCESS)
		hugetlb_cgroup_migrate(hpage, new_hpage);

	unlock_page(hpage);
out:
	if (rc != -EAGAIN)
		putback_active_hugepage(hpage);

	/*
	 * If migration was not successful and there's a freeing callback, use
	 * it.  Otherwise, put_page() will drop the reference grabbed during
	 * isolation.
	 */
	if (rc != MIGRATEPAGE_SUCCESS && put_new_page)
		put_new_page(new_hpage, private);
	else
		put_page(new_hpage);

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

/*
 * migrate_pages - migrate the pages specified in a list, to the free pages
 *		   supplied as the target for the page migration
 *
 * @from:		The list of pages to be migrated.
 * @get_new_page:	The function used to allocate free pages to be used
 *			as the target of the page migration.
 * @put_new_page:	The function used to free target pages if migration
 *			fails, or NULL if no special handling is necessary.
 * @private:		Private data to be passed on to get_new_page()
 * @mode:		The migration mode that specifies the constraints for
 *			page migration, if any.
 * @reason:		The reason for page migration.
 *
 * The function returns after 10 attempts or if no pages are movable any more
 * because the list has become empty or no retryable pages exist any more.
 * The caller should call putback_lru_pages() to return pages to the LRU
 * or free list only if ret != 0.
 *
 * Returns the number of pages that were not migrated, or an error code.
 */
int migrate_pages(struct list_head *from, new_page_t get_new_page,
		free_page_t put_new_page, unsigned long private,
		enum migrate_mode mode, int reason)
{
	int retry = 1;
	int nr_failed = 0;
	int nr_succeeded = 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();

			if (PageHuge(page))
				rc = unmap_and_move_huge_page(get_new_page,
						put_new_page, private, page,
						pass > 2, mode);
			else
				rc = unmap_and_move(get_new_page, put_new_page,
						private, page, pass > 2, mode);

			switch(rc) {
			case -ENOMEM:
				goto out;
			case -EAGAIN:
				retry++;
				break;
			case MIGRATEPAGE_SUCCESS:
				nr_succeeded++;
				break;
			default:
				/*
				 * Permanent failure (-EBUSY, -ENOSYS, etc.):
				 * unlike -EAGAIN case, the failed page is
				 * removed from migration page list and not
				 * retried in the next outer loop.
				 */
				nr_failed++;
				break;
			}
		}
	}
	rc = nr_failed + retry;
out:
	if (nr_succeeded)
		count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded);
	if (nr_failed)
		count_vm_events(PGMIGRATE_FAIL, nr_failed);
	trace_mm_migrate_pages(nr_succeeded, nr_failed, mode, reason);

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

	return rc;
}

#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;

	if (PageHuge(p))
		return alloc_huge_page_node(page_hstate(compound_head(p)),
					pm->node);
	else
		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 || pp->addr < vma->vm_start || !vma_migratable(vma))
			goto set_status;

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

		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))
			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;

		if (PageHuge(page)) {
			if (PageHead(page))
				isolate_huge_page(page, &pagelist);
			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, NULL,
				(unsigned long)pm, MIGRATE_SYNC, MR_SYSCALL);
		if (err)
			putback_movable_pages(&pagelist);
	}

	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, nodemask_t task_nodes,
			 unsigned long nr_pages,
			 const void __user * __user *pages,
			 const int __user *nodes,
			 int __user *status, int flags)
{
	struct page_to_node *pm;
	unsigned long chunk_nr_pages;
	unsigned long chunk_start;
	int err;

	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_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 || addr < vma->vm_start)
			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))
			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;
	nodemask_t task_nodes;

	/* 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 */
	rcu_read_lock();
	task = pid ? find_task_by_vpid(pid) : current;
	if (!task) {
		rcu_read_unlock();
		return -ESRCH;
	}
	get_task_struct(task);

	/*
	 * 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.
	 */
	tcred = __task_cred(task);
	if (!uid_eq(cred->euid, tcred->suid) && !uid_eq(cred->euid, tcred->uid) &&
	    !uid_eq(cred->uid,  tcred->suid) && !uid_eq(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;

	task_nodes = cpuset_mems_allowed(task);
	mm = get_task_mm(task);
	put_task_struct(task);

	if (!mm)
		return -EINVAL;

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

	mmput(mm);
	return err;

out:
	put_task_struct(task);
	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;
}

#ifdef CONFIG_NUMA_BALANCING
/*
 * Returns true if this is a safe migration target node for misplaced NUMA
 * pages. Currently it only checks the watermarks which crude
 */
static bool migrate_balanced_pgdat(struct pglist_data *pgdat,
				   unsigned long nr_migrate_pages)
{
	int z;
	for (z = pgdat->nr_zones - 1; z >= 0; z--) {
		struct zone *zone = pgdat->node_zones + z;

		if (!populated_zone(zone))
			continue;

		if (!zone_reclaimable(zone))
			continue;

		/* Avoid waking kswapd by allocating pages_to_migrate pages. */
		if (!zone_watermark_ok(zone, 0,
				       high_wmark_pages(zone) +
				       nr_migrate_pages,
				       0, 0))
			continue;
		return true;
	}
	return false;
}

static struct page *alloc_misplaced_dst_page(struct page *page,
					   unsigned long data,
					   int **result)
{
	int nid = (int) data;
	struct page *newpage;

	newpage = alloc_pages_exact_node(nid,
					 (GFP_HIGHUSER_MOVABLE |
					  __GFP_THISNODE | __GFP_NOMEMALLOC |
					  __GFP_NORETRY | __GFP_NOWARN) &
					 ~GFP_IOFS, 0);

	return newpage;
}

/*
 * page migration rate limiting control.
 * Do not migrate more than @pages_to_migrate in a @migrate_interval_millisecs
 * window of time. Default here says do not migrate more than 1280M per second.
 * If a node is rate-limited then PTE NUMA updates are also rate-limited. However
 * as it is faults that reset the window, pte updates will happen unconditionally
 * if there has not been a fault since @pteupdate_interval_millisecs after the
 * throttle window closed.
 */
static unsigned int migrate_interval_millisecs __read_mostly = 100;
static unsigned int pteupdate_interval_millisecs __read_mostly = 1000;
static unsigned int ratelimit_pages __read_mostly = 128 << (20 - PAGE_SHIFT);

/* Returns true if NUMA migration is currently rate limited */
bool migrate_ratelimited(int node)
{
	pg_data_t *pgdat = NODE_DATA(node);

	if (time_after(jiffies, pgdat->numabalancing_migrate_next_window +
				msecs_to_jiffies(pteupdate_interval_millisecs)))
		return false;

	if (pgdat->numabalancing_migrate_nr_pages < ratelimit_pages)
		return false;

	return true;
}

/* Returns true if the node is migrate rate-limited after the update */
static bool numamigrate_update_ratelimit(pg_data_t *pgdat,
					unsigned long nr_pages)
{
	/*
	 * Rate-limit the amount of data that is being migrated to a node.
	 * Optimal placement is no good if the memory bus is saturated and
	 * all the time is being spent migrating!
	 */
	if (time_after(jiffies, pgdat->numabalancing_migrate_next_window)) {
		spin_lock(&pgdat->numabalancing_migrate_lock);
		pgdat->numabalancing_migrate_nr_pages = 0;
		pgdat->numabalancing_migrate_next_window = jiffies +
			msecs_to_jiffies(migrate_interval_millisecs);
		spin_unlock(&pgdat->numabalancing_migrate_lock);
	}
	if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages) {
		trace_mm_numa_migrate_ratelimit(current, pgdat->node_id,
								nr_pages);
		return true;
	}

	/*
	 * This is an unlocked non-atomic update so errors are possible.
	 * The consequences are failing to migrate when we potentiall should
	 * have which is not severe enough to warrant locking. If it is ever
	 * a problem, it can be converted to a per-cpu counter.
	 */
	pgdat->numabalancing_migrate_nr_pages += nr_pages;
	return false;
}

static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
{
	int page_lru;

	VM_BUG_ON_PAGE(compound_order(page) && !PageTransHuge(page), page);

	/* Avoid migrating to a node that is nearly full */
	if (!migrate_balanced_pgdat(pgdat, 1UL << compound_order(page)))
		return 0;

	if (isolate_lru_page(page))
		return 0;

	/*
	 * migrate_misplaced_transhuge_page() skips page migration's usual
	 * check on page_count(), so we must do it here, now that the page
	 * has been isolated: a GUP pin, or any other pin, prevents migration.
	 * The expected page count is 3: 1 for page's mapcount and 1 for the
	 * caller's pin and 1 for the reference taken by isolate_lru_page().
	 */
	if (PageTransHuge(page) && page_count(page) != 3) {
		putback_lru_page(page);
		return 0;
	}

	page_lru = page_is_file_cache(page);
	mod_zone_page_state(page_zone(page), NR_ISOLATED_ANON + page_lru,
				hpage_nr_pages(page));

	/*
	 * Isolating the page has taken another reference, so the
	 * caller's reference can be safely dropped without the page
	 * disappearing underneath us during migration.
	 */
	put_page(page);
	return 1;
}

bool pmd_trans_migrating(pmd_t pmd)
{
	struct page *page = pmd_page(pmd);
	return PageLocked(page);
}

void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd)
{
	struct page *page = pmd_page(*pmd);
	wait_on_page_locked(page);
}

/*
 * Attempt to migrate a misplaced page to the specified destination
 * node. Caller is expected to have an elevated reference count on
 * the page that will be dropped by this function before returning.
 */
int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
			   int node)
{
	pg_data_t *pgdat = NODE_DATA(node);
	int isolated;
	int nr_remaining;
	LIST_HEAD(migratepages);

	/*
	 * Don't migrate file pages that are mapped in multiple processes
	 * with execute permissions as they are probably shared libraries.
	 */
	if (page_mapcount(page) != 1 && page_is_file_cache(page) &&
	    (vma->vm_flags & VM_EXEC))
		goto out;

	/*
	 * Rate-limit the amount of data that is being migrated to a node.
	 * Optimal placement is no good if the memory bus is saturated and
	 * all the time is being spent migrating!
	 */
	if (numamigrate_update_ratelimit(pgdat, 1))
		goto out;

	isolated = numamigrate_isolate_page(pgdat, page);
	if (!isolated)
		goto out;

	list_add(&page->lru, &migratepages);
	nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page,
				     NULL, node, MIGRATE_ASYNC,
				     MR_NUMA_MISPLACED);
	if (nr_remaining) {
		if (!list_empty(&migratepages)) {
			list_del(&page->lru);
			dec_zone_page_state(page, NR_ISOLATED_ANON +
					page_is_file_cache(page));
			putback_lru_page(page);
		}
		isolated = 0;
	} else
		count_vm_numa_event(NUMA_PAGE_MIGRATE);
	BUG_ON(!list_empty(&migratepages));
	return isolated;

out:
	put_page(page);
	return 0;
}
#endif /* CONFIG_NUMA_BALANCING */

#if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
/*
 * Migrates a THP to a given target node. page must be locked and is unlocked
 * before returning.
 */
int migrate_misplaced_transhuge_page(struct mm_struct *mm,
				struct vm_area_struct *vma,
				pmd_t *pmd, pmd_t entry,
				unsigned long address,
				struct page *page, int node)
{
	spinlock_t *ptl;
	pg_data_t *pgdat = NODE_DATA(node);
	int isolated = 0;
	struct page *new_page = NULL;
	int page_lru = page_is_file_cache(page);
	unsigned long mmun_start = address & HPAGE_PMD_MASK;
	unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE;
	pmd_t orig_entry;

	/*
	 * Rate-limit the amount of data that is being migrated to a node.
	 * Optimal placement is no good if the memory bus is saturated and
	 * all the time is being spent migrating!
	 */
	if (numamigrate_update_ratelimit(pgdat, HPAGE_PMD_NR))
		goto out_dropref;

	new_page = alloc_pages_node(node,
		(GFP_TRANSHUGE | __GFP_THISNODE) & ~__GFP_WAIT,
		HPAGE_PMD_ORDER);
	if (!new_page)
		goto out_fail;

	isolated = numamigrate_isolate_page(pgdat, page);
	if (!isolated) {
		put_page(new_page);
		goto out_fail;
	}

	if (mm_tlb_flush_pending(mm))
		flush_tlb_range(vma, mmun_start, mmun_end);

	/* Prepare a page as a migration target */
	__set_page_locked(new_page);
	SetPageSwapBacked(new_page);

	/* anon mapping, we can simply copy page->mapping to the new page: */
	new_page->mapping = page->mapping;
	new_page->index = page->index;
	migrate_page_copy(new_page, page);
	WARN_ON(PageLRU(new_page));

	/* Recheck the target PMD */
	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
	ptl = pmd_lock(mm, pmd);
	if (unlikely(!pmd_same(*pmd, entry) || page_count(page) != 2)) {
fail_putback:
		spin_unlock(ptl);
		mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);

		/* Reverse changes made by migrate_page_copy() */
		if (TestClearPageActive(new_page))
			SetPageActive(page);
		if (TestClearPageUnevictable(new_page))
			SetPageUnevictable(page);
		mlock_migrate_page(page, new_page);

		unlock_page(new_page);
		put_page(new_page);		/* Free it */

		/* Retake the callers reference and putback on LRU */
		get_page(page);
		putback_lru_page(page);
		mod_zone_page_state(page_zone(page),
			 NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR);

		goto out_unlock;
	}

	orig_entry = *pmd;
	entry = mk_pmd(new_page, vma->vm_page_prot);
	entry = pmd_mkhuge(entry);
	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);

	/*
	 * Clear the old entry under pagetable lock and establish the new PTE.
	 * Any parallel GUP will either observe the old page blocking on the
	 * page lock, block on the page table lock or observe the new page.
	 * The SetPageUptodate on the new page and page_add_new_anon_rmap
	 * guarantee the copy is visible before the pagetable update.
	 */
	flush_cache_range(vma, mmun_start, mmun_end);
	page_add_anon_rmap(new_page, vma, mmun_start);
	pmdp_clear_flush(vma, mmun_start, pmd);
	set_pmd_at(mm, mmun_start, pmd, entry);
	flush_tlb_range(vma, mmun_start, mmun_end);
	update_mmu_cache_pmd(vma, address, &entry);

	if (page_count(page) != 2) {
		set_pmd_at(mm, mmun_start, pmd, orig_entry);
		flush_tlb_range(vma, mmun_start, mmun_end);
		update_mmu_cache_pmd(vma, address, &entry);
		page_remove_rmap(new_page);
		goto fail_putback;
	}

	mem_cgroup_migrate(page, new_page, false);

	page_remove_rmap(page);

	spin_unlock(ptl);
	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);

	/* Take an "isolate" reference and put new page on the LRU. */
	get_page(new_page);
	putback_lru_page(new_page);

	unlock_page(new_page);
	unlock_page(page);
	put_page(page);			/* Drop the rmap reference */
	put_page(page);			/* Drop the LRU isolation reference */

	count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR);
	count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR);

	mod_zone_page_state(page_zone(page),
			NR_ISOLATED_ANON + page_lru,
			-HPAGE_PMD_NR);
	return isolated;

out_fail:
	count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
out_dropref:
	ptl = pmd_lock(mm, pmd);
	if (pmd_same(*pmd, entry)) {
		entry = pmd_mknonnuma(entry);
		set_pmd_at(mm, mmun_start, pmd, entry);
		update_mmu_cache_pmd(vma, address, &entry);
	}
	spin_unlock(ptl);

out_unlock:
	unlock_page(page);
	put_page(page);
	return 0;
}
#endif /* CONFIG_NUMA_BALANCING */

#endif /* CONFIG_NUMA */