summaryrefslogtreecommitdiffstats
path: root/mm/compaction.c
blob: 4af1577adb5c3b33d720403b83d18d7037d45045 (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
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
/*
 * linux/mm/compaction.c
 *
 * Memory compaction for the reduction of external fragmentation. Note that
 * this heavily depends upon page migration to do all the real heavy
 * lifting
 *
 * Copyright IBM Corp. 2007-2010 Mel Gorman <mel@csn.ul.ie>
 */
#include <linux/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/balloon_compaction.h>
#include <linux/page-isolation.h>
#include <linux/kasan.h>
#include <linux/kthread.h>
#include <linux/freezer.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)
{
	struct page *page;

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

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

#ifdef CONFIG_COMPACTION

/* 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 = COMPACT_CONTENDED_LOCK;
			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 = COMPACT_CONTENDED_SCHED;
		return true;
	}

	if (need_resched()) {
		if (cc->mode == MIGRATE_ASYNC) {
			cc->contended = COMPACT_CONTENDED_SCHED;
			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 = COMPACT_CONTENDED_SCHED;
			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;

	cursor = pfn_to_page(blockpfn);

	/* Isolate free pages. */
	for (; blockpfn < end_pfn; blockpfn++, cursor++) {
		int isolated, i;
		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, break it into order-0 pages */
		isolated = split_free_page(page);
		total_isolated += isolated;
		for (i = 0; i < isolated; i++) {
			list_add(&page->lru, freelist);
			page++;
		}

		/* If a page was split, advance to the end of it */
		if (isolated) {
			cc->nr_freepages += isolated;
			if (!strict &&
				cc->nr_migratepages <= cc->nr_freepages) {
				blockpfn += isolated;
				break;
			}

			blockpfn += isolated - 1;
			cursor += isolated - 1;
			continue;
		}

isolate_fail:
		if (strict)
			break;
		else
			continue;

	}

	/*
	 * 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;

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

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

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

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

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

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

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

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

	if (list_empty(&cc->migratepages))
		return;

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

	mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
	mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
}

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

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

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

/**
 * isolate_migratepages_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++) {
		bool is_lru;

		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, 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;
		}

		/*
		 * Check may be lockless but that's ok as we recheck later.
		 * It's possible to migrate LRU pages and balloon pages
		 * Skip any other type of page
		 */
		is_lru = PageLRU(page);
		if (!is_lru) {
			if (unlikely(balloon_page_movable(page))) {
				if (balloon_page_isolate(page)) {
					/* Successfully isolated */
					goto isolate_success;
				}
			}
		}

		/*
		 * 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;
		}

		if (!is_lru)
			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,
								&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);

		/* 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));

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,	flags);
				locked = false;
			}
			acct_isolated(zone, cc);
			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, 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;
	}
	acct_isolated(cc->zone, cc);

	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 page *page)
{
	/* 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;
	}

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

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

/*
 * Test whether the free scanner has reached the same or lower pageblock than
 * the migration scanner, and compaction should thus terminate.
 */
static inline bool compact_scanners_met(struct compact_control *cc)
{
	return (cc->free_pfn >> pageblock_order)
		<= (cc->migrate_pfn >> pageblock_order);
}

/*
 * Based on information in the current compact_control, find blocks
 * suitable for isolating free pages from and then isolate them.
 */
static void isolate_freepages(struct compact_control *cc)
{
	struct zone *zone = cc->zone;
	struct page *page;
	unsigned long block_start_pfn;	/* start of current pageblock */
	unsigned long isolate_start_pfn; /* exact pfn we start at */
	unsigned long block_end_pfn;	/* end of current pageblock */
	unsigned long low_pfn;	     /* lowest pfn scanner is able to scan */
	struct list_head *freelist = &cc->freepages;

	/*
	 * Initialise the free scanner. The starting point is where we last
	 * successfully isolated from, zone-cached value, or the end of the
	 * zone when isolating for the first time. For looping we also need
	 * this pfn aligned down to the pageblock boundary, because we do
	 * block_start_pfn -= pageblock_nr_pages in the for loop.
	 * For ending point, take care when isolating in last pageblock of a
	 * a zone which ends in the middle of a pageblock.
	 * The low boundary is the end of the pageblock the migration scanner
	 * is using.
	 */
	isolate_start_pfn = cc->free_pfn;
	block_start_pfn = pageblock_start_pfn(cc->free_pfn);
	block_end_pfn = min(block_start_pfn + pageblock_nr_pages,
						zone_end_pfn(zone));
	low_pfn = pageblock_end_pfn(cc->migrate_pfn);

	/*
	 * Isolate free pages until enough are available to migrate the
	 * pages on cc->migratepages. We stop searching if the migrate
	 * and free page scanners meet or enough free pages are isolated.
	 */
	for (; block_start_pfn >= low_pfn;
				block_end_pfn = block_start_pfn,
				block_start_pfn -= pageblock_nr_pages,
				isolate_start_pfn = block_start_pfn) {

		/*
		 * This can iterate a massively long zone without finding any
		 * suitable migration targets, so periodically check if we need
		 * to schedule, or even abort async compaction.
		 */
		if (!(block_start_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages))
						&& compact_should_abort(cc))
			break;

		page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn,
									zone);
		if (!page)
			continue;

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

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

		/* Found a block suitable for isolating free pages from. */
		isolate_freepages_block(cc, &isolate_start_pfn,
					block_end_pfn, freelist, false);

		/*
		 * If we isolated enough freepages, or aborted due to async
		 * compaction being contended, terminate the loop.
		 * Remember where the free scanner should restart next time,
		 * which is where isolate_freepages_block() left off.
		 * But if it scanned the whole pageblock, isolate_start_pfn
		 * now points at block_end_pfn, which is the start of the next
		 * pageblock.
		 * In that case we will however want to restart at the start
		 * of the previous pageblock.
		 */
		if ((cc->nr_freepages >= cc->nr_migratepages)
							|| cc->contended) {
			if (isolate_start_pfn >= block_end_pfn)
				isolate_start_pfn =
					block_start_pfn - pageblock_nr_pages;
			break;
		} else {
			/*
			 * isolate_freepages_block() should not terminate
			 * prematurely unless contended, or isolated enough
			 */
			VM_BUG_ON(isolate_start_pfn < block_end_pfn);
		}
	}

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

	/*
	 * Record where the free scanner will restart next time. Either we
	 * broke from the loop and set isolate_start_pfn based on the last
	 * call to isolate_freepages_block(), or we met the migration scanner
	 * and the loop terminated due to isolate_start_pfn < low_pfn
	 */
	cc->free_pfn = isolate_start_pfn;
}

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

	/*
	 * Isolate free pages if necessary, and if we are not aborting due to
	 * contention.
	 */
	if (list_empty(&cc->freepages)) {
		if (!cc->contended)
			isolate_freepages(cc);

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

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

	return freepage;
}

/*
 * This is a migrate-callback that "frees" freepages back to the isolated
 * freelist.  All pages on the freelist are from the same zone, so there is no
 * special handling needed for NUMA.
 */
static void compaction_free(struct page *page, unsigned long data)
{
	struct compact_control *cc = (struct compact_control *)data;

	list_add(&page->lru, &cc->freepages);
	cc->nr_freepages++;
}

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

/*
 * Allow userspace to control policy on scanning the unevictable LRU for
 * compactable pages.
 */
int sysctl_compact_unevictable_allowed __read_mostly = 1;

/*
 * Isolate all pages that can be migrated from the first suitable block,
 * starting at the block pointed to by the migrate scanner pfn within
 * compact_control.
 */
static isolate_migrate_t isolate_migratepages(struct zone *zone,
					struct compact_control *cc)
{
	unsigned long block_start_pfn;
	unsigned long block_end_pfn;
	unsigned long low_pfn;
	struct page *page;
	const isolate_mode_t isolate_mode =
		(sysctl_compact_unevictable_allowed ? ISOLATE_UNEVICTABLE : 0) |
		(cc->mode == MIGRATE_ASYNC ? ISOLATE_ASYNC_MIGRATE : 0);

	/*
	 * Start at where we last stopped, or beginning of the zone as
	 * initialized by compact_zone()
	 */
	low_pfn = cc->migrate_pfn;
	block_start_pfn = pageblock_start_pfn(low_pfn);
	if (block_start_pfn < zone->zone_start_pfn)
		block_start_pfn = zone->zone_start_pfn;

	/* Only scan within a pageblock boundary */
	block_end_pfn = pageblock_end_pfn(low_pfn);

	/*
	 * Iterate over whole pageblocks until we find the first suitable.
	 * Do not cross the free scanner.
	 */
	for (; block_end_pfn <= cc->free_pfn;
			low_pfn = block_end_pfn,
			block_start_pfn = block_end_pfn,
			block_end_pfn += pageblock_nr_pages) {

		/*
		 * This can potentially iterate a massively long zone with
		 * many pageblocks unsuitable, so periodically check if we
		 * need to schedule, or even abort async compaction.
		 */
		if (!(low_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages))
						&& compact_should_abort(cc))
			break;

		page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn,
									zone);
		if (!page)
			continue;

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

		/*
		 * For async compaction, also only scan in MOVABLE blocks.
		 * Async compaction is optimistic to see if the minimum amount
		 * of work satisfies the allocation.
		 */
		if (cc->mode == MIGRATE_ASYNC &&
		    !migrate_async_suitable(get_pageblock_migratetype(page)))
			continue;

		/* Perform the isolation */
		low_pfn = isolate_migratepages_block(cc, low_pfn,
						block_end_pfn, isolate_mode);

		if (!low_pfn || cc->contended) {
			acct_isolated(zone, cc);
			return ISOLATE_ABORT;
		}

		/*
		 * Either we isolated something and proceed with migration. Or
		 * we failed and compact_zone should decide if we should
		 * continue or not.
		 */
		break;
	}

	acct_isolated(zone, cc);
	/* Record where migration scanner will be restarted. */
	cc->migrate_pfn = low_pfn;

	return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE;
}

/*
 * order == -1 is expected when compacting via
 * /proc/sys/vm/compact_memory
 */
static inline bool is_via_compact_memory(int order)
{
	return order == -1;
}

static enum compact_result __compact_finished(struct zone *zone, struct compact_control *cc,
			    const int migratetype)
{
	unsigned int order;
	unsigned long watermark;

	if (cc->contended || fatal_signal_pending(current))
		return COMPACT_CONTENDED;

	/* Compaction run completes if the migrate and free scanner meet */
	if (compact_scanners_met(cc)) {
		/* Let the next compaction start anew. */
		reset_cached_positions(zone);

		/*
		 * Mark that the PG_migrate_skip information should be cleared
		 * by kswapd when it goes to sleep. kcompactd does not set the
		 * flag itself as the decision to be clear should be directly
		 * based on an allocation request.
		 */
		if (cc->direct_compaction)
			zone->compact_blockskip_flush = true;

		if (cc->whole_zone)
			return COMPACT_COMPLETE;
		else
			return COMPACT_PARTIAL_SKIPPED;
	}

	if (is_via_compact_memory(cc->order))
		return COMPACT_CONTINUE;

	/* Compaction run is not finished if the watermark is not met */
	watermark = low_wmark_pages(zone);

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

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

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

#ifdef CONFIG_CMA
		/* MIGRATE_MOVABLE can fallback on MIGRATE_CMA */
		if (migratetype == MIGRATE_MOVABLE &&
			!list_empty(&area->free_list[MIGRATE_CMA]))
			return COMPACT_PARTIAL;
#endif
		/*
		 * Job done if allocation would steal freepages from
		 * other migratetype buddy lists.
		 */
		if (find_suitable_fallback(area, order, migratetype,
						true, &can_steal) != -1)
			return COMPACT_PARTIAL;
	}

	return COMPACT_NO_SUITABLE_PAGE;
}

static enum compact_result compact_finished(struct zone *zone,
			struct compact_control *cc,
			const int migratetype)
{
	int ret;

	ret = __compact_finished(zone, cc, migratetype);
	trace_mm_compaction_finished(zone, cc->order, ret);
	if (ret == COMPACT_NO_SUITABLE_PAGE)
		ret = COMPACT_CONTINUE;

	return ret;
}

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

	if (is_via_compact_memory(order))
		return COMPACT_CONTINUE;

	watermark = low_wmark_pages(zone);
	/*
	 * If watermarks for high-order allocation are already met, there
	 * should be no need for compaction at all.
	 */
	if (zone_watermark_ok(zone, order, watermark, classzone_idx,
								alloc_flags))
		return COMPACT_PARTIAL;

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

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

	return COMPACT_CONTINUE;
}

enum compact_result compaction_suitable(struct zone *zone, int order,
					unsigned int alloc_flags,
					int classzone_idx)
{
	enum compact_result ret;

	ret = __compaction_suitable(zone, order, alloc_flags, classzone_idx);
	trace_mm_compaction_suitable(zone, order, ret);
	if (ret == COMPACT_NOT_SUITABLE_ZONE)
		ret = COMPACT_SKIPPED;

	return ret;
}

static enum compact_result compact_zone(struct zone *zone, struct compact_control *cc)
{
	enum compact_result ret;
	unsigned long start_pfn = zone->zone_start_pfn;
	unsigned long end_pfn = zone_end_pfn(zone);
	const int migratetype = gfpflags_to_migratetype(cc->gfp_mask);
	const bool sync = cc->mode != MIGRATE_ASYNC;

	ret = compaction_suitable(zone, cc->order, cc->alloc_flags,
							cc->classzone_idx);
	/* Compaction is likely to fail */
	if (ret == COMPACT_PARTIAL || ret == COMPACT_SKIPPED)
		return ret;

	/* huh, compaction_suitable is returning something unexpected */
	VM_BUG_ON(ret != COMPACT_CONTINUE);

	/*
	 * Clear pageblock skip if there were failures recently and compaction
	 * is about to be retried after being deferred.
	 */
	if (compaction_restarting(zone, cc->order))
		__reset_isolation_suitable(zone);

	/*
	 * Setup to move all movable pages to the end of the zone. Used cached
	 * information on where the scanners should start but check that it
	 * is initialised by ensuring the values are within zone boundaries.
	 */
	cc->migrate_pfn = zone->compact_cached_migrate_pfn[sync];
	cc->free_pfn = zone->compact_cached_free_pfn;
	if (cc->free_pfn < start_pfn || cc->free_pfn >= end_pfn) {
		cc->free_pfn = pageblock_start_pfn(end_pfn - 1);
		zone->compact_cached_free_pfn = cc->free_pfn;
	}
	if (cc->migrate_pfn < start_pfn || cc->migrate_pfn >= end_pfn) {
		cc->migrate_pfn = start_pfn;
		zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn;
		zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn;
	}

	if (cc->migrate_pfn == start_pfn)
		cc->whole_zone = true;

	cc->last_migrated_pfn = 0;

	trace_mm_compaction_begin(start_pfn, cc->migrate_pfn,
				cc->free_pfn, end_pfn, sync);

	migrate_prep_local();

	while ((ret = compact_finished(zone, cc, migratetype)) ==
						COMPACT_CONTINUE) {
		int err;

		switch (isolate_migratepages(zone, cc)) {
		case ISOLATE_ABORT:
			ret = COMPACT_CONTENDED;
			putback_movable_pages(&cc->migratepages);
			cc->nr_migratepages = 0;
			goto out;
		case ISOLATE_NONE:
			/*
			 * We haven't isolated and migrated anything, but
			 * there might still be unflushed migrations from
			 * previous cc->order aligned block.
			 */
			goto check_drain;
		case ISOLATE_SUCCESS:
			;
		}

		err = migrate_pages(&cc->migratepages, compaction_alloc,
				compaction_free, (unsigned long)cc, cc->mode,
				MR_COMPACTION);

		trace_mm_compaction_migratepages(cc->nr_migratepages, err,
							&cc->migratepages);

		/* All pages were either migrated or will be released */
		cc->nr_migratepages = 0;
		if (err) {
			putback_movable_pages(&cc->migratepages);
			/*
			 * migrate_pages() may return -ENOMEM when scanners meet
			 * and we want compact_finished() to detect it
			 */
			if (err == -ENOMEM && !compact_scanners_met(cc)) {
				ret = COMPACT_CONTENDED;
				goto out;
			}
			/*
			 * We failed to migrate at least one page in the current
			 * order-aligned block, so skip the rest of it.
			 */
			if (cc->direct_compaction &&
						(cc->mode == MIGRATE_ASYNC)) {
				cc->migrate_pfn = block_end_pfn(
						cc->migrate_pfn - 1, cc->order);
				/* Draining pcplists is useless in this case */
				cc->last_migrated_pfn = 0;

			}
		}

check_drain:
		/*
		 * Has the migration scanner moved away from the previous
		 * cc->order aligned block where we migrated from? If yes,
		 * flush the pages that were freed, so that they can merge and
		 * compact_finished() can detect immediately if allocation
		 * would succeed.
		 */
		if (cc->order > 0 && cc->last_migrated_pfn) {
			int cpu;
			unsigned long current_block_start =
				block_start_pfn(cc->migrate_pfn, cc->order);

			if (cc->last_migrated_pfn < current_block_start) {
				cpu = get_cpu();
				lru_add_drain_cpu(cpu);
				drain_local_pages(zone);
				put_cpu();
				/* No more flushing until we migrate again */
				cc->last_migrated_pfn = 0;
			}
		}

	}

out:
	/*
	 * Release free pages and update where the free scanner should restart,
	 * so we don't leave any returned pages behind in the next attempt.
	 */
	if (cc->nr_freepages > 0) {
		unsigned long free_pfn = release_freepages(&cc->freepages);

		cc->nr_freepages = 0;
		VM_BUG_ON(free_pfn == 0);
		/* The cached pfn is always the first in a pageblock */
		free_pfn = pageblock_start_pfn(free_pfn);
		/*
		 * Only go back, not forward. The cached pfn might have been
		 * already reset to zone end in compact_finished()
		 */
		if (free_pfn > zone->compact_cached_free_pfn)
			zone->compact_cached_free_pfn = free_pfn;
	}

	trace_mm_compaction_end(start_pfn, cc->migrate_pfn,
				cc->free_pfn, end_pfn, sync, ret);

	if (ret == COMPACT_CONTENDED)
		ret = COMPACT_PARTIAL;

	return ret;
}

static enum compact_result compact_zone_order(struct zone *zone, int order,
		gfp_t gfp_mask, enum migrate_mode mode, int *contended,
		unsigned int alloc_flags, int classzone_idx)
{
	enum compact_result ret;
	struct compact_control cc = {
		.nr_freepages = 0,
		.nr_migratepages = 0,
		.order = order,
		.gfp_mask = gfp_mask,
		.zone = zone,
		.mode = mode,
		.alloc_flags = alloc_flags,
		.classzone_idx = classzone_idx,
		.direct_compaction = true,
	};
	INIT_LIST_HEAD(&cc.freepages);
	INIT_LIST_HEAD(&cc.migratepages);

	ret = compact_zone(zone, &cc);

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

	*contended = cc.contended;
	return ret;
}

int sysctl_extfrag_threshold = 500;

/**
 * try_to_compact_pages - Direct compact to satisfy a high-order allocation
 * @gfp_mask: The GFP mask of the current allocation
 * @order: The order of the current allocation
 * @alloc_flags: The allocation flags of the current allocation
 * @ac: The context of current allocation
 * @mode: The migration mode for async, sync light, or sync migration
 * @contended: Return value that determines if compaction was aborted due to
 *	       need_resched() or lock contention
 *
 * This is the main entry point for direct page compaction.
 */
enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
		unsigned int alloc_flags, const struct alloc_context *ac,
		enum migrate_mode mode, int *contended)
{
	int may_enter_fs = gfp_mask & __GFP_FS;
	int may_perform_io = gfp_mask & __GFP_IO;
	struct zoneref *z;
	struct zone *zone;
	enum compact_result rc = COMPACT_SKIPPED;
	int all_zones_contended = COMPACT_CONTENDED_LOCK; /* init for &= op */

	*contended = COMPACT_CONTENDED_NONE;

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

	trace_mm_compaction_try_to_compact_pages(order, gfp_mask, mode);

	/* Compact each zone in the list */
	for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx,
								ac->nodemask) {
		enum compact_result status;
		int zone_contended;

		if (compaction_deferred(zone, order)) {
			rc = max_t(enum compact_result, COMPACT_DEFERRED, rc);
			continue;
		}

		status = compact_zone_order(zone, order, gfp_mask, mode,
				&zone_contended, alloc_flags,
				ac_classzone_idx(ac));
		rc = max(status, rc);
		/*
		 * It takes at least one zone that wasn't lock contended
		 * to clear all_zones_contended.
		 */
		all_zones_contended &= zone_contended;

		/* If a normal allocation would succeed, stop compacting */
		if (zone_watermark_ok(zone, order, low_wmark_pages(zone),
					ac_classzone_idx(ac), alloc_flags)) {
			/*
			 * We think the allocation will succeed in this zone,
			 * but it is not certain, hence the false. The caller
			 * will repeat this with true if allocation indeed
			 * succeeds in this zone.
			 */
			compaction_defer_reset(zone, order, false);
			/*
			 * It is possible that async compaction aborted due to
			 * need_resched() and the watermarks were ok thanks to
			 * somebody else freeing memory. The allocation can
			 * however still fail so we better signal the
			 * need_resched() contention anyway (this will not
			 * prevent the allocation attempt).
			 */
			if (zone_contended == COMPACT_CONTENDED_SCHED)
				*contended = COMPACT_CONTENDED_SCHED;

			goto break_loop;
		}

		if (mode != MIGRATE_ASYNC && (status == COMPACT_COMPLETE ||
					status == COMPACT_PARTIAL_SKIPPED)) {
			/*
			 * We think that allocation won't succeed in this zone
			 * so we defer compaction there. If it ends up
			 * succeeding after all, it will be reset.
			 */
			defer_compaction(zone, order);
		}

		/*
		 * We might have stopped compacting due to need_resched() in
		 * async compaction, or due to a fatal signal detected. In that
		 * case do not try further zones and signal need_resched()
		 * contention.
		 */
		if ((zone_contended == COMPACT_CONTENDED_SCHED)
					|| fatal_signal_pending(current)) {
			*contended = COMPACT_CONTENDED_SCHED;
			goto break_loop;
		}

		continue;
break_loop:
		/*
		 * We might not have tried all the zones, so  be conservative
		 * and assume they are not all lock contended.
		 */
		all_zones_contended = 0;
		break;
	}

	/*
	 * If at least one zone wasn't deferred or skipped, we report if all
	 * zones that were tried were lock contended.
	 */
	if (rc > COMPACT_INACTIVE && all_zones_contended)
		*contended = COMPACT_CONTENDED_LOCK;

	return rc;
}


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

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

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

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

		/*
		 * When called via /proc/sys/vm/compact_memory
		 * this makes sure we compact the whole zone regardless of
		 * cached scanner positions.
		 */
		if (is_via_compact_memory(cc->order))
			__reset_isolation_suitable(zone);

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

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

		if (is_via_compact_memory(cc->order))
			continue;

		if (zone_watermark_ok(zone, cc->order,
				low_wmark_pages(zone), 0, 0))
			compaction_defer_reset(zone, cc->order, false);
	}
}

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

	if (!order)
		return;

	__compact_pgdat(pgdat, &cc);
}

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

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

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

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

	for_each_online_node(nid)
		compact_node(nid);
}

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

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

	return 0;
}

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

	return 0;
}

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

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

		compact_node(nid);
	}

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

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

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

static inline bool kcompactd_work_requested(pg_data_t *pgdat)
{
	return pgdat->kcompactd_max_order > 0 || kthread_should_stop();
}

static bool kcompactd_node_suitable(pg_data_t *pgdat)
{
	int zoneid;
	struct zone *zone;
	enum zone_type classzone_idx = pgdat->kcompactd_classzone_idx;

	for (zoneid = 0; zoneid < classzone_idx; zoneid++) {
		zone = &pgdat->node_zones[zoneid];

		if (!populated_zone(zone))
			continue;

		if (compaction_suitable(zone, pgdat->kcompactd_max_order, 0,
					classzone_idx) == COMPACT_CONTINUE)
			return true;
	}

	return false;
}

static void kcompactd_do_work(pg_data_t *pgdat)
{
	/*
	 * With no special task, compact all zones so that a page of requested
	 * order is allocatable.
	 */
	int zoneid;
	struct zone *zone;
	struct compact_control cc = {
		.order = pgdat->kcompactd_max_order,
		.classzone_idx = pgdat->kcompactd_classzone_idx,
		.mode = MIGRATE_SYNC_LIGHT,
		.ignore_skip_hint = true,

	};
	bool success = false;

	trace_mm_compaction_kcompactd_wake(pgdat->node_id, cc.order,
							cc.classzone_idx);
	count_vm_event(KCOMPACTD_WAKE);

	for (zoneid = 0; zoneid < cc.classzone_idx; zoneid++) {
		int status;

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

		if (compaction_deferred(zone, cc.order))
			continue;

		if (compaction_suitable(zone, cc.order, 0, zoneid) !=
							COMPACT_CONTINUE)
			continue;

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

		if (kthread_should_stop())
			return;
		status = compact_zone(zone, &cc);

		if (zone_watermark_ok(zone, cc.order, low_wmark_pages(zone),
						cc.classzone_idx, 0)) {
			success = true;
			compaction_defer_reset(zone, cc.order, false);
		} else if (status == COMPACT_PARTIAL_SKIPPED || status == COMPACT_COMPLETE) {
			/*
			 * We use sync migration mode here, so we defer like
			 * sync direct compaction does.
			 */
			defer_compaction(zone, cc.order);
		}

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

	/*
	 * Regardless of success, we are done until woken up next. But remember
	 * the requested order/classzone_idx in case it was higher/tighter than
	 * our current ones
	 */
	if (pgdat->kcompactd_max_order <= cc.order)
		pgdat->kcompactd_max_order = 0;
	if (pgdat->kcompactd_classzone_idx >= cc.classzone_idx)
		pgdat->kcompactd_classzone_idx = pgdat->nr_zones - 1;
}

void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx)
{
	if (!order)
		return;

	if (pgdat->kcompactd_max_order < order)
		pgdat->kcompactd_max_order = order;

	if (pgdat->kcompactd_classzone_idx > classzone_idx)
		pgdat->kcompactd_classzone_idx = classzone_idx;

	if (!waitqueue_active(&pgdat->kcompactd_wait))
		return;

	if (!kcompactd_node_suitable(pgdat))
		return;

	trace_mm_compaction_wakeup_kcompactd(pgdat->node_id, order,
							classzone_idx);
	wake_up_interruptible(&pgdat->kcompactd_wait);
}

/*
 * The background compaction daemon, started as a kernel thread
 * from the init process.
 */
static int kcompactd(void *p)
{
	pg_data_t *pgdat = (pg_data_t*)p;
	struct task_struct *tsk = current;

	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);

	if (!cpumask_empty(cpumask))
		set_cpus_allowed_ptr(tsk, cpumask);

	set_freezable();

	pgdat->kcompactd_max_order = 0;
	pgdat->kcompactd_classzone_idx = pgdat->nr_zones - 1;

	while (!kthread_should_stop()) {
		trace_mm_compaction_kcompactd_sleep(pgdat->node_id);
		wait_event_freezable(pgdat->kcompactd_wait,
				kcompactd_work_requested(pgdat));

		kcompactd_do_work(pgdat);
	}

	return 0;
}

/*
 * This kcompactd start function will be called by init and node-hot-add.
 * On node-hot-add, kcompactd will moved to proper cpus if cpus are hot-added.
 */
int kcompactd_run(int nid)
{
	pg_data_t *pgdat = NODE_DATA(nid);
	int ret = 0;

	if (pgdat->kcompactd)
		return 0;

	pgdat->kcompactd = kthread_run(kcompactd, pgdat, "kcompactd%d", nid);
	if (IS_ERR(pgdat->kcompactd)) {
		pr_err("Failed to start kcompactd on node %d\n", nid);
		ret = PTR_ERR(pgdat->kcompactd);
		pgdat->kcompactd = NULL;
	}
	return ret;
}

/*
 * Called by memory hotplug when all memory in a node is offlined. Caller must
 * hold mem_hotplug_begin/end().
 */
void kcompactd_stop(int nid)
{
	struct task_struct *kcompactd = NODE_DATA(nid)->kcompactd;

	if (kcompactd) {
		kthread_stop(kcompactd);
		NODE_DATA(nid)->kcompactd = NULL;
	}
}

/*
 * It's optimal to keep kcompactd on the same CPUs as their memory, but
 * not required for correctness. So if the last cpu in a node goes
 * away, we get changed to run anywhere: as the first one comes back,
 * restore their cpu bindings.
 */
static int cpu_callback(struct notifier_block *nfb, unsigned long action,
			void *hcpu)
{
	int nid;

	if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
		for_each_node_state(nid, N_MEMORY) {
			pg_data_t *pgdat = NODE_DATA(nid);
			const struct cpumask *mask;

			mask = cpumask_of_node(pgdat->node_id);

			if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
				/* One of our CPUs online: restore mask */
				set_cpus_allowed_ptr(pgdat->kcompactd, mask);
		}
	}
	return NOTIFY_OK;
}

static int __init kcompactd_init(void)
{
	int nid;

	for_each_node_state(nid, N_MEMORY)
		kcompactd_run(nid);
	hotcpu_notifier(cpu_callback, 0);
	return 0;
}
subsys_initcall(kcompactd_init)

#endif /* CONFIG_COMPACTION */