summaryrefslogtreecommitdiff
path: root/mm/migrate.c
blob: 1a9cfcf857d24a1d3377164ae42d96a85a691a9b (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
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
// SPDX-License-Identifier: GPL-2.0
/*
 * Memory Migration functionality - linux/mm/migrate.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/backing-dev.h>
#include <linux/compaction.h>
#include <linux/syscalls.h>
#include <linux/compat.h>
#include <linux/hugetlb.h>
#include <linux/hugetlb_cgroup.h>
#include <linux/gfp.h>
#include <linux/pfn_t.h>
#include <linux/memremap.h>
#include <linux/userfaultfd_k.h>
#include <linux/balloon_compaction.h>
#include <linux/page_idle.h>
#include <linux/page_owner.h>
#include <linux/sched/mm.h>
#include <linux/ptrace.h>
#include <linux/oom.h>
#include <linux/memory.h>
#include <linux/random.h>
#include <linux/sched/sysctl.h>
#include <linux/memory-tiers.h>

#include <asm/tlbflush.h>

#include <trace/events/migrate.h>

#include "internal.h"

int isolate_movable_page(struct page *page, isolate_mode_t mode)
{
	struct folio *folio = folio_get_nontail_page(page);
	const struct movable_operations *mops;

	/*
	 * Avoid burning cycles with pages that are yet under __free_pages(),
	 * or just got freed under us.
	 *
	 * In case we 'win' a race for a movable page being freed under us and
	 * raise its refcount preventing __free_pages() from doing its job
	 * the put_page() at the end of this block will take care of
	 * release this page, thus avoiding a nasty leakage.
	 */
	if (!folio)
		goto out;

	if (unlikely(folio_test_slab(folio)))
		goto out_putfolio;
	/* Pairs with smp_wmb() in slab freeing, e.g. SLUB's __free_slab() */
	smp_rmb();
	/*
	 * Check movable flag before taking the page lock because
	 * we use non-atomic bitops on newly allocated page flags so
	 * unconditionally grabbing the lock ruins page's owner side.
	 */
	if (unlikely(!__folio_test_movable(folio)))
		goto out_putfolio;
	/* Pairs with smp_wmb() in slab allocation, e.g. SLUB's alloc_slab_page() */
	smp_rmb();
	if (unlikely(folio_test_slab(folio)))
		goto out_putfolio;

	/*
	 * As movable pages are not isolated from LRU lists, concurrent
	 * compaction threads can race against page migration functions
	 * as well as race against the releasing a page.
	 *
	 * In order to avoid having an already isolated movable page
	 * being (wrongly) re-isolated while it is under migration,
	 * or to avoid attempting to isolate pages being released,
	 * lets be sure we have the page lock
	 * before proceeding with the movable page isolation steps.
	 */
	if (unlikely(!folio_trylock(folio)))
		goto out_putfolio;

	if (!folio_test_movable(folio) || folio_test_isolated(folio))
		goto out_no_isolated;

	mops = folio_movable_ops(folio);
	VM_BUG_ON_FOLIO(!mops, folio);

	if (!mops->isolate_page(&folio->page, mode))
		goto out_no_isolated;

	/* Driver shouldn't use PG_isolated bit of page->flags */
	WARN_ON_ONCE(folio_test_isolated(folio));
	folio_set_isolated(folio);
	folio_unlock(folio);

	return 0;

out_no_isolated:
	folio_unlock(folio);
out_putfolio:
	folio_put(folio);
out:
	return -EBUSY;
}

static void putback_movable_folio(struct folio *folio)
{
	const struct movable_operations *mops = folio_movable_ops(folio);

	mops->putback_page(&folio->page);
	folio_clear_isolated(folio);
}

/*
 * 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_hugetlb().
 */
void putback_movable_pages(struct list_head *l)
{
	struct folio *folio;
	struct folio *folio2;

	list_for_each_entry_safe(folio, folio2, l, lru) {
		if (unlikely(folio_test_hugetlb(folio))) {
			folio_putback_active_hugetlb(folio);
			continue;
		}
		list_del(&folio->lru);
		/*
		 * We isolated non-lru movable folio so here we can use
		 * __PageMovable because LRU folio's mapping cannot have
		 * PAGE_MAPPING_MOVABLE.
		 */
		if (unlikely(__folio_test_movable(folio))) {
			VM_BUG_ON_FOLIO(!folio_test_isolated(folio), folio);
			folio_lock(folio);
			if (folio_test_movable(folio))
				putback_movable_folio(folio);
			else
				folio_clear_isolated(folio);
			folio_unlock(folio);
			folio_put(folio);
		} else {
			node_stat_mod_folio(folio, NR_ISOLATED_ANON +
					folio_is_file_lru(folio), -folio_nr_pages(folio));
			folio_putback_lru(folio);
		}
	}
}

/*
 * Restore a potential migration pte to a working pte entry
 */
static bool remove_migration_pte(struct folio *folio,
		struct vm_area_struct *vma, unsigned long addr, void *old)
{
	DEFINE_FOLIO_VMA_WALK(pvmw, old, vma, addr, PVMW_SYNC | PVMW_MIGRATION);

	while (page_vma_mapped_walk(&pvmw)) {
		rmap_t rmap_flags = RMAP_NONE;
		pte_t pte;
		swp_entry_t entry;
		struct page *new;
		unsigned long idx = 0;

		/* pgoff is invalid for ksm pages, but they are never large */
		if (folio_test_large(folio) && !folio_test_hugetlb(folio))
			idx = linear_page_index(vma, pvmw.address) - pvmw.pgoff;
		new = folio_page(folio, idx);

#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
		/* PMD-mapped THP migration entry */
		if (!pvmw.pte) {
			VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) ||
					!folio_test_pmd_mappable(folio), folio);
			remove_migration_pmd(&pvmw, new);
			continue;
		}
#endif

		folio_get(folio);
		pte = mk_pte(new, READ_ONCE(vma->vm_page_prot));
		if (pte_swp_soft_dirty(*pvmw.pte))
			pte = pte_mksoft_dirty(pte);

		/*
		 * Recheck VMA as permissions can change since migration started
		 */
		entry = pte_to_swp_entry(*pvmw.pte);
		if (!is_migration_entry_young(entry))
			pte = pte_mkold(pte);
		if (folio_test_dirty(folio) && is_migration_entry_dirty(entry))
			pte = pte_mkdirty(pte);
		if (is_writable_migration_entry(entry))
			pte = maybe_mkwrite(pte, vma);
		else if (pte_swp_uffd_wp(*pvmw.pte))
			pte = pte_mkuffd_wp(pte);

		if (folio_test_anon(folio) && !is_readable_migration_entry(entry))
			rmap_flags |= RMAP_EXCLUSIVE;

		if (unlikely(is_device_private_page(new))) {
			if (pte_write(pte))
				entry = make_writable_device_private_entry(
							page_to_pfn(new));
			else
				entry = make_readable_device_private_entry(
							page_to_pfn(new));
			pte = swp_entry_to_pte(entry);
			if (pte_swp_soft_dirty(*pvmw.pte))
				pte = pte_swp_mksoft_dirty(pte);
			if (pte_swp_uffd_wp(*pvmw.pte))
				pte = pte_swp_mkuffd_wp(pte);
		}

#ifdef CONFIG_HUGETLB_PAGE
		if (folio_test_hugetlb(folio)) {
			unsigned int shift = huge_page_shift(hstate_vma(vma));

			pte = pte_mkhuge(pte);
			pte = arch_make_huge_pte(pte, shift, vma->vm_flags);
			if (folio_test_anon(folio))
				hugepage_add_anon_rmap(new, vma, pvmw.address,
						       rmap_flags);
			else
				page_dup_file_rmap(new, true);
			set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte);
		} else
#endif
		{
			if (folio_test_anon(folio))
				page_add_anon_rmap(new, vma, pvmw.address,
						   rmap_flags);
			else
				page_add_file_rmap(new, vma, false);
			set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte);
		}
		if (vma->vm_flags & VM_LOCKED)
			mlock_drain_local();

		trace_remove_migration_pte(pvmw.address, pte_val(pte),
					   compound_order(new));

		/* No need to invalidate - it was non-present before */
		update_mmu_cache(vma, pvmw.address, pvmw.pte);
	}

	return true;
}

/*
 * Get rid of all migration entries and replace them by
 * references to the indicated page.
 */
void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked)
{
	struct rmap_walk_control rwc = {
		.rmap_one = remove_migration_pte,
		.arg = src,
	};

	if (locked)
		rmap_walk_locked(dst, &rwc);
	else
		rmap_walk(dst, &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;

	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;

	migration_entry_wait_on_locked(entry, ptep, ptl);
	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);
}

#ifdef CONFIG_HUGETLB_PAGE
/*
 * The vma read lock must be held upon entry. Holding that lock prevents either
 * the pte or the ptl from being freed.
 *
 * This function will release the vma lock before returning.
 */
void __migration_entry_wait_huge(struct vm_area_struct *vma,
				 pte_t *ptep, spinlock_t *ptl)
{
	pte_t pte;

	hugetlb_vma_assert_locked(vma);
	spin_lock(ptl);
	pte = huge_ptep_get(ptep);

	if (unlikely(!is_hugetlb_entry_migration(pte))) {
		spin_unlock(ptl);
		hugetlb_vma_unlock_read(vma);
	} else {
		/*
		 * If migration entry existed, safe to release vma lock
		 * here because the pgtable page won't be freed without the
		 * pgtable lock released.  See comment right above pgtable
		 * lock release in migration_entry_wait_on_locked().
		 */
		hugetlb_vma_unlock_read(vma);
		migration_entry_wait_on_locked(pte_to_swp_entry(pte), NULL, ptl);
	}
}

void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte)
{
	spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), vma->vm_mm, pte);

	__migration_entry_wait_huge(vma, pte, ptl);
}
#endif

#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd)
{
	spinlock_t *ptl;

	ptl = pmd_lock(mm, pmd);
	if (!is_pmd_migration_entry(*pmd))
		goto unlock;
	migration_entry_wait_on_locked(pmd_to_swp_entry(*pmd), NULL, ptl);
	return;
unlock:
	spin_unlock(ptl);
}
#endif

static int folio_expected_refs(struct address_space *mapping,
		struct folio *folio)
{
	int refs = 1;
	if (!mapping)
		return refs;

	refs += folio_nr_pages(folio);
	if (folio_test_private(folio))
		refs++;

	return refs;
}

/*
 * 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 folio_migrate_mapping(struct address_space *mapping,
		struct folio *newfolio, struct folio *folio, int extra_count)
{
	XA_STATE(xas, &mapping->i_pages, folio_index(folio));
	struct zone *oldzone, *newzone;
	int dirty;
	int expected_count = folio_expected_refs(mapping, folio) + extra_count;
	long nr = folio_nr_pages(folio);

	if (!mapping) {
		/* Anonymous page without mapping */
		if (folio_ref_count(folio) != expected_count)
			return -EAGAIN;

		/* No turning back from here */
		newfolio->index = folio->index;
		newfolio->mapping = folio->mapping;
		if (folio_test_swapbacked(folio))
			__folio_set_swapbacked(newfolio);

		return MIGRATEPAGE_SUCCESS;
	}

	oldzone = folio_zone(folio);
	newzone = folio_zone(newfolio);

	xas_lock_irq(&xas);
	if (!folio_ref_freeze(folio, expected_count)) {
		xas_unlock_irq(&xas);
		return -EAGAIN;
	}

	/*
	 * Now we know that no one else is looking at the folio:
	 * no turning back from here.
	 */
	newfolio->index = folio->index;
	newfolio->mapping = folio->mapping;
	folio_ref_add(newfolio, nr); /* add cache reference */
	if (folio_test_swapbacked(folio)) {
		__folio_set_swapbacked(newfolio);
		if (folio_test_swapcache(folio)) {
			folio_set_swapcache(newfolio);
			newfolio->private = folio_get_private(folio);
		}
	} else {
		VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio);
	}

	/* Move dirty while page refs frozen and newpage not yet exposed */
	dirty = folio_test_dirty(folio);
	if (dirty) {
		folio_clear_dirty(folio);
		folio_set_dirty(newfolio);
	}

	xas_store(&xas, newfolio);

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

	xas_unlock(&xas);
	/* Leave irq disabled to prevent preemption while updating stats */

	/*
	 * 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_MAPPED if they
	 * are mapped to swap space.
	 */
	if (newzone != oldzone) {
		struct lruvec *old_lruvec, *new_lruvec;
		struct mem_cgroup *memcg;

		memcg = folio_memcg(folio);
		old_lruvec = mem_cgroup_lruvec(memcg, oldzone->zone_pgdat);
		new_lruvec = mem_cgroup_lruvec(memcg, newzone->zone_pgdat);

		__mod_lruvec_state(old_lruvec, NR_FILE_PAGES, -nr);
		__mod_lruvec_state(new_lruvec, NR_FILE_PAGES, nr);
		if (folio_test_swapbacked(folio) && !folio_test_swapcache(folio)) {
			__mod_lruvec_state(old_lruvec, NR_SHMEM, -nr);
			__mod_lruvec_state(new_lruvec, NR_SHMEM, nr);
		}
#ifdef CONFIG_SWAP
		if (folio_test_swapcache(folio)) {
			__mod_lruvec_state(old_lruvec, NR_SWAPCACHE, -nr);
			__mod_lruvec_state(new_lruvec, NR_SWAPCACHE, nr);
		}
#endif
		if (dirty && mapping_can_writeback(mapping)) {
			__mod_lruvec_state(old_lruvec, NR_FILE_DIRTY, -nr);
			__mod_zone_page_state(oldzone, NR_ZONE_WRITE_PENDING, -nr);
			__mod_lruvec_state(new_lruvec, NR_FILE_DIRTY, nr);
			__mod_zone_page_state(newzone, NR_ZONE_WRITE_PENDING, nr);
		}
	}
	local_irq_enable();

	return MIGRATEPAGE_SUCCESS;
}
EXPORT_SYMBOL(folio_migrate_mapping);

/*
 * The expected number of remaining references is the same as that
 * of folio_migrate_mapping().
 */
int migrate_huge_page_move_mapping(struct address_space *mapping,
				   struct folio *dst, struct folio *src)
{
	XA_STATE(xas, &mapping->i_pages, folio_index(src));
	int expected_count;

	xas_lock_irq(&xas);
	expected_count = 2 + folio_has_private(src);
	if (!folio_ref_freeze(src, expected_count)) {
		xas_unlock_irq(&xas);
		return -EAGAIN;
	}

	dst->index = src->index;
	dst->mapping = src->mapping;

	folio_get(dst);

	xas_store(&xas, dst);

	folio_ref_unfreeze(src, expected_count - 1);

	xas_unlock_irq(&xas);

	return MIGRATEPAGE_SUCCESS;
}

/*
 * Copy the flags and some other ancillary information
 */
void folio_migrate_flags(struct folio *newfolio, struct folio *folio)
{
	int cpupid;

	if (folio_test_error(folio))
		folio_set_error(newfolio);
	if (folio_test_referenced(folio))
		folio_set_referenced(newfolio);
	if (folio_test_uptodate(folio))
		folio_mark_uptodate(newfolio);
	if (folio_test_clear_active(folio)) {
		VM_BUG_ON_FOLIO(folio_test_unevictable(folio), folio);
		folio_set_active(newfolio);
	} else if (folio_test_clear_unevictable(folio))
		folio_set_unevictable(newfolio);
	if (folio_test_workingset(folio))
		folio_set_workingset(newfolio);
	if (folio_test_checked(folio))
		folio_set_checked(newfolio);
	/*
	 * PG_anon_exclusive (-> PG_mappedtodisk) is always migrated via
	 * migration entries. We can still have PG_anon_exclusive set on an
	 * effectively unmapped and unreferenced first sub-pages of an
	 * anonymous THP: we can simply copy it here via PG_mappedtodisk.
	 */
	if (folio_test_mappedtodisk(folio))
		folio_set_mappedtodisk(newfolio);

	/* Move dirty on pages not done by folio_migrate_mapping() */
	if (folio_test_dirty(folio))
		folio_set_dirty(newfolio);

	if (folio_test_young(folio))
		folio_set_young(newfolio);
	if (folio_test_idle(folio))
		folio_set_idle(newfolio);

	/*
	 * Copy NUMA information to the new page, to prevent over-eager
	 * future migrations of this same page.
	 */
	cpupid = page_cpupid_xchg_last(&folio->page, -1);
	/*
	 * For memory tiering mode, when migrate between slow and fast
	 * memory node, reset cpupid, because that is used to record
	 * page access time in slow memory node.
	 */
	if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) {
		bool f_toptier = node_is_toptier(page_to_nid(&folio->page));
		bool t_toptier = node_is_toptier(page_to_nid(&newfolio->page));

		if (f_toptier != t_toptier)
			cpupid = -1;
	}
	page_cpupid_xchg_last(&newfolio->page, cpupid);

	folio_migrate_ksm(newfolio, folio);
	/*
	 * Please do not reorder this without considering how mm/ksm.c's
	 * get_ksm_page() depends upon ksm_migrate_page() and PageSwapCache().
	 */
	if (folio_test_swapcache(folio))
		folio_clear_swapcache(folio);
	folio_clear_private(folio);

	/* page->private contains hugetlb specific flags */
	if (!folio_test_hugetlb(folio))
		folio->private = NULL;

	/*
	 * If any waiters have accumulated on the new page then
	 * wake them up.
	 */
	if (folio_test_writeback(newfolio))
		folio_end_writeback(newfolio);

	/*
	 * PG_readahead shares the same bit with PG_reclaim.  The above
	 * end_page_writeback() may clear PG_readahead mistakenly, so set the
	 * bit after that.
	 */
	if (folio_test_readahead(folio))
		folio_set_readahead(newfolio);

	folio_copy_owner(newfolio, folio);

	if (!folio_test_hugetlb(folio))
		mem_cgroup_migrate(folio, newfolio);
}
EXPORT_SYMBOL(folio_migrate_flags);

void folio_migrate_copy(struct folio *newfolio, struct folio *folio)
{
	folio_copy(newfolio, folio);
	folio_migrate_flags(newfolio, folio);
}
EXPORT_SYMBOL(folio_migrate_copy);

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

int migrate_folio_extra(struct address_space *mapping, struct folio *dst,
		struct folio *src, enum migrate_mode mode, int extra_count)
{
	int rc;

	BUG_ON(folio_test_writeback(src));	/* Writeback must be complete */

	rc = folio_migrate_mapping(mapping, dst, src, extra_count);

	if (rc != MIGRATEPAGE_SUCCESS)
		return rc;

	if (mode != MIGRATE_SYNC_NO_COPY)
		folio_migrate_copy(dst, src);
	else
		folio_migrate_flags(dst, src);
	return MIGRATEPAGE_SUCCESS;
}

/**
 * migrate_folio() - Simple folio migration.
 * @mapping: The address_space containing the folio.
 * @dst: The folio to migrate the data to.
 * @src: The folio containing the current data.
 * @mode: How to migrate the page.
 *
 * Common logic to directly migrate a single LRU folio suitable for
 * folios that do not use PagePrivate/PagePrivate2.
 *
 * Folios are locked upon entry and exit.
 */
int migrate_folio(struct address_space *mapping, struct folio *dst,
		struct folio *src, enum migrate_mode mode)
{
	return migrate_folio_extra(mapping, dst, src, mode, 0);
}
EXPORT_SYMBOL(migrate_folio);

#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 {
			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 {
		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;
			bh = head;
			while (bh != failed_bh) {
				unlock_buffer(bh);
				bh = bh->b_this_page;
			}
			return false;
		}

		bh = bh->b_this_page;
	} while (bh != head);
	return true;
}

static int __buffer_migrate_folio(struct address_space *mapping,
		struct folio *dst, struct folio *src, enum migrate_mode mode,
		bool check_refs)
{
	struct buffer_head *bh, *head;
	int rc;
	int expected_count;

	head = folio_buffers(src);
	if (!head)
		return migrate_folio(mapping, dst, src, mode);

	/* Check whether page does not have extra refs before we do more work */
	expected_count = folio_expected_refs(mapping, src);
	if (folio_ref_count(src) != expected_count)
		return -EAGAIN;

	if (!buffer_migrate_lock_buffers(head, mode))
		return -EAGAIN;

	if (check_refs) {
		bool busy;
		bool invalidated = false;

recheck_buffers:
		busy = false;
		spin_lock(&mapping->private_lock);
		bh = head;
		do {
			if (atomic_read(&bh->b_count)) {
				busy = true;
				break;
			}
			bh = bh->b_this_page;
		} while (bh != head);
		if (busy) {
			if (invalidated) {
				rc = -EAGAIN;
				goto unlock_buffers;
			}
			spin_unlock(&mapping->private_lock);
			invalidate_bh_lrus();
			invalidated = true;
			goto recheck_buffers;
		}
	}

	rc = folio_migrate_mapping(mapping, dst, src, 0);
	if (rc != MIGRATEPAGE_SUCCESS)
		goto unlock_buffers;

	folio_attach_private(dst, folio_detach_private(src));

	bh = head;
	do {
		set_bh_page(bh, &dst->page, bh_offset(bh));
		bh = bh->b_this_page;
	} while (bh != head);

	if (mode != MIGRATE_SYNC_NO_COPY)
		folio_migrate_copy(dst, src);
	else
		folio_migrate_flags(dst, src);

	rc = MIGRATEPAGE_SUCCESS;
unlock_buffers:
	if (check_refs)
		spin_unlock(&mapping->private_lock);
	bh = head;
	do {
		unlock_buffer(bh);
		bh = bh->b_this_page;
	} while (bh != head);

	return rc;
}

/**
 * buffer_migrate_folio() - Migration function for folios with buffers.
 * @mapping: The address space containing @src.
 * @dst: The folio to migrate to.
 * @src: The folio to migrate from.
 * @mode: How to migrate the folio.
 *
 * This function can only be used if the underlying filesystem guarantees
 * that no other references to @src exist. For example attached buffer
 * heads are accessed only under the folio lock.  If your filesystem cannot
 * provide this guarantee, buffer_migrate_folio_norefs() may be more
 * appropriate.
 *
 * Return: 0 on success or a negative errno on failure.
 */
int buffer_migrate_folio(struct address_space *mapping,
		struct folio *dst, struct folio *src, enum migrate_mode mode)
{
	return __buffer_migrate_folio(mapping, dst, src, mode, false);
}
EXPORT_SYMBOL(buffer_migrate_folio);

/**
 * buffer_migrate_folio_norefs() - Migration function for folios with buffers.
 * @mapping: The address space containing @src.
 * @dst: The folio to migrate to.
 * @src: The folio to migrate from.
 * @mode: How to migrate the folio.
 *
 * Like buffer_migrate_folio() except that this variant is more careful
 * and checks that there are also no buffer head references. This function
 * is the right one for mappings where buffer heads are directly looked
 * up and referenced (such as block device mappings).
 *
 * Return: 0 on success or a negative errno on failure.
 */
int buffer_migrate_folio_norefs(struct address_space *mapping,
		struct folio *dst, struct folio *src, enum migrate_mode mode)
{
	return __buffer_migrate_folio(mapping, dst, src, mode, true);
}
EXPORT_SYMBOL_GPL(buffer_migrate_folio_norefs);
#endif

int filemap_migrate_folio(struct address_space *mapping,
		struct folio *dst, struct folio *src, enum migrate_mode mode)
{
	int ret;

	ret = folio_migrate_mapping(mapping, dst, src, 0);
	if (ret != MIGRATEPAGE_SUCCESS)
		return ret;

	if (folio_get_private(src))
		folio_attach_private(dst, folio_detach_private(src));

	if (mode != MIGRATE_SYNC_NO_COPY)
		folio_migrate_copy(dst, src);
	else
		folio_migrate_flags(dst, src);
	return MIGRATEPAGE_SUCCESS;
}
EXPORT_SYMBOL_GPL(filemap_migrate_folio);

/*
 * Writeback a folio to clean the dirty state
 */
static int writeout(struct address_space *mapping, struct folio *folio)
{
	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 (!folio_clear_dirty_for_io(folio))
		/* Someone else already triggered a write */
		return -EAGAIN;

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

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

	if (rc != AOP_WRITEPAGE_ACTIVATE)
		/* unlocked. Relock */
		folio_lock(folio);

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

/*
 * Default handling if a filesystem does not provide a migration function.
 */
static int fallback_migrate_folio(struct address_space *mapping,
		struct folio *dst, struct folio *src, enum migrate_mode mode)
{
	if (folio_test_dirty(src)) {
		/* Only writeback folios in full synchronous migration */
		switch (mode) {
		case MIGRATE_SYNC:
		case MIGRATE_SYNC_NO_COPY:
			break;
		default:
			return -EBUSY;
		}
		return writeout(mapping, src);
	}

	/*
	 * Buffers may be managed in a filesystem specific way.
	 * We must have no buffers or drop them.
	 */
	if (folio_test_private(src) &&
	    !filemap_release_folio(src, GFP_KERNEL))
		return mode == MIGRATE_SYNC ? -EAGAIN : -EBUSY;

	return migrate_folio(mapping, dst, src, 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_folio(struct folio *dst, struct folio *src,
				enum migrate_mode mode)
{
	int rc = -EAGAIN;
	bool is_lru = !__PageMovable(&src->page);

	VM_BUG_ON_FOLIO(!folio_test_locked(src), src);
	VM_BUG_ON_FOLIO(!folio_test_locked(dst), dst);

	if (likely(is_lru)) {
		struct address_space *mapping = folio_mapping(src);

		if (!mapping)
			rc = migrate_folio(mapping, dst, src, mode);
		else if (mapping->a_ops->migrate_folio)
			/*
			 * Most folios have a mapping and most filesystems
			 * provide a migrate_folio callback. Anonymous folios
			 * are part of swap space which also has its own
			 * migrate_folio callback. This is the most common path
			 * for page migration.
			 */
			rc = mapping->a_ops->migrate_folio(mapping, dst, src,
								mode);
		else
			rc = fallback_migrate_folio(mapping, dst, src, mode);
	} else {
		const struct movable_operations *mops;

		/*
		 * In case of non-lru page, it could be released after
		 * isolation step. In that case, we shouldn't try migration.
		 */
		VM_BUG_ON_FOLIO(!folio_test_isolated(src), src);
		if (!folio_test_movable(src)) {
			rc = MIGRATEPAGE_SUCCESS;
			folio_clear_isolated(src);
			goto out;
		}

		mops = folio_movable_ops(src);
		rc = mops->migrate_page(&dst->page, &src->page, mode);
		WARN_ON_ONCE(rc == MIGRATEPAGE_SUCCESS &&
				!folio_test_isolated(src));
	}

	/*
	 * When successful, old pagecache src->mapping must be cleared before
	 * src is freed; but stats require that PageAnon be left as PageAnon.
	 */
	if (rc == MIGRATEPAGE_SUCCESS) {
		if (__PageMovable(&src->page)) {
			VM_BUG_ON_FOLIO(!folio_test_isolated(src), src);

			/*
			 * We clear PG_movable under page_lock so any compactor
			 * cannot try to migrate this page.
			 */
			folio_clear_isolated(src);
		}

		/*
		 * Anonymous and movable src->mapping will be cleared by
		 * free_pages_prepare so don't reset it here for keeping
		 * the type to work PageAnon, for example.
		 */
		if (!folio_mapping_flags(src))
			src->mapping = NULL;

		if (likely(!folio_is_zone_device(dst)))
			flush_dcache_folio(dst);
	}
out:
	return rc;
}

static int __unmap_and_move(struct folio *src, struct folio *dst,
				int force, enum migrate_mode mode)
{
	int rc = -EAGAIN;
	bool page_was_mapped = false;
	struct anon_vma *anon_vma = NULL;
	bool is_lru = !__PageMovable(&src->page);

	if (!folio_trylock(src)) {
		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_readahead). 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;

		folio_lock(src);
	}

	if (folio_test_writeback(src)) {
		/*
		 * 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
		 */
		switch (mode) {
		case MIGRATE_SYNC:
		case MIGRATE_SYNC_NO_COPY:
			break;
		default:
			rc = -EBUSY;
			goto out_unlock;
		}
		if (!force)
			goto out_unlock;
		folio_wait_writeback(src);
	}

	/*
	 * By try_to_migrate(), src->mapcount goes down to 0 here. In this case,
	 * we cannot notice that anon_vma is freed while we migrate 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.
	 *
	 * Only folio_get_anon_vma() understands the subtleties of
	 * getting a hold on an anon_vma from outside one of its mms.
	 * But if we cannot get anon_vma, then we won't need it anyway,
	 * because that implies that the anon page is no longer mapped
	 * (and cannot be remapped so long as we hold the page lock).
	 */
	if (folio_test_anon(src) && !folio_test_ksm(src))
		anon_vma = folio_get_anon_vma(src);

	/*
	 * Block others from accessing the new page when we get around to
	 * establishing additional references. We are usually the only one
	 * holding a reference to dst at this point. We used to have a BUG
	 * here if folio_trylock(dst) fails, but would like to allow for
	 * cases where there might be a race with the previous use of dst.
	 * This is much like races on refcount of oldpage: just don't BUG().
	 */
	if (unlikely(!folio_trylock(dst)))
		goto out_unlock;

	if (unlikely(!is_lru)) {
		rc = move_to_new_folio(dst, src, mode);
		goto out_unlock_both;
	}

	/*
	 * 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 src->mapping==NULL page will
	 * trigger a BUG.  So handle it here.
	 * 2. An orphaned page (see truncate_cleanup_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 (!src->mapping) {
		if (folio_test_private(src)) {
			try_to_free_buffers(src);
			goto out_unlock_both;
		}
	} else if (folio_mapped(src)) {
		/* Establish migration ptes */
		VM_BUG_ON_FOLIO(folio_test_anon(src) &&
			       !folio_test_ksm(src) && !anon_vma, src);
		try_to_migrate(src, 0);
		page_was_mapped = true;
	}

	if (!folio_mapped(src))
		rc = move_to_new_folio(dst, src, mode);

	/*
	 * When successful, push dst to LRU immediately: so that if it
	 * turns out to be an mlocked page, remove_migration_ptes() will
	 * automatically build up the correct dst->mlock_count for it.
	 *
	 * We would like to do something similar for the old page, when
	 * unsuccessful, and other cases when a page has been temporarily
	 * isolated from the unevictable LRU: but this case is the easiest.
	 */
	if (rc == MIGRATEPAGE_SUCCESS) {
		folio_add_lru(dst);
		if (page_was_mapped)
			lru_add_drain();
	}

	if (page_was_mapped)
		remove_migration_ptes(src,
			rc == MIGRATEPAGE_SUCCESS ? dst : src, false);

out_unlock_both:
	folio_unlock(dst);
out_unlock:
	/* Drop an anon_vma reference if we took one */
	if (anon_vma)
		put_anon_vma(anon_vma);
	folio_unlock(src);
out:
	/*
	 * If migration is successful, decrease refcount of dst,
	 * which will not free the page because new page owner increased
	 * refcounter.
	 */
	if (rc == MIGRATEPAGE_SUCCESS)
		folio_put(dst);

	return rc;
}

/*
 * Obtain the lock on folio, remove all ptes and migrate the folio
 * to the newly allocated folio in dst.
 */
static int unmap_and_move(new_page_t get_new_page,
				   free_page_t put_new_page,
				   unsigned long private, struct folio *src,
				   int force, enum migrate_mode mode,
				   enum migrate_reason reason,
				   struct list_head *ret)
{
	struct folio *dst;
	int rc = MIGRATEPAGE_SUCCESS;
	struct page *newpage = NULL;

	if (!thp_migration_supported() && folio_test_transhuge(src))
		return -ENOSYS;

	if (folio_ref_count(src) == 1) {
		/* Folio was freed from under us. So we are done. */
		folio_clear_active(src);
		folio_clear_unevictable(src);
		/* free_pages_prepare() will clear PG_isolated. */
		goto out;
	}

	newpage = get_new_page(&src->page, private);
	if (!newpage)
		return -ENOMEM;
	dst = page_folio(newpage);

	dst->private = NULL;
	rc = __unmap_and_move(src, dst, force, mode);
	if (rc == MIGRATEPAGE_SUCCESS)
		set_page_owner_migrate_reason(&dst->page, reason);

out:
	if (rc != -EAGAIN) {
		/*
		 * A folio that has been migrated has all references
		 * removed and will be freed. A folio that has not been
		 * migrated will have kept its references and be restored.
		 */
		list_del(&src->lru);
	}

	/*
	 * If migration is successful, releases reference grabbed during
	 * isolation. Otherwise, restore the folio to right list unless
	 * we want to retry.
	 */
	if (rc == MIGRATEPAGE_SUCCESS) {
		/*
		 * Compaction can migrate also non-LRU folios which are
		 * not accounted to NR_ISOLATED_*. They can be recognized
		 * as __folio_test_movable
		 */
		if (likely(!__folio_test_movable(src)))
			mod_node_page_state(folio_pgdat(src), NR_ISOLATED_ANON +
					folio_is_file_lru(src), -folio_nr_pages(src));

		if (reason != MR_MEMORY_FAILURE)
			/*
			 * We release the folio in page_handle_poison.
			 */
			folio_put(src);
	} else {
		if (rc != -EAGAIN)
			list_add_tail(&src->lru, ret);

		if (put_new_page)
			put_new_page(&dst->page, private);
		else
			folio_put(dst);
	}

	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 reason,
				struct list_head *ret)
{
	struct folio *dst, *src = page_folio(hpage);
	int rc = -EAGAIN;
	int page_was_mapped = 0;
	struct page *new_hpage;
	struct anon_vma *anon_vma = NULL;
	struct address_space *mapping = NULL;

	/*
	 * Migratability of hugepages depends on architectures and their 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)))
		return -ENOSYS;

	if (folio_ref_count(src) == 1) {
		/* page was freed from under us. So we are done. */
		folio_putback_active_hugetlb(src);
		return MIGRATEPAGE_SUCCESS;
	}

	new_hpage = get_new_page(hpage, private);
	if (!new_hpage)
		return -ENOMEM;
	dst = page_folio(new_hpage);

	if (!folio_trylock(src)) {
		if (!force)
			goto out;
		switch (mode) {
		case MIGRATE_SYNC:
		case MIGRATE_SYNC_NO_COPY:
			break;
		default:
			goto out;
		}
		folio_lock(src);
	}

	/*
	 * Check for pages which are in the process of being freed.  Without
	 * folio_mapping() set, hugetlbfs specific move page routine will not
	 * be called and we could leak usage counts for subpools.
	 */
	if (hugetlb_folio_subpool(src) && !folio_mapping(src)) {
		rc = -EBUSY;
		goto out_unlock;
	}

	if (folio_test_anon(src))
		anon_vma = folio_get_anon_vma(src);

	if (unlikely(!folio_trylock(dst)))
		goto put_anon;

	if (folio_mapped(src)) {
		enum ttu_flags ttu = 0;

		if (!folio_test_anon(src)) {
			/*
			 * In shared mappings, try_to_unmap could potentially
			 * call huge_pmd_unshare.  Because of this, take
			 * semaphore in write mode here and set TTU_RMAP_LOCKED
			 * to let lower levels know we have taken the lock.
			 */
			mapping = hugetlb_page_mapping_lock_write(hpage);
			if (unlikely(!mapping))
				goto unlock_put_anon;

			ttu = TTU_RMAP_LOCKED;
		}

		try_to_migrate(src, ttu);
		page_was_mapped = 1;

		if (ttu & TTU_RMAP_LOCKED)
			i_mmap_unlock_write(mapping);
	}

	if (!folio_mapped(src))
		rc = move_to_new_folio(dst, src, mode);

	if (page_was_mapped)
		remove_migration_ptes(src,
			rc == MIGRATEPAGE_SUCCESS ? dst : src, false);

unlock_put_anon:
	folio_unlock(dst);

put_anon:
	if (anon_vma)
		put_anon_vma(anon_vma);

	if (rc == MIGRATEPAGE_SUCCESS) {
		move_hugetlb_state(src, dst, reason);
		put_new_page = NULL;
	}

out_unlock:
	folio_unlock(src);
out:
	if (rc == MIGRATEPAGE_SUCCESS)
		folio_putback_active_hugetlb(src);
	else if (rc != -EAGAIN)
		list_move_tail(&src->lru, ret);

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

	return rc;
}

static inline int try_split_folio(struct folio *folio, struct list_head *split_folios)
{
	int rc;

	folio_lock(folio);
	rc = split_folio_to_list(folio, split_folios);
	folio_unlock(folio);
	if (!rc)
		list_move_tail(&folio->lru, split_folios);

	return rc;
}

struct migrate_pages_stats {
	int nr_succeeded;	/* Normal and large folios migrated successfully, in
				   units of base pages */
	int nr_failed_pages;	/* Normal and large folios failed to be migrated, in
				   units of base pages.  Untried folios aren't counted */
	int nr_thp_succeeded;	/* THP migrated successfully */
	int nr_thp_failed;	/* THP failed to be migrated */
	int nr_thp_split;	/* THP split before migrating */
};

/*
 * migrate_pages - migrate the folios specified in a list, to the free folios
 *		   supplied as the target for the page migration
 *
 * @from:		The list of folios to be migrated.
 * @get_new_page:	The function used to allocate free folios to be used
 *			as the target of the folio migration.
 * @put_new_page:	The function used to free target folios 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
 *			folio migration, if any.
 * @reason:		The reason for folio migration.
 * @ret_succeeded:	Set to the number of folios migrated successfully if
 *			the caller passes a non-NULL pointer.
 *
 * The function returns after 10 attempts or if no folios are movable any more
 * because the list has become empty or no retryable folios exist any more.
 * It is caller's responsibility to call putback_movable_pages() to return folios
 * to the LRU or free list only if ret != 0.
 *
 * Returns the number of {normal folio, large folio, hugetlb} that were not
 * migrated, or an error code. The number of large folio splits will be
 * considered as the number of non-migrated large folio, no matter how many
 * split folios of the large folio are migrated successfully.
 */
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, unsigned int *ret_succeeded)
{
	int retry = 1;
	int large_retry = 1;
	int thp_retry = 1;
	int nr_failed = 0;
	int nr_retry_pages = 0;
	int nr_large_failed = 0;
	int pass = 0;
	bool is_large = false;
	bool is_thp = false;
	struct folio *folio, *folio2;
	int rc, nr_pages;
	LIST_HEAD(ret_folios);
	LIST_HEAD(split_folios);
	bool nosplit = (reason == MR_NUMA_MISPLACED);
	bool no_split_folio_counting = false;
	struct migrate_pages_stats stats;

	trace_mm_migrate_pages_start(mode, reason);

	memset(&stats, 0, sizeof(stats));
split_folio_migration:
	for (pass = 0; pass < 10 && (retry || large_retry); pass++) {
		retry = 0;
		large_retry = 0;
		thp_retry = 0;
		nr_retry_pages = 0;

		list_for_each_entry_safe(folio, folio2, from, lru) {
			/*
			 * Large folio statistics is based on the source large
			 * folio. Capture required information that might get
			 * lost during migration.
			 */
			is_large = folio_test_large(folio) && !folio_test_hugetlb(folio);
			is_thp = is_large && folio_test_pmd_mappable(folio);
			nr_pages = folio_nr_pages(folio);
			cond_resched();

			if (folio_test_hugetlb(folio))
				rc = unmap_and_move_huge_page(get_new_page,
						put_new_page, private,
						&folio->page, pass > 2, mode,
						reason,
						&ret_folios);
			else
				rc = unmap_and_move(get_new_page, put_new_page,
						private, folio, pass > 2, mode,
						reason, &ret_folios);
			/*
			 * The rules are:
			 *	Success: non hugetlb folio will be freed, hugetlb
			 *		 folio will be put back
			 *	-EAGAIN: stay on the from list
			 *	-ENOMEM: stay on the from list
			 *	-ENOSYS: stay on the from list
			 *	Other errno: put on ret_folios list then splice to
			 *		     from list
			 */
			switch(rc) {
			/*
			 * Large folio migration might be unsupported or
			 * the allocation could've failed so we should retry
			 * on the same folio with the large folio split
			 * to normal folios.
			 *
			 * Split folios are put in split_folios, and
			 * we will migrate them after the rest of the
			 * list is processed.
			 */
			case -ENOSYS:
				/* Large folio migration is unsupported */
				if (is_large) {
					nr_large_failed++;
					stats.nr_thp_failed += is_thp;
					if (!try_split_folio(folio, &split_folios)) {
						stats.nr_thp_split += is_thp;
						break;
					}
				/* Hugetlb migration is unsupported */
				} else if (!no_split_folio_counting) {
					nr_failed++;
				}

				stats.nr_failed_pages += nr_pages;
				list_move_tail(&folio->lru, &ret_folios);
				break;
			case -ENOMEM:
				/*
				 * When memory is low, don't bother to try to migrate
				 * other folios, just exit.
				 */
				if (is_large) {
					nr_large_failed++;
					stats.nr_thp_failed += is_thp;
					/* Large folio NUMA faulting doesn't split to retry. */
					if (!nosplit) {
						int ret = try_split_folio(folio, &split_folios);

						if (!ret) {
							stats.nr_thp_split += is_thp;
							break;
						} else if (reason == MR_LONGTERM_PIN &&
							   ret == -EAGAIN) {
							/*
							 * Try again to split large folio to
							 * mitigate the failure of longterm pinning.
							 */
							large_retry++;
							thp_retry += is_thp;
							nr_retry_pages += nr_pages;
							break;
						}
					}
				} else if (!no_split_folio_counting) {
					nr_failed++;
				}

				stats.nr_failed_pages += nr_pages + nr_retry_pages;
				/*
				 * There might be some split folios of fail-to-migrate large
				 * folios left in split_folios list. Move them back to migration
				 * list so that they could be put back to the right list by
				 * the caller otherwise the folio refcnt will be leaked.
				 */
				list_splice_init(&split_folios, from);
				/* nr_failed isn't updated for not used */
				nr_large_failed += large_retry;
				stats.nr_thp_failed += thp_retry;
				goto out;
			case -EAGAIN:
				if (is_large) {
					large_retry++;
					thp_retry += is_thp;
				} else if (!no_split_folio_counting) {
					retry++;
				}
				nr_retry_pages += nr_pages;
				break;
			case MIGRATEPAGE_SUCCESS:
				stats.nr_succeeded += nr_pages;
				stats.nr_thp_succeeded += is_thp;
				break;
			default:
				/*
				 * Permanent failure (-EBUSY, etc.):
				 * unlike -EAGAIN case, the failed folio is
				 * removed from migration folio list and not
				 * retried in the next outer loop.
				 */
				if (is_large) {
					nr_large_failed++;
					stats.nr_thp_failed += is_thp;
				} else if (!no_split_folio_counting) {
					nr_failed++;
				}

				stats.nr_failed_pages += nr_pages;
				break;
			}
		}
	}
	nr_failed += retry;
	nr_large_failed += large_retry;
	stats.nr_thp_failed += thp_retry;
	stats.nr_failed_pages += nr_retry_pages;
	/*
	 * Try to migrate split folios of fail-to-migrate large folios, no
	 * nr_failed counting in this round, since all split folios of a
	 * large folio is counted as 1 failure in the first round.
	 */
	if (!list_empty(&split_folios)) {
		/*
		 * Move non-migrated folios (after 10 retries) to ret_folios
		 * to avoid migrating them again.
		 */
		list_splice_init(from, &ret_folios);
		list_splice_init(&split_folios, from);
		no_split_folio_counting = true;
		retry = 1;
		goto split_folio_migration;
	}

	rc = nr_failed + nr_large_failed;
out:
	/*
	 * Put the permanent failure folio back to migration list, they
	 * will be put back to the right list by the caller.
	 */
	list_splice(&ret_folios, from);

	/*
	 * Return 0 in case all split folios of fail-to-migrate large folios
	 * are migrated successfully.
	 */
	if (list_empty(from))
		rc = 0;

	count_vm_events(PGMIGRATE_SUCCESS, stats.nr_succeeded);
	count_vm_events(PGMIGRATE_FAIL, stats.nr_failed_pages);
	count_vm_events(THP_MIGRATION_SUCCESS, stats.nr_thp_succeeded);
	count_vm_events(THP_MIGRATION_FAIL, stats.nr_thp_failed);
	count_vm_events(THP_MIGRATION_SPLIT, stats.nr_thp_split);
	trace_mm_migrate_pages(stats.nr_succeeded, stats.nr_failed_pages,
			       stats.nr_thp_succeeded, stats.nr_thp_failed,
			       stats.nr_thp_split, mode, reason);

	if (ret_succeeded)
		*ret_succeeded = stats.nr_succeeded;

	return rc;
}

struct page *alloc_migration_target(struct page *page, unsigned long private)
{
	struct folio *folio = page_folio(page);
	struct migration_target_control *mtc;
	gfp_t gfp_mask;
	unsigned int order = 0;
	struct folio *hugetlb_folio = NULL;
	struct folio *new_folio = NULL;
	int nid;
	int zidx;

	mtc = (struct migration_target_control *)private;
	gfp_mask = mtc->gfp_mask;
	nid = mtc->nid;
	if (nid == NUMA_NO_NODE)
		nid = folio_nid(folio);

	if (folio_test_hugetlb(folio)) {
		struct hstate *h = folio_hstate(folio);

		gfp_mask = htlb_modify_alloc_mask(h, gfp_mask);
		hugetlb_folio = alloc_hugetlb_folio_nodemask(h, nid,
						mtc->nmask, gfp_mask);
		return &hugetlb_folio->page;
	}

	if (folio_test_large(folio)) {
		/*
		 * clear __GFP_RECLAIM to make the migration callback
		 * consistent with regular THP allocations.
		 */
		gfp_mask &= ~__GFP_RECLAIM;
		gfp_mask |= GFP_TRANSHUGE;
		order = folio_order(folio);
	}
	zidx = zone_idx(folio_zone(folio));
	if (is_highmem_idx(zidx) || zidx == ZONE_MOVABLE)
		gfp_mask |= __GFP_HIGHMEM;

	new_folio = __folio_alloc(gfp_mask, order, nid, mtc->nmask);

	return &new_folio->page;
}

#ifdef CONFIG_NUMA

static int store_status(int __user *status, int start, int value, int nr)
{
	while (nr-- > 0) {
		if (put_user(value, status + start))
			return -EFAULT;
		start++;
	}

	return 0;
}

static int do_move_pages_to_node(struct mm_struct *mm,
		struct list_head *pagelist, int node)
{
	int err;
	struct migration_target_control mtc = {
		.nid = node,
		.gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE,
	};

	err = migrate_pages(pagelist, alloc_migration_target, NULL,
		(unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL, NULL);
	if (err)
		putback_movable_pages(pagelist);
	return err;
}

/*
 * Resolves the given address to a struct page, isolates it from the LRU and
 * puts it to the given pagelist.
 * Returns:
 *     errno - if the page cannot be found/isolated
 *     0 - when it doesn't have to be migrated because it is already on the
 *         target node
 *     1 - when it has been queued
 */
static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
		int node, struct list_head *pagelist, bool migrate_all)
{
	struct vm_area_struct *vma;
	struct page *page;
	int err;

	mmap_read_lock(mm);
	err = -EFAULT;
	vma = vma_lookup(mm, addr);
	if (!vma || !vma_migratable(vma))
		goto out;

	/* FOLL_DUMP to ignore special (like zero) pages */
	page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP);

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

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

	if (is_zone_device_page(page))
		goto out_putpage;

	err = 0;
	if (page_to_nid(page) == node)
		goto out_putpage;

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

	if (PageHuge(page)) {
		if (PageHead(page)) {
			err = isolate_hugetlb(page_folio(page), pagelist);
			if (!err)
				err = 1;
		}
	} else {
		struct page *head;

		head = compound_head(page);
		err = isolate_lru_page(head);
		if (err)
			goto out_putpage;

		err = 1;
		list_add_tail(&head->lru, pagelist);
		mod_node_page_state(page_pgdat(head),
			NR_ISOLATED_ANON + page_is_file_lru(head),
			thp_nr_pages(head));
	}
out_putpage:
	/*
	 * Either remove the duplicate refcount from
	 * isolate_lru_page() or drop the page ref if it was
	 * not isolated.
	 */
	put_page(page);
out:
	mmap_read_unlock(mm);
	return err;
}

static int move_pages_and_store_status(struct mm_struct *mm, int node,
		struct list_head *pagelist, int __user *status,
		int start, int i, unsigned long nr_pages)
{
	int err;

	if (list_empty(pagelist))
		return 0;

	err = do_move_pages_to_node(mm, pagelist, node);
	if (err) {
		/*
		 * Positive err means the number of failed
		 * pages to migrate.  Since we are going to
		 * abort and return the number of non-migrated
		 * pages, so need to include the rest of the
		 * nr_pages that have not been attempted as
		 * well.
		 */
		if (err > 0)
			err += nr_pages - i;
		return err;
	}
	return store_status(status, start, node, i - start);
}

/*
 * 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)
{
	int current_node = NUMA_NO_NODE;
	LIST_HEAD(pagelist);
	int start, i;
	int err = 0, err1;

	lru_cache_disable();

	for (i = start = 0; i < nr_pages; i++) {
		const void __user *p;
		unsigned long addr;
		int node;

		err = -EFAULT;
		if (get_user(p, pages + i))
			goto out_flush;
		if (get_user(node, nodes + i))
			goto out_flush;
		addr = (unsigned long)untagged_addr(p);

		err = -ENODEV;
		if (node < 0 || node >= MAX_NUMNODES)
			goto out_flush;
		if (!node_state(node, N_MEMORY))
			goto out_flush;

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

		if (current_node == NUMA_NO_NODE) {
			current_node = node;
			start = i;
		} else if (node != current_node) {
			err = move_pages_and_store_status(mm, current_node,
					&pagelist, status, start, i, nr_pages);
			if (err)
				goto out;
			start = i;
			current_node = node;
		}

		/*
		 * Errors in the page lookup or isolation are not fatal and we simply
		 * report them via status
		 */
		err = add_page_for_migration(mm, addr, current_node,
				&pagelist, flags & MPOL_MF_MOVE_ALL);

		if (err > 0) {
			/* The page is successfully queued for migration */
			continue;
		}

		/*
		 * The move_pages() man page does not have an -EEXIST choice, so
		 * use -EFAULT instead.
		 */
		if (err == -EEXIST)
			err = -EFAULT;

		/*
		 * If the page is already on the target node (!err), store the
		 * node, otherwise, store the err.
		 */
		err = store_status(status, i, err ? : current_node, 1);
		if (err)
			goto out_flush;

		err = move_pages_and_store_status(mm, current_node, &pagelist,
				status, start, i, nr_pages);
		if (err) {
			/* We have accounted for page i */
			if (err > 0)
				err--;
			goto out;
		}
		current_node = NUMA_NO_NODE;
	}
out_flush:
	/* Make sure we do not overwrite the existing error */
	err1 = move_pages_and_store_status(mm, current_node, &pagelist,
				status, start, i, nr_pages);
	if (err >= 0)
		err = err1;
out:
	lru_cache_enable();
	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;

	mmap_read_lock(mm);

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

		/* FOLL_DUMP to ignore special (like zero) pages */
		page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP);

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

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

		if (!is_zone_device_page(page))
			err = page_to_nid(page);

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

		pages++;
		status++;
	}

	mmap_read_unlock(mm);
}

static int get_compat_pages_array(const void __user *chunk_pages[],
				  const void __user * __user *pages,
				  unsigned long chunk_nr)
{
	compat_uptr_t __user *pages32 = (compat_uptr_t __user *)pages;
	compat_uptr_t p;
	int i;

	for (i = 0; i < chunk_nr; i++) {
		if (get_user(p, pages32 + i))
			return -EFAULT;
		chunk_pages[i] = compat_ptr(p);
	}

	return 0;
}

/*
 * 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 16UL
	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 = min(nr_pages, DO_PAGES_STAT_CHUNK_NR);

		if (in_compat_syscall()) {
			if (get_compat_pages_array(chunk_pages, pages,
						   chunk_nr))
				break;
		} else {
			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;
}

static struct mm_struct *find_mm_struct(pid_t pid, nodemask_t *mem_nodes)
{
	struct task_struct *task;
	struct mm_struct *mm;

	/*
	 * There is no need to check if current process has the right to modify
	 * the specified process when they are same.
	 */
	if (!pid) {
		mmget(current->mm);
		*mem_nodes = cpuset_mems_allowed(current);
		return current->mm;
	}

	/* Find the mm_struct */
	rcu_read_lock();
	task = find_task_by_vpid(pid);
	if (!task) {
		rcu_read_unlock();
		return ERR_PTR(-ESRCH);
	}
	get_task_struct(task);

	/*
	 * Check if this process has the right to modify the specified
	 * process. Use the regular "ptrace_may_access()" checks.
	 */
	if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) {
		rcu_read_unlock();
		mm = ERR_PTR(-EPERM);
		goto out;
	}
	rcu_read_unlock();

	mm = ERR_PTR(security_task_movememory(task));
	if (IS_ERR(mm))
		goto out;
	*mem_nodes = cpuset_mems_allowed(task);
	mm = get_task_mm(task);
out:
	put_task_struct(task);
	if (!mm)
		mm = ERR_PTR(-EINVAL);
	return mm;
}

/*
 * Move a list of pages in the address space of the currently executing
 * process.
 */
static int kernel_move_pages(pid_t pid, unsigned long nr_pages,
			     const void __user * __user *pages,
			     const int __user *nodes,
			     int __user *status, int flags)
{
	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;

	mm = find_mm_struct(pid, &task_nodes);
	if (IS_ERR(mm))
		return PTR_ERR(mm);

	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;
}

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)
{
	return kernel_move_pages(pid, nr_pages, pages, nodes, status, flags);
}

#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 is 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 (!managed_zone(zone))
			continue;

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

static struct page *alloc_misplaced_dst_page(struct page *page,
					   unsigned long data)
{
	int nid = (int) data;
	int order = compound_order(page);
	gfp_t gfp = __GFP_THISNODE;
	struct folio *new;

	if (order > 0)
		gfp |= GFP_TRANSHUGE_LIGHT;
	else {
		gfp |= GFP_HIGHUSER_MOVABLE | __GFP_NOMEMALLOC | __GFP_NORETRY |
			__GFP_NOWARN;
		gfp &= ~__GFP_RECLAIM;
	}
	new = __folio_alloc_node(gfp, order, nid);

	return &new->page;
}

static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
{
	int nr_pages = thp_nr_pages(page);
	int order = compound_order(page);

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

	/* Do not migrate THP mapped by multiple processes */
	if (PageTransHuge(page) && total_mapcount(page) > 1)
		return 0;

	/* Avoid migrating to a node that is nearly full */
	if (!migrate_balanced_pgdat(pgdat, nr_pages)) {
		int z;

		if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING))
			return 0;
		for (z = pgdat->nr_zones - 1; z >= 0; z--) {
			if (managed_zone(pgdat->node_zones + z))
				break;
		}
		wakeup_kswapd(pgdat->node_zones + z, 0, order, ZONE_MOVABLE);
		return 0;
	}

	if (isolate_lru_page(page))
		return 0;

	mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_is_file_lru(page),
			    nr_pages);

	/*
	 * 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;
}

/*
 * 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;
	unsigned int nr_succeeded;
	LIST_HEAD(migratepages);
	int nr_pages = thp_nr_pages(page);

	/*
	 * 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_lru(page) &&
	    (vma->vm_flags & VM_EXEC))
		goto out;

	/*
	 * Also do not migrate dirty pages as not all filesystems can move
	 * dirty pages in MIGRATE_ASYNC mode which is a waste of cycles.
	 */
	if (page_is_file_lru(page) && PageDirty(page))
		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, &nr_succeeded);
	if (nr_remaining) {
		if (!list_empty(&migratepages)) {
			list_del(&page->lru);
			mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON +
					page_is_file_lru(page), -nr_pages);
			putback_lru_page(page);
		}
		isolated = 0;
	}
	if (nr_succeeded) {
		count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_succeeded);
		if (!node_is_toptier(page_to_nid(page)) && node_is_toptier(node))
			mod_node_page_state(pgdat, PGPROMOTE_SUCCESS,
					    nr_succeeded);
	}
	BUG_ON(!list_empty(&migratepages));
	return isolated;

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