summaryrefslogtreecommitdiffstats
path: root/mm/migrate.c
blob: efa9941ebe031cf6c7bc8be8bb1551d79007f22d (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
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
// 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/pagewalk.h>
#include <linux/pfn_t.h>
#include <linux/memremap.h>
#include <linux/userfaultfd_k.h>
#include <linux/balloon_compaction.h>
#include <linux/mmu_notifier.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 <asm/tlbflush.h>

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

#include "internal.h"

int isolate_movable_page(struct page *page, isolate_mode_t mode)
{
	struct address_space *mapping;

	/*
	 * 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 (unlikely(!get_page_unless_zero(page)))
		goto out;

	/*
	 * Check PageMovable before holding a PG_lock because page's owner
	 * assumes anybody doesn't touch PG_lock of newly allocated page
	 * so unconditionally grabbing the lock ruins page's owner side.
	 */
	if (unlikely(!__PageMovable(page)))
		goto out_putpage;
	/*
	 * 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(!trylock_page(page)))
		goto out_putpage;

	if (!PageMovable(page) || PageIsolated(page))
		goto out_no_isolated;

	mapping = page_mapping(page);
	VM_BUG_ON_PAGE(!mapping, page);

	if (!mapping->a_ops->isolate_page(page, mode))
		goto out_no_isolated;

	/* Driver shouldn't use PG_isolated bit of page->flags */
	WARN_ON_ONCE(PageIsolated(page));
	__SetPageIsolated(page);
	unlock_page(page);

	return 0;

out_no_isolated:
	unlock_page(page);
out_putpage:
	put_page(page);
out:
	return -EBUSY;
}

static void putback_movable_page(struct page *page)
{
	struct address_space *mapping;

	mapping = page_mapping(page);
	mapping->a_ops->putback_page(page);
	__ClearPageIsolated(page);
}

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

	list_for_each_entry_safe(page, page2, l, lru) {
		if (unlikely(PageHuge(page))) {
			putback_active_hugepage(page);
			continue;
		}
		list_del(&page->lru);
		/*
		 * We isolated non-lru movable page so here we can use
		 * __PageMovable because LRU page's mapping cannot have
		 * PAGE_MAPPING_MOVABLE.
		 */
		if (unlikely(__PageMovable(page))) {
			VM_BUG_ON_PAGE(!PageIsolated(page), page);
			lock_page(page);
			if (PageMovable(page))
				putback_movable_page(page);
			else
				__ClearPageIsolated(page);
			unlock_page(page);
			put_page(page);
		} else {
			mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON +
					page_is_file_lru(page), -thp_nr_pages(page));
			putback_lru_page(page);
		}
	}
}

/*
 * Restore a potential migration pte to a working pte entry
 */
static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
				 unsigned long addr, void *old)
{
	struct page_vma_mapped_walk pvmw = {
		.page = old,
		.vma = vma,
		.address = addr,
		.flags = PVMW_SYNC | PVMW_MIGRATION,
	};
	struct page *new;
	pte_t pte;
	swp_entry_t entry;

	VM_BUG_ON_PAGE(PageTail(page), page);
	while (page_vma_mapped_walk(&pvmw)) {
		if (PageKsm(page))
			new = page;
		else
			new = page - pvmw.page->index +
				linear_page_index(vma, pvmw.address);

#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
		/* PMD-mapped THP migration entry */
		if (!pvmw.pte) {
			VM_BUG_ON_PAGE(PageHuge(page) || !PageTransCompound(page), page);
			remove_migration_pmd(&pvmw, new);
			continue;
		}
#endif

		get_page(new);
		pte = pte_mkold(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_writable_migration_entry(entry))
			pte = maybe_mkwrite(pte, vma);
		else if (pte_swp_uffd_wp(*pvmw.pte))
			pte = pte_mkuffd_wp(pte);

		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 (PageHuge(new)) {
			unsigned int shift = huge_page_shift(hstate_vma(vma));

			pte = pte_mkhuge(pte);
			pte = arch_make_huge_pte(pte, shift, vma->vm_flags);
			set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte);
			if (PageAnon(new))
				hugepage_add_anon_rmap(new, vma, pvmw.address);
			else
				page_dup_rmap(new, true);
		} else
#endif
		{
			set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte);

			if (PageAnon(new))
				page_add_anon_rmap(new, vma, pvmw.address, false);
			else
				page_add_file_rmap(new, false);
		}
		if (vma->vm_flags & VM_LOCKED && !PageTransCompound(new))
			mlock_vma_page(new);

		if (PageTransHuge(page) && PageMlocked(page))
			clear_page_mlock(page);

		/* 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 page *old, struct page *new, bool locked)
{
	struct rmap_walk_control rwc = {
		.rmap_one = remove_migration_pte,
		.arg = old,
	};

	if (locked)
		rmap_walk_locked(new, &rwc);
	else
		rmap_walk(new, &rwc);
}

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

	spin_lock(ptl);
	pte = *ptep;
	if (!is_swap_pte(pte))
		goto out;

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

	page = pfn_swap_entry_to_page(entry);
	page = compound_head(page);

	/*
	 * Once page cache replacement of page migration started, page_count
	 * is zero; but we must not call put_and_wait_on_page_locked() without
	 * a ref. Use get_page_unless_zero(), and just fault again if it fails.
	 */
	if (!get_page_unless_zero(page))
		goto out;
	pte_unmap_unlock(ptep, ptl);
	put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE);
	return;
out:
	pte_unmap_unlock(ptep, ptl);
}

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

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

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

	ptl = pmd_lock(mm, pmd);
	if (!is_pmd_migration_entry(*pmd))
		goto unlock;
	page = pfn_swap_entry_to_page(pmd_to_swp_entry(*pmd));
	if (!get_page_unless_zero(page))
		goto unlock;
	spin_unlock(ptl);
	put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE);
	return;
unlock:
	spin_unlock(ptl);
}
#endif

static int expected_page_refs(struct address_space *mapping, struct page *page)
{
	int expected_count = 1;

	/*
	 * Device private pages have an extra refcount as they are
	 * ZONE_DEVICE pages.
	 */
	expected_count += is_device_private_page(page);
	if (mapping)
		expected_count += compound_nr(page) + page_has_private(page);

	return expected_count;
}

/*
 * 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 = expected_page_refs(mapping, &folio->page) + 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_count(folio) != expected_count ||
	    xas_load(&xas) != folio) {
		xas_unlock_irq(&xas);
		return -EAGAIN;
	}

	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);
	if (nr > 1) {
		int i;

		for (i = 1; i < nr; i++) {
			xas_next(&xas);
			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 page *newpage, struct page *page)
{
	XA_STATE(xas, &mapping->i_pages, page_index(page));
	int expected_count;

	xas_lock_irq(&xas);
	expected_count = 2 + page_has_private(page);
	if (page_count(page) != expected_count || xas_load(&xas) != page) {
		xas_unlock_irq(&xas);
		return -EAGAIN;
	}

	if (!page_ref_freeze(page, expected_count)) {
		xas_unlock_irq(&xas);
		return -EAGAIN;
	}

	newpage->index = page->index;
	newpage->mapping = page->mapping;

	get_page(newpage);

	xas_store(&xas, newpage);

	page_ref_unfreeze(page, 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);
	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);
	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
 ***********************************************************/

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

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

	rc = folio_migrate_mapping(mapping, newfolio, folio, 0);

	if (rc != MIGRATEPAGE_SUCCESS)
		return rc;

	if (mode != MIGRATE_SYNC_NO_COPY)
		folio_migrate_copy(newfolio, folio);
	else
		folio_migrate_flags(newfolio, folio);
	return MIGRATEPAGE_SUCCESS;
}
EXPORT_SYMBOL(migrate_page);

#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_page(struct address_space *mapping,
		struct page *newpage, struct page *page, enum migrate_mode mode,
		bool check_refs)
{
	struct buffer_head *bh, *head;
	int rc;
	int expected_count;

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

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

	head = page_buffers(page);
	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 = migrate_page_move_mapping(mapping, newpage, page, 0);
	if (rc != MIGRATEPAGE_SUCCESS)
		goto unlock_buffers;

	attach_page_private(newpage, detach_page_private(page));

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

	} while (bh != head);

	if (mode != MIGRATE_SYNC_NO_COPY)
		migrate_page_copy(newpage, page);
	else
		migrate_page_states(newpage, page);

	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;
}

/*
 * Migration function for pages with buffers. This function can only be used
 * if the underlying filesystem guarantees that no other references to "page"
 * exist. For example attached buffer heads are accessed only under page lock.
 */
int buffer_migrate_page(struct address_space *mapping,
		struct page *newpage, struct page *page, enum migrate_mode mode)
{
	return __buffer_migrate_page(mapping, newpage, page, mode, false);
}
EXPORT_SYMBOL(buffer_migrate_page);

/*
 * Same as above 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).
 */
int buffer_migrate_page_norefs(struct address_space *mapping,
		struct page *newpage, struct page *page, enum migrate_mode mode)
{
	return __buffer_migrate_page(mapping, newpage, page, mode, true);
}
#endif

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

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

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

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

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

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

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

/*
 * Default handling if a filesystem does not provide a migration function.
 */
static int fallback_migrate_page(struct address_space *mapping,
	struct page *newpage, struct page *page, enum migrate_mode mode)
{
	if (PageDirty(page)) {
		/* Only writeback pages in full synchronous migration */
		switch (mode) {
		case MIGRATE_SYNC:
		case MIGRATE_SYNC_NO_COPY:
			break;
		default:
			return -EBUSY;
		}
		return writeout(mapping, page);
	}

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

	return migrate_page(mapping, newpage, page, mode);
}

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

	VM_BUG_ON_PAGE(!PageLocked(page), page);
	VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);

	mapping = page_mapping(page);

	if (likely(is_lru)) {
		if (!mapping)
			rc = migrate_page(mapping, newpage, page, mode);
		else if (mapping->a_ops->migratepage)
			/*
			 * Most pages have a mapping and most filesystems
			 * provide a migratepage callback. Anonymous pages
			 * are part of swap space which also has its own
			 * migratepage callback. This is the most common path
			 * for page migration.
			 */
			rc = mapping->a_ops->migratepage(mapping, newpage,
							page, mode);
		else
			rc = fallback_migrate_page(mapping, newpage,
							page, mode);
	} else {
		/*
		 * In case of non-lru page, it could be released after
		 * isolation step. In that case, we shouldn't try migration.
		 */
		VM_BUG_ON_PAGE(!PageIsolated(page), page);
		if (!PageMovable(page)) {
			rc = MIGRATEPAGE_SUCCESS;
			__ClearPageIsolated(page);
			goto out;
		}

		rc = mapping->a_ops->migratepage(mapping, newpage,
						page, mode);
		WARN_ON_ONCE(rc == MIGRATEPAGE_SUCCESS &&
			!PageIsolated(page));
	}

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

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

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

		if (likely(!is_zone_device_page(newpage)))
			flush_dcache_page(newpage);

	}
out:
	return rc;
}

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

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

		/*
		 * It's not safe for direct compaction to call lock_page.
		 * For example, during page readahead pages are added locked
		 * to the LRU. Later, when the IO completes the pages are
		 * marked uptodate and unlocked. However, the queueing
		 * could be merging multiple pages for one bio (e.g.
		 * mpage_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;

		lock_page(page);
	}

	if (PageWriteback(page)) {
		/*
		 * Only in the case of a full synchronous migration is it
		 * necessary to wait for PageWriteback. In the async case,
		 * the retry loop is too short and in the sync-light case,
		 * the overhead of stalling is too much
		 */
		switch (mode) {
		case MIGRATE_SYNC:
		case MIGRATE_SYNC_NO_COPY:
			break;
		default:
			rc = -EBUSY;
			goto out_unlock;
		}
		if (!force)
			goto out_unlock;
		wait_on_page_writeback(page);
	}

	/*
	 * By try_to_migrate(), page->mapcount goes down to 0 here. In this case,
	 * we cannot notice that anon_vma is freed while we migrates a page.
	 * This get_anon_vma() delays freeing anon_vma pointer until the end
	 * of migration. File cache pages are no problem because of page_lock()
	 * File Caches may use write_page() or lock_page() in migration, then,
	 * just care Anon page here.
	 *
	 * Only page_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 (PageAnon(page) && !PageKsm(page))
		anon_vma = page_get_anon_vma(page);

	/*
	 * 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 newpage at this point. We used to have a BUG
	 * here if trylock_page(newpage) fails, but would like to allow for
	 * cases where there might be a race with the previous use of newpage.
	 * This is much like races on refcount of oldpage: just don't BUG().
	 */
	if (unlikely(!trylock_page(newpage)))
		goto out_unlock;

	if (unlikely(!is_lru)) {
		rc = move_to_new_page(newpage, page, 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 page->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 (!page->mapping) {
		VM_BUG_ON_PAGE(PageAnon(page), page);
		if (page_has_private(page)) {
			try_to_free_buffers(page);
			goto out_unlock_both;
		}
	} else if (page_mapped(page)) {
		/* Establish migration ptes */
		VM_BUG_ON_PAGE(PageAnon(page) && !PageKsm(page) && !anon_vma,
				page);
		try_to_migrate(page, 0);
		page_was_mapped = true;
	}

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

	if (page_was_mapped)
		remove_migration_ptes(page,
			rc == MIGRATEPAGE_SUCCESS ? newpage : page, false);

out_unlock_both:
	unlock_page(newpage);
out_unlock:
	/* Drop an anon_vma reference if we took one */
	if (anon_vma)
		put_anon_vma(anon_vma);
	unlock_page(page);
out:
	/*
	 * If migration is successful, decrease refcount of the newpage
	 * which will not free the page because new page owner increased
	 * refcounter. As well, if it is LRU page, add the page to LRU
	 * list in here. Use the old state of the isolated source page to
	 * determine if we migrated a LRU page. newpage was already unlocked
	 * and possibly modified by its owner - don't rely on the page
	 * state.
	 */
	if (rc == MIGRATEPAGE_SUCCESS) {
		if (unlikely(!is_lru))
			put_page(newpage);
		else
			putback_lru_page(newpage);
	}

	return rc;
}


/*
 * node_demotion[] example:
 *
 * Consider a system with two sockets.  Each socket has
 * three classes of memory attached: fast, medium and slow.
 * Each memory class is placed in its own NUMA node.  The
 * CPUs are placed in the node with the "fast" memory.  The
 * 6 NUMA nodes (0-5) might be split among the sockets like
 * this:
 *
 *	Socket A: 0, 1, 2
 *	Socket B: 3, 4, 5
 *
 * When Node 0 fills up, its memory should be migrated to
 * Node 1.  When Node 1 fills up, it should be migrated to
 * Node 2.  The migration path start on the nodes with the
 * processors (since allocations default to this node) and
 * fast memory, progress through medium and end with the
 * slow memory:
 *
 *	0 -> 1 -> 2 -> stop
 *	3 -> 4 -> 5 -> stop
 *
 * This is represented in the node_demotion[] like this:
 *
 *	{  1, // Node 0 migrates to 1
 *	   2, // Node 1 migrates to 2
 *	  -1, // Node 2 does not migrate
 *	   4, // Node 3 migrates to 4
 *	   5, // Node 4 migrates to 5
 *	  -1} // Node 5 does not migrate
 */

/*
 * Writes to this array occur without locking.  Cycles are
 * not allowed: Node X demotes to Y which demotes to X...
 *
 * If multiple reads are performed, a single rcu_read_lock()
 * must be held over all reads to ensure that no cycles are
 * observed.
 */
static int node_demotion[MAX_NUMNODES] __read_mostly =
	{[0 ...  MAX_NUMNODES - 1] = NUMA_NO_NODE};

/**
 * next_demotion_node() - Get the next node in the demotion path
 * @node: The starting node to lookup the next node
 *
 * Return: node id for next memory node in the demotion path hierarchy
 * from @node; NUMA_NO_NODE if @node is terminal.  This does not keep
 * @node online or guarantee that it *continues* to be the next demotion
 * target.
 */
int next_demotion_node(int node)
{
	int target;

	/*
	 * node_demotion[] is updated without excluding this
	 * function from running.  RCU doesn't provide any
	 * compiler barriers, so the READ_ONCE() is required
	 * to avoid compiler reordering or read merging.
	 *
	 * Make sure to use RCU over entire code blocks if
	 * node_demotion[] reads need to be consistent.
	 */
	rcu_read_lock();
	target = READ_ONCE(node_demotion[node]);
	rcu_read_unlock();

	return target;
}

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

	if (!thp_migration_supported() && PageTransHuge(page))
		return -ENOSYS;

	if (page_count(page) == 1) {
		/* page was freed from under us. So we are done. */
		ClearPageActive(page);
		ClearPageUnevictable(page);
		if (unlikely(__PageMovable(page))) {
			lock_page(page);
			if (!PageMovable(page))
				__ClearPageIsolated(page);
			unlock_page(page);
		}
		goto out;
	}

	newpage = get_new_page(page, private);
	if (!newpage)
		return -ENOMEM;

	rc = __unmap_and_move(page, newpage, force, mode);
	if (rc == MIGRATEPAGE_SUCCESS)
		set_page_owner_migrate_reason(newpage, reason);

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

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

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

		if (put_new_page)
			put_new_page(newpage, private);
		else
			put_page(newpage);
	}

	return rc;
}

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

	if (page_count(hpage) == 1) {
		/* page was freed from under us. So we are done. */
		putback_active_hugepage(hpage);
		return MIGRATEPAGE_SUCCESS;
	}

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

	if (!trylock_page(hpage)) {
		if (!force)
			goto out;
		switch (mode) {
		case MIGRATE_SYNC:
		case MIGRATE_SYNC_NO_COPY:
			break;
		default:
			goto out;
		}
		lock_page(hpage);
	}

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

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

	if (unlikely(!trylock_page(new_hpage)))
		goto put_anon;

	if (page_mapped(hpage)) {
		bool mapping_locked = false;
		enum ttu_flags ttu = 0;

		if (!PageAnon(hpage)) {
			/*
			 * 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;

			mapping_locked = true;
			ttu |= TTU_RMAP_LOCKED;
		}

		try_to_migrate(hpage, ttu);
		page_was_mapped = 1;

		if (mapping_locked)
			i_mmap_unlock_write(mapping);
	}

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

	if (page_was_mapped)
		remove_migration_ptes(hpage,
			rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, false);

unlock_put_anon:
	unlock_page(new_hpage);

put_anon:
	if (anon_vma)
		put_anon_vma(anon_vma);

	if (rc == MIGRATEPAGE_SUCCESS) {
		move_hugetlb_state(hpage, new_hpage, reason);
		put_new_page = NULL;
	}

out_unlock:
	unlock_page(hpage);
out:
	if (rc == MIGRATEPAGE_SUCCESS)
		putback_active_hugepage(hpage);
	else if (rc != -EAGAIN)
		list_move_tail(&hpage->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
		putback_active_hugepage(new_hpage);

	return rc;
}

static inline int try_split_thp(struct page *page, struct page **page2,
				struct list_head *from)
{
	int rc = 0;

	lock_page(page);
	rc = split_huge_page_to_list(page, from);
	unlock_page(page);
	if (!rc)
		list_safe_reset_next(page, *page2, lru);

	return rc;
}

/*
 * migrate_pages - migrate the pages specified in a list, to the free pages
 *		   supplied as the target for the page migration
 *
 * @from:		The list of pages to be migrated.
 * @get_new_page:	The function used to allocate free pages to be used
 *			as the target of the page migration.
 * @put_new_page:	The function used to free target pages if migration
 *			fails, or NULL if no special handling is necessary.
 * @private:		Private data to be passed on to get_new_page()
 * @mode:		The migration mode that specifies the constraints for
 *			page migration, if any.
 * @reason:		The reason for page migration.
 * @ret_succeeded:	Set to the number of pages migrated successfully if
 *			the caller passes a non-NULL pointer.
 *
 * The function returns after 10 attempts or if no pages are movable any more
 * because the list has become empty or no retryable pages exist any more.
 * It is caller's responsibility to call putback_movable_pages() to return pages
 * to the LRU or free list only if ret != 0.
 *
 * Returns the number of pages that were not migrated, or an error code.
 */
int migrate_pages(struct list_head *from, new_page_t get_new_page,
		free_page_t put_new_page, unsigned long private,
		enum migrate_mode mode, int reason, unsigned int *ret_succeeded)
{
	int retry = 1;
	int thp_retry = 1;
	int nr_failed = 0;
	int nr_succeeded = 0;
	int nr_thp_succeeded = 0;
	int nr_thp_failed = 0;
	int nr_thp_split = 0;
	int pass = 0;
	bool is_thp = false;
	struct page *page;
	struct page *page2;
	int swapwrite = current->flags & PF_SWAPWRITE;
	int rc, nr_subpages;
	LIST_HEAD(ret_pages);
	bool nosplit = (reason == MR_NUMA_MISPLACED);

	trace_mm_migrate_pages_start(mode, reason);

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

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

		list_for_each_entry_safe(page, page2, from, lru) {
retry:
			/*
			 * THP statistics is based on the source huge page.
			 * Capture required information that might get lost
			 * during migration.
			 */
			is_thp = PageTransHuge(page) && !PageHuge(page);
			nr_subpages = thp_nr_pages(page);
			cond_resched();

			if (PageHuge(page))
				rc = unmap_and_move_huge_page(get_new_page,
						put_new_page, private, page,
						pass > 2, mode, reason,
						&ret_pages);
			else
				rc = unmap_and_move(get_new_page, put_new_page,
						private, page, pass > 2, mode,
						reason, &ret_pages);
			/*
			 * The rules are:
			 *	Success: non hugetlb page will be freed, hugetlb
			 *		 page will be put back
			 *	-EAGAIN: stay on the from list
			 *	-ENOMEM: stay on the from list
			 *	Other errno: put on ret_pages list then splice to
			 *		     from list
			 */
			switch(rc) {
			/*
			 * THP migration might be unsupported or the
			 * allocation could've failed so we should
			 * retry on the same page with the THP split
			 * to base pages.
			 *
			 * Head page is retried immediately and tail
			 * pages are added to the tail of the list so
			 * we encounter them after the rest of the list
			 * is processed.
			 */
			case -ENOSYS:
				/* THP migration is unsupported */
				if (is_thp) {
					if (!try_split_thp(page, &page2, from)) {
						nr_thp_split++;
						goto retry;
					}

					nr_thp_failed++;
					nr_failed += nr_subpages;
					break;
				}

				/* Hugetlb migration is unsupported */
				nr_failed++;
				break;
			case -ENOMEM:
				/*
				 * When memory is low, don't bother to try to migrate
				 * other pages, just exit.
				 * THP NUMA faulting doesn't split THP to retry.
				 */
				if (is_thp && !nosplit) {
					if (!try_split_thp(page, &page2, from)) {
						nr_thp_split++;
						goto retry;
					}

					nr_thp_failed++;
					nr_failed += nr_subpages;
					goto out;
				}
				nr_failed++;
				goto out;
			case -EAGAIN:
				if (is_thp) {
					thp_retry++;
					break;
				}
				retry++;
				break;
			case MIGRATEPAGE_SUCCESS:
				if (is_thp) {
					nr_thp_succeeded++;
					nr_succeeded += nr_subpages;
					break;
				}
				nr_succeeded++;
				break;
			default:
				/*
				 * Permanent failure (-EBUSY, etc.):
				 * unlike -EAGAIN case, the failed page is
				 * removed from migration page list and not
				 * retried in the next outer loop.
				 */
				if (is_thp) {
					nr_thp_failed++;
					nr_failed += nr_subpages;
					break;
				}
				nr_failed++;
				break;
			}
		}
	}
	nr_failed += retry + thp_retry;
	nr_thp_failed += thp_retry;
	rc = nr_failed;
out:
	/*
	 * Put the permanent failure page back to migration list, they
	 * will be put back to the right list by the caller.
	 */
	list_splice(&ret_pages, from);

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

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

	if (ret_succeeded)
		*ret_succeeded = nr_succeeded;

	return rc;
}

struct page *alloc_migration_target(struct page *page, unsigned long private)
{
	struct migration_target_control *mtc;
	gfp_t gfp_mask;
	unsigned int order = 0;
	struct page *new_page = 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 = page_to_nid(page);

	if (PageHuge(page)) {
		struct hstate *h = page_hstate(compound_head(page));

		gfp_mask = htlb_modify_alloc_mask(h, gfp_mask);
		return alloc_huge_page_nodemask(h, nid, mtc->nmask, gfp_mask);
	}

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

	new_page = __alloc_pages(gfp_mask, order, nid, mtc->nmask);

	if (new_page && PageTransHuge(new_page))
		prep_transhuge_page(new_page);

	return new_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;
	unsigned int follflags;
	int err;

	mmap_read_lock(mm);
	err = -EFAULT;
	vma = find_vma(mm, addr);
	if (!vma || addr < vma->vm_start || !vma_migratable(vma))
		goto out;

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

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

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

	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)) {
			isolate_huge_page(page, pagelist);
			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 - 1;
		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;
		}

		/*
		 * 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)
			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_DUMP);

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

		err = page ? page_to_nid(page) : -ENOENT;
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 16
	const void __user *chunk_pages[DO_PAGES_STAT_CHUNK_NR];
	int chunk_status[DO_PAGES_STAT_CHUNK_NR];

	while (nr_pages) {
		unsigned long chunk_nr;

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

		if (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 crude
 */
static bool migrate_balanced_pgdat(struct pglist_data *pgdat,
				   unsigned long nr_migrate_pages)
{
	int z;

	for (z = pgdat->nr_zones - 1; z >= 0; z--) {
		struct zone *zone = pgdat->node_zones + z;

		if (!populated_zone(zone))
			continue;

		/* 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;
	struct page *newpage;

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

	return newpage;
}

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

	newpage = alloc_pages_node(nid, (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE),
				   HPAGE_PMD_ORDER);
	if (!newpage)
		goto out;

	prep_transhuge_page(newpage);

out:
	return newpage;
}

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

	VM_BUG_ON_PAGE(compound_order(page) && !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))
		return 0;

	if (isolate_lru_page(page))
		return 0;

	page_lru = page_is_file_lru(page);
	mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_lru,
			    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;
	LIST_HEAD(migratepages);
	new_page_t *new;
	bool compound;
	int nr_pages = thp_nr_pages(page);

	/*
	 * PTE mapped THP or HugeTLB page can't reach here so the page could
	 * be either base page or THP.  And it must be head page if it is
	 * THP.
	 */
	compound = PageTransHuge(page);

	if (compound)
		new = alloc_misplaced_dst_page_thp;
	else
		new = alloc_misplaced_dst_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, *new, NULL, node,
				     MIGRATE_ASYNC, MR_NUMA_MISPLACED, NULL);
	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;
	} else
		count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_pages);
	BUG_ON(!list_empty(&migratepages));
	return isolated;

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

#ifdef CONFIG_DEVICE_PRIVATE
static int migrate_vma_collect_skip(unsigned long start,
				    unsigned long end,
				    struct mm_walk *walk)
{
	struct migrate_vma *migrate = walk->private;
	unsigned long addr;

	for (addr = start; addr < end; addr += PAGE_SIZE) {
		migrate->dst[migrate->npages] = 0;
		migrate->src[migrate->npages++] = 0;
	}

	return 0;
}

static int migrate_vma_collect_hole(unsigned long start,
				    unsigned long end,
				    __always_unused int depth,
				    struct mm_walk *walk)
{
	struct migrate_vma *migrate = walk->private;
	unsigned long addr;

	/* Only allow populating anonymous memory. */
	if (!vma_is_anonymous(walk->vma))
		return migrate_vma_collect_skip(start, end, walk);

	for (addr = start; addr < end; addr += PAGE_SIZE) {
		migrate->src[migrate->npages] = MIGRATE_PFN_MIGRATE;
		migrate->dst[migrate->npages] = 0;
		migrate->npages++;
		migrate->cpages++;
	}

	return 0;
}

static int migrate_vma_collect_pmd(pmd_t *pmdp,
				   unsigned long start,
				   unsigned long end,
				   struct mm_walk *walk)
{
	struct migrate_vma *migrate = walk->private;
	struct vm_area_struct *vma = walk->vma;
	struct mm_struct *mm = vma->vm_mm;
	unsigned long addr = start, unmapped = 0;
	spinlock_t *ptl;
	pte_t *ptep;

again:
	if (pmd_none(*pmdp))
		return migrate_vma_collect_hole(start, end, -1, walk);

	if (pmd_trans_huge(*pmdp)) {
		struct page *page;

		ptl = pmd_lock(mm, pmdp);
		if (unlikely(!pmd_trans_huge(*pmdp))) {
			spin_unlock(ptl);
			goto again;
		}

		page = pmd_page(*pmdp);
		if (is_huge_zero_page(page)) {
			spin_unlock(ptl);
			split_huge_pmd(vma, pmdp, addr);
			if (pmd_trans_unstable(pmdp))
				return migrate_vma_collect_skip(start, end,
								walk);
		} else {
			int ret;

			get_page(page);
			spin_unlock(ptl);
			if (unlikely(!trylock_page(page)))
				return migrate_vma_collect_skip(start, end,
								walk);
			ret = split_huge_page(page);
			unlock_page(page);
			put_page(page);
			if (ret)
				return migrate_vma_collect_skip(start, end,
								walk);
			if (pmd_none(*pmdp))
				return migrate_vma_collect_hole(start, end, -1,
								walk);
		}
	}

	if (unlikely(pmd_bad(*pmdp)))
		return migrate_vma_collect_skip(start, end, walk);

	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
	arch_enter_lazy_mmu_mode();

	for (; addr < end; addr += PAGE_SIZE, ptep++) {
		unsigned long mpfn = 0, pfn;
		struct page *page;
		swp_entry_t entry;
		pte_t pte;

		pte = *ptep;

		if (pte_none(pte)) {
			if (vma_is_anonymous(vma)) {
				mpfn = MIGRATE_PFN_MIGRATE;
				migrate->cpages++;
			}
			goto next;
		}

		if (!pte_present(pte)) {
			/*
			 * Only care about unaddressable device page special
			 * page table entry. Other special swap entries are not
			 * migratable, and we ignore regular swapped page.
			 */
			entry = pte_to_swp_entry(pte);
			if (!is_device_private_entry(entry))
				goto next;

			page = pfn_swap_entry_to_page(entry);
			if (!(migrate->flags &
				MIGRATE_VMA_SELECT_DEVICE_PRIVATE) ||
			    page->pgmap->owner != migrate->pgmap_owner)
				goto next;

			mpfn = migrate_pfn(page_to_pfn(page)) |
					MIGRATE_PFN_MIGRATE;
			if (is_writable_device_private_entry(entry))
				mpfn |= MIGRATE_PFN_WRITE;
		} else {
			if (!(migrate->flags & MIGRATE_VMA_SELECT_SYSTEM))
				goto next;
			pfn = pte_pfn(pte);
			if (is_zero_pfn(pfn)) {
				mpfn = MIGRATE_PFN_MIGRATE;
				migrate->cpages++;
				goto next;
			}
			page = vm_normal_page(migrate->vma, addr, pte);
			mpfn = migrate_pfn(pfn) | MIGRATE_PFN_MIGRATE;
			mpfn |= pte_write(pte) ? MIGRATE_PFN_WRITE : 0;
		}

		/* FIXME support THP */
		if (!page || !page->mapping || PageTransCompound(page)) {
			mpfn = 0;
			goto next;
		}

		/*
		 * By getting a reference on the page we pin it and that blocks
		 * any kind of migration. Side effect is that it "freezes" the
		 * pte.
		 *
		 * We drop this reference after isolating the page from the lru
		 * for non device page (device page are not on the lru and thus
		 * can't be dropped from it).
		 */
		get_page(page);
		migrate->cpages++;

		/*
		 * Optimize for the common case where page is only mapped once
		 * in one process. If we can lock the page, then we can safely
		 * set up a special migration page table entry now.
		 */
		if (trylock_page(page)) {
			pte_t swp_pte;

			mpfn |= MIGRATE_PFN_LOCKED;
			ptep_get_and_clear(mm, addr, ptep);

			/* Setup special migration page table entry */
			if (mpfn & MIGRATE_PFN_WRITE)
				entry = make_writable_migration_entry(
							page_to_pfn(page));
			else
				entry = make_readable_migration_entry(
							page_to_pfn(page));
			swp_pte = swp_entry_to_pte(entry);
			if (pte_present(pte)) {
				if (pte_soft_dirty(pte))
					swp_pte = pte_swp_mksoft_dirty(swp_pte);
				if (pte_uffd_wp(pte))
					swp_pte = pte_swp_mkuffd_wp(swp_pte);
			} else {
				if (pte_swp_soft_dirty(pte))
					swp_pte = pte_swp_mksoft_dirty(swp_pte);
				if (pte_swp_uffd_wp(pte))
					swp_pte = pte_swp_mkuffd_wp(swp_pte);
			}
			set_pte_at(mm, addr, ptep, swp_pte);

			/*
			 * This is like regular unmap: we remove the rmap and
			 * drop page refcount. Page won't be freed, as we took
			 * a reference just above.
			 */
			page_remove_rmap(page, false);
			put_page(page);

			if (pte_present(pte))
				unmapped++;
		}

next:
		migrate->dst[migrate->npages] = 0;
		migrate->src[migrate->npages++] = mpfn;
	}
	arch_leave_lazy_mmu_mode();
	pte_unmap_unlock(ptep - 1, ptl);

	/* Only flush the TLB if we actually modified any entries */
	if (unmapped)
		flush_tlb_range(walk->vma, start, end);

	return 0;
}

static const struct mm_walk_ops migrate_vma_walk_ops = {
	.pmd_entry		= migrate_vma_collect_pmd,
	.pte_hole		= migrate_vma_collect_hole,
};

/*
 * migrate_vma_collect() - collect pages over a range of virtual addresses
 * @migrate: migrate struct containing all migration information
 *
 * This will walk the CPU page table. For each virtual address backed by a
 * valid page, it updates the src array and takes a reference on the page, in
 * order to pin the page until we lock it and unmap it.
 */
static void migrate_vma_collect(struct migrate_vma *migrate)
{
	struct mmu_notifier_range range;

	/*
	 * Note that the pgmap_owner is passed to the mmu notifier callback so
	 * that the registered device driver can skip invalidating device
	 * private page mappings that won't be migrated.
	 */
	mmu_notifier_range_init_owner(&range, MMU_NOTIFY_MIGRATE, 0,
		migrate->vma, migrate->vma->vm_mm, migrate->start, migrate->end,
		migrate->pgmap_owner);
	mmu_notifier_invalidate_range_start(&range);

	walk_page_range(migrate->vma->vm_mm, migrate->start, migrate->end,
			&migrate_vma_walk_ops, migrate);

	mmu_notifier_invalidate_range_end(&range);
	migrate->end = migrate->start + (migrate->npages << PAGE_SHIFT);
}

/*
 * migrate_vma_check_page() - check if page is pinned or not
 * @page: struct page to check
 *
 * Pinned pages cannot be migrated. This is the same test as in
 * folio_migrate_mapping(), except that here we allow migration of a
 * ZONE_DEVICE page.
 */
static bool migrate_vma_check_page(struct page *page)
{
	/*
	 * One extra ref because caller holds an extra reference, either from
	 * isolate_lru_page() for a regular page, or migrate_vma_collect() for
	 * a device page.
	 */
	int extra = 1;

	/*
	 * FIXME support THP (transparent huge page), it is bit more complex to
	 * check them than regular pages, because they can be mapped with a pmd
	 * or with a pte (split pte mapping).
	 */
	if (PageCompound(page))
		return false;

	/* Page from ZONE_DEVICE have one extra reference */
	if (is_zone_device_page(page)) {
		/*
		 * Private page can never be pin as they have no valid pte and
		 * GUP will fail for those. Yet if there is a pending migration
		 * a thread might try to wait on the pte migration entry and
		 * will bump the page reference count. Sadly there is no way to
		 * differentiate a regular pin from migration wait. Hence to
		 * avoid 2 racing thread trying to migrate back to CPU to enter
		 * infinite loop (one stopping migration because the other is
		 * waiting on pte migration entry). We always return true here.
		 *
		 * FIXME proper solution is to rework migration_entry_wait() so
		 * it does not need to take a reference on page.
		 */
		return is_device_private_page(page);
	}

	/* For file back page */
	if (page_mapping(page))
		extra += 1 + page_has_private(page);

	if ((page_count(page) - extra) > page_mapcount(page))
		return false;

	return true;
}

/*
 * migrate_vma_prepare() - lock pages and isolate them from the lru
 * @migrate: migrate struct containing all migration information
 *
 * This locks pages that have been collected by migrate_vma_collect(). Once each
 * page is locked it is isolated from the lru (for non-device pages). Finally,
 * the ref taken by migrate_vma_collect() is dropped, as locked pages cannot be
 * migrated by concurrent kernel threads.
 */
static void migrate_vma_prepare(struct migrate_vma *migrate)
{
	const unsigned long npages = migrate->npages;
	const unsigned long start = migrate->start;
	unsigned long addr, i, restore = 0;
	bool allow_drain = true;

	lru_add_drain();

	for (i = 0; (i < npages) && migrate->cpages; i++) {
		struct page *page = migrate_pfn_to_page(migrate->src[i]);
		bool remap = true;

		if (!page)
			continue;

		if (!(migrate->src[i] & MIGRATE_PFN_LOCKED)) {
			/*
			 * Because we are migrating several pages there can be
			 * a deadlock between 2 concurrent migration where each
			 * are waiting on each other page lock.
			 *
			 * Make migrate_vma() a best effort thing and backoff
			 * for any page we can not lock right away.
			 */
			if (!trylock_page(page)) {
				migrate->src[i] = 0;
				migrate->cpages--;
				put_page(page);
				continue;
			}
			remap = false;
			migrate->src[i] |= MIGRATE_PFN_LOCKED;
		}

		/* ZONE_DEVICE pages are not on LRU */
		if (!is_zone_device_page(page)) {
			if (!PageLRU(page) && allow_drain) {
				/* Drain CPU's pagevec */
				lru_add_drain_all();
				allow_drain = false;
			}

			if (isolate_lru_page(page)) {
				if (remap) {
					migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
					migrate->cpages--;
					restore++;
				} else {
					migrate->src[i] = 0;
					unlock_page(page);
					migrate->cpages--;
					put_page(page);
				}
				continue;
			}

			/* Drop the reference we took in collect */
			put_page(page);
		}

		if (!migrate_vma_check_page(page)) {
			if (remap) {
				migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
				migrate->cpages--;
				restore++;

				if (!is_zone_device_page(page)) {
					get_page(page);
					putback_lru_page(page);
				}
			} else {
				migrate->src[i] = 0;
				unlock_page(page);
				migrate->cpages--;

				if (!is_zone_device_page(page))
					putback_lru_page(page);
				else
					put_page(page);
			}
		}
	}

	for (i = 0, addr = start; i < npages && restore; i++, addr += PAGE_SIZE) {
		struct page *page = migrate_pfn_to_page(migrate->src[i]);

		if (!page || (migrate->src[i] & MIGRATE_PFN_MIGRATE))
			continue;

		remove_migration_pte(page, migrate->vma, addr, page);

		migrate->src[i] = 0;
		unlock_page(page);
		put_page(page);
		restore--;
	}
}

/*
 * migrate_vma_unmap() - replace page mapping with special migration pte entry
 * @migrate: migrate struct containing all migration information
 *
 * Replace page mapping (CPU page table pte) with a special migration pte entry
 * and check again if it has been pinned. Pinned pages are restored because we
 * cannot migrate them.
 *
 * This is the last step before we call the device driver callback to allocate
 * destination memory and copy contents of original page over to new page.
 */
static void migrate_vma_unmap(struct migrate_vma *migrate)
{
	const unsigned long npages = migrate->npages;
	const unsigned long start = migrate->start;
	unsigned long addr, i, restore = 0;

	for (i = 0; i < npages; i++) {
		struct page *page = migrate_pfn_to_page(migrate->src[i]);

		if (!page || !(migrate->src[i] & MIGRATE_PFN_MIGRATE))
			continue;

		if (page_mapped(page)) {
			try_to_migrate(page, 0);
			if (page_mapped(page))
				goto restore;
		}

		if (migrate_vma_check_page(page))
			continue;

restore:
		migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
		migrate->cpages--;
		restore++;
	}

	for (addr = start, i = 0; i < npages && restore; addr += PAGE_SIZE, i++) {
		struct page *page = migrate_pfn_to_page(migrate->src[i]);

		if (!page || (migrate->src[i] & MIGRATE_PFN_MIGRATE))
			continue;

		remove_migration_ptes(page, page, false);

		migrate->src[i] = 0;
		unlock_page(page);
		restore--;

		if (is_zone_device_page(page))
			put_page(page);
		else
			putback_lru_page(page);
	}
}

/**
 * migrate_vma_setup() - prepare to migrate a range of memory
 * @args: contains the vma, start, and pfns arrays for the migration
 *
 * Returns: negative errno on failures, 0 when 0 or more pages were migrated
 * without an error.
 *
 * Prepare to migrate a range of memory virtual address range by collecting all
 * the pages backing each virtual address in the range, saving them inside the
 * src array.  Then lock those pages and unmap them. Once the pages are locked
 * and unmapped, check whether each page is pinned or not.  Pages that aren't
 * pinned have the MIGRATE_PFN_MIGRATE flag set (by this function) in the
 * corresponding src array entry.  Then restores any pages that are pinned, by
 * remapping and unlocking those pages.
 *
 * The caller should then allocate destination memory and copy source memory to
 * it for all those entries (ie with MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE
 * flag set).  Once these are allocated and copied, the caller must update each
 * corresponding entry in the dst array with the pfn value of the destination
 * page and with the MIGRATE_PFN_VALID and MIGRATE_PFN_LOCKED flags set
 * (destination pages must have their struct pages locked, via lock_page()).
 *
 * Note that the caller does not have to migrate all the pages that are marked
 * with MIGRATE_PFN_MIGRATE flag in src array unless this is a migration from
 * device memory to system memory.  If the caller cannot migrate a device page
 * back to system memory, then it must return VM_FAULT_SIGBUS, which has severe
 * consequences for the userspace process, so it must be avoided if at all
 * possible.
 *
 * For empty entries inside CPU page table (pte_none() or pmd_none() is true) we
 * do set MIGRATE_PFN_MIGRATE flag inside the corresponding source array thus
 * allowing the caller to allocate device memory for those unbacked virtual
 * addresses.  For this the caller simply has to allocate device memory and
 * properly set the destination entry like for regular migration.  Note that
 * this can still fail, and thus inside the device driver you must check if the
 * migration was successful for those entries after calling migrate_vma_pages(),
 * just like for regular migration.
 *
 * After that, the callers must call migrate_vma_pages() to go over each entry
 * in the src array that has the MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE flag
 * set. If the corresponding entry in dst array has MIGRATE_PFN_VALID flag set,
 * then migrate_vma_pages() to migrate struct page information from the source
 * struct page to the destination struct page.  If it fails to migrate the
 * struct page information, then it clears the MIGRATE_PFN_MIGRATE flag in the
 * src array.
 *
 * At this point all successfully migrated pages have an entry in the src
 * array with MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE flag set and the dst
 * array entry with MIGRATE_PFN_VALID flag set.
 *
 * Once migrate_vma_pages() returns the caller may inspect which pages were
 * successfully migrated, and which were not.  Successfully migrated pages will
 * have the MIGRATE_PFN_MIGRATE flag set for their src array entry.
 *
 * It is safe to update device page table after migrate_vma_pages() because
 * both destination and source page are still locked, and the mmap_lock is held
 * in read mode (hence no one can unmap the range being migrated).
 *
 * Once the caller is done cleaning up things and updating its page table (if it
 * chose to do so, this is not an obligation) it finally calls
 * migrate_vma_finalize() to update the CPU page table to point to new pages
 * for successfully migrated pages or otherwise restore the CPU page table to
 * point to the original source pages.
 */
int migrate_vma_setup(struct migrate_vma *args)
{
	long nr_pages = (args->end - args->start) >> PAGE_SHIFT;

	args->start &= PAGE_MASK;
	args->end &= PAGE_MASK;
	if (!args->vma || is_vm_hugetlb_page(args->vma) ||
	    (args->vma->vm_flags & VM_SPECIAL) || vma_is_dax(args->vma))
		return -EINVAL;
	if (nr_pages <= 0)
		return -EINVAL;
	if (args->start < args->vma->vm_start ||
	    args->start >= args->vma->vm_end)
		return -EINVAL;
	if (args->end <= args->vma->vm_start || args->end > args->vma->vm_end)
		return -EINVAL;
	if (!args->src || !args->dst)
		return -EINVAL;

	memset(args->src, 0, sizeof(*args->src) * nr_pages);
	args->cpages = 0;
	args->npages = 0;

	migrate_vma_collect(args);

	if (args->cpages)
		migrate_vma_prepare(args);
	if (args->cpages)
		migrate_vma_unmap(args);

	/*
	 * At this point pages are locked and unmapped, and thus they have
	 * stable content and can safely be copied to destination memory that
	 * is allocated by the drivers.
	 */
	return 0;

}
EXPORT_SYMBOL(migrate_vma_setup);

/*
 * This code closely matches the code in:
 *   __handle_mm_fault()
 *     handle_pte_fault()
 *       do_anonymous_page()
 * to map in an anonymous zero page but the struct page will be a ZONE_DEVICE
 * private page.
 */
static void migrate_vma_insert_page(struct migrate_vma *migrate,
				    unsigned long addr,
				    struct page *page,
				    unsigned long *src)
{
	struct vm_area_struct *vma = migrate->vma;
	struct mm_struct *mm = vma->vm_mm;
	bool flush = false;
	spinlock_t *ptl;
	pte_t entry;
	pgd_t *pgdp;
	p4d_t *p4dp;
	pud_t *pudp;
	pmd_t *pmdp;
	pte_t *ptep;

	/* Only allow populating anonymous memory */
	if (!vma_is_anonymous(vma))
		goto abort;

	pgdp = pgd_offset(mm, addr);
	p4dp = p4d_alloc(mm, pgdp, addr);
	if (!p4dp)
		goto abort;
	pudp = pud_alloc(mm, p4dp, addr);
	if (!pudp)
		goto abort;
	pmdp = pmd_alloc(mm, pudp, addr);
	if (!pmdp)
		goto abort;

	if (pmd_trans_huge(*pmdp) || pmd_devmap(*pmdp))
		goto abort;

	/*
	 * Use pte_alloc() instead of pte_alloc_map().  We can't run
	 * pte_offset_map() on pmds where a huge pmd might be created
	 * from a different thread.
	 *
	 * pte_alloc_map() is safe to use under mmap_write_lock(mm) or when
	 * parallel threads are excluded by other means.
	 *
	 * Here we only have mmap_read_lock(mm).
	 */
	if (pte_alloc(mm, pmdp))
		goto abort;

	/* See the comment in pte_alloc_one_map() */
	if (unlikely(pmd_trans_unstable(pmdp)))
		goto abort;

	if (unlikely(anon_vma_prepare(vma)))
		goto abort;
	if (mem_cgroup_charge(page_folio(page), vma->vm_mm, GFP_KERNEL))
		goto abort;

	/*
	 * The memory barrier inside __SetPageUptodate makes sure that
	 * preceding stores to the page contents become visible before
	 * the set_pte_at() write.
	 */
	__SetPageUptodate(page);

	if (is_zone_device_page(page)) {
		if (is_device_private_page(page)) {
			swp_entry_t swp_entry;

			if (vma->vm_flags & VM_WRITE)
				swp_entry = make_writable_device_private_entry(
							page_to_pfn(page));
			else
				swp_entry = make_readable_device_private_entry(
							page_to_pfn(page));
			entry = swp_entry_to_pte(swp_entry);
		} else {
			/*
			 * For now we only support migrating to un-addressable
			 * device memory.
			 */
			pr_warn_once("Unsupported ZONE_DEVICE page type.\n");
			goto abort;
		}
	} else {
		entry = mk_pte(page, vma->vm_page_prot);
		if (vma->vm_flags & VM_WRITE)
			entry = pte_mkwrite(pte_mkdirty(entry));
	}

	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);

	if (check_stable_address_space(mm))
		goto unlock_abort;

	if (pte_present(*ptep)) {
		unsigned long pfn = pte_pfn(*ptep);

		if (!is_zero_pfn(pfn))
			goto unlock_abort;
		flush = true;
	} else if (!pte_none(*ptep))
		goto unlock_abort;

	/*
	 * Check for userfaultfd but do not deliver the fault. Instead,
	 * just back off.
	 */
	if (userfaultfd_missing(vma))
		goto unlock_abort;

	inc_mm_counter(mm, MM_ANONPAGES);
	page_add_new_anon_rmap(page, vma, addr, false);
	if (!is_zone_device_page(page))
		lru_cache_add_inactive_or_unevictable(page, vma);
	get_page(page);

	if (flush) {
		flush_cache_page(vma, addr, pte_pfn(*ptep));
		ptep_clear_flush_notify(vma, addr, ptep);
		set_pte_at_notify(mm, addr, ptep, entry);
		update_mmu_cache(vma, addr, ptep);
	} else {
		/* No need to invalidate - it was non-present before */
		set_pte_at(mm, addr, ptep, entry);
		update_mmu_cache(vma, addr, ptep);
	}

	pte_unmap_unlock(ptep, ptl);
	*src = MIGRATE_PFN_MIGRATE;
	return;

unlock_abort:
	pte_unmap_unlock(ptep, ptl);
abort:
	*src &= ~MIGRATE_PFN_MIGRATE;
}

/**
 * migrate_vma_pages() - migrate meta-data from src page to dst page
 * @migrate: migrate struct containing all migration information
 *
 * This migrates struct page meta-data from source struct page to destination
 * struct page. This effectively finishes the migration from source page to the
 * destination page.
 */
void migrate_vma_pages(struct migrate_vma *migrate)
{
	const unsigned long npages = migrate->npages;
	const unsigned long start = migrate->start;
	struct mmu_notifier_range range;
	unsigned long addr, i;
	bool notified = false;

	for (i = 0, addr = start; i < npages; addr += PAGE_SIZE, i++) {
		struct page *newpage = migrate_pfn_to_page(migrate->dst[i]);
		struct page *page = migrate_pfn_to_page(migrate->src[i]);
		struct address_space *mapping;
		int r;

		if (!newpage) {
			migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
			continue;
		}

		if (!page) {
			if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE))
				continue;
			if (!notified) {
				notified = true;

				mmu_notifier_range_init_owner(&range,
					MMU_NOTIFY_MIGRATE, 0, migrate->vma,
					migrate->vma->vm_mm, addr, migrate->end,
					migrate->pgmap_owner);
				mmu_notifier_invalidate_range_start(&range);
			}
			migrate_vma_insert_page(migrate, addr, newpage,
						&migrate->src[i]);
			continue;
		}

		mapping = page_mapping(page);

		if (is_zone_device_page(newpage)) {
			if (is_device_private_page(newpage)) {
				/*
				 * For now only support private anonymous when
				 * migrating to un-addressable device memory.
				 */
				if (mapping) {
					migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
					continue;
				}
			} else {
				/*
				 * Other types of ZONE_DEVICE page are not
				 * supported.
				 */
				migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
				continue;
			}
		}

		r = migrate_page(mapping, newpage, page, MIGRATE_SYNC_NO_COPY);
		if (r != MIGRATEPAGE_SUCCESS)
			migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
	}

	/*
	 * No need to double call mmu_notifier->invalidate_range() callback as
	 * the above ptep_clear_flush_notify() inside migrate_vma_insert_page()
	 * did already call it.
	 */
	if (notified)
		mmu_notifier_invalidate_range_only_end(&range);
}
EXPORT_SYMBOL(migrate_vma_pages);

/**
 * migrate_vma_finalize() - restore CPU page table entry
 * @migrate: migrate struct containing all migration information
 *
 * This replaces the special migration pte entry with either a mapping to the
 * new page if migration was successful for that page, or to the original page
 * otherwise.
 *
 * This also unlocks the pages and puts them back on the lru, or drops the extra
 * refcount, for device pages.
 */
void migrate_vma_finalize(struct migrate_vma *migrate)
{
	const unsigned long npages = migrate->npages;
	unsigned long i;

	for (i = 0; i < npages; i++) {
		struct page *newpage = migrate_pfn_to_page(migrate->dst[i]);
		struct page *page = migrate_pfn_to_page(migrate->src[i]);

		if (!page) {
			if (newpage) {
				unlock_page(newpage);
				put_page(newpage);
			}
			continue;
		}

		if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE) || !newpage) {
			if (newpage) {
				unlock_page(newpage);
				put_page(newpage);
			}
			newpage = page;
		}

		remove_migration_ptes(page, newpage, false);
		unlock_page(page);

		if (is_zone_device_page(page))
			put_page(page);
		else
			putback_lru_page(page);

		if (newpage != page) {
			unlock_page(newpage);
			if (is_zone_device_page(newpage))
				put_page(newpage);
			else
				putback_lru_page(newpage);
		}
	}
}
EXPORT_SYMBOL(migrate_vma_finalize);
#endif /* CONFIG_DEVICE_PRIVATE */

#if defined(CONFIG_HOTPLUG_CPU)
/* Disable reclaim-based migration. */
static void __disable_all_migrate_targets(void)
{
	int node;

	for_each_online_node(node)
		node_demotion[node] = NUMA_NO_NODE;
}

static void disable_all_migrate_targets(void)
{
	__disable_all_migrate_targets();

	/*
	 * Ensure that the "disable" is visible across the system.
	 * Readers will see either a combination of before+disable
	 * state or disable+after.  They will never see before and
	 * after state together.
	 *
	 * The before+after state together might have cycles and
	 * could cause readers to do things like loop until this
	 * function finishes.  This ensures they can only see a
	 * single "bad" read and would, for instance, only loop
	 * once.
	 */
	synchronize_rcu();
}

/*
 * Find an automatic demotion target for 'node'.
 * Failing here is OK.  It might just indicate
 * being at the end of a chain.
 */
static int establish_migrate_target(int node, nodemask_t *used)
{
	int migration_target;

	/*
	 * Can not set a migration target on a
	 * node with it already set.
	 *
	 * No need for READ_ONCE() here since this
	 * in the write path for node_demotion[].
	 * This should be the only thread writing.
	 */
	if (node_demotion[node] != NUMA_NO_NODE)
		return NUMA_NO_NODE;

	migration_target = find_next_best_node(node, used);
	if (migration_target == NUMA_NO_NODE)
		return NUMA_NO_NODE;

	node_demotion[node] = migration_target;

	return migration_target;
}

/*
 * When memory fills up on a node, memory contents can be
 * automatically migrated to another node instead of
 * discarded at reclaim.
 *
 * Establish a "migration path" which will start at nodes
 * with CPUs and will follow the priorities used to build the
 * page allocator zonelists.
 *
 * The difference here is that cycles must be avoided.  If
 * node0 migrates to node1, then neither node1, nor anything
 * node1 migrates to can migrate to node0.
 *
 * This function can run simultaneously with readers of
 * node_demotion[].  However, it can not run simultaneously
 * with itself.  Exclusion is provided by memory hotplug events
 * being single-threaded.
 */
static void __set_migration_target_nodes(void)
{
	nodemask_t next_pass	= NODE_MASK_NONE;
	nodemask_t this_pass	= NODE_MASK_NONE;
	nodemask_t used_targets = NODE_MASK_NONE;
	int node;

	/*
	 * Avoid any oddities like cycles that could occur
	 * from changes in the topology.  This will leave
	 * a momentary gap when migration is disabled.
	 */
	disable_all_migrate_targets();

	/*
	 * Allocations go close to CPUs, first.  Assume that
	 * the migration path starts at the nodes with CPUs.
	 */
	next_pass = node_states[N_CPU];
again:
	this_pass = next_pass;
	next_pass = NODE_MASK_NONE;
	/*
	 * To avoid cycles in the migration "graph", ensure
	 * that migration sources are not future targets by
	 * setting them in 'used_targets'.  Do this only
	 * once per pass so that multiple source nodes can
	 * share a target node.
	 *
	 * 'used_targets' will become unavailable in future
	 * passes.  This limits some opportunities for
	 * multiple source nodes to share a destination.
	 */
	nodes_or(used_targets, used_targets, this_pass);
	for_each_node_mask(node, this_pass) {
		int target_node = establish_migrate_target(node, &used_targets);

		if (target_node == NUMA_NO_NODE)
			continue;

		/*
		 * Visit targets from this pass in the next pass.
		 * Eventually, every node will have been part of
		 * a pass, and will become set in 'used_targets'.
		 */
		node_set(target_node, next_pass);
	}
	/*
	 * 'next_pass' contains nodes which became migration
	 * targets in this pass.  Make additional passes until
	 * no more migrations targets are available.
	 */
	if (!nodes_empty(next_pass))
		goto again;
}

/*
 * For callers that do not hold get_online_mems() already.
 */
static void set_migration_target_nodes(void)
{
	get_online_mems();
	__set_migration_target_nodes();
	put_online_mems();
}

/*
 * This leaves migrate-on-reclaim transiently disabled between
 * the MEM_GOING_OFFLINE and MEM_OFFLINE events.  This runs
 * whether reclaim-based migration is enabled or not, which
 * ensures that the user can turn reclaim-based migration at
 * any time without needing to recalculate migration targets.
 *
 * These callbacks already hold get_online_mems().  That is why
 * __set_migration_target_nodes() can be used as opposed to
 * set_migration_target_nodes().
 */
static int __meminit migrate_on_reclaim_callback(struct notifier_block *self,
						 unsigned long action, void *_arg)
{
	struct memory_notify *arg = _arg;

	/*
	 * Only update the node migration order when a node is
	 * changing status, like online->offline.  This avoids
	 * the overhead of synchronize_rcu() in most cases.
	 */
	if (arg->status_change_nid < 0)
		return notifier_from_errno(0);

	switch (action) {
	case MEM_GOING_OFFLINE:
		/*
		 * Make sure there are not transient states where
		 * an offline node is a migration target.  This
		 * will leave migration disabled until the offline
		 * completes and the MEM_OFFLINE case below runs.
		 */
		disable_all_migrate_targets();
		break;
	case MEM_OFFLINE:
	case MEM_ONLINE:
		/*
		 * Recalculate the target nodes once the node
		 * reaches its final state (online or offline).
		 */
		__set_migration_target_nodes();
		break;
	case MEM_CANCEL_OFFLINE:
		/*
		 * MEM_GOING_OFFLINE disabled all the migration
		 * targets.  Reenable them.
		 */
		__set_migration_target_nodes();
		break;
	case MEM_GOING_ONLINE:
	case MEM_CANCEL_ONLINE:
		break;
	}

	return notifier_from_errno(0);
}

/*
 * React to hotplug events that might affect the migration targets
 * like events that online or offline NUMA nodes.
 *
 * The ordering is also currently dependent on which nodes have
 * CPUs.  That means we need CPU on/offline notification too.
 */
static int migration_online_cpu(unsigned int cpu)
{
	set_migration_target_nodes();
	return 0;
}

static int migration_offline_cpu(unsigned int cpu)
{
	set_migration_target_nodes();
	return 0;
}

static int __init migrate_on_reclaim_init(void)
{
	int ret;

	ret = cpuhp_setup_state_nocalls(CPUHP_MM_DEMOTION_DEAD, "mm/demotion:offline",
					NULL, migration_offline_cpu);
	/*
	 * In the unlikely case that this fails, the automatic
	 * migration targets may become suboptimal for nodes
	 * where N_CPU changes.  With such a small impact in a
	 * rare case, do not bother trying to do anything special.
	 */
	WARN_ON(ret < 0);
	ret = cpuhp_setup_state(CPUHP_AP_MM_DEMOTION_ONLINE, "mm/demotion:online",
				migration_online_cpu, NULL);
	WARN_ON(ret < 0);

	hotplug_memory_notifier(migrate_on_reclaim_callback, 100);
	return 0;
}
late_initcall(migrate_on_reclaim_init);
#endif /* CONFIG_HOTPLUG_CPU */