summaryrefslogtreecommitdiffstats
path: root/mm/compaction.c
blob: e731d45befc780865b5ecb6681fe00de31099e7a (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
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
// SPDX-License-Identifier: GPL-2.0
/*
 * linux/mm/compaction.c
 *
 * Memory compaction for the reduction of external fragmentation. Note that
 * this heavily depends upon page migration to do all the real heavy
 * lifting
 *
 * Copyright IBM Corp. 2007-2010 Mel Gorman <mel@csn.ul.ie>
 */
#include <linux/cpu.h>
#include <linux/swap.h>
#include <linux/migrate.h>
#include <linux/compaction.h>
#include <linux/mm_inline.h>
#include <linux/sched/signal.h>
#include <linux/backing-dev.h>
#include <linux/sysctl.h>
#include <linux/sysfs.h>
#include <linux/page-isolation.h>
#include <linux/kasan.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/page_owner.h>
#include <linux/psi.h>
#include "internal.h"

#ifdef CONFIG_COMPACTION
/*
 * Fragmentation score check interval for proactive compaction purposes.
 */
#define HPAGE_FRAG_CHECK_INTERVAL_MSEC	(500)

static inline void count_compact_event(enum vm_event_item item)
{
	count_vm_event(item);
}

static inline void count_compact_events(enum vm_event_item item, long delta)
{
	count_vm_events(item, delta);
}

/*
 * order == -1 is expected when compacting proactively via
 * 1. /proc/sys/vm/compact_memory
 * 2. /sys/devices/system/node/nodex/compact
 * 3. /proc/sys/vm/compaction_proactiveness
 */
static inline bool is_via_compact_memory(int order)
{
	return order == -1;
}

#else
#define count_compact_event(item) do { } while (0)
#define count_compact_events(item, delta) do { } while (0)
static inline bool is_via_compact_memory(int order) { return false; }
#endif

#if defined CONFIG_COMPACTION || defined CONFIG_CMA

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

#define block_start_pfn(pfn, order)	round_down(pfn, 1UL << (order))
#define block_end_pfn(pfn, order)	ALIGN((pfn) + 1, 1UL << (order))

/*
 * Page order with-respect-to which proactive compaction
 * calculates external fragmentation, which is used as
 * the "fragmentation score" of a node/zone.
 */
#if defined CONFIG_TRANSPARENT_HUGEPAGE
#define COMPACTION_HPAGE_ORDER	HPAGE_PMD_ORDER
#elif defined CONFIG_HUGETLBFS
#define COMPACTION_HPAGE_ORDER	HUGETLB_PAGE_ORDER
#else
#define COMPACTION_HPAGE_ORDER	(PMD_SHIFT - PAGE_SHIFT)
#endif

static void split_map_pages(struct list_head *freepages)
{
	unsigned int i, order;
	struct page *page, *next;
	LIST_HEAD(tmp_list);

	for (order = 0; order < NR_PAGE_ORDERS; order++) {
		list_for_each_entry_safe(page, next, &freepages[order], lru) {
			unsigned int nr_pages;

			list_del(&page->lru);

			nr_pages = 1 << order;

			post_alloc_hook(page, order, __GFP_MOVABLE);
			if (order)
				split_page(page, order);

			for (i = 0; i < nr_pages; i++) {
				list_add(&page->lru, &tmp_list);
				page++;
			}
		}
		list_splice_init(&tmp_list, &freepages[0]);
	}
}

static unsigned long release_free_list(struct list_head *freepages)
{
	int order;
	unsigned long high_pfn = 0;

	for (order = 0; order < NR_PAGE_ORDERS; order++) {
		struct page *page, *next;

		list_for_each_entry_safe(page, next, &freepages[order], lru) {
			unsigned long pfn = page_to_pfn(page);

			list_del(&page->lru);
			/*
			 * Convert free pages into post allocation pages, so
			 * that we can free them via __free_page.
			 */
			post_alloc_hook(page, order, __GFP_MOVABLE);
			__free_pages(page, order);
			if (pfn > high_pfn)
				high_pfn = pfn;
		}
	}
	return high_pfn;
}

#ifdef CONFIG_COMPACTION
bool PageMovable(struct page *page)
{
	const struct movable_operations *mops;

	VM_BUG_ON_PAGE(!PageLocked(page), page);
	if (!__PageMovable(page))
		return false;

	mops = page_movable_ops(page);
	if (mops)
		return true;

	return false;
}

void __SetPageMovable(struct page *page, const struct movable_operations *mops)
{
	VM_BUG_ON_PAGE(!PageLocked(page), page);
	VM_BUG_ON_PAGE((unsigned long)mops & PAGE_MAPPING_MOVABLE, page);
	page->mapping = (void *)((unsigned long)mops | PAGE_MAPPING_MOVABLE);
}
EXPORT_SYMBOL(__SetPageMovable);

void __ClearPageMovable(struct page *page)
{
	VM_BUG_ON_PAGE(!PageMovable(page), page);
	/*
	 * This page still has the type of a movable page, but it's
	 * actually not movable any more.
	 */
	page->mapping = (void *)PAGE_MAPPING_MOVABLE;
}
EXPORT_SYMBOL(__ClearPageMovable);

/* Do not skip compaction more than 64 times */
#define COMPACT_MAX_DEFER_SHIFT 6

/*
 * Compaction is deferred when compaction fails to result in a page
 * allocation success. 1 << compact_defer_shift, compactions are skipped up
 * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT
 */
static void defer_compaction(struct zone *zone, int order)
{
	zone->compact_considered = 0;
	zone->compact_defer_shift++;

	if (order < zone->compact_order_failed)
		zone->compact_order_failed = order;

	if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT)
		zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT;

	trace_mm_compaction_defer_compaction(zone, order);
}

/* Returns true if compaction should be skipped this time */
static bool compaction_deferred(struct zone *zone, int order)
{
	unsigned long defer_limit = 1UL << zone->compact_defer_shift;

	if (order < zone->compact_order_failed)
		return false;

	/* Avoid possible overflow */
	if (++zone->compact_considered >= defer_limit) {
		zone->compact_considered = defer_limit;
		return false;
	}

	trace_mm_compaction_deferred(zone, order);

	return true;
}

/*
 * Update defer tracking counters after successful compaction of given order,
 * which means an allocation either succeeded (alloc_success == true) or is
 * expected to succeed.
 */
void compaction_defer_reset(struct zone *zone, int order,
		bool alloc_success)
{
	if (alloc_success) {
		zone->compact_considered = 0;
		zone->compact_defer_shift = 0;
	}
	if (order >= zone->compact_order_failed)
		zone->compact_order_failed = order + 1;

	trace_mm_compaction_defer_reset(zone, order);
}

/* Returns true if restarting compaction after many failures */
static bool compaction_restarting(struct zone *zone, int order)
{
	if (order < zone->compact_order_failed)
		return false;

	return zone->compact_defer_shift == COMPACT_MAX_DEFER_SHIFT &&
		zone->compact_considered >= 1UL << zone->compact_defer_shift;
}

/* Returns true if the pageblock should be scanned for pages to isolate. */
static inline bool isolation_suitable(struct compact_control *cc,
					struct page *page)
{
	if (cc->ignore_skip_hint)
		return true;

	return !get_pageblock_skip(page);
}

static void reset_cached_positions(struct zone *zone)
{
	zone->compact_cached_migrate_pfn[0] = zone->zone_start_pfn;
	zone->compact_cached_migrate_pfn[1] = zone->zone_start_pfn;
	zone->compact_cached_free_pfn =
				pageblock_start_pfn(zone_end_pfn(zone) - 1);
}

#ifdef CONFIG_SPARSEMEM
/*
 * If the PFN falls into an offline section, return the start PFN of the
 * next online section. If the PFN falls into an online section or if
 * there is no next online section, return 0.
 */
static unsigned long skip_offline_sections(unsigned long start_pfn)
{
	unsigned long start_nr = pfn_to_section_nr(start_pfn);

	if (online_section_nr(start_nr))
		return 0;

	while (++start_nr <= __highest_present_section_nr) {
		if (online_section_nr(start_nr))
			return section_nr_to_pfn(start_nr);
	}

	return 0;
}

/*
 * If the PFN falls into an offline section, return the end PFN of the
 * next online section in reverse. If the PFN falls into an online section
 * or if there is no next online section in reverse, return 0.
 */
static unsigned long skip_offline_sections_reverse(unsigned long start_pfn)
{
	unsigned long start_nr = pfn_to_section_nr(start_pfn);

	if (!start_nr || online_section_nr(start_nr))
		return 0;

	while (start_nr-- > 0) {
		if (online_section_nr(start_nr))
			return section_nr_to_pfn(start_nr) + PAGES_PER_SECTION;
	}

	return 0;
}
#else
static unsigned long skip_offline_sections(unsigned long start_pfn)
{
	return 0;
}

static unsigned long skip_offline_sections_reverse(unsigned long start_pfn)
{
	return 0;
}
#endif

/*
 * Compound pages of >= pageblock_order should consistently be skipped until
 * released. It is always pointless to compact pages of such order (if they are
 * migratable), and the pageblocks they occupy cannot contain any free pages.
 */
static bool pageblock_skip_persistent(struct page *page)
{
	if (!PageCompound(page))
		return false;

	page = compound_head(page);

	if (compound_order(page) >= pageblock_order)
		return true;

	return false;
}

static bool
__reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source,
							bool check_target)
{
	struct page *page = pfn_to_online_page(pfn);
	struct page *block_page;
	struct page *end_page;
	unsigned long block_pfn;

	if (!page)
		return false;
	if (zone != page_zone(page))
		return false;
	if (pageblock_skip_persistent(page))
		return false;

	/*
	 * If skip is already cleared do no further checking once the
	 * restart points have been set.
	 */
	if (check_source && check_target && !get_pageblock_skip(page))
		return true;

	/*
	 * If clearing skip for the target scanner, do not select a
	 * non-movable pageblock as the starting point.
	 */
	if (!check_source && check_target &&
	    get_pageblock_migratetype(page) != MIGRATE_MOVABLE)
		return false;

	/* Ensure the start of the pageblock or zone is online and valid */
	block_pfn = pageblock_start_pfn(pfn);
	block_pfn = max(block_pfn, zone->zone_start_pfn);
	block_page = pfn_to_online_page(block_pfn);
	if (block_page) {
		page = block_page;
		pfn = block_pfn;
	}

	/* Ensure the end of the pageblock or zone is online and valid */
	block_pfn = pageblock_end_pfn(pfn) - 1;
	block_pfn = min(block_pfn, zone_end_pfn(zone) - 1);
	end_page = pfn_to_online_page(block_pfn);
	if (!end_page)
		return false;

	/*
	 * Only clear the hint if a sample indicates there is either a
	 * free page or an LRU page in the block. One or other condition
	 * is necessary for the block to be a migration source/target.
	 */
	do {
		if (check_source && PageLRU(page)) {
			clear_pageblock_skip(page);
			return true;
		}

		if (check_target && PageBuddy(page)) {
			clear_pageblock_skip(page);
			return true;
		}

		page += (1 << PAGE_ALLOC_COSTLY_ORDER);
	} while (page <= end_page);

	return false;
}

/*
 * This function is called to clear all cached information on pageblocks that
 * should be skipped for page isolation when the migrate and free page scanner
 * meet.
 */
static void __reset_isolation_suitable(struct zone *zone)
{
	unsigned long migrate_pfn = zone->zone_start_pfn;
	unsigned long free_pfn = zone_end_pfn(zone) - 1;
	unsigned long reset_migrate = free_pfn;
	unsigned long reset_free = migrate_pfn;
	bool source_set = false;
	bool free_set = false;

	/* Only flush if a full compaction finished recently */
	if (!zone->compact_blockskip_flush)
		return;

	zone->compact_blockskip_flush = false;

	/*
	 * Walk the zone and update pageblock skip information. Source looks
	 * for PageLRU while target looks for PageBuddy. When the scanner
	 * is found, both PageBuddy and PageLRU are checked as the pageblock
	 * is suitable as both source and target.
	 */
	for (; migrate_pfn < free_pfn; migrate_pfn += pageblock_nr_pages,
					free_pfn -= pageblock_nr_pages) {
		cond_resched();

		/* Update the migrate PFN */
		if (__reset_isolation_pfn(zone, migrate_pfn, true, source_set) &&
		    migrate_pfn < reset_migrate) {
			source_set = true;
			reset_migrate = migrate_pfn;
			zone->compact_init_migrate_pfn = reset_migrate;
			zone->compact_cached_migrate_pfn[0] = reset_migrate;
			zone->compact_cached_migrate_pfn[1] = reset_migrate;
		}

		/* Update the free PFN */
		if (__reset_isolation_pfn(zone, free_pfn, free_set, true) &&
		    free_pfn > reset_free) {
			free_set = true;
			reset_free = free_pfn;
			zone->compact_init_free_pfn = reset_free;
			zone->compact_cached_free_pfn = reset_free;
		}
	}

	/* Leave no distance if no suitable block was reset */
	if (reset_migrate >= reset_free) {
		zone->compact_cached_migrate_pfn[0] = migrate_pfn;
		zone->compact_cached_migrate_pfn[1] = migrate_pfn;
		zone->compact_cached_free_pfn = free_pfn;
	}
}

void reset_isolation_suitable(pg_data_t *pgdat)
{
	int zoneid;

	for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
		struct zone *zone = &pgdat->node_zones[zoneid];
		if (!populated_zone(zone))
			continue;

		__reset_isolation_suitable(zone);
	}
}

/*
 * Sets the pageblock skip bit if it was clear. Note that this is a hint as
 * locks are not required for read/writers. Returns true if it was already set.
 */
static bool test_and_set_skip(struct compact_control *cc, struct page *page)
{
	bool skip;

	/* Do not update if skip hint is being ignored */
	if (cc->ignore_skip_hint)
		return false;

	skip = get_pageblock_skip(page);
	if (!skip && !cc->no_set_skip_hint)
		set_pageblock_skip(page);

	return skip;
}

static void update_cached_migrate(struct compact_control *cc, unsigned long pfn)
{
	struct zone *zone = cc->zone;

	/* Set for isolation rather than compaction */
	if (cc->no_set_skip_hint)
		return;

	pfn = pageblock_end_pfn(pfn);

	/* Update where async and sync compaction should restart */
	if (pfn > zone->compact_cached_migrate_pfn[0])
		zone->compact_cached_migrate_pfn[0] = pfn;
	if (cc->mode != MIGRATE_ASYNC &&
	    pfn > zone->compact_cached_migrate_pfn[1])
		zone->compact_cached_migrate_pfn[1] = pfn;
}

/*
 * If no pages were isolated then mark this pageblock to be skipped in the
 * future. The information is later cleared by __reset_isolation_suitable().
 */
static void update_pageblock_skip(struct compact_control *cc,
			struct page *page, unsigned long pfn)
{
	struct zone *zone = cc->zone;

	if (cc->no_set_skip_hint)
		return;

	set_pageblock_skip(page);

	if (pfn < zone->compact_cached_free_pfn)
		zone->compact_cached_free_pfn = pfn;
}
#else
static inline bool isolation_suitable(struct compact_control *cc,
					struct page *page)
{
	return true;
}

static inline bool pageblock_skip_persistent(struct page *page)
{
	return false;
}

static inline void update_pageblock_skip(struct compact_control *cc,
			struct page *page, unsigned long pfn)
{
}

static void update_cached_migrate(struct compact_control *cc, unsigned long pfn)
{
}

static bool test_and_set_skip(struct compact_control *cc, struct page *page)
{
	return false;
}
#endif /* CONFIG_COMPACTION */

/*
 * Compaction requires the taking of some coarse locks that are potentially
 * very heavily contended. For async compaction, trylock and record if the
 * lock is contended. The lock will still be acquired but compaction will
 * abort when the current block is finished regardless of success rate.
 * Sync compaction acquires the lock.
 *
 * Always returns true which makes it easier to track lock state in callers.
 */
static bool compact_lock_irqsave(spinlock_t *lock, unsigned long *flags,
						struct compact_control *cc)
	__acquires(lock)
{
	/* Track if the lock is contended in async mode */
	if (cc->mode == MIGRATE_ASYNC && !cc->contended) {
		if (spin_trylock_irqsave(lock, *flags))
			return true;

		cc->contended = true;
	}

	spin_lock_irqsave(lock, *flags);
	return true;
}

/*
 * Compaction requires the taking of some coarse locks that are potentially
 * very heavily contended. The lock should be periodically unlocked to avoid
 * having disabled IRQs for a long time, even when there is nobody waiting on
 * the lock. It might also be that allowing the IRQs will result in
 * need_resched() becoming true. If scheduling is needed, compaction schedules.
 * Either compaction type will also abort if a fatal signal is pending.
 * In either case if the lock was locked, it is dropped and not regained.
 *
 * Returns true if compaction should abort due to fatal signal pending.
 * Returns false when compaction can continue.
 */
static bool compact_unlock_should_abort(spinlock_t *lock,
		unsigned long flags, bool *locked, struct compact_control *cc)
{
	if (*locked) {
		spin_unlock_irqrestore(lock, flags);
		*locked = false;
	}

	if (fatal_signal_pending(current)) {
		cc->contended = true;
		return true;
	}

	cond_resched();

	return false;
}

/*
 * Isolate free pages onto a private freelist. If @strict is true, will abort
 * returning 0 on any invalid PFNs or non-free pages inside of the pageblock
 * (even though it may still end up isolating some pages).
 */
static unsigned long isolate_freepages_block(struct compact_control *cc,
				unsigned long *start_pfn,
				unsigned long end_pfn,
				struct list_head *freelist,
				unsigned int stride,
				bool strict)
{
	int nr_scanned = 0, total_isolated = 0;
	struct page *page;
	unsigned long flags = 0;
	bool locked = false;
	unsigned long blockpfn = *start_pfn;
	unsigned int order;

	/* Strict mode is for isolation, speed is secondary */
	if (strict)
		stride = 1;

	page = pfn_to_page(blockpfn);

	/* Isolate free pages. */
	for (; blockpfn < end_pfn; blockpfn += stride, page += stride) {
		int isolated;

		/*
		 * Periodically drop the lock (if held) regardless of its
		 * contention, to give chance to IRQs. Abort if fatal signal
		 * pending.
		 */
		if (!(blockpfn % COMPACT_CLUSTER_MAX)
		    && compact_unlock_should_abort(&cc->zone->lock, flags,
								&locked, cc))
			break;

		nr_scanned++;

		/*
		 * For compound pages such as THP and hugetlbfs, we can save
		 * potentially a lot of iterations if we skip them at once.
		 * The check is racy, but we can consider only valid values
		 * and the only danger is skipping too much.
		 */
		if (PageCompound(page)) {
			const unsigned int order = compound_order(page);

			if (blockpfn + (1UL << order) <= end_pfn) {
				blockpfn += (1UL << order) - 1;
				page += (1UL << order) - 1;
				nr_scanned += (1UL << order) - 1;
			}

			goto isolate_fail;
		}

		if (!PageBuddy(page))
			goto isolate_fail;

		/* If we already hold the lock, we can skip some rechecking. */
		if (!locked) {
			locked = compact_lock_irqsave(&cc->zone->lock,
								&flags, cc);

			/* Recheck this is a buddy page under lock */
			if (!PageBuddy(page))
				goto isolate_fail;
		}

		/* Found a free page, will break it into order-0 pages */
		order = buddy_order(page);
		isolated = __isolate_free_page(page, order);
		if (!isolated)
			break;
		set_page_private(page, order);

		nr_scanned += isolated - 1;
		total_isolated += isolated;
		cc->nr_freepages += isolated;
		list_add_tail(&page->lru, &freelist[order]);

		if (!strict && cc->nr_migratepages <= cc->nr_freepages) {
			blockpfn += isolated;
			break;
		}
		/* Advance to the end of split page */
		blockpfn += isolated - 1;
		page += isolated - 1;
		continue;

isolate_fail:
		if (strict)
			break;

	}

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

	/*
	 * Be careful to not go outside of the pageblock.
	 */
	if (unlikely(blockpfn > end_pfn))
		blockpfn = end_pfn;

	trace_mm_compaction_isolate_freepages(*start_pfn, blockpfn,
					nr_scanned, total_isolated);

	/* Record how far we have got within the block */
	*start_pfn = blockpfn;

	/*
	 * If strict isolation is requested by CMA then check that all the
	 * pages requested were isolated. If there were any failures, 0 is
	 * returned and CMA will fail.
	 */
	if (strict && blockpfn < end_pfn)
		total_isolated = 0;

	cc->total_free_scanned += nr_scanned;
	if (total_isolated)
		count_compact_events(COMPACTISOLATED, total_isolated);
	return total_isolated;
}

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

	for (order = 0; order < NR_PAGE_ORDERS; order++)
		INIT_LIST_HEAD(&tmp_freepages[order]);

	pfn = start_pfn;
	block_start_pfn = pageblock_start_pfn(pfn);
	if (block_start_pfn < cc->zone->zone_start_pfn)
		block_start_pfn = cc->zone->zone_start_pfn;
	block_end_pfn = pageblock_end_pfn(pfn);

	for (; pfn < end_pfn; pfn += isolated,
				block_start_pfn = block_end_pfn,
				block_end_pfn += pageblock_nr_pages) {
		/* Protect pfn from changing by isolate_freepages_block */
		unsigned long isolate_start_pfn = pfn;

		/*
		 * pfn could pass the block_end_pfn if isolated freepage
		 * is more than pageblock order. In this case, we adjust
		 * scanning range to right one.
		 */
		if (pfn >= block_end_pfn) {
			block_start_pfn = pageblock_start_pfn(pfn);
			block_end_pfn = pageblock_end_pfn(pfn);
		}

		block_end_pfn = min(block_end_pfn, end_pfn);

		if (!pageblock_pfn_to_page(block_start_pfn,
					block_end_pfn, cc->zone))
			break;

		isolated = isolate_freepages_block(cc, &isolate_start_pfn,
					block_end_pfn, tmp_freepages, 0, true);

		/*
		 * In strict mode, isolate_freepages_block() returns 0 if
		 * there are any holes in the block (ie. invalid PFNs or
		 * non-free pages).
		 */
		if (!isolated)
			break;

		/*
		 * If we managed to isolate pages, it is always (1 << n) *
		 * pageblock_nr_pages for some non-negative n.  (Max order
		 * page may span two pageblocks).
		 */
	}

	if (pfn < end_pfn) {
		/* Loop terminated early, cleanup. */
		release_free_list(tmp_freepages);
		return 0;
	}

	/* __isolate_free_page() does not map the pages */
	split_map_pages(tmp_freepages);

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

/* Similar to reclaim, but different enough that they don't share logic */
static bool too_many_isolated(struct compact_control *cc)
{
	pg_data_t *pgdat = cc->zone->zone_pgdat;
	bool too_many;

	unsigned long active, inactive, isolated;

	inactive = node_page_state(pgdat, NR_INACTIVE_FILE) +
			node_page_state(pgdat, NR_INACTIVE_ANON);
	active = node_page_state(pgdat, NR_ACTIVE_FILE) +
			node_page_state(pgdat, NR_ACTIVE_ANON);
	isolated = node_page_state(pgdat, NR_ISOLATED_FILE) +
			node_page_state(pgdat, NR_ISOLATED_ANON);

	/*
	 * Allow GFP_NOFS to isolate past the limit set for regular
	 * compaction runs. This prevents an ABBA deadlock when other
	 * compactors have already isolated to the limit, but are
	 * blocked on filesystem locks held by the GFP_NOFS thread.
	 */
	if (cc->gfp_mask & __GFP_FS) {
		inactive >>= 3;
		active >>= 3;
	}

	too_many = isolated > (inactive + active) / 2;
	if (!too_many)
		wake_throttle_isolated(pgdat);

	return too_many;
}

/**
 * skip_isolation_on_order() - determine when to skip folio isolation based on
 *			       folio order and compaction target order
 * @order:		to-be-isolated folio order
 * @target_order:	compaction target order
 *
 * This avoids unnecessary folio isolations during compaction.
 */
static bool skip_isolation_on_order(int order, int target_order)
{
	/*
	 * Unless we are performing global compaction (i.e.,
	 * is_via_compact_memory), skip any folios that are larger than the
	 * target order: we wouldn't be here if we'd have a free folio with
	 * the desired target_order, so migrating this folio would likely fail
	 * later.
	 */
	if (!is_via_compact_memory(target_order) && order >= target_order)
		return true;
	/*
	 * We limit memory compaction to pageblocks and won't try
	 * creating free blocks of memory that are larger than that.
	 */
	return order >= pageblock_order;
}

/**
 * isolate_migratepages_block() - isolate all migrate-able pages within
 *				  a single pageblock
 * @cc:		Compaction control structure.
 * @low_pfn:	The first PFN to isolate
 * @end_pfn:	The one-past-the-last PFN to isolate, within same pageblock
 * @mode:	Isolation mode to be used.
 *
 * Isolate all pages that can be migrated from the range specified by
 * [low_pfn, end_pfn). The range is expected to be within same pageblock.
 * Returns errno, like -EAGAIN or -EINTR in case e.g signal pending or congestion,
 * -ENOMEM in case we could not allocate a page, or 0.
 * cc->migrate_pfn will contain the next pfn to scan.
 *
 * The pages are isolated on cc->migratepages list (not required to be empty),
 * and cc->nr_migratepages is updated accordingly.
 */
static int
isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
			unsigned long end_pfn, isolate_mode_t mode)
{
	pg_data_t *pgdat = cc->zone->zone_pgdat;
	unsigned long nr_scanned = 0, nr_isolated = 0;
	struct lruvec *lruvec;
	unsigned long flags = 0;
	struct lruvec *locked = NULL;
	struct folio *folio = NULL;
	struct page *page = NULL, *valid_page = NULL;
	struct address_space *mapping;
	unsigned long start_pfn = low_pfn;
	bool skip_on_failure = false;
	unsigned long next_skip_pfn = 0;
	bool skip_updated = false;
	int ret = 0;

	cc->migrate_pfn = low_pfn;

	/*
	 * Ensure that there are not too many pages isolated from the LRU
	 * list by either parallel reclaimers or compaction. If there are,
	 * delay for some time until fewer pages are isolated
	 */
	while (unlikely(too_many_isolated(cc))) {
		/* stop isolation if there are still pages not migrated */
		if (cc->nr_migratepages)
			return -EAGAIN;

		/* async migration should just abort */
		if (cc->mode == MIGRATE_ASYNC)
			return -EAGAIN;

		reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED);

		if (fatal_signal_pending(current))
			return -EINTR;
	}

	cond_resched();

	if (cc->direct_compaction && (cc->mode == MIGRATE_ASYNC)) {
		skip_on_failure = true;
		next_skip_pfn = block_end_pfn(low_pfn, cc->order);
	}

	/* Time to isolate some pages for migration */
	for (; low_pfn < end_pfn; low_pfn++) {
		bool is_dirty, is_unevictable;

		if (skip_on_failure && low_pfn >= next_skip_pfn) {
			/*
			 * We have isolated all migration candidates in the
			 * previous order-aligned block, and did not skip it due
			 * to failure. We should migrate the pages now and
			 * hopefully succeed compaction.
			 */
			if (nr_isolated)
				break;

			/*
			 * We failed to isolate in the previous order-aligned
			 * block. Set the new boundary to the end of the
			 * current block. Note we can't simply increase
			 * next_skip_pfn by 1 << order, as low_pfn might have
			 * been incremented by a higher number due to skipping
			 * a compound or a high-order buddy page in the
			 * previous loop iteration.
			 */
			next_skip_pfn = block_end_pfn(low_pfn, cc->order);
		}

		/*
		 * Periodically drop the lock (if held) regardless of its
		 * contention, to give chance to IRQs. Abort completely if
		 * a fatal signal is pending.
		 */
		if (!(low_pfn % COMPACT_CLUSTER_MAX)) {
			if (locked) {
				unlock_page_lruvec_irqrestore(locked, flags);
				locked = NULL;
			}

			if (fatal_signal_pending(current)) {
				cc->contended = true;
				ret = -EINTR;

				goto fatal_pending;
			}

			cond_resched();
		}

		nr_scanned++;

		page = pfn_to_page(low_pfn);

		/*
		 * Check if the pageblock has already been marked skipped.
		 * Only the first PFN is checked as the caller isolates
		 * COMPACT_CLUSTER_MAX at a time so the second call must
		 * not falsely conclude that the block should be skipped.
		 */
		if (!valid_page && (pageblock_aligned(low_pfn) ||
				    low_pfn == cc->zone->zone_start_pfn)) {
			if (!isolation_suitable(cc, page)) {
				low_pfn = end_pfn;
				folio = NULL;
				goto isolate_abort;
			}
			valid_page = page;
		}

		if (PageHuge(page)) {
			/*
			 * skip hugetlbfs if we are not compacting for pages
			 * bigger than its order. THPs and other compound pages
			 * are handled below.
			 */
			if (!cc->alloc_contig) {
				const unsigned int order = compound_order(page);

				if (order <= MAX_PAGE_ORDER) {
					low_pfn += (1UL << order) - 1;
					nr_scanned += (1UL << order) - 1;
				}
				goto isolate_fail;
			}
			/* for alloc_contig case */
			if (locked) {
				unlock_page_lruvec_irqrestore(locked, flags);
				locked = NULL;
			}

			ret = isolate_or_dissolve_huge_page(page, &cc->migratepages);

			/*
			 * Fail isolation in case isolate_or_dissolve_huge_page()
			 * reports an error. In case of -ENOMEM, abort right away.
			 */
			if (ret < 0) {
				 /* Do not report -EBUSY down the chain */
				if (ret == -EBUSY)
					ret = 0;
				low_pfn += compound_nr(page) - 1;
				nr_scanned += compound_nr(page) - 1;
				goto isolate_fail;
			}

			if (PageHuge(page)) {
				/*
				 * Hugepage was successfully isolated and placed
				 * on the cc->migratepages list.
				 */
				folio = page_folio(page);
				low_pfn += folio_nr_pages(folio) - 1;
				goto isolate_success_no_list;
			}

			/*
			 * Ok, the hugepage was dissolved. Now these pages are
			 * Buddy and cannot be re-allocated because they are
			 * isolated. Fall-through as the check below handles
			 * Buddy pages.
			 */
		}

		/*
		 * Skip if free. We read page order here without zone lock
		 * which is generally unsafe, but the race window is small and
		 * the worst thing that can happen is that we skip some
		 * potential isolation targets.
		 */
		if (PageBuddy(page)) {
			unsigned long freepage_order = buddy_order_unsafe(page);

			/*
			 * Without lock, we cannot be sure that what we got is
			 * a valid page order. Consider only values in the
			 * valid order range to prevent low_pfn overflow.
			 */
			if (freepage_order > 0 && freepage_order <= MAX_PAGE_ORDER) {
				low_pfn += (1UL << freepage_order) - 1;
				nr_scanned += (1UL << freepage_order) - 1;
			}
			continue;
		}

		/*
		 * Regardless of being on LRU, compound pages such as THP
		 * (hugetlbfs is handled above) are not to be compacted unless
		 * we are attempting an allocation larger than the compound
		 * page size. We can potentially save a lot of iterations if we
		 * skip them at once. The check is racy, but we can consider
		 * only valid values and the only danger is skipping too much.
		 */
		if (PageCompound(page) && !cc->alloc_contig) {
			const unsigned int order = compound_order(page);

			/* Skip based on page order and compaction target order. */
			if (skip_isolation_on_order(order, cc->order)) {
				if (order <= MAX_PAGE_ORDER) {
					low_pfn += (1UL << order) - 1;
					nr_scanned += (1UL << order) - 1;
				}
				goto isolate_fail;
			}
		}

		/*
		 * Check may be lockless but that's ok as we recheck later.
		 * It's possible to migrate LRU and non-lru movable pages.
		 * Skip any other type of page
		 */
		if (!PageLRU(page)) {
			/*
			 * __PageMovable can return false positive so we need
			 * to verify it under page_lock.
			 */
			if (unlikely(__PageMovable(page)) &&
					!PageIsolated(page)) {
				if (locked) {
					unlock_page_lruvec_irqrestore(locked, flags);
					locked = NULL;
				}

				if (isolate_movable_page(page, mode)) {
					folio = page_folio(page);
					goto isolate_success;
				}
			}

			goto isolate_fail;
		}

		/*
		 * Be careful not to clear PageLRU until after we're
		 * sure the page is not being freed elsewhere -- the
		 * page release code relies on it.
		 */
		folio = folio_get_nontail_page(page);
		if (unlikely(!folio))
			goto isolate_fail;

		/*
		 * Migration will fail if an anonymous page is pinned in memory,
		 * so avoid taking lru_lock and isolating it unnecessarily in an
		 * admittedly racy check.
		 */
		mapping = folio_mapping(folio);
		if (!mapping && (folio_ref_count(folio) - 1) > folio_mapcount(folio))
			goto isolate_fail_put;

		/*
		 * Only allow to migrate anonymous pages in GFP_NOFS context
		 * because those do not depend on fs locks.
		 */
		if (!(cc->gfp_mask & __GFP_FS) && mapping)
			goto isolate_fail_put;

		/* Only take pages on LRU: a check now makes later tests safe */
		if (!folio_test_lru(folio))
			goto isolate_fail_put;

		is_unevictable = folio_test_unevictable(folio);

		/* Compaction might skip unevictable pages but CMA takes them */
		if (!(mode & ISOLATE_UNEVICTABLE) && is_unevictable)
			goto isolate_fail_put;

		/*
		 * To minimise LRU disruption, the caller can indicate with
		 * ISOLATE_ASYNC_MIGRATE that it only wants to isolate pages
		 * it will be able to migrate without blocking - clean pages
		 * for the most part.  PageWriteback would require blocking.
		 */
		if ((mode & ISOLATE_ASYNC_MIGRATE) && folio_test_writeback(folio))
			goto isolate_fail_put;

		is_dirty = folio_test_dirty(folio);

		if (((mode & ISOLATE_ASYNC_MIGRATE) && is_dirty) ||
		    (mapping && is_unevictable)) {
			bool migrate_dirty = true;
			bool is_unmovable;

			/*
			 * Only folios without mappings or that have
			 * a ->migrate_folio callback are possible to migrate
			 * without blocking.
			 *
			 * Folios from unmovable mappings are not migratable.
			 *
			 * However, we can be racing with truncation, which can
			 * free the mapping that we need to check. Truncation
			 * holds the folio lock until after the folio is removed
			 * from the page so holding it ourselves is sufficient.
			 *
			 * To avoid locking the folio just to check unmovable,
			 * assume every unmovable folio is also unevictable,
			 * which is a cheaper test.  If our assumption goes
			 * wrong, it's not a correctness bug, just potentially
			 * wasted cycles.
			 */
			if (!folio_trylock(folio))
				goto isolate_fail_put;

			mapping = folio_mapping(folio);
			if ((mode & ISOLATE_ASYNC_MIGRATE) && is_dirty) {
				migrate_dirty = !mapping ||
						mapping->a_ops->migrate_folio;
			}
			is_unmovable = mapping && mapping_unmovable(mapping);
			folio_unlock(folio);
			if (!migrate_dirty || is_unmovable)
				goto isolate_fail_put;
		}

		/* Try isolate the folio */
		if (!folio_test_clear_lru(folio))
			goto isolate_fail_put;

		lruvec = folio_lruvec(folio);

		/* If we already hold the lock, we can skip some rechecking */
		if (lruvec != locked) {
			if (locked)
				unlock_page_lruvec_irqrestore(locked, flags);

			compact_lock_irqsave(&lruvec->lru_lock, &flags, cc);
			locked = lruvec;

			lruvec_memcg_debug(lruvec, folio);

			/*
			 * Try get exclusive access under lock. If marked for
			 * skip, the scan is aborted unless the current context
			 * is a rescan to reach the end of the pageblock.
			 */
			if (!skip_updated && valid_page) {
				skip_updated = true;
				if (test_and_set_skip(cc, valid_page) &&
				    !cc->finish_pageblock) {
					low_pfn = end_pfn;
					goto isolate_abort;
				}
			}

			/*
			 * Check LRU folio order under the lock
			 */
			if (unlikely(skip_isolation_on_order(folio_order(folio),
							     cc->order) &&
				     !cc->alloc_contig)) {
				low_pfn += folio_nr_pages(folio) - 1;
				nr_scanned += folio_nr_pages(folio) - 1;
				folio_set_lru(folio);
				goto isolate_fail_put;
			}
		}

		/* The folio is taken off the LRU */
		if (folio_test_large(folio))
			low_pfn += folio_nr_pages(folio) - 1;

		/* Successfully isolated */
		lruvec_del_folio(lruvec, folio);
		node_stat_mod_folio(folio,
				NR_ISOLATED_ANON + folio_is_file_lru(folio),
				folio_nr_pages(folio));

isolate_success:
		list_add(&folio->lru, &cc->migratepages);
isolate_success_no_list:
		cc->nr_migratepages += folio_nr_pages(folio);
		nr_isolated += folio_nr_pages(folio);
		nr_scanned += folio_nr_pages(folio) - 1;

		/*
		 * Avoid isolating too much unless this block is being
		 * fully scanned (e.g. dirty/writeback pages, parallel allocation)
		 * or a lock is contended. For contention, isolate quickly to
		 * potentially remove one source of contention.
		 */
		if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX &&
		    !cc->finish_pageblock && !cc->contended) {
			++low_pfn;
			break;
		}

		continue;

isolate_fail_put:
		/* Avoid potential deadlock in freeing page under lru_lock */
		if (locked) {
			unlock_page_lruvec_irqrestore(locked, flags);
			locked = NULL;
		}
		folio_put(folio);

isolate_fail:
		if (!skip_on_failure && ret != -ENOMEM)
			continue;

		/*
		 * We have isolated some pages, but then failed. Release them
		 * instead of migrating, as we cannot form the cc->order buddy
		 * page anyway.
		 */
		if (nr_isolated) {
			if (locked) {
				unlock_page_lruvec_irqrestore(locked, flags);
				locked = NULL;
			}
			putback_movable_pages(&cc->migratepages);
			cc->nr_migratepages = 0;
			nr_isolated = 0;
		}

		if (low_pfn < next_skip_pfn) {
			low_pfn = next_skip_pfn - 1;
			/*
			 * The check near the loop beginning would have updated
			 * next_skip_pfn too, but this is a bit simpler.
			 */
			next_skip_pfn += 1UL << cc->order;
		}

		if (ret == -ENOMEM)
			break;
	}

	/*
	 * The PageBuddy() check could have potentially brought us outside
	 * the range to be scanned.
	 */
	if (unlikely(low_pfn > end_pfn))
		low_pfn = end_pfn;

	folio = NULL;

isolate_abort:
	if (locked)
		unlock_page_lruvec_irqrestore(locked, flags);
	if (folio) {
		folio_set_lru(folio);
		folio_put(folio);
	}

	/*
	 * Update the cached scanner pfn once the pageblock has been scanned.
	 * Pages will either be migrated in which case there is no point
	 * scanning in the near future or migration failed in which case the
	 * failure reason may persist. The block is marked for skipping if
	 * there were no pages isolated in the block or if the block is
	 * rescanned twice in a row.
	 */
	if (low_pfn == end_pfn && (!nr_isolated || cc->finish_pageblock)) {
		if (!cc->no_set_skip_hint && valid_page && !skip_updated)
			set_pageblock_skip(valid_page);
		update_cached_migrate(cc, low_pfn);
	}

	trace_mm_compaction_isolate_migratepages(start_pfn, low_pfn,
						nr_scanned, nr_isolated);

fatal_pending:
	cc->total_migrate_scanned += nr_scanned;
	if (nr_isolated)
		count_compact_events(COMPACTISOLATED, nr_isolated);

	cc->migrate_pfn = low_pfn;

	return ret;
}

/**
 * isolate_migratepages_range() - isolate migrate-able pages in a PFN range
 * @cc:        Compaction control structure.
 * @start_pfn: The first PFN to start isolating.
 * @end_pfn:   The one-past-last PFN.
 *
 * Returns -EAGAIN when contented, -EINTR in case of a signal pending, -ENOMEM
 * in case we could not allocate a page, or 0.
 */
int
isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
							unsigned long end_pfn)
{
	unsigned long pfn, block_start_pfn, block_end_pfn;
	int ret = 0;

	/* Scan block by block. First and last block may be incomplete */
	pfn = start_pfn;
	block_start_pfn = pageblock_start_pfn(pfn);
	if (block_start_pfn < cc->zone->zone_start_pfn)
		block_start_pfn = cc->zone->zone_start_pfn;
	block_end_pfn = pageblock_end_pfn(pfn);

	for (; pfn < end_pfn; pfn = block_end_pfn,
				block_start_pfn = block_end_pfn,
				block_end_pfn += pageblock_nr_pages) {

		block_end_pfn = min(block_end_pfn, end_pfn);

		if (!pageblock_pfn_to_page(block_start_pfn,
					block_end_pfn, cc->zone))
			continue;

		ret = isolate_migratepages_block(cc, pfn, block_end_pfn,
						 ISOLATE_UNEVICTABLE);

		if (ret)
			break;

		if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX)
			break;
	}

	return ret;
}

#endif /* CONFIG_COMPACTION || CONFIG_CMA */
#ifdef CONFIG_COMPACTION

static bool suitable_migration_source(struct compact_control *cc,
							struct page *page)
{
	int block_mt;

	if (pageblock_skip_persistent(page))
		return false;

	if ((cc->mode != MIGRATE_ASYNC) || !cc->direct_compaction)
		return true;

	block_mt = get_pageblock_migratetype(page);

	if (cc->migratetype == MIGRATE_MOVABLE)
		return is_migrate_movable(block_mt);
	else
		return block_mt == cc->migratetype;
}

/* Returns true if the page is within a block suitable for migration to */
static bool suitable_migration_target(struct compact_control *cc,
							struct page *page)
{
	/* If the page is a large free page, then disallow migration */
	if (PageBuddy(page)) {
		int order = cc->order > 0 ? cc->order : pageblock_order;

		/*
		 * We are checking page_order without zone->lock taken. But
		 * the only small danger is that we skip a potentially suitable
		 * pageblock, so it's not worth to check order for valid range.
		 */
		if (buddy_order_unsafe(page) >= order)
			return false;
	}

	if (cc->ignore_block_suitable)
		return true;

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

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

static inline unsigned int
freelist_scan_limit(struct compact_control *cc)
{
	unsigned short shift = BITS_PER_LONG - 1;

	return (COMPACT_CLUSTER_MAX >> min(shift, cc->fast_search_fail)) + 1;
}

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

/*
 * Used when scanning for a suitable migration target which scans freelists
 * in reverse. Reorders the list such as the unscanned pages are scanned
 * first on the next iteration of the free scanner
 */
static void
move_freelist_head(struct list_head *freelist, struct page *freepage)
{
	LIST_HEAD(sublist);

	if (!list_is_first(&freepage->buddy_list, freelist)) {
		list_cut_before(&sublist, freelist, &freepage->buddy_list);
		list_splice_tail(&sublist, freelist);
	}
}

/*
 * Similar to move_freelist_head except used by the migration scanner
 * when scanning forward. It's possible for these list operations to
 * move against each other if they search the free list exactly in
 * lockstep.
 */
static void
move_freelist_tail(struct list_head *freelist, struct page *freepage)
{
	LIST_HEAD(sublist);

	if (!list_is_last(&freepage->buddy_list, freelist)) {
		list_cut_position(&sublist, freelist, &freepage->buddy_list);
		list_splice_tail(&sublist, freelist);
	}
}

static void
fast_isolate_around(struct compact_control *cc, unsigned long pfn)
{
	unsigned long start_pfn, end_pfn;
	struct page *page;

	/* Do not search around if there are enough pages already */
	if (cc->nr_freepages >= cc->nr_migratepages)
		return;

	/* Minimise scanning during async compaction */
	if (cc->direct_compaction && cc->mode == MIGRATE_ASYNC)
		return;

	/* Pageblock boundaries */
	start_pfn = max(pageblock_start_pfn(pfn), cc->zone->zone_start_pfn);
	end_pfn = min(pageblock_end_pfn(pfn), zone_end_pfn(cc->zone));

	page = pageblock_pfn_to_page(start_pfn, end_pfn, cc->zone);
	if (!page)
		return;

	isolate_freepages_block(cc, &start_pfn, end_pfn, cc->freepages, 1, false);

	/* Skip this pageblock in the future as it's full or nearly full */
	if (start_pfn == end_pfn && !cc->no_set_skip_hint)
		set_pageblock_skip(page);
}

/* Search orders in round-robin fashion */
static int next_search_order(struct compact_control *cc, int order)
{
	order--;
	if (order < 0)
		order = cc->order - 1;

	/* Search wrapped around? */
	if (order == cc->search_order) {
		cc->search_order--;
		if (cc->search_order < 0)
			cc->search_order = cc->order - 1;
		return -1;
	}

	return order;
}

static void fast_isolate_freepages(struct compact_control *cc)
{
	unsigned int limit = max(1U, freelist_scan_limit(cc) >> 1);
	unsigned int nr_scanned = 0, total_isolated = 0;
	unsigned long low_pfn, min_pfn, highest = 0;
	unsigned long nr_isolated = 0;
	unsigned long distance;
	struct page *page = NULL;
	bool scan_start = false;
	int order;

	/* Full compaction passes in a negative order */
	if (cc->order <= 0)
		return;

	/*
	 * If starting the scan, use a deeper search and use the highest
	 * PFN found if a suitable one is not found.
	 */
	if (cc->free_pfn >= cc->zone->compact_init_free_pfn) {
		limit = pageblock_nr_pages >> 1;
		scan_start = true;
	}

	/*
	 * Preferred point is in the top quarter of the scan space but take
	 * a pfn from the top half if the search is problematic.
	 */
	distance = (cc->free_pfn - cc->migrate_pfn);
	low_pfn = pageblock_start_pfn(cc->free_pfn - (distance >> 2));
	min_pfn = pageblock_start_pfn(cc->free_pfn - (distance >> 1));

	if (WARN_ON_ONCE(min_pfn > low_pfn))
		low_pfn = min_pfn;

	/*
	 * Search starts from the last successful isolation order or the next
	 * order to search after a previous failure
	 */
	cc->search_order = min_t(unsigned int, cc->order - 1, cc->search_order);

	for (order = cc->search_order;
	     !page && order >= 0;
	     order = next_search_order(cc, order)) {
		struct free_area *area = &cc->zone->free_area[order];
		struct list_head *freelist;
		struct page *freepage;
		unsigned long flags;
		unsigned int order_scanned = 0;
		unsigned long high_pfn = 0;

		if (!area->nr_free)
			continue;

		spin_lock_irqsave(&cc->zone->lock, flags);
		freelist = &area->free_list[MIGRATE_MOVABLE];
		list_for_each_entry_reverse(freepage, freelist, buddy_list) {
			unsigned long pfn;

			order_scanned++;
			nr_scanned++;
			pfn = page_to_pfn(freepage);

			if (pfn >= highest)
				highest = max(pageblock_start_pfn(pfn),
					      cc->zone->zone_start_pfn);

			if (pfn >= low_pfn) {
				cc->fast_search_fail = 0;
				cc->search_order = order;
				page = freepage;
				break;
			}

			if (pfn >= min_pfn && pfn > high_pfn) {
				high_pfn = pfn;

				/* Shorten the scan if a candidate is found */
				limit >>= 1;
			}

			if (order_scanned >= limit)
				break;
		}

		/* Use a maximum candidate pfn if a preferred one was not found */
		if (!page && high_pfn) {
			page = pfn_to_page(high_pfn);

			/* Update freepage for the list reorder below */
			freepage = page;
		}

		/* Reorder to so a future search skips recent pages */
		move_freelist_head(freelist, freepage);

		/* Isolate the page if available */
		if (page) {
			if (__isolate_free_page(page, order)) {
				set_page_private(page, order);
				nr_isolated = 1 << order;
				nr_scanned += nr_isolated - 1;
				total_isolated += nr_isolated;
				cc->nr_freepages += nr_isolated;
				list_add_tail(&page->lru, &cc->freepages[order]);
				count_compact_events(COMPACTISOLATED, nr_isolated);
			} else {
				/* If isolation fails, abort the search */
				order = cc->search_order + 1;
				page = NULL;
			}
		}

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

		/* Skip fast search if enough freepages isolated */
		if (cc->nr_freepages >= cc->nr_migratepages)
			break;

		/*
		 * Smaller scan on next order so the total scan is related
		 * to freelist_scan_limit.
		 */
		if (order_scanned >= limit)
			limit = max(1U, limit >> 1);
	}

	trace_mm_compaction_fast_isolate_freepages(min_pfn, cc->free_pfn,
						   nr_scanned, total_isolated);

	if (!page) {
		cc->fast_search_fail++;
		if (scan_start) {
			/*
			 * Use the highest PFN found above min. If one was
			 * not found, be pessimistic for direct compaction
			 * and use the min mark.
			 */
			if (highest >= min_pfn) {
				page = pfn_to_page(highest);
				cc->free_pfn = highest;
			} else {
				if (cc->direct_compaction && pfn_valid(min_pfn)) {
					page = pageblock_pfn_to_page(min_pfn,
						min(pageblock_end_pfn(min_pfn),
						    zone_end_pfn(cc->zone)),
						cc->zone);
					if (page && !suitable_migration_target(cc, page))
						page = NULL;

					cc->free_pfn = min_pfn;
				}
			}
		}
	}

	if (highest && highest >= cc->zone->compact_cached_free_pfn) {
		highest -= pageblock_nr_pages;
		cc->zone->compact_cached_free_pfn = highest;
	}

	cc->total_free_scanned += nr_scanned;
	if (!page)
		return;

	low_pfn = page_to_pfn(page);
	fast_isolate_around(cc, low_pfn);
}

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

	/* Try a small search of the free lists for a candidate */
	fast_isolate_freepages(cc);
	if (cc->nr_freepages)
		return;

	/*
	 * Initialise the free scanner. The starting point is where we last
	 * successfully isolated from, zone-cached value, or the end of the
	 * zone when isolating for the first time. For looping we also need
	 * this pfn aligned down to the pageblock boundary, because we do
	 * block_start_pfn -= pageblock_nr_pages in the for loop.
	 * For ending point, take care when isolating in last pageblock of a
	 * zone which ends in the middle of a pageblock.
	 * The low boundary is the end of the pageblock the migration scanner
	 * is using.
	 */
	isolate_start_pfn = cc->free_pfn;
	block_start_pfn = pageblock_start_pfn(isolate_start_pfn);
	block_end_pfn = min(block_start_pfn + pageblock_nr_pages,
						zone_end_pfn(zone));
	low_pfn = pageblock_end_pfn(cc->migrate_pfn);
	stride = cc->mode == MIGRATE_ASYNC ? COMPACT_CLUSTER_MAX : 1;

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

		/*
		 * This can iterate a massively long zone without finding any
		 * suitable migration targets, so periodically check resched.
		 */
		if (!(block_start_pfn % (COMPACT_CLUSTER_MAX * pageblock_nr_pages)))
			cond_resched();

		page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn,
									zone);
		if (!page) {
			unsigned long next_pfn;

			next_pfn = skip_offline_sections_reverse(block_start_pfn);
			if (next_pfn)
				block_start_pfn = max(next_pfn, low_pfn);

			continue;
		}

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

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

		/* Found a block suitable for isolating free pages from. */
		nr_isolated = isolate_freepages_block(cc, &isolate_start_pfn,
					block_end_pfn, cc->freepages, stride, false);

		/* Update the skip hint if the full pageblock was scanned */
		if (isolate_start_pfn == block_end_pfn)
			update_pageblock_skip(cc, page, block_start_pfn -
					      pageblock_nr_pages);

		/* Are enough freepages isolated? */
		if (cc->nr_freepages >= cc->nr_migratepages) {
			if (isolate_start_pfn >= block_end_pfn) {
				/*
				 * Restart at previous pageblock if more
				 * freepages can be isolated next time.
				 */
				isolate_start_pfn =
					block_start_pfn - pageblock_nr_pages;
			}
			break;
		} else if (isolate_start_pfn < block_end_pfn) {
			/*
			 * If isolation failed early, do not continue
			 * needlessly.
			 */
			break;
		}

		/* Adjust stride depending on isolation */
		if (nr_isolated) {
			stride = 1;
			continue;
		}
		stride = min_t(unsigned int, COMPACT_CLUSTER_MAX, stride << 1);
	}

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

/*
 * This is a migrate-callback that "allocates" freepages by taking pages
 * from the isolated freelists in the block we are migrating to.
 */
static struct folio *compaction_alloc_noprof(struct folio *src, unsigned long data)
{
	struct compact_control *cc = (struct compact_control *)data;
	struct folio *dst;
	int order = folio_order(src);
	bool has_isolated_pages = false;
	int start_order;
	struct page *freepage;
	unsigned long size;

again:
	for (start_order = order; start_order < NR_PAGE_ORDERS; start_order++)
		if (!list_empty(&cc->freepages[start_order]))
			break;

	/* no free pages in the list */
	if (start_order == NR_PAGE_ORDERS) {
		if (has_isolated_pages)
			return NULL;
		isolate_freepages(cc);
		has_isolated_pages = true;
		goto again;
	}

	freepage = list_first_entry(&cc->freepages[start_order], struct page,
				lru);
	size = 1 << start_order;

	list_del(&freepage->lru);

	while (start_order > order) {
		start_order--;
		size >>= 1;

		list_add(&freepage[size].lru, &cc->freepages[start_order]);
		set_page_private(&freepage[size], start_order);
	}
	dst = (struct folio *)freepage;

	post_alloc_hook(&dst->page, order, __GFP_MOVABLE);
	if (order)
		prep_compound_page(&dst->page, order);
	cc->nr_freepages -= 1 << order;
	cc->nr_migratepages -= 1 << order;
	return page_rmappable_folio(&dst->page);
}

static struct folio *compaction_alloc(struct folio *src, unsigned long data)
{
	return alloc_hooks(compaction_alloc_noprof(src, data));
}

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

	if (folio_put_testzero(dst)) {
		free_pages_prepare(page, order);
		list_add(&dst->lru, &cc->freepages[order]);
		cc->nr_freepages += 1 << order;
	}
	cc->nr_migratepages += 1 << order;
	/*
	 * someone else has referenced the page, we cannot take it back to our
	 * free list.
	 */
}

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

/*
 * Allow userspace to control policy on scanning the unevictable LRU for
 * compactable pages.
 */
static int sysctl_compact_unevictable_allowed __read_mostly = CONFIG_COMPACT_UNEVICTABLE_DEFAULT;
/*
 * Tunable for proactive compaction. It determines how
 * aggressively the kernel should compact memory in the
 * background. It takes values in the range [0, 100].
 */
static unsigned int __read_mostly sysctl_compaction_proactiveness = 20;
static int sysctl_extfrag_threshold = 500;
static int __read_mostly sysctl_compact_memory;

static inline void
update_fast_start_pfn(struct compact_control *cc, unsigned long pfn)
{
	if (cc->fast_start_pfn == ULONG_MAX)
		return;

	if (!cc->fast_start_pfn)
		cc->fast_start_pfn = pfn;

	cc->fast_start_pfn = min(cc->fast_start_pfn, pfn);
}

static inline unsigned long
reinit_migrate_pfn(struct compact_control *cc)
{
	if (!cc->fast_start_pfn || cc->fast_start_pfn == ULONG_MAX)
		return cc->migrate_pfn;

	cc->migrate_pfn = cc->fast_start_pfn;
	cc->fast_start_pfn = ULONG_MAX;

	return cc->migrate_pfn;
}

/*
 * Briefly search the free lists for a migration source that already has
 * some free pages to reduce the number of pages that need migration
 * before a pageblock is free.
 */
static unsigned long fast_find_migrateblock(struct compact_control *cc)
{
	unsigned int limit = freelist_scan_limit(cc);
	unsigned int nr_scanned = 0;
	unsigned long distance;
	unsigned long pfn = cc->migrate_pfn;
	unsigned long high_pfn;
	int order;
	bool found_block = false;

	/* Skip hints are relied on to avoid repeats on the fast search */
	if (cc->ignore_skip_hint)
		return pfn;

	/*
	 * If the pageblock should be finished then do not select a different
	 * pageblock.
	 */
	if (cc->finish_pageblock)
		return pfn;

	/*
	 * If the migrate_pfn is not at the start of a zone or the start
	 * of a pageblock then assume this is a continuation of a previous
	 * scan restarted due to COMPACT_CLUSTER_MAX.
	 */
	if (pfn != cc->zone->zone_start_pfn && pfn != pageblock_start_pfn(pfn))
		return pfn;

	/*
	 * For smaller orders, just linearly scan as the number of pages
	 * to migrate should be relatively small and does not necessarily
	 * justify freeing up a large block for a small allocation.
	 */
	if (cc->order <= PAGE_ALLOC_COSTLY_ORDER)
		return pfn;

	/*
	 * Only allow kcompactd and direct requests for movable pages to
	 * quickly clear out a MOVABLE pageblock for allocation. This
	 * reduces the risk that a large movable pageblock is freed for
	 * an unmovable/reclaimable small allocation.
	 */
	if (cc->direct_compaction && cc->migratetype != MIGRATE_MOVABLE)
		return pfn;

	/*
	 * When starting the migration scanner, pick any pageblock within the
	 * first half of the search space. Otherwise try and pick a pageblock
	 * within the first eighth to reduce the chances that a migration
	 * target later becomes a source.
	 */
	distance = (cc->free_pfn - cc->migrate_pfn) >> 1;
	if (cc->migrate_pfn != cc->zone->zone_start_pfn)
		distance >>= 2;
	high_pfn = pageblock_start_pfn(cc->migrate_pfn + distance);

	for (order = cc->order - 1;
	     order >= PAGE_ALLOC_COSTLY_ORDER && !found_block && nr_scanned < limit;
	     order--) {
		struct free_area *area = &cc->zone->free_area[order];
		struct list_head *freelist;
		unsigned long flags;
		struct page *freepage;

		if (!area->nr_free)
			continue;

		spin_lock_irqsave(&cc->zone->lock, flags);
		freelist = &area->free_list[MIGRATE_MOVABLE];
		list_for_each_entry(freepage, freelist, buddy_list) {
			unsigned long free_pfn;

			if (nr_scanned++ >= limit) {
				move_freelist_tail(freelist, freepage);
				break;
			}

			free_pfn = page_to_pfn(freepage);
			if (free_pfn < high_pfn) {
				/*
				 * Avoid if skipped recently. Ideally it would
				 * move to the tail but even safe iteration of
				 * the list assumes an entry is deleted, not
				 * reordered.
				 */
				if (get_pageblock_skip(freepage))
					continue;

				/* Reorder to so a future search skips recent pages */
				move_freelist_tail(freelist, freepage);

				update_fast_start_pfn(cc, free_pfn);
				pfn = pageblock_start_pfn(free_pfn);
				if (pfn < cc->zone->zone_start_pfn)
					pfn = cc->zone->zone_start_pfn;
				cc->fast_search_fail = 0;
				found_block = true;
				break;
			}
		}
		spin_unlock_irqrestore(&cc->zone->lock, flags);
	}

	cc->total_migrate_scanned += nr_scanned;

	/*
	 * If fast scanning failed then use a cached entry for a page block
	 * that had free pages as the basis for starting a linear scan.
	 */
	if (!found_block) {
		cc->fast_search_fail++;
		pfn = reinit_migrate_pfn(cc);
	}
	return pfn;
}

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

	/*
	 * Start at where we last stopped, or beginning of the zone as
	 * initialized by compact_zone(). The first failure will use
	 * the lowest PFN as the starting point for linear scanning.
	 */
	low_pfn = fast_find_migrateblock(cc);
	block_start_pfn = pageblock_start_pfn(low_pfn);
	if (block_start_pfn < cc->zone->zone_start_pfn)
		block_start_pfn = cc->zone->zone_start_pfn;

	/*
	 * fast_find_migrateblock() has already ensured the pageblock is not
	 * set with a skipped flag, so to avoid the isolation_suitable check
	 * below again, check whether the fast search was successful.
	 */
	fast_find_block = low_pfn != cc->migrate_pfn && !cc->fast_search_fail;

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

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

		/*
		 * This can potentially iterate a massively long zone with
		 * many pageblocks unsuitable, so periodically check if we
		 * need to schedule.
		 */
		if (!(low_pfn % (COMPACT_CLUSTER_MAX * pageblock_nr_pages)))
			cond_resched();

		page = pageblock_pfn_to_page(block_start_pfn,
						block_end_pfn, cc->zone);
		if (!page) {
			unsigned long next_pfn;

			next_pfn = skip_offline_sections(block_start_pfn);
			if (next_pfn)
				block_end_pfn = min(next_pfn, cc->free_pfn);
			continue;
		}

		/*
		 * If isolation recently failed, do not retry. Only check the
		 * pageblock once. COMPACT_CLUSTER_MAX causes a pageblock
		 * to be visited multiple times. Assume skip was checked
		 * before making it "skip" so other compaction instances do
		 * not scan the same block.
		 */
		if ((pageblock_aligned(low_pfn) ||
		     low_pfn == cc->zone->zone_start_pfn) &&
		    !fast_find_block && !isolation_suitable(cc, page))
			continue;

		/*
		 * For async direct compaction, only scan the pageblocks of the
		 * same migratetype without huge pages. Async direct compaction
		 * is optimistic to see if the minimum amount of work satisfies
		 * the allocation. The cached PFN is updated as it's possible
		 * that all remaining blocks between source and target are
		 * unsuitable and the compaction scanners fail to meet.
		 */
		if (!suitable_migration_source(cc, page)) {
			update_cached_migrate(cc, block_end_pfn);
			continue;
		}

		/* Perform the isolation */
		if (isolate_migratepages_block(cc, low_pfn, block_end_pfn,
						isolate_mode))
			return ISOLATE_ABORT;

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

	return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE;
}

/*
 * Determine whether kswapd is (or recently was!) running on this node.
 *
 * pgdat_kswapd_lock() pins pgdat->kswapd, so a concurrent kswapd_stop() can't
 * zero it.
 */
static bool kswapd_is_running(pg_data_t *pgdat)
{
	bool running;

	pgdat_kswapd_lock(pgdat);
	running = pgdat->kswapd && task_is_running(pgdat->kswapd);
	pgdat_kswapd_unlock(pgdat);

	return running;
}

/*
 * A zone's fragmentation score is the external fragmentation wrt to the
 * COMPACTION_HPAGE_ORDER. It returns a value in the range [0, 100].
 */
static unsigned int fragmentation_score_zone(struct zone *zone)
{
	return extfrag_for_order(zone, COMPACTION_HPAGE_ORDER);
}

/*
 * A weighted zone's fragmentation score is the external fragmentation
 * wrt to the COMPACTION_HPAGE_ORDER scaled by the zone's size. It
 * returns a value in the range [0, 100].
 *
 * The scaling factor ensures that proactive compaction focuses on larger
 * zones like ZONE_NORMAL, rather than smaller, specialized zones like
 * ZONE_DMA32. For smaller zones, the score value remains close to zero,
 * and thus never exceeds the high threshold for proactive compaction.
 */
static unsigned int fragmentation_score_zone_weighted(struct zone *zone)
{
	unsigned long score;

	score = zone->present_pages * fragmentation_score_zone(zone);
	return div64_ul(score, zone->zone_pgdat->node_present_pages + 1);
}

/*
 * The per-node proactive (background) compaction process is started by its
 * corresponding kcompactd thread when the node's fragmentation score
 * exceeds the high threshold. The compaction process remains active till
 * the node's score falls below the low threshold, or one of the back-off
 * conditions is met.
 */
static unsigned int fragmentation_score_node(pg_data_t *pgdat)
{
	unsigned int score = 0;
	int zoneid;

	for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
		struct zone *zone;

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

	return score;
}

static unsigned int fragmentation_score_wmark(bool low)
{
	unsigned int wmark_low;

	/*
	 * Cap the low watermark to avoid excessive compaction
	 * activity in case a user sets the proactiveness tunable
	 * close to 100 (maximum).
	 */
	wmark_low = max(100U - sysctl_compaction_proactiveness, 5U);
	return low ? wmark_low : min(wmark_low + 10, 100U);
}

static bool should_proactive_compact_node(pg_data_t *pgdat)
{
	int wmark_high;

	if (!sysctl_compaction_proactiveness || kswapd_is_running(pgdat))
		return false;

	wmark_high = fragmentation_score_wmark(false);
	return fragmentation_score_node(pgdat) > wmark_high;
}

static enum compact_result __compact_finished(struct compact_control *cc)
{
	unsigned int order;
	const int migratetype = cc->migratetype;
	int ret;

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

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

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

	if (cc->proactive_compaction) {
		int score, wmark_low;
		pg_data_t *pgdat;

		pgdat = cc->zone->zone_pgdat;
		if (kswapd_is_running(pgdat))
			return COMPACT_PARTIAL_SKIPPED;

		score = fragmentation_score_zone(cc->zone);
		wmark_low = fragmentation_score_wmark(true);

		if (score > wmark_low)
			ret = COMPACT_CONTINUE;
		else
			ret = COMPACT_SUCCESS;

		goto out;
	}

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

	/*
	 * Always finish scanning a pageblock to reduce the possibility of
	 * fallbacks in the future. This is particularly important when
	 * migration source is unmovable/reclaimable but it's not worth
	 * special casing.
	 */
	if (!pageblock_aligned(cc->migrate_pfn))
		return COMPACT_CONTINUE;

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

		/* Job done if page is free of the right migratetype */
		if (!free_area_empty(area, migratetype))
			return COMPACT_SUCCESS;

#ifdef CONFIG_CMA
		/* MIGRATE_MOVABLE can fallback on MIGRATE_CMA */
		if (migratetype == MIGRATE_MOVABLE &&
			!free_area_empty(area, MIGRATE_CMA))
			return COMPACT_SUCCESS;
#endif
		/*
		 * Job done if allocation would steal freepages from
		 * other migratetype buddy lists.
		 */
		if (find_suitable_fallback(area, order, migratetype,
						true, &can_steal) != -1)
			/*
			 * Movable pages are OK in any pageblock. If we are
			 * stealing for a non-movable allocation, make sure
			 * we finish compacting the current pageblock first
			 * (which is assured by the above migrate_pfn align
			 * check) so it is as free as possible and we won't
			 * have to steal another one soon.
			 */
			return COMPACT_SUCCESS;
	}

out:
	if (cc->contended || fatal_signal_pending(current))
		ret = COMPACT_CONTENDED;

	return ret;
}

static enum compact_result compact_finished(struct compact_control *cc)
{
	int ret;

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

	return ret;
}

static bool __compaction_suitable(struct zone *zone, int order,
				  int highest_zoneidx,
				  unsigned long wmark_target)
{
	unsigned long watermark;
	/*
	 * Watermarks for order-0 must be met for compaction to be able to
	 * isolate free pages for migration targets. This means that the
	 * watermark and alloc_flags have to match, or be more pessimistic than
	 * the check in __isolate_free_page(). We don't use the direct
	 * compactor's alloc_flags, as they are not relevant for freepage
	 * isolation. We however do use the direct compactor's highest_zoneidx
	 * to skip over zones where lowmem reserves would prevent allocation
	 * even if compaction succeeds.
	 * For costly orders, we require low watermark instead of min for
	 * compaction to proceed to increase its chances.
	 * ALLOC_CMA is used, as pages in CMA pageblocks are considered
	 * suitable migration targets
	 */
	watermark = (order > PAGE_ALLOC_COSTLY_ORDER) ?
				low_wmark_pages(zone) : min_wmark_pages(zone);
	watermark += compact_gap(order);
	return __zone_watermark_ok(zone, 0, watermark, highest_zoneidx,
				   ALLOC_CMA, wmark_target);
}

/*
 * compaction_suitable: Is this suitable to run compaction on this zone now?
 */
bool compaction_suitable(struct zone *zone, int order, int highest_zoneidx)
{
	enum compact_result compact_result;
	bool suitable;

	suitable = __compaction_suitable(zone, order, highest_zoneidx,
					 zone_page_state(zone, NR_FREE_PAGES));
	/*
	 * fragmentation index determines if allocation failures are due to
	 * low memory or external fragmentation
	 *
	 * index of -1000 would imply allocations might succeed depending on
	 * watermarks, but we already failed the high-order watermark check
	 * index towards 0 implies failure is due to lack of memory
	 * index towards 1000 implies failure is due to fragmentation
	 *
	 * Only compact if a failure would be due to fragmentation. Also
	 * ignore fragindex for non-costly orders where the alternative to
	 * a successful reclaim/compaction is OOM. Fragindex and the
	 * vm.extfrag_threshold sysctl is meant as a heuristic to prevent
	 * excessive compaction for costly orders, but it should not be at the
	 * expense of system stability.
	 */
	if (suitable) {
		compact_result = COMPACT_CONTINUE;
		if (order > PAGE_ALLOC_COSTLY_ORDER) {
			int fragindex = fragmentation_index(zone, order);

			if (fragindex >= 0 &&
			    fragindex <= sysctl_extfrag_threshold) {
				suitable = false;
				compact_result = COMPACT_NOT_SUITABLE_ZONE;
			}
		}
	} else {
		compact_result = COMPACT_SKIPPED;
	}

	trace_mm_compaction_suitable(zone, order, compact_result);

	return suitable;
}

bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
		int alloc_flags)
{
	struct zone *zone;
	struct zoneref *z;

	/*
	 * Make sure at least one zone would pass __compaction_suitable if we continue
	 * retrying the reclaim.
	 */
	for_each_zone_zonelist_nodemask(zone, z, ac->zonelist,
				ac->highest_zoneidx, ac->nodemask) {
		unsigned long available;

		/*
		 * Do not consider all the reclaimable memory because we do not
		 * want to trash just for a single high order allocation which
		 * is even not guaranteed to appear even if __compaction_suitable
		 * is happy about the watermark check.
		 */
		available = zone_reclaimable_pages(zone) / order;
		available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
		if (__compaction_suitable(zone, order, ac->highest_zoneidx,
					  available))
			return true;
	}

	return false;
}

/*
 * Should we do compaction for target allocation order.
 * Return COMPACT_SUCCESS if allocation for target order can be already
 * satisfied
 * Return COMPACT_SKIPPED if compaction for target order is likely to fail
 * Return COMPACT_CONTINUE if compaction for target order should be ran
 */
static enum compact_result
compaction_suit_allocation_order(struct zone *zone, unsigned int order,
				 int highest_zoneidx, unsigned int alloc_flags)
{
	unsigned long watermark;

	watermark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK);
	if (zone_watermark_ok(zone, order, watermark, highest_zoneidx,
			      alloc_flags))
		return COMPACT_SUCCESS;

	if (!compaction_suitable(zone, order, highest_zoneidx))
		return COMPACT_SKIPPED;

	return COMPACT_CONTINUE;
}

static enum compact_result
compact_zone(struct compact_control *cc, struct capture_control *capc)
{
	enum compact_result ret;
	unsigned long start_pfn = cc->zone->zone_start_pfn;
	unsigned long end_pfn = zone_end_pfn(cc->zone);
	unsigned long last_migrated_pfn;
	const bool sync = cc->mode != MIGRATE_ASYNC;
	bool update_cached;
	unsigned int nr_succeeded = 0, nr_migratepages;
	int order;

	/*
	 * These counters track activities during zone compaction.  Initialize
	 * them before compacting a new zone.
	 */
	cc->total_migrate_scanned = 0;
	cc->total_free_scanned = 0;
	cc->nr_migratepages = 0;
	cc->nr_freepages = 0;
	for (order = 0; order < NR_PAGE_ORDERS; order++)
		INIT_LIST_HEAD(&cc->freepages[order]);
	INIT_LIST_HEAD(&cc->migratepages);

	cc->migratetype = gfp_migratetype(cc->gfp_mask);

	if (!is_via_compact_memory(cc->order)) {
		ret = compaction_suit_allocation_order(cc->zone, cc->order,
						       cc->highest_zoneidx,
						       cc->alloc_flags);
		if (ret != COMPACT_CONTINUE)
			return ret;
	}

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

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

		if (cc->migrate_pfn <= cc->zone->compact_init_migrate_pfn)
			cc->whole_zone = true;
	}

	last_migrated_pfn = 0;

	/*
	 * Migrate has separate cached PFNs for ASYNC and SYNC* migration on
	 * the basis that some migrations will fail in ASYNC mode. However,
	 * if the cached PFNs match and pageblocks are skipped due to having
	 * no isolation candidates, then the sync state does not matter.
	 * Until a pageblock with isolation candidates is found, keep the
	 * cached PFNs in sync to avoid revisiting the same blocks.
	 */
	update_cached = !sync &&
		cc->zone->compact_cached_migrate_pfn[0] == cc->zone->compact_cached_migrate_pfn[1];

	trace_mm_compaction_begin(cc, start_pfn, end_pfn, sync);

	/* lru_add_drain_all could be expensive with involving other CPUs */
	lru_add_drain();

	while ((ret = compact_finished(cc)) == COMPACT_CONTINUE) {
		int err;
		unsigned long iteration_start_pfn = cc->migrate_pfn;

		/*
		 * Avoid multiple rescans of the same pageblock which can
		 * happen if a page cannot be isolated (dirty/writeback in
		 * async mode) or if the migrated pages are being allocated
		 * before the pageblock is cleared.  The first rescan will
		 * capture the entire pageblock for migration. If it fails,
		 * it'll be marked skip and scanning will proceed as normal.
		 */
		cc->finish_pageblock = false;
		if (pageblock_start_pfn(last_migrated_pfn) ==
		    pageblock_start_pfn(iteration_start_pfn)) {
			cc->finish_pageblock = true;
		}

rescan:
		switch (isolate_migratepages(cc)) {
		case ISOLATE_ABORT:
			ret = COMPACT_CONTENDED;
			putback_movable_pages(&cc->migratepages);
			cc->nr_migratepages = 0;
			goto out;
		case ISOLATE_NONE:
			if (update_cached) {
				cc->zone->compact_cached_migrate_pfn[1] =
					cc->zone->compact_cached_migrate_pfn[0];
			}

			/*
			 * We haven't isolated and migrated anything, but
			 * there might still be unflushed migrations from
			 * previous cc->order aligned block.
			 */
			goto check_drain;
		case ISOLATE_SUCCESS:
			update_cached = false;
			last_migrated_pfn = max(cc->zone->zone_start_pfn,
				pageblock_start_pfn(cc->migrate_pfn - 1));
		}

		/*
		 * Record the number of pages to migrate since the
		 * compaction_alloc/free() will update cc->nr_migratepages
		 * properly.
		 */
		nr_migratepages = cc->nr_migratepages;
		err = migrate_pages(&cc->migratepages, compaction_alloc,
				compaction_free, (unsigned long)cc, cc->mode,
				MR_COMPACTION, &nr_succeeded);

		trace_mm_compaction_migratepages(nr_migratepages, nr_succeeded);

		/* All pages were either migrated or will be released */
		cc->nr_migratepages = 0;
		if (err) {
			putback_movable_pages(&cc->migratepages);
			/*
			 * migrate_pages() may return -ENOMEM when scanners meet
			 * and we want compact_finished() to detect it
			 */
			if (err == -ENOMEM && !compact_scanners_met(cc)) {
				ret = COMPACT_CONTENDED;
				goto out;
			}
			/*
			 * If an ASYNC or SYNC_LIGHT fails to migrate a page
			 * within the pageblock_order-aligned block and
			 * fast_find_migrateblock may be used then scan the
			 * remainder of the pageblock. This will mark the
			 * pageblock "skip" to avoid rescanning in the near
			 * future. This will isolate more pages than necessary
			 * for the request but avoid loops due to
			 * fast_find_migrateblock revisiting blocks that were
			 * recently partially scanned.
			 */
			if (!pageblock_aligned(cc->migrate_pfn) &&
			    !cc->ignore_skip_hint && !cc->finish_pageblock &&
			    (cc->mode < MIGRATE_SYNC)) {
				cc->finish_pageblock = true;

				/*
				 * Draining pcplists does not help THP if
				 * any page failed to migrate. Even after
				 * drain, the pageblock will not be free.
				 */
				if (cc->order == COMPACTION_HPAGE_ORDER)
					last_migrated_pfn = 0;

				goto rescan;
			}
		}

		/* Stop if a page has been captured */
		if (capc && capc->page) {
			ret = COMPACT_SUCCESS;
			break;
		}

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

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

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

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

	count_compact_events(COMPACTMIGRATE_SCANNED, cc->total_migrate_scanned);
	count_compact_events(COMPACTFREE_SCANNED, cc->total_free_scanned);

	trace_mm_compaction_end(cc, start_pfn, end_pfn, sync, ret);

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

	return ret;
}

static enum compact_result compact_zone_order(struct zone *zone, int order,
		gfp_t gfp_mask, enum compact_priority prio,
		unsigned int alloc_flags, int highest_zoneidx,
		struct page **capture)
{
	enum compact_result ret;
	struct compact_control cc = {
		.order = order,
		.search_order = order,
		.gfp_mask = gfp_mask,
		.zone = zone,
		.mode = (prio == COMPACT_PRIO_ASYNC) ?
					MIGRATE_ASYNC :	MIGRATE_SYNC_LIGHT,
		.alloc_flags = alloc_flags,
		.highest_zoneidx = highest_zoneidx,
		.direct_compaction = true,
		.whole_zone = (prio == MIN_COMPACT_PRIORITY),
		.ignore_skip_hint = (prio == MIN_COMPACT_PRIORITY),
		.ignore_block_suitable = (prio == MIN_COMPACT_PRIORITY)
	};
	struct capture_control capc = {
		.cc = &cc,
		.page = NULL,
	};

	/*
	 * Make sure the structs are really initialized before we expose the
	 * capture control, in case we are interrupted and the interrupt handler
	 * frees a page.
	 */
	barrier();
	WRITE_ONCE(current->capture_control, &capc);

	ret = compact_zone(&cc, &capc);

	/*
	 * Make sure we hide capture control first before we read the captured
	 * page pointer, otherwise an interrupt could free and capture a page
	 * and we would leak it.
	 */
	WRITE_ONCE(current->capture_control, NULL);
	*capture = READ_ONCE(capc.page);
	/*
	 * Technically, it is also possible that compaction is skipped but
	 * the page is still captured out of luck(IRQ came and freed the page).
	 * Returning COMPACT_SUCCESS in such cases helps in properly accounting
	 * the COMPACT[STALL|FAIL] when compaction is skipped.
	 */
	if (*capture)
		ret = COMPACT_SUCCESS;

	return ret;
}

/**
 * try_to_compact_pages - Direct compact to satisfy a high-order allocation
 * @gfp_mask: The GFP mask of the current allocation
 * @order: The order of the current allocation
 * @alloc_flags: The allocation flags of the current allocation
 * @ac: The context of current allocation
 * @prio: Determines how hard direct compaction should try to succeed
 * @capture: Pointer to free page created by compaction will be stored here
 *
 * This is the main entry point for direct page compaction.
 */
enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
		unsigned int alloc_flags, const struct alloc_context *ac,
		enum compact_priority prio, struct page **capture)
{
	struct zoneref *z;
	struct zone *zone;
	enum compact_result rc = COMPACT_SKIPPED;

	if (!gfp_compaction_allowed(gfp_mask))
		return COMPACT_SKIPPED;

	trace_mm_compaction_try_to_compact_pages(order, gfp_mask, prio);

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

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

		status = compact_zone_order(zone, order, gfp_mask, prio,
				alloc_flags, ac->highest_zoneidx, capture);
		rc = max(status, rc);

		/* The allocation should succeed, stop compacting */
		if (status == COMPACT_SUCCESS) {
			/*
			 * We think the allocation will succeed in this zone,
			 * but it is not certain, hence the false. The caller
			 * will repeat this with true if allocation indeed
			 * succeeds in this zone.
			 */
			compaction_defer_reset(zone, order, false);

			break;
		}

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

		/*
		 * We might have stopped compacting due to need_resched() in
		 * async compaction, or due to a fatal signal detected. In that
		 * case do not try further zones
		 */
		if ((prio == COMPACT_PRIO_ASYNC && need_resched())
					|| fatal_signal_pending(current))
			break;
	}

	return rc;
}

/*
 * compact_node() - compact all zones within a node
 * @pgdat: The node page data
 * @proactive: Whether the compaction is proactive
 *
 * For proactive compaction, compact till each zone's fragmentation score
 * reaches within proactive compaction thresholds (as determined by the
 * proactiveness tunable), it is possible that the function returns before
 * reaching score targets due to various back-off conditions, such as,
 * contention on per-node or per-zone locks.
 */
static int compact_node(pg_data_t *pgdat, bool proactive)
{
	int zoneid;
	struct zone *zone;
	struct compact_control cc = {
		.order = -1,
		.mode = proactive ? MIGRATE_SYNC_LIGHT : MIGRATE_SYNC,
		.ignore_skip_hint = true,
		.whole_zone = true,
		.gfp_mask = GFP_KERNEL,
		.proactive_compaction = proactive,
	};

	for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
		zone = &pgdat->node_zones[zoneid];
		if (!populated_zone(zone))
			continue;

		if (fatal_signal_pending(current))
			return -EINTR;

		cc.zone = zone;

		compact_zone(&cc, NULL);

		if (proactive) {
			count_compact_events(KCOMPACTD_MIGRATE_SCANNED,
					     cc.total_migrate_scanned);
			count_compact_events(KCOMPACTD_FREE_SCANNED,
					     cc.total_free_scanned);
		}
	}

	return 0;
}

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

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

	for_each_online_node(nid) {
		ret = compact_node(NODE_DATA(nid), false);
		if (ret)
			return ret;
	}

	return 0;
}

static int compaction_proactiveness_sysctl_handler(struct ctl_table *table, int write,
		void *buffer, size_t *length, loff_t *ppos)
{
	int rc, nid;

	rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
	if (rc)
		return rc;

	if (write && sysctl_compaction_proactiveness) {
		for_each_online_node(nid) {
			pg_data_t *pgdat = NODE_DATA(nid);

			if (pgdat->proactive_compact_trigger)
				continue;

			pgdat->proactive_compact_trigger = true;
			trace_mm_compaction_wakeup_kcompactd(pgdat->node_id, -1,
							     pgdat->nr_zones - 1);
			wake_up_interruptible(&pgdat->kcompactd_wait);
		}
	}

	return 0;
}

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

	ret = proc_dointvec(table, write, buffer, length, ppos);
	if (ret)
		return ret;

	if (sysctl_compact_memory != 1)
		return -EINVAL;

	if (write)
		ret = compact_nodes();

	return ret;
}

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

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

		compact_node(NODE_DATA(nid), false);
	}

	return count;
}
static DEVICE_ATTR_WO(compact);

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

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

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

static bool kcompactd_node_suitable(pg_data_t *pgdat)
{
	int zoneid;
	struct zone *zone;
	enum zone_type highest_zoneidx = pgdat->kcompactd_highest_zoneidx;
	enum compact_result ret;

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

		if (!populated_zone(zone))
			continue;

		ret = compaction_suit_allocation_order(zone,
				pgdat->kcompactd_max_order,
				highest_zoneidx, ALLOC_WMARK_MIN);
		if (ret == COMPACT_CONTINUE)
			return true;
	}

	return false;
}

static void kcompactd_do_work(pg_data_t *pgdat)
{
	/*
	 * With no special task, compact all zones so that a page of requested
	 * order is allocatable.
	 */
	int zoneid;
	struct zone *zone;
	struct compact_control cc = {
		.order = pgdat->kcompactd_max_order,
		.search_order = pgdat->kcompactd_max_order,
		.highest_zoneidx = pgdat->kcompactd_highest_zoneidx,
		.mode = MIGRATE_SYNC_LIGHT,
		.ignore_skip_hint = false,
		.gfp_mask = GFP_KERNEL,
	};
	enum compact_result ret;

	trace_mm_compaction_kcompactd_wake(pgdat->node_id, cc.order,
							cc.highest_zoneidx);
	count_compact_event(KCOMPACTD_WAKE);

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

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

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

		ret = compaction_suit_allocation_order(zone,
				cc.order, zoneid, ALLOC_WMARK_MIN);
		if (ret != COMPACT_CONTINUE)
			continue;

		if (kthread_should_stop())
			return;

		cc.zone = zone;
		status = compact_zone(&cc, NULL);

		if (status == COMPACT_SUCCESS) {
			compaction_defer_reset(zone, cc.order, false);
		} else if (status == COMPACT_PARTIAL_SKIPPED || status == COMPACT_COMPLETE) {
			/*
			 * Buddy pages may become stranded on pcps that could
			 * otherwise coalesce on the zone's free area for
			 * order >= cc.order.  This is ratelimited by the
			 * upcoming deferral.
			 */
			drain_all_pages(zone);

			/*
			 * We use sync migration mode here, so we defer like
			 * sync direct compaction does.
			 */
			defer_compaction(zone, cc.order);
		}

		count_compact_events(KCOMPACTD_MIGRATE_SCANNED,
				     cc.total_migrate_scanned);
		count_compact_events(KCOMPACTD_FREE_SCANNED,
				     cc.total_free_scanned);
	}

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

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

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

	if (pgdat->kcompactd_highest_zoneidx > highest_zoneidx)
		pgdat->kcompactd_highest_zoneidx = highest_zoneidx;

	/*
	 * Pairs with implicit barrier in wait_event_freezable()
	 * such that wakeups are not missed.
	 */
	if (!wq_has_sleeper(&pgdat->kcompactd_wait))
		return;

	if (!kcompactd_node_suitable(pgdat))
		return;

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

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

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

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

	set_freezable();

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

	while (!kthread_should_stop()) {
		unsigned long pflags;

		/*
		 * Avoid the unnecessary wakeup for proactive compaction
		 * when it is disabled.
		 */
		if (!sysctl_compaction_proactiveness)
			timeout = MAX_SCHEDULE_TIMEOUT;
		trace_mm_compaction_kcompactd_sleep(pgdat->node_id);
		if (wait_event_freezable_timeout(pgdat->kcompactd_wait,
			kcompactd_work_requested(pgdat), timeout) &&
			!pgdat->proactive_compact_trigger) {

			psi_memstall_enter(&pflags);
			kcompactd_do_work(pgdat);
			psi_memstall_leave(&pflags);
			/*
			 * Reset the timeout value. The defer timeout from
			 * proactive compaction is lost here but that is fine
			 * as the condition of the zone changing substantionally
			 * then carrying on with the previous defer interval is
			 * not useful.
			 */
			timeout = default_timeout;
			continue;
		}

		/*
		 * Start the proactive work with default timeout. Based
		 * on the fragmentation score, this timeout is updated.
		 */
		timeout = default_timeout;
		if (should_proactive_compact_node(pgdat)) {
			unsigned int prev_score, score;

			prev_score = fragmentation_score_node(pgdat);
			compact_node(pgdat, true);
			score = fragmentation_score_node(pgdat);
			/*
			 * Defer proactive compaction if the fragmentation
			 * score did not go down i.e. no progress made.
			 */
			if (unlikely(score >= prev_score))
				timeout =
				   default_timeout << COMPACT_MAX_DEFER_SHIFT;
		}
		if (unlikely(pgdat->proactive_compact_trigger))
			pgdat->proactive_compact_trigger = false;
	}

	return 0;
}

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

	if (pgdat->kcompactd)
		return;

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

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

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

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

	for_each_node_state(nid, N_MEMORY) {
		pg_data_t *pgdat = NODE_DATA(nid);
		const struct cpumask *mask;

		mask = cpumask_of_node(pgdat->node_id);

		if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
			/* One of our CPUs online: restore mask */
			if (pgdat->kcompactd)
				set_cpus_allowed_ptr(pgdat->kcompactd, mask);
	}
	return 0;
}

static int proc_dointvec_minmax_warn_RT_change(struct ctl_table *table,
		int write, void *buffer, size_t *lenp, loff_t *ppos)
{
	int ret, old;

	if (!IS_ENABLED(CONFIG_PREEMPT_RT) || !write)
		return proc_dointvec_minmax(table, write, buffer, lenp, ppos);

	old = *(int *)table->data;
	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
	if (ret)
		return ret;
	if (old != *(int *)table->data)
		pr_warn_once("sysctl attribute %s changed by %s[%d]\n",
			     table->procname, current->comm,
			     task_pid_nr(current));
	return ret;
}

static struct ctl_table vm_compaction[] = {
	{
		.procname	= "compact_memory",
		.data		= &sysctl_compact_memory,
		.maxlen		= sizeof(int),
		.mode		= 0200,
		.proc_handler	= sysctl_compaction_handler,
	},
	{
		.procname	= "compaction_proactiveness",
		.data		= &sysctl_compaction_proactiveness,
		.maxlen		= sizeof(sysctl_compaction_proactiveness),
		.mode		= 0644,
		.proc_handler	= compaction_proactiveness_sysctl_handler,
		.extra1		= SYSCTL_ZERO,
		.extra2		= SYSCTL_ONE_HUNDRED,
	},
	{
		.procname	= "extfrag_threshold",
		.data		= &sysctl_extfrag_threshold,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= SYSCTL_ZERO,
		.extra2		= SYSCTL_ONE_THOUSAND,
	},
	{
		.procname	= "compact_unevictable_allowed",
		.data		= &sysctl_compact_unevictable_allowed,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax_warn_RT_change,
		.extra1		= SYSCTL_ZERO,
		.extra2		= SYSCTL_ONE,
	},
};

static int __init kcompactd_init(void)
{
	int nid;
	int ret;

	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
					"mm/compaction:online",
					kcompactd_cpu_online, NULL);
	if (ret < 0) {
		pr_err("kcompactd: failed to register hotplug callbacks.\n");
		return ret;
	}

	for_each_node_state(nid, N_MEMORY)
		kcompactd_run(nid);
	register_sysctl_init("vm", vm_compaction);
	return 0;
}
subsys_initcall(kcompactd_init)

#endif /* CONFIG_COMPACTION */