summaryrefslogtreecommitdiff
path: root/mm/huge_memory.c
blob: 4fc43859e59a31932a657cd2fac2b511c00e812b (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 *  Copyright (C) 2009  Red Hat, Inc.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/sched/coredump.h>
#include <linux/sched/numa_balancing.h>
#include <linux/highmem.h>
#include <linux/hugetlb.h>
#include <linux/mmu_notifier.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/shrinker.h>
#include <linux/mm_inline.h>
#include <linux/swapops.h>
#include <linux/backing-dev.h>
#include <linux/dax.h>
#include <linux/khugepaged.h>
#include <linux/freezer.h>
#include <linux/pfn_t.h>
#include <linux/mman.h>
#include <linux/memremap.h>
#include <linux/pagemap.h>
#include <linux/debugfs.h>
#include <linux/migrate.h>
#include <linux/hashtable.h>
#include <linux/userfaultfd_k.h>
#include <linux/page_idle.h>
#include <linux/shmem_fs.h>
#include <linux/oom.h>
#include <linux/numa.h>
#include <linux/page_owner.h>
#include <linux/sched/sysctl.h>
#include <linux/memory-tiers.h>

#include <asm/tlb.h>
#include <asm/pgalloc.h>
#include "internal.h"
#include "swap.h"

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

/*
 * By default, transparent hugepage support is disabled in order to avoid
 * risking an increased memory footprint for applications that are not
 * guaranteed to benefit from it. When transparent hugepage support is
 * enabled, it is for all mappings, and khugepaged scans all mappings.
 * Defrag is invoked by khugepaged hugepage allocations and by page faults
 * for all hugepage allocations.
 */
unsigned long transparent_hugepage_flags __read_mostly =
#ifdef CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS
	(1<<TRANSPARENT_HUGEPAGE_FLAG)|
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE_MADVISE
	(1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)|
#endif
	(1<<TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG)|
	(1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)|
	(1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);

static struct shrinker deferred_split_shrinker;

static atomic_t huge_zero_refcount;
struct page *huge_zero_page __read_mostly;
unsigned long huge_zero_pfn __read_mostly = ~0UL;

bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags,
			bool smaps, bool in_pf, bool enforce_sysfs)
{
	if (!vma->vm_mm)		/* vdso */
		return false;

	/*
	 * Explicitly disabled through madvise or prctl, or some
	 * architectures may disable THP for some mappings, for
	 * example, s390 kvm.
	 * */
	if ((vm_flags & VM_NOHUGEPAGE) ||
	    test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
		return false;
	/*
	 * If the hardware/firmware marked hugepage support disabled.
	 */
	if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_NEVER_DAX))
		return false;

	/* khugepaged doesn't collapse DAX vma, but page fault is fine. */
	if (vma_is_dax(vma))
		return in_pf;

	/*
	 * Special VMA and hugetlb VMA.
	 * Must be checked after dax since some dax mappings may have
	 * VM_MIXEDMAP set.
	 */
	if (vm_flags & VM_NO_KHUGEPAGED)
		return false;

	/*
	 * Check alignment for file vma and size for both file and anon vma.
	 *
	 * Skip the check for page fault. Huge fault does the check in fault
	 * handlers. And this check is not suitable for huge PUD fault.
	 */
	if (!in_pf &&
	    !transhuge_vma_suitable(vma, (vma->vm_end - HPAGE_PMD_SIZE)))
		return false;

	/*
	 * Enabled via shmem mount options or sysfs settings.
	 * Must be done before hugepage flags check since shmem has its
	 * own flags.
	 */
	if (!in_pf && shmem_file(vma->vm_file))
		return shmem_is_huge(file_inode(vma->vm_file), vma->vm_pgoff,
				     !enforce_sysfs, vma->vm_mm, vm_flags);

	/* Enforce sysfs THP requirements as necessary */
	if (enforce_sysfs &&
	    (!hugepage_flags_enabled() || (!(vm_flags & VM_HUGEPAGE) &&
					   !hugepage_flags_always())))
		return false;

	/* Only regular file is valid */
	if (!in_pf && file_thp_enabled(vma))
		return true;

	if (!vma_is_anonymous(vma))
		return false;

	if (vma_is_temporary_stack(vma))
		return false;

	/*
	 * THPeligible bit of smaps should show 1 for proper VMAs even
	 * though anon_vma is not initialized yet.
	 *
	 * Allow page fault since anon_vma may be not initialized until
	 * the first page fault.
	 */
	if (!vma->anon_vma)
		return (smaps || in_pf);

	return true;
}

static bool get_huge_zero_page(void)
{
	struct page *zero_page;
retry:
	if (likely(atomic_inc_not_zero(&huge_zero_refcount)))
		return true;

	zero_page = alloc_pages((GFP_TRANSHUGE | __GFP_ZERO) & ~__GFP_MOVABLE,
			HPAGE_PMD_ORDER);
	if (!zero_page) {
		count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED);
		return false;
	}
	preempt_disable();
	if (cmpxchg(&huge_zero_page, NULL, zero_page)) {
		preempt_enable();
		__free_pages(zero_page, compound_order(zero_page));
		goto retry;
	}
	WRITE_ONCE(huge_zero_pfn, page_to_pfn(zero_page));

	/* We take additional reference here. It will be put back by shrinker */
	atomic_set(&huge_zero_refcount, 2);
	preempt_enable();
	count_vm_event(THP_ZERO_PAGE_ALLOC);
	return true;
}

static void put_huge_zero_page(void)
{
	/*
	 * Counter should never go to zero here. Only shrinker can put
	 * last reference.
	 */
	BUG_ON(atomic_dec_and_test(&huge_zero_refcount));
}

struct page *mm_get_huge_zero_page(struct mm_struct *mm)
{
	if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags))
		return READ_ONCE(huge_zero_page);

	if (!get_huge_zero_page())
		return NULL;

	if (test_and_set_bit(MMF_HUGE_ZERO_PAGE, &mm->flags))
		put_huge_zero_page();

	return READ_ONCE(huge_zero_page);
}

void mm_put_huge_zero_page(struct mm_struct *mm)
{
	if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags))
		put_huge_zero_page();
}

static unsigned long shrink_huge_zero_page_count(struct shrinker *shrink,
					struct shrink_control *sc)
{
	/* we can free zero page only if last reference remains */
	return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0;
}

static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
				       struct shrink_control *sc)
{
	if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
		struct page *zero_page = xchg(&huge_zero_page, NULL);
		BUG_ON(zero_page == NULL);
		WRITE_ONCE(huge_zero_pfn, ~0UL);
		__free_pages(zero_page, compound_order(zero_page));
		return HPAGE_PMD_NR;
	}

	return 0;
}

static struct shrinker huge_zero_page_shrinker = {
	.count_objects = shrink_huge_zero_page_count,
	.scan_objects = shrink_huge_zero_page_scan,
	.seeks = DEFAULT_SEEKS,
};

#ifdef CONFIG_SYSFS
static ssize_t enabled_show(struct kobject *kobj,
			    struct kobj_attribute *attr, char *buf)
{
	const char *output;

	if (test_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags))
		output = "[always] madvise never";
	else if (test_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
			  &transparent_hugepage_flags))
		output = "always [madvise] never";
	else
		output = "always madvise [never]";

	return sysfs_emit(buf, "%s\n", output);
}

static ssize_t enabled_store(struct kobject *kobj,
			     struct kobj_attribute *attr,
			     const char *buf, size_t count)
{
	ssize_t ret = count;

	if (sysfs_streq(buf, "always")) {
		clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
		set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
	} else if (sysfs_streq(buf, "madvise")) {
		clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
		set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
	} else if (sysfs_streq(buf, "never")) {
		clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
		clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
	} else
		ret = -EINVAL;

	if (ret > 0) {
		int err = start_stop_khugepaged();
		if (err)
			ret = err;
	}
	return ret;
}

static struct kobj_attribute enabled_attr = __ATTR_RW(enabled);

ssize_t single_hugepage_flag_show(struct kobject *kobj,
				  struct kobj_attribute *attr, char *buf,
				  enum transparent_hugepage_flag flag)
{
	return sysfs_emit(buf, "%d\n",
			  !!test_bit(flag, &transparent_hugepage_flags));
}

ssize_t single_hugepage_flag_store(struct kobject *kobj,
				 struct kobj_attribute *attr,
				 const char *buf, size_t count,
				 enum transparent_hugepage_flag flag)
{
	unsigned long value;
	int ret;

	ret = kstrtoul(buf, 10, &value);
	if (ret < 0)
		return ret;
	if (value > 1)
		return -EINVAL;

	if (value)
		set_bit(flag, &transparent_hugepage_flags);
	else
		clear_bit(flag, &transparent_hugepage_flags);

	return count;
}

static ssize_t defrag_show(struct kobject *kobj,
			   struct kobj_attribute *attr, char *buf)
{
	const char *output;

	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG,
		     &transparent_hugepage_flags))
		output = "[always] defer defer+madvise madvise never";
	else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG,
			  &transparent_hugepage_flags))
		output = "always [defer] defer+madvise madvise never";
	else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG,
			  &transparent_hugepage_flags))
		output = "always defer [defer+madvise] madvise never";
	else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG,
			  &transparent_hugepage_flags))
		output = "always defer defer+madvise [madvise] never";
	else
		output = "always defer defer+madvise madvise [never]";

	return sysfs_emit(buf, "%s\n", output);
}

static ssize_t defrag_store(struct kobject *kobj,
			    struct kobj_attribute *attr,
			    const char *buf, size_t count)
{
	if (sysfs_streq(buf, "always")) {
		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
	} else if (sysfs_streq(buf, "defer+madvise")) {
		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
	} else if (sysfs_streq(buf, "defer")) {
		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
	} else if (sysfs_streq(buf, "madvise")) {
		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
	} else if (sysfs_streq(buf, "never")) {
		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
	} else
		return -EINVAL;

	return count;
}
static struct kobj_attribute defrag_attr = __ATTR_RW(defrag);

static ssize_t use_zero_page_show(struct kobject *kobj,
				  struct kobj_attribute *attr, char *buf)
{
	return single_hugepage_flag_show(kobj, attr, buf,
					 TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
}
static ssize_t use_zero_page_store(struct kobject *kobj,
		struct kobj_attribute *attr, const char *buf, size_t count)
{
	return single_hugepage_flag_store(kobj, attr, buf, count,
				 TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
}
static struct kobj_attribute use_zero_page_attr = __ATTR_RW(use_zero_page);

static ssize_t hpage_pmd_size_show(struct kobject *kobj,
				   struct kobj_attribute *attr, char *buf)
{
	return sysfs_emit(buf, "%lu\n", HPAGE_PMD_SIZE);
}
static struct kobj_attribute hpage_pmd_size_attr =
	__ATTR_RO(hpage_pmd_size);

static struct attribute *hugepage_attr[] = {
	&enabled_attr.attr,
	&defrag_attr.attr,
	&use_zero_page_attr.attr,
	&hpage_pmd_size_attr.attr,
#ifdef CONFIG_SHMEM
	&shmem_enabled_attr.attr,
#endif
	NULL,
};

static const struct attribute_group hugepage_attr_group = {
	.attrs = hugepage_attr,
};

static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj)
{
	int err;

	*hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj);
	if (unlikely(!*hugepage_kobj)) {
		pr_err("failed to create transparent hugepage kobject\n");
		return -ENOMEM;
	}

	err = sysfs_create_group(*hugepage_kobj, &hugepage_attr_group);
	if (err) {
		pr_err("failed to register transparent hugepage group\n");
		goto delete_obj;
	}

	err = sysfs_create_group(*hugepage_kobj, &khugepaged_attr_group);
	if (err) {
		pr_err("failed to register transparent hugepage group\n");
		goto remove_hp_group;
	}

	return 0;

remove_hp_group:
	sysfs_remove_group(*hugepage_kobj, &hugepage_attr_group);
delete_obj:
	kobject_put(*hugepage_kobj);
	return err;
}

static void __init hugepage_exit_sysfs(struct kobject *hugepage_kobj)
{
	sysfs_remove_group(hugepage_kobj, &khugepaged_attr_group);
	sysfs_remove_group(hugepage_kobj, &hugepage_attr_group);
	kobject_put(hugepage_kobj);
}
#else
static inline int hugepage_init_sysfs(struct kobject **hugepage_kobj)
{
	return 0;
}

static inline void hugepage_exit_sysfs(struct kobject *hugepage_kobj)
{
}
#endif /* CONFIG_SYSFS */

static int __init hugepage_init(void)
{
	int err;
	struct kobject *hugepage_kobj;

	if (!has_transparent_hugepage()) {
		/*
		 * Hardware doesn't support hugepages, hence disable
		 * DAX PMD support.
		 */
		transparent_hugepage_flags = 1 << TRANSPARENT_HUGEPAGE_NEVER_DAX;
		return -EINVAL;
	}

	/*
	 * hugepages can't be allocated by the buddy allocator
	 */
	MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER >= MAX_ORDER);
	/*
	 * we use page->mapping and page->index in second tail page
	 * as list_head: assuming THP order >= 2
	 */
	MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER < 2);

	err = hugepage_init_sysfs(&hugepage_kobj);
	if (err)
		goto err_sysfs;

	err = khugepaged_init();
	if (err)
		goto err_slab;

	err = register_shrinker(&huge_zero_page_shrinker, "thp-zero");
	if (err)
		goto err_hzp_shrinker;
	err = register_shrinker(&deferred_split_shrinker, "thp-deferred_split");
	if (err)
		goto err_split_shrinker;

	/*
	 * By default disable transparent hugepages on smaller systems,
	 * where the extra memory used could hurt more than TLB overhead
	 * is likely to save.  The admin can still enable it through /sys.
	 */
	if (totalram_pages() < (512 << (20 - PAGE_SHIFT))) {
		transparent_hugepage_flags = 0;
		return 0;
	}

	err = start_stop_khugepaged();
	if (err)
		goto err_khugepaged;

	return 0;
err_khugepaged:
	unregister_shrinker(&deferred_split_shrinker);
err_split_shrinker:
	unregister_shrinker(&huge_zero_page_shrinker);
err_hzp_shrinker:
	khugepaged_destroy();
err_slab:
	hugepage_exit_sysfs(hugepage_kobj);
err_sysfs:
	return err;
}
subsys_initcall(hugepage_init);

static int __init setup_transparent_hugepage(char *str)
{
	int ret = 0;
	if (!str)
		goto out;
	if (!strcmp(str, "always")) {
		set_bit(TRANSPARENT_HUGEPAGE_FLAG,
			&transparent_hugepage_flags);
		clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
			  &transparent_hugepage_flags);
		ret = 1;
	} else if (!strcmp(str, "madvise")) {
		clear_bit(TRANSPARENT_HUGEPAGE_FLAG,
			  &transparent_hugepage_flags);
		set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
			&transparent_hugepage_flags);
		ret = 1;
	} else if (!strcmp(str, "never")) {
		clear_bit(TRANSPARENT_HUGEPAGE_FLAG,
			  &transparent_hugepage_flags);
		clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
			  &transparent_hugepage_flags);
		ret = 1;
	}
out:
	if (!ret)
		pr_warn("transparent_hugepage= cannot parse, ignored\n");
	return ret;
}
__setup("transparent_hugepage=", setup_transparent_hugepage);

pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
{
	if (likely(vma->vm_flags & VM_WRITE))
		pmd = pmd_mkwrite(pmd);
	return pmd;
}

#ifdef CONFIG_MEMCG
static inline
struct deferred_split *get_deferred_split_queue(struct folio *folio)
{
	struct mem_cgroup *memcg = folio_memcg(folio);
	struct pglist_data *pgdat = NODE_DATA(folio_nid(folio));

	if (memcg)
		return &memcg->deferred_split_queue;
	else
		return &pgdat->deferred_split_queue;
}
#else
static inline
struct deferred_split *get_deferred_split_queue(struct folio *folio)
{
	struct pglist_data *pgdat = NODE_DATA(folio_nid(folio));

	return &pgdat->deferred_split_queue;
}
#endif

void prep_transhuge_page(struct page *page)
{
	struct folio *folio = (struct folio *)page;

	VM_BUG_ON_FOLIO(folio_order(folio) < 2, folio);
	INIT_LIST_HEAD(&folio->_deferred_list);
	set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR);
}

static inline bool is_transparent_hugepage(struct page *page)
{
	struct folio *folio;

	if (!PageCompound(page))
		return false;

	folio = page_folio(page);
	return is_huge_zero_page(&folio->page) ||
	       folio->_folio_dtor == TRANSHUGE_PAGE_DTOR;
}

static unsigned long __thp_get_unmapped_area(struct file *filp,
		unsigned long addr, unsigned long len,
		loff_t off, unsigned long flags, unsigned long size)
{
	loff_t off_end = off + len;
	loff_t off_align = round_up(off, size);
	unsigned long len_pad, ret;

	if (off_end <= off_align || (off_end - off_align) < size)
		return 0;

	len_pad = len + size;
	if (len_pad < len || (off + len_pad) < off)
		return 0;

	ret = current->mm->get_unmapped_area(filp, addr, len_pad,
					      off >> PAGE_SHIFT, flags);

	/*
	 * The failure might be due to length padding. The caller will retry
	 * without the padding.
	 */
	if (IS_ERR_VALUE(ret))
		return 0;

	/*
	 * Do not try to align to THP boundary if allocation at the address
	 * hint succeeds.
	 */
	if (ret == addr)
		return addr;

	ret += (off - ret) & (size - 1);
	return ret;
}

unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr,
		unsigned long len, unsigned long pgoff, unsigned long flags)
{
	unsigned long ret;
	loff_t off = (loff_t)pgoff << PAGE_SHIFT;

	ret = __thp_get_unmapped_area(filp, addr, len, off, flags, PMD_SIZE);
	if (ret)
		return ret;

	return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
}
EXPORT_SYMBOL_GPL(thp_get_unmapped_area);

static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
			struct page *page, gfp_t gfp)
{
	struct vm_area_struct *vma = vmf->vma;
	pgtable_t pgtable;
	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
	vm_fault_t ret = 0;

	VM_BUG_ON_PAGE(!PageCompound(page), page);

	if (mem_cgroup_charge(page_folio(page), vma->vm_mm, gfp)) {
		put_page(page);
		count_vm_event(THP_FAULT_FALLBACK);
		count_vm_event(THP_FAULT_FALLBACK_CHARGE);
		return VM_FAULT_FALLBACK;
	}
	cgroup_throttle_swaprate(page, gfp);

	pgtable = pte_alloc_one(vma->vm_mm);
	if (unlikely(!pgtable)) {
		ret = VM_FAULT_OOM;
		goto release;
	}

	clear_huge_page(page, vmf->address, HPAGE_PMD_NR);
	/*
	 * The memory barrier inside __SetPageUptodate makes sure that
	 * clear_huge_page writes become visible before the set_pmd_at()
	 * write.
	 */
	__SetPageUptodate(page);

	vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
	if (unlikely(!pmd_none(*vmf->pmd))) {
		goto unlock_release;
	} else {
		pmd_t entry;

		ret = check_stable_address_space(vma->vm_mm);
		if (ret)
			goto unlock_release;

		/* Deliver the page fault to userland */
		if (userfaultfd_missing(vma)) {
			spin_unlock(vmf->ptl);
			put_page(page);
			pte_free(vma->vm_mm, pgtable);
			ret = handle_userfault(vmf, VM_UFFD_MISSING);
			VM_BUG_ON(ret & VM_FAULT_FALLBACK);
			return ret;
		}

		entry = mk_huge_pmd(page, vma->vm_page_prot);
		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
		page_add_new_anon_rmap(page, vma, haddr);
		lru_cache_add_inactive_or_unevictable(page, vma);
		pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
		set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry);
		update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
		add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
		mm_inc_nr_ptes(vma->vm_mm);
		spin_unlock(vmf->ptl);
		count_vm_event(THP_FAULT_ALLOC);
		count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC);
	}

	return 0;
unlock_release:
	spin_unlock(vmf->ptl);
release:
	if (pgtable)
		pte_free(vma->vm_mm, pgtable);
	put_page(page);
	return ret;

}

/*
 * always: directly stall for all thp allocations
 * defer: wake kswapd and fail if not immediately available
 * defer+madvise: wake kswapd and directly stall for MADV_HUGEPAGE, otherwise
 *		  fail if not immediately available
 * madvise: directly stall for MADV_HUGEPAGE, otherwise fail if not immediately
 *	    available
 * never: never stall for any thp allocation
 */
gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma)
{
	const bool vma_madvised = vma && (vma->vm_flags & VM_HUGEPAGE);

	/* Always do synchronous compaction */
	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
		return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY);

	/* Kick kcompactd and fail quickly */
	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
		return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM;

	/* Synchronous compaction if madvised, otherwise kick kcompactd */
	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags))
		return GFP_TRANSHUGE_LIGHT |
			(vma_madvised ? __GFP_DIRECT_RECLAIM :
					__GFP_KSWAPD_RECLAIM);

	/* Only do synchronous compaction if madvised */
	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
		return GFP_TRANSHUGE_LIGHT |
		       (vma_madvised ? __GFP_DIRECT_RECLAIM : 0);

	return GFP_TRANSHUGE_LIGHT;
}

/* Caller must hold page table lock. */
static void set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
		struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd,
		struct page *zero_page)
{
	pmd_t entry;
	if (!pmd_none(*pmd))
		return;
	entry = mk_pmd(zero_page, vma->vm_page_prot);
	entry = pmd_mkhuge(entry);
	pgtable_trans_huge_deposit(mm, pmd, pgtable);
	set_pmd_at(mm, haddr, pmd, entry);
	mm_inc_nr_ptes(mm);
}

vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
{
	struct vm_area_struct *vma = vmf->vma;
	gfp_t gfp;
	struct folio *folio;
	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;

	if (!transhuge_vma_suitable(vma, haddr))
		return VM_FAULT_FALLBACK;
	if (unlikely(anon_vma_prepare(vma)))
		return VM_FAULT_OOM;
	khugepaged_enter_vma(vma, vma->vm_flags);

	if (!(vmf->flags & FAULT_FLAG_WRITE) &&
			!mm_forbids_zeropage(vma->vm_mm) &&
			transparent_hugepage_use_zero_page()) {
		pgtable_t pgtable;
		struct page *zero_page;
		vm_fault_t ret;
		pgtable = pte_alloc_one(vma->vm_mm);
		if (unlikely(!pgtable))
			return VM_FAULT_OOM;
		zero_page = mm_get_huge_zero_page(vma->vm_mm);
		if (unlikely(!zero_page)) {
			pte_free(vma->vm_mm, pgtable);
			count_vm_event(THP_FAULT_FALLBACK);
			return VM_FAULT_FALLBACK;
		}
		vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
		ret = 0;
		if (pmd_none(*vmf->pmd)) {
			ret = check_stable_address_space(vma->vm_mm);
			if (ret) {
				spin_unlock(vmf->ptl);
				pte_free(vma->vm_mm, pgtable);
			} else if (userfaultfd_missing(vma)) {
				spin_unlock(vmf->ptl);
				pte_free(vma->vm_mm, pgtable);
				ret = handle_userfault(vmf, VM_UFFD_MISSING);
				VM_BUG_ON(ret & VM_FAULT_FALLBACK);
			} else {
				set_huge_zero_page(pgtable, vma->vm_mm, vma,
						   haddr, vmf->pmd, zero_page);
				update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
				spin_unlock(vmf->ptl);
			}
		} else {
			spin_unlock(vmf->ptl);
			pte_free(vma->vm_mm, pgtable);
		}
		return ret;
	}
	gfp = vma_thp_gfp_mask(vma);
	folio = vma_alloc_folio(gfp, HPAGE_PMD_ORDER, vma, haddr, true);
	if (unlikely(!folio)) {
		count_vm_event(THP_FAULT_FALLBACK);
		return VM_FAULT_FALLBACK;
	}
	return __do_huge_pmd_anonymous_page(vmf, &folio->page, gfp);
}

static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
		pmd_t *pmd, pfn_t pfn, pgprot_t prot, bool write,
		pgtable_t pgtable)
{
	struct mm_struct *mm = vma->vm_mm;
	pmd_t entry;
	spinlock_t *ptl;

	ptl = pmd_lock(mm, pmd);
	if (!pmd_none(*pmd)) {
		if (write) {
			if (pmd_pfn(*pmd) != pfn_t_to_pfn(pfn)) {
				WARN_ON_ONCE(!is_huge_zero_pmd(*pmd));
				goto out_unlock;
			}
			entry = pmd_mkyoung(*pmd);
			entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
			if (pmdp_set_access_flags(vma, addr, pmd, entry, 1))
				update_mmu_cache_pmd(vma, addr, pmd);
		}

		goto out_unlock;
	}

	entry = pmd_mkhuge(pfn_t_pmd(pfn, prot));
	if (pfn_t_devmap(pfn))
		entry = pmd_mkdevmap(entry);
	if (write) {
		entry = pmd_mkyoung(pmd_mkdirty(entry));
		entry = maybe_pmd_mkwrite(entry, vma);
	}

	if (pgtable) {
		pgtable_trans_huge_deposit(mm, pmd, pgtable);
		mm_inc_nr_ptes(mm);
		pgtable = NULL;
	}

	set_pmd_at(mm, addr, pmd, entry);
	update_mmu_cache_pmd(vma, addr, pmd);

out_unlock:
	spin_unlock(ptl);
	if (pgtable)
		pte_free(mm, pgtable);
}

/**
 * vmf_insert_pfn_pmd_prot - insert a pmd size pfn
 * @vmf: Structure describing the fault
 * @pfn: pfn to insert
 * @pgprot: page protection to use
 * @write: whether it's a write fault
 *
 * Insert a pmd size pfn. See vmf_insert_pfn() for additional info and
 * also consult the vmf_insert_mixed_prot() documentation when
 * @pgprot != @vmf->vma->vm_page_prot.
 *
 * Return: vm_fault_t value.
 */
vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn,
				   pgprot_t pgprot, bool write)
{
	unsigned long addr = vmf->address & PMD_MASK;
	struct vm_area_struct *vma = vmf->vma;
	pgtable_t pgtable = NULL;

	/*
	 * If we had pmd_special, we could avoid all these restrictions,
	 * but we need to be consistent with PTEs and architectures that
	 * can't support a 'special' bit.
	 */
	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) &&
			!pfn_t_devmap(pfn));
	BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
						(VM_PFNMAP|VM_MIXEDMAP));
	BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));

	if (addr < vma->vm_start || addr >= vma->vm_end)
		return VM_FAULT_SIGBUS;

	if (arch_needs_pgtable_deposit()) {
		pgtable = pte_alloc_one(vma->vm_mm);
		if (!pgtable)
			return VM_FAULT_OOM;
	}

	track_pfn_insert(vma, &pgprot, pfn);

	insert_pfn_pmd(vma, addr, vmf->pmd, pfn, pgprot, write, pgtable);
	return VM_FAULT_NOPAGE;
}
EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd_prot);

#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma)
{
	if (likely(vma->vm_flags & VM_WRITE))
		pud = pud_mkwrite(pud);
	return pud;
}

static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
		pud_t *pud, pfn_t pfn, pgprot_t prot, bool write)
{
	struct mm_struct *mm = vma->vm_mm;
	pud_t entry;
	spinlock_t *ptl;

	ptl = pud_lock(mm, pud);
	if (!pud_none(*pud)) {
		if (write) {
			if (pud_pfn(*pud) != pfn_t_to_pfn(pfn)) {
				WARN_ON_ONCE(!is_huge_zero_pud(*pud));
				goto out_unlock;
			}
			entry = pud_mkyoung(*pud);
			entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma);
			if (pudp_set_access_flags(vma, addr, pud, entry, 1))
				update_mmu_cache_pud(vma, addr, pud);
		}
		goto out_unlock;
	}

	entry = pud_mkhuge(pfn_t_pud(pfn, prot));
	if (pfn_t_devmap(pfn))
		entry = pud_mkdevmap(entry);
	if (write) {
		entry = pud_mkyoung(pud_mkdirty(entry));
		entry = maybe_pud_mkwrite(entry, vma);
	}
	set_pud_at(mm, addr, pud, entry);
	update_mmu_cache_pud(vma, addr, pud);

out_unlock:
	spin_unlock(ptl);
}

/**
 * vmf_insert_pfn_pud_prot - insert a pud size pfn
 * @vmf: Structure describing the fault
 * @pfn: pfn to insert
 * @pgprot: page protection to use
 * @write: whether it's a write fault
 *
 * Insert a pud size pfn. See vmf_insert_pfn() for additional info and
 * also consult the vmf_insert_mixed_prot() documentation when
 * @pgprot != @vmf->vma->vm_page_prot.
 *
 * Return: vm_fault_t value.
 */
vm_fault_t vmf_insert_pfn_pud_prot(struct vm_fault *vmf, pfn_t pfn,
				   pgprot_t pgprot, bool write)
{
	unsigned long addr = vmf->address & PUD_MASK;
	struct vm_area_struct *vma = vmf->vma;

	/*
	 * If we had pud_special, we could avoid all these restrictions,
	 * but we need to be consistent with PTEs and architectures that
	 * can't support a 'special' bit.
	 */
	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) &&
			!pfn_t_devmap(pfn));
	BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
						(VM_PFNMAP|VM_MIXEDMAP));
	BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));

	if (addr < vma->vm_start || addr >= vma->vm_end)
		return VM_FAULT_SIGBUS;

	track_pfn_insert(vma, &pgprot, pfn);

	insert_pfn_pud(vma, addr, vmf->pud, pfn, pgprot, write);
	return VM_FAULT_NOPAGE;
}
EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud_prot);
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */

static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
		      pmd_t *pmd, bool write)
{
	pmd_t _pmd;

	_pmd = pmd_mkyoung(*pmd);
	if (write)
		_pmd = pmd_mkdirty(_pmd);
	if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK,
				  pmd, _pmd, write))
		update_mmu_cache_pmd(vma, addr, pmd);
}

struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
		pmd_t *pmd, int flags, struct dev_pagemap **pgmap)
{
	unsigned long pfn = pmd_pfn(*pmd);
	struct mm_struct *mm = vma->vm_mm;
	struct page *page;
	int ret;

	assert_spin_locked(pmd_lockptr(mm, pmd));

	if (flags & FOLL_WRITE && !pmd_write(*pmd))
		return NULL;

	if (pmd_present(*pmd) && pmd_devmap(*pmd))
		/* pass */;
	else
		return NULL;

	if (flags & FOLL_TOUCH)
		touch_pmd(vma, addr, pmd, flags & FOLL_WRITE);

	/*
	 * device mapped pages can only be returned if the
	 * caller will manage the page reference count.
	 */
	if (!(flags & (FOLL_GET | FOLL_PIN)))
		return ERR_PTR(-EEXIST);

	pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT;
	*pgmap = get_dev_pagemap(pfn, *pgmap);
	if (!*pgmap)
		return ERR_PTR(-EFAULT);
	page = pfn_to_page(pfn);
	ret = try_grab_page(page, flags);
	if (ret)
		page = ERR_PTR(ret);

	return page;
}

int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
		  pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
		  struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
{
	spinlock_t *dst_ptl, *src_ptl;
	struct page *src_page;
	pmd_t pmd;
	pgtable_t pgtable = NULL;
	int ret = -ENOMEM;

	/* Skip if can be re-fill on fault */
	if (!vma_is_anonymous(dst_vma))
		return 0;

	pgtable = pte_alloc_one(dst_mm);
	if (unlikely(!pgtable))
		goto out;

	dst_ptl = pmd_lock(dst_mm, dst_pmd);
	src_ptl = pmd_lockptr(src_mm, src_pmd);
	spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);

	ret = -EAGAIN;
	pmd = *src_pmd;

#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
	if (unlikely(is_swap_pmd(pmd))) {
		swp_entry_t entry = pmd_to_swp_entry(pmd);

		VM_BUG_ON(!is_pmd_migration_entry(pmd));
		if (!is_readable_migration_entry(entry)) {
			entry = make_readable_migration_entry(
							swp_offset(entry));
			pmd = swp_entry_to_pmd(entry);
			if (pmd_swp_soft_dirty(*src_pmd))
				pmd = pmd_swp_mksoft_dirty(pmd);
			if (pmd_swp_uffd_wp(*src_pmd))
				pmd = pmd_swp_mkuffd_wp(pmd);
			set_pmd_at(src_mm, addr, src_pmd, pmd);
		}
		add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
		mm_inc_nr_ptes(dst_mm);
		pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
		if (!userfaultfd_wp(dst_vma))
			pmd = pmd_swp_clear_uffd_wp(pmd);
		set_pmd_at(dst_mm, addr, dst_pmd, pmd);
		ret = 0;
		goto out_unlock;
	}
#endif

	if (unlikely(!pmd_trans_huge(pmd))) {
		pte_free(dst_mm, pgtable);
		goto out_unlock;
	}
	/*
	 * When page table lock is held, the huge zero pmd should not be
	 * under splitting since we don't split the page itself, only pmd to
	 * a page table.
	 */
	if (is_huge_zero_pmd(pmd)) {
		/*
		 * get_huge_zero_page() will never allocate a new page here,
		 * since we already have a zero page to copy. It just takes a
		 * reference.
		 */
		mm_get_huge_zero_page(dst_mm);
		goto out_zero_page;
	}

	src_page = pmd_page(pmd);
	VM_BUG_ON_PAGE(!PageHead(src_page), src_page);

	get_page(src_page);
	if (unlikely(page_try_dup_anon_rmap(src_page, true, src_vma))) {
		/* Page maybe pinned: split and retry the fault on PTEs. */
		put_page(src_page);
		pte_free(dst_mm, pgtable);
		spin_unlock(src_ptl);
		spin_unlock(dst_ptl);
		__split_huge_pmd(src_vma, src_pmd, addr, false, NULL);
		return -EAGAIN;
	}
	add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
out_zero_page:
	mm_inc_nr_ptes(dst_mm);
	pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
	pmdp_set_wrprotect(src_mm, addr, src_pmd);
	if (!userfaultfd_wp(dst_vma))
		pmd = pmd_clear_uffd_wp(pmd);
	pmd = pmd_mkold(pmd_wrprotect(pmd));
	set_pmd_at(dst_mm, addr, dst_pmd, pmd);

	ret = 0;
out_unlock:
	spin_unlock(src_ptl);
	spin_unlock(dst_ptl);
out:
	return ret;
}

#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
static void touch_pud(struct vm_area_struct *vma, unsigned long addr,
		      pud_t *pud, bool write)
{
	pud_t _pud;

	_pud = pud_mkyoung(*pud);
	if (write)
		_pud = pud_mkdirty(_pud);
	if (pudp_set_access_flags(vma, addr & HPAGE_PUD_MASK,
				  pud, _pud, write))
		update_mmu_cache_pud(vma, addr, pud);
}

struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
		pud_t *pud, int flags, struct dev_pagemap **pgmap)
{
	unsigned long pfn = pud_pfn(*pud);
	struct mm_struct *mm = vma->vm_mm;
	struct page *page;
	int ret;

	assert_spin_locked(pud_lockptr(mm, pud));

	if (flags & FOLL_WRITE && !pud_write(*pud))
		return NULL;

	if (pud_present(*pud) && pud_devmap(*pud))
		/* pass */;
	else
		return NULL;

	if (flags & FOLL_TOUCH)
		touch_pud(vma, addr, pud, flags & FOLL_WRITE);

	/*
	 * device mapped pages can only be returned if the
	 * caller will manage the page reference count.
	 *
	 * At least one of FOLL_GET | FOLL_PIN must be set, so assert that here:
	 */
	if (!(flags & (FOLL_GET | FOLL_PIN)))
		return ERR_PTR(-EEXIST);

	pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT;
	*pgmap = get_dev_pagemap(pfn, *pgmap);
	if (!*pgmap)
		return ERR_PTR(-EFAULT);
	page = pfn_to_page(pfn);

	ret = try_grab_page(page, flags);
	if (ret)
		page = ERR_PTR(ret);

	return page;
}

int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
		  pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
		  struct vm_area_struct *vma)
{
	spinlock_t *dst_ptl, *src_ptl;
	pud_t pud;
	int ret;

	dst_ptl = pud_lock(dst_mm, dst_pud);
	src_ptl = pud_lockptr(src_mm, src_pud);
	spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);

	ret = -EAGAIN;
	pud = *src_pud;
	if (unlikely(!pud_trans_huge(pud) && !pud_devmap(pud)))
		goto out_unlock;

	/*
	 * When page table lock is held, the huge zero pud should not be
	 * under splitting since we don't split the page itself, only pud to
	 * a page table.
	 */
	if (is_huge_zero_pud(pud)) {
		/* No huge zero pud yet */
	}

	/*
	 * TODO: once we support anonymous pages, use page_try_dup_anon_rmap()
	 * and split if duplicating fails.
	 */
	pudp_set_wrprotect(src_mm, addr, src_pud);
	pud = pud_mkold(pud_wrprotect(pud));
	set_pud_at(dst_mm, addr, dst_pud, pud);

	ret = 0;
out_unlock:
	spin_unlock(src_ptl);
	spin_unlock(dst_ptl);
	return ret;
}

void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud)
{
	bool write = vmf->flags & FAULT_FLAG_WRITE;

	vmf->ptl = pud_lock(vmf->vma->vm_mm, vmf->pud);
	if (unlikely(!pud_same(*vmf->pud, orig_pud)))
		goto unlock;

	touch_pud(vmf->vma, vmf->address, vmf->pud, write);
unlock:
	spin_unlock(vmf->ptl);
}
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */

void huge_pmd_set_accessed(struct vm_fault *vmf)
{
	bool write = vmf->flags & FAULT_FLAG_WRITE;

	vmf->ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
	if (unlikely(!pmd_same(*vmf->pmd, vmf->orig_pmd)))
		goto unlock;

	touch_pmd(vmf->vma, vmf->address, vmf->pmd, write);

unlock:
	spin_unlock(vmf->ptl);
}

vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf)
{
	const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE;
	struct vm_area_struct *vma = vmf->vma;
	struct folio *folio;
	struct page *page;
	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
	pmd_t orig_pmd = vmf->orig_pmd;

	vmf->ptl = pmd_lockptr(vma->vm_mm, vmf->pmd);
	VM_BUG_ON_VMA(!vma->anon_vma, vma);

	if (is_huge_zero_pmd(orig_pmd))
		goto fallback;

	spin_lock(vmf->ptl);

	if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) {
		spin_unlock(vmf->ptl);
		return 0;
	}

	page = pmd_page(orig_pmd);
	folio = page_folio(page);
	VM_BUG_ON_PAGE(!PageHead(page), page);

	/* Early check when only holding the PT lock. */
	if (PageAnonExclusive(page))
		goto reuse;

	if (!folio_trylock(folio)) {
		folio_get(folio);
		spin_unlock(vmf->ptl);
		folio_lock(folio);
		spin_lock(vmf->ptl);
		if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) {
			spin_unlock(vmf->ptl);
			folio_unlock(folio);
			folio_put(folio);
			return 0;
		}
		folio_put(folio);
	}

	/* Recheck after temporarily dropping the PT lock. */
	if (PageAnonExclusive(page)) {
		folio_unlock(folio);
		goto reuse;
	}

	/*
	 * See do_wp_page(): we can only reuse the folio exclusively if
	 * there are no additional references. Note that we always drain
	 * the LRU pagevecs immediately after adding a THP.
	 */
	if (folio_ref_count(folio) >
			1 + folio_test_swapcache(folio) * folio_nr_pages(folio))
		goto unlock_fallback;
	if (folio_test_swapcache(folio))
		folio_free_swap(folio);
	if (folio_ref_count(folio) == 1) {
		pmd_t entry;

		page_move_anon_rmap(page, vma);
		folio_unlock(folio);
reuse:
		if (unlikely(unshare)) {
			spin_unlock(vmf->ptl);
			return 0;
		}
		entry = pmd_mkyoung(orig_pmd);
		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
		if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry, 1))
			update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
		spin_unlock(vmf->ptl);
		return 0;
	}

unlock_fallback:
	folio_unlock(folio);
	spin_unlock(vmf->ptl);
fallback:
	__split_huge_pmd(vma, vmf->pmd, vmf->address, false, NULL);
	return VM_FAULT_FALLBACK;
}

static inline bool can_change_pmd_writable(struct vm_area_struct *vma,
					   unsigned long addr, pmd_t pmd)
{
	struct page *page;

	if (WARN_ON_ONCE(!(vma->vm_flags & VM_WRITE)))
		return false;

	/* Don't touch entries that are not even readable (NUMA hinting). */
	if (pmd_protnone(pmd))
		return false;

	/* Do we need write faults for softdirty tracking? */
	if (vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd))
		return false;

	/* Do we need write faults for uffd-wp tracking? */
	if (userfaultfd_huge_pmd_wp(vma, pmd))
		return false;

	if (!(vma->vm_flags & VM_SHARED)) {
		/* See can_change_pte_writable(). */
		page = vm_normal_page_pmd(vma, addr, pmd);
		return page && PageAnon(page) && PageAnonExclusive(page);
	}

	/* See can_change_pte_writable(). */
	return pmd_dirty(pmd);
}

/* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */
static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page,
					struct vm_area_struct *vma,
					unsigned int flags)
{
	/* If the pmd is writable, we can write to the page. */
	if (pmd_write(pmd))
		return true;

	/* Maybe FOLL_FORCE is set to override it? */
	if (!(flags & FOLL_FORCE))
		return false;

	/* But FOLL_FORCE has no effect on shared mappings */
	if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED))
		return false;

	/* ... or read-only private ones */
	if (!(vma->vm_flags & VM_MAYWRITE))
		return false;

	/* ... or already writable ones that just need to take a write fault */
	if (vma->vm_flags & VM_WRITE)
		return false;

	/*
	 * See can_change_pte_writable(): we broke COW and could map the page
	 * writable if we have an exclusive anonymous page ...
	 */
	if (!page || !PageAnon(page) || !PageAnonExclusive(page))
		return false;

	/* ... and a write-fault isn't required for other reasons. */
	if (vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd))
		return false;
	return !userfaultfd_huge_pmd_wp(vma, pmd);
}

struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
				   unsigned long addr,
				   pmd_t *pmd,
				   unsigned int flags)
{
	struct mm_struct *mm = vma->vm_mm;
	struct page *page;
	int ret;

	assert_spin_locked(pmd_lockptr(mm, pmd));

	page = pmd_page(*pmd);
	VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page);

	if ((flags & FOLL_WRITE) &&
	    !can_follow_write_pmd(*pmd, page, vma, flags))
		return NULL;

	/* Avoid dumping huge zero page */
	if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd))
		return ERR_PTR(-EFAULT);

	/* Full NUMA hinting faults to serialise migration in fault paths */
	if (pmd_protnone(*pmd) && !gup_can_follow_protnone(flags))
		return NULL;

	if (!pmd_write(*pmd) && gup_must_unshare(vma, flags, page))
		return ERR_PTR(-EMLINK);

	VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
			!PageAnonExclusive(page), page);

	ret = try_grab_page(page, flags);
	if (ret)
		return ERR_PTR(ret);

	if (flags & FOLL_TOUCH)
		touch_pmd(vma, addr, pmd, flags & FOLL_WRITE);

	page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
	VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page);

	return page;
}

/* NUMA hinting page fault entry point for trans huge pmds */
vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
{
	struct vm_area_struct *vma = vmf->vma;
	pmd_t oldpmd = vmf->orig_pmd;
	pmd_t pmd;
	struct page *page;
	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
	int page_nid = NUMA_NO_NODE;
	int target_nid, last_cpupid = (-1 & LAST_CPUPID_MASK);
	bool migrated = false, writable = false;
	int flags = 0;

	vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
	if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) {
		spin_unlock(vmf->ptl);
		goto out;
	}

	pmd = pmd_modify(oldpmd, vma->vm_page_prot);

	/*
	 * Detect now whether the PMD could be writable; this information
	 * is only valid while holding the PT lock.
	 */
	writable = pmd_write(pmd);
	if (!writable && vma_wants_manual_pte_write_upgrade(vma) &&
	    can_change_pmd_writable(vma, vmf->address, pmd))
		writable = true;

	page = vm_normal_page_pmd(vma, haddr, pmd);
	if (!page)
		goto out_map;

	/* See similar comment in do_numa_page for explanation */
	if (!writable)
		flags |= TNF_NO_GROUP;

	page_nid = page_to_nid(page);
	/*
	 * For memory tiering mode, cpupid of slow memory page is used
	 * to record page access time.  So use default value.
	 */
	if (node_is_toptier(page_nid))
		last_cpupid = page_cpupid_last(page);
	target_nid = numa_migrate_prep(page, vma, haddr, page_nid,
				       &flags);

	if (target_nid == NUMA_NO_NODE) {
		put_page(page);
		goto out_map;
	}

	spin_unlock(vmf->ptl);
	writable = false;

	migrated = migrate_misplaced_page(page, vma, target_nid);
	if (migrated) {
		flags |= TNF_MIGRATED;
		page_nid = target_nid;
	} else {
		flags |= TNF_MIGRATE_FAIL;
		vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
		if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) {
			spin_unlock(vmf->ptl);
			goto out;
		}
		goto out_map;
	}

out:
	if (page_nid != NUMA_NO_NODE)
		task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR,
				flags);

	return 0;

out_map:
	/* Restore the PMD */
	pmd = pmd_modify(oldpmd, vma->vm_page_prot);
	pmd = pmd_mkyoung(pmd);
	if (writable)
		pmd = pmd_mkwrite(pmd);
	set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd);
	update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
	spin_unlock(vmf->ptl);
	goto out;
}

/*
 * Return true if we do MADV_FREE successfully on entire pmd page.
 * Otherwise, return false.
 */
bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
		pmd_t *pmd, unsigned long addr, unsigned long next)
{
	spinlock_t *ptl;
	pmd_t orig_pmd;
	struct folio *folio;
	struct mm_struct *mm = tlb->mm;
	bool ret = false;

	tlb_change_page_size(tlb, HPAGE_PMD_SIZE);

	ptl = pmd_trans_huge_lock(pmd, vma);
	if (!ptl)
		goto out_unlocked;

	orig_pmd = *pmd;
	if (is_huge_zero_pmd(orig_pmd))
		goto out;

	if (unlikely(!pmd_present(orig_pmd))) {
		VM_BUG_ON(thp_migration_supported() &&
				  !is_pmd_migration_entry(orig_pmd));
		goto out;
	}

	folio = pfn_folio(pmd_pfn(orig_pmd));
	/*
	 * If other processes are mapping this folio, we couldn't discard
	 * the folio unless they all do MADV_FREE so let's skip the folio.
	 */
	if (folio_mapcount(folio) != 1)
		goto out;

	if (!folio_trylock(folio))
		goto out;

	/*
	 * If user want to discard part-pages of THP, split it so MADV_FREE
	 * will deactivate only them.
	 */
	if (next - addr != HPAGE_PMD_SIZE) {
		folio_get(folio);
		spin_unlock(ptl);
		split_folio(folio);
		folio_unlock(folio);
		folio_put(folio);
		goto out_unlocked;
	}

	if (folio_test_dirty(folio))
		folio_clear_dirty(folio);
	folio_unlock(folio);

	if (pmd_young(orig_pmd) || pmd_dirty(orig_pmd)) {
		pmdp_invalidate(vma, addr, pmd);
		orig_pmd = pmd_mkold(orig_pmd);
		orig_pmd = pmd_mkclean(orig_pmd);

		set_pmd_at(mm, addr, pmd, orig_pmd);
		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
	}

	folio_mark_lazyfree(folio);
	ret = true;
out:
	spin_unlock(ptl);
out_unlocked:
	return ret;
}

static inline void zap_deposited_table(struct mm_struct *mm, pmd_t *pmd)
{
	pgtable_t pgtable;

	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
	pte_free(mm, pgtable);
	mm_dec_nr_ptes(mm);
}

int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
		 pmd_t *pmd, unsigned long addr)
{
	pmd_t orig_pmd;
	spinlock_t *ptl;

	tlb_change_page_size(tlb, HPAGE_PMD_SIZE);

	ptl = __pmd_trans_huge_lock(pmd, vma);
	if (!ptl)
		return 0;
	/*
	 * For architectures like ppc64 we look at deposited pgtable
	 * when calling pmdp_huge_get_and_clear. So do the
	 * pgtable_trans_huge_withdraw after finishing pmdp related
	 * operations.
	 */
	orig_pmd = pmdp_huge_get_and_clear_full(vma, addr, pmd,
						tlb->fullmm);
	tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
	if (vma_is_special_huge(vma)) {
		if (arch_needs_pgtable_deposit())
			zap_deposited_table(tlb->mm, pmd);
		spin_unlock(ptl);
	} else if (is_huge_zero_pmd(orig_pmd)) {
		zap_deposited_table(tlb->mm, pmd);
		spin_unlock(ptl);
	} else {
		struct page *page = NULL;
		int flush_needed = 1;

		if (pmd_present(orig_pmd)) {
			page = pmd_page(orig_pmd);
			page_remove_rmap(page, vma, true);
			VM_BUG_ON_PAGE(page_mapcount(page) < 0, page);
			VM_BUG_ON_PAGE(!PageHead(page), page);
		} else if (thp_migration_supported()) {
			swp_entry_t entry;

			VM_BUG_ON(!is_pmd_migration_entry(orig_pmd));
			entry = pmd_to_swp_entry(orig_pmd);
			page = pfn_swap_entry_to_page(entry);
			flush_needed = 0;
		} else
			WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!");

		if (PageAnon(page)) {
			zap_deposited_table(tlb->mm, pmd);
			add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
		} else {
			if (arch_needs_pgtable_deposit())
				zap_deposited_table(tlb->mm, pmd);
			add_mm_counter(tlb->mm, mm_counter_file(page), -HPAGE_PMD_NR);
		}

		spin_unlock(ptl);
		if (flush_needed)
			tlb_remove_page_size(tlb, page, HPAGE_PMD_SIZE);
	}
	return 1;
}

#ifndef pmd_move_must_withdraw
static inline int pmd_move_must_withdraw(spinlock_t *new_pmd_ptl,
					 spinlock_t *old_pmd_ptl,
					 struct vm_area_struct *vma)
{
	/*
	 * With split pmd lock we also need to move preallocated
	 * PTE page table if new_pmd is on different PMD page table.
	 *
	 * We also don't deposit and withdraw tables for file pages.
	 */
	return (new_pmd_ptl != old_pmd_ptl) && vma_is_anonymous(vma);
}
#endif

static pmd_t move_soft_dirty_pmd(pmd_t pmd)
{
#ifdef CONFIG_MEM_SOFT_DIRTY
	if (unlikely(is_pmd_migration_entry(pmd)))
		pmd = pmd_swp_mksoft_dirty(pmd);
	else if (pmd_present(pmd))
		pmd = pmd_mksoft_dirty(pmd);
#endif
	return pmd;
}

bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
		  unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd)
{
	spinlock_t *old_ptl, *new_ptl;
	pmd_t pmd;
	struct mm_struct *mm = vma->vm_mm;
	bool force_flush = false;

	/*
	 * The destination pmd shouldn't be established, free_pgtables()
	 * should have release it.
	 */
	if (WARN_ON(!pmd_none(*new_pmd))) {
		VM_BUG_ON(pmd_trans_huge(*new_pmd));
		return false;
	}

	/*
	 * We don't have to worry about the ordering of src and dst
	 * ptlocks because exclusive mmap_lock prevents deadlock.
	 */
	old_ptl = __pmd_trans_huge_lock(old_pmd, vma);
	if (old_ptl) {
		new_ptl = pmd_lockptr(mm, new_pmd);
		if (new_ptl != old_ptl)
			spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
		pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd);
		if (pmd_present(pmd))
			force_flush = true;
		VM_BUG_ON(!pmd_none(*new_pmd));

		if (pmd_move_must_withdraw(new_ptl, old_ptl, vma)) {
			pgtable_t pgtable;
			pgtable = pgtable_trans_huge_withdraw(mm, old_pmd);
			pgtable_trans_huge_deposit(mm, new_pmd, pgtable);
		}
		pmd = move_soft_dirty_pmd(pmd);
		set_pmd_at(mm, new_addr, new_pmd, pmd);
		if (force_flush)
			flush_pmd_tlb_range(vma, old_addr, old_addr + PMD_SIZE);
		if (new_ptl != old_ptl)
			spin_unlock(new_ptl);
		spin_unlock(old_ptl);
		return true;
	}
	return false;
}

/*
 * Returns
 *  - 0 if PMD could not be locked
 *  - 1 if PMD was locked but protections unchanged and TLB flush unnecessary
 *      or if prot_numa but THP migration is not supported
 *  - HPAGE_PMD_NR if protections changed and TLB flush necessary
 */
int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
		    pmd_t *pmd, unsigned long addr, pgprot_t newprot,
		    unsigned long cp_flags)
{
	struct mm_struct *mm = vma->vm_mm;
	spinlock_t *ptl;
	pmd_t oldpmd, entry;
	bool prot_numa = cp_flags & MM_CP_PROT_NUMA;
	bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
	bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
	int ret = 1;

	tlb_change_page_size(tlb, HPAGE_PMD_SIZE);

	if (prot_numa && !thp_migration_supported())
		return 1;

	ptl = __pmd_trans_huge_lock(pmd, vma);
	if (!ptl)
		return 0;

#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
	if (is_swap_pmd(*pmd)) {
		swp_entry_t entry = pmd_to_swp_entry(*pmd);
		struct page *page = pfn_swap_entry_to_page(entry);

		VM_BUG_ON(!is_pmd_migration_entry(*pmd));
		if (is_writable_migration_entry(entry)) {
			pmd_t newpmd;
			/*
			 * A protection check is difficult so
			 * just be safe and disable write
			 */
			if (PageAnon(page))
				entry = make_readable_exclusive_migration_entry(swp_offset(entry));
			else
				entry = make_readable_migration_entry(swp_offset(entry));
			newpmd = swp_entry_to_pmd(entry);
			if (pmd_swp_soft_dirty(*pmd))
				newpmd = pmd_swp_mksoft_dirty(newpmd);
			if (pmd_swp_uffd_wp(*pmd))
				newpmd = pmd_swp_mkuffd_wp(newpmd);
			set_pmd_at(mm, addr, pmd, newpmd);
		}
		goto unlock;
	}
#endif

	if (prot_numa) {
		struct page *page;
		bool toptier;
		/*
		 * Avoid trapping faults against the zero page. The read-only
		 * data is likely to be read-cached on the local CPU and
		 * local/remote hits to the zero page are not interesting.
		 */
		if (is_huge_zero_pmd(*pmd))
			goto unlock;

		if (pmd_protnone(*pmd))
			goto unlock;

		page = pmd_page(*pmd);
		toptier = node_is_toptier(page_to_nid(page));
		/*
		 * Skip scanning top tier node if normal numa
		 * balancing is disabled
		 */
		if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) &&
		    toptier)
			goto unlock;

		if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING &&
		    !toptier)
			xchg_page_access_time(page, jiffies_to_msecs(jiffies));
	}
	/*
	 * In case prot_numa, we are under mmap_read_lock(mm). It's critical
	 * to not clear pmd intermittently to avoid race with MADV_DONTNEED
	 * which is also under mmap_read_lock(mm):
	 *
	 *	CPU0:				CPU1:
	 *				change_huge_pmd(prot_numa=1)
	 *				 pmdp_huge_get_and_clear_notify()
	 * madvise_dontneed()
	 *  zap_pmd_range()
	 *   pmd_trans_huge(*pmd) == 0 (without ptl)
	 *   // skip the pmd
	 *				 set_pmd_at();
	 *				 // pmd is re-established
	 *
	 * The race makes MADV_DONTNEED miss the huge pmd and don't clear it
	 * which may break userspace.
	 *
	 * pmdp_invalidate_ad() is required to make sure we don't miss
	 * dirty/young flags set by hardware.
	 */
	oldpmd = pmdp_invalidate_ad(vma, addr, pmd);

	entry = pmd_modify(oldpmd, newprot);
	if (uffd_wp)
		entry = pmd_mkuffd_wp(entry);
	else if (uffd_wp_resolve)
		/*
		 * Leave the write bit to be handled by PF interrupt
		 * handler, then things like COW could be properly
		 * handled.
		 */
		entry = pmd_clear_uffd_wp(entry);

	/* See change_pte_range(). */
	if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) && !pmd_write(entry) &&
	    can_change_pmd_writable(vma, addr, entry))
		entry = pmd_mkwrite(entry);

	ret = HPAGE_PMD_NR;
	set_pmd_at(mm, addr, pmd, entry);

	if (huge_pmd_needs_flush(oldpmd, entry))
		tlb_flush_pmd_range(tlb, addr, HPAGE_PMD_SIZE);
unlock:
	spin_unlock(ptl);
	return ret;
}

/*
 * Returns page table lock pointer if a given pmd maps a thp, NULL otherwise.
 *
 * Note that if it returns page table lock pointer, this routine returns without
 * unlocking page table lock. So callers must unlock it.
 */
spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma)
{
	spinlock_t *ptl;
	ptl = pmd_lock(vma->vm_mm, pmd);
	if (likely(is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) ||
			pmd_devmap(*pmd)))
		return ptl;
	spin_unlock(ptl);
	return NULL;
}

/*
 * Returns page table lock pointer if a given pud maps a thp, NULL otherwise.
 *
 * Note that if it returns page table lock pointer, this routine returns without
 * unlocking page table lock. So callers must unlock it.
 */
spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma)
{
	spinlock_t *ptl;

	ptl = pud_lock(vma->vm_mm, pud);
	if (likely(pud_trans_huge(*pud) || pud_devmap(*pud)))
		return ptl;
	spin_unlock(ptl);
	return NULL;
}

#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
		 pud_t *pud, unsigned long addr)
{
	spinlock_t *ptl;

	ptl = __pud_trans_huge_lock(pud, vma);
	if (!ptl)
		return 0;

	pudp_huge_get_and_clear_full(tlb->mm, addr, pud, tlb->fullmm);
	tlb_remove_pud_tlb_entry(tlb, pud, addr);
	if (vma_is_special_huge(vma)) {
		spin_unlock(ptl);
		/* No zero page support yet */
	} else {
		/* No support for anonymous PUD pages yet */
		BUG();
	}
	return 1;
}

static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud,
		unsigned long haddr)
{
	VM_BUG_ON(haddr & ~HPAGE_PUD_MASK);
	VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
	VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma);
	VM_BUG_ON(!pud_trans_huge(*pud) && !pud_devmap(*pud));

	count_vm_event(THP_SPLIT_PUD);

	pudp_huge_clear_flush_notify(vma, haddr, pud);
}

void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
		unsigned long address)
{
	spinlock_t *ptl;
	struct mmu_notifier_range range;

	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
				address & HPAGE_PUD_MASK,
				(address & HPAGE_PUD_MASK) + HPAGE_PUD_SIZE);
	mmu_notifier_invalidate_range_start(&range);
	ptl = pud_lock(vma->vm_mm, pud);
	if (unlikely(!pud_trans_huge(*pud) && !pud_devmap(*pud)))
		goto out;
	__split_huge_pud_locked(vma, pud, range.start);

out:
	spin_unlock(ptl);
	/*
	 * No need to double call mmu_notifier->invalidate_range() callback as
	 * the above pudp_huge_clear_flush_notify() did already call it.
	 */
	mmu_notifier_invalidate_range_only_end(&range);
}
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */

static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
		unsigned long haddr, pmd_t *pmd)
{
	struct mm_struct *mm = vma->vm_mm;
	pgtable_t pgtable;
	pmd_t _pmd;
	int i;

	/*
	 * Leave pmd empty until pte is filled note that it is fine to delay
	 * notification until mmu_notifier_invalidate_range_end() as we are
	 * replacing a zero pmd write protected page with a zero pte write
	 * protected page.
	 *
	 * See Documentation/mm/mmu_notifier.rst
	 */
	pmdp_huge_clear_flush(vma, haddr, pmd);

	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
	pmd_populate(mm, &_pmd, pgtable);

	for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
		pte_t *pte, entry;
		entry = pfn_pte(my_zero_pfn(haddr), vma->vm_page_prot);
		entry = pte_mkspecial(entry);
		pte = pte_offset_map(&_pmd, haddr);
		VM_BUG_ON(!pte_none(*pte));
		set_pte_at(mm, haddr, pte, entry);
		pte_unmap(pte);
	}
	smp_wmb(); /* make pte visible before pmd */
	pmd_populate(mm, pmd, pgtable);
}

static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
		unsigned long haddr, bool freeze)
{
	struct mm_struct *mm = vma->vm_mm;
	struct page *page;
	pgtable_t pgtable;
	pmd_t old_pmd, _pmd;
	bool young, write, soft_dirty, pmd_migration = false, uffd_wp = false;
	bool anon_exclusive = false, dirty = false;
	unsigned long addr;
	int i;

	VM_BUG_ON(haddr & ~HPAGE_PMD_MASK);
	VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
	VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PMD_SIZE, vma);
	VM_BUG_ON(!is_pmd_migration_entry(*pmd) && !pmd_trans_huge(*pmd)
				&& !pmd_devmap(*pmd));

	count_vm_event(THP_SPLIT_PMD);

	if (!vma_is_anonymous(vma)) {
		old_pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd);
		/*
		 * We are going to unmap this huge page. So
		 * just go ahead and zap it
		 */
		if (arch_needs_pgtable_deposit())
			zap_deposited_table(mm, pmd);
		if (vma_is_special_huge(vma))
			return;
		if (unlikely(is_pmd_migration_entry(old_pmd))) {
			swp_entry_t entry;

			entry = pmd_to_swp_entry(old_pmd);
			page = pfn_swap_entry_to_page(entry);
		} else {
			page = pmd_page(old_pmd);
			if (!PageDirty(page) && pmd_dirty(old_pmd))
				set_page_dirty(page);
			if (!PageReferenced(page) && pmd_young(old_pmd))
				SetPageReferenced(page);
			page_remove_rmap(page, vma, true);
			put_page(page);
		}
		add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR);
		return;
	}

	if (is_huge_zero_pmd(*pmd)) {
		/*
		 * FIXME: Do we want to invalidate secondary mmu by calling
		 * mmu_notifier_invalidate_range() see comments below inside
		 * __split_huge_pmd() ?
		 *
		 * We are going from a zero huge page write protected to zero
		 * small page also write protected so it does not seems useful
		 * to invalidate secondary mmu at this time.
		 */
		return __split_huge_zero_page_pmd(vma, haddr, pmd);
	}

	/*
	 * Up to this point the pmd is present and huge and userland has the
	 * whole access to the hugepage during the split (which happens in
	 * place). If we overwrite the pmd with the not-huge version pointing
	 * to the pte here (which of course we could if all CPUs were bug
	 * free), userland could trigger a small page size TLB miss on the
	 * small sized TLB while the hugepage TLB entry is still established in
	 * the huge TLB. Some CPU doesn't like that.
	 * See http://support.amd.com/TechDocs/41322_10h_Rev_Gd.pdf, Erratum
	 * 383 on page 105. Intel should be safe but is also warns that it's
	 * only safe if the permission and cache attributes of the two entries
	 * loaded in the two TLB is identical (which should be the case here).
	 * But it is generally safer to never allow small and huge TLB entries
	 * for the same virtual address to be loaded simultaneously. So instead
	 * of doing "pmd_populate(); flush_pmd_tlb_range();" we first mark the
	 * current pmd notpresent (atomically because here the pmd_trans_huge
	 * must remain set at all times on the pmd until the split is complete
	 * for this pmd), then we flush the SMP TLB and finally we write the
	 * non-huge version of the pmd entry with pmd_populate.
	 */
	old_pmd = pmdp_invalidate(vma, haddr, pmd);

	pmd_migration = is_pmd_migration_entry(old_pmd);
	if (unlikely(pmd_migration)) {
		swp_entry_t entry;

		entry = pmd_to_swp_entry(old_pmd);
		page = pfn_swap_entry_to_page(entry);
		write = is_writable_migration_entry(entry);
		if (PageAnon(page))
			anon_exclusive = is_readable_exclusive_migration_entry(entry);
		young = is_migration_entry_young(entry);
		dirty = is_migration_entry_dirty(entry);
		soft_dirty = pmd_swp_soft_dirty(old_pmd);
		uffd_wp = pmd_swp_uffd_wp(old_pmd);
	} else {
		page = pmd_page(old_pmd);
		if (pmd_dirty(old_pmd)) {
			dirty = true;
			SetPageDirty(page);
		}
		write = pmd_write(old_pmd);
		young = pmd_young(old_pmd);
		soft_dirty = pmd_soft_dirty(old_pmd);
		uffd_wp = pmd_uffd_wp(old_pmd);

		VM_BUG_ON_PAGE(!page_count(page), page);

		/*
		 * Without "freeze", we'll simply split the PMD, propagating the
		 * PageAnonExclusive() flag for each PTE by setting it for
		 * each subpage -- no need to (temporarily) clear.
		 *
		 * With "freeze" we want to replace mapped pages by
		 * migration entries right away. This is only possible if we
		 * managed to clear PageAnonExclusive() -- see
		 * set_pmd_migration_entry().
		 *
		 * In case we cannot clear PageAnonExclusive(), split the PMD
		 * only and let try_to_migrate_one() fail later.
		 *
		 * See page_try_share_anon_rmap(): invalidate PMD first.
		 */
		anon_exclusive = PageAnon(page) && PageAnonExclusive(page);
		if (freeze && anon_exclusive && page_try_share_anon_rmap(page))
			freeze = false;
		if (!freeze)
			page_ref_add(page, HPAGE_PMD_NR - 1);
	}

	/*
	 * Withdraw the table only after we mark the pmd entry invalid.
	 * This's critical for some architectures (Power).
	 */
	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
	pmd_populate(mm, &_pmd, pgtable);

	for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) {
		pte_t entry, *pte;
		/*
		 * Note that NUMA hinting access restrictions are not
		 * transferred to avoid any possibility of altering
		 * permissions across VMAs.
		 */
		if (freeze || pmd_migration) {
			swp_entry_t swp_entry;
			if (write)
				swp_entry = make_writable_migration_entry(
							page_to_pfn(page + i));
			else if (anon_exclusive)
				swp_entry = make_readable_exclusive_migration_entry(
							page_to_pfn(page + i));
			else
				swp_entry = make_readable_migration_entry(
							page_to_pfn(page + i));
			if (young)
				swp_entry = make_migration_entry_young(swp_entry);
			if (dirty)
				swp_entry = make_migration_entry_dirty(swp_entry);
			entry = swp_entry_to_pte(swp_entry);
			if (soft_dirty)
				entry = pte_swp_mksoft_dirty(entry);
			if (uffd_wp)
				entry = pte_swp_mkuffd_wp(entry);
		} else {
			entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot));
			entry = maybe_mkwrite(entry, vma);
			if (anon_exclusive)
				SetPageAnonExclusive(page + i);
			if (!young)
				entry = pte_mkold(entry);
			/* NOTE: this may set soft-dirty too on some archs */
			if (dirty)
				entry = pte_mkdirty(entry);
			/*
			 * NOTE: this needs to happen after pte_mkdirty,
			 * because some archs (sparc64, loongarch) could
			 * set hw write bit when mkdirty.
			 */
			if (!write)
				entry = pte_wrprotect(entry);
			if (soft_dirty)
				entry = pte_mksoft_dirty(entry);
			if (uffd_wp)
				entry = pte_mkuffd_wp(entry);
			page_add_anon_rmap(page + i, vma, addr, false);
		}
		pte = pte_offset_map(&_pmd, addr);
		BUG_ON(!pte_none(*pte));
		set_pte_at(mm, addr, pte, entry);
		pte_unmap(pte);
	}

	if (!pmd_migration)
		page_remove_rmap(page, vma, true);
	if (freeze)
		put_page(page);

	smp_wmb(); /* make pte visible before pmd */
	pmd_populate(mm, pmd, pgtable);
}

void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
		unsigned long address, bool freeze, struct folio *folio)
{
	spinlock_t *ptl;
	struct mmu_notifier_range range;

	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
				address & HPAGE_PMD_MASK,
				(address & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE);
	mmu_notifier_invalidate_range_start(&range);
	ptl = pmd_lock(vma->vm_mm, pmd);

	/*
	 * If caller asks to setup a migration entry, we need a folio to check
	 * pmd against. Otherwise we can end up replacing wrong folio.
	 */
	VM_BUG_ON(freeze && !folio);
	VM_WARN_ON_ONCE(folio && !folio_test_locked(folio));

	if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) ||
	    is_pmd_migration_entry(*pmd)) {
		/*
		 * It's safe to call pmd_page when folio is set because it's
		 * guaranteed that pmd is present.
		 */
		if (folio && folio != page_folio(pmd_page(*pmd)))
			goto out;
		__split_huge_pmd_locked(vma, pmd, range.start, freeze);
	}

out:
	spin_unlock(ptl);
	/*
	 * No need to double call mmu_notifier->invalidate_range() callback.
	 * They are 3 cases to consider inside __split_huge_pmd_locked():
	 *  1) pmdp_huge_clear_flush_notify() call invalidate_range() obvious
	 *  2) __split_huge_zero_page_pmd() read only zero page and any write
	 *    fault will trigger a flush_notify before pointing to a new page
	 *    (it is fine if the secondary mmu keeps pointing to the old zero
	 *    page in the meantime)
	 *  3) Split a huge pmd into pte pointing to the same page. No need
	 *     to invalidate secondary tlb entry they are all still valid.
	 *     any further changes to individual pte will notify. So no need
	 *     to call mmu_notifier->invalidate_range()
	 */
	mmu_notifier_invalidate_range_only_end(&range);
}

void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
		bool freeze, struct folio *folio)
{
	pmd_t *pmd = mm_find_pmd(vma->vm_mm, address);

	if (!pmd)
		return;

	__split_huge_pmd(vma, pmd, address, freeze, folio);
}

static inline void split_huge_pmd_if_needed(struct vm_area_struct *vma, unsigned long address)
{
	/*
	 * If the new address isn't hpage aligned and it could previously
	 * contain an hugepage: check if we need to split an huge pmd.
	 */
	if (!IS_ALIGNED(address, HPAGE_PMD_SIZE) &&
	    range_in_vma(vma, ALIGN_DOWN(address, HPAGE_PMD_SIZE),
			 ALIGN(address, HPAGE_PMD_SIZE)))
		split_huge_pmd_address(vma, address, false, NULL);
}

void vma_adjust_trans_huge(struct vm_area_struct *vma,
			     unsigned long start,
			     unsigned long end,
			     long adjust_next)
{
	/* Check if we need to split start first. */
	split_huge_pmd_if_needed(vma, start);

	/* Check if we need to split end next. */
	split_huge_pmd_if_needed(vma, end);

	/*
	 * If we're also updating the next vma vm_start,
	 * check if we need to split it.
	 */
	if (adjust_next > 0) {
		struct vm_area_struct *next = find_vma(vma->vm_mm, vma->vm_end);
		unsigned long nstart = next->vm_start;
		nstart += adjust_next;
		split_huge_pmd_if_needed(next, nstart);
	}
}

static void unmap_folio(struct folio *folio)
{
	enum ttu_flags ttu_flags = TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD |
		TTU_SYNC;

	VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);

	/*
	 * Anon pages need migration entries to preserve them, but file
	 * pages can simply be left unmapped, then faulted back on demand.
	 * If that is ever changed (perhaps for mlock), update remap_page().
	 */
	if (folio_test_anon(folio))
		try_to_migrate(folio, ttu_flags);
	else
		try_to_unmap(folio, ttu_flags | TTU_IGNORE_MLOCK);
}

static void remap_page(struct folio *folio, unsigned long nr)
{
	int i = 0;

	/* If unmap_folio() uses try_to_migrate() on file, remove this check */
	if (!folio_test_anon(folio))
		return;
	for (;;) {
		remove_migration_ptes(folio, folio, true);
		i += folio_nr_pages(folio);
		if (i >= nr)
			break;
		folio = folio_next(folio);
	}
}

static void lru_add_page_tail(struct page *head, struct page *tail,
		struct lruvec *lruvec, struct list_head *list)
{
	VM_BUG_ON_PAGE(!PageHead(head), head);
	VM_BUG_ON_PAGE(PageCompound(tail), head);
	VM_BUG_ON_PAGE(PageLRU(tail), head);
	lockdep_assert_held(&lruvec->lru_lock);

	if (list) {
		/* page reclaim is reclaiming a huge page */
		VM_WARN_ON(PageLRU(head));
		get_page(tail);
		list_add_tail(&tail->lru, list);
	} else {
		/* head is still on lru (and we have it frozen) */
		VM_WARN_ON(!PageLRU(head));
		if (PageUnevictable(tail))
			tail->mlock_count = 0;
		else
			list_add_tail(&tail->lru, &head->lru);
		SetPageLRU(tail);
	}
}

static void __split_huge_page_tail(struct page *head, int tail,
		struct lruvec *lruvec, struct list_head *list)
{
	struct page *page_tail = head + tail;

	VM_BUG_ON_PAGE(atomic_read(&page_tail->_mapcount) != -1, page_tail);

	/*
	 * Clone page flags before unfreezing refcount.
	 *
	 * After successful get_page_unless_zero() might follow flags change,
	 * for example lock_page() which set PG_waiters.
	 *
	 * Note that for mapped sub-pages of an anonymous THP,
	 * PG_anon_exclusive has been cleared in unmap_folio() and is stored in
	 * the migration entry instead from where remap_page() will restore it.
	 * We can still have PG_anon_exclusive set on effectively unmapped and
	 * unreferenced sub-pages of an anonymous THP: we can simply drop
	 * PG_anon_exclusive (-> PG_mappedtodisk) for these here.
	 */
	page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
	page_tail->flags |= (head->flags &
			((1L << PG_referenced) |
			 (1L << PG_swapbacked) |
			 (1L << PG_swapcache) |
			 (1L << PG_mlocked) |
			 (1L << PG_uptodate) |
			 (1L << PG_active) |
			 (1L << PG_workingset) |
			 (1L << PG_locked) |
			 (1L << PG_unevictable) |
#ifdef CONFIG_ARCH_USES_PG_ARCH_X
			 (1L << PG_arch_2) |
			 (1L << PG_arch_3) |
#endif
			 (1L << PG_dirty) |
			 LRU_GEN_MASK | LRU_REFS_MASK));

	/* ->mapping in first and second tail page is replaced by other uses */
	VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING,
			page_tail);
	page_tail->mapping = head->mapping;
	page_tail->index = head->index + tail;

	/*
	 * page->private should not be set in tail pages with the exception
	 * of swap cache pages that store the swp_entry_t in tail pages.
	 * Fix up and warn once if private is unexpectedly set.
	 *
	 * What of 32-bit systems, on which folio->_pincount overlays
	 * head[1].private?  No problem: THP_SWAP is not enabled on 32-bit, and
	 * pincount must be 0 for folio_ref_freeze() to have succeeded.
	 */
	if (!folio_test_swapcache(page_folio(head))) {
		VM_WARN_ON_ONCE_PAGE(page_tail->private != 0, page_tail);
		page_tail->private = 0;
	}

	/* Page flags must be visible before we make the page non-compound. */
	smp_wmb();

	/*
	 * Clear PageTail before unfreezing page refcount.
	 *
	 * After successful get_page_unless_zero() might follow put_page()
	 * which needs correct compound_head().
	 */
	clear_compound_head(page_tail);

	/* Finally unfreeze refcount. Additional reference from page cache. */
	page_ref_unfreeze(page_tail, 1 + (!PageAnon(head) ||
					  PageSwapCache(head)));

	if (page_is_young(head))
		set_page_young(page_tail);
	if (page_is_idle(head))
		set_page_idle(page_tail);

	page_cpupid_xchg_last(page_tail, page_cpupid_last(head));

	/*
	 * always add to the tail because some iterators expect new
	 * pages to show after the currently processed elements - e.g.
	 * migrate_pages
	 */
	lru_add_page_tail(head, page_tail, lruvec, list);
}

static void __split_huge_page(struct page *page, struct list_head *list,
		pgoff_t end)
{
	struct folio *folio = page_folio(page);
	struct page *head = &folio->page;
	struct lruvec *lruvec;
	struct address_space *swap_cache = NULL;
	unsigned long offset = 0;
	unsigned int nr = thp_nr_pages(head);
	int i;

	/* complete memcg works before add pages to LRU */
	split_page_memcg(head, nr);

	if (PageAnon(head) && PageSwapCache(head)) {
		swp_entry_t entry = { .val = page_private(head) };

		offset = swp_offset(entry);
		swap_cache = swap_address_space(entry);
		xa_lock(&swap_cache->i_pages);
	}

	/* lock lru list/PageCompound, ref frozen by page_ref_freeze */
	lruvec = folio_lruvec_lock(folio);

	ClearPageHasHWPoisoned(head);

	for (i = nr - 1; i >= 1; i--) {
		__split_huge_page_tail(head, i, lruvec, list);
		/* Some pages can be beyond EOF: drop them from page cache */
		if (head[i].index >= end) {
			struct folio *tail = page_folio(head + i);

			if (shmem_mapping(head->mapping))
				shmem_uncharge(head->mapping->host, 1);
			else if (folio_test_clear_dirty(tail))
				folio_account_cleaned(tail,
					inode_to_wb(folio->mapping->host));
			__filemap_remove_folio(tail, NULL);
			folio_put(tail);
		} else if (!PageAnon(page)) {
			__xa_store(&head->mapping->i_pages, head[i].index,
					head + i, 0);
		} else if (swap_cache) {
			__xa_store(&swap_cache->i_pages, offset + i,
					head + i, 0);
		}
	}

	ClearPageCompound(head);
	unlock_page_lruvec(lruvec);
	/* Caller disabled irqs, so they are still disabled here */

	split_page_owner(head, nr);

	/* See comment in __split_huge_page_tail() */
	if (PageAnon(head)) {
		/* Additional pin to swap cache */
		if (PageSwapCache(head)) {
			page_ref_add(head, 2);
			xa_unlock(&swap_cache->i_pages);
		} else {
			page_ref_inc(head);
		}
	} else {
		/* Additional pin to page cache */
		page_ref_add(head, 2);
		xa_unlock(&head->mapping->i_pages);
	}
	local_irq_enable();

	remap_page(folio, nr);

	if (PageSwapCache(head)) {
		swp_entry_t entry = { .val = page_private(head) };

		split_swap_cluster(entry);
	}

	for (i = 0; i < nr; i++) {
		struct page *subpage = head + i;
		if (subpage == page)
			continue;
		unlock_page(subpage);

		/*
		 * Subpages may be freed if there wasn't any mapping
		 * like if add_to_swap() is running on a lru page that
		 * had its mapping zapped. And freeing these pages
		 * requires taking the lru_lock so we do the put_page
		 * of the tail pages after the split is complete.
		 */
		free_page_and_swap_cache(subpage);
	}
}

/* Racy check whether the huge page can be split */
bool can_split_folio(struct folio *folio, int *pextra_pins)
{
	int extra_pins;

	/* Additional pins from page cache */
	if (folio_test_anon(folio))
		extra_pins = folio_test_swapcache(folio) ?
				folio_nr_pages(folio) : 0;
	else
		extra_pins = folio_nr_pages(folio);
	if (pextra_pins)
		*pextra_pins = extra_pins;
	return folio_mapcount(folio) == folio_ref_count(folio) - extra_pins - 1;
}

/*
 * This function splits huge page into normal pages. @page can point to any
 * subpage of huge page to split. Split doesn't change the position of @page.
 *
 * Only caller must hold pin on the @page, otherwise split fails with -EBUSY.
 * The huge page must be locked.
 *
 * If @list is null, tail pages will be added to LRU list, otherwise, to @list.
 *
 * Both head page and tail pages will inherit mapping, flags, and so on from
 * the hugepage.
 *
 * GUP pin and PG_locked transferred to @page. Rest subpages can be freed if
 * they are not mapped.
 *
 * Returns 0 if the hugepage is split successfully.
 * Returns -EBUSY if the page is pinned or if anon_vma disappeared from under
 * us.
 */
int split_huge_page_to_list(struct page *page, struct list_head *list)
{
	struct folio *folio = page_folio(page);
	struct deferred_split *ds_queue = get_deferred_split_queue(folio);
	XA_STATE(xas, &folio->mapping->i_pages, folio->index);
	struct anon_vma *anon_vma = NULL;
	struct address_space *mapping = NULL;
	int extra_pins, ret;
	pgoff_t end;
	bool is_hzp;

	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
	VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);

	is_hzp = is_huge_zero_page(&folio->page);
	VM_WARN_ON_ONCE_FOLIO(is_hzp, folio);
	if (is_hzp)
		return -EBUSY;

	if (folio_test_writeback(folio))
		return -EBUSY;

	if (folio_test_anon(folio)) {
		/*
		 * The caller does not necessarily hold an mmap_lock that would
		 * prevent the anon_vma disappearing so we first we take a
		 * reference to it and then lock the anon_vma for write. This
		 * is similar to folio_lock_anon_vma_read except the write lock
		 * is taken to serialise against parallel split or collapse
		 * operations.
		 */
		anon_vma = folio_get_anon_vma(folio);
		if (!anon_vma) {
			ret = -EBUSY;
			goto out;
		}
		end = -1;
		mapping = NULL;
		anon_vma_lock_write(anon_vma);
	} else {
		gfp_t gfp;

		mapping = folio->mapping;

		/* Truncated ? */
		if (!mapping) {
			ret = -EBUSY;
			goto out;
		}

		gfp = current_gfp_context(mapping_gfp_mask(mapping) &
							GFP_RECLAIM_MASK);

		if (folio_test_private(folio) &&
				!filemap_release_folio(folio, gfp)) {
			ret = -EBUSY;
			goto out;
		}

		xas_split_alloc(&xas, folio, folio_order(folio), gfp);
		if (xas_error(&xas)) {
			ret = xas_error(&xas);
			goto out;
		}

		anon_vma = NULL;
		i_mmap_lock_read(mapping);

		/*
		 *__split_huge_page() may need to trim off pages beyond EOF:
		 * but on 32-bit, i_size_read() takes an irq-unsafe seqlock,
		 * which cannot be nested inside the page tree lock. So note
		 * end now: i_size itself may be changed at any moment, but
		 * folio lock is good enough to serialize the trimming.
		 */
		end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
		if (shmem_mapping(mapping))
			end = shmem_fallocend(mapping->host, end);
	}

	/*
	 * Racy check if we can split the page, before unmap_folio() will
	 * split PMDs
	 */
	if (!can_split_folio(folio, &extra_pins)) {
		ret = -EAGAIN;
		goto out_unlock;
	}

	unmap_folio(folio);

	/* block interrupt reentry in xa_lock and spinlock */
	local_irq_disable();
	if (mapping) {
		/*
		 * Check if the folio is present in page cache.
		 * We assume all tail are present too, if folio is there.
		 */
		xas_lock(&xas);
		xas_reset(&xas);
		if (xas_load(&xas) != folio)
			goto fail;
	}

	/* Prevent deferred_split_scan() touching ->_refcount */
	spin_lock(&ds_queue->split_queue_lock);
	if (folio_ref_freeze(folio, 1 + extra_pins)) {
		if (!list_empty(&folio->_deferred_list)) {
			ds_queue->split_queue_len--;
			list_del(&folio->_deferred_list);
		}
		spin_unlock(&ds_queue->split_queue_lock);
		if (mapping) {
			int nr = folio_nr_pages(folio);

			xas_split(&xas, folio, folio_order(folio));
			if (folio_test_swapbacked(folio)) {
				__lruvec_stat_mod_folio(folio, NR_SHMEM_THPS,
							-nr);
			} else {
				__lruvec_stat_mod_folio(folio, NR_FILE_THPS,
							-nr);
				filemap_nr_thps_dec(mapping);
			}
		}

		__split_huge_page(page, list, end);
		ret = 0;
	} else {
		spin_unlock(&ds_queue->split_queue_lock);
fail:
		if (mapping)
			xas_unlock(&xas);
		local_irq_enable();
		remap_page(folio, folio_nr_pages(folio));
		ret = -EAGAIN;
	}

out_unlock:
	if (anon_vma) {
		anon_vma_unlock_write(anon_vma);
		put_anon_vma(anon_vma);
	}
	if (mapping)
		i_mmap_unlock_read(mapping);
out:
	xas_destroy(&xas);
	count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED);
	return ret;
}

void free_transhuge_page(struct page *page)
{
	struct folio *folio = (struct folio *)page;
	struct deferred_split *ds_queue = get_deferred_split_queue(folio);
	unsigned long flags;

	spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
	if (!list_empty(&folio->_deferred_list)) {
		ds_queue->split_queue_len--;
		list_del(&folio->_deferred_list);
	}
	spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
	free_compound_page(page);
}

void deferred_split_folio(struct folio *folio)
{
	struct deferred_split *ds_queue = get_deferred_split_queue(folio);
#ifdef CONFIG_MEMCG
	struct mem_cgroup *memcg = folio_memcg(folio);
#endif
	unsigned long flags;

	VM_BUG_ON_FOLIO(folio_order(folio) < 2, folio);

	/*
	 * The try_to_unmap() in page reclaim path might reach here too,
	 * this may cause a race condition to corrupt deferred split queue.
	 * And, if page reclaim is already handling the same folio, it is
	 * unnecessary to handle it again in shrinker.
	 *
	 * Check the swapcache flag to determine if the folio is being
	 * handled by page reclaim since THP swap would add the folio into
	 * swap cache before calling try_to_unmap().
	 */
	if (folio_test_swapcache(folio))
		return;

	if (!list_empty(&folio->_deferred_list))
		return;

	spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
	if (list_empty(&folio->_deferred_list)) {
		count_vm_event(THP_DEFERRED_SPLIT_PAGE);
		list_add_tail(&folio->_deferred_list, &ds_queue->split_queue);
		ds_queue->split_queue_len++;
#ifdef CONFIG_MEMCG
		if (memcg)
			set_shrinker_bit(memcg, folio_nid(folio),
					 deferred_split_shrinker.id);
#endif
	}
	spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
}

static unsigned long deferred_split_count(struct shrinker *shrink,
		struct shrink_control *sc)
{
	struct pglist_data *pgdata = NODE_DATA(sc->nid);
	struct deferred_split *ds_queue = &pgdata->deferred_split_queue;

#ifdef CONFIG_MEMCG
	if (sc->memcg)
		ds_queue = &sc->memcg->deferred_split_queue;
#endif
	return READ_ONCE(ds_queue->split_queue_len);
}

static unsigned long deferred_split_scan(struct shrinker *shrink,
		struct shrink_control *sc)
{
	struct pglist_data *pgdata = NODE_DATA(sc->nid);
	struct deferred_split *ds_queue = &pgdata->deferred_split_queue;
	unsigned long flags;
	LIST_HEAD(list);
	struct folio *folio, *next;
	int split = 0;

#ifdef CONFIG_MEMCG
	if (sc->memcg)
		ds_queue = &sc->memcg->deferred_split_queue;
#endif

	spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
	/* Take pin on all head pages to avoid freeing them under us */
	list_for_each_entry_safe(folio, next, &ds_queue->split_queue,
							_deferred_list) {
		if (folio_try_get(folio)) {
			list_move(&folio->_deferred_list, &list);
		} else {
			/* We lost race with folio_put() */
			list_del_init(&folio->_deferred_list);
			ds_queue->split_queue_len--;
		}
		if (!--sc->nr_to_scan)
			break;
	}
	spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);

	list_for_each_entry_safe(folio, next, &list, _deferred_list) {
		if (!folio_trylock(folio))
			goto next;
		/* split_huge_page() removes page from list on success */
		if (!split_folio(folio))
			split++;
		folio_unlock(folio);
next:
		folio_put(folio);
	}

	spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
	list_splice_tail(&list, &ds_queue->split_queue);
	spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);

	/*
	 * Stop shrinker if we didn't split any page, but the queue is empty.
	 * This can happen if pages were freed under us.
	 */
	if (!split && list_empty(&ds_queue->split_queue))
		return SHRINK_STOP;
	return split;
}

static struct shrinker deferred_split_shrinker = {
	.count_objects = deferred_split_count,
	.scan_objects = deferred_split_scan,
	.seeks = DEFAULT_SEEKS,
	.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE |
		 SHRINKER_NONSLAB,
};

#ifdef CONFIG_DEBUG_FS
static void split_huge_pages_all(void)
{
	struct zone *zone;
	struct page *page;
	struct folio *folio;
	unsigned long pfn, max_zone_pfn;
	unsigned long total = 0, split = 0;

	pr_debug("Split all THPs\n");
	for_each_zone(zone) {
		if (!managed_zone(zone))
			continue;
		max_zone_pfn = zone_end_pfn(zone);
		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) {
			int nr_pages;

			page = pfn_to_online_page(pfn);
			if (!page || PageTail(page))
				continue;
			folio = page_folio(page);
			if (!folio_try_get(folio))
				continue;

			if (unlikely(page_folio(page) != folio))
				goto next;

			if (zone != folio_zone(folio))
				goto next;

			if (!folio_test_large(folio)
				|| folio_test_hugetlb(folio)
				|| !folio_test_lru(folio))
				goto next;

			total++;
			folio_lock(folio);
			nr_pages = folio_nr_pages(folio);
			if (!split_folio(folio))
				split++;
			pfn += nr_pages - 1;
			folio_unlock(folio);
next:
			folio_put(folio);
			cond_resched();
		}
	}

	pr_debug("%lu of %lu THP split\n", split, total);
}

static inline bool vma_not_suitable_for_thp_split(struct vm_area_struct *vma)
{
	return vma_is_special_huge(vma) || (vma->vm_flags & VM_IO) ||
		    is_vm_hugetlb_page(vma);
}

static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
				unsigned long vaddr_end)
{
	int ret = 0;
	struct task_struct *task;
	struct mm_struct *mm;
	unsigned long total = 0, split = 0;
	unsigned long addr;

	vaddr_start &= PAGE_MASK;
	vaddr_end &= PAGE_MASK;

	/* Find the task_struct from pid */
	rcu_read_lock();
	task = find_task_by_vpid(pid);
	if (!task) {
		rcu_read_unlock();
		ret = -ESRCH;
		goto out;
	}
	get_task_struct(task);
	rcu_read_unlock();

	/* Find the mm_struct */
	mm = get_task_mm(task);
	put_task_struct(task);

	if (!mm) {
		ret = -EINVAL;
		goto out;
	}

	pr_debug("Split huge pages in pid: %d, vaddr: [0x%lx - 0x%lx]\n",
		 pid, vaddr_start, vaddr_end);

	mmap_read_lock(mm);
	/*
	 * always increase addr by PAGE_SIZE, since we could have a PTE page
	 * table filled with PTE-mapped THPs, each of which is distinct.
	 */
	for (addr = vaddr_start; addr < vaddr_end; addr += PAGE_SIZE) {
		struct vm_area_struct *vma = vma_lookup(mm, addr);
		struct page *page;

		if (!vma)
			break;

		/* skip special VMA and hugetlb VMA */
		if (vma_not_suitable_for_thp_split(vma)) {
			addr = vma->vm_end;
			continue;
		}

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

		if (IS_ERR_OR_NULL(page))
			continue;

		if (!is_transparent_hugepage(page))
			goto next;

		total++;
		if (!can_split_folio(page_folio(page), NULL))
			goto next;

		if (!trylock_page(page))
			goto next;

		if (!split_huge_page(page))
			split++;

		unlock_page(page);
next:
		put_page(page);
		cond_resched();
	}
	mmap_read_unlock(mm);
	mmput(mm);

	pr_debug("%lu of %lu THP split\n", split, total);

out:
	return ret;
}

static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start,
				pgoff_t off_end)
{
	struct filename *file;
	struct file *candidate;
	struct address_space *mapping;
	int ret = -EINVAL;
	pgoff_t index;
	int nr_pages = 1;
	unsigned long total = 0, split = 0;

	file = getname_kernel(file_path);
	if (IS_ERR(file))
		return ret;

	candidate = file_open_name(file, O_RDONLY, 0);
	if (IS_ERR(candidate))
		goto out;

	pr_debug("split file-backed THPs in file: %s, page offset: [0x%lx - 0x%lx]\n",
		 file_path, off_start, off_end);

	mapping = candidate->f_mapping;

	for (index = off_start; index < off_end; index += nr_pages) {
		struct folio *folio = __filemap_get_folio(mapping, index,
						FGP_ENTRY, 0);

		nr_pages = 1;
		if (xa_is_value(folio) || !folio)
			continue;

		if (!folio_test_large(folio))
			goto next;

		total++;
		nr_pages = folio_nr_pages(folio);

		if (!folio_trylock(folio))
			goto next;

		if (!split_folio(folio))
			split++;

		folio_unlock(folio);
next:
		folio_put(folio);
		cond_resched();
	}

	filp_close(candidate, NULL);
	ret = 0;

	pr_debug("%lu of %lu file-backed THP split\n", split, total);
out:
	putname(file);
	return ret;
}

#define MAX_INPUT_BUF_SZ 255

static ssize_t split_huge_pages_write(struct file *file, const char __user *buf,
				size_t count, loff_t *ppops)
{
	static DEFINE_MUTEX(split_debug_mutex);
	ssize_t ret;
	/* hold pid, start_vaddr, end_vaddr or file_path, off_start, off_end */
	char input_buf[MAX_INPUT_BUF_SZ];
	int pid;
	unsigned long vaddr_start, vaddr_end;

	ret = mutex_lock_interruptible(&split_debug_mutex);
	if (ret)
		return ret;

	ret = -EFAULT;

	memset(input_buf, 0, MAX_INPUT_BUF_SZ);
	if (copy_from_user(input_buf, buf, min_t(size_t, count, MAX_INPUT_BUF_SZ)))
		goto out;

	input_buf[MAX_INPUT_BUF_SZ - 1] = '\0';

	if (input_buf[0] == '/') {
		char *tok;
		char *buf = input_buf;
		char file_path[MAX_INPUT_BUF_SZ];
		pgoff_t off_start = 0, off_end = 0;
		size_t input_len = strlen(input_buf);

		tok = strsep(&buf, ",");
		if (tok) {
			strcpy(file_path, tok);
		} else {
			ret = -EINVAL;
			goto out;
		}

		ret = sscanf(buf, "0x%lx,0x%lx", &off_start, &off_end);
		if (ret != 2) {
			ret = -EINVAL;
			goto out;
		}
		ret = split_huge_pages_in_file(file_path, off_start, off_end);
		if (!ret)
			ret = input_len;

		goto out;
	}

	ret = sscanf(input_buf, "%d,0x%lx,0x%lx", &pid, &vaddr_start, &vaddr_end);
	if (ret == 1 && pid == 1) {
		split_huge_pages_all();
		ret = strlen(input_buf);
		goto out;
	} else if (ret != 3) {
		ret = -EINVAL;
		goto out;
	}

	ret = split_huge_pages_pid(pid, vaddr_start, vaddr_end);
	if (!ret)
		ret = strlen(input_buf);
out:
	mutex_unlock(&split_debug_mutex);
	return ret;

}

static const struct file_operations split_huge_pages_fops = {
	.owner	 = THIS_MODULE,
	.write	 = split_huge_pages_write,
	.llseek  = no_llseek,
};

static int __init split_huge_pages_debugfs(void)
{
	debugfs_create_file("split_huge_pages", 0200, NULL, NULL,
			    &split_huge_pages_fops);
	return 0;
}
late_initcall(split_huge_pages_debugfs);
#endif

#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
		struct page *page)
{
	struct vm_area_struct *vma = pvmw->vma;
	struct mm_struct *mm = vma->vm_mm;
	unsigned long address = pvmw->address;
	bool anon_exclusive;
	pmd_t pmdval;
	swp_entry_t entry;
	pmd_t pmdswp;

	if (!(pvmw->pmd && !pvmw->pte))
		return 0;

	flush_cache_range(vma, address, address + HPAGE_PMD_SIZE);
	pmdval = pmdp_invalidate(vma, address, pvmw->pmd);

	/* See page_try_share_anon_rmap(): invalidate PMD first. */
	anon_exclusive = PageAnon(page) && PageAnonExclusive(page);
	if (anon_exclusive && page_try_share_anon_rmap(page)) {
		set_pmd_at(mm, address, pvmw->pmd, pmdval);
		return -EBUSY;
	}

	if (pmd_dirty(pmdval))
		set_page_dirty(page);
	if (pmd_write(pmdval))
		entry = make_writable_migration_entry(page_to_pfn(page));
	else if (anon_exclusive)
		entry = make_readable_exclusive_migration_entry(page_to_pfn(page));
	else
		entry = make_readable_migration_entry(page_to_pfn(page));
	if (pmd_young(pmdval))
		entry = make_migration_entry_young(entry);
	if (pmd_dirty(pmdval))
		entry = make_migration_entry_dirty(entry);
	pmdswp = swp_entry_to_pmd(entry);
	if (pmd_soft_dirty(pmdval))
		pmdswp = pmd_swp_mksoft_dirty(pmdswp);
	set_pmd_at(mm, address, pvmw->pmd, pmdswp);
	page_remove_rmap(page, vma, true);
	put_page(page);
	trace_set_migration_pmd(address, pmd_val(pmdswp));

	return 0;
}

void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
{
	struct vm_area_struct *vma = pvmw->vma;
	struct mm_struct *mm = vma->vm_mm;
	unsigned long address = pvmw->address;
	unsigned long haddr = address & HPAGE_PMD_MASK;
	pmd_t pmde;
	swp_entry_t entry;

	if (!(pvmw->pmd && !pvmw->pte))
		return;

	entry = pmd_to_swp_entry(*pvmw->pmd);
	get_page(new);
	pmde = mk_huge_pmd(new, READ_ONCE(vma->vm_page_prot));
	if (pmd_swp_soft_dirty(*pvmw->pmd))
		pmde = pmd_mksoft_dirty(pmde);
	if (pmd_swp_uffd_wp(*pvmw->pmd))
		pmde = pmd_mkuffd_wp(pmde);
	if (!is_migration_entry_young(entry))
		pmde = pmd_mkold(pmde);
	/* NOTE: this may contain setting soft-dirty on some archs */
	if (PageDirty(new) && is_migration_entry_dirty(entry))
		pmde = pmd_mkdirty(pmde);
	if (is_writable_migration_entry(entry))
		pmde = maybe_pmd_mkwrite(pmde, vma);
	else
		pmde = pmd_wrprotect(pmde);

	if (PageAnon(new)) {
		rmap_t rmap_flags = RMAP_COMPOUND;

		if (!is_readable_migration_entry(entry))
			rmap_flags |= RMAP_EXCLUSIVE;

		page_add_anon_rmap(new, vma, haddr, rmap_flags);
	} else {
		page_add_file_rmap(new, vma, true);
	}
	VM_BUG_ON(pmd_write(pmde) && PageAnon(new) && !PageAnonExclusive(new));
	set_pmd_at(mm, haddr, pvmw->pmd, pmde);

	/* No need to invalidate - it was non-present before */
	update_mmu_cache_pmd(vma, address, pvmw->pmd);
	trace_remove_migration_pmd(address, pmd_val(pmde));
}
#endif