aboutsummaryrefslogtreecommitdiff
path: root/mm/hugetlb.c
blob: af20b77a624ac9fd043beed9310faeba8c8ae441 (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
/*
 * Generic hugetlb support.
 * (C) William Irwin, April 2004
 */
#include <linux/list.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/seq_file.h>
#include <linux/sysctl.h>
#include <linux/highmem.h>
#include <linux/mmu_notifier.h>
#include <linux/nodemask.h>
#include <linux/pagemap.h>
#include <linux/mempolicy.h>
#include <linux/cpuset.h>
#include <linux/mutex.h>
#include <linux/bootmem.h>
#include <linux/sysfs.h>
#include <linux/slab.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/swapops.h>

#include <asm/page.h>
#include <asm/pgtable.h>
#include <linux/io.h>

#include <linux/hugetlb.h>
#include <linux/node.h>
#include "internal.h"

const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL;
static gfp_t htlb_alloc_mask = GFP_HIGHUSER;
unsigned long hugepages_treat_as_movable;

static int max_hstate;
unsigned int default_hstate_idx;
struct hstate hstates[HUGE_MAX_HSTATE];

__initdata LIST_HEAD(huge_boot_pages);

/* for command line parsing */
static struct hstate * __initdata parsed_hstate;
static unsigned long __initdata default_hstate_max_huge_pages;
static unsigned long __initdata default_hstate_size;

#define for_each_hstate(h) \
	for ((h) = hstates; (h) < &hstates[max_hstate]; (h)++)

/*
 * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages
 */
static DEFINE_SPINLOCK(hugetlb_lock);

static inline void unlock_or_release_subpool(struct hugepage_subpool *spool)
{
	bool free = (spool->count == 0) && (spool->used_hpages == 0);

	spin_unlock(&spool->lock);

	/* If no pages are used, and no other handles to the subpool
	 * remain, free the subpool the subpool remain */
	if (free)
		kfree(spool);
}

struct hugepage_subpool *hugepage_new_subpool(long nr_blocks)
{
	struct hugepage_subpool *spool;

	spool = kmalloc(sizeof(*spool), GFP_KERNEL);
	if (!spool)
		return NULL;

	spin_lock_init(&spool->lock);
	spool->count = 1;
	spool->max_hpages = nr_blocks;
	spool->used_hpages = 0;

	return spool;
}

void hugepage_put_subpool(struct hugepage_subpool *spool)
{
	spin_lock(&spool->lock);
	BUG_ON(!spool->count);
	spool->count--;
	unlock_or_release_subpool(spool);
}

static int hugepage_subpool_get_pages(struct hugepage_subpool *spool,
				      long delta)
{
	int ret = 0;

	if (!spool)
		return 0;

	spin_lock(&spool->lock);
	if ((spool->used_hpages + delta) <= spool->max_hpages) {
		spool->used_hpages += delta;
	} else {
		ret = -ENOMEM;
	}
	spin_unlock(&spool->lock);

	return ret;
}

static void hugepage_subpool_put_pages(struct hugepage_subpool *spool,
				       long delta)
{
	if (!spool)
		return;

	spin_lock(&spool->lock);
	spool->used_hpages -= delta;
	/* If hugetlbfs_put_super couldn't free spool due to
	* an outstanding quota reference, free it now. */
	unlock_or_release_subpool(spool);
}

static inline struct hugepage_subpool *subpool_inode(struct inode *inode)
{
	return HUGETLBFS_SB(inode->i_sb)->spool;
}

static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma)
{
	return subpool_inode(vma->vm_file->f_dentry->d_inode);
}

/*
 * Region tracking -- allows tracking of reservations and instantiated pages
 *                    across the pages in a mapping.
 *
 * The region data structures are protected by a combination of the mmap_sem
 * and the hugetlb_instantion_mutex.  To access or modify a region the caller
 * must either hold the mmap_sem for write, or the mmap_sem for read and
 * the hugetlb_instantiation mutex:
 *
 *	down_write(&mm->mmap_sem);
 * or
 *	down_read(&mm->mmap_sem);
 *	mutex_lock(&hugetlb_instantiation_mutex);
 */
struct file_region {
	struct list_head link;
	long from;
	long to;
};

static long region_add(struct list_head *head, long f, long t)
{
	struct file_region *rg, *nrg, *trg;

	/* Locate the region we are either in or before. */
	list_for_each_entry(rg, head, link)
		if (f <= rg->to)
			break;

	/* Round our left edge to the current segment if it encloses us. */
	if (f > rg->from)
		f = rg->from;

	/* Check for and consume any regions we now overlap with. */
	nrg = rg;
	list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
		if (&rg->link == head)
			break;
		if (rg->from > t)
			break;

		/* If this area reaches higher then extend our area to
		 * include it completely.  If this is not the first area
		 * which we intend to reuse, free it. */
		if (rg->to > t)
			t = rg->to;
		if (rg != nrg) {
			list_del(&rg->link);
			kfree(rg);
		}
	}
	nrg->from = f;
	nrg->to = t;
	return 0;
}

static long region_chg(struct list_head *head, long f, long t)
{
	struct file_region *rg, *nrg;
	long chg = 0;

	/* Locate the region we are before or in. */
	list_for_each_entry(rg, head, link)
		if (f <= rg->to)
			break;

	/* If we are below the current region then a new region is required.
	 * Subtle, allocate a new region at the position but make it zero
	 * size such that we can guarantee to record the reservation. */
	if (&rg->link == head || t < rg->from) {
		nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
		if (!nrg)
			return -ENOMEM;
		nrg->from = f;
		nrg->to   = f;
		INIT_LIST_HEAD(&nrg->link);
		list_add(&nrg->link, rg->link.prev);

		return t - f;
	}

	/* Round our left edge to the current segment if it encloses us. */
	if (f > rg->from)
		f = rg->from;
	chg = t - f;

	/* Check for and consume any regions we now overlap with. */
	list_for_each_entry(rg, rg->link.prev, link) {
		if (&rg->link == head)
			break;
		if (rg->from > t)
			return chg;

		/* We overlap with this area, if it extends further than
		 * us then we must extend ourselves.  Account for its
		 * existing reservation. */
		if (rg->to > t) {
			chg += rg->to - t;
			t = rg->to;
		}
		chg -= rg->to - rg->from;
	}
	return chg;
}

static long region_truncate(struct list_head *head, long end)
{
	struct file_region *rg, *trg;
	long chg = 0;

	/* Locate the region we are either in or before. */
	list_for_each_entry(rg, head, link)
		if (end <= rg->to)
			break;
	if (&rg->link == head)
		return 0;

	/* If we are in the middle of a region then adjust it. */
	if (end > rg->from) {
		chg = rg->to - end;
		rg->to = end;
		rg = list_entry(rg->link.next, typeof(*rg), link);
	}

	/* Drop any remaining regions. */
	list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
		if (&rg->link == head)
			break;
		chg += rg->to - rg->from;
		list_del(&rg->link);
		kfree(rg);
	}
	return chg;
}

static long region_count(struct list_head *head, long f, long t)
{
	struct file_region *rg;
	long chg = 0;

	/* Locate each segment we overlap with, and count that overlap. */
	list_for_each_entry(rg, head, link) {
		int seg_from;
		int seg_to;

		if (rg->to <= f)
			continue;
		if (rg->from >= t)
			break;

		seg_from = max(rg->from, f);
		seg_to = min(rg->to, t);

		chg += seg_to - seg_from;
	}

	return chg;
}

/*
 * Convert the address within this vma to the page offset within
 * the mapping, in pagecache page units; huge pages here.
 */
static pgoff_t vma_hugecache_offset(struct hstate *h,
			struct vm_area_struct *vma, unsigned long address)
{
	return ((address - vma->vm_start) >> huge_page_shift(h)) +
			(vma->vm_pgoff >> huge_page_order(h));
}

pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
				     unsigned long address)
{
	return vma_hugecache_offset(hstate_vma(vma), vma, address);
}

/*
 * Return the size of the pages allocated when backing a VMA. In the majority
 * cases this will be same size as used by the page table entries.
 */
unsigned long vma_kernel_pagesize(struct vm_area_struct *vma)
{
	struct hstate *hstate;

	if (!is_vm_hugetlb_page(vma))
		return PAGE_SIZE;

	hstate = hstate_vma(vma);

	return 1UL << (hstate->order + PAGE_SHIFT);
}
EXPORT_SYMBOL_GPL(vma_kernel_pagesize);

/*
 * Return the page size being used by the MMU to back a VMA. In the majority
 * of cases, the page size used by the kernel matches the MMU size. On
 * architectures where it differs, an architecture-specific version of this
 * function is required.
 */
#ifndef vma_mmu_pagesize
unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
{
	return vma_kernel_pagesize(vma);
}
#endif

/*
 * Flags for MAP_PRIVATE reservations.  These are stored in the bottom
 * bits of the reservation map pointer, which are always clear due to
 * alignment.
 */
#define HPAGE_RESV_OWNER    (1UL << 0)
#define HPAGE_RESV_UNMAPPED (1UL << 1)
#define HPAGE_RESV_MASK (HPAGE_RESV_OWNER | HPAGE_RESV_UNMAPPED)

/*
 * These helpers are used to track how many pages are reserved for
 * faults in a MAP_PRIVATE mapping. Only the process that called mmap()
 * is guaranteed to have their future faults succeed.
 *
 * With the exception of reset_vma_resv_huge_pages() which is called at fork(),
 * the reserve counters are updated with the hugetlb_lock held. It is safe
 * to reset the VMA at fork() time as it is not in use yet and there is no
 * chance of the global counters getting corrupted as a result of the values.
 *
 * The private mapping reservation is represented in a subtly different
 * manner to a shared mapping.  A shared mapping has a region map associated
 * with the underlying file, this region map represents the backing file
 * pages which have ever had a reservation assigned which this persists even
 * after the page is instantiated.  A private mapping has a region map
 * associated with the original mmap which is attached to all VMAs which
 * reference it, this region map represents those offsets which have consumed
 * reservation ie. where pages have been instantiated.
 */
static unsigned long get_vma_private_data(struct vm_area_struct *vma)
{
	return (unsigned long)vma->vm_private_data;
}

static void set_vma_private_data(struct vm_area_struct *vma,
							unsigned long value)
{
	vma->vm_private_data = (void *)value;
}

struct resv_map {
	struct kref refs;
	struct list_head regions;
};

static struct resv_map *resv_map_alloc(void)
{
	struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL);
	if (!resv_map)
		return NULL;

	kref_init(&resv_map->refs);
	INIT_LIST_HEAD(&resv_map->regions);

	return resv_map;
}

static void resv_map_release(struct kref *ref)
{
	struct resv_map *resv_map = container_of(ref, struct resv_map, refs);

	/* Clear out any active regions before we release the map. */
	region_truncate(&resv_map->regions, 0);
	kfree(resv_map);
}

static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
{
	VM_BUG_ON(!is_vm_hugetlb_page(vma));
	if (!(vma->vm_flags & VM_MAYSHARE))
		return (struct resv_map *)(get_vma_private_data(vma) &
							~HPAGE_RESV_MASK);
	return NULL;
}

static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map)
{
	VM_BUG_ON(!is_vm_hugetlb_page(vma));
	VM_BUG_ON(vma->vm_flags & VM_MAYSHARE);

	set_vma_private_data(vma, (get_vma_private_data(vma) &
				HPAGE_RESV_MASK) | (unsigned long)map);
}

static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags)
{
	VM_BUG_ON(!is_vm_hugetlb_page(vma));
	VM_BUG_ON(vma->vm_flags & VM_MAYSHARE);

	set_vma_private_data(vma, get_vma_private_data(vma) | flags);
}

static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag)
{
	VM_BUG_ON(!is_vm_hugetlb_page(vma));

	return (get_vma_private_data(vma) & flag) != 0;
}

/* Decrement the reserved pages in the hugepage pool by one */
static void decrement_hugepage_resv_vma(struct hstate *h,
			struct vm_area_struct *vma)
{
	if (vma->vm_flags & VM_NORESERVE)
		return;

	if (vma->vm_flags & VM_MAYSHARE) {
		/* Shared mappings always use reserves */
		h->resv_huge_pages--;
	} else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
		/*
		 * Only the process that called mmap() has reserves for
		 * private mappings.
		 */
		h->resv_huge_pages--;
	}
}

/* Reset counters to 0 and clear all HPAGE_RESV_* flags */
void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
{
	VM_BUG_ON(!is_vm_hugetlb_page(vma));
	if (!(vma->vm_flags & VM_MAYSHARE))
		vma->vm_private_data = (void *)0;
}

/* Returns true if the VMA has associated reserve pages */
static int vma_has_reserves(struct vm_area_struct *vma)
{
	if (vma->vm_flags & VM_MAYSHARE)
		return 1;
	if (is_vma_resv_set(vma, HPAGE_RESV_OWNER))
		return 1;
	return 0;
}

static void copy_gigantic_page(struct page *dst, struct page *src)
{
	int i;
	struct hstate *h = page_hstate(src);
	struct page *dst_base = dst;
	struct page *src_base = src;

	for (i = 0; i < pages_per_huge_page(h); ) {
		cond_resched();
		copy_highpage(dst, src);

		i++;
		dst = mem_map_next(dst, dst_base, i);
		src = mem_map_next(src, src_base, i);
	}
}

void copy_huge_page(struct page *dst, struct page *src)
{
	int i;
	struct hstate *h = page_hstate(src);

	if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) {
		copy_gigantic_page(dst, src);
		return;
	}

	might_sleep();
	for (i = 0; i < pages_per_huge_page(h); i++) {
		cond_resched();
		copy_highpage(dst + i, src + i);
	}
}

static void enqueue_huge_page(struct hstate *h, struct page *page)
{
	int nid = page_to_nid(page);
	list_add(&page->lru, &h->hugepage_freelists[nid]);
	h->free_huge_pages++;
	h->free_huge_pages_node[nid]++;
}

static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
{
	struct page *page;

	if (list_empty(&h->hugepage_freelists[nid]))
		return NULL;
	page = list_entry(h->hugepage_freelists[nid].next, struct page, lru);
	list_del(&page->lru);
	set_page_refcounted(page);
	h->free_huge_pages--;
	h->free_huge_pages_node[nid]--;
	return page;
}

static struct page *dequeue_huge_page_vma(struct hstate *h,
				struct vm_area_struct *vma,
				unsigned long address, int avoid_reserve)
{
	struct page *page = NULL;
	struct mempolicy *mpol;
	nodemask_t *nodemask;
	struct zonelist *zonelist;
	struct zone *zone;
	struct zoneref *z;
	unsigned int cpuset_mems_cookie;

retry_cpuset:
	cpuset_mems_cookie = get_mems_allowed();
	zonelist = huge_zonelist(vma, address,
					htlb_alloc_mask, &mpol, &nodemask);
	/*
	 * A child process with MAP_PRIVATE mappings created by their parent
	 * have no page reserves. This check ensures that reservations are
	 * not "stolen". The child may still get SIGKILLed
	 */
	if (!vma_has_reserves(vma) &&
			h->free_huge_pages - h->resv_huge_pages == 0)
		goto err;

	/* If reserves cannot be used, ensure enough pages are in the pool */
	if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0)
		goto err;

	for_each_zone_zonelist_nodemask(zone, z, zonelist,
						MAX_NR_ZONES - 1, nodemask) {
		if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask)) {
			page = dequeue_huge_page_node(h, zone_to_nid(zone));
			if (page) {
				if (!avoid_reserve)
					decrement_hugepage_resv_vma(h, vma);
				break;
			}
		}
	}

	mpol_cond_put(mpol);
	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
		goto retry_cpuset;
	return page;

err:
	mpol_cond_put(mpol);
	return NULL;
}

static void update_and_free_page(struct hstate *h, struct page *page)
{
	int i;

	VM_BUG_ON(h->order >= MAX_ORDER);

	h->nr_huge_pages--;
	h->nr_huge_pages_node[page_to_nid(page)]--;
	for (i = 0; i < pages_per_huge_page(h); i++) {
		page[i].flags &= ~(1 << PG_locked | 1 << PG_error |
				1 << PG_referenced | 1 << PG_dirty |
				1 << PG_active | 1 << PG_reserved |
				1 << PG_private | 1 << PG_writeback);
	}
	set_compound_page_dtor(page, NULL);
	set_page_refcounted(page);
	arch_release_hugepage(page);
	__free_pages(page, huge_page_order(h));
}

struct hstate *size_to_hstate(unsigned long size)
{
	struct hstate *h;

	for_each_hstate(h) {
		if (huge_page_size(h) == size)
			return h;
	}
	return NULL;
}

static void free_huge_page(struct page *page)
{
	/*
	 * Can't pass hstate in here because it is called from the
	 * compound page destructor.
	 */
	struct hstate *h = page_hstate(page);
	int nid = page_to_nid(page);
	struct hugepage_subpool *spool =
		(struct hugepage_subpool *)page_private(page);

	set_page_private(page, 0);
	page->mapping = NULL;
	BUG_ON(page_count(page));
	BUG_ON(page_mapcount(page));
	INIT_LIST_HEAD(&page->lru);

	spin_lock(&hugetlb_lock);
	if (h->surplus_huge_pages_node[nid] && huge_page_order(h) < MAX_ORDER) {
		update_and_free_page(h, page);
		h->surplus_huge_pages--;
		h->surplus_huge_pages_node[nid]--;
	} else {
		enqueue_huge_page(h, page);
	}
	spin_unlock(&hugetlb_lock);
	hugepage_subpool_put_pages(spool, 1);
}

static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
{
	set_compound_page_dtor(page, free_huge_page);
	spin_lock(&hugetlb_lock);
	h->nr_huge_pages++;
	h->nr_huge_pages_node[nid]++;
	spin_unlock(&hugetlb_lock);
	put_page(page); /* free it into the hugepage allocator */
}

static void prep_compound_gigantic_page(struct page *page, unsigned long order)
{
	int i;
	int nr_pages = 1 << order;
	struct page *p = page + 1;

	/* we rely on prep_new_huge_page to set the destructor */
	set_compound_order(page, order);
	__SetPageHead(page);
	for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
		__SetPageTail(p);
		set_page_count(p, 0);
		p->first_page = page;
	}
}

int PageHuge(struct page *page)
{
	compound_page_dtor *dtor;

	if (!PageCompound(page))
		return 0;

	page = compound_head(page);
	dtor = get_compound_page_dtor(page);

	return dtor == free_huge_page;
}
EXPORT_SYMBOL_GPL(PageHuge);

pgoff_t __basepage_index(struct page *page)
{
	struct page *page_head = compound_head(page);
	pgoff_t index = page_index(page_head);
	unsigned long compound_idx;

	if (!PageHuge(page_head))
		return page_index(page);

	if (compound_order(page_head) >= MAX_ORDER)
		compound_idx = page_to_pfn(page) - page_to_pfn(page_head);
	else
		compound_idx = page - page_head;

	return (index << compound_order(page_head)) + compound_idx;
}

static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
{
	struct page *page;

	if (h->order >= MAX_ORDER)
		return NULL;

	page = alloc_pages_exact_node(nid,
		htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
						__GFP_REPEAT|__GFP_NOWARN,
		huge_page_order(h));
	if (page) {
		if (arch_prepare_hugepage(page)) {
			__free_pages(page, huge_page_order(h));
			return NULL;
		}
		prep_new_huge_page(h, page, nid);
	}

	return page;
}

/*
 * common helper functions for hstate_next_node_to_{alloc|free}.
 * We may have allocated or freed a huge page based on a different
 * nodes_allowed previously, so h->next_node_to_{alloc|free} might
 * be outside of *nodes_allowed.  Ensure that we use an allowed
 * node for alloc or free.
 */
static int next_node_allowed(int nid, nodemask_t *nodes_allowed)
{
	nid = next_node(nid, *nodes_allowed);
	if (nid == MAX_NUMNODES)
		nid = first_node(*nodes_allowed);
	VM_BUG_ON(nid >= MAX_NUMNODES);

	return nid;
}

static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed)
{
	if (!node_isset(nid, *nodes_allowed))
		nid = next_node_allowed(nid, nodes_allowed);
	return nid;
}

/*
 * returns the previously saved node ["this node"] from which to
 * allocate a persistent huge page for the pool and advance the
 * next node from which to allocate, handling wrap at end of node
 * mask.
 */
static int hstate_next_node_to_alloc(struct hstate *h,
					nodemask_t *nodes_allowed)
{
	int nid;

	VM_BUG_ON(!nodes_allowed);

	nid = get_valid_node_allowed(h->next_nid_to_alloc, nodes_allowed);
	h->next_nid_to_alloc = next_node_allowed(nid, nodes_allowed);

	return nid;
}

static int alloc_fresh_huge_page(struct hstate *h, nodemask_t *nodes_allowed)
{
	struct page *page;
	int start_nid;
	int next_nid;
	int ret = 0;

	start_nid = hstate_next_node_to_alloc(h, nodes_allowed);
	next_nid = start_nid;

	do {
		page = alloc_fresh_huge_page_node(h, next_nid);
		if (page) {
			ret = 1;
			break;
		}
		next_nid = hstate_next_node_to_alloc(h, nodes_allowed);
	} while (next_nid != start_nid);

	if (ret)
		count_vm_event(HTLB_BUDDY_PGALLOC);
	else
		count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);

	return ret;
}

/*
 * helper for free_pool_huge_page() - return the previously saved
 * node ["this node"] from which to free a huge page.  Advance the
 * next node id whether or not we find a free huge page to free so
 * that the next attempt to free addresses the next node.
 */
static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
{
	int nid;

	VM_BUG_ON(!nodes_allowed);

	nid = get_valid_node_allowed(h->next_nid_to_free, nodes_allowed);
	h->next_nid_to_free = next_node_allowed(nid, nodes_allowed);

	return nid;
}

/*
 * Free huge page from pool from next node to free.
 * Attempt to keep persistent huge pages more or less
 * balanced over allowed nodes.
 * Called with hugetlb_lock locked.
 */
static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
							 bool acct_surplus)
{
	int start_nid;
	int next_nid;
	int ret = 0;

	start_nid = hstate_next_node_to_free(h, nodes_allowed);
	next_nid = start_nid;

	do {
		/*
		 * If we're returning unused surplus pages, only examine
		 * nodes with surplus pages.
		 */
		if ((!acct_surplus || h->surplus_huge_pages_node[next_nid]) &&
		    !list_empty(&h->hugepage_freelists[next_nid])) {
			struct page *page =
				list_entry(h->hugepage_freelists[next_nid].next,
					  struct page, lru);
			list_del(&page->lru);
			h->free_huge_pages--;
			h->free_huge_pages_node[next_nid]--;
			if (acct_surplus) {
				h->surplus_huge_pages--;
				h->surplus_huge_pages_node[next_nid]--;
			}
			update_and_free_page(h, page);
			ret = 1;
			break;
		}
		next_nid = hstate_next_node_to_free(h, nodes_allowed);
	} while (next_nid != start_nid);

	return ret;
}

static struct page *alloc_buddy_huge_page(struct hstate *h, int nid)
{
	struct page *page;
	unsigned int r_nid;

	if (h->order >= MAX_ORDER)
		return NULL;

	/*
	 * Assume we will successfully allocate the surplus page to
	 * prevent racing processes from causing the surplus to exceed
	 * overcommit
	 *
	 * This however introduces a different race, where a process B
	 * tries to grow the static hugepage pool while alloc_pages() is
	 * called by process A. B will only examine the per-node
	 * counters in determining if surplus huge pages can be
	 * converted to normal huge pages in adjust_pool_surplus(). A
	 * won't be able to increment the per-node counter, until the
	 * lock is dropped by B, but B doesn't drop hugetlb_lock until
	 * no more huge pages can be converted from surplus to normal
	 * state (and doesn't try to convert again). Thus, we have a
	 * case where a surplus huge page exists, the pool is grown, and
	 * the surplus huge page still exists after, even though it
	 * should just have been converted to a normal huge page. This
	 * does not leak memory, though, as the hugepage will be freed
	 * once it is out of use. It also does not allow the counters to
	 * go out of whack in adjust_pool_surplus() as we don't modify
	 * the node values until we've gotten the hugepage and only the
	 * per-node value is checked there.
	 */
	spin_lock(&hugetlb_lock);
	if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) {
		spin_unlock(&hugetlb_lock);
		return NULL;
	} else {
		h->nr_huge_pages++;
		h->surplus_huge_pages++;
	}
	spin_unlock(&hugetlb_lock);

	if (nid == NUMA_NO_NODE)
		page = alloc_pages(htlb_alloc_mask|__GFP_COMP|
				   __GFP_REPEAT|__GFP_NOWARN,
				   huge_page_order(h));
	else
		page = alloc_pages_exact_node(nid,
			htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
			__GFP_REPEAT|__GFP_NOWARN, huge_page_order(h));

	if (page && arch_prepare_hugepage(page)) {
		__free_pages(page, huge_page_order(h));
		page = NULL;
	}

	spin_lock(&hugetlb_lock);
	if (page) {
		r_nid = page_to_nid(page);
		set_compound_page_dtor(page, free_huge_page);
		/*
		 * We incremented the global counters already
		 */
		h->nr_huge_pages_node[r_nid]++;
		h->surplus_huge_pages_node[r_nid]++;
		__count_vm_event(HTLB_BUDDY_PGALLOC);
	} else {
		h->nr_huge_pages--;
		h->surplus_huge_pages--;
		__count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
	}
	spin_unlock(&hugetlb_lock);

	return page;
}

/*
 * This allocation function is useful in the context where vma is irrelevant.
 * E.g. soft-offlining uses this function because it only cares physical
 * address of error page.
 */
struct page *alloc_huge_page_node(struct hstate *h, int nid)
{
	struct page *page;

	spin_lock(&hugetlb_lock);
	page = dequeue_huge_page_node(h, nid);
	spin_unlock(&hugetlb_lock);

	if (!page)
		page = alloc_buddy_huge_page(h, nid);

	return page;
}

/*
 * Increase the hugetlb pool such that it can accommodate a reservation
 * of size 'delta'.
 */
static int gather_surplus_pages(struct hstate *h, int delta)
{
	struct list_head surplus_list;
	struct page *page, *tmp;
	int ret, i;
	int needed, allocated;
	bool alloc_ok = true;

	needed = (h->resv_huge_pages + delta) - h->free_huge_pages;
	if (needed <= 0) {
		h->resv_huge_pages += delta;
		return 0;
	}

	allocated = 0;
	INIT_LIST_HEAD(&surplus_list);

	ret = -ENOMEM;
retry:
	spin_unlock(&hugetlb_lock);
	for (i = 0; i < needed; i++) {
		page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
		if (!page) {
			alloc_ok = false;
			break;
		}
		list_add(&page->lru, &surplus_list);
	}
	allocated += i;

	/*
	 * After retaking hugetlb_lock, we need to recalculate 'needed'
	 * because either resv_huge_pages or free_huge_pages may have changed.
	 */
	spin_lock(&hugetlb_lock);
	needed = (h->resv_huge_pages + delta) -
			(h->free_huge_pages + allocated);
	if (needed > 0) {
		if (alloc_ok)
			goto retry;
		/*
		 * We were not able to allocate enough pages to
		 * satisfy the entire reservation so we free what
		 * we've allocated so far.
		 */
		goto free;
	}
	/*
	 * The surplus_list now contains _at_least_ the number of extra pages
	 * needed to accommodate the reservation.  Add the appropriate number
	 * of pages to the hugetlb pool and free the extras back to the buddy
	 * allocator.  Commit the entire reservation here to prevent another
	 * process from stealing the pages as they are added to the pool but
	 * before they are reserved.
	 */
	needed += allocated;
	h->resv_huge_pages += delta;
	ret = 0;

	/* Free the needed pages to the hugetlb pool */
	list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
		if ((--needed) < 0)
			break;
		list_del(&page->lru);
		/*
		 * This page is now managed by the hugetlb allocator and has
		 * no users -- drop the buddy allocator's reference.
		 */
		put_page_testzero(page);
		VM_BUG_ON(page_count(page));
		enqueue_huge_page(h, page);
	}
free:
	spin_unlock(&hugetlb_lock);

	/* Free unnecessary surplus pages to the buddy allocator */
	if (!list_empty(&surplus_list)) {
		list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
			list_del(&page->lru);
			put_page(page);
		}
	}
	spin_lock(&hugetlb_lock);

	return ret;
}

/*
 * When releasing a hugetlb pool reservation, any surplus pages that were
 * allocated to satisfy the reservation must be explicitly freed if they were
 * never used.
 * Called with hugetlb_lock held.
 */
static void return_unused_surplus_pages(struct hstate *h,
					unsigned long unused_resv_pages)
{
	unsigned long nr_pages;

	/* Uncommit the reservation */
	h->resv_huge_pages -= unused_resv_pages;

	/* Cannot return gigantic pages currently */
	if (h->order >= MAX_ORDER)
		return;

	nr_pages = min(unused_resv_pages, h->surplus_huge_pages);

	/*
	 * We want to release as many surplus pages as possible, spread
	 * evenly across all nodes with memory. Iterate across these nodes
	 * until we can no longer free unreserved surplus pages. This occurs
	 * when the nodes with surplus pages have no free pages.
	 * free_pool_huge_page() will balance the the freed pages across the
	 * on-line nodes with memory and will handle the hstate accounting.
	 */
	while (nr_pages--) {
		if (!free_pool_huge_page(h, &node_states[N_HIGH_MEMORY], 1))
			break;
	}
}

/*
 * Determine if the huge page at addr within the vma has an associated
 * reservation.  Where it does not we will need to logically increase
 * reservation and actually increase subpool usage before an allocation
 * can occur.  Where any new reservation would be required the
 * reservation change is prepared, but not committed.  Once the page
 * has been allocated from the subpool and instantiated the change should
 * be committed via vma_commit_reservation.  No action is required on
 * failure.
 */
static long vma_needs_reservation(struct hstate *h,
			struct vm_area_struct *vma, unsigned long addr)
{
	struct address_space *mapping = vma->vm_file->f_mapping;
	struct inode *inode = mapping->host;

	if (vma->vm_flags & VM_MAYSHARE) {
		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
		return region_chg(&inode->i_mapping->private_list,
							idx, idx + 1);

	} else if (!is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
		return 1;

	} else  {
		long err;
		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
		struct resv_map *reservations = vma_resv_map(vma);

		err = region_chg(&reservations->regions, idx, idx + 1);
		if (err < 0)
			return err;
		return 0;
	}
}
static void vma_commit_reservation(struct hstate *h,
			struct vm_area_struct *vma, unsigned long addr)
{
	struct address_space *mapping = vma->vm_file->f_mapping;
	struct inode *inode = mapping->host;

	if (vma->vm_flags & VM_MAYSHARE) {
		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
		region_add(&inode->i_mapping->private_list, idx, idx + 1);

	} else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
		struct resv_map *reservations = vma_resv_map(vma);

		/* Mark this page used in the map. */
		region_add(&reservations->regions, idx, idx + 1);
	}
}

static struct page *alloc_huge_page(struct vm_area_struct *vma,
				    unsigned long addr, int avoid_reserve)
{
	struct hugepage_subpool *spool = subpool_vma(vma);
	struct hstate *h = hstate_vma(vma);
	struct page *page;
	long chg;

	/*
	 * Processes that did not create the mapping will have no
	 * reserves and will not have accounted against subpool
	 * limit. Check that the subpool limit can be made before
	 * satisfying the allocation MAP_NORESERVE mappings may also
	 * need pages and subpool limit allocated allocated if no reserve
	 * mapping overlaps.
	 */
	chg = vma_needs_reservation(h, vma, addr);
	if (chg < 0)
		return ERR_PTR(-VM_FAULT_OOM);
	if (chg)
		if (hugepage_subpool_get_pages(spool, chg))
			return ERR_PTR(-VM_FAULT_SIGBUS);

	spin_lock(&hugetlb_lock);
	page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve);
	spin_unlock(&hugetlb_lock);

	if (!page) {
		page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
		if (!page) {
			hugepage_subpool_put_pages(spool, chg);
			return ERR_PTR(-VM_FAULT_SIGBUS);
		}
	}

	set_page_private(page, (unsigned long)spool);

	vma_commit_reservation(h, vma, addr);

	return page;
}

int __weak alloc_bootmem_huge_page(struct hstate *h)
{
	struct huge_bootmem_page *m;
	int nr_nodes = nodes_weight(node_states[N_HIGH_MEMORY]);

	while (nr_nodes) {
		void *addr;

		addr = __alloc_bootmem_node_nopanic(
				NODE_DATA(hstate_next_node_to_alloc(h,
						&node_states[N_HIGH_MEMORY])),
				huge_page_size(h), huge_page_size(h), 0);

		if (addr) {
			/*
			 * Use the beginning of the huge page to store the
			 * huge_bootmem_page struct (until gather_bootmem
			 * puts them into the mem_map).
			 */
			m = addr;
			goto found;
		}
		nr_nodes--;
	}
	return 0;

found:
	BUG_ON((unsigned long)virt_to_phys(m) & (huge_page_size(h) - 1));
	/* Put them into a private list first because mem_map is not up yet */
	list_add(&m->list, &huge_boot_pages);
	m->hstate = h;
	return 1;
}

static void prep_compound_huge_page(struct page *page, int order)
{
	if (unlikely(order > (MAX_ORDER - 1)))
		prep_compound_gigantic_page(page, order);
	else
		prep_compound_page(page, order);
}

/* Put bootmem huge pages into the standard lists after mem_map is up */
static void __init gather_bootmem_prealloc(void)
{
	struct huge_bootmem_page *m;

	list_for_each_entry(m, &huge_boot_pages, list) {
		struct hstate *h = m->hstate;
		struct page *page;

#ifdef CONFIG_HIGHMEM
		page = pfn_to_page(m->phys >> PAGE_SHIFT);
		free_bootmem_late((unsigned long)m,
				  sizeof(struct huge_bootmem_page));
#else
		page = virt_to_page(m);
#endif
		__ClearPageReserved(page);
		WARN_ON(page_count(page) != 1);
		prep_compound_huge_page(page, h->order);
		prep_new_huge_page(h, page, page_to_nid(page));
		/*
		 * If we had gigantic hugepages allocated at boot time, we need
		 * to restore the 'stolen' pages to totalram_pages in order to
		 * fix confusing memory reports from free(1) and another
		 * side-effects, like CommitLimit going negative.
		 */
		if (h->order > (MAX_ORDER - 1))
			totalram_pages += 1 << h->order;
	}
}

static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
{
	unsigned long i;

	for (i = 0; i < h->max_huge_pages; ++i) {
		if (h->order >= MAX_ORDER) {
			if (!alloc_bootmem_huge_page(h))
				break;
		} else if (!alloc_fresh_huge_page(h,
					 &node_states[N_HIGH_MEMORY]))
			break;
	}
	h->max_huge_pages = i;
}

static void __init hugetlb_init_hstates(void)
{
	struct hstate *h;

	for_each_hstate(h) {
		/* oversize hugepages were init'ed in early boot */
		if (h->order < MAX_ORDER)
			hugetlb_hstate_alloc_pages(h);
	}
}

static char * __init memfmt(char *buf, unsigned long n)
{
	if (n >= (1UL << 30))
		sprintf(buf, "%lu GB", n >> 30);
	else if (n >= (1UL << 20))
		sprintf(buf, "%lu MB", n >> 20);
	else
		sprintf(buf, "%lu KB", n >> 10);
	return buf;
}

static void __init report_hugepages(void)
{
	struct hstate *h;

	for_each_hstate(h) {
		char buf[32];
		printk(KERN_INFO "HugeTLB registered %s page size, "
				 "pre-allocated %ld pages\n",
			memfmt(buf, huge_page_size(h)),
			h->free_huge_pages);
	}
}

#ifdef CONFIG_HIGHMEM
static void try_to_free_low(struct hstate *h, unsigned long count,
						nodemask_t *nodes_allowed)
{
	int i;

	if (h->order >= MAX_ORDER)
		return;

	for_each_node_mask(i, *nodes_allowed) {
		struct page *page, *next;
		struct list_head *freel = &h->hugepage_freelists[i];
		list_for_each_entry_safe(page, next, freel, lru) {
			if (count >= h->nr_huge_pages)
				return;
			if (PageHighMem(page))
				continue;
			list_del(&page->lru);
			update_and_free_page(h, page);
			h->free_huge_pages--;
			h->free_huge_pages_node[page_to_nid(page)]--;
		}
	}
}
#else
static inline void try_to_free_low(struct hstate *h, unsigned long count,
						nodemask_t *nodes_allowed)
{
}
#endif

/*
 * Increment or decrement surplus_huge_pages.  Keep node-specific counters
 * balanced by operating on them in a round-robin fashion.
 * Returns 1 if an adjustment was made.
 */
static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed,
				int delta)
{
	int start_nid, next_nid;
	int ret = 0;

	VM_BUG_ON(delta != -1 && delta != 1);

	if (delta < 0)
		start_nid = hstate_next_node_to_alloc(h, nodes_allowed);
	else
		start_nid = hstate_next_node_to_free(h, nodes_allowed);
	next_nid = start_nid;

	do {
		int nid = next_nid;
		if (delta < 0)  {
			/*
			 * To shrink on this node, there must be a surplus page
			 */
			if (!h->surplus_huge_pages_node[nid]) {
				next_nid = hstate_next_node_to_alloc(h,
								nodes_allowed);
				continue;
			}
		}
		if (delta > 0) {
			/*
			 * Surplus cannot exceed the total number of pages
			 */
			if (h->surplus_huge_pages_node[nid] >=
						h->nr_huge_pages_node[nid]) {
				next_nid = hstate_next_node_to_free(h,
								nodes_allowed);
				continue;
			}
		}

		h->surplus_huge_pages += delta;
		h->surplus_huge_pages_node[nid] += delta;
		ret = 1;
		break;
	} while (next_nid != start_nid);

	return ret;
}

#define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
						nodemask_t *nodes_allowed)
{
	unsigned long min_count, ret;

	if (h->order >= MAX_ORDER)
		return h->max_huge_pages;

	/*
	 * Increase the pool size
	 * First take pages out of surplus state.  Then make up the
	 * remaining difference by allocating fresh huge pages.
	 *
	 * We might race with alloc_buddy_huge_page() here and be unable
	 * to convert a surplus huge page to a normal huge page. That is
	 * not critical, though, it just means the overall size of the
	 * pool might be one hugepage larger than it needs to be, but
	 * within all the constraints specified by the sysctls.
	 */
	spin_lock(&hugetlb_lock);
	while (h->surplus_huge_pages && count > persistent_huge_pages(h)) {
		if (!adjust_pool_surplus(h, nodes_allowed, -1))
			break;
	}

	while (count > persistent_huge_pages(h)) {
		/*
		 * If this allocation races such that we no longer need the
		 * page, free_huge_page will handle it by freeing the page
		 * and reducing the surplus.
		 */
		spin_unlock(&hugetlb_lock);
		ret = alloc_fresh_huge_page(h, nodes_allowed);
		spin_lock(&hugetlb_lock);
		if (!ret)
			goto out;

		/* Bail for signals. Probably ctrl-c from user */
		if (signal_pending(current))
			goto out;
	}

	/*
	 * Decrease the pool size
	 * First return free pages to the buddy allocator (being careful
	 * to keep enough around to satisfy reservations).  Then place
	 * pages into surplus state as needed so the pool will shrink
	 * to the desired size as pages become free.
	 *
	 * By placing pages into the surplus state independent of the
	 * overcommit value, we are allowing the surplus pool size to
	 * exceed overcommit. There are few sane options here. Since
	 * alloc_buddy_huge_page() is checking the global counter,
	 * though, we'll note that we're not allowed to exceed surplus
	 * and won't grow the pool anywhere else. Not until one of the
	 * sysctls are changed, or the surplus pages go out of use.
	 */
	min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages;
	min_count = max(count, min_count);
	try_to_free_low(h, min_count, nodes_allowed);
	while (min_count < persistent_huge_pages(h)) {
		if (!free_pool_huge_page(h, nodes_allowed, 0))
			break;
	}
	while (count < persistent_huge_pages(h)) {
		if (!adjust_pool_surplus(h, nodes_allowed, 1))
			break;
	}
out:
	ret = persistent_huge_pages(h);
	spin_unlock(&hugetlb_lock);
	return ret;
}

#define HSTATE_ATTR_RO(_name) \
	static struct kobj_attribute _name##_attr = __ATTR_RO(_name)

#define HSTATE_ATTR(_name) \
	static struct kobj_attribute _name##_attr = \
		__ATTR(_name, 0644, _name##_show, _name##_store)

static struct kobject *hugepages_kobj;
static struct kobject *hstate_kobjs[HUGE_MAX_HSTATE];

static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp);

static struct hstate *kobj_to_hstate(struct kobject *kobj, int *nidp)
{
	int i;

	for (i = 0; i < HUGE_MAX_HSTATE; i++)
		if (hstate_kobjs[i] == kobj) {
			if (nidp)
				*nidp = NUMA_NO_NODE;
			return &hstates[i];
		}

	return kobj_to_node_hstate(kobj, nidp);
}

static ssize_t nr_hugepages_show_common(struct kobject *kobj,
					struct kobj_attribute *attr, char *buf)
{
	struct hstate *h;
	unsigned long nr_huge_pages;
	int nid;

	h = kobj_to_hstate(kobj, &nid);
	if (nid == NUMA_NO_NODE)
		nr_huge_pages = h->nr_huge_pages;
	else
		nr_huge_pages = h->nr_huge_pages_node[nid];

	return sprintf(buf, "%lu\n", nr_huge_pages);
}

static ssize_t nr_hugepages_store_common(bool obey_mempolicy,
			struct kobject *kobj, struct kobj_attribute *attr,
			const char *buf, size_t len)
{
	int err;
	int nid;
	unsigned long count;
	struct hstate *h;
	NODEMASK_ALLOC(nodemask_t, nodes_allowed, GFP_KERNEL | __GFP_NORETRY);

	err = strict_strtoul(buf, 10, &count);
	if (err)
		goto out;

	h = kobj_to_hstate(kobj, &nid);
	if (h->order >= MAX_ORDER) {
		err = -EINVAL;
		goto out;
	}

	if (nid == NUMA_NO_NODE) {
		/*
		 * global hstate attribute
		 */
		if (!(obey_mempolicy &&
				init_nodemask_of_mempolicy(nodes_allowed))) {
			NODEMASK_FREE(nodes_allowed);
			nodes_allowed = &node_states[N_HIGH_MEMORY];
		}
	} else if (nodes_allowed) {
		/*
		 * per node hstate attribute: adjust count to global,
		 * but restrict alloc/free to the specified node.
		 */
		count += h->nr_huge_pages - h->nr_huge_pages_node[nid];
		init_nodemask_of_node(nodes_allowed, nid);
	} else
		nodes_allowed = &node_states[N_HIGH_MEMORY];

	h->max_huge_pages = set_max_huge_pages(h, count, nodes_allowed);

	if (nodes_allowed != &node_states[N_HIGH_MEMORY])
		NODEMASK_FREE(nodes_allowed);

	return len;
out:
	NODEMASK_FREE(nodes_allowed);
	return err;
}

static ssize_t nr_hugepages_show(struct kobject *kobj,
				       struct kobj_attribute *attr, char *buf)
{
	return nr_hugepages_show_common(kobj, attr, buf);
}

static ssize_t nr_hugepages_store(struct kobject *kobj,
	       struct kobj_attribute *attr, const char *buf, size_t len)
{
	return nr_hugepages_store_common(false, kobj, attr, buf, len);
}
HSTATE_ATTR(nr_hugepages);

#ifdef CONFIG_NUMA

/*
 * hstate attribute for optionally mempolicy-based constraint on persistent
 * huge page alloc/free.
 */
static ssize_t nr_hugepages_mempolicy_show(struct kobject *kobj,
				       struct kobj_attribute *attr, char *buf)
{
	return nr_hugepages_show_common(kobj, attr, buf);
}

static ssize_t nr_hugepages_mempolicy_store(struct kobject *kobj,
	       struct kobj_attribute *attr, const char *buf, size_t len)
{
	return nr_hugepages_store_common(true, kobj, attr, buf, len);
}
HSTATE_ATTR(nr_hugepages_mempolicy);
#endif


static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj,
					struct kobj_attribute *attr, char *buf)
{
	struct hstate *h = kobj_to_hstate(kobj, NULL);
	return sprintf(buf, "%lu\n", h->nr_overcommit_huge_pages);
}

static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj,
		struct kobj_attribute *attr, const char *buf, size_t count)
{
	int err;
	unsigned long input;
	struct hstate *h = kobj_to_hstate(kobj, NULL);

	if (h->order >= MAX_ORDER)
		return -EINVAL;

	err = strict_strtoul(buf, 10, &input);
	if (err)
		return err;

	spin_lock(&hugetlb_lock);
	h->nr_overcommit_huge_pages = input;
	spin_unlock(&hugetlb_lock);

	return count;
}
HSTATE_ATTR(nr_overcommit_hugepages);

static ssize_t free_hugepages_show(struct kobject *kobj,
					struct kobj_attribute *attr, char *buf)
{
	struct hstate *h;
	unsigned long free_huge_pages;
	int nid;

	h = kobj_to_hstate(kobj, &nid);
	if (nid == NUMA_NO_NODE)
		free_huge_pages = h->free_huge_pages;
	else
		free_huge_pages = h->free_huge_pages_node[nid];

	return sprintf(buf, "%lu\n", free_huge_pages);
}
HSTATE_ATTR_RO(free_hugepages);

static ssize_t resv_hugepages_show(struct kobject *kobj,
					struct kobj_attribute *attr, char *buf)
{
	struct hstate *h = kobj_to_hstate(kobj, NULL);
	return sprintf(buf, "%lu\n", h->resv_huge_pages);
}
HSTATE_ATTR_RO(resv_hugepages);

static ssize_t surplus_hugepages_show(struct kobject *kobj,
					struct kobj_attribute *attr, char *buf)
{
	struct hstate *h;
	unsigned long surplus_huge_pages;
	int nid;

	h = kobj_to_hstate(kobj, &nid);
	if (nid == NUMA_NO_NODE)
		surplus_huge_pages = h->surplus_huge_pages;
	else
		surplus_huge_pages = h->surplus_huge_pages_node[nid];

	return sprintf(buf, "%lu\n", surplus_huge_pages);
}
HSTATE_ATTR_RO(surplus_hugepages);

static struct attribute *hstate_attrs[] = {
	&nr_hugepages_attr.attr,
	&nr_overcommit_hugepages_attr.attr,
	&free_hugepages_attr.attr,
	&resv_hugepages_attr.attr,
	&surplus_hugepages_attr.attr,
#ifdef CONFIG_NUMA
	&nr_hugepages_mempolicy_attr.attr,
#endif
	NULL,
};

static struct attribute_group hstate_attr_group = {
	.attrs = hstate_attrs,
};

static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent,
				    struct kobject **hstate_kobjs,
				    struct attribute_group *hstate_attr_group)
{
	int retval;
	int hi = h - hstates;

	hstate_kobjs[hi] = kobject_create_and_add(h->name, parent);
	if (!hstate_kobjs[hi])
		return -ENOMEM;

	retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group);
	if (retval)
		kobject_put(hstate_kobjs[hi]);

	return retval;
}

static void __init hugetlb_sysfs_init(void)
{
	struct hstate *h;
	int err;

	hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj);
	if (!hugepages_kobj)
		return;

	for_each_hstate(h) {
		err = hugetlb_sysfs_add_hstate(h, hugepages_kobj,
					 hstate_kobjs, &hstate_attr_group);
		if (err)
			printk(KERN_ERR "Hugetlb: Unable to add hstate %s",
								h->name);
	}
}

#ifdef CONFIG_NUMA

/*
 * node_hstate/s - associate per node hstate attributes, via their kobjects,
 * with node devices in node_devices[] using a parallel array.  The array
 * index of a node device or _hstate == node id.
 * This is here to avoid any static dependency of the node device driver, in
 * the base kernel, on the hugetlb module.
 */
struct node_hstate {
	struct kobject		*hugepages_kobj;
	struct kobject		*hstate_kobjs[HUGE_MAX_HSTATE];
};
struct node_hstate node_hstates[MAX_NUMNODES];

/*
 * A subset of global hstate attributes for node devices
 */
static struct attribute *per_node_hstate_attrs[] = {
	&nr_hugepages_attr.attr,
	&free_hugepages_attr.attr,
	&surplus_hugepages_attr.attr,
	NULL,
};

static struct attribute_group per_node_hstate_attr_group = {
	.attrs = per_node_hstate_attrs,
};

/*
 * kobj_to_node_hstate - lookup global hstate for node device hstate attr kobj.
 * Returns node id via non-NULL nidp.
 */
static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp)
{
	int nid;

	for (nid = 0; nid < nr_node_ids; nid++) {
		struct node_hstate *nhs = &node_hstates[nid];
		int i;
		for (i = 0; i < HUGE_MAX_HSTATE; i++)
			if (nhs->hstate_kobjs[i] == kobj) {
				if (nidp)
					*nidp = nid;
				return &hstates[i];
			}
	}

	BUG();
	return NULL;
}

/*
 * Unregister hstate attributes from a single node device.
 * No-op if no hstate attributes attached.
 */
void hugetlb_unregister_node(struct node *node)
{
	struct hstate *h;
	struct node_hstate *nhs = &node_hstates[node->dev.id];

	if (!nhs->hugepages_kobj)
		return;		/* no hstate attributes */

	for_each_hstate(h)
		if (nhs->hstate_kobjs[h - hstates]) {
			kobject_put(nhs->hstate_kobjs[h - hstates]);
			nhs->hstate_kobjs[h - hstates] = NULL;
		}

	kobject_put(nhs->hugepages_kobj);
	nhs->hugepages_kobj = NULL;
}

/*
 * hugetlb module exit:  unregister hstate attributes from node devices
 * that have them.
 */
static void hugetlb_unregister_all_nodes(void)
{
	int nid;

	/*
	 * disable node device registrations.
	 */
	register_hugetlbfs_with_node(NULL, NULL);

	/*
	 * remove hstate attributes from any nodes that have them.
	 */
	for (nid = 0; nid < nr_node_ids; nid++)
		hugetlb_unregister_node(&node_devices[nid]);
}

/*
 * Register hstate attributes for a single node device.
 * No-op if attributes already registered.
 */
void hugetlb_register_node(struct node *node)
{
	struct hstate *h;
	struct node_hstate *nhs = &node_hstates[node->dev.id];
	int err;

	if (nhs->hugepages_kobj)
		return;		/* already allocated */

	nhs->hugepages_kobj = kobject_create_and_add("hugepages",
							&node->dev.kobj);
	if (!nhs->hugepages_kobj)
		return;

	for_each_hstate(h) {
		err = hugetlb_sysfs_add_hstate(h, nhs->hugepages_kobj,
						nhs->hstate_kobjs,
						&per_node_hstate_attr_group);
		if (err) {
			printk(KERN_ERR "Hugetlb: Unable to add hstate %s"
					" for node %d\n",
						h->name, node->dev.id);
			hugetlb_unregister_node(node);
			break;
		}
	}
}

/*
 * hugetlb init time:  register hstate attributes for all registered node
 * devices of nodes that have memory.  All on-line nodes should have
 * registered their associated device by this time.
 */
static void hugetlb_register_all_nodes(void)
{
	int nid;

	for_each_node_state(nid, N_HIGH_MEMORY) {
		struct node *node = &node_devices[nid];
		if (node->dev.id == nid)
			hugetlb_register_node(node);
	}

	/*
	 * Let the node device driver know we're here so it can
	 * [un]register hstate attributes on node hotplug.
	 */
	register_hugetlbfs_with_node(hugetlb_register_node,
				     hugetlb_unregister_node);
}
#else	/* !CONFIG_NUMA */

static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp)
{
	BUG();
	if (nidp)
		*nidp = -1;
	return NULL;
}

static void hugetlb_unregister_all_nodes(void) { }

static void hugetlb_register_all_nodes(void) { }

#endif

static void __exit hugetlb_exit(void)
{
	struct hstate *h;

	hugetlb_unregister_all_nodes();

	for_each_hstate(h) {
		kobject_put(hstate_kobjs[h - hstates]);
	}

	kobject_put(hugepages_kobj);
}
module_exit(hugetlb_exit);

static int __init hugetlb_init(void)
{
	/* Some platform decide whether they support huge pages at boot
	 * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when
	 * there is no such support
	 */
	if (HPAGE_SHIFT == 0)
		return 0;

	if (!size_to_hstate(default_hstate_size)) {
		default_hstate_size = HPAGE_SIZE;
		if (!size_to_hstate(default_hstate_size))
			hugetlb_add_hstate(HUGETLB_PAGE_ORDER);
	}
	default_hstate_idx = size_to_hstate(default_hstate_size) - hstates;
	if (default_hstate_max_huge_pages)
		default_hstate.max_huge_pages = default_hstate_max_huge_pages;

	hugetlb_init_hstates();

	gather_bootmem_prealloc();

	report_hugepages();

	hugetlb_sysfs_init();

	hugetlb_register_all_nodes();

	return 0;
}
module_init(hugetlb_init);

/* Should be called on processing a hugepagesz=... option */
void __init hugetlb_add_hstate(unsigned order)
{
	struct hstate *h;
	unsigned long i;

	if (size_to_hstate(PAGE_SIZE << order)) {
		printk(KERN_WARNING "hugepagesz= specified twice, ignoring\n");
		return;
	}
	BUG_ON(max_hstate >= HUGE_MAX_HSTATE);
	BUG_ON(order == 0);
	h = &hstates[max_hstate++];
	h->order = order;
	h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1);
	h->nr_huge_pages = 0;
	h->free_huge_pages = 0;
	for (i = 0; i < MAX_NUMNODES; ++i)
		INIT_LIST_HEAD(&h->hugepage_freelists[i]);
	h->next_nid_to_alloc = first_node(node_states[N_HIGH_MEMORY]);
	h->next_nid_to_free = first_node(node_states[N_HIGH_MEMORY]);
	snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",
					huge_page_size(h)/1024);

	parsed_hstate = h;
}

static int __init hugetlb_nrpages_setup(char *s)
{
	unsigned long *mhp;
	static unsigned long *last_mhp;

	/*
	 * !max_hstate means we haven't parsed a hugepagesz= parameter yet,
	 * so this hugepages= parameter goes to the "default hstate".
	 */
	if (!max_hstate)
		mhp = &default_hstate_max_huge_pages;
	else
		mhp = &parsed_hstate->max_huge_pages;

	if (mhp == last_mhp) {
		printk(KERN_WARNING "hugepages= specified twice without "
			"interleaving hugepagesz=, ignoring\n");
		return 1;
	}

	if (sscanf(s, "%lu", mhp) <= 0)
		*mhp = 0;

	/*
	 * Global state is always initialized later in hugetlb_init.
	 * But we need to allocate >= MAX_ORDER hstates here early to still
	 * use the bootmem allocator.
	 */
	if (max_hstate && parsed_hstate->order >= MAX_ORDER)
		hugetlb_hstate_alloc_pages(parsed_hstate);

	last_mhp = mhp;

	return 1;
}
__setup("hugepages=", hugetlb_nrpages_setup);

static int __init hugetlb_default_setup(char *s)
{
	default_hstate_size = memparse(s, &s);
	return 1;
}
__setup("default_hugepagesz=", hugetlb_default_setup);

static unsigned int cpuset_mems_nr(unsigned int *array)
{
	int node;
	unsigned int nr = 0;

	for_each_node_mask(node, cpuset_current_mems_allowed)
		nr += array[node];

	return nr;
}

#ifdef CONFIG_SYSCTL
static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
			 struct ctl_table *table, int write,
			 void __user *buffer, size_t *length, loff_t *ppos)
{
	struct hstate *h = &default_hstate;
	unsigned long tmp;
	int ret;

	tmp = h->max_huge_pages;

	if (write && h->order >= MAX_ORDER)
		return -EINVAL;

	table->data = &tmp;
	table->maxlen = sizeof(unsigned long);
	ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
	if (ret)
		goto out;

	if (write) {
		NODEMASK_ALLOC(nodemask_t, nodes_allowed,
						GFP_KERNEL | __GFP_NORETRY);
		if (!(obey_mempolicy &&
			       init_nodemask_of_mempolicy(nodes_allowed))) {
			NODEMASK_FREE(nodes_allowed);
			nodes_allowed = &node_states[N_HIGH_MEMORY];
		}
		h->max_huge_pages = set_max_huge_pages(h, tmp, nodes_allowed);

		if (nodes_allowed != &node_states[N_HIGH_MEMORY])
			NODEMASK_FREE(nodes_allowed);
	}
out:
	return ret;
}

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

	return hugetlb_sysctl_handler_common(false, table, write,
							buffer, length, ppos);
}

#ifdef CONFIG_NUMA
int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write,
			  void __user *buffer, size_t *length, loff_t *ppos)
{
	return hugetlb_sysctl_handler_common(true, table, write,
							buffer, length, ppos);
}
#endif /* CONFIG_NUMA */

int hugetlb_treat_movable_handler(struct ctl_table *table, int write,
			void __user *buffer,
			size_t *length, loff_t *ppos)
{
	proc_dointvec(table, write, buffer, length, ppos);
	if (hugepages_treat_as_movable)
		htlb_alloc_mask = GFP_HIGHUSER_MOVABLE;
	else
		htlb_alloc_mask = GFP_HIGHUSER;
	return 0;
}

int hugetlb_overcommit_handler(struct ctl_table *table, int write,
			void __user *buffer,
			size_t *length, loff_t *ppos)
{
	struct hstate *h = &default_hstate;
	unsigned long tmp;
	int ret;

	tmp = h->nr_overcommit_huge_pages;

	if (write && h->order >= MAX_ORDER)
		return -EINVAL;

	table->data = &tmp;
	table->maxlen = sizeof(unsigned long);
	ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
	if (ret)
		goto out;

	if (write) {
		spin_lock(&hugetlb_lock);
		h->nr_overcommit_huge_pages = tmp;
		spin_unlock(&hugetlb_lock);
	}
out:
	return ret;
}

#endif /* CONFIG_SYSCTL */

void hugetlb_report_meminfo(struct seq_file *m)
{
	struct hstate *h = &default_hstate;
	seq_printf(m,
			"HugePages_Total:   %5lu\n"
			"HugePages_Free:    %5lu\n"
			"HugePages_Rsvd:    %5lu\n"
			"HugePages_Surp:    %5lu\n"
			"Hugepagesize:   %8lu kB\n",
			h->nr_huge_pages,
			h->free_huge_pages,
			h->resv_huge_pages,
			h->surplus_huge_pages,
			1UL << (huge_page_order(h) + PAGE_SHIFT - 10));
}

int hugetlb_report_node_meminfo(int nid, char *buf)
{
	struct hstate *h = &default_hstate;
	return sprintf(buf,
		"Node %d HugePages_Total: %5u\n"
		"Node %d HugePages_Free:  %5u\n"
		"Node %d HugePages_Surp:  %5u\n",
		nid, h->nr_huge_pages_node[nid],
		nid, h->free_huge_pages_node[nid],
		nid, h->surplus_huge_pages_node[nid]);
}

/* Return the number pages of memory we physically have, in PAGE_SIZE units. */
unsigned long hugetlb_total_pages(void)
{
	struct hstate *h;
	unsigned long nr_total_pages = 0;

	for_each_hstate(h)
		nr_total_pages += h->nr_huge_pages * pages_per_huge_page(h);
	return nr_total_pages;
}

static int hugetlb_acct_memory(struct hstate *h, long delta)
{
	int ret = -ENOMEM;

	spin_lock(&hugetlb_lock);
	/*
	 * When cpuset is configured, it breaks the strict hugetlb page
	 * reservation as the accounting is done on a global variable. Such
	 * reservation is completely rubbish in the presence of cpuset because
	 * the reservation is not checked against page availability for the
	 * current cpuset. Application can still potentially OOM'ed by kernel
	 * with lack of free htlb page in cpuset that the task is in.
	 * Attempt to enforce strict accounting with cpuset is almost
	 * impossible (or too ugly) because cpuset is too fluid that
	 * task or memory node can be dynamically moved between cpusets.
	 *
	 * The change of semantics for shared hugetlb mapping with cpuset is
	 * undesirable. However, in order to preserve some of the semantics,
	 * we fall back to check against current free page availability as
	 * a best attempt and hopefully to minimize the impact of changing
	 * semantics that cpuset has.
	 */
	if (delta > 0) {
		if (gather_surplus_pages(h, delta) < 0)
			goto out;

		if (delta > cpuset_mems_nr(h->free_huge_pages_node)) {
			return_unused_surplus_pages(h, delta);
			goto out;
		}
	}

	ret = 0;
	if (delta < 0)
		return_unused_surplus_pages(h, (unsigned long) -delta);

out:
	spin_unlock(&hugetlb_lock);
	return ret;
}

static void hugetlb_vm_op_open(struct vm_area_struct *vma)
{
	struct resv_map *reservations = vma_resv_map(vma);

	/*
	 * This new VMA should share its siblings reservation map if present.
	 * The VMA will only ever have a valid reservation map pointer where
	 * it is being copied for another still existing VMA.  As that VMA
	 * has a reference to the reservation map it cannot disappear until
	 * after this open call completes.  It is therefore safe to take a
	 * new reference here without additional locking.
	 */
	if (reservations)
		kref_get(&reservations->refs);
}

static void resv_map_put(struct vm_area_struct *vma)
{
	struct resv_map *reservations = vma_resv_map(vma);

	if (!reservations)
		return;
	kref_put(&reservations->refs, resv_map_release);
}

static void hugetlb_vm_op_close(struct vm_area_struct *vma)
{
	struct hstate *h = hstate_vma(vma);
	struct resv_map *reservations = vma_resv_map(vma);
	struct hugepage_subpool *spool = subpool_vma(vma);
	unsigned long reserve;
	unsigned long start;
	unsigned long end;

	if (reservations) {
		start = vma_hugecache_offset(h, vma, vma->vm_start);
		end = vma_hugecache_offset(h, vma, vma->vm_end);

		reserve = (end - start) -
			region_count(&reservations->regions, start, end);

		resv_map_put(vma);

		if (reserve) {
			hugetlb_acct_memory(h, -reserve);
			hugepage_subpool_put_pages(spool, reserve);
		}
	}
}

/*
 * We cannot handle pagefaults against hugetlb pages at all.  They cause
 * handle_mm_fault() to try to instantiate regular-sized pages in the
 * hugegpage VMA.  do_page_fault() is supposed to trap this, so BUG is we get
 * this far.
 */
static int hugetlb_vm_op_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	BUG();
	return 0;
}

const struct vm_operations_struct hugetlb_vm_ops = {
	.fault = hugetlb_vm_op_fault,
	.open = hugetlb_vm_op_open,
	.close = hugetlb_vm_op_close,
};

static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
				int writable)
{
	pte_t entry;

	if (writable) {
		entry =
		    pte_mkwrite(pte_mkdirty(mk_pte(page, vma->vm_page_prot)));
	} else {
		entry = huge_pte_wrprotect(mk_pte(page, vma->vm_page_prot));
	}
	entry = pte_mkyoung(entry);
	entry = pte_mkhuge(entry);

	return entry;
}

static void set_huge_ptep_writable(struct vm_area_struct *vma,
				   unsigned long address, pte_t *ptep)
{
	pte_t entry;

	entry = pte_mkwrite(pte_mkdirty(huge_ptep_get(ptep)));
	if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1))
		update_mmu_cache(vma, address, ptep);
}


int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
			    struct vm_area_struct *vma)
{
	pte_t *src_pte, *dst_pte, entry;
	struct page *ptepage;
	unsigned long addr;
	int cow;
	struct hstate *h = hstate_vma(vma);
	unsigned long sz = huge_page_size(h);

	cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;

	for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
		src_pte = huge_pte_offset(src, addr);
		if (!src_pte)
			continue;
		dst_pte = huge_pte_alloc(dst, addr, sz);
		if (!dst_pte)
			goto nomem;

		/* If the pagetables are shared don't copy or take references */
		if (dst_pte == src_pte)
			continue;

		spin_lock(&dst->page_table_lock);
		spin_lock_nested(&src->page_table_lock, SINGLE_DEPTH_NESTING);
		if (!huge_pte_none(huge_ptep_get(src_pte))) {
			if (cow)
				huge_ptep_set_wrprotect(src, addr, src_pte);
			entry = huge_ptep_get(src_pte);
			ptepage = pte_page(entry);
			get_page(ptepage);
			page_dup_rmap(ptepage);
			set_huge_pte_at(dst, addr, dst_pte, entry);
		}
		spin_unlock(&src->page_table_lock);
		spin_unlock(&dst->page_table_lock);
	}
	return 0;

nomem:
	return -ENOMEM;
}

static int is_hugetlb_entry_migration(pte_t pte)
{
	swp_entry_t swp;

	if (huge_pte_none(pte) || pte_present(pte))
		return 0;
	swp = pte_to_swp_entry(pte);
	if (non_swap_entry(swp) && is_migration_entry(swp))
		return 1;
	else
		return 0;
}

static int is_hugetlb_entry_hwpoisoned(pte_t pte)
{
	swp_entry_t swp;

	if (huge_pte_none(pte) || pte_present(pte))
		return 0;
	swp = pte_to_swp_entry(pte);
	if (non_swap_entry(swp) && is_hwpoison_entry(swp))
		return 1;
	else
		return 0;
}

void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
			    unsigned long end, struct page *ref_page)
{
	struct mm_struct *mm = vma->vm_mm;
	unsigned long address;
	pte_t *ptep;
	pte_t pte;
	struct page *page;
	struct page *tmp;
	struct hstate *h = hstate_vma(vma);
	unsigned long sz = huge_page_size(h);

	/*
	 * A page gathering list, protected by per file i_mmap_mutex. The
	 * lock is used to avoid list corruption from multiple unmapping
	 * of the same page since we are using page->lru.
	 */
	LIST_HEAD(page_list);

	WARN_ON(!is_vm_hugetlb_page(vma));
	BUG_ON(start & ~huge_page_mask(h));
	BUG_ON(end & ~huge_page_mask(h));

	mmu_notifier_invalidate_range_start(mm, start, end);
	spin_lock(&mm->page_table_lock);
	for (address = start; address < end; address += sz) {
		ptep = huge_pte_offset(mm, address);
		if (!ptep)
			continue;

		if (huge_pmd_unshare(mm, &address, ptep))
			continue;

		pte = huge_ptep_get(ptep);
		if (huge_pte_none(pte))
			continue;

		/*
		 * HWPoisoned hugepage is already unmapped and dropped reference
		 */
		if (unlikely(is_hugetlb_entry_hwpoisoned(pte)))
			continue;

		page = pte_page(pte);
		/*
		 * If a reference page is supplied, it is because a specific
		 * page is being unmapped, not a range. Ensure the page we
		 * are about to unmap is the actual page of interest.
		 */
		if (ref_page) {
			if (page != ref_page)
				continue;

			/*
			 * Mark the VMA as having unmapped its page so that
			 * future faults in this VMA will fail rather than
			 * looking like data was lost
			 */
			set_vma_resv_flags(vma, HPAGE_RESV_UNMAPPED);
		}

		pte = huge_ptep_get_and_clear(mm, address, ptep);
		if (pte_dirty(pte))
			set_page_dirty(page);
		list_add(&page->lru, &page_list);

		/* Bail out after unmapping reference page if supplied */
		if (ref_page)
			break;
	}
	flush_tlb_range(vma, start, end);
	spin_unlock(&mm->page_table_lock);
	mmu_notifier_invalidate_range_end(mm, start, end);
	list_for_each_entry_safe(page, tmp, &page_list, lru) {
		page_remove_rmap(page);
		list_del(&page->lru);
		put_page(page);
	}
}

void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
			  unsigned long end, struct page *ref_page)
{
	mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
	__unmap_hugepage_range(vma, start, end, ref_page);
	/*
	 * Clear this flag so that x86's huge_pmd_share page_table_shareable
	 * test will fail on a vma being torn down, and not grab a page table
	 * on its way out.  We're lucky that the flag has such an appropriate
	 * name, and can in fact be safely cleared here. We could clear it
	 * before the __unmap_hugepage_range above, but all that's necessary
	 * is to clear it before releasing the i_mmap_mutex below.
	 *
	 * This works because in the contexts this is called, the VMA is
	 * going to be destroyed. It is not vunerable to madvise(DONTNEED)
	 * because madvise is not supported on hugetlbfs. The same applies
	 * for direct IO. unmap_hugepage_range() is only being called just
	 * before free_pgtables() so clearing VM_MAYSHARE will not cause
	 * surprises later.
	 */
	vma->vm_flags &= ~VM_MAYSHARE;
	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
}

/*
 * This is called when the original mapper is failing to COW a MAP_PRIVATE
 * mappping it owns the reserve page for. The intention is to unmap the page
 * from other VMAs and let the children be SIGKILLed if they are faulting the
 * same region.
 */
static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
				struct page *page, unsigned long address)
{
	struct hstate *h = hstate_vma(vma);
	struct vm_area_struct *iter_vma;
	struct address_space *mapping;
	struct prio_tree_iter iter;
	pgoff_t pgoff;

	/*
	 * vm_pgoff is in PAGE_SIZE units, hence the different calculation
	 * from page cache lookup which is in HPAGE_SIZE units.
	 */
	address = address & huge_page_mask(h);
	pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) +
			vma->vm_pgoff;
	mapping = vma->vm_file->f_dentry->d_inode->i_mapping;

	/*
	 * Take the mapping lock for the duration of the table walk. As
	 * this mapping should be shared between all the VMAs,
	 * __unmap_hugepage_range() is called as the lock is already held
	 */
	mutex_lock(&mapping->i_mmap_mutex);
	vma_prio_tree_foreach(iter_vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
		/* Do not unmap the current VMA */
		if (iter_vma == vma)
			continue;

		/*
		 * Unmap the page from other VMAs without their own reserves.
		 * They get marked to be SIGKILLed if they fault in these
		 * areas. This is because a future no-page fault on this VMA
		 * could insert a zeroed page instead of the data existing
		 * from the time of fork. This would look like data corruption
		 */
		if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER))
			__unmap_hugepage_range(iter_vma,
				address, address + huge_page_size(h),
				page);
	}
	mutex_unlock(&mapping->i_mmap_mutex);

	return 1;
}

/*
 * Hugetlb_cow() should be called with page lock of the original hugepage held.
 * Called with hugetlb_instantiation_mutex held and pte_page locked so we
 * cannot race with other handlers or page migration.
 * Keep the pte_same checks anyway to make transition from the mutex easier.
 */
static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
			unsigned long address, pte_t *ptep, pte_t pte,
			struct page *pagecache_page)
{
	struct hstate *h = hstate_vma(vma);
	struct page *old_page, *new_page;
	int avoidcopy;
	int outside_reserve = 0;

	old_page = pte_page(pte);

retry_avoidcopy:
	/* If no-one else is actually using this page, avoid the copy
	 * and just make the page writable */
	avoidcopy = (page_mapcount(old_page) == 1);
	if (avoidcopy) {
		if (PageAnon(old_page))
			page_move_anon_rmap(old_page, vma, address);
		set_huge_ptep_writable(vma, address, ptep);
		return 0;
	}

	/*
	 * If the process that created a MAP_PRIVATE mapping is about to
	 * perform a COW due to a shared page count, attempt to satisfy
	 * the allocation without using the existing reserves. The pagecache
	 * page is used to determine if the reserve at this address was
	 * consumed or not. If reserves were used, a partial faulted mapping
	 * at the time of fork() could consume its reserves on COW instead
	 * of the full address range.
	 */
	if (!(vma->vm_flags & VM_MAYSHARE) &&
			is_vma_resv_set(vma, HPAGE_RESV_OWNER) &&
			old_page != pagecache_page)
		outside_reserve = 1;

	page_cache_get(old_page);

	/* Drop page_table_lock as buddy allocator may be called */
	spin_unlock(&mm->page_table_lock);
	new_page = alloc_huge_page(vma, address, outside_reserve);

	if (IS_ERR(new_page)) {
		page_cache_release(old_page);

		/*
		 * If a process owning a MAP_PRIVATE mapping fails to COW,
		 * it is due to references held by a child and an insufficient
		 * huge page pool. To guarantee the original mappers
		 * reliability, unmap the page from child processes. The child
		 * may get SIGKILLed if it later faults.
		 */
		if (outside_reserve) {
			BUG_ON(huge_pte_none(pte));
			if (unmap_ref_private(mm, vma, old_page, address)) {
				BUG_ON(huge_pte_none(pte));
				spin_lock(&mm->page_table_lock);
				ptep = huge_pte_offset(mm, address & huge_page_mask(h));
				if (likely(pte_same(huge_ptep_get(ptep), pte)))
					goto retry_avoidcopy;
				/*
				 * race occurs while re-acquiring page_table_lock, and
				 * our job is done.
				 */
				return 0;
			}
			WARN_ON_ONCE(1);
		}

		/* Caller expects lock to be held */
		spin_lock(&mm->page_table_lock);
		return -PTR_ERR(new_page);
	}

	/*
	 * When the original hugepage is shared one, it does not have
	 * anon_vma prepared.
	 */
	if (unlikely(anon_vma_prepare(vma))) {
		page_cache_release(new_page);
		page_cache_release(old_page);
		/* Caller expects lock to be held */
		spin_lock(&mm->page_table_lock);
		return VM_FAULT_OOM;
	}

	copy_user_huge_page(new_page, old_page, address, vma,
			    pages_per_huge_page(h));
	__SetPageUptodate(new_page);

	/*
	 * Retake the page_table_lock to check for racing updates
	 * before the page tables are altered
	 */
	spin_lock(&mm->page_table_lock);
	ptep = huge_pte_offset(mm, address & huge_page_mask(h));
	if (likely(pte_same(huge_ptep_get(ptep), pte))) {
		/* Break COW */
		mmu_notifier_invalidate_range_start(mm,
			address & huge_page_mask(h),
			(address & huge_page_mask(h)) + huge_page_size(h));
		huge_ptep_clear_flush(vma, address, ptep);
		set_huge_pte_at(mm, address, ptep,
				make_huge_pte(vma, new_page, 1));
		page_remove_rmap(old_page);
		hugepage_add_new_anon_rmap(new_page, vma, address);
		/* Make the old page be freed below */
		new_page = old_page;
		mmu_notifier_invalidate_range_end(mm,
			address & huge_page_mask(h),
			(address & huge_page_mask(h)) + huge_page_size(h));
	}
	page_cache_release(new_page);
	page_cache_release(old_page);
	return 0;
}

/* Return the pagecache page at a given address within a VMA */
static struct page *hugetlbfs_pagecache_page(struct hstate *h,
			struct vm_area_struct *vma, unsigned long address)
{
	struct address_space *mapping;
	pgoff_t idx;

	mapping = vma->vm_file->f_mapping;
	idx = vma_hugecache_offset(h, vma, address);

	return find_lock_page(mapping, idx);
}

/*
 * Return whether there is a pagecache page to back given address within VMA.
 * Caller follow_hugetlb_page() holds page_table_lock so we cannot lock_page.
 */
static bool hugetlbfs_pagecache_present(struct hstate *h,
			struct vm_area_struct *vma, unsigned long address)
{
	struct address_space *mapping;
	pgoff_t idx;
	struct page *page;

	mapping = vma->vm_file->f_mapping;
	idx = vma_hugecache_offset(h, vma, address);

	page = find_get_page(mapping, idx);
	if (page)
		put_page(page);
	return page != NULL;
}

static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
			unsigned long address, pte_t *ptep, unsigned int flags)
{
	struct hstate *h = hstate_vma(vma);
	int ret = VM_FAULT_SIGBUS;
	int anon_rmap = 0;
	pgoff_t idx;
	unsigned long size;
	struct page *page;
	struct address_space *mapping;
	pte_t new_pte;

	/*
	 * Currently, we are forced to kill the process in the event the
	 * original mapper has unmapped pages from the child due to a failed
	 * COW. Warn that such a situation has occurred as it may not be obvious
	 */
	if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) {
		printk(KERN_WARNING
			"PID %d killed due to inadequate hugepage pool\n",
			current->pid);
		return ret;
	}

	mapping = vma->vm_file->f_mapping;
	idx = vma_hugecache_offset(h, vma, address);

	/*
	 * Use page lock to guard against racing truncation
	 * before we get page_table_lock.
	 */
retry:
	page = find_lock_page(mapping, idx);
	if (!page) {
		size = i_size_read(mapping->host) >> huge_page_shift(h);
		if (idx >= size)
			goto out;
		page = alloc_huge_page(vma, address, 0);
		if (IS_ERR(page)) {
			ret = -PTR_ERR(page);
			goto out;
		}
		clear_huge_page(page, address, pages_per_huge_page(h));
		__SetPageUptodate(page);

		if (vma->vm_flags & VM_MAYSHARE) {
			int err;
			struct inode *inode = mapping->host;

			err = add_to_page_cache(page, mapping, idx, GFP_KERNEL);
			if (err) {
				put_page(page);
				if (err == -EEXIST)
					goto retry;
				goto out;
			}

			spin_lock(&inode->i_lock);
			inode->i_blocks += blocks_per_huge_page(h);
			spin_unlock(&inode->i_lock);
		} else {
			lock_page(page);
			if (unlikely(anon_vma_prepare(vma))) {
				ret = VM_FAULT_OOM;
				goto backout_unlocked;
			}
			anon_rmap = 1;
		}
	} else {
		/*
		 * If memory error occurs between mmap() and fault, some process
		 * don't have hwpoisoned swap entry for errored virtual address.
		 * So we need to block hugepage fault by PG_hwpoison bit check.
		 */
		if (unlikely(PageHWPoison(page))) {
			ret = VM_FAULT_HWPOISON |
			      VM_FAULT_SET_HINDEX(h - hstates);
			goto backout_unlocked;
		}
	}

	/*
	 * If we are going to COW a private mapping later, we examine the
	 * pending reservations for this page now. This will ensure that
	 * any allocations necessary to record that reservation occur outside
	 * the spinlock.
	 */
	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED))
		if (vma_needs_reservation(h, vma, address) < 0) {
			ret = VM_FAULT_OOM;
			goto backout_unlocked;
		}

	spin_lock(&mm->page_table_lock);
	size = i_size_read(mapping->host) >> huge_page_shift(h);
	if (idx >= size)
		goto backout;

	ret = 0;
	if (!huge_pte_none(huge_ptep_get(ptep)))
		goto backout;

	if (anon_rmap)
		hugepage_add_new_anon_rmap(page, vma, address);
	else
		page_dup_rmap(page);
	new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE)
				&& (vma->vm_flags & VM_SHARED)));
	set_huge_pte_at(mm, address, ptep, new_pte);

	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
		/* Optimization, do the COW without a second fault */
		ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page);
	}

	spin_unlock(&mm->page_table_lock);
	unlock_page(page);
out:
	return ret;

backout:
	spin_unlock(&mm->page_table_lock);
backout_unlocked:
	unlock_page(page);
	put_page(page);
	goto out;
}

int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
			unsigned long address, unsigned int flags)
{
	pte_t *ptep;
	pte_t entry;
	int ret;
	struct page *page = NULL;
	struct page *pagecache_page = NULL;
	static DEFINE_MUTEX(hugetlb_instantiation_mutex);
	struct hstate *h = hstate_vma(vma);

	address &= huge_page_mask(h);

	ptep = huge_pte_offset(mm, address);
	if (ptep) {
		entry = huge_ptep_get(ptep);
		if (unlikely(is_hugetlb_entry_migration(entry))) {
			migration_entry_wait_huge(mm, ptep);
			return 0;
		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
			return VM_FAULT_HWPOISON_LARGE |
			       VM_FAULT_SET_HINDEX(h - hstates);
	}

	ptep = huge_pte_alloc(mm, address, huge_page_size(h));
	if (!ptep)
		return VM_FAULT_OOM;

	/*
	 * Serialize hugepage allocation and instantiation, so that we don't
	 * get spurious allocation failures if two CPUs race to instantiate
	 * the same page in the page cache.
	 */
	mutex_lock(&hugetlb_instantiation_mutex);
	entry = huge_ptep_get(ptep);
	if (huge_pte_none(entry)) {
		ret = hugetlb_no_page(mm, vma, address, ptep, flags);
		goto out_mutex;
	}

	ret = 0;

	/*
	 * If we are going to COW the mapping later, we examine the pending
	 * reservations for this page now. This will ensure that any
	 * allocations necessary to record that reservation occur outside the
	 * spinlock. For private mappings, we also lookup the pagecache
	 * page now as it is used to determine if a reservation has been
	 * consumed.
	 */
	if ((flags & FAULT_FLAG_WRITE) && !pte_write(entry)) {
		if (vma_needs_reservation(h, vma, address) < 0) {
			ret = VM_FAULT_OOM;
			goto out_mutex;
		}

		if (!(vma->vm_flags & VM_MAYSHARE))
			pagecache_page = hugetlbfs_pagecache_page(h,
								vma, address);
	}

	/*
	 * hugetlb_cow() requires page locks of pte_page(entry) and
	 * pagecache_page, so here we need take the former one
	 * when page != pagecache_page or !pagecache_page.
	 * Note that locking order is always pagecache_page -> page,
	 * so no worry about deadlock.
	 */
	page = pte_page(entry);
	get_page(page);
	if (page != pagecache_page)
		lock_page(page);

	spin_lock(&mm->page_table_lock);
	/* Check for a racing update before calling hugetlb_cow */
	if (unlikely(!pte_same(entry, huge_ptep_get(ptep))))
		goto out_page_table_lock;


	if (flags & FAULT_FLAG_WRITE) {
		if (!pte_write(entry)) {
			ret = hugetlb_cow(mm, vma, address, ptep, entry,
							pagecache_page);
			goto out_page_table_lock;
		}
		entry = pte_mkdirty(entry);
	}
	entry = pte_mkyoung(entry);
	if (huge_ptep_set_access_flags(vma, address, ptep, entry,
						flags & FAULT_FLAG_WRITE))
		update_mmu_cache(vma, address, ptep);

out_page_table_lock:
	spin_unlock(&mm->page_table_lock);

	if (pagecache_page) {
		unlock_page(pagecache_page);
		put_page(pagecache_page);
	}
	if (page != pagecache_page)
		unlock_page(page);
	put_page(page);

out_mutex:
	mutex_unlock(&hugetlb_instantiation_mutex);

	return ret;
}

/* Can be overriden by architectures */
__attribute__((weak)) struct page *
follow_huge_pud(struct mm_struct *mm, unsigned long address,
	       pud_t *pud, int write)
{
	BUG();
	return NULL;
}

int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
			struct page **pages, struct vm_area_struct **vmas,
			unsigned long *position, int *length, int i,
			unsigned int flags)
{
	unsigned long pfn_offset;
	unsigned long vaddr = *position;
	int remainder = *length;
	struct hstate *h = hstate_vma(vma);

	spin_lock(&mm->page_table_lock);
	while (vaddr < vma->vm_end && remainder) {
		pte_t *pte;
		int absent;
		struct page *page;

		/*
		 * Some archs (sparc64, sh*) have multiple pte_ts to
		 * each hugepage.  We have to make sure we get the
		 * first, for the page indexing below to work.
		 */
		pte = huge_pte_offset(mm, vaddr & huge_page_mask(h));
		absent = !pte || huge_pte_none(huge_ptep_get(pte));

		/*
		 * When coredumping, it suits get_dump_page if we just return
		 * an error where there's an empty slot with no huge pagecache
		 * to back it.  This way, we avoid allocating a hugepage, and
		 * the sparse dumpfile avoids allocating disk blocks, but its
		 * huge holes still show up with zeroes where they need to be.
		 */
		if (absent && (flags & FOLL_DUMP) &&
		    !hugetlbfs_pagecache_present(h, vma, vaddr)) {
			remainder = 0;
			break;
		}

		/*
		 * We need call hugetlb_fault for both hugepages under migration
		 * (in which case hugetlb_fault waits for the migration,) and
		 * hwpoisoned hugepages (in which case we need to prevent the
		 * caller from accessing to them.) In order to do this, we use
		 * here is_swap_pte instead of is_hugetlb_entry_migration and
		 * is_hugetlb_entry_hwpoisoned. This is because it simply covers
		 * both cases, and because we can't follow correct pages
		 * directly from any kind of swap entries.
		 */
		if (absent || is_swap_pte(huge_ptep_get(pte)) ||
		    ((flags & FOLL_WRITE) && !pte_write(huge_ptep_get(pte)))) {
			int ret;

			spin_unlock(&mm->page_table_lock);
			ret = hugetlb_fault(mm, vma, vaddr,
				(flags & FOLL_WRITE) ? FAULT_FLAG_WRITE : 0);
			spin_lock(&mm->page_table_lock);
			if (!(ret & VM_FAULT_ERROR))
				continue;

			remainder = 0;
			break;
		}

		pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT;
		page = pte_page(huge_ptep_get(pte));
same_page:
		if (pages) {
			pages[i] = mem_map_offset(page, pfn_offset);
			get_page(pages[i]);
		}

		if (vmas)
			vmas[i] = vma;

		vaddr += PAGE_SIZE;
		++pfn_offset;
		--remainder;
		++i;
		if (vaddr < vma->vm_end && remainder &&
				pfn_offset < pages_per_huge_page(h)) {
			/*
			 * We use pfn_offset to avoid touching the pageframes
			 * of this compound page.
			 */
			goto same_page;
		}
	}
	spin_unlock(&mm->page_table_lock);
	*length = remainder;
	*position = vaddr;

	return i ? i : -EFAULT;
}

void hugetlb_change_protection(struct vm_area_struct *vma,
		unsigned long address, unsigned long end, pgprot_t newprot)
{
	struct mm_struct *mm = vma->vm_mm;
	unsigned long start = address;
	pte_t *ptep;
	pte_t pte;
	struct hstate *h = hstate_vma(vma);

	BUG_ON(address >= end);
	flush_cache_range(vma, address, end);

	mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
	spin_lock(&mm->page_table_lock);
	for (; address < end; address += huge_page_size(h)) {
		ptep = huge_pte_offset(mm, address);
		if (!ptep)
			continue;
		if (huge_pmd_unshare(mm, &address, ptep))
			continue;
		if (!huge_pte_none(huge_ptep_get(ptep))) {
			pte = huge_ptep_get_and_clear(mm, address, ptep);
			pte = pte_mkhuge(pte_modify(pte, newprot));
			set_huge_pte_at(mm, address, ptep, pte);
		}
	}
	spin_unlock(&mm->page_table_lock);
	/*
	 * Must flush TLB before releasing i_mmap_mutex: x86's huge_pmd_unshare
	 * may have cleared our pud entry and done put_page on the page table:
	 * once we release i_mmap_mutex, another task can do the final put_page
	 * and that page table be reused and filled with junk.
	 */
	flush_tlb_range(vma, start, end);
	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
}

int hugetlb_reserve_pages(struct inode *inode,
					long from, long to,
					struct vm_area_struct *vma,
					vm_flags_t vm_flags)
{
	long ret, chg;
	struct hstate *h = hstate_inode(inode);
	struct hugepage_subpool *spool = subpool_inode(inode);

	/*
	 * Only apply hugepage reservation if asked. At fault time, an
	 * attempt will be made for VM_NORESERVE to allocate a page
	 * without using reserves
	 */
	if (vm_flags & VM_NORESERVE)
		return 0;

	/*
	 * Shared mappings base their reservation on the number of pages that
	 * are already allocated on behalf of the file. Private mappings need
	 * to reserve the full area even if read-only as mprotect() may be
	 * called to make the mapping read-write. Assume !vma is a shm mapping
	 */
	if (!vma || vma->vm_flags & VM_MAYSHARE)
		chg = region_chg(&inode->i_mapping->private_list, from, to);
	else {
		struct resv_map *resv_map = resv_map_alloc();
		if (!resv_map)
			return -ENOMEM;

		chg = to - from;

		set_vma_resv_map(vma, resv_map);
		set_vma_resv_flags(vma, HPAGE_RESV_OWNER);
	}

	if (chg < 0) {
		ret = chg;
		goto out_err;
	}

	/* There must be enough pages in the subpool for the mapping */
	if (hugepage_subpool_get_pages(spool, chg)) {
		ret = -ENOSPC;
		goto out_err;
	}

	/*
	 * Check enough hugepages are available for the reservation.
	 * Hand the pages back to the subpool if there are not
	 */
	ret = hugetlb_acct_memory(h, chg);
	if (ret < 0) {
		hugepage_subpool_put_pages(spool, chg);
		goto out_err;
	}

	/*
	 * Account for the reservations made. Shared mappings record regions
	 * that have reservations as they are shared by multiple VMAs.
	 * When the last VMA disappears, the region map says how much
	 * the reservation was and the page cache tells how much of
	 * the reservation was consumed. Private mappings are per-VMA and
	 * only the consumed reservations are tracked. When the VMA
	 * disappears, the original reservation is the VMA size and the
	 * consumed reservations are stored in the map. Hence, nothing
	 * else has to be done for private mappings here
	 */
	if (!vma || vma->vm_flags & VM_MAYSHARE)
		region_add(&inode->i_mapping->private_list, from, to);
	return 0;
out_err:
	if (vma)
		resv_map_put(vma);
	return ret;
}

void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
{
	struct hstate *h = hstate_inode(inode);
	long chg = region_truncate(&inode->i_mapping->private_list, offset);
	struct hugepage_subpool *spool = subpool_inode(inode);

	spin_lock(&inode->i_lock);
	inode->i_blocks -= (blocks_per_huge_page(h) * freed);
	spin_unlock(&inode->i_lock);

	hugepage_subpool_put_pages(spool, (chg - freed));
	hugetlb_acct_memory(h, -(chg - freed));
}

#ifdef CONFIG_MEMORY_FAILURE

/* Should be called in hugetlb_lock */
static int is_hugepage_on_freelist(struct page *hpage)
{
	struct page *page;
	struct page *tmp;
	struct hstate *h = page_hstate(hpage);
	int nid = page_to_nid(hpage);

	list_for_each_entry_safe(page, tmp, &h->hugepage_freelists[nid], lru)
		if (page == hpage)
			return 1;
	return 0;
}

/*
 * This function is called from memory failure code.
 * Assume the caller holds page lock of the head page.
 */
int dequeue_hwpoisoned_huge_page(struct page *hpage)
{
	struct hstate *h = page_hstate(hpage);
	int nid = page_to_nid(hpage);
	int ret = -EBUSY;

	spin_lock(&hugetlb_lock);
	if (is_hugepage_on_freelist(hpage)) {
		list_del(&hpage->lru);
		set_page_refcounted(hpage);
		h->free_huge_pages--;
		h->free_huge_pages_node[nid]--;
		ret = 0;
	}
	spin_unlock(&hugetlb_lock);
	return ret;
}
#endif