summaryrefslogtreecommitdiff
path: root/mm/mempolicy.c
blob: 4cc19f6ab6c6f84da6bb99955f5026a9bc066a76 (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
/*
 * Simple NUMA memory policy for the Linux kernel.
 *
 * Copyright 2003,2004 Andi Kleen, SuSE Labs.
 * (C) Copyright 2005 Christoph Lameter, Silicon Graphics, Inc.
 * Subject to the GNU Public License, version 2.
 *
 * NUMA policy allows the user to give hints in which node(s) memory should
 * be allocated.
 *
 * Support four policies per VMA and per process:
 *
 * The VMA policy has priority over the process policy for a page fault.
 *
 * interleave     Allocate memory interleaved over a set of nodes,
 *                with normal fallback if it fails.
 *                For VMA based allocations this interleaves based on the
 *                offset into the backing object or offset into the mapping
 *                for anonymous memory. For process policy an process counter
 *                is used.
 *
 * bind           Only allocate memory on a specific set of nodes,
 *                no fallback.
 *                FIXME: memory is allocated starting with the first node
 *                to the last. It would be better if bind would truly restrict
 *                the allocation to memory nodes instead
 *
 * preferred       Try a specific node first before normal fallback.
 *                As a special case NUMA_NO_NODE here means do the allocation
 *                on the local CPU. This is normally identical to default,
 *                but useful to set in a VMA when you have a non default
 *                process policy.
 *
 * default        Allocate on the local node first, or when on a VMA
 *                use the process policy. This is what Linux always did
 *		  in a NUMA aware kernel and still does by, ahem, default.
 *
 * The process policy is applied for most non interrupt memory allocations
 * in that process' context. Interrupts ignore the policies and always
 * try to allocate on the local CPU. The VMA policy is only applied for memory
 * allocations for a VMA in the VM.
 *
 * Currently there are a few corner cases in swapping where the policy
 * is not applied, but the majority should be handled. When process policy
 * is used it is not remembered over swap outs/swap ins.
 *
 * Only the highest zone in the zone hierarchy gets policied. Allocations
 * requesting a lower zone just use default policy. This implies that
 * on systems with highmem kernel lowmem allocation don't get policied.
 * Same with GFP_DMA allocations.
 *
 * For shmfs/tmpfs/hugetlbfs shared memory the policy is shared between
 * all users and remembered even when nobody has memory mapped.
 */

/* Notebook:
   fix mmap readahead to honour policy and enable policy for any page cache
   object
   statistics for bigpages
   global policy for page cache? currently it uses process policy. Requires
   first item above.
   handle mremap for shared memory (currently ignored for the policy)
   grows down?
   make bind policy root only? It can trigger oom much faster and the
   kernel is not always grateful with that.
*/

#include <linux/mempolicy.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/hugetlb.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/nodemask.h>
#include <linux/cpuset.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/export.h>
#include <linux/nsproxy.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/compat.h>
#include <linux/swap.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
#include <linux/migrate.h>
#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/ctype.h>
#include <linux/mm_inline.h>
#include <linux/mmu_notifier.h>

#include <asm/tlbflush.h>
#include <asm/uaccess.h>
#include <linux/random.h>

#include "internal.h"

/* Internal flags */
#define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0)	/* Skip checks for continuous vmas */
#define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1)		/* Invert check for nodemask */

static struct kmem_cache *policy_cache;
static struct kmem_cache *sn_cache;

/* Highest zone. An specific allocation for a zone below that is not
   policied. */
enum zone_type policy_zone = 0;

/*
 * run-time system-wide default policy => local allocation
 */
static struct mempolicy default_policy = {
	.refcnt = ATOMIC_INIT(1), /* never free it */
	.mode = MPOL_PREFERRED,
	.flags = MPOL_F_LOCAL,
};

static struct mempolicy preferred_node_policy[MAX_NUMNODES];

static struct mempolicy *get_task_policy(struct task_struct *p)
{
	struct mempolicy *pol = p->mempolicy;

	if (!pol) {
		int node = numa_node_id();

		if (node != NUMA_NO_NODE) {
			pol = &preferred_node_policy[node];
			/*
			 * preferred_node_policy is not initialised early in
			 * boot
			 */
			if (!pol->mode)
				pol = NULL;
		}
	}

	return pol;
}

static const struct mempolicy_operations {
	int (*create)(struct mempolicy *pol, const nodemask_t *nodes);
	/*
	 * If read-side task has no lock to protect task->mempolicy, write-side
	 * task will rebind the task->mempolicy by two step. The first step is
	 * setting all the newly nodes, and the second step is cleaning all the
	 * disallowed nodes. In this way, we can avoid finding no node to alloc
	 * page.
	 * If we have a lock to protect task->mempolicy in read-side, we do
	 * rebind directly.
	 *
	 * step:
	 * 	MPOL_REBIND_ONCE - do rebind work at once
	 * 	MPOL_REBIND_STEP1 - set all the newly nodes
	 * 	MPOL_REBIND_STEP2 - clean all the disallowed nodes
	 */
	void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes,
			enum mpol_rebind_step step);
} mpol_ops[MPOL_MAX];

/* Check that the nodemask contains at least one populated zone */
static int is_valid_nodemask(const nodemask_t *nodemask)
{
	return nodes_intersects(*nodemask, node_states[N_MEMORY]);
}

static inline int mpol_store_user_nodemask(const struct mempolicy *pol)
{
	return pol->flags & MPOL_MODE_FLAGS;
}

static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig,
				   const nodemask_t *rel)
{
	nodemask_t tmp;
	nodes_fold(tmp, *orig, nodes_weight(*rel));
	nodes_onto(*ret, tmp, *rel);
}

static int mpol_new_interleave(struct mempolicy *pol, const nodemask_t *nodes)
{
	if (nodes_empty(*nodes))
		return -EINVAL;
	pol->v.nodes = *nodes;
	return 0;
}

static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes)
{
	if (!nodes)
		pol->flags |= MPOL_F_LOCAL;	/* local allocation */
	else if (nodes_empty(*nodes))
		return -EINVAL;			/*  no allowed nodes */
	else
		pol->v.preferred_node = first_node(*nodes);
	return 0;
}

static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes)
{
	if (!is_valid_nodemask(nodes))
		return -EINVAL;
	pol->v.nodes = *nodes;
	return 0;
}

/*
 * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if
 * any, for the new policy.  mpol_new() has already validated the nodes
 * parameter with respect to the policy mode and flags.  But, we need to
 * handle an empty nodemask with MPOL_PREFERRED here.
 *
 * Must be called holding task's alloc_lock to protect task's mems_allowed
 * and mempolicy.  May also be called holding the mmap_semaphore for write.
 */
static int mpol_set_nodemask(struct mempolicy *pol,
		     const nodemask_t *nodes, struct nodemask_scratch *nsc)
{
	int ret;

	/* if mode is MPOL_DEFAULT, pol is NULL. This is right. */
	if (pol == NULL)
		return 0;
	/* Check N_MEMORY */
	nodes_and(nsc->mask1,
		  cpuset_current_mems_allowed, node_states[N_MEMORY]);

	VM_BUG_ON(!nodes);
	if (pol->mode == MPOL_PREFERRED && nodes_empty(*nodes))
		nodes = NULL;	/* explicit local allocation */
	else {
		if (pol->flags & MPOL_F_RELATIVE_NODES)
			mpol_relative_nodemask(&nsc->mask2, nodes,&nsc->mask1);
		else
			nodes_and(nsc->mask2, *nodes, nsc->mask1);

		if (mpol_store_user_nodemask(pol))
			pol->w.user_nodemask = *nodes;
		else
			pol->w.cpuset_mems_allowed =
						cpuset_current_mems_allowed;
	}

	if (nodes)
		ret = mpol_ops[pol->mode].create(pol, &nsc->mask2);
	else
		ret = mpol_ops[pol->mode].create(pol, NULL);
	return ret;
}

/*
 * This function just creates a new policy, does some check and simple
 * initialization. You must invoke mpol_set_nodemask() to set nodes.
 */
static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
				  nodemask_t *nodes)
{
	struct mempolicy *policy;

	pr_debug("setting mode %d flags %d nodes[0] %lx\n",
		 mode, flags, nodes ? nodes_addr(*nodes)[0] : NUMA_NO_NODE);

	if (mode == MPOL_DEFAULT) {
		if (nodes && !nodes_empty(*nodes))
			return ERR_PTR(-EINVAL);
		return NULL;
	}
	VM_BUG_ON(!nodes);

	/*
	 * MPOL_PREFERRED cannot be used with MPOL_F_STATIC_NODES or
	 * MPOL_F_RELATIVE_NODES if the nodemask is empty (local allocation).
	 * All other modes require a valid pointer to a non-empty nodemask.
	 */
	if (mode == MPOL_PREFERRED) {
		if (nodes_empty(*nodes)) {
			if (((flags & MPOL_F_STATIC_NODES) ||
			     (flags & MPOL_F_RELATIVE_NODES)))
				return ERR_PTR(-EINVAL);
		}
	} else if (mode == MPOL_LOCAL) {
		if (!nodes_empty(*nodes))
			return ERR_PTR(-EINVAL);
		mode = MPOL_PREFERRED;
	} else if (nodes_empty(*nodes))
		return ERR_PTR(-EINVAL);
	policy = kmem_cache_alloc(policy_cache, GFP_KERNEL);
	if (!policy)
		return ERR_PTR(-ENOMEM);
	atomic_set(&policy->refcnt, 1);
	policy->mode = mode;
	policy->flags = flags;

	return policy;
}

/* Slow path of a mpol destructor. */
void __mpol_put(struct mempolicy *p)
{
	if (!atomic_dec_and_test(&p->refcnt))
		return;
	kmem_cache_free(policy_cache, p);
}

static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes,
				enum mpol_rebind_step step)
{
}

/*
 * step:
 * 	MPOL_REBIND_ONCE  - do rebind work at once
 * 	MPOL_REBIND_STEP1 - set all the newly nodes
 * 	MPOL_REBIND_STEP2 - clean all the disallowed nodes
 */
static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes,
				 enum mpol_rebind_step step)
{
	nodemask_t tmp;

	if (pol->flags & MPOL_F_STATIC_NODES)
		nodes_and(tmp, pol->w.user_nodemask, *nodes);
	else if (pol->flags & MPOL_F_RELATIVE_NODES)
		mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes);
	else {
		/*
		 * if step == 1, we use ->w.cpuset_mems_allowed to cache the
		 * result
		 */
		if (step == MPOL_REBIND_ONCE || step == MPOL_REBIND_STEP1) {
			nodes_remap(tmp, pol->v.nodes,
					pol->w.cpuset_mems_allowed, *nodes);
			pol->w.cpuset_mems_allowed = step ? tmp : *nodes;
		} else if (step == MPOL_REBIND_STEP2) {
			tmp = pol->w.cpuset_mems_allowed;
			pol->w.cpuset_mems_allowed = *nodes;
		} else
			BUG();
	}

	if (nodes_empty(tmp))
		tmp = *nodes;

	if (step == MPOL_REBIND_STEP1)
		nodes_or(pol->v.nodes, pol->v.nodes, tmp);
	else if (step == MPOL_REBIND_ONCE || step == MPOL_REBIND_STEP2)
		pol->v.nodes = tmp;
	else
		BUG();

	if (!node_isset(current->il_next, tmp)) {
		current->il_next = next_node(current->il_next, tmp);
		if (current->il_next >= MAX_NUMNODES)
			current->il_next = first_node(tmp);
		if (current->il_next >= MAX_NUMNODES)
			current->il_next = numa_node_id();
	}
}

static void mpol_rebind_preferred(struct mempolicy *pol,
				  const nodemask_t *nodes,
				  enum mpol_rebind_step step)
{
	nodemask_t tmp;

	if (pol->flags & MPOL_F_STATIC_NODES) {
		int node = first_node(pol->w.user_nodemask);

		if (node_isset(node, *nodes)) {
			pol->v.preferred_node = node;
			pol->flags &= ~MPOL_F_LOCAL;
		} else
			pol->flags |= MPOL_F_LOCAL;
	} else if (pol->flags & MPOL_F_RELATIVE_NODES) {
		mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes);
		pol->v.preferred_node = first_node(tmp);
	} else if (!(pol->flags & MPOL_F_LOCAL)) {
		pol->v.preferred_node = node_remap(pol->v.preferred_node,
						   pol->w.cpuset_mems_allowed,
						   *nodes);
		pol->w.cpuset_mems_allowed = *nodes;
	}
}

/*
 * mpol_rebind_policy - Migrate a policy to a different set of nodes
 *
 * If read-side task has no lock to protect task->mempolicy, write-side
 * task will rebind the task->mempolicy by two step. The first step is
 * setting all the newly nodes, and the second step is cleaning all the
 * disallowed nodes. In this way, we can avoid finding no node to alloc
 * page.
 * If we have a lock to protect task->mempolicy in read-side, we do
 * rebind directly.
 *
 * step:
 * 	MPOL_REBIND_ONCE  - do rebind work at once
 * 	MPOL_REBIND_STEP1 - set all the newly nodes
 * 	MPOL_REBIND_STEP2 - clean all the disallowed nodes
 */
static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask,
				enum mpol_rebind_step step)
{
	if (!pol)
		return;
	if (!mpol_store_user_nodemask(pol) && step == MPOL_REBIND_ONCE &&
	    nodes_equal(pol->w.cpuset_mems_allowed, *newmask))
		return;

	if (step == MPOL_REBIND_STEP1 && (pol->flags & MPOL_F_REBINDING))
		return;

	if (step == MPOL_REBIND_STEP2 && !(pol->flags & MPOL_F_REBINDING))
		BUG();

	if (step == MPOL_REBIND_STEP1)
		pol->flags |= MPOL_F_REBINDING;
	else if (step == MPOL_REBIND_STEP2)
		pol->flags &= ~MPOL_F_REBINDING;
	else if (step >= MPOL_REBIND_NSTEP)
		BUG();

	mpol_ops[pol->mode].rebind(pol, newmask, step);
}

/*
 * Wrapper for mpol_rebind_policy() that just requires task
 * pointer, and updates task mempolicy.
 *
 * Called with task's alloc_lock held.
 */

void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new,
			enum mpol_rebind_step step)
{
	mpol_rebind_policy(tsk->mempolicy, new, step);
}

/*
 * Rebind each vma in mm to new nodemask.
 *
 * Call holding a reference to mm.  Takes mm->mmap_sem during call.
 */

void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
{
	struct vm_area_struct *vma;

	down_write(&mm->mmap_sem);
	for (vma = mm->mmap; vma; vma = vma->vm_next)
		mpol_rebind_policy(vma->vm_policy, new, MPOL_REBIND_ONCE);
	up_write(&mm->mmap_sem);
}

static const struct mempolicy_operations mpol_ops[MPOL_MAX] = {
	[MPOL_DEFAULT] = {
		.rebind = mpol_rebind_default,
	},
	[MPOL_INTERLEAVE] = {
		.create = mpol_new_interleave,
		.rebind = mpol_rebind_nodemask,
	},
	[MPOL_PREFERRED] = {
		.create = mpol_new_preferred,
		.rebind = mpol_rebind_preferred,
	},
	[MPOL_BIND] = {
		.create = mpol_new_bind,
		.rebind = mpol_rebind_nodemask,
	},
};

static void migrate_page_add(struct page *page, struct list_head *pagelist,
				unsigned long flags);

/*
 * Scan through pages checking if pages follow certain conditions,
 * and move them to the pagelist if they do.
 */
static int queue_pages_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
		unsigned long addr, unsigned long end,
		const nodemask_t *nodes, unsigned long flags,
		void *private)
{
	pte_t *orig_pte;
	pte_t *pte;
	spinlock_t *ptl;

	orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
	do {
		struct page *page;
		int nid;

		if (!pte_present(*pte))
			continue;
		page = vm_normal_page(vma, addr, *pte);
		if (!page)
			continue;
		/*
		 * vm_normal_page() filters out zero pages, but there might
		 * still be PageReserved pages to skip, perhaps in a VDSO.
		 */
		if (PageReserved(page))
			continue;
		nid = page_to_nid(page);
		if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
			continue;

		if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
			migrate_page_add(page, private, flags);
		else
			break;
	} while (pte++, addr += PAGE_SIZE, addr != end);
	pte_unmap_unlock(orig_pte, ptl);
	return addr != end;
}

static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma,
		pmd_t *pmd, const nodemask_t *nodes, unsigned long flags,
				    void *private)
{
#ifdef CONFIG_HUGETLB_PAGE
	int nid;
	struct page *page;

	spin_lock(&vma->vm_mm->page_table_lock);
	page = pte_page(huge_ptep_get((pte_t *)pmd));
	nid = page_to_nid(page);
	if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
		goto unlock;
	/* With MPOL_MF_MOVE, we migrate only unshared hugepage. */
	if (flags & (MPOL_MF_MOVE_ALL) ||
	    (flags & MPOL_MF_MOVE && page_mapcount(page) == 1))
		isolate_huge_page(page, private);
unlock:
	spin_unlock(&vma->vm_mm->page_table_lock);
#else
	BUG();
#endif
}

static inline int queue_pages_pmd_range(struct vm_area_struct *vma, pud_t *pud,
		unsigned long addr, unsigned long end,
		const nodemask_t *nodes, unsigned long flags,
		void *private)
{
	pmd_t *pmd;
	unsigned long next;

	pmd = pmd_offset(pud, addr);
	do {
		next = pmd_addr_end(addr, end);
		if (!pmd_present(*pmd))
			continue;
		if (pmd_huge(*pmd) && is_vm_hugetlb_page(vma)) {
			queue_pages_hugetlb_pmd_range(vma, pmd, nodes,
						flags, private);
			continue;
		}
		split_huge_page_pmd(vma, addr, pmd);
		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
			continue;
		if (queue_pages_pte_range(vma, pmd, addr, next, nodes,
				    flags, private))
			return -EIO;
	} while (pmd++, addr = next, addr != end);
	return 0;
}

static inline int queue_pages_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
		unsigned long addr, unsigned long end,
		const nodemask_t *nodes, unsigned long flags,
		void *private)
{
	pud_t *pud;
	unsigned long next;

	pud = pud_offset(pgd, addr);
	do {
		next = pud_addr_end(addr, end);
		if (pud_huge(*pud) && is_vm_hugetlb_page(vma))
			continue;
		if (pud_none_or_clear_bad(pud))
			continue;
		if (queue_pages_pmd_range(vma, pud, addr, next, nodes,
				    flags, private))
			return -EIO;
	} while (pud++, addr = next, addr != end);
	return 0;
}

static inline int queue_pages_pgd_range(struct vm_area_struct *vma,
		unsigned long addr, unsigned long end,
		const nodemask_t *nodes, unsigned long flags,
		void *private)
{
	pgd_t *pgd;
	unsigned long next;

	pgd = pgd_offset(vma->vm_mm, addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none_or_clear_bad(pgd))
			continue;
		if (queue_pages_pud_range(vma, pgd, addr, next, nodes,
				    flags, private))
			return -EIO;
	} while (pgd++, addr = next, addr != end);
	return 0;
}

#ifdef CONFIG_ARCH_USES_NUMA_PROT_NONE
/*
 * This is used to mark a range of virtual addresses to be inaccessible.
 * These are later cleared by a NUMA hinting fault. Depending on these
 * faults, pages may be migrated for better NUMA placement.
 *
 * This is assuming that NUMA faults are handled using PROT_NONE. If
 * an architecture makes a different choice, it will need further
 * changes to the core.
 */
unsigned long change_prot_numa(struct vm_area_struct *vma,
			unsigned long addr, unsigned long end)
{
	int nr_updated;
	BUILD_BUG_ON(_PAGE_NUMA != _PAGE_PROTNONE);

	nr_updated = change_protection(vma, addr, end, vma->vm_page_prot, 0, 1);
	if (nr_updated)
		count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated);

	return nr_updated;
}
#else
static unsigned long change_prot_numa(struct vm_area_struct *vma,
			unsigned long addr, unsigned long end)
{
	return 0;
}
#endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */

/*
 * Walk through page tables and collect pages to be migrated.
 *
 * If pages found in a given range are on a set of nodes (determined by
 * @nodes and @flags,) it's isolated and queued to the pagelist which is
 * passed via @private.)
 */
static struct vm_area_struct *
queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
		const nodemask_t *nodes, unsigned long flags, void *private)
{
	int err;
	struct vm_area_struct *first, *vma, *prev;


	first = find_vma(mm, start);
	if (!first)
		return ERR_PTR(-EFAULT);
	prev = NULL;
	for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) {
		unsigned long endvma = vma->vm_end;

		if (endvma > end)
			endvma = end;
		if (vma->vm_start > start)
			start = vma->vm_start;

		if (!(flags & MPOL_MF_DISCONTIG_OK)) {
			if (!vma->vm_next && vma->vm_end < end)
				return ERR_PTR(-EFAULT);
			if (prev && prev->vm_end < vma->vm_start)
				return ERR_PTR(-EFAULT);
		}

		if (flags & MPOL_MF_LAZY) {
			change_prot_numa(vma, start, endvma);
			goto next;
		}

		if ((flags & MPOL_MF_STRICT) ||
		     ((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) &&
		      vma_migratable(vma))) {

			err = queue_pages_pgd_range(vma, start, endvma, nodes,
						flags, private);
			if (err) {
				first = ERR_PTR(err);
				break;
			}
		}
next:
		prev = vma;
	}
	return first;
}

/*
 * Apply policy to a single VMA
 * This must be called with the mmap_sem held for writing.
 */
static int vma_replace_policy(struct vm_area_struct *vma,
						struct mempolicy *pol)
{
	int err;
	struct mempolicy *old;
	struct mempolicy *new;

	pr_debug("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n",
		 vma->vm_start, vma->vm_end, vma->vm_pgoff,
		 vma->vm_ops, vma->vm_file,
		 vma->vm_ops ? vma->vm_ops->set_policy : NULL);

	new = mpol_dup(pol);
	if (IS_ERR(new))
		return PTR_ERR(new);

	if (vma->vm_ops && vma->vm_ops->set_policy) {
		err = vma->vm_ops->set_policy(vma, new);
		if (err)
			goto err_out;
	}

	old = vma->vm_policy;
	vma->vm_policy = new; /* protected by mmap_sem */
	mpol_put(old);

	return 0;
 err_out:
	mpol_put(new);
	return err;
}

/* Step 2: apply policy to a range and do splits. */
static int mbind_range(struct mm_struct *mm, unsigned long start,
		       unsigned long end, struct mempolicy *new_pol)
{
	struct vm_area_struct *next;
	struct vm_area_struct *prev;
	struct vm_area_struct *vma;
	int err = 0;
	pgoff_t pgoff;
	unsigned long vmstart;
	unsigned long vmend;

	vma = find_vma(mm, start);
	if (!vma || vma->vm_start > start)
		return -EFAULT;

	prev = vma->vm_prev;
	if (start > vma->vm_start)
		prev = vma;

	for (; vma && vma->vm_start < end; prev = vma, vma = next) {
		next = vma->vm_next;
		vmstart = max(start, vma->vm_start);
		vmend   = min(end, vma->vm_end);

		if (mpol_equal(vma_policy(vma), new_pol))
			continue;

		pgoff = vma->vm_pgoff +
			((vmstart - vma->vm_start) >> PAGE_SHIFT);
		prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags,
				  vma->anon_vma, vma->vm_file, pgoff,
				  new_pol);
		if (prev) {
			vma = prev;
			next = vma->vm_next;
			if (mpol_equal(vma_policy(vma), new_pol))
				continue;
			/* vma_merge() joined vma && vma->next, case 8 */
			goto replace;
		}
		if (vma->vm_start != vmstart) {
			err = split_vma(vma->vm_mm, vma, vmstart, 1);
			if (err)
				goto out;
		}
		if (vma->vm_end != vmend) {
			err = split_vma(vma->vm_mm, vma, vmend, 0);
			if (err)
				goto out;
		}
 replace:
		err = vma_replace_policy(vma, new_pol);
		if (err)
			goto out;
	}

 out:
	return err;
}

/*
 * Update task->flags PF_MEMPOLICY bit: set iff non-default
 * mempolicy.  Allows more rapid checking of this (combined perhaps
 * with other PF_* flag bits) on memory allocation hot code paths.
 *
 * If called from outside this file, the task 'p' should -only- be
 * a newly forked child not yet visible on the task list, because
 * manipulating the task flags of a visible task is not safe.
 *
 * The above limitation is why this routine has the funny name
 * mpol_fix_fork_child_flag().
 *
 * It is also safe to call this with a task pointer of current,
 * which the static wrapper mpol_set_task_struct_flag() does,
 * for use within this file.
 */

void mpol_fix_fork_child_flag(struct task_struct *p)
{
	if (p->mempolicy)
		p->flags |= PF_MEMPOLICY;
	else
		p->flags &= ~PF_MEMPOLICY;
}

static void mpol_set_task_struct_flag(void)
{
	mpol_fix_fork_child_flag(current);
}

/* Set the process memory policy */
static long do_set_mempolicy(unsigned short mode, unsigned short flags,
			     nodemask_t *nodes)
{
	struct mempolicy *new, *old;
	struct mm_struct *mm = current->mm;
	NODEMASK_SCRATCH(scratch);
	int ret;

	if (!scratch)
		return -ENOMEM;

	new = mpol_new(mode, flags, nodes);
	if (IS_ERR(new)) {
		ret = PTR_ERR(new);
		goto out;
	}
	/*
	 * prevent changing our mempolicy while show_numa_maps()
	 * is using it.
	 * Note:  do_set_mempolicy() can be called at init time
	 * with no 'mm'.
	 */
	if (mm)
		down_write(&mm->mmap_sem);
	task_lock(current);
	ret = mpol_set_nodemask(new, nodes, scratch);
	if (ret) {
		task_unlock(current);
		if (mm)
			up_write(&mm->mmap_sem);
		mpol_put(new);
		goto out;
	}
	old = current->mempolicy;
	current->mempolicy = new;
	mpol_set_task_struct_flag();
	if (new && new->mode == MPOL_INTERLEAVE &&
	    nodes_weight(new->v.nodes))
		current->il_next = first_node(new->v.nodes);
	task_unlock(current);
	if (mm)
		up_write(&mm->mmap_sem);

	mpol_put(old);
	ret = 0;
out:
	NODEMASK_SCRATCH_FREE(scratch);
	return ret;
}

/*
 * Return nodemask for policy for get_mempolicy() query
 *
 * Called with task's alloc_lock held
 */
static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes)
{
	nodes_clear(*nodes);
	if (p == &default_policy)
		return;

	switch (p->mode) {
	case MPOL_BIND:
		/* Fall through */
	case MPOL_INTERLEAVE:
		*nodes = p->v.nodes;
		break;
	case MPOL_PREFERRED:
		if (!(p->flags & MPOL_F_LOCAL))
			node_set(p->v.preferred_node, *nodes);
		/* else return empty node mask for local allocation */
		break;
	default:
		BUG();
	}
}

static int lookup_node(struct mm_struct *mm, unsigned long addr)
{
	struct page *p;
	int err;

	err = get_user_pages(current, mm, addr & PAGE_MASK, 1, 0, 0, &p, NULL);
	if (err >= 0) {
		err = page_to_nid(p);
		put_page(p);
	}
	return err;
}

/* Retrieve NUMA policy */
static long do_get_mempolicy(int *policy, nodemask_t *nmask,
			     unsigned long addr, unsigned long flags)
{
	int err;
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma = NULL;
	struct mempolicy *pol = current->mempolicy;

	if (flags &
		~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED))
		return -EINVAL;

	if (flags & MPOL_F_MEMS_ALLOWED) {
		if (flags & (MPOL_F_NODE|MPOL_F_ADDR))
			return -EINVAL;
		*policy = 0;	/* just so it's initialized */
		task_lock(current);
		*nmask  = cpuset_current_mems_allowed;
		task_unlock(current);
		return 0;
	}

	if (flags & MPOL_F_ADDR) {
		/*
		 * Do NOT fall back to task policy if the
		 * vma/shared policy at addr is NULL.  We
		 * want to return MPOL_DEFAULT in this case.
		 */
		down_read(&mm->mmap_sem);
		vma = find_vma_intersection(mm, addr, addr+1);
		if (!vma) {
			up_read(&mm->mmap_sem);
			return -EFAULT;
		}
		if (vma->vm_ops && vma->vm_ops->get_policy)
			pol = vma->vm_ops->get_policy(vma, addr);
		else
			pol = vma->vm_policy;
	} else if (addr)
		return -EINVAL;

	if (!pol)
		pol = &default_policy;	/* indicates default behavior */

	if (flags & MPOL_F_NODE) {
		if (flags & MPOL_F_ADDR) {
			err = lookup_node(mm, addr);
			if (err < 0)
				goto out;
			*policy = err;
		} else if (pol == current->mempolicy &&
				pol->mode == MPOL_INTERLEAVE) {
			*policy = current->il_next;
		} else {
			err = -EINVAL;
			goto out;
		}
	} else {
		*policy = pol == &default_policy ? MPOL_DEFAULT :
						pol->mode;
		/*
		 * Internal mempolicy flags must be masked off before exposing
		 * the policy to userspace.
		 */
		*policy |= (pol->flags & MPOL_MODE_FLAGS);
	}

	if (vma) {
		up_read(&current->mm->mmap_sem);
		vma = NULL;
	}

	err = 0;
	if (nmask) {
		if (mpol_store_user_nodemask(pol)) {
			*nmask = pol->w.user_nodemask;
		} else {
			task_lock(current);
			get_policy_nodemask(pol, nmask);
			task_unlock(current);
		}
	}

 out:
	mpol_cond_put(pol);
	if (vma)
		up_read(&current->mm->mmap_sem);
	return err;
}

#ifdef CONFIG_MIGRATION
/*
 * page migration
 */
static void migrate_page_add(struct page *page, struct list_head *pagelist,
				unsigned long flags)
{
	/*
	 * Avoid migrating a page that is shared with others.
	 */
	if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1) {
		if (!isolate_lru_page(page)) {
			list_add_tail(&page->lru, pagelist);
			inc_zone_page_state(page, NR_ISOLATED_ANON +
					    page_is_file_cache(page));
		}
	}
}

static struct page *new_node_page(struct page *page, unsigned long node, int **x)
{
	if (PageHuge(page))
		return alloc_huge_page_node(page_hstate(compound_head(page)),
					node);
	else
		return alloc_pages_exact_node(node, GFP_HIGHUSER_MOVABLE, 0);
}

/*
 * Migrate pages from one node to a target node.
 * Returns error or the number of pages not migrated.
 */
static int migrate_to_node(struct mm_struct *mm, int source, int dest,
			   int flags)
{
	nodemask_t nmask;
	LIST_HEAD(pagelist);
	int err = 0;

	nodes_clear(nmask);
	node_set(source, nmask);

	/*
	 * This does not "check" the range but isolates all pages that
	 * need migration.  Between passing in the full user address
	 * space range and MPOL_MF_DISCONTIG_OK, this call can not fail.
	 */
	VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)));
	queue_pages_range(mm, mm->mmap->vm_start, mm->task_size, &nmask,
			flags | MPOL_MF_DISCONTIG_OK, &pagelist);

	if (!list_empty(&pagelist)) {
		err = migrate_pages(&pagelist, new_node_page, dest,
					MIGRATE_SYNC, MR_SYSCALL);
		if (err)
			putback_movable_pages(&pagelist);
	}

	return err;
}

/*
 * Move pages between the two nodesets so as to preserve the physical
 * layout as much as possible.
 *
 * Returns the number of page that could not be moved.
 */
int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
		     const nodemask_t *to, int flags)
{
	int busy = 0;
	int err;
	nodemask_t tmp;

	err = migrate_prep();
	if (err)
		return err;

	down_read(&mm->mmap_sem);

	err = migrate_vmas(mm, from, to, flags);
	if (err)
		goto out;

	/*
	 * Find a 'source' bit set in 'tmp' whose corresponding 'dest'
	 * bit in 'to' is not also set in 'tmp'.  Clear the found 'source'
	 * bit in 'tmp', and return that <source, dest> pair for migration.
	 * The pair of nodemasks 'to' and 'from' define the map.
	 *
	 * If no pair of bits is found that way, fallback to picking some
	 * pair of 'source' and 'dest' bits that are not the same.  If the
	 * 'source' and 'dest' bits are the same, this represents a node
	 * that will be migrating to itself, so no pages need move.
	 *
	 * If no bits are left in 'tmp', or if all remaining bits left
	 * in 'tmp' correspond to the same bit in 'to', return false
	 * (nothing left to migrate).
	 *
	 * This lets us pick a pair of nodes to migrate between, such that
	 * if possible the dest node is not already occupied by some other
	 * source node, minimizing the risk of overloading the memory on a
	 * node that would happen if we migrated incoming memory to a node
	 * before migrating outgoing memory source that same node.
	 *
	 * A single scan of tmp is sufficient.  As we go, we remember the
	 * most recent <s, d> pair that moved (s != d).  If we find a pair
	 * that not only moved, but what's better, moved to an empty slot
	 * (d is not set in tmp), then we break out then, with that pair.
	 * Otherwise when we finish scanning from_tmp, we at least have the
	 * most recent <s, d> pair that moved.  If we get all the way through
	 * the scan of tmp without finding any node that moved, much less
	 * moved to an empty node, then there is nothing left worth migrating.
	 */

	tmp = *from;
	while (!nodes_empty(tmp)) {
		int s,d;
		int source = NUMA_NO_NODE;
		int dest = 0;

		for_each_node_mask(s, tmp) {

			/*
			 * do_migrate_pages() tries to maintain the relative
			 * node relationship of the pages established between
			 * threads and memory areas.
                         *
			 * However if the number of source nodes is not equal to
			 * the number of destination nodes we can not preserve
			 * this node relative relationship.  In that case, skip
			 * copying memory from a node that is in the destination
			 * mask.
			 *
			 * Example: [2,3,4] -> [3,4,5] moves everything.
			 *          [0-7] - > [3,4,5] moves only 0,1,2,6,7.
			 */

			if ((nodes_weight(*from) != nodes_weight(*to)) &&
						(node_isset(s, *to)))
				continue;

			d = node_remap(s, *from, *to);
			if (s == d)
				continue;

			source = s;	/* Node moved. Memorize */
			dest = d;

			/* dest not in remaining from nodes? */
			if (!node_isset(dest, tmp))
				break;
		}
		if (source == NUMA_NO_NODE)
			break;

		node_clear(source, tmp);
		err = migrate_to_node(mm, source, dest, flags);
		if (err > 0)
			busy += err;
		if (err < 0)
			break;
	}
out:
	up_read(&mm->mmap_sem);
	if (err < 0)
		return err;
	return busy;

}

/*
 * Allocate a new page for page migration based on vma policy.
 * Start assuming that page is mapped by vma pointed to by @private.
 * Search forward from there, if not.  N.B., this assumes that the
 * list of pages handed to migrate_pages()--which is how we get here--
 * is in virtual address order.
 */
static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
{
	struct vm_area_struct *vma = (struct vm_area_struct *)private;
	unsigned long uninitialized_var(address);

	while (vma) {
		address = page_address_in_vma(page, vma);
		if (address != -EFAULT)
			break;
		vma = vma->vm_next;
	}
	/*
	 * queue_pages_range() confirms that @page belongs to some vma,
	 * so vma shouldn't be NULL.
	 */
	BUG_ON(!vma);

	if (PageHuge(page))
		return alloc_huge_page_noerr(vma, address, 1);
	return alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
}
#else

static void migrate_page_add(struct page *page, struct list_head *pagelist,
				unsigned long flags)
{
}

int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
		     const nodemask_t *to, int flags)
{
	return -ENOSYS;
}

static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
{
	return NULL;
}
#endif

static long do_mbind(unsigned long start, unsigned long len,
		     unsigned short mode, unsigned short mode_flags,
		     nodemask_t *nmask, unsigned long flags)
{
	struct vm_area_struct *vma;
	struct mm_struct *mm = current->mm;
	struct mempolicy *new;
	unsigned long end;
	int err;
	LIST_HEAD(pagelist);

	if (flags & ~(unsigned long)MPOL_MF_VALID)
		return -EINVAL;
	if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE))
		return -EPERM;

	if (start & ~PAGE_MASK)
		return -EINVAL;

	if (mode == MPOL_DEFAULT)
		flags &= ~MPOL_MF_STRICT;

	len = (len + PAGE_SIZE - 1) & PAGE_MASK;
	end = start + len;

	if (end < start)
		return -EINVAL;
	if (end == start)
		return 0;

	new = mpol_new(mode, mode_flags, nmask);
	if (IS_ERR(new))
		return PTR_ERR(new);

	if (flags & MPOL_MF_LAZY)
		new->flags |= MPOL_F_MOF;

	/*
	 * If we are using the default policy then operation
	 * on discontinuous address spaces is okay after all
	 */
	if (!new)
		flags |= MPOL_MF_DISCONTIG_OK;

	pr_debug("mbind %lx-%lx mode:%d flags:%d nodes:%lx\n",
		 start, start + len, mode, mode_flags,
		 nmask ? nodes_addr(*nmask)[0] : NUMA_NO_NODE);

	if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {

		err = migrate_prep();
		if (err)
			goto mpol_out;
	}
	{
		NODEMASK_SCRATCH(scratch);
		if (scratch) {
			down_write(&mm->mmap_sem);
			task_lock(current);
			err = mpol_set_nodemask(new, nmask, scratch);
			task_unlock(current);
			if (err)
				up_write(&mm->mmap_sem);
		} else
			err = -ENOMEM;
		NODEMASK_SCRATCH_FREE(scratch);
	}
	if (err)
		goto mpol_out;

	vma = queue_pages_range(mm, start, end, nmask,
			  flags | MPOL_MF_INVERT, &pagelist);

	err = PTR_ERR(vma);	/* maybe ... */
	if (!IS_ERR(vma))
		err = mbind_range(mm, start, end, new);

	if (!err) {
		int nr_failed = 0;

		if (!list_empty(&pagelist)) {
			WARN_ON_ONCE(flags & MPOL_MF_LAZY);
			nr_failed = migrate_pages(&pagelist, new_vma_page,
					(unsigned long)vma,
					MIGRATE_SYNC, MR_MEMPOLICY_MBIND);
			if (nr_failed)
				putback_movable_pages(&pagelist);
		}

		if (nr_failed && (flags & MPOL_MF_STRICT))
			err = -EIO;
	} else
		putback_lru_pages(&pagelist);

	up_write(&mm->mmap_sem);
 mpol_out:
	mpol_put(new);
	return err;
}

/*
 * User space interface with variable sized bitmaps for nodelists.
 */

/* Copy a node mask from user space. */
static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask,
		     unsigned long maxnode)
{
	unsigned long k;
	unsigned long nlongs;
	unsigned long endmask;

	--maxnode;
	nodes_clear(*nodes);
	if (maxnode == 0 || !nmask)
		return 0;
	if (maxnode > PAGE_SIZE*BITS_PER_BYTE)
		return -EINVAL;

	nlongs = BITS_TO_LONGS(maxnode);
	if ((maxnode % BITS_PER_LONG) == 0)
		endmask = ~0UL;
	else
		endmask = (1UL << (maxnode % BITS_PER_LONG)) - 1;

	/* When the user specified more nodes than supported just check
	   if the non supported part is all zero. */
	if (nlongs > BITS_TO_LONGS(MAX_NUMNODES)) {
		if (nlongs > PAGE_SIZE/sizeof(long))
			return -EINVAL;
		for (k = BITS_TO_LONGS(MAX_NUMNODES); k < nlongs; k++) {
			unsigned long t;
			if (get_user(t, nmask + k))
				return -EFAULT;
			if (k == nlongs - 1) {
				if (t & endmask)
					return -EINVAL;
			} else if (t)
				return -EINVAL;
		}
		nlongs = BITS_TO_LONGS(MAX_NUMNODES);
		endmask = ~0UL;
	}

	if (copy_from_user(nodes_addr(*nodes), nmask, nlongs*sizeof(unsigned long)))
		return -EFAULT;
	nodes_addr(*nodes)[nlongs-1] &= endmask;
	return 0;
}

/* Copy a kernel node mask to user space */
static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode,
			      nodemask_t *nodes)
{
	unsigned long copy = ALIGN(maxnode-1, 64) / 8;
	const int nbytes = BITS_TO_LONGS(MAX_NUMNODES) * sizeof(long);

	if (copy > nbytes) {
		if (copy > PAGE_SIZE)
			return -EINVAL;
		if (clear_user((char __user *)mask + nbytes, copy - nbytes))
			return -EFAULT;
		copy = nbytes;
	}
	return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0;
}

SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len,
		unsigned long, mode, unsigned long __user *, nmask,
		unsigned long, maxnode, unsigned, flags)
{
	nodemask_t nodes;
	int err;
	unsigned short mode_flags;

	mode_flags = mode & MPOL_MODE_FLAGS;
	mode &= ~MPOL_MODE_FLAGS;
	if (mode >= MPOL_MAX)
		return -EINVAL;
	if ((mode_flags & MPOL_F_STATIC_NODES) &&
	    (mode_flags & MPOL_F_RELATIVE_NODES))
		return -EINVAL;
	err = get_nodes(&nodes, nmask, maxnode);
	if (err)
		return err;
	return do_mbind(start, len, mode, mode_flags, &nodes, flags);
}

/* Set the process memory policy */
SYSCALL_DEFINE3(set_mempolicy, int, mode, unsigned long __user *, nmask,
		unsigned long, maxnode)
{
	int err;
	nodemask_t nodes;
	unsigned short flags;

	flags = mode & MPOL_MODE_FLAGS;
	mode &= ~MPOL_MODE_FLAGS;
	if ((unsigned int)mode >= MPOL_MAX)
		return -EINVAL;
	if ((flags & MPOL_F_STATIC_NODES) && (flags & MPOL_F_RELATIVE_NODES))
		return -EINVAL;
	err = get_nodes(&nodes, nmask, maxnode);
	if (err)
		return err;
	return do_set_mempolicy(mode, flags, &nodes);
}

SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode,
		const unsigned long __user *, old_nodes,
		const unsigned long __user *, new_nodes)
{
	const struct cred *cred = current_cred(), *tcred;
	struct mm_struct *mm = NULL;
	struct task_struct *task;
	nodemask_t task_nodes;
	int err;
	nodemask_t *old;
	nodemask_t *new;
	NODEMASK_SCRATCH(scratch);

	if (!scratch)
		return -ENOMEM;

	old = &scratch->mask1;
	new = &scratch->mask2;

	err = get_nodes(old, old_nodes, maxnode);
	if (err)
		goto out;

	err = get_nodes(new, new_nodes, maxnode);
	if (err)
		goto out;

	/* Find the mm_struct */
	rcu_read_lock();
	task = pid ? find_task_by_vpid(pid) : current;
	if (!task) {
		rcu_read_unlock();
		err = -ESRCH;
		goto out;
	}
	get_task_struct(task);

	err = -EINVAL;

	/*
	 * Check if this process has the right to modify the specified
	 * process. The right exists if the process has administrative
	 * capabilities, superuser privileges or the same
	 * userid as the target process.
	 */
	tcred = __task_cred(task);
	if (!uid_eq(cred->euid, tcred->suid) && !uid_eq(cred->euid, tcred->uid) &&
	    !uid_eq(cred->uid,  tcred->suid) && !uid_eq(cred->uid,  tcred->uid) &&
	    !capable(CAP_SYS_NICE)) {
		rcu_read_unlock();
		err = -EPERM;
		goto out_put;
	}
	rcu_read_unlock();

	task_nodes = cpuset_mems_allowed(task);
	/* Is the user allowed to access the target nodes? */
	if (!nodes_subset(*new, task_nodes) && !capable(CAP_SYS_NICE)) {
		err = -EPERM;
		goto out_put;
	}

	if (!nodes_subset(*new, node_states[N_MEMORY])) {
		err = -EINVAL;
		goto out_put;
	}

	err = security_task_movememory(task);
	if (err)
		goto out_put;

	mm = get_task_mm(task);
	put_task_struct(task);

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

	err = do_migrate_pages(mm, old, new,
		capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE);

	mmput(mm);
out:
	NODEMASK_SCRATCH_FREE(scratch);

	return err;

out_put:
	put_task_struct(task);
	goto out;

}


/* Retrieve NUMA policy */
SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
		unsigned long __user *, nmask, unsigned long, maxnode,
		unsigned long, addr, unsigned long, flags)
{
	int err;
	int uninitialized_var(pval);
	nodemask_t nodes;

	if (nmask != NULL && maxnode < MAX_NUMNODES)
		return -EINVAL;

	err = do_get_mempolicy(&pval, &nodes, addr, flags);

	if (err)
		return err;

	if (policy && put_user(pval, policy))
		return -EFAULT;

	if (nmask)
		err = copy_nodes_to_user(nmask, maxnode, &nodes);

	return err;
}

#ifdef CONFIG_COMPAT

asmlinkage long compat_sys_get_mempolicy(int __user *policy,
				     compat_ulong_t __user *nmask,
				     compat_ulong_t maxnode,
				     compat_ulong_t addr, compat_ulong_t flags)
{
	long err;
	unsigned long __user *nm = NULL;
	unsigned long nr_bits, alloc_size;
	DECLARE_BITMAP(bm, MAX_NUMNODES);

	nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
	alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;

	if (nmask)
		nm = compat_alloc_user_space(alloc_size);

	err = sys_get_mempolicy(policy, nm, nr_bits+1, addr, flags);

	if (!err && nmask) {
		unsigned long copy_size;
		copy_size = min_t(unsigned long, sizeof(bm), alloc_size);
		err = copy_from_user(bm, nm, copy_size);
		/* ensure entire bitmap is zeroed */
		err |= clear_user(nmask, ALIGN(maxnode-1, 8) / 8);
		err |= compat_put_bitmap(nmask, bm, nr_bits);
	}

	return err;
}

asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask,
				     compat_ulong_t maxnode)
{
	long err = 0;
	unsigned long __user *nm = NULL;
	unsigned long nr_bits, alloc_size;
	DECLARE_BITMAP(bm, MAX_NUMNODES);

	nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
	alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;

	if (nmask) {
		err = compat_get_bitmap(bm, nmask, nr_bits);
		nm = compat_alloc_user_space(alloc_size);
		err |= copy_to_user(nm, bm, alloc_size);
	}

	if (err)
		return -EFAULT;

	return sys_set_mempolicy(mode, nm, nr_bits+1);
}

asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len,
			     compat_ulong_t mode, compat_ulong_t __user *nmask,
			     compat_ulong_t maxnode, compat_ulong_t flags)
{
	long err = 0;
	unsigned long __user *nm = NULL;
	unsigned long nr_bits, alloc_size;
	nodemask_t bm;

	nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
	alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;

	if (nmask) {
		err = compat_get_bitmap(nodes_addr(bm), nmask, nr_bits);
		nm = compat_alloc_user_space(alloc_size);
		err |= copy_to_user(nm, nodes_addr(bm), alloc_size);
	}

	if (err)
		return -EFAULT;

	return sys_mbind(start, len, mode, nm, nr_bits+1, flags);
}

#endif

/*
 * get_vma_policy(@task, @vma, @addr)
 * @task - task for fallback if vma policy == default
 * @vma   - virtual memory area whose policy is sought
 * @addr  - address in @vma for shared policy lookup
 *
 * Returns effective policy for a VMA at specified address.
 * Falls back to @task or system default policy, as necessary.
 * Current or other task's task mempolicy and non-shared vma policies must be
 * protected by task_lock(task) by the caller.
 * Shared policies [those marked as MPOL_F_SHARED] require an extra reference
 * count--added by the get_policy() vm_op, as appropriate--to protect against
 * freeing by another task.  It is the caller's responsibility to free the
 * extra reference for shared policies.
 */
struct mempolicy *get_vma_policy(struct task_struct *task,
		struct vm_area_struct *vma, unsigned long addr)
{
	struct mempolicy *pol = get_task_policy(task);

	if (vma) {
		if (vma->vm_ops && vma->vm_ops->get_policy) {
			struct mempolicy *vpol = vma->vm_ops->get_policy(vma,
									addr);
			if (vpol)
				pol = vpol;
		} else if (vma->vm_policy) {
			pol = vma->vm_policy;

			/*
			 * shmem_alloc_page() passes MPOL_F_SHARED policy with
			 * a pseudo vma whose vma->vm_ops=NULL. Take a reference
			 * count on these policies which will be dropped by
			 * mpol_cond_put() later
			 */
			if (mpol_needs_cond_ref(pol))
				mpol_get(pol);
		}
	}
	if (!pol)
		pol = &default_policy;
	return pol;
}

bool vma_policy_mof(struct task_struct *task, struct vm_area_struct *vma)
{
	struct mempolicy *pol = get_task_policy(task);
	if (vma) {
		if (vma->vm_ops && vma->vm_ops->get_policy) {
			bool ret = false;

			pol = vma->vm_ops->get_policy(vma, vma->vm_start);
			if (pol && (pol->flags & MPOL_F_MOF))
				ret = true;
			mpol_cond_put(pol);

			return ret;
		} else if (vma->vm_policy) {
			pol = vma->vm_policy;
		}
	}

	if (!pol)
		return default_policy.flags & MPOL_F_MOF;

	return pol->flags & MPOL_F_MOF;
}

static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone)
{
	enum zone_type dynamic_policy_zone = policy_zone;

	BUG_ON(dynamic_policy_zone == ZONE_MOVABLE);

	/*
	 * if policy->v.nodes has movable memory only,
	 * we apply policy when gfp_zone(gfp) = ZONE_MOVABLE only.
	 *
	 * policy->v.nodes is intersect with node_states[N_MEMORY].
	 * so if the following test faile, it implies
	 * policy->v.nodes has movable memory only.
	 */
	if (!nodes_intersects(policy->v.nodes, node_states[N_HIGH_MEMORY]))
		dynamic_policy_zone = ZONE_MOVABLE;

	return zone >= dynamic_policy_zone;
}

/*
 * Return a nodemask representing a mempolicy for filtering nodes for
 * page allocation
 */
static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy)
{
	/* Lower zones don't get a nodemask applied for MPOL_BIND */
	if (unlikely(policy->mode == MPOL_BIND) &&
			apply_policy_zone(policy, gfp_zone(gfp)) &&
			cpuset_nodemask_valid_mems_allowed(&policy->v.nodes))
		return &policy->v.nodes;

	return NULL;
}

/* Return a zonelist indicated by gfp for node representing a mempolicy */
static struct zonelist *policy_zonelist(gfp_t gfp, struct mempolicy *policy,
	int nd)
{
	switch (policy->mode) {
	case MPOL_PREFERRED:
		if (!(policy->flags & MPOL_F_LOCAL))
			nd = policy->v.preferred_node;
		break;
	case MPOL_BIND:
		/*
		 * Normally, MPOL_BIND allocations are node-local within the
		 * allowed nodemask.  However, if __GFP_THISNODE is set and the
		 * current node isn't part of the mask, we use the zonelist for
		 * the first node in the mask instead.
		 */
		if (unlikely(gfp & __GFP_THISNODE) &&
				unlikely(!node_isset(nd, policy->v.nodes)))
			nd = first_node(policy->v.nodes);
		break;
	default:
		BUG();
	}
	return node_zonelist(nd, gfp);
}

/* Do dynamic interleaving for a process */
static unsigned interleave_nodes(struct mempolicy *policy)
{
	unsigned nid, next;
	struct task_struct *me = current;

	nid = me->il_next;
	next = next_node(nid, policy->v.nodes);
	if (next >= MAX_NUMNODES)
		next = first_node(policy->v.nodes);
	if (next < MAX_NUMNODES)
		me->il_next = next;
	return nid;
}

/*
 * Depending on the memory policy provide a node from which to allocate the
 * next slab entry.
 * @policy must be protected by freeing by the caller.  If @policy is
 * the current task's mempolicy, this protection is implicit, as only the
 * task can change it's policy.  The system default policy requires no
 * such protection.
 */
unsigned slab_node(void)
{
	struct mempolicy *policy;

	if (in_interrupt())
		return numa_node_id();

	policy = current->mempolicy;
	if (!policy || policy->flags & MPOL_F_LOCAL)
		return numa_node_id();

	switch (policy->mode) {
	case MPOL_PREFERRED:
		/*
		 * handled MPOL_F_LOCAL above
		 */
		return policy->v.preferred_node;

	case MPOL_INTERLEAVE:
		return interleave_nodes(policy);

	case MPOL_BIND: {
		/*
		 * Follow bind policy behavior and start allocation at the
		 * first node.
		 */
		struct zonelist *zonelist;
		struct zone *zone;
		enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL);
		zonelist = &NODE_DATA(numa_node_id())->node_zonelists[0];
		(void)first_zones_zonelist(zonelist, highest_zoneidx,
							&policy->v.nodes,
							&zone);
		return zone ? zone->node : numa_node_id();
	}

	default:
		BUG();
	}
}

/* Do static interleaving for a VMA with known offset. */
static unsigned offset_il_node(struct mempolicy *pol,
		struct vm_area_struct *vma, unsigned long off)
{
	unsigned nnodes = nodes_weight(pol->v.nodes);
	unsigned target;
	int c;
	int nid = NUMA_NO_NODE;

	if (!nnodes)
		return numa_node_id();
	target = (unsigned int)off % nnodes;
	c = 0;
	do {
		nid = next_node(nid, pol->v.nodes);
		c++;
	} while (c <= target);
	return nid;
}

/* Determine a node number for interleave */
static inline unsigned interleave_nid(struct mempolicy *pol,
		 struct vm_area_struct *vma, unsigned long addr, int shift)
{
	if (vma) {
		unsigned long off;

		/*
		 * for small pages, there is no difference between
		 * shift and PAGE_SHIFT, so the bit-shift is safe.
		 * for huge pages, since vm_pgoff is in units of small
		 * pages, we need to shift off the always 0 bits to get
		 * a useful offset.
		 */
		BUG_ON(shift < PAGE_SHIFT);
		off = vma->vm_pgoff >> (shift - PAGE_SHIFT);
		off += (addr - vma->vm_start) >> shift;
		return offset_il_node(pol, vma, off);
	} else
		return interleave_nodes(pol);
}

/*
 * Return the bit number of a random bit set in the nodemask.
 * (returns NUMA_NO_NODE if nodemask is empty)
 */
int node_random(const nodemask_t *maskp)
{
	int w, bit = NUMA_NO_NODE;

	w = nodes_weight(*maskp);
	if (w)
		bit = bitmap_ord_to_pos(maskp->bits,
			get_random_int() % w, MAX_NUMNODES);
	return bit;
}

#ifdef CONFIG_HUGETLBFS
/*
 * huge_zonelist(@vma, @addr, @gfp_flags, @mpol)
 * @vma = virtual memory area whose policy is sought
 * @addr = address in @vma for shared policy lookup and interleave policy
 * @gfp_flags = for requested zone
 * @mpol = pointer to mempolicy pointer for reference counted mempolicy
 * @nodemask = pointer to nodemask pointer for MPOL_BIND nodemask
 *
 * Returns a zonelist suitable for a huge page allocation and a pointer
 * to the struct mempolicy for conditional unref after allocation.
 * If the effective policy is 'BIND, returns a pointer to the mempolicy's
 * @nodemask for filtering the zonelist.
 *
 * Must be protected by get_mems_allowed()
 */
struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr,
				gfp_t gfp_flags, struct mempolicy **mpol,
				nodemask_t **nodemask)
{
	struct zonelist *zl;

	*mpol = get_vma_policy(current, vma, addr);
	*nodemask = NULL;	/* assume !MPOL_BIND */

	if (unlikely((*mpol)->mode == MPOL_INTERLEAVE)) {
		zl = node_zonelist(interleave_nid(*mpol, vma, addr,
				huge_page_shift(hstate_vma(vma))), gfp_flags);
	} else {
		zl = policy_zonelist(gfp_flags, *mpol, numa_node_id());
		if ((*mpol)->mode == MPOL_BIND)
			*nodemask = &(*mpol)->v.nodes;
	}
	return zl;
}

/*
 * init_nodemask_of_mempolicy
 *
 * If the current task's mempolicy is "default" [NULL], return 'false'
 * to indicate default policy.  Otherwise, extract the policy nodemask
 * for 'bind' or 'interleave' policy into the argument nodemask, or
 * initialize the argument nodemask to contain the single node for
 * 'preferred' or 'local' policy and return 'true' to indicate presence
 * of non-default mempolicy.
 *
 * We don't bother with reference counting the mempolicy [mpol_get/put]
 * because the current task is examining it's own mempolicy and a task's
 * mempolicy is only ever changed by the task itself.
 *
 * N.B., it is the caller's responsibility to free a returned nodemask.
 */
bool init_nodemask_of_mempolicy(nodemask_t *mask)
{
	struct mempolicy *mempolicy;
	int nid;

	if (!(mask && current->mempolicy))
		return false;

	task_lock(current);
	mempolicy = current->mempolicy;
	switch (mempolicy->mode) {
	case MPOL_PREFERRED:
		if (mempolicy->flags & MPOL_F_LOCAL)
			nid = numa_node_id();
		else
			nid = mempolicy->v.preferred_node;
		init_nodemask_of_node(mask, nid);
		break;

	case MPOL_BIND:
		/* Fall through */
	case MPOL_INTERLEAVE:
		*mask =  mempolicy->v.nodes;
		break;

	default:
		BUG();
	}
	task_unlock(current);

	return true;
}
#endif

/*
 * mempolicy_nodemask_intersects
 *
 * If tsk's mempolicy is "default" [NULL], return 'true' to indicate default
 * policy.  Otherwise, check for intersection between mask and the policy
 * nodemask for 'bind' or 'interleave' policy.  For 'perferred' or 'local'
 * policy, always return true since it may allocate elsewhere on fallback.
 *
 * Takes task_lock(tsk) to prevent freeing of its mempolicy.
 */
bool mempolicy_nodemask_intersects(struct task_struct *tsk,
					const nodemask_t *mask)
{
	struct mempolicy *mempolicy;
	bool ret = true;

	if (!mask)
		return ret;
	task_lock(tsk);
	mempolicy = tsk->mempolicy;
	if (!mempolicy)
		goto out;

	switch (mempolicy->mode) {
	case MPOL_PREFERRED:
		/*
		 * MPOL_PREFERRED and MPOL_F_LOCAL are only preferred nodes to
		 * allocate from, they may fallback to other nodes when oom.
		 * Thus, it's possible for tsk to have allocated memory from
		 * nodes in mask.
		 */
		break;
	case MPOL_BIND:
	case MPOL_INTERLEAVE:
		ret = nodes_intersects(mempolicy->v.nodes, *mask);
		break;
	default:
		BUG();
	}
out:
	task_unlock(tsk);
	return ret;
}

/* Allocate a page in interleaved policy.
   Own path because it needs to do special accounting. */
static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
					unsigned nid)
{
	struct zonelist *zl;
	struct page *page;

	zl = node_zonelist(nid, gfp);
	page = __alloc_pages(gfp, order, zl);
	if (page && page_zone(page) == zonelist_zone(&zl->_zonerefs[0]))
		inc_zone_page_state(page, NUMA_INTERLEAVE_HIT);
	return page;
}

/**
 * 	alloc_pages_vma	- Allocate a page for a VMA.
 *
 * 	@gfp:
 *      %GFP_USER    user allocation.
 *      %GFP_KERNEL  kernel allocations,
 *      %GFP_HIGHMEM highmem/user allocations,
 *      %GFP_FS      allocation should not call back into a file system.
 *      %GFP_ATOMIC  don't sleep.
 *
 *	@order:Order of the GFP allocation.
 * 	@vma:  Pointer to VMA or NULL if not available.
 *	@addr: Virtual Address of the allocation. Must be inside the VMA.
 *
 * 	This function allocates a page from the kernel page pool and applies
 *	a NUMA policy associated with the VMA or the current process.
 *	When VMA is not NULL caller must hold down_read on the mmap_sem of the
 *	mm_struct of the VMA to prevent it from going away. Should be used for
 *	all allocations for pages that will be mapped into
 * 	user space. Returns NULL when no page can be allocated.
 *
 *	Should be called with the mm_sem of the vma hold.
 */
struct page *
alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
		unsigned long addr, int node)
{
	struct mempolicy *pol;
	struct page *page;
	unsigned int cpuset_mems_cookie;

retry_cpuset:
	pol = get_vma_policy(current, vma, addr);
	cpuset_mems_cookie = get_mems_allowed();

	if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
		unsigned nid;

		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order);
		mpol_cond_put(pol);
		page = alloc_page_interleave(gfp, order, nid);
		if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
			goto retry_cpuset;

		return page;
	}
	page = __alloc_pages_nodemask(gfp, order,
				      policy_zonelist(gfp, pol, node),
				      policy_nodemask(gfp, pol));
	if (unlikely(mpol_needs_cond_ref(pol)))
		__mpol_put(pol);
	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
		goto retry_cpuset;
	return page;
}

/**
 * 	alloc_pages_current - Allocate pages.
 *
 *	@gfp:
 *		%GFP_USER   user allocation,
 *      	%GFP_KERNEL kernel allocation,
 *      	%GFP_HIGHMEM highmem allocation,
 *      	%GFP_FS     don't call back into a file system.
 *      	%GFP_ATOMIC don't sleep.
 *	@order: Power of two of allocation size in pages. 0 is a single page.
 *
 *	Allocate a page from the kernel page pool.  When not in
 *	interrupt context and apply the current process NUMA policy.
 *	Returns NULL when no page can be allocated.
 *
 *	Don't call cpuset_update_task_memory_state() unless
 *	1) it's ok to take cpuset_sem (can WAIT), and
 *	2) allocating for current task (not interrupt).
 */
struct page *alloc_pages_current(gfp_t gfp, unsigned order)
{
	struct mempolicy *pol = get_task_policy(current);
	struct page *page;
	unsigned int cpuset_mems_cookie;

	if (!pol || in_interrupt() || (gfp & __GFP_THISNODE))
		pol = &default_policy;

retry_cpuset:
	cpuset_mems_cookie = get_mems_allowed();

	/*
	 * No reference counting needed for current->mempolicy
	 * nor system default_policy
	 */
	if (pol->mode == MPOL_INTERLEAVE)
		page = alloc_page_interleave(gfp, order, interleave_nodes(pol));
	else
		page = __alloc_pages_nodemask(gfp, order,
				policy_zonelist(gfp, pol, numa_node_id()),
				policy_nodemask(gfp, pol));

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

	return page;
}
EXPORT_SYMBOL(alloc_pages_current);

int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst)
{
	struct mempolicy *pol = mpol_dup(vma_policy(src));

	if (IS_ERR(pol))
		return PTR_ERR(pol);
	dst->vm_policy = pol;
	return 0;
}

/*
 * If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it
 * rebinds the mempolicy its copying by calling mpol_rebind_policy()
 * with the mems_allowed returned by cpuset_mems_allowed().  This
 * keeps mempolicies cpuset relative after its cpuset moves.  See
 * further kernel/cpuset.c update_nodemask().
 *
 * current's mempolicy may be rebinded by the other task(the task that changes
 * cpuset's mems), so we needn't do rebind work for current task.
 */

/* Slow path of a mempolicy duplicate */
struct mempolicy *__mpol_dup(struct mempolicy *old)
{
	struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL);

	if (!new)
		return ERR_PTR(-ENOMEM);

	/* task's mempolicy is protected by alloc_lock */
	if (old == current->mempolicy) {
		task_lock(current);
		*new = *old;
		task_unlock(current);
	} else
		*new = *old;

	rcu_read_lock();
	if (current_cpuset_is_being_rebound()) {
		nodemask_t mems = cpuset_mems_allowed(current);
		if (new->flags & MPOL_F_REBINDING)
			mpol_rebind_policy(new, &mems, MPOL_REBIND_STEP2);
		else
			mpol_rebind_policy(new, &mems, MPOL_REBIND_ONCE);
	}
	rcu_read_unlock();
	atomic_set(&new->refcnt, 1);
	return new;
}

/* Slow path of a mempolicy comparison */
bool __mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
	if (!a || !b)
		return false;
	if (a->mode != b->mode)
		return false;
	if (a->flags != b->flags)
		return false;
	if (mpol_store_user_nodemask(a))
		if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask))
			return false;

	switch (a->mode) {
	case MPOL_BIND:
		/* Fall through */
	case MPOL_INTERLEAVE:
		return !!nodes_equal(a->v.nodes, b->v.nodes);
	case MPOL_PREFERRED:
		return a->v.preferred_node == b->v.preferred_node;
	default:
		BUG();
		return false;
	}
}

/*
 * Shared memory backing store policy support.
 *
 * Remember policies even when nobody has shared memory mapped.
 * The policies are kept in Red-Black tree linked from the inode.
 * They are protected by the sp->lock spinlock, which should be held
 * for any accesses to the tree.
 */

/* lookup first element intersecting start-end */
/* Caller holds sp->lock */
static struct sp_node *
sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end)
{
	struct rb_node *n = sp->root.rb_node;

	while (n) {
		struct sp_node *p = rb_entry(n, struct sp_node, nd);

		if (start >= p->end)
			n = n->rb_right;
		else if (end <= p->start)
			n = n->rb_left;
		else
			break;
	}
	if (!n)
		return NULL;
	for (;;) {
		struct sp_node *w = NULL;
		struct rb_node *prev = rb_prev(n);
		if (!prev)
			break;
		w = rb_entry(prev, struct sp_node, nd);
		if (w->end <= start)
			break;
		n = prev;
	}
	return rb_entry(n, struct sp_node, nd);
}

/* Insert a new shared policy into the list. */
/* Caller holds sp->lock */
static void sp_insert(struct shared_policy *sp, struct sp_node *new)
{
	struct rb_node **p = &sp->root.rb_node;
	struct rb_node *parent = NULL;
	struct sp_node *nd;

	while (*p) {
		parent = *p;
		nd = rb_entry(parent, struct sp_node, nd);
		if (new->start < nd->start)
			p = &(*p)->rb_left;
		else if (new->end > nd->end)
			p = &(*p)->rb_right;
		else
			BUG();
	}
	rb_link_node(&new->nd, parent, p);
	rb_insert_color(&new->nd, &sp->root);
	pr_debug("inserting %lx-%lx: %d\n", new->start, new->end,
		 new->policy ? new->policy->mode : 0);
}

/* Find shared policy intersecting idx */
struct mempolicy *
mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx)
{
	struct mempolicy *pol = NULL;
	struct sp_node *sn;

	if (!sp->root.rb_node)
		return NULL;
	spin_lock(&sp->lock);
	sn = sp_lookup(sp, idx, idx+1);
	if (sn) {
		mpol_get(sn->policy);
		pol = sn->policy;
	}
	spin_unlock(&sp->lock);
	return pol;
}

static void sp_free(struct sp_node *n)
{
	mpol_put(n->policy);
	kmem_cache_free(sn_cache, n);
}

#ifdef CONFIG_NUMA_BALANCING
static bool numa_migrate_deferred(struct task_struct *p, int last_cpupid)
{
	/* Never defer a private fault */
	if (cpupid_match_pid(p, last_cpupid))
		return false;

	if (p->numa_migrate_deferred) {
		p->numa_migrate_deferred--;
		return true;
	}
	return false;
}

static inline void defer_numa_migrate(struct task_struct *p)
{
	p->numa_migrate_deferred = sysctl_numa_balancing_migrate_deferred;
}
#else
static inline bool numa_migrate_deferred(struct task_struct *p, int last_cpupid)
{
	return false;
}

static inline void defer_numa_migrate(struct task_struct *p)
{
}
#endif /* CONFIG_NUMA_BALANCING */

/**
 * mpol_misplaced - check whether current page node is valid in policy
 *
 * @page   - page to be checked
 * @vma    - vm area where page mapped
 * @addr   - virtual address where page mapped
 *
 * Lookup current policy node id for vma,addr and "compare to" page's
 * node id.
 *
 * Returns:
 *	-1	- not misplaced, page is in the right node
 *	node	- node id where the page should be
 *
 * Policy determination "mimics" alloc_page_vma().
 * Called from fault path where we know the vma and faulting address.
 */
int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long addr)
{
	struct mempolicy *pol;
	struct zone *zone;
	int curnid = page_to_nid(page);
	unsigned long pgoff;
	int thiscpu = raw_smp_processor_id();
	int thisnid = cpu_to_node(thiscpu);
	int polnid = -1;
	int ret = -1;

	BUG_ON(!vma);

	pol = get_vma_policy(current, vma, addr);
	if (!(pol->flags & MPOL_F_MOF))
		goto out;

	switch (pol->mode) {
	case MPOL_INTERLEAVE:
		BUG_ON(addr >= vma->vm_end);
		BUG_ON(addr < vma->vm_start);

		pgoff = vma->vm_pgoff;
		pgoff += (addr - vma->vm_start) >> PAGE_SHIFT;
		polnid = offset_il_node(pol, vma, pgoff);
		break;

	case MPOL_PREFERRED:
		if (pol->flags & MPOL_F_LOCAL)
			polnid = numa_node_id();
		else
			polnid = pol->v.preferred_node;
		break;

	case MPOL_BIND:
		/*
		 * allows binding to multiple nodes.
		 * use current page if in policy nodemask,
		 * else select nearest allowed node, if any.
		 * If no allowed nodes, use current [!misplaced].
		 */
		if (node_isset(curnid, pol->v.nodes))
			goto out;
		(void)first_zones_zonelist(
				node_zonelist(numa_node_id(), GFP_HIGHUSER),
				gfp_zone(GFP_HIGHUSER),
				&pol->v.nodes, &zone);
		polnid = zone->node;
		break;

	default:
		BUG();
	}

	/* Migrate the page towards the node whose CPU is referencing it */
	if (pol->flags & MPOL_F_MORON) {
		int last_cpupid;
		int this_cpupid;

		polnid = thisnid;
		this_cpupid = cpu_pid_to_cpupid(thiscpu, current->pid);

		/*
		 * Multi-stage node selection is used in conjunction
		 * with a periodic migration fault to build a temporal
		 * task<->page relation. By using a two-stage filter we
		 * remove short/unlikely relations.
		 *
		 * Using P(p) ~ n_p / n_t as per frequentist
		 * probability, we can equate a task's usage of a
		 * particular page (n_p) per total usage of this
		 * page (n_t) (in a given time-span) to a probability.
		 *
		 * Our periodic faults will sample this probability and
		 * getting the same result twice in a row, given these
		 * samples are fully independent, is then given by
		 * P(n)^2, provided our sample period is sufficiently
		 * short compared to the usage pattern.
		 *
		 * This quadric squishes small probabilities, making
		 * it less likely we act on an unlikely task<->page
		 * relation.
		 */
		last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
		if (!cpupid_pid_unset(last_cpupid) && cpupid_to_nid(last_cpupid) != thisnid) {

			/* See sysctl_numa_balancing_migrate_deferred comment */
			if (!cpupid_match_pid(current, last_cpupid))
				defer_numa_migrate(current);

			goto out;
		}

		/*
		 * The quadratic filter above reduces extraneous migration
		 * of shared pages somewhat. This code reduces it even more,
		 * reducing the overhead of page migrations of shared pages.
		 * This makes workloads with shared pages rely more on
		 * "move task near its memory", and less on "move memory
		 * towards its task", which is exactly what we want.
		 */
		if (numa_migrate_deferred(current, last_cpupid))
			goto out;
	}

	if (curnid != polnid)
		ret = polnid;
out:
	mpol_cond_put(pol);

	return ret;
}

static void sp_delete(struct shared_policy *sp, struct sp_node *n)
{
	pr_debug("deleting %lx-l%lx\n", n->start, n->end);
	rb_erase(&n->nd, &sp->root);
	sp_free(n);
}

static void sp_node_init(struct sp_node *node, unsigned long start,
			unsigned long end, struct mempolicy *pol)
{
	node->start = start;
	node->end = end;
	node->policy = pol;
}

static struct sp_node *sp_alloc(unsigned long start, unsigned long end,
				struct mempolicy *pol)
{
	struct sp_node *n;
	struct mempolicy *newpol;

	n = kmem_cache_alloc(sn_cache, GFP_KERNEL);
	if (!n)
		return NULL;

	newpol = mpol_dup(pol);
	if (IS_ERR(newpol)) {
		kmem_cache_free(sn_cache, n);
		return NULL;
	}
	newpol->flags |= MPOL_F_SHARED;
	sp_node_init(n, start, end, newpol);

	return n;
}

/* Replace a policy range. */
static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
				 unsigned long end, struct sp_node *new)
{
	struct sp_node *n;
	struct sp_node *n_new = NULL;
	struct mempolicy *mpol_new = NULL;
	int ret = 0;

restart:
	spin_lock(&sp->lock);
	n = sp_lookup(sp, start, end);
	/* Take care of old policies in the same range. */
	while (n && n->start < end) {
		struct rb_node *next = rb_next(&n->nd);
		if (n->start >= start) {
			if (n->end <= end)
				sp_delete(sp, n);
			else
				n->start = end;
		} else {
			/* Old policy spanning whole new range. */
			if (n->end > end) {
				if (!n_new)
					goto alloc_new;

				*mpol_new = *n->policy;
				atomic_set(&mpol_new->refcnt, 1);
				sp_node_init(n_new, end, n->end, mpol_new);
				n->end = start;
				sp_insert(sp, n_new);
				n_new = NULL;
				mpol_new = NULL;
				break;
			} else
				n->end = start;
		}
		if (!next)
			break;
		n = rb_entry(next, struct sp_node, nd);
	}
	if (new)
		sp_insert(sp, new);
	spin_unlock(&sp->lock);
	ret = 0;

err_out:
	if (mpol_new)
		mpol_put(mpol_new);
	if (n_new)
		kmem_cache_free(sn_cache, n_new);

	return ret;

alloc_new:
	spin_unlock(&sp->lock);
	ret = -ENOMEM;
	n_new = kmem_cache_alloc(sn_cache, GFP_KERNEL);
	if (!n_new)
		goto err_out;
	mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL);
	if (!mpol_new)
		goto err_out;
	goto restart;
}

/**
 * mpol_shared_policy_init - initialize shared policy for inode
 * @sp: pointer to inode shared policy
 * @mpol:  struct mempolicy to install
 *
 * Install non-NULL @mpol in inode's shared policy rb-tree.
 * On entry, the current task has a reference on a non-NULL @mpol.
 * This must be released on exit.
 * This is called at get_inode() calls and we can use GFP_KERNEL.
 */
void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
{
	int ret;

	sp->root = RB_ROOT;		/* empty tree == default mempolicy */
	spin_lock_init(&sp->lock);

	if (mpol) {
		struct vm_area_struct pvma;
		struct mempolicy *new;
		NODEMASK_SCRATCH(scratch);

		if (!scratch)
			goto put_mpol;
		/* contextualize the tmpfs mount point mempolicy */
		new = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask);
		if (IS_ERR(new))
			goto free_scratch; /* no valid nodemask intersection */

		task_lock(current);
		ret = mpol_set_nodemask(new, &mpol->w.user_nodemask, scratch);
		task_unlock(current);
		if (ret)
			goto put_new;

		/* Create pseudo-vma that contains just the policy */
		memset(&pvma, 0, sizeof(struct vm_area_struct));
		pvma.vm_end = TASK_SIZE;	/* policy covers entire file */
		mpol_set_shared_policy(sp, &pvma, new); /* adds ref */

put_new:
		mpol_put(new);			/* drop initial ref */
free_scratch:
		NODEMASK_SCRATCH_FREE(scratch);
put_mpol:
		mpol_put(mpol);	/* drop our incoming ref on sb mpol */
	}
}

int mpol_set_shared_policy(struct shared_policy *info,
			struct vm_area_struct *vma, struct mempolicy *npol)
{
	int err;
	struct sp_node *new = NULL;
	unsigned long sz = vma_pages(vma);

	pr_debug("set_shared_policy %lx sz %lu %d %d %lx\n",
		 vma->vm_pgoff,
		 sz, npol ? npol->mode : -1,
		 npol ? npol->flags : -1,
		 npol ? nodes_addr(npol->v.nodes)[0] : NUMA_NO_NODE);

	if (npol) {
		new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, npol);
		if (!new)
			return -ENOMEM;
	}
	err = shared_policy_replace(info, vma->vm_pgoff, vma->vm_pgoff+sz, new);
	if (err && new)
		sp_free(new);
	return err;
}

/* Free a backing policy store on inode delete. */
void mpol_free_shared_policy(struct shared_policy *p)
{
	struct sp_node *n;
	struct rb_node *next;

	if (!p->root.rb_node)
		return;
	spin_lock(&p->lock);
	next = rb_first(&p->root);
	while (next) {
		n = rb_entry(next, struct sp_node, nd);
		next = rb_next(&n->nd);
		sp_delete(p, n);
	}
	spin_unlock(&p->lock);
}

#ifdef CONFIG_NUMA_BALANCING
static bool __initdata numabalancing_override;

static void __init check_numabalancing_enable(void)
{
	bool numabalancing_default = false;

	if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED))
		numabalancing_default = true;

	if (nr_node_ids > 1 && !numabalancing_override) {
		printk(KERN_INFO "Enabling automatic NUMA balancing. "
			"Configure with numa_balancing= or sysctl");
		set_numabalancing_state(numabalancing_default);
	}
}

static int __init setup_numabalancing(char *str)
{
	int ret = 0;
	if (!str)
		goto out;
	numabalancing_override = true;

	if (!strcmp(str, "enable")) {
		set_numabalancing_state(true);
		ret = 1;
	} else if (!strcmp(str, "disable")) {
		set_numabalancing_state(false);
		ret = 1;
	}
out:
	if (!ret)
		printk(KERN_WARNING "Unable to parse numa_balancing=\n");

	return ret;
}
__setup("numa_balancing=", setup_numabalancing);
#else
static inline void __init check_numabalancing_enable(void)
{
}
#endif /* CONFIG_NUMA_BALANCING */

/* assumes fs == KERNEL_DS */
void __init numa_policy_init(void)
{
	nodemask_t interleave_nodes;
	unsigned long largest = 0;
	int nid, prefer = 0;

	policy_cache = kmem_cache_create("numa_policy",
					 sizeof(struct mempolicy),
					 0, SLAB_PANIC, NULL);

	sn_cache = kmem_cache_create("shared_policy_node",
				     sizeof(struct sp_node),
				     0, SLAB_PANIC, NULL);

	for_each_node(nid) {
		preferred_node_policy[nid] = (struct mempolicy) {
			.refcnt = ATOMIC_INIT(1),
			.mode = MPOL_PREFERRED,
			.flags = MPOL_F_MOF | MPOL_F_MORON,
			.v = { .preferred_node = nid, },
		};
	}

	/*
	 * Set interleaving policy for system init. Interleaving is only
	 * enabled across suitably sized nodes (default is >= 16MB), or
	 * fall back to the largest node if they're all smaller.
	 */
	nodes_clear(interleave_nodes);
	for_each_node_state(nid, N_MEMORY) {
		unsigned long total_pages = node_present_pages(nid);

		/* Preserve the largest node */
		if (largest < total_pages) {
			largest = total_pages;
			prefer = nid;
		}

		/* Interleave this node? */
		if ((total_pages << PAGE_SHIFT) >= (16 << 20))
			node_set(nid, interleave_nodes);
	}

	/* All too small, use the largest */
	if (unlikely(nodes_empty(interleave_nodes)))
		node_set(prefer, interleave_nodes);

	if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes))
		printk("numa_policy_init: interleaving failed\n");

	check_numabalancing_enable();
}

/* Reset policy of current process to default */
void numa_default_policy(void)
{
	do_set_mempolicy(MPOL_DEFAULT, 0, NULL);
}

/*
 * Parse and format mempolicy from/to strings
 */

/*
 * "local" is implemented internally by MPOL_PREFERRED with MPOL_F_LOCAL flag.
 */
static const char * const policy_modes[] =
{
	[MPOL_DEFAULT]    = "default",
	[MPOL_PREFERRED]  = "prefer",
	[MPOL_BIND]       = "bind",
	[MPOL_INTERLEAVE] = "interleave",
	[MPOL_LOCAL]      = "local",
};


#ifdef CONFIG_TMPFS
/**
 * mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option.
 * @str:  string containing mempolicy to parse
 * @mpol:  pointer to struct mempolicy pointer, returned on success.
 *
 * Format of input:
 *	<mode>[=<flags>][:<nodelist>]
 *
 * On success, returns 0, else 1
 */
int mpol_parse_str(char *str, struct mempolicy **mpol)
{
	struct mempolicy *new = NULL;
	unsigned short mode;
	unsigned short mode_flags;
	nodemask_t nodes;
	char *nodelist = strchr(str, ':');
	char *flags = strchr(str, '=');
	int err = 1;

	if (nodelist) {
		/* NUL-terminate mode or flags string */
		*nodelist++ = '\0';
		if (nodelist_parse(nodelist, nodes))
			goto out;
		if (!nodes_subset(nodes, node_states[N_MEMORY]))
			goto out;
	} else
		nodes_clear(nodes);

	if (flags)
		*flags++ = '\0';	/* terminate mode string */

	for (mode = 0; mode < MPOL_MAX; mode++) {
		if (!strcmp(str, policy_modes[mode])) {
			break;
		}
	}
	if (mode >= MPOL_MAX)
		goto out;

	switch (mode) {
	case MPOL_PREFERRED:
		/*
		 * Insist on a nodelist of one node only
		 */
		if (nodelist) {
			char *rest = nodelist;
			while (isdigit(*rest))
				rest++;
			if (*rest)
				goto out;
		}
		break;
	case MPOL_INTERLEAVE:
		/*
		 * Default to online nodes with memory if no nodelist
		 */
		if (!nodelist)
			nodes = node_states[N_MEMORY];
		break;
	case MPOL_LOCAL:
		/*
		 * Don't allow a nodelist;  mpol_new() checks flags
		 */
		if (nodelist)
			goto out;
		mode = MPOL_PREFERRED;
		break;
	case MPOL_DEFAULT:
		/*
		 * Insist on a empty nodelist
		 */
		if (!nodelist)
			err = 0;
		goto out;
	case MPOL_BIND:
		/*
		 * Insist on a nodelist
		 */
		if (!nodelist)
			goto out;
	}

	mode_flags = 0;
	if (flags) {
		/*
		 * Currently, we only support two mutually exclusive
		 * mode flags.
		 */
		if (!strcmp(flags, "static"))
			mode_flags |= MPOL_F_STATIC_NODES;
		else if (!strcmp(flags, "relative"))
			mode_flags |= MPOL_F_RELATIVE_NODES;
		else
			goto out;
	}

	new = mpol_new(mode, mode_flags, &nodes);
	if (IS_ERR(new))
		goto out;

	/*
	 * Save nodes for mpol_to_str() to show the tmpfs mount options
	 * for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo.
	 */
	if (mode != MPOL_PREFERRED)
		new->v.nodes = nodes;
	else if (nodelist)
		new->v.preferred_node = first_node(nodes);
	else
		new->flags |= MPOL_F_LOCAL;

	/*
	 * Save nodes for contextualization: this will be used to "clone"
	 * the mempolicy in a specific context [cpuset] at a later time.
	 */
	new->w.user_nodemask = nodes;

	err = 0;

out:
	/* Restore string for error message */
	if (nodelist)
		*--nodelist = ':';
	if (flags)
		*--flags = '=';
	if (!err)
		*mpol = new;
	return err;
}
#endif /* CONFIG_TMPFS */

/**
 * mpol_to_str - format a mempolicy structure for printing
 * @buffer:  to contain formatted mempolicy string
 * @maxlen:  length of @buffer
 * @pol:  pointer to mempolicy to be formatted
 *
 * Convert @pol into a string.  If @buffer is too short, truncate the string.
 * Recommend a @maxlen of at least 32 for the longest mode, "interleave", the
 * longest flag, "relative", and to display at least a few node ids.
 */
void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
{
	char *p = buffer;
	nodemask_t nodes = NODE_MASK_NONE;
	unsigned short mode = MPOL_DEFAULT;
	unsigned short flags = 0;

	if (pol && pol != &default_policy) {
		mode = pol->mode;
		flags = pol->flags;
	}

	switch (mode) {
	case MPOL_DEFAULT:
		break;
	case MPOL_PREFERRED:
		if (flags & MPOL_F_LOCAL)
			mode = MPOL_LOCAL;
		else
			node_set(pol->v.preferred_node, nodes);
		break;
	case MPOL_BIND:
	case MPOL_INTERLEAVE:
		nodes = pol->v.nodes;
		break;
	default:
		WARN_ON_ONCE(1);
		snprintf(p, maxlen, "unknown");
		return;
	}

	p += snprintf(p, maxlen, policy_modes[mode]);

	if (flags & MPOL_MODE_FLAGS) {
		p += snprintf(p, buffer + maxlen - p, "=");

		/*
		 * Currently, the only defined flags are mutually exclusive
		 */
		if (flags & MPOL_F_STATIC_NODES)
			p += snprintf(p, buffer + maxlen - p, "static");
		else if (flags & MPOL_F_RELATIVE_NODES)
			p += snprintf(p, buffer + maxlen - p, "relative");
	}

	if (!nodes_empty(nodes)) {
		p += snprintf(p, buffer + maxlen - p, ":");
	 	p += nodelist_scnprintf(p, buffer + maxlen - p, nodes);
	}
}