summaryrefslogtreecommitdiff
path: root/mm/mmap.c
blob: 3937479d0e071c0fe2884cbd371745d291067354 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
// SPDX-License-Identifier: GPL-2.0-only
/*
 * mm/mmap.c
 *
 * Written by obz.
 *
 * Address space accounting code	<alan@lxorguk.ukuu.org.uk>
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/backing-dev.h>
#include <linux/mm.h>
#include <linux/mm_inline.h>
#include <linux/shm.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/syscalls.h>
#include <linux/capability.h>
#include <linux/init.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/personality.h>
#include <linux/security.h>
#include <linux/hugetlb.h>
#include <linux/shmem_fs.h>
#include <linux/profile.h>
#include <linux/export.h>
#include <linux/mount.h>
#include <linux/mempolicy.h>
#include <linux/rmap.h>
#include <linux/mmu_notifier.h>
#include <linux/mmdebug.h>
#include <linux/perf_event.h>
#include <linux/audit.h>
#include <linux/khugepaged.h>
#include <linux/uprobes.h>
#include <linux/notifier.h>
#include <linux/memory.h>
#include <linux/printk.h>
#include <linux/userfaultfd_k.h>
#include <linux/moduleparam.h>
#include <linux/pkeys.h>
#include <linux/oom.h>
#include <linux/sched/mm.h>
#include <linux/ksm.h>

#include <linux/uaccess.h>
#include <asm/cacheflush.h>
#include <asm/tlb.h>
#include <asm/mmu_context.h>

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

#include "internal.h"

#ifndef arch_mmap_check
#define arch_mmap_check(addr, len, flags)	(0)
#endif

#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS
const int mmap_rnd_bits_min = CONFIG_ARCH_MMAP_RND_BITS_MIN;
const int mmap_rnd_bits_max = CONFIG_ARCH_MMAP_RND_BITS_MAX;
int mmap_rnd_bits __read_mostly = CONFIG_ARCH_MMAP_RND_BITS;
#endif
#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
const int mmap_rnd_compat_bits_min = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN;
const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX;
int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS;
#endif

static bool ignore_rlimit_data;
core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644);

static void unmap_region(struct mm_struct *mm, struct maple_tree *mt,
		struct vm_area_struct *vma, struct vm_area_struct *prev,
		struct vm_area_struct *next, unsigned long start,
		unsigned long end, bool mm_wr_locked);

static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags)
{
	return pgprot_modify(oldprot, vm_get_page_prot(vm_flags));
}

/* Update vma->vm_page_prot to reflect vma->vm_flags. */
void vma_set_page_prot(struct vm_area_struct *vma)
{
	unsigned long vm_flags = vma->vm_flags;
	pgprot_t vm_page_prot;

	vm_page_prot = vm_pgprot_modify(vma->vm_page_prot, vm_flags);
	if (vma_wants_writenotify(vma, vm_page_prot)) {
		vm_flags &= ~VM_SHARED;
		vm_page_prot = vm_pgprot_modify(vm_page_prot, vm_flags);
	}
	/* remove_protection_ptes reads vma->vm_page_prot without mmap_lock */
	WRITE_ONCE(vma->vm_page_prot, vm_page_prot);
}

/*
 * Requires inode->i_mapping->i_mmap_rwsem
 */
static void __remove_shared_vm_struct(struct vm_area_struct *vma,
		struct file *file, struct address_space *mapping)
{
	if (vma->vm_flags & VM_SHARED)
		mapping_unmap_writable(mapping);

	flush_dcache_mmap_lock(mapping);
	vma_interval_tree_remove(vma, &mapping->i_mmap);
	flush_dcache_mmap_unlock(mapping);
}

/*
 * Unlink a file-based vm structure from its interval tree, to hide
 * vma from rmap and vmtruncate before freeing its page tables.
 */
void unlink_file_vma(struct vm_area_struct *vma)
{
	struct file *file = vma->vm_file;

	if (file) {
		struct address_space *mapping = file->f_mapping;
		i_mmap_lock_write(mapping);
		__remove_shared_vm_struct(vma, file, mapping);
		i_mmap_unlock_write(mapping);
	}
}

/*
 * Close a vm structure and free it.
 */
static void remove_vma(struct vm_area_struct *vma, bool unreachable)
{
	might_sleep();
	if (vma->vm_ops && vma->vm_ops->close)
		vma->vm_ops->close(vma);
	if (vma->vm_file)
		fput(vma->vm_file);
	mpol_put(vma_policy(vma));
	if (unreachable)
		__vm_area_free(vma);
	else
		vm_area_free(vma);
}

static inline struct vm_area_struct *vma_prev_limit(struct vma_iterator *vmi,
						    unsigned long min)
{
	return mas_prev(&vmi->mas, min);
}

static inline int vma_iter_clear_gfp(struct vma_iterator *vmi,
			unsigned long start, unsigned long end, gfp_t gfp)
{
	vmi->mas.index = start;
	vmi->mas.last = end - 1;
	mas_store_gfp(&vmi->mas, NULL, gfp);
	if (unlikely(mas_is_err(&vmi->mas)))
		return -ENOMEM;

	return 0;
}

/*
 * check_brk_limits() - Use platform specific check of range & verify mlock
 * limits.
 * @addr: The address to check
 * @len: The size of increase.
 *
 * Return: 0 on success.
 */
static int check_brk_limits(unsigned long addr, unsigned long len)
{
	unsigned long mapped_addr;

	mapped_addr = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED);
	if (IS_ERR_VALUE(mapped_addr))
		return mapped_addr;

	return mlock_future_ok(current->mm, current->mm->def_flags, len)
		? 0 : -EAGAIN;
}
static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *brkvma,
		unsigned long addr, unsigned long request, unsigned long flags);
SYSCALL_DEFINE1(brk, unsigned long, brk)
{
	unsigned long newbrk, oldbrk, origbrk;
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *brkvma, *next = NULL;
	unsigned long min_brk;
	bool populate = false;
	LIST_HEAD(uf);
	struct vma_iterator vmi;

	if (mmap_write_lock_killable(mm))
		return -EINTR;

	origbrk = mm->brk;

#ifdef CONFIG_COMPAT_BRK
	/*
	 * CONFIG_COMPAT_BRK can still be overridden by setting
	 * randomize_va_space to 2, which will still cause mm->start_brk
	 * to be arbitrarily shifted
	 */
	if (current->brk_randomized)
		min_brk = mm->start_brk;
	else
		min_brk = mm->end_data;
#else
	min_brk = mm->start_brk;
#endif
	if (brk < min_brk)
		goto out;

	/*
	 * Check against rlimit here. If this check is done later after the test
	 * of oldbrk with newbrk then it can escape the test and let the data
	 * segment grow beyond its set limit the in case where the limit is
	 * not page aligned -Ram Gupta
	 */
	if (check_data_rlimit(rlimit(RLIMIT_DATA), brk, mm->start_brk,
			      mm->end_data, mm->start_data))
		goto out;

	newbrk = PAGE_ALIGN(brk);
	oldbrk = PAGE_ALIGN(mm->brk);
	if (oldbrk == newbrk) {
		mm->brk = brk;
		goto success;
	}

	/* Always allow shrinking brk. */
	if (brk <= mm->brk) {
		/* Search one past newbrk */
		vma_iter_init(&vmi, mm, newbrk);
		brkvma = vma_find(&vmi, oldbrk);
		if (!brkvma || brkvma->vm_start >= oldbrk)
			goto out; /* mapping intersects with an existing non-brk vma. */
		/*
		 * mm->brk must be protected by write mmap_lock.
		 * do_vma_munmap() will drop the lock on success,  so update it
		 * before calling do_vma_munmap().
		 */
		mm->brk = brk;
		if (do_vma_munmap(&vmi, brkvma, newbrk, oldbrk, &uf, true))
			goto out;

		goto success_unlocked;
	}

	if (check_brk_limits(oldbrk, newbrk - oldbrk))
		goto out;

	/*
	 * Only check if the next VMA is within the stack_guard_gap of the
	 * expansion area
	 */
	vma_iter_init(&vmi, mm, oldbrk);
	next = vma_find(&vmi, newbrk + PAGE_SIZE + stack_guard_gap);
	if (next && newbrk + PAGE_SIZE > vm_start_gap(next))
		goto out;

	brkvma = vma_prev_limit(&vmi, mm->start_brk);
	/* Ok, looks good - let it rip. */
	if (do_brk_flags(&vmi, brkvma, oldbrk, newbrk - oldbrk, 0) < 0)
		goto out;

	mm->brk = brk;
	if (mm->def_flags & VM_LOCKED)
		populate = true;

success:
	mmap_write_unlock(mm);
success_unlocked:
	userfaultfd_unmap_complete(mm, &uf);
	if (populate)
		mm_populate(oldbrk, newbrk - oldbrk);
	return brk;

out:
	mm->brk = origbrk;
	mmap_write_unlock(mm);
	return origbrk;
}

#if defined(CONFIG_DEBUG_VM_MAPLE_TREE)
static void validate_mm(struct mm_struct *mm)
{
	int bug = 0;
	int i = 0;
	struct vm_area_struct *vma;
	VMA_ITERATOR(vmi, mm, 0);

	mt_validate(&mm->mm_mt);
	for_each_vma(vmi, vma) {
#ifdef CONFIG_DEBUG_VM_RB
		struct anon_vma *anon_vma = vma->anon_vma;
		struct anon_vma_chain *avc;
#endif
		unsigned long vmi_start, vmi_end;
		bool warn = 0;

		vmi_start = vma_iter_addr(&vmi);
		vmi_end = vma_iter_end(&vmi);
		if (VM_WARN_ON_ONCE_MM(vma->vm_end != vmi_end, mm))
			warn = 1;

		if (VM_WARN_ON_ONCE_MM(vma->vm_start != vmi_start, mm))
			warn = 1;

		if (warn) {
			pr_emerg("issue in %s\n", current->comm);
			dump_stack();
			dump_vma(vma);
			pr_emerg("tree range: %px start %lx end %lx\n", vma,
				 vmi_start, vmi_end - 1);
			vma_iter_dump_tree(&vmi);
		}

#ifdef CONFIG_DEBUG_VM_RB
		if (anon_vma) {
			anon_vma_lock_read(anon_vma);
			list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
				anon_vma_interval_tree_verify(avc);
			anon_vma_unlock_read(anon_vma);
		}
#endif
		i++;
	}
	if (i != mm->map_count) {
		pr_emerg("map_count %d vma iterator %d\n", mm->map_count, i);
		bug = 1;
	}
	VM_BUG_ON_MM(bug, mm);
}

#else /* !CONFIG_DEBUG_VM_MAPLE_TREE */
#define validate_mm(mm) do { } while (0)
#endif /* CONFIG_DEBUG_VM_MAPLE_TREE */

/*
 * vma has some anon_vma assigned, and is already inserted on that
 * anon_vma's interval trees.
 *
 * Before updating the vma's vm_start / vm_end / vm_pgoff fields, the
 * vma must be removed from the anon_vma's interval trees using
 * anon_vma_interval_tree_pre_update_vma().
 *
 * After the update, the vma will be reinserted using
 * anon_vma_interval_tree_post_update_vma().
 *
 * The entire update must be protected by exclusive mmap_lock and by
 * the root anon_vma's mutex.
 */
static inline void
anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma)
{
	struct anon_vma_chain *avc;

	list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
		anon_vma_interval_tree_remove(avc, &avc->anon_vma->rb_root);
}

static inline void
anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma)
{
	struct anon_vma_chain *avc;

	list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
		anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root);
}

static unsigned long count_vma_pages_range(struct mm_struct *mm,
		unsigned long addr, unsigned long end)
{
	VMA_ITERATOR(vmi, mm, addr);
	struct vm_area_struct *vma;
	unsigned long nr_pages = 0;

	for_each_vma_range(vmi, vma, end) {
		unsigned long vm_start = max(addr, vma->vm_start);
		unsigned long vm_end = min(end, vma->vm_end);

		nr_pages += PHYS_PFN(vm_end - vm_start);
	}

	return nr_pages;
}

static void __vma_link_file(struct vm_area_struct *vma,
			    struct address_space *mapping)
{
	if (vma->vm_flags & VM_SHARED)
		mapping_allow_writable(mapping);

	flush_dcache_mmap_lock(mapping);
	vma_interval_tree_insert(vma, &mapping->i_mmap);
	flush_dcache_mmap_unlock(mapping);
}

static int vma_link(struct mm_struct *mm, struct vm_area_struct *vma)
{
	VMA_ITERATOR(vmi, mm, 0);
	struct address_space *mapping = NULL;

	if (vma_iter_prealloc(&vmi))
		return -ENOMEM;

	if (vma->vm_file) {
		mapping = vma->vm_file->f_mapping;
		i_mmap_lock_write(mapping);
	}

	vma_iter_store(&vmi, vma);

	if (mapping) {
		__vma_link_file(vma, mapping);
		i_mmap_unlock_write(mapping);
	}

	mm->map_count++;
	validate_mm(mm);
	return 0;
}

/*
 * init_multi_vma_prep() - Initializer for struct vma_prepare
 * @vp: The vma_prepare struct
 * @vma: The vma that will be altered once locked
 * @next: The next vma if it is to be adjusted
 * @remove: The first vma to be removed
 * @remove2: The second vma to be removed
 */
static inline void init_multi_vma_prep(struct vma_prepare *vp,
		struct vm_area_struct *vma, struct vm_area_struct *next,
		struct vm_area_struct *remove, struct vm_area_struct *remove2)
{
	memset(vp, 0, sizeof(struct vma_prepare));
	vp->vma = vma;
	vp->anon_vma = vma->anon_vma;
	vp->remove = remove;
	vp->remove2 = remove2;
	vp->adj_next = next;
	if (!vp->anon_vma && next)
		vp->anon_vma = next->anon_vma;

	vp->file = vma->vm_file;
	if (vp->file)
		vp->mapping = vma->vm_file->f_mapping;

}

/*
 * init_vma_prep() - Initializer wrapper for vma_prepare struct
 * @vp: The vma_prepare struct
 * @vma: The vma that will be altered once locked
 */
static inline void init_vma_prep(struct vma_prepare *vp,
				 struct vm_area_struct *vma)
{
	init_multi_vma_prep(vp, vma, NULL, NULL, NULL);
}


/*
 * vma_prepare() - Helper function for handling locking VMAs prior to altering
 * @vp: The initialized vma_prepare struct
 */
static inline void vma_prepare(struct vma_prepare *vp)
{
	vma_start_write(vp->vma);
	if (vp->adj_next)
		vma_start_write(vp->adj_next);
	/* vp->insert is always a newly created VMA, no need for locking */
	if (vp->remove)
		vma_start_write(vp->remove);
	if (vp->remove2)
		vma_start_write(vp->remove2);

	if (vp->file) {
		uprobe_munmap(vp->vma, vp->vma->vm_start, vp->vma->vm_end);

		if (vp->adj_next)
			uprobe_munmap(vp->adj_next, vp->adj_next->vm_start,
				      vp->adj_next->vm_end);

		i_mmap_lock_write(vp->mapping);
		if (vp->insert && vp->insert->vm_file) {
			/*
			 * Put into interval tree now, so instantiated pages
			 * are visible to arm/parisc __flush_dcache_page
			 * throughout; but we cannot insert into address
			 * space until vma start or end is updated.
			 */
			__vma_link_file(vp->insert,
					vp->insert->vm_file->f_mapping);
		}
	}

	if (vp->anon_vma) {
		anon_vma_lock_write(vp->anon_vma);
		anon_vma_interval_tree_pre_update_vma(vp->vma);
		if (vp->adj_next)
			anon_vma_interval_tree_pre_update_vma(vp->adj_next);
	}

	if (vp->file) {
		flush_dcache_mmap_lock(vp->mapping);
		vma_interval_tree_remove(vp->vma, &vp->mapping->i_mmap);
		if (vp->adj_next)
			vma_interval_tree_remove(vp->adj_next,
						 &vp->mapping->i_mmap);
	}

}

/*
 * vma_complete- Helper function for handling the unlocking after altering VMAs,
 * or for inserting a VMA.
 *
 * @vp: The vma_prepare struct
 * @vmi: The vma iterator
 * @mm: The mm_struct
 */
static inline void vma_complete(struct vma_prepare *vp,
				struct vma_iterator *vmi, struct mm_struct *mm)
{
	if (vp->file) {
		if (vp->adj_next)
			vma_interval_tree_insert(vp->adj_next,
						 &vp->mapping->i_mmap);
		vma_interval_tree_insert(vp->vma, &vp->mapping->i_mmap);
		flush_dcache_mmap_unlock(vp->mapping);
	}

	if (vp->remove && vp->file) {
		__remove_shared_vm_struct(vp->remove, vp->file, vp->mapping);
		if (vp->remove2)
			__remove_shared_vm_struct(vp->remove2, vp->file,
						  vp->mapping);
	} else if (vp->insert) {
		/*
		 * split_vma has split insert from vma, and needs
		 * us to insert it before dropping the locks
		 * (it may either follow vma or precede it).
		 */
		vma_iter_store(vmi, vp->insert);
		mm->map_count++;
	}

	if (vp->anon_vma) {
		anon_vma_interval_tree_post_update_vma(vp->vma);
		if (vp->adj_next)
			anon_vma_interval_tree_post_update_vma(vp->adj_next);
		anon_vma_unlock_write(vp->anon_vma);
	}

	if (vp->file) {
		i_mmap_unlock_write(vp->mapping);
		uprobe_mmap(vp->vma);

		if (vp->adj_next)
			uprobe_mmap(vp->adj_next);
	}

	if (vp->remove) {
again:
		vma_mark_detached(vp->remove, true);
		if (vp->file) {
			uprobe_munmap(vp->remove, vp->remove->vm_start,
				      vp->remove->vm_end);
			fput(vp->file);
		}
		if (vp->remove->anon_vma)
			anon_vma_merge(vp->vma, vp->remove);
		mm->map_count--;
		mpol_put(vma_policy(vp->remove));
		if (!vp->remove2)
			WARN_ON_ONCE(vp->vma->vm_end < vp->remove->vm_end);
		vm_area_free(vp->remove);

		/*
		 * In mprotect's case 6 (see comments on vma_merge),
		 * we are removing both mid and next vmas
		 */
		if (vp->remove2) {
			vp->remove = vp->remove2;
			vp->remove2 = NULL;
			goto again;
		}
	}
	if (vp->insert && vp->file)
		uprobe_mmap(vp->insert);
}

/*
 * dup_anon_vma() - Helper function to duplicate anon_vma
 * @dst: The destination VMA
 * @src: The source VMA
 *
 * Returns: 0 on success.
 */
static inline int dup_anon_vma(struct vm_area_struct *dst,
			       struct vm_area_struct *src)
{
	/*
	 * Easily overlooked: when mprotect shifts the boundary, make sure the
	 * expanding vma has anon_vma set if the shrinking vma had, to cover any
	 * anon pages imported.
	 */
	if (src->anon_vma && !dst->anon_vma) {
		vma_start_write(dst);
		dst->anon_vma = src->anon_vma;
		return anon_vma_clone(dst, src);
	}

	return 0;
}

/*
 * vma_expand - Expand an existing VMA
 *
 * @vmi: The vma iterator
 * @vma: The vma to expand
 * @start: The start of the vma
 * @end: The exclusive end of the vma
 * @pgoff: The page offset of vma
 * @next: The current of next vma.
 *
 * Expand @vma to @start and @end.  Can expand off the start and end.  Will
 * expand over @next if it's different from @vma and @end == @next->vm_end.
 * Checking if the @vma can expand and merge with @next needs to be handled by
 * the caller.
 *
 * Returns: 0 on success
 */
int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma,
	       unsigned long start, unsigned long end, pgoff_t pgoff,
	       struct vm_area_struct *next)
{
	bool remove_next = false;
	struct vma_prepare vp;

	if (next && (vma != next) && (end == next->vm_end)) {
		int ret;

		remove_next = true;
		ret = dup_anon_vma(vma, next);
		if (ret)
			return ret;
	}

	init_multi_vma_prep(&vp, vma, NULL, remove_next ? next : NULL, NULL);
	/* Not merging but overwriting any part of next is not handled. */
	VM_WARN_ON(next && !vp.remove &&
		  next != vma && end > next->vm_start);
	/* Only handles expanding */
	VM_WARN_ON(vma->vm_start < start || vma->vm_end > end);

	if (vma_iter_prealloc(vmi))
		goto nomem;

	vma_prepare(&vp);
	vma_adjust_trans_huge(vma, start, end, 0);
	/* VMA iterator points to previous, so set to start if necessary */
	if (vma_iter_addr(vmi) != start)
		vma_iter_set(vmi, start);

	vma->vm_start = start;
	vma->vm_end = end;
	vma->vm_pgoff = pgoff;
	/* Note: mas must be pointing to the expanding VMA */
	vma_iter_store(vmi, vma);

	vma_complete(&vp, vmi, vma->vm_mm);
	validate_mm(vma->vm_mm);
	return 0;

nomem:
	return -ENOMEM;
}

/*
 * vma_shrink() - Reduce an existing VMAs memory area
 * @vmi: The vma iterator
 * @vma: The VMA to modify
 * @start: The new start
 * @end: The new end
 *
 * Returns: 0 on success, -ENOMEM otherwise
 */
int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma,
	       unsigned long start, unsigned long end, pgoff_t pgoff)
{
	struct vma_prepare vp;

	WARN_ON((vma->vm_start != start) && (vma->vm_end != end));

	if (vma_iter_prealloc(vmi))
		return -ENOMEM;

	init_vma_prep(&vp, vma);
	vma_prepare(&vp);
	vma_adjust_trans_huge(vma, start, end, 0);

	if (vma->vm_start < start)
		vma_iter_clear(vmi, vma->vm_start, start);

	if (vma->vm_end > end)
		vma_iter_clear(vmi, end, vma->vm_end);

	vma->vm_start = start;
	vma->vm_end = end;
	vma->vm_pgoff = pgoff;
	vma_complete(&vp, vmi, vma->vm_mm);
	validate_mm(vma->vm_mm);
	return 0;
}

/*
 * If the vma has a ->close operation then the driver probably needs to release
 * per-vma resources, so we don't attempt to merge those if the caller indicates
 * the current vma may be removed as part of the merge.
 */
static inline bool is_mergeable_vma(struct vm_area_struct *vma,
		struct file *file, unsigned long vm_flags,
		struct vm_userfaultfd_ctx vm_userfaultfd_ctx,
		struct anon_vma_name *anon_name, bool may_remove_vma)
{
	/*
	 * VM_SOFTDIRTY should not prevent from VMA merging, if we
	 * match the flags but dirty bit -- the caller should mark
	 * merged VMA as dirty. If dirty bit won't be excluded from
	 * comparison, we increase pressure on the memory system forcing
	 * the kernel to generate new VMAs when old one could be
	 * extended instead.
	 */
	if ((vma->vm_flags ^ vm_flags) & ~VM_SOFTDIRTY)
		return false;
	if (vma->vm_file != file)
		return false;
	if (may_remove_vma && vma->vm_ops && vma->vm_ops->close)
		return false;
	if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx))
		return false;
	if (!anon_vma_name_eq(anon_vma_name(vma), anon_name))
		return false;
	return true;
}

static inline bool is_mergeable_anon_vma(struct anon_vma *anon_vma1,
		 struct anon_vma *anon_vma2, struct vm_area_struct *vma)
{
	/*
	 * The list_is_singular() test is to avoid merging VMA cloned from
	 * parents. This can improve scalability caused by anon_vma lock.
	 */
	if ((!anon_vma1 || !anon_vma2) && (!vma ||
		list_is_singular(&vma->anon_vma_chain)))
		return true;
	return anon_vma1 == anon_vma2;
}

/*
 * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff)
 * in front of (at a lower virtual address and file offset than) the vma.
 *
 * We cannot merge two vmas if they have differently assigned (non-NULL)
 * anon_vmas, nor if same anon_vma is assigned but offsets incompatible.
 *
 * We don't check here for the merged mmap wrapping around the end of pagecache
 * indices (16TB on ia32) because do_mmap() does not permit mmap's which
 * wrap, nor mmaps which cover the final page at index -1UL.
 *
 * We assume the vma may be removed as part of the merge.
 */
static bool
can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags,
		struct anon_vma *anon_vma, struct file *file,
		pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx,
		struct anon_vma_name *anon_name)
{
	if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name, true) &&
	    is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
		if (vma->vm_pgoff == vm_pgoff)
			return true;
	}
	return false;
}

/*
 * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff)
 * beyond (at a higher virtual address and file offset than) the vma.
 *
 * We cannot merge two vmas if they have differently assigned (non-NULL)
 * anon_vmas, nor if same anon_vma is assigned but offsets incompatible.
 *
 * We assume that vma is not removed as part of the merge.
 */
static bool
can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
		struct anon_vma *anon_vma, struct file *file,
		pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx,
		struct anon_vma_name *anon_name)
{
	if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name, false) &&
	    is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
		pgoff_t vm_pglen;
		vm_pglen = vma_pages(vma);
		if (vma->vm_pgoff + vm_pglen == vm_pgoff)
			return true;
	}
	return false;
}

/*
 * Given a mapping request (addr,end,vm_flags,file,pgoff,anon_name),
 * figure out whether that can be merged with its predecessor or its
 * successor.  Or both (it neatly fills a hole).
 *
 * In most cases - when called for mmap, brk or mremap - [addr,end) is
 * certain not to be mapped by the time vma_merge is called; but when
 * called for mprotect, it is certain to be already mapped (either at
 * an offset within prev, or at the start of next), and the flags of
 * this area are about to be changed to vm_flags - and the no-change
 * case has already been eliminated.
 *
 * The following mprotect cases have to be considered, where **** is
 * the area passed down from mprotect_fixup, never extending beyond one
 * vma, PPPP is the previous vma, CCCC is a concurrent vma that starts
 * at the same address as **** and is of the same or larger span, and
 * NNNN the next vma after ****:
 *
 *     ****             ****                   ****
 *    PPPPPPNNNNNN    PPPPPPNNNNNN       PPPPPPCCCCCC
 *    cannot merge    might become       might become
 *                    PPNNNNNNNNNN       PPPPPPPPPPCC
 *    mmap, brk or    case 4 below       case 5 below
 *    mremap move:
 *                        ****               ****
 *                    PPPP    NNNN       PPPPCCCCNNNN
 *                    might become       might become
 *                    PPPPPPPPPPPP 1 or  PPPPPPPPPPPP 6 or
 *                    PPPPPPPPNNNN 2 or  PPPPPPPPNNNN 7 or
 *                    PPPPNNNNNNNN 3     PPPPNNNNNNNN 8
 *
 * It is important for case 8 that the vma CCCC overlapping the
 * region **** is never going to extended over NNNN. Instead NNNN must
 * be extended in region **** and CCCC must be removed. This way in
 * all cases where vma_merge succeeds, the moment vma_merge drops the
 * rmap_locks, the properties of the merged vma will be already
 * correct for the whole merged range. Some of those properties like
 * vm_page_prot/vm_flags may be accessed by rmap_walks and they must
 * be correct for the whole merged range immediately after the
 * rmap_locks are released. Otherwise if NNNN would be removed and
 * CCCC would be extended over the NNNN range, remove_migration_ptes
 * or other rmap walkers (if working on addresses beyond the "end"
 * parameter) may establish ptes with the wrong permissions of CCCC
 * instead of the right permissions of NNNN.
 *
 * In the code below:
 * PPPP is represented by *prev
 * CCCC is represented by *curr or not represented at all (NULL)
 * NNNN is represented by *next or not represented at all (NULL)
 * **** is not represented - it will be merged and the vma containing the
 *      area is returned, or the function will return NULL
 */
struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm,
			struct vm_area_struct *prev, unsigned long addr,
			unsigned long end, unsigned long vm_flags,
			struct anon_vma *anon_vma, struct file *file,
			pgoff_t pgoff, struct mempolicy *policy,
			struct vm_userfaultfd_ctx vm_userfaultfd_ctx,
			struct anon_vma_name *anon_name)
{
	struct vm_area_struct *curr, *next, *res;
	struct vm_area_struct *vma, *adjust, *remove, *remove2;
	struct vma_prepare vp;
	pgoff_t vma_pgoff;
	int err = 0;
	bool merge_prev = false;
	bool merge_next = false;
	bool vma_expanded = false;
	unsigned long vma_start = addr;
	unsigned long vma_end = end;
	pgoff_t pglen = (end - addr) >> PAGE_SHIFT;
	long adj_start = 0;

	validate_mm(mm);
	/*
	 * We later require that vma->vm_flags == vm_flags,
	 * so this tests vma->vm_flags & VM_SPECIAL, too.
	 */
	if (vm_flags & VM_SPECIAL)
		return NULL;

	/* Does the input range span an existing VMA? (cases 5 - 8) */
	curr = find_vma_intersection(mm, prev ? prev->vm_end : 0, end);

	if (!curr ||			/* cases 1 - 4 */
	    end == curr->vm_end)	/* cases 6 - 8, adjacent VMA */
		next = vma_lookup(mm, end);
	else
		next = NULL;		/* case 5 */

	if (prev) {
		vma_start = prev->vm_start;
		vma_pgoff = prev->vm_pgoff;

		/* Can we merge the predecessor? */
		if (addr == prev->vm_end && mpol_equal(vma_policy(prev), policy)
		    && can_vma_merge_after(prev, vm_flags, anon_vma, file,
					   pgoff, vm_userfaultfd_ctx, anon_name)) {
			merge_prev = true;
			vma_prev(vmi);
		}
	}

	/* Can we merge the successor? */
	if (next && mpol_equal(policy, vma_policy(next)) &&
	    can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen,
				 vm_userfaultfd_ctx, anon_name)) {
		merge_next = true;
	}

	/* Verify some invariant that must be enforced by the caller. */
	VM_WARN_ON(prev && addr <= prev->vm_start);
	VM_WARN_ON(curr && (addr != curr->vm_start || end > curr->vm_end));
	VM_WARN_ON(addr >= end);

	if (!merge_prev && !merge_next)
		return NULL; /* Not mergeable. */

	res = vma = prev;
	remove = remove2 = adjust = NULL;

	/* Can we merge both the predecessor and the successor? */
	if (merge_prev && merge_next &&
	    is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) {
		remove = next;				/* case 1 */
		vma_end = next->vm_end;
		err = dup_anon_vma(prev, next);
		if (curr) {				/* case 6 */
			remove = curr;
			remove2 = next;
			if (!next->anon_vma)
				err = dup_anon_vma(prev, curr);
		}
	} else if (merge_prev) {			/* case 2 */
		if (curr) {
			err = dup_anon_vma(prev, curr);
			if (end == curr->vm_end) {	/* case 7 */
				remove = curr;
			} else {			/* case 5 */
				adjust = curr;
				adj_start = (end - curr->vm_start);
			}
		}
	} else { /* merge_next */
		res = next;
		if (prev && addr < prev->vm_end) {	/* case 4 */
			vma_end = addr;
			adjust = next;
			adj_start = -(prev->vm_end - addr);
			err = dup_anon_vma(next, prev);
		} else {
			/*
			 * Note that cases 3 and 8 are the ONLY ones where prev
			 * is permitted to be (but is not necessarily) NULL.
			 */
			vma = next;			/* case 3 */
			vma_start = addr;
			vma_end = next->vm_end;
			vma_pgoff = next->vm_pgoff - pglen;
			if (curr) {			/* case 8 */
				vma_pgoff = curr->vm_pgoff;
				remove = curr;
				err = dup_anon_vma(next, curr);
			}
		}
	}

	/* Error in anon_vma clone. */
	if (err)
		return NULL;

	if (vma_iter_prealloc(vmi))
		return NULL;

	init_multi_vma_prep(&vp, vma, adjust, remove, remove2);
	VM_WARN_ON(vp.anon_vma && adjust && adjust->anon_vma &&
		   vp.anon_vma != adjust->anon_vma);

	vma_prepare(&vp);
	vma_adjust_trans_huge(vma, vma_start, vma_end, adj_start);
	if (vma_start < vma->vm_start || vma_end > vma->vm_end)
		vma_expanded = true;

	vma->vm_start = vma_start;
	vma->vm_end = vma_end;
	vma->vm_pgoff = vma_pgoff;

	if (vma_expanded)
		vma_iter_store(vmi, vma);

	if (adj_start) {
		adjust->vm_start += adj_start;
		adjust->vm_pgoff += adj_start >> PAGE_SHIFT;
		if (adj_start < 0) {
			WARN_ON(vma_expanded);
			vma_iter_store(vmi, next);
		}
	}

	vma_complete(&vp, vmi, mm);
	vma_iter_free(vmi);
	validate_mm(mm);
	khugepaged_enter_vma(res, vm_flags);

	return res;
}

/*
 * Rough compatibility check to quickly see if it's even worth looking
 * at sharing an anon_vma.
 *
 * They need to have the same vm_file, and the flags can only differ
 * in things that mprotect may change.
 *
 * NOTE! The fact that we share an anon_vma doesn't _have_ to mean that
 * we can merge the two vma's. For example, we refuse to merge a vma if
 * there is a vm_ops->close() function, because that indicates that the
 * driver is doing some kind of reference counting. But that doesn't
 * really matter for the anon_vma sharing case.
 */
static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *b)
{
	return a->vm_end == b->vm_start &&
		mpol_equal(vma_policy(a), vma_policy(b)) &&
		a->vm_file == b->vm_file &&
		!((a->vm_flags ^ b->vm_flags) & ~(VM_ACCESS_FLAGS | VM_SOFTDIRTY)) &&
		b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT);
}

/*
 * Do some basic sanity checking to see if we can re-use the anon_vma
 * from 'old'. The 'a'/'b' vma's are in VM order - one of them will be
 * the same as 'old', the other will be the new one that is trying
 * to share the anon_vma.
 *
 * NOTE! This runs with mmap_lock held for reading, so it is possible that
 * the anon_vma of 'old' is concurrently in the process of being set up
 * by another page fault trying to merge _that_. But that's ok: if it
 * is being set up, that automatically means that it will be a singleton
 * acceptable for merging, so we can do all of this optimistically. But
 * we do that READ_ONCE() to make sure that we never re-load the pointer.
 *
 * IOW: that the "list_is_singular()" test on the anon_vma_chain only
 * matters for the 'stable anon_vma' case (ie the thing we want to avoid
 * is to return an anon_vma that is "complex" due to having gone through
 * a fork).
 *
 * We also make sure that the two vma's are compatible (adjacent,
 * and with the same memory policies). That's all stable, even with just
 * a read lock on the mmap_lock.
 */
static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b)
{
	if (anon_vma_compatible(a, b)) {
		struct anon_vma *anon_vma = READ_ONCE(old->anon_vma);

		if (anon_vma && list_is_singular(&old->anon_vma_chain))
			return anon_vma;
	}
	return NULL;
}

/*
 * find_mergeable_anon_vma is used by anon_vma_prepare, to check
 * neighbouring vmas for a suitable anon_vma, before it goes off
 * to allocate a new anon_vma.  It checks because a repetitive
 * sequence of mprotects and faults may otherwise lead to distinct
 * anon_vmas being allocated, preventing vma merge in subsequent
 * mprotect.
 */
struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma)
{
	MA_STATE(mas, &vma->vm_mm->mm_mt, vma->vm_end, vma->vm_end);
	struct anon_vma *anon_vma = NULL;
	struct vm_area_struct *prev, *next;

	/* Try next first. */
	next = mas_walk(&mas);
	if (next) {
		anon_vma = reusable_anon_vma(next, vma, next);
		if (anon_vma)
			return anon_vma;
	}

	prev = mas_prev(&mas, 0);
	VM_BUG_ON_VMA(prev != vma, vma);
	prev = mas_prev(&mas, 0);
	/* Try prev next. */
	if (prev)
		anon_vma = reusable_anon_vma(prev, prev, vma);

	/*
	 * We might reach here with anon_vma == NULL if we can't find
	 * any reusable anon_vma.
	 * There's no absolute need to look only at touching neighbours:
	 * we could search further afield for "compatible" anon_vmas.
	 * But it would probably just be a waste of time searching,
	 * or lead to too many vmas hanging off the same anon_vma.
	 * We're trying to allow mprotect remerging later on,
	 * not trying to minimize memory used for anon_vmas.
	 */
	return anon_vma;
}

/*
 * If a hint addr is less than mmap_min_addr change hint to be as
 * low as possible but still greater than mmap_min_addr
 */
static inline unsigned long round_hint_to_min(unsigned long hint)
{
	hint &= PAGE_MASK;
	if (((void *)hint != NULL) &&
	    (hint < mmap_min_addr))
		return PAGE_ALIGN(mmap_min_addr);
	return hint;
}

bool mlock_future_ok(struct mm_struct *mm, unsigned long flags,
			unsigned long bytes)
{
	unsigned long locked_pages, limit_pages;

	if (!(flags & VM_LOCKED) || capable(CAP_IPC_LOCK))
		return true;

	locked_pages = bytes >> PAGE_SHIFT;
	locked_pages += mm->locked_vm;

	limit_pages = rlimit(RLIMIT_MEMLOCK);
	limit_pages >>= PAGE_SHIFT;

	return locked_pages <= limit_pages;
}

static inline u64 file_mmap_size_max(struct file *file, struct inode *inode)
{
	if (S_ISREG(inode->i_mode))
		return MAX_LFS_FILESIZE;

	if (S_ISBLK(inode->i_mode))
		return MAX_LFS_FILESIZE;

	if (S_ISSOCK(inode->i_mode))
		return MAX_LFS_FILESIZE;

	/* Special "we do even unsigned file positions" case */
	if (file->f_mode & FMODE_UNSIGNED_OFFSET)
		return 0;

	/* Yes, random drivers might want more. But I'm tired of buggy drivers */
	return ULONG_MAX;
}

static inline bool file_mmap_ok(struct file *file, struct inode *inode,
				unsigned long pgoff, unsigned long len)
{
	u64 maxsize = file_mmap_size_max(file, inode);

	if (maxsize && len > maxsize)
		return false;
	maxsize -= len;
	if (pgoff > maxsize >> PAGE_SHIFT)
		return false;
	return true;
}

/*
 * The caller must write-lock current->mm->mmap_lock.
 */
unsigned long do_mmap(struct file *file, unsigned long addr,
			unsigned long len, unsigned long prot,
			unsigned long flags, unsigned long pgoff,
			unsigned long *populate, struct list_head *uf)
{
	struct mm_struct *mm = current->mm;
	vm_flags_t vm_flags;
	int pkey = 0;

	validate_mm(mm);
	*populate = 0;

	if (!len)
		return -EINVAL;

	/*
	 * Does the application expect PROT_READ to imply PROT_EXEC?
	 *
	 * (the exception is when the underlying filesystem is noexec
	 *  mounted, in which case we dont add PROT_EXEC.)
	 */
	if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC))
		if (!(file && path_noexec(&file->f_path)))
			prot |= PROT_EXEC;

	/* force arch specific MAP_FIXED handling in get_unmapped_area */
	if (flags & MAP_FIXED_NOREPLACE)
		flags |= MAP_FIXED;

	if (!(flags & MAP_FIXED))
		addr = round_hint_to_min(addr);

	/* Careful about overflows.. */
	len = PAGE_ALIGN(len);
	if (!len)
		return -ENOMEM;

	/* offset overflow? */
	if ((pgoff + (len >> PAGE_SHIFT)) < pgoff)
		return -EOVERFLOW;

	/* Too many mappings? */
	if (mm->map_count > sysctl_max_map_count)
		return -ENOMEM;

	/* Obtain the address to map to. we verify (or select) it and ensure
	 * that it represents a valid section of the address space.
	 */
	addr = get_unmapped_area(file, addr, len, pgoff, flags);
	if (IS_ERR_VALUE(addr))
		return addr;

	if (flags & MAP_FIXED_NOREPLACE) {
		if (find_vma_intersection(mm, addr, addr + len))
			return -EEXIST;
	}

	if (prot == PROT_EXEC) {
		pkey = execute_only_pkey(mm);
		if (pkey < 0)
			pkey = 0;
	}

	/* Do simple checking here so the lower-level routines won't have
	 * to. we assume access permissions have been handled by the open
	 * of the memory object, so we don't do any here.
	 */
	vm_flags = calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(flags) |
			mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;

	if (flags & MAP_LOCKED)
		if (!can_do_mlock())
			return -EPERM;

	if (!mlock_future_ok(mm, vm_flags, len))
		return -EAGAIN;

	if (file) {
		struct inode *inode = file_inode(file);
		unsigned long flags_mask;

		if (!file_mmap_ok(file, inode, pgoff, len))
			return -EOVERFLOW;

		flags_mask = LEGACY_MAP_MASK | file->f_op->mmap_supported_flags;

		switch (flags & MAP_TYPE) {
		case MAP_SHARED:
			/*
			 * Force use of MAP_SHARED_VALIDATE with non-legacy
			 * flags. E.g. MAP_SYNC is dangerous to use with
			 * MAP_SHARED as you don't know which consistency model
			 * you will get. We silently ignore unsupported flags
			 * with MAP_SHARED to preserve backward compatibility.
			 */
			flags &= LEGACY_MAP_MASK;
			fallthrough;
		case MAP_SHARED_VALIDATE:
			if (flags & ~flags_mask)
				return -EOPNOTSUPP;
			if (prot & PROT_WRITE) {
				if (!(file->f_mode & FMODE_WRITE))
					return -EACCES;
				if (IS_SWAPFILE(file->f_mapping->host))
					return -ETXTBSY;
			}

			/*
			 * Make sure we don't allow writing to an append-only
			 * file..
			 */
			if (IS_APPEND(inode) && (file->f_mode & FMODE_WRITE))
				return -EACCES;

			vm_flags |= VM_SHARED | VM_MAYSHARE;
			if (!(file->f_mode & FMODE_WRITE))
				vm_flags &= ~(VM_MAYWRITE | VM_SHARED);
			fallthrough;
		case MAP_PRIVATE:
			if (!(file->f_mode & FMODE_READ))
				return -EACCES;
			if (path_noexec(&file->f_path)) {
				if (vm_flags & VM_EXEC)
					return -EPERM;
				vm_flags &= ~VM_MAYEXEC;
			}

			if (!file->f_op->mmap)
				return -ENODEV;
			if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
				return -EINVAL;
			break;

		default:
			return -EINVAL;
		}
	} else {
		switch (flags & MAP_TYPE) {
		case MAP_SHARED:
			if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
				return -EINVAL;
			/*
			 * Ignore pgoff.
			 */
			pgoff = 0;
			vm_flags |= VM_SHARED | VM_MAYSHARE;
			break;
		case MAP_PRIVATE:
			/*
			 * Set pgoff according to addr for anon_vma.
			 */
			pgoff = addr >> PAGE_SHIFT;
			break;
		default:
			return -EINVAL;
		}
	}

	/*
	 * Set 'VM_NORESERVE' if we should not account for the
	 * memory use of this mapping.
	 */
	if (flags & MAP_NORESERVE) {
		/* We honor MAP_NORESERVE if allowed to overcommit */
		if (sysctl_overcommit_memory != OVERCOMMIT_NEVER)
			vm_flags |= VM_NORESERVE;

		/* hugetlb applies strict overcommit unless MAP_NORESERVE */
		if (file && is_file_hugepages(file))
			vm_flags |= VM_NORESERVE;
	}

	addr = mmap_region(file, addr, len, vm_flags, pgoff, uf);
	if (!IS_ERR_VALUE(addr) &&
	    ((vm_flags & VM_LOCKED) ||
	     (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE))
		*populate = len;
	return addr;
}

unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len,
			      unsigned long prot, unsigned long flags,
			      unsigned long fd, unsigned long pgoff)
{
	struct file *file = NULL;
	unsigned long retval;

	if (!(flags & MAP_ANONYMOUS)) {
		audit_mmap_fd(fd, flags);
		file = fget(fd);
		if (!file)
			return -EBADF;
		if (is_file_hugepages(file)) {
			len = ALIGN(len, huge_page_size(hstate_file(file)));
		} else if (unlikely(flags & MAP_HUGETLB)) {
			retval = -EINVAL;
			goto out_fput;
		}
	} else if (flags & MAP_HUGETLB) {
		struct hstate *hs;

		hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK);
		if (!hs)
			return -EINVAL;

		len = ALIGN(len, huge_page_size(hs));
		/*
		 * VM_NORESERVE is used because the reservations will be
		 * taken when vm_ops->mmap() is called
		 */
		file = hugetlb_file_setup(HUGETLB_ANON_FILE, len,
				VM_NORESERVE,
				HUGETLB_ANONHUGE_INODE,
				(flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK);
		if (IS_ERR(file))
			return PTR_ERR(file);
	}

	retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff);
out_fput:
	if (file)
		fput(file);
	return retval;
}

SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
		unsigned long, prot, unsigned long, flags,
		unsigned long, fd, unsigned long, pgoff)
{
	return ksys_mmap_pgoff(addr, len, prot, flags, fd, pgoff);
}

#ifdef __ARCH_WANT_SYS_OLD_MMAP
struct mmap_arg_struct {
	unsigned long addr;
	unsigned long len;
	unsigned long prot;
	unsigned long flags;
	unsigned long fd;
	unsigned long offset;
};

SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
{
	struct mmap_arg_struct a;

	if (copy_from_user(&a, arg, sizeof(a)))
		return -EFAULT;
	if (offset_in_page(a.offset))
		return -EINVAL;

	return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
			       a.offset >> PAGE_SHIFT);
}
#endif /* __ARCH_WANT_SYS_OLD_MMAP */

static bool vm_ops_needs_writenotify(const struct vm_operations_struct *vm_ops)
{
	return vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite);
}

static bool vma_is_shared_writable(struct vm_area_struct *vma)
{
	return (vma->vm_flags & (VM_WRITE | VM_SHARED)) ==
		(VM_WRITE | VM_SHARED);
}

static bool vma_fs_can_writeback(struct vm_area_struct *vma)
{
	/* No managed pages to writeback. */
	if (vma->vm_flags & VM_PFNMAP)
		return false;

	return vma->vm_file && vma->vm_file->f_mapping &&
		mapping_can_writeback(vma->vm_file->f_mapping);
}

/*
 * Does this VMA require the underlying folios to have their dirty state
 * tracked?
 */
bool vma_needs_dirty_tracking(struct vm_area_struct *vma)
{
	/* Only shared, writable VMAs require dirty tracking. */
	if (!vma_is_shared_writable(vma))
		return false;

	/* Does the filesystem need to be notified? */
	if (vm_ops_needs_writenotify(vma->vm_ops))
		return true;

	/*
	 * Even if the filesystem doesn't indicate a need for writenotify, if it
	 * can writeback, dirty tracking is still required.
	 */
	return vma_fs_can_writeback(vma);
}

/*
 * Some shared mappings will want the pages marked read-only
 * to track write events. If so, we'll downgrade vm_page_prot
 * to the private version (using protection_map[] without the
 * VM_SHARED bit).
 */
int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot)
{
	/* If it was private or non-writable, the write bit is already clear */
	if (!vma_is_shared_writable(vma))
		return 0;

	/* The backer wishes to know when pages are first written to? */
	if (vm_ops_needs_writenotify(vma->vm_ops))
		return 1;

	/* The open routine did something to the protections that pgprot_modify
	 * won't preserve? */
	if (pgprot_val(vm_page_prot) !=
	    pgprot_val(vm_pgprot_modify(vm_page_prot, vma->vm_flags)))
		return 0;

	/*
	 * Do we need to track softdirty? hugetlb does not support softdirty
	 * tracking yet.
	 */
	if (vma_soft_dirty_enabled(vma) && !is_vm_hugetlb_page(vma))
		return 1;

	/* Do we need write faults for uffd-wp tracking? */
	if (userfaultfd_wp(vma))
		return 1;

	/* Can the mapping track the dirty pages? */
	return vma_fs_can_writeback(vma);
}

/*
 * We account for memory if it's a private writeable mapping,
 * not hugepages and VM_NORESERVE wasn't set.
 */
static inline int accountable_mapping(struct file *file, vm_flags_t vm_flags)
{
	/*
	 * hugetlb has its own accounting separate from the core VM
	 * VM_HUGETLB may not be set yet so we cannot check for that flag.
	 */
	if (file && is_file_hugepages(file))
		return 0;

	return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE;
}

/**
 * unmapped_area() - Find an area between the low_limit and the high_limit with
 * the correct alignment and offset, all from @info. Note: current->mm is used
 * for the search.
 *
 * @info: The unmapped area information including the range [low_limit -
 * high_limit), the alignment offset and mask.
 *
 * Return: A memory address or -ENOMEM.
 */
static unsigned long unmapped_area(struct vm_unmapped_area_info *info)
{
	unsigned long length, gap;
	unsigned long low_limit, high_limit;
	struct vm_area_struct *tmp;

	MA_STATE(mas, &current->mm->mm_mt, 0, 0);

	/* Adjust search length to account for worst case alignment overhead */
	length = info->length + info->align_mask;
	if (length < info->length)
		return -ENOMEM;

	low_limit = info->low_limit;
	if (low_limit < mmap_min_addr)
		low_limit = mmap_min_addr;
	high_limit = info->high_limit;
retry:
	if (mas_empty_area(&mas, low_limit, high_limit - 1, length))
		return -ENOMEM;

	gap = mas.index;
	gap += (info->align_offset - gap) & info->align_mask;
	tmp = mas_next(&mas, ULONG_MAX);
	if (tmp && (tmp->vm_flags & VM_GROWSDOWN)) { /* Avoid prev check if possible */
		if (vm_start_gap(tmp) < gap + length - 1) {
			low_limit = tmp->vm_end;
			mas_reset(&mas);
			goto retry;
		}
	} else {
		tmp = mas_prev(&mas, 0);
		if (tmp && vm_end_gap(tmp) > gap) {
			low_limit = vm_end_gap(tmp);
			mas_reset(&mas);
			goto retry;
		}
	}

	return gap;
}

/**
 * unmapped_area_topdown() - Find an area between the low_limit and the
 * high_limit with the correct alignment and offset at the highest available
 * address, all from @info. Note: current->mm is used for the search.
 *
 * @info: The unmapped area information including the range [low_limit -
 * high_limit), the alignment offset and mask.
 *
 * Return: A memory address or -ENOMEM.
 */
static unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info)
{
	unsigned long length, gap, gap_end;
	unsigned long low_limit, high_limit;
	struct vm_area_struct *tmp;

	MA_STATE(mas, &current->mm->mm_mt, 0, 0);
	/* Adjust search length to account for worst case alignment overhead */
	length = info->length + info->align_mask;
	if (length < info->length)
		return -ENOMEM;

	low_limit = info->low_limit;
	if (low_limit < mmap_min_addr)
		low_limit = mmap_min_addr;
	high_limit = info->high_limit;
retry:
	if (mas_empty_area_rev(&mas, low_limit, high_limit - 1, length))
		return -ENOMEM;

	gap = mas.last + 1 - info->length;
	gap -= (gap - info->align_offset) & info->align_mask;
	gap_end = mas.last;
	tmp = mas_next(&mas, ULONG_MAX);
	if (tmp && (tmp->vm_flags & VM_GROWSDOWN)) { /* Avoid prev check if possible */
		if (vm_start_gap(tmp) <= gap_end) {
			high_limit = vm_start_gap(tmp);
			mas_reset(&mas);
			goto retry;
		}
	} else {
		tmp = mas_prev(&mas, 0);
		if (tmp && vm_end_gap(tmp) > gap) {
			high_limit = tmp->vm_start;
			mas_reset(&mas);
			goto retry;
		}
	}

	return gap;
}

/*
 * Search for an unmapped address range.
 *
 * We are looking for a range that:
 * - does not intersect with any VMA;
 * - is contained within the [low_limit, high_limit) interval;
 * - is at least the desired size.
 * - satisfies (begin_addr & align_mask) == (align_offset & align_mask)
 */
unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info)
{
	unsigned long addr;

	if (info->flags & VM_UNMAPPED_AREA_TOPDOWN)
		addr = unmapped_area_topdown(info);
	else
		addr = unmapped_area(info);

	trace_vm_unmapped_area(addr, info);
	return addr;
}

/* Get an address range which is currently unmapped.
 * For shmat() with addr=0.
 *
 * Ugly calling convention alert:
 * Return value with the low bits set means error value,
 * ie
 *	if (ret & ~PAGE_MASK)
 *		error = ret;
 *
 * This function "knows" that -ENOMEM has the bits set.
 */
unsigned long
generic_get_unmapped_area(struct file *filp, unsigned long addr,
			  unsigned long len, unsigned long pgoff,
			  unsigned long flags)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma, *prev;
	struct vm_unmapped_area_info info;
	const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags);

	if (len > mmap_end - mmap_min_addr)
		return -ENOMEM;

	if (flags & MAP_FIXED)
		return addr;

	if (addr) {
		addr = PAGE_ALIGN(addr);
		vma = find_vma_prev(mm, addr, &prev);
		if (mmap_end - len >= addr && addr >= mmap_min_addr &&
		    (!vma || addr + len <= vm_start_gap(vma)) &&
		    (!prev || addr >= vm_end_gap(prev)))
			return addr;
	}

	info.flags = 0;
	info.length = len;
	info.low_limit = mm->mmap_base;
	info.high_limit = mmap_end;
	info.align_mask = 0;
	info.align_offset = 0;
	return vm_unmapped_area(&info);
}

#ifndef HAVE_ARCH_UNMAPPED_AREA
unsigned long
arch_get_unmapped_area(struct file *filp, unsigned long addr,
		       unsigned long len, unsigned long pgoff,
		       unsigned long flags)
{
	return generic_get_unmapped_area(filp, addr, len, pgoff, flags);
}
#endif

/*
 * This mmap-allocator allocates new areas top-down from below the
 * stack's low limit (the base):
 */
unsigned long
generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
				  unsigned long len, unsigned long pgoff,
				  unsigned long flags)
{
	struct vm_area_struct *vma, *prev;
	struct mm_struct *mm = current->mm;
	struct vm_unmapped_area_info info;
	const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags);

	/* requested length too big for entire address space */
	if (len > mmap_end - mmap_min_addr)
		return -ENOMEM;

	if (flags & MAP_FIXED)
		return addr;

	/* requesting a specific address */
	if (addr) {
		addr = PAGE_ALIGN(addr);
		vma = find_vma_prev(mm, addr, &prev);
		if (mmap_end - len >= addr && addr >= mmap_min_addr &&
				(!vma || addr + len <= vm_start_gap(vma)) &&
				(!prev || addr >= vm_end_gap(prev)))
			return addr;
	}

	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
	info.length = len;
	info.low_limit = PAGE_SIZE;
	info.high_limit = arch_get_mmap_base(addr, mm->mmap_base);
	info.align_mask = 0;
	info.align_offset = 0;
	addr = vm_unmapped_area(&info);

	/*
	 * A failed mmap() very likely causes application failure,
	 * so fall back to the bottom-up function here. This scenario
	 * can happen with large stack limits and large mmap()
	 * allocations.
	 */
	if (offset_in_page(addr)) {
		VM_BUG_ON(addr != -ENOMEM);
		info.flags = 0;
		info.low_limit = TASK_UNMAPPED_BASE;
		info.high_limit = mmap_end;
		addr = vm_unmapped_area(&info);
	}

	return addr;
}

#ifndef HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
unsigned long
arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
			       unsigned long len, unsigned long pgoff,
			       unsigned long flags)
{
	return generic_get_unmapped_area_topdown(filp, addr, len, pgoff, flags);
}
#endif

unsigned long
get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
		unsigned long pgoff, unsigned long flags)
{
	unsigned long (*get_area)(struct file *, unsigned long,
				  unsigned long, unsigned long, unsigned long);

	unsigned long error = arch_mmap_check(addr, len, flags);
	if (error)
		return error;

	/* Careful about overflows.. */
	if (len > TASK_SIZE)
		return -ENOMEM;

	get_area = current->mm->get_unmapped_area;
	if (file) {
		if (file->f_op->get_unmapped_area)
			get_area = file->f_op->get_unmapped_area;
	} else if (flags & MAP_SHARED) {
		/*
		 * mmap_region() will call shmem_zero_setup() to create a file,
		 * so use shmem's get_unmapped_area in case it can be huge.
		 * do_mmap() will clear pgoff, so match alignment.
		 */
		pgoff = 0;
		get_area = shmem_get_unmapped_area;
	}

	addr = get_area(file, addr, len, pgoff, flags);
	if (IS_ERR_VALUE(addr))
		return addr;

	if (addr > TASK_SIZE - len)
		return -ENOMEM;
	if (offset_in_page(addr))
		return -EINVAL;

	error = security_mmap_addr(addr);
	return error ? error : addr;
}

EXPORT_SYMBOL(get_unmapped_area);

/**
 * find_vma_intersection() - Look up the first VMA which intersects the interval
 * @mm: The process address space.
 * @start_addr: The inclusive start user address.
 * @end_addr: The exclusive end user address.
 *
 * Returns: The first VMA within the provided range, %NULL otherwise.  Assumes
 * start_addr < end_addr.
 */
struct vm_area_struct *find_vma_intersection(struct mm_struct *mm,
					     unsigned long start_addr,
					     unsigned long end_addr)
{
	unsigned long index = start_addr;

	mmap_assert_locked(mm);
	return mt_find(&mm->mm_mt, &index, end_addr - 1);
}
EXPORT_SYMBOL(find_vma_intersection);

/**
 * find_vma() - Find the VMA for a given address, or the next VMA.
 * @mm: The mm_struct to check
 * @addr: The address
 *
 * Returns: The VMA associated with addr, or the next VMA.
 * May return %NULL in the case of no VMA at addr or above.
 */
struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
{
	unsigned long index = addr;

	mmap_assert_locked(mm);
	return mt_find(&mm->mm_mt, &index, ULONG_MAX);
}
EXPORT_SYMBOL(find_vma);

/**
 * find_vma_prev() - Find the VMA for a given address, or the next vma and
 * set %pprev to the previous VMA, if any.
 * @mm: The mm_struct to check
 * @addr: The address
 * @pprev: The pointer to set to the previous VMA
 *
 * Note that RCU lock is missing here since the external mmap_lock() is used
 * instead.
 *
 * Returns: The VMA associated with @addr, or the next vma.
 * May return %NULL in the case of no vma at addr or above.
 */
struct vm_area_struct *
find_vma_prev(struct mm_struct *mm, unsigned long addr,
			struct vm_area_struct **pprev)
{
	struct vm_area_struct *vma;
	MA_STATE(mas, &mm->mm_mt, addr, addr);

	vma = mas_walk(&mas);
	*pprev = mas_prev(&mas, 0);
	if (!vma)
		vma = mas_next(&mas, ULONG_MAX);
	return vma;
}

/*
 * Verify that the stack growth is acceptable and
 * update accounting. This is shared with both the
 * grow-up and grow-down cases.
 */
static int acct_stack_growth(struct vm_area_struct *vma,
			     unsigned long size, unsigned long grow)
{
	struct mm_struct *mm = vma->vm_mm;
	unsigned long new_start;

	/* address space limit tests */
	if (!may_expand_vm(mm, vma->vm_flags, grow))
		return -ENOMEM;

	/* Stack limit test */
	if (size > rlimit(RLIMIT_STACK))
		return -ENOMEM;

	/* mlock limit tests */
	if (!mlock_future_ok(mm, vma->vm_flags, grow << PAGE_SHIFT))
		return -ENOMEM;

	/* Check to ensure the stack will not grow into a hugetlb-only region */
	new_start = (vma->vm_flags & VM_GROWSUP) ? vma->vm_start :
			vma->vm_end - size;
	if (is_hugepage_only_range(vma->vm_mm, new_start, size))
		return -EFAULT;

	/*
	 * Overcommit..  This must be the final test, as it will
	 * update security statistics.
	 */
	if (security_vm_enough_memory_mm(mm, grow))
		return -ENOMEM;

	return 0;
}

#if defined(CONFIG_STACK_GROWSUP) || defined(CONFIG_IA64)
/*
 * PA-RISC uses this for its stack; IA64 for its Register Backing Store.
 * vma is the last one with address > vma->vm_end.  Have to extend vma.
 */
static int expand_upwards(struct vm_area_struct *vma, unsigned long address)
{
	struct mm_struct *mm = vma->vm_mm;
	struct vm_area_struct *next;
	unsigned long gap_addr;
	int error = 0;
	MA_STATE(mas, &mm->mm_mt, 0, 0);

	if (!(vma->vm_flags & VM_GROWSUP))
		return -EFAULT;

	/* Guard against exceeding limits of the address space. */
	address &= PAGE_MASK;
	if (address >= (TASK_SIZE & PAGE_MASK))
		return -ENOMEM;
	address += PAGE_SIZE;

	/* Enforce stack_guard_gap */
	gap_addr = address + stack_guard_gap;

	/* Guard against overflow */
	if (gap_addr < address || gap_addr > TASK_SIZE)
		gap_addr = TASK_SIZE;

	next = find_vma_intersection(mm, vma->vm_end, gap_addr);
	if (next && vma_is_accessible(next)) {
		if (!(next->vm_flags & VM_GROWSUP))
			return -ENOMEM;
		/* Check that both stack segments have the same anon_vma? */
	}

	if (mas_preallocate(&mas, GFP_KERNEL))
		return -ENOMEM;

	/* We must make sure the anon_vma is allocated. */
	if (unlikely(anon_vma_prepare(vma))) {
		mas_destroy(&mas);
		return -ENOMEM;
	}

	/* Lock the VMA before expanding to prevent concurrent page faults */
	vma_start_write(vma);
	/*
	 * vma->vm_start/vm_end cannot change under us because the caller
	 * is required to hold the mmap_lock in read mode.  We need the
	 * anon_vma lock to serialize against concurrent expand_stacks.
	 */
	anon_vma_lock_write(vma->anon_vma);

	/* Somebody else might have raced and expanded it already */
	if (address > vma->vm_end) {
		unsigned long size, grow;

		size = address - vma->vm_start;
		grow = (address - vma->vm_end) >> PAGE_SHIFT;

		error = -ENOMEM;
		if (vma->vm_pgoff + (size >> PAGE_SHIFT) >= vma->vm_pgoff) {
			error = acct_stack_growth(vma, size, grow);
			if (!error) {
				/*
				 * We only hold a shared mmap_lock lock here, so
				 * we need to protect against concurrent vma
				 * expansions.  anon_vma_lock_write() doesn't
				 * help here, as we don't guarantee that all
				 * growable vmas in a mm share the same root
				 * anon vma.  So, we reuse mm->page_table_lock
				 * to guard against concurrent vma expansions.
				 */
				spin_lock(&mm->page_table_lock);
				if (vma->vm_flags & VM_LOCKED)
					mm->locked_vm += grow;
				vm_stat_account(mm, vma->vm_flags, grow);
				anon_vma_interval_tree_pre_update_vma(vma);
				vma->vm_end = address;
				/* Overwrite old entry in mtree. */
				mas_set_range(&mas, vma->vm_start, address - 1);
				mas_store_prealloc(&mas, vma);
				anon_vma_interval_tree_post_update_vma(vma);
				spin_unlock(&mm->page_table_lock);

				perf_event_mmap(vma);
			}
		}
	}
	anon_vma_unlock_write(vma->anon_vma);
	khugepaged_enter_vma(vma, vma->vm_flags);
	mas_destroy(&mas);
	return error;
}
#endif /* CONFIG_STACK_GROWSUP || CONFIG_IA64 */

/*
 * vma is the first one with address < vma->vm_start.  Have to extend vma.
 * mmap_lock held for writing.
 */
int expand_downwards(struct vm_area_struct *vma, unsigned long address)
{
	struct mm_struct *mm = vma->vm_mm;
	MA_STATE(mas, &mm->mm_mt, vma->vm_start, vma->vm_start);
	struct vm_area_struct *prev;
	int error = 0;

	if (!(vma->vm_flags & VM_GROWSDOWN))
		return -EFAULT;

	address &= PAGE_MASK;
	if (address < mmap_min_addr || address < FIRST_USER_ADDRESS)
		return -EPERM;

	/* Enforce stack_guard_gap */
	prev = mas_prev(&mas, 0);
	/* Check that both stack segments have the same anon_vma? */
	if (prev) {
		if (!(prev->vm_flags & VM_GROWSDOWN) &&
		    vma_is_accessible(prev) &&
		    (address - prev->vm_end < stack_guard_gap))
			return -ENOMEM;
	}

	if (mas_preallocate(&mas, GFP_KERNEL))
		return -ENOMEM;

	/* We must make sure the anon_vma is allocated. */
	if (unlikely(anon_vma_prepare(vma))) {
		mas_destroy(&mas);
		return -ENOMEM;
	}

	/* Lock the VMA before expanding to prevent concurrent page faults */
	vma_start_write(vma);
	/*
	 * vma->vm_start/vm_end cannot change under us because the caller
	 * is required to hold the mmap_lock in read mode.  We need the
	 * anon_vma lock to serialize against concurrent expand_stacks.
	 */
	anon_vma_lock_write(vma->anon_vma);

	/* Somebody else might have raced and expanded it already */
	if (address < vma->vm_start) {
		unsigned long size, grow;

		size = vma->vm_end - address;
		grow = (vma->vm_start - address) >> PAGE_SHIFT;

		error = -ENOMEM;
		if (grow <= vma->vm_pgoff) {
			error = acct_stack_growth(vma, size, grow);
			if (!error) {
				/*
				 * We only hold a shared mmap_lock lock here, so
				 * we need to protect against concurrent vma
				 * expansions.  anon_vma_lock_write() doesn't
				 * help here, as we don't guarantee that all
				 * growable vmas in a mm share the same root
				 * anon vma.  So, we reuse mm->page_table_lock
				 * to guard against concurrent vma expansions.
				 */
				spin_lock(&mm->page_table_lock);
				if (vma->vm_flags & VM_LOCKED)
					mm->locked_vm += grow;
				vm_stat_account(mm, vma->vm_flags, grow);
				anon_vma_interval_tree_pre_update_vma(vma);
				vma->vm_start = address;
				vma->vm_pgoff -= grow;
				/* Overwrite old entry in mtree. */
				mas_set_range(&mas, address, vma->vm_end - 1);
				mas_store_prealloc(&mas, vma);
				anon_vma_interval_tree_post_update_vma(vma);
				spin_unlock(&mm->page_table_lock);

				perf_event_mmap(vma);
			}
		}
	}
	anon_vma_unlock_write(vma->anon_vma);
	khugepaged_enter_vma(vma, vma->vm_flags);
	mas_destroy(&mas);
	return error;
}

/* enforced gap between the expanding stack and other mappings. */
unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT;

static int __init cmdline_parse_stack_guard_gap(char *p)
{
	unsigned long val;
	char *endptr;

	val = simple_strtoul(p, &endptr, 10);
	if (!*endptr)
		stack_guard_gap = val << PAGE_SHIFT;

	return 1;
}
__setup("stack_guard_gap=", cmdline_parse_stack_guard_gap);

#ifdef CONFIG_STACK_GROWSUP
int expand_stack_locked(struct vm_area_struct *vma, unsigned long address)
{
	return expand_upwards(vma, address);
}

struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned long addr)
{
	struct vm_area_struct *vma, *prev;

	addr &= PAGE_MASK;
	vma = find_vma_prev(mm, addr, &prev);
	if (vma && (vma->vm_start <= addr))
		return vma;
	if (!prev)
		return NULL;
	if (expand_stack_locked(prev, addr))
		return NULL;
	if (prev->vm_flags & VM_LOCKED)
		populate_vma_page_range(prev, addr, prev->vm_end, NULL);
	return prev;
}
#else
int expand_stack_locked(struct vm_area_struct *vma, unsigned long address)
{
	if (unlikely(!(vma->vm_flags & VM_GROWSDOWN)))
		return -EINVAL;
	return expand_downwards(vma, address);
}

struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned long addr)
{
	struct vm_area_struct *vma;
	unsigned long start;

	addr &= PAGE_MASK;
	vma = find_vma(mm, addr);
	if (!vma)
		return NULL;
	if (vma->vm_start <= addr)
		return vma;
	start = vma->vm_start;
	if (expand_stack_locked(vma, addr))
		return NULL;
	if (vma->vm_flags & VM_LOCKED)
		populate_vma_page_range(vma, addr, start, NULL);
	return vma;
}
#endif

/*
 * IA64 has some horrid mapping rules: it can expand both up and down,
 * but with various special rules.
 *
 * We'll get rid of this architecture eventually, so the ugliness is
 * temporary.
 */
#ifdef CONFIG_IA64
static inline bool vma_expand_ok(struct vm_area_struct *vma, unsigned long addr)
{
	return REGION_NUMBER(addr) == REGION_NUMBER(vma->vm_start) &&
		REGION_OFFSET(addr) < RGN_MAP_LIMIT;
}

/*
 * IA64 stacks grow down, but there's a special register backing store
 * that can grow up. Only sequentially, though, so the new address must
 * match vm_end.
 */
static inline int vma_expand_up(struct vm_area_struct *vma, unsigned long addr)
{
	if (!vma_expand_ok(vma, addr))
		return -EFAULT;
	if (vma->vm_end != (addr & PAGE_MASK))
		return -EFAULT;
	return expand_upwards(vma, addr);
}

static inline bool vma_expand_down(struct vm_area_struct *vma, unsigned long addr)
{
	if (!vma_expand_ok(vma, addr))
		return -EFAULT;
	return expand_downwards(vma, addr);
}

#elif defined(CONFIG_STACK_GROWSUP)

#define vma_expand_up(vma,addr) expand_upwards(vma, addr)
#define vma_expand_down(vma, addr) (-EFAULT)

#else

#define vma_expand_up(vma,addr) (-EFAULT)
#define vma_expand_down(vma, addr) expand_downwards(vma, addr)

#endif

/*
 * expand_stack(): legacy interface for page faulting. Don't use unless
 * you have to.
 *
 * This is called with the mm locked for reading, drops the lock, takes
 * the lock for writing, tries to look up a vma again, expands it if
 * necessary, and downgrades the lock to reading again.
 *
 * If no vma is found or it can't be expanded, it returns NULL and has
 * dropped the lock.
 */
struct vm_area_struct *expand_stack(struct mm_struct *mm, unsigned long addr)
{
	struct vm_area_struct *vma, *prev;

	mmap_read_unlock(mm);
	if (mmap_write_lock_killable(mm))
		return NULL;

	vma = find_vma_prev(mm, addr, &prev);
	if (vma && vma->vm_start <= addr)
		goto success;

	if (prev && !vma_expand_up(prev, addr)) {
		vma = prev;
		goto success;
	}

	if (vma && !vma_expand_down(vma, addr))
		goto success;

	mmap_write_unlock(mm);
	return NULL;

success:
	mmap_write_downgrade(mm);
	return vma;
}

/*
 * Ok - we have the memory areas we should free on a maple tree so release them,
 * and do the vma updates.
 *
 * Called with the mm semaphore held.
 */
static inline void remove_mt(struct mm_struct *mm, struct ma_state *mas)
{
	unsigned long nr_accounted = 0;
	struct vm_area_struct *vma;

	/* Update high watermark before we lower total_vm */
	update_hiwater_vm(mm);
	mas_for_each(mas, vma, ULONG_MAX) {
		long nrpages = vma_pages(vma);

		if (vma->vm_flags & VM_ACCOUNT)
			nr_accounted += nrpages;
		vm_stat_account(mm, vma->vm_flags, -nrpages);
		remove_vma(vma, false);
	}
	vm_unacct_memory(nr_accounted);
	validate_mm(mm);
}

/*
 * Get rid of page table information in the indicated region.
 *
 * Called with the mm semaphore held.
 */
static void unmap_region(struct mm_struct *mm, struct maple_tree *mt,
		struct vm_area_struct *vma, struct vm_area_struct *prev,
		struct vm_area_struct *next,
		unsigned long start, unsigned long end, bool mm_wr_locked)
{
	struct mmu_gather tlb;

	lru_add_drain();
	tlb_gather_mmu(&tlb, mm);
	update_hiwater_rss(mm);
	unmap_vmas(&tlb, mt, vma, start, end, mm_wr_locked);
	free_pgtables(&tlb, mt, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS,
				 next ? next->vm_start : USER_PGTABLES_CEILING,
				 mm_wr_locked);
	tlb_finish_mmu(&tlb);
}

/*
 * __split_vma() bypasses sysctl_max_map_count checking.  We use this where it
 * has already been checked or doesn't make sense to fail.
 * VMA Iterator will point to the end VMA.
 */
int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
		unsigned long addr, int new_below)
{
	struct vma_prepare vp;
	struct vm_area_struct *new;
	int err;

	validate_mm(vma->vm_mm);

	WARN_ON(vma->vm_start >= addr);
	WARN_ON(vma->vm_end <= addr);

	if (vma->vm_ops && vma->vm_ops->may_split) {
		err = vma->vm_ops->may_split(vma, addr);
		if (err)
			return err;
	}

	new = vm_area_dup(vma);
	if (!new)
		return -ENOMEM;

	err = -ENOMEM;
	if (vma_iter_prealloc(vmi))
		goto out_free_vma;

	if (new_below) {
		new->vm_end = addr;
	} else {
		new->vm_start = addr;
		new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT);
	}

	err = vma_dup_policy(vma, new);
	if (err)
		goto out_free_vmi;

	err = anon_vma_clone(new, vma);
	if (err)
		goto out_free_mpol;

	if (new->vm_file)
		get_file(new->vm_file);

	if (new->vm_ops && new->vm_ops->open)
		new->vm_ops->open(new);

	init_vma_prep(&vp, vma);
	vp.insert = new;
	vma_prepare(&vp);
	vma_adjust_trans_huge(vma, vma->vm_start, addr, 0);

	if (new_below) {
		vma->vm_start = addr;
		vma->vm_pgoff += (addr - new->vm_start) >> PAGE_SHIFT;
	} else {
		vma->vm_end = addr;
	}

	/* vma_complete stores the new vma */
	vma_complete(&vp, vmi, vma->vm_mm);

	/* Success. */
	if (new_below)
		vma_next(vmi);
	validate_mm(vma->vm_mm);
	return 0;

out_free_mpol:
	mpol_put(vma_policy(new));
out_free_vmi:
	vma_iter_free(vmi);
out_free_vma:
	vm_area_free(new);
	validate_mm(vma->vm_mm);
	return err;
}

/*
 * Split a vma into two pieces at address 'addr', a new vma is allocated
 * either for the first part or the tail.
 */
int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
	      unsigned long addr, int new_below)
{
	if (vma->vm_mm->map_count >= sysctl_max_map_count)
		return -ENOMEM;

	return __split_vma(vmi, vma, addr, new_below);
}

/*
 * do_vmi_align_munmap() - munmap the aligned region from @start to @end.
 * @vmi: The vma iterator
 * @vma: The starting vm_area_struct
 * @mm: The mm_struct
 * @start: The aligned start address to munmap.
 * @end: The aligned end address to munmap.
 * @uf: The userfaultfd list_head
 * @unlock: Set to true to drop the mmap_lock.  unlocking only happens on
 * success.
 *
 * Return: 0 on success and drops the lock if so directed, error and leaves the
 * lock held otherwise.
 */
static int
do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma,
		    struct mm_struct *mm, unsigned long start,
		    unsigned long end, struct list_head *uf, bool unlock)
{
	struct vm_area_struct *prev, *next = NULL;
	struct maple_tree mt_detach;
	int count = 0;
	int error = -ENOMEM;
	unsigned long locked_vm = 0;
	MA_STATE(mas_detach, &mt_detach, 0, 0);
	mt_init_flags(&mt_detach, vmi->mas.tree->ma_flags & MT_FLAGS_LOCK_MASK);
	mt_set_external_lock(&mt_detach, &mm->mmap_lock);

	/*
	 * If we need to split any vma, do it now to save pain later.
	 *
	 * Note: mremap's move_vma VM_ACCOUNT handling assumes a partially
	 * unmapped vm_area_struct will remain in use: so lower split_vma
	 * places tmp vma above, and higher split_vma places tmp vma below.
	 */

	/* Does it split the first one? */
	if (start > vma->vm_start) {

		/*
		 * Make sure that map_count on return from munmap() will
		 * not exceed its limit; but let map_count go just above
		 * its limit temporarily, to help free resources as expected.
		 */
		if (end < vma->vm_end && mm->map_count >= sysctl_max_map_count)
			goto map_count_exceeded;

		error = __split_vma(vmi, vma, start, 0);
		if (error)
			goto start_split_failed;

		vma = vma_iter_load(vmi);
	}

	prev = vma_prev(vmi);
	if (unlikely((!prev)))
		vma_iter_set(vmi, start);

	/*
	 * Detach a range of VMAs from the mm. Using next as a temp variable as
	 * it is always overwritten.
	 */
	for_each_vma_range(*vmi, next, end) {
		/* Does it split the end? */
		if (next->vm_end > end) {
			error = __split_vma(vmi, next, end, 0);
			if (error)
				goto end_split_failed;
		}
		vma_start_write(next);
		mas_set_range(&mas_detach, next->vm_start, next->vm_end - 1);
		error = mas_store_gfp(&mas_detach, next, GFP_KERNEL);
		if (error)
			goto munmap_gather_failed;
		vma_mark_detached(next, true);
		if (next->vm_flags & VM_LOCKED)
			locked_vm += vma_pages(next);

		count++;
		if (unlikely(uf)) {
			/*
			 * If userfaultfd_unmap_prep returns an error the vmas
			 * will remain split, but userland will get a
			 * highly unexpected error anyway. This is no
			 * different than the case where the first of the two
			 * __split_vma fails, but we don't undo the first
			 * split, despite we could. This is unlikely enough
			 * failure that it's not worth optimizing it for.
			 */
			error = userfaultfd_unmap_prep(next, start, end, uf);

			if (error)
				goto userfaultfd_error;
		}
#ifdef CONFIG_DEBUG_VM_MAPLE_TREE
		BUG_ON(next->vm_start < start);
		BUG_ON(next->vm_start > end);
#endif
	}

	if (vma_iter_end(vmi) > end)
		next = vma_iter_load(vmi);

	if (!next)
		next = vma_next(vmi);

#if defined(CONFIG_DEBUG_VM_MAPLE_TREE)
	/* Make sure no VMAs are about to be lost. */
	{
		MA_STATE(test, &mt_detach, start, end - 1);
		struct vm_area_struct *vma_mas, *vma_test;
		int test_count = 0;

		vma_iter_set(vmi, start);
		rcu_read_lock();
		vma_test = mas_find(&test, end - 1);
		for_each_vma_range(*vmi, vma_mas, end) {
			BUG_ON(vma_mas != vma_test);
			test_count++;
			vma_test = mas_next(&test, end - 1);
		}
		rcu_read_unlock();
		BUG_ON(count != test_count);
	}
#endif
	vma_iter_set(vmi, start);
	error = vma_iter_clear_gfp(vmi, start, end, GFP_KERNEL);
	if (error)
		goto clear_tree_failed;

	/* Point of no return */
	mm->locked_vm -= locked_vm;
	mm->map_count -= count;
	if (unlock)
		mmap_write_downgrade(mm);

	/*
	 * We can free page tables without write-locking mmap_lock because VMAs
	 * were isolated before we downgraded mmap_lock.
	 */
	unmap_region(mm, &mt_detach, vma, prev, next, start, end, !unlock);
	/* Statistics and freeing VMAs */
	mas_set(&mas_detach, start);
	remove_mt(mm, &mas_detach);
	__mt_destroy(&mt_detach);
	validate_mm(mm);
	if (unlock)
		mmap_read_unlock(mm);

	return 0;

clear_tree_failed:
userfaultfd_error:
munmap_gather_failed:
end_split_failed:
	mas_set(&mas_detach, 0);
	mas_for_each(&mas_detach, next, end)
		vma_mark_detached(next, false);

	__mt_destroy(&mt_detach);
start_split_failed:
map_count_exceeded:
	validate_mm(mm);
	return error;
}

/*
 * do_vmi_munmap() - munmap a given range.
 * @vmi: The vma iterator
 * @mm: The mm_struct
 * @start: The start address to munmap
 * @len: The length of the range to munmap
 * @uf: The userfaultfd list_head
 * @unlock: set to true if the user wants to drop the mmap_lock on success
 *
 * This function takes a @mas that is either pointing to the previous VMA or set
 * to MA_START and sets it up to remove the mapping(s).  The @len will be
 * aligned and any arch_unmap work will be preformed.
 *
 * Return: 0 on success and drops the lock if so directed, error and leaves the
 * lock held otherwise.
 */
int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm,
		  unsigned long start, size_t len, struct list_head *uf,
		  bool unlock)
{
	unsigned long end;
	struct vm_area_struct *vma;

	if ((offset_in_page(start)) || start > TASK_SIZE || len > TASK_SIZE-start)
		return -EINVAL;

	end = start + PAGE_ALIGN(len);
	if (end == start)
		return -EINVAL;

	 /* arch_unmap() might do unmaps itself.  */
	arch_unmap(mm, start, end);

	/* Find the first overlapping VMA */
	vma = vma_find(vmi, end);
	if (!vma) {
		if (unlock)
			mmap_write_unlock(mm);
		return 0;
	}

	return do_vmi_align_munmap(vmi, vma, mm, start, end, uf, unlock);
}

/* do_munmap() - Wrapper function for non-maple tree aware do_munmap() calls.
 * @mm: The mm_struct
 * @start: The start address to munmap
 * @len: The length to be munmapped.
 * @uf: The userfaultfd list_head
 *
 * Return: 0 on success, error otherwise.
 */
int do_munmap(struct mm_struct *mm, unsigned long start, size_t len,
	      struct list_head *uf)
{
	VMA_ITERATOR(vmi, mm, start);

	return do_vmi_munmap(&vmi, mm, start, len, uf, false);
}

unsigned long mmap_region(struct file *file, unsigned long addr,
		unsigned long len, vm_flags_t vm_flags, unsigned long pgoff,
		struct list_head *uf)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma = NULL;
	struct vm_area_struct *next, *prev, *merge;
	pgoff_t pglen = len >> PAGE_SHIFT;
	unsigned long charged = 0;
	unsigned long end = addr + len;
	unsigned long merge_start = addr, merge_end = end;
	pgoff_t vm_pgoff;
	int error;
	VMA_ITERATOR(vmi, mm, addr);

	/* Check against address space limit. */
	if (!may_expand_vm(mm, vm_flags, len >> PAGE_SHIFT)) {
		unsigned long nr_pages;

		/*
		 * MAP_FIXED may remove pages of mappings that intersects with
		 * requested mapping. Account for the pages it would unmap.
		 */
		nr_pages = count_vma_pages_range(mm, addr, end);

		if (!may_expand_vm(mm, vm_flags,
					(len >> PAGE_SHIFT) - nr_pages))
			return -ENOMEM;
	}

	/* Unmap any existing mapping in the area */
	if (do_vmi_munmap(&vmi, mm, addr, len, uf, false))
		return -ENOMEM;

	/*
	 * Private writable mapping: check memory availability
	 */
	if (accountable_mapping(file, vm_flags)) {
		charged = len >> PAGE_SHIFT;
		if (security_vm_enough_memory_mm(mm, charged))
			return -ENOMEM;
		vm_flags |= VM_ACCOUNT;
	}

	next = vma_next(&vmi);
	prev = vma_prev(&vmi);
	if (vm_flags & VM_SPECIAL)
		goto cannot_expand;

	/* Attempt to expand an old mapping */
	/* Check next */
	if (next && next->vm_start == end && !vma_policy(next) &&
	    can_vma_merge_before(next, vm_flags, NULL, file, pgoff+pglen,
				 NULL_VM_UFFD_CTX, NULL)) {
		merge_end = next->vm_end;
		vma = next;
		vm_pgoff = next->vm_pgoff - pglen;
	}

	/* Check prev */
	if (prev && prev->vm_end == addr && !vma_policy(prev) &&
	    (vma ? can_vma_merge_after(prev, vm_flags, vma->anon_vma, file,
				       pgoff, vma->vm_userfaultfd_ctx, NULL) :
		   can_vma_merge_after(prev, vm_flags, NULL, file, pgoff,
				       NULL_VM_UFFD_CTX, NULL))) {
		merge_start = prev->vm_start;
		vma = prev;
		vm_pgoff = prev->vm_pgoff;
	}


	/* Actually expand, if possible */
	if (vma &&
	    !vma_expand(&vmi, vma, merge_start, merge_end, vm_pgoff, next)) {
		khugepaged_enter_vma(vma, vm_flags);
		goto expanded;
	}

cannot_expand:
	if (prev)
		vma_iter_next_range(&vmi);

	/*
	 * Determine the object being mapped and call the appropriate
	 * specific mapper. the address has already been validated, but
	 * not unmapped, but the maps are removed from the list.
	 */
	vma = vm_area_alloc(mm);
	if (!vma) {
		error = -ENOMEM;
		goto unacct_error;
	}

	vma_iter_set(&vmi, addr);
	vma->vm_start = addr;
	vma->vm_end = end;
	vm_flags_init(vma, vm_flags);
	vma->vm_page_prot = vm_get_page_prot(vm_flags);
	vma->vm_pgoff = pgoff;

	if (file) {
		if (vm_flags & VM_SHARED) {
			error = mapping_map_writable(file->f_mapping);
			if (error)
				goto free_vma;
		}

		vma->vm_file = get_file(file);
		error = call_mmap(file, vma);
		if (error)
			goto unmap_and_free_vma;

		/*
		 * Expansion is handled above, merging is handled below.
		 * Drivers should not alter the address of the VMA.
		 */
		error = -EINVAL;
		if (WARN_ON((addr != vma->vm_start)))
			goto close_and_free_vma;

		vma_iter_set(&vmi, addr);
		/*
		 * If vm_flags changed after call_mmap(), we should try merge
		 * vma again as we may succeed this time.
		 */
		if (unlikely(vm_flags != vma->vm_flags && prev)) {
			merge = vma_merge(&vmi, mm, prev, vma->vm_start,
				    vma->vm_end, vma->vm_flags, NULL,
				    vma->vm_file, vma->vm_pgoff, NULL,
				    NULL_VM_UFFD_CTX, NULL);
			if (merge) {
				/*
				 * ->mmap() can change vma->vm_file and fput
				 * the original file. So fput the vma->vm_file
				 * here or we would add an extra fput for file
				 * and cause general protection fault
				 * ultimately.
				 */
				fput(vma->vm_file);
				vm_area_free(vma);
				vma = merge;
				/* Update vm_flags to pick up the change. */
				vm_flags = vma->vm_flags;
				goto unmap_writable;
			}
		}

		vm_flags = vma->vm_flags;
	} else if (vm_flags & VM_SHARED) {
		error = shmem_zero_setup(vma);
		if (error)
			goto free_vma;
	} else {
		vma_set_anonymous(vma);
	}

	if (map_deny_write_exec(vma, vma->vm_flags)) {
		error = -EACCES;
		goto close_and_free_vma;
	}

	/* Allow architectures to sanity-check the vm_flags */
	error = -EINVAL;
	if (!arch_validate_flags(vma->vm_flags))
		goto close_and_free_vma;

	error = -ENOMEM;
	if (vma_iter_prealloc(&vmi))
		goto close_and_free_vma;

	/* Lock the VMA since it is modified after insertion into VMA tree */
	vma_start_write(vma);
	if (vma->vm_file)
		i_mmap_lock_write(vma->vm_file->f_mapping);

	vma_iter_store(&vmi, vma);
	mm->map_count++;
	if (vma->vm_file) {
		if (vma->vm_flags & VM_SHARED)
			mapping_allow_writable(vma->vm_file->f_mapping);

		flush_dcache_mmap_lock(vma->vm_file->f_mapping);
		vma_interval_tree_insert(vma, &vma->vm_file->f_mapping->i_mmap);
		flush_dcache_mmap_unlock(vma->vm_file->f_mapping);
		i_mmap_unlock_write(vma->vm_file->f_mapping);
	}

	/*
	 * vma_merge() calls khugepaged_enter_vma() either, the below
	 * call covers the non-merge case.
	 */
	khugepaged_enter_vma(vma, vma->vm_flags);

	/* Once vma denies write, undo our temporary denial count */
unmap_writable:
	if (file && vm_flags & VM_SHARED)
		mapping_unmap_writable(file->f_mapping);
	file = vma->vm_file;
	ksm_add_vma(vma);
expanded:
	perf_event_mmap(vma);

	vm_stat_account(mm, vm_flags, len >> PAGE_SHIFT);
	if (vm_flags & VM_LOCKED) {
		if ((vm_flags & VM_SPECIAL) || vma_is_dax(vma) ||
					is_vm_hugetlb_page(vma) ||
					vma == get_gate_vma(current->mm))
			vm_flags_clear(vma, VM_LOCKED_MASK);
		else
			mm->locked_vm += (len >> PAGE_SHIFT);
	}

	if (file)
		uprobe_mmap(vma);

	/*
	 * New (or expanded) vma always get soft dirty status.
	 * Otherwise user-space soft-dirty page tracker won't
	 * be able to distinguish situation when vma area unmapped,
	 * then new mapped in-place (which must be aimed as
	 * a completely new data area).
	 */
	vm_flags_set(vma, VM_SOFTDIRTY);

	vma_set_page_prot(vma);

	validate_mm(mm);
	return addr;

close_and_free_vma:
	if (file && vma->vm_ops && vma->vm_ops->close)
		vma->vm_ops->close(vma);

	if (file || vma->vm_file) {
unmap_and_free_vma:
		fput(vma->vm_file);
		vma->vm_file = NULL;

		/* Undo any partial mapping done by a device driver. */
		unmap_region(mm, &mm->mm_mt, vma, prev, next, vma->vm_start,
			     vma->vm_end, true);
	}
	if (file && (vm_flags & VM_SHARED))
		mapping_unmap_writable(file->f_mapping);
free_vma:
	vm_area_free(vma);
unacct_error:
	if (charged)
		vm_unacct_memory(charged);
	validate_mm(mm);
	return error;
}

static int __vm_munmap(unsigned long start, size_t len, bool unlock)
{
	int ret;
	struct mm_struct *mm = current->mm;
	LIST_HEAD(uf);
	VMA_ITERATOR(vmi, mm, start);

	if (mmap_write_lock_killable(mm))
		return -EINTR;

	ret = do_vmi_munmap(&vmi, mm, start, len, &uf, unlock);
	if (ret || !unlock)
		mmap_write_unlock(mm);

	userfaultfd_unmap_complete(mm, &uf);
	return ret;
}

int vm_munmap(unsigned long start, size_t len)
{
	return __vm_munmap(start, len, false);
}
EXPORT_SYMBOL(vm_munmap);

SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
{
	addr = untagged_addr(addr);
	return __vm_munmap(addr, len, true);
}


/*
 * Emulation of deprecated remap_file_pages() syscall.
 */
SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
		unsigned long, prot, unsigned long, pgoff, unsigned long, flags)
{

	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	unsigned long populate = 0;
	unsigned long ret = -EINVAL;
	struct file *file;

	pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/mm/remap_file_pages.rst.\n",
		     current->comm, current->pid);

	if (prot)
		return ret;
	start = start & PAGE_MASK;
	size = size & PAGE_MASK;

	if (start + size <= start)
		return ret;

	/* Does pgoff wrap? */
	if (pgoff + (size >> PAGE_SHIFT) < pgoff)
		return ret;

	if (mmap_write_lock_killable(mm))
		return -EINTR;

	vma = vma_lookup(mm, start);

	if (!vma || !(vma->vm_flags & VM_SHARED))
		goto out;

	if (start + size > vma->vm_end) {
		VMA_ITERATOR(vmi, mm, vma->vm_end);
		struct vm_area_struct *next, *prev = vma;

		for_each_vma_range(vmi, next, start + size) {
			/* hole between vmas ? */
			if (next->vm_start != prev->vm_end)
				goto out;

			if (next->vm_file != vma->vm_file)
				goto out;

			if (next->vm_flags != vma->vm_flags)
				goto out;

			if (start + size <= next->vm_end)
				break;

			prev = next;
		}

		if (!next)
			goto out;
	}

	prot |= vma->vm_flags & VM_READ ? PROT_READ : 0;
	prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0;
	prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0;

	flags &= MAP_NONBLOCK;
	flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE;
	if (vma->vm_flags & VM_LOCKED)
		flags |= MAP_LOCKED;

	file = get_file(vma->vm_file);
	ret = do_mmap(vma->vm_file, start, size,
			prot, flags, pgoff, &populate, NULL);
	fput(file);
out:
	mmap_write_unlock(mm);
	if (populate)
		mm_populate(ret, populate);
	if (!IS_ERR_VALUE(ret))
		ret = 0;
	return ret;
}

/*
 * do_vma_munmap() - Unmap a full or partial vma.
 * @vmi: The vma iterator pointing at the vma
 * @vma: The first vma to be munmapped
 * @start: the start of the address to unmap
 * @end: The end of the address to unmap
 * @uf: The userfaultfd list_head
 * @unlock: Drop the lock on success
 *
 * unmaps a VMA mapping when the vma iterator is already in position.
 * Does not handle alignment.
 *
 * Return: 0 on success drops the lock of so directed, error on failure and will
 * still hold the lock.
 */
int do_vma_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma,
		unsigned long start, unsigned long end, struct list_head *uf,
		bool unlock)
{
	struct mm_struct *mm = vma->vm_mm;

	arch_unmap(mm, start, end);
	return do_vmi_align_munmap(vmi, vma, mm, start, end, uf, unlock);
}

/*
 * do_brk_flags() - Increase the brk vma if the flags match.
 * @vmi: The vma iterator
 * @addr: The start address
 * @len: The length of the increase
 * @vma: The vma,
 * @flags: The VMA Flags
 *
 * Extend the brk VMA from addr to addr + len.  If the VMA is NULL or the flags
 * do not match then create a new anonymous VMA.  Eventually we may be able to
 * do some brk-specific accounting here.
 */
static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
		unsigned long addr, unsigned long len, unsigned long flags)
{
	struct mm_struct *mm = current->mm;
	struct vma_prepare vp;

	validate_mm(mm);
	/*
	 * Check against address space limits by the changed size
	 * Note: This happens *after* clearing old mappings in some code paths.
	 */
	flags |= VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
	if (!may_expand_vm(mm, flags, len >> PAGE_SHIFT))
		return -ENOMEM;

	if (mm->map_count > sysctl_max_map_count)
		return -ENOMEM;

	if (security_vm_enough_memory_mm(mm, len >> PAGE_SHIFT))
		return -ENOMEM;

	/*
	 * Expand the existing vma if possible; Note that singular lists do not
	 * occur after forking, so the expand will only happen on new VMAs.
	 */
	if (vma && vma->vm_end == addr && !vma_policy(vma) &&
	    can_vma_merge_after(vma, flags, NULL, NULL,
				addr >> PAGE_SHIFT, NULL_VM_UFFD_CTX, NULL)) {
		if (vma_iter_prealloc(vmi))
			goto unacct_fail;

		init_vma_prep(&vp, vma);
		vma_prepare(&vp);
		vma_adjust_trans_huge(vma, vma->vm_start, addr + len, 0);
		vma->vm_end = addr + len;
		vm_flags_set(vma, VM_SOFTDIRTY);
		vma_iter_store(vmi, vma);

		vma_complete(&vp, vmi, mm);
		khugepaged_enter_vma(vma, flags);
		goto out;
	}

	/* create a vma struct for an anonymous mapping */
	vma = vm_area_alloc(mm);
	if (!vma)
		goto unacct_fail;

	vma_set_anonymous(vma);
	vma->vm_start = addr;
	vma->vm_end = addr + len;
	vma->vm_pgoff = addr >> PAGE_SHIFT;
	vm_flags_init(vma, flags);
	vma->vm_page_prot = vm_get_page_prot(flags);
	if (vma_iter_store_gfp(vmi, vma, GFP_KERNEL))
		goto mas_store_fail;

	mm->map_count++;
	ksm_add_vma(vma);
out:
	perf_event_mmap(vma);
	mm->total_vm += len >> PAGE_SHIFT;
	mm->data_vm += len >> PAGE_SHIFT;
	if (flags & VM_LOCKED)
		mm->locked_vm += (len >> PAGE_SHIFT);
	vm_flags_set(vma, VM_SOFTDIRTY);
	validate_mm(mm);
	return 0;

mas_store_fail:
	vm_area_free(vma);
unacct_fail:
	vm_unacct_memory(len >> PAGE_SHIFT);
	return -ENOMEM;
}

int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma = NULL;
	unsigned long len;
	int ret;
	bool populate;
	LIST_HEAD(uf);
	VMA_ITERATOR(vmi, mm, addr);

	len = PAGE_ALIGN(request);
	if (len < request)
		return -ENOMEM;
	if (!len)
		return 0;

	if (mmap_write_lock_killable(mm))
		return -EINTR;

	/* Until we need other flags, refuse anything except VM_EXEC. */
	if ((flags & (~VM_EXEC)) != 0)
		return -EINVAL;

	ret = check_brk_limits(addr, len);
	if (ret)
		goto limits_failed;

	ret = do_vmi_munmap(&vmi, mm, addr, len, &uf, 0);
	if (ret)
		goto munmap_failed;

	vma = vma_prev(&vmi);
	ret = do_brk_flags(&vmi, vma, addr, len, flags);
	populate = ((mm->def_flags & VM_LOCKED) != 0);
	mmap_write_unlock(mm);
	userfaultfd_unmap_complete(mm, &uf);
	if (populate && !ret)
		mm_populate(addr, len);
	return ret;

munmap_failed:
limits_failed:
	mmap_write_unlock(mm);
	return ret;
}
EXPORT_SYMBOL(vm_brk_flags);

int vm_brk(unsigned long addr, unsigned long len)
{
	return vm_brk_flags(addr, len, 0);
}
EXPORT_SYMBOL(vm_brk);

/* Release all mmaps. */
void exit_mmap(struct mm_struct *mm)
{
	struct mmu_gather tlb;
	struct vm_area_struct *vma;
	unsigned long nr_accounted = 0;
	MA_STATE(mas, &mm->mm_mt, 0, 0);
	int count = 0;

	/* mm's last user has gone, and its about to be pulled down */
	mmu_notifier_release(mm);

	mmap_read_lock(mm);
	arch_exit_mmap(mm);

	vma = mas_find(&mas, ULONG_MAX);
	if (!vma) {
		/* Can happen if dup_mmap() received an OOM */
		mmap_read_unlock(mm);
		return;
	}

	lru_add_drain();
	flush_cache_mm(mm);
	tlb_gather_mmu_fullmm(&tlb, mm);
	/* update_hiwater_rss(mm) here? but nobody should be looking */
	/* Use ULONG_MAX here to ensure all VMAs in the mm are unmapped */
	unmap_vmas(&tlb, &mm->mm_mt, vma, 0, ULONG_MAX, false);
	mmap_read_unlock(mm);

	/*
	 * Set MMF_OOM_SKIP to hide this task from the oom killer/reaper
	 * because the memory has been already freed.
	 */
	set_bit(MMF_OOM_SKIP, &mm->flags);
	mmap_write_lock(mm);
	mt_clear_in_rcu(&mm->mm_mt);
	free_pgtables(&tlb, &mm->mm_mt, vma, FIRST_USER_ADDRESS,
		      USER_PGTABLES_CEILING, true);
	tlb_finish_mmu(&tlb);

	/*
	 * Walk the list again, actually closing and freeing it, with preemption
	 * enabled, without holding any MM locks besides the unreachable
	 * mmap_write_lock.
	 */
	do {
		if (vma->vm_flags & VM_ACCOUNT)
			nr_accounted += vma_pages(vma);
		remove_vma(vma, true);
		count++;
		cond_resched();
	} while ((vma = mas_find(&mas, ULONG_MAX)) != NULL);

	BUG_ON(count != mm->map_count);

	trace_exit_mmap(mm);
	__mt_destroy(&mm->mm_mt);
	mmap_write_unlock(mm);
	vm_unacct_memory(nr_accounted);
}

/* Insert vm structure into process list sorted by address
 * and into the inode's i_mmap tree.  If vm_file is non-NULL
 * then i_mmap_rwsem is taken here.
 */
int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
{
	unsigned long charged = vma_pages(vma);


	if (find_vma_intersection(mm, vma->vm_start, vma->vm_end))
		return -ENOMEM;

	if ((vma->vm_flags & VM_ACCOUNT) &&
	     security_vm_enough_memory_mm(mm, charged))
		return -ENOMEM;

	/*
	 * The vm_pgoff of a purely anonymous vma should be irrelevant
	 * until its first write fault, when page's anon_vma and index
	 * are set.  But now set the vm_pgoff it will almost certainly
	 * end up with (unless mremap moves it elsewhere before that
	 * first wfault), so /proc/pid/maps tells a consistent story.
	 *
	 * By setting it to reflect the virtual start address of the
	 * vma, merges and splits can happen in a seamless way, just
	 * using the existing file pgoff checks and manipulations.
	 * Similarly in do_mmap and in do_brk_flags.
	 */
	if (vma_is_anonymous(vma)) {
		BUG_ON(vma->anon_vma);
		vma->vm_pgoff = vma->vm_start >> PAGE_SHIFT;
	}

	if (vma_link(mm, vma)) {
		vm_unacct_memory(charged);
		return -ENOMEM;
	}

	return 0;
}

/*
 * Copy the vma structure to a new location in the same mm,
 * prior to moving page table entries, to effect an mremap move.
 */
struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
	unsigned long addr, unsigned long len, pgoff_t pgoff,
	bool *need_rmap_locks)
{
	struct vm_area_struct *vma = *vmap;
	unsigned long vma_start = vma->vm_start;
	struct mm_struct *mm = vma->vm_mm;
	struct vm_area_struct *new_vma, *prev;
	bool faulted_in_anon_vma = true;
	VMA_ITERATOR(vmi, mm, addr);

	validate_mm(mm);
	/*
	 * If anonymous vma has not yet been faulted, update new pgoff
	 * to match new location, to increase its chance of merging.
	 */
	if (unlikely(vma_is_anonymous(vma) && !vma->anon_vma)) {
		pgoff = addr >> PAGE_SHIFT;
		faulted_in_anon_vma = false;
	}

	new_vma = find_vma_prev(mm, addr, &prev);
	if (new_vma && new_vma->vm_start < addr + len)
		return NULL;	/* should never get here */

	new_vma = vma_merge(&vmi, mm, prev, addr, addr + len, vma->vm_flags,
			    vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
			    vma->vm_userfaultfd_ctx, anon_vma_name(vma));
	if (new_vma) {
		/*
		 * Source vma may have been merged into new_vma
		 */
		if (unlikely(vma_start >= new_vma->vm_start &&
			     vma_start < new_vma->vm_end)) {
			/*
			 * The only way we can get a vma_merge with
			 * self during an mremap is if the vma hasn't
			 * been faulted in yet and we were allowed to
			 * reset the dst vma->vm_pgoff to the
			 * destination address of the mremap to allow
			 * the merge to happen. mremap must change the
			 * vm_pgoff linearity between src and dst vmas
			 * (in turn preventing a vma_merge) to be
			 * safe. It is only safe to keep the vm_pgoff
			 * linear if there are no pages mapped yet.
			 */
			VM_BUG_ON_VMA(faulted_in_anon_vma, new_vma);
			*vmap = vma = new_vma;
		}
		*need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff);
	} else {
		new_vma = vm_area_dup(vma);
		if (!new_vma)
			goto out;
		new_vma->vm_start = addr;
		new_vma->vm_end = addr + len;
		new_vma->vm_pgoff = pgoff;
		if (vma_dup_policy(vma, new_vma))
			goto out_free_vma;
		if (anon_vma_clone(new_vma, vma))
			goto out_free_mempol;
		if (new_vma->vm_file)
			get_file(new_vma->vm_file);
		if (new_vma->vm_ops && new_vma->vm_ops->open)
			new_vma->vm_ops->open(new_vma);
		vma_start_write(new_vma);
		if (vma_link(mm, new_vma))
			goto out_vma_link;
		*need_rmap_locks = false;
	}
	validate_mm(mm);
	return new_vma;

out_vma_link:
	if (new_vma->vm_ops && new_vma->vm_ops->close)
		new_vma->vm_ops->close(new_vma);

	if (new_vma->vm_file)
		fput(new_vma->vm_file);

	unlink_anon_vmas(new_vma);
out_free_mempol:
	mpol_put(vma_policy(new_vma));
out_free_vma:
	vm_area_free(new_vma);
out:
	validate_mm(mm);
	return NULL;
}

/*
 * Return true if the calling process may expand its vm space by the passed
 * number of pages
 */
bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages)
{
	if (mm->total_vm + npages > rlimit(RLIMIT_AS) >> PAGE_SHIFT)
		return false;

	if (is_data_mapping(flags) &&
	    mm->data_vm + npages > rlimit(RLIMIT_DATA) >> PAGE_SHIFT) {
		/* Workaround for Valgrind */
		if (rlimit(RLIMIT_DATA) == 0 &&
		    mm->data_vm + npages <= rlimit_max(RLIMIT_DATA) >> PAGE_SHIFT)
			return true;

		pr_warn_once("%s (%d): VmData %lu exceed data ulimit %lu. Update limits%s.\n",
			     current->comm, current->pid,
			     (mm->data_vm + npages) << PAGE_SHIFT,
			     rlimit(RLIMIT_DATA),
			     ignore_rlimit_data ? "" : " or use boot option ignore_rlimit_data");

		if (!ignore_rlimit_data)
			return false;
	}

	return true;
}

void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages)
{
	WRITE_ONCE(mm->total_vm, READ_ONCE(mm->total_vm)+npages);

	if (is_exec_mapping(flags))
		mm->exec_vm += npages;
	else if (is_stack_mapping(flags))
		mm->stack_vm += npages;
	else if (is_data_mapping(flags))
		mm->data_vm += npages;
}

static vm_fault_t special_mapping_fault(struct vm_fault *vmf);

/*
 * Having a close hook prevents vma merging regardless of flags.
 */
static void special_mapping_close(struct vm_area_struct *vma)
{
}

static const char *special_mapping_name(struct vm_area_struct *vma)
{
	return ((struct vm_special_mapping *)vma->vm_private_data)->name;
}

static int special_mapping_mremap(struct vm_area_struct *new_vma)
{
	struct vm_special_mapping *sm = new_vma->vm_private_data;

	if (WARN_ON_ONCE(current->mm != new_vma->vm_mm))
		return -EFAULT;

	if (sm->mremap)
		return sm->mremap(sm, new_vma);

	return 0;
}

static int special_mapping_split(struct vm_area_struct *vma, unsigned long addr)
{
	/*
	 * Forbid splitting special mappings - kernel has expectations over
	 * the number of pages in mapping. Together with VM_DONTEXPAND
	 * the size of vma should stay the same over the special mapping's
	 * lifetime.
	 */
	return -EINVAL;
}

static const struct vm_operations_struct special_mapping_vmops = {
	.close = special_mapping_close,
	.fault = special_mapping_fault,
	.mremap = special_mapping_mremap,
	.name = special_mapping_name,
	/* vDSO code relies that VVAR can't be accessed remotely */
	.access = NULL,
	.may_split = special_mapping_split,
};

static const struct vm_operations_struct legacy_special_mapping_vmops = {
	.close = special_mapping_close,
	.fault = special_mapping_fault,
};

static vm_fault_t special_mapping_fault(struct vm_fault *vmf)
{
	struct vm_area_struct *vma = vmf->vma;
	pgoff_t pgoff;
	struct page **pages;

	if (vma->vm_ops == &legacy_special_mapping_vmops) {
		pages = vma->vm_private_data;
	} else {
		struct vm_special_mapping *sm = vma->vm_private_data;

		if (sm->fault)
			return sm->fault(sm, vmf->vma, vmf);

		pages = sm->pages;
	}

	for (pgoff = vmf->pgoff; pgoff && *pages; ++pages)
		pgoff--;

	if (*pages) {
		struct page *page = *pages;
		get_page(page);
		vmf->page = page;
		return 0;
	}

	return VM_FAULT_SIGBUS;
}

static struct vm_area_struct *__install_special_mapping(
	struct mm_struct *mm,
	unsigned long addr, unsigned long len,
	unsigned long vm_flags, void *priv,
	const struct vm_operations_struct *ops)
{
	int ret;
	struct vm_area_struct *vma;

	validate_mm(mm);
	vma = vm_area_alloc(mm);
	if (unlikely(vma == NULL))
		return ERR_PTR(-ENOMEM);

	vma->vm_start = addr;
	vma->vm_end = addr + len;

	vm_flags_init(vma, (vm_flags | mm->def_flags |
		      VM_DONTEXPAND | VM_SOFTDIRTY) & ~VM_LOCKED_MASK);
	vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);

	vma->vm_ops = ops;
	vma->vm_private_data = priv;

	ret = insert_vm_struct(mm, vma);
	if (ret)
		goto out;

	vm_stat_account(mm, vma->vm_flags, len >> PAGE_SHIFT);

	perf_event_mmap(vma);

	validate_mm(mm);
	return vma;

out:
	vm_area_free(vma);
	validate_mm(mm);
	return ERR_PTR(ret);
}

bool vma_is_special_mapping(const struct vm_area_struct *vma,
	const struct vm_special_mapping *sm)
{
	return vma->vm_private_data == sm &&
		(vma->vm_ops == &special_mapping_vmops ||
		 vma->vm_ops == &legacy_special_mapping_vmops);
}

/*
 * Called with mm->mmap_lock held for writing.
 * Insert a new vma covering the given region, with the given flags.
 * Its pages are supplied by the given array of struct page *.
 * The array can be shorter than len >> PAGE_SHIFT if it's null-terminated.
 * The region past the last page supplied will always produce SIGBUS.
 * The array pointer and the pages it points to are assumed to stay alive
 * for as long as this mapping might exist.
 */
struct vm_area_struct *_install_special_mapping(
	struct mm_struct *mm,
	unsigned long addr, unsigned long len,
	unsigned long vm_flags, const struct vm_special_mapping *spec)
{
	return __install_special_mapping(mm, addr, len, vm_flags, (void *)spec,
					&special_mapping_vmops);
}

int install_special_mapping(struct mm_struct *mm,
			    unsigned long addr, unsigned long len,
			    unsigned long vm_flags, struct page **pages)
{
	struct vm_area_struct *vma = __install_special_mapping(
		mm, addr, len, vm_flags, (void *)pages,
		&legacy_special_mapping_vmops);

	return PTR_ERR_OR_ZERO(vma);
}

static DEFINE_MUTEX(mm_all_locks_mutex);

static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma)
{
	if (!test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) {
		/*
		 * The LSB of head.next can't change from under us
		 * because we hold the mm_all_locks_mutex.
		 */
		down_write_nest_lock(&anon_vma->root->rwsem, &mm->mmap_lock);
		/*
		 * We can safely modify head.next after taking the
		 * anon_vma->root->rwsem. If some other vma in this mm shares
		 * the same anon_vma we won't take it again.
		 *
		 * No need of atomic instructions here, head.next
		 * can't change from under us thanks to the
		 * anon_vma->root->rwsem.
		 */
		if (__test_and_set_bit(0, (unsigned long *)
				       &anon_vma->root->rb_root.rb_root.rb_node))
			BUG();
	}
}

static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping)
{
	if (!test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) {
		/*
		 * AS_MM_ALL_LOCKS can't change from under us because
		 * we hold the mm_all_locks_mutex.
		 *
		 * Operations on ->flags have to be atomic because
		 * even if AS_MM_ALL_LOCKS is stable thanks to the
		 * mm_all_locks_mutex, there may be other cpus
		 * changing other bitflags in parallel to us.
		 */
		if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags))
			BUG();
		down_write_nest_lock(&mapping->i_mmap_rwsem, &mm->mmap_lock);
	}
}

/*
 * This operation locks against the VM for all pte/vma/mm related
 * operations that could ever happen on a certain mm. This includes
 * vmtruncate, try_to_unmap, and all page faults.
 *
 * The caller must take the mmap_lock in write mode before calling
 * mm_take_all_locks(). The caller isn't allowed to release the
 * mmap_lock until mm_drop_all_locks() returns.
 *
 * mmap_lock in write mode is required in order to block all operations
 * that could modify pagetables and free pages without need of
 * altering the vma layout. It's also needed in write mode to avoid new
 * anon_vmas to be associated with existing vmas.
 *
 * A single task can't take more than one mm_take_all_locks() in a row
 * or it would deadlock.
 *
 * The LSB in anon_vma->rb_root.rb_node and the AS_MM_ALL_LOCKS bitflag in
 * mapping->flags avoid to take the same lock twice, if more than one
 * vma in this mm is backed by the same anon_vma or address_space.
 *
 * We take locks in following order, accordingly to comment at beginning
 * of mm/rmap.c:
 *   - all hugetlbfs_i_mmap_rwsem_key locks (aka mapping->i_mmap_rwsem for
 *     hugetlb mapping);
 *   - all vmas marked locked
 *   - all i_mmap_rwsem locks;
 *   - all anon_vma->rwseml
 *
 * We can take all locks within these types randomly because the VM code
 * doesn't nest them and we protected from parallel mm_take_all_locks() by
 * mm_all_locks_mutex.
 *
 * mm_take_all_locks() and mm_drop_all_locks are expensive operations
 * that may have to take thousand of locks.
 *
 * mm_take_all_locks() can fail if it's interrupted by signals.
 */
int mm_take_all_locks(struct mm_struct *mm)
{
	struct vm_area_struct *vma;
	struct anon_vma_chain *avc;
	MA_STATE(mas, &mm->mm_mt, 0, 0);

	mmap_assert_write_locked(mm);

	mutex_lock(&mm_all_locks_mutex);

	mas_for_each(&mas, vma, ULONG_MAX) {
		if (signal_pending(current))
			goto out_unlock;
		vma_start_write(vma);
	}

	mas_set(&mas, 0);
	mas_for_each(&mas, vma, ULONG_MAX) {
		if (signal_pending(current))
			goto out_unlock;
		if (vma->vm_file && vma->vm_file->f_mapping &&
				is_vm_hugetlb_page(vma))
			vm_lock_mapping(mm, vma->vm_file->f_mapping);
	}

	mas_set(&mas, 0);
	mas_for_each(&mas, vma, ULONG_MAX) {
		if (signal_pending(current))
			goto out_unlock;
		if (vma->vm_file && vma->vm_file->f_mapping &&
				!is_vm_hugetlb_page(vma))
			vm_lock_mapping(mm, vma->vm_file->f_mapping);
	}

	mas_set(&mas, 0);
	mas_for_each(&mas, vma, ULONG_MAX) {
		if (signal_pending(current))
			goto out_unlock;
		if (vma->anon_vma)
			list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
				vm_lock_anon_vma(mm, avc->anon_vma);
	}

	return 0;

out_unlock:
	mm_drop_all_locks(mm);
	return -EINTR;
}

static void vm_unlock_anon_vma(struct anon_vma *anon_vma)
{
	if (test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) {
		/*
		 * The LSB of head.next can't change to 0 from under
		 * us because we hold the mm_all_locks_mutex.
		 *
		 * We must however clear the bitflag before unlocking
		 * the vma so the users using the anon_vma->rb_root will
		 * never see our bitflag.
		 *
		 * No need of atomic instructions here, head.next
		 * can't change from under us until we release the
		 * anon_vma->root->rwsem.
		 */
		if (!__test_and_clear_bit(0, (unsigned long *)
					  &anon_vma->root->rb_root.rb_root.rb_node))
			BUG();
		anon_vma_unlock_write(anon_vma);
	}
}

static void vm_unlock_mapping(struct address_space *mapping)
{
	if (test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) {
		/*
		 * AS_MM_ALL_LOCKS can't change to 0 from under us
		 * because we hold the mm_all_locks_mutex.
		 */
		i_mmap_unlock_write(mapping);
		if (!test_and_clear_bit(AS_MM_ALL_LOCKS,
					&mapping->flags))
			BUG();
	}
}

/*
 * The mmap_lock cannot be released by the caller until
 * mm_drop_all_locks() returns.
 */
void mm_drop_all_locks(struct mm_struct *mm)
{
	struct vm_area_struct *vma;
	struct anon_vma_chain *avc;
	MA_STATE(mas, &mm->mm_mt, 0, 0);

	mmap_assert_write_locked(mm);
	BUG_ON(!mutex_is_locked(&mm_all_locks_mutex));

	mas_for_each(&mas, vma, ULONG_MAX) {
		if (vma->anon_vma)
			list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
				vm_unlock_anon_vma(avc->anon_vma);
		if (vma->vm_file && vma->vm_file->f_mapping)
			vm_unlock_mapping(vma->vm_file->f_mapping);
	}
	vma_end_write_all(mm);

	mutex_unlock(&mm_all_locks_mutex);
}

/*
 * initialise the percpu counter for VM
 */
void __init mmap_init(void)
{
	int ret;

	ret = percpu_counter_init(&vm_committed_as, 0, GFP_KERNEL);
	VM_BUG_ON(ret);
}

/*
 * Initialise sysctl_user_reserve_kbytes.
 *
 * This is intended to prevent a user from starting a single memory hogging
 * process, such that they cannot recover (kill the hog) in OVERCOMMIT_NEVER
 * mode.
 *
 * The default value is min(3% of free memory, 128MB)
 * 128MB is enough to recover with sshd/login, bash, and top/kill.
 */
static int init_user_reserve(void)
{
	unsigned long free_kbytes;

	free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10);

	sysctl_user_reserve_kbytes = min(free_kbytes / 32, 1UL << 17);
	return 0;
}
subsys_initcall(init_user_reserve);

/*
 * Initialise sysctl_admin_reserve_kbytes.
 *
 * The purpose of sysctl_admin_reserve_kbytes is to allow the sys admin
 * to log in and kill a memory hogging process.
 *
 * Systems with more than 256MB will reserve 8MB, enough to recover
 * with sshd, bash, and top in OVERCOMMIT_GUESS. Smaller systems will
 * only reserve 3% of free pages by default.
 */
static int init_admin_reserve(void)
{
	unsigned long free_kbytes;

	free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10);

	sysctl_admin_reserve_kbytes = min(free_kbytes / 32, 1UL << 13);
	return 0;
}
subsys_initcall(init_admin_reserve);

/*
 * Reinititalise user and admin reserves if memory is added or removed.
 *
 * The default user reserve max is 128MB, and the default max for the
 * admin reserve is 8MB. These are usually, but not always, enough to
 * enable recovery from a memory hogging process using login/sshd, a shell,
 * and tools like top. It may make sense to increase or even disable the
 * reserve depending on the existence of swap or variations in the recovery
 * tools. So, the admin may have changed them.
 *
 * If memory is added and the reserves have been eliminated or increased above
 * the default max, then we'll trust the admin.
 *
 * If memory is removed and there isn't enough free memory, then we
 * need to reset the reserves.
 *
 * Otherwise keep the reserve set by the admin.
 */
static int reserve_mem_notifier(struct notifier_block *nb,
			     unsigned long action, void *data)
{
	unsigned long tmp, free_kbytes;

	switch (action) {
	case MEM_ONLINE:
		/* Default max is 128MB. Leave alone if modified by operator. */
		tmp = sysctl_user_reserve_kbytes;
		if (0 < tmp && tmp < (1UL << 17))
			init_user_reserve();

		/* Default max is 8MB.  Leave alone if modified by operator. */
		tmp = sysctl_admin_reserve_kbytes;
		if (0 < tmp && tmp < (1UL << 13))
			init_admin_reserve();

		break;
	case MEM_OFFLINE:
		free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10);

		if (sysctl_user_reserve_kbytes > free_kbytes) {
			init_user_reserve();
			pr_info("vm.user_reserve_kbytes reset to %lu\n",
				sysctl_user_reserve_kbytes);
		}

		if (sysctl_admin_reserve_kbytes > free_kbytes) {
			init_admin_reserve();
			pr_info("vm.admin_reserve_kbytes reset to %lu\n",
				sysctl_admin_reserve_kbytes);
		}
		break;
	default:
		break;
	}
	return NOTIFY_OK;
}

static int __meminit init_reserve_notifier(void)
{
	if (hotplug_memory_notifier(reserve_mem_notifier, DEFAULT_CALLBACK_PRI))
		pr_err("Failed registering memory add/remove notifier for admin reserve\n");

	return 0;
}
subsys_initcall(init_reserve_notifier);