Free Electrons

Embedded Linux Experts

   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
/*
 *	linux/mm/filemap.c
 *
 * Copyright (C) 1994-1999  Linus Torvalds
 */

/*
 * This file handles the generic file mmap semantics used by
 * most "normal" filesystems (but you don't /have/ to use this:
 * the NFS filesystem used to do this differently, for example)
 */
#include <linux/export.h>
#include <linux/compiler.h>
#include <linux/dax.h>
#include <linux/fs.h>
#include <linux/sched/signal.h>
#include <linux/uaccess.h>
#include <linux/capability.h>
#include <linux/kernel_stat.h>
#include <linux/gfp.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/uio.h>
#include <linux/hash.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/security.h>
#include <linux/cpuset.h>
#include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */
#include <linux/hugetlb.h>
#include <linux/memcontrol.h>
#include <linux/cleancache.h>
#include <linux/rmap.h>
#include "internal.h"

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

/*
 * FIXME: remove all knowledge of the buffer layer from the core VM
 */
#include <linux/buffer_head.h> /* for try_to_free_buffers */

#include <asm/mman.h>

/*
 * Shared mappings implemented 30.11.1994. It's not fully working yet,
 * though.
 *
 * Shared mappings now work. 15.8.1995  Bruno.
 *
 * finished 'unifying' the page and buffer cache and SMP-threaded the
 * page-cache, 21.05.1999, Ingo Molnar <mingo@redhat.com>
 *
 * SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <andrea@suse.de>
 */

/*
 * Lock ordering:
 *
 *  ->i_mmap_rwsem		(truncate_pagecache)
 *    ->private_lock		(__free_pte->__set_page_dirty_buffers)
 *      ->swap_lock		(exclusive_swap_page, others)
 *        ->mapping->tree_lock
 *
 *  ->i_mutex
 *    ->i_mmap_rwsem		(truncate->unmap_mapping_range)
 *
 *  ->mmap_sem
 *    ->i_mmap_rwsem
 *      ->page_table_lock or pte_lock	(various, mainly in memory.c)
 *        ->mapping->tree_lock	(arch-dependent flush_dcache_mmap_lock)
 *
 *  ->mmap_sem
 *    ->lock_page		(access_process_vm)
 *
 *  ->i_mutex			(generic_perform_write)
 *    ->mmap_sem		(fault_in_pages_readable->do_page_fault)
 *
 *  bdi->wb.list_lock
 *    sb_lock			(fs/fs-writeback.c)
 *    ->mapping->tree_lock	(__sync_single_inode)
 *
 *  ->i_mmap_rwsem
 *    ->anon_vma.lock		(vma_adjust)
 *
 *  ->anon_vma.lock
 *    ->page_table_lock or pte_lock	(anon_vma_prepare and various)
 *
 *  ->page_table_lock or pte_lock
 *    ->swap_lock		(try_to_unmap_one)
 *    ->private_lock		(try_to_unmap_one)
 *    ->tree_lock		(try_to_unmap_one)
 *    ->zone_lru_lock(zone)	(follow_page->mark_page_accessed)
 *    ->zone_lru_lock(zone)	(check_pte_range->isolate_lru_page)
 *    ->private_lock		(page_remove_rmap->set_page_dirty)
 *    ->tree_lock		(page_remove_rmap->set_page_dirty)
 *    bdi.wb->list_lock		(page_remove_rmap->set_page_dirty)
 *    ->inode->i_lock		(page_remove_rmap->set_page_dirty)
 *    ->memcg->move_lock	(page_remove_rmap->lock_page_memcg)
 *    bdi.wb->list_lock		(zap_pte_range->set_page_dirty)
 *    ->inode->i_lock		(zap_pte_range->set_page_dirty)
 *    ->private_lock		(zap_pte_range->__set_page_dirty_buffers)
 *
 * ->i_mmap_rwsem
 *   ->tasklist_lock            (memory_failure, collect_procs_ao)
 */

static int page_cache_tree_insert(struct address_space *mapping,
				  struct page *page, void **shadowp)
{
	struct radix_tree_node *node;
	void **slot;
	int error;

	error = __radix_tree_create(&mapping->page_tree, page->index, 0,
				    &node, &slot);
	if (error)
		return error;
	if (*slot) {
		void *p;

		p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
		if (!radix_tree_exceptional_entry(p))
			return -EEXIST;

		mapping->nrexceptional--;
		if (!dax_mapping(mapping)) {
			if (shadowp)
				*shadowp = p;
		} else {
			/* DAX can replace empty locked entry with a hole */
			WARN_ON_ONCE(p !=
				dax_radix_locked_entry(0, RADIX_DAX_EMPTY));
			/* Wakeup waiters for exceptional entry lock */
			dax_wake_mapping_entry_waiter(mapping, page->index, p,
						      true);
		}
	}
	__radix_tree_replace(&mapping->page_tree, node, slot, page,
			     workingset_update_node, mapping);
	mapping->nrpages++;
	return 0;
}

static void page_cache_tree_delete(struct address_space *mapping,
				   struct page *page, void *shadow)
{
	int i, nr;

	/* hugetlb pages are represented by one entry in the radix tree */
	nr = PageHuge(page) ? 1 : hpage_nr_pages(page);

	VM_BUG_ON_PAGE(!PageLocked(page), page);
	VM_BUG_ON_PAGE(PageTail(page), page);
	VM_BUG_ON_PAGE(nr != 1 && shadow, page);

	for (i = 0; i < nr; i++) {
		struct radix_tree_node *node;
		void **slot;

		__radix_tree_lookup(&mapping->page_tree, page->index + i,
				    &node, &slot);

		VM_BUG_ON_PAGE(!node && nr != 1, page);

		radix_tree_clear_tags(&mapping->page_tree, node, slot);
		__radix_tree_replace(&mapping->page_tree, node, slot, shadow,
				     workingset_update_node, mapping);
	}

	if (shadow) {
		mapping->nrexceptional += nr;
		/*
		 * Make sure the nrexceptional update is committed before
		 * the nrpages update so that final truncate racing
		 * with reclaim does not see both counters 0 at the
		 * same time and miss a shadow entry.
		 */
		smp_wmb();
	}
	mapping->nrpages -= nr;
}

/*
 * Delete a page from the page cache and free it. Caller has to make
 * sure the page is locked and that nobody else uses it - or that usage
 * is safe.  The caller must hold the mapping's tree_lock.
 */
void __delete_from_page_cache(struct page *page, void *shadow)
{
	struct address_space *mapping = page->mapping;
	int nr = hpage_nr_pages(page);

	trace_mm_filemap_delete_from_page_cache(page);
	/*
	 * if we're uptodate, flush out into the cleancache, otherwise
	 * invalidate any existing cleancache entries.  We can't leave
	 * stale data around in the cleancache once our page is gone
	 */
	if (PageUptodate(page) && PageMappedToDisk(page))
		cleancache_put_page(page);
	else
		cleancache_invalidate_page(mapping, page);

	VM_BUG_ON_PAGE(PageTail(page), page);
	VM_BUG_ON_PAGE(page_mapped(page), page);
	if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(page_mapped(page))) {
		int mapcount;

		pr_alert("BUG: Bad page cache in process %s  pfn:%05lx\n",
			 current->comm, page_to_pfn(page));
		dump_page(page, "still mapped when deleted");
		dump_stack();
		add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);

		mapcount = page_mapcount(page);
		if (mapping_exiting(mapping) &&
		    page_count(page) >= mapcount + 2) {
			/*
			 * All vmas have already been torn down, so it's
			 * a good bet that actually the page is unmapped,
			 * and we'd prefer not to leak it: if we're wrong,
			 * some other bad page check should catch it later.
			 */
			page_mapcount_reset(page);
			page_ref_sub(page, mapcount);
		}
	}

	page_cache_tree_delete(mapping, page, shadow);

	page->mapping = NULL;
	/* Leave page->index set: truncation lookup relies upon it */

	/* hugetlb pages do not participate in page cache accounting. */
	if (PageHuge(page))
		return;

	__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr);
	if (PageSwapBacked(page)) {
		__mod_node_page_state(page_pgdat(page), NR_SHMEM, -nr);
		if (PageTransHuge(page))
			__dec_node_page_state(page, NR_SHMEM_THPS);
	} else {
		VM_BUG_ON_PAGE(PageTransHuge(page), page);
	}

	/*
	 * At this point page must be either written or cleaned by truncate.
	 * Dirty page here signals a bug and loss of unwritten data.
	 *
	 * This fixes dirty accounting after removing the page entirely but
	 * leaves PageDirty set: it has no effect for truncated page and
	 * anyway will be cleared before returning page into buddy allocator.
	 */
	if (WARN_ON_ONCE(PageDirty(page)))
		account_page_cleaned(page, mapping, inode_to_wb(mapping->host));
}

/**
 * delete_from_page_cache - delete page from page cache
 * @page: the page which the kernel is trying to remove from page cache
 *
 * This must be called only on pages that have been verified to be in the page
 * cache and locked.  It will never put the page into the free list, the caller
 * has a reference on the page.
 */
void delete_from_page_cache(struct page *page)
{
	struct address_space *mapping = page_mapping(page);
	unsigned long flags;
	void (*freepage)(struct page *);

	BUG_ON(!PageLocked(page));

	freepage = mapping->a_ops->freepage;

	spin_lock_irqsave(&mapping->tree_lock, flags);
	__delete_from_page_cache(page, NULL);
	spin_unlock_irqrestore(&mapping->tree_lock, flags);

	if (freepage)
		freepage(page);

	if (PageTransHuge(page) && !PageHuge(page)) {
		page_ref_sub(page, HPAGE_PMD_NR);
		VM_BUG_ON_PAGE(page_count(page) <= 0, page);
	} else {
		put_page(page);
	}
}
EXPORT_SYMBOL(delete_from_page_cache);

int filemap_check_errors(struct address_space *mapping)
{
	int ret = 0;
	/* Check for outstanding write errors */
	if (test_bit(AS_ENOSPC, &mapping->flags) &&
	    test_and_clear_bit(AS_ENOSPC, &mapping->flags))
		ret = -ENOSPC;
	if (test_bit(AS_EIO, &mapping->flags) &&
	    test_and_clear_bit(AS_EIO, &mapping->flags))
		ret = -EIO;
	return ret;
}
EXPORT_SYMBOL(filemap_check_errors);

static int filemap_check_and_keep_errors(struct address_space *mapping)
{
	/* Check for outstanding write errors */
	if (test_bit(AS_EIO, &mapping->flags))
		return -EIO;
	if (test_bit(AS_ENOSPC, &mapping->flags))
		return -ENOSPC;
	return 0;
}

/**
 * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range
 * @mapping:	address space structure to write
 * @start:	offset in bytes where the range starts
 * @end:	offset in bytes where the range ends (inclusive)
 * @sync_mode:	enable synchronous operation
 *
 * Start writeback against all of a mapping's dirty pages that lie
 * within the byte offsets <start, end> inclusive.
 *
 * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as
 * opposed to a regular memory cleansing writeback.  The difference between
 * these two operations is that if a dirty page/buffer is encountered, it must
 * be waited upon, and not just skipped over.
 */
int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
				loff_t end, int sync_mode)
{
	int ret;
	struct writeback_control wbc = {
		.sync_mode = sync_mode,
		.nr_to_write = LONG_MAX,
		.range_start = start,
		.range_end = end,
	};

	if (!mapping_cap_writeback_dirty(mapping))
		return 0;

	wbc_attach_fdatawrite_inode(&wbc, mapping->host);
	ret = do_writepages(mapping, &wbc);
	wbc_detach_inode(&wbc);
	return ret;
}

static inline int __filemap_fdatawrite(struct address_space *mapping,
	int sync_mode)
{
	return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode);
}

int filemap_fdatawrite(struct address_space *mapping)
{
	return __filemap_fdatawrite(mapping, WB_SYNC_ALL);
}
EXPORT_SYMBOL(filemap_fdatawrite);

int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
				loff_t end)
{
	return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL);
}
EXPORT_SYMBOL(filemap_fdatawrite_range);

/**
 * filemap_flush - mostly a non-blocking flush
 * @mapping:	target address_space
 *
 * This is a mostly non-blocking flush.  Not suitable for data-integrity
 * purposes - I/O may not be started against all dirty pages.
 */
int filemap_flush(struct address_space *mapping)
{
	return __filemap_fdatawrite(mapping, WB_SYNC_NONE);
}
EXPORT_SYMBOL(filemap_flush);

/**
 * filemap_range_has_page - check if a page exists in range.
 * @mapping:           address space within which to check
 * @start_byte:        offset in bytes where the range starts
 * @end_byte:          offset in bytes where the range ends (inclusive)
 *
 * Find at least one page in the range supplied, usually used to check if
 * direct writing in this range will trigger a writeback.
 */
bool filemap_range_has_page(struct address_space *mapping,
			   loff_t start_byte, loff_t end_byte)
{
	pgoff_t index = start_byte >> PAGE_SHIFT;
	pgoff_t end = end_byte >> PAGE_SHIFT;
	struct pagevec pvec;
	bool ret;

	if (end_byte < start_byte)
		return false;

	if (mapping->nrpages == 0)
		return false;

	pagevec_init(&pvec, 0);
	if (!pagevec_lookup(&pvec, mapping, index, 1))
		return false;
	ret = (pvec.pages[0]->index <= end);
	pagevec_release(&pvec);
	return ret;
}
EXPORT_SYMBOL(filemap_range_has_page);

static void __filemap_fdatawait_range(struct address_space *mapping,
				     loff_t start_byte, loff_t end_byte)
{
	pgoff_t index = start_byte >> PAGE_SHIFT;
	pgoff_t end = end_byte >> PAGE_SHIFT;
	struct pagevec pvec;
	int nr_pages;

	if (end_byte < start_byte)
		return;

	pagevec_init(&pvec, 0);
	while ((index <= end) &&
			(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
			PAGECACHE_TAG_WRITEBACK,
			min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1)) != 0) {
		unsigned i;

		for (i = 0; i < nr_pages; i++) {
			struct page *page = pvec.pages[i];

			/* until radix tree lookup accepts end_index */
			if (page->index > end)
				continue;

			wait_on_page_writeback(page);
			ClearPageError(page);
		}
		pagevec_release(&pvec);
		cond_resched();
	}
}

/**
 * filemap_fdatawait_range - wait for writeback to complete
 * @mapping:		address space structure to wait for
 * @start_byte:		offset in bytes where the range starts
 * @end_byte:		offset in bytes where the range ends (inclusive)
 *
 * Walk the list of under-writeback pages of the given address space
 * in the given range and wait for all of them.  Check error status of
 * the address space and return it.
 *
 * Since the error status of the address space is cleared by this function,
 * callers are responsible for checking the return value and handling and/or
 * reporting the error.
 */
int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
			    loff_t end_byte)
{
	__filemap_fdatawait_range(mapping, start_byte, end_byte);
	return filemap_check_errors(mapping);
}
EXPORT_SYMBOL(filemap_fdatawait_range);

/**
 * filemap_fdatawait_keep_errors - wait for writeback without clearing errors
 * @mapping: address space structure to wait for
 *
 * Walk the list of under-writeback pages of the given address space
 * and wait for all of them.  Unlike filemap_fdatawait(), this function
 * does not clear error status of the address space.
 *
 * Use this function if callers don't handle errors themselves.  Expected
 * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2),
 * fsfreeze(8)
 */
int filemap_fdatawait_keep_errors(struct address_space *mapping)
{
	loff_t i_size = i_size_read(mapping->host);

	if (i_size == 0)
		return 0;

	__filemap_fdatawait_range(mapping, 0, i_size - 1);
	return filemap_check_and_keep_errors(mapping);
}
EXPORT_SYMBOL(filemap_fdatawait_keep_errors);

/**
 * filemap_fdatawait - wait for all under-writeback pages to complete
 * @mapping: address space structure to wait for
 *
 * Walk the list of under-writeback pages of the given address space
 * and wait for all of them.  Check error status of the address space
 * and return it.
 *
 * Since the error status of the address space is cleared by this function,
 * callers are responsible for checking the return value and handling and/or
 * reporting the error.
 */
int filemap_fdatawait(struct address_space *mapping)
{
	loff_t i_size = i_size_read(mapping->host);

	if (i_size == 0)
		return 0;

	return filemap_fdatawait_range(mapping, 0, i_size - 1);
}
EXPORT_SYMBOL(filemap_fdatawait);

int filemap_write_and_wait(struct address_space *mapping)
{
	int err = 0;

	if ((!dax_mapping(mapping) && mapping->nrpages) ||
	    (dax_mapping(mapping) && mapping->nrexceptional)) {
		err = filemap_fdatawrite(mapping);
		/*
		 * Even if the above returned error, the pages may be
		 * written partially (e.g. -ENOSPC), so we wait for it.
		 * But the -EIO is special case, it may indicate the worst
		 * thing (e.g. bug) happened, so we avoid waiting for it.
		 */
		if (err != -EIO) {
			int err2 = filemap_fdatawait(mapping);
			if (!err)
				err = err2;
		} else {
			/* Clear any previously stored errors */
			filemap_check_errors(mapping);
		}
	} else {
		err = filemap_check_errors(mapping);
	}
	return err;
}
EXPORT_SYMBOL(filemap_write_and_wait);

/**
 * filemap_write_and_wait_range - write out & wait on a file range
 * @mapping:	the address_space for the pages
 * @lstart:	offset in bytes where the range starts
 * @lend:	offset in bytes where the range ends (inclusive)
 *
 * Write out and wait upon file offsets lstart->lend, inclusive.
 *
 * Note that @lend is inclusive (describes the last byte to be written) so
 * that this function can be used to write to the very end-of-file (end = -1).
 */
int filemap_write_and_wait_range(struct address_space *mapping,
				 loff_t lstart, loff_t lend)
{
	int err = 0;

	if ((!dax_mapping(mapping) && mapping->nrpages) ||
	    (dax_mapping(mapping) && mapping->nrexceptional)) {
		err = __filemap_fdatawrite_range(mapping, lstart, lend,
						 WB_SYNC_ALL);
		/* See comment of filemap_write_and_wait() */
		if (err != -EIO) {
			int err2 = filemap_fdatawait_range(mapping,
						lstart, lend);
			if (!err)
				err = err2;
		} else {
			/* Clear any previously stored errors */
			filemap_check_errors(mapping);
		}
	} else {
		err = filemap_check_errors(mapping);
	}
	return err;
}
EXPORT_SYMBOL(filemap_write_and_wait_range);

void __filemap_set_wb_err(struct address_space *mapping, int err)
{
	errseq_t eseq = __errseq_set(&mapping->wb_err, err);

	trace_filemap_set_wb_err(mapping, eseq);
}
EXPORT_SYMBOL(__filemap_set_wb_err);

/**
 * file_check_and_advance_wb_err - report wb error (if any) that was previously
 * 				   and advance wb_err to current one
 * @file: struct file on which the error is being reported
 *
 * When userland calls fsync (or something like nfsd does the equivalent), we
 * want to report any writeback errors that occurred since the last fsync (or
 * since the file was opened if there haven't been any).
 *
 * Grab the wb_err from the mapping. If it matches what we have in the file,
 * then just quickly return 0. The file is all caught up.
 *
 * If it doesn't match, then take the mapping value, set the "seen" flag in
 * it and try to swap it into place. If it works, or another task beat us
 * to it with the new value, then update the f_wb_err and return the error
 * portion. The error at this point must be reported via proper channels
 * (a'la fsync, or NFS COMMIT operation, etc.).
 *
 * While we handle mapping->wb_err with atomic operations, the f_wb_err
 * value is protected by the f_lock since we must ensure that it reflects
 * the latest value swapped in for this file descriptor.
 */
int file_check_and_advance_wb_err(struct file *file)
{
	int err = 0;
	errseq_t old = READ_ONCE(file->f_wb_err);
	struct address_space *mapping = file->f_mapping;

	/* Locklessly handle the common case where nothing has changed */
	if (errseq_check(&mapping->wb_err, old)) {
		/* Something changed, must use slow path */
		spin_lock(&file->f_lock);
		old = file->f_wb_err;
		err = errseq_check_and_advance(&mapping->wb_err,
						&file->f_wb_err);
		trace_file_check_and_advance_wb_err(file, old);
		spin_unlock(&file->f_lock);
	}
	return err;
}
EXPORT_SYMBOL(file_check_and_advance_wb_err);

/**
 * file_write_and_wait_range - write out & wait on a file range
 * @file:	file pointing to address_space with pages
 * @lstart:	offset in bytes where the range starts
 * @lend:	offset in bytes where the range ends (inclusive)
 *
 * Write out and wait upon file offsets lstart->lend, inclusive.
 *
 * Note that @lend is inclusive (describes the last byte to be written) so
 * that this function can be used to write to the very end-of-file (end = -1).
 *
 * After writing out and waiting on the data, we check and advance the
 * f_wb_err cursor to the latest value, and return any errors detected there.
 */
int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend)
{
	int err = 0, err2;
	struct address_space *mapping = file->f_mapping;

	if ((!dax_mapping(mapping) && mapping->nrpages) ||
	    (dax_mapping(mapping) && mapping->nrexceptional)) {
		err = __filemap_fdatawrite_range(mapping, lstart, lend,
						 WB_SYNC_ALL);
		/* See comment of filemap_write_and_wait() */
		if (err != -EIO)
			__filemap_fdatawait_range(mapping, lstart, lend);
	}
	err2 = file_check_and_advance_wb_err(file);
	if (!err)
		err = err2;
	return err;
}
EXPORT_SYMBOL(file_write_and_wait_range);

/**
 * replace_page_cache_page - replace a pagecache page with a new one
 * @old:	page to be replaced
 * @new:	page to replace with
 * @gfp_mask:	allocation mode
 *
 * This function replaces a page in the pagecache with a new one.  On
 * success it acquires the pagecache reference for the new page and
 * drops it for the old page.  Both the old and new pages must be
 * locked.  This function does not add the new page to the LRU, the
 * caller must do that.
 *
 * The remove + add is atomic.  The only way this function can fail is
 * memory allocation failure.
 */
int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
{
	int error;

	VM_BUG_ON_PAGE(!PageLocked(old), old);
	VM_BUG_ON_PAGE(!PageLocked(new), new);
	VM_BUG_ON_PAGE(new->mapping, new);

	error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
	if (!error) {
		struct address_space *mapping = old->mapping;
		void (*freepage)(struct page *);
		unsigned long flags;

		pgoff_t offset = old->index;
		freepage = mapping->a_ops->freepage;

		get_page(new);
		new->mapping = mapping;
		new->index = offset;

		spin_lock_irqsave(&mapping->tree_lock, flags);
		__delete_from_page_cache(old, NULL);
		error = page_cache_tree_insert(mapping, new, NULL);
		BUG_ON(error);

		/*
		 * hugetlb pages do not participate in page cache accounting.
		 */
		if (!PageHuge(new))
			__inc_node_page_state(new, NR_FILE_PAGES);
		if (PageSwapBacked(new))
			__inc_node_page_state(new, NR_SHMEM);
		spin_unlock_irqrestore(&mapping->tree_lock, flags);
		mem_cgroup_migrate(old, new);
		radix_tree_preload_end();
		if (freepage)
			freepage(old);
		put_page(old);
	}

	return error;
}
EXPORT_SYMBOL_GPL(replace_page_cache_page);

static int __add_to_page_cache_locked(struct page *page,
				      struct address_space *mapping,
				      pgoff_t offset, gfp_t gfp_mask,
				      void **shadowp)
{
	int huge = PageHuge(page);
	struct mem_cgroup *memcg;
	int error;

	VM_BUG_ON_PAGE(!PageLocked(page), page);
	VM_BUG_ON_PAGE(PageSwapBacked(page), page);

	if (!huge) {
		error = mem_cgroup_try_charge(page, current->mm,
					      gfp_mask, &memcg, false);
		if (error)
			return error;
	}

	error = radix_tree_maybe_preload(gfp_mask & ~__GFP_HIGHMEM);
	if (error) {
		if (!huge)
			mem_cgroup_cancel_charge(page, memcg, false);
		return error;
	}

	get_page(page);
	page->mapping = mapping;
	page->index = offset;

	spin_lock_irq(&mapping->tree_lock);
	error = page_cache_tree_insert(mapping, page, shadowp);
	radix_tree_preload_end();
	if (unlikely(error))
		goto err_insert;

	/* hugetlb pages do not participate in page cache accounting. */
	if (!huge)
		__inc_node_page_state(page, NR_FILE_PAGES);
	spin_unlock_irq(&mapping->tree_lock);
	if (!huge)
		mem_cgroup_commit_charge(page, memcg, false, false);
	trace_mm_filemap_add_to_page_cache(page);
	return 0;
err_insert:
	page->mapping = NULL;
	/* Leave page->index set: truncation relies upon it */
	spin_unlock_irq(&mapping->tree_lock);
	if (!huge)
		mem_cgroup_cancel_charge(page, memcg, false);
	put_page(page);
	return error;
}

/**
 * add_to_page_cache_locked - add a locked page to the pagecache
 * @page:	page to add
 * @mapping:	the page's address_space
 * @offset:	page index
 * @gfp_mask:	page allocation mode
 *
 * This function is used to add a page to the pagecache. It must be locked.
 * This function does not add the page to the LRU.  The caller must do that.
 */
int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
		pgoff_t offset, gfp_t gfp_mask)
{
	return __add_to_page_cache_locked(page, mapping, offset,
					  gfp_mask, NULL);
}
EXPORT_SYMBOL(add_to_page_cache_locked);

int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
				pgoff_t offset, gfp_t gfp_mask)
{
	void *shadow = NULL;
	int ret;

	__SetPageLocked(page);
	ret = __add_to_page_cache_locked(page, mapping, offset,
					 gfp_mask, &shadow);
	if (unlikely(ret))
		__ClearPageLocked(page);
	else {
		/*
		 * The page might have been evicted from cache only
		 * recently, in which case it should be activated like
		 * any other repeatedly accessed page.
		 * The exception is pages getting rewritten; evicting other
		 * data from the working set, only to cache data that will
		 * get overwritten with something else, is a waste of memory.
		 */
		if (!(gfp_mask & __GFP_WRITE) &&
		    shadow && workingset_refault(shadow)) {
			SetPageActive(page);
			workingset_activation(page);
		} else
			ClearPageActive(page);
		lru_cache_add(page);
	}
	return ret;
}
EXPORT_SYMBOL_GPL(add_to_page_cache_lru);

#ifdef CONFIG_NUMA
struct page *__page_cache_alloc(gfp_t gfp)
{
	int n;
	struct page *page;

	if (cpuset_do_page_mem_spread()) {
		unsigned int cpuset_mems_cookie;
		do {
			cpuset_mems_cookie = read_mems_allowed_begin();
			n = cpuset_mem_spread_node();
			page = __alloc_pages_node(n, gfp, 0);
		} while (!page && read_mems_allowed_retry(cpuset_mems_cookie));

		return page;
	}
	return alloc_pages(gfp, 0);
}
EXPORT_SYMBOL(__page_cache_alloc);
#endif

/*
 * In order to wait for pages to become available there must be
 * waitqueues associated with pages. By using a hash table of
 * waitqueues where the bucket discipline is to maintain all
 * waiters on the same queue and wake all when any of the pages
 * become available, and for the woken contexts to check to be
 * sure the appropriate page became available, this saves space
 * at a cost of "thundering herd" phenomena during rare hash
 * collisions.
 */
#define PAGE_WAIT_TABLE_BITS 8
#define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS)
static wait_queue_head_t page_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned;

static wait_queue_head_t *page_waitqueue(struct page *page)
{
	return &page_wait_table[hash_ptr(page, PAGE_WAIT_TABLE_BITS)];
}

void __init pagecache_init(void)
{
	int i;

	for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++)
		init_waitqueue_head(&page_wait_table[i]);

	page_writeback_init();
}

/* This has the same layout as wait_bit_key - see fs/cachefiles/rdwr.c */
struct wait_page_key {
	struct page *page;
	int bit_nr;
	int page_match;
};

struct wait_page_queue {
	struct page *page;
	int bit_nr;
	wait_queue_entry_t wait;
};

static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg)
{
	struct wait_page_key *key = arg;
	struct wait_page_queue *wait_page
		= container_of(wait, struct wait_page_queue, wait);

	if (wait_page->page != key->page)
	       return 0;
	key->page_match = 1;

	if (wait_page->bit_nr != key->bit_nr)
		return 0;

	/* Stop walking if it's locked */
	if (test_bit(key->bit_nr, &key->page->flags))
		return -1;

	return autoremove_wake_function(wait, mode, sync, key);
}

static void wake_up_page_bit(struct page *page, int bit_nr)
{
	wait_queue_head_t *q = page_waitqueue(page);
	struct wait_page_key key;
	unsigned long flags;

	key.page = page;
	key.bit_nr = bit_nr;
	key.page_match = 0;

	spin_lock_irqsave(&q->lock, flags);
	__wake_up_locked_key(q, TASK_NORMAL, &key);
	/*
	 * It is possible for other pages to have collided on the waitqueue
	 * hash, so in that case check for a page match. That prevents a long-
	 * term waiter
	 *
	 * It is still possible to miss a case here, when we woke page waiters
	 * and removed them from the waitqueue, but there are still other
	 * page waiters.
	 */
	if (!waitqueue_active(q) || !key.page_match) {
		ClearPageWaiters(page);
		/*
		 * It's possible to miss clearing Waiters here, when we woke
		 * our page waiters, but the hashed waitqueue has waiters for
		 * other pages on it.
		 *
		 * That's okay, it's a rare case. The next waker will clear it.
		 */
	}
	spin_unlock_irqrestore(&q->lock, flags);
}

static void wake_up_page(struct page *page, int bit)
{
	if (!PageWaiters(page))
		return;
	wake_up_page_bit(page, bit);
}

static inline int wait_on_page_bit_common(wait_queue_head_t *q,
		struct page *page, int bit_nr, int state, bool lock)
{
	struct wait_page_queue wait_page;
	wait_queue_entry_t *wait = &wait_page.wait;
	int ret = 0;

	init_wait(wait);
	wait->flags = lock ? WQ_FLAG_EXCLUSIVE : 0;
	wait->func = wake_page_function;
	wait_page.page = page;
	wait_page.bit_nr = bit_nr;

	for (;;) {
		spin_lock_irq(&q->lock);

		if (likely(list_empty(&wait->entry))) {
			__add_wait_queue_entry_tail(q, wait);
			SetPageWaiters(page);
		}

		set_current_state(state);

		spin_unlock_irq(&q->lock);

		if (likely(test_bit(bit_nr, &page->flags))) {
			io_schedule();
		}

		if (lock) {
			if (!test_and_set_bit_lock(bit_nr, &page->flags))
				break;
		} else {
			if (!test_bit(bit_nr, &page->flags))
				break;
		}

		if (unlikely(signal_pending_state(state, current))) {
			ret = -EINTR;
			break;
		}
	}

	finish_wait(q, wait);

	/*
	 * A signal could leave PageWaiters set. Clearing it here if
	 * !waitqueue_active would be possible (by open-coding finish_wait),
	 * but still fail to catch it in the case of wait hash collision. We
	 * already can fail to clear wait hash collision cases, so don't
	 * bother with signals either.
	 */

	return ret;
}

void wait_on_page_bit(struct page *page, int bit_nr)
{
	wait_queue_head_t *q = page_waitqueue(page);
	wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, false);
}
EXPORT_SYMBOL(wait_on_page_bit);

int wait_on_page_bit_killable(struct page *page, int bit_nr)
{
	wait_queue_head_t *q = page_waitqueue(page);
	return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, false);
}

/**
 * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
 * @page: Page defining the wait queue of interest
 * @waiter: Waiter to add to the queue
 *
 * Add an arbitrary @waiter to the wait queue for the nominated @page.
 */
void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter)
{
	wait_queue_head_t *q = page_waitqueue(page);
	unsigned long flags;

	spin_lock_irqsave(&q->lock, flags);
	__add_wait_queue_entry_tail(q, waiter);
	SetPageWaiters(page);
	spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL_GPL(add_page_wait_queue);

#ifndef clear_bit_unlock_is_negative_byte

/*
 * PG_waiters is the high bit in the same byte as PG_lock.
 *
 * On x86 (and on many other architectures), we can clear PG_lock and
 * test the sign bit at the same time. But if the architecture does
 * not support that special operation, we just do this all by hand
 * instead.
 *
 * The read of PG_waiters has to be after (or concurrently with) PG_locked
 * being cleared, but a memory barrier should be unneccssary since it is
 * in the same byte as PG_locked.
 */
static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem)
{
	clear_bit_unlock(nr, mem);
	/* smp_mb__after_atomic(); */
	return test_bit(PG_waiters, mem);
}

#endif

/**
 * unlock_page - unlock a locked page
 * @page: the page
 *
 * Unlocks the page and wakes up sleepers in ___wait_on_page_locked().
 * Also wakes sleepers in wait_on_page_writeback() because the wakeup
 * mechanism between PageLocked pages and PageWriteback pages is shared.
 * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
 *
 * Note that this depends on PG_waiters being the sign bit in the byte
 * that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to
 * clear the PG_locked bit and test PG_waiters at the same time fairly
 * portably (architectures that do LL/SC can test any bit, while x86 can
 * test the sign bit).
 */
void unlock_page(struct page *page)
{
	BUILD_BUG_ON(PG_waiters != 7);
	page = compound_head(page);
	VM_BUG_ON_PAGE(!PageLocked(page), page);
	if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags))
		wake_up_page_bit(page, PG_locked);
}
EXPORT_SYMBOL(unlock_page);

/**
 * end_page_writeback - end writeback against a page
 * @page: the page
 */
void end_page_writeback(struct page *page)
{
	/*
	 * TestClearPageReclaim could be used here but it is an atomic
	 * operation and overkill in this particular case. Failing to
	 * shuffle a page marked for immediate reclaim is too mild to
	 * justify taking an atomic operation penalty at the end of
	 * ever page writeback.
	 */
	if (PageReclaim(page)) {
		ClearPageReclaim(page);
		rotate_reclaimable_page(page);
	}

	if (!test_clear_page_writeback(page))
		BUG();

	smp_mb__after_atomic();
	wake_up_page(page, PG_writeback);
}
EXPORT_SYMBOL(end_page_writeback);

/*
 * After completing I/O on a page, call this routine to update the page
 * flags appropriately
 */
void page_endio(struct page *page, bool is_write, int err)
{
	if (!is_write) {
		if (!err) {
			SetPageUptodate(page);
		} else {
			ClearPageUptodate(page);
			SetPageError(page);
		}
		unlock_page(page);
	} else {
		if (err) {
			struct address_space *mapping;

			SetPageError(page);
			mapping = page_mapping(page);
			if (mapping)
				mapping_set_error(mapping, err);
		}
		end_page_writeback(page);
	}
}
EXPORT_SYMBOL_GPL(page_endio);

/**
 * __lock_page - get a lock on the page, assuming we need to sleep to get it
 * @__page: the page to lock
 */
void __lock_page(struct page *__page)
{
	struct page *page = compound_head(__page);
	wait_queue_head_t *q = page_waitqueue(page);
	wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, true);
}
EXPORT_SYMBOL(__lock_page);

int __lock_page_killable(struct page *__page)
{
	struct page *page = compound_head(__page);
	wait_queue_head_t *q = page_waitqueue(page);
	return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE, true);
}
EXPORT_SYMBOL_GPL(__lock_page_killable);

/*
 * Return values:
 * 1 - page is locked; mmap_sem is still held.
 * 0 - page is not locked.
 *     mmap_sem has been released (up_read()), unless flags had both
 *     FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_RETRY_NOWAIT set, in
 *     which case mmap_sem is still held.
 *
 * If neither ALLOW_RETRY nor KILLABLE are set, will always return 1
 * with the page locked and the mmap_sem unperturbed.
 */
int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
			 unsigned int flags)
{
	if (flags & FAULT_FLAG_ALLOW_RETRY) {
		/*
		 * CAUTION! In this case, mmap_sem is not released
		 * even though return 0.
		 */
		if (flags & FAULT_FLAG_RETRY_NOWAIT)
			return 0;

		up_read(&mm->mmap_sem);
		if (flags & FAULT_FLAG_KILLABLE)
			wait_on_page_locked_killable(page);
		else
			wait_on_page_locked(page);
		return 0;
	} else {
		if (flags & FAULT_FLAG_KILLABLE) {
			int ret;

			ret = __lock_page_killable(page);
			if (ret) {
				up_read(&mm->mmap_sem);
				return 0;
			}
		} else
			__lock_page(page);
		return 1;
	}
}

/**
 * page_cache_next_hole - find the next hole (not-present entry)
 * @mapping: mapping
 * @index: index
 * @max_scan: maximum range to search
 *
 * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the
 * lowest indexed hole.
 *
 * Returns: the index of the hole if found, otherwise returns an index
 * outside of the set specified (in which case 'return - index >=
 * max_scan' will be true). In rare cases of index wrap-around, 0 will
 * be returned.
 *
 * page_cache_next_hole may be called under rcu_read_lock. However,
 * like radix_tree_gang_lookup, this will not atomically search a
 * snapshot of the tree at a single point in time. For example, if a
 * hole is created at index 5, then subsequently a hole is created at
 * index 10, page_cache_next_hole covering both indexes may return 10
 * if called under rcu_read_lock.
 */
pgoff_t page_cache_next_hole(struct address_space *mapping,
			     pgoff_t index, unsigned long max_scan)
{
	unsigned long i;

	for (i = 0; i < max_scan; i++) {
		struct page *page;

		page = radix_tree_lookup(&mapping->page_tree, index);
		if (!page || radix_tree_exceptional_entry(page))
			break;
		index++;
		if (index == 0)
			break;
	}

	return index;
}
EXPORT_SYMBOL(page_cache_next_hole);

/**
 * page_cache_prev_hole - find the prev hole (not-present entry)
 * @mapping: mapping
 * @index: index
 * @max_scan: maximum range to search
 *
 * Search backwards in the range [max(index-max_scan+1, 0), index] for
 * the first hole.
 *
 * Returns: the index of the hole if found, otherwise returns an index
 * outside of the set specified (in which case 'index - return >=
 * max_scan' will be true). In rare cases of wrap-around, ULONG_MAX
 * will be returned.
 *
 * page_cache_prev_hole may be called under rcu_read_lock. However,
 * like radix_tree_gang_lookup, this will not atomically search a
 * snapshot of the tree at a single point in time. For example, if a
 * hole is created at index 10, then subsequently a hole is created at
 * index 5, page_cache_prev_hole covering both indexes may return 5 if
 * called under rcu_read_lock.
 */
pgoff_t page_cache_prev_hole(struct address_space *mapping,
			     pgoff_t index, unsigned long max_scan)
{
	unsigned long i;

	for (i = 0; i < max_scan; i++) {
		struct page *page;

		page = radix_tree_lookup(&mapping->page_tree, index);
		if (!page || radix_tree_exceptional_entry(page))
			break;
		index--;
		if (index == ULONG_MAX)
			break;
	}

	return index;
}
EXPORT_SYMBOL(page_cache_prev_hole);

/**
 * find_get_entry - find and get a page cache entry
 * @mapping: the address_space to search
 * @offset: the page cache index
 *
 * Looks up the page cache slot at @mapping & @offset.  If there is a
 * page cache page, it is returned with an increased refcount.
 *
 * If the slot holds a shadow entry of a previously evicted page, or a
 * swap entry from shmem/tmpfs, it is returned.
 *
 * Otherwise, %NULL is returned.
 */
struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)
{
	void **pagep;
	struct page *head, *page;

	rcu_read_lock();
repeat:
	page = NULL;
	pagep = radix_tree_lookup_slot(&mapping->page_tree, offset);
	if (pagep) {
		page = radix_tree_deref_slot(pagep);
		if (unlikely(!page))
			goto out;
		if (radix_tree_exception(page)) {
			if (radix_tree_deref_retry(page))
				goto repeat;
			/*
			 * A shadow entry of a recently evicted page,
			 * or a swap entry from shmem/tmpfs.  Return
			 * it without attempting to raise page count.
			 */
			goto out;
		}

		head = compound_head(page);
		if (!page_cache_get_speculative(head))
			goto repeat;

		/* The page was split under us? */
		if (compound_head(page) != head) {
			put_page(head);
			goto repeat;
		}

		/*
		 * Has the page moved?
		 * This is part of the lockless pagecache protocol. See
		 * include/linux/pagemap.h for details.
		 */
		if (unlikely(page != *pagep)) {
			put_page(head);
			goto repeat;
		}
	}
out:
	rcu_read_unlock();

	return page;
}
EXPORT_SYMBOL(find_get_entry);

/**
 * find_lock_entry - locate, pin and lock a page cache entry
 * @mapping: the address_space to search
 * @offset: the page cache index
 *
 * Looks up the page cache slot at @mapping & @offset.  If there is a
 * page cache page, it is returned locked and with an increased
 * refcount.
 *
 * If the slot holds a shadow entry of a previously evicted page, or a
 * swap entry from shmem/tmpfs, it is returned.
 *
 * Otherwise, %NULL is returned.
 *
 * find_lock_entry() may sleep.
 */
struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset)
{
	struct page *page;

repeat:
	page = find_get_entry(mapping, offset);
	if (page && !radix_tree_exception(page)) {
		lock_page(page);
		/* Has the page been truncated? */
		if (unlikely(page_mapping(page) != mapping)) {
			unlock_page(page);
			put_page(page);
			goto repeat;
		}
		VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page);
	}
	return page;
}
EXPORT_SYMBOL(find_lock_entry);

/**
 * pagecache_get_page - find and get a page reference
 * @mapping: the address_space to search
 * @offset: the page index
 * @fgp_flags: PCG flags
 * @gfp_mask: gfp mask to use for the page cache data page allocation
 *
 * Looks up the page cache slot at @mapping & @offset.
 *
 * PCG flags modify how the page is returned.
 *
 * @fgp_flags can be:
 *
 * - FGP_ACCESSED: the page will be marked accessed
 * - FGP_LOCK: Page is return locked
 * - FGP_CREAT: If page is not present then a new page is allocated using
 *   @gfp_mask and added to the page cache and the VM's LRU
 *   list. The page is returned locked and with an increased
 *   refcount. Otherwise, NULL is returned.
 *
 * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even
 * if the GFP flags specified for FGP_CREAT are atomic.
 *
 * If there is a page cache page, it is returned with an increased refcount.
 */
struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
	int fgp_flags, gfp_t gfp_mask)
{
	struct page *page;

repeat:
	page = find_get_entry(mapping, offset);
	if (radix_tree_exceptional_entry(page))
		page = NULL;
	if (!page)
		goto no_page;

	if (fgp_flags & FGP_LOCK) {
		if (fgp_flags & FGP_NOWAIT) {
			if (!trylock_page(page)) {
				put_page(page);
				return NULL;
			}
		} else {
			lock_page(page);
		}

		/* Has the page been truncated? */
		if (unlikely(page->mapping != mapping)) {
			unlock_page(page);
			put_page(page);
			goto repeat;
		}
		VM_BUG_ON_PAGE(page->index != offset, page);
	}

	if (page && (fgp_flags & FGP_ACCESSED))
		mark_page_accessed(page);

no_page:
	if (!page && (fgp_flags & FGP_CREAT)) {
		int err;
		if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping))
			gfp_mask |= __GFP_WRITE;
		if (fgp_flags & FGP_NOFS)
			gfp_mask &= ~__GFP_FS;

		page = __page_cache_alloc(gfp_mask);
		if (!page)
			return NULL;

		if (WARN_ON_ONCE(!(fgp_flags & FGP_LOCK)))
			fgp_flags |= FGP_LOCK;

		/* Init accessed so avoid atomic mark_page_accessed later */
		if (fgp_flags & FGP_ACCESSED)
			__SetPageReferenced(page);

		err = add_to_page_cache_lru(page, mapping, offset,
				gfp_mask & GFP_RECLAIM_MASK);
		if (unlikely(err)) {
			put_page(page);
			page = NULL;
			if (err == -EEXIST)
				goto repeat;
		}
	}

	return page;
}
EXPORT_SYMBOL(pagecache_get_page);

/**
 * find_get_entries - gang pagecache lookup
 * @mapping:	The address_space to search
 * @start:	The starting page cache index
 * @nr_entries:	The maximum number of entries
 * @entries:	Where the resulting entries are placed
 * @indices:	The cache indices corresponding to the entries in @entries
 *
 * find_get_entries() will search for and return a group of up to
 * @nr_entries entries in the mapping.  The entries are placed at
 * @entries.  find_get_entries() takes a reference against any actual
 * pages it returns.
 *
 * The search returns a group of mapping-contiguous page cache entries
 * with ascending indexes.  There may be holes in the indices due to
 * not-present pages.
 *
 * Any shadow entries of evicted pages, or swap entries from
 * shmem/tmpfs, are included in the returned array.
 *
 * find_get_entries() returns the number of pages and shadow entries
 * which were found.
 */
unsigned find_get_entries(struct address_space *mapping,
			  pgoff_t start, unsigned int nr_entries,
			  struct page **entries, pgoff_t *indices)
{
	void **slot;
	unsigned int ret = 0;
	struct radix_tree_iter iter;

	if (!nr_entries)
		return 0;

	rcu_read_lock();
	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
		struct page *head, *page;
repeat:
		page = radix_tree_deref_slot(slot);
		if (unlikely(!page))
			continue;
		if (radix_tree_exception(page)) {
			if (radix_tree_deref_retry(page)) {
				slot = radix_tree_iter_retry(&iter);
				continue;
			}
			/*
			 * A shadow entry of a recently evicted page, a swap
			 * entry from shmem/tmpfs or a DAX entry.  Return it
			 * without attempting to raise page count.
			 */
			goto export;
		}

		head = compound_head(page);
		if (!page_cache_get_speculative(head))
			goto repeat;

		/* The page was split under us? */
		if (compound_head(page) != head) {
			put_page(head);
			goto repeat;
		}

		/* Has the page moved? */
		if (unlikely(page != *slot)) {
			put_page(head);
			goto repeat;
		}
export:
		indices[ret] = iter.index;
		entries[ret] = page;
		if (++ret == nr_entries)
			break;
	}
	rcu_read_unlock();
	return ret;
}

/**
 * find_get_pages - gang pagecache lookup
 * @mapping:	The address_space to search
 * @start:	The starting page index
 * @nr_pages:	The maximum number of pages
 * @pages:	Where the resulting pages are placed
 *
 * find_get_pages() will search for and return a group of up to
 * @nr_pages pages in the mapping.  The pages are placed at @pages.
 * find_get_pages() takes a reference against the returned pages.
 *
 * The search returns a group of mapping-contiguous pages with ascending
 * indexes.  There may be holes in the indices due to not-present pages.
 *
 * find_get_pages() returns the number of pages which were found.
 */
unsigned find_get_pages(struct address_space *mapping, pgoff_t start,
			    unsigned int nr_pages, struct page **pages)
{
	struct radix_tree_iter iter;
	void **slot;
	unsigned ret = 0;

	if (unlikely(!nr_pages))
		return 0;

	rcu_read_lock();
	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
		struct page *head, *page;
repeat:
		page = radix_tree_deref_slot(slot);
		if (unlikely(!page))
			continue;

		if (radix_tree_exception(page)) {
			if (radix_tree_deref_retry(page)) {
				slot = radix_tree_iter_retry(&iter);
				continue;
			}
			/*
			 * A shadow entry of a recently evicted page,
			 * or a swap entry from shmem/tmpfs.  Skip
			 * over it.
			 */
			continue;
		}

		head = compound_head(page);
		if (!page_cache_get_speculative(head))
			goto repeat;

		/* The page was split under us? */
		if (compound_head(page) != head) {
			put_page(head);
			goto repeat;
		}

		/* Has the page moved? */
		if (unlikely(page != *slot)) {
			put_page(head);
			goto repeat;
		}

		pages[ret] = page;
		if (++ret == nr_pages)
			break;
	}

	rcu_read_unlock();
	return ret;
}

/**
 * find_get_pages_contig - gang contiguous pagecache lookup
 * @mapping:	The address_space to search
 * @index:	The starting page index
 * @nr_pages:	The maximum number of pages
 * @pages:	Where the resulting pages are placed
 *
 * find_get_pages_contig() works exactly like find_get_pages(), except
 * that the returned number of pages are guaranteed to be contiguous.
 *
 * find_get_pages_contig() returns the number of pages which were found.
 */
unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
			       unsigned int nr_pages, struct page **pages)
{
	struct radix_tree_iter iter;
	void **slot;
	unsigned int ret = 0;

	if (unlikely(!nr_pages))
		return 0;

	rcu_read_lock();
	radix_tree_for_each_contig(slot, &mapping->page_tree, &iter, index) {
		struct page *head, *page;
repeat:
		page = radix_tree_deref_slot(slot);
		/* The hole, there no reason to continue */
		if (unlikely(!page))
			break;

		if (radix_tree_exception(page)) {
			if (radix_tree_deref_retry(page)) {
				slot = radix_tree_iter_retry(&iter);
				continue;
			}
			/*
			 * A shadow entry of a recently evicted page,
			 * or a swap entry from shmem/tmpfs.  Stop
			 * looking for contiguous pages.
			 */
			break;
		}

		head = compound_head(page);
		if (!page_cache_get_speculative(head))
			goto repeat;

		/* The page was split under us? */
		if (compound_head(page) != head) {
			put_page(head);
			goto repeat;
		}

		/* Has the page moved? */
		if (unlikely(page != *slot)) {
			put_page(head);
			goto repeat;
		}

		/*
		 * must check mapping and index after taking the ref.
		 * otherwise we can get both false positives and false
		 * negatives, which is just confusing to the caller.
		 */
		if (page->mapping == NULL || page_to_pgoff(page) != iter.index) {
			put_page(page);
			break;
		}

		pages[ret] = page;
		if (++ret == nr_pages)
			break;
	}
	rcu_read_unlock();
	return ret;
}
EXPORT_SYMBOL(find_get_pages_contig);

/**
 * find_get_pages_tag - find and return pages that match @tag
 * @mapping:	the address_space to search
 * @index:	the starting page index
 * @tag:	the tag index
 * @nr_pages:	the maximum number of pages
 * @pages:	where the resulting pages are placed
 *
 * Like find_get_pages, except we only return pages which are tagged with
 * @tag.   We update @index to index the next page for the traversal.
 */
unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
			int tag, unsigned int nr_pages, struct page **pages)
{
	struct radix_tree_iter iter;
	void **slot;
	unsigned ret = 0;

	if (unlikely(!nr_pages))
		return 0;

	rcu_read_lock();
	radix_tree_for_each_tagged(slot, &mapping->page_tree,
				   &iter, *index, tag) {
		struct page *head, *page;
repeat:
		page = radix_tree_deref_slot(slot);
		if (unlikely(!page))
			continue;

		if (radix_tree_exception(page)) {
			if (radix_tree_deref_retry(page)) {
				slot = radix_tree_iter_retry(&iter);
				continue;
			}
			/*
			 * A shadow entry of a recently evicted page.
			 *
			 * Those entries should never be tagged, but
			 * this tree walk is lockless and the tags are
			 * looked up in bulk, one radix tree node at a
			 * time, so there is a sizable window for page
			 * reclaim to evict a page we saw tagged.
			 *
			 * Skip over it.
			 */
			continue;
		}

		head = compound_head(page);
		if (!page_cache_get_speculative(head))
			goto repeat;

		/* The page was split under us? */
		if (compound_head(page) != head) {
			put_page(head);
			goto repeat;
		}

		/* Has the page moved? */
		if (unlikely(page != *slot)) {
			put_page(head);
			goto repeat;
		}

		pages[ret] = page;
		if (++ret == nr_pages)
			break;
	}

	rcu_read_unlock();

	if (ret)
		*index = pages[ret - 1]->index + 1;

	return ret;
}
EXPORT_SYMBOL(find_get_pages_tag);

/**
 * find_get_entries_tag - find and return entries that match @tag
 * @mapping:	the address_space to search
 * @start:	the starting page cache index
 * @tag:	the tag index
 * @nr_entries:	the maximum number of entries
 * @entries:	where the resulting entries are placed
 * @indices:	the cache indices corresponding to the entries in @entries
 *
 * Like find_get_entries, except we only return entries which are tagged with
 * @tag.
 */
unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
			int tag, unsigned int nr_entries,
			struct page **entries, pgoff_t *indices)
{
	void **slot;
	unsigned int ret = 0;
	struct radix_tree_iter iter;

	if (!nr_entries)
		return 0;

	rcu_read_lock();
	radix_tree_for_each_tagged(slot, &mapping->page_tree,
				   &iter, start, tag) {
		struct page *head, *page;
repeat:
		page = radix_tree_deref_slot(slot);
		if (unlikely(!page))
			continue;
		if (radix_tree_exception(page)) {
			if (radix_tree_deref_retry(page)) {
				slot = radix_tree_iter_retry(&iter);
				continue;
			}

			/*
			 * A shadow entry of a recently evicted page, a swap
			 * entry from shmem/tmpfs or a DAX entry.  Return it
			 * without attempting to raise page count.
			 */
			goto export;
		}

		head = compound_head(page);
		if (!page_cache_get_speculative(head))
			goto repeat;

		/* The page was split under us? */
		if (compound_head(page) != head) {
			put_page(head);
			goto repeat;
		}

		/* Has the page moved? */
		if (unlikely(page != *slot)) {
			put_page(head);
			goto repeat;
		}
export:
		indices[ret] = iter.index;
		entries[ret] = page;
		if (++ret == nr_entries)
			break;
	}
	rcu_read_unlock();
	return ret;
}
EXPORT_SYMBOL(find_get_entries_tag);

/*
 * CD/DVDs are error prone. When a medium error occurs, the driver may fail
 * a _large_ part of the i/o request. Imagine the worst scenario:
 *
 *      ---R__________________________________________B__________
 *         ^ reading here                             ^ bad block(assume 4k)
 *
 * read(R) => miss => readahead(R...B) => media error => frustrating retries
 * => failing the whole request => read(R) => read(R+1) =>
 * readahead(R+1...B+1) => bang => read(R+2) => read(R+3) =>
 * readahead(R+3...B+2) => bang => read(R+3) => read(R+4) =>
 * readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ......
 *
 * It is going insane. Fix it by quickly scaling down the readahead size.
 */
static void shrink_readahead_size_eio(struct file *filp,
					struct file_ra_state *ra)
{
	ra->ra_pages /= 4;
}

/**
 * do_generic_file_read - generic file read routine
 * @filp:	the file to read
 * @ppos:	current file position
 * @iter:	data destination
 * @written:	already copied
 *
 * This is a generic file read routine, and uses the
 * mapping->a_ops->readpage() function for the actual low-level stuff.
 *
 * This is really ugly. But the goto's actually try to clarify some
 * of the logic when it comes to error handling etc.
 */
static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos,
		struct iov_iter *iter, ssize_t written)
{
	struct address_space *mapping = filp->f_mapping;
	struct inode *inode = mapping->host;
	struct file_ra_state *ra = &filp->f_ra;
	pgoff_t index;
	pgoff_t last_index;
	pgoff_t prev_index;
	unsigned long offset;      /* offset into pagecache page */
	unsigned int prev_offset;
	int error = 0;

	if (unlikely(*ppos >= inode->i_sb->s_maxbytes))
		return 0;
	iov_iter_truncate(iter, inode->i_sb->s_maxbytes);

	index = *ppos >> PAGE_SHIFT;
	prev_index = ra->prev_pos >> PAGE_SHIFT;
	prev_offset = ra->prev_pos & (PAGE_SIZE-1);
	last_index = (*ppos + iter->count + PAGE_SIZE-1) >> PAGE_SHIFT;
	offset = *ppos & ~PAGE_MASK;

	for (;;) {
		struct page *page;
		pgoff_t end_index;
		loff_t isize;
		unsigned long nr, ret;

		cond_resched();
find_page:
		if (fatal_signal_pending(current)) {
			error = -EINTR;
			goto out;
		}

		page = find_get_page(mapping, index);
		if (!page) {
			page_cache_sync_readahead(mapping,
					ra, filp,
					index, last_index - index);
			page = find_get_page(mapping, index);
			if (unlikely(page == NULL))
				goto no_cached_page;
		}
		if (PageReadahead(page)) {
			page_cache_async_readahead(mapping,
					ra, filp, page,
					index, last_index - index);
		}
		if (!PageUptodate(page)) {
			/*
			 * See comment in do_read_cache_page on why
			 * wait_on_page_locked is used to avoid unnecessarily
			 * serialisations and why it's safe.
			 */
			error = wait_on_page_locked_killable(page);
			if (unlikely(error))
				goto readpage_error;
			if (PageUptodate(page))
				goto page_ok;

			if (inode->i_blkbits == PAGE_SHIFT ||
					!mapping->a_ops->is_partially_uptodate)
				goto page_not_up_to_date;
			/* pipes can't handle partially uptodate pages */
			if (unlikely(iter->type & ITER_PIPE))
				goto page_not_up_to_date;
			if (!trylock_page(page))
				goto page_not_up_to_date;
			/* Did it get truncated before we got the lock? */
			if (!page->mapping)
				goto page_not_up_to_date_locked;
			if (!mapping->a_ops->is_partially_uptodate(page,
							offset, iter->count))
				goto page_not_up_to_date_locked;
			unlock_page(page);
		}
page_ok:
		/*
		 * i_size must be checked after we know the page is Uptodate.
		 *
		 * Checking i_size after the check allows us to calculate
		 * the correct value for "nr", which means the zero-filled
		 * part of the page is not copied back to userspace (unless
		 * another truncate extends the file - this is desired though).
		 */

		isize = i_size_read(inode);
		end_index = (isize - 1) >> PAGE_SHIFT;
		if (unlikely(!isize || index > end_index)) {
			put_page(page);
			goto out;
		}

		/* nr is the maximum number of bytes to copy from this page */
		nr = PAGE_SIZE;
		if (index == end_index) {
			nr = ((isize - 1) & ~PAGE_MASK) + 1;
			if (nr <= offset) {
				put_page(page);
				goto out;
			}
		}
		nr = nr - offset;

		/* If users can be writing to this page using arbitrary
		 * virtual addresses, take care about potential aliasing
		 * before reading the page on the kernel side.
		 */
		if (mapping_writably_mapped(mapping))
			flush_dcache_page(page);

		/*
		 * When a sequential read accesses a page several times,
		 * only mark it as accessed the first time.
		 */
		if (prev_index != index || offset != prev_offset)
			mark_page_accessed(page);
		prev_index = index;

		/*
		 * Ok, we have the page, and it's up-to-date, so
		 * now we can copy it to user space...
		 */

		ret = copy_page_to_iter(page, offset, nr, iter);
		offset += ret;
		index += offset >> PAGE_SHIFT;
		offset &= ~PAGE_MASK;
		prev_offset = offset;

		put_page(page);
		written += ret;
		if (!iov_iter_count(iter))
			goto out;
		if (ret < nr) {
			error = -EFAULT;
			goto out;
		}
		continue;

page_not_up_to_date:
		/* Get exclusive access to the page ... */
		error = lock_page_killable(page);
		if (unlikely(error))
			goto readpage_error;

page_not_up_to_date_locked:
		/* Did it get truncated before we got the lock? */
		if (!page->mapping) {
			unlock_page(page);
			put_page(page);
			continue;
		}

		/* Did somebody else fill it already? */
		if (PageUptodate(page)) {
			unlock_page(page);
			goto page_ok;
		}

readpage:
		/*
		 * A previous I/O error may have been due to temporary
		 * failures, eg. multipath errors.
		 * PG_error will be set again if readpage fails.
		 */
		ClearPageError(page);
		/* Start the actual read. The read will unlock the page. */
		error = mapping->a_ops->readpage(filp, page);

		if (unlikely(error)) {
			if (error == AOP_TRUNCATED_PAGE) {
				put_page(page);
				error = 0;
				goto find_page;
			}
			goto readpage_error;
		}

		if (!PageUptodate(page)) {
			error = lock_page_killable(page);
			if (unlikely(error))
				goto readpage_error;
			if (!PageUptodate(page)) {
				if (page->mapping == NULL) {
					/*
					 * invalidate_mapping_pages got it
					 */
					unlock_page(page);
					put_page(page);
					goto find_page;
				}
				unlock_page(page);
				shrink_readahead_size_eio(filp, ra);
				error = -EIO;
				goto readpage_error;
			}
			unlock_page(page);
		}

		goto page_ok;

readpage_error:
		/* UHHUH! A synchronous read error occurred. Report it */
		put_page(page);
		goto out;

no_cached_page:
		/*
		 * Ok, it wasn't cached, so we need to create a new
		 * page..
		 */
		page = page_cache_alloc_cold(mapping);
		if (!page) {
			error = -ENOMEM;
			goto out;
		}
		error = add_to_page_cache_lru(page, mapping, index,
				mapping_gfp_constraint(mapping, GFP_KERNEL));
		if (error) {
			put_page(page);
			if (error == -EEXIST) {
				error = 0;
				goto find_page;
			}
			goto out;
		}
		goto readpage;
	}

out:
	ra->prev_pos = prev_index;
	ra->prev_pos <<= PAGE_SHIFT;
	ra->prev_pos |= prev_offset;

	*ppos = ((loff_t)index << PAGE_SHIFT) + offset;
	file_accessed(filp);
	return written ? written : error;
}

/**
 * generic_file_read_iter - generic filesystem read routine
 * @iocb:	kernel I/O control block
 * @iter:	destination for the data read
 *
 * This is the "read_iter()" routine for all filesystems
 * that can use the page cache directly.
 */
ssize_t
generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
{
	struct file *file = iocb->ki_filp;
	ssize_t retval = 0;
	size_t count = iov_iter_count(iter);

	if (!count)
		goto out; /* skip atime */

	if (iocb->ki_flags & IOCB_DIRECT) {
		struct address_space *mapping = file->f_mapping;
		struct inode *inode = mapping->host;
		loff_t size;

		size = i_size_read(inode);
		if (iocb->ki_flags & IOCB_NOWAIT) {
			if (filemap_range_has_page(mapping, iocb->ki_pos,
						   iocb->ki_pos + count - 1))
				return -EAGAIN;
		} else {
			retval = filemap_write_and_wait_range(mapping,
						iocb->ki_pos,
					        iocb->ki_pos + count - 1);
			if (retval < 0)
				goto out;
		}

		file_accessed(file);

		retval = mapping->a_ops->direct_IO(iocb, iter);
		if (retval >= 0) {
			iocb->ki_pos += retval;
			count -= retval;
		}
		iov_iter_revert(iter, count - iov_iter_count(iter));

		/*
		 * Btrfs can have a short DIO read if we encounter
		 * compressed extents, so if there was an error, or if
		 * we've already read everything we wanted to, or if
		 * there was a short read because we hit EOF, go ahead
		 * and return.  Otherwise fallthrough to buffered io for
		 * the rest of the read.  Buffered reads will not work for
		 * DAX files, so don't bother trying.
		 */
		if (retval < 0 || !count || iocb->ki_pos >= size ||
		    IS_DAX(inode))
			goto out;
	}

	retval = do_generic_file_read(file, &iocb->ki_pos, iter, retval);
out:
	return retval;
}
EXPORT_SYMBOL(generic_file_read_iter);

#ifdef CONFIG_MMU
/**
 * page_cache_read - adds requested page to the page cache if not already there
 * @file:	file to read
 * @offset:	page index
 * @gfp_mask:	memory allocation flags
 *
 * This adds the requested page to the page cache if it isn't already there,
 * and schedules an I/O to read in its contents from disk.
 */
static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask)
{
	struct address_space *mapping = file->f_mapping;
	struct page *page;
	int ret;

	do {
		page = __page_cache_alloc(gfp_mask|__GFP_COLD);
		if (!page)
			return -ENOMEM;

		ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask & GFP_KERNEL);
		if (ret == 0)
			ret = mapping->a_ops->readpage(file, page);
		else if (ret == -EEXIST)
			ret = 0; /* losing race to add is OK */

		put_page(page);

	} while (ret == AOP_TRUNCATED_PAGE);

	return ret;
}

#define MMAP_LOTSAMISS  (100)

/*
 * Synchronous readahead happens when we don't even find
 * a page in the page cache at all.
 */
static void do_sync_mmap_readahead(struct vm_area_struct *vma,
				   struct file_ra_state *ra,
				   struct file *file,
				   pgoff_t offset)
{
	struct address_space *mapping = file->f_mapping;

	/* If we don't want any read-ahead, don't bother */
	if (vma->vm_flags & VM_RAND_READ)
		return;
	if (!ra->ra_pages)
		return;

	if (vma->vm_flags & VM_SEQ_READ) {
		page_cache_sync_readahead(mapping, ra, file, offset,
					  ra->ra_pages);
		return;
	}

	/* Avoid banging the cache line if not needed */
	if (ra->mmap_miss < MMAP_LOTSAMISS * 10)
		ra->mmap_miss++;

	/*
	 * Do we miss much more than hit in this file? If so,
	 * stop bothering with read-ahead. It will only hurt.
	 */
	if (ra->mmap_miss > MMAP_LOTSAMISS)
		return;

	/*
	 * mmap read-around
	 */
	ra->start = max_t(long, 0, offset - ra->ra_pages / 2);
	ra->size = ra->ra_pages;
	ra->async_size = ra->ra_pages / 4;
	ra_submit(ra, mapping, file);
}

/*
 * Asynchronous readahead happens when we find the page and PG_readahead,
 * so we want to possibly extend the readahead further..
 */
static void do_async_mmap_readahead(struct vm_area_struct *vma,
				    struct file_ra_state *ra,
				    struct file *file,
				    struct page *page,
				    pgoff_t offset)
{
	struct address_space *mapping = file->f_mapping;

	/* If we don't want any read-ahead, don't bother */
	if (vma->vm_flags & VM_RAND_READ)
		return;
	if (ra->mmap_miss > 0)
		ra->mmap_miss--;
	if (PageReadahead(page))
		page_cache_async_readahead(mapping, ra, file,
					   page, offset, ra->ra_pages);
}

/**
 * filemap_fault - read in file data for page fault handling
 * @vmf:	struct vm_fault containing details of the fault
 *
 * filemap_fault() is invoked via the vma operations vector for a
 * mapped memory region to read in file data during a page fault.
 *
 * The goto's are kind of ugly, but this streamlines the normal case of having
 * it in the page cache, and handles the special cases reasonably without
 * having a lot of duplicated code.
 *
 * vma->vm_mm->mmap_sem must be held on entry.
 *
 * If our return value has VM_FAULT_RETRY set, it's because
 * lock_page_or_retry() returned 0.
 * The mmap_sem has usually been released in this case.
 * See __lock_page_or_retry() for the exception.
 *
 * If our return value does not have VM_FAULT_RETRY set, the mmap_sem
 * has not been released.
 *
 * We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set.
 */
int filemap_fault(struct vm_fault *vmf)
{
	int error;
	struct file *file = vmf->vma->vm_file;
	struct address_space *mapping = file->f_mapping;
	struct file_ra_state *ra = &file->f_ra;
	struct inode *inode = mapping->host;
	pgoff_t offset = vmf->pgoff;
	pgoff_t max_off;
	struct page *page;
	int ret = 0;

	max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
	if (unlikely(offset >= max_off))
		return VM_FAULT_SIGBUS;

	/*
	 * Do we have something in the page cache already?
	 */
	page = find_get_page(mapping, offset);
	if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) {
		/*
		 * We found the page, so try async readahead before
		 * waiting for the lock.
		 */
		do_async_mmap_readahead(vmf->vma, ra, file, page, offset);
	} else if (!page) {
		/* No page in the page cache at all */
		do_sync_mmap_readahead(vmf->vma, ra, file, offset);
		count_vm_event(PGMAJFAULT);
		count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT);
		ret = VM_FAULT_MAJOR;
retry_find:
		page = find_get_page(mapping, offset);
		if (!page)
			goto no_cached_page;
	}

	if (!lock_page_or_retry(page, vmf->vma->vm_mm, vmf->flags)) {
		put_page(page);
		return ret | VM_FAULT_RETRY;
	}

	/* Did it get truncated? */
	if (unlikely(page->mapping != mapping)) {
		unlock_page(page);
		put_page(page);
		goto retry_find;
	}
	VM_BUG_ON_PAGE(page->index != offset, page);

	/*
	 * We have a locked page in the page cache, now we need to check
	 * that it's up-to-date. If not, it is going to be due to an error.
	 */
	if (unlikely(!PageUptodate(page)))
		goto page_not_uptodate;

	/*
	 * Found the page and have a reference on it.
	 * We must recheck i_size under page lock.
	 */
	max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
	if (unlikely(offset >= max_off)) {
		unlock_page(page);
		put_page(page);
		return VM_FAULT_SIGBUS;
	}

	vmf->page = page;
	return ret | VM_FAULT_LOCKED;

no_cached_page:
	/*
	 * We're only likely to ever get here if MADV_RANDOM is in
	 * effect.
	 */
	error = page_cache_read(file, offset, vmf->gfp_mask);

	/*
	 * The page we want has now been added to the page cache.
	 * In the unlikely event that someone removed it in the
	 * meantime, we'll just come back here and read it again.
	 */
	if (error >= 0)
		goto retry_find;

	/*
	 * An error return from page_cache_read can result if the
	 * system is low on memory, or a problem occurs while trying
	 * to schedule I/O.
	 */
	if (error == -ENOMEM)
		return VM_FAULT_OOM;
	return VM_FAULT_SIGBUS;

page_not_uptodate:
	/*
	 * Umm, take care of errors if the page isn't up-to-date.
	 * Try to re-read it _once_. We do this synchronously,
	 * because there really aren't any performance issues here
	 * and we need to check for errors.
	 */
	ClearPageError(page);
	error = mapping->a_ops->readpage(file, page);
	if (!error) {
		wait_on_page_locked(page);
		if (!PageUptodate(page))
			error = -EIO;
	}
	put_page(page);

	if (!error || error == AOP_TRUNCATED_PAGE)
		goto retry_find;

	/* Things didn't work out. Return zero to tell the mm layer so. */
	shrink_readahead_size_eio(file, ra);
	return VM_FAULT_SIGBUS;
}
EXPORT_SYMBOL(filemap_fault);

void filemap_map_pages(struct vm_fault *vmf,
		pgoff_t start_pgoff, pgoff_t end_pgoff)
{
	struct radix_tree_iter iter;
	void **slot;
	struct file *file = vmf->vma->vm_file;
	struct address_space *mapping = file->f_mapping;
	pgoff_t last_pgoff = start_pgoff;
	unsigned long max_idx;
	struct page *head, *page;

	rcu_read_lock();
	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter,
			start_pgoff) {
		if (iter.index > end_pgoff)
			break;
repeat:
		page = radix_tree_deref_slot(slot);
		if (unlikely(!page))
			goto next;
		if (radix_tree_exception(page)) {
			if (radix_tree_deref_retry(page)) {
				slot = radix_tree_iter_retry(&iter);
				continue;
			}
			goto next;
		}

		head = compound_head(page);
		if (!page_cache_get_speculative(head))
			goto repeat;

		/* The page was split under us? */
		if (compound_head(page) != head) {
			put_page(head);
			goto repeat;
		}

		/* Has the page moved? */
		if (unlikely(page != *slot)) {
			put_page(head);
			goto repeat;
		}

		if (!PageUptodate(page) ||
				PageReadahead(page) ||
				PageHWPoison(page))
			goto skip;
		if (!trylock_page(page))
			goto skip;

		if (page->mapping != mapping || !PageUptodate(page))
			goto unlock;

		max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
		if (page->index >= max_idx)
			goto unlock;

		if (file->f_ra.mmap_miss > 0)
			file->f_ra.mmap_miss--;

		vmf->address += (iter.index - last_pgoff) << PAGE_SHIFT;
		if (vmf->pte)
			vmf->pte += iter.index - last_pgoff;
		last_pgoff = iter.index;
		if (alloc_set_pte(vmf, NULL, page))
			goto unlock;
		unlock_page(page);
		goto next;
unlock:
		unlock_page(page);
skip:
		put_page(page);
next:
		/* Huge page is mapped? No need to proceed. */
		if (pmd_trans_huge(*vmf->pmd))
			break;
		if (iter.index == end_pgoff)
			break;
	}
	rcu_read_unlock();
}
EXPORT_SYMBOL(filemap_map_pages);

int filemap_page_mkwrite(struct vm_fault *vmf)
{
	struct page *page = vmf->page;
	struct inode *inode = file_inode(vmf->vma->vm_file);
	int ret = VM_FAULT_LOCKED;

	sb_start_pagefault(inode->i_sb);
	file_update_time(vmf->vma->vm_file);
	lock_page(page);
	if (page->mapping != inode->i_mapping) {
		unlock_page(page);
		ret = VM_FAULT_NOPAGE;
		goto out;
	}
	/*
	 * We mark the page dirty already here so that when freeze is in
	 * progress, we are guaranteed that writeback during freezing will
	 * see the dirty page and writeprotect it again.
	 */
	set_page_dirty(page);
	wait_for_stable_page(page);
out:
	sb_end_pagefault(inode->i_sb);
	return ret;
}
EXPORT_SYMBOL(filemap_page_mkwrite);

const struct vm_operations_struct generic_file_vm_ops = {
	.fault		= filemap_fault,
	.map_pages	= filemap_map_pages,
	.page_mkwrite	= filemap_page_mkwrite,
};

/* This is used for a general mmap of a disk file */

int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
{
	struct address_space *mapping = file->f_mapping;

	if (!mapping->a_ops->readpage)
		return -ENOEXEC;
	file_accessed(file);
	vma->vm_ops = &generic_file_vm_ops;
	return 0;
}

/*
 * This is for filesystems which do not implement ->writepage.
 */
int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma)
{
	if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE))
		return -EINVAL;
	return generic_file_mmap(file, vma);
}
#else
int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
{
	return -ENOSYS;
}
int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma)
{
	return -ENOSYS;
}
#endif /* CONFIG_MMU */

EXPORT_SYMBOL(generic_file_mmap);
EXPORT_SYMBOL(generic_file_readonly_mmap);

static struct page *wait_on_page_read(struct page *page)
{
	if (!IS_ERR(page)) {
		wait_on_page_locked(page);
		if (!PageUptodate(page)) {
			put_page(page);
			page = ERR_PTR(-EIO);
		}
	}
	return page;
}

static struct page *do_read_cache_page(struct address_space *mapping,
				pgoff_t index,
				int (*filler)(void *, struct page *),
				void *data,
				gfp_t gfp)
{
	struct page *page;
	int err;
repeat:
	page = find_get_page(mapping, index);
	if (!page) {
		page = __page_cache_alloc(gfp | __GFP_COLD);
		if (!page)
			return ERR_PTR(-ENOMEM);
		err = add_to_page_cache_lru(page, mapping, index, gfp);
		if (unlikely(err)) {
			put_page(page);
			if (err == -EEXIST)
				goto repeat;
			/* Presumably ENOMEM for radix tree node */
			return ERR_PTR(err);
		}

filler:
		err = filler(data, page);
		if (err < 0) {
			put_page(page);
			return ERR_PTR(err);
		}

		page = wait_on_page_read(page);
		if (IS_ERR(page))
			return page;
		goto out;
	}
	if (PageUptodate(page))
		goto out;

	/*
	 * Page is not up to date and may be locked due one of the following
	 * case a: Page is being filled and the page lock is held
	 * case b: Read/write error clearing the page uptodate status
	 * case c: Truncation in progress (page locked)
	 * case d: Reclaim in progress
	 *
	 * Case a, the page will be up to date when the page is unlocked.
	 *    There is no need to serialise on the page lock here as the page
	 *    is pinned so the lock gives no additional protection. Even if the
	 *    the page is truncated, the data is still valid if PageUptodate as
	 *    it's a race vs truncate race.
	 * Case b, the page will not be up to date
	 * Case c, the page may be truncated but in itself, the data may still
	 *    be valid after IO completes as it's a read vs truncate race. The
	 *    operation must restart if the page is not uptodate on unlock but
	 *    otherwise serialising on page lock to stabilise the mapping gives
	 *    no additional guarantees to the caller as the page lock is
	 *    released before return.
	 * Case d, similar to truncation. If reclaim holds the page lock, it
	 *    will be a race with remove_mapping that determines if the mapping
	 *    is valid on unlock but otherwise the data is valid and there is
	 *    no need to serialise with page lock.
	 *
	 * As the page lock gives no additional guarantee, we optimistically
	 * wait on the page to be unlocked and check if it's up to date and
	 * use the page if it is. Otherwise, the page lock is required to
	 * distinguish between the different cases. The motivation is that we
	 * avoid spurious serialisations and wakeups when multiple processes
	 * wait on the same page for IO to complete.
	 */
	wait_on_page_locked(page);
	if (PageUptodate(page))
		goto out;

	/* Distinguish between all the cases under the safety of the lock */
	lock_page(page);

	/* Case c or d, restart the operation */
	if (!page->mapping) {
		unlock_page(page);
		put_page(page);
		goto repeat;
	}

	/* Someone else locked and filled the page in a very small window */
	if (PageUptodate(page)) {
		unlock_page(page);
		goto out;
	}
	goto filler;

out:
	mark_page_accessed(page);
	return page;
}

/**
 * read_cache_page - read into page cache, fill it if needed
 * @mapping:	the page's address_space
 * @index:	the page index
 * @filler:	function to perform the read
 * @data:	first arg to filler(data, page) function, often left as NULL
 *
 * Read into the page cache. If a page already exists, and PageUptodate() is
 * not set, try to fill the page and wait for it to become unlocked.
 *
 * If the page does not get brought uptodate, return -EIO.
 */
struct page *read_cache_page(struct address_space *mapping,
				pgoff_t index,
				int (*filler)(void *, struct page *),
				void *data)
{
	return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping));
}
EXPORT_SYMBOL(read_cache_page);

/**
 * read_cache_page_gfp - read into page cache, using specified page allocation flags.
 * @mapping:	the page's address_space
 * @index:	the page index
 * @gfp:	the page allocator flags to use if allocating
 *
 * This is the same as "read_mapping_page(mapping, index, NULL)", but with
 * any new page allocations done using the specified allocation flags.
 *
 * If the page does not get brought uptodate, return -EIO.
 */
struct page *read_cache_page_gfp(struct address_space *mapping,
				pgoff_t index,
				gfp_t gfp)
{
	filler_t *filler = (filler_t *)mapping->a_ops->readpage;

	return do_read_cache_page(mapping, index, filler, NULL, gfp);
}
EXPORT_SYMBOL(read_cache_page_gfp);

/*
 * Performs necessary checks before doing a write
 *
 * Can adjust writing position or amount of bytes to write.
 * Returns appropriate error code that caller should return or
 * zero in case that write should be allowed.
 */
inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file->f_mapping->host;
	unsigned long limit = rlimit(RLIMIT_FSIZE);
	loff_t pos;

	if (!iov_iter_count(from))
		return 0;

	/* FIXME: this is for backwards compatibility with 2.4 */
	if (iocb->ki_flags & IOCB_APPEND)
		iocb->ki_pos = i_size_read(inode);

	pos = iocb->ki_pos;

	if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
		return -EINVAL;

	if (limit != RLIM_INFINITY) {
		if (iocb->ki_pos >= limit) {
			send_sig(SIGXFSZ, current, 0);
			return -EFBIG;
		}
		iov_iter_truncate(from, limit - (unsigned long)pos);
	}

	/*
	 * LFS rule
	 */
	if (unlikely(pos + iov_iter_count(from) > MAX_NON_LFS &&
				!(file->f_flags & O_LARGEFILE))) {
		if (pos >= MAX_NON_LFS)
			return -EFBIG;
		iov_iter_truncate(from, MAX_NON_LFS - (unsigned long)pos);
	}

	/*
	 * Are we about to exceed the fs block limit ?
	 *
	 * If we have written data it becomes a short write.  If we have
	 * exceeded without writing data we send a signal and return EFBIG.
	 * Linus frestrict idea will clean these up nicely..
	 */
	if (unlikely(pos >= inode->i_sb->s_maxbytes))
		return -EFBIG;

	iov_iter_truncate(from, inode->i_sb->s_maxbytes - pos);
	return iov_iter_count(from);
}
EXPORT_SYMBOL(generic_write_checks);

int pagecache_write_begin(struct file *file, struct address_space *mapping,
				loff_t pos, unsigned len, unsigned flags,
				struct page **pagep, void **fsdata)
{
	const struct address_space_operations *aops = mapping->a_ops;

	return aops->write_begin(file, mapping, pos, len, flags,
							pagep, fsdata);
}
EXPORT_SYMBOL(pagecache_write_begin);

int pagecache_write_end(struct file *file, struct address_space *mapping,
				loff_t pos, unsigned len, unsigned copied,
				struct page *page, void *fsdata)
{
	const struct address_space_operations *aops = mapping->a_ops;

	return aops->write_end(file, mapping, pos, len, copied, page, fsdata);
}
EXPORT_SYMBOL(pagecache_write_end);

ssize_t
generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
{
	struct file	*file = iocb->ki_filp;
	struct address_space *mapping = file->f_mapping;
	struct inode	*inode = mapping->host;
	loff_t		pos = iocb->ki_pos;
	ssize_t		written;
	size_t		write_len;
	pgoff_t		end;

	write_len = iov_iter_count(from);
	end = (pos + write_len - 1) >> PAGE_SHIFT;

	if (iocb->ki_flags & IOCB_NOWAIT) {
		/* If there are pages to writeback, return */
		if (filemap_range_has_page(inode->i_mapping, pos,
					   pos + iov_iter_count(from)))
			return -EAGAIN;
	} else {
		written = filemap_write_and_wait_range(mapping, pos,
							pos + write_len - 1);
		if (written)
			goto out;
	}

	/*
	 * After a write we want buffered reads to be sure to go to disk to get
	 * the new data.  We invalidate clean cached page from the region we're
	 * about to write.  We do this *before* the write so that we can return
	 * without clobbering -EIOCBQUEUED from ->direct_IO().
	 */
	written = invalidate_inode_pages2_range(mapping,
					pos >> PAGE_SHIFT, end);
	/*
	 * If a page can not be invalidated, return 0 to fall back
	 * to buffered write.
	 */
	if (written) {
		if (written == -EBUSY)
			return 0;
		goto out;
	}

	written = mapping->a_ops->direct_IO(iocb, from);

	/*
	 * Finally, try again to invalidate clean pages which might have been
	 * cached by non-direct readahead, or faulted in by get_user_pages()
	 * if the source of the write was an mmap'ed region of the file
	 * we're writing.  Either one is a pretty crazy thing to do,
	 * so we don't support it 100%.  If this invalidation
	 * fails, tough, the write still worked...
	 */
	invalidate_inode_pages2_range(mapping,
				pos >> PAGE_SHIFT, end);

	if (written > 0) {
		pos += written;
		write_len -= written;
		if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) {
			i_size_write(inode, pos);
			mark_inode_dirty(inode);
		}
		iocb->ki_pos = pos;
	}
	iov_iter_revert(from, write_len - iov_iter_count(from));
out:
	return written;
}
EXPORT_SYMBOL(generic_file_direct_write);

/*
 * Find or create a page at the given pagecache position. Return the locked
 * page. This function is specifically for buffered writes.
 */
struct page *grab_cache_page_write_begin(struct address_space *mapping,
					pgoff_t index, unsigned flags)
{
	struct page *page;
	int fgp_flags = FGP_LOCK|FGP_WRITE|FGP_CREAT;

	if (flags & AOP_FLAG_NOFS)
		fgp_flags |= FGP_NOFS;

	page = pagecache_get_page(mapping, index, fgp_flags,
			mapping_gfp_mask(mapping));
	if (page)
		wait_for_stable_page(page);

	return page;
}
EXPORT_SYMBOL(grab_cache_page_write_begin);

ssize_t generic_perform_write(struct file *file,
				struct iov_iter *i, loff_t pos)
{
	struct address_space *mapping = file->f_mapping;
	const struct address_space_operations *a_ops = mapping->a_ops;
	long status = 0;
	ssize_t written = 0;
	unsigned int flags = 0;

	do {
		struct page *page;
		unsigned long offset;	/* Offset into pagecache page */
		unsigned long bytes;	/* Bytes to write to page */
		size_t copied;		/* Bytes copied from user */
		void *fsdata;

		offset = (pos & (PAGE_SIZE - 1));
		bytes = min_t(unsigned long, PAGE_SIZE - offset,
						iov_iter_count(i));

again:
		/*
		 * Bring in the user page that we will copy from _first_.
		 * Otherwise there's a nasty deadlock on copying from the
		 * same page as we're writing to, without it being marked
		 * up-to-date.
		 *
		 * Not only is this an optimisation, but it is also required
		 * to check that the address is actually valid, when atomic
		 * usercopies are used, below.
		 */
		if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
			status = -EFAULT;
			break;
		}

		if (fatal_signal_pending(current)) {
			status = -EINTR;
			break;
		}

		status = a_ops->write_begin(file, mapping, pos, bytes, flags,
						&page, &fsdata);
		if (unlikely(status < 0))
			break;

		if (mapping_writably_mapped(mapping))
			flush_dcache_page(page);

		copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
		flush_dcache_page(page);

		status = a_ops->write_end(file, mapping, pos, bytes, copied,
						page, fsdata);
		if (unlikely(status < 0))
			break;
		copied = status;

		cond_resched();

		iov_iter_advance(i, copied);
		if (unlikely(copied == 0)) {
			/*
			 * If we were unable to copy any data at all, we must
			 * fall back to a single segment length write.
			 *
			 * If we didn't fallback here, we could livelock
			 * because not all segments in the iov can be copied at
			 * once without a pagefault.
			 */
			bytes = min_t(unsigned long, PAGE_SIZE - offset,
						iov_iter_single_seg_count(i));
			goto again;
		}
		pos += copied;
		written += copied;

		balance_dirty_pages_ratelimited(mapping);
	} while (iov_iter_count(i));

	return written ? written : status;
}
EXPORT_SYMBOL(generic_perform_write);

/**
 * __generic_file_write_iter - write data to a file
 * @iocb:	IO state structure (file, offset, etc.)
 * @from:	iov_iter with data to write
 *
 * This function does all the work needed for actually writing data to a
 * file. It does all basic checks, removes SUID from the file, updates
 * modification times and calls proper subroutines depending on whether we
 * do direct IO or a standard buffered write.
 *
 * It expects i_mutex to be grabbed unless we work on a block device or similar
 * object which does not need locking at all.
 *
 * This function does *not* take care of syncing data in case of O_SYNC write.
 * A caller has to handle it. This is mainly due to the fact that we want to
 * avoid syncing under i_mutex.
 */
ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	struct file *file = iocb->ki_filp;
	struct address_space * mapping = file->f_mapping;
	struct inode 	*inode = mapping->host;
	ssize_t		written = 0;
	ssize_t		err;
	ssize_t		status;

	/* We can write back this queue in page reclaim */
	current->backing_dev_info = inode_to_bdi(inode);
	err = file_remove_privs(file);
	if (err)
		goto out;

	err = file_update_time(file);
	if (err)
		goto out;

	if (iocb->ki_flags & IOCB_DIRECT) {
		loff_t pos, endbyte;

		written = generic_file_direct_write(iocb, from);
		/*
		 * If the write stopped short of completing, fall back to
		 * buffered writes.  Some filesystems do this for writes to
		 * holes, for example.  For DAX files, a buffered write will
		 * not succeed (even if it did, DAX does not handle dirty
		 * page-cache pages correctly).
		 */
		if (written < 0 || !iov_iter_count(from) || IS_DAX(inode))
			goto out;

		status = generic_perform_write(file, from, pos = iocb->ki_pos);
		/*
		 * If generic_perform_write() returned a synchronous error
		 * then we want to return the number of bytes which were
		 * direct-written, or the error code if that was zero.  Note
		 * that this differs from normal direct-io semantics, which
		 * will return -EFOO even if some bytes were written.
		 */
		if (unlikely(status < 0)) {
			err = status;
			goto out;
		}
		/*
		 * We need to ensure that the page cache pages are written to
		 * disk and invalidated to preserve the expected O_DIRECT
		 * semantics.
		 */
		endbyte = pos + status - 1;
		err = filemap_write_and_wait_range(mapping, pos, endbyte);
		if (err == 0) {
			iocb->ki_pos = endbyte + 1;
			written += status;
			invalidate_mapping_pages(mapping,
						 pos >> PAGE_SHIFT,
						 endbyte >> PAGE_SHIFT);
		} else {
			/*
			 * We don't know how much we wrote, so just return
			 * the number of bytes which were direct-written
			 */
		}
	} else {
		written = generic_perform_write(file, from, iocb->ki_pos);
		if (likely(written > 0))
			iocb->ki_pos += written;
	}
out:
	current->backing_dev_info = NULL;
	return written ? written : err;
}
EXPORT_SYMBOL(__generic_file_write_iter);

/**
 * generic_file_write_iter - write data to a file
 * @iocb:	IO state structure
 * @from:	iov_iter with data to write
 *
 * This is a wrapper around __generic_file_write_iter() to be used by most
 * filesystems. It takes care of syncing the file in case of O_SYNC file
 * and acquires i_mutex as needed.
 */
ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file->f_mapping->host;
	ssize_t ret;

	inode_lock(inode);
	ret = generic_write_checks(iocb, from);
	if (ret > 0)
		ret = __generic_file_write_iter(iocb, from);
	inode_unlock(inode);

	if (ret > 0)
		ret = generic_write_sync(iocb, ret);
	return ret;
}
EXPORT_SYMBOL(generic_file_write_iter);

/**
 * try_to_release_page() - release old fs-specific metadata on a page
 *
 * @page: the page which the kernel is trying to free
 * @gfp_mask: memory allocation flags (and I/O mode)
 *
 * The address_space is to try to release any data against the page
 * (presumably at page->private).  If the release was successful, return '1'.
 * Otherwise return zero.
 *
 * This may also be called if PG_fscache is set on a page, indicating that the
 * page is known to the local caching routines.
 *
 * The @gfp_mask argument specifies whether I/O may be performed to release
 * this page (__GFP_IO), and whether the call may block (__GFP_RECLAIM & __GFP_FS).
 *
 */
int try_to_release_page(struct page *page, gfp_t gfp_mask)
{
	struct address_space * const mapping = page->mapping;

	BUG_ON(!PageLocked(page));
	if (PageWriteback(page))
		return 0;

	if (mapping && mapping->a_ops->releasepage)
		return mapping->a_ops->releasepage(page, gfp_mask);
	return try_to_free_buffers(page);
}

EXPORT_SYMBOL(try_to_release_page);