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
/*
 * Memory merging support.
 *
 * This code enables dynamic sharing of identical pages found in different
 * memory areas, even if they are not shared by fork()
 *
 * Copyright (C) 2008-2009 Red Hat, Inc.
 * Authors:
 *	Izik Eidus
 *	Andrea Arcangeli
 *	Chris Wright
 *	Hugh Dickins
 *
 * This work is licensed under the terms of the GNU GPL, version 2.
 */

#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/mman.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/sched/coredump.h>
#include <linux/rwsem.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/spinlock.h>
#include <linux/jhash.h>
#include <linux/delay.h>
#include <linux/kthread.h>
#include <linux/wait.h>
#include <linux/slab.h>
#include <linux/rbtree.h>
#include <linux/memory.h>
#include <linux/mmu_notifier.h>
#include <linux/swap.h>
#include <linux/ksm.h>
#include <linux/hashtable.h>
#include <linux/freezer.h>
#include <linux/oom.h>
#include <linux/numa.h>

#include <asm/tlbflush.h>
#include "internal.h"

#ifdef CONFIG_NUMA
#define NUMA(x)		(x)
#define DO_NUMA(x)	do { (x); } while (0)
#else
#define NUMA(x)		(0)
#define DO_NUMA(x)	do { } while (0)
#endif

/*
 * A few notes about the KSM scanning process,
 * to make it easier to understand the data structures below:
 *
 * In order to reduce excessive scanning, KSM sorts the memory pages by their
 * contents into a data structure that holds pointers to the pages' locations.
 *
 * Since the contents of the pages may change at any moment, KSM cannot just
 * insert the pages into a normal sorted tree and expect it to find anything.
 * Therefore KSM uses two data structures - the stable and the unstable tree.
 *
 * The stable tree holds pointers to all the merged pages (ksm pages), sorted
 * by their contents.  Because each such page is write-protected, searching on
 * this tree is fully assured to be working (except when pages are unmapped),
 * and therefore this tree is called the stable tree.
 *
 * In addition to the stable tree, KSM uses a second data structure called the
 * unstable tree: this tree holds pointers to pages which have been found to
 * be "unchanged for a period of time".  The unstable tree sorts these pages
 * by their contents, but since they are not write-protected, KSM cannot rely
 * upon the unstable tree to work correctly - the unstable tree is liable to
 * be corrupted as its contents are modified, and so it is called unstable.
 *
 * KSM solves this problem by several techniques:
 *
 * 1) The unstable tree is flushed every time KSM completes scanning all
 *    memory areas, and then the tree is rebuilt again from the beginning.
 * 2) KSM will only insert into the unstable tree, pages whose hash value
 *    has not changed since the previous scan of all memory areas.
 * 3) The unstable tree is a RedBlack Tree - so its balancing is based on the
 *    colors of the nodes and not on their contents, assuring that even when
 *    the tree gets "corrupted" it won't get out of balance, so scanning time
 *    remains the same (also, searching and inserting nodes in an rbtree uses
 *    the same algorithm, so we have no overhead when we flush and rebuild).
 * 4) KSM never flushes the stable tree, which means that even if it were to
 *    take 10 attempts to find a page in the unstable tree, once it is found,
 *    it is secured in the stable tree.  (When we scan a new page, we first
 *    compare it against the stable tree, and then against the unstable tree.)
 *
 * If the merge_across_nodes tunable is unset, then KSM maintains multiple
 * stable trees and multiple unstable trees: one of each for each NUMA node.
 */

/**
 * struct mm_slot - ksm information per mm that is being scanned
 * @link: link to the mm_slots hash list
 * @mm_list: link into the mm_slots list, rooted in ksm_mm_head
 * @rmap_list: head for this mm_slot's singly-linked list of rmap_items
 * @mm: the mm that this information is valid for
 */
struct mm_slot {
	struct hlist_node link;
	struct list_head mm_list;
	struct rmap_item *rmap_list;
	struct mm_struct *mm;
};

/**
 * struct ksm_scan - cursor for scanning
 * @mm_slot: the current mm_slot we are scanning
 * @address: the next address inside that to be scanned
 * @rmap_list: link to the next rmap to be scanned in the rmap_list
 * @seqnr: count of completed full scans (needed when removing unstable node)
 *
 * There is only the one ksm_scan instance of this cursor structure.
 */
struct ksm_scan {
	struct mm_slot *mm_slot;
	unsigned long address;
	struct rmap_item **rmap_list;
	unsigned long seqnr;
};

/**
 * struct stable_node - node of the stable rbtree
 * @node: rb node of this ksm page in the stable tree
 * @head: (overlaying parent) &migrate_nodes indicates temporarily on that list
 * @list: linked into migrate_nodes, pending placement in the proper node tree
 * @hlist: hlist head of rmap_items using this ksm page
 * @kpfn: page frame number of this ksm page (perhaps temporarily on wrong nid)
 * @nid: NUMA node id of stable tree in which linked (may not match kpfn)
 */
struct stable_node {
	union {
		struct rb_node node;	/* when node of stable tree */
		struct {		/* when listed for migration */
			struct list_head *head;
			struct list_head list;
		};
	};
	struct hlist_head hlist;
	unsigned long kpfn;
#ifdef CONFIG_NUMA
	int nid;
#endif
};

/**
 * struct rmap_item - reverse mapping item for virtual addresses
 * @rmap_list: next rmap_item in mm_slot's singly-linked rmap_list
 * @anon_vma: pointer to anon_vma for this mm,address, when in stable tree
 * @nid: NUMA node id of unstable tree in which linked (may not match page)
 * @mm: the memory structure this rmap_item is pointing into
 * @address: the virtual address this rmap_item tracks (+ flags in low bits)
 * @oldchecksum: previous checksum of the page at that virtual address
 * @node: rb node of this rmap_item in the unstable tree
 * @head: pointer to stable_node heading this list in the stable tree
 * @hlist: link into hlist of rmap_items hanging off that stable_node
 */
struct rmap_item {
	struct rmap_item *rmap_list;
	union {
		struct anon_vma *anon_vma;	/* when stable */
#ifdef CONFIG_NUMA
		int nid;		/* when node of unstable tree */
#endif
	};
	struct mm_struct *mm;
	unsigned long address;		/* + low bits used for flags below */
	unsigned int oldchecksum;	/* when unstable */
	union {
		struct rb_node node;	/* when node of unstable tree */
		struct {		/* when listed from stable tree */
			struct stable_node *head;
			struct hlist_node hlist;
		};
	};
};

#define SEQNR_MASK	0x0ff	/* low bits of unstable tree seqnr */
#define UNSTABLE_FLAG	0x100	/* is a node of the unstable tree */
#define STABLE_FLAG	0x200	/* is listed from the stable tree */

/* The stable and unstable tree heads */
static struct rb_root one_stable_tree[1] = { RB_ROOT };
static struct rb_root one_unstable_tree[1] = { RB_ROOT };
static struct rb_root *root_stable_tree = one_stable_tree;
static struct rb_root *root_unstable_tree = one_unstable_tree;

/* Recently migrated nodes of stable tree, pending proper placement */
static LIST_HEAD(migrate_nodes);

#define MM_SLOTS_HASH_BITS 10
static DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS);

static struct mm_slot ksm_mm_head = {
	.mm_list = LIST_HEAD_INIT(ksm_mm_head.mm_list),
};
static struct ksm_scan ksm_scan = {
	.mm_slot = &ksm_mm_head,
};

static struct kmem_cache *rmap_item_cache;
static struct kmem_cache *stable_node_cache;
static struct kmem_cache *mm_slot_cache;

/* The number of nodes in the stable tree */
static unsigned long ksm_pages_shared;

/* The number of page slots additionally sharing those nodes */
static unsigned long ksm_pages_sharing;

/* The number of nodes in the unstable tree */
static unsigned long ksm_pages_unshared;

/* The number of rmap_items in use: to calculate pages_volatile */
static unsigned long ksm_rmap_items;

/* Number of pages ksmd should scan in one batch */
static unsigned int ksm_thread_pages_to_scan = 100;

/* Milliseconds ksmd should sleep between batches */
static unsigned int ksm_thread_sleep_millisecs = 20;

/* Checksum of an empty (zeroed) page */
static unsigned int zero_checksum __read_mostly;

/* Whether to merge empty (zeroed) pages with actual zero pages */
static bool ksm_use_zero_pages __read_mostly;

#ifdef CONFIG_NUMA
/* Zeroed when merging across nodes is not allowed */
static unsigned int ksm_merge_across_nodes = 1;
static int ksm_nr_node_ids = 1;
#else
#define ksm_merge_across_nodes	1U
#define ksm_nr_node_ids		1
#endif

#define KSM_RUN_STOP	0
#define KSM_RUN_MERGE	1
#define KSM_RUN_UNMERGE	2
#define KSM_RUN_OFFLINE	4
static unsigned long ksm_run = KSM_RUN_STOP;
static void wait_while_offlining(void);

static DECLARE_WAIT_QUEUE_HEAD(ksm_thread_wait);
static DEFINE_MUTEX(ksm_thread_mutex);
static DEFINE_SPINLOCK(ksm_mmlist_lock);

#define KSM_KMEM_CACHE(__struct, __flags) kmem_cache_create("ksm_"#__struct,\
		sizeof(struct __struct), __alignof__(struct __struct),\
		(__flags), NULL)

static int __init ksm_slab_init(void)
{
	rmap_item_cache = KSM_KMEM_CACHE(rmap_item, 0);
	if (!rmap_item_cache)
		goto out;

	stable_node_cache = KSM_KMEM_CACHE(stable_node, 0);
	if (!stable_node_cache)
		goto out_free1;

	mm_slot_cache = KSM_KMEM_CACHE(mm_slot, 0);
	if (!mm_slot_cache)
		goto out_free2;

	return 0;

out_free2:
	kmem_cache_destroy(stable_node_cache);
out_free1:
	kmem_cache_destroy(rmap_item_cache);
out:
	return -ENOMEM;
}

static void __init ksm_slab_free(void)
{
	kmem_cache_destroy(mm_slot_cache);
	kmem_cache_destroy(stable_node_cache);
	kmem_cache_destroy(rmap_item_cache);
	mm_slot_cache = NULL;
}

static inline struct rmap_item *alloc_rmap_item(void)
{
	struct rmap_item *rmap_item;

	rmap_item = kmem_cache_zalloc(rmap_item_cache, GFP_KERNEL |
						__GFP_NORETRY | __GFP_NOWARN);
	if (rmap_item)
		ksm_rmap_items++;
	return rmap_item;
}

static inline void free_rmap_item(struct rmap_item *rmap_item)
{
	ksm_rmap_items--;
	rmap_item->mm = NULL;	/* debug safety */
	kmem_cache_free(rmap_item_cache, rmap_item);
}

static inline struct stable_node *alloc_stable_node(void)
{
	/*
	 * The allocation can take too long with GFP_KERNEL when memory is under
	 * pressure, which may lead to hung task warnings.  Adding __GFP_HIGH
	 * grants access to memory reserves, helping to avoid this problem.
	 */
	return kmem_cache_alloc(stable_node_cache, GFP_KERNEL | __GFP_HIGH);
}

static inline void free_stable_node(struct stable_node *stable_node)
{
	kmem_cache_free(stable_node_cache, stable_node);
}

static inline struct mm_slot *alloc_mm_slot(void)
{
	if (!mm_slot_cache)	/* initialization failed */
		return NULL;
	return kmem_cache_zalloc(mm_slot_cache, GFP_KERNEL);
}

static inline void free_mm_slot(struct mm_slot *mm_slot)
{
	kmem_cache_free(mm_slot_cache, mm_slot);
}

static struct mm_slot *get_mm_slot(struct mm_struct *mm)
{
	struct mm_slot *slot;

	hash_for_each_possible(mm_slots_hash, slot, link, (unsigned long)mm)
		if (slot->mm == mm)
			return slot;

	return NULL;
}

static void insert_to_mm_slots_hash(struct mm_struct *mm,
				    struct mm_slot *mm_slot)
{
	mm_slot->mm = mm;
	hash_add(mm_slots_hash, &mm_slot->link, (unsigned long)mm);
}

/*
 * ksmd, and unmerge_and_remove_all_rmap_items(), must not touch an mm's
 * page tables after it has passed through ksm_exit() - which, if necessary,
 * takes mmap_sem briefly to serialize against them.  ksm_exit() does not set
 * a special flag: they can just back out as soon as mm_users goes to zero.
 * ksm_test_exit() is used throughout to make this test for exit: in some
 * places for correctness, in some places just to avoid unnecessary work.
 */
static inline bool ksm_test_exit(struct mm_struct *mm)
{
	return atomic_read(&mm->mm_users) == 0;
}

/*
 * We use break_ksm to break COW on a ksm page: it's a stripped down
 *
 *	if (get_user_pages(addr, 1, 1, 1, &page, NULL) == 1)
 *		put_page(page);
 *
 * but taking great care only to touch a ksm page, in a VM_MERGEABLE vma,
 * in case the application has unmapped and remapped mm,addr meanwhile.
 * Could a ksm page appear anywhere else?  Actually yes, in a VM_PFNMAP
 * mmap of /dev/mem or /dev/kmem, where we would not want to touch it.
 *
 * FAULT_FLAG/FOLL_REMOTE are because we do this outside the context
 * of the process that owns 'vma'.  We also do not want to enforce
 * protection keys here anyway.
 */
static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
{
	struct page *page;
	int ret = 0;

	do {
		cond_resched();
		page = follow_page(vma, addr,
				FOLL_GET | FOLL_MIGRATION | FOLL_REMOTE);
		if (IS_ERR_OR_NULL(page))
			break;
		if (PageKsm(page))
			ret = handle_mm_fault(vma, addr,
					FAULT_FLAG_WRITE | FAULT_FLAG_REMOTE);
		else
			ret = VM_FAULT_WRITE;
		put_page(page);
	} while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM)));
	/*
	 * We must loop because handle_mm_fault() may back out if there's
	 * any difficulty e.g. if pte accessed bit gets updated concurrently.
	 *
	 * VM_FAULT_WRITE is what we have been hoping for: it indicates that
	 * COW has been broken, even if the vma does not permit VM_WRITE;
	 * but note that a concurrent fault might break PageKsm for us.
	 *
	 * VM_FAULT_SIGBUS could occur if we race with truncation of the
	 * backing file, which also invalidates anonymous pages: that's
	 * okay, that truncation will have unmapped the PageKsm for us.
	 *
	 * VM_FAULT_OOM: at the time of writing (late July 2009), setting
	 * aside mem_cgroup limits, VM_FAULT_OOM would only be set if the
	 * current task has TIF_MEMDIE set, and will be OOM killed on return
	 * to user; and ksmd, having no mm, would never be chosen for that.
	 *
	 * But if the mm is in a limited mem_cgroup, then the fault may fail
	 * with VM_FAULT_OOM even if the current task is not TIF_MEMDIE; and
	 * even ksmd can fail in this way - though it's usually breaking ksm
	 * just to undo a merge it made a moment before, so unlikely to oom.
	 *
	 * That's a pity: we might therefore have more kernel pages allocated
	 * than we're counting as nodes in the stable tree; but ksm_do_scan
	 * will retry to break_cow on each pass, so should recover the page
	 * in due course.  The important thing is to not let VM_MERGEABLE
	 * be cleared while any such pages might remain in the area.
	 */
	return (ret & VM_FAULT_OOM) ? -ENOMEM : 0;
}

static struct vm_area_struct *find_mergeable_vma(struct mm_struct *mm,
		unsigned long addr)
{
	struct vm_area_struct *vma;
	if (ksm_test_exit(mm))
		return NULL;
	vma = find_vma(mm, addr);
	if (!vma || vma->vm_start > addr)
		return NULL;
	if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma)
		return NULL;
	return vma;
}

static void break_cow(struct rmap_item *rmap_item)
{
	struct mm_struct *mm = rmap_item->mm;
	unsigned long addr = rmap_item->address;
	struct vm_area_struct *vma;

	/*
	 * It is not an accident that whenever we want to break COW
	 * to undo, we also need to drop a reference to the anon_vma.
	 */
	put_anon_vma(rmap_item->anon_vma);

	down_read(&mm->mmap_sem);
	vma = find_mergeable_vma(mm, addr);
	if (vma)
		break_ksm(vma, addr);
	up_read(&mm->mmap_sem);
}

static struct page *get_mergeable_page(struct rmap_item *rmap_item)
{
	struct mm_struct *mm = rmap_item->mm;
	unsigned long addr = rmap_item->address;
	struct vm_area_struct *vma;
	struct page *page;

	down_read(&mm->mmap_sem);
	vma = find_mergeable_vma(mm, addr);
	if (!vma)
		goto out;

	page = follow_page(vma, addr, FOLL_GET);
	if (IS_ERR_OR_NULL(page))
		goto out;
	if (PageAnon(page)) {
		flush_anon_page(vma, page, addr);
		flush_dcache_page(page);
	} else {
		put_page(page);
out:
		page = NULL;
	}
	up_read(&mm->mmap_sem);
	return page;
}

/*
 * This helper is used for getting right index into array of tree roots.
 * When merge_across_nodes knob is set to 1, there are only two rb-trees for
 * stable and unstable pages from all nodes with roots in index 0. Otherwise,
 * every node has its own stable and unstable tree.
 */
static inline int get_kpfn_nid(unsigned long kpfn)
{
	return ksm_merge_across_nodes ? 0 : NUMA(pfn_to_nid(kpfn));
}

static void remove_node_from_stable_tree(struct stable_node *stable_node)
{
	struct rmap_item *rmap_item;

	hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) {
		if (rmap_item->hlist.next)
			ksm_pages_sharing--;
		else
			ksm_pages_shared--;
		put_anon_vma(rmap_item->anon_vma);
		rmap_item->address &= PAGE_MASK;
		cond_resched();
	}

	if (stable_node->head == &migrate_nodes)
		list_del(&stable_node->list);
	else
		rb_erase(&stable_node->node,
			 root_stable_tree + NUMA(stable_node->nid));
	free_stable_node(stable_node);
}

/*
 * get_ksm_page: checks if the page indicated by the stable node
 * is still its ksm page, despite having held no reference to it.
 * In which case we can trust the content of the page, and it
 * returns the gotten page; but if the page has now been zapped,
 * remove the stale node from the stable tree and return NULL.
 * But beware, the stable node's page might be being migrated.
 *
 * You would expect the stable_node to hold a reference to the ksm page.
 * But if it increments the page's count, swapping out has to wait for
 * ksmd to come around again before it can free the page, which may take
 * seconds or even minutes: much too unresponsive.  So instead we use a
 * "keyhole reference": access to the ksm page from the stable node peeps
 * out through its keyhole to see if that page still holds the right key,
 * pointing back to this stable node.  This relies on freeing a PageAnon
 * page to reset its page->mapping to NULL, and relies on no other use of
 * a page to put something that might look like our key in page->mapping.
 * is on its way to being freed; but it is an anomaly to bear in mind.
 */
static struct page *get_ksm_page(struct stable_node *stable_node, bool lock_it)
{
	struct page *page;
	void *expected_mapping;
	unsigned long kpfn;

	expected_mapping = (void *)((unsigned long)stable_node |
					PAGE_MAPPING_KSM);
again:
	kpfn = READ_ONCE(stable_node->kpfn);
	page = pfn_to_page(kpfn);

	/*
	 * page is computed from kpfn, so on most architectures reading
	 * page->mapping is naturally ordered after reading node->kpfn,
	 * but on Alpha we need to be more careful.
	 */
	smp_read_barrier_depends();
	if (READ_ONCE(page->mapping) != expected_mapping)
		goto stale;

	/*
	 * We cannot do anything with the page while its refcount is 0.
	 * Usually 0 means free, or tail of a higher-order page: in which
	 * case this node is no longer referenced, and should be freed;
	 * however, it might mean that the page is under page_freeze_refs().
	 * The __remove_mapping() case is easy, again the node is now stale;
	 * but if page is swapcache in migrate_page_move_mapping(), it might
	 * still be our page, in which case it's essential to keep the node.
	 */
	while (!get_page_unless_zero(page)) {
		/*
		 * Another check for page->mapping != expected_mapping would
		 * work here too.  We have chosen the !PageSwapCache test to
		 * optimize the common case, when the page is or is about to
		 * be freed: PageSwapCache is cleared (under spin_lock_irq)
		 * in the freeze_refs section of __remove_mapping(); but Anon
		 * page->mapping reset to NULL later, in free_pages_prepare().
		 */
		if (!PageSwapCache(page))
			goto stale;
		cpu_relax();
	}

	if (READ_ONCE(page->mapping) != expected_mapping) {
		put_page(page);
		goto stale;
	}

	if (lock_it) {
		lock_page(page);
		if (READ_ONCE(page->mapping) != expected_mapping) {
			unlock_page(page);
			put_page(page);
			goto stale;
		}
	}
	return page;

stale:
	/*
	 * We come here from above when page->mapping or !PageSwapCache
	 * suggests that the node is stale; but it might be under migration.
	 * We need smp_rmb(), matching the smp_wmb() in ksm_migrate_page(),
	 * before checking whether node->kpfn has been changed.
	 */
	smp_rmb();
	if (READ_ONCE(stable_node->kpfn) != kpfn)
		goto again;
	remove_node_from_stable_tree(stable_node);
	return NULL;
}

/*
 * Removing rmap_item from stable or unstable tree.
 * This function will clean the information from the stable/unstable tree.
 */
static void remove_rmap_item_from_tree(struct rmap_item *rmap_item)
{
	if (rmap_item->address & STABLE_FLAG) {
		struct stable_node *stable_node;
		struct page *page;

		stable_node = rmap_item->head;
		page = get_ksm_page(stable_node, true);
		if (!page)
			goto out;

		hlist_del(&rmap_item->hlist);
		unlock_page(page);
		put_page(page);

		if (!hlist_empty(&stable_node->hlist))
			ksm_pages_sharing--;
		else
			ksm_pages_shared--;

		put_anon_vma(rmap_item->anon_vma);
		rmap_item->address &= PAGE_MASK;

	} else if (rmap_item->address & UNSTABLE_FLAG) {
		unsigned char age;
		/*
		 * Usually ksmd can and must skip the rb_erase, because
		 * root_unstable_tree was already reset to RB_ROOT.
		 * But be careful when an mm is exiting: do the rb_erase
		 * if this rmap_item was inserted by this scan, rather
		 * than left over from before.
		 */
		age = (unsigned char)(ksm_scan.seqnr - rmap_item->address);
		BUG_ON(age > 1);
		if (!age)
			rb_erase(&rmap_item->node,
				 root_unstable_tree + NUMA(rmap_item->nid));
		ksm_pages_unshared--;
		rmap_item->address &= PAGE_MASK;
	}
out:
	cond_resched();		/* we're called from many long loops */
}

static void remove_trailing_rmap_items(struct mm_slot *mm_slot,
				       struct rmap_item **rmap_list)
{
	while (*rmap_list) {
		struct rmap_item *rmap_item = *rmap_list;
		*rmap_list = rmap_item->rmap_list;
		remove_rmap_item_from_tree(rmap_item);
		free_rmap_item(rmap_item);
	}
}

/*
 * Though it's very tempting to unmerge rmap_items from stable tree rather
 * than check every pte of a given vma, the locking doesn't quite work for
 * that - an rmap_item is assigned to the stable tree after inserting ksm
 * page and upping mmap_sem.  Nor does it fit with the way we skip dup'ing
 * rmap_items from parent to child at fork time (so as not to waste time
 * if exit comes before the next scan reaches it).
 *
 * Similarly, although we'd like to remove rmap_items (so updating counts
 * and freeing memory) when unmerging an area, it's easier to leave that
 * to the next pass of ksmd - consider, for example, how ksmd might be
 * in cmp_and_merge_page on one of the rmap_items we would be removing.
 */
static int unmerge_ksm_pages(struct vm_area_struct *vma,
			     unsigned long start, unsigned long end)
{
	unsigned long addr;
	int err = 0;

	for (addr = start; addr < end && !err; addr += PAGE_SIZE) {
		if (ksm_test_exit(vma->vm_mm))
			break;
		if (signal_pending(current))
			err = -ERESTARTSYS;
		else
			err = break_ksm(vma, addr);
	}
	return err;
}

#ifdef CONFIG_SYSFS
/*
 * Only called through the sysfs control interface:
 */
static int remove_stable_node(struct stable_node *stable_node)
{
	struct page *page;
	int err;

	page = get_ksm_page(stable_node, true);
	if (!page) {
		/*
		 * get_ksm_page did remove_node_from_stable_tree itself.
		 */
		return 0;
	}

	if (WARN_ON_ONCE(page_mapped(page))) {
		/*
		 * This should not happen: but if it does, just refuse to let
		 * merge_across_nodes be switched - there is no need to panic.
		 */
		err = -EBUSY;
	} else {
		/*
		 * The stable node did not yet appear stale to get_ksm_page(),
		 * since that allows for an unmapped ksm page to be recognized
		 * right up until it is freed; but the node is safe to remove.
		 * This page might be in a pagevec waiting to be freed,
		 * or it might be PageSwapCache (perhaps under writeback),
		 * or it might have been removed from swapcache a moment ago.
		 */
		set_page_stable_node(page, NULL);
		remove_node_from_stable_tree(stable_node);
		err = 0;
	}

	unlock_page(page);
	put_page(page);
	return err;
}

static int remove_all_stable_nodes(void)
{
	struct stable_node *stable_node, *next;
	int nid;
	int err = 0;

	for (nid = 0; nid < ksm_nr_node_ids; nid++) {
		while (root_stable_tree[nid].rb_node) {
			stable_node = rb_entry(root_stable_tree[nid].rb_node,
						struct stable_node, node);
			if (remove_stable_node(stable_node)) {
				err = -EBUSY;
				break;	/* proceed to next nid */
			}
			cond_resched();
		}
	}
	list_for_each_entry_safe(stable_node, next, &migrate_nodes, list) {
		if (remove_stable_node(stable_node))
			err = -EBUSY;
		cond_resched();
	}
	return err;
}

static int unmerge_and_remove_all_rmap_items(void)
{
	struct mm_slot *mm_slot;
	struct mm_struct *mm;
	struct vm_area_struct *vma;
	int err = 0;

	spin_lock(&ksm_mmlist_lock);
	ksm_scan.mm_slot = list_entry(ksm_mm_head.mm_list.next,
						struct mm_slot, mm_list);
	spin_unlock(&ksm_mmlist_lock);

	for (mm_slot = ksm_scan.mm_slot;
			mm_slot != &ksm_mm_head; mm_slot = ksm_scan.mm_slot) {
		mm = mm_slot->mm;
		down_read(&mm->mmap_sem);
		for (vma = mm->mmap; vma; vma = vma->vm_next) {
			if (ksm_test_exit(mm))
				break;
			if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma)
				continue;
			err = unmerge_ksm_pages(vma,
						vma->vm_start, vma->vm_end);
			if (err)
				goto error;
		}

		remove_trailing_rmap_items(mm_slot, &mm_slot->rmap_list);
		up_read(&mm->mmap_sem);

		spin_lock(&ksm_mmlist_lock);
		ksm_scan.mm_slot = list_entry(mm_slot->mm_list.next,
						struct mm_slot, mm_list);
		if (ksm_test_exit(mm)) {
			hash_del(&mm_slot->link);
			list_del(&mm_slot->mm_list);
			spin_unlock(&ksm_mmlist_lock);

			free_mm_slot(mm_slot);
			clear_bit(MMF_VM_MERGEABLE, &mm->flags);
			mmdrop(mm);
		} else
			spin_unlock(&ksm_mmlist_lock);
	}

	/* Clean up stable nodes, but don't worry if some are still busy */
	remove_all_stable_nodes();
	ksm_scan.seqnr = 0;
	return 0;

error:
	up_read(&mm->mmap_sem);
	spin_lock(&ksm_mmlist_lock);
	ksm_scan.mm_slot = &ksm_mm_head;
	spin_unlock(&ksm_mmlist_lock);
	return err;
}
#endif /* CONFIG_SYSFS */

static u32 calc_checksum(struct page *page)
{
	u32 checksum;
	void *addr = kmap_atomic(page);
	checksum = jhash2(addr, PAGE_SIZE / 4, 17);
	kunmap_atomic(addr);
	return checksum;
}

static int memcmp_pages(struct page *page1, struct page *page2)
{
	char *addr1, *addr2;
	int ret;

	addr1 = kmap_atomic(page1);
	addr2 = kmap_atomic(page2);
	ret = memcmp(addr1, addr2, PAGE_SIZE);
	kunmap_atomic(addr2);
	kunmap_atomic(addr1);
	return ret;
}

static inline int pages_identical(struct page *page1, struct page *page2)
{
	return !memcmp_pages(page1, page2);
}

static int write_protect_page(struct vm_area_struct *vma, struct page *page,
			      pte_t *orig_pte)
{
	struct mm_struct *mm = vma->vm_mm;
	struct page_vma_mapped_walk pvmw = {
		.page = page,
		.vma = vma,
	};
	int swapped;
	int err = -EFAULT;
	unsigned long mmun_start;	/* For mmu_notifiers */
	unsigned long mmun_end;		/* For mmu_notifiers */

	pvmw.address = page_address_in_vma(page, vma);
	if (pvmw.address == -EFAULT)
		goto out;

	BUG_ON(PageTransCompound(page));

	mmun_start = pvmw.address;
	mmun_end   = pvmw.address + PAGE_SIZE;
	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);

	if (!page_vma_mapped_walk(&pvmw))
		goto out_mn;
	if (WARN_ONCE(!pvmw.pte, "Unexpected PMD mapping?"))
		goto out_unlock;

	if (pte_write(*pvmw.pte) || pte_dirty(*pvmw.pte) ||
	    (pte_protnone(*pvmw.pte) && pte_savedwrite(*pvmw.pte))) {
		pte_t entry;

		swapped = PageSwapCache(page);
		flush_cache_page(vma, pvmw.address, page_to_pfn(page));
		/*
		 * Ok this is tricky, when get_user_pages_fast() run it doesn't
		 * take any lock, therefore the check that we are going to make
		 * with the pagecount against the mapcount is racey and
		 * O_DIRECT can happen right after the check.
		 * So we clear the pte and flush the tlb before the check
		 * this assure us that no O_DIRECT can happen after the check
		 * or in the middle of the check.
		 */
		entry = ptep_clear_flush_notify(vma, pvmw.address, pvmw.pte);
		/*
		 * Check that no O_DIRECT or similar I/O is in progress on the
		 * page
		 */
		if (page_mapcount(page) + 1 + swapped != page_count(page)) {
			set_pte_at(mm, pvmw.address, pvmw.pte, entry);
			goto out_unlock;
		}
		if (pte_dirty(entry))
			set_page_dirty(page);

		if (pte_protnone(entry))
			entry = pte_mkclean(pte_clear_savedwrite(entry));
		else
			entry = pte_mkclean(pte_wrprotect(entry));
		set_pte_at_notify(mm, pvmw.address, pvmw.pte, entry);
	}
	*orig_pte = *pvmw.pte;
	err = 0;

out_unlock:
	page_vma_mapped_walk_done(&pvmw);
out_mn:
	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
out:
	return err;
}

/**
 * replace_page - replace page in vma by new ksm page
 * @vma:      vma that holds the pte pointing to page
 * @page:     the page we are replacing by kpage
 * @kpage:    the ksm page we replace page by
 * @orig_pte: the original value of the pte
 *
 * Returns 0 on success, -EFAULT on failure.
 */
static int replace_page(struct vm_area_struct *vma, struct page *page,
			struct page *kpage, pte_t orig_pte)
{
	struct mm_struct *mm = vma->vm_mm;
	pmd_t *pmd;
	pte_t *ptep;
	pte_t newpte;
	spinlock_t *ptl;
	unsigned long addr;
	int err = -EFAULT;
	unsigned long mmun_start;	/* For mmu_notifiers */
	unsigned long mmun_end;		/* For mmu_notifiers */

	addr = page_address_in_vma(page, vma);
	if (addr == -EFAULT)
		goto out;

	pmd = mm_find_pmd(mm, addr);
	if (!pmd)
		goto out;

	mmun_start = addr;
	mmun_end   = addr + PAGE_SIZE;
	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);

	ptep = pte_offset_map_lock(mm, pmd, addr, &ptl);
	if (!pte_same(*ptep, orig_pte)) {
		pte_unmap_unlock(ptep, ptl);
		goto out_mn;
	}

	/*
	 * No need to check ksm_use_zero_pages here: we can only have a
	 * zero_page here if ksm_use_zero_pages was enabled alreaady.
	 */
	if (!is_zero_pfn(page_to_pfn(kpage))) {
		get_page(kpage);
		page_add_anon_rmap(kpage, vma, addr, false);
		newpte = mk_pte(kpage, vma->vm_page_prot);
	} else {
		newpte = pte_mkspecial(pfn_pte(page_to_pfn(kpage),
					       vma->vm_page_prot));
	}

	flush_cache_page(vma, addr, pte_pfn(*ptep));
	ptep_clear_flush_notify(vma, addr, ptep);
	set_pte_at_notify(mm, addr, ptep, newpte);

	page_remove_rmap(page, false);
	if (!page_mapped(page))
		try_to_free_swap(page);
	put_page(page);

	pte_unmap_unlock(ptep, ptl);
	err = 0;
out_mn:
	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
out:
	return err;
}

/*
 * try_to_merge_one_page - take two pages and merge them into one
 * @vma: the vma that holds the pte pointing to page
 * @page: the PageAnon page that we want to replace with kpage
 * @kpage: the PageKsm page that we want to map instead of page,
 *         or NULL the first time when we want to use page as kpage.
 *
 * This function returns 0 if the pages were merged, -EFAULT otherwise.
 */
static int try_to_merge_one_page(struct vm_area_struct *vma,
				 struct page *page, struct page *kpage)
{
	pte_t orig_pte = __pte(0);
	int err = -EFAULT;

	if (page == kpage)			/* ksm page forked */
		return 0;

	if (!PageAnon(page))
		goto out;

	/*
	 * We need the page lock to read a stable PageSwapCache in
	 * write_protect_page().  We use trylock_page() instead of
	 * lock_page() because we don't want to wait here - we
	 * prefer to continue scanning and merging different pages,
	 * then come back to this page when it is unlocked.
	 */
	if (!trylock_page(page))
		goto out;

	if (PageTransCompound(page)) {
		if (split_huge_page(page))
			goto out_unlock;
	}

	/*
	 * If this anonymous page is mapped only here, its pte may need
	 * to be write-protected.  If it's mapped elsewhere, all of its
	 * ptes are necessarily already write-protected.  But in either
	 * case, we need to lock and check page_count is not raised.
	 */
	if (write_protect_page(vma, page, &orig_pte) == 0) {
		if (!kpage) {
			/*
			 * While we hold page lock, upgrade page from
			 * PageAnon+anon_vma to PageKsm+NULL stable_node:
			 * stable_tree_insert() will update stable_node.
			 */
			set_page_stable_node(page, NULL);
			mark_page_accessed(page);
			/*
			 * Page reclaim just frees a clean page with no dirty
			 * ptes: make sure that the ksm page would be swapped.
			 */
			if (!PageDirty(page))
				SetPageDirty(page);
			err = 0;
		} else if (pages_identical(page, kpage))
			err = replace_page(vma, page, kpage, orig_pte);
	}

	if ((vma->vm_flags & VM_LOCKED) && kpage && !err) {
		munlock_vma_page(page);
		if (!PageMlocked(kpage)) {
			unlock_page(page);
			lock_page(kpage);
			mlock_vma_page(kpage);
			page = kpage;		/* for final unlock */
		}
	}

out_unlock:
	unlock_page(page);
out:
	return err;
}

/*
 * try_to_merge_with_ksm_page - like try_to_merge_two_pages,
 * but no new kernel page is allocated: kpage must already be a ksm page.
 *
 * This function returns 0 if the pages were merged, -EFAULT otherwise.
 */
static int try_to_merge_with_ksm_page(struct rmap_item *rmap_item,
				      struct page *page, struct page *kpage)
{
	struct mm_struct *mm = rmap_item->mm;
	struct vm_area_struct *vma;
	int err = -EFAULT;

	down_read(&mm->mmap_sem);
	vma = find_mergeable_vma(mm, rmap_item->address);
	if (!vma)
		goto out;

	err = try_to_merge_one_page(vma, page, kpage);
	if (err)
		goto out;

	/* Unstable nid is in union with stable anon_vma: remove first */
	remove_rmap_item_from_tree(rmap_item);

	/* Must get reference to anon_vma while still holding mmap_sem */
	rmap_item->anon_vma = vma->anon_vma;
	get_anon_vma(vma->anon_vma);
out:
	up_read(&mm->mmap_sem);
	return err;
}

/*
 * try_to_merge_two_pages - take two identical pages and prepare them
 * to be merged into one page.
 *
 * This function returns the kpage if we successfully merged two identical
 * pages into one ksm page, NULL otherwise.
 *
 * Note that this function upgrades page to ksm page: if one of the pages
 * is already a ksm page, try_to_merge_with_ksm_page should be used.
 */
static struct page *try_to_merge_two_pages(struct rmap_item *rmap_item,
					   struct page *page,
					   struct rmap_item *tree_rmap_item,
					   struct page *tree_page)
{
	int err;

	err = try_to_merge_with_ksm_page(rmap_item, page, NULL);
	if (!err) {
		err = try_to_merge_with_ksm_page(tree_rmap_item,
							tree_page, page);
		/*
		 * If that fails, we have a ksm page with only one pte
		 * pointing to it: so break it.
		 */
		if (err)
			break_cow(rmap_item);
	}
	return err ? NULL : page;
}

/*
 * stable_tree_search - search for page inside the stable tree
 *
 * This function checks if there is a page inside the stable tree
 * with identical content to the page that we are scanning right now.
 *
 * This function returns the stable tree node of identical content if found,
 * NULL otherwise.
 */
static struct page *stable_tree_search(struct page *page)
{
	int nid;
	struct rb_root *root;
	struct rb_node **new;
	struct rb_node *parent;
	struct stable_node *stable_node;
	struct stable_node *page_node;

	page_node = page_stable_node(page);
	if (page_node && page_node->head != &migrate_nodes) {
		/* ksm page forked */
		get_page(page);
		return page;
	}

	nid = get_kpfn_nid(page_to_pfn(page));
	root = root_stable_tree + nid;
again:
	new = &root->rb_node;
	parent = NULL;

	while (*new) {
		struct page *tree_page;
		int ret;

		cond_resched();
		stable_node = rb_entry(*new, struct stable_node, node);
		tree_page = get_ksm_page(stable_node, false);
		if (!tree_page) {
			/*
			 * If we walked over a stale stable_node,
			 * get_ksm_page() will call rb_erase() and it
			 * may rebalance the tree from under us. So
			 * restart the search from scratch. Returning
			 * NULL would be safe too, but we'd generate
			 * false negative insertions just because some
			 * stable_node was stale.
			 */
			goto again;
		}

		ret = memcmp_pages(page, tree_page);
		put_page(tree_page);

		parent = *new;
		if (ret < 0)
			new = &parent->rb_left;
		else if (ret > 0)
			new = &parent->rb_right;
		else {
			/*
			 * Lock and unlock the stable_node's page (which
			 * might already have been migrated) so that page
			 * migration is sure to notice its raised count.
			 * It would be more elegant to return stable_node
			 * than kpage, but that involves more changes.
			 */
			tree_page = get_ksm_page(stable_node, true);
			if (tree_page) {
				unlock_page(tree_page);
				if (get_kpfn_nid(stable_node->kpfn) !=
						NUMA(stable_node->nid)) {
					put_page(tree_page);
					goto replace;
				}
				return tree_page;
			}
			/*
			 * There is now a place for page_node, but the tree may
			 * have been rebalanced, so re-evaluate parent and new.
			 */
			if (page_node)
				goto again;
			return NULL;
		}
	}

	if (!page_node)
		return NULL;

	list_del(&page_node->list);
	DO_NUMA(page_node->nid = nid);
	rb_link_node(&page_node->node, parent, new);
	rb_insert_color(&page_node->node, root);
	get_page(page);
	return page;

replace:
	if (page_node) {
		list_del(&page_node->list);
		DO_NUMA(page_node->nid = nid);
		rb_replace_node(&stable_node->node, &page_node->node, root);
		get_page(page);
	} else {
		rb_erase(&stable_node->node, root);
		page = NULL;
	}
	stable_node->head = &migrate_nodes;
	list_add(&stable_node->list, stable_node->head);
	return page;
}

/*
 * stable_tree_insert - insert stable tree node pointing to new ksm page
 * into the stable tree.
 *
 * This function returns the stable tree node just allocated on success,
 * NULL otherwise.
 */
static struct stable_node *stable_tree_insert(struct page *kpage)
{
	int nid;
	unsigned long kpfn;
	struct rb_root *root;
	struct rb_node **new;
	struct rb_node *parent;
	struct stable_node *stable_node;

	kpfn = page_to_pfn(kpage);
	nid = get_kpfn_nid(kpfn);
	root = root_stable_tree + nid;
again:
	parent = NULL;
	new = &root->rb_node;

	while (*new) {
		struct page *tree_page;
		int ret;

		cond_resched();
		stable_node = rb_entry(*new, struct stable_node, node);
		tree_page = get_ksm_page(stable_node, false);
		if (!tree_page) {
			/*
			 * If we walked over a stale stable_node,
			 * get_ksm_page() will call rb_erase() and it
			 * may rebalance the tree from under us. So
			 * restart the search from scratch. Returning
			 * NULL would be safe too, but we'd generate
			 * false negative insertions just because some
			 * stable_node was stale.
			 */
			goto again;
		}

		ret = memcmp_pages(kpage, tree_page);
		put_page(tree_page);

		parent = *new;
		if (ret < 0)
			new = &parent->rb_left;
		else if (ret > 0)
			new = &parent->rb_right;
		else {
			/*
			 * It is not a bug that stable_tree_search() didn't
			 * find this node: because at that time our page was
			 * not yet write-protected, so may have changed since.
			 */
			return NULL;
		}
	}

	stable_node = alloc_stable_node();
	if (!stable_node)
		return NULL;

	INIT_HLIST_HEAD(&stable_node->hlist);
	stable_node->kpfn = kpfn;
	set_page_stable_node(kpage, stable_node);
	DO_NUMA(stable_node->nid = nid);
	rb_link_node(&stable_node->node, parent, new);
	rb_insert_color(&stable_node->node, root);

	return stable_node;
}

/*
 * unstable_tree_search_insert - search for identical page,
 * else insert rmap_item into the unstable tree.
 *
 * This function searches for a page in the unstable tree identical to the
 * page currently being scanned; and if no identical page is found in the
 * tree, we insert rmap_item as a new object into the unstable tree.
 *
 * This function returns pointer to rmap_item found to be identical
 * to the currently scanned page, NULL otherwise.
 *
 * This function does both searching and inserting, because they share
 * the same walking algorithm in an rbtree.
 */
static
struct rmap_item *unstable_tree_search_insert(struct rmap_item *rmap_item,
					      struct page *page,
					      struct page **tree_pagep)
{
	struct rb_node **new;
	struct rb_root *root;
	struct rb_node *parent = NULL;
	int nid;

	nid = get_kpfn_nid(page_to_pfn(page));
	root = root_unstable_tree + nid;
	new = &root->rb_node;

	while (*new) {
		struct rmap_item *tree_rmap_item;
		struct page *tree_page;
		int ret;

		cond_resched();
		tree_rmap_item = rb_entry(*new, struct rmap_item, node);
		tree_page = get_mergeable_page(tree_rmap_item);
		if (!tree_page)
			return NULL;

		/*
		 * Don't substitute a ksm page for a forked page.
		 */
		if (page == tree_page) {
			put_page(tree_page);
			return NULL;
		}

		ret = memcmp_pages(page, tree_page);

		parent = *new;
		if (ret < 0) {
			put_page(tree_page);
			new = &parent->rb_left;
		} else if (ret > 0) {
			put_page(tree_page);
			new = &parent->rb_right;
		} else if (!ksm_merge_across_nodes &&
			   page_to_nid(tree_page) != nid) {
			/*
			 * If tree_page has been migrated to another NUMA node,
			 * it will be flushed out and put in the right unstable
			 * tree next time: only merge with it when across_nodes.
			 */
			put_page(tree_page);
			return NULL;
		} else {
			*tree_pagep = tree_page;
			return tree_rmap_item;
		}
	}

	rmap_item->address |= UNSTABLE_FLAG;
	rmap_item->address |= (ksm_scan.seqnr & SEQNR_MASK);
	DO_NUMA(rmap_item->nid = nid);
	rb_link_node(&rmap_item->node, parent, new);
	rb_insert_color(&rmap_item->node, root);

	ksm_pages_unshared++;
	return NULL;
}

/*
 * stable_tree_append - add another rmap_item to the linked list of
 * rmap_items hanging off a given node of the stable tree, all sharing
 * the same ksm page.
 */
static void stable_tree_append(struct rmap_item *rmap_item,
			       struct stable_node *stable_node)
{
	rmap_item->head = stable_node;
	rmap_item->address |= STABLE_FLAG;
	hlist_add_head(&rmap_item->hlist, &stable_node->hlist);

	if (rmap_item->hlist.next)
		ksm_pages_sharing++;
	else
		ksm_pages_shared++;
}

/*
 * cmp_and_merge_page - first see if page can be merged into the stable tree;
 * if not, compare checksum to previous and if it's the same, see if page can
 * be inserted into the unstable tree, or merged with a page already there and
 * both transferred to the stable tree.
 *
 * @page: the page that we are searching identical page to.
 * @rmap_item: the reverse mapping into the virtual address of this page
 */
static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item)
{
	struct rmap_item *tree_rmap_item;
	struct page *tree_page = NULL;
	struct stable_node *stable_node;
	struct page *kpage;
	unsigned int checksum;
	int err;

	stable_node = page_stable_node(page);
	if (stable_node) {
		if (stable_node->head != &migrate_nodes &&
		    get_kpfn_nid(stable_node->kpfn) != NUMA(stable_node->nid)) {
			rb_erase(&stable_node->node,
				 root_stable_tree + NUMA(stable_node->nid));
			stable_node->head = &migrate_nodes;
			list_add(&stable_node->list, stable_node->head);
		}
		if (stable_node->head != &migrate_nodes &&
		    rmap_item->head == stable_node)
			return;
	}

	/* We first start with searching the page inside the stable tree */
	kpage = stable_tree_search(page);
	if (kpage == page && rmap_item->head == stable_node) {
		put_page(kpage);
		return;
	}

	remove_rmap_item_from_tree(rmap_item);

	if (kpage) {
		err = try_to_merge_with_ksm_page(rmap_item, page, kpage);
		if (!err) {
			/*
			 * The page was successfully merged:
			 * add its rmap_item to the stable tree.
			 */
			lock_page(kpage);
			stable_tree_append(rmap_item, page_stable_node(kpage));
			unlock_page(kpage);
		}
		put_page(kpage);
		return;
	}

	/*
	 * If the hash value of the page has changed from the last time
	 * we calculated it, this page is changing frequently: therefore we
	 * don't want to insert it in the unstable tree, and we don't want
	 * to waste our time searching for something identical to it there.
	 */
	checksum = calc_checksum(page);
	if (rmap_item->oldchecksum != checksum) {
		rmap_item->oldchecksum = checksum;
		return;
	}

	/*
	 * Same checksum as an empty page. We attempt to merge it with the
	 * appropriate zero page if the user enabled this via sysfs.
	 */
	if (ksm_use_zero_pages && (checksum == zero_checksum)) {
		struct vm_area_struct *vma;

		vma = find_mergeable_vma(rmap_item->mm, rmap_item->address);
		err = try_to_merge_one_page(vma, page,
					    ZERO_PAGE(rmap_item->address));
		/*
		 * In case of failure, the page was not really empty, so we
		 * need to continue. Otherwise we're done.
		 */
		if (!err)
			return;
	}
	tree_rmap_item =
		unstable_tree_search_insert(rmap_item, page, &tree_page);
	if (tree_rmap_item) {
		kpage = try_to_merge_two_pages(rmap_item, page,
						tree_rmap_item, tree_page);
		put_page(tree_page);
		if (kpage) {
			/*
			 * The pages were successfully merged: insert new
			 * node in the stable tree and add both rmap_items.
			 */
			lock_page(kpage);
			stable_node = stable_tree_insert(kpage);
			if (stable_node) {
				stable_tree_append(tree_rmap_item, stable_node);
				stable_tree_append(rmap_item, stable_node);
			}
			unlock_page(kpage);

			/*
			 * If we fail to insert the page into the stable tree,
			 * we will have 2 virtual addresses that are pointing
			 * to a ksm page left outside the stable tree,
			 * in which case we need to break_cow on both.
			 */
			if (!stable_node) {
				break_cow(tree_rmap_item);
				break_cow(rmap_item);
			}
		}
	}
}

static struct rmap_item *get_next_rmap_item(struct mm_slot *mm_slot,
					    struct rmap_item **rmap_list,
					    unsigned long addr)
{
	struct rmap_item *rmap_item;

	while (*rmap_list) {
		rmap_item = *rmap_list;
		if ((rmap_item->address & PAGE_MASK) == addr)
			return rmap_item;
		if (rmap_item->address > addr)
			break;
		*rmap_list = rmap_item->rmap_list;
		remove_rmap_item_from_tree(rmap_item);
		free_rmap_item(rmap_item);
	}

	rmap_item = alloc_rmap_item();
	if (rmap_item) {
		/* It has already been zeroed */
		rmap_item->mm = mm_slot->mm;
		rmap_item->address = addr;
		rmap_item->rmap_list = *rmap_list;
		*rmap_list = rmap_item;
	}
	return rmap_item;
}

static struct rmap_item *scan_get_next_rmap_item(struct page **page)
{
	struct mm_struct *mm;
	struct mm_slot *slot;
	struct vm_area_struct *vma;
	struct rmap_item *rmap_item;
	int nid;

	if (list_empty(&ksm_mm_head.mm_list))
		return NULL;

	slot = ksm_scan.mm_slot;
	if (slot == &ksm_mm_head) {
		/*
		 * A number of pages can hang around indefinitely on per-cpu
		 * pagevecs, raised page count preventing write_protect_page
		 * from merging them.  Though it doesn't really matter much,
		 * it is puzzling to see some stuck in pages_volatile until
		 * other activity jostles them out, and they also prevented
		 * LTP's KSM test from succeeding deterministically; so drain
		 * them here (here rather than on entry to ksm_do_scan(),
		 * so we don't IPI too often when pages_to_scan is set low).
		 */
		lru_add_drain_all();

		/*
		 * Whereas stale stable_nodes on the stable_tree itself
		 * get pruned in the regular course of stable_tree_search(),
		 * those moved out to the migrate_nodes list can accumulate:
		 * so prune them once before each full scan.
		 */
		if (!ksm_merge_across_nodes) {
			struct stable_node *stable_node, *next;
			struct page *page;

			list_for_each_entry_safe(stable_node, next,
						 &migrate_nodes, list) {
				page = get_ksm_page(stable_node, false);
				if (page)
					put_page(page);
				cond_resched();
			}
		}

		for (nid = 0; nid < ksm_nr_node_ids; nid++)
			root_unstable_tree[nid] = RB_ROOT;

		spin_lock(&ksm_mmlist_lock);
		slot = list_entry(slot->mm_list.next, struct mm_slot, mm_list);
		ksm_scan.mm_slot = slot;
		spin_unlock(&ksm_mmlist_lock);
		/*
		 * Although we tested list_empty() above, a racing __ksm_exit
		 * of the last mm on the list may have removed it since then.
		 */
		if (slot == &ksm_mm_head)
			return NULL;
next_mm:
		ksm_scan.address = 0;
		ksm_scan.rmap_list = &slot->rmap_list;
	}

	mm = slot->mm;
	down_read(&mm->mmap_sem);
	if (ksm_test_exit(mm))
		vma = NULL;
	else
		vma = find_vma(mm, ksm_scan.address);

	for (; vma; vma = vma->vm_next) {
		if (!(vma->vm_flags & VM_MERGEABLE))
			continue;
		if (ksm_scan.address < vma->vm_start)
			ksm_scan.address = vma->vm_start;
		if (!vma->anon_vma)
			ksm_scan.address = vma->vm_end;

		while (ksm_scan.address < vma->vm_end) {
			if (ksm_test_exit(mm))
				break;
			*page = follow_page(vma, ksm_scan.address, FOLL_GET);
			if (IS_ERR_OR_NULL(*page)) {
				ksm_scan.address += PAGE_SIZE;
				cond_resched();
				continue;
			}
			if (PageAnon(*page)) {
				flush_anon_page(vma, *page, ksm_scan.address);
				flush_dcache_page(*page);
				rmap_item = get_next_rmap_item(slot,
					ksm_scan.rmap_list, ksm_scan.address);
				if (rmap_item) {
					ksm_scan.rmap_list =
							&rmap_item->rmap_list;
					ksm_scan.address += PAGE_SIZE;
				} else
					put_page(*page);
				up_read(&mm->mmap_sem);
				return rmap_item;
			}
			put_page(*page);
			ksm_scan.address += PAGE_SIZE;
			cond_resched();
		}
	}

	if (ksm_test_exit(mm)) {
		ksm_scan.address = 0;
		ksm_scan.rmap_list = &slot->rmap_list;
	}
	/*
	 * Nuke all the rmap_items that are above this current rmap:
	 * because there were no VM_MERGEABLE vmas with such addresses.
	 */
	remove_trailing_rmap_items(slot, ksm_scan.rmap_list);

	spin_lock(&ksm_mmlist_lock);
	ksm_scan.mm_slot = list_entry(slot->mm_list.next,
						struct mm_slot, mm_list);
	if (ksm_scan.address == 0) {
		/*
		 * We've completed a full scan of all vmas, holding mmap_sem
		 * throughout, and found no VM_MERGEABLE: so do the same as
		 * __ksm_exit does to remove this mm from all our lists now.
		 * This applies either when cleaning up after __ksm_exit
		 * (but beware: we can reach here even before __ksm_exit),
		 * or when all VM_MERGEABLE areas have been unmapped (and
		 * mmap_sem then protects against race with MADV_MERGEABLE).
		 */
		hash_del(&slot->link);
		list_del(&slot->mm_list);
		spin_unlock(&ksm_mmlist_lock);

		free_mm_slot(slot);
		clear_bit(MMF_VM_MERGEABLE, &mm->flags);
		up_read(&mm->mmap_sem);
		mmdrop(mm);
	} else {
		up_read(&mm->mmap_sem);
		/*
		 * up_read(&mm->mmap_sem) first because after
		 * spin_unlock(&ksm_mmlist_lock) run, the "mm" may
		 * already have been freed under us by __ksm_exit()
		 * because the "mm_slot" is still hashed and
		 * ksm_scan.mm_slot doesn't point to it anymore.
		 */
		spin_unlock(&ksm_mmlist_lock);
	}

	/* Repeat until we've completed scanning the whole list */
	slot = ksm_scan.mm_slot;
	if (slot != &ksm_mm_head)
		goto next_mm;

	ksm_scan.seqnr++;
	return NULL;
}

/**
 * ksm_do_scan  - the ksm scanner main worker function.
 * @scan_npages - number of pages we want to scan before we return.
 */
static void ksm_do_scan(unsigned int scan_npages)
{
	struct rmap_item *rmap_item;
	struct page *uninitialized_var(page);

	while (scan_npages-- && likely(!freezing(current))) {
		cond_resched();
		rmap_item = scan_get_next_rmap_item(&page);
		if (!rmap_item)
			return;
		cmp_and_merge_page(page, rmap_item);
		put_page(page);
	}
}

static int ksmd_should_run(void)
{
	return (ksm_run & KSM_RUN_MERGE) && !list_empty(&ksm_mm_head.mm_list);
}

static int ksm_scan_thread(void *nothing)
{
	set_freezable();
	set_user_nice(current, 5);

	while (!kthread_should_stop()) {
		mutex_lock(&ksm_thread_mutex);
		wait_while_offlining();
		if (ksmd_should_run())
			ksm_do_scan(ksm_thread_pages_to_scan);
		mutex_unlock(&ksm_thread_mutex);

		try_to_freeze();

		if (ksmd_should_run()) {
			schedule_timeout_interruptible(
				msecs_to_jiffies(ksm_thread_sleep_millisecs));
		} else {
			wait_event_freezable(ksm_thread_wait,
				ksmd_should_run() || kthread_should_stop());
		}
	}
	return 0;
}

int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
		unsigned long end, int advice, unsigned long *vm_flags)
{
	struct mm_struct *mm = vma->vm_mm;
	int err;

	switch (advice) {
	case MADV_MERGEABLE:
		/*
		 * Be somewhat over-protective for now!
		 */
		if (*vm_flags & (VM_MERGEABLE | VM_SHARED  | VM_MAYSHARE   |
				 VM_PFNMAP    | VM_IO      | VM_DONTEXPAND |
				 VM_HUGETLB | VM_MIXEDMAP))
			return 0;		/* just ignore the advice */

#ifdef VM_SAO
		if (*vm_flags & VM_SAO)
			return 0;
#endif

		if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) {
			err = __ksm_enter(mm);
			if (err)
				return err;
		}

		*vm_flags |= VM_MERGEABLE;
		break;

	case MADV_UNMERGEABLE:
		if (!(*vm_flags & VM_MERGEABLE))
			return 0;		/* just ignore the advice */

		if (vma->anon_vma) {
			err = unmerge_ksm_pages(vma, start, end);
			if (err)
				return err;
		}

		*vm_flags &= ~VM_MERGEABLE;
		break;
	}

	return 0;
}

int __ksm_enter(struct mm_struct *mm)
{
	struct mm_slot *mm_slot;
	int needs_wakeup;

	mm_slot = alloc_mm_slot();
	if (!mm_slot)
		return -ENOMEM;

	/* Check ksm_run too?  Would need tighter locking */
	needs_wakeup = list_empty(&ksm_mm_head.mm_list);

	spin_lock(&ksm_mmlist_lock);
	insert_to_mm_slots_hash(mm, mm_slot);
	/*
	 * When KSM_RUN_MERGE (or KSM_RUN_STOP),
	 * insert just behind the scanning cursor, to let the area settle
	 * down a little; when fork is followed by immediate exec, we don't
	 * want ksmd to waste time setting up and tearing down an rmap_list.
	 *
	 * But when KSM_RUN_UNMERGE, it's important to insert ahead of its
	 * scanning cursor, otherwise KSM pages in newly forked mms will be
	 * missed: then we might as well insert at the end of the list.
	 */
	if (ksm_run & KSM_RUN_UNMERGE)
		list_add_tail(&mm_slot->mm_list, &ksm_mm_head.mm_list);
	else
		list_add_tail(&mm_slot->mm_list, &ksm_scan.mm_slot->mm_list);
	spin_unlock(&ksm_mmlist_lock);

	set_bit(MMF_VM_MERGEABLE, &mm->flags);
	mmgrab(mm);

	if (needs_wakeup)
		wake_up_interruptible(&ksm_thread_wait);

	return 0;
}

void __ksm_exit(struct mm_struct *mm)
{
	struct mm_slot *mm_slot;
	int easy_to_free = 0;

	/*
	 * This process is exiting: if it's straightforward (as is the
	 * case when ksmd was never running), free mm_slot immediately.
	 * But if it's at the cursor or has rmap_items linked to it, use
	 * mmap_sem to synchronize with any break_cows before pagetables
	 * are freed, and leave the mm_slot on the list for ksmd to free.
	 * Beware: ksm may already have noticed it exiting and freed the slot.
	 */

	spin_lock(&ksm_mmlist_lock);
	mm_slot = get_mm_slot(mm);
	if (mm_slot && ksm_scan.mm_slot != mm_slot) {
		if (!mm_slot->rmap_list) {
			hash_del(&mm_slot->link);
			list_del(&mm_slot->mm_list);
			easy_to_free = 1;
		} else {
			list_move(&mm_slot->mm_list,
				  &ksm_scan.mm_slot->mm_list);
		}
	}
	spin_unlock(&ksm_mmlist_lock);

	if (easy_to_free) {
		free_mm_slot(mm_slot);
		clear_bit(MMF_VM_MERGEABLE, &mm->flags);
		mmdrop(mm);
	} else if (mm_slot) {
		down_write(&mm->mmap_sem);
		up_write(&mm->mmap_sem);
	}
}

struct page *ksm_might_need_to_copy(struct page *page,
			struct vm_area_struct *vma, unsigned long address)
{
	struct anon_vma *anon_vma = page_anon_vma(page);
	struct page *new_page;

	if (PageKsm(page)) {
		if (page_stable_node(page) &&
		    !(ksm_run & KSM_RUN_UNMERGE))
			return page;	/* no need to copy it */
	} else if (!anon_vma) {
		return page;		/* no need to copy it */
	} else if (anon_vma->root == vma->anon_vma->root &&
		 page->index == linear_page_index(vma, address)) {
		return page;		/* still no need to copy it */
	}
	if (!PageUptodate(page))
		return page;		/* let do_swap_page report the error */

	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
	if (new_page) {
		copy_user_highpage(new_page, page, address, vma);

		SetPageDirty(new_page);
		__SetPageUptodate(new_page);
		__SetPageLocked(new_page);
	}

	return new_page;
}

void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc)
{
	struct stable_node *stable_node;
	struct rmap_item *rmap_item;
	int search_new_forks = 0;

	VM_BUG_ON_PAGE(!PageKsm(page), page);

	/*
	 * Rely on the page lock to protect against concurrent modifications
	 * to that page's node of the stable tree.
	 */
	VM_BUG_ON_PAGE(!PageLocked(page), page);

	stable_node = page_stable_node(page);
	if (!stable_node)
		return;
again:
	hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) {
		struct anon_vma *anon_vma = rmap_item->anon_vma;
		struct anon_vma_chain *vmac;
		struct vm_area_struct *vma;

		cond_resched();
		anon_vma_lock_read(anon_vma);
		anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root,
					       0, ULONG_MAX) {
			cond_resched();
			vma = vmac->vma;
			if (rmap_item->address < vma->vm_start ||
			    rmap_item->address >= vma->vm_end)
				continue;
			/*
			 * Initially we examine only the vma which covers this
			 * rmap_item; but later, if there is still work to do,
			 * we examine covering vmas in other mms: in case they
			 * were forked from the original since ksmd passed.
			 */
			if ((rmap_item->mm == vma->vm_mm) == search_new_forks)
				continue;

			if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))
				continue;

			if (!rwc->rmap_one(page, vma,
					rmap_item->address, rwc->arg)) {
				anon_vma_unlock_read(anon_vma);
				return;
			}
			if (rwc->done && rwc->done(page)) {
				anon_vma_unlock_read(anon_vma);
				return;
			}
		}
		anon_vma_unlock_read(anon_vma);
	}
	if (!search_new_forks++)
		goto again;
}

#ifdef CONFIG_MIGRATION
void ksm_migrate_page(struct page *newpage, struct page *oldpage)
{
	struct stable_node *stable_node;

	VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage);
	VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
	VM_BUG_ON_PAGE(newpage->mapping != oldpage->mapping, newpage);

	stable_node = page_stable_node(newpage);
	if (stable_node) {
		VM_BUG_ON_PAGE(stable_node->kpfn != page_to_pfn(oldpage), oldpage);
		stable_node->kpfn = page_to_pfn(newpage);
		/*
		 * newpage->mapping was set in advance; now we need smp_wmb()
		 * to make sure that the new stable_node->kpfn is visible
		 * to get_ksm_page() before it can see that oldpage->mapping
		 * has gone stale (or that PageSwapCache has been cleared).
		 */
		smp_wmb();
		set_page_stable_node(oldpage, NULL);
	}
}
#endif /* CONFIG_MIGRATION */

#ifdef CONFIG_MEMORY_HOTREMOVE
static void wait_while_offlining(void)
{
	while (ksm_run & KSM_RUN_OFFLINE) {
		mutex_unlock(&ksm_thread_mutex);
		wait_on_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE),
			    TASK_UNINTERRUPTIBLE);
		mutex_lock(&ksm_thread_mutex);
	}
}

static void ksm_check_stable_tree(unsigned long start_pfn,
				  unsigned long end_pfn)
{
	struct stable_node *stable_node, *next;
	struct rb_node *node;
	int nid;

	for (nid = 0; nid < ksm_nr_node_ids; nid++) {
		node = rb_first(root_stable_tree + nid);
		while (node) {
			stable_node = rb_entry(node, struct stable_node, node);
			if (stable_node->kpfn >= start_pfn &&
			    stable_node->kpfn < end_pfn) {
				/*
				 * Don't get_ksm_page, page has already gone:
				 * which is why we keep kpfn instead of page*
				 */
				remove_node_from_stable_tree(stable_node);
				node = rb_first(root_stable_tree + nid);
			} else
				node = rb_next(node);
			cond_resched();
		}
	}
	list_for_each_entry_safe(stable_node, next, &migrate_nodes, list) {
		if (stable_node->kpfn >= start_pfn &&
		    stable_node->kpfn < end_pfn)
			remove_node_from_stable_tree(stable_node);
		cond_resched();
	}
}

static int ksm_memory_callback(struct notifier_block *self,
			       unsigned long action, void *arg)
{
	struct memory_notify *mn = arg;

	switch (action) {
	case MEM_GOING_OFFLINE:
		/*
		 * Prevent ksm_do_scan(), unmerge_and_remove_all_rmap_items()
		 * and remove_all_stable_nodes() while memory is going offline:
		 * it is unsafe for them to touch the stable tree at this time.
		 * But unmerge_ksm_pages(), rmap lookups and other entry points
		 * which do not need the ksm_thread_mutex are all safe.
		 */
		mutex_lock(&ksm_thread_mutex);
		ksm_run |= KSM_RUN_OFFLINE;
		mutex_unlock(&ksm_thread_mutex);
		break;

	case MEM_OFFLINE:
		/*
		 * Most of the work is done by page migration; but there might
		 * be a few stable_nodes left over, still pointing to struct
		 * pages which have been offlined: prune those from the tree,
		 * otherwise get_ksm_page() might later try to access a
		 * non-existent struct page.
		 */
		ksm_check_stable_tree(mn->start_pfn,
				      mn->start_pfn + mn->nr_pages);
		/* fallthrough */

	case MEM_CANCEL_OFFLINE:
		mutex_lock(&ksm_thread_mutex);
		ksm_run &= ~KSM_RUN_OFFLINE;
		mutex_unlock(&ksm_thread_mutex);

		smp_mb();	/* wake_up_bit advises this */
		wake_up_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE));
		break;
	}
	return NOTIFY_OK;
}
#else
static void wait_while_offlining(void)
{
}
#endif /* CONFIG_MEMORY_HOTREMOVE */

#ifdef CONFIG_SYSFS
/*
 * This all compiles without CONFIG_SYSFS, but is a waste of space.
 */

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

static ssize_t sleep_millisecs_show(struct kobject *kobj,
				    struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%u\n", ksm_thread_sleep_millisecs);
}

static ssize_t sleep_millisecs_store(struct kobject *kobj,
				     struct kobj_attribute *attr,
				     const char *buf, size_t count)
{
	unsigned long msecs;
	int err;

	err = kstrtoul(buf, 10, &msecs);
	if (err || msecs > UINT_MAX)
		return -EINVAL;

	ksm_thread_sleep_millisecs = msecs;

	return count;
}
KSM_ATTR(sleep_millisecs);

static ssize_t pages_to_scan_show(struct kobject *kobj,
				  struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%u\n", ksm_thread_pages_to_scan);
}

static ssize_t pages_to_scan_store(struct kobject *kobj,
				   struct kobj_attribute *attr,
				   const char *buf, size_t count)
{
	int err;
	unsigned long nr_pages;

	err = kstrtoul(buf, 10, &nr_pages);
	if (err || nr_pages > UINT_MAX)
		return -EINVAL;

	ksm_thread_pages_to_scan = nr_pages;

	return count;
}
KSM_ATTR(pages_to_scan);

static ssize_t run_show(struct kobject *kobj, struct kobj_attribute *attr,
			char *buf)
{
	return sprintf(buf, "%lu\n", ksm_run);
}

static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr,
			 const char *buf, size_t count)
{
	int err;
	unsigned long flags;

	err = kstrtoul(buf, 10, &flags);
	if (err || flags > UINT_MAX)
		return -EINVAL;
	if (flags > KSM_RUN_UNMERGE)
		return -EINVAL;

	/*
	 * KSM_RUN_MERGE sets ksmd running, and 0 stops it running.
	 * KSM_RUN_UNMERGE stops it running and unmerges all rmap_items,
	 * breaking COW to free the pages_shared (but leaves mm_slots
	 * on the list for when ksmd may be set running again).
	 */

	mutex_lock(&ksm_thread_mutex);
	wait_while_offlining();
	if (ksm_run != flags) {
		ksm_run = flags;
		if (flags & KSM_RUN_UNMERGE) {
			set_current_oom_origin();
			err = unmerge_and_remove_all_rmap_items();
			clear_current_oom_origin();
			if (err) {
				ksm_run = KSM_RUN_STOP;
				count = err;
			}
		}
	}
	mutex_unlock(&ksm_thread_mutex);

	if (flags & KSM_RUN_MERGE)
		wake_up_interruptible(&ksm_thread_wait);

	return count;
}
KSM_ATTR(run);

#ifdef CONFIG_NUMA
static ssize_t merge_across_nodes_show(struct kobject *kobj,
				struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%u\n", ksm_merge_across_nodes);
}

static ssize_t merge_across_nodes_store(struct kobject *kobj,
				   struct kobj_attribute *attr,
				   const char *buf, size_t count)
{
	int err;
	unsigned long knob;

	err = kstrtoul(buf, 10, &knob);
	if (err)
		return err;
	if (knob > 1)
		return -EINVAL;

	mutex_lock(&ksm_thread_mutex);
	wait_while_offlining();
	if (ksm_merge_across_nodes != knob) {
		if (ksm_pages_shared || remove_all_stable_nodes())
			err = -EBUSY;
		else if (root_stable_tree == one_stable_tree) {
			struct rb_root *buf;
			/*
			 * This is the first time that we switch away from the
			 * default of merging across nodes: must now allocate
			 * a buffer to hold as many roots as may be needed.
			 * Allocate stable and unstable together:
			 * MAXSMP NODES_SHIFT 10 will use 16kB.
			 */
			buf = kcalloc(nr_node_ids + nr_node_ids, sizeof(*buf),
				      GFP_KERNEL);
			/* Let us assume that RB_ROOT is NULL is zero */
			if (!buf)
				err = -ENOMEM;
			else {
				root_stable_tree = buf;
				root_unstable_tree = buf + nr_node_ids;
				/* Stable tree is empty but not the unstable */
				root_unstable_tree[0] = one_unstable_tree[0];
			}
		}
		if (!err) {
			ksm_merge_across_nodes = knob;
			ksm_nr_node_ids = knob ? 1 : nr_node_ids;
		}
	}
	mutex_unlock(&ksm_thread_mutex);

	return err ? err : count;
}
KSM_ATTR(merge_across_nodes);
#endif

static ssize_t use_zero_pages_show(struct kobject *kobj,
				struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%u\n", ksm_use_zero_pages);
}
static ssize_t use_zero_pages_store(struct kobject *kobj,
				   struct kobj_attribute *attr,
				   const char *buf, size_t count)
{
	int err;
	bool value;

	err = kstrtobool(buf, &value);
	if (err)
		return -EINVAL;

	ksm_use_zero_pages = value;

	return count;
}
KSM_ATTR(use_zero_pages);

static ssize_t pages_shared_show(struct kobject *kobj,
				 struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%lu\n", ksm_pages_shared);
}
KSM_ATTR_RO(pages_shared);

static ssize_t pages_sharing_show(struct kobject *kobj,
				  struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%lu\n", ksm_pages_sharing);
}
KSM_ATTR_RO(pages_sharing);

static ssize_t pages_unshared_show(struct kobject *kobj,
				   struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%lu\n", ksm_pages_unshared);
}
KSM_ATTR_RO(pages_unshared);

static ssize_t pages_volatile_show(struct kobject *kobj,
				   struct kobj_attribute *attr, char *buf)
{
	long ksm_pages_volatile;

	ksm_pages_volatile = ksm_rmap_items - ksm_pages_shared
				- ksm_pages_sharing - ksm_pages_unshared;
	/*
	 * It was not worth any locking to calculate that statistic,
	 * but it might therefore sometimes be negative: conceal that.
	 */
	if (ksm_pages_volatile < 0)
		ksm_pages_volatile = 0;
	return sprintf(buf, "%ld\n", ksm_pages_volatile);
}
KSM_ATTR_RO(pages_volatile);

static ssize_t full_scans_show(struct kobject *kobj,
			       struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%lu\n", ksm_scan.seqnr);
}
KSM_ATTR_RO(full_scans);

static struct attribute *ksm_attrs[] = {
	&sleep_millisecs_attr.attr,
	&pages_to_scan_attr.attr,
	&run_attr.attr,
	&pages_shared_attr.attr,
	&pages_sharing_attr.attr,
	&pages_unshared_attr.attr,
	&pages_volatile_attr.attr,
	&full_scans_attr.attr,
#ifdef CONFIG_NUMA
	&merge_across_nodes_attr.attr,
#endif
	&use_zero_pages_attr.attr,
	NULL,
};

static struct attribute_group ksm_attr_group = {
	.attrs = ksm_attrs,
	.name = "ksm",
};
#endif /* CONFIG_SYSFS */

static int __init ksm_init(void)
{
	struct task_struct *ksm_thread;
	int err;

	/* The correct value depends on page size and endianness */
	zero_checksum = calc_checksum(ZERO_PAGE(0));
	/* Default to false for backwards compatibility */
	ksm_use_zero_pages = false;

	err = ksm_slab_init();
	if (err)
		goto out;

	ksm_thread = kthread_run(ksm_scan_thread, NULL, "ksmd");
	if (IS_ERR(ksm_thread)) {
		pr_err("ksm: creating kthread failed\n");
		err = PTR_ERR(ksm_thread);
		goto out_free;
	}

#ifdef CONFIG_SYSFS
	err = sysfs_create_group(mm_kobj, &ksm_attr_group);
	if (err) {
		pr_err("ksm: register sysfs failed\n");
		kthread_stop(ksm_thread);
		goto out_free;
	}
#else
	ksm_run = KSM_RUN_MERGE;	/* no way for user to start it */

#endif /* CONFIG_SYSFS */

#ifdef CONFIG_MEMORY_HOTREMOVE
	/* There is no significance to this priority 100 */
	hotplug_memory_notifier(ksm_memory_callback, 100);
#endif
	return 0;

out_free:
	ksm_slab_free();
out:
	return err;
}
subsys_initcall(ksm_init);