summaryrefslogtreecommitdiff
path: root/mm/rmap.c
blob: a0cbbf201c9864e02d7ffe9c50bdc72183f5f216 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
/*
 * mm/rmap.c - physical to virtual reverse mappings
 *
 * Copyright 2001, Rik van Riel <riel@conectiva.com.br>
 * Released under the General Public License (GPL).
 *
 * Simple, low overhead reverse mapping scheme.
 * Please try to keep this thing as modular as possible.
 *
 * Provides methods for unmapping each kind of mapped page:
 * the anon methods track anonymous pages, and
 * the file methods track pages belonging to an inode.
 *
 * Original design by Rik van Riel <riel@conectiva.com.br> 2001
 * File methods by Dave McCracken <dmccr@us.ibm.com> 2003, 2004
 * Anonymous methods by Andrea Arcangeli <andrea@suse.de> 2004
 * Contributions by Hugh Dickins 2003, 2004
 */

/*
 * Lock ordering in mm:
 *
 * inode->i_rwsem	(while writing or truncating, not reading or faulting)
 *   mm->mmap_lock
 *     mapping->invalidate_lock (in filemap_fault)
 *       page->flags PG_locked (lock_page)   * (see hugetlbfs below)
 *         hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share)
 *           mapping->i_mmap_rwsem
 *             hugetlb_fault_mutex (hugetlbfs specific page fault mutex)
 *             anon_vma->rwsem
 *               mm->page_table_lock or pte_lock
 *                 swap_lock (in swap_duplicate, swap_info_get)
 *                   mmlist_lock (in mmput, drain_mmlist and others)
 *                   mapping->private_lock (in block_dirty_folio)
 *                     folio_lock_memcg move_lock (in block_dirty_folio)
 *                       i_pages lock (widely used)
 *                         lruvec->lru_lock (in folio_lruvec_lock_irq)
 *                   inode->i_lock (in set_page_dirty's __mark_inode_dirty)
 *                   bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty)
 *                     sb_lock (within inode_lock in fs/fs-writeback.c)
 *                     i_pages lock (widely used, in set_page_dirty,
 *                               in arch-dependent flush_dcache_mmap_lock,
 *                               within bdi.wb->list_lock in __sync_single_inode)
 *
 * anon_vma->rwsem,mapping->i_mmap_rwsem   (memory_failure, collect_procs_anon)
 *   ->tasklist_lock
 *     pte map lock
 *
 * * hugetlbfs PageHuge() pages take locks in this order:
 *         mapping->i_mmap_rwsem
 *           hugetlb_fault_mutex (hugetlbfs specific page fault mutex)
 *             page->flags PG_locked (lock_page)
 */

#include <linux/mm.h>
#include <linux/sched/mm.h>
#include <linux/sched/task.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/rcupdate.h>
#include <linux/export.h>
#include <linux/memcontrol.h>
#include <linux/mmu_notifier.h>
#include <linux/migrate.h>
#include <linux/hugetlb.h>
#include <linux/huge_mm.h>
#include <linux/backing-dev.h>
#include <linux/page_idle.h>
#include <linux/memremap.h>
#include <linux/userfaultfd_k.h>

#include <asm/tlbflush.h>

#define CREATE_TRACE_POINTS
#include <trace/events/tlb.h>
#include <trace/events/migrate.h>

#include "internal.h"

static struct kmem_cache *anon_vma_cachep;
static struct kmem_cache *anon_vma_chain_cachep;

static inline struct anon_vma *anon_vma_alloc(void)
{
	struct anon_vma *anon_vma;

	anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
	if (anon_vma) {
		atomic_set(&anon_vma->refcount, 1);
		anon_vma->degree = 1;	/* Reference for first vma */
		anon_vma->parent = anon_vma;
		/*
		 * Initialise the anon_vma root to point to itself. If called
		 * from fork, the root will be reset to the parents anon_vma.
		 */
		anon_vma->root = anon_vma;
	}

	return anon_vma;
}

static inline void anon_vma_free(struct anon_vma *anon_vma)
{
	VM_BUG_ON(atomic_read(&anon_vma->refcount));

	/*
	 * Synchronize against folio_lock_anon_vma_read() such that
	 * we can safely hold the lock without the anon_vma getting
	 * freed.
	 *
	 * Relies on the full mb implied by the atomic_dec_and_test() from
	 * put_anon_vma() against the acquire barrier implied by
	 * down_read_trylock() from folio_lock_anon_vma_read(). This orders:
	 *
	 * folio_lock_anon_vma_read()	VS	put_anon_vma()
	 *   down_read_trylock()		  atomic_dec_and_test()
	 *   LOCK				  MB
	 *   atomic_read()			  rwsem_is_locked()
	 *
	 * LOCK should suffice since the actual taking of the lock must
	 * happen _before_ what follows.
	 */
	might_sleep();
	if (rwsem_is_locked(&anon_vma->root->rwsem)) {
		anon_vma_lock_write(anon_vma);
		anon_vma_unlock_write(anon_vma);
	}

	kmem_cache_free(anon_vma_cachep, anon_vma);
}

static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp)
{
	return kmem_cache_alloc(anon_vma_chain_cachep, gfp);
}

static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain)
{
	kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain);
}

static void anon_vma_chain_link(struct vm_area_struct *vma,
				struct anon_vma_chain *avc,
				struct anon_vma *anon_vma)
{
	avc->vma = vma;
	avc->anon_vma = anon_vma;
	list_add(&avc->same_vma, &vma->anon_vma_chain);
	anon_vma_interval_tree_insert(avc, &anon_vma->rb_root);
}

/**
 * __anon_vma_prepare - attach an anon_vma to a memory region
 * @vma: the memory region in question
 *
 * This makes sure the memory mapping described by 'vma' has
 * an 'anon_vma' attached to it, so that we can associate the
 * anonymous pages mapped into it with that anon_vma.
 *
 * The common case will be that we already have one, which
 * is handled inline by anon_vma_prepare(). But if
 * not we either need to find an adjacent mapping that we
 * can re-use the anon_vma from (very common when the only
 * reason for splitting a vma has been mprotect()), or we
 * allocate a new one.
 *
 * Anon-vma allocations are very subtle, because we may have
 * optimistically looked up an anon_vma in folio_lock_anon_vma_read()
 * and that may actually touch the rwsem even in the newly
 * allocated vma (it depends on RCU to make sure that the
 * anon_vma isn't actually destroyed).
 *
 * As a result, we need to do proper anon_vma locking even
 * for the new allocation. At the same time, we do not want
 * to do any locking for the common case of already having
 * an anon_vma.
 *
 * This must be called with the mmap_lock held for reading.
 */
int __anon_vma_prepare(struct vm_area_struct *vma)
{
	struct mm_struct *mm = vma->vm_mm;
	struct anon_vma *anon_vma, *allocated;
	struct anon_vma_chain *avc;

	might_sleep();

	avc = anon_vma_chain_alloc(GFP_KERNEL);
	if (!avc)
		goto out_enomem;

	anon_vma = find_mergeable_anon_vma(vma);
	allocated = NULL;
	if (!anon_vma) {
		anon_vma = anon_vma_alloc();
		if (unlikely(!anon_vma))
			goto out_enomem_free_avc;
		allocated = anon_vma;
	}

	anon_vma_lock_write(anon_vma);
	/* page_table_lock to protect against threads */
	spin_lock(&mm->page_table_lock);
	if (likely(!vma->anon_vma)) {
		vma->anon_vma = anon_vma;
		anon_vma_chain_link(vma, avc, anon_vma);
		/* vma reference or self-parent link for new root */
		anon_vma->degree++;
		allocated = NULL;
		avc = NULL;
	}
	spin_unlock(&mm->page_table_lock);
	anon_vma_unlock_write(anon_vma);

	if (unlikely(allocated))
		put_anon_vma(allocated);
	if (unlikely(avc))
		anon_vma_chain_free(avc);

	return 0;

 out_enomem_free_avc:
	anon_vma_chain_free(avc);
 out_enomem:
	return -ENOMEM;
}

/*
 * This is a useful helper function for locking the anon_vma root as
 * we traverse the vma->anon_vma_chain, looping over anon_vma's that
 * have the same vma.
 *
 * Such anon_vma's should have the same root, so you'd expect to see
 * just a single mutex_lock for the whole traversal.
 */
static inline struct anon_vma *lock_anon_vma_root(struct anon_vma *root, struct anon_vma *anon_vma)
{
	struct anon_vma *new_root = anon_vma->root;
	if (new_root != root) {
		if (WARN_ON_ONCE(root))
			up_write(&root->rwsem);
		root = new_root;
		down_write(&root->rwsem);
	}
	return root;
}

static inline void unlock_anon_vma_root(struct anon_vma *root)
{
	if (root)
		up_write(&root->rwsem);
}

/*
 * Attach the anon_vmas from src to dst.
 * Returns 0 on success, -ENOMEM on failure.
 *
 * anon_vma_clone() is called by __vma_adjust(), __split_vma(), copy_vma() and
 * anon_vma_fork(). The first three want an exact copy of src, while the last
 * one, anon_vma_fork(), may try to reuse an existing anon_vma to prevent
 * endless growth of anon_vma. Since dst->anon_vma is set to NULL before call,
 * we can identify this case by checking (!dst->anon_vma && src->anon_vma).
 *
 * If (!dst->anon_vma && src->anon_vma) is true, this function tries to find
 * and reuse existing anon_vma which has no vmas and only one child anon_vma.
 * This prevents degradation of anon_vma hierarchy to endless linear chain in
 * case of constantly forking task. On the other hand, an anon_vma with more
 * than one child isn't reused even if there was no alive vma, thus rmap
 * walker has a good chance of avoiding scanning the whole hierarchy when it
 * searches where page is mapped.
 */
int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
{
	struct anon_vma_chain *avc, *pavc;
	struct anon_vma *root = NULL;

	list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) {
		struct anon_vma *anon_vma;

		avc = anon_vma_chain_alloc(GFP_NOWAIT | __GFP_NOWARN);
		if (unlikely(!avc)) {
			unlock_anon_vma_root(root);
			root = NULL;
			avc = anon_vma_chain_alloc(GFP_KERNEL);
			if (!avc)
				goto enomem_failure;
		}
		anon_vma = pavc->anon_vma;
		root = lock_anon_vma_root(root, anon_vma);
		anon_vma_chain_link(dst, avc, anon_vma);

		/*
		 * Reuse existing anon_vma if its degree lower than two,
		 * that means it has no vma and only one anon_vma child.
		 *
		 * Do not chose parent anon_vma, otherwise first child
		 * will always reuse it. Root anon_vma is never reused:
		 * it has self-parent reference and at least one child.
		 */
		if (!dst->anon_vma && src->anon_vma &&
		    anon_vma != src->anon_vma && anon_vma->degree < 2)
			dst->anon_vma = anon_vma;
	}
	if (dst->anon_vma)
		dst->anon_vma->degree++;
	unlock_anon_vma_root(root);
	return 0;

 enomem_failure:
	/*
	 * dst->anon_vma is dropped here otherwise its degree can be incorrectly
	 * decremented in unlink_anon_vmas().
	 * We can safely do this because callers of anon_vma_clone() don't care
	 * about dst->anon_vma if anon_vma_clone() failed.
	 */
	dst->anon_vma = NULL;
	unlink_anon_vmas(dst);
	return -ENOMEM;
}

/*
 * Attach vma to its own anon_vma, as well as to the anon_vmas that
 * the corresponding VMA in the parent process is attached to.
 * Returns 0 on success, non-zero on failure.
 */
int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
{
	struct anon_vma_chain *avc;
	struct anon_vma *anon_vma;
	int error;

	/* Don't bother if the parent process has no anon_vma here. */
	if (!pvma->anon_vma)
		return 0;

	/* Drop inherited anon_vma, we'll reuse existing or allocate new. */
	vma->anon_vma = NULL;

	/*
	 * First, attach the new VMA to the parent VMA's anon_vmas,
	 * so rmap can find non-COWed pages in child processes.
	 */
	error = anon_vma_clone(vma, pvma);
	if (error)
		return error;

	/* An existing anon_vma has been reused, all done then. */
	if (vma->anon_vma)
		return 0;

	/* Then add our own anon_vma. */
	anon_vma = anon_vma_alloc();
	if (!anon_vma)
		goto out_error;
	avc = anon_vma_chain_alloc(GFP_KERNEL);
	if (!avc)
		goto out_error_free_anon_vma;

	/*
	 * The root anon_vma's rwsem is the lock actually used when we
	 * lock any of the anon_vmas in this anon_vma tree.
	 */
	anon_vma->root = pvma->anon_vma->root;
	anon_vma->parent = pvma->anon_vma;
	/*
	 * With refcounts, an anon_vma can stay around longer than the
	 * process it belongs to. The root anon_vma needs to be pinned until
	 * this anon_vma is freed, because the lock lives in the root.
	 */
	get_anon_vma(anon_vma->root);
	/* Mark this anon_vma as the one where our new (COWed) pages go. */
	vma->anon_vma = anon_vma;
	anon_vma_lock_write(anon_vma);
	anon_vma_chain_link(vma, avc, anon_vma);
	anon_vma->parent->degree++;
	anon_vma_unlock_write(anon_vma);

	return 0;

 out_error_free_anon_vma:
	put_anon_vma(anon_vma);
 out_error:
	unlink_anon_vmas(vma);
	return -ENOMEM;
}

void unlink_anon_vmas(struct vm_area_struct *vma)
{
	struct anon_vma_chain *avc, *next;
	struct anon_vma *root = NULL;

	/*
	 * Unlink each anon_vma chained to the VMA.  This list is ordered
	 * from newest to oldest, ensuring the root anon_vma gets freed last.
	 */
	list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
		struct anon_vma *anon_vma = avc->anon_vma;

		root = lock_anon_vma_root(root, anon_vma);
		anon_vma_interval_tree_remove(avc, &anon_vma->rb_root);

		/*
		 * Leave empty anon_vmas on the list - we'll need
		 * to free them outside the lock.
		 */
		if (RB_EMPTY_ROOT(&anon_vma->rb_root.rb_root)) {
			anon_vma->parent->degree--;
			continue;
		}

		list_del(&avc->same_vma);
		anon_vma_chain_free(avc);
	}
	if (vma->anon_vma) {
		vma->anon_vma->degree--;

		/*
		 * vma would still be needed after unlink, and anon_vma will be prepared
		 * when handle fault.
		 */
		vma->anon_vma = NULL;
	}
	unlock_anon_vma_root(root);

	/*
	 * Iterate the list once more, it now only contains empty and unlinked
	 * anon_vmas, destroy them. Could not do before due to __put_anon_vma()
	 * needing to write-acquire the anon_vma->root->rwsem.
	 */
	list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
		struct anon_vma *anon_vma = avc->anon_vma;

		VM_WARN_ON(anon_vma->degree);
		put_anon_vma(anon_vma);

		list_del(&avc->same_vma);
		anon_vma_chain_free(avc);
	}
}

static void anon_vma_ctor(void *data)
{
	struct anon_vma *anon_vma = data;

	init_rwsem(&anon_vma->rwsem);
	atomic_set(&anon_vma->refcount, 0);
	anon_vma->rb_root = RB_ROOT_CACHED;
}

void __init anon_vma_init(void)
{
	anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma),
			0, SLAB_TYPESAFE_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT,
			anon_vma_ctor);
	anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain,
			SLAB_PANIC|SLAB_ACCOUNT);
}

/*
 * Getting a lock on a stable anon_vma from a page off the LRU is tricky!
 *
 * Since there is no serialization what so ever against page_remove_rmap()
 * the best this function can do is return a refcount increased anon_vma
 * that might have been relevant to this page.
 *
 * The page might have been remapped to a different anon_vma or the anon_vma
 * returned may already be freed (and even reused).
 *
 * In case it was remapped to a different anon_vma, the new anon_vma will be a
 * child of the old anon_vma, and the anon_vma lifetime rules will therefore
 * ensure that any anon_vma obtained from the page will still be valid for as
 * long as we observe page_mapped() [ hence all those page_mapped() tests ].
 *
 * All users of this function must be very careful when walking the anon_vma
 * chain and verify that the page in question is indeed mapped in it
 * [ something equivalent to page_mapped_in_vma() ].
 *
 * Since anon_vma's slab is SLAB_TYPESAFE_BY_RCU and we know from
 * page_remove_rmap() that the anon_vma pointer from page->mapping is valid
 * if there is a mapcount, we can dereference the anon_vma after observing
 * those.
 */
struct anon_vma *page_get_anon_vma(struct page *page)
{
	struct anon_vma *anon_vma = NULL;
	unsigned long anon_mapping;

	rcu_read_lock();
	anon_mapping = (unsigned long)READ_ONCE(page->mapping);
	if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
		goto out;
	if (!page_mapped(page))
		goto out;

	anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
	if (!atomic_inc_not_zero(&anon_vma->refcount)) {
		anon_vma = NULL;
		goto out;
	}

	/*
	 * If this page is still mapped, then its anon_vma cannot have been
	 * freed.  But if it has been unmapped, we have no security against the
	 * anon_vma structure being freed and reused (for another anon_vma:
	 * SLAB_TYPESAFE_BY_RCU guarantees that - so the atomic_inc_not_zero()
	 * above cannot corrupt).
	 */
	if (!page_mapped(page)) {
		rcu_read_unlock();
		put_anon_vma(anon_vma);
		return NULL;
	}
out:
	rcu_read_unlock();

	return anon_vma;
}

/*
 * Similar to page_get_anon_vma() except it locks the anon_vma.
 *
 * Its a little more complex as it tries to keep the fast path to a single
 * atomic op -- the trylock. If we fail the trylock, we fall back to getting a
 * reference like with page_get_anon_vma() and then block on the mutex.
 */
struct anon_vma *folio_lock_anon_vma_read(struct folio *folio)
{
	struct anon_vma *anon_vma = NULL;
	struct anon_vma *root_anon_vma;
	unsigned long anon_mapping;

	rcu_read_lock();
	anon_mapping = (unsigned long)READ_ONCE(folio->mapping);
	if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
		goto out;
	if (!folio_mapped(folio))
		goto out;

	anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
	root_anon_vma = READ_ONCE(anon_vma->root);
	if (down_read_trylock(&root_anon_vma->rwsem)) {
		/*
		 * If the folio is still mapped, then this anon_vma is still
		 * its anon_vma, and holding the mutex ensures that it will
		 * not go away, see anon_vma_free().
		 */
		if (!folio_mapped(folio)) {
			up_read(&root_anon_vma->rwsem);
			anon_vma = NULL;
		}
		goto out;
	}

	/* trylock failed, we got to sleep */
	if (!atomic_inc_not_zero(&anon_vma->refcount)) {
		anon_vma = NULL;
		goto out;
	}

	if (!folio_mapped(folio)) {
		rcu_read_unlock();
		put_anon_vma(anon_vma);
		return NULL;
	}

	/* we pinned the anon_vma, its safe to sleep */
	rcu_read_unlock();
	anon_vma_lock_read(anon_vma);

	if (atomic_dec_and_test(&anon_vma->refcount)) {
		/*
		 * Oops, we held the last refcount, release the lock
		 * and bail -- can't simply use put_anon_vma() because
		 * we'll deadlock on the anon_vma_lock_write() recursion.
		 */
		anon_vma_unlock_read(anon_vma);
		__put_anon_vma(anon_vma);
		anon_vma = NULL;
	}

	return anon_vma;

out:
	rcu_read_unlock();
	return anon_vma;
}

void page_unlock_anon_vma_read(struct anon_vma *anon_vma)
{
	anon_vma_unlock_read(anon_vma);
}

#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
/*
 * Flush TLB entries for recently unmapped pages from remote CPUs. It is
 * important if a PTE was dirty when it was unmapped that it's flushed
 * before any IO is initiated on the page to prevent lost writes. Similarly,
 * it must be flushed before freeing to prevent data leakage.
 */
void try_to_unmap_flush(void)
{
	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;

	if (!tlb_ubc->flush_required)
		return;

	arch_tlbbatch_flush(&tlb_ubc->arch);
	tlb_ubc->flush_required = false;
	tlb_ubc->writable = false;
}

/* Flush iff there are potentially writable TLB entries that can race with IO */
void try_to_unmap_flush_dirty(void)
{
	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;

	if (tlb_ubc->writable)
		try_to_unmap_flush();
}

/*
 * Bits 0-14 of mm->tlb_flush_batched record pending generations.
 * Bits 16-30 of mm->tlb_flush_batched bit record flushed generations.
 */
#define TLB_FLUSH_BATCH_FLUSHED_SHIFT	16
#define TLB_FLUSH_BATCH_PENDING_MASK			\
	((1 << (TLB_FLUSH_BATCH_FLUSHED_SHIFT - 1)) - 1)
#define TLB_FLUSH_BATCH_PENDING_LARGE			\
	(TLB_FLUSH_BATCH_PENDING_MASK / 2)

static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable)
{
	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
	int batch, nbatch;

	arch_tlbbatch_add_mm(&tlb_ubc->arch, mm);
	tlb_ubc->flush_required = true;

	/*
	 * Ensure compiler does not re-order the setting of tlb_flush_batched
	 * before the PTE is cleared.
	 */
	barrier();
	batch = atomic_read(&mm->tlb_flush_batched);
retry:
	if ((batch & TLB_FLUSH_BATCH_PENDING_MASK) > TLB_FLUSH_BATCH_PENDING_LARGE) {
		/*
		 * Prevent `pending' from catching up with `flushed' because of
		 * overflow.  Reset `pending' and `flushed' to be 1 and 0 if
		 * `pending' becomes large.
		 */
		nbatch = atomic_cmpxchg(&mm->tlb_flush_batched, batch, 1);
		if (nbatch != batch) {
			batch = nbatch;
			goto retry;
		}
	} else {
		atomic_inc(&mm->tlb_flush_batched);
	}

	/*
	 * If the PTE was dirty then it's best to assume it's writable. The
	 * caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush()
	 * before the page is queued for IO.
	 */
	if (writable)
		tlb_ubc->writable = true;
}

/*
 * Returns true if the TLB flush should be deferred to the end of a batch of
 * unmap operations to reduce IPIs.
 */
static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags)
{
	bool should_defer = false;

	if (!(flags & TTU_BATCH_FLUSH))
		return false;

	/* If remote CPUs need to be flushed then defer batch the flush */
	if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids)
		should_defer = true;
	put_cpu();

	return should_defer;
}

/*
 * Reclaim unmaps pages under the PTL but do not flush the TLB prior to
 * releasing the PTL if TLB flushes are batched. It's possible for a parallel
 * operation such as mprotect or munmap to race between reclaim unmapping
 * the page and flushing the page. If this race occurs, it potentially allows
 * access to data via a stale TLB entry. Tracking all mm's that have TLB
 * batching in flight would be expensive during reclaim so instead track
 * whether TLB batching occurred in the past and if so then do a flush here
 * if required. This will cost one additional flush per reclaim cycle paid
 * by the first operation at risk such as mprotect and mumap.
 *
 * This must be called under the PTL so that an access to tlb_flush_batched
 * that is potentially a "reclaim vs mprotect/munmap/etc" race will synchronise
 * via the PTL.
 */
void flush_tlb_batched_pending(struct mm_struct *mm)
{
	int batch = atomic_read(&mm->tlb_flush_batched);
	int pending = batch & TLB_FLUSH_BATCH_PENDING_MASK;
	int flushed = batch >> TLB_FLUSH_BATCH_FLUSHED_SHIFT;

	if (pending != flushed) {
		flush_tlb_mm(mm);
		/*
		 * If the new TLB flushing is pending during flushing, leave
		 * mm->tlb_flush_batched as is, to avoid losing flushing.
		 */
		atomic_cmpxchg(&mm->tlb_flush_batched, batch,
			       pending | (pending << TLB_FLUSH_BATCH_FLUSHED_SHIFT));
	}
}
#else
static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable)
{
}

static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags)
{
	return false;
}
#endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */

/*
 * At what user virtual address is page expected in vma?
 * Caller should check the page is actually part of the vma.
 */
unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
{
	struct folio *folio = page_folio(page);
	if (folio_test_anon(folio)) {
		struct anon_vma *page__anon_vma = folio_anon_vma(folio);
		/*
		 * Note: swapoff's unuse_vma() is more efficient with this
		 * check, and needs it to match anon_vma when KSM is active.
		 */
		if (!vma->anon_vma || !page__anon_vma ||
		    vma->anon_vma->root != page__anon_vma->root)
			return -EFAULT;
	} else if (!vma->vm_file) {
		return -EFAULT;
	} else if (vma->vm_file->f_mapping != folio->mapping) {
		return -EFAULT;
	}

	return vma_address(page, vma);
}

pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
{
	pgd_t *pgd;
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd = NULL;
	pmd_t pmde;

	pgd = pgd_offset(mm, address);
	if (!pgd_present(*pgd))
		goto out;

	p4d = p4d_offset(pgd, address);
	if (!p4d_present(*p4d))
		goto out;

	pud = pud_offset(p4d, address);
	if (!pud_present(*pud))
		goto out;

	pmd = pmd_offset(pud, address);
	/*
	 * Some THP functions use the sequence pmdp_huge_clear_flush(), set_pmd_at()
	 * without holding anon_vma lock for write.  So when looking for a
	 * genuine pmde (in which to find pte), test present and !THP together.
	 */
	pmde = *pmd;
	barrier();
	if (!pmd_present(pmde) || pmd_trans_huge(pmde))
		pmd = NULL;
out:
	return pmd;
}

struct folio_referenced_arg {
	int mapcount;
	int referenced;
	unsigned long vm_flags;
	struct mem_cgroup *memcg;
};
/*
 * arg: folio_referenced_arg will be passed
 */
static bool folio_referenced_one(struct folio *folio,
		struct vm_area_struct *vma, unsigned long address, void *arg)
{
	struct folio_referenced_arg *pra = arg;
	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0);
	int referenced = 0;

	while (page_vma_mapped_walk(&pvmw)) {
		address = pvmw.address;

		if ((vma->vm_flags & VM_LOCKED) &&
		    (!folio_test_large(folio) || !pvmw.pte)) {
			/* Restore the mlock which got missed */
			mlock_vma_folio(folio, vma, !pvmw.pte);
			page_vma_mapped_walk_done(&pvmw);
			pra->vm_flags |= VM_LOCKED;
			return false; /* To break the loop */
		}

		if (pvmw.pte) {
			if (ptep_clear_flush_young_notify(vma, address,
						pvmw.pte)) {
				/*
				 * Don't treat a reference through
				 * a sequentially read mapping as such.
				 * If the folio has been used in another mapping,
				 * we will catch it; if this other mapping is
				 * already gone, the unmap path will have set
				 * the referenced flag or activated the folio.
				 */
				if (likely(!(vma->vm_flags & VM_SEQ_READ)))
					referenced++;
			}
		} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
			if (pmdp_clear_flush_young_notify(vma, address,
						pvmw.pmd))
				referenced++;
		} else {
			/* unexpected pmd-mapped folio? */
			WARN_ON_ONCE(1);
		}

		pra->mapcount--;
	}

	if (referenced)
		folio_clear_idle(folio);
	if (folio_test_clear_young(folio))
		referenced++;

	if (referenced) {
		pra->referenced++;
		pra->vm_flags |= vma->vm_flags & ~VM_LOCKED;
	}

	if (!pra->mapcount)
		return false; /* To break the loop */

	return true;
}

static bool invalid_folio_referenced_vma(struct vm_area_struct *vma, void *arg)
{
	struct folio_referenced_arg *pra = arg;
	struct mem_cgroup *memcg = pra->memcg;

	if (!mm_match_cgroup(vma->vm_mm, memcg))
		return true;

	return false;
}

/**
 * folio_referenced() - Test if the folio was referenced.
 * @folio: The folio to test.
 * @is_locked: Caller holds lock on the folio.
 * @memcg: target memory cgroup
 * @vm_flags: A combination of all the vma->vm_flags which referenced the folio.
 *
 * Quick test_and_clear_referenced for all mappings of a folio,
 *
 * Return: The number of mappings which referenced the folio.
 */
int folio_referenced(struct folio *folio, int is_locked,
		     struct mem_cgroup *memcg, unsigned long *vm_flags)
{
	int we_locked = 0;
	struct folio_referenced_arg pra = {
		.mapcount = folio_mapcount(folio),
		.memcg = memcg,
	};
	struct rmap_walk_control rwc = {
		.rmap_one = folio_referenced_one,
		.arg = (void *)&pra,
		.anon_lock = folio_lock_anon_vma_read,
	};

	*vm_flags = 0;
	if (!pra.mapcount)
		return 0;

	if (!folio_raw_mapping(folio))
		return 0;

	if (!is_locked && (!folio_test_anon(folio) || folio_test_ksm(folio))) {
		we_locked = folio_trylock(folio);
		if (!we_locked)
			return 1;
	}

	/*
	 * If we are reclaiming on behalf of a cgroup, skip
	 * counting on behalf of references from different
	 * cgroups
	 */
	if (memcg) {
		rwc.invalid_vma = invalid_folio_referenced_vma;
	}

	rmap_walk(folio, &rwc);
	*vm_flags = pra.vm_flags;

	if (we_locked)
		folio_unlock(folio);

	return pra.referenced;
}

static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw)
{
	int cleaned = 0;
	struct vm_area_struct *vma = pvmw->vma;
	struct mmu_notifier_range range;
	unsigned long address = pvmw->address;

	/*
	 * We have to assume the worse case ie pmd for invalidation. Note that
	 * the folio can not be freed from this function.
	 */
	mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE,
				0, vma, vma->vm_mm, address,
				vma_address_end(pvmw));
	mmu_notifier_invalidate_range_start(&range);

	while (page_vma_mapped_walk(pvmw)) {
		int ret = 0;

		address = pvmw->address;
		if (pvmw->pte) {
			pte_t entry;
			pte_t *pte = pvmw->pte;

			if (!pte_dirty(*pte) && !pte_write(*pte))
				continue;

			flush_cache_page(vma, address, pte_pfn(*pte));
			entry = ptep_clear_flush(vma, address, pte);
			entry = pte_wrprotect(entry);
			entry = pte_mkclean(entry);
			set_pte_at(vma->vm_mm, address, pte, entry);
			ret = 1;
		} else {
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
			pmd_t *pmd = pvmw->pmd;
			pmd_t entry;

			if (!pmd_dirty(*pmd) && !pmd_write(*pmd))
				continue;

			flush_cache_range(vma, address,
					  address + HPAGE_PMD_SIZE);
			entry = pmdp_invalidate(vma, address, pmd);
			entry = pmd_wrprotect(entry);
			entry = pmd_mkclean(entry);
			set_pmd_at(vma->vm_mm, address, pmd, entry);
			ret = 1;
#else
			/* unexpected pmd-mapped folio? */
			WARN_ON_ONCE(1);
#endif
		}

		/*
		 * No need to call mmu_notifier_invalidate_range() as we are
		 * downgrading page table protection not changing it to point
		 * to a new page.
		 *
		 * See Documentation/vm/mmu_notifier.rst
		 */
		if (ret)
			cleaned++;
	}

	mmu_notifier_invalidate_range_end(&range);

	return cleaned;
}

static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma,
			     unsigned long address, void *arg)
{
	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_SYNC);
	int *cleaned = arg;

	*cleaned += page_vma_mkclean_one(&pvmw);

	return true;
}

static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg)
{
	if (vma->vm_flags & VM_SHARED)
		return false;

	return true;
}

int folio_mkclean(struct folio *folio)
{
	int cleaned = 0;
	struct address_space *mapping;
	struct rmap_walk_control rwc = {
		.arg = (void *)&cleaned,
		.rmap_one = page_mkclean_one,
		.invalid_vma = invalid_mkclean_vma,
	};

	BUG_ON(!folio_test_locked(folio));

	if (!folio_mapped(folio))
		return 0;

	mapping = folio_mapping(folio);
	if (!mapping)
		return 0;

	rmap_walk(folio, &rwc);

	return cleaned;
}
EXPORT_SYMBOL_GPL(folio_mkclean);

/**
 * pfn_mkclean_range - Cleans the PTEs (including PMDs) mapped with range of
 *                     [@pfn, @pfn + @nr_pages) at the specific offset (@pgoff)
 *                     within the @vma of shared mappings. And since clean PTEs
 *                     should also be readonly, write protects them too.
 * @pfn: start pfn.
 * @nr_pages: number of physically contiguous pages srarting with @pfn.
 * @pgoff: page offset that the @pfn mapped with.
 * @vma: vma that @pfn mapped within.
 *
 * Returns the number of cleaned PTEs (including PMDs).
 */
int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff,
		      struct vm_area_struct *vma)
{
	struct page_vma_mapped_walk pvmw = {
		.pfn		= pfn,
		.nr_pages	= nr_pages,
		.pgoff		= pgoff,
		.vma		= vma,
		.flags		= PVMW_SYNC,
	};

	if (invalid_mkclean_vma(vma, NULL))
		return 0;

	pvmw.address = vma_pgoff_address(pgoff, nr_pages, vma);
	VM_BUG_ON_VMA(pvmw.address == -EFAULT, vma);

	return page_vma_mkclean_one(&pvmw);
}

/**
 * page_move_anon_rmap - move a page to our anon_vma
 * @page:	the page to move to our anon_vma
 * @vma:	the vma the page belongs to
 *
 * When a page belongs exclusively to one process after a COW event,
 * that page can be moved into the anon_vma that belongs to just that
 * process, so the rmap code will not search the parent or sibling
 * processes.
 */
void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma)
{
	struct anon_vma *anon_vma = vma->anon_vma;

	page = compound_head(page);

	VM_BUG_ON_PAGE(!PageLocked(page), page);
	VM_BUG_ON_VMA(!anon_vma, vma);

	anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
	/*
	 * Ensure that anon_vma and the PAGE_MAPPING_ANON bit are written
	 * simultaneously, so a concurrent reader (eg folio_referenced()'s
	 * folio_test_anon()) will not see one without the other.
	 */
	WRITE_ONCE(page->mapping, (struct address_space *) anon_vma);
}

/**
 * __page_set_anon_rmap - set up new anonymous rmap
 * @page:	Page or Hugepage to add to rmap
 * @vma:	VM area to add page to.
 * @address:	User virtual address of the mapping	
 * @exclusive:	the page is exclusively owned by the current process
 */
static void __page_set_anon_rmap(struct page *page,
	struct vm_area_struct *vma, unsigned long address, int exclusive)
{
	struct anon_vma *anon_vma = vma->anon_vma;

	BUG_ON(!anon_vma);

	if (PageAnon(page))
		return;

	/*
	 * If the page isn't exclusively mapped into this vma,
	 * we must use the _oldest_ possible anon_vma for the
	 * page mapping!
	 */
	if (!exclusive)
		anon_vma = anon_vma->root;

	/*
	 * page_idle does a lockless/optimistic rmap scan on page->mapping.
	 * Make sure the compiler doesn't split the stores of anon_vma and
	 * the PAGE_MAPPING_ANON type identifier, otherwise the rmap code
	 * could mistake the mapping for a struct address_space and crash.
	 */
	anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
	WRITE_ONCE(page->mapping, (struct address_space *) anon_vma);
	page->index = linear_page_index(vma, address);
}

/**
 * __page_check_anon_rmap - sanity check anonymous rmap addition
 * @page:	the page to add the mapping to
 * @vma:	the vm area in which the mapping is added
 * @address:	the user virtual address mapped
 */
static void __page_check_anon_rmap(struct page *page,
	struct vm_area_struct *vma, unsigned long address)
{
	struct folio *folio = page_folio(page);
	/*
	 * The page's anon-rmap details (mapping and index) are guaranteed to
	 * be set up correctly at this point.
	 *
	 * We have exclusion against page_add_anon_rmap because the caller
	 * always holds the page locked.
	 *
	 * We have exclusion against page_add_new_anon_rmap because those pages
	 * are initially only visible via the pagetables, and the pte is locked
	 * over the call to page_add_new_anon_rmap.
	 */
	VM_BUG_ON_FOLIO(folio_anon_vma(folio)->root != vma->anon_vma->root,
			folio);
	VM_BUG_ON_PAGE(page_to_pgoff(page) != linear_page_index(vma, address),
		       page);
}

/**
 * page_add_anon_rmap - add pte mapping to an anonymous page
 * @page:	the page to add the mapping to
 * @vma:	the vm area in which the mapping is added
 * @address:	the user virtual address mapped
 * @flags:	the rmap flags
 *
 * The caller needs to hold the pte lock, and the page must be locked in
 * the anon_vma case: to serialize mapping,index checking after setting,
 * and to ensure that PageAnon is not being upgraded racily to PageKsm
 * (but PageKsm is never downgraded to PageAnon).
 */
void page_add_anon_rmap(struct page *page,
	struct vm_area_struct *vma, unsigned long address, rmap_t flags)
{
	bool compound = flags & RMAP_COMPOUND;
	bool first;

	if (unlikely(PageKsm(page)))
		lock_page_memcg(page);
	else
		VM_BUG_ON_PAGE(!PageLocked(page), page);

	if (compound) {
		atomic_t *mapcount;
		VM_BUG_ON_PAGE(!PageLocked(page), page);
		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
		mapcount = compound_mapcount_ptr(page);
		first = atomic_inc_and_test(mapcount);
	} else {
		first = atomic_inc_and_test(&page->_mapcount);
	}

	if (first) {
		int nr = compound ? thp_nr_pages(page) : 1;
		/*
		 * We use the irq-unsafe __{inc|mod}_zone_page_stat because
		 * these counters are not modified in interrupt context, and
		 * pte lock(a spinlock) is held, which implies preemption
		 * disabled.
		 */
		if (compound)
			__mod_lruvec_page_state(page, NR_ANON_THPS, nr);
		__mod_lruvec_page_state(page, NR_ANON_MAPPED, nr);
	}

	if (unlikely(PageKsm(page)))
		unlock_page_memcg(page);

	/* address might be in next vma when migration races vma_adjust */
	else if (first)
		__page_set_anon_rmap(page, vma, address,
				     !!(flags & RMAP_EXCLUSIVE));
	else
		__page_check_anon_rmap(page, vma, address);

	mlock_vma_page(page, vma, compound);
}

/**
 * page_add_new_anon_rmap - add pte mapping to a new anonymous page
 * @page:	the page to add the mapping to
 * @vma:	the vm area in which the mapping is added
 * @address:	the user virtual address mapped
 * @compound:	charge the page as compound or small page
 *
 * Same as page_add_anon_rmap but must only be called on *new* pages.
 * This means the inc-and-test can be bypassed.
 * Page does not have to be locked.
 */
void page_add_new_anon_rmap(struct page *page,
	struct vm_area_struct *vma, unsigned long address, bool compound)
{
	int nr = compound ? thp_nr_pages(page) : 1;

	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
	__SetPageSwapBacked(page);
	if (compound) {
		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
		/* increment count (starts at -1) */
		atomic_set(compound_mapcount_ptr(page), 0);
		atomic_set(compound_pincount_ptr(page), 0);

		__mod_lruvec_page_state(page, NR_ANON_THPS, nr);
	} else {
		/* Anon THP always mapped first with PMD */
		VM_BUG_ON_PAGE(PageTransCompound(page), page);
		/* increment count (starts at -1) */
		atomic_set(&page->_mapcount, 0);
	}
	__mod_lruvec_page_state(page, NR_ANON_MAPPED, nr);
	__page_set_anon_rmap(page, vma, address, 1);
}

/**
 * page_add_file_rmap - add pte mapping to a file page
 * @page:	the page to add the mapping to
 * @vma:	the vm area in which the mapping is added
 * @compound:	charge the page as compound or small page
 *
 * The caller needs to hold the pte lock.
 */
void page_add_file_rmap(struct page *page,
	struct vm_area_struct *vma, bool compound)
{
	int i, nr = 0;

	VM_BUG_ON_PAGE(compound && !PageTransHuge(page), page);
	lock_page_memcg(page);
	if (compound && PageTransHuge(page)) {
		int nr_pages = thp_nr_pages(page);

		for (i = 0; i < nr_pages; i++) {
			if (atomic_inc_and_test(&page[i]._mapcount))
				nr++;
		}
		if (!atomic_inc_and_test(compound_mapcount_ptr(page)))
			goto out;

		/*
		 * It is racy to ClearPageDoubleMap in page_remove_file_rmap();
		 * but page lock is held by all page_add_file_rmap() compound
		 * callers, and SetPageDoubleMap below warns if !PageLocked:
		 * so here is a place that DoubleMap can be safely cleared.
		 */
		VM_WARN_ON_ONCE(!PageLocked(page));
		if (nr == nr_pages && PageDoubleMap(page))
			ClearPageDoubleMap(page);

		if (PageSwapBacked(page))
			__mod_lruvec_page_state(page, NR_SHMEM_PMDMAPPED,
						nr_pages);
		else
			__mod_lruvec_page_state(page, NR_FILE_PMDMAPPED,
						nr_pages);
	} else {
		if (PageTransCompound(page) && page_mapping(page)) {
			VM_WARN_ON_ONCE(!PageLocked(page));
			SetPageDoubleMap(compound_head(page));
		}
		if (atomic_inc_and_test(&page->_mapcount))
			nr++;
	}
out:
	if (nr)
		__mod_lruvec_page_state(page, NR_FILE_MAPPED, nr);
	unlock_page_memcg(page);

	mlock_vma_page(page, vma, compound);
}

static void page_remove_file_rmap(struct page *page, bool compound)
{
	int i, nr = 0;

	VM_BUG_ON_PAGE(compound && !PageHead(page), page);

	/* Hugepages are not counted in NR_FILE_MAPPED for now. */
	if (unlikely(PageHuge(page))) {
		/* hugetlb pages are always mapped with pmds */
		atomic_dec(compound_mapcount_ptr(page));
		return;
	}

	/* page still mapped by someone else? */
	if (compound && PageTransHuge(page)) {
		int nr_pages = thp_nr_pages(page);

		for (i = 0; i < nr_pages; i++) {
			if (atomic_add_negative(-1, &page[i]._mapcount))
				nr++;
		}
		if (!atomic_add_negative(-1, compound_mapcount_ptr(page)))
			goto out;
		if (PageSwapBacked(page))
			__mod_lruvec_page_state(page, NR_SHMEM_PMDMAPPED,
						-nr_pages);
		else
			__mod_lruvec_page_state(page, NR_FILE_PMDMAPPED,
						-nr_pages);
	} else {
		if (atomic_add_negative(-1, &page->_mapcount))
			nr++;
	}
out:
	if (nr)
		__mod_lruvec_page_state(page, NR_FILE_MAPPED, -nr);
}

static void page_remove_anon_compound_rmap(struct page *page)
{
	int i, nr;

	if (!atomic_add_negative(-1, compound_mapcount_ptr(page)))
		return;

	/* Hugepages are not counted in NR_ANON_PAGES for now. */
	if (unlikely(PageHuge(page)))
		return;

	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
		return;

	__mod_lruvec_page_state(page, NR_ANON_THPS, -thp_nr_pages(page));

	if (TestClearPageDoubleMap(page)) {
		/*
		 * Subpages can be mapped with PTEs too. Check how many of
		 * them are still mapped.
		 */
		for (i = 0, nr = 0; i < thp_nr_pages(page); i++) {
			if (atomic_add_negative(-1, &page[i]._mapcount))
				nr++;
		}

		/*
		 * Queue the page for deferred split if at least one small
		 * page of the compound page is unmapped, but at least one
		 * small page is still mapped.
		 */
		if (nr && nr < thp_nr_pages(page))
			deferred_split_huge_page(page);
	} else {
		nr = thp_nr_pages(page);
	}

	if (nr)
		__mod_lruvec_page_state(page, NR_ANON_MAPPED, -nr);
}

/**
 * page_remove_rmap - take down pte mapping from a page
 * @page:	page to remove mapping from
 * @vma:	the vm area from which the mapping is removed
 * @compound:	uncharge the page as compound or small page
 *
 * The caller needs to hold the pte lock.
 */
void page_remove_rmap(struct page *page,
	struct vm_area_struct *vma, bool compound)
{
	lock_page_memcg(page);

	if (!PageAnon(page)) {
		page_remove_file_rmap(page, compound);
		goto out;
	}

	if (compound) {
		page_remove_anon_compound_rmap(page);
		goto out;
	}

	/* page still mapped by someone else? */
	if (!atomic_add_negative(-1, &page->_mapcount))
		goto out;

	/*
	 * We use the irq-unsafe __{inc|mod}_zone_page_stat because
	 * these counters are not modified in interrupt context, and
	 * pte lock(a spinlock) is held, which implies preemption disabled.
	 */
	__dec_lruvec_page_state(page, NR_ANON_MAPPED);

	if (PageTransCompound(page))
		deferred_split_huge_page(compound_head(page));

	/*
	 * It would be tidy to reset the PageAnon mapping here,
	 * but that might overwrite a racing page_add_anon_rmap
	 * which increments mapcount after us but sets mapping
	 * before us: so leave the reset to free_unref_page,
	 * and remember that it's only reliable while mapped.
	 * Leaving it set also helps swapoff to reinstate ptes
	 * faster for those pages still in swapcache.
	 */
out:
	unlock_page_memcg(page);

	munlock_vma_page(page, vma, compound);
}

/*
 * @arg: enum ttu_flags will be passed to this argument
 */
static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
		     unsigned long address, void *arg)
{
	struct mm_struct *mm = vma->vm_mm;
	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0);
	pte_t pteval;
	struct page *subpage;
	bool ret = true;
	struct mmu_notifier_range range;
	enum ttu_flags flags = (enum ttu_flags)(long)arg;

	/*
	 * When racing against e.g. zap_pte_range() on another cpu,
	 * in between its ptep_get_and_clear_full() and page_remove_rmap(),
	 * try_to_unmap() may return before page_mapped() has become false,
	 * if page table locking is skipped: use TTU_SYNC to wait for that.
	 */
	if (flags & TTU_SYNC)
		pvmw.flags = PVMW_SYNC;

	if (flags & TTU_SPLIT_HUGE_PMD)
		split_huge_pmd_address(vma, address, false, folio);

	/*
	 * For THP, we have to assume the worse case ie pmd for invalidation.
	 * For hugetlb, it could be much worse if we need to do pud
	 * invalidation in the case of pmd sharing.
	 *
	 * Note that the folio can not be freed in this function as call of
	 * try_to_unmap() must hold a reference on the folio.
	 */
	range.end = vma_address_end(&pvmw);
	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
				address, range.end);
	if (folio_test_hugetlb(folio)) {
		/*
		 * If sharing is possible, start and end will be adjusted
		 * accordingly.
		 */
		adjust_range_if_pmd_sharing_possible(vma, &range.start,
						     &range.end);
	}
	mmu_notifier_invalidate_range_start(&range);

	while (page_vma_mapped_walk(&pvmw)) {
		/* Unexpected PMD-mapped THP? */
		VM_BUG_ON_FOLIO(!pvmw.pte, folio);

		/*
		 * If the folio is in an mlock()d vma, we must not swap it out.
		 */
		if (!(flags & TTU_IGNORE_MLOCK) &&
		    (vma->vm_flags & VM_LOCKED)) {
			/* Restore the mlock which got missed */
			mlock_vma_folio(folio, vma, false);
			page_vma_mapped_walk_done(&pvmw);
			ret = false;
			break;
		}

		subpage = folio_page(folio,
					pte_pfn(*pvmw.pte) - folio_pfn(folio));
		address = pvmw.address;

		if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) {
			/*
			 * To call huge_pmd_unshare, i_mmap_rwsem must be
			 * held in write mode.  Caller needs to explicitly
			 * do this outside rmap routines.
			 */
			VM_BUG_ON(!(flags & TTU_RMAP_LOCKED));
			if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) {
				/*
				 * huge_pmd_unshare unmapped an entire PMD
				 * page.  There is no way of knowing exactly
				 * which PMDs may be cached for this mm, so
				 * we must flush them all.  start/end were
				 * already adjusted above to cover this range.
				 */
				flush_cache_range(vma, range.start, range.end);
				flush_tlb_range(vma, range.start, range.end);
				mmu_notifier_invalidate_range(mm, range.start,
							      range.end);

				/*
				 * The ref count of the PMD page was dropped
				 * which is part of the way map counting
				 * is done for shared PMDs.  Return 'true'
				 * here.  When there is no other sharing,
				 * huge_pmd_unshare returns false and we will
				 * unmap the actual page and drop map count
				 * to zero.
				 */
				page_vma_mapped_walk_done(&pvmw);
				break;
			}
		}

		/* Nuke the page table entry. */
		flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
		if (should_defer_flush(mm, flags)) {
			/*
			 * We clear the PTE but do not flush so potentially
			 * a remote CPU could still be writing to the folio.
			 * If the entry was previously clean then the
			 * architecture must guarantee that a clear->dirty
			 * transition on a cached TLB entry is written through
			 * and traps if the PTE is unmapped.
			 */
			pteval = ptep_get_and_clear(mm, address, pvmw.pte);

			set_tlb_ubc_flush_pending(mm, pte_dirty(pteval));
		} else {
			pteval = ptep_clear_flush(vma, address, pvmw.pte);
		}

		/* Set the dirty flag on the folio now the pte is gone. */
		if (pte_dirty(pteval))
			folio_mark_dirty(folio);

		/* Update high watermark before we lower rss */
		update_hiwater_rss(mm);

		if (PageHWPoison(subpage) && !(flags & TTU_IGNORE_HWPOISON)) {
			pteval = swp_entry_to_pte(make_hwpoison_entry(subpage));
			if (folio_test_hugetlb(folio)) {
				hugetlb_count_sub(folio_nr_pages(folio), mm);
				set_huge_swap_pte_at(mm, address,
						     pvmw.pte, pteval,
						     vma_mmu_pagesize(vma));
			} else {
				dec_mm_counter(mm, mm_counter(&folio->page));
				set_pte_at(mm, address, pvmw.pte, pteval);
			}

		} else if (pte_unused(pteval) && !userfaultfd_armed(vma)) {
			/*
			 * The guest indicated that the page content is of no
			 * interest anymore. Simply discard the pte, vmscan
			 * will take care of the rest.
			 * A future reference will then fault in a new zero
			 * page. When userfaultfd is active, we must not drop
			 * this page though, as its main user (postcopy
			 * migration) will not expect userfaults on already
			 * copied pages.
			 */
			dec_mm_counter(mm, mm_counter(&folio->page));
			/* We have to invalidate as we cleared the pte */
			mmu_notifier_invalidate_range(mm, address,
						      address + PAGE_SIZE);
		} else if (folio_test_anon(folio)) {
			swp_entry_t entry = { .val = page_private(subpage) };
			pte_t swp_pte;
			/*
			 * Store the swap location in the pte.
			 * See handle_pte_fault() ...
			 */
			if (unlikely(folio_test_swapbacked(folio) !=
					folio_test_swapcache(folio))) {
				WARN_ON_ONCE(1);
				ret = false;
				/* We have to invalidate as we cleared the pte */
				mmu_notifier_invalidate_range(mm, address,
							address + PAGE_SIZE);
				page_vma_mapped_walk_done(&pvmw);
				break;
			}

			/* MADV_FREE page check */
			if (!folio_test_swapbacked(folio)) {
				int ref_count, map_count;

				/*
				 * Synchronize with gup_pte_range():
				 * - clear PTE; barrier; read refcount
				 * - inc refcount; barrier; read PTE
				 */
				smp_mb();

				ref_count = folio_ref_count(folio);
				map_count = folio_mapcount(folio);

				/*
				 * Order reads for page refcount and dirty flag
				 * (see comments in __remove_mapping()).
				 */
				smp_rmb();

				/*
				 * The only page refs must be one from isolation
				 * plus the rmap(s) (dropped by discard:).
				 */
				if (ref_count == 1 + map_count &&
				    !folio_test_dirty(folio)) {
					/* Invalidate as we cleared the pte */
					mmu_notifier_invalidate_range(mm,
						address, address + PAGE_SIZE);
					dec_mm_counter(mm, MM_ANONPAGES);
					goto discard;
				}

				/*
				 * If the folio was redirtied, it cannot be
				 * discarded. Remap the page to page table.
				 */
				set_pte_at(mm, address, pvmw.pte, pteval);
				folio_set_swapbacked(folio);
				ret = false;
				page_vma_mapped_walk_done(&pvmw);
				break;
			}

			if (swap_duplicate(entry) < 0) {
				set_pte_at(mm, address, pvmw.pte, pteval);
				ret = false;
				page_vma_mapped_walk_done(&pvmw);
				break;
			}
			if (arch_unmap_one(mm, vma, address, pteval) < 0) {
				swap_free(entry);
				set_pte_at(mm, address, pvmw.pte, pteval);
				ret = false;
				page_vma_mapped_walk_done(&pvmw);
				break;
			}
			if (list_empty(&mm->mmlist)) {
				spin_lock(&mmlist_lock);
				if (list_empty(&mm->mmlist))
					list_add(&mm->mmlist, &init_mm.mmlist);
				spin_unlock(&mmlist_lock);
			}
			dec_mm_counter(mm, MM_ANONPAGES);
			inc_mm_counter(mm, MM_SWAPENTS);
			swp_pte = swp_entry_to_pte(entry);
			if (pte_soft_dirty(pteval))
				swp_pte = pte_swp_mksoft_dirty(swp_pte);
			if (pte_uffd_wp(pteval))
				swp_pte = pte_swp_mkuffd_wp(swp_pte);
			set_pte_at(mm, address, pvmw.pte, swp_pte);
			/* Invalidate as we cleared the pte */
			mmu_notifier_invalidate_range(mm, address,
						      address + PAGE_SIZE);
		} else {
			/*
			 * This is a locked file-backed folio,
			 * so it cannot be removed from the page
			 * cache and replaced by a new folio before
			 * mmu_notifier_invalidate_range_end, so no
			 * concurrent thread might update its page table
			 * to point at a new folio while a device is
			 * still using this folio.
			 *
			 * See Documentation/vm/mmu_notifier.rst
			 */
			dec_mm_counter(mm, mm_counter_file(&folio->page));
		}
discard:
		/*
		 * No need to call mmu_notifier_invalidate_range() it has be
		 * done above for all cases requiring it to happen under page
		 * table lock before mmu_notifier_invalidate_range_end()
		 *
		 * See Documentation/vm/mmu_notifier.rst
		 */
		page_remove_rmap(subpage, vma, folio_test_hugetlb(folio));
		if (vma->vm_flags & VM_LOCKED)
			mlock_page_drain_local();
		folio_put(folio);
	}

	mmu_notifier_invalidate_range_end(&range);

	return ret;
}

static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg)
{
	return vma_is_temporary_stack(vma);
}

static int page_not_mapped(struct folio *folio)
{
	return !folio_mapped(folio);
}

/**
 * try_to_unmap - Try to remove all page table mappings to a folio.
 * @folio: The folio to unmap.
 * @flags: action and flags
 *
 * Tries to remove all the page table entries which are mapping this
 * folio.  It is the caller's responsibility to check if the folio is
 * still mapped if needed (use TTU_SYNC to prevent accounting races).
 *
 * Context: Caller must hold the folio lock.
 */
void try_to_unmap(struct folio *folio, enum ttu_flags flags)
{
	struct rmap_walk_control rwc = {
		.rmap_one = try_to_unmap_one,
		.arg = (void *)flags,
		.done = page_not_mapped,
		.anon_lock = folio_lock_anon_vma_read,
	};

	if (flags & TTU_RMAP_LOCKED)
		rmap_walk_locked(folio, &rwc);
	else
		rmap_walk(folio, &rwc);
}

/*
 * @arg: enum ttu_flags will be passed to this argument.
 *
 * If TTU_SPLIT_HUGE_PMD is specified any PMD mappings will be split into PTEs
 * containing migration entries.
 */
static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
		     unsigned long address, void *arg)
{
	struct mm_struct *mm = vma->vm_mm;
	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0);
	pte_t pteval;
	struct page *subpage;
	bool ret = true;
	struct mmu_notifier_range range;
	enum ttu_flags flags = (enum ttu_flags)(long)arg;

	/*
	 * When racing against e.g. zap_pte_range() on another cpu,
	 * in between its ptep_get_and_clear_full() and page_remove_rmap(),
	 * try_to_migrate() may return before page_mapped() has become false,
	 * if page table locking is skipped: use TTU_SYNC to wait for that.
	 */
	if (flags & TTU_SYNC)
		pvmw.flags = PVMW_SYNC;

	/*
	 * unmap_page() in mm/huge_memory.c is the only user of migration with
	 * TTU_SPLIT_HUGE_PMD and it wants to freeze.
	 */
	if (flags & TTU_SPLIT_HUGE_PMD)
		split_huge_pmd_address(vma, address, true, folio);

	/*
	 * For THP, we have to assume the worse case ie pmd for invalidation.
	 * For hugetlb, it could be much worse if we need to do pud
	 * invalidation in the case of pmd sharing.
	 *
	 * Note that the page can not be free in this function as call of
	 * try_to_unmap() must hold a reference on the page.
	 */
	range.end = vma_address_end(&pvmw);
	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
				address, range.end);
	if (folio_test_hugetlb(folio)) {
		/*
		 * If sharing is possible, start and end will be adjusted
		 * accordingly.
		 */
		adjust_range_if_pmd_sharing_possible(vma, &range.start,
						     &range.end);
	}
	mmu_notifier_invalidate_range_start(&range);

	while (page_vma_mapped_walk(&pvmw)) {
#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
		/* PMD-mapped THP migration entry */
		if (!pvmw.pte) {
			subpage = folio_page(folio,
				pmd_pfn(*pvmw.pmd) - folio_pfn(folio));
			VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) ||
					!folio_test_pmd_mappable(folio), folio);

			set_pmd_migration_entry(&pvmw, subpage);
			continue;
		}
#endif

		/* Unexpected PMD-mapped THP? */
		VM_BUG_ON_FOLIO(!pvmw.pte, folio);

		subpage = folio_page(folio,
				pte_pfn(*pvmw.pte) - folio_pfn(folio));
		address = pvmw.address;

		if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) {
			/*
			 * To call huge_pmd_unshare, i_mmap_rwsem must be
			 * held in write mode.  Caller needs to explicitly
			 * do this outside rmap routines.
			 */
			VM_BUG_ON(!(flags & TTU_RMAP_LOCKED));
			if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) {
				/*
				 * huge_pmd_unshare unmapped an entire PMD
				 * page.  There is no way of knowing exactly
				 * which PMDs may be cached for this mm, so
				 * we must flush them all.  start/end were
				 * already adjusted above to cover this range.
				 */
				flush_cache_range(vma, range.start, range.end);
				flush_tlb_range(vma, range.start, range.end);
				mmu_notifier_invalidate_range(mm, range.start,
							      range.end);

				/*
				 * The ref count of the PMD page was dropped
				 * which is part of the way map counting
				 * is done for shared PMDs.  Return 'true'
				 * here.  When there is no other sharing,
				 * huge_pmd_unshare returns false and we will
				 * unmap the actual page and drop map count
				 * to zero.
				 */
				page_vma_mapped_walk_done(&pvmw);
				break;
			}
		}

		/* Nuke the page table entry. */
		flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
		pteval = ptep_clear_flush(vma, address, pvmw.pte);

		/* Set the dirty flag on the folio now the pte is gone. */
		if (pte_dirty(pteval))
			folio_mark_dirty(folio);

		/* Update high watermark before we lower rss */
		update_hiwater_rss(mm);

		if (folio_is_zone_device(folio)) {
			unsigned long pfn = folio_pfn(folio);
			swp_entry_t entry;
			pte_t swp_pte;

			/*
			 * Store the pfn of the page in a special migration
			 * pte. do_swap_page() will wait until the migration
			 * pte is removed and then restart fault handling.
			 */
			entry = pte_to_swp_entry(pteval);
			if (is_writable_device_private_entry(entry))
				entry = make_writable_migration_entry(pfn);
			else
				entry = make_readable_migration_entry(pfn);
			swp_pte = swp_entry_to_pte(entry);

			/*
			 * pteval maps a zone device page and is therefore
			 * a swap pte.
			 */
			if (pte_swp_soft_dirty(pteval))
				swp_pte = pte_swp_mksoft_dirty(swp_pte);
			if (pte_swp_uffd_wp(pteval))
				swp_pte = pte_swp_mkuffd_wp(swp_pte);
			set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte);
			trace_set_migration_pte(pvmw.address, pte_val(swp_pte),
						compound_order(&folio->page));
			/*
			 * No need to invalidate here it will synchronize on
			 * against the special swap migration pte.
			 *
			 * The assignment to subpage above was computed from a
			 * swap PTE which results in an invalid pointer.
			 * Since only PAGE_SIZE pages can currently be
			 * migrated, just set it to page. This will need to be
			 * changed when hugepage migrations to device private
			 * memory are supported.
			 */
			subpage = &folio->page;
		} else if (PageHWPoison(subpage)) {
			pteval = swp_entry_to_pte(make_hwpoison_entry(subpage));
			if (folio_test_hugetlb(folio)) {
				hugetlb_count_sub(folio_nr_pages(folio), mm);
				set_huge_swap_pte_at(mm, address,
						     pvmw.pte, pteval,
						     vma_mmu_pagesize(vma));
			} else {
				dec_mm_counter(mm, mm_counter(&folio->page));
				set_pte_at(mm, address, pvmw.pte, pteval);
			}

		} else if (pte_unused(pteval) && !userfaultfd_armed(vma)) {
			/*
			 * The guest indicated that the page content is of no
			 * interest anymore. Simply discard the pte, vmscan
			 * will take care of the rest.
			 * A future reference will then fault in a new zero
			 * page. When userfaultfd is active, we must not drop
			 * this page though, as its main user (postcopy
			 * migration) will not expect userfaults on already
			 * copied pages.
			 */
			dec_mm_counter(mm, mm_counter(&folio->page));
			/* We have to invalidate as we cleared the pte */
			mmu_notifier_invalidate_range(mm, address,
						      address + PAGE_SIZE);
		} else {
			swp_entry_t entry;
			pte_t swp_pte;

			if (arch_unmap_one(mm, vma, address, pteval) < 0) {
				set_pte_at(mm, address, pvmw.pte, pteval);
				ret = false;
				page_vma_mapped_walk_done(&pvmw);
				break;
			}

			/*
			 * Store the pfn of the page in a special migration
			 * pte. do_swap_page() will wait until the migration
			 * pte is removed and then restart fault handling.
			 */
			if (pte_write(pteval))
				entry = make_writable_migration_entry(
							page_to_pfn(subpage));
			else
				entry = make_readable_migration_entry(
							page_to_pfn(subpage));

			swp_pte = swp_entry_to_pte(entry);
			if (pte_soft_dirty(pteval))
				swp_pte = pte_swp_mksoft_dirty(swp_pte);
			if (pte_uffd_wp(pteval))
				swp_pte = pte_swp_mkuffd_wp(swp_pte);
			set_pte_at(mm, address, pvmw.pte, swp_pte);
			trace_set_migration_pte(address, pte_val(swp_pte),
						compound_order(&folio->page));
			/*
			 * No need to invalidate here it will synchronize on
			 * against the special swap migration pte.
			 */
		}

		/*
		 * No need to call mmu_notifier_invalidate_range() it has be
		 * done above for all cases requiring it to happen under page
		 * table lock before mmu_notifier_invalidate_range_end()
		 *
		 * See Documentation/vm/mmu_notifier.rst
		 */
		page_remove_rmap(subpage, vma, folio_test_hugetlb(folio));
		if (vma->vm_flags & VM_LOCKED)
			mlock_page_drain_local();
		folio_put(folio);
	}

	mmu_notifier_invalidate_range_end(&range);

	return ret;
}

/**
 * try_to_migrate - try to replace all page table mappings with swap entries
 * @folio: the folio to replace page table entries for
 * @flags: action and flags
 *
 * Tries to remove all the page table entries which are mapping this folio and
 * replace them with special swap entries. Caller must hold the folio lock.
 */
void try_to_migrate(struct folio *folio, enum ttu_flags flags)
{
	struct rmap_walk_control rwc = {
		.rmap_one = try_to_migrate_one,
		.arg = (void *)flags,
		.done = page_not_mapped,
		.anon_lock = folio_lock_anon_vma_read,
	};

	/*
	 * Migration always ignores mlock and only supports TTU_RMAP_LOCKED and
	 * TTU_SPLIT_HUGE_PMD and TTU_SYNC flags.
	 */
	if (WARN_ON_ONCE(flags & ~(TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD |
					TTU_SYNC)))
		return;

	if (folio_is_zone_device(folio) && !folio_is_device_private(folio))
		return;

	/*
	 * During exec, a temporary VMA is setup and later moved.
	 * The VMA is moved under the anon_vma lock but not the
	 * page tables leading to a race where migration cannot
	 * find the migration ptes. Rather than increasing the
	 * locking requirements of exec(), migration skips
	 * temporary VMAs until after exec() completes.
	 */
	if (!folio_test_ksm(folio) && folio_test_anon(folio))
		rwc.invalid_vma = invalid_migration_vma;

	if (flags & TTU_RMAP_LOCKED)
		rmap_walk_locked(folio, &rwc);
	else
		rmap_walk(folio, &rwc);
}

#ifdef CONFIG_DEVICE_PRIVATE
struct make_exclusive_args {
	struct mm_struct *mm;
	unsigned long address;
	void *owner;
	bool valid;
};

static bool page_make_device_exclusive_one(struct folio *folio,
		struct vm_area_struct *vma, unsigned long address, void *priv)
{
	struct mm_struct *mm = vma->vm_mm;
	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0);
	struct make_exclusive_args *args = priv;
	pte_t pteval;
	struct page *subpage;
	bool ret = true;
	struct mmu_notifier_range range;
	swp_entry_t entry;
	pte_t swp_pte;

	mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma,
				      vma->vm_mm, address, min(vma->vm_end,
				      address + folio_size(folio)),
				      args->owner);
	mmu_notifier_invalidate_range_start(&range);

	while (page_vma_mapped_walk(&pvmw)) {
		/* Unexpected PMD-mapped THP? */
		VM_BUG_ON_FOLIO(!pvmw.pte, folio);

		if (!pte_present(*pvmw.pte)) {
			ret = false;
			page_vma_mapped_walk_done(&pvmw);
			break;
		}

		subpage = folio_page(folio,
				pte_pfn(*pvmw.pte) - folio_pfn(folio));
		address = pvmw.address;

		/* Nuke the page table entry. */
		flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
		pteval = ptep_clear_flush(vma, address, pvmw.pte);

		/* Set the dirty flag on the folio now the pte is gone. */
		if (pte_dirty(pteval))
			folio_mark_dirty(folio);

		/*
		 * Check that our target page is still mapped at the expected
		 * address.
		 */
		if (args->mm == mm && args->address == address &&
		    pte_write(pteval))
			args->valid = true;

		/*
		 * Store the pfn of the page in a special migration
		 * pte. do_swap_page() will wait until the migration
		 * pte is removed and then restart fault handling.
		 */
		if (pte_write(pteval))
			entry = make_writable_device_exclusive_entry(
							page_to_pfn(subpage));
		else
			entry = make_readable_device_exclusive_entry(
							page_to_pfn(subpage));
		swp_pte = swp_entry_to_pte(entry);
		if (pte_soft_dirty(pteval))
			swp_pte = pte_swp_mksoft_dirty(swp_pte);
		if (pte_uffd_wp(pteval))
			swp_pte = pte_swp_mkuffd_wp(swp_pte);

		set_pte_at(mm, address, pvmw.pte, swp_pte);

		/*
		 * There is a reference on the page for the swap entry which has
		 * been removed, so shouldn't take another.
		 */
		page_remove_rmap(subpage, vma, false);
	}

	mmu_notifier_invalidate_range_end(&range);

	return ret;
}

/**
 * folio_make_device_exclusive - Mark the folio exclusively owned by a device.
 * @folio: The folio to replace page table entries for.
 * @mm: The mm_struct where the folio is expected to be mapped.
 * @address: Address where the folio is expected to be mapped.
 * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier callbacks
 *
 * Tries to remove all the page table entries which are mapping this
 * folio and replace them with special device exclusive swap entries to
 * grant a device exclusive access to the folio.
 *
 * Context: Caller must hold the folio lock.
 * Return: false if the page is still mapped, or if it could not be unmapped
 * from the expected address. Otherwise returns true (success).
 */
static bool folio_make_device_exclusive(struct folio *folio,
		struct mm_struct *mm, unsigned long address, void *owner)
{
	struct make_exclusive_args args = {
		.mm = mm,
		.address = address,
		.owner = owner,
		.valid = false,
	};
	struct rmap_walk_control rwc = {
		.rmap_one = page_make_device_exclusive_one,
		.done = page_not_mapped,
		.anon_lock = folio_lock_anon_vma_read,
		.arg = &args,
	};

	/*
	 * Restrict to anonymous folios for now to avoid potential writeback
	 * issues.
	 */
	if (!folio_test_anon(folio))
		return false;

	rmap_walk(folio, &rwc);

	return args.valid && !folio_mapcount(folio);
}

/**
 * make_device_exclusive_range() - Mark a range for exclusive use by a device
 * @mm: mm_struct of assoicated target process
 * @start: start of the region to mark for exclusive device access
 * @end: end address of region
 * @pages: returns the pages which were successfully marked for exclusive access
 * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier to allow filtering
 *
 * Returns: number of pages found in the range by GUP. A page is marked for
 * exclusive access only if the page pointer is non-NULL.
 *
 * This function finds ptes mapping page(s) to the given address range, locks
 * them and replaces mappings with special swap entries preventing userspace CPU
 * access. On fault these entries are replaced with the original mapping after
 * calling MMU notifiers.
 *
 * A driver using this to program access from a device must use a mmu notifier
 * critical section to hold a device specific lock during programming. Once
 * programming is complete it should drop the page lock and reference after
 * which point CPU access to the page will revoke the exclusive access.
 */
int make_device_exclusive_range(struct mm_struct *mm, unsigned long start,
				unsigned long end, struct page **pages,
				void *owner)
{
	long npages = (end - start) >> PAGE_SHIFT;
	long i;

	npages = get_user_pages_remote(mm, start, npages,
				       FOLL_GET | FOLL_WRITE | FOLL_SPLIT_PMD,
				       pages, NULL, NULL);
	if (npages < 0)
		return npages;

	for (i = 0; i < npages; i++, start += PAGE_SIZE) {
		struct folio *folio = page_folio(pages[i]);
		if (PageTail(pages[i]) || !folio_trylock(folio)) {
			folio_put(folio);
			pages[i] = NULL;
			continue;
		}

		if (!folio_make_device_exclusive(folio, mm, start, owner)) {
			folio_unlock(folio);
			folio_put(folio);
			pages[i] = NULL;
		}
	}

	return npages;
}
EXPORT_SYMBOL_GPL(make_device_exclusive_range);
#endif

void __put_anon_vma(struct anon_vma *anon_vma)
{
	struct anon_vma *root = anon_vma->root;

	anon_vma_free(anon_vma);
	if (root != anon_vma && atomic_dec_and_test(&root->refcount))
		anon_vma_free(root);
}

static struct anon_vma *rmap_walk_anon_lock(struct folio *folio,
					const struct rmap_walk_control *rwc)
{
	struct anon_vma *anon_vma;

	if (rwc->anon_lock)
		return rwc->anon_lock(folio);

	/*
	 * Note: remove_migration_ptes() cannot use folio_lock_anon_vma_read()
	 * because that depends on page_mapped(); but not all its usages
	 * are holding mmap_lock. Users without mmap_lock are required to
	 * take a reference count to prevent the anon_vma disappearing
	 */
	anon_vma = folio_anon_vma(folio);
	if (!anon_vma)
		return NULL;

	anon_vma_lock_read(anon_vma);
	return anon_vma;
}

/*
 * rmap_walk_anon - do something to anonymous page using the object-based
 * rmap method
 * @page: the page to be handled
 * @rwc: control variable according to each walk type
 *
 * Find all the mappings of a page using the mapping pointer and the vma chains
 * contained in the anon_vma struct it points to.
 */
static void rmap_walk_anon(struct folio *folio,
		const struct rmap_walk_control *rwc, bool locked)
{
	struct anon_vma *anon_vma;
	pgoff_t pgoff_start, pgoff_end;
	struct anon_vma_chain *avc;

	if (locked) {
		anon_vma = folio_anon_vma(folio);
		/* anon_vma disappear under us? */
		VM_BUG_ON_FOLIO(!anon_vma, folio);
	} else {
		anon_vma = rmap_walk_anon_lock(folio, rwc);
	}
	if (!anon_vma)
		return;

	pgoff_start = folio_pgoff(folio);
	pgoff_end = pgoff_start + folio_nr_pages(folio) - 1;
	anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root,
			pgoff_start, pgoff_end) {
		struct vm_area_struct *vma = avc->vma;
		unsigned long address = vma_address(&folio->page, vma);

		VM_BUG_ON_VMA(address == -EFAULT, vma);
		cond_resched();

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

		if (!rwc->rmap_one(folio, vma, address, rwc->arg))
			break;
		if (rwc->done && rwc->done(folio))
			break;
	}

	if (!locked)
		anon_vma_unlock_read(anon_vma);
}

/*
 * rmap_walk_file - do something to file page using the object-based rmap method
 * @page: the page to be handled
 * @rwc: control variable according to each walk type
 *
 * Find all the mappings of a page using the mapping pointer and the vma chains
 * contained in the address_space struct it points to.
 */
static void rmap_walk_file(struct folio *folio,
		const struct rmap_walk_control *rwc, bool locked)
{
	struct address_space *mapping = folio_mapping(folio);
	pgoff_t pgoff_start, pgoff_end;
	struct vm_area_struct *vma;

	/*
	 * The page lock not only makes sure that page->mapping cannot
	 * suddenly be NULLified by truncation, it makes sure that the
	 * structure at mapping cannot be freed and reused yet,
	 * so we can safely take mapping->i_mmap_rwsem.
	 */
	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);

	if (!mapping)
		return;

	pgoff_start = folio_pgoff(folio);
	pgoff_end = pgoff_start + folio_nr_pages(folio) - 1;
	if (!locked)
		i_mmap_lock_read(mapping);
	vma_interval_tree_foreach(vma, &mapping->i_mmap,
			pgoff_start, pgoff_end) {
		unsigned long address = vma_address(&folio->page, vma);

		VM_BUG_ON_VMA(address == -EFAULT, vma);
		cond_resched();

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

		if (!rwc->rmap_one(folio, vma, address, rwc->arg))
			goto done;
		if (rwc->done && rwc->done(folio))
			goto done;
	}

done:
	if (!locked)
		i_mmap_unlock_read(mapping);
}

void rmap_walk(struct folio *folio, const struct rmap_walk_control *rwc)
{
	if (unlikely(folio_test_ksm(folio)))
		rmap_walk_ksm(folio, rwc);
	else if (folio_test_anon(folio))
		rmap_walk_anon(folio, rwc, false);
	else
		rmap_walk_file(folio, rwc, false);
}

/* Like rmap_walk, but caller holds relevant rmap lock */
void rmap_walk_locked(struct folio *folio, const struct rmap_walk_control *rwc)
{
	/* no ksm support for now */
	VM_BUG_ON_FOLIO(folio_test_ksm(folio), folio);
	if (folio_test_anon(folio))
		rmap_walk_anon(folio, rwc, true);
	else
		rmap_walk_file(folio, rwc, true);
}

#ifdef CONFIG_HUGETLB_PAGE
/*
 * The following two functions are for anonymous (private mapped) hugepages.
 * Unlike common anonymous pages, anonymous hugepages have no accounting code
 * and no lru code, because we handle hugepages differently from common pages.
 */
void hugepage_add_anon_rmap(struct page *page,
			    struct vm_area_struct *vma, unsigned long address)
{
	struct anon_vma *anon_vma = vma->anon_vma;
	int first;

	BUG_ON(!PageLocked(page));
	BUG_ON(!anon_vma);
	/* address might be in next vma when migration races vma_adjust */
	first = atomic_inc_and_test(compound_mapcount_ptr(page));
	if (first)
		__page_set_anon_rmap(page, vma, address, 0);
}

void hugepage_add_new_anon_rmap(struct page *page,
			struct vm_area_struct *vma, unsigned long address)
{
	BUG_ON(address < vma->vm_start || address >= vma->vm_end);
	atomic_set(compound_mapcount_ptr(page), 0);
	atomic_set(compound_pincount_ptr(page), 0);

	__page_set_anon_rmap(page, vma, address, 1);
}
#endif /* CONFIG_HUGETLB_PAGE */