summaryrefslogtreecommitdiffstats
path: root/mm/rmap.c
blob: a2e5ce1fa08142f60a0abba7ea6512fe6713555c (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
/*
 * 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_mutex	(while writing or truncating, not reading or faulting)
 *   mm->mmap_sem
 *     page->flags PG_locked (lock_page)
 *       mapping->i_mmap_mutex
 *         anon_vma->mutex
 *           mm->page_table_lock or pte_lock
 *             zone->lru_lock (in mark_page_accessed, isolate_lru_page)
 *             swap_lock (in swap_duplicate, swap_info_get)
 *               mmlist_lock (in mmput, drain_mmlist and others)
 *               mapping->private_lock (in __set_page_dirty_buffers)
 *               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)
 *                 mapping->tree_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->mutex,mapping->i_mutex      (memory_failure, collect_procs_anon)
 *   ->tasklist_lock
 *     pte map lock
 */

#include <linux/mm.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 <asm/tlbflush.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);
		/*
		 * 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 page_lock_anon_vma() 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
	 * mutex_trylock() from page_lock_anon_vma(). This orders:
	 *
	 * page_lock_anon_vma()		VS	put_anon_vma()
	 *   mutex_trylock()			  atomic_dec_and_test()
	 *   LOCK				  MB
	 *   atomic_read()			  mutex_is_locked()
	 *
	 * LOCK should suffice since the actual taking of the lock must
	 * happen _before_ what follows.
	 */
	if (mutex_is_locked(&anon_vma->root->mutex)) {
		anon_vma_lock(anon_vma);
		anon_vma_unlock(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);
}

/**
 * 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, 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 page_lock_anon_vma()
 * and that may actually touch the spinlock 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_sem held for reading.
 */
int anon_vma_prepare(struct vm_area_struct *vma)
{
	struct anon_vma *anon_vma = vma->anon_vma;
	struct anon_vma_chain *avc;

	might_sleep();
	if (unlikely(!anon_vma)) {
		struct mm_struct *mm = vma->vm_mm;
		struct anon_vma *allocated;

		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(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;
			avc->anon_vma = anon_vma;
			avc->vma = vma;
			list_add(&avc->same_vma, &vma->anon_vma_chain);
			list_add_tail(&avc->same_anon_vma, &anon_vma->head);
			allocated = NULL;
			avc = NULL;
		}
		spin_unlock(&mm->page_table_lock);
		anon_vma_unlock(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))
			mutex_unlock(&root->mutex);
		root = new_root;
		mutex_lock(&root->mutex);
	}
	return root;
}

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

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);

	/*
	 * It's critical to add new vmas to the tail of the anon_vma,
	 * see comment in huge_memory.c:__split_huge_page().
	 */
	list_add_tail(&avc->same_anon_vma, &anon_vma->head);
}

/*
 * Attach the anon_vmas from src to dst.
 * Returns 0 on success, -ENOMEM on failure.
 */
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);
	}
	unlock_anon_vma_root(root);
	return 0;

 enomem_failure:
	unlink_anon_vmas(dst);
	return -ENOMEM;
}

/*
 * Some rmap walk that needs to find all ptes/hugepmds without false
 * negatives (like migrate and split_huge_page) running concurrent
 * with operations that copy or move pagetables (like mremap() and
 * fork()) to be safe. They depend on the anon_vma "same_anon_vma"
 * list to be in a certain order: the dst_vma must be placed after the
 * src_vma in the list. This is always guaranteed by fork() but
 * mremap() needs to call this function to enforce it in case the
 * dst_vma isn't newly allocated and chained with the anon_vma_clone()
 * function but just an extension of a pre-existing vma through
 * vma_merge.
 *
 * NOTE: the same_anon_vma list can still be changed by other
 * processes while mremap runs because mremap doesn't hold the
 * anon_vma mutex to prevent modifications to the list while it
 * runs. All we need to enforce is that the relative order of this
 * process vmas isn't changing (we don't care about other vmas
 * order). Each vma corresponds to an anon_vma_chain structure so
 * there's no risk that other processes calling anon_vma_moveto_tail()
 * and changing the same_anon_vma list under mremap() will screw with
 * the relative order of this process vmas in the list, because we
 * they can't alter the order of any vma that belongs to this
 * process. And there can't be another anon_vma_moveto_tail() running
 * concurrently with mremap() coming from this process because we hold
 * the mmap_sem for the whole mremap(). fork() ordering dependency
 * also shouldn't be affected because fork() only cares that the
 * parent vmas are placed in the list before the child vmas and
 * anon_vma_moveto_tail() won't reorder vmas from either the fork()
 * parent or child.
 */
void anon_vma_moveto_tail(struct vm_area_struct *dst)
{
	struct anon_vma_chain *pavc;
	struct anon_vma *root = NULL;

	list_for_each_entry_reverse(pavc, &dst->anon_vma_chain, same_vma) {
		struct anon_vma *anon_vma = pavc->anon_vma;
		VM_BUG_ON(pavc->vma != dst);
		root = lock_anon_vma_root(root, anon_vma);
		list_del(&pavc->same_anon_vma);
		list_add_tail(&pavc->same_anon_vma, &anon_vma->head);
	}
	unlock_anon_vma_root(root);
}

/*
 * 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;

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

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

	/* 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 spinlock 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;
	/*
	 * 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(anon_vma);
	anon_vma_chain_link(vma, avc, anon_vma);
	anon_vma_unlock(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);
		list_del(&avc->same_anon_vma);

		/*
		 * Leave empty anon_vmas on the list - we'll need
		 * to free them outside the lock.
		 */
		if (list_empty(&anon_vma->head))
			continue;

		list_del(&avc->same_vma);
		anon_vma_chain_free(avc);
	}
	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 acquire the anon_vma->root->mutex.
	 */
	list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
		struct anon_vma *anon_vma = avc->anon_vma;

		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;

	mutex_init(&anon_vma->mutex);
	atomic_set(&anon_vma->refcount, 0);
	INIT_LIST_HEAD(&anon_vma->head);
}

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

/*
 * 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 locked 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 DESTROY_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) ACCESS_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_DESTROY_BY_RCU guarantees that - so the atomic_inc_not_zero()
	 * above cannot corrupt).
	 */
	if (!page_mapped(page)) {
		put_anon_vma(anon_vma);
		anon_vma = 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 *page_lock_anon_vma(struct page *page)
{
	struct anon_vma *anon_vma = NULL;
	struct anon_vma *root_anon_vma;
	unsigned long anon_mapping;

	rcu_read_lock();
	anon_mapping = (unsigned long) ACCESS_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);
	root_anon_vma = ACCESS_ONCE(anon_vma->root);
	if (mutex_trylock(&root_anon_vma->mutex)) {
		/*
		 * If the page 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 (!page_mapped(page)) {
			mutex_unlock(&root_anon_vma->mutex);
			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 (!page_mapped(page)) {
		put_anon_vma(anon_vma);
		anon_vma = NULL;
		goto out;
	}

	/* we pinned the anon_vma, its safe to sleep */
	rcu_read_unlock();
	anon_vma_lock(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() recursion.
		 */
		anon_vma_unlock(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(struct anon_vma *anon_vma)
{
	anon_vma_unlock(anon_vma);
}

/*
 * At what user virtual address is page expected in @vma?
 * Returns virtual address or -EFAULT if page's index/offset is not
 * within the range mapped the @vma.
 */
inline unsigned long
vma_address(struct page *page, struct vm_area_struct *vma)
{
	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
	unsigned long address;

	if (unlikely(is_vm_hugetlb_page(vma)))
		pgoff = page->index << huge_page_order(page_hstate(page));
	address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
	if (unlikely(address < vma->vm_start || address >= vma->vm_end)) {
		/* page should be within @vma mapping range */
		return -EFAULT;
	}
	return address;
}

/*
 * 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)
{
	if (PageAnon(page)) {
		struct anon_vma *page__anon_vma = page_anon_vma(page);
		/*
		 * 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 (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) {
		if (!vma->vm_file ||
		    vma->vm_file->f_mapping != page->mapping)
			return -EFAULT;
	} else
		return -EFAULT;
	return vma_address(page, vma);
}

/*
 * Check that @page is mapped at @address into @mm.
 *
 * If @sync is false, page_check_address may perform a racy check to avoid
 * the page table lock when the pte is not present (helpful when reclaiming
 * highly shared pages).
 *
 * On success returns with pte mapped and locked.
 */
pte_t *__page_check_address(struct page *page, struct mm_struct *mm,
			  unsigned long address, spinlock_t **ptlp, int sync)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;
	spinlock_t *ptl;

	if (unlikely(PageHuge(page))) {
		pte = huge_pte_offset(mm, address);
		ptl = &mm->page_table_lock;
		goto check;
	}

	pgd = pgd_offset(mm, address);
	if (!pgd_present(*pgd))
		return NULL;

	pud = pud_offset(pgd, address);
	if (!pud_present(*pud))
		return NULL;

	pmd = pmd_offset(pud, address);
	if (!pmd_present(*pmd))
		return NULL;
	if (pmd_trans_huge(*pmd))
		return NULL;

	pte = pte_offset_map(pmd, address);
	/* Make a quick check before getting the lock */
	if (!sync && !pte_present(*pte)) {
		pte_unmap(pte);
		return NULL;
	}

	ptl = pte_lockptr(mm, pmd);
check:
	spin_lock(ptl);
	if (pte_present(*pte) && page_to_pfn(page) == pte_pfn(*pte)) {
		*ptlp = ptl;
		return pte;
	}
	pte_unmap_unlock(pte, ptl);
	return NULL;
}

/**
 * page_mapped_in_vma - check whether a page is really mapped in a VMA
 * @page: the page to test
 * @vma: the VMA to test
 *
 * Returns 1 if the page is mapped into the page tables of the VMA, 0
 * if the page is not mapped into the page tables of this VMA.  Only
 * valid for normal file or anonymous VMAs.
 */
int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
{
	unsigned long address;
	pte_t *pte;
	spinlock_t *ptl;

	address = vma_address(page, vma);
	if (address == -EFAULT)		/* out of vma range */
		return 0;
	pte = page_check_address(page, vma->vm_mm, address, &ptl, 1);
	if (!pte)			/* the page is not in this mm */
		return 0;
	pte_unmap_unlock(pte, ptl);

	return 1;
}

/*
 * Subfunctions of page_referenced: page_referenced_one called
 * repeatedly from either page_referenced_anon or page_referenced_file.
 */
int page_referenced_one(struct page *page, struct vm_area_struct *vma,
			unsigned long address, unsigned int *mapcount,
			unsigned long *vm_flags)
{
	struct mm_struct *mm = vma->vm_mm;
	int referenced = 0;

	if (unlikely(PageTransHuge(page))) {
		pmd_t *pmd;

		spin_lock(&mm->page_table_lock);
		/*
		 * rmap might return false positives; we must filter
		 * these out using page_check_address_pmd().
		 */
		pmd = page_check_address_pmd(page, mm, address,
					     PAGE_CHECK_ADDRESS_PMD_FLAG);
		if (!pmd) {
			spin_unlock(&mm->page_table_lock);
			goto out;
		}

		if (vma->vm_flags & VM_LOCKED) {
			spin_unlock(&mm->page_table_lock);
			*mapcount = 0;	/* break early from loop */
			*vm_flags |= VM_LOCKED;
			goto out;
		}

		/* go ahead even if the pmd is pmd_trans_splitting() */
		if (pmdp_clear_flush_young_notify(vma, address, pmd))
			referenced++;
		spin_unlock(&mm->page_table_lock);
	} else {
		pte_t *pte;
		spinlock_t *ptl;

		/*
		 * rmap might return false positives; we must filter
		 * these out using page_check_address().
		 */
		pte = page_check_address(page, mm, address, &ptl, 0);
		if (!pte)
			goto out;

		if (vma->vm_flags & VM_LOCKED) {
			pte_unmap_unlock(pte, ptl);
			*mapcount = 0;	/* break early from loop */
			*vm_flags |= VM_LOCKED;
			goto out;
		}

		if (ptep_clear_flush_young_notify(vma, address, pte)) {
			/*
			 * Don't treat a reference through a sequentially read
			 * mapping as such.  If the page has been used in
			 * another mapping, we will catch it; if this other
			 * mapping is already gone, the unmap path will have
			 * set PG_referenced or activated the page.
			 */
			if (likely(!VM_SequentialReadHint(vma)))
				referenced++;
		}
		pte_unmap_unlock(pte, ptl);
	}

	/* Pretend the page is referenced if the task has the
	   swap token and is in the middle of a page fault. */
	if (mm != current->mm && has_swap_token(mm) &&
			rwsem_is_locked(&mm->mmap_sem))
		referenced++;

	(*mapcount)--;

	if (referenced)
		*vm_flags |= vma->vm_flags;
out:
	return referenced;
}

static int page_referenced_anon(struct page *page,
				struct mem_cgroup *mem_cont,
				unsigned long *vm_flags)
{
	unsigned int mapcount;
	struct anon_vma *anon_vma;
	struct anon_vma_chain *avc;
	int referenced = 0;

	anon_vma = page_lock_anon_vma(page);
	if (!anon_vma)
		return referenced;

	mapcount = page_mapcount(page);
	list_for_each_entry(avc, &anon_vma->head, same_anon_vma) {
		struct vm_area_struct *vma = avc->vma;
		unsigned long address = vma_address(page, vma);
		if (address == -EFAULT)
			continue;
		/*
		 * If we are reclaiming on behalf of a cgroup, skip
		 * counting on behalf of references from different
		 * cgroups
		 */
		if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont))
			continue;
		referenced += page_referenced_one(page, vma, address,
						  &mapcount, vm_flags);
		if (!mapcount)
			break;
	}

	page_unlock_anon_vma(anon_vma);
	return referenced;
}

/**
 * page_referenced_file - referenced check for object-based rmap
 * @page: the page we're checking references on.
 * @mem_cont: target memory controller
 * @vm_flags: collect encountered vma->vm_flags who actually referenced the page
 *
 * For an object-based mapped page, find all the places it is mapped and
 * check/clear the referenced flag.  This is done by following the page->mapping
 * pointer, then walking the chain of vmas it holds.  It returns the number
 * of references it found.
 *
 * This function is only called from page_referenced for object-based pages.
 */
static int page_referenced_file(struct page *page,
				struct mem_cgroup *mem_cont,
				unsigned long *vm_flags)
{
	unsigned int mapcount;
	struct address_space *mapping = page->mapping;
	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
	struct vm_area_struct *vma;
	struct prio_tree_iter iter;
	int referenced = 0;

	/*
	 * The caller's checks on page->mapping and !PageAnon have made
	 * sure that this is a file page: the check for page->mapping
	 * excludes the case just before it gets set on an anon page.
	 */
	BUG_ON(PageAnon(page));

	/*
	 * 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_mutex.
	 */
	BUG_ON(!PageLocked(page));

	mutex_lock(&mapping->i_mmap_mutex);

	/*
	 * i_mmap_mutex does not stabilize mapcount at all, but mapcount
	 * is more likely to be accurate if we note it after spinning.
	 */
	mapcount = page_mapcount(page);

	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
		unsigned long address = vma_address(page, vma);
		if (address == -EFAULT)
			continue;
		/*
		 * If we are reclaiming on behalf of a cgroup, skip
		 * counting on behalf of references from different
		 * cgroups
		 */
		if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont))
			continue;
		referenced += page_referenced_one(page, vma, address,
						  &mapcount, vm_flags);
		if (!mapcount)
			break;
	}

	mutex_unlock(&mapping->i_mmap_mutex);
	return referenced;
}

/**
 * page_referenced - test if the page was referenced
 * @page: the page to test
 * @is_locked: caller holds lock on the page
 * @mem_cont: target memory controller
 * @vm_flags: collect encountered vma->vm_flags who actually referenced the page
 *
 * Quick test_and_clear_referenced for all mappings to a page,
 * returns the number of ptes which referenced the page.
 */
int page_referenced(struct page *page,
		    int is_locked,
		    struct mem_cgroup *mem_cont,
		    unsigned long *vm_flags)
{
	int referenced = 0;
	int we_locked = 0;

	*vm_flags = 0;
	if (page_mapped(page) && page_rmapping(page)) {
		if (!is_locked && (!PageAnon(page) || PageKsm(page))) {
			we_locked = trylock_page(page);
			if (!we_locked) {
				referenced++;
				goto out;
			}
		}
		if (unlikely(PageKsm(page)))
			referenced += page_referenced_ksm(page, mem_cont,
								vm_flags);
		else if (PageAnon(page))
			referenced += page_referenced_anon(page, mem_cont,
								vm_flags);
		else if (page->mapping)
			referenced += page_referenced_file(page, mem_cont,
								vm_flags);
		if (we_locked)
			unlock_page(page);

		if (page_test_and_clear_young(page_to_pfn(page)))
			referenced++;
	}
out:
	return referenced;
}

static int page_mkclean_one(struct page *page, struct vm_area_struct *vma,
			    unsigned long address)
{
	struct mm_struct *mm = vma->vm_mm;
	pte_t *pte;
	spinlock_t *ptl;
	int ret = 0;

	pte = page_check_address(page, mm, address, &ptl, 1);
	if (!pte)
		goto out;

	if (pte_dirty(*pte) || pte_write(*pte)) {
		pte_t entry;

		flush_cache_page(vma, address, pte_pfn(*pte));
		entry = ptep_clear_flush_notify(vma, address, pte);
		entry = pte_wrprotect(entry);
		entry = pte_mkclean(entry);
		set_pte_at(mm, address, pte, entry);
		ret = 1;
	}

	pte_unmap_unlock(pte, ptl);
out:
	return ret;
}

static int page_mkclean_file(struct address_space *mapping, struct page *page)
{
	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
	struct vm_area_struct *vma;
	struct prio_tree_iter iter;
	int ret = 0;

	BUG_ON(PageAnon(page));

	mutex_lock(&mapping->i_mmap_mutex);
	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
		if (vma->vm_flags & VM_SHARED) {
			unsigned long address = vma_address(page, vma);
			if (address == -EFAULT)
				continue;
			ret += page_mkclean_one(page, vma, address);
		}
	}
	mutex_unlock(&mapping->i_mmap_mutex);
	return ret;
}

int page_mkclean(struct page *page)
{
	int ret = 0;

	BUG_ON(!PageLocked(page));

	if (page_mapped(page)) {
		struct address_space *mapping = page_mapping(page);
		if (mapping) {
			ret = page_mkclean_file(mapping, page);
			if (page_test_and_clear_dirty(page_to_pfn(page), 1))
				ret = 1;
		}
	}

	return ret;
}
EXPORT_SYMBOL_GPL(page_mkclean);

/**
 * 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
 * @address:	the user virtual address mapped
 *
 * 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, unsigned long address)
{
	struct anon_vma *anon_vma = vma->anon_vma;

	VM_BUG_ON(!PageLocked(page));
	VM_BUG_ON(!anon_vma);
	VM_BUG_ON(page->index != linear_page_index(vma, address));

	anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
	page->mapping = (struct address_space *) anon_vma;
}

/**
 * __page_set_anon_rmap - set up new anonymous rmap
 * @page:	Page 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;

	anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
	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)
{
#ifdef CONFIG_DEBUG_VM
	/*
	 * 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, except if called from page_dup_rmap,
	 * in which case the page is already known to be setup.
	 *
	 * 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.
	 */
	BUG_ON(page_anon_vma(page)->root != vma->anon_vma->root);
	BUG_ON(page->index != linear_page_index(vma, address));
#endif
}

/**
 * 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
 *
 * 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)
{
	do_page_add_anon_rmap(page, vma, address, 0);
}

/*
 * Special version of the above for do_swap_page, which often runs
 * into pages that are exclusively owned by the current process.
 * Everybody else should continue to use page_add_anon_rmap above.
 */
void do_page_add_anon_rmap(struct page *page,
	struct vm_area_struct *vma, unsigned long address, int exclusive)
{
	int first = atomic_inc_and_test(&page->_mapcount);
	if (first) {
		if (!PageTransHuge(page))
			__inc_zone_page_state(page, NR_ANON_PAGES);
		else
			__inc_zone_page_state(page,
					      NR_ANON_TRANSPARENT_HUGEPAGES);
	}
	if (unlikely(PageKsm(page)))
		return;

	VM_BUG_ON(!PageLocked(page));
	/* address might be in next vma when migration races vma_adjust */
	if (first)
		__page_set_anon_rmap(page, vma, address, exclusive);
	else
		__page_check_anon_rmap(page, vma, address);
}

/**
 * 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
 *
 * 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)
{
	VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
	SetPageSwapBacked(page);
	atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */
	if (!PageTransHuge(page))
		__inc_zone_page_state(page, NR_ANON_PAGES);
	else
		__inc_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES);
	__page_set_anon_rmap(page, vma, address, 1);
	if (page_evictable(page, vma))
		lru_cache_add_lru(page, LRU_ACTIVE_ANON);
	else
		add_page_to_unevictable_list(page);
}

/**
 * page_add_file_rmap - add pte mapping to a file page
 * @page: the page to add the mapping to
 *
 * The caller needs to hold the pte lock.
 */
void page_add_file_rmap(struct page *page)
{
	if (atomic_inc_and_test(&page->_mapcount)) {
		__inc_zone_page_state(page, NR_FILE_MAPPED);
		mem_cgroup_inc_page_stat(page, MEMCG_NR_FILE_MAPPED);
	}
}

/**
 * page_remove_rmap - take down pte mapping from a page
 * @page: page to remove mapping from
 *
 * The caller needs to hold the pte lock.
 */
void page_remove_rmap(struct page *page)
{
	/* page still mapped by someone else? */
	if (!atomic_add_negative(-1, &page->_mapcount))
		return;

	/*
	 * Now that the last pte has gone, s390 must transfer dirty
	 * flag from storage key to struct page.  We can usually skip
	 * this if the page is anon, so about to be freed; but perhaps
	 * not if it's in swapcache - there might be another pte slot
	 * containing the swap entry, but page not yet written to swap.
	 */
	if ((!PageAnon(page) || PageSwapCache(page)) &&
	    page_test_and_clear_dirty(page_to_pfn(page), 1))
		set_page_dirty(page);
	/*
	 * Hugepages are not counted in NR_ANON_PAGES nor NR_FILE_MAPPED
	 * and not charged by memcg for now.
	 */
	if (unlikely(PageHuge(page)))
		return;
	if (PageAnon(page)) {
		mem_cgroup_uncharge_page(page);
		if (!PageTransHuge(page))
			__dec_zone_page_state(page, NR_ANON_PAGES);
		else
			__dec_zone_page_state(page,
					      NR_ANON_TRANSPARENT_HUGEPAGES);
	} else {
		__dec_zone_page_state(page, NR_FILE_MAPPED);
		mem_cgroup_dec_page_stat(page, MEMCG_NR_FILE_MAPPED);
	}
	/*
	 * 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_hot_cold_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.
	 */
}

/*
 * Subfunctions of try_to_unmap: try_to_unmap_one called
 * repeatedly from try_to_unmap_ksm, try_to_unmap_anon or try_to_unmap_file.
 */
int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
		     unsigned long address, enum ttu_flags flags)
{
	struct mm_struct *mm = vma->vm_mm;
	pte_t *pte;
	pte_t pteval;
	spinlock_t *ptl;
	int ret = SWAP_AGAIN;

	pte = page_check_address(page, mm, address, &ptl, 0);
	if (!pte)
		goto out;

	/*
	 * If the page is mlock()d, we cannot swap it out.
	 * If it's recently referenced (perhaps page_referenced
	 * skipped over this mm) then we should reactivate it.
	 */
	if (!(flags & TTU_IGNORE_MLOCK)) {
		if (vma->vm_flags & VM_LOCKED)
			goto out_mlock;

		if (TTU_ACTION(flags) == TTU_MUNLOCK)
			goto out_unmap;
	}
	if (!(flags & TTU_IGNORE_ACCESS)) {
		if (ptep_clear_flush_young_notify(vma, address, pte)) {
			ret = SWAP_FAIL;
			goto out_unmap;
		}
  	}

	/* Nuke the page table entry. */
	flush_cache_page(vma, address, page_to_pfn(page));
	pteval = ptep_clear_flush_notify(vma, address, pte);

	/* Move the dirty bit to the physical page now the pte is gone. */
	if (pte_dirty(pteval))
		set_page_dirty(page);

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

	if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) {
		if (PageAnon(page))
			dec_mm_counter(mm, MM_ANONPAGES);
		else
			dec_mm_counter(mm, MM_FILEPAGES);
		set_pte_at(mm, address, pte,
				swp_entry_to_pte(make_hwpoison_entry(page)));
	} else if (PageAnon(page)) {
		swp_entry_t entry = { .val = page_private(page) };

		if (PageSwapCache(page)) {
			/*
			 * Store the swap location in the pte.
			 * See handle_pte_fault() ...
			 */
			if (swap_duplicate(entry) < 0) {
				set_pte_at(mm, address, pte, pteval);
				ret = SWAP_FAIL;
				goto out_unmap;
			}
			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);
		} else if (PAGE_MIGRATION) {
			/*
			 * 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.
			 */
			BUG_ON(TTU_ACTION(flags) != TTU_MIGRATION);
			entry = make_migration_entry(page, pte_write(pteval));
		}
		set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
		BUG_ON(pte_file(*pte));
	} else if (PAGE_MIGRATION && (TTU_ACTION(flags) == TTU_MIGRATION)) {
		/* Establish migration entry for a file page */
		swp_entry_t entry;
		entry = make_migration_entry(page, pte_write(pteval));
		set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
	} else
		dec_mm_counter(mm, MM_FILEPAGES);

	page_remove_rmap(page);
	page_cache_release(page);

out_unmap:
	pte_unmap_unlock(pte, ptl);
out:
	return ret;

out_mlock:
	pte_unmap_unlock(pte, ptl);


	/*
	 * We need mmap_sem locking, Otherwise VM_LOCKED check makes
	 * unstable result and race. Plus, We can't wait here because
	 * we now hold anon_vma->mutex or mapping->i_mmap_mutex.
	 * if trylock failed, the page remain in evictable lru and later
	 * vmscan could retry to move the page to unevictable lru if the
	 * page is actually mlocked.
	 */
	if (down_read_trylock(&vma->vm_mm->mmap_sem)) {
		if (vma->vm_flags & VM_LOCKED) {
			mlock_vma_page(page);
			ret = SWAP_MLOCK;
		}
		up_read(&vma->vm_mm->mmap_sem);
	}
	return ret;
}

/*
 * objrmap doesn't work for nonlinear VMAs because the assumption that
 * offset-into-file correlates with offset-into-virtual-addresses does not hold.
 * Consequently, given a particular page and its ->index, we cannot locate the
 * ptes which are mapping that page without an exhaustive linear search.
 *
 * So what this code does is a mini "virtual scan" of each nonlinear VMA which
 * maps the file to which the target page belongs.  The ->vm_private_data field
 * holds the current cursor into that scan.  Successive searches will circulate
 * around the vma's virtual address space.
 *
 * So as more replacement pressure is applied to the pages in a nonlinear VMA,
 * more scanning pressure is placed against them as well.   Eventually pages
 * will become fully unmapped and are eligible for eviction.
 *
 * For very sparsely populated VMAs this is a little inefficient - chances are
 * there there won't be many ptes located within the scan cluster.  In this case
 * maybe we could scan further - to the end of the pte page, perhaps.
 *
 * Mlocked pages:  check VM_LOCKED under mmap_sem held for read, if we can
 * acquire it without blocking.  If vma locked, mlock the pages in the cluster,
 * rather than unmapping them.  If we encounter the "check_page" that vmscan is
 * trying to unmap, return SWAP_MLOCK, else default SWAP_AGAIN.
 */
#define CLUSTER_SIZE	min(32*PAGE_SIZE, PMD_SIZE)
#define CLUSTER_MASK	(~(CLUSTER_SIZE - 1))

static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
		struct vm_area_struct *vma, struct page *check_page)
{
	struct mm_struct *mm = vma->vm_mm;
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;
	pte_t pteval;
	spinlock_t *ptl;
	struct page *page;
	unsigned long address;
	unsigned long end;
	int ret = SWAP_AGAIN;
	int locked_vma = 0;

	address = (vma->vm_start + cursor) & CLUSTER_MASK;
	end = address + CLUSTER_SIZE;
	if (address < vma->vm_start)
		address = vma->vm_start;
	if (end > vma->vm_end)
		end = vma->vm_end;

	pgd = pgd_offset(mm, address);
	if (!pgd_present(*pgd))
		return ret;

	pud = pud_offset(pgd, address);
	if (!pud_present(*pud))
		return ret;

	pmd = pmd_offset(pud, address);
	if (!pmd_present(*pmd))
		return ret;

	/*
	 * If we can acquire the mmap_sem for read, and vma is VM_LOCKED,
	 * keep the sem while scanning the cluster for mlocking pages.
	 */
	if (down_read_trylock(&vma->vm_mm->mmap_sem)) {
		locked_vma = (vma->vm_flags & VM_LOCKED);
		if (!locked_vma)
			up_read(&vma->vm_mm->mmap_sem); /* don't need it */
	}

	pte = pte_offset_map_lock(mm, pmd, address, &ptl);

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

	for (; address < end; pte++, address += PAGE_SIZE) {
		if (!pte_present(*pte))
			continue;
		page = vm_normal_page(vma, address, *pte);
		BUG_ON(!page || PageAnon(page));

		if (locked_vma) {
			mlock_vma_page(page);   /* no-op if already mlocked */
			if (page == check_page)
				ret = SWAP_MLOCK;
			continue;	/* don't unmap */
		}

		if (ptep_clear_flush_young_notify(vma, address, pte))
			continue;

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

		/* If nonlinear, store the file page offset in the pte. */
		if (page->index != linear_page_index(vma, address))
			set_pte_at(mm, address, pte, pgoff_to_pte(page->index));

		/* Move the dirty bit to the physical page now the pte is gone. */
		if (pte_dirty(pteval))
			set_page_dirty(page);

		page_remove_rmap(page);
		page_cache_release(page);
		dec_mm_counter(mm, MM_FILEPAGES);
		(*mapcount)--;
	}
	pte_unmap_unlock(pte - 1, ptl);
	if (locked_vma)
		up_read(&vma->vm_mm->mmap_sem);
	return ret;
}

bool is_vma_temporary_stack(struct vm_area_struct *vma)
{
	int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP);

	if (!maybe_stack)
		return false;

	if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) ==
						VM_STACK_INCOMPLETE_SETUP)
		return true;

	return false;
}

/**
 * try_to_unmap_anon - unmap or unlock anonymous page using the object-based
 * rmap method
 * @page: the page to unmap/unlock
 * @flags: action and flags
 *
 * Find all the mappings of a page using the mapping pointer and the vma chains
 * contained in the anon_vma struct it points to.
 *
 * This function is only called from try_to_unmap/try_to_munlock for
 * anonymous pages.
 * When called from try_to_munlock(), the mmap_sem of the mm containing the vma
 * where the page was found will be held for write.  So, we won't recheck
 * vm_flags for that VMA.  That should be OK, because that vma shouldn't be
 * 'LOCKED.
 */
static int try_to_unmap_anon(struct page *page, enum ttu_flags flags)
{
	struct anon_vma *anon_vma;
	struct anon_vma_chain *avc;
	int ret = SWAP_AGAIN;

	anon_vma = page_lock_anon_vma(page);
	if (!anon_vma)
		return ret;

	list_for_each_entry(avc, &anon_vma->head, same_anon_vma) {
		struct vm_area_struct *vma = avc->vma;
		unsigned long address;

		/*
		 * 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 (PAGE_MIGRATION && (flags & TTU_MIGRATION) &&
				is_vma_temporary_stack(vma))
			continue;

		address = vma_address(page, vma);
		if (address == -EFAULT)
			continue;
		ret = try_to_unmap_one(page, vma, address, flags);
		if (ret != SWAP_AGAIN || !page_mapped(page))
			break;
	}

	page_unlock_anon_vma(anon_vma);
	return ret;
}

/**
 * try_to_unmap_file - unmap/unlock file page using the object-based rmap method
 * @page: the page to unmap/unlock
 * @flags: action and flags
 *
 * Find all the mappings of a page using the mapping pointer and the vma chains
 * contained in the address_space struct it points to.
 *
 * This function is only called from try_to_unmap/try_to_munlock for
 * object-based pages.
 * When called from try_to_munlock(), the mmap_sem of the mm containing the vma
 * where the page was found will be held for write.  So, we won't recheck
 * vm_flags for that VMA.  That should be OK, because that vma shouldn't be
 * 'LOCKED.
 */
static int try_to_unmap_file(struct page *page, enum ttu_flags flags)
{
	struct address_space *mapping = page->mapping;
	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
	struct vm_area_struct *vma;
	struct prio_tree_iter iter;
	int ret = SWAP_AGAIN;
	unsigned long cursor;
	unsigned long max_nl_cursor = 0;
	unsigned long max_nl_size = 0;
	unsigned int mapcount;

	mutex_lock(&mapping->i_mmap_mutex);
	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
		unsigned long address = vma_address(page, vma);
		if (address == -EFAULT)
			continue;
		ret = try_to_unmap_one(page, vma, address, flags);
		if (ret != SWAP_AGAIN || !page_mapped(page))
			goto out;
	}

	if (list_empty(&mapping->i_mmap_nonlinear))
		goto out;

	/*
	 * We don't bother to try to find the munlocked page in nonlinears.
	 * It's costly. Instead, later, page reclaim logic may call
	 * try_to_unmap(TTU_MUNLOCK) and recover PG_mlocked lazily.
	 */
	if (TTU_ACTION(flags) == TTU_MUNLOCK)
		goto out;

	list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
						shared.vm_set.list) {
		cursor = (unsigned long) vma->vm_private_data;
		if (cursor > max_nl_cursor)
			max_nl_cursor = cursor;
		cursor = vma->vm_end - vma->vm_start;
		if (cursor > max_nl_size)
			max_nl_size = cursor;
	}

	if (max_nl_size == 0) {	/* all nonlinears locked or reserved ? */
		ret = SWAP_FAIL;
		goto out;
	}

	/*
	 * We don't try to search for this page in the nonlinear vmas,
	 * and page_referenced wouldn't have found it anyway.  Instead
	 * just walk the nonlinear vmas trying to age and unmap some.
	 * The mapcount of the page we came in with is irrelevant,
	 * but even so use it as a guide to how hard we should try?
	 */
	mapcount = page_mapcount(page);
	if (!mapcount)
		goto out;
	cond_resched();

	max_nl_size = (max_nl_size + CLUSTER_SIZE - 1) & CLUSTER_MASK;
	if (max_nl_cursor == 0)
		max_nl_cursor = CLUSTER_SIZE;

	do {
		list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
						shared.vm_set.list) {
			cursor = (unsigned long) vma->vm_private_data;
			while ( cursor < max_nl_cursor &&
				cursor < vma->vm_end - vma->vm_start) {
				if (try_to_unmap_cluster(cursor, &mapcount,
						vma, page) == SWAP_MLOCK)
					ret = SWAP_MLOCK;
				cursor += CLUSTER_SIZE;
				vma->vm_private_data = (void *) cursor;
				if ((int)mapcount <= 0)
					goto out;
			}
			vma->vm_private_data = (void *) max_nl_cursor;
		}
		cond_resched();
		max_nl_cursor += CLUSTER_SIZE;
	} while (max_nl_cursor <= max_nl_size);

	/*
	 * Don't loop forever (perhaps all the remaining pages are
	 * in locked vmas).  Reset cursor on all unreserved nonlinear
	 * vmas, now forgetting on which ones it had fallen behind.
	 */
	list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list)
		vma->vm_private_data = NULL;
out:
	mutex_unlock(&mapping->i_mmap_mutex);
	return ret;
}

/**
 * try_to_unmap - try to remove all page table mappings to a page
 * @page: the page to get unmapped
 * @flags: action and flags
 *
 * Tries to remove all the page table entries which are mapping this
 * page, used in the pageout path.  Caller must hold the page lock.
 * Return values are:
 *
 * SWAP_SUCCESS	- we succeeded in removing all mappings
 * SWAP_AGAIN	- we missed a mapping, try again later
 * SWAP_FAIL	- the page is unswappable
 * SWAP_MLOCK	- page is mlocked.
 */
int try_to_unmap(struct page *page, enum ttu_flags flags)
{
	int ret;

	BUG_ON(!PageLocked(page));
	VM_BUG_ON(!PageHuge(page) && PageTransHuge(page));

	if (unlikely(PageKsm(page)))
		ret = try_to_unmap_ksm(page, flags);
	else if (PageAnon(page))
		ret = try_to_unmap_anon(page, flags);
	else
		ret = try_to_unmap_file(page, flags);
	if (ret != SWAP_MLOCK && !page_mapped(page))
		ret = SWAP_SUCCESS;
	return ret;
}

/**
 * try_to_munlock - try to munlock a page
 * @page: the page to be munlocked
 *
 * Called from munlock code.  Checks all of the VMAs mapping the page
 * to make sure nobody else has this page mlocked. The page will be
 * returned with PG_mlocked cleared if no other vmas have it mlocked.
 *
 * Return values are:
 *
 * SWAP_AGAIN	- no vma is holding page mlocked, or,
 * SWAP_AGAIN	- page mapped in mlocked vma -- couldn't acquire mmap sem
 * SWAP_FAIL	- page cannot be located at present
 * SWAP_MLOCK	- page is now mlocked.
 */
int try_to_munlock(struct page *page)
{
	VM_BUG_ON(!PageLocked(page) || PageLRU(page));

	if (unlikely(PageKsm(page)))
		return try_to_unmap_ksm(page, TTU_MUNLOCK);
	else if (PageAnon(page))
		return try_to_unmap_anon(page, TTU_MUNLOCK);
	else
		return try_to_unmap_file(page, TTU_MUNLOCK);
}

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

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

	anon_vma_free(anon_vma);
}

#ifdef CONFIG_MIGRATION
/*
 * rmap_walk() and its helpers rmap_walk_anon() and rmap_walk_file():
 * Called by migrate.c to remove migration ptes, but might be used more later.
 */
static int rmap_walk_anon(struct page *page, int (*rmap_one)(struct page *,
		struct vm_area_struct *, unsigned long, void *), void *arg)
{
	struct anon_vma *anon_vma;
	struct anon_vma_chain *avc;
	int ret = SWAP_AGAIN;

	/*
	 * Note: remove_migration_ptes() cannot use page_lock_anon_vma()
	 * because that depends on page_mapped(); but not all its usages
	 * are holding mmap_sem. Users without mmap_sem are required to
	 * take a reference count to prevent the anon_vma disappearing
	 */
	anon_vma = page_anon_vma(page);
	if (!anon_vma)
		return ret;
	anon_vma_lock(anon_vma);
	list_for_each_entry(avc, &anon_vma->head, same_anon_vma) {
		struct vm_area_struct *vma = avc->vma;
		unsigned long address = vma_address(page, vma);
		if (address == -EFAULT)
			continue;
		ret = rmap_one(page, vma, address, arg);
		if (ret != SWAP_AGAIN)
			break;
	}
	anon_vma_unlock(anon_vma);
	return ret;
}

static int rmap_walk_file(struct page *page, int (*rmap_one)(struct page *,
		struct vm_area_struct *, unsigned long, void *), void *arg)
{
	struct address_space *mapping = page->mapping;
	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
	struct vm_area_struct *vma;
	struct prio_tree_iter iter;
	int ret = SWAP_AGAIN;

	if (!mapping)
		return ret;
	mutex_lock(&mapping->i_mmap_mutex);
	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
		unsigned long address = vma_address(page, vma);
		if (address == -EFAULT)
			continue;
		ret = rmap_one(page, vma, address, arg);
		if (ret != SWAP_AGAIN)
			break;
	}
	/*
	 * No nonlinear handling: being always shared, nonlinear vmas
	 * never contain migration ptes.  Decide what to do about this
	 * limitation to linear when we need rmap_walk() on nonlinear.
	 */
	mutex_unlock(&mapping->i_mmap_mutex);
	return ret;
}

int rmap_walk(struct page *page, int (*rmap_one)(struct page *,
		struct vm_area_struct *, unsigned long, void *), void *arg)
{
	VM_BUG_ON(!PageLocked(page));

	if (unlikely(PageKsm(page)))
		return rmap_walk_ksm(page, rmap_one, arg);
	else if (PageAnon(page))
		return rmap_walk_anon(page, rmap_one, arg);
	else
		return rmap_walk_file(page, rmap_one, arg);
}
#endif /* CONFIG_MIGRATION */

#ifdef CONFIG_HUGETLB_PAGE
/*
 * The following three 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.
 */
static void __hugepage_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 (!exclusive)
		anon_vma = anon_vma->root;

	anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
	page->mapping = (struct address_space *) anon_vma;
	page->index = linear_page_index(vma, address);
}

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(&page->_mapcount);
	if (first)
		__hugepage_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(&page->_mapcount, 0);
	__hugepage_set_anon_rmap(page, vma, address, 1);
}
#endif /* CONFIG_HUGETLB_PAGE */
OpenPOWER on IntegriCloud