Home Home > GIT Browse
summaryrefslogtreecommitdiff
blob: 0a7013a26019e9760894bb28b1a5c096cac90b7d (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
/*
 *  linux/mm/memory.c
 *
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 */

/*
 * demand-loading started 01.12.91 - seems it is high on the list of
 * things wanted, and it should be easy to implement. - Linus
 */

/*
 * Ok, demand-loading was easy, shared pages a little bit tricker. Shared
 * pages started 02.12.91, seems to work. - Linus.
 *
 * Tested sharing by executing about 30 /bin/sh: under the old kernel it
 * would have taken more than the 6M I have free, but it worked well as
 * far as I could see.
 *
 * Also corrected some "invalidate()"s - I wasn't doing enough of them.
 */

/*
 * Real VM (paging to/from disk) started 18.12.91. Much more work and
 * thought has to go into this. Oh, well..
 * 19.12.91  -  works, somewhat. Sometimes I get faults, don't know why.
 *		Found it. Everything seems to work now.
 * 20.12.91  -  Ok, making the swap-device changeable like the root.
 */

/*
 * 05.04.94  -  Multi-page memory management added for v1.1.
 * 		Idea by Alex Bligh (alex@cconcepts.co.uk)
 *
 * 16.07.99  -  Support of BIGMEM added by Gerhard Wichert, Siemens AG
 *		(Gerhard.Wichert@pdb.siemens.de)
 */

#include <linux/kernel_stat.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/mman.h>
#include <linux/swap.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/module.h>
#include <linux/init.h>

#include <asm/pgalloc.h>
#include <asm/uaccess.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/pgtable.h>

#include <linux/swapops.h>
#include <linux/elf.h>

#ifndef CONFIG_DISCONTIGMEM
/* use the per-pgdat data instead for discontigmem - mbligh */
unsigned long max_mapnr;
struct page *mem_map;

EXPORT_SYMBOL(max_mapnr);
EXPORT_SYMBOL(mem_map);
#endif

unsigned long num_physpages;
/*
 * A number of key systems in x86 including ioremap() rely on the assumption
 * that high_memory defines the upper bound on direct map memory, then end
 * of ZONE_NORMAL.  Under CONFIG_DISCONTIG this means that max_low_pfn and
 * highstart_pfn must be the same; there must be no gap between ZONE_NORMAL
 * and ZONE_HIGHMEM.
 */
void * high_memory;
struct page *highmem_start_page;
unsigned long vmalloc_earlyreserve;

EXPORT_SYMBOL(num_physpages);
EXPORT_SYMBOL(highmem_start_page);
EXPORT_SYMBOL(high_memory);
EXPORT_SYMBOL(vmalloc_earlyreserve);

/*
 * We special-case the C-O-W ZERO_PAGE, because it's such
 * a common occurrence (no need to read the page to know
 * that it's zero - better for the cache and memory subsystem).
 */
static inline void copy_cow_page(struct page * from, struct page * to, unsigned long address)
{
	if (from == ZERO_PAGE(address)) {
		clear_user_highpage(to, address);
		return;
	}
	copy_user_highpage(to, from, address);
}

/*
 * Note: this doesn't free the actual pages themselves. That
 * has been handled earlier when unmapping all the memory regions.
 */
static inline void free_one_pmd(struct mmu_gather *tlb, pmd_t * dir)
{
	struct page *page;

	if (pmd_none(*dir))
		return;
	if (unlikely(pmd_bad(*dir))) {
		pmd_ERROR(*dir);
		pmd_clear(dir);
		return;
	}
	page = pmd_page(*dir);
	pmd_clear(dir);
	dec_page_state(nr_page_table_pages);
	pte_free_tlb(tlb, page);
}

static inline void free_one_pgd(struct mmu_gather *tlb, pgd_t * dir)
{
	int j;
	pmd_t * pmd;

	if (pgd_none(*dir))
		return;
	if (unlikely(pgd_bad(*dir))) {
		pgd_ERROR(*dir);
		pgd_clear(dir);
		return;
	}
	pmd = pmd_offset(dir, 0);
	pgd_clear(dir);
	for (j = 0; j < PTRS_PER_PMD ; j++)
		free_one_pmd(tlb, pmd+j);
	pmd_free_tlb(tlb, pmd);
}

/*
 * This function clears all user-level page tables of a process - this
 * is needed by execve(), so that old pages aren't in the way.
 *
 * Must be called with pagetable lock held.
 */
void clear_page_tables(struct mmu_gather *tlb, unsigned long first, int nr)
{
	pgd_t * page_dir = tlb->mm->pgd;

	page_dir += first;
	do {
		free_one_pgd(tlb, page_dir);
		page_dir++;
	} while (--nr);
}

pte_t fastcall * pte_alloc_map(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
{
	if (!pmd_present(*pmd)) {
		struct page *new;

		spin_unlock(&mm->page_table_lock);
		new = pte_alloc_one(mm, address);
		spin_lock(&mm->page_table_lock);
		if (!new)
			return NULL;

		/*
		 * Because we dropped the lock, we should re-check the
		 * entry, as somebody else could have populated it..
		 */
		if (pmd_present(*pmd)) {
			pte_free(new);
			goto out;
		}
		inc_page_state(nr_page_table_pages);
		pmd_populate(mm, pmd, new);
	}
out:
	return pte_offset_map(pmd, address);
}

pte_t fastcall * pte_alloc_kernel(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
{
	if (!pmd_present(*pmd)) {
		pte_t *new;

		spin_unlock(&mm->page_table_lock);
		new = pte_alloc_one_kernel(mm, address);
		spin_lock(&mm->page_table_lock);
		if (!new)
			return NULL;

		/*
		 * Because we dropped the lock, we should re-check the
		 * entry, as somebody else could have populated it..
		 */
		if (pmd_present(*pmd)) {
			pte_free_kernel(new);
			goto out;
		}
		pmd_populate_kernel(mm, pmd, new);
	}
out:
	return pte_offset_kernel(pmd, address);
}
#define PTE_TABLE_MASK	((PTRS_PER_PTE-1) * sizeof(pte_t))
#define PMD_TABLE_MASK	((PTRS_PER_PMD-1) * sizeof(pmd_t))

/*
 * copy one vm_area from one task to the other. Assumes the page tables
 * already present in the new task to be cleared in the whole range
 * covered by this vma.
 *
 * 08Jan98 Merged into one routine from several inline routines to reduce
 *         variable count and make things faster. -jj
 *
 * dst->page_table_lock is held on entry and exit,
 * but may be dropped within pmd_alloc() and pte_alloc_map().
 */
int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
			struct vm_area_struct *vma)
{
	pgd_t * src_pgd, * dst_pgd;
	unsigned long address = vma->vm_start;
	unsigned long end = vma->vm_end;
	unsigned long cow;

	if (is_vm_hugetlb_page(vma))
		return copy_hugetlb_page_range(dst, src, vma);

	cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
	src_pgd = pgd_offset(src, address)-1;
	dst_pgd = pgd_offset(dst, address)-1;

	for (;;) {
		pmd_t * src_pmd, * dst_pmd;

		src_pgd++; dst_pgd++;
		
		/* copy_pmd_range */
		
		if (pgd_none(*src_pgd))
			goto skip_copy_pmd_range;
		if (unlikely(pgd_bad(*src_pgd))) {
			pgd_ERROR(*src_pgd);
			pgd_clear(src_pgd);
skip_copy_pmd_range:	address = (address + PGDIR_SIZE) & PGDIR_MASK;
			if (!address || (address >= end))
				goto out;
			continue;
		}

		src_pmd = pmd_offset(src_pgd, address);
		dst_pmd = pmd_alloc(dst, dst_pgd, address);
		if (!dst_pmd)
			goto nomem;

		do {
			pte_t * src_pte, * dst_pte;
		
			/* copy_pte_range */
		
			if (pmd_none(*src_pmd))
				goto skip_copy_pte_range;
			if (unlikely(pmd_bad(*src_pmd))) {
				pmd_ERROR(*src_pmd);
				pmd_clear(src_pmd);
skip_copy_pte_range:
				address = (address + PMD_SIZE) & PMD_MASK;
				if (address >= end)
					goto out;
				goto cont_copy_pmd_range;
			}

			dst_pte = pte_alloc_map(dst, dst_pmd, address);
			if (!dst_pte)
				goto nomem;
			spin_lock(&src->page_table_lock);	
			src_pte = pte_offset_map_nested(src_pmd, address);
			do {
				pte_t pte = *src_pte;
				struct page *page;
				unsigned long pfn;

				/* copy_one_pte */

				if (pte_none(pte))
					goto cont_copy_pte_range_noset;
				/* pte contains position in swap, so copy. */
				if (!pte_present(pte)) {
					if (!pte_file(pte))
						swap_duplicate(pte_to_swp_entry(pte));
					set_pte(dst_pte, pte);
					goto cont_copy_pte_range_noset;
				}
				pfn = pte_pfn(pte);
				/* the pte points outside of valid memory, the
				 * mapping is assumed to be good, meaningful
				 * and not mapped via rmap - duplicate the
				 * mapping as is.
				 */
				page = NULL;
				if (pfn_valid(pfn)) 
					page = pfn_to_page(pfn); 

				if (!page || PageReserved(page)) {
					set_pte(dst_pte, pte);
					goto cont_copy_pte_range_noset;
				}

				/*
				 * If it's a COW mapping, write protect it both
				 * in the parent and the child
				 */
				if (cow) {
					ptep_set_wrprotect(src_pte);
					pte = *src_pte;
				}

				/*
				 * If it's a shared mapping, mark it clean in
				 * the child
				 */
				if (vma->vm_flags & VM_SHARED)
					pte = pte_mkclean(pte);
				pte = pte_mkold(pte);
				get_page(page);
				dst->rss++;
				set_pte(dst_pte, pte);
				page_dup_rmap(page);
cont_copy_pte_range_noset:
				address += PAGE_SIZE;
				if (address >= end) {
					pte_unmap_nested(src_pte);
					pte_unmap(dst_pte);
					goto out_unlock;
				}
				src_pte++;
				dst_pte++;
			} while ((unsigned long)src_pte & PTE_TABLE_MASK);
			pte_unmap_nested(src_pte-1);
			pte_unmap(dst_pte-1);
			spin_unlock(&src->page_table_lock);
			cond_resched_lock(&dst->page_table_lock);
cont_copy_pmd_range:
			src_pmd++;
			dst_pmd++;
		} while ((unsigned long)src_pmd & PMD_TABLE_MASK);
	}
out_unlock:
	spin_unlock(&src->page_table_lock);
out:
	return 0;
nomem:
	return -ENOMEM;
}

static void zap_pte_range(struct mmu_gather *tlb,
		pmd_t *pmd, unsigned long address,
		unsigned long size, struct zap_details *details)
{
	unsigned long offset;
	pte_t *ptep;

	if (pmd_none(*pmd))
		return;
	if (unlikely(pmd_bad(*pmd))) {
		pmd_ERROR(*pmd);
		pmd_clear(pmd);
		return;
	}
	ptep = pte_offset_map(pmd, address);
	offset = address & ~PMD_MASK;
	if (offset + size > PMD_SIZE)
		size = PMD_SIZE - offset;
	size &= PAGE_MASK;
	if (details && !details->check_mapping && !details->nonlinear_vma)
		details = NULL;
	for (offset=0; offset < size; ptep++, offset += PAGE_SIZE) {
		pte_t pte = *ptep;
		if (pte_none(pte))
			continue;
		if (pte_present(pte)) {
			struct page *page = NULL;
			unsigned long pfn = pte_pfn(pte);
			if (pfn_valid(pfn)) {
				page = pfn_to_page(pfn);
				if (PageReserved(page))
					page = NULL;
			}
			if (unlikely(details) && page) {
				/*
				 * unmap_shared_mapping_pages() wants to
				 * invalidate cache without truncating:
				 * unmap shared but keep private pages.
				 */
				if (details->check_mapping &&
				    details->check_mapping != page->mapping)
					continue;
				/*
				 * Each page->index must be checked when
				 * invalidating or truncating nonlinear.
				 */
				if (details->nonlinear_vma &&
				    (page->index < details->first_index ||
				     page->index > details->last_index))
					continue;
			}
			pte = ptep_get_and_clear(ptep);
			tlb_remove_tlb_entry(tlb, ptep, address+offset);
			if (unlikely(!page))
				continue;
			if (unlikely(details) && details->nonlinear_vma
			    && linear_page_index(details->nonlinear_vma,
					address+offset) != page->index)
				set_pte(ptep, pgoff_to_pte(page->index));
			if (pte_dirty(pte))
				set_page_dirty(page);
			if (pte_young(pte) && !PageAnon(page))
				mark_page_accessed(page);
			tlb->freed++;
			page_remove_rmap(page);
			tlb_remove_page(tlb, page);
			continue;
		}
		/*
		 * If details->check_mapping, we leave swap entries;
		 * if details->nonlinear_vma, we leave file entries.
		 */
		if (unlikely(details))
			continue;
		if (!pte_file(pte))
			free_swap_and_cache(pte_to_swp_entry(pte));
		pte_clear(ptep);
	}
	pte_unmap(ptep-1);
}

static void zap_pmd_range(struct mmu_gather *tlb,
		pgd_t * dir, unsigned long address,
		unsigned long size, struct zap_details *details)
{
	pmd_t * pmd;
	unsigned long end;

	if (pgd_none(*dir))
		return;
	if (unlikely(pgd_bad(*dir))) {
		pgd_ERROR(*dir);
		pgd_clear(dir);
		return;
	}
	pmd = pmd_offset(dir, address);
	end = address + size;
	if (end > ((address + PGDIR_SIZE) & PGDIR_MASK))
		end = ((address + PGDIR_SIZE) & PGDIR_MASK);
	do {
		zap_pte_range(tlb, pmd, address, end - address, details);
		address = (address + PMD_SIZE) & PMD_MASK; 
		pmd++;
	} while (address && (address < end));
}

static void unmap_page_range(struct mmu_gather *tlb,
		struct vm_area_struct *vma, unsigned long address,
		unsigned long end, struct zap_details *details)
{
	pgd_t * dir;

	BUG_ON(address >= end);
	dir = pgd_offset(vma->vm_mm, address);
	tlb_start_vma(tlb, vma);
	do {
		zap_pmd_range(tlb, dir, address, end - address, details);
		address = (address + PGDIR_SIZE) & PGDIR_MASK;
		dir++;
	} while (address && (address < end));
	tlb_end_vma(tlb, vma);
}

/* Dispose of an entire struct mmu_gather per rescheduling point */
#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT)
#define ZAP_BLOCK_SIZE	(FREE_PTE_NR * PAGE_SIZE)
#endif

/* For UP, 256 pages at a time gives nice low latency */
#if !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT)
#define ZAP_BLOCK_SIZE	(256 * PAGE_SIZE)
#endif

/* No preempt: go for improved straight-line efficiency */
#if !defined(CONFIG_PREEMPT)
#define ZAP_BLOCK_SIZE	(1024 * PAGE_SIZE)
#endif

/**
 * unmap_vmas - unmap a range of memory covered by a list of vma's
 * @tlbp: address of the caller's struct mmu_gather
 * @mm: the controlling mm_struct
 * @vma: the starting vma
 * @start_addr: virtual address at which to start unmapping
 * @end_addr: virtual address at which to end unmapping
 * @nr_accounted: Place number of unmapped pages in vm-accountable vma's here
 * @details: details of nonlinear truncation or shared cache invalidation
 *
 * Returns the number of vma's which were covered by the unmapping.
 *
 * Unmap all pages in the vma list.  Called under page_table_lock.
 *
 * We aim to not hold page_table_lock for too long (for scheduling latency
 * reasons).  So zap pages in ZAP_BLOCK_SIZE bytecounts.  This means we need to
 * return the ending mmu_gather to the caller.
 *
 * Only addresses between `start' and `end' will be unmapped.
 *
 * The VMA list must be sorted in ascending virtual address order.
 *
 * unmap_vmas() assumes that the caller will flush the whole unmapped address
 * range after unmap_vmas() returns.  So the only responsibility here is to
 * ensure that any thus-far unmapped pages are flushed before unmap_vmas()
 * drops the lock and schedules.
 */
int unmap_vmas(struct mmu_gather **tlbp, struct mm_struct *mm,
		struct vm_area_struct *vma, unsigned long start_addr,
		unsigned long end_addr, unsigned long *nr_accounted,
		struct zap_details *details)
{
	unsigned long zap_bytes = ZAP_BLOCK_SIZE;
	unsigned long tlb_start = 0;	/* For tlb_finish_mmu */
	int tlb_start_valid = 0;
	int ret = 0;
	int atomic = details && details->atomic;

	for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) {
		unsigned long start;
		unsigned long end;

		start = max(vma->vm_start, start_addr);
		if (start >= vma->vm_end)
			continue;
		end = min(vma->vm_end, end_addr);
		if (end <= vma->vm_start)
			continue;

		if (vma->vm_flags & VM_ACCOUNT)
			*nr_accounted += (end - start) >> PAGE_SHIFT;

		ret++;
		while (start != end) {
			unsigned long block;

			if (!tlb_start_valid) {
				tlb_start = start;
				tlb_start_valid = 1;
			}

			if (is_vm_hugetlb_page(vma)) {
				block = end - start;
				unmap_hugepage_range(vma, start, end);
			} else {
				block = min(zap_bytes, end - start);
				unmap_page_range(*tlbp, vma, start,
						start + block, details);
			}

			start += block;
			zap_bytes -= block;
			if ((long)zap_bytes > 0)
				continue;
			if (!atomic && need_resched()) {
				int fullmm = tlb_is_full_mm(*tlbp);
				tlb_finish_mmu(*tlbp, tlb_start, start);
				cond_resched_lock(&mm->page_table_lock);
				*tlbp = tlb_gather_mmu(mm, fullmm);
				tlb_start_valid = 0;
			}
			zap_bytes = ZAP_BLOCK_SIZE;
		}
	}
	return ret;
}

/**
 * zap_page_range - remove user pages in a given range
 * @vma: vm_area_struct holding the applicable pages
 * @address: starting address of pages to zap
 * @size: number of bytes to zap
 * @details: details of nonlinear truncation or shared cache invalidation
 */
void zap_page_range(struct vm_area_struct *vma, unsigned long address,
		unsigned long size, struct zap_details *details)
{
	struct mm_struct *mm = vma->vm_mm;
	struct mmu_gather *tlb;
	unsigned long end = address + size;
	unsigned long nr_accounted = 0;

	if (is_vm_hugetlb_page(vma)) {
		zap_hugepage_range(vma, address, size);
		return;
	}

	lru_add_drain();
	spin_lock(&mm->page_table_lock);
	tlb = tlb_gather_mmu(mm, 0);
	unmap_vmas(&tlb, mm, vma, address, end, &nr_accounted, details);
	tlb_finish_mmu(tlb, address, end);
	spin_unlock(&mm->page_table_lock);
}

/*
 * Do a quick page-table lookup for a single page.
 * mm->page_table_lock must be held.
 */
struct page *
follow_page(struct mm_struct *mm, unsigned long address, int write) 
{
	pgd_t *pgd;
	pmd_t *pmd;
	pte_t *ptep, pte;
	unsigned long pfn;
	struct page *page;

	page = follow_huge_addr(mm, address, write);
	if (! IS_ERR(page))
		return page;

	pgd = pgd_offset(mm, address);
	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
		goto out;

	pmd = pmd_offset(pgd, address);
	if (pmd_none(*pmd))
		goto out;
	if (pmd_huge(*pmd))
		return follow_huge_pmd(mm, address, pmd, write);
	if (unlikely(pmd_bad(*pmd)))
		goto out;

	ptep = pte_offset_map(pmd, address);
	if (!ptep)
		goto out;

	pte = *ptep;
	pte_unmap(ptep);
	if (pte_present(pte)) {
		if (write && !pte_write(pte))
			goto out;
		pfn = pte_pfn(pte);
		if (pfn_valid(pfn)) {
			page = pfn_to_page(pfn);
			if (write && !pte_dirty(pte) && !PageDirty(page))
				set_page_dirty(page);
			mark_page_accessed(page);
			return page;
		}
	}

out:
	return NULL;
}

/* 
 * Given a physical address, is there a useful struct page pointing to
 * it?  This may become more complex in the future if we start dealing
 * with IO-aperture pages for direct-IO.
 */

static inline struct page *get_page_map(struct page *page)
{
	if (!pfn_valid(page_to_pfn(page)))
		return NULL;
	return page;
}


static inline int
untouched_anonymous_page(struct mm_struct* mm, struct vm_area_struct *vma,
			 unsigned long address)
{
	pgd_t *pgd;
	pmd_t *pmd;

	/* Check if the vma is for an anonymous mapping. */
	if (vma->vm_ops && vma->vm_ops->nopage)
		return 0;

	/* Check if page directory entry exists. */
	pgd = pgd_offset(mm, address);
	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
		return 1;

	/* Check if page middle directory entry exists. */
	pmd = pmd_offset(pgd, address);
	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
		return 1;

	/* There is a pte slot for 'address' in 'mm'. */
	return 0;
}


int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
		unsigned long start, int len, int write, int force,
		struct page **pages, struct vm_area_struct **vmas)
{
	int i;
	unsigned int flags;

	/* 
	 * Require read or write permissions.
	 * If 'force' is set, we only require the "MAY" flags.
	 */
	flags = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
	flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
	i = 0;

	do {
		struct vm_area_struct *	vma;

		vma = find_extend_vma(mm, start);
		if (!vma && in_gate_area(tsk, start)) {
			unsigned long pg = start & PAGE_MASK;
			struct vm_area_struct *gate_vma = get_gate_vma(tsk);
			pgd_t *pgd;
			pmd_t *pmd;
			pte_t *pte;
			if (write) /* user gate pages are read-only */
				return i ? : -EFAULT;
			pgd = pgd_offset_gate(mm, pg);
			if (!pgd)
				return i ? : -EFAULT;
			pmd = pmd_offset(pgd, pg);
			if (!pmd)
				return i ? : -EFAULT;
			pte = pte_offset_map(pmd, pg);
			if (!pte)
				return i ? : -EFAULT;
			if (!pte_present(*pte)) {
				pte_unmap(pte);
				return i ? : -EFAULT;
			}
			if (pages) {
				pages[i] = pte_page(*pte);
				get_page(pages[i]);
			}
			pte_unmap(pte);
			if (vmas)
				vmas[i] = gate_vma;
			i++;
			start += PAGE_SIZE;
			len--;
			continue;
		}

		if (!vma || (pages && (vma->vm_flags & VM_IO))
				|| !(flags & vma->vm_flags))
			return i ? : -EFAULT;

		if (is_vm_hugetlb_page(vma)) {
			i = follow_hugetlb_page(mm, vma, pages, vmas,
						&start, &len, i);
			continue;
		}
		spin_lock(&mm->page_table_lock);
		do {
			struct page *map;
			int lookup_write = write;
			while (!(map = follow_page(mm, start, lookup_write))) {
				/*
				 * Shortcut for anonymous pages. We don't want
				 * to force the creation of pages tables for
				 * insanly big anonymously mapped areas that
				 * nobody touched so far. This is important
				 * for doing a core dump for these mappings.
				 */
				if (!lookup_write &&
				    untouched_anonymous_page(mm,vma,start)) {
					map = ZERO_PAGE(start);
					break;
				}
				spin_unlock(&mm->page_table_lock);
				switch (handle_mm_fault(mm,vma,start,write)) {
				case VM_FAULT_MINOR:
					tsk->min_flt++;
					break;
				case VM_FAULT_MAJOR:
					tsk->maj_flt++;
					break;
				case VM_FAULT_SIGBUS:
					return i ? i : -EFAULT;
				case VM_FAULT_OOM:
					return i ? i : -ENOMEM;
				default:
					BUG();
				}
				/*
				 * Now that we have performed a write fault
				 * and surely no longer have a shared page we
				 * shouldn't write, we shouldn't ignore an
				 * unwritable page in the page table if
				 * we are forcing write access.
				 */
				lookup_write = write && !force;
				spin_lock(&mm->page_table_lock);
			}
			if (pages) {
				pages[i] = get_page_map(map);
				if (!pages[i]) {
					spin_unlock(&mm->page_table_lock);
					while (i--)
						page_cache_release(pages[i]);
					i = -EFAULT;
					goto out;
				}
				flush_dcache_page(pages[i]);
				if (!PageReserved(pages[i]))
					page_cache_get(pages[i]);
			}
			if (vmas)
				vmas[i] = vma;
			i++;
			start += PAGE_SIZE;
			len--;
		} while(len && start < vma->vm_end);
		spin_unlock(&mm->page_table_lock);
	} while(len);
out:
	return i;
}

EXPORT_SYMBOL(get_user_pages);

static void zeromap_pte_range(pte_t * pte, unsigned long address,
                                     unsigned long size, pgprot_t prot)
{
	unsigned long end;

	address &= ~PMD_MASK;
	end = address + size;
	if (end > PMD_SIZE)
		end = PMD_SIZE;
	do {
		pte_t zero_pte = pte_wrprotect(mk_pte(ZERO_PAGE(address), prot));
		BUG_ON(!pte_none(*pte));
		set_pte(pte, zero_pte);
		address += PAGE_SIZE;
		pte++;
	} while (address && (address < end));
}

static inline int zeromap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address,
                                    unsigned long size, pgprot_t prot)
{
	unsigned long base, end;

	base = address & PGDIR_MASK;
	address &= ~PGDIR_MASK;
	end = address + size;
	if (end > PGDIR_SIZE)
		end = PGDIR_SIZE;
	do {
		pte_t * pte = pte_alloc_map(mm, pmd, base + address);
		if (!pte)
			return -ENOMEM;
		zeromap_pte_range(pte, base + address, end - address, prot);
		pte_unmap(pte);
		address = (address + PMD_SIZE) & PMD_MASK;
		pmd++;
	} while (address && (address < end));
	return 0;
}

int zeromap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size, pgprot_t prot)
{
	int error = 0;
	pgd_t * dir;
	unsigned long beg = address;
	unsigned long end = address + size;
	struct mm_struct *mm = vma->vm_mm;

	dir = pgd_offset(mm, address);
	flush_cache_range(vma, beg, end);
	if (address >= end)
		BUG();

	spin_lock(&mm->page_table_lock);
	do {
		pmd_t *pmd = pmd_alloc(mm, dir, address);
		error = -ENOMEM;
		if (!pmd)
			break;
		error = zeromap_pmd_range(mm, pmd, address, end - address, prot);
		if (error)
			break;
		address = (address + PGDIR_SIZE) & PGDIR_MASK;
		dir++;
	} while (address && (address < end));
	/*
	 * Why flush? zeromap_pte_range has a BUG_ON for !pte_none()
	 */
	flush_tlb_range(vma, beg, end);
	spin_unlock(&mm->page_table_lock);
	return error;
}

/*
 * maps a range of physical memory into the requested pages. the old
 * mappings are removed. any references to nonexistent pages results
 * in null mappings (currently treated as "copy-on-access")
 */
static inline void remap_pte_range(pte_t * pte, unsigned long address, unsigned long size,
	unsigned long phys_addr, pgprot_t prot)
{
	unsigned long end;
	unsigned long pfn;

	address &= ~PMD_MASK;
	end = address + size;
	if (end > PMD_SIZE)
		end = PMD_SIZE;
	pfn = phys_addr >> PAGE_SHIFT;
	do {
		BUG_ON(!pte_none(*pte));
		if (!pfn_valid(pfn) || PageReserved(pfn_to_page(pfn)))
 			set_pte(pte, pfn_pte(pfn, prot));
		address += PAGE_SIZE;
		pfn++;
		pte++;
	} while (address && (address < end));
}

static inline int remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size,
	unsigned long phys_addr, pgprot_t prot)
{
	unsigned long base, end;

	base = address & PGDIR_MASK;
	address &= ~PGDIR_MASK;
	end = address + size;
	if (end > PGDIR_SIZE)
		end = PGDIR_SIZE;
	phys_addr -= address;
	do {
		pte_t * pte = pte_alloc_map(mm, pmd, base + address);
		if (!pte)
			return -ENOMEM;
		remap_pte_range(pte, base + address, end - address, address + phys_addr, prot);
		pte_unmap(pte);
		address = (address + PMD_SIZE) & PMD_MASK;
		pmd++;
	} while (address && (address < end));
	return 0;
}

/*  Note: this is only safe if the mm semaphore is held when called. */
int remap_page_range(struct vm_area_struct *vma, unsigned long from, unsigned long phys_addr, unsigned long size, pgprot_t prot)
{
	int error = 0;
	pgd_t * dir;
	unsigned long beg = from;
	unsigned long end = from + size;
	struct mm_struct *mm = vma->vm_mm;

	phys_addr -= from;
	dir = pgd_offset(mm, from);
	flush_cache_range(vma, beg, end);
	if (from >= end)
		BUG();

	spin_lock(&mm->page_table_lock);
	do {
		pmd_t *pmd = pmd_alloc(mm, dir, from);
		error = -ENOMEM;
		if (!pmd)
			break;
		error = remap_pmd_range(mm, pmd, from, end - from, phys_addr + from, prot);
		if (error)
			break;
		from = (from + PGDIR_SIZE) & PGDIR_MASK;
		dir++;
	} while (from && (from < end));
	/*
	 * Why flush? remap_pte_range has a BUG_ON for !pte_none()
	 */
	flush_tlb_range(vma, beg, end);
	spin_unlock(&mm->page_table_lock);
	return error;
}

EXPORT_SYMBOL(remap_page_range);

/*
 * Do pte_mkwrite, but only if the vma says VM_WRITE.  We do this when
 * servicing faults for write access.  In the normal case, do always want
 * pte_mkwrite.  But get_user_pages can cause write faults for mappings
 * that do not have writing enabled, when used by access_process_vm.
 */
static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
{
	if (likely(vma->vm_flags & VM_WRITE))
		pte = pte_mkwrite(pte);
	return pte;
}

/*
 * We hold the mm semaphore for reading and vma->vm_mm->page_table_lock
 */
static inline void break_cow(struct vm_area_struct * vma, struct page * new_page, unsigned long address, 
		pte_t *page_table)
{
	pte_t entry;

	flush_cache_page(vma, address);
	entry = maybe_mkwrite(pte_mkdirty(mk_pte(new_page, vma->vm_page_prot)),
			      vma);
	ptep_establish(vma, address, page_table, entry);
	update_mmu_cache(vma, address, entry);
}

/*
 * This routine handles present pages, when users try to write
 * to a shared page. It is done by copying the page to a new address
 * and decrementing the shared-page counter for the old page.
 *
 * Goto-purists beware: the only reason for goto's here is that it results
 * in better assembly code.. The "default" path will see no jumps at all.
 *
 * Note that this routine assumes that the protection checks have been
 * done by the caller (the low-level page fault routine in most cases).
 * Thus we can safely just mark it writable once we've done any necessary
 * COW.
 *
 * We also mark the page dirty at this point even though the page will
 * change only once the write actually happens. This avoids a few races,
 * and potentially makes it more efficient.
 *
 * We hold the mm semaphore and the page_table_lock on entry and exit
 * with the page_table_lock released.
 */
static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma,
	unsigned long address, pte_t *page_table, pmd_t *pmd, pte_t pte)
{
	struct page *old_page, *new_page;
	unsigned long pfn = pte_pfn(pte);
	pte_t entry;

	if (unlikely(!pfn_valid(pfn))) {
		/*
		 * This should really halt the system so it can be debugged or
		 * at least the kernel stops what it's doing before it corrupts
		 * data, but for the moment just pretend this is OOM.
		 */
		pte_unmap(page_table);
		printk(KERN_ERR "do_wp_page: bogus page at address %08lx\n",
				address);
		spin_unlock(&mm->page_table_lock);
		return VM_FAULT_OOM;
	}
	old_page = pfn_to_page(pfn);

	if (!TestSetPageLocked(old_page)) {
		int reuse = can_share_swap_page(old_page);
		unlock_page(old_page);
		if (reuse) {
			flush_cache_page(vma, address);
			entry = maybe_mkwrite(pte_mkyoung(pte_mkdirty(pte)),
					      vma);
			ptep_set_access_flags(vma, address, page_table, entry, 1);
			update_mmu_cache(vma, address, entry);
			pte_unmap(page_table);
			spin_unlock(&mm->page_table_lock);
			return VM_FAULT_MINOR;
		}
	}
	pte_unmap(page_table);

	/*
	 * Ok, we need to copy. Oh, well..
	 */
	if (!PageReserved(old_page))
		page_cache_get(old_page);
	spin_unlock(&mm->page_table_lock);

	if (unlikely(anon_vma_prepare(vma)))
		goto no_new_page;
	new_page = alloc_page_vma(GFP_HIGHUSER, vma, address);
	if (!new_page)
		goto no_new_page;
	copy_cow_page(old_page,new_page,address);

	/*
	 * Re-check the pte - we dropped the lock
	 */
	spin_lock(&mm->page_table_lock);
	page_table = pte_offset_map(pmd, address);
	if (likely(pte_same(*page_table, pte))) {
		if (PageReserved(old_page))
			++mm->rss;
		else
			page_remove_rmap(old_page);
		break_cow(vma, new_page, address, page_table);
		lru_cache_add_active(new_page);
		page_add_anon_rmap(new_page, vma, address);

		/* Free the old page.. */
		new_page = old_page;
	}
	pte_unmap(page_table);
	page_cache_release(new_page);
	page_cache_release(old_page);
	spin_unlock(&mm->page_table_lock);
	return VM_FAULT_MINOR;

no_new_page:
	page_cache_release(old_page);
	return VM_FAULT_OOM;
}

/*
 * Helper function for unmap_mapping_range().
 */
static inline void unmap_mapping_range_list(struct prio_tree_root *root,
					    struct zap_details *details)
{
	struct vm_area_struct *vma;
	struct prio_tree_iter iter;
	pgoff_t vba, vea, zba, zea;

	vma_prio_tree_foreach(vma, &iter, root,
			details->first_index, details->last_index) {
		vba = vma->vm_pgoff;
		vea = vba + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) - 1;
		/* Assume for now that PAGE_CACHE_SHIFT == PAGE_SHIFT */
		zba = details->first_index;
		if (zba < vba)
			zba = vba;
		zea = details->last_index;
		if (zea > vea)
			zea = vea;
		zap_page_range(vma,
			((zba - vba) << PAGE_SHIFT) + vma->vm_start,
			(zea - zba + 1) << PAGE_SHIFT, details);
	}
}

/**
 * unmap_mapping_range - unmap the portion of all mmaps
 * in the specified address_space corresponding to the specified
 * page range in the underlying file.
 * @address_space: the address space containing mmaps to be unmapped.
 * @holebegin: byte in first page to unmap, relative to the start of
 * the underlying file.  This will be rounded down to a PAGE_SIZE
 * boundary.  Note that this is different from vmtruncate(), which
 * must keep the partial page.  In contrast, we must get rid of
 * partial pages.
 * @holelen: size of prospective hole in bytes.  This will be rounded
 * up to a PAGE_SIZE boundary.  A holelen of zero truncates to the
 * end of the file.
 * @even_cows: 1 when truncating a file, unmap even private COWed pages;
 * but 0 when invalidating pagecache, don't throw away private data.
 */
void unmap_mapping_range(struct address_space *mapping,
		loff_t const holebegin, loff_t const holelen, int even_cows)
{
	struct zap_details details;
	pgoff_t hba = holebegin >> PAGE_SHIFT;
	pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;

	/* Check for overflow. */
	if (sizeof(holelen) > sizeof(hlen)) {
		long long holeend =
			(holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
		if (holeend & ~(long long)ULONG_MAX)
			hlen = ULONG_MAX - hba + 1;
	}

	details.check_mapping = even_cows? NULL: mapping;
	details.nonlinear_vma = NULL;
	details.first_index = hba;
	details.last_index = hba + hlen - 1;
	details.atomic = 1;	/* A spinlock is held */
	if (details.last_index < details.first_index)
		details.last_index = ULONG_MAX;

	spin_lock(&mapping->i_mmap_lock);
	/* Protect against page fault */
	atomic_inc(&mapping->truncate_count);

	if (unlikely(!prio_tree_empty(&mapping->i_mmap)))
		unmap_mapping_range_list(&mapping->i_mmap, &details);

	/*
	 * In nonlinear VMAs there is no correspondence between virtual address
	 * offset and file offset.  So we must perform an exhaustive search
	 * across *all* the pages in each nonlinear VMA, not just the pages
	 * whose virtual address lies outside the file truncation point.
	 */
	if (unlikely(!list_empty(&mapping->i_mmap_nonlinear))) {
		struct vm_area_struct *vma;
		list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
						shared.vm_set.list) {
			details.nonlinear_vma = vma;
			zap_page_range(vma, vma->vm_start,
				vma->vm_end - vma->vm_start, &details);
		}
	}
	spin_unlock(&mapping->i_mmap_lock);
}
EXPORT_SYMBOL(unmap_mapping_range);

/*
 * Handle all mappings that got truncated by a "truncate()"
 * system call.
 *
 * NOTE! We have to be ready to update the memory sharing
 * between the file and the memory map for a potential last
 * incomplete page.  Ugly, but necessary.
 */
int vmtruncate(struct inode * inode, loff_t offset)
{
	struct address_space *mapping = inode->i_mapping;
	unsigned long limit;

	if (inode->i_size < offset)
		goto do_expand;
	/*
	 * truncation of in-use swapfiles is disallowed - it would cause
	 * subsequent swapout to scribble on the now-freed blocks.
	 */
	if (IS_SWAPFILE(inode))
		goto out_busy;
	i_size_write(inode, offset);
	unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
	truncate_inode_pages(mapping, offset);
	goto out_truncate;

do_expand:
	limit = current->rlim[RLIMIT_FSIZE].rlim_cur;
	if (limit != RLIM_INFINITY && offset > limit)
		goto out_sig;
	if (offset > inode->i_sb->s_maxbytes)
		goto out_big;
	i_size_write(inode, offset);

out_truncate:
	if (inode->i_op && inode->i_op->truncate)
		inode->i_op->truncate(inode);
	return 0;
out_sig:
	send_sig(SIGXFSZ, current, 0);
out_big:
	return -EFBIG;
out_busy:
	return -ETXTBSY;
}

EXPORT_SYMBOL(vmtruncate);

/* 
 * Primitive swap readahead code. We simply read an aligned block of
 * (1 << page_cluster) entries in the swap area. This method is chosen
 * because it doesn't cost us any seek time.  We also make sure to queue
 * the 'original' request together with the readahead ones...  
 *
 * This has been extended to use the NUMA policies from the mm triggering
 * the readahead.
 *
 * Caller must hold down_read on the vma->vm_mm if vma is not NULL.
 */
void swapin_readahead(swp_entry_t entry, unsigned long addr,struct vm_area_struct *vma)
{
#ifdef CONFIG_NUMA
	struct vm_area_struct *next_vma = vma ? vma->vm_next : NULL;
#endif
	int i, num;
	struct page *new_page;
	unsigned long offset;

	/*
	 * Get the number of handles we should do readahead io to.
	 */
	num = valid_swaphandles(entry, &offset);
	for (i = 0; i < num; offset++, i++) {
		/* Ok, do the async read-ahead now */
		new_page = read_swap_cache_async(swp_entry(swp_type(entry),
							   offset), vma, addr);
		if (!new_page)
			break;
		page_cache_release(new_page);
#ifdef CONFIG_NUMA
		/*
		 * Find the next applicable VMA for the NUMA policy.
		 */
		addr += PAGE_SIZE;
		if (addr == 0)
			vma = NULL;
		if (vma) {
			if (addr >= vma->vm_end) {
				vma = next_vma;
				next_vma = vma ? vma->vm_next : NULL;
			}
			if (vma && addr < vma->vm_start)
				vma = NULL;
		} else {
			if (next_vma && addr >= next_vma->vm_start) {
				vma = next_vma;
				next_vma = vma->vm_next;
			}
		}
#endif
	}
	lru_add_drain();	/* Push any new pages onto the LRU now */
}

/*
 * We hold the mm semaphore and the page_table_lock on entry and
 * should release the pagetable lock on exit..
 */
static int do_swap_page(struct mm_struct * mm,
	struct vm_area_struct * vma, unsigned long address,
	pte_t *page_table, pmd_t *pmd, pte_t orig_pte, int write_access)
{
	struct page *page;
	swp_entry_t entry = pte_to_swp_entry(orig_pte);
	pte_t pte;
	int ret = VM_FAULT_MINOR;

	pte_unmap(page_table);
	spin_unlock(&mm->page_table_lock);
	page = lookup_swap_cache(entry);
	if (!page) {
 		swapin_readahead(entry, address, vma);
 		page = read_swap_cache_async(entry, vma, address);
		if (!page) {
			/*
			 * Back out if somebody else faulted in this pte while
			 * we released the page table lock.
			 */
			spin_lock(&mm->page_table_lock);
			page_table = pte_offset_map(pmd, address);
			if (likely(pte_same(*page_table, orig_pte)))
				ret = VM_FAULT_OOM;
			else
				ret = VM_FAULT_MINOR;
			pte_unmap(page_table);
			spin_unlock(&mm->page_table_lock);
			goto out;
		}

		/* Had to read the page from swap area: Major fault */
		ret = VM_FAULT_MAJOR;
		inc_page_state(pgmajfault);
		grab_swap_token();
	}

	mark_page_accessed(page);
	lock_page(page);

	/*
	 * Back out if somebody else faulted in this pte while we
	 * released the page table lock.
	 */
	spin_lock(&mm->page_table_lock);
	page_table = pte_offset_map(pmd, address);
	if (unlikely(!pte_same(*page_table, orig_pte))) {
		pte_unmap(page_table);
		spin_unlock(&mm->page_table_lock);
		unlock_page(page);
		page_cache_release(page);
		ret = VM_FAULT_MINOR;
		goto out;
	}

	/* The page isn't present yet, go ahead with the fault. */
		
	swap_free(entry);
	if (vm_swap_full())
		remove_exclusive_swap_page(page);

	mm->rss++;
	pte = mk_pte(page, vma->vm_page_prot);
	if (write_access && can_share_swap_page(page)) {
		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
		write_access = 0;
	}
	unlock_page(page);

	flush_icache_page(vma, page);
	set_pte(page_table, pte);
	page_add_anon_rmap(page, vma, address);

	if (write_access) {
		if (do_wp_page(mm, vma, address,
				page_table, pmd, pte) == VM_FAULT_OOM)
			ret = VM_FAULT_OOM;
		goto out;
	}

	/* No need to invalidate - it was non-present before */
	update_mmu_cache(vma, address, pte);
	pte_unmap(page_table);
	spin_unlock(&mm->page_table_lock);
out:
	return ret;
}

/*
 * We are called with the MM semaphore and page_table_lock
 * spinlock held to protect against concurrent faults in
 * multithreaded programs. 
 */
static int
do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
		pte_t *page_table, pmd_t *pmd, int write_access,
		unsigned long addr)
{
	pte_t entry;
	struct page * page = ZERO_PAGE(addr);

	/* Read-only mapping of ZERO_PAGE. */
	entry = pte_wrprotect(mk_pte(ZERO_PAGE(addr), vma->vm_page_prot));

	/* ..except if it's a write access */
	if (write_access) {
		/* Allocate our own private page. */
		pte_unmap(page_table);
		spin_unlock(&mm->page_table_lock);

		if (unlikely(anon_vma_prepare(vma)))
			goto no_mem;
		page = alloc_page_vma(GFP_HIGHUSER, vma, addr);
		if (!page)
			goto no_mem;
		clear_user_highpage(page, addr);

		spin_lock(&mm->page_table_lock);
		page_table = pte_offset_map(pmd, addr);

		if (!pte_none(*page_table)) {
			pte_unmap(page_table);
			page_cache_release(page);
			spin_unlock(&mm->page_table_lock);
			goto out;
		}
		mm->rss++;
		entry = maybe_mkwrite(pte_mkdirty(mk_pte(page,
							 vma->vm_page_prot)),
				      vma);
		lru_cache_add_active(page);
		mark_page_accessed(page);
		page_add_anon_rmap(page, vma, addr);
	}

	set_pte(page_table, entry);
	pte_unmap(page_table);

	/* No need to invalidate - it was non-present before */
	update_mmu_cache(vma, addr, entry);
	spin_unlock(&mm->page_table_lock);
out:
	return VM_FAULT_MINOR;
no_mem:
	return VM_FAULT_OOM;
}

/*
 * do_no_page() tries to create a new page mapping. It aggressively
 * tries to share with existing pages, but makes a separate copy if
 * the "write_access" parameter is true in order to avoid the next
 * page fault.
 *
 * As this is called only for pages that do not currently exist, we
 * do not need to flush old virtual caches or the TLB.
 *
 * This is called with the MM semaphore held and the page table
 * spinlock held. Exit with the spinlock released.
 */
static int
do_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
	unsigned long address, int write_access, pte_t *page_table, pmd_t *pmd)
{
	struct page * new_page;
	struct address_space *mapping = NULL;
	pte_t entry;
	int sequence = 0;
	int ret = VM_FAULT_MINOR;
	int anon = 0;

	if (!vma->vm_ops || !vma->vm_ops->nopage)
		return do_anonymous_page(mm, vma, page_table,
					pmd, write_access, address);
	pte_unmap(page_table);
	spin_unlock(&mm->page_table_lock);

	if (vma->vm_file) {
		mapping = vma->vm_file->f_mapping;
		sequence = atomic_read(&mapping->truncate_count);
	}
	smp_rmb();  /* Prevent CPU from reordering lock-free ->nopage() */
retry:
	new_page = vma->vm_ops->nopage(vma, address & PAGE_MASK, &ret);

	/* no page was available -- either SIGBUS or OOM */
	if (new_page == NOPAGE_SIGBUS)
		return VM_FAULT_SIGBUS;
	if (new_page == NOPAGE_OOM)
		return VM_FAULT_OOM;

	/*
	 * Should we do an early C-O-W break?
	 */
	if (write_access && !(vma->vm_flags & VM_SHARED)) {
		struct page *page;

		if (unlikely(anon_vma_prepare(vma)))
			goto oom;
		page = alloc_page_vma(GFP_HIGHUSER, vma, address);
		if (!page)
			goto oom;
		copy_user_highpage(page, new_page, address);
		page_cache_release(new_page);
		new_page = page;
		anon = 1;
	}

	spin_lock(&mm->page_table_lock);
	/*
	 * For a file-backed vma, someone could have truncated or otherwise
	 * invalidated this page.  If unmap_mapping_range got called,
	 * retry getting the page.
	 */
	if (mapping &&
	      (unlikely(sequence != atomic_read(&mapping->truncate_count)))) {
		sequence = atomic_read(&mapping->truncate_count);
		spin_unlock(&mm->page_table_lock);
		page_cache_release(new_page);
		goto retry;
	}
	page_table = pte_offset_map(pmd, address);

	/*
	 * This silly early PAGE_DIRTY setting removes a race
	 * due to the bad i386 page protection. But it's valid
	 * for other architectures too.
	 *
	 * Note that if write_access is true, we either now have
	 * an exclusive copy of the page, or this is a shared mapping,
	 * so we can make it writable and dirty to avoid having to
	 * handle that later.
	 */
	/* Only go through if we didn't race with anybody else... */
	if (pte_none(*page_table)) {
		if (!PageReserved(new_page))
			++mm->rss;
		flush_icache_page(vma, new_page);
		entry = mk_pte(new_page, vma->vm_page_prot);
		if (write_access)
			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
		set_pte(page_table, entry);
		if (anon) {
			lru_cache_add_active(new_page);
			page_add_anon_rmap(new_page, vma, address);
		} else
			page_add_file_rmap(new_page);
		pte_unmap(page_table);
	} else {
		/* One of our sibling threads was faster, back out. */
		pte_unmap(page_table);
		page_cache_release(new_page);
		spin_unlock(&mm->page_table_lock);
		goto out;
	}

	/* no need to invalidate: a not-present page shouldn't be cached */
	update_mmu_cache(vma, address, entry);
	spin_unlock(&mm->page_table_lock);
out:
	return ret;
oom:
	page_cache_release(new_page);
	ret = VM_FAULT_OOM;
	goto out;
}

/*
 * Fault of a previously existing named mapping. Repopulate the pte
 * from the encoded file_pte if possible. This enables swappable
 * nonlinear vmas.
 */
static int do_file_page(struct mm_struct * mm, struct vm_area_struct * vma,
	unsigned long address, int write_access, pte_t *pte, pmd_t *pmd)
{
	unsigned long pgoff;
	int err;

	BUG_ON(!vma->vm_ops || !vma->vm_ops->nopage);
	/*
	 * Fall back to the linear mapping if the fs does not support
	 * ->populate:
	 */
	if (!vma->vm_ops || !vma->vm_ops->populate || 
			(write_access && !(vma->vm_flags & VM_SHARED))) {
		pte_clear(pte);
		return do_no_page(mm, vma, address, write_access, pte, pmd);
	}

	pgoff = pte_to_pgoff(*pte);

	pte_unmap(pte);
	spin_unlock(&mm->page_table_lock);

	err = vma->vm_ops->populate(vma, address & PAGE_MASK, PAGE_SIZE, vma->vm_page_prot, pgoff, 0);
	if (err == -ENOMEM)
		return VM_FAULT_OOM;
	if (err)
		return VM_FAULT_SIGBUS;
	return VM_FAULT_MAJOR;
}

/*
 * These routines also need to handle stuff like marking pages dirty
 * and/or accessed for architectures that don't do it in hardware (most
 * RISC architectures).  The early dirtying is also good on the i386.
 *
 * There is also a hook called "update_mmu_cache()" that architectures
 * with external mmu caches can use to update those (ie the Sparc or
 * PowerPC hashed page tables that act as extended TLBs).
 *
 * Note the "page_table_lock". It is to protect against kswapd removing
 * pages from under us. Note that kswapd only ever _removes_ pages, never
 * adds them. As such, once we have noticed that the page is not present,
 * we can drop the lock early.
 *
 * The adding of pages is protected by the MM semaphore (which we hold),
 * so we don't need to worry about a page being suddenly been added into
 * our VM.
 *
 * We enter with the pagetable spinlock held, we are supposed to
 * release it when done.
 */
static inline int handle_pte_fault(struct mm_struct *mm,
	struct vm_area_struct * vma, unsigned long address,
	int write_access, pte_t *pte, pmd_t *pmd)
{
	pte_t entry;

	entry = *pte;
	if (!pte_present(entry)) {
		/*
		 * If it truly wasn't present, we know that kswapd
		 * and the PTE updates will not touch it later. So
		 * drop the lock.
		 */
		if (pte_none(entry))
			return do_no_page(mm, vma, address, write_access, pte, pmd);
		if (pte_file(entry))
			return do_file_page(mm, vma, address, write_access, pte, pmd);
		return do_swap_page(mm, vma, address, pte, pmd, entry, write_access);
	}

	if (write_access) {
		if (!pte_write(entry))
			return do_wp_page(mm, vma, address, pte, pmd, entry);

		entry = pte_mkdirty(entry);
	}
	entry = pte_mkyoung(entry);
	ptep_set_access_flags(vma, address, pte, entry, write_access);
	update_mmu_cache(vma, address, entry);
	pte_unmap(pte);
	spin_unlock(&mm->page_table_lock);
	return VM_FAULT_MINOR;
}

/*
 * By the time we get here, we already hold the mm semaphore
 */
int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct * vma,
	unsigned long address, int write_access)
{
	pgd_t *pgd;
	pmd_t *pmd;

	__set_current_state(TASK_RUNNING);
	pgd = pgd_offset(mm, address);

	inc_page_state(pgfault);

	if (is_vm_hugetlb_page(vma))
		return VM_FAULT_SIGBUS;	/* mapping truncation does this. */

	/*
	 * We need the page table lock to synchronize with kswapd
	 * and the SMP-safe atomic PTE updates.
	 */
	spin_lock(&mm->page_table_lock);
	pmd = pmd_alloc(mm, pgd, address);

	if (pmd) {
		pte_t * pte = pte_alloc_map(mm, pmd, address);
		if (pte)
			return handle_pte_fault(mm, vma, address, write_access, pte, pmd);
	}
	spin_unlock(&mm->page_table_lock);
	return VM_FAULT_OOM;
}

/*
 * Allocate page middle directory.
 *
 * We've already handled the fast-path in-line, and we own the
 * page table lock.
 *
 * On a two-level page table, this ends up actually being entirely
 * optimized away.
 */
pmd_t fastcall *__pmd_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
{
	pmd_t *new;

	spin_unlock(&mm->page_table_lock);
	new = pmd_alloc_one(mm, address);
	spin_lock(&mm->page_table_lock);
	if (!new)
		return NULL;

	/*
	 * Because we dropped the lock, we should re-check the
	 * entry, as somebody else could have populated it..
	 */
	if (pgd_present(*pgd)) {
		pmd_free(new);
		goto out;
	}
	pgd_populate(mm, pgd, new);
out:
	return pmd_offset(pgd, address);
}

int make_pages_present(unsigned long addr, unsigned long end)
{
	int ret, len, write;
	struct vm_area_struct * vma;

	vma = find_vma(current->mm, addr);
	if (!vma)
		return -1;
	write = (vma->vm_flags & VM_WRITE) != 0;
	if (addr >= end)
		BUG();
	if (end > vma->vm_end)
		BUG();
	len = (end+PAGE_SIZE-1)/PAGE_SIZE-addr/PAGE_SIZE;
	ret = get_user_pages(current, current->mm, addr,
			len, write, 0, NULL, NULL);
	if (ret < 0)
		return ret;
	return ret == len ? 0 : -1;
}

/* 
 * Map a vmalloc()-space virtual address to the physical page.
 */
struct page * vmalloc_to_page(void * vmalloc_addr)
{
	unsigned long addr = (unsigned long) vmalloc_addr;
	struct page *page = NULL;
	pgd_t *pgd = pgd_offset_k(addr);
	pmd_t *pmd;
	pte_t *ptep, pte;
  
	if (!pgd_none(*pgd)) {
		pmd = pmd_offset(pgd, addr);
		if (!pmd_none(*pmd)) {
			preempt_disable();
			ptep = pte_offset_map(pmd, addr);
			pte = *ptep;
			if (pte_present(pte))
				page = pte_page(pte);
			pte_unmap(ptep);
			preempt_enable();
		}
	}
	return page;
}

EXPORT_SYMBOL(vmalloc_to_page);

#if !defined(CONFIG_ARCH_GATE_AREA)

#if defined(AT_SYSINFO_EHDR)
struct vm_area_struct gate_vma;

static int __init gate_vma_init(void)
{
	gate_vma.vm_mm = NULL;
	gate_vma.vm_start = FIXADDR_USER_START;
	gate_vma.vm_end = FIXADDR_USER_END;
	gate_vma.vm_page_prot = PAGE_READONLY;
	gate_vma.vm_flags = 0;
	return 0;
}
__initcall(gate_vma_init);
#endif

struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
{
#ifdef AT_SYSINFO_EHDR
	return &gate_vma;
#else
	return NULL;
#endif
}

int in_gate_area(struct task_struct *task, unsigned long addr)
{
#ifdef AT_SYSINFO_EHDR
	if ((addr >= FIXADDR_USER_START) && (addr < FIXADDR_USER_END))
		return 1;
#endif
	return 0;
}

#endif