aboutsummaryrefslogtreecommitdiffstats
path: root/mm/hugetlb.c
blob: 4cf7a90e91402cf5edf805b31e2c40e57ef798ff (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
/*
 * Generic hugetlb support.
 * (C) William Irwin, April 2004
 */
#include <linux/gfp.h>
#include <linux/list.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/sysctl.h>
#include <linux/highmem.h>
#include <linux/nodemask.h>
#include <linux/pagemap.h>
#include <linux/mempolicy.h>
#include <linux/cpuset.h>
#include <linux/mutex.h>

#include <asm/page.h>
#include <asm/pgtable.h>

#include <linux/hugetlb.h>
#include "internal.h"

const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL;
static gfp_t htlb_alloc_mask = GFP_HIGHUSER;
unsigned long hugepages_treat_as_movable;

static int max_hstate;
unsigned int default_hstate_idx;
struct hstate hstates[HUGE_MAX_HSTATE];

/* for command line parsing */
static struct hstate * __initdata parsed_hstate;
static unsigned long __initdata default_hstate_max_huge_pages;

#define for_each_hstate(h) \
	for ((h) = hstates; (h) < &hstates[max_hstate]; (h)++)

/*
 * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages
 */
static DEFINE_SPINLOCK(hugetlb_lock);

/*
 * Region tracking -- allows tracking of reservations and instantiated pages
 *                    across the pages in a mapping.
 *
 * The region data structures are protected by a combination of the mmap_sem
 * and the hugetlb_instantion_mutex.  To access or modify a region the caller
 * must either hold the mmap_sem for write, or the mmap_sem for read and
 * the hugetlb_instantiation mutex:
 *
 * 	down_write(&mm->mmap_sem);
 * or
 * 	down_read(&mm->mmap_sem);
 * 	mutex_lock(&hugetlb_instantiation_mutex);
 */
struct file_region {
	struct list_head link;
	long from;
	long to;
};

static long region_add(struct list_head *head, long f, long t)
{
	struct file_region *rg, *nrg, *trg;

	/* Locate the region we are either in or before. */
	list_for_each_entry(rg, head, link)
		if (f <= rg->to)
			break;

	/* Round our left edge to the current segment if it encloses us. */
	if (f > rg->from)
		f = rg->from;

	/* Check for and consume any regions we now overlap with. */
	nrg = rg;
	list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
		if (&rg->link == head)
			break;
		if (rg->from > t)
			break;

		/* If this area reaches higher then extend our area to
		 * include it completely.  If this is not the first area
		 * which we intend to reuse, free it. */
		if (rg->to > t)
			t = rg->to;
		if (rg != nrg) {
			list_del(&rg->link);
			kfree(rg);
		}
	}
	nrg->from = f;
	nrg->to = t;
	return 0;
}

static long region_chg(struct list_head *head, long f, long t)
{
	struct file_region *rg, *nrg;
	long chg = 0;

	/* Locate the region we are before or in. */
	list_for_each_entry(rg, head, link)
		if (f <= rg->to)
			break;

	/* If we are below the current region then a new region is required.
	 * Subtle, allocate a new region at the position but make it zero
	 * size such that we can guarantee to record the reservation. */
	if (&rg->link == head || t < rg->from) {
		nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
		if (!nrg)
			return -ENOMEM;
		nrg->from = f;
		nrg->to   = f;
		INIT_LIST_HEAD(&nrg->link);
		list_add(&nrg->link, rg->link.prev);

		return t - f;
	}

	/* Round our left edge to the current segment if it encloses us. */
	if (f > rg->from)
		f = rg->from;
	chg = t - f;

	/* Check for and consume any regions we now overlap with. */
	list_for_each_entry(rg, rg->link.prev, link) {
		if (&rg->link == head)
			break;
		if (rg->from > t)
			return chg;

		/* We overlap with this area, if it extends futher than
		 * us then we must extend ourselves.  Account for its
		 * existing reservation. */
		if (rg->to > t) {
			chg += rg->to - t;
			t = rg->to;
		}
		chg -= rg->to - rg->from;
	}
	return chg;
}

static long region_truncate(struct list_head *head, long end)
{
	struct file_region *rg, *trg;
	long chg = 0;

	/* Locate the region we are either in or before. */
	list_for_each_entry(rg, head, link)
		if (end <= rg->to)
			break;
	if (&rg->link == head)
		return 0;

	/* If we are in the middle of a region then adjust it. */
	if (end > rg->from) {
		chg = rg->to - end;
		rg->to = end;
		rg = list_entry(rg->link.next, typeof(*rg), link);
	}

	/* Drop any remaining regions. */
	list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
		if (&rg->link == head)
			break;
		chg += rg->to - rg->from;
		list_del(&rg->link);
		kfree(rg);
	}
	return chg;
}

static long region_count(struct list_head *head, long f, long t)
{
	struct file_region *rg;
	long chg = 0;

	/* Locate each segment we overlap with, and count that overlap. */
	list_for_each_entry(rg, head, link) {
		int seg_from;
		int seg_to;

		if (rg->to <= f)
			continue;
		if (rg->from >= t)
			break;

		seg_from = max(rg->from, f);
		seg_to = min(rg->to, t);

		chg += seg_to - seg_from;
	}

	return chg;
}

/*
 * Convert the address within this vma to the page offset within
 * the mapping, in pagecache page units; huge pages here.
 */
static pgoff_t vma_hugecache_offset(struct hstate *h,
			struct vm_area_struct *vma, unsigned long address)
{
	return ((address - vma->vm_start) >> huge_page_shift(h)) +
			(vma->vm_pgoff >> huge_page_order(h));
}

/*
 * Flags for MAP_PRIVATE reservations.  These are stored in the bottom
 * bits of the reservation map pointer, which are always clear due to
 * alignment.
 */
#define HPAGE_RESV_OWNER    (1UL << 0)
#define HPAGE_RESV_UNMAPPED (1UL << 1)
#define HPAGE_RESV_MASK (HPAGE_RESV_OWNER | HPAGE_RESV_UNMAPPED)

/*
 * These helpers are used to track how many pages are reserved for
 * faults in a MAP_PRIVATE mapping. Only the process that called mmap()
 * is guaranteed to have their future faults succeed.
 *
 * With the exception of reset_vma_resv_huge_pages() which is called at fork(),
 * the reserve counters are updated with the hugetlb_lock held. It is safe
 * to reset the VMA at fork() time as it is not in use yet and there is no
 * chance of the global counters getting corrupted as a result of the values.
 *
 * The private mapping reservation is represented in a subtly different
 * manner to a shared mapping.  A shared mapping has a region map associated
 * with the underlying file, this region map represents the backing file
 * pages which have ever had a reservation assigned which this persists even
 * after the page is instantiated.  A private mapping has a region map
 * associated with the original mmap which is attached to all VMAs which
 * reference it, this region map represents those offsets which have consumed
 * reservation ie. where pages have been instantiated.
 */
static unsigned long get_vma_private_data(struct vm_area_struct *vma)
{
	return (unsigned long)vma->vm_private_data;
}

static void set_vma_private_data(struct vm_area_struct *vma,
							unsigned long value)
{
	vma->vm_private_data = (void *)value;
}

struct resv_map {
	struct kref refs;
	struct list_head regions;
};

struct resv_map *resv_map_alloc(void)
{
	struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL);
	if (!resv_map)
		return NULL;

	kref_init(&resv_map->refs);
	INIT_LIST_HEAD(&resv_map->regions);

	return resv_map;
}

void resv_map_release(struct kref *ref)
{
	struct resv_map *resv_map = container_of(ref, struct resv_map, refs);

	/* Clear out any active regions before we release the map. */
	region_truncate(&resv_map->regions, 0);
	kfree(resv_map);
}

static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
{
	VM_BUG_ON(!is_vm_hugetlb_page(vma));
	if (!(vma->vm_flags & VM_SHARED))
		return (struct resv_map *)(get_vma_private_data(vma) &
							~HPAGE_RESV_MASK);
	return 0;
}

static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map)
{
	VM_BUG_ON(!is_vm_hugetlb_page(vma));
	VM_BUG_ON(vma->vm_flags & VM_SHARED);

	set_vma_private_data(vma, (get_vma_private_data(vma) &
				HPAGE_RESV_MASK) | (unsigned long)map);
}

static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags)
{
	VM_BUG_ON(!is_vm_hugetlb_page(vma));
	VM_BUG_ON(vma->vm_flags & VM_SHARED);

	set_vma_private_data(vma, get_vma_private_data(vma) | flags);
}

static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag)
{
	VM_BUG_ON(!is_vm_hugetlb_page(vma));

	return (get_vma_private_data(vma) & flag) != 0;
}

/* Decrement the reserved pages in the hugepage pool by one */
static void decrement_hugepage_resv_vma(struct hstate *h,
			struct vm_area_struct *vma)
{
	if (vma->vm_flags & VM_NORESERVE)
		return;

	if (vma->vm_flags & VM_SHARED) {
		/* Shared mappings always use reserves */
		h->resv_huge_pages--;
	} else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
		/*
		 * Only the process that called mmap() has reserves for
		 * private mappings.
		 */
		h->resv_huge_pages--;
	}
}

/* Reset counters to 0 and clear all HPAGE_RESV_* flags */
void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
{
	VM_BUG_ON(!is_vm_hugetlb_page(vma));
	if (!(vma->vm_flags & VM_SHARED))
		vma->vm_private_data = (void *)0;
}

/* Returns true if the VMA has associated reserve pages */
static int vma_has_private_reserves(struct vm_area_struct *vma)
{
	if (vma->vm_flags & VM_SHARED)
		return 0;
	if (!is_vma_resv_set(vma, HPAGE_RESV_OWNER))
		return 0;
	return 1;
}

static void clear_huge_page(struct page *page,
			unsigned long addr, unsigned long sz)
{
	int i;

	might_sleep();
	for (i = 0; i < sz/PAGE_SIZE; i++) {
		cond_resched();
		clear_user_highpage(page + i, addr + i * PAGE_SIZE);
	}
}

static void copy_huge_page(struct page *dst, struct page *src,
			   unsigned long addr, struct vm_area_struct *vma)
{
	int i;
	struct hstate *h = hstate_vma(vma);

	might_sleep();
	for (i = 0; i < pages_per_huge_page(h); i++) {
		cond_resched();
		copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma);
	}
}

static void enqueue_huge_page(struct hstate *h, struct page *page)
{
	int nid = page_to_nid(page);
	list_add(&page->lru, &h->hugepage_freelists[nid]);
	h->free_huge_pages++;
	h->free_huge_pages_node[nid]++;
}

static struct page *dequeue_huge_page(struct hstate *h)
{
	int nid;
	struct page *page = NULL;

	for (nid = 0; nid < MAX_NUMNODES; ++nid) {
		if (!list_empty(&h->hugepage_freelists[nid])) {
			page = list_entry(h->hugepage_freelists[nid].next,
					  struct page, lru);
			list_del(&page->lru);
			h->free_huge_pages--;
			h->free_huge_pages_node[nid]--;
			break;
		}
	}
	return page;
}

static struct page *dequeue_huge_page_vma(struct hstate *h,
				struct vm_area_struct *vma,
				unsigned long address, int avoid_reserve)
{
	int nid;
	struct page *page = NULL;
	struct mempolicy *mpol;
	nodemask_t *nodemask;
	struct zonelist *zonelist = huge_zonelist(vma, address,
					htlb_alloc_mask, &mpol, &nodemask);
	struct zone *zone;
	struct zoneref *z;

	/*
	 * A child process with MAP_PRIVATE mappings created by their parent
	 * have no page reserves. This check ensures that reservations are
	 * not "stolen". The child may still get SIGKILLed
	 */
	if (!vma_has_private_reserves(vma) &&
			h->free_huge_pages - h->resv_huge_pages == 0)
		return NULL;

	/* If reserves cannot be used, ensure enough pages are in the pool */
	if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0)
		return NULL;

	for_each_zone_zonelist_nodemask(zone, z, zonelist,
						MAX_NR_ZONES - 1, nodemask) {
		nid = zone_to_nid(zone);
		if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask) &&
		    !list_empty(&h->hugepage_freelists[nid])) {
			page = list_entry(h->hugepage_freelists[nid].next,
					  struct page, lru);
			list_del(&page->lru);
			h->free_huge_pages--;
			h->free_huge_pages_node[nid]--;

			if (!avoid_reserve)
				decrement_hugepage_resv_vma(h, vma);

			break;
		}
	}
	mpol_cond_put(mpol);
	return page;
}

static void update_and_free_page(struct hstate *h, struct page *page)
{
	int i;

	h->nr_huge_pages--;
	h->nr_huge_pages_node[page_to_nid(page)]--;
	for (i = 0; i < pages_per_huge_page(h); i++) {
		page[i].flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced |
				1 << PG_dirty | 1 << PG_active | 1 << PG_reserved |
				1 << PG_private | 1<< PG_writeback);
	}
	set_compound_page_dtor(page, NULL);
	set_page_refcounted(page);
	arch_release_hugepage(page);
	__free_pages(page, huge_page_order(h));
}

struct hstate *size_to_hstate(unsigned long size)
{
	struct hstate *h;

	for_each_hstate(h) {
		if (huge_page_size(h) == size)
			return h;
	}
	return NULL;
}

static void free_huge_page(struct page *page)
{
	/*
	 * Can't pass hstate in here because it is called from the
	 * compound page destructor.
	 */
	struct hstate *h = page_hstate(page);
	int nid = page_to_nid(page);
	struct address_space *mapping;

	mapping = (struct address_space *) page_private(page);
	set_page_private(page, 0);
	BUG_ON(page_count(page));
	INIT_LIST_HEAD(&page->lru);

	spin_lock(&hugetlb_lock);
	if (h->surplus_huge_pages_node[nid]) {
		update_and_free_page(h, page);
		h->surplus_huge_pages--;
		h->surplus_huge_pages_node[nid]--;
	} else {
		enqueue_huge_page(h, page);
	}
	spin_unlock(&hugetlb_lock);
	if (mapping)
		hugetlb_put_quota(mapping, 1);
}

/*
 * Increment or decrement surplus_huge_pages.  Keep node-specific counters
 * balanced by operating on them in a round-robin fashion.
 * Returns 1 if an adjustment was made.
 */
static int adjust_pool_surplus(struct hstate *h, int delta)
{
	static int prev_nid;
	int nid = prev_nid;
	int ret = 0;

	VM_BUG_ON(delta != -1 && delta != 1);
	do {
		nid = next_node(nid, node_online_map);
		if (nid == MAX_NUMNODES)
			nid = first_node(node_online_map);

		/* To shrink on this node, there must be a surplus page */
		if (delta < 0 && !h->surplus_huge_pages_node[nid])
			continue;
		/* Surplus cannot exceed the total number of pages */
		if (delta > 0 && h->surplus_huge_pages_node[nid] >=
						h->nr_huge_pages_node[nid])
			continue;

		h->surplus_huge_pages += delta;
		h->surplus_huge_pages_node[nid] += delta;
		ret = 1;
		break;
	} while (nid != prev_nid);

	prev_nid = nid;
	return ret;
}

static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
{
	set_compound_page_dtor(page, free_huge_page);
	spin_lock(&hugetlb_lock);
	h->nr_huge_pages++;
	h->nr_huge_pages_node[nid]++;
	spin_unlock(&hugetlb_lock);
	put_page(page); /* free it into the hugepage allocator */
}

static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
{
	struct page *page;

	page = alloc_pages_node(nid,
		htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
						__GFP_REPEAT|__GFP_NOWARN,
		huge_page_order(h));
	if (page) {
		if (arch_prepare_hugepage(page)) {
			__free_pages(page, HUGETLB_PAGE_ORDER);
			return NULL;
		}
		prep_new_huge_page(h, page, nid);
	}

	return page;
}

static int alloc_fresh_huge_page(struct hstate *h)
{
	struct page *page;
	int start_nid;
	int next_nid;
	int ret = 0;

	start_nid = h->hugetlb_next_nid;

	do {
		page = alloc_fresh_huge_page_node(h, h->hugetlb_next_nid);
		if (page)
			ret = 1;
		/*
		 * Use a helper variable to find the next node and then
		 * copy it back to hugetlb_next_nid afterwards:
		 * otherwise there's a window in which a racer might
		 * pass invalid nid MAX_NUMNODES to alloc_pages_node.
		 * But we don't need to use a spin_lock here: it really
		 * doesn't matter if occasionally a racer chooses the
		 * same nid as we do.  Move nid forward in the mask even
		 * if we just successfully allocated a hugepage so that
		 * the next caller gets hugepages on the next node.
		 */
		next_nid = next_node(h->hugetlb_next_nid, node_online_map);
		if (next_nid == MAX_NUMNODES)
			next_nid = first_node(node_online_map);
		h->hugetlb_next_nid = next_nid;
	} while (!page && h->hugetlb_next_nid != start_nid);

	if (ret)
		count_vm_event(HTLB_BUDDY_PGALLOC);
	else
		count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);

	return ret;
}

static struct page *alloc_buddy_huge_page(struct hstate *h,
			struct vm_area_struct *vma, unsigned long address)
{
	struct page *page;
	unsigned int nid;

	/*
	 * Assume we will successfully allocate the surplus page to
	 * prevent racing processes from causing the surplus to exceed
	 * overcommit
	 *
	 * This however introduces a different race, where a process B
	 * tries to grow the static hugepage pool while alloc_pages() is
	 * called by process A. B will only examine the per-node
	 * counters in determining if surplus huge pages can be
	 * converted to normal huge pages in adjust_pool_surplus(). A
	 * won't be able to increment the per-node counter, until the
	 * lock is dropped by B, but B doesn't drop hugetlb_lock until
	 * no more huge pages can be converted from surplus to normal
	 * state (and doesn't try to convert again). Thus, we have a
	 * case where a surplus huge page exists, the pool is grown, and
	 * the surplus huge page still exists after, even though it
	 * should just have been converted to a normal huge page. This
	 * does not leak memory, though, as the hugepage will be freed
	 * once it is out of use. It also does not allow the counters to
	 * go out of whack in adjust_pool_surplus() as we don't modify
	 * the node values until we've gotten the hugepage and only the
	 * per-node value is checked there.
	 */
	spin_lock(&hugetlb_lock);
	if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) {
		spin_unlock(&hugetlb_lock);
		return NULL;
	} else {
		h->nr_huge_pages++;
		h->surplus_huge_pages++;
	}
	spin_unlock(&hugetlb_lock);

	page = alloc_pages(htlb_alloc_mask|__GFP_COMP|
					__GFP_REPEAT|__GFP_NOWARN,
					huge_page_order(h));

	spin_lock(&hugetlb_lock);
	if (page) {
		/*
		 * This page is now managed by the hugetlb allocator and has
		 * no users -- drop the buddy allocator's reference.
		 */
		put_page_testzero(page);
		VM_BUG_ON(page_count(page));
		nid = page_to_nid(page);
		set_compound_page_dtor(page, free_huge_page);
		/*
		 * We incremented the global counters already
		 */
		h->nr_huge_pages_node[nid]++;
		h->surplus_huge_pages_node[nid]++;
		__count_vm_event(HTLB_BUDDY_PGALLOC);
	} else {
		h->nr_huge_pages--;
		h->surplus_huge_pages--;
		__count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
	}
	spin_unlock(&hugetlb_lock);

	return page;
}

/*
 * Increase the hugetlb pool such that it can accomodate a reservation
 * of size 'delta'.
 */
static int gather_surplus_pages(struct hstate *h, int delta)
{
	struct list_head surplus_list;
	struct page *page, *tmp;
	int ret, i;
	int needed, allocated;

	needed = (h->resv_huge_pages + delta) - h->free_huge_pages;
	if (needed <= 0) {
		h->resv_huge_pages += delta;
		return 0;
	}

	allocated = 0;
	INIT_LIST_HEAD(&surplus_list);

	ret = -ENOMEM;
retry:
	spin_unlock(&hugetlb_lock);
	for (i = 0; i < needed; i++) {
		page = alloc_buddy_huge_page(h, NULL, 0);
		if (!page) {
			/*
			 * We were not able to allocate enough pages to
			 * satisfy the entire reservation so we free what
			 * we've allocated so far.
			 */
			spin_lock(&hugetlb_lock);
			needed = 0;
			goto free;
		}

		list_add(&page->lru, &surplus_list);
	}
	allocated += needed;

	/*
	 * After retaking hugetlb_lock, we need to recalculate 'needed'
	 * because either resv_huge_pages or free_huge_pages may have changed.
	 */
	spin_lock(&hugetlb_lock);
	needed = (h->resv_huge_pages + delta) -
			(h->free_huge_pages + allocated);
	if (needed > 0)
		goto retry;

	/*
	 * The surplus_list now contains _at_least_ the number of extra pages
	 * needed to accomodate the reservation.  Add the appropriate number
	 * of pages to the hugetlb pool and free the extras back to the buddy
	 * allocator.  Commit the entire reservation here to prevent another
	 * process from stealing the pages as they are added to the pool but
	 * before they are reserved.
	 */
	needed += allocated;
	h->resv_huge_pages += delta;
	ret = 0;
free:
	/* Free the needed pages to the hugetlb pool */
	list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
		if ((--needed) < 0)
			break;
		list_del(&page->lru);
		enqueue_huge_page(h, page);
	}

	/* Free unnecessary surplus pages to the buddy allocator */
	if (!list_empty(&surplus_list)) {
		spin_unlock(&hugetlb_lock);
		list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
			list_del(&page->lru);
			/*
			 * The page has a reference count of zero already, so
			 * call free_huge_page directly instead of using
			 * put_page.  This must be done with hugetlb_lock
			 * unlocked which is safe because free_huge_page takes
			 * hugetlb_lock before deciding how to free the page.
			 */
			free_huge_page(page);
		}
		spin_lock(&hugetlb_lock);
	}

	return ret;
}

/*
 * When releasing a hugetlb pool reservation, any surplus pages that were
 * allocated to satisfy the reservation must be explicitly freed if they were
 * never used.
 */
static void return_unused_surplus_pages(struct hstate *h,
					unsigned long unused_resv_pages)
{
	static int nid = -1;
	struct page *page;
	unsigned long nr_pages;

	/*
	 * We want to release as many surplus pages as possible, spread
	 * evenly across all nodes. Iterate across all nodes until we
	 * can no longer free unreserved surplus pages. This occurs when
	 * the nodes with surplus pages have no free pages.
	 */
	unsigned long remaining_iterations = num_online_nodes();

	/* Uncommit the reservation */
	h->resv_huge_pages -= unused_resv_pages;

	nr_pages = min(unused_resv_pages, h->surplus_huge_pages);

	while (remaining_iterations-- && nr_pages) {
		nid = next_node(nid, node_online_map);
		if (nid == MAX_NUMNODES)
			nid = first_node(node_online_map);

		if (!h->surplus_huge_pages_node[nid])
			continue;

		if (!list_empty(&h->hugepage_freelists[nid])) {
			page = list_entry(h->hugepage_freelists[nid].next,
					  struct page, lru);
			list_del(&page->lru);
			update_and_free_page(h, page);
			h->free_huge_pages--;
			h->free_huge_pages_node[nid]--;
			h->surplus_huge_pages--;
			h->surplus_huge_pages_node[nid]--;
			nr_pages--;
			remaining_iterations = num_online_nodes();
		}
	}
}

/*
 * Determine if the huge page at addr within the vma has an associated
 * reservation.  Where it does not we will need to logically increase
 * reservation and actually increase quota before an allocation can occur.
 * Where any new reservation would be required the reservation change is
 * prepared, but not committed.  Once the page has been quota'd allocated
 * an instantiated the change should be committed via vma_commit_reservation.
 * No action is required on failure.
 */
static int vma_needs_reservation(struct hstate *h,
			struct vm_area_struct *vma, unsigned long addr)
{
	struct address_space *mapping = vma->vm_file->f_mapping;
	struct inode *inode = mapping->host;

	if (vma->vm_flags & VM_SHARED) {
		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
		return region_chg(&inode->i_mapping->private_list,
							idx, idx + 1);

	} else if (!is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
		return 1;

	} else  {
		int err;
		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
		struct resv_map *reservations = vma_resv_map(vma);

		err = region_chg(&reservations->regions, idx, idx + 1);
		if (err < 0)
			return err;
		return 0;
	}
}
static void vma_commit_reservation(struct hstate *h,
			struct vm_area_struct *vma, unsigned long addr)
{
	struct address_space *mapping = vma->vm_file->f_mapping;
	struct inode *inode = mapping->host;

	if (vma->vm_flags & VM_SHARED) {
		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
		region_add(&inode->i_mapping->private_list, idx, idx + 1);

	} else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
		struct resv_map *reservations = vma_resv_map(vma);

		/* Mark this page used in the map. */
		region_add(&reservations->regions, idx, idx + 1);
	}
}

static struct page *alloc_huge_page(struct vm_area_struct *vma,
				    unsigned long addr, int avoid_reserve)
{
	struct hstate *h = hstate_vma(vma);
	struct page *page;
	struct address_space *mapping = vma->vm_file->f_mapping;
	struct inode *inode = mapping->host;
	unsigned int chg;

	/*
	 * Processes that did not create the mapping will have no reserves and
	 * will not have accounted against quota. Check that the quota can be
	 * made before satisfying the allocation
	 * MAP_NORESERVE mappings may also need pages and quota allocated
	 * if no reserve mapping overlaps.
	 */
	chg = vma_needs_reservation(h, vma, addr);
	if (chg < 0)
		return ERR_PTR(chg);
	if (chg)
		if (hugetlb_get_quota(inode->i_mapping, chg))
			return ERR_PTR(-ENOSPC);

	spin_lock(&hugetlb_lock);
	page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve);
	spin_unlock(&hugetlb_lock);

	if (!page) {
		page = alloc_buddy_huge_page(h, vma, addr);
		if (!page) {
			hugetlb_put_quota(inode->i_mapping, chg);
			return ERR_PTR(-VM_FAULT_OOM);
		}
	}

	set_page_refcounted(page);
	set_page_private(page, (unsigned long) mapping);

	vma_commit_reservation(h, vma, addr);

	return page;
}

static void __init hugetlb_init_one_hstate(struct hstate *h)
{
	unsigned long i;

	for (i = 0; i < MAX_NUMNODES; ++i)
		INIT_LIST_HEAD(&h->hugepage_freelists[i]);

	h->hugetlb_next_nid = first_node(node_online_map);

	for (i = 0; i < h->max_huge_pages; ++i) {
		if (!alloc_fresh_huge_page(h))
			break;
	}
	h->max_huge_pages = h->free_huge_pages = h->nr_huge_pages = i;
}

static void __init hugetlb_init_hstates(void)
{
	struct hstate *h;

	for_each_hstate(h) {
		hugetlb_init_one_hstate(h);
	}
}

static void __init report_hugepages(void)
{
	struct hstate *h;

	for_each_hstate(h) {
		printk(KERN_INFO "Total HugeTLB memory allocated, "
				"%ld %dMB pages\n",
				h->free_huge_pages,
				1 << (h->order + PAGE_SHIFT - 20));
	}
}

static int __init hugetlb_init(void)
{
	BUILD_BUG_ON(HPAGE_SHIFT == 0);

	if (!size_to_hstate(HPAGE_SIZE)) {
		hugetlb_add_hstate(HUGETLB_PAGE_ORDER);
		parsed_hstate->max_huge_pages = default_hstate_max_huge_pages;
	}
	default_hstate_idx = size_to_hstate(HPAGE_SIZE) - hstates;

	hugetlb_init_hstates();

	report_hugepages();

	return 0;
}
module_init(hugetlb_init);

/* Should be called on processing a hugepagesz=... option */
void __init hugetlb_add_hstate(unsigned order)
{
	struct hstate *h;
	if (size_to_hstate(PAGE_SIZE << order)) {
		printk(KERN_WARNING "hugepagesz= specified twice, ignoring\n");
		return;
	}
	BUG_ON(max_hstate >= HUGE_MAX_HSTATE);
	BUG_ON(order == 0);
	h = &hstates[max_hstate++];
	h->order = order;
	h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1);
	hugetlb_init_one_hstate(h);
	parsed_hstate = h;
}

static int __init hugetlb_setup(char *s)
{
	unsigned long *mhp;

	/*
	 * !max_hstate means we haven't parsed a hugepagesz= parameter yet,
	 * so this hugepages= parameter goes to the "default hstate".
	 */
	if (!max_hstate)
		mhp = &default_hstate_max_huge_pages;
	else
		mhp = &parsed_hstate->max_huge_pages;

	if (sscanf(s, "%lu", mhp) <= 0)
		*mhp = 0;

	return 1;
}
__setup("hugepages=", hugetlb_setup);

static unsigned int cpuset_mems_nr(unsigned int *array)
{
	int node;
	unsigned int nr = 0;

	for_each_node_mask(node, cpuset_current_mems_allowed)
		nr += array[node];

	return nr;
}

#ifdef CONFIG_SYSCTL
#ifdef CONFIG_HIGHMEM
static void try_to_free_low(struct hstate *h, unsigned long count)
{
	int i;

	for (i = 0; i < MAX_NUMNODES; ++i) {
		struct page *page, *next;
		struct list_head *freel = &h->hugepage_freelists[i];
		list_for_each_entry_safe(page, next, freel, lru) {
			if (count >= h->nr_huge_pages)
				return;
			if (PageHighMem(page))
				continue;
			list_del(&page->lru);
			update_and_free_page(h, page);
			h->free_huge_pages--;
			h->free_huge_pages_node[page_to_nid(page)]--;
		}
	}
}
#else
static inline void try_to_free_low(struct hstate *h, unsigned long count)
{
}
#endif

#define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count)
{
	unsigned long min_count, ret;

	/*
	 * Increase the pool size
	 * First take pages out of surplus state.  Then make up the
	 * remaining difference by allocating fresh huge pages.
	 *
	 * We might race with alloc_buddy_huge_page() here and be unable
	 * to convert a surplus huge page to a normal huge page. That is
	 * not critical, though, it just means the overall size of the
	 * pool might be one hugepage larger than it needs to be, but
	 * within all the constraints specified by the sysctls.
	 */
	spin_lock(&hugetlb_lock);
	while (h->surplus_huge_pages && count > persistent_huge_pages(h)) {
		if (!adjust_pool_surplus(h, -1))
			break;
	}

	while (count > persistent_huge_pages(h)) {
		/*
		 * If this allocation races such that we no longer need the
		 * page, free_huge_page will handle it by freeing the page
		 * and reducing the surplus.
		 */
		spin_unlock(&hugetlb_lock);
		ret = alloc_fresh_huge_page(h);
		spin_lock(&hugetlb_lock);
		if (!ret)
			goto out;

	}

	/*
	 * Decrease the pool size
	 * First return free pages to the buddy allocator (being careful
	 * to keep enough around to satisfy reservations).  Then place
	 * pages into surplus state as needed so the pool will shrink
	 * to the desired size as pages become free.
	 *
	 * By placing pages into the surplus state independent of the
	 * overcommit value, we are allowing the surplus pool size to
	 * exceed overcommit. There are few sane options here. Since
	 * alloc_buddy_huge_page() is checking the global counter,
	 * though, we'll note that we're not allowed to exceed surplus
	 * and won't grow the pool anywhere else. Not until one of the
	 * sysctls are changed, or the surplus pages go out of use.
	 */
	min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages;
	min_count = max(count, min_count);
	try_to_free_low(h, min_count);
	while (min_count < persistent_huge_pages(h)) {
		struct page *page = dequeue_huge_page(h);
		if (!page)
			break;
		update_and_free_page(h, page);
	}
	while (count < persistent_huge_pages(h)) {
		if (!adjust_pool_surplus(h, 1))
			break;
	}
out:
	ret = persistent_huge_pages(h);
	spin_unlock(&hugetlb_lock);
	return ret;
}

int hugetlb_sysctl_handler(struct ctl_table *table, int write,
			   struct file *file, void __user *buffer,
			   size_t *length, loff_t *ppos)
{
	struct hstate *h = &default_hstate;
	unsigned long tmp;

	if (!write)
		tmp = h->max_huge_pages;

	table->data = &tmp;
	table->maxlen = sizeof(unsigned long);
	proc_doulongvec_minmax(table, write, file, buffer, length, ppos);

	if (write)
		h->max_huge_pages = set_max_huge_pages(h, tmp);

	return 0;
}

int hugetlb_treat_movable_handler(struct ctl_table *table, int write,
			struct file *file, void __user *buffer,
			size_t *length, loff_t *ppos)
{
	proc_dointvec(table, write, file, buffer, length, ppos);
	if (hugepages_treat_as_movable)
		htlb_alloc_mask = GFP_HIGHUSER_MOVABLE;
	else
		htlb_alloc_mask = GFP_HIGHUSER;
	return 0;
}

int hugetlb_overcommit_handler(struct ctl_table *table, int write,
			struct file *file, void __user *buffer,
			size_t *length, loff_t *ppos)
{
	struct hstate *h = &default_hstate;
	unsigned long tmp;

	if (!write)
		tmp = h->nr_overcommit_huge_pages;

	table->data = &tmp;
	table->maxlen = sizeof(unsigned long);
	proc_doulongvec_minmax(table, write, file, buffer, length, ppos);

	if (write) {
		spin_lock(&hugetlb_lock);
		h->nr_overcommit_huge_pages = tmp;
		spin_unlock(&hugetlb_lock);
	}

	return 0;
}

#endif /* CONFIG_SYSCTL */

int hugetlb_report_meminfo(char *buf)
{
	struct hstate *h = &default_hstate;
	return sprintf(buf,
			"HugePages_Total: %5lu\n"
			"HugePages_Free:  %5lu\n"
			"HugePages_Rsvd:  %5lu\n"
			"HugePages_Surp:  %5lu\n"
			"Hugepagesize:    %5lu kB\n",
			h->nr_huge_pages,
			h->free_huge_pages,
			h->resv_huge_pages,
			h->surplus_huge_pages,
			1UL << (huge_page_order(h) + PAGE_SHIFT - 10));
}

int hugetlb_report_node_meminfo(int nid, char *buf)
{
	struct hstate *h = &default_hstate;
	return sprintf(buf,
		"Node %d HugePages_Total: %5u\n"
		"Node %d HugePages_Free:  %5u\n"
		"Node %d HugePages_Surp:  %5u\n",
		nid, h->nr_huge_pages_node[nid],
		nid, h->free_huge_pages_node[nid],
		nid, h->surplus_huge_pages_node[nid]);
}

/* Return the number pages of memory we physically have, in PAGE_SIZE units. */
unsigned long hugetlb_total_pages(void)
{
	struct hstate *h = &default_hstate;
	return h->nr_huge_pages * pages_per_huge_page(h);
}

static int hugetlb_acct_memory(struct hstate *h, long delta)
{
	int ret = -ENOMEM;

	spin_lock(&hugetlb_lock);
	/*
	 * When cpuset is configured, it breaks the strict hugetlb page
	 * reservation as the accounting is done on a global variable. Such
	 * reservation is completely rubbish in the presence of cpuset because
	 * the reservation is not checked against page availability for the
	 * current cpuset. Application can still potentially OOM'ed by kernel
	 * with lack of free htlb page in cpuset that the task is in.
	 * Attempt to enforce strict accounting with cpuset is almost
	 * impossible (or too ugly) because cpuset is too fluid that
	 * task or memory node can be dynamically moved between cpusets.
	 *
	 * The change of semantics for shared hugetlb mapping with cpuset is
	 * undesirable. However, in order to preserve some of the semantics,
	 * we fall back to check against current free page availability as
	 * a best attempt and hopefully to minimize the impact of changing
	 * semantics that cpuset has.
	 */
	if (delta > 0) {
		if (gather_surplus_pages(h, delta) < 0)
			goto out;

		if (delta > cpuset_mems_nr(h->free_huge_pages_node)) {
			return_unused_surplus_pages(h, delta);
			goto out;
		}
	}

	ret = 0;
	if (delta < 0)
		return_unused_surplus_pages(h, (unsigned long) -delta);

out:
	spin_unlock(&hugetlb_lock);
	return ret;
}

static void hugetlb_vm_op_open(struct vm_area_struct *vma)
{
	struct resv_map *reservations = vma_resv_map(vma);

	/*
	 * This new VMA should share its siblings reservation map if present.
	 * The VMA will only ever have a valid reservation map pointer where
	 * it is being copied for another still existing VMA.  As that VMA
	 * has a reference to the reservation map it cannot dissappear until
	 * after this open call completes.  It is therefore safe to take a
	 * new reference here without additional locking.
	 */
	if (reservations)
		kref_get(&reservations->refs);
}

static void hugetlb_vm_op_close(struct vm_area_struct *vma)
{
	struct hstate *h = hstate_vma(vma);
	struct resv_map *reservations = vma_resv_map(vma);
	unsigned long reserve;
	unsigned long start;
	unsigned long end;

	if (reservations) {
		start = vma_hugecache_offset(h, vma, vma->vm_start);
		end = vma_hugecache_offset(h, vma, vma->vm_end);

		reserve = (end - start) -
			region_count(&reservations->regions, start, end);

		kref_put(&reservations->refs, resv_map_release);

		if (reserve)
			hugetlb_acct_memory(h, -reserve);
	}
}

/*
 * We cannot handle pagefaults against hugetlb pages at all.  They cause
 * handle_mm_fault() to try to instantiate regular-sized pages in the
 * hugegpage VMA.  do_page_fault() is supposed to trap this, so BUG is we get
 * this far.
 */
static int hugetlb_vm_op_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	BUG();
	return 0;
}

struct vm_operations_struct hugetlb_vm_ops = {
	.fault = hugetlb_vm_op_fault,
	.open = hugetlb_vm_op_open,
	.close = hugetlb_vm_op_close,
};

static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
				int writable)
{
	pte_t entry;

	if (writable) {
		entry =
		    pte_mkwrite(pte_mkdirty(mk_pte(page, vma->vm_page_prot)));
	} else {
		entry = huge_pte_wrprotect(mk_pte(page, vma->vm_page_prot));
	}
	entry = pte_mkyoung(entry);
	entry = pte_mkhuge(entry);

	return entry;
}

static void set_huge_ptep_writable(struct vm_area_struct *vma,
				   unsigned long address, pte_t *ptep)
{
	pte_t entry;

	entry = pte_mkwrite(pte_mkdirty(huge_ptep_get(ptep)));
	if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) {
		update_mmu_cache(vma, address, entry);
	}
}


int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
			    struct vm_area_struct *vma)
{
	pte_t *src_pte, *dst_pte, entry;
	struct page *ptepage;
	unsigned long addr;
	int cow;
	struct hstate *h = hstate_vma(vma);
	unsigned long sz = huge_page_size(h);

	cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;

	for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
		src_pte = huge_pte_offset(src, addr);
		if (!src_pte)
			continue;
		dst_pte = huge_pte_alloc(dst, addr, sz);
		if (!dst_pte)
			goto nomem;

		/* If the pagetables are shared don't copy or take references */
		if (dst_pte == src_pte)
			continue;

		spin_lock(&dst->page_table_lock);
		spin_lock_nested(&src->page_table_lock, SINGLE_DEPTH_NESTING);
		if (!huge_pte_none(huge_ptep_get(src_pte))) {
			if (cow)
				huge_ptep_set_wrprotect(src, addr, src_pte);
			entry = huge_ptep_get(src_pte);
			ptepage = pte_page(entry);
			get_page(ptepage);
			set_huge_pte_at(dst, addr, dst_pte, entry);
		}
		spin_unlock(&src->page_table_lock);
		spin_unlock(&dst->page_table_lock);
	}
	return 0;

nomem:
	return -ENOMEM;
}

void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
			    unsigned long end, struct page *ref_page)
{
	struct mm_struct *mm = vma->vm_mm;
	unsigned long address;
	pte_t *ptep;
	pte_t pte;
	struct page *page;
	struct page *tmp;
	struct hstate *h = hstate_vma(vma);
	unsigned long sz = huge_page_size(h);

	/*
	 * A page gathering list, protected by per file i_mmap_lock. The
	 * lock is used to avoid list corruption from multiple unmapping
	 * of the same page since we are using page->lru.
	 */
	LIST_HEAD(page_list);

	WARN_ON(!is_vm_hugetlb_page(vma));
	BUG_ON(start & ~huge_page_mask(h));
	BUG_ON(end & ~huge_page_mask(h));

	spin_lock(&mm->page_table_lock);
	for (address = start; address < end; address += sz) {
		ptep = huge_pte_offset(mm, address);
		if (!ptep)
			continue;

		if (huge_pmd_unshare(mm, &address, ptep))
			continue;

		/*
		 * If a reference page is supplied, it is because a specific
		 * page is being unmapped, not a range. Ensure the page we
		 * are about to unmap is the actual page of interest.
		 */
		if (ref_page) {
			pte = huge_ptep_get(ptep);
			if (huge_pte_none(pte))
				continue;
			page = pte_page(pte);
			if (page != ref_page)
				continue;

			/*
			 * Mark the VMA as having unmapped its page so that
			 * future faults in this VMA will fail rather than
			 * looking like data was lost
			 */
			set_vma_resv_flags(vma, HPAGE_RESV_UNMAPPED);
		}

		pte = huge_ptep_get_and_clear(mm, address, ptep);
		if (huge_pte_none(pte))
			continue;

		page = pte_page(pte);
		if (pte_dirty(pte))
			set_page_dirty(page);
		list_add(&page->lru, &page_list);
	}
	spin_unlock(&mm->page_table_lock);
	flush_tlb_range(vma, start, end);
	list_for_each_entry_safe(page, tmp, &page_list, lru) {
		list_del(&page->lru);
		put_page(page);
	}
}

void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
			  unsigned long end, struct page *ref_page)
{
	spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
	__unmap_hugepage_range(vma, start, end, ref_page);
	spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
}

/*
 * This is called when the original mapper is failing to COW a MAP_PRIVATE
 * mappping it owns the reserve page for. The intention is to unmap the page
 * from other VMAs and let the children be SIGKILLed if they are faulting the
 * same region.
 */
int unmap_ref_private(struct mm_struct *mm,
					struct vm_area_struct *vma,
					struct page *page,
					unsigned long address)
{
	struct vm_area_struct *iter_vma;
	struct address_space *mapping;
	struct prio_tree_iter iter;
	pgoff_t pgoff;

	/*
	 * vm_pgoff is in PAGE_SIZE units, hence the different calculation
	 * from page cache lookup which is in HPAGE_SIZE units.
	 */
	address = address & huge_page_mask(hstate_vma(vma));
	pgoff = ((address - vma->vm_start) >> PAGE_SHIFT)
		+ (vma->vm_pgoff >> PAGE_SHIFT);
	mapping = (struct address_space *)page_private(page);

	vma_prio_tree_foreach(iter_vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
		/* Do not unmap the current VMA */
		if (iter_vma == vma)
			continue;

		/*
		 * Unmap the page from other VMAs without their own reserves.
		 * They get marked to be SIGKILLed if they fault in these
		 * areas. This is because a future no-page fault on this VMA
		 * could insert a zeroed page instead of the data existing
		 * from the time of fork. This would look like data corruption
		 */
		if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER))
			unmap_hugepage_range(iter_vma,
				address, address + HPAGE_SIZE,
				page);
	}

	return 1;
}

static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
			unsigned long address, pte_t *ptep, pte_t pte,
			struct page *pagecache_page)
{
	struct hstate *h = hstate_vma(vma);
	struct page *old_page, *new_page;
	int avoidcopy;
	int outside_reserve = 0;

	old_page = pte_page(pte);

retry_avoidcopy:
	/* If no-one else is actually using this page, avoid the copy
	 * and just make the page writable */
	avoidcopy = (page_count(old_page) == 1);
	if (avoidcopy) {
		set_huge_ptep_writable(vma, address, ptep);
		return 0;
	}

	/*
	 * If the process that created a MAP_PRIVATE mapping is about to
	 * perform a COW due to a shared page count, attempt to satisfy
	 * the allocation without using the existing reserves. The pagecache
	 * page is used to determine if the reserve at this address was
	 * consumed or not. If reserves were used, a partial faulted mapping
	 * at the time of fork() could consume its reserves on COW instead
	 * of the full address range.
	 */
	if (!(vma->vm_flags & VM_SHARED) &&
			is_vma_resv_set(vma, HPAGE_RESV_OWNER) &&
			old_page != pagecache_page)
		outside_reserve = 1;

	page_cache_get(old_page);
	new_page = alloc_huge_page(vma, address, outside_reserve);

	if (IS_ERR(new_page)) {
		page_cache_release(old_page);

		/*
		 * If a process owning a MAP_PRIVATE mapping fails to COW,
		 * it is due to references held by a child and an insufficient
		 * huge page pool. To guarantee the original mappers
		 * reliability, unmap the page from child processes. The child
		 * may get SIGKILLed if it later faults.
		 */
		if (outside_reserve) {
			BUG_ON(huge_pte_none(pte));
			if (unmap_ref_private(mm, vma, old_page, address)) {
				BUG_ON(page_count(old_page) != 1);
				BUG_ON(huge_pte_none(pte));
				goto retry_avoidcopy;
			}
			WARN_ON_ONCE(1);
		}

		return -PTR_ERR(new_page);
	}

	spin_unlock(&mm->page_table_lock);
	copy_huge_page(new_page, old_page, address, vma);
	__SetPageUptodate(new_page);
	spin_lock(&mm->page_table_lock);

	ptep = huge_pte_offset(mm, address & huge_page_mask(h));
	if (likely(pte_same(huge_ptep_get(ptep), pte))) {
		/* Break COW */
		huge_ptep_clear_flush(vma, address, ptep);
		set_huge_pte_at(mm, address, ptep,
				make_huge_pte(vma, new_page, 1));
		/* Make the old page be freed below */
		new_page = old_page;
	}
	page_cache_release(new_page);
	page_cache_release(old_page);
	return 0;
}

/* Return the pagecache page at a given address within a VMA */
static struct page *hugetlbfs_pagecache_page(struct hstate *h,
			struct vm_area_struct *vma, unsigned long address)
{
	struct address_space *mapping;
	pgoff_t idx;

	mapping = vma->vm_file->f_mapping;
	idx = vma_hugecache_offset(h, vma, address);

	return find_lock_page(mapping, idx);
}

static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
			unsigned long address, pte_t *ptep, int write_access)
{
	struct hstate *h = hstate_vma(vma);
	int ret = VM_FAULT_SIGBUS;
	pgoff_t idx;
	unsigned long size;
	struct page *page;
	struct address_space *mapping;
	pte_t new_pte;

	/*
	 * Currently, we are forced to kill the process in the event the
	 * original mapper has unmapped pages from the child due to a failed
	 * COW. Warn that such a situation has occured as it may not be obvious
	 */
	if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) {
		printk(KERN_WARNING
			"PID %d killed due to inadequate hugepage pool\n",
			current->pid);
		return ret;
	}

	mapping = vma->vm_file->f_mapping;
	idx = vma_hugecache_offset(h, vma, address);

	/*
	 * Use page lock to guard against racing truncation
	 * before we get page_table_lock.
	 */
retry:
	page = find_lock_page(mapping, idx);
	if (!page) {
		size = i_size_read(mapping->host) >> huge_page_shift(h);
		if (idx >= size)
			goto out;
		page = alloc_huge_page(vma, address, 0);
		if (IS_ERR(page)) {
			ret = -PTR_ERR(page);
			goto out;
		}
		clear_huge_page(page, address, huge_page_size(h));
		__SetPageUptodate(page);

		if (vma->vm_flags & VM_SHARED) {
			int err;
			struct inode *inode = mapping->host;

			err = add_to_page_cache(page, mapping, idx, GFP_KERNEL);
			if (err) {
				put_page(page);
				if (err == -EEXIST)
					goto retry;
				goto out;
			}

			spin_lock(&inode->i_lock);
			inode->i_blocks += blocks_per_huge_page(h);
			spin_unlock(&inode->i_lock);
		} else
			lock_page(page);
	}

	spin_lock(&mm->page_table_lock);
	size = i_size_read(mapping->host) >> huge_page_shift(h);
	if (idx >= size)
		goto backout;

	ret = 0;
	if (!huge_pte_none(huge_ptep_get(ptep)))
		goto backout;

	new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE)
				&& (vma->vm_flags & VM_SHARED)));
	set_huge_pte_at(mm, address, ptep, new_pte);

	if (write_access && !(vma->vm_flags & VM_SHARED)) {
		/* Optimization, do the COW without a second fault */
		ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page);
	}

	spin_unlock(&mm->page_table_lock);
	unlock_page(page);
out:
	return ret;

backout:
	spin_unlock(&mm->page_table_lock);
	unlock_page(page);
	put_page(page);
	goto out;
}

int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
			unsigned long address, int write_access)
{
	pte_t *ptep;
	pte_t entry;
	int ret;
	static DEFINE_MUTEX(hugetlb_instantiation_mutex);
	struct hstate *h = hstate_vma(vma);

	ptep = huge_pte_alloc(mm, address, huge_page_size(h));
	if (!ptep)
		return VM_FAULT_OOM;

	/*
	 * Serialize hugepage allocation and instantiation, so that we don't
	 * get spurious allocation failures if two CPUs race to instantiate
	 * the same page in the page cache.
	 */
	mutex_lock(&hugetlb_instantiation_mutex);
	entry = huge_ptep_get(ptep);
	if (huge_pte_none(entry)) {
		ret = hugetlb_no_page(mm, vma, address, ptep, write_access);
		mutex_unlock(&hugetlb_instantiation_mutex);
		return ret;
	}

	ret = 0;

	spin_lock(&mm->page_table_lock);
	/* Check for a racing update before calling hugetlb_cow */
	if (likely(pte_same(entry, huge_ptep_get(ptep))))
		if (write_access && !pte_write(entry)) {
			struct page *page;
			page = hugetlbfs_pagecache_page(h, vma, address);
			ret = hugetlb_cow(mm, vma, address, ptep, entry, page);
			if (page) {
				unlock_page(page);
				put_page(page);
			}
		}
	spin_unlock(&mm->page_table_lock);
	mutex_unlock(&hugetlb_instantiation_mutex);

	return ret;
}

int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
			struct page **pages, struct vm_area_struct **vmas,
			unsigned long *position, int *length, int i,
			int write)
{
	unsigned long pfn_offset;
	unsigned long vaddr = *position;
	int remainder = *length;
	struct hstate *h = hstate_vma(vma);

	spin_lock(&mm->page_table_lock);
	while (vaddr < vma->vm_end && remainder) {
		pte_t *pte;
		struct page *page;

		/*
		 * Some archs (sparc64, sh*) have multiple pte_ts to
		 * each hugepage.  We have to make * sure we get the
		 * first, for the page indexing below to work.
		 */
		pte = huge_pte_offset(mm, vaddr & huge_page_mask(h));

		if (!pte || huge_pte_none(huge_ptep_get(pte)) ||
		    (write && !pte_write(huge_ptep_get(pte)))) {
			int ret;

			spin_unlock(&mm->page_table_lock);
			ret = hugetlb_fault(mm, vma, vaddr, write);
			spin_lock(&mm->page_table_lock);
			if (!(ret & VM_FAULT_ERROR))
				continue;

			remainder = 0;
			if (!i)
				i = -EFAULT;
			break;
		}

		pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT;
		page = pte_page(huge_ptep_get(pte));
same_page:
		if (pages) {
			get_page(page);
			pages[i] = page + pfn_offset;
		}

		if (vmas)
			vmas[i] = vma;

		vaddr += PAGE_SIZE;
		++pfn_offset;
		--remainder;
		++i;
		if (vaddr < vma->vm_end && remainder &&
				pfn_offset < pages_per_huge_page(h)) {
			/*
			 * We use pfn_offset to avoid touching the pageframes
			 * of this compound page.
			 */
			goto same_page;
		}
	}
	spin_unlock(&mm->page_table_lock);
	*length = remainder;
	*position = vaddr;

	return i;
}

void hugetlb_change_protection(struct vm_area_struct *vma,
		unsigned long address, unsigned long end, pgprot_t newprot)
{
	struct mm_struct *mm = vma->vm_mm;
	unsigned long start = address;
	pte_t *ptep;
	pte_t pte;
	struct hstate *h = hstate_vma(vma);

	BUG_ON(address >= end);
	flush_cache_range(vma, address, end);

	spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
	spin_lock(&mm->page_table_lock);
	for (; address < end; address += huge_page_size(h)) {
		ptep = huge_pte_offset(mm, address);
		if (!ptep)
			continue;
		if (huge_pmd_unshare(mm, &address, ptep))
			continue;
		if (!huge_pte_none(huge_ptep_get(ptep))) {
			pte = huge_ptep_get_and_clear(mm, address, ptep);
			pte = pte_mkhuge(pte_modify(pte, newprot));
			set_huge_pte_at(mm, address, ptep, pte);
		}
	}
	spin_unlock(&mm->page_table_lock);
	spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);

	flush_tlb_range(vma, start, end);
}

int hugetlb_reserve_pages(struct inode *inode,
					long from, long to,
					struct vm_area_struct *vma)
{
	long ret, chg;
	struct hstate *h = hstate_inode(inode);

	if (vma && vma->vm_flags & VM_NORESERVE)
		return 0;

	/*
	 * Shared mappings base their reservation on the number of pages that
	 * are already allocated on behalf of the file. Private mappings need
	 * to reserve the full area even if read-only as mprotect() may be
	 * called to make the mapping read-write. Assume !vma is a shm mapping
	 */
	if (!vma || vma->vm_flags & VM_SHARED)
		chg = region_chg(&inode->i_mapping->private_list, from, to);
	else {
		struct resv_map *resv_map = resv_map_alloc();
		if (!resv_map)
			return -ENOMEM;

		chg = to - from;

		set_vma_resv_map(vma, resv_map);
		set_vma_resv_flags(vma, HPAGE_RESV_OWNER);
	}

	if (chg < 0)
		return chg;

	if (hugetlb_get_quota(inode->i_mapping, chg))
		return -ENOSPC;
	ret = hugetlb_acct_memory(h, chg);
	if (ret < 0) {
		hugetlb_put_quota(inode->i_mapping, chg);
		return ret;
	}
	if (!vma || vma->vm_flags & VM_SHARED)
		region_add(&inode->i_mapping->private_list, from, to);
	return 0;
}

void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
{
	struct hstate *h = hstate_inode(inode);
	long chg = region_truncate(&inode->i_mapping->private_list, offset);

	spin_lock(&inode->i_lock);
	inode->i_blocks -= blocks_per_huge_page(h);
	spin_unlock(&inode->i_lock);

	hugetlb_put_quota(inode->i_mapping, (chg - freed));
	hugetlb_acct_memory(h, -(chg - freed));
}