summaryrefslogtreecommitdiff
path: root/mm/mempolicy.c
blob: 4c0510e9e7f660223d069b9578f4b07e92a90f39 (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
/*
 * Simple NUMA memory policy for the Linux kernel.
 *
 * Copyright 2003,2004 Andi Kleen, SuSE Labs.
 * (C) Copyright 2005 Christoph Lameter, Silicon Graphics, Inc.
 * Subject to the GNU Public License, version 2.
 *
 * NUMA policy allows the user to give hints in which node(s) memory should
 * be allocated.
 *
 * Support four policies per VMA and per process:
 *
 * The VMA policy has priority over the process policy for a page fault.
 *
 * interleave     Allocate memory interleaved over a set of nodes,
 *                with normal fallback if it fails.
 *                For VMA based allocations this interleaves based on the
 *                offset into the backing object or offset into the mapping
 *                for anonymous memory. For process policy an process counter
 *                is used.
 *
 * bind           Only allocate memory on a specific set of nodes,
 *                no fallback.
 *                FIXME: memory is allocated starting with the first node
 *                to the last. It would be better if bind would truly restrict
 *                the allocation to memory nodes instead
 *
 * preferred       Try a specific node first before normal fallback.
 *                As a special case node -1 here means do the allocation
 *                on the local CPU. This is normally identical to default,
 *                but useful to set in a VMA when you have a non default
 *                process policy.
 *
 * default        Allocate on the local node first, or when on a VMA
 *                use the process policy. This is what Linux always did
 *		  in a NUMA aware kernel and still does by, ahem, default.
 *
 * The process policy is applied for most non interrupt memory allocations
 * in that process' context. Interrupts ignore the policies and always
 * try to allocate on the local CPU. The VMA policy is only applied for memory
 * allocations for a VMA in the VM.
 *
 * Currently there are a few corner cases in swapping where the policy
 * is not applied, but the majority should be handled. When process policy
 * is used it is not remembered over swap outs/swap ins.
 *
 * Only the highest zone in the zone hierarchy gets policied. Allocations
 * requesting a lower zone just use default policy. This implies that
 * on systems with highmem kernel lowmem allocation don't get policied.
 * Same with GFP_DMA allocations.
 *
 * For shmfs/tmpfs/hugetlbfs shared memory the policy is shared between
 * all users and remembered even when nobody has memory mapped.
 */

/* Notebook:
   fix mmap readahead to honour policy and enable policy for any page cache
   object
   statistics for bigpages
   global policy for page cache? currently it uses process policy. Requires
   first item above.
   handle mremap for shared memory (currently ignored for the policy)
   grows down?
   make bind policy root only? It can trigger oom much faster and the
   kernel is not always grateful with that.
   could replace all the switch()es with a mempolicy_ops structure.
*/

#include <linux/mempolicy.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/hugetlb.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/nodemask.h>
#include <linux/cpuset.h>
#include <linux/gfp.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/compat.h>
#include <linux/mempolicy.h>
#include <linux/swap.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>

#include <asm/tlbflush.h>
#include <asm/uaccess.h>

/* Internal flags */
#define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0)	/* Skip checks for continuous vmas */
#define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1)		/* Invert check for nodemask */
#define MPOL_MF_STATS (MPOL_MF_INTERNAL << 2)		/* Gather statistics */

static kmem_cache_t *policy_cache;
static kmem_cache_t *sn_cache;

#define PDprintk(fmt...)

/* Highest zone. An specific allocation for a zone below that is not
   policied. */
int policy_zone = ZONE_DMA;

struct mempolicy default_policy = {
	.refcnt = ATOMIC_INIT(1), /* never free it */
	.policy = MPOL_DEFAULT,
};

/* Do sanity checking on a policy */
static int mpol_check_policy(int mode, nodemask_t *nodes)
{
	int empty = nodes_empty(*nodes);

	switch (mode) {
	case MPOL_DEFAULT:
		if (!empty)
			return -EINVAL;
		break;
	case MPOL_BIND:
	case MPOL_INTERLEAVE:
		/* Preferred will only use the first bit, but allow
		   more for now. */
		if (empty)
			return -EINVAL;
		break;
	}
	return nodes_subset(*nodes, node_online_map) ? 0 : -EINVAL;
}
/* Generate a custom zonelist for the BIND policy. */
static struct zonelist *bind_zonelist(nodemask_t *nodes)
{
	struct zonelist *zl;
	int num, max, nd;

	max = 1 + MAX_NR_ZONES * nodes_weight(*nodes);
	zl = kmalloc(sizeof(void *) * max, GFP_KERNEL);
	if (!zl)
		return NULL;
	num = 0;
	for_each_node_mask(nd, *nodes)
		zl->zones[num++] = &NODE_DATA(nd)->node_zones[policy_zone];
	zl->zones[num] = NULL;
	return zl;
}

/* Create a new policy */
static struct mempolicy *mpol_new(int mode, nodemask_t *nodes)
{
	struct mempolicy *policy;

	PDprintk("setting mode %d nodes[0] %lx\n", mode, nodes_addr(*nodes)[0]);
	if (mode == MPOL_DEFAULT)
		return NULL;
	policy = kmem_cache_alloc(policy_cache, GFP_KERNEL);
	if (!policy)
		return ERR_PTR(-ENOMEM);
	atomic_set(&policy->refcnt, 1);
	switch (mode) {
	case MPOL_INTERLEAVE:
		policy->v.nodes = *nodes;
		if (nodes_weight(*nodes) == 0) {
			kmem_cache_free(policy_cache, policy);
			return ERR_PTR(-EINVAL);
		}
		break;
	case MPOL_PREFERRED:
		policy->v.preferred_node = first_node(*nodes);
		if (policy->v.preferred_node >= MAX_NUMNODES)
			policy->v.preferred_node = -1;
		break;
	case MPOL_BIND:
		policy->v.zonelist = bind_zonelist(nodes);
		if (policy->v.zonelist == NULL) {
			kmem_cache_free(policy_cache, policy);
			return ERR_PTR(-ENOMEM);
		}
		break;
	}
	policy->policy = mode;
	return policy;
}

/* Check if we are the only process mapping the page in question */
static inline int single_mm_mapping(struct mm_struct *mm,
			struct address_space *mapping)
{
	struct vm_area_struct *vma;
	struct prio_tree_iter iter;
	int rc = 1;

	spin_lock(&mapping->i_mmap_lock);
	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, 0, ULONG_MAX)
		if (mm != vma->vm_mm) {
			rc = 0;
			goto out;
		}
	list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list)
		if (mm != vma->vm_mm) {
			rc = 0;
			goto out;
		}
out:
	spin_unlock(&mapping->i_mmap_lock);
	return rc;
}

/*
 * Add a page to be migrated to the pagelist
 */
static void migrate_page_add(struct vm_area_struct *vma,
	struct page *page, struct list_head *pagelist, unsigned long flags)
{
	/*
	 * Avoid migrating a page that is shared by others and not writable.
	 */
	if ((flags & MPOL_MF_MOVE_ALL) || !page->mapping || PageAnon(page) ||
	    mapping_writably_mapped(page->mapping) ||
	    single_mm_mapping(vma->vm_mm, page->mapping)) {
		int rc = isolate_lru_page(page);

		if (rc == 1)
			list_add(&page->lru, pagelist);
		/*
		 * If the isolate attempt was not successful then we just
		 * encountered an unswappable page. Something must be wrong.
	 	 */
		WARN_ON(rc == 0);
	}
}

static void gather_stats(struct page *, void *);

/* Scan through pages checking if pages follow certain conditions. */
static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
		unsigned long addr, unsigned long end,
		const nodemask_t *nodes, unsigned long flags,
		void *private)
{
	pte_t *orig_pte;
	pte_t *pte;
	spinlock_t *ptl;

	orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
	do {
		struct page *page;
		unsigned int nid;

		if (!pte_present(*pte))
			continue;
		page = vm_normal_page(vma, addr, *pte);
		if (!page)
			continue;
		nid = page_to_nid(page);
		if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
			continue;

		if (flags & MPOL_MF_STATS)
			gather_stats(page, private);
		else if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
			spin_unlock(ptl);
			migrate_page_add(vma, page, private, flags);
			spin_lock(ptl);
		}
		else
			break;
	} while (pte++, addr += PAGE_SIZE, addr != end);
	pte_unmap_unlock(orig_pte, ptl);
	return addr != end;
}

static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud,
		unsigned long addr, unsigned long end,
		const nodemask_t *nodes, unsigned long flags,
		void *private)
{
	pmd_t *pmd;
	unsigned long next;

	pmd = pmd_offset(pud, addr);
	do {
		next = pmd_addr_end(addr, end);
		if (pmd_none_or_clear_bad(pmd))
			continue;
		if (check_pte_range(vma, pmd, addr, next, nodes,
				    flags, private))
			return -EIO;
	} while (pmd++, addr = next, addr != end);
	return 0;
}

static inline int check_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
		unsigned long addr, unsigned long end,
		const nodemask_t *nodes, unsigned long flags,
		void *private)
{
	pud_t *pud;
	unsigned long next;

	pud = pud_offset(pgd, addr);
	do {
		next = pud_addr_end(addr, end);
		if (pud_none_or_clear_bad(pud))
			continue;
		if (check_pmd_range(vma, pud, addr, next, nodes,
				    flags, private))
			return -EIO;
	} while (pud++, addr = next, addr != end);
	return 0;
}

static inline int check_pgd_range(struct vm_area_struct *vma,
		unsigned long addr, unsigned long end,
		const nodemask_t *nodes, unsigned long flags,
		void *private)
{
	pgd_t *pgd;
	unsigned long next;

	pgd = pgd_offset(vma->vm_mm, addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none_or_clear_bad(pgd))
			continue;
		if (check_pud_range(vma, pgd, addr, next, nodes,
				    flags, private))
			return -EIO;
	} while (pgd++, addr = next, addr != end);
	return 0;
}

/* Check if a vma is migratable */
static inline int vma_migratable(struct vm_area_struct *vma)
{
	if (vma->vm_flags & (
		VM_LOCKED|VM_IO|VM_HUGETLB|VM_PFNMAP))
		return 0;
	return 1;
}

/*
 * Check if all pages in a range are on a set of nodes.
 * If pagelist != NULL then isolate pages from the LRU and
 * put them on the pagelist.
 */
static struct vm_area_struct *
check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
		const nodemask_t *nodes, unsigned long flags, void *private)
{
	int err;
	struct vm_area_struct *first, *vma, *prev;

	first = find_vma(mm, start);
	if (!first)
		return ERR_PTR(-EFAULT);
	prev = NULL;
	for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) {
		if (!(flags & MPOL_MF_DISCONTIG_OK)) {
			if (!vma->vm_next && vma->vm_end < end)
				return ERR_PTR(-EFAULT);
			if (prev && prev->vm_end < vma->vm_start)
				return ERR_PTR(-EFAULT);
		}
		if (!is_vm_hugetlb_page(vma) &&
		    ((flags & MPOL_MF_STRICT) ||
		     ((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) &&
				vma_migratable(vma)))) {
			unsigned long endvma = vma->vm_end;

			if (endvma > end)
				endvma = end;
			if (vma->vm_start > start)
				start = vma->vm_start;
			err = check_pgd_range(vma, start, endvma, nodes,
						flags, private);
			if (err) {
				first = ERR_PTR(err);
				break;
			}
		}
		prev = vma;
	}
	return first;
}

/* Apply policy to a single VMA */
static int policy_vma(struct vm_area_struct *vma, struct mempolicy *new)
{
	int err = 0;
	struct mempolicy *old = vma->vm_policy;

	PDprintk("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n",
		 vma->vm_start, vma->vm_end, vma->vm_pgoff,
		 vma->vm_ops, vma->vm_file,
		 vma->vm_ops ? vma->vm_ops->set_policy : NULL);

	if (vma->vm_ops && vma->vm_ops->set_policy)
		err = vma->vm_ops->set_policy(vma, new);
	if (!err) {
		mpol_get(new);
		vma->vm_policy = new;
		mpol_free(old);
	}
	return err;
}

/* Step 2: apply policy to a range and do splits. */
static int mbind_range(struct vm_area_struct *vma, unsigned long start,
		       unsigned long end, struct mempolicy *new)
{
	struct vm_area_struct *next;
	int err;

	err = 0;
	for (; vma && vma->vm_start < end; vma = next) {
		next = vma->vm_next;
		if (vma->vm_start < start)
			err = split_vma(vma->vm_mm, vma, start, 1);
		if (!err && vma->vm_end > end)
			err = split_vma(vma->vm_mm, vma, end, 0);
		if (!err)
			err = policy_vma(vma, new);
		if (err)
			break;
	}
	return err;
}

static int contextualize_policy(int mode, nodemask_t *nodes)
{
	if (!nodes)
		return 0;

	/* Update current mems_allowed */
	cpuset_update_current_mems_allowed();
	/* Ignore nodes not set in current->mems_allowed */
	cpuset_restrict_to_mems_allowed(nodes->bits);
	return mpol_check_policy(mode, nodes);
}

static int swap_pages(struct list_head *pagelist)
{
	LIST_HEAD(moved);
	LIST_HEAD(failed);
	int n;

	n = migrate_pages(pagelist, NULL, &moved, &failed);
	putback_lru_pages(&failed);
	putback_lru_pages(&moved);

	return n;
}

long do_mbind(unsigned long start, unsigned long len,
		unsigned long mode, nodemask_t *nmask, unsigned long flags)
{
	struct vm_area_struct *vma;
	struct mm_struct *mm = current->mm;
	struct mempolicy *new;
	unsigned long end;
	int err;
	LIST_HEAD(pagelist);

	if ((flags & ~(unsigned long)(MPOL_MF_STRICT |
				      MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
	    || mode > MPOL_MAX)
		return -EINVAL;
	if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_RESOURCE))
		return -EPERM;

	if (start & ~PAGE_MASK)
		return -EINVAL;

	if (mode == MPOL_DEFAULT)
		flags &= ~MPOL_MF_STRICT;

	len = (len + PAGE_SIZE - 1) & PAGE_MASK;
	end = start + len;

	if (end < start)
		return -EINVAL;
	if (end == start)
		return 0;

	if (mpol_check_policy(mode, nmask))
		return -EINVAL;

	new = mpol_new(mode, nmask);
	if (IS_ERR(new))
		return PTR_ERR(new);

	/*
	 * If we are using the default policy then operation
	 * on discontinuous address spaces is okay after all
	 */
	if (!new)
		flags |= MPOL_MF_DISCONTIG_OK;

	PDprintk("mbind %lx-%lx mode:%ld nodes:%lx\n",start,start+len,
			mode,nodes_addr(nodes)[0]);

	down_write(&mm->mmap_sem);
	vma = check_range(mm, start, end, nmask,
			  flags | MPOL_MF_INVERT, &pagelist);

	err = PTR_ERR(vma);
	if (!IS_ERR(vma)) {
		int nr_failed = 0;

		err = mbind_range(vma, start, end, new);
		if (!list_empty(&pagelist))
			nr_failed = swap_pages(&pagelist);

		if (!err && nr_failed && (flags & MPOL_MF_STRICT))
			err = -EIO;
	}
	if (!list_empty(&pagelist))
		putback_lru_pages(&pagelist);

	up_write(&mm->mmap_sem);
	mpol_free(new);
	return err;
}

/* Set the process memory policy */
long do_set_mempolicy(int mode, nodemask_t *nodes)
{
	struct mempolicy *new;

	if (contextualize_policy(mode, nodes))
		return -EINVAL;
	new = mpol_new(mode, nodes);
	if (IS_ERR(new))
		return PTR_ERR(new);
	mpol_free(current->mempolicy);
	current->mempolicy = new;
	if (new && new->policy == MPOL_INTERLEAVE)
		current->il_next = first_node(new->v.nodes);
	return 0;
}

/* Fill a zone bitmap for a policy */
static void get_zonemask(struct mempolicy *p, nodemask_t *nodes)
{
	int i;

	nodes_clear(*nodes);
	switch (p->policy) {
	case MPOL_BIND:
		for (i = 0; p->v.zonelist->zones[i]; i++)
			node_set(p->v.zonelist->zones[i]->zone_pgdat->node_id,
				*nodes);
		break;
	case MPOL_DEFAULT:
		break;
	case MPOL_INTERLEAVE:
		*nodes = p->v.nodes;
		break;
	case MPOL_PREFERRED:
		/* or use current node instead of online map? */
		if (p->v.preferred_node < 0)
			*nodes = node_online_map;
		else
			node_set(p->v.preferred_node, *nodes);
		break;
	default:
		BUG();
	}
}

static int lookup_node(struct mm_struct *mm, unsigned long addr)
{
	struct page *p;
	int err;

	err = get_user_pages(current, mm, addr & PAGE_MASK, 1, 0, 0, &p, NULL);
	if (err >= 0) {
		err = page_to_nid(p);
		put_page(p);
	}
	return err;
}

/* Retrieve NUMA policy */
long do_get_mempolicy(int *policy, nodemask_t *nmask,
			unsigned long addr, unsigned long flags)
{
	int err;
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma = NULL;
	struct mempolicy *pol = current->mempolicy;

	cpuset_update_current_mems_allowed();
	if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR))
		return -EINVAL;
	if (flags & MPOL_F_ADDR) {
		down_read(&mm->mmap_sem);
		vma = find_vma_intersection(mm, addr, addr+1);
		if (!vma) {
			up_read(&mm->mmap_sem);
			return -EFAULT;
		}
		if (vma->vm_ops && vma->vm_ops->get_policy)
			pol = vma->vm_ops->get_policy(vma, addr);
		else
			pol = vma->vm_policy;
	} else if (addr)
		return -EINVAL;

	if (!pol)
		pol = &default_policy;

	if (flags & MPOL_F_NODE) {
		if (flags & MPOL_F_ADDR) {
			err = lookup_node(mm, addr);
			if (err < 0)
				goto out;
			*policy = err;
		} else if (pol == current->mempolicy &&
				pol->policy == MPOL_INTERLEAVE) {
			*policy = current->il_next;
		} else {
			err = -EINVAL;
			goto out;
		}
	} else
		*policy = pol->policy;

	if (vma) {
		up_read(&current->mm->mmap_sem);
		vma = NULL;
	}

	err = 0;
	if (nmask)
		get_zonemask(pol, nmask);

 out:
	if (vma)
		up_read(&current->mm->mmap_sem);
	return err;
}

/*
 * For now migrate_pages simply swaps out the pages from nodes that are in
 * the source set but not in the target set. In the future, we would
 * want a function that moves pages between the two nodesets in such
 * a way as to preserve the physical layout as much as possible.
 *
 * Returns the number of page that could not be moved.
 */
int do_migrate_pages(struct mm_struct *mm,
	const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
{
	LIST_HEAD(pagelist);
	int count = 0;
	nodemask_t nodes;

	nodes_andnot(nodes, *from_nodes, *to_nodes);

	down_read(&mm->mmap_sem);
	check_range(mm, mm->mmap->vm_start, TASK_SIZE, &nodes,
			flags | MPOL_MF_DISCONTIG_OK, &pagelist);

	if (!list_empty(&pagelist)) {
		count = swap_pages(&pagelist);
		putback_lru_pages(&pagelist);
	}

	up_read(&mm->mmap_sem);
	return count;
}

/*
 * User space interface with variable sized bitmaps for nodelists.
 */

/* Copy a node mask from user space. */
static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask,
		     unsigned long maxnode)
{
	unsigned long k;
	unsigned long nlongs;
	unsigned long endmask;

	--maxnode;
	nodes_clear(*nodes);
	if (maxnode == 0 || !nmask)
		return 0;

	nlongs = BITS_TO_LONGS(maxnode);
	if ((maxnode % BITS_PER_LONG) == 0)
		endmask = ~0UL;
	else
		endmask = (1UL << (maxnode % BITS_PER_LONG)) - 1;

	/* When the user specified more nodes than supported just check
	   if the non supported part is all zero. */
	if (nlongs > BITS_TO_LONGS(MAX_NUMNODES)) {
		if (nlongs > PAGE_SIZE/sizeof(long))
			return -EINVAL;
		for (k = BITS_TO_LONGS(MAX_NUMNODES); k < nlongs; k++) {
			unsigned long t;
			if (get_user(t, nmask + k))
				return -EFAULT;
			if (k == nlongs - 1) {
				if (t & endmask)
					return -EINVAL;
			} else if (t)
				return -EINVAL;
		}
		nlongs = BITS_TO_LONGS(MAX_NUMNODES);
		endmask = ~0UL;
	}

	if (copy_from_user(nodes_addr(*nodes), nmask, nlongs*sizeof(unsigned long)))
		return -EFAULT;
	nodes_addr(*nodes)[nlongs-1] &= endmask;
	return 0;
}

/* Copy a kernel node mask to user space */
static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode,
			      nodemask_t *nodes)
{
	unsigned long copy = ALIGN(maxnode-1, 64) / 8;
	const int nbytes = BITS_TO_LONGS(MAX_NUMNODES) * sizeof(long);

	if (copy > nbytes) {
		if (copy > PAGE_SIZE)
			return -EINVAL;
		if (clear_user((char __user *)mask + nbytes, copy - nbytes))
			return -EFAULT;
		copy = nbytes;
	}
	return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0;
}

asmlinkage long sys_mbind(unsigned long start, unsigned long len,
			unsigned long mode,
			unsigned long __user *nmask, unsigned long maxnode,
			unsigned flags)
{
	nodemask_t nodes;
	int err;

	err = get_nodes(&nodes, nmask, maxnode);
	if (err)
		return err;
	return do_mbind(start, len, mode, &nodes, flags);
}

/* Set the process memory policy */
asmlinkage long sys_set_mempolicy(int mode, unsigned long __user *nmask,
		unsigned long maxnode)
{
	int err;
	nodemask_t nodes;

	if (mode < 0 || mode > MPOL_MAX)
		return -EINVAL;
	err = get_nodes(&nodes, nmask, maxnode);
	if (err)
		return err;
	return do_set_mempolicy(mode, &nodes);
}

/* Macro needed until Paul implements this function in kernel/cpusets.c */
#define cpuset_mems_allowed(task) node_online_map

asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode,
		const unsigned long __user *old_nodes,
		const unsigned long __user *new_nodes)
{
	struct mm_struct *mm;
	struct task_struct *task;
	nodemask_t old;
	nodemask_t new;
	nodemask_t task_nodes;
	int err;

	err = get_nodes(&old, old_nodes, maxnode);
	if (err)
		return err;

	err = get_nodes(&new, new_nodes, maxnode);
	if (err)
		return err;

	/* Find the mm_struct */
	read_lock(&tasklist_lock);
	task = pid ? find_task_by_pid(pid) : current;
	if (!task) {
		read_unlock(&tasklist_lock);
		return -ESRCH;
	}
	mm = get_task_mm(task);
	read_unlock(&tasklist_lock);

	if (!mm)
		return -EINVAL;

	/*
	 * Check if this process has the right to modify the specified
	 * process. The right exists if the process has administrative
	 * capabilities, superuser priviledges or the same
	 * userid as the target process.
	 */
	if ((current->euid != task->suid) && (current->euid != task->uid) &&
	    (current->uid != task->suid) && (current->uid != task->uid) &&
	    !capable(CAP_SYS_ADMIN)) {
		err = -EPERM;
		goto out;
	}

	task_nodes = cpuset_mems_allowed(task);
	/* Is the user allowed to access the target nodes? */
	if (!nodes_subset(new, task_nodes) && !capable(CAP_SYS_ADMIN)) {
		err = -EPERM;
		goto out;
	}

	err = do_migrate_pages(mm, &old, &new, MPOL_MF_MOVE);
out:
	mmput(mm);
	return err;
}


/* Retrieve NUMA policy */
asmlinkage long sys_get_mempolicy(int __user *policy,
				unsigned long __user *nmask,
				unsigned long maxnode,
				unsigned long addr, unsigned long flags)
{
	int err, pval;
	nodemask_t nodes;

	if (nmask != NULL && maxnode < MAX_NUMNODES)
		return -EINVAL;

	err = do_get_mempolicy(&pval, &nodes, addr, flags);

	if (err)
		return err;

	if (policy && put_user(pval, policy))
		return -EFAULT;

	if (nmask)
		err = copy_nodes_to_user(nmask, maxnode, &nodes);

	return err;
}

#ifdef CONFIG_COMPAT

asmlinkage long compat_sys_get_mempolicy(int __user *policy,
				     compat_ulong_t __user *nmask,
				     compat_ulong_t maxnode,
				     compat_ulong_t addr, compat_ulong_t flags)
{
	long err;
	unsigned long __user *nm = NULL;
	unsigned long nr_bits, alloc_size;
	DECLARE_BITMAP(bm, MAX_NUMNODES);

	nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
	alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;

	if (nmask)
		nm = compat_alloc_user_space(alloc_size);

	err = sys_get_mempolicy(policy, nm, nr_bits+1, addr, flags);

	if (!err && nmask) {
		err = copy_from_user(bm, nm, alloc_size);
		/* ensure entire bitmap is zeroed */
		err |= clear_user(nmask, ALIGN(maxnode-1, 8) / 8);
		err |= compat_put_bitmap(nmask, bm, nr_bits);
	}

	return err;
}

asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask,
				     compat_ulong_t maxnode)
{
	long err = 0;
	unsigned long __user *nm = NULL;
	unsigned long nr_bits, alloc_size;
	DECLARE_BITMAP(bm, MAX_NUMNODES);

	nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
	alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;

	if (nmask) {
		err = compat_get_bitmap(bm, nmask, nr_bits);
		nm = compat_alloc_user_space(alloc_size);
		err |= copy_to_user(nm, bm, alloc_size);
	}

	if (err)
		return -EFAULT;

	return sys_set_mempolicy(mode, nm, nr_bits+1);
}

asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len,
			     compat_ulong_t mode, compat_ulong_t __user *nmask,
			     compat_ulong_t maxnode, compat_ulong_t flags)
{
	long err = 0;
	unsigned long __user *nm = NULL;
	unsigned long nr_bits, alloc_size;
	nodemask_t bm;

	nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
	alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;

	if (nmask) {
		err = compat_get_bitmap(nodes_addr(bm), nmask, nr_bits);
		nm = compat_alloc_user_space(alloc_size);
		err |= copy_to_user(nm, nodes_addr(bm), alloc_size);
	}

	if (err)
		return -EFAULT;

	return sys_mbind(start, len, mode, nm, nr_bits+1, flags);
}

#endif

/* Return effective policy for a VMA */
struct mempolicy *
get_vma_policy(struct task_struct *task, struct vm_area_struct *vma, unsigned long addr)
{
	struct mempolicy *pol = task->mempolicy;

	if (vma) {
		if (vma->vm_ops && vma->vm_ops->get_policy)
			pol = vma->vm_ops->get_policy(vma, addr);
		else if (vma->vm_policy &&
				vma->vm_policy->policy != MPOL_DEFAULT)
			pol = vma->vm_policy;
	}
	if (!pol)
		pol = &default_policy;
	return pol;
}

/* Return a zonelist representing a mempolicy */
static struct zonelist *zonelist_policy(gfp_t gfp, struct mempolicy *policy)
{
	int nd;

	switch (policy->policy) {
	case MPOL_PREFERRED:
		nd = policy->v.preferred_node;
		if (nd < 0)
			nd = numa_node_id();
		break;
	case MPOL_BIND:
		/* Lower zones don't get a policy applied */
		/* Careful: current->mems_allowed might have moved */
		if (gfp_zone(gfp) >= policy_zone)
			if (cpuset_zonelist_valid_mems_allowed(policy->v.zonelist))
				return policy->v.zonelist;
		/*FALL THROUGH*/
	case MPOL_INTERLEAVE: /* should not happen */
	case MPOL_DEFAULT:
		nd = numa_node_id();
		break;
	default:
		nd = 0;
		BUG();
	}
	return NODE_DATA(nd)->node_zonelists + gfp_zone(gfp);
}

/* Do dynamic interleaving for a process */
static unsigned interleave_nodes(struct mempolicy *policy)
{
	unsigned nid, next;
	struct task_struct *me = current;

	nid = me->il_next;
	next = next_node(nid, policy->v.nodes);
	if (next >= MAX_NUMNODES)
		next = first_node(policy->v.nodes);
	me->il_next = next;
	return nid;
}

/* Do static interleaving for a VMA with known offset. */
static unsigned offset_il_node(struct mempolicy *pol,
		struct vm_area_struct *vma, unsigned long off)
{
	unsigned nnodes = nodes_weight(pol->v.nodes);
	unsigned target = (unsigned)off % nnodes;
	int c;
	int nid = -1;

	c = 0;
	do {
		nid = next_node(nid, pol->v.nodes);
		c++;
	} while (c <= target);
	return nid;
}

/* Determine a node number for interleave */
static inline unsigned interleave_nid(struct mempolicy *pol,
		 struct vm_area_struct *vma, unsigned long addr, int shift)
{
	if (vma) {
		unsigned long off;

		off = vma->vm_pgoff;
		off += (addr - vma->vm_start) >> shift;
		return offset_il_node(pol, vma, off);
	} else
		return interleave_nodes(pol);
}

/* Return a zonelist suitable for a huge page allocation. */
struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr)
{
	struct mempolicy *pol = get_vma_policy(current, vma, addr);

	if (pol->policy == MPOL_INTERLEAVE) {
		unsigned nid;

		nid = interleave_nid(pol, vma, addr, HPAGE_SHIFT);
		return NODE_DATA(nid)->node_zonelists + gfp_zone(GFP_HIGHUSER);
	}
	return zonelist_policy(GFP_HIGHUSER, pol);
}

/* Allocate a page in interleaved policy.
   Own path because it needs to do special accounting. */
static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
					unsigned nid)
{
	struct zonelist *zl;
	struct page *page;

	zl = NODE_DATA(nid)->node_zonelists + gfp_zone(gfp);
	page = __alloc_pages(gfp, order, zl);
	if (page && page_zone(page) == zl->zones[0]) {
		zone_pcp(zl->zones[0],get_cpu())->interleave_hit++;
		put_cpu();
	}
	return page;
}

/**
 * 	alloc_page_vma	- Allocate a page for a VMA.
 *
 * 	@gfp:
 *      %GFP_USER    user allocation.
 *      %GFP_KERNEL  kernel allocations,
 *      %GFP_HIGHMEM highmem/user allocations,
 *      %GFP_FS      allocation should not call back into a file system.
 *      %GFP_ATOMIC  don't sleep.
 *
 * 	@vma:  Pointer to VMA or NULL if not available.
 *	@addr: Virtual Address of the allocation. Must be inside the VMA.
 *
 * 	This function allocates a page from the kernel page pool and applies
 *	a NUMA policy associated with the VMA or the current process.
 *	When VMA is not NULL caller must hold down_read on the mmap_sem of the
 *	mm_struct of the VMA to prevent it from going away. Should be used for
 *	all allocations for pages that will be mapped into
 * 	user space. Returns NULL when no page can be allocated.
 *
 *	Should be called with the mm_sem of the vma hold.
 */
struct page *
alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
{
	struct mempolicy *pol = get_vma_policy(current, vma, addr);

	cpuset_update_current_mems_allowed();

	if (unlikely(pol->policy == MPOL_INTERLEAVE)) {
		unsigned nid;

		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT);
		return alloc_page_interleave(gfp, 0, nid);
	}
	return __alloc_pages(gfp, 0, zonelist_policy(gfp, pol));
}

/**
 * 	alloc_pages_current - Allocate pages.
 *
 *	@gfp:
 *		%GFP_USER   user allocation,
 *      	%GFP_KERNEL kernel allocation,
 *      	%GFP_HIGHMEM highmem allocation,
 *      	%GFP_FS     don't call back into a file system.
 *      	%GFP_ATOMIC don't sleep.
 *	@order: Power of two of allocation size in pages. 0 is a single page.
 *
 *	Allocate a page from the kernel page pool.  When not in
 *	interrupt context and apply the current process NUMA policy.
 *	Returns NULL when no page can be allocated.
 *
 *	Don't call cpuset_update_current_mems_allowed() unless
 *	1) it's ok to take cpuset_sem (can WAIT), and
 *	2) allocating for current task (not interrupt).
 */
struct page *alloc_pages_current(gfp_t gfp, unsigned order)
{
	struct mempolicy *pol = current->mempolicy;

	if ((gfp & __GFP_WAIT) && !in_interrupt())
		cpuset_update_current_mems_allowed();
	if (!pol || in_interrupt())
		pol = &default_policy;
	if (pol->policy == MPOL_INTERLEAVE)
		return alloc_page_interleave(gfp, order, interleave_nodes(pol));
	return __alloc_pages(gfp, order, zonelist_policy(gfp, pol));
}
EXPORT_SYMBOL(alloc_pages_current);

/* Slow path of a mempolicy copy */
struct mempolicy *__mpol_copy(struct mempolicy *old)
{
	struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL);

	if (!new)
		return ERR_PTR(-ENOMEM);
	*new = *old;
	atomic_set(&new->refcnt, 1);
	if (new->policy == MPOL_BIND) {
		int sz = ksize(old->v.zonelist);
		new->v.zonelist = kmalloc(sz, SLAB_KERNEL);
		if (!new->v.zonelist) {
			kmem_cache_free(policy_cache, new);
			return ERR_PTR(-ENOMEM);
		}
		memcpy(new->v.zonelist, old->v.zonelist, sz);
	}
	return new;
}

/* Slow path of a mempolicy comparison */
int __mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
	if (!a || !b)
		return 0;
	if (a->policy != b->policy)
		return 0;
	switch (a->policy) {
	case MPOL_DEFAULT:
		return 1;
	case MPOL_INTERLEAVE:
		return nodes_equal(a->v.nodes, b->v.nodes);
	case MPOL_PREFERRED:
		return a->v.preferred_node == b->v.preferred_node;
	case MPOL_BIND: {
		int i;
		for (i = 0; a->v.zonelist->zones[i]; i++)
			if (a->v.zonelist->zones[i] != b->v.zonelist->zones[i])
				return 0;
		return b->v.zonelist->zones[i] == NULL;
	}
	default:
		BUG();
		return 0;
	}
}

/* Slow path of a mpol destructor. */
void __mpol_free(struct mempolicy *p)
{
	if (!atomic_dec_and_test(&p->refcnt))
		return;
	if (p->policy == MPOL_BIND)
		kfree(p->v.zonelist);
	p->policy = MPOL_DEFAULT;
	kmem_cache_free(policy_cache, p);
}

/*
 * Shared memory backing store policy support.
 *
 * Remember policies even when nobody has shared memory mapped.
 * The policies are kept in Red-Black tree linked from the inode.
 * They are protected by the sp->lock spinlock, which should be held
 * for any accesses to the tree.
 */

/* lookup first element intersecting start-end */
/* Caller holds sp->lock */
static struct sp_node *
sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end)
{
	struct rb_node *n = sp->root.rb_node;

	while (n) {
		struct sp_node *p = rb_entry(n, struct sp_node, nd);

		if (start >= p->end)
			n = n->rb_right;
		else if (end <= p->start)
			n = n->rb_left;
		else
			break;
	}
	if (!n)
		return NULL;
	for (;;) {
		struct sp_node *w = NULL;
		struct rb_node *prev = rb_prev(n);
		if (!prev)
			break;
		w = rb_entry(prev, struct sp_node, nd);
		if (w->end <= start)
			break;
		n = prev;
	}
	return rb_entry(n, struct sp_node, nd);
}

/* Insert a new shared policy into the list. */
/* Caller holds sp->lock */
static void sp_insert(struct shared_policy *sp, struct sp_node *new)
{
	struct rb_node **p = &sp->root.rb_node;
	struct rb_node *parent = NULL;
	struct sp_node *nd;

	while (*p) {
		parent = *p;
		nd = rb_entry(parent, struct sp_node, nd);
		if (new->start < nd->start)
			p = &(*p)->rb_left;
		else if (new->end > nd->end)
			p = &(*p)->rb_right;
		else
			BUG();
	}
	rb_link_node(&new->nd, parent, p);
	rb_insert_color(&new->nd, &sp->root);
	PDprintk("inserting %lx-%lx: %d\n", new->start, new->end,
		 new->policy ? new->policy->policy : 0);
}

/* Find shared policy intersecting idx */
struct mempolicy *
mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx)
{
	struct mempolicy *pol = NULL;
	struct sp_node *sn;

	if (!sp->root.rb_node)
		return NULL;
	spin_lock(&sp->lock);
	sn = sp_lookup(sp, idx, idx+1);
	if (sn) {
		mpol_get(sn->policy);
		pol = sn->policy;
	}
	spin_unlock(&sp->lock);
	return pol;
}

static void sp_delete(struct shared_policy *sp, struct sp_node *n)
{
	PDprintk("deleting %lx-l%x\n", n->start, n->end);
	rb_erase(&n->nd, &sp->root);
	mpol_free(n->policy);
	kmem_cache_free(sn_cache, n);
}

struct sp_node *
sp_alloc(unsigned long start, unsigned long end, struct mempolicy *pol)
{
	struct sp_node *n = kmem_cache_alloc(sn_cache, GFP_KERNEL);

	if (!n)
		return NULL;
	n->start = start;
	n->end = end;
	mpol_get(pol);
	n->policy = pol;
	return n;
}

/* Replace a policy range. */
static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
				 unsigned long end, struct sp_node *new)
{
	struct sp_node *n, *new2 = NULL;

restart:
	spin_lock(&sp->lock);
	n = sp_lookup(sp, start, end);
	/* Take care of old policies in the same range. */
	while (n && n->start < end) {
		struct rb_node *next = rb_next(&n->nd);
		if (n->start >= start) {
			if (n->end <= end)
				sp_delete(sp, n);
			else
				n->start = end;
		} else {
			/* Old policy spanning whole new range. */
			if (n->end > end) {
				if (!new2) {
					spin_unlock(&sp->lock);
					new2 = sp_alloc(end, n->end, n->policy);
					if (!new2)
						return -ENOMEM;
					goto restart;
				}
				n->end = start;
				sp_insert(sp, new2);
				new2 = NULL;
				break;
			} else
				n->end = start;
		}
		if (!next)
			break;
		n = rb_entry(next, struct sp_node, nd);
	}
	if (new)
		sp_insert(sp, new);
	spin_unlock(&sp->lock);
	if (new2) {
		mpol_free(new2->policy);
		kmem_cache_free(sn_cache, new2);
	}
	return 0;
}

int mpol_set_shared_policy(struct shared_policy *info,
			struct vm_area_struct *vma, struct mempolicy *npol)
{
	int err;
	struct sp_node *new = NULL;
	unsigned long sz = vma_pages(vma);

	PDprintk("set_shared_policy %lx sz %lu %d %lx\n",
		 vma->vm_pgoff,
		 sz, npol? npol->policy : -1,
		npol ? nodes_addr(npol->v.nodes)[0] : -1);

	if (npol) {
		new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, npol);
		if (!new)
			return -ENOMEM;
	}
	err = shared_policy_replace(info, vma->vm_pgoff, vma->vm_pgoff+sz, new);
	if (err && new)
		kmem_cache_free(sn_cache, new);
	return err;
}

/* Free a backing policy store on inode delete. */
void mpol_free_shared_policy(struct shared_policy *p)
{
	struct sp_node *n;
	struct rb_node *next;

	if (!p->root.rb_node)
		return;
	spin_lock(&p->lock);
	next = rb_first(&p->root);
	while (next) {
		n = rb_entry(next, struct sp_node, nd);
		next = rb_next(&n->nd);
		rb_erase(&n->nd, &p->root);
		mpol_free(n->policy);
		kmem_cache_free(sn_cache, n);
	}
	spin_unlock(&p->lock);
}

/* assumes fs == KERNEL_DS */
void __init numa_policy_init(void)
{
	policy_cache = kmem_cache_create("numa_policy",
					 sizeof(struct mempolicy),
					 0, SLAB_PANIC, NULL, NULL);

	sn_cache = kmem_cache_create("shared_policy_node",
				     sizeof(struct sp_node),
				     0, SLAB_PANIC, NULL, NULL);

	/* Set interleaving policy for system init. This way not all
	   the data structures allocated at system boot end up in node zero. */

	if (do_set_mempolicy(MPOL_INTERLEAVE, &node_online_map))
		printk("numa_policy_init: interleaving failed\n");
}

/* Reset policy of current process to default */
void numa_default_policy(void)
{
	do_set_mempolicy(MPOL_DEFAULT, NULL);
}

/* Migrate a policy to a different set of nodes */
static void rebind_policy(struct mempolicy *pol, const nodemask_t *old,
							const nodemask_t *new)
{
	nodemask_t tmp;

	if (!pol)
		return;

	switch (pol->policy) {
	case MPOL_DEFAULT:
		break;
	case MPOL_INTERLEAVE:
		nodes_remap(tmp, pol->v.nodes, *old, *new);
		pol->v.nodes = tmp;
		current->il_next = node_remap(current->il_next, *old, *new);
		break;
	case MPOL_PREFERRED:
		pol->v.preferred_node = node_remap(pol->v.preferred_node,
								*old, *new);
		break;
	case MPOL_BIND: {
		nodemask_t nodes;
		struct zone **z;
		struct zonelist *zonelist;

		nodes_clear(nodes);
		for (z = pol->v.zonelist->zones; *z; z++)
			node_set((*z)->zone_pgdat->node_id, nodes);
		nodes_remap(tmp, nodes, *old, *new);
		nodes = tmp;

		zonelist = bind_zonelist(&nodes);

		/* If no mem, then zonelist is NULL and we keep old zonelist.
		 * If that old zonelist has no remaining mems_allowed nodes,
		 * then zonelist_policy() will "FALL THROUGH" to MPOL_DEFAULT.
		 */

		if (zonelist) {
			/* Good - got mem - substitute new zonelist */
			kfree(pol->v.zonelist);
			pol->v.zonelist = zonelist;
		}
		break;
	}
	default:
		BUG();
		break;
	}
}

/*
 * Someone moved this task to different nodes.  Fixup mempolicies.
 *
 * TODO - fixup current->mm->vma and shmfs/tmpfs/hugetlbfs policies as well,
 * once we have a cpuset mechanism to mark which cpuset subtree is migrating.
 */
void numa_policy_rebind(const nodemask_t *old, const nodemask_t *new)
{
	rebind_policy(current->mempolicy, old, new);
}

/*
 * Display pages allocated per node and memory policy via /proc.
 */

static const char *policy_types[] = { "default", "prefer", "bind",
				      "interleave" };

/*
 * Convert a mempolicy into a string.
 * Returns the number of characters in buffer (if positive)
 * or an error (negative)
 */
static inline int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
{
	char *p = buffer;
	int l;
	nodemask_t nodes;
	int mode = pol ? pol->policy : MPOL_DEFAULT;

	switch (mode) {
	case MPOL_DEFAULT:
		nodes_clear(nodes);
		break;

	case MPOL_PREFERRED:
		nodes_clear(nodes);
		node_set(pol->v.preferred_node, nodes);
		break;

	case MPOL_BIND:
		get_zonemask(pol, &nodes);
		break;

	case MPOL_INTERLEAVE:
		nodes = pol->v.nodes;
		break;

	default:
		BUG();
		return -EFAULT;
	}

	l = strlen(policy_types[mode]);
 	if (buffer + maxlen < p + l + 1)
 		return -ENOSPC;

	strcpy(p, policy_types[mode]);
	p += l;

	if (!nodes_empty(nodes)) {
		if (buffer + maxlen < p + 2)
			return -ENOSPC;
		*p++ = '=';
	 	p += nodelist_scnprintf(p, buffer + maxlen - p, nodes);
	}
	return p - buffer;
}

struct numa_maps {
	unsigned long pages;
	unsigned long anon;
	unsigned long mapped;
	unsigned long mapcount_max;
	unsigned long node[MAX_NUMNODES];
};

static void gather_stats(struct page *page, void *private)
{
	struct numa_maps *md = private;
	int count = page_mapcount(page);

	if (count)
		md->mapped++;

	if (count > md->mapcount_max)
		md->mapcount_max = count;

	md->pages++;

	if (PageAnon(page))
		md->anon++;

	md->node[page_to_nid(page)]++;
	cond_resched();
}

int show_numa_map(struct seq_file *m, void *v)
{
	struct task_struct *task = m->private;
	struct vm_area_struct *vma = v;
	struct numa_maps *md;
	int n;
	char buffer[50];

	if (!vma->vm_mm)
		return 0;

	md = kzalloc(sizeof(struct numa_maps), GFP_KERNEL);
	if (!md)
		return 0;

	check_pgd_range(vma, vma->vm_start, vma->vm_end,
		    &node_online_map, MPOL_MF_STATS, md);

	if (md->pages) {
		mpol_to_str(buffer, sizeof(buffer),
			    get_vma_policy(task, vma, vma->vm_start));

		seq_printf(m, "%08lx %s pages=%lu mapped=%lu maxref=%lu",
			   vma->vm_start, buffer, md->pages,
			   md->mapped, md->mapcount_max);

		if (md->anon)
			seq_printf(m," anon=%lu",md->anon);

		for_each_online_node(n)
			if (md->node[n])
				seq_printf(m, " N%d=%lu", n, md->node[n]);

		seq_putc(m, '\n');
	}
	kfree(md);

	if (m->count < m->size)
		m->version = (vma != get_gate_vma(task)) ? vma->vm_start : 0;
	return 0;
}