summaryrefslogtreecommitdiffstats
path: root/kernel/power/snapshot.c
blob: fc53ad06812843d346a777711b97a7f4698c76e3 (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
/*
 * linux/kernel/power/snapshot.c
 *
 * This file provides system snapshot/restore functionality for swsusp.
 *
 * Copyright (C) 1998-2005 Pavel Machek <pavel@suse.cz>
 * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
 *
 * This file is released under the GPLv2.
 *
 */

#include <linux/version.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/suspend.h>
#include <linux/smp_lock.h>
#include <linux/delay.h>
#include <linux/bitops.h>
#include <linux/spinlock.h>
#include <linux/kernel.h>
#include <linux/pm.h>
#include <linux/device.h>
#include <linux/bootmem.h>
#include <linux/syscalls.h>
#include <linux/console.h>
#include <linux/highmem.h>

#include <asm/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/io.h>

#include "power.h"

/* List of PBEs needed for restoring the pages that were allocated before
 * the suspend and included in the suspend image, but have also been
 * allocated by the "resume" kernel, so their contents cannot be written
 * directly to their "original" page frames.
 */
struct pbe *restore_pblist;

/* Pointer to an auxiliary buffer (1 page) */
static void *buffer;

/**
 *	@safe_needed - on resume, for storing the PBE list and the image,
 *	we can only use memory pages that do not conflict with the pages
 *	used before suspend.  The unsafe pages have PageNosaveFree set
 *	and we count them using unsafe_pages.
 *
 *	Each allocated image page is marked as PageNosave and PageNosaveFree
 *	so that swsusp_free() can release it.
 */

#define PG_ANY		0
#define PG_SAFE		1
#define PG_UNSAFE_CLEAR	1
#define PG_UNSAFE_KEEP	0

static unsigned int allocated_unsafe_pages;

static void *get_image_page(gfp_t gfp_mask, int safe_needed)
{
	void *res;

	res = (void *)get_zeroed_page(gfp_mask);
	if (safe_needed)
		while (res && PageNosaveFree(virt_to_page(res))) {
			/* The page is unsafe, mark it for swsusp_free() */
			SetPageNosave(virt_to_page(res));
			allocated_unsafe_pages++;
			res = (void *)get_zeroed_page(gfp_mask);
		}
	if (res) {
		SetPageNosave(virt_to_page(res));
		SetPageNosaveFree(virt_to_page(res));
	}
	return res;
}

unsigned long get_safe_page(gfp_t gfp_mask)
{
	return (unsigned long)get_image_page(gfp_mask, PG_SAFE);
}

static struct page *alloc_image_page(gfp_t gfp_mask)
{
	struct page *page;

	page = alloc_page(gfp_mask);
	if (page) {
		SetPageNosave(page);
		SetPageNosaveFree(page);
	}
	return page;
}

/**
 *	free_image_page - free page represented by @addr, allocated with
 *	get_image_page (page flags set by it must be cleared)
 */

static inline void free_image_page(void *addr, int clear_nosave_free)
{
	struct page *page;

	BUG_ON(!virt_addr_valid(addr));

	page = virt_to_page(addr);

	ClearPageNosave(page);
	if (clear_nosave_free)
		ClearPageNosaveFree(page);

	__free_page(page);
}

/* struct linked_page is used to build chains of pages */

#define LINKED_PAGE_DATA_SIZE	(PAGE_SIZE - sizeof(void *))

struct linked_page {
	struct linked_page *next;
	char data[LINKED_PAGE_DATA_SIZE];
} __attribute__((packed));

static inline void
free_list_of_pages(struct linked_page *list, int clear_page_nosave)
{
	while (list) {
		struct linked_page *lp = list->next;

		free_image_page(list, clear_page_nosave);
		list = lp;
	}
}

/**
  *	struct chain_allocator is used for allocating small objects out of
  *	a linked list of pages called 'the chain'.
  *
  *	The chain grows each time when there is no room for a new object in
  *	the current page.  The allocated objects cannot be freed individually.
  *	It is only possible to free them all at once, by freeing the entire
  *	chain.
  *
  *	NOTE: The chain allocator may be inefficient if the allocated objects
  *	are not much smaller than PAGE_SIZE.
  */

struct chain_allocator {
	struct linked_page *chain;	/* the chain */
	unsigned int used_space;	/* total size of objects allocated out
					 * of the current page
					 */
	gfp_t gfp_mask;		/* mask for allocating pages */
	int safe_needed;	/* if set, only "safe" pages are allocated */
};

static void
chain_init(struct chain_allocator *ca, gfp_t gfp_mask, int safe_needed)
{
	ca->chain = NULL;
	ca->used_space = LINKED_PAGE_DATA_SIZE;
	ca->gfp_mask = gfp_mask;
	ca->safe_needed = safe_needed;
}

static void *chain_alloc(struct chain_allocator *ca, unsigned int size)
{
	void *ret;

	if (LINKED_PAGE_DATA_SIZE - ca->used_space < size) {
		struct linked_page *lp;

		lp = get_image_page(ca->gfp_mask, ca->safe_needed);
		if (!lp)
			return NULL;

		lp->next = ca->chain;
		ca->chain = lp;
		ca->used_space = 0;
	}
	ret = ca->chain->data + ca->used_space;
	ca->used_space += size;
	return ret;
}

static void chain_free(struct chain_allocator *ca, int clear_page_nosave)
{
	free_list_of_pages(ca->chain, clear_page_nosave);
	memset(ca, 0, sizeof(struct chain_allocator));
}

/**
 *	Data types related to memory bitmaps.
 *
 *	Memory bitmap is a structure consiting of many linked lists of
 *	objects.  The main list's elements are of type struct zone_bitmap
 *	and each of them corresonds to one zone.  For each zone bitmap
 *	object there is a list of objects of type struct bm_block that
 *	represent each blocks of bit chunks in which information is
 *	stored.
 *
 *	struct memory_bitmap contains a pointer to the main list of zone
 *	bitmap objects, a struct bm_position used for browsing the bitmap,
 *	and a pointer to the list of pages used for allocating all of the
 *	zone bitmap objects and bitmap block objects.
 *
 *	NOTE: It has to be possible to lay out the bitmap in memory
 *	using only allocations of order 0.  Additionally, the bitmap is
 *	designed to work with arbitrary number of zones (this is over the
 *	top for now, but let's avoid making unnecessary assumptions ;-).
 *
 *	struct zone_bitmap contains a pointer to a list of bitmap block
 *	objects and a pointer to the bitmap block object that has been
 *	most recently used for setting bits.  Additionally, it contains the
 *	pfns that correspond to the start and end of the represented zone.
 *
 *	struct bm_block contains a pointer to the memory page in which
 *	information is stored (in the form of a block of bit chunks
 *	of type unsigned long each).  It also contains the pfns that
 *	correspond to the start and end of the represented memory area and
 *	the number of bit chunks in the block.
 *
 *	NOTE: Memory bitmaps are used for two types of operations only:
 *	"set a bit" and "find the next bit set".  Moreover, the searching
 *	is always carried out after all of the "set a bit" operations
 *	on given bitmap.
 */

#define BM_END_OF_MAP	(~0UL)

#define BM_CHUNKS_PER_BLOCK	(PAGE_SIZE / sizeof(long))
#define BM_BITS_PER_CHUNK	(sizeof(long) << 3)
#define BM_BITS_PER_BLOCK	(PAGE_SIZE << 3)

struct bm_block {
	struct bm_block *next;		/* next element of the list */
	unsigned long start_pfn;	/* pfn represented by the first bit */
	unsigned long end_pfn;	/* pfn represented by the last bit plus 1 */
	unsigned int size;	/* number of bit chunks */
	unsigned long *data;	/* chunks of bits representing pages */
};

struct zone_bitmap {
	struct zone_bitmap *next;	/* next element of the list */
	unsigned long start_pfn;	/* minimal pfn in this zone */
	unsigned long end_pfn;		/* maximal pfn in this zone plus 1 */
	struct bm_block *bm_blocks;	/* list of bitmap blocks */
	struct bm_block *cur_block;	/* recently used bitmap block */
};

/* strcut bm_position is used for browsing memory bitmaps */

struct bm_position {
	struct zone_bitmap *zone_bm;
	struct bm_block *block;
	int chunk;
	int bit;
};

struct memory_bitmap {
	struct zone_bitmap *zone_bm_list;	/* list of zone bitmaps */
	struct linked_page *p_list;	/* list of pages used to store zone
					 * bitmap objects and bitmap block
					 * objects
					 */
	struct bm_position cur;	/* most recently used bit position */
};

/* Functions that operate on memory bitmaps */

static inline void memory_bm_reset_chunk(struct memory_bitmap *bm)
{
	bm->cur.chunk = 0;
	bm->cur.bit = -1;
}

static void memory_bm_position_reset(struct memory_bitmap *bm)
{
	struct zone_bitmap *zone_bm;

	zone_bm = bm->zone_bm_list;
	bm->cur.zone_bm = zone_bm;
	bm->cur.block = zone_bm->bm_blocks;
	memory_bm_reset_chunk(bm);
}

static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free);

/**
 *	create_bm_block_list - create a list of block bitmap objects
 */

static inline struct bm_block *
create_bm_block_list(unsigned int nr_blocks, struct chain_allocator *ca)
{
	struct bm_block *bblist = NULL;

	while (nr_blocks-- > 0) {
		struct bm_block *bb;

		bb = chain_alloc(ca, sizeof(struct bm_block));
		if (!bb)
			return NULL;

		bb->next = bblist;
		bblist = bb;
	}
	return bblist;
}

/**
 *	create_zone_bm_list - create a list of zone bitmap objects
 */

static inline struct zone_bitmap *
create_zone_bm_list(unsigned int nr_zones, struct chain_allocator *ca)
{
	struct zone_bitmap *zbmlist = NULL;

	while (nr_zones-- > 0) {
		struct zone_bitmap *zbm;

		zbm = chain_alloc(ca, sizeof(struct zone_bitmap));
		if (!zbm)
			return NULL;

		zbm->next = zbmlist;
		zbmlist = zbm;
	}
	return zbmlist;
}

/**
  *	memory_bm_create - allocate memory for a memory bitmap
  */

static int
memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed)
{
	struct chain_allocator ca;
	struct zone *zone;
	struct zone_bitmap *zone_bm;
	struct bm_block *bb;
	unsigned int nr;

	chain_init(&ca, gfp_mask, safe_needed);

	/* Compute the number of zones */
	nr = 0;
	for_each_zone(zone)
		if (populated_zone(zone))
			nr++;

	/* Allocate the list of zones bitmap objects */
	zone_bm = create_zone_bm_list(nr, &ca);
	bm->zone_bm_list = zone_bm;
	if (!zone_bm) {
		chain_free(&ca, PG_UNSAFE_CLEAR);
		return -ENOMEM;
	}

	/* Initialize the zone bitmap objects */
	for_each_zone(zone) {
		unsigned long pfn;

		if (!populated_zone(zone))
			continue;

		zone_bm->start_pfn = zone->zone_start_pfn;
		zone_bm->end_pfn = zone->zone_start_pfn + zone->spanned_pages;
		/* Allocate the list of bitmap block objects */
		nr = DIV_ROUND_UP(zone->spanned_pages, BM_BITS_PER_BLOCK);
		bb = create_bm_block_list(nr, &ca);
		zone_bm->bm_blocks = bb;
		zone_bm->cur_block = bb;
		if (!bb)
			goto Free;

		nr = zone->spanned_pages;
		pfn = zone->zone_start_pfn;
		/* Initialize the bitmap block objects */
		while (bb) {
			unsigned long *ptr;

			ptr = get_image_page(gfp_mask, safe_needed);
			bb->data = ptr;
			if (!ptr)
				goto Free;

			bb->start_pfn = pfn;
			if (nr >= BM_BITS_PER_BLOCK) {
				pfn += BM_BITS_PER_BLOCK;
				bb->size = BM_CHUNKS_PER_BLOCK;
				nr -= BM_BITS_PER_BLOCK;
			} else {
				/* This is executed only once in the loop */
				pfn += nr;
				bb->size = DIV_ROUND_UP(nr, BM_BITS_PER_CHUNK);
			}
			bb->end_pfn = pfn;
			bb = bb->next;
		}
		zone_bm = zone_bm->next;
	}
	bm->p_list = ca.chain;
	memory_bm_position_reset(bm);
	return 0;

 Free:
	bm->p_list = ca.chain;
	memory_bm_free(bm, PG_UNSAFE_CLEAR);
	return -ENOMEM;
}

/**
  *	memory_bm_free - free memory occupied by the memory bitmap @bm
  */

static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free)
{
	struct zone_bitmap *zone_bm;

	/* Free the list of bit blocks for each zone_bitmap object */
	zone_bm = bm->zone_bm_list;
	while (zone_bm) {
		struct bm_block *bb;

		bb = zone_bm->bm_blocks;
		while (bb) {
			if (bb->data)
				free_image_page(bb->data, clear_nosave_free);
			bb = bb->next;
		}
		zone_bm = zone_bm->next;
	}
	free_list_of_pages(bm->p_list, clear_nosave_free);
	bm->zone_bm_list = NULL;
}

/**
 *	memory_bm_set_bit - set the bit in the bitmap @bm that corresponds
 *	to given pfn.  The cur_zone_bm member of @bm and the cur_block member
 *	of @bm->cur_zone_bm are updated.
 *
 *	If the bit cannot be set, the function returns -EINVAL .
 */

static int
memory_bm_set_bit(struct memory_bitmap *bm, unsigned long pfn)
{
	struct zone_bitmap *zone_bm;
	struct bm_block *bb;

	/* Check if the pfn is from the current zone */
	zone_bm = bm->cur.zone_bm;
	if (pfn < zone_bm->start_pfn || pfn >= zone_bm->end_pfn) {
		zone_bm = bm->zone_bm_list;
		/* We don't assume that the zones are sorted by pfns */
		while (pfn < zone_bm->start_pfn || pfn >= zone_bm->end_pfn) {
			zone_bm = zone_bm->next;
			if (unlikely(!zone_bm))
				return -EINVAL;
		}
		bm->cur.zone_bm = zone_bm;
	}
	/* Check if the pfn corresponds to the current bitmap block */
	bb = zone_bm->cur_block;
	if (pfn < bb->start_pfn)
		bb = zone_bm->bm_blocks;

	while (pfn >= bb->end_pfn) {
		bb = bb->next;
		if (unlikely(!bb))
			return -EINVAL;
	}
	zone_bm->cur_block = bb;
	pfn -= bb->start_pfn;
	set_bit(pfn % BM_BITS_PER_CHUNK, bb->data + pfn / BM_BITS_PER_CHUNK);
	return 0;
}

/* Two auxiliary functions for memory_bm_next_pfn */

/* Find the first set bit in the given chunk, if there is one */

static inline int next_bit_in_chunk(int bit, unsigned long *chunk_p)
{
	bit++;
	while (bit < BM_BITS_PER_CHUNK) {
		if (test_bit(bit, chunk_p))
			return bit;

		bit++;
	}
	return -1;
}

/* Find a chunk containing some bits set in given block of bits */

static inline int next_chunk_in_block(int n, struct bm_block *bb)
{
	n++;
	while (n < bb->size) {
		if (bb->data[n])
			return n;

		n++;
	}
	return -1;
}

/**
 *	memory_bm_next_pfn - find the pfn that corresponds to the next set bit
 *	in the bitmap @bm.  If the pfn cannot be found, BM_END_OF_MAP is
 *	returned.
 *
 *	It is required to run memory_bm_position_reset() before the first call to
 *	this function.
 */

static unsigned long memory_bm_next_pfn(struct memory_bitmap *bm)
{
	struct zone_bitmap *zone_bm;
	struct bm_block *bb;
	int chunk;
	int bit;

	do {
		bb = bm->cur.block;
		do {
			chunk = bm->cur.chunk;
			bit = bm->cur.bit;
			do {
				bit = next_bit_in_chunk(bit, bb->data + chunk);
				if (bit >= 0)
					goto Return_pfn;

				chunk = next_chunk_in_block(chunk, bb);
				bit = -1;
			} while (chunk >= 0);
			bb = bb->next;
			bm->cur.block = bb;
			memory_bm_reset_chunk(bm);
		} while (bb);
		zone_bm = bm->cur.zone_bm->next;
		if (zone_bm) {
			bm->cur.zone_bm = zone_bm;
			bm->cur.block = zone_bm->bm_blocks;
			memory_bm_reset_chunk(bm);
		}
	} while (zone_bm);
	memory_bm_position_reset(bm);
	return BM_END_OF_MAP;

 Return_pfn:
	bm->cur.chunk = chunk;
	bm->cur.bit = bit;
	return bb->start_pfn + chunk * BM_BITS_PER_CHUNK + bit;
}

/**
 *	snapshot_additional_pages - estimate the number of additional pages
 *	be needed for setting up the suspend image data structures for given
 *	zone (usually the returned value is greater than the exact number)
 */

unsigned int snapshot_additional_pages(struct zone *zone)
{
	unsigned int res;

	res = DIV_ROUND_UP(zone->spanned_pages, BM_BITS_PER_BLOCK);
	res += DIV_ROUND_UP(res * sizeof(struct bm_block), PAGE_SIZE);
	return 2 * res;
}

#ifdef CONFIG_HIGHMEM
/**
 *	count_free_highmem_pages - compute the total number of free highmem
 *	pages, system-wide.
 */

static unsigned int count_free_highmem_pages(void)
{
	struct zone *zone;
	unsigned int cnt = 0;

	for_each_zone(zone)
		if (populated_zone(zone) && is_highmem(zone))
			cnt += zone_page_state(zone, NR_FREE_PAGES);

	return cnt;
}

/**
 *	saveable_highmem_page - Determine whether a highmem page should be
 *	included in the suspend image.
 *
 *	We should save the page if it isn't Nosave or NosaveFree, or Reserved,
 *	and it isn't a part of a free chunk of pages.
 */

static struct page *saveable_highmem_page(unsigned long pfn)
{
	struct page *page;

	if (!pfn_valid(pfn))
		return NULL;

	page = pfn_to_page(pfn);

	BUG_ON(!PageHighMem(page));

	if (PageNosave(page) || PageReserved(page) || PageNosaveFree(page))
		return NULL;

	return page;
}

/**
 *	count_highmem_pages - compute the total number of saveable highmem
 *	pages.
 */

unsigned int count_highmem_pages(void)
{
	struct zone *zone;
	unsigned int n = 0;

	for_each_zone(zone) {
		unsigned long pfn, max_zone_pfn;

		if (!is_highmem(zone))
			continue;

		mark_free_pages(zone);
		max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
			if (saveable_highmem_page(pfn))
				n++;
	}
	return n;
}
#else
static inline void *saveable_highmem_page(unsigned long pfn) { return NULL; }
static inline unsigned int count_highmem_pages(void) { return 0; }
#endif /* CONFIG_HIGHMEM */

/**
 *	pfn_is_nosave - check if given pfn is in the 'nosave' section
 */

static inline int pfn_is_nosave(unsigned long pfn)
{
	unsigned long nosave_begin_pfn = __pa(&__nosave_begin) >> PAGE_SHIFT;
	unsigned long nosave_end_pfn = PAGE_ALIGN(__pa(&__nosave_end)) >> PAGE_SHIFT;
	return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn);
}

/**
 *	saveable - Determine whether a non-highmem page should be included in
 *	the suspend image.
 *
 *	We should save the page if it isn't Nosave, and is not in the range
 *	of pages statically defined as 'unsaveable', and it isn't a part of
 *	a free chunk of pages.
 */

static struct page *saveable_page(unsigned long pfn)
{
	struct page *page;

	if (!pfn_valid(pfn))
		return NULL;

	page = pfn_to_page(pfn);

	BUG_ON(PageHighMem(page));

	if (PageNosave(page) || PageNosaveFree(page))
		return NULL;

	if (PageReserved(page) && pfn_is_nosave(pfn))
		return NULL;

	return page;
}

/**
 *	count_data_pages - compute the total number of saveable non-highmem
 *	pages.
 */

unsigned int count_data_pages(void)
{
	struct zone *zone;
	unsigned long pfn, max_zone_pfn;
	unsigned int n = 0;

	for_each_zone(zone) {
		if (is_highmem(zone))
			continue;

		mark_free_pages(zone);
		max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
			if(saveable_page(pfn))
				n++;
	}
	return n;
}

/* This is needed, because copy_page and memcpy are not usable for copying
 * task structs.
 */
static inline void do_copy_page(long *dst, long *src)
{
	int n;

	for (n = PAGE_SIZE / sizeof(long); n; n--)
		*dst++ = *src++;
}

#ifdef CONFIG_HIGHMEM
static inline struct page *
page_is_saveable(struct zone *zone, unsigned long pfn)
{
	return is_highmem(zone) ?
			saveable_highmem_page(pfn) : saveable_page(pfn);
}

static inline void
copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
{
	struct page *s_page, *d_page;
	void *src, *dst;

	s_page = pfn_to_page(src_pfn);
	d_page = pfn_to_page(dst_pfn);
	if (PageHighMem(s_page)) {
		src = kmap_atomic(s_page, KM_USER0);
		dst = kmap_atomic(d_page, KM_USER1);
		do_copy_page(dst, src);
		kunmap_atomic(src, KM_USER0);
		kunmap_atomic(dst, KM_USER1);
	} else {
		src = page_address(s_page);
		if (PageHighMem(d_page)) {
			/* Page pointed to by src may contain some kernel
			 * data modified by kmap_atomic()
			 */
			do_copy_page(buffer, src);
			dst = kmap_atomic(pfn_to_page(dst_pfn), KM_USER0);
			memcpy(dst, buffer, PAGE_SIZE);
			kunmap_atomic(dst, KM_USER0);
		} else {
			dst = page_address(d_page);
			do_copy_page(dst, src);
		}
	}
}
#else
#define page_is_saveable(zone, pfn)	saveable_page(pfn)

static inline void
copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
{
	do_copy_page(page_address(pfn_to_page(dst_pfn)),
			page_address(pfn_to_page(src_pfn)));
}
#endif /* CONFIG_HIGHMEM */

static void
copy_data_pages(struct memory_bitmap *copy_bm, struct memory_bitmap *orig_bm)
{
	struct zone *zone;
	unsigned long pfn;

	for_each_zone(zone) {
		unsigned long max_zone_pfn;

		mark_free_pages(zone);
		max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
			if (page_is_saveable(zone, pfn))
				memory_bm_set_bit(orig_bm, pfn);
	}
	memory_bm_position_reset(orig_bm);
	memory_bm_position_reset(copy_bm);
	do {
		pfn = memory_bm_next_pfn(orig_bm);
		if (likely(pfn != BM_END_OF_MAP))
			copy_data_page(memory_bm_next_pfn(copy_bm), pfn);
	} while (pfn != BM_END_OF_MAP);
}

/* Total number of image pages */
static unsigned int nr_copy_pages;
/* Number of pages needed for saving the original pfns of the image pages */
static unsigned int nr_meta_pages;

/**
 *	swsusp_free - free pages allocated for the suspend.
 *
 *	Suspend pages are alocated before the atomic copy is made, so we
 *	need to release them after the resume.
 */

void swsusp_free(void)
{
	struct zone *zone;
	unsigned long pfn, max_zone_pfn;

	for_each_zone(zone) {
		max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
			if (pfn_valid(pfn)) {
				struct page *page = pfn_to_page(pfn);

				if (PageNosave(page) && PageNosaveFree(page)) {
					ClearPageNosave(page);
					ClearPageNosaveFree(page);
					__free_page(page);
				}
			}
	}
	nr_copy_pages = 0;
	nr_meta_pages = 0;
	restore_pblist = NULL;
	buffer = NULL;
}

#ifdef CONFIG_HIGHMEM
/**
  *	count_pages_for_highmem - compute the number of non-highmem pages
  *	that will be necessary for creating copies of highmem pages.
  */

static unsigned int count_pages_for_highmem(unsigned int nr_highmem)
{
	unsigned int free_highmem = count_free_highmem_pages();

	if (free_highmem >= nr_highmem)
		nr_highmem = 0;
	else
		nr_highmem -= free_highmem;

	return nr_highmem;
}
#else
static unsigned int
count_pages_for_highmem(unsigned int nr_highmem) { return 0; }
#endif /* CONFIG_HIGHMEM */

/**
 *	enough_free_mem - Make sure we have enough free memory for the
 *	snapshot image.
 */

static int enough_free_mem(unsigned int nr_pages, unsigned int nr_highmem)
{
	struct zone *zone;
	unsigned int free = 0, meta = 0;

	for_each_zone(zone) {
		meta += snapshot_additional_pages(zone);
		if (!is_highmem(zone))
			free += zone_page_state(zone, NR_FREE_PAGES);
	}

	nr_pages += count_pages_for_highmem(nr_highmem);
	pr_debug("swsusp: Normal pages needed: %u + %u + %u, available pages: %u\n",
		nr_pages, PAGES_FOR_IO, meta, free);

	return free > nr_pages + PAGES_FOR_IO + meta;
}

#ifdef CONFIG_HIGHMEM
/**
 *	get_highmem_buffer - if there are some highmem pages in the suspend
 *	image, we may need the buffer to copy them and/or load their data.
 */

static inline int get_highmem_buffer(int safe_needed)
{
	buffer = get_image_page(GFP_ATOMIC | __GFP_COLD, safe_needed);
	return buffer ? 0 : -ENOMEM;
}

/**
 *	alloc_highmem_image_pages - allocate some highmem pages for the image.
 *	Try to allocate as many pages as needed, but if the number of free
 *	highmem pages is lesser than that, allocate them all.
 */

static inline unsigned int
alloc_highmem_image_pages(struct memory_bitmap *bm, unsigned int nr_highmem)
{
	unsigned int to_alloc = count_free_highmem_pages();

	if (to_alloc > nr_highmem)
		to_alloc = nr_highmem;

	nr_highmem -= to_alloc;
	while (to_alloc-- > 0) {
		struct page *page;

		page = alloc_image_page(__GFP_HIGHMEM);
		memory_bm_set_bit(bm, page_to_pfn(page));
	}
	return nr_highmem;
}
#else
static inline int get_highmem_buffer(int safe_needed) { return 0; }

static inline unsigned int
alloc_highmem_image_pages(struct memory_bitmap *bm, unsigned int n) { return 0; }
#endif /* CONFIG_HIGHMEM */

/**
 *	swsusp_alloc - allocate memory for the suspend image
 *
 *	We first try to allocate as many highmem pages as there are
 *	saveable highmem pages in the system.  If that fails, we allocate
 *	non-highmem pages for the copies of the remaining highmem ones.
 *
 *	In this approach it is likely that the copies of highmem pages will
 *	also be located in the high memory, because of the way in which
 *	copy_data_pages() works.
 */

static int
swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm,
		unsigned int nr_pages, unsigned int nr_highmem)
{
	int error;

	error = memory_bm_create(orig_bm, GFP_ATOMIC | __GFP_COLD, PG_ANY);
	if (error)
		goto Free;

	error = memory_bm_create(copy_bm, GFP_ATOMIC | __GFP_COLD, PG_ANY);
	if (error)
		goto Free;

	if (nr_highmem > 0) {
		error = get_highmem_buffer(PG_ANY);
		if (error)
			goto Free;

		nr_pages += alloc_highmem_image_pages(copy_bm, nr_highmem);
	}
	while (nr_pages-- > 0) {
		struct page *page = alloc_image_page(GFP_ATOMIC | __GFP_COLD);

		if (!page)
			goto Free;

		memory_bm_set_bit(copy_bm, page_to_pfn(page));
	}
	return 0;

 Free:
	swsusp_free();
	return -ENOMEM;
}

/* Memory bitmap used for marking saveable pages (during suspend) or the
 * suspend image pages (during resume)
 */
static struct memory_bitmap orig_bm;
/* Memory bitmap used on suspend for marking allocated pages that will contain
 * the copies of saveable pages.  During resume it is initially used for
 * marking the suspend image pages, but then its set bits are duplicated in
 * @orig_bm and it is released.  Next, on systems with high memory, it may be
 * used for marking "safe" highmem pages, but it has to be reinitialized for
 * this purpose.
 */
static struct memory_bitmap copy_bm;

asmlinkage int swsusp_save(void)
{
	unsigned int nr_pages, nr_highmem;

	printk("swsusp: critical section: \n");

	drain_local_pages();
	nr_pages = count_data_pages();
	nr_highmem = count_highmem_pages();
	printk("swsusp: Need to copy %u pages\n", nr_pages + nr_highmem);

	if (!enough_free_mem(nr_pages, nr_highmem)) {
		printk(KERN_ERR "swsusp: Not enough free memory\n");
		return -ENOMEM;
	}

	if (swsusp_alloc(&orig_bm, &copy_bm, nr_pages, nr_highmem)) {
		printk(KERN_ERR "swsusp: Memory allocation failed\n");
		return -ENOMEM;
	}

	/* During allocating of suspend pagedir, new cold pages may appear.
	 * Kill them.
	 */
	drain_local_pages();
	copy_data_pages(&copy_bm, &orig_bm);

	/*
	 * End of critical section. From now on, we can write to memory,
	 * but we should not touch disk. This specially means we must _not_
	 * touch swap space! Except we must write out our image of course.
	 */

	nr_pages += nr_highmem;
	nr_copy_pages = nr_pages;
	nr_meta_pages = DIV_ROUND_UP(nr_pages * sizeof(long), PAGE_SIZE);

	printk("swsusp: critical section/: done (%d pages copied)\n", nr_pages);

	return 0;
}

static void init_header(struct swsusp_info *info)
{
	memset(info, 0, sizeof(struct swsusp_info));
	info->version_code = LINUX_VERSION_CODE;
	info->num_physpages = num_physpages;
	memcpy(&info->uts, init_utsname(), sizeof(struct new_utsname));
	info->cpus = num_online_cpus();
	info->image_pages = nr_copy_pages;
	info->pages = nr_copy_pages + nr_meta_pages + 1;
	info->size = info->pages;
	info->size <<= PAGE_SHIFT;
}

/**
 *	pack_pfns - pfns corresponding to the set bits found in the bitmap @bm
 *	are stored in the array @buf[] (1 page at a time)
 */

static inline void
pack_pfns(unsigned long *buf, struct memory_bitmap *bm)
{
	int j;

	for (j = 0; j < PAGE_SIZE / sizeof(long); j++) {
		buf[j] = memory_bm_next_pfn(bm);
		if (unlikely(buf[j] == BM_END_OF_MAP))
			break;
	}
}

/**
 *	snapshot_read_next - used for reading the system memory snapshot.
 *
 *	On the first call to it @handle should point to a zeroed
 *	snapshot_handle structure.  The structure gets updated and a pointer
 *	to it should be passed to this function every next time.
 *
 *	The @count parameter should contain the number of bytes the caller
 *	wants to read from the snapshot.  It must not be zero.
 *
 *	On success the function returns a positive number.  Then, the caller
 *	is allowed to read up to the returned number of bytes from the memory
 *	location computed by the data_of() macro.  The number returned
 *	may be smaller than @count, but this only happens if the read would
 *	cross a page boundary otherwise.
 *
 *	The function returns 0 to indicate the end of data stream condition,
 *	and a negative number is returned on error.  In such cases the
 *	structure pointed to by @handle is not updated and should not be used
 *	any more.
 */

int snapshot_read_next(struct snapshot_handle *handle, size_t count)
{
	if (handle->cur > nr_meta_pages + nr_copy_pages)
		return 0;

	if (!buffer) {
		/* This makes the buffer be freed by swsusp_free() */
		buffer = get_image_page(GFP_ATOMIC, PG_ANY);
		if (!buffer)
			return -ENOMEM;
	}
	if (!handle->offset) {
		init_header((struct swsusp_info *)buffer);
		handle->buffer = buffer;
		memory_bm_position_reset(&orig_bm);
		memory_bm_position_reset(&copy_bm);
	}
	if (handle->prev < handle->cur) {
		if (handle->cur <= nr_meta_pages) {
			memset(buffer, 0, PAGE_SIZE);
			pack_pfns(buffer, &orig_bm);
		} else {
			struct page *page;

			page = pfn_to_page(memory_bm_next_pfn(&copy_bm));
			if (PageHighMem(page)) {
				/* Highmem pages are copied to the buffer,
				 * because we can't return with a kmapped
				 * highmem page (we may not be called again).
				 */
				void *kaddr;

				kaddr = kmap_atomic(page, KM_USER0);
				memcpy(buffer, kaddr, PAGE_SIZE);
				kunmap_atomic(kaddr, KM_USER0);
				handle->buffer = buffer;
			} else {
				handle->buffer = page_address(page);
			}
		}
		handle->prev = handle->cur;
	}
	handle->buf_offset = handle->cur_offset;
	if (handle->cur_offset + count >= PAGE_SIZE) {
		count = PAGE_SIZE - handle->cur_offset;
		handle->cur_offset = 0;
		handle->cur++;
	} else {
		handle->cur_offset += count;
	}
	handle->offset += count;
	return count;
}

/**
 *	mark_unsafe_pages - mark the pages that cannot be used for storing
 *	the image during resume, because they conflict with the pages that
 *	had been used before suspend
 */

static int mark_unsafe_pages(struct memory_bitmap *bm)
{
	struct zone *zone;
	unsigned long pfn, max_zone_pfn;

	/* Clear page flags */
	for_each_zone(zone) {
		max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
			if (pfn_valid(pfn))
				ClearPageNosaveFree(pfn_to_page(pfn));
	}

	/* Mark pages that correspond to the "original" pfns as "unsafe" */
	memory_bm_position_reset(bm);
	do {
		pfn = memory_bm_next_pfn(bm);
		if (likely(pfn != BM_END_OF_MAP)) {
			if (likely(pfn_valid(pfn)))
				SetPageNosaveFree(pfn_to_page(pfn));
			else
				return -EFAULT;
		}
	} while (pfn != BM_END_OF_MAP);

	allocated_unsafe_pages = 0;

	return 0;
}

static void
duplicate_memory_bitmap(struct memory_bitmap *dst, struct memory_bitmap *src)
{
	unsigned long pfn;

	memory_bm_position_reset(src);
	pfn = memory_bm_next_pfn(src);
	while (pfn != BM_END_OF_MAP) {
		memory_bm_set_bit(dst, pfn);
		pfn = memory_bm_next_pfn(src);
	}
}

static inline int check_header(struct swsusp_info *info)
{
	char *reason = NULL;

	if (info->version_code != LINUX_VERSION_CODE)
		reason = "kernel version";
	if (info->num_physpages != num_physpages)
		reason = "memory size";
	if (strcmp(info->uts.sysname,init_utsname()->sysname))
		reason = "system type";
	if (strcmp(info->uts.release,init_utsname()->release))
		reason = "kernel release";
	if (strcmp(info->uts.version,init_utsname()->version))
		reason = "version";
	if (strcmp(info->uts.machine,init_utsname()->machine))
		reason = "machine";
	if (reason) {
		printk(KERN_ERR "swsusp: Resume mismatch: %s\n", reason);
		return -EPERM;
	}
	return 0;
}

/**
 *	load header - check the image header and copy data from it
 */

static int
load_header(struct swsusp_info *info)
{
	int error;

	restore_pblist = NULL;
	error = check_header(info);
	if (!error) {
		nr_copy_pages = info->image_pages;
		nr_meta_pages = info->pages - info->image_pages - 1;
	}
	return error;
}

/**
 *	unpack_orig_pfns - for each element of @buf[] (1 page at a time) set
 *	the corresponding bit in the memory bitmap @bm
 */

static inline void
unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm)
{
	int j;

	for (j = 0; j < PAGE_SIZE / sizeof(long); j++) {
		if (unlikely(buf[j] == BM_END_OF_MAP))
			break;

		memory_bm_set_bit(bm, buf[j]);
	}
}

/* List of "safe" pages that may be used to store data loaded from the suspend
 * image
 */
static struct linked_page *safe_pages_list;

#ifdef CONFIG_HIGHMEM
/* struct highmem_pbe is used for creating the list of highmem pages that
 * should be restored atomically during the resume from disk, because the page
 * frames they have occupied before the suspend are in use.
 */
struct highmem_pbe {
	struct page *copy_page;	/* data is here now */
	struct page *orig_page;	/* data was here before the suspend */
	struct highmem_pbe *next;
};

/* List of highmem PBEs needed for restoring the highmem pages that were
 * allocated before the suspend and included in the suspend image, but have
 * also been allocated by the "resume" kernel, so their contents cannot be
 * written directly to their "original" page frames.
 */
static struct highmem_pbe *highmem_pblist;

/**
 *	count_highmem_image_pages - compute the number of highmem pages in the
 *	suspend image.  The bits in the memory bitmap @bm that correspond to the
 *	image pages are assumed to be set.
 */

static unsigned int count_highmem_image_pages(struct memory_bitmap *bm)
{
	unsigned long pfn;
	unsigned int cnt = 0;

	memory_bm_position_reset(bm);
	pfn = memory_bm_next_pfn(bm);
	while (pfn != BM_END_OF_MAP) {
		if (PageHighMem(pfn_to_page(pfn)))
			cnt++;

		pfn = memory_bm_next_pfn(bm);
	}
	return cnt;
}

/**
 *	prepare_highmem_image - try to allocate as many highmem pages as
 *	there are highmem image pages (@nr_highmem_p points to the variable
 *	containing the number of highmem image pages).  The pages that are
 *	"safe" (ie. will not be overwritten when the suspend image is
 *	restored) have the corresponding bits set in @bm (it must be
 *	unitialized).
 *
 *	NOTE: This function should not be called if there are no highmem
 *	image pages.
 */

static unsigned int safe_highmem_pages;

static struct memory_bitmap *safe_highmem_bm;

static int
prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p)
{
	unsigned int to_alloc;

	if (memory_bm_create(bm, GFP_ATOMIC, PG_SAFE))
		return -ENOMEM;

	if (get_highmem_buffer(PG_SAFE))
		return -ENOMEM;

	to_alloc = count_free_highmem_pages();
	if (to_alloc > *nr_highmem_p)
		to_alloc = *nr_highmem_p;
	else
		*nr_highmem_p = to_alloc;

	safe_highmem_pages = 0;
	while (to_alloc-- > 0) {
		struct page *page;

		page = alloc_page(__GFP_HIGHMEM);
		if (!PageNosaveFree(page)) {
			/* The page is "safe", set its bit the bitmap */
			memory_bm_set_bit(bm, page_to_pfn(page));
			safe_highmem_pages++;
		}
		/* Mark the page as allocated */
		SetPageNosave(page);
		SetPageNosaveFree(page);
	}
	memory_bm_position_reset(bm);
	safe_highmem_bm = bm;
	return 0;
}

/**
 *	get_highmem_page_buffer - for given highmem image page find the buffer
 *	that suspend_write_next() should set for its caller to write to.
 *
 *	If the page is to be saved to its "original" page frame or a copy of
 *	the page is to be made in the highmem, @buffer is returned.  Otherwise,
 *	the copy of the page is to be made in normal memory, so the address of
 *	the copy is returned.
 *
 *	If @buffer is returned, the caller of suspend_write_next() will write
 *	the page's contents to @buffer, so they will have to be copied to the
 *	right location on the next call to suspend_write_next() and it is done
 *	with the help of copy_last_highmem_page().  For this purpose, if
 *	@buffer is returned, @last_highmem page is set to the page to which
 *	the data will have to be copied from @buffer.
 */

static struct page *last_highmem_page;

static void *
get_highmem_page_buffer(struct page *page, struct chain_allocator *ca)
{
	struct highmem_pbe *pbe;
	void *kaddr;

	if (PageNosave(page) && PageNosaveFree(page)) {
		/* We have allocated the "original" page frame and we can
		 * use it directly to store the loaded page.
		 */
		last_highmem_page = page;
		return buffer;
	}
	/* The "original" page frame has not been allocated and we have to
	 * use a "safe" page frame to store the loaded page.
	 */
	pbe = chain_alloc(ca, sizeof(struct highmem_pbe));
	if (!pbe) {
		swsusp_free();
		return NULL;
	}
	pbe->orig_page = page;
	if (safe_highmem_pages > 0) {
		struct page *tmp;

		/* Copy of the page will be stored in high memory */
		kaddr = buffer;
		tmp = pfn_to_page(memory_bm_next_pfn(safe_highmem_bm));
		safe_highmem_pages--;
		last_highmem_page = tmp;
		pbe->copy_page = tmp;
	} else {
		/* Copy of the page will be stored in normal memory */
		kaddr = safe_pages_list;
		safe_pages_list = safe_pages_list->next;
		pbe->copy_page = virt_to_page(kaddr);
	}
	pbe->next = highmem_pblist;
	highmem_pblist = pbe;
	return kaddr;
}

/**
 *	copy_last_highmem_page - copy the contents of a highmem image from
 *	@buffer, where the caller of snapshot_write_next() has place them,
 *	to the right location represented by @last_highmem_page .
 */

static void copy_last_highmem_page(void)
{
	if (last_highmem_page) {
		void *dst;

		dst = kmap_atomic(last_highmem_page, KM_USER0);
		memcpy(dst, buffer, PAGE_SIZE);
		kunmap_atomic(dst, KM_USER0);
		last_highmem_page = NULL;
	}
}

static inline int last_highmem_page_copied(void)
{
	return !last_highmem_page;
}

static inline void free_highmem_data(void)
{
	if (safe_highmem_bm)
		memory_bm_free(safe_highmem_bm, PG_UNSAFE_CLEAR);

	if (buffer)
		free_image_page(buffer, PG_UNSAFE_CLEAR);
}
#else
static inline int get_safe_write_buffer(void) { return 0; }

static unsigned int
count_highmem_image_pages(struct memory_bitmap *bm) { return 0; }

static inline int
prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p)
{
	return 0;
}

static inline void *
get_highmem_page_buffer(struct page *page, struct chain_allocator *ca)
{
	return NULL;
}

static inline void copy_last_highmem_page(void) {}
static inline int last_highmem_page_copied(void) { return 1; }
static inline void free_highmem_data(void) {}
#endif /* CONFIG_HIGHMEM */

/**
 *	prepare_image - use the memory bitmap @bm to mark the pages that will
 *	be overwritten in the process of restoring the system memory state
 *	from the suspend image ("unsafe" pages) and allocate memory for the
 *	image.
 *
 *	The idea is to allocate a new memory bitmap first and then allocate
 *	as many pages as needed for the image data, but not to assign these
 *	pages to specific tasks initially.  Instead, we just mark them as
 *	allocated and create a lists of "safe" pages that will be used
 *	later.  On systems with high memory a list of "safe" highmem pages is
 *	also created.
 */

#define PBES_PER_LINKED_PAGE	(LINKED_PAGE_DATA_SIZE / sizeof(struct pbe))

static int
prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm)
{
	unsigned int nr_pages, nr_highmem;
	struct linked_page *sp_list, *lp;
	int error;

	/* If there is no highmem, the buffer will not be necessary */
	free_image_page(buffer, PG_UNSAFE_CLEAR);
	buffer = NULL;

	nr_highmem = count_highmem_image_pages(bm);
	error = mark_unsafe_pages(bm);
	if (error)
		goto Free;

	error = memory_bm_create(new_bm, GFP_ATOMIC, PG_SAFE);
	if (error)
		goto Free;

	duplicate_memory_bitmap(new_bm, bm);
	memory_bm_free(bm, PG_UNSAFE_KEEP);
	if (nr_highmem > 0) {
		error = prepare_highmem_image(bm, &nr_highmem);
		if (error)
			goto Free;
	}
	/* Reserve some safe pages for potential later use.
	 *
	 * NOTE: This way we make sure there will be enough safe pages for the
	 * chain_alloc() in get_buffer().  It is a bit wasteful, but
	 * nr_copy_pages cannot be greater than 50% of the memory anyway.
	 */
	sp_list = NULL;
	/* nr_copy_pages cannot be lesser than allocated_unsafe_pages */
	nr_pages = nr_copy_pages - nr_highmem - allocated_unsafe_pages;
	nr_pages = DIV_ROUND_UP(nr_pages, PBES_PER_LINKED_PAGE);
	while (nr_pages > 0) {
		lp = get_image_page(GFP_ATOMIC, PG_SAFE);
		if (!lp) {
			error = -ENOMEM;
			goto Free;
		}
		lp->next = sp_list;
		sp_list = lp;
		nr_pages--;
	}
	/* Preallocate memory for the image */
	safe_pages_list = NULL;
	nr_pages = nr_copy_pages - nr_highmem - allocated_unsafe_pages;
	while (nr_pages > 0) {
		lp = (struct linked_page *)get_zeroed_page(GFP_ATOMIC);
		if (!lp) {
			error = -ENOMEM;
			goto Free;
		}
		if (!PageNosaveFree(virt_to_page(lp))) {
			/* The page is "safe", add it to the list */
			lp->next = safe_pages_list;
			safe_pages_list = lp;
		}
		/* Mark the page as allocated */
		SetPageNosave(virt_to_page(lp));
		SetPageNosaveFree(virt_to_page(lp));
		nr_pages--;
	}
	/* Free the reserved safe pages so that chain_alloc() can use them */
	while (sp_list) {
		lp = sp_list->next;
		free_image_page(sp_list, PG_UNSAFE_CLEAR);
		sp_list = lp;
	}
	return 0;

 Free:
	swsusp_free();
	return error;
}

/**
 *	get_buffer - compute the address that snapshot_write_next() should
 *	set for its caller to write to.
 */

static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca)
{
	struct pbe *pbe;
	struct page *page = pfn_to_page(memory_bm_next_pfn(bm));

	if (PageHighMem(page))
		return get_highmem_page_buffer(page, ca);

	if (PageNosave(page) && PageNosaveFree(page))
		/* We have allocated the "original" page frame and we can
		 * use it directly to store the loaded page.
		 */
		return page_address(page);

	/* The "original" page frame has not been allocated and we have to
	 * use a "safe" page frame to store the loaded page.
	 */
	pbe = chain_alloc(ca, sizeof(struct pbe));
	if (!pbe) {
		swsusp_free();
		return NULL;
	}
	pbe->orig_address = page_address(page);
	pbe->address = safe_pages_list;
	safe_pages_list = safe_pages_list->next;
	pbe->next = restore_pblist;
	restore_pblist = pbe;
	return pbe->address;
}

/**
 *	snapshot_write_next - used for writing the system memory snapshot.
 *
 *	On the first call to it @handle should point to a zeroed
 *	snapshot_handle structure.  The structure gets updated and a pointer
 *	to it should be passed to this function every next time.
 *
 *	The @count parameter should contain the number of bytes the caller
 *	wants to write to the image.  It must not be zero.
 *
 *	On success the function returns a positive number.  Then, the caller
 *	is allowed to write up to the returned number of bytes to the memory
 *	location computed by the data_of() macro.  The number returned
 *	may be smaller than @count, but this only happens if the write would
 *	cross a page boundary otherwise.
 *
 *	The function returns 0 to indicate the "end of file" condition,
 *	and a negative number is returned on error.  In such cases the
 *	structure pointed to by @handle is not updated and should not be used
 *	any more.
 */

int snapshot_write_next(struct snapshot_handle *handle, size_t count)
{
	static struct chain_allocator ca;
	int error = 0;

	/* Check if we have already loaded the entire image */
	if (handle->prev && handle->cur > nr_meta_pages + nr_copy_pages)
		return 0;

	if (handle->offset == 0) {
		if (!buffer)
			/* This makes the buffer be freed by swsusp_free() */
			buffer = get_image_page(GFP_ATOMIC, PG_ANY);

		if (!buffer)
			return -ENOMEM;

		handle->buffer = buffer;
	}
	handle->sync_read = 1;
	if (handle->prev < handle->cur) {
		if (handle->prev == 0) {
			error = load_header(buffer);
			if (error)
				return error;

			error = memory_bm_create(&copy_bm, GFP_ATOMIC, PG_ANY);
			if (error)
				return error;

		} else if (handle->prev <= nr_meta_pages) {
			unpack_orig_pfns(buffer, &copy_bm);
			if (handle->prev == nr_meta_pages) {
				error = prepare_image(&orig_bm, &copy_bm);
				if (error)
					return error;

				chain_init(&ca, GFP_ATOMIC, PG_SAFE);
				memory_bm_position_reset(&orig_bm);
				restore_pblist = NULL;
				handle->buffer = get_buffer(&orig_bm, &ca);
				handle->sync_read = 0;
				if (!handle->buffer)
					return -ENOMEM;
			}
		} else {
			copy_last_highmem_page();
			handle->buffer = get_buffer(&orig_bm, &ca);
			if (handle->buffer != buffer)
				handle->sync_read = 0;
		}
		handle->prev = handle->cur;
	}
	handle->buf_offset = handle->cur_offset;
	if (handle->cur_offset + count >= PAGE_SIZE) {
		count = PAGE_SIZE - handle->cur_offset;
		handle->cur_offset = 0;
		handle->cur++;
	} else {
		handle->cur_offset += count;
	}
	handle->offset += count;
	return count;
}

/**
 *	snapshot_write_finalize - must be called after the last call to
 *	snapshot_write_next() in case the last page in the image happens
 *	to be a highmem page and its contents should be stored in the
 *	highmem.  Additionally, it releases the memory that will not be
 *	used any more.
 */

void snapshot_write_finalize(struct snapshot_handle *handle)
{
	copy_last_highmem_page();
	/* Free only if we have loaded the image entirely */
	if (handle->prev && handle->cur > nr_meta_pages + nr_copy_pages) {
		memory_bm_free(&orig_bm, PG_UNSAFE_CLEAR);
		free_highmem_data();
	}
}

int snapshot_image_loaded(struct snapshot_handle *handle)
{
	return !(!nr_copy_pages || !last_highmem_page_copied() ||
			handle->cur <= nr_meta_pages + nr_copy_pages);
}

#ifdef CONFIG_HIGHMEM
/* Assumes that @buf is ready and points to a "safe" page */
static inline void
swap_two_pages_data(struct page *p1, struct page *p2, void *buf)
{
	void *kaddr1, *kaddr2;

	kaddr1 = kmap_atomic(p1, KM_USER0);
	kaddr2 = kmap_atomic(p2, KM_USER1);
	memcpy(buf, kaddr1, PAGE_SIZE);
	memcpy(kaddr1, kaddr2, PAGE_SIZE);
	memcpy(kaddr2, buf, PAGE_SIZE);
	kunmap_atomic(kaddr1, KM_USER0);
	kunmap_atomic(kaddr2, KM_USER1);
}

/**
 *	restore_highmem - for each highmem page that was allocated before
 *	the suspend and included in the suspend image, and also has been
 *	allocated by the "resume" kernel swap its current (ie. "before
 *	resume") contents with the previous (ie. "before suspend") one.
 *
 *	If the resume eventually fails, we can call this function once
 *	again and restore the "before resume" highmem state.
 */

int restore_highmem(void)
{
	struct highmem_pbe *pbe = highmem_pblist;
	void *buf;

	if (!pbe)
		return 0;

	buf = get_image_page(GFP_ATOMIC, PG_SAFE);
	if (!buf)
		return -ENOMEM;

	while (pbe) {
		swap_two_pages_data(pbe->copy_page, pbe->orig_page, buf);
		pbe = pbe->next;
	}
	free_image_page(buf, PG_UNSAFE_CLEAR);
	return 0;
}
#endif /* CONFIG_HIGHMEM */