aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/power/swsusp.c
blob: c05f46e7348f54c0658f670370094cb1de30a9f5 (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
/*
 * linux/kernel/power/swsusp.c
 *
 * This file provides code to write suspend image to swap and read it back.
 *
 * Copyright (C) 1998-2001 Gabor Kuti <seasons@fornax.hu>
 * Copyright (C) 1998,2001-2005 Pavel Machek <pavel@suse.cz>
 *
 * This file is released under the GPLv2.
 *
 * I'd like to thank the following people for their work:
 *
 * Pavel Machek <pavel@ucw.cz>:
 * Modifications, defectiveness pointing, being with me at the very beginning,
 * suspend to swap space, stop all tasks. Port to 2.4.18-ac and 2.5.17.
 *
 * Steve Doddi <dirk@loth.demon.co.uk>:
 * Support the possibility of hardware state restoring.
 *
 * Raph <grey.havens@earthling.net>:
 * Support for preserving states of network devices and virtual console
 * (including X and svgatextmode)
 *
 * Kurt Garloff <garloff@suse.de>:
 * Straightened the critical function in order to prevent compilers from
 * playing tricks with local variables.
 *
 * Andreas Mohr <a.mohr@mailto.de>
 *
 * Alex Badea <vampire@go.ro>:
 * Fixed runaway init
 *
 * Andreas Steinmetz <ast@domdv.de>:
 * Added encrypted suspend option
 *
 * More state savers are welcome. Especially for the scsi layer...
 *
 * For TODOs,FIXMEs also look in Documentation/power/swsusp.txt
 */

#include <linux/module.h>
#include <linux/mm.h>
#include <linux/suspend.h>
#include <linux/smp_lock.h>
#include <linux/file.h>
#include <linux/utsname.h>
#include <linux/version.h>
#include <linux/delay.h>
#include <linux/bitops.h>
#include <linux/spinlock.h>
#include <linux/genhd.h>
#include <linux/kernel.h>
#include <linux/major.h>
#include <linux/swap.h>
#include <linux/pm.h>
#include <linux/device.h>
#include <linux/buffer_head.h>
#include <linux/swapops.h>
#include <linux/bootmem.h>
#include <linux/syscalls.h>
#include <linux/highmem.h>
#include <linux/bio.h>

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

#include <linux/random.h>
#include <linux/crypto.h>
#include <asm/scatterlist.h>

#include "power.h"

#ifdef CONFIG_HIGHMEM
int save_highmem(void);
int restore_highmem(void);
#else
static int save_highmem(void) { return 0; }
static int restore_highmem(void) { return 0; }
#endif

#define CIPHER "aes"
#define MAXKEY 32
#define MAXIV  32

extern char resume_file[];

/* Local variables that should not be affected by save */
unsigned int nr_copy_pages __nosavedata = 0;

/* Suspend pagedir is allocated before final copy, therefore it
   must be freed after resume

   Warning: this is even more evil than it seems. Pagedirs this file
   talks about are completely different from page directories used by
   MMU hardware.
 */
suspend_pagedir_t *pagedir_nosave __nosavedata = NULL;

#define SWSUSP_SIG	"S1SUSPEND"

static struct swsusp_header {
	char reserved[PAGE_SIZE - 20 - MAXKEY - MAXIV - sizeof(swp_entry_t)];
	u8 key_iv[MAXKEY+MAXIV];
	swp_entry_t swsusp_info;
	char	orig_sig[10];
	char	sig[10];
} __attribute__((packed, aligned(PAGE_SIZE))) swsusp_header;

static struct swsusp_info swsusp_info;

/*
 * Saving part...
 */

/* We memorize in swapfile_used what swap devices are used for suspension */
#define SWAPFILE_UNUSED    0
#define SWAPFILE_SUSPEND   1	/* This is the suspending device */
#define SWAPFILE_IGNORED   2	/* Those are other swap devices ignored for suspension */

static unsigned short swapfile_used[MAX_SWAPFILES];
static unsigned short root_swap;

static int write_page(unsigned long addr, swp_entry_t *loc);
static int bio_read_page(pgoff_t page_off, void *page);

static u8 key_iv[MAXKEY+MAXIV];

#ifdef CONFIG_SWSUSP_ENCRYPT

static int crypto_init(int mode, void **mem)
{
	int error = 0;
	int len;
	char *modemsg;
	struct crypto_tfm *tfm;

	modemsg = mode ? "suspend not possible" : "resume not possible";

	tfm = crypto_alloc_tfm(CIPHER, CRYPTO_TFM_MODE_CBC);
	if(!tfm) {
		printk(KERN_ERR "swsusp: no tfm, %s\n", modemsg);
		error = -EINVAL;
		goto out;
	}

	if(MAXKEY < crypto_tfm_alg_min_keysize(tfm)) {
		printk(KERN_ERR "swsusp: key buffer too small, %s\n", modemsg);
		error = -ENOKEY;
		goto fail;
	}

	if (mode)
		get_random_bytes(key_iv, MAXKEY+MAXIV);

	len = crypto_tfm_alg_max_keysize(tfm);
	if (len > MAXKEY)
		len = MAXKEY;

	if (crypto_cipher_setkey(tfm, key_iv, len)) {
		printk(KERN_ERR "swsusp: key setup failure, %s\n", modemsg);
		error = -EKEYREJECTED;
		goto fail;
	}

	len = crypto_tfm_alg_ivsize(tfm);

	if (MAXIV < len) {
		printk(KERN_ERR "swsusp: iv buffer too small, %s\n", modemsg);
		error = -EOVERFLOW;
		goto fail;
	}

	crypto_cipher_set_iv(tfm, key_iv+MAXKEY, len);

	*mem=(void *)tfm;

	goto out;

fail:	crypto_free_tfm(tfm);
out:	return error;
}

static __inline__ void crypto_exit(void *mem)
{
	crypto_free_tfm((struct crypto_tfm *)mem);
}

static __inline__ int crypto_write(struct pbe *p, void *mem)
{
	int error = 0;
	struct scatterlist src, dst;

	src.page   = virt_to_page(p->address);
	src.offset = 0;
	src.length = PAGE_SIZE;
	dst.page   = virt_to_page((void *)&swsusp_header);
	dst.offset = 0;
	dst.length = PAGE_SIZE;

	error = crypto_cipher_encrypt((struct crypto_tfm *)mem, &dst, &src,
					PAGE_SIZE);

	if (!error)
		error = write_page((unsigned long)&swsusp_header,
				&(p->swap_address));
	return error;
}

static __inline__ int crypto_read(struct pbe *p, void *mem)
{
	int error = 0;
	struct scatterlist src, dst;

	error = bio_read_page(swp_offset(p->swap_address), (void *)p->address);
	if (!error) {
		src.offset = 0;
		src.length = PAGE_SIZE;
		dst.offset = 0;
		dst.length = PAGE_SIZE;
		src.page = dst.page = virt_to_page((void *)p->address);

		error = crypto_cipher_decrypt((struct crypto_tfm *)mem, &dst,
						&src, PAGE_SIZE);
	}
	return error;
}
#else
static __inline__ int crypto_init(int mode, void *mem)
{
	return 0;
}

static __inline__ void crypto_exit(void *mem)
{
}

static __inline__ int crypto_write(struct pbe *p, void *mem)
{
	return write_page(p->address, &(p->swap_address));
}

static __inline__ int crypto_read(struct pbe *p, void *mem)
{
	return bio_read_page(swp_offset(p->swap_address), (void *)p->address);
}
#endif

static int mark_swapfiles(swp_entry_t prev)
{
	int error;

	rw_swap_page_sync(READ,
			  swp_entry(root_swap, 0),
			  virt_to_page((unsigned long)&swsusp_header));
	if (!memcmp("SWAP-SPACE",swsusp_header.sig, 10) ||
	    !memcmp("SWAPSPACE2",swsusp_header.sig, 10)) {
		memcpy(swsusp_header.orig_sig,swsusp_header.sig, 10);
		memcpy(swsusp_header.sig,SWSUSP_SIG, 10);
		memcpy(swsusp_header.key_iv, key_iv, MAXKEY+MAXIV);
		swsusp_header.swsusp_info = prev;
		error = rw_swap_page_sync(WRITE,
					  swp_entry(root_swap, 0),
					  virt_to_page((unsigned long)
						       &swsusp_header));
	} else {
		pr_debug("swsusp: Partition is not swap space.\n");
		error = -ENODEV;
	}
	return error;
}

/*
 * Check whether the swap device is the specified resume
 * device, irrespective of whether they are specified by
 * identical names.
 *
 * (Thus, device inode aliasing is allowed.  You can say /dev/hda4
 * instead of /dev/ide/host0/bus0/target0/lun0/part4 [if using devfs]
 * and they'll be considered the same device.  This is *necessary* for
 * devfs, since the resume code can only recognize the form /dev/hda4,
 * but the suspend code would see the long name.)
 */
static int is_resume_device(const struct swap_info_struct *swap_info)
{
	struct file *file = swap_info->swap_file;
	struct inode *inode = file->f_dentry->d_inode;

	return S_ISBLK(inode->i_mode) &&
		swsusp_resume_device == MKDEV(imajor(inode), iminor(inode));
}

static int swsusp_swap_check(void) /* This is called before saving image */
{
	int i, len;

	len=strlen(resume_file);
	root_swap = 0xFFFF;

	spin_lock(&swap_lock);
	for (i=0; i<MAX_SWAPFILES; i++) {
		if (!(swap_info[i].flags & SWP_WRITEOK)) {
			swapfile_used[i]=SWAPFILE_UNUSED;
		} else {
			if (!len) {
	    			printk(KERN_WARNING "resume= option should be used to set suspend device" );
				if (root_swap == 0xFFFF) {
					swapfile_used[i] = SWAPFILE_SUSPEND;
					root_swap = i;
				} else
					swapfile_used[i] = SWAPFILE_IGNORED;
			} else {
	  			/* we ignore all swap devices that are not the resume_file */
				if (is_resume_device(&swap_info[i])) {
					swapfile_used[i] = SWAPFILE_SUSPEND;
					root_swap = i;
				} else {
				  	swapfile_used[i] = SWAPFILE_IGNORED;
				}
			}
		}
	}
	spin_unlock(&swap_lock);
	return (root_swap != 0xffff) ? 0 : -ENODEV;
}

/**
 * This is called after saving image so modification
 * will be lost after resume... and that's what we want.
 * we make the device unusable. A new call to
 * lock_swapdevices can unlock the devices.
 */
static void lock_swapdevices(void)
{
	int i;

	spin_lock(&swap_lock);
	for (i = 0; i< MAX_SWAPFILES; i++)
		if (swapfile_used[i] == SWAPFILE_IGNORED) {
			swap_info[i].flags ^= SWP_WRITEOK;
		}
	spin_unlock(&swap_lock);
}

/**
 *	write_page - Write one page to a fresh swap location.
 *	@addr:	Address we're writing.
 *	@loc:	Place to store the entry we used.
 *
 *	Allocate a new swap entry and 'sync' it. Note we discard -EIO
 *	errors. That is an artifact left over from swsusp. It did not
 *	check the return of rw_swap_page_sync() at all, since most pages
 *	written back to swap would return -EIO.
 *	This is a partial improvement, since we will at least return other
 *	errors, though we need to eventually fix the damn code.
 */
static int write_page(unsigned long addr, swp_entry_t *loc)
{
	swp_entry_t entry;
	int error = 0;

	entry = get_swap_page();
	if (swp_offset(entry) &&
	    swapfile_used[swp_type(entry)] == SWAPFILE_SUSPEND) {
		error = rw_swap_page_sync(WRITE, entry,
					  virt_to_page(addr));
		if (error == -EIO)
			error = 0;
		if (!error)
			*loc = entry;
	} else
		error = -ENOSPC;
	return error;
}

/**
 *	data_free - Free the swap entries used by the saved image.
 *
 *	Walk the list of used swap entries and free each one.
 *	This is only used for cleanup when suspend fails.
 */
static void data_free(void)
{
	swp_entry_t entry;
	struct pbe *p;

	for_each_pbe (p, pagedir_nosave) {
		entry = p->swap_address;
		if (entry.val)
			swap_free(entry);
		else
			break;
	}
}

/**
 *	data_write - Write saved image to swap.
 *
 *	Walk the list of pages in the image and sync each one to swap.
 */
static int data_write(void)
{
	int error = 0, i = 0;
	unsigned int mod = nr_copy_pages / 100;
	struct pbe *p;
	void *tfm;

	if ((error = crypto_init(1, &tfm)))
		return error;

	if (!mod)
		mod = 1;

	printk( "Writing data to swap (%d pages)...     ", nr_copy_pages );
	for_each_pbe (p, pagedir_nosave) {
		if (!(i%mod))
			printk( "\b\b\b\b%3d%%", i / mod );
		if ((error = crypto_write(p, tfm))) {
			crypto_exit(tfm);
			return error;
		}
		i++;
	}
	printk("\b\b\b\bdone\n");
	crypto_exit(tfm);
	return error;
}

static void dump_info(void)
{
	pr_debug(" swsusp: Version: %u\n",swsusp_info.version_code);
	pr_debug(" swsusp: Num Pages: %ld\n",swsusp_info.num_physpages);
	pr_debug(" swsusp: UTS Sys: %s\n",swsusp_info.uts.sysname);
	pr_debug(" swsusp: UTS Node: %s\n",swsusp_info.uts.nodename);
	pr_debug(" swsusp: UTS Release: %s\n",swsusp_info.uts.release);
	pr_debug(" swsusp: UTS Version: %s\n",swsusp_info.uts.version);
	pr_debug(" swsusp: UTS Machine: %s\n",swsusp_info.uts.machine);
	pr_debug(" swsusp: UTS Domain: %s\n",swsusp_info.uts.domainname);
	pr_debug(" swsusp: CPUs: %d\n",swsusp_info.cpus);
	pr_debug(" swsusp: Image: %ld Pages\n",swsusp_info.image_pages);
	pr_debug(" swsusp: Pagedir: %ld Pages\n",swsusp_info.pagedir_pages);
}

static void init_header(void)
{
	memset(&swsusp_info, 0, sizeof(swsusp_info));
	swsusp_info.version_code = LINUX_VERSION_CODE;
	swsusp_info.num_physpages = num_physpages;
	memcpy(&swsusp_info.uts, &system_utsname, sizeof(system_utsname));

	swsusp_info.suspend_pagedir = pagedir_nosave;
	swsusp_info.cpus = num_online_cpus();
	swsusp_info.image_pages = nr_copy_pages;
}

static int close_swap(void)
{
	swp_entry_t entry;
	int error;

	dump_info();
	error = write_page((unsigned long)&swsusp_info, &entry);
	if (!error) {
		printk( "S" );
		error = mark_swapfiles(entry);
		printk( "|\n" );
	}
	return error;
}

/**
 *	free_pagedir_entries - Free pages used by the page directory.
 *
 *	This is used during suspend for error recovery.
 */

static void free_pagedir_entries(void)
{
	int i;

	for (i = 0; i < swsusp_info.pagedir_pages; i++)
		swap_free(swsusp_info.pagedir[i]);
}


/**
 *	write_pagedir - Write the array of pages holding the page directory.
 *	@last:	Last swap entry we write (needed for header).
 */

static int write_pagedir(void)
{
	int error = 0;
	unsigned int n = 0;
	struct pbe *pbe;

	printk( "Writing pagedir...");
	for_each_pb_page (pbe, pagedir_nosave) {
		if ((error = write_page((unsigned long)pbe, &swsusp_info.pagedir[n++])))
			return error;
	}

	swsusp_info.pagedir_pages = n;
	printk("done (%u pages)\n", n);
	return error;
}

/**
 *	enough_swap - Make sure we have enough swap to save the image.
 *
 *	Returns TRUE or FALSE after checking the total amount of swap
 *	space avaiable.
 *
 *	FIXME: si_swapinfo(&i) returns all swap devices information.
 *	We should only consider resume_device.
 */

static int enough_swap(unsigned int nr_pages)
{
	struct sysinfo i;

	si_swapinfo(&i);
	pr_debug("swsusp: available swap: %lu pages\n", i.freeswap);
	return i.freeswap > (nr_pages + PAGES_FOR_IO +
		(nr_pages + PBES_PER_PAGE - 1) / PBES_PER_PAGE);
}

/**
 *	write_suspend_image - Write entire image and metadata.
 *
 */
static int write_suspend_image(void)
{
	int error;

	if (!enough_swap(nr_copy_pages)) {
		printk(KERN_ERR "swsusp: Not enough free swap\n");
		return -ENOSPC;
	}

	init_header();
	if ((error = data_write()))
		goto FreeData;

	if ((error = write_pagedir()))
		goto FreePagedir;

	if ((error = close_swap()))
		goto FreePagedir;
 Done:
	memset(key_iv, 0, MAXKEY+MAXIV);
	return error;
 FreePagedir:
	free_pagedir_entries();
 FreeData:
	data_free();
	goto Done;
}

/* It is important _NOT_ to umount filesystems at this point. We want
 * them synced (in case something goes wrong) but we DO not want to mark
 * filesystem clean: it is not. (And it does not matter, if we resume
 * correctly, we'll mark system clean, anyway.)
 */
int swsusp_write(void)
{
	int error;

	if ((error = swsusp_swap_check())) {
		printk(KERN_ERR "swsusp: cannot find swap device, try swapon -a.\n");
		return error;
	}
	lock_swapdevices();
	error = write_suspend_image();
	/* This will unlock ignored swap devices since writing is finished */
	lock_swapdevices();
	return error;
}



int swsusp_suspend(void)
{
	int error;

	if ((error = arch_prepare_suspend()))
		return error;
	local_irq_disable();
	/* At this point, device_suspend() has been called, but *not*
	 * device_power_down(). We *must* device_power_down() now.
	 * Otherwise, drivers for some devices (e.g. interrupt controllers)
	 * become desynchronized with the actual state of the hardware
	 * at resume time, and evil weirdness ensues.
	 */
	if ((error = device_power_down(PMSG_FREEZE))) {
		printk(KERN_ERR "Some devices failed to power down, aborting suspend\n");
		goto Enable_irqs;
	}

	if ((error = save_highmem())) {
		printk(KERN_ERR "swsusp: Not enough free pages for highmem\n");
		goto Restore_highmem;
	}

	save_processor_state();
	if ((error = swsusp_arch_suspend()))
		printk(KERN_ERR "Error %d suspending\n", error);
	/* Restore control flow magically appears here */
	restore_processor_state();
Restore_highmem:
	restore_highmem();
	device_power_up();
Enable_irqs:
	local_irq_enable();
	return error;
}

int swsusp_resume(void)
{
	int error;
	local_irq_disable();
	if (device_power_down(PMSG_FREEZE))
		printk(KERN_ERR "Some devices failed to power down, very bad\n");
	/* We'll ignore saved state, but this gets preempt count (etc) right */
	save_processor_state();
	error = swsusp_arch_resume();
	/* Code below is only ever reached in case of failure. Otherwise
	 * execution continues at place where swsusp_arch_suspend was called
         */
	BUG_ON(!error);
	/* The only reason why swsusp_arch_resume() can fail is memory being
	 * very tight, so we have to free it as soon as we can to avoid
	 * subsequent failures
	 */
	swsusp_free();
	restore_processor_state();
	restore_highmem();
	touch_softlockup_watchdog();
	device_power_up();
	local_irq_enable();
	return error;
}

/**
 *	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 void mark_unsafe_pages(struct pbe *pblist)
{
	struct zone *zone;
	unsigned long zone_pfn;
	struct pbe *p;

	if (!pblist) /* a sanity check */
		return;

	/* Clear page flags */
	for_each_zone (zone) {
		for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn)
			if (pfn_valid(zone_pfn + zone->zone_start_pfn))
				ClearPageNosaveFree(pfn_to_page(zone_pfn +
					zone->zone_start_pfn));
	}

	/* Mark orig addresses */
	for_each_pbe (p, pblist)
		SetPageNosaveFree(virt_to_page(p->orig_address));

}

static void copy_page_backup_list(struct pbe *dst, struct pbe *src)
{
	/* We assume both lists contain the same number of elements */
	while (src) {
		dst->orig_address = src->orig_address;
		dst->swap_address = src->swap_address;
		dst = dst->next;
		src = src->next;
	}
}

/*
 *	Using bio to read from swap.
 *	This code requires a bit more work than just using buffer heads
 *	but, it is the recommended way for 2.5/2.6.
 *	The following are to signal the beginning and end of I/O. Bios
 *	finish asynchronously, while we want them to happen synchronously.
 *	A simple atomic_t, and a wait loop take care of this problem.
 */

static atomic_t io_done = ATOMIC_INIT(0);

static int end_io(struct bio *bio, unsigned int num, int err)
{
	if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
		panic("I/O error reading memory image");
	atomic_set(&io_done, 0);
	return 0;
}

static struct block_device *resume_bdev;

/**
 *	submit - submit BIO request.
 *	@rw:	READ or WRITE.
 *	@off	physical offset of page.
 *	@page:	page we're reading or writing.
 *
 *	Straight from the textbook - allocate and initialize the bio.
 *	If we're writing, make sure the page is marked as dirty.
 *	Then submit it and wait.
 */

static int submit(int rw, pgoff_t page_off, void *page)
{
	int error = 0;
	struct bio *bio;

	bio = bio_alloc(GFP_ATOMIC, 1);
	if (!bio)
		return -ENOMEM;
	bio->bi_sector = page_off * (PAGE_SIZE >> 9);
	bio_get(bio);
	bio->bi_bdev = resume_bdev;
	bio->bi_end_io = end_io;

	if (bio_add_page(bio, virt_to_page(page), PAGE_SIZE, 0) < PAGE_SIZE) {
		printk("swsusp: ERROR: adding page to bio at %ld\n",page_off);
		error = -EFAULT;
		goto Done;
	}

	if (rw == WRITE)
		bio_set_pages_dirty(bio);

	atomic_set(&io_done, 1);
	submit_bio(rw | (1 << BIO_RW_SYNC), bio);
	while (atomic_read(&io_done))
		yield();

 Done:
	bio_put(bio);
	return error;
}

static int bio_read_page(pgoff_t page_off, void *page)
{
	return submit(READ, page_off, page);
}

static int bio_write_page(pgoff_t page_off, void *page)
{
	return submit(WRITE, page_off, page);
}

/*
 * Sanity check if this image makes sense with this kernel/swap context
 * I really don't think that it's foolproof but more than nothing..
 */

static const char *sanity_check(void)
{
	dump_info();
	if (swsusp_info.version_code != LINUX_VERSION_CODE)
		return "kernel version";
	if (swsusp_info.num_physpages != num_physpages)
		return "memory size";
	if (strcmp(swsusp_info.uts.sysname,system_utsname.sysname))
		return "system type";
	if (strcmp(swsusp_info.uts.release,system_utsname.release))
		return "kernel release";
	if (strcmp(swsusp_info.uts.version,system_utsname.version))
		return "version";
	if (strcmp(swsusp_info.uts.machine,system_utsname.machine))
		return "machine";
#if 0
	/* We can't use number of online CPUs when we use hotplug to remove them ;-))) */
	if (swsusp_info.cpus != num_possible_cpus())
		return "number of cpus";
#endif
	return NULL;
}


static int check_header(void)
{
	const char *reason = NULL;
	int error;

	if ((error = bio_read_page(swp_offset(swsusp_header.swsusp_info), &swsusp_info)))
		return error;

 	/* Is this same machine? */
	if ((reason = sanity_check())) {
		printk(KERN_ERR "swsusp: Resume mismatch: %s\n",reason);
		return -EPERM;
	}
	nr_copy_pages = swsusp_info.image_pages;
	return error;
}

static int check_sig(void)
{
	int error;

	memset(&swsusp_header, 0, sizeof(swsusp_header));
	if ((error = bio_read_page(0, &swsusp_header)))
		return error;
	if (!memcmp(SWSUSP_SIG, swsusp_header.sig, 10)) {
		memcpy(swsusp_header.sig, swsusp_header.orig_sig, 10);
		memcpy(key_iv, swsusp_header.key_iv, MAXKEY+MAXIV);
		memset(swsusp_header.key_iv, 0, MAXKEY+MAXIV);

		/*
		 * Reset swap signature now.
		 */
		error = bio_write_page(0, &swsusp_header);
	} else {
		return -EINVAL;
	}
	if (!error)
		pr_debug("swsusp: Signature found, resuming\n");
	return error;
}

/**
 *	data_read - Read image pages from swap.
 *
 *	You do not need to check for overlaps, check_pagedir()
 *	already did that.
 */

static int data_read(struct pbe *pblist)
{
	struct pbe *p;
	int error = 0;
	int i = 0;
	int mod = swsusp_info.image_pages / 100;
	void *tfm;

	if ((error = crypto_init(0, &tfm)))
		return error;

	if (!mod)
		mod = 1;

	printk("swsusp: Reading image data (%lu pages):     ",
			swsusp_info.image_pages);

	for_each_pbe (p, pblist) {
		if (!(i % mod))
			printk("\b\b\b\b%3d%%", i / mod);

		if ((error = crypto_read(p, tfm))) {
			crypto_exit(tfm);
			return error;
		}

		i++;
	}
	printk("\b\b\b\bdone\n");
	crypto_exit(tfm);
	return error;
}

/**
 *	read_pagedir - Read page backup list pages from swap
 */

static int read_pagedir(struct pbe *pblist)
{
	struct pbe *pbpage, *p;
	unsigned int i = 0;
	int error;

	if (!pblist)
		return -EFAULT;

	printk("swsusp: Reading pagedir (%lu pages)\n",
			swsusp_info.pagedir_pages);

	for_each_pb_page (pbpage, pblist) {
		unsigned long offset = swp_offset(swsusp_info.pagedir[i++]);

		error = -EFAULT;
		if (offset) {
			p = (pbpage + PB_PAGE_SKIP)->next;
			error = bio_read_page(offset, (void *)pbpage);
			(pbpage + PB_PAGE_SKIP)->next = p;
		}
		if (error)
			break;
	}

	if (!error)
		BUG_ON(i != swsusp_info.pagedir_pages);

	return error;
}


static int check_suspend_image(void)
{
	int error = 0;

	if ((error = check_sig()))
		return error;

	if ((error = check_header()))
		return error;

	return 0;
}

static int read_suspend_image(void)
{
	int error = 0;
	struct pbe *p;

	if (!(p = alloc_pagedir(nr_copy_pages, GFP_ATOMIC, 0)))
		return -ENOMEM;

	if ((error = read_pagedir(p)))
		return error;
	create_pbe_list(p, nr_copy_pages);
	mark_unsafe_pages(p);
	pagedir_nosave = alloc_pagedir(nr_copy_pages, GFP_ATOMIC, 1);
	if (pagedir_nosave) {
		create_pbe_list(pagedir_nosave, nr_copy_pages);
		copy_page_backup_list(pagedir_nosave, p);
	}
	free_pagedir(p);
	if (!pagedir_nosave)
		return -ENOMEM;

	/* Allocate memory for the image and read the data from swap */

	error = alloc_data_pages(pagedir_nosave, GFP_ATOMIC, 1);

	if (!error)
		error = data_read(pagedir_nosave);

	return error;
}

/**
 *      swsusp_check - Check for saved image in swap
 */

int swsusp_check(void)
{
	int error;

	resume_bdev = open_by_devnum(swsusp_resume_device, FMODE_READ);
	if (!IS_ERR(resume_bdev)) {
		set_blocksize(resume_bdev, PAGE_SIZE);
		error = check_suspend_image();
		if (error)
		    blkdev_put(resume_bdev);
	} else
		error = PTR_ERR(resume_bdev);

	if (!error)
		pr_debug("swsusp: resume file found\n");
	else
		pr_debug("swsusp: Error %d check for resume file\n", error);
	return error;
}

/**
 *	swsusp_read - Read saved image from swap.
 */

int swsusp_read(void)
{
	int error;

	if (IS_ERR(resume_bdev)) {
		pr_debug("swsusp: block device not initialised\n");
		return PTR_ERR(resume_bdev);
	}

	error = read_suspend_image();
	blkdev_put(resume_bdev);
	memset(key_iv, 0, MAXKEY+MAXIV);

	if (!error)
		pr_debug("swsusp: Reading resume file was successful\n");
	else
		pr_debug("swsusp: Error %d resuming\n", error);
	return error;
}

/**
 *	swsusp_close - close swap device.
 */

void swsusp_close(void)
{
	if (IS_ERR(resume_bdev)) {
		pr_debug("swsusp: block device not initialised\n");
		return;
	}

	blkdev_put(resume_bdev);
}