summaryrefslogtreecommitdiff
path: root/kernel/power/tuxonice_prepare_image.c
blob: e0593252fbc834d52004e0b0087e65f0a5a7983a (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
/*
 * kernel/power/tuxonice_prepare_image.c
 *
 * Copyright (C) 2003-2015 Nigel Cunningham (nigel at nigelcunningham com au)
 *
 * This file is released under the GPLv2.
 *
 * We need to eat memory until we can:
 * 1. Perform the save without changing anything (RAM_NEEDED < #pages)
 * 2. Fit it all in available space (toiActiveAllocator->available_space() >=
 *    main_storage_needed())
 * 3. Reload the pagedir and pageset1 to places that don't collide with their
 *    final destinations, not knowing to what extent the resumed kernel will
 *    overlap with the one loaded at boot time. I think the resumed kernel
 *    should overlap completely, but I don't want to rely on this as it is
 *    an unproven assumption. We therefore assume there will be no overlap at
 *    all (worse case).
 * 4. Meet the user's requested limit (if any) on the size of the image.
 *    The limit is in MB, so pages/256 (assuming 4K pages).
 *
 */

#include <linux/highmem.h>
#include <linux/freezer.h>
#include <linux/hardirq.h>
#include <linux/mmzone.h>
#include <linux/console.h>
#include <linux/tuxonice.h>

#include "tuxonice_pageflags.h"
#include "tuxonice_modules.h"
#include "tuxonice_io.h"
#include "tuxonice_ui.h"
#include "tuxonice_prepare_image.h"
#include "tuxonice.h"
#include "tuxonice_extent.h"
#include "tuxonice_checksum.h"
#include "tuxonice_sysfs.h"
#include "tuxonice_alloc.h"
#include "tuxonice_atomic_copy.h"
#include "tuxonice_builtin.h"

static unsigned long num_nosave, main_storage_allocated, storage_limit,
	    header_storage_needed;
unsigned long extra_pd1_pages_allowance =
	CONFIG_TOI_DEFAULT_EXTRA_PAGES_ALLOWANCE;
long image_size_limit = CONFIG_TOI_DEFAULT_IMAGE_SIZE_LIMIT;
static int no_ps2_needed;

struct attention_list {
	struct task_struct *task;
	struct attention_list *next;
};

static struct attention_list *attention_list;

#define PAGESET1 0
#define PAGESET2 1

void free_attention_list(void)
{
	struct attention_list *last = NULL;

	while (attention_list) {
		last = attention_list;
		attention_list = attention_list->next;
		toi_kfree(6, last, sizeof(*last));
	}
}

static int build_attention_list(void)
{
	int i, task_count = 0;
	struct task_struct *p;
	struct attention_list *next;

	/*
	 * Count all userspace process (with task->mm) marked PF_NOFREEZE.
	 */
	toi_read_lock_tasklist();
	for_each_process(p)
		if ((p->flags & PF_NOFREEZE) || p == current)
			task_count++;
	toi_read_unlock_tasklist();

	/*
	 * Allocate attention list structs.
	 */
	for (i = 0; i < task_count; i++) {
		struct attention_list *this =
			toi_kzalloc(6, sizeof(struct attention_list),
					TOI_WAIT_GFP);
		if (!this) {
			printk(KERN_INFO "Failed to allocate slab for "
					"attention list.\n");
			free_attention_list();
			return 1;
		}
		this->next = NULL;
		if (attention_list)
			this->next = attention_list;
		attention_list = this;
	}

	next = attention_list;
	toi_read_lock_tasklist();
	for_each_process(p)
		if ((p->flags & PF_NOFREEZE) || p == current) {
			next->task = p;
			next = next->next;
		}
	toi_read_unlock_tasklist();
	return 0;
}

static void pageset2_full(void)
{
	struct zone *zone;
	struct page *page;
	unsigned long flags;
	int i;

        toi_trace_index++;

	for_each_populated_zone(zone) {
		spin_lock_irqsave(&zone->lru_lock, flags);
		for_each_lru(i) {
			if (!zone_page_state(zone, NR_LRU_BASE + i))
				continue;

			list_for_each_entry(page, &zone->lruvec.lists[i], lru) {
				struct address_space *mapping;

				mapping = page_mapping(page);
				if (!mapping || !mapping->host ||
				    !(mapping->host->i_flags & S_ATOMIC_COPY)) {
                                    if (PageTOI_RO(page) && test_result_state(TOI_KEPT_IMAGE)) {
                                        TOI_TRACE_DEBUG(page_to_pfn(page), "_Pageset2 unmodified.");
                                    } else {
                                        TOI_TRACE_DEBUG(page_to_pfn(page), "_Pageset2 pageset2_full.");
                                        SetPagePageset2(page);
                                    }
                                }
			}
		}
		spin_unlock_irqrestore(&zone->lru_lock, flags);
	}
}

/*
 * toi_mark_task_as_pageset
 * Functionality   : Marks all the saveable pages belonging to a given process
 * 		     as belonging to a particular pageset.
 */

static void toi_mark_task_as_pageset(struct task_struct *t, int pageset2)
{
	struct vm_area_struct *vma;
	struct mm_struct *mm;

	mm = t->active_mm;

	if (!mm || !mm->mmap)
		return;

        toi_trace_index++;

	if (!irqs_disabled())
		down_read(&mm->mmap_sem);

	for (vma = mm->mmap; vma; vma = vma->vm_next) {
		unsigned long posn;

		if (!vma->vm_start ||
		    vma->vm_flags & VM_PFNMAP)
			continue;

		for (posn = vma->vm_start; posn < vma->vm_end;
				posn += PAGE_SIZE) {
			struct page *page = follow_page(vma, posn, 0);
			struct address_space *mapping;

			if (!page || !pfn_valid(page_to_pfn(page)))
				continue;

			mapping = page_mapping(page);
			if (mapping && mapping->host &&
			    mapping->host->i_flags & S_ATOMIC_COPY && pageset2)
				continue;

                        if (PageTOI_RO(page) && test_result_state(TOI_KEPT_IMAGE)) {
                                TOI_TRACE_DEBUG(page_to_pfn(page), "_Unmodified %d", pageset2 ? 1 : 2);
                                continue;
                        }

			if (pageset2) {
                                TOI_TRACE_DEBUG(page_to_pfn(page), "_MarkTaskAsPageset 1");
				SetPagePageset2(page);
                        } else {
                                TOI_TRACE_DEBUG(page_to_pfn(page), "_MarkTaskAsPageset 2");
				ClearPagePageset2(page);
				SetPagePageset1(page);
			}
		}
	}

	if (!irqs_disabled())
		up_read(&mm->mmap_sem);
}

static void mark_tasks(int pageset)
{
	struct task_struct *p;

	toi_read_lock_tasklist();
	for_each_process(p) {
		if (!p->mm)
			continue;

		if (p->flags & PF_KTHREAD)
			continue;

		toi_mark_task_as_pageset(p, pageset);
	}
	toi_read_unlock_tasklist();

}

/* mark_pages_for_pageset2
 *
 * Description:	Mark unshared pages in processes not needed for hibernate as
 * 		being able to be written out in a separate pagedir.
 * 		HighMem pages are simply marked as pageset2. They won't be
 * 		needed during hibernate.
 */

static void toi_mark_pages_for_pageset2(void)
{
	struct attention_list *this = attention_list;

	memory_bm_clear(pageset2_map);

	if (test_action_state(TOI_NO_PAGESET2) || no_ps2_needed)
		return;

	if (test_action_state(TOI_PAGESET2_FULL))
		pageset2_full();
	else
		mark_tasks(PAGESET2);

	/*
	 * Because the tasks in attention_list are ones related to hibernating,
	 * we know that they won't go away under us.
	 */

	while (this) {
		if (!test_result_state(TOI_ABORTED))
			toi_mark_task_as_pageset(this->task, PAGESET1);
		this = this->next;
	}
}

/*
 * The atomic copy of pageset1 is stored in pageset2 pages.
 * But if pageset1 is larger (normally only just after boot),
 * we need to allocate extra pages to store the atomic copy.
 * The following data struct and functions are used to handle
 * the allocation and freeing of that memory.
 */

static unsigned long extra_pages_allocated;

struct extras {
	struct page *page;
	int order;
	struct extras *next;
};

static struct extras *extras_list;

/* toi_free_extra_pagedir_memory
 *
 * Description:	Free previously allocated extra pagedir memory.
 */
void toi_free_extra_pagedir_memory(void)
{
	/* Free allocated pages */
	while (extras_list) {
		struct extras *this = extras_list;
		int i;

		extras_list = this->next;

		for (i = 0; i < (1 << this->order); i++)
			ClearPageNosave(this->page + i);

		toi_free_pages(9, this->page, this->order);
		toi_kfree(7, this, sizeof(*this));
	}

	extra_pages_allocated = 0;
}

/* toi_allocate_extra_pagedir_memory
 *
 * Description:	Allocate memory for making the atomic copy of pagedir1 in the
 * 		case where it is bigger than pagedir2.
 * Arguments:	int	num_to_alloc: Number of extra pages needed.
 * Result:	int. 	Number of extra pages we now have allocated.
 */
static int toi_allocate_extra_pagedir_memory(int extra_pages_needed)
{
	int j, order, num_to_alloc = extra_pages_needed - extra_pages_allocated;
	gfp_t flags = TOI_ATOMIC_GFP;

	if (num_to_alloc < 1)
		return 0;

	order = fls(num_to_alloc);
	if (order >= MAX_ORDER)
		order = MAX_ORDER - 1;

	while (num_to_alloc) {
		struct page *newpage;
		unsigned long virt;
		struct extras *extras_entry;

		while ((1 << order) > num_to_alloc)
			order--;

		extras_entry = (struct extras *) toi_kzalloc(7,
			sizeof(struct extras), TOI_ATOMIC_GFP);

		if (!extras_entry)
			return extra_pages_allocated;

		virt = toi_get_free_pages(9, flags, order);
		while (!virt && order) {
			order--;
			virt = toi_get_free_pages(9, flags, order);
		}

		if (!virt) {
			toi_kfree(7, extras_entry, sizeof(*extras_entry));
			return extra_pages_allocated;
		}

		newpage = virt_to_page(virt);

		extras_entry->page = newpage;
		extras_entry->order = order;
		extras_entry->next = extras_list;

		extras_list = extras_entry;

		for (j = 0; j < (1 << order); j++) {
			SetPageNosave(newpage + j);
			SetPagePageset1Copy(newpage + j);
		}

		extra_pages_allocated += (1 << order);
		num_to_alloc -= (1 << order);
	}

	return extra_pages_allocated;
}

/*
 * real_nr_free_pages: Count pcp pages for a zone type or all zones
 * (-1 for all, otherwise zone_idx() result desired).
 */
unsigned long real_nr_free_pages(unsigned long zone_idx_mask)
{
	struct zone *zone;
	int result = 0, cpu;

	/* PCP lists */
	for_each_populated_zone(zone) {
		if (!(zone_idx_mask & (1 << zone_idx(zone))))
			continue;

		for_each_online_cpu(cpu) {
			struct per_cpu_pageset *pset =
				per_cpu_ptr(zone->pageset, cpu);
			struct per_cpu_pages *pcp = &pset->pcp;
			result += pcp->count;
		}

		result += zone_page_state(zone, NR_FREE_PAGES);
	}
	return result;
}

/*
 * Discover how much extra memory will be required by the drivers
 * when they're asked to hibernate. We can then ensure that amount
 * of memory is available when we really want it.
 */
static void get_extra_pd1_allowance(void)
{
	unsigned long orig_num_free = real_nr_free_pages(all_zones_mask), final;

	toi_prepare_status(CLEAR_BAR, "Finding allowance for drivers.");

	if (toi_go_atomic(PMSG_FREEZE, 1))
		return;

	final = real_nr_free_pages(all_zones_mask);
	toi_end_atomic(ATOMIC_ALL_STEPS, 1, 0);

	extra_pd1_pages_allowance = (orig_num_free > final) ?
		orig_num_free - final + MIN_EXTRA_PAGES_ALLOWANCE :
		MIN_EXTRA_PAGES_ALLOWANCE;
}

/*
 * Amount of storage needed, possibly taking into account the
 * expected compression ratio and possibly also ignoring our
 * allowance for extra pages.
 */
static unsigned long main_storage_needed(int use_ecr,
		int ignore_extra_pd1_allow)
{
	return (pagedir1.size + pagedir2.size +
	  (ignore_extra_pd1_allow ? 0 : extra_pd1_pages_allowance)) *
	 (use_ecr ? toi_expected_compression_ratio() : 100) / 100;
}

/*
 * Storage needed for the image header, in bytes until the return.
 */
unsigned long get_header_storage_needed(void)
{
	unsigned long bytes = sizeof(struct toi_header) +
			toi_header_storage_for_modules() +
			toi_pageflags_space_needed() +
			fs_info_space_needed();

	return DIV_ROUND_UP(bytes, PAGE_SIZE);
}

/*
 * When freeing memory, pages from either pageset might be freed.
 *
 * When seeking to free memory to be able to hibernate, for every ps1 page
 * freed, we need 2 less pages for the atomic copy because there is one less
 * page to copy and one more page into which data can be copied.
 *
 * Freeing ps2 pages saves us nothing directly. No more memory is available
 * for the atomic copy. Indirectly, a ps1 page might be freed (slab?), but
 * that's too much work to figure out.
 *
 * => ps1_to_free functions
 *
 * Of course if we just want to reduce the image size, because of storage
 * limitations or an image size limit either ps will do.
 *
 * => any_to_free function
 */

static unsigned long lowpages_usable_for_highmem_copy(void)
{
	unsigned long needed = get_lowmem_size(pagedir1) +
			extra_pd1_pages_allowance + MIN_FREE_RAM +
			toi_memory_for_modules(0),
		available = get_lowmem_size(pagedir2) +
			 real_nr_free_low_pages() + extra_pages_allocated;

	return available > needed ? available - needed : 0;
}

static unsigned long highpages_ps1_to_free(void)
{
	unsigned long need = get_highmem_size(pagedir1),
		      available = get_highmem_size(pagedir2) +
			      real_nr_free_high_pages() +
			      lowpages_usable_for_highmem_copy();

	return need > available ? DIV_ROUND_UP(need - available, 2) : 0;
}

static unsigned long lowpages_ps1_to_free(void)
{
	unsigned long needed = get_lowmem_size(pagedir1) +
			extra_pd1_pages_allowance + MIN_FREE_RAM +
			toi_memory_for_modules(0),
		available = get_lowmem_size(pagedir2) +
			 real_nr_free_low_pages() + extra_pages_allocated;

	return needed > available ? DIV_ROUND_UP(needed - available, 2) : 0;
}

static unsigned long current_image_size(void)
{
	return pagedir1.size + pagedir2.size + header_storage_needed;
}

static unsigned long storage_still_required(void)
{
	unsigned long needed = main_storage_needed(1, 1);
	return needed > storage_limit ? needed - storage_limit : 0;
}

static unsigned long ram_still_required(void)
{
	unsigned long needed = MIN_FREE_RAM + toi_memory_for_modules(0) +
		2 * extra_pd1_pages_allowance,
		  available = real_nr_free_low_pages() + extra_pages_allocated;
	return needed > available ? needed - available : 0;
}

unsigned long any_to_free(int use_image_size_limit)
{
	int use_soft_limit = use_image_size_limit && image_size_limit > 0;
	unsigned long current_size = current_image_size(),
		      soft_limit = use_soft_limit ? (image_size_limit << 8) : 0,
		      to_free = use_soft_limit ? (current_size > soft_limit ?
				      current_size - soft_limit : 0) : 0,
		      storage_limit = storage_still_required(),
		      ram_limit = ram_still_required(),
		      first_max = max(to_free, storage_limit);

	return max(first_max, ram_limit);
}

static int need_pageset2(void)
{
	return (real_nr_free_low_pages() + extra_pages_allocated -
		2 * extra_pd1_pages_allowance - MIN_FREE_RAM -
		 toi_memory_for_modules(0) - pagedir1.size) < pagedir2.size;
}

/* amount_needed
 *
 * Calculates the amount by which the image size needs to be reduced to meet
 * our constraints.
 */
static unsigned long amount_needed(int use_image_size_limit)
{
	return max(highpages_ps1_to_free() + lowpages_ps1_to_free(),
			any_to_free(use_image_size_limit));
}

static int image_not_ready(int use_image_size_limit)
{
	toi_message(TOI_EAT_MEMORY, TOI_LOW, 1,
		"Amount still needed (%lu) > 0:%u,"
		" Storage allocd: %lu < %lu: %u.\n",
			amount_needed(use_image_size_limit),
			(amount_needed(use_image_size_limit) > 0),
			main_storage_allocated,
			main_storage_needed(1, 1),
			main_storage_allocated < main_storage_needed(1, 1));

	toi_cond_pause(0, NULL);

	return (amount_needed(use_image_size_limit) > 0) ||
		 main_storage_allocated < main_storage_needed(1, 1);
}

static void display_failure_reason(int tries_exceeded)
{
	unsigned long storage_required = storage_still_required(),
	    ram_required = ram_still_required(),
	    high_ps1 = highpages_ps1_to_free(),
	    low_ps1 = lowpages_ps1_to_free();

	printk(KERN_INFO "Failed to prepare the image because...\n");

	if (!storage_limit) {
		printk(KERN_INFO "- You need some storage available to be "
				"able to hibernate.\n");
		return;
	}

	if (tries_exceeded)
		printk(KERN_INFO "- The maximum number of iterations was "
				"reached without successfully preparing the "
				"image.\n");

	if (storage_required) {
		printk(KERN_INFO " - We need at least %lu pages of storage "
				"(ignoring the header), but only have %lu.\n",
				main_storage_needed(1, 1),
				main_storage_allocated);
		set_abort_result(TOI_INSUFFICIENT_STORAGE);
	}

	if (ram_required) {
		printk(KERN_INFO " - We need %lu more free pages of low "
				"memory.\n", ram_required);
		printk(KERN_INFO "     Minimum free     : %8d\n", MIN_FREE_RAM);
		printk(KERN_INFO "   + Reqd. by modules : %8lu\n",
				toi_memory_for_modules(0));
		printk(KERN_INFO "   + 2 * extra allow  : %8lu\n",
				2 * extra_pd1_pages_allowance);
		printk(KERN_INFO "   - Currently free   : %8lu\n",
				real_nr_free_low_pages());
		printk(KERN_INFO "   - Pages allocd     : %8lu\n",
				extra_pages_allocated);
		printk(KERN_INFO "                      : ========\n");
		printk(KERN_INFO "     Still needed     : %8lu\n",
				ram_required);

		/* Print breakdown of memory needed for modules */
		toi_memory_for_modules(1);
		set_abort_result(TOI_UNABLE_TO_FREE_ENOUGH_MEMORY);
	}

	if (high_ps1) {
		printk(KERN_INFO "- We need to free %lu highmem pageset 1 "
				"pages.\n", high_ps1);
		set_abort_result(TOI_UNABLE_TO_FREE_ENOUGH_MEMORY);
	}

	if (low_ps1) {
		printk(KERN_INFO " - We need to free %ld lowmem pageset 1 "
				"pages.\n", low_ps1);
		set_abort_result(TOI_UNABLE_TO_FREE_ENOUGH_MEMORY);
	}
}

static void display_stats(int always, int sub_extra_pd1_allow)
{
	char buffer[255];
	snprintf(buffer, 254,
		"Free:%lu(%lu). Sets:%lu(%lu),%lu(%lu). "
		"Nosave:%lu-%lu=%lu. Storage:%lu/%lu(%lu=>%lu). "
		"Needed:%lu,%lu,%lu(%u,%lu,%lu,%ld) (PS2:%s)\n",

		/* Free */
		real_nr_free_pages(all_zones_mask),
		real_nr_free_low_pages(),

		/* Sets */
		pagedir1.size, pagedir1.size - get_highmem_size(pagedir1),
		pagedir2.size, pagedir2.size - get_highmem_size(pagedir2),

		/* Nosave */
		num_nosave, extra_pages_allocated,
		num_nosave - extra_pages_allocated,

		/* Storage */
		main_storage_allocated,
		storage_limit,
		main_storage_needed(1, sub_extra_pd1_allow),
		main_storage_needed(1, 1),

		/* Needed */
		lowpages_ps1_to_free(), highpages_ps1_to_free(),
		any_to_free(1),
		MIN_FREE_RAM, toi_memory_for_modules(0),
		extra_pd1_pages_allowance,
		image_size_limit,

		need_pageset2() ? "yes" : "no");

	if (always)
		printk("%s", buffer);
	else
		toi_message(TOI_EAT_MEMORY, TOI_MEDIUM, 1, buffer);
}

/* flag_image_pages
 *
 * This routine generates our lists of pages to be stored in each
 * pageset. Since we store the data using extents, and adding new
 * extents might allocate a new extent page, this routine may well
 * be called more than once.
 */
static void flag_image_pages(int atomic_copy)
{
	int num_free = 0, num_unmodified = 0;
	unsigned long loop;
	struct zone *zone;

	pagedir1.size = 0;
	pagedir2.size = 0;

	set_highmem_size(pagedir1, 0);
	set_highmem_size(pagedir2, 0);

	num_nosave = 0;
        toi_trace_index++;

	memory_bm_clear(pageset1_map);

	toi_generate_free_page_map();

	/*
	 * Pages not to be saved are marked Nosave irrespective of being
	 * reserved.
	 */
	for_each_populated_zone(zone) {
		int highmem = is_highmem(zone);

		for (loop = 0; loop < zone->spanned_pages; loop++) {
			unsigned long pfn = zone->zone_start_pfn + loop;
			struct page *page;
			int chunk_size;

			if (!pfn_valid(pfn)) {
                            TOI_TRACE_DEBUG(pfn, "_Flag Invalid");
                            continue;
                        }

			chunk_size = toi_size_of_free_region(zone, pfn);
			if (chunk_size) {
                            unsigned long y;
                            for (y = pfn; y < pfn + chunk_size; y++) {
                                page = pfn_to_page(y);
                                TOI_TRACE_DEBUG(y, "_Flag Free");
                                ClearPagePageset1(page);
                                ClearPagePageset2(page);
                            }
				num_free += chunk_size;
				loop += chunk_size - 1;
				continue;
			}

			page = pfn_to_page(pfn);

			if (PageNosave(page)) {
                            char *desc = PagePageset1Copy(page) ? "Pageset1Copy" : "NoSave";
                            TOI_TRACE_DEBUG(pfn, "_Flag %s", desc);
                            num_nosave++;
                            continue;
                        }

			page = highmem ? saveable_highmem_page(zone, pfn) :
				saveable_page(zone, pfn);

			if (!page) {
                                TOI_TRACE_DEBUG(pfn, "_Flag Nosave2");
				num_nosave++;
				continue;
			}

                        if (PageTOI_RO(page) && test_result_state(TOI_KEPT_IMAGE)) {
                            TOI_TRACE_DEBUG(pfn, "_Unmodified");
                            num_unmodified++;
                            continue;
                        }

			if (PagePageset2(page)) {
				pagedir2.size++;
                                TOI_TRACE_DEBUG(pfn, "_Flag PS2");
				if (PageHighMem(page))
					inc_highmem_size(pagedir2);
				else
					SetPagePageset1Copy(page);
				if (PageResave(page)) {
					SetPagePageset1(page);
					ClearPagePageset1Copy(page);
					pagedir1.size++;
					if (PageHighMem(page))
						inc_highmem_size(pagedir1);
				}
			} else {
				pagedir1.size++;
                                TOI_TRACE_DEBUG(pfn, "_Flag PS1");
				SetPagePageset1(page);
				if (PageHighMem(page))
					inc_highmem_size(pagedir1);
			}
		}
	}

	if (!atomic_copy)
		toi_message(TOI_EAT_MEMORY, TOI_MEDIUM, 0,
			"Count data pages: Set1 (%d) + Set2 (%d) + Nosave (%ld)"
				    " + Unmodified (%d) + NumFree (%d) = %d.\n",
			pagedir1.size, pagedir2.size, num_nosave, num_unmodified,
                        num_free, pagedir1.size + pagedir2.size + num_nosave + num_free);
}

void toi_recalculate_image_contents(int atomic_copy)
{
	memory_bm_clear(pageset1_map);
	if (!atomic_copy) {
		unsigned long pfn;
		memory_bm_position_reset(pageset2_map);
		for (pfn = memory_bm_next_pfn(pageset2_map, 0);
				pfn != BM_END_OF_MAP;
				pfn = memory_bm_next_pfn(pageset2_map, 0))
			ClearPagePageset1Copy(pfn_to_page(pfn));
		/* Need to call this before getting pageset1_size! */
		toi_mark_pages_for_pageset2();
	}
        memory_bm_position_reset(pageset2_map);
	flag_image_pages(atomic_copy);

	if (!atomic_copy) {
		storage_limit = toiActiveAllocator->storage_available();
		display_stats(0, 0);
	}
}

int try_allocate_extra_memory(void)
{
	unsigned long wanted = pagedir1.size +  extra_pd1_pages_allowance -
		get_lowmem_size(pagedir2);
	if (wanted > extra_pages_allocated) {
		unsigned long got = toi_allocate_extra_pagedir_memory(wanted);
		if (wanted < got) {
			toi_message(TOI_EAT_MEMORY, TOI_LOW, 1,
				"Want %d extra pages for pageset1, got %d.\n",
				wanted, got);
			return 1;
		}
	}
	return 0;
}

/* update_image
 *
 * Allocate [more] memory and storage for the image.
 */
static void update_image(int ps2_recalc)
{
	int old_header_req;
	unsigned long seek;

	if (try_allocate_extra_memory())
		return;

	if (ps2_recalc)
		goto recalc;

	thaw_kernel_threads();

	/*
	 * Allocate remaining storage space, if possible, up to the
	 * maximum we know we'll need. It's okay to allocate the
	 * maximum if the writer is the swapwriter, but
	 * we don't want to grab all available space on an NFS share.
	 * We therefore ignore the expected compression ratio here,
	 * thereby trying to allocate the maximum image size we could
	 * need (assuming compression doesn't expand the image), but
	 * don't complain if we can't get the full amount we're after.
	 */

	do {
		int result;

		old_header_req = header_storage_needed;
		toiActiveAllocator->reserve_header_space(header_storage_needed);

		/* How much storage is free with the reservation applied? */
		storage_limit = toiActiveAllocator->storage_available();
		seek = min(storage_limit, main_storage_needed(0, 0));

		result = toiActiveAllocator->allocate_storage(seek);
		if (result)
			printk("Failed to allocate storage (%d).\n", result);

		main_storage_allocated =
			toiActiveAllocator->storage_allocated();

		/* Need more header because more storage allocated? */
		header_storage_needed = get_header_storage_needed();

	} while (header_storage_needed > old_header_req);

	if (freeze_kernel_threads())
		set_abort_result(TOI_FREEZING_FAILED);

recalc:
	toi_recalculate_image_contents(0);
}

/* attempt_to_freeze
 *
 * Try to freeze processes.
 */

static int attempt_to_freeze(void)
{
	int result;

	/* Stop processes before checking again */
	toi_prepare_status(CLEAR_BAR, "Freezing processes & syncing "
			"filesystems.");
	result = freeze_processes();

	if (result)
		set_abort_result(TOI_FREEZING_FAILED);

	result = freeze_kernel_threads();

	if (result)
		set_abort_result(TOI_FREEZING_FAILED);

	return result;
}

/* eat_memory
 *
 * Try to free some memory, either to meet hard or soft constraints on the image
 * characteristics.
 *
 * Hard constraints:
 * - Pageset1 must be < half of memory;
 * - We must have enough memory free at resume time to have pageset1
 *   be able to be loaded in pages that don't conflict with where it has to
 *   be restored.
 * Soft constraints
 * - User specificied image size limit.
 */
static void eat_memory(void)
{
	unsigned long amount_wanted = 0;
	int did_eat_memory = 0;

	/*
	 * Note that if we have enough storage space and enough free memory, we
	 * may exit without eating anything. We give up when the last 10
	 * iterations ate no extra pages because we're not going to get much
	 * more anyway, but the few pages we get will take a lot of time.
	 *
	 * We freeze processes before beginning, and then unfreeze them if we
	 * need to eat memory until we think we have enough. If our attempts
	 * to freeze fail, we give up and abort.
	 */

	amount_wanted = amount_needed(1);

	switch (image_size_limit) {
	case -1: /* Don't eat any memory */
		if (amount_wanted > 0) {
			set_abort_result(TOI_WOULD_EAT_MEMORY);
			return;
		}
		break;
	case -2:  /* Free caches only */
		drop_pagecache();
		toi_recalculate_image_contents(0);
		amount_wanted = amount_needed(1);
		break;
	default:
		break;
	}

	if (amount_wanted > 0 && !test_result_state(TOI_ABORTED) &&
			image_size_limit != -1) {
		unsigned long request = amount_wanted;
		unsigned long high_req = max(highpages_ps1_to_free(),
				any_to_free(1));
		unsigned long low_req = lowpages_ps1_to_free();
		unsigned long got = 0;

		toi_prepare_status(CLEAR_BAR,
				"Seeking to free %ldMB of memory.",
				MB(amount_wanted));

		thaw_kernel_threads();

		/*
		 * Ask for too many because shrink_memory_mask doesn't
		 * currently return enough most of the time.
		 */
		
		if (low_req)
			got = shrink_memory_mask(low_req, GFP_KERNEL);
		if (high_req)
			shrink_memory_mask(high_req - got, GFP_HIGHUSER);

		did_eat_memory = 1;

		toi_recalculate_image_contents(0);

		amount_wanted = amount_needed(1);

		printk(KERN_DEBUG "Asked shrink_memory_mask for %ld low pages &"
				" %ld pages from anywhere, got %ld.\n",
				high_req, low_req,
				request - amount_wanted);

		toi_cond_pause(0, NULL);

		if (freeze_kernel_threads())
			set_abort_result(TOI_FREEZING_FAILED);
	}

	if (did_eat_memory)
		toi_recalculate_image_contents(0);
}

/* toi_prepare_image
 *
 * Entry point to the whole image preparation section.
 *
 * We do four things:
 * - Freeze processes;
 * - Ensure image size constraints are met;
 * - Complete all the preparation for saving the image,
 *   including allocation of storage. The only memory
 *   that should be needed when we're finished is that
 *   for actually storing the image (and we know how
 *   much is needed for that because the modules tell
 *   us).
 * - Make sure that all dirty buffers are written out.
 */
#define MAX_TRIES 2
int toi_prepare_image(void)
{
	int result = 1, tries = 1;

	main_storage_allocated = 0;
	no_ps2_needed = 0;

	if (attempt_to_freeze())
		return 1;

	lock_device_hotplug();
	set_toi_state(TOI_DEVICE_HOTPLUG_LOCKED);

	if (!extra_pd1_pages_allowance)
		get_extra_pd1_allowance();

	storage_limit = toiActiveAllocator->storage_available();

	if (!storage_limit) {
		printk(KERN_INFO "No storage available. Didn't try to prepare "
				"an image.\n");
		display_failure_reason(0);
		set_abort_result(TOI_NOSTORAGE_AVAILABLE);
		return 1;
	}

	if (build_attention_list()) {
		abort_hibernate(TOI_UNABLE_TO_PREPARE_IMAGE,
				"Unable to successfully prepare the image.\n");
		return 1;
	}

	toi_recalculate_image_contents(0);

	do {
		toi_prepare_status(CLEAR_BAR,
				"Preparing Image. Try %d.", tries);

		eat_memory();

		if (test_result_state(TOI_ABORTED))
			break;

		update_image(0);

		tries++;

	} while (image_not_ready(1) && tries <= MAX_TRIES &&
			!test_result_state(TOI_ABORTED));

	result = image_not_ready(0);

        /* TODO: Handle case where need to remove existing image and resave
         * instead of adding to incremental image. */

	if (!test_result_state(TOI_ABORTED)) {
		if (result) {
			display_stats(1, 0);
			display_failure_reason(tries > MAX_TRIES);
			abort_hibernate(TOI_UNABLE_TO_PREPARE_IMAGE,
				"Unable to successfully prepare the image.\n");
		} else {
			/* Pageset 2 needed? */
			if (!need_pageset2() &&
				  test_action_state(TOI_NO_PS2_IF_UNNEEDED)) {
				no_ps2_needed = 1;
				toi_recalculate_image_contents(0);
				update_image(1);
			}

			toi_cond_pause(1, "Image preparation complete.");
		}
	}

	return result ? result : allocate_checksum_pages();
}