aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/power/snapshot.c
blob: 41f66365f0d85daa0c772430ff9872c0395030aa (plain) (blame)
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
/*
 * linux/kernel/power/snapshot.c
 *
 * This file provide system snapshot/restore functionality.
 *
 * Copyright (C) 1998-2005 Pavel Machek <pavel@suse.cz>
 *
 * This file is released under the GPLv2, and is based on swsusp.c.
 *
 */


#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"

struct pbe *pagedir_nosave;
unsigned int nr_copy_pages;

#ifdef CONFIG_HIGHMEM
unsigned int count_highmem_pages(void)
{
	struct zone *zone;
	unsigned long zone_pfn;
	unsigned int n = 0;

	for_each_zone (zone)
		if (is_highmem(zone)) {
			mark_free_pages(zone);
			for (zone_pfn = 0; zone_pfn < zone->spanned_pages; zone_pfn++) {
				struct page *page;
				unsigned long pfn = zone_pfn + zone->zone_start_pfn;
				if (!pfn_valid(pfn))
					continue;
				page = pfn_to_page(pfn);
				if (PageReserved(page))
					continue;
				if (PageNosaveFree(page))
					continue;
				n++;
			}
		}
	return n;
}

struct highmem_page {
	char *data;
	struct page *page;
	struct highmem_page *next;
};

static struct highmem_page *highmem_copy;

static int save_highmem_zone(struct zone *zone)
{
	unsigned long zone_pfn;
	mark_free_pages(zone);
	for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn) {
		struct page *page;
		struct highmem_page *save;
		void *kaddr;
		unsigned long pfn = zone_pfn + zone->zone_start_pfn;

		if (!(pfn%1000))
			printk(".");
		if (!pfn_valid(pfn))
			continue;
		page = pfn_to_page(pfn);
		/*
		 * This condition results from rvmalloc() sans vmalloc_32()
		 * and architectural memory reservations. This should be
		 * corrected eventually when the cases giving rise to this
		 * are better understood.
		 */
		if (PageReserved(page)) {
			printk("highmem reserved page?!\n");
			continue;
		}
		BUG_ON(PageNosave(page));
		if (PageNosaveFree(page))
			continue;
		save = kmalloc(sizeof(struct highmem_page), GFP_ATOMIC);
		if (!save)
			return -ENOMEM;
		save->next = highmem_copy;
		save->page = page;
		save->data = (void *) get_zeroed_page(GFP_ATOMIC);
		if (!save->data) {
			kfree(save);
			return -ENOMEM;
		}
		kaddr = kmap_atomic(page, KM_USER0);
		memcpy(save->data, kaddr, PAGE_SIZE);
		kunmap_atomic(kaddr, KM_USER0);
		highmem_copy = save;
	}
	return 0;
}

int save_highmem(void)
{
	struct zone *zone;
	int res = 0;

	pr_debug("swsusp: Saving Highmem\n");
	for_each_zone (zone) {
		if (is_highmem(zone))
			res = save_highmem_zone(zone);
		if (res)
			return res;
	}
	return 0;
}

int restore_highmem(void)
{
	printk("swsusp: Restoring Highmem\n");
	while (highmem_copy) {
		struct highmem_page *save = highmem_copy;
		void *kaddr;
		highmem_copy = save->next;

		kaddr = kmap_atomic(save->page, KM_USER0);
		memcpy(kaddr, save->data, PAGE_SIZE);
		kunmap_atomic(kaddr, KM_USER0);
		free_page((long) save->data);
		kfree(save);
	}
	return 0;
}
#endif

static 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 page should be cloned or not.
 *	@pfn:	The page
 *
 *	We save a page if it's Reserved, and not in the range of pages
 *	statically defined as 'unsaveable', or if it isn't reserved, and
 *	isn't part of a free chunk of pages.
 */

static int saveable(struct zone *zone, unsigned long *zone_pfn)
{
	unsigned long pfn = *zone_pfn + zone->zone_start_pfn;
	struct page *page;

	if (!pfn_valid(pfn))
		return 0;

	page = pfn_to_page(pfn);
	BUG_ON(PageReserved(page) && PageNosave(page));
	if (PageNosave(page))
		return 0;
	if (PageReserved(page) && pfn_is_nosave(pfn))
		return 0;
	if (PageNosaveFree(page))
		return 0;

	return 1;
}

unsigned int count_data_pages(void)
{
	struct zone *zone;
	unsigned long zone_pfn;
	unsigned int n = 0;

	for_each_zone (zone) {
		if (is_highmem(zone))
			continue;
		mark_free_pages(zone);
		for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn)
			n += saveable(zone, &zone_pfn);
	}
	return n;
}

static void copy_data_pages(struct pbe *pblist)
{
	struct zone *zone;
	unsigned long zone_pfn;
	struct pbe *pbe, *p;

	pbe = pblist;
	for_each_zone (zone) {
		if (is_highmem(zone))
			continue;
		mark_free_pages(zone);
		/* This is necessary for swsusp_free() */
		for_each_pb_page (p, pblist)
			SetPageNosaveFree(virt_to_page(p));
		for_each_pbe (p, pblist)
			SetPageNosaveFree(virt_to_page(p->address));
		for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn) {
			if (saveable(zone, &zone_pfn)) {
				struct page *page;
				page = pfn_to_page(zone_pfn + zone->zone_start_pfn);
				BUG_ON(!pbe);
				pbe->orig_address = (unsigned long)page_address(page);
				/* copy_page is not usable for copying task structs. */
				memcpy((void *)pbe->address, (void *)pbe->orig_address, PAGE_SIZE);
				pbe = pbe->next;
			}
		}
	}
	BUG_ON(pbe);
}


/**
 *	free_pagedir - free pages allocated with alloc_pagedir()
 */

void free_pagedir(struct pbe *pblist)
{
	struct pbe *pbe;

	while (pblist) {
		pbe = (pblist + PB_PAGE_SKIP)->next;
		ClearPageNosave(virt_to_page(pblist));
		ClearPageNosaveFree(virt_to_page(pblist));
		free_page((unsigned long)pblist);
		pblist = pbe;
	}
}

/**
 *	fill_pb_page - Create a list of PBEs on a given memory page
 */

static inline void fill_pb_page(struct pbe *pbpage)
{
	struct pbe *p;

	p = pbpage;
	pbpage += PB_PAGE_SKIP;
	do
		p->next = p + 1;
	while (++p < pbpage);
}

/**
 *	create_pbe_list - Create a list of PBEs on top of a given chain
 *	of memory pages allocated with alloc_pagedir()
 */

static inline void create_pbe_list(struct pbe *pblist, unsigned int nr_pages)
{
	struct pbe *pbpage, *p;
	unsigned int num = PBES_PER_PAGE;

	for_each_pb_page (pbpage, pblist) {
		if (num >= nr_pages)
			break;

		fill_pb_page(pbpage);
		num += PBES_PER_PAGE;
	}
	if (pbpage) {
		for (num -= PBES_PER_PAGE - 1, p = pbpage; num < nr_pages; p++, num++)
			p->next = p + 1;
		p->next = NULL;
	}
}

/**
 *	On resume it is necessary to trace and eventually free the unsafe
 *	pages that have been allocated, because they are needed for I/O
 *	(on x86-64 we likely will "eat" these pages once again while
 *	creating the temporary page translation tables)
 */

struct eaten_page {
	struct eaten_page *next;
	char padding[PAGE_SIZE - sizeof(void *)];
};

static struct eaten_page *eaten_pages = NULL;

void release_eaten_pages(void)
{
	struct eaten_page *p, *q;

	p = eaten_pages;
	while (p) {
		q = p->next;
		/* We don't want swsusp_free() to free this page again */
		ClearPageNosave(virt_to_page(p));
		free_page((unsigned long)p);
		p = q;
	}
	eaten_pages = NULL;
}

/**
 *	@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
 *	which had been used before suspend.
 *
 *	The unsafe pages are marked with the PG_nosave_free flag
 *
 *	Allocated but unusable (ie eaten) memory pages should be marked
 *	so that swsusp_free() can release them
 */

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

	if (safe_needed)
		do {
			res = (void *)get_zeroed_page(gfp_mask);
			if (res && PageNosaveFree(virt_to_page(res))) {
				/* This is for swsusp_free() */
				SetPageNosave(virt_to_page(res));
				((struct eaten_page *)res)->next = eaten_pages;
				eaten_pages = res;
			}
		} while (res && PageNosaveFree(virt_to_page(res)));
	else
		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)alloc_image_page(gfp_mask, 1);
}

/**
 *	alloc_pagedir - Allocate the page directory.
 *
 *	First, determine exactly how many pages we need and
 *	allocate them.
 *
 *	We arrange the pages in a chain: each page is an array of PBES_PER_PAGE
 *	struct pbe elements (pbes) and the last element in the page points
 *	to the next page.
 *
 *	On each page we set up a list of struct_pbe elements.
 */

struct pbe *alloc_pagedir(unsigned int nr_pages, gfp_t gfp_mask, int safe_needed)
{
	unsigned int num;
	struct pbe *pblist, *pbe;

	if (!nr_pages)
		return NULL;

	pr_debug("alloc_pagedir(): nr_pages = %d\n", nr_pages);
	pblist = alloc_image_page(gfp_mask, safe_needed);
	/* FIXME: rewrite this ugly loop */
	for (pbe = pblist, num = PBES_PER_PAGE; pbe && num < nr_pages;
        		pbe = pbe->next, num += PBES_PER_PAGE) {
		pbe += PB_PAGE_SKIP;
		pbe->next = alloc_image_page(gfp_mask, safe_needed);
	}
	if (!pbe) { /* get_zeroed_page() failed */
		free_pagedir(pblist);
		pblist = NULL;
        } else
        	create_pbe_list(pblist, nr_pages);
	return pblist;
}

/**
 * Free pages we allocated for suspend. Suspend pages are alocated
 * before atomic copy, so we need to free them after resume.
 */

void swsusp_free(void)
{
	struct zone *zone;
	unsigned long zone_pfn;

	for_each_zone(zone) {
		for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn)
			if (pfn_valid(zone_pfn + zone->zone_start_pfn)) {
				struct page *page;
				page = pfn_to_page(zone_pfn + zone->zone_start_pfn);
				if (PageNosave(page) && PageNosaveFree(page)) {
					ClearPageNosave(page);
					ClearPageNosaveFree(page);
					free_page((long) page_address(page));
				}
			}
	}
}


/**
 *	enough_free_mem - Make sure we enough free memory to snapshot.
 *
 *	Returns TRUE or FALSE after checking the number of available
 *	free pages.
 */

static int enough_free_mem(unsigned int nr_pages)
{
	struct zone *zone;
	unsigned int n = 0;

	for_each_zone (zone)
		if (!is_highmem(zone))
			n += zone->free_pages;
	pr_debug("swsusp: available memory: %u pages\n", n);
	return n > (nr_pages + PAGES_FOR_IO +
		(nr_pages + PBES_PER_PAGE - 1) / PBES_PER_PAGE);
}

int alloc_data_pages(struct pbe *pblist, gfp_t gfp_mask, int safe_needed)
{
	struct pbe *p;

	for_each_pbe (p, pblist) {
		p->address = (unsigned long)alloc_image_page(gfp_mask, safe_needed);
		if (!p->address)
			return -ENOMEM;
	}
	return 0;
}

static struct pbe *swsusp_alloc(unsigned int nr_pages)
{
	struct pbe *pblist;

	if (!(pblist = alloc_pagedir(nr_pages, GFP_ATOMIC | __GFP_COLD, 0))) {
		printk(KERN_ERR "suspend: Allocating pagedir failed.\n");
		return NULL;
	}

	if (alloc_data_pages(pblist, GFP_ATOMIC | __GFP_COLD, 0)) {
		printk(KERN_ERR "suspend: Allocating image pages failed.\n");
		swsusp_free();
		return NULL;
	}

	return pblist;
}

asmlinkage int swsusp_save(void)
{
	unsigned int nr_pages;

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

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

	pr_debug("swsusp: pages needed: %u + %lu + %u, free: %u\n",
		 nr_pages,
		 (nr_pages + PBES_PER_PAGE - 1) / PBES_PER_PAGE,
		 PAGES_FOR_IO, nr_free_pages());

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

	pagedir_nosave = swsusp_alloc(nr_pages);
	if (!pagedir_nosave)
		return -ENOMEM;

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

	/*
	 * 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_copy_pages = nr_pages;

	printk("swsusp: critical section/: done (%d pages copied)\n", nr_pages);
	return 0;
}