swsusp.c.bak

电源管理代码 基于linux2.6.10！apm方式的电源管理！很好的资料！做arm平台使用

/*
 * linux/kernel/power/swsusp.c
 *
 * This file is to realize architecture-independent
 * machine suspend feature using pretty near only high-level routines
 *
 * Copyright (C) 1998-2001 Gabor Kuti <[e-mail]>
 * Copyright (C) 1998,2001-2004 Pavel Machek <[e-mail]>
 *
 * This file is released under the GPLv2.
 *
 * I'd like to thank the following people for their work:
 * 
 * Pavel Machek <[e-mail]>:
 * 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 <[e-mail]>: 
 * Support the possibility of hardware state restoring.
 *
 * Raph <[e-mail]>:
 * Support for preserving states of network devices and virtual console
 * (including X and svgatextmode)
 *
 * Kurt Garloff <[e-mail]>:
 * Straightened the critical function in order to prevent compilers from
 * playing tricks with local variables.
 *
 * Andreas Mohr <[e-mail]>
 *
 * Alex Badea <[e-mail]>:
 * Fixed runaway init
 *
 * 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/reboot.h>
#include <linux/bitops.h>
#include <linux/vt_kern.h>
#include <linux/kbd_kern.h>
#include <linux/keyboard.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/console.h>
#include <linux/highmem.h>
#include <linux/bio.h>

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

#include "power.h"

/* References to section boundaries */
extern char __nosave_begin, __nosave_end;

extern int is_head_of_free_region(struct page *);

/* Variables to be preserved over suspend */
int pagedir_order_check;
int nr_copy_pages_check;

extern char resume_file[];
static dev_t resume_device;
/* 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 evil. There are actually two pagedirs at time of
   resume. One is "pagedir_save", which is empty frame allocated at
   time of suspend, that must be freed. Second is "pagedir_nosave", 
   allocated at time of resume, that travels through memory not to
   collide with anything.

   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;
static suspend_pagedir_t *pagedir_save;
static int pagedir_order __nosavedata = 0;

#define SWSUSP_SIG	"S1SUSPEND"

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

struct swsusp_info swsusp_info;

/*
 * XXX: We try to keep some more pages free so that I/O operations succeed
 * without paging. Might this be more?
 */
#define PAGES_FOR_IO	512

/*
 * 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 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);
		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) &&
		resume_device == MKDEV(imajor(inode), iminor(inode));
}

int swsusp_swap_check(void) /* This is called before saving image */
{
	int i, len;
	
	len=strlen(resume_file);
	root_swap = 0xFFFF;
	
	swap_list_lock();
	for(i=0; i<MAX_SWAPFILES; i++) {
		if (swap_info[i].flags == 0) {
			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;
				}
			}
		}
	}
	swap_list_unlock();
	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;

	swap_list_lock();
	for(i = 0; i< MAX_SWAPFILES; i++)
		if(swapfile_used[i] == SWAPFILE_IGNORED) {
			swap_info[i].flags ^= 0xFF;
		}
	swap_list_unlock();
}



/**
 *	write_swap_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;
	int i;

	for (i = 0; i < nr_copy_pages; i++) {
		entry = (pagedir_nosave + i)->swap_address;
		if (entry.val)
			swap_free(entry);
		else
			break;
		(pagedir_nosave + i)->swap_address = (swp_entry_t){0};
	}
}


/**
 *	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;
	int i;
	unsigned int mod = nr_copy_pages / 100;

	if (!mod)
		mod = 1;

	printk( "Writing data to swap (%d pages)...     ", nr_copy_pages );
	for (i = 0; i < nr_copy_pages && !error; i++) {
		if (!(i%mod))
			printk( "\b\b\b\b%3d%%", i / mod );
		error = write_page((pagedir_nosave+i)->address,
					  &((pagedir_nosave+i)->swap_address));
	}
	printk("\b\b\b\bdone\n");
	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;
	dump_info();
}

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

	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)
{
	unsigned long addr = (unsigned long)pagedir_nosave;
	int error = 0;
	int n = SUSPEND_PD_PAGES(nr_copy_pages);
	int i;

	swsusp_info.pagedir_pages = n;
	printk( "Writing pagedir (%d pages)\n", n);
	for (i = 0; i < n && !error; i++, addr += PAGE_SIZE)
		error = write_page(addr, &swsusp_info.pagedir[i]);
	return error;
}

/**
 *	write_suspend_image - Write entire image and metadata.
 *
 */

static int write_suspend_image(void)
{
	int error;

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

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

	if ((error = close_swap()))
		goto FreePagedir;
 Done:
	return error;
 FreePagedir:
	free_pagedir_entries();
 FreeData:
	data_free();
	goto Done;
}


#ifdef CONFIG_HIGHMEM
struct highmem_page {
	char *data;
	struct page *page;
	struct highmem_page *next;
};

struct highmem_page *highmem_copy = NULL;

static int save_highmem_zone(struct zone *zone)
{
	unsigned long zone_pfn;
	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;
		int chunk_size;

		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;
		}
		if ((chunk_size = is_head_of_free_region(page))) {
			pfn += chunk_size - 1;
			zone_pfn += chunk_size - 1;
			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;
}
#endif /* CONFIG_HIGHMEM */


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

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


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.
 *	If it is part of a free chunk, we update @pfn to point to the last 
 *	page of the chunk.
 */

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

	if (!pfn_valid(pfn))
		return 0;

	if (!(pfn%1000))
		printk(".");
	page = pfn_to_page(pfn);
	BUG_ON(PageReserved(page) && PageNosave(page));
	if (PageNosave(page))
		return 0;
	if (PageReserved(page) && pfn_is_nosave(pfn)) {
		pr_debug("[nosave pfn 0x%lx]", pfn);
		return 0;
	}
	if ((chunk_size = is_head_of_free_region(page))) {
		*zone_pfn += chunk_size - 1;
		return 0;
	}

	return 1;
}

static void count_data_pages(void)
{
	struct zone *zone;
	unsigned long zone_pfn;

	nr_copy_pages = 0;

	for_each_zone(zone) {
		if (!is_highmem(zone)) {
			for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn)
				nr_copy_pages += saveable(zone, &zone_pfn);
		}
	}
}


static void copy_data_pages(void)
{
	struct zone *zone;
	unsigned long zone_pfn;
	struct pbe * pbe = pagedir_nosave;
	
	for_each_zone(zone) {
		if (!is_highmem(zone))
			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);
					pbe->orig_address = (long) page_address(page);
					/* copy_page is no usable for copying task structs. */
					memcpy((void *)pbe->address, (void *)pbe->orig_address, PAGE_SIZE);
					pbe++;
				}
			}
	}
}


static void free_suspend_pagedir_zone(struct zone *zone, unsigned long pagedir)
{
	unsigned long zone_pfn, pagedir_end, pagedir_pfn, pagedir_end_pfn;
	pagedir_end = pagedir + (PAGE_SIZE << pagedir_order);
	pagedir_pfn = __pa(pagedir) >> PAGE_SHIFT;
	pagedir_end_pfn = __pa(pagedir_end) >> PAGE_SHIFT;
	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 (!TestClearPageNosave(page))
			continue;
		else if (pfn >= pagedir_pfn && pfn < pagedir_end_pfn)
			continue;
		__free_page(page);
	}
}

void swsusp_free(void)
{
	unsigned long p = (unsigned long)pagedir_save;
	struct zone *zone;
	for_each_zone(zone) {
		if (!is_highmem(zone))
			free_suspend_pagedir_zone(zone, p);
	}