Creation of Cybook 2416 (actually Gen4) repository

kernel/power/Kconfig

@@ -0,0 +1,173 @@
+config PM
+	bool "Power Management support"
+	depends on !IA64_HP_SIM
+	---help---
+	  "Power Management" means that parts of your computer are shut
+	  off or put into a power conserving "sleep" mode if they are not
+	  being used.  There are two competing standards for doing this: APM
+	  and ACPI.  If you want to use either one, say Y here and then also
+	  to the requisite support below.
+
+	  Power Management is most important for battery powered laptop
+	  computers; if you have a laptop, check out the Linux Laptop home
+	  page on the WWW at <http://www.linux-on-laptops.com/> or
+	  Tuxmobil - Linux on Mobile Computers at <http://www.tuxmobil.org/>
+	  and the Battery Powered Linux mini-HOWTO, available from
+	  <http://www.tldp.org/docs.html#howto>.
+
+	  Note that, even if you say N here, Linux on the x86 architecture
+	  will issue the hlt instruction if nothing is to be done, thereby
+	  sending the processor to sleep and saving power.
+
+config PM_LEGACY
+	bool "Legacy Power Management API (DEPRECATED)"
+	depends on PM
+	default n
+	---help---
+	   Support for pm_register() and friends.  This old API is obsoleted
+	   by the driver model.
+
+	   If unsure, say N.
+
+config PM_CPU_MODE
+	bool "PM_CPU_MODE"
+	depends on PM
+        default y
+	---help---
+        This is for the power consumption of CPU mode 
+
+config PM_DEBUG
+	bool "Power Management Debug Support"
+	depends on PM
+	---help---
+	This option enables verbose debugging support in the Power Management
+	code. This is helpful when debugging and reporting various PM bugs, 
+	like suspend support.
+
+config DISABLE_CONSOLE_SUSPEND
+	bool "Keep console(s) enabled during suspend/resume (DANGEROUS)"
+	depends on PM && PM_DEBUG
+	default n
+	---help---
+	This option turns off the console suspend mechanism that prevents
+	debug messages from reaching the console during the suspend/resume
+	operations.  This may be helpful when debugging device drivers'
+	suspend/resume routines, but may itself lead to problems, for example
+	if netconsole is used.
+
+config PM_TRACE
+	bool "Suspend/resume event tracing"
+	depends on PM && PM_DEBUG && X86_32 && EXPERIMENTAL
+	default n
+	---help---
+	This enables some cheesy code to save the last PM event point in the
+	RTC across reboots, so that you can debug a machine that just hangs
+	during suspend (or more commonly, during resume).
+
+	To use this debugging feature you should attempt to suspend the machine,
+	then reboot it, then run
+
+		dmesg -s 1000000 | grep 'hash matches'
+
+	CAUTION: this option will cause your machine's real-time clock to be
+	set to an invalid time after a resume.
+
+config PM_SYSFS_DEPRECATED
+	bool "Driver model /sys/devices/.../power/state files (DEPRECATED)"
+	depends on PM && SYSFS
+	default n
+	help
+	  The driver model started out with a sysfs file intended to provide
+	  a userspace hook for device power management.  This feature has never
+	  worked very well, except for limited testing purposes, and so it will
+	  be removed.   It's not clear that a generic mechanism could really
+	  handle the wide variability of device power states; any replacements
+	  are likely to be bus or driver specific.
+
+config SOFTWARE_SUSPEND
+	bool "Software Suspend"
+	depends on PM && SWAP && ((X86 && (!SMP || SUSPEND_SMP)) || ((FRV || PPC32) && !SMP))
+	---help---
+	  Enable the suspend to disk (STD) functionality.
+
+	  You can suspend your machine with 'echo disk > /sys/power/state'.
+	  Alternatively, you can use the additional userland tools available
+	  from <http://suspend.sf.net>.
+
+	  In principle it does not require ACPI or APM, although for example
+	  ACPI will be used if available.
+
+	  It creates an image which is saved in your active swap. Upon the next
+	  boot, pass the 'resume=/dev/swappartition' argument to the kernel to
+	  have it detect the saved image, restore memory state from it, and
+	  continue to run as before. If you do not want the previous state to
+	  be reloaded, then use the 'noresume' kernel command line argument.
+	  Note, however, that fsck will be run on your filesystems and you will
+	  need to run mkswap against the swap partition used for the suspend.
+
+	  It also works with swap files to a limited extent (for details see
+	  <file:Documentation/power/swsusp-and-swap-files.txt>).
+
+	  Right now you may boot without resuming and resume later but in the
+	  meantime you cannot use the swap partition(s)/file(s) involved in
+	  suspending.  Also in this case you must not use the filesystems
+	  that were mounted before the suspend.  In particular, you MUST NOT
+	  MOUNT any journaled filesystems mounted before the suspend or they
+	  will get corrupted in a nasty way.
+
+	  For more information take a look at <file:Documentation/power/swsusp.txt>.
+
+config PM_STD_PARTITION
+	string "Default resume partition"
+	depends on SOFTWARE_SUSPEND
+	default ""
+	---help---
+	  The default resume partition is the partition that the suspend-
+	  to-disk implementation will look for a suspended disk image. 
+
+	  The partition specified here will be different for almost every user. 
+	  It should be a valid swap partition (at least for now) that is turned
+	  on before suspending. 
+
+	  The partition specified can be overridden by specifying:
+
+		resume=/dev/<other device> 
+
+	  which will set the resume partition to the device specified. 
+
+	  Note there is currently not a way to specify which device to save the
+	  suspended image to. It will simply pick the first available swap 
+	  device.
+
+config SUSPEND_SMP
+	bool
+	depends on HOTPLUG_CPU && X86 && PM
+	default y
+
+config APM_EMULATION
+	tristate "Advanced Power Management Emulation"
+	depends on PM && SYS_SUPPORTS_APM_EMULATION
+	help
+	  APM is a BIOS specification for saving power using several different
+	  techniques. This is mostly useful for battery powered laptops with
+	  APM compliant BIOSes. If you say Y here, the system time will be
+	  reset after a RESUME operation, the /proc/apm device will provide
+	  battery status information, and user-space programs will receive
+	  notification of APM "events" (e.g. battery status change).
+
+	  In order to use APM, you will need supporting software. For location
+	  and more information, read <file:Documentation/pm.txt> and the
+	  Battery Powered Linux mini-HOWTO, available from
+	  <http://www.tldp.org/docs.html#howto>.
+
+	  This driver does not spin down disk drives (see the hdparm(8)
+	  manpage ("man 8 hdparm") for that), and it doesn't turn off
+	  VESA-compliant "green" monitors.
+
+	  Generally, if you don't have a battery in your machine, there isn't
+	  much point in using this driver and you should say N. If you get
+	  random kernel OOPSes or reboots that don't seem to be related to
+	  anything, try disabling/enabling this option (or disabling/enabling
+	  APM in your BIOS).
+
+source "drivers/char/s3c-dvfs/Kconfig"

kernel/power/Makefile

@@ -0,0 +1,10 @@
+
+ifeq ($(CONFIG_PM_DEBUG),y)
+EXTRA_CFLAGS	+=	-DDEBUG
+endif
+
+obj-y				:= main.o process.o console.o
+obj-$(CONFIG_PM_LEGACY)		+= pm.o
+obj-$(CONFIG_SOFTWARE_SUSPEND)	+= swsusp.o disk.o snapshot.o swap.o user.o
+
+obj-$(CONFIG_MAGIC_SYSRQ)	+= poweroff.o

kernel/power/console.c

@@ -0,0 +1,58 @@
+/*
+ * drivers/power/process.c - Functions for saving/restoring console.
+ *
+ * Originally from swsusp.
+ */
+
+#include <linux/vt_kern.h>
+#include <linux/kbd_kern.h>
+#include <linux/console.h>
+#include "power.h"
+
+#if defined(CONFIG_VT) && defined(CONFIG_VT_CONSOLE)
+#define SUSPEND_CONSOLE	(MAX_NR_CONSOLES-1)
+
+static int orig_fgconsole, orig_kmsg;
+
+int pm_prepare_console(void)
+{
+	acquire_console_sem();
+
+	orig_fgconsole = fg_console;
+
+	if (vc_allocate(SUSPEND_CONSOLE)) {
+	  /* we can't have a free VC for now. Too bad,
+	   * we don't want to mess the screen for now. */
+		release_console_sem();
+		return 1;
+	}
+
+	if (set_console(SUSPEND_CONSOLE)) {
+		/*
+		 * We're unable to switch to the SUSPEND_CONSOLE.
+		 * Let the calling function know so it can decide
+		 * what to do.
+		 */
+		release_console_sem();
+		return 1;
+	}
+	release_console_sem();
+
+	if (vt_waitactive(SUSPEND_CONSOLE)) {
+		pr_debug("Suspend: Can't switch VCs.");
+		return 1;
+	}
+	orig_kmsg = kmsg_redirect;
+	kmsg_redirect = SUSPEND_CONSOLE;
+	return 0;
+}
+
+void pm_restore_console(void)
+{
+	acquire_console_sem();
+	set_console(orig_fgconsole);
+	release_console_sem();
+	kmsg_redirect = orig_kmsg;
+	return;
+}
+#endif

kernel/power/disk.c

@@ -0,0 +1,465 @@
+/*
+ * kernel/power/disk.c - Suspend-to-disk support.
+ *
+ * Copyright (c) 2003 Patrick Mochel
+ * Copyright (c) 2003 Open Source Development Lab
+ * Copyright (c) 2004 Pavel Machek <pavel@suse.cz>
+ *
+ * This file is released under the GPLv2.
+ *
+ */
+
+#include <linux/suspend.h>
+#include <linux/syscalls.h>
+#include <linux/reboot.h>
+#include <linux/string.h>
+#include <linux/device.h>
+#include <linux/delay.h>
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/pm.h>
+#include <linux/console.h>
+#include <linux/cpu.h>
+#include <linux/freezer.h>
+
+#include "power.h"
+
+
+static int noresume = 0;
+char resume_file[256] = CONFIG_PM_STD_PARTITION;
+dev_t swsusp_resume_device;
+sector_t swsusp_resume_block;
+
+/**
+ *	platform_prepare - prepare the machine for hibernation using the
+ *	platform driver if so configured and return an error code if it fails
+ */
+
+static inline int platform_prepare(void)
+{
+	int error = 0;
+
+	if (pm_disk_mode == PM_DISK_PLATFORM) {
+		if (pm_ops && pm_ops->prepare)
+			error = pm_ops->prepare(PM_SUSPEND_DISK);
+	}
+	return error;
+}
+
+/**
+ *	power_down - Shut machine down for hibernate.
+ *	@mode:		Suspend-to-disk mode
+ *
+ *	Use the platform driver, if configured so, and return gracefully if it
+ *	fails.
+ *	Otherwise, try to power off and reboot. If they fail, halt the machine,
+ *	there ain't no turning back.
+ */
+
+static void power_down(suspend_disk_method_t mode)
+{
+	switch(mode) {
+	case PM_DISK_PLATFORM:
+		if (pm_ops && pm_ops->enter) {
+			kernel_shutdown_prepare(SYSTEM_SUSPEND_DISK);
+			pm_ops->enter(PM_SUSPEND_DISK);
+			break;
+		}
+	case PM_DISK_SHUTDOWN:
+		kernel_power_off();
+		break;
+	case PM_DISK_REBOOT:
+		kernel_restart(NULL);
+		break;
+	}
+	kernel_halt();
+	/* Valid image is on the disk, if we continue we risk serious data corruption
+	   after resume. */
+	printk(KERN_CRIT "Please power me down manually\n");
+	while(1);
+}
+
+static inline void platform_finish(void)
+{
+	if (pm_disk_mode == PM_DISK_PLATFORM) {
+		if (pm_ops && pm_ops->finish)
+			pm_ops->finish(PM_SUSPEND_DISK);
+	}
+}
+
+static void unprepare_processes(void)
+{
+	thaw_processes();
+	pm_restore_console();
+}
+
+static int prepare_processes(void)
+{
+	int error = 0;
+
+	pm_prepare_console();
+	if (freeze_processes()) {
+		error = -EBUSY;
+		unprepare_processes();
+	}
+	return error;
+}
+
+/**
+ *	pm_suspend_disk - The granpappy of hibernation power management.
+ *
+ *	If we're going through the firmware, then get it over with quickly.
+ *
+ *	If not, then call swsusp to do its thing, then figure out how
+ *	to power down the system.
+ */
+
+int pm_suspend_disk(void)
+{
+	int error;
+
+	error = prepare_processes();
+	if (error)
+		return error;
+
+	if (pm_disk_mode == PM_DISK_TESTPROC) {
+		printk("swsusp debug: Waiting for 5 seconds.\n");
+		mdelay(5000);
+		goto Thaw;
+	}
+	/* Free memory before shutting down devices. */
+	error = swsusp_shrink_memory();
+	if (error)
+		goto Thaw;
+
+	error = platform_prepare();
+	if (error)
+		goto Thaw;
+
+	suspend_console();
+	error = device_suspend(PMSG_FREEZE);
+	if (error) {
+		printk(KERN_ERR "PM: Some devices failed to suspend\n");
+		goto Resume_devices;
+	}
+	error = disable_nonboot_cpus();
+	if (error)
+		goto Enable_cpus;
+
+	if (pm_disk_mode == PM_DISK_TEST) {
+		printk("swsusp debug: Waiting for 5 seconds.\n");
+		mdelay(5000);
+		goto Enable_cpus;
+	}
+
+	pr_debug("PM: snapshotting memory.\n");
+	in_suspend = 1;
+	error = swsusp_suspend();
+	if (error)
+		goto Enable_cpus;
+
+	if (in_suspend) {
+		enable_nonboot_cpus();
+		platform_finish();
+		device_resume();
+		resume_console();
+		pr_debug("PM: writing image.\n");
+		error = swsusp_write();
+		if (!error)
+			power_down(pm_disk_mode);
+		else {
+			swsusp_free();
+			goto Thaw;
+		}
+	} else {
+		pr_debug("PM: Image restored successfully.\n");
+	}
+
+	swsusp_free();
+ Enable_cpus:
+	enable_nonboot_cpus();
+ Resume_devices:
+	platform_finish();
+	device_resume();
+	resume_console();
+ Thaw:
+	unprepare_processes();
+	return error;
+}
+
+
+/**
+ *	software_resume - Resume from a saved image.
+ *
+ *	Called as a late_initcall (so all devices are discovered and
+ *	initialized), we call swsusp to see if we have a saved image or not.
+ *	If so, we quiesce devices, the restore the saved image. We will
+ *	return above (in pm_suspend_disk() ) if everything goes well.
+ *	Otherwise, we fail gracefully and return to the normally
+ *	scheduled program.
+ *
+ */
+
+static int software_resume(void)
+{
+	int error;
+
+	mutex_lock(&pm_mutex);
+	if (!swsusp_resume_device) {
+		if (!strlen(resume_file)) {
+			mutex_unlock(&pm_mutex);
+			return -ENOENT;
+		}
+		swsusp_resume_device = name_to_dev_t(resume_file);
+		pr_debug("swsusp: Resume From Partition %s\n", resume_file);
+	} else {
+		pr_debug("swsusp: Resume From Partition %d:%d\n",
+			 MAJOR(swsusp_resume_device), MINOR(swsusp_resume_device));
+	}
+
+	if (noresume) {
+		/**
+		 * FIXME: If noresume is specified, we need to find the partition
+		 * and reset it back to normal swap space.
+		 */
+		mutex_unlock(&pm_mutex);
+		return 0;
+	}
+
+	pr_debug("PM: Checking swsusp image.\n");
+
+	error = swsusp_check();
+	if (error)
+		goto Done;
+
+	pr_debug("PM: Preparing processes for restore.\n");
+
+	error = prepare_processes();
+	if (error) {
+		swsusp_close();
+		goto Done;
+	}
+
+	pr_debug("PM: Reading swsusp image.\n");
+
+	error = swsusp_read();
+	if (error) {
+		swsusp_free();
+		goto Thaw;
+	}
+
+	pr_debug("PM: Preparing devices for restore.\n");
+
+	suspend_console();
+	error = device_suspend(PMSG_PRETHAW);
+	if (error)
+		goto Free;
+
+	error = disable_nonboot_cpus();
+	if (!error)
+		swsusp_resume();
+
+	enable_nonboot_cpus();
+ Free:
+	swsusp_free();
+	device_resume();
+	resume_console();
+ Thaw:
+	printk(KERN_ERR "PM: Restore failed, recovering.\n");
+	unprepare_processes();
+ Done:
+	/* For success case, the suspend path will release the lock */
+	mutex_unlock(&pm_mutex);
+	pr_debug("PM: Resume from disk failed.\n");
+	return 0;
+}
+
+late_initcall(software_resume);
+
+
+static const char * const pm_disk_modes[] = {
+	[PM_DISK_FIRMWARE]	= "firmware",
+	[PM_DISK_PLATFORM]	= "platform",
+	[PM_DISK_SHUTDOWN]	= "shutdown",
+	[PM_DISK_REBOOT]	= "reboot",
+	[PM_DISK_TEST]		= "test",
+	[PM_DISK_TESTPROC]	= "testproc",
+};
+
+/**
+ *	disk - Control suspend-to-disk mode
+ *
+ *	Suspend-to-disk can be handled in several ways. The greatest
+ *	distinction is who writes memory to disk - the firmware or the OS.
+ *	If the firmware does it, we assume that it also handles suspending
+ *	the system.
+ *	If the OS does it, then we have three options for putting the system
+ *	to sleep - using the platform driver (e.g. ACPI or other PM registers),
+ *	powering off the system or rebooting the system (for testing).
+ *
+ *	The system will support either 'firmware' or 'platform', and that is
+ *	known a priori (and encoded in pm_ops). But, the user may choose
+ *	'shutdown' or 'reboot' as alternatives.
+ *
+ *	show() will display what the mode is currently set to.
+ *	store() will accept one of
+ *
+ *	'firmware'
+ *	'platform'
+ *	'shutdown'
+ *	'reboot'
+ *
+ *	It will only change to 'firmware' or 'platform' if the system
+ *	supports it (as determined from pm_ops->pm_disk_mode).
+ */
+
+static ssize_t disk_show(struct subsystem * subsys, char * buf)
+{
+	return sprintf(buf, "%s\n", pm_disk_modes[pm_disk_mode]);
+}
+
+
+static ssize_t disk_store(struct subsystem * s, const char * buf, size_t n)
+{
+	int error = 0;
+	int i;
+	int len;
+	char *p;
+	suspend_disk_method_t mode = 0;
+
+	p = memchr(buf, '\n', n);
+	len = p ? p - buf : n;
+
+	mutex_lock(&pm_mutex);
+	for (i = PM_DISK_FIRMWARE; i < PM_DISK_MAX; i++) {
+		if (!strncmp(buf, pm_disk_modes[i], len)) {
+			mode = i;
+			break;
+		}
+	}
+	if (mode) {
+		if (mode == PM_DISK_SHUTDOWN || mode == PM_DISK_REBOOT ||
+		     mode == PM_DISK_TEST || mode == PM_DISK_TESTPROC) {
+			pm_disk_mode = mode;
+		} else {
+			if (pm_ops && pm_ops->enter &&
+			    (mode == pm_ops->pm_disk_mode))
+				pm_disk_mode = mode;
+			else
+				error = -EINVAL;
+		}
+	} else {
+		error = -EINVAL;
+	}
+
+	pr_debug("PM: suspend-to-disk mode set to '%s'\n",
+		 pm_disk_modes[mode]);
+	mutex_unlock(&pm_mutex);
+	return error ? error : n;
+}
+
+power_attr(disk);
+
+static ssize_t resume_show(struct subsystem * subsys, char *buf)
+{
+	return sprintf(buf,"%d:%d\n", MAJOR(swsusp_resume_device),
+		       MINOR(swsusp_resume_device));
+}
+
+static ssize_t resume_store(struct subsystem *subsys, const char *buf, size_t n)
+{
+	unsigned int maj, min;
+	dev_t res;
+	int ret = -EINVAL;
+
+	if (sscanf(buf, "%u:%u", &maj, &min) != 2)
+		goto out;
+
+	res = MKDEV(maj,min);
+	if (maj != MAJOR(res) || min != MINOR(res))
+		goto out;
+
+	mutex_lock(&pm_mutex);
+	swsusp_resume_device = res;
+	mutex_unlock(&pm_mutex);
+	printk("Attempting manual resume\n");
+	noresume = 0;
+	software_resume();
+	ret = n;
+ out:
+	return ret;
+}
+
+power_attr(resume);
+
+static ssize_t image_size_show(struct subsystem * subsys, char *buf)
+{
+	return sprintf(buf, "%lu\n", image_size);
+}
+
+static ssize_t image_size_store(struct subsystem * subsys, const char * buf, size_t n)
+{
+	unsigned long size;
+
+	if (sscanf(buf, "%lu", &size) == 1) {
+		image_size = size;
+		return n;
+	}
+
+	return -EINVAL;
+}
+
+power_attr(image_size);
+
+static struct attribute * g[] = {
+	&disk_attr.attr,
+	&resume_attr.attr,
+	&image_size_attr.attr,
+	NULL,
+};
+
+
+static struct attribute_group attr_group = {
+	.attrs = g,
+};
+
+
+static int __init pm_disk_init(void)
+{
+	return sysfs_create_group(&power_subsys.kset.kobj,&attr_group);
+}
+
+core_initcall(pm_disk_init);
+
+
+static int __init resume_setup(char *str)
+{
+	if (noresume)
+		return 1;
+
+	strncpy( resume_file, str, 255 );
+	return 1;
+}
+
+static int __init resume_offset_setup(char *str)
+{
+	unsigned long long offset;
+
+	if (noresume)
+		return 1;
+
+	if (sscanf(str, "%llu", &offset) == 1)
+		swsusp_resume_block = offset;
+
+	return 1;
+}
+
+static int __init noresume_setup(char *str)
+{
+	noresume = 1;
+	return 1;
+}
+
+__setup("noresume", noresume_setup);
+__setup("resume_offset=", resume_offset_setup);
+__setup("resume=", resume_setup);

kernel/power/main.c

@@ -0,0 +1,451 @@
+/*
+ * kernel/power/main.c - PM subsystem core functionality.
+ *
+ * Copyright (c) 2003 Patrick Mochel
+ * Copyright (c) 2003 Open Source Development Lab
+ * 
+ * This file is released under the GPLv2
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/suspend.h>
+#include <linux/kobject.h>
+#include <linux/string.h>
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/pm.h>
+#include <linux/console.h>
+#include <linux/cpu.h>
+#include <linux/resume-trace.h>
+#include <linux/freezer.h>
+#include <linux/vmstat.h>
+#include "power.h"
+#if 0
+/* Qisda, ShiYong Lin, 2009/07/18, Send message when sleep{*/
+#include <linux/input.h>
+/* Qisda, ShiYong Lin, 2009/07/18, Send message when sleep}*/
+#endif
+#ifdef CONFIG_PM_CPU_MODE
+extern unsigned char pm_cpu_mode;
+#endif
+
+/*This is just an arbitrary number */
+#define FREE_PAGE_NUMBER (100)
+
+DEFINE_MUTEX(pm_mutex);
+
+struct pm_ops *pm_ops;
+suspend_disk_method_t pm_disk_mode = PM_DISK_PLATFORM;
+/* Qisda, ShiYong Lin, 2009/07/18, Send message when sleep{*/
+extern void pm_keypad_message_to_ap (void);
+/* Qisda, ShiYong Lin, 2009/07/18, Send message when sleep}*/
+
+/**
+ *	pm_set_ops - Set the global power method table. 
+ *	@ops:	Pointer to ops structure.
+ */
+
+void pm_set_ops(struct pm_ops * ops)
+{
+	mutex_lock(&pm_mutex);
+	pm_ops = ops;
+	mutex_unlock(&pm_mutex);
+}
+
+static inline void pm_finish(suspend_state_t state)
+{
+	if (pm_ops->finish)
+		pm_ops->finish(state);
+}
+
+/**
+ *	suspend_prepare - Do prep work before entering low-power state.
+ *	@state:		State we're entering.
+ *
+ *	This is common code that is called for each state that we're 
+ *	entering. Allocate a console, stop all processes, then make sure
+ *	the platform can enter the requested state.
+ */
+
+static int suspend_prepare(suspend_state_t state)
+{
+	int error;
+	unsigned int free_pages;
+
+	if (!pm_ops || !pm_ops->enter)
+		return -EPERM;
+
+	pm_prepare_console();
+
+	if (freeze_processes()) {
+		error = -EAGAIN;
+		goto Thaw;
+	}
+
+	if ((free_pages = global_page_state(NR_FREE_PAGES))
+			< FREE_PAGE_NUMBER) {
+		pr_debug("PM: free some memory\n");
+		shrink_all_memory(FREE_PAGE_NUMBER - free_pages);
+		if (nr_free_pages() < FREE_PAGE_NUMBER) {
+			error = -ENOMEM;
+			printk(KERN_ERR "PM: No enough memory\n");
+			goto Thaw;
+		}
+	}
+
+	if (pm_ops->prepare) {
+		if ((error = pm_ops->prepare(state)))
+			goto Thaw;
+	}
+
+	suspend_console();
+	error = device_suspend(PMSG_SUSPEND);
+	if (error) {
+		printk(KERN_ERR "Some devices failed to suspend\n");
+		goto Resume_devices;
+	}
+	error = disable_nonboot_cpus();
+	if (!error)
+		return 0;
+
+	enable_nonboot_cpus();
+ Resume_devices:
+	pm_finish(state);
+	device_resume();
+	resume_console();
+ Thaw:
+	thaw_processes();
+	pm_restore_console();
+	return error;
+}
+
+
+int suspend_enter(suspend_state_t state)
+{
+	int error = 0;
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	if ((error = device_power_down(PMSG_SUSPEND))) {
+		printk(KERN_ERR "Some devices failed to power down\n");
+		goto Done;
+	}
+	error = pm_ops->enter(state);
+	device_power_up();
+ Done:
+	local_irq_restore(flags);
+	return error;
+}
+
+
+/**
+ *	suspend_finish - Do final work before exiting suspend sequence.
+ *	@state:		State we're coming out of.
+ *
+ *	Call platform code to clean up, restart processes, and free the 
+ *	console that we've allocated. This is not called for suspend-to-disk.
+ */
+
+static void suspend_finish(suspend_state_t state)
+{
+	enable_nonboot_cpus();
+	pm_finish(state);
+	device_resume();
+	resume_console();
+	thaw_processes();
+	pm_restore_console();
+}
+
+
+
+
+static const char * const pm_states[PM_SUSPEND_MAX] = {
+	[PM_SUSPEND_STANDBY]	= "standby",
+	[PM_SUSPEND_MEM]	    = "mem",
+#ifdef CONFIG_PM_CPU_MODE
+	[PM_SUSPEND_CPU_MODE]	= "cpu",
+#endif
+#ifdef CONFIG_SOFTWARE_SUSPEND
+	[PM_SUSPEND_DISK]	    = "disk",
+#endif
+};
+
+static inline int valid_state(suspend_state_t state)
+{
+	/* Suspend-to-disk does not really need low-level support.
+	 * It can work with reboot if needed. */
+	if (state == PM_SUSPEND_DISK)
+		return 1;
+
+	/* all other states need lowlevel support and need to be
+	 * valid to the lowlevel implementation, no valid callback
+	 * implies that all are valid. */
+	if (!pm_ops || (pm_ops->valid && !pm_ops->valid(state)))
+		return 0;
+	return 1;
+}
+
+#ifdef CONFIG_PM_CPU_MODE
+static int suspend_pm_cpu_mode_prepare(suspend_state_t state)
+{
+	return suspend_prepare(state);
+}
+
+
+int suspend_pm_cpu_mode_enter(suspend_state_t state)
+{
+	int error = 0;
+	unsigned long flags;
+    printk("suspend_cpu_mode_enter\n");
+	local_irq_save(flags);
+
+/*
+	if ((error = device_power_down(PMSG_SUSPEND))) {
+		printk(KERN_ERR "Some devices failed to power down\n");
+		goto Done;
+	}
+*/
+	error = pm_ops->enter(state);
+
+	device_power_up();
+ Done:
+	local_irq_restore(flags);
+	return error;
+}
+
+
+static void suspend_pm_cpu_mode_finish(suspend_state_t state)
+{
+	enable_nonboot_cpus();
+	pm_finish(state);
+	device_resume();
+//    s3c24xx_cpu_mode_serial_resume();
+	resume_console();
+	thaw_processes();
+	pm_restore_console();
+}
+
+static int enter_pm_cpu_mode(suspend_state_t state)
+{
+	int error;   
+
+	if (!valid_state(state))
+		return -ENODEV;
+
+	if (!mutex_trylock(&pm_mutex))
+		return -EBUSY;
+
+	if (state == PM_SUSPEND_DISK) {
+		error = pm_suspend_disk();
+		goto Unlock;
+	}
+
+	pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]);
+	if ((error = suspend_pm_cpu_mode_prepare(state)))
+		goto Unlock;
+
+//	pr_debug("PM: Entering %s sleep\n", pm_states[state]);
+	error = suspend_pm_cpu_mode_enter(state);
+	pr_debug("PM: Finishing wakeup.\n");
+	suspend_pm_cpu_mode_finish(state);
+ Unlock:
+	mutex_unlock(&pm_mutex);
+/* Qisda, ShiYong Lin, 2009/09/28, Add the sleep event message when sleep {*/
+    s3c_keypad_pm_sleep_message_to_ap(0);
+//    printk(KERN_ERR "Sleep end enter_pm_cpu_mode, %d\n", state);
+/* } Qisda, ShiYong Lin, 2009/09/28, Add the sleep event message when sleep */
+	return error;
+}
+#endif
+
+
+/**
+ *	enter_state - Do common work of entering low-power state.
+ *	@state:		pm_state structure for state we're entering.
+ *
+ *	Make sure we're the only ones trying to enter a sleep state. Fail
+ *	if someone has beat us to it, since we don't want anything weird to
+ *	happen when we wake up.
+ *	Then, do the setup for suspend, enter the state, and cleaup (after
+ *	we've woken up).
+ */
+
+static int enter_state(suspend_state_t state)
+{
+	int error;
+
+	if (!valid_state(state))
+		return -ENODEV;
+	if (!mutex_trylock(&pm_mutex))
+		return -EBUSY;
+
+	if (state == PM_SUSPEND_DISK) {
+		error = pm_suspend_disk();
+		goto Unlock;
+	}
+
+	pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]);
+	if ((error = suspend_prepare(state)))
+		goto Unlock;
+
+	pr_debug("PM: Entering %s sleep\n", pm_states[state]);
+	error = suspend_enter(state);
+
+	pr_debug("PM: Finishing wakeup.\n");
+	suspend_finish(state);
+ Unlock:
+	mutex_unlock(&pm_mutex);
+/* Qisda, ShiYong Lin, 2009/09/28, Add the sleep event message when sleep {*/
+    s3c_keypad_pm_sleep_message_to_ap(0);
+/* } Qisda, ShiYong Lin, 2009/09/28, Add the sleep event message when sleep */
+	return error;
+}
+
+/*
+ * This is main interface to the outside world. It needs to be
+ * called from process context.
+ */
+int software_suspend(void)
+{
+	return enter_state(PM_SUSPEND_DISK);
+}
+
+
+/**
+ *	pm_suspend - Externally visible function for suspending system.
+ *	@state:		Enumarted value of state to enter.
+ *
+ *	Determine whether or not value is within range, get state 
+ *	structure, and enter (above).
+ */
+
+int pm_suspend(suspend_state_t state)
+{
+	if (state > PM_SUSPEND_ON && state <= PM_SUSPEND_MAX)
+		return enter_state(state);
+	return -EINVAL;
+}
+
+EXPORT_SYMBOL(pm_suspend);
+
+decl_subsys(power,NULL,NULL);
+
+
+/**
+ *	state - control system power state.
+ *
+ *	show() returns what states are supported, which is hard-coded to
+ *	'standby' (Power-On Suspend), 'mem' (Suspend-to-RAM), and
+ *	'disk' (Suspend-to-Disk).
+ *
+ *	store() accepts one of those strings, translates it into the 
+ *	proper enumerated value, and initiates a suspend transition.
+ */
+
+static ssize_t state_show(struct subsystem * subsys, char * buf)
+{
+	int i;
+	char * s = buf;
+
+	for (i = 0; i < PM_SUSPEND_MAX; i++) {
+		if (pm_states[i] && valid_state(i))
+			s += sprintf(s,"%s ", pm_states[i]);
+	}
+	s += sprintf(s,"\n");
+	return (s - buf);
+}
+
+static ssize_t state_store(struct subsystem * subsys, const char * buf, size_t n)
+{
+	suspend_state_t state = PM_SUSPEND_STANDBY;
+	const char * const *s;
+	char *p;
+	int error;
+	int len;
+
+	p = memchr(buf, '\n', n);
+	len = p ? p - buf : n;
+
+	for (s = &pm_states[state]; state < PM_SUSPEND_MAX; s++, state++) {
+		if (*s && !strncmp(buf, *s, len))
+			break;
+	}
+
+#ifdef CONFIG_PM_CPU_MODE
+    printk(KERN_ERR "state_store, %d\n", state);
+	if (state < PM_SUSPEND_MAX && (state == PM_SUSPEND_CPU_MODE || 
+        state == PM_SUSPEND_MEM) ){
+        if(pm_cpu_mode){
+//            state = 0;
+            error = enter_pm_cpu_mode(state);
+        }
+        else{
+            error = enter_state(state);
+        }
+    }
+    else{
+        error = -EINVAL;
+    }
+    printk(KERN_ERR "end, leave state_store, %d\n", state);	
+#else
+	if (state < PM_SUSPEND_MAX && *s)
+		error = enter_state(state);
+	else
+		error = -EINVAL;
+#endif
+	return error ? error : n;
+}
+
+power_attr(state);
+
+#ifdef CONFIG_PM_TRACE
+int pm_trace_enabled;
+
+static ssize_t pm_trace_show(struct subsystem * subsys, char * buf)
+{
+	return sprintf(buf, "%d\n", pm_trace_enabled);
+}
+
+static ssize_t
+pm_trace_store(struct subsystem * subsys, const char * buf, size_t n)
+{
+	int val;
+
+	if (sscanf(buf, "%d", &val) == 1) {
+		pm_trace_enabled = !!val;
+		return n;
+	}
+	return -EINVAL;
+}
+
+power_attr(pm_trace);
+
+static struct attribute * g[] = {
+	&state_attr.attr,
+	&pm_trace_attr.attr,
+	NULL,
+};
+#else
+static struct attribute * g[] = {
+	&state_attr.attr,
+	NULL,
+};
+#endif /* CONFIG_PM_TRACE */
+
+static struct attribute_group attr_group = {
+	.attrs = g,
+};
+
+
+static int __init pm_init(void)
+{
+	int error = subsystem_register(&power_subsys);
+	if (!error)
+		error = sysfs_create_group(&power_subsys.kset.kobj,&attr_group);
+	return error;
+}
+
+core_initcall(pm_init);

kernel/power/pm.c

@@ -0,0 +1,209 @@
+/*
+ *  pm.c - Power management interface
+ *
+ *  Copyright (C) 2000 Andrew Henroid
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/pm.h>
+#include <linux/pm_legacy.h>
+#include <linux/interrupt.h>
+#include <linux/mutex.h>
+
+int pm_active;
+
+/*
+ *	Locking notes:
+ *		pm_devs_lock can be a semaphore providing pm ops are not called
+ *	from an interrupt handler (already a bad idea so no change here). Each
+ *	change must be protected so that an unlink of an entry doesn't clash
+ *	with a pm send - which is permitted to sleep in the current architecture
+ *
+ *	Module unloads clashing with pm events now work out safely, the module 
+ *	unload path will block until the event has been sent. It may well block
+ *	until a resume but that will be fine.
+ */
+ 
+static DEFINE_MUTEX(pm_devs_lock);
+static LIST_HEAD(pm_devs);
+
+/**
+ *	pm_register - register a device with power management
+ *	@type: device type 
+ *	@id: device ID
+ *	@callback: callback function
+ *
+ *	Add a device to the list of devices that wish to be notified about
+ *	power management events. A &pm_dev structure is returned on success,
+ *	on failure the return is %NULL.
+ *
+ *      The callback function will be called in process context and
+ *      it may sleep.
+ */
+ 
+struct pm_dev *pm_register(pm_dev_t type,
+			   unsigned long id,
+			   pm_callback callback)
+{
+	struct pm_dev *dev = kzalloc(sizeof(struct pm_dev), GFP_KERNEL);
+	if (dev) {
+		dev->type = type;
+		dev->id = id;
+		dev->callback = callback;
+
+		mutex_lock(&pm_devs_lock);
+		list_add(&dev->entry, &pm_devs);
+		mutex_unlock(&pm_devs_lock);
+	}
+	return dev;
+}
+
+/**
+ *	pm_send - send request to a single device
+ *	@dev: device to send to
+ *	@rqst: power management request
+ *	@data: data for the callback
+ *
+ *	Issue a power management request to a given device. The 
+ *	%PM_SUSPEND and %PM_RESUME events are handled specially. The
+ *	data field must hold the intended next state. No call is made
+ *	if the state matches.
+ *
+ *	BUGS: what stops two power management requests occurring in parallel
+ *	and conflicting.
+ *
+ *	WARNING: Calling pm_send directly is not generally recommended, in
+ *	particular there is no locking against the pm_dev going away. The
+ *	caller must maintain all needed locking or have 'inside knowledge'
+ *	on the safety. Also remember that this function is not locked against
+ *	pm_unregister. This means that you must handle SMP races on callback
+ *	execution and unload yourself.
+ */
+ 
+static int pm_send(struct pm_dev *dev, pm_request_t rqst, void *data)
+{
+	int status = 0;
+	unsigned long prev_state, next_state;
+
+	if (in_interrupt())
+		BUG();
+
+	switch (rqst) {
+	case PM_SUSPEND:
+	case PM_RESUME:
+		prev_state = dev->state;
+		next_state = (unsigned long) data;
+		if (prev_state != next_state) {
+			if (dev->callback)
+				status = (*dev->callback)(dev, rqst, data);
+			if (!status) {
+				dev->state = next_state;
+				dev->prev_state = prev_state;
+			}
+		}
+		else {
+			dev->prev_state = prev_state;
+		}
+		break;
+	default:
+		if (dev->callback)
+			status = (*dev->callback)(dev, rqst, data);
+		break;
+	}
+	return status;
+}
+
+/*
+ * Undo incomplete request
+ */
+static void pm_undo_all(struct pm_dev *last)
+{
+	struct list_head *entry = last->entry.prev;
+	while (entry != &pm_devs) {
+		struct pm_dev *dev = list_entry(entry, struct pm_dev, entry);
+		if (dev->state != dev->prev_state) {
+			/* previous state was zero (running) resume or
+			 * previous state was non-zero (suspended) suspend
+			 */
+			pm_request_t undo = (dev->prev_state
+					     ? PM_SUSPEND:PM_RESUME);
+			pm_send(dev, undo, (void*) dev->prev_state);
+		}
+		entry = entry->prev;
+	}
+}
+
+/**
+ *	pm_send_all - send request to all managed devices
+ *	@rqst: power management request
+ *	@data: data for the callback
+ *
+ *	Issue a power management request to a all devices. The 
+ *	%PM_SUSPEND events are handled specially. Any device is 
+ *	permitted to fail a suspend by returning a non zero (error)
+ *	value from its callback function. If any device vetoes a 
+ *	suspend request then all other devices that have suspended 
+ *	during the processing of this request are restored to their
+ *	previous state.
+ *
+ *	WARNING:  This function takes the pm_devs_lock. The lock is not dropped until
+ *	the callbacks have completed. This prevents races against pm locking
+ *	functions, races against module unload pm_unregister code. It does
+ *	mean however that you must not issue pm_ functions within the callback
+ *	or you will deadlock and users will hate you.
+ *
+ *	Zero is returned on success. If a suspend fails then the status
+ *	from the device that vetoes the suspend is returned.
+ *
+ *	BUGS: what stops two power management requests occurring in parallel
+ *	and conflicting.
+ */
+ 
+int pm_send_all(pm_request_t rqst, void *data)
+{
+	struct list_head *entry;
+	
+	mutex_lock(&pm_devs_lock);
+	entry = pm_devs.next;
+	while (entry != &pm_devs) {
+		struct pm_dev *dev = list_entry(entry, struct pm_dev, entry);
+		if (dev->callback) {
+			int status = pm_send(dev, rqst, data);
+			if (status) {
+				/* return devices to previous state on
+				 * failed suspend request
+				 */
+				if (rqst == PM_SUSPEND)
+					pm_undo_all(dev);
+				mutex_unlock(&pm_devs_lock);
+				return status;
+			}
+		}
+		entry = entry->next;
+	}
+	mutex_unlock(&pm_devs_lock);
+	return 0;
+}
+
+EXPORT_SYMBOL(pm_register);
+EXPORT_SYMBOL(pm_send_all);
+EXPORT_SYMBOL(pm_active);
+
+

kernel/power/power.h

@@ -0,0 +1,179 @@
+#include <linux/suspend.h>
+#include <linux/utsname.h>
+
+struct swsusp_info {
+	struct new_utsname	uts;
+	u32			version_code;
+	unsigned long		num_physpages;
+	int			cpus;
+	unsigned long		image_pages;
+	unsigned long		pages;
+	unsigned long		size;
+} __attribute__((aligned(PAGE_SIZE)));
+
+
+
+#ifdef CONFIG_SOFTWARE_SUSPEND
+extern int pm_suspend_disk(void);
+
+#else
+static inline int pm_suspend_disk(void)
+{
+	return -EPERM;
+}
+#endif
+
+extern struct mutex pm_mutex;
+
+#define power_attr(_name) \
+static struct subsys_attribute _name##_attr = {	\
+	.attr	= {				\
+		.name = __stringify(_name),	\
+		.mode = 0644,			\
+	},					\
+	.show	= _name##_show,			\
+	.store	= _name##_store,		\
+}
+
+extern struct subsystem power_subsys;
+
+/* References to section boundaries */
+extern const void __nosave_begin, __nosave_end;
+
+/* Preferred image size in bytes (default 500 MB) */
+extern unsigned long image_size;
+extern int in_suspend;
+extern dev_t swsusp_resume_device;
+extern sector_t swsusp_resume_block;
+
+extern asmlinkage int swsusp_arch_suspend(void);
+extern asmlinkage int swsusp_arch_resume(void);
+
+extern unsigned int count_data_pages(void);
+
+/**
+ *	Auxiliary structure used for reading the snapshot image data and
+ *	metadata from and writing them to the list of page backup entries
+ *	(PBEs) which is the main data structure of swsusp.
+ *
+ *	Using struct snapshot_handle we can transfer the image, including its
+ *	metadata, as a continuous sequence of bytes with the help of
+ *	snapshot_read_next() and snapshot_write_next().
+ *
+ *	The code that writes the image to a storage or transfers it to
+ *	the user land is required to use snapshot_read_next() for this
+ *	purpose and it should not make any assumptions regarding the internal
+ *	structure of the image.  Similarly, the code that reads the image from
+ *	a storage or transfers it from the user land is required to use
+ *	snapshot_write_next().
+ *
+ *	This may allow us to change the internal structure of the image
+ *	in the future with considerably less effort.
+ */
+
+struct snapshot_handle {
+	loff_t		offset;	/* number of the last byte ready for reading
+				 * or writing in the sequence
+				 */
+	unsigned int	cur;	/* number of the block of PAGE_SIZE bytes the
+				 * next operation will refer to (ie. current)
+				 */
+	unsigned int	cur_offset;	/* offset with respect to the current
+					 * block (for the next operation)
+					 */
+	unsigned int	prev;	/* number of the block of PAGE_SIZE bytes that
+				 * was the current one previously
+				 */
+	void		*buffer;	/* address of the block to read from
+					 * or write to
+					 */
+	unsigned int	buf_offset;	/* location to read from or write to,
+					 * given as a displacement from 'buffer'
+					 */
+	int		sync_read;	/* Set to one to notify the caller of
+					 * snapshot_write_next() that it may
+					 * need to call wait_on_bio_chain()
+					 */
+};
+
+/* This macro returns the address from/to which the caller of
+ * snapshot_read_next()/snapshot_write_next() is allowed to
+ * read/write data after the function returns
+ */
+#define data_of(handle)	((handle).buffer + (handle).buf_offset)
+
+extern unsigned int snapshot_additional_pages(struct zone *zone);
+extern int snapshot_read_next(struct snapshot_handle *handle, size_t count);
+extern int snapshot_write_next(struct snapshot_handle *handle, size_t count);
+extern void snapshot_write_finalize(struct snapshot_handle *handle);
+extern int snapshot_image_loaded(struct snapshot_handle *handle);
+
+/*
+ * This structure is used to pass the values needed for the identification
+ * of the resume swap area from a user space to the kernel via the
+ * SNAPSHOT_SET_SWAP_AREA ioctl
+ */
+struct resume_swap_area {
+	loff_t offset;
+	u_int32_t dev;
+} __attribute__((packed));
+
+#define SNAPSHOT_IOC_MAGIC	'3'
+#define SNAPSHOT_FREEZE			_IO(SNAPSHOT_IOC_MAGIC, 1)
+#define SNAPSHOT_UNFREEZE		_IO(SNAPSHOT_IOC_MAGIC, 2)
+#define SNAPSHOT_ATOMIC_SNAPSHOT	_IOW(SNAPSHOT_IOC_MAGIC, 3, void *)
+#define SNAPSHOT_ATOMIC_RESTORE		_IO(SNAPSHOT_IOC_MAGIC, 4)
+#define SNAPSHOT_FREE			_IO(SNAPSHOT_IOC_MAGIC, 5)
+#define SNAPSHOT_SET_IMAGE_SIZE		_IOW(SNAPSHOT_IOC_MAGIC, 6, unsigned long)
+#define SNAPSHOT_AVAIL_SWAP		_IOR(SNAPSHOT_IOC_MAGIC, 7, void *)
+#define SNAPSHOT_GET_SWAP_PAGE		_IOR(SNAPSHOT_IOC_MAGIC, 8, void *)
+#define SNAPSHOT_FREE_SWAP_PAGES	_IO(SNAPSHOT_IOC_MAGIC, 9)
+#define SNAPSHOT_SET_SWAP_FILE		_IOW(SNAPSHOT_IOC_MAGIC, 10, unsigned int)
+#define SNAPSHOT_S2RAM			_IO(SNAPSHOT_IOC_MAGIC, 11)
+#define SNAPSHOT_PMOPS			_IOW(SNAPSHOT_IOC_MAGIC, 12, unsigned int)
+#define SNAPSHOT_SET_SWAP_AREA		_IOW(SNAPSHOT_IOC_MAGIC, 13, \
+							struct resume_swap_area)
+#define SNAPSHOT_IOC_MAXNR	13
+
+#define PMOPS_PREPARE	1
+#define PMOPS_ENTER	2
+#define PMOPS_FINISH	3
+
+/**
+ *	The bitmap is used for tracing allocated swap pages
+ *
+ *	The entire bitmap consists of a number of bitmap_page
+ *	structures linked with the help of the .next member.
+ *	Thus each page can be allocated individually, so we only
+ *	need to make 0-order memory allocations to create
+ *	the bitmap.
+ */
+
+#define BITMAP_PAGE_SIZE	(PAGE_SIZE - sizeof(void *))
+#define BITMAP_PAGE_CHUNKS	(BITMAP_PAGE_SIZE / sizeof(long))
+#define BITS_PER_CHUNK		(sizeof(long) * 8)
+#define BITMAP_PAGE_BITS	(BITMAP_PAGE_CHUNKS * BITS_PER_CHUNK)
+
+struct bitmap_page {
+	unsigned long		chunks[BITMAP_PAGE_CHUNKS];
+	struct bitmap_page	*next;
+};
+
+extern void free_bitmap(struct bitmap_page *bitmap);
+extern struct bitmap_page *alloc_bitmap(unsigned int nr_bits);
+extern sector_t alloc_swapdev_block(int swap, struct bitmap_page *bitmap);
+extern void free_all_swap_pages(int swap, struct bitmap_page *bitmap);
+
+extern int swsusp_check(void);
+extern int swsusp_shrink_memory(void);
+extern void swsusp_free(void);
+extern int swsusp_suspend(void);
+extern int swsusp_resume(void);
+extern int swsusp_read(void);
+extern int swsusp_write(void);
+extern void swsusp_close(void);
+extern int suspend_enter(suspend_state_t state);
+
+struct timeval;
+extern void swsusp_show_speed(struct timeval *, struct timeval *,
+				unsigned int, char *);

kernel/power/poweroff.c

@@ -0,0 +1,44 @@
+/*
+ * poweroff.c - sysrq handler to gracefully power down machine.
+ *
+ * This file is released under the GPL v2
+ */
+
+#include <linux/kernel.h>
+#include <linux/sysrq.h>
+#include <linux/init.h>
+#include <linux/pm.h>
+#include <linux/workqueue.h>
+#include <linux/reboot.h>
+
+/*
+ * When the user hits Sys-Rq o to power down the machine this is the
+ * callback we use.
+ */
+
+static void do_poweroff(struct work_struct *dummy)
+{
+	kernel_power_off();
+}
+
+static DECLARE_WORK(poweroff_work, do_poweroff);
+
+static void handle_poweroff(int key, struct tty_struct *tty)
+{
+	schedule_work(&poweroff_work);
+}
+
+static struct sysrq_key_op	sysrq_poweroff_op = {
+	.handler        = handle_poweroff,
+	.help_msg       = "powerOff",
+	.action_msg     = "Power Off",
+ 	.enable_mask	= SYSRQ_ENABLE_BOOT,
+};
+
+static int pm_sysrq_init(void)
+{
+	register_sysrq_key('o', &sysrq_poweroff_op);
+	return 0;
+}
+
+subsys_initcall(pm_sysrq_init);

kernel/power/process.c

@@ -0,0 +1,219 @@
+/*
+ * drivers/power/process.c - Functions for starting/stopping processes on 
+ *                           suspend transitions.
+ *
+ * Originally from swsusp.
+ */
+
+
+#undef DEBUG
+
+#include <linux/smp_lock.h>
+#include <linux/interrupt.h>
+#include <linux/suspend.h>
+#include <linux/module.h>
+#include <linux/syscalls.h>
+#include <linux/freezer.h>
+
+/* 
+ * Timeout for stopping processes
+ */
+#define TIMEOUT	(20 * HZ)
+
+#define FREEZER_KERNEL_THREADS 0
+#define FREEZER_USER_SPACE 1
+
+static inline int freezeable(struct task_struct * p)
+{
+	if ((p == current) || 
+	    (p->flags & PF_NOFREEZE) ||
+	    (p->exit_state == EXIT_ZOMBIE) ||
+	    (p->exit_state == EXIT_DEAD))
+		return 0;
+	return 1;
+}
+
+/* Refrigerator is place where frozen processes are stored :-). */
+void refrigerator(void)
+{
+	/* Hmm, should we be allowed to suspend when there are realtime
+	   processes around? */
+	long save;
+	save = current->state;
+	pr_debug("%s entered refrigerator\n", current->comm);
+
+	frozen_process(current);
+	spin_lock_irq(&current->sighand->siglock);
+	recalc_sigpending(); /* We sent fake signal, clean it up */
+	spin_unlock_irq(&current->sighand->siglock);
+
+	while (frozen(current)) {
+		current->state = TASK_UNINTERRUPTIBLE;
+		schedule();
+	}
+	pr_debug("%s left refrigerator\n", current->comm);
+	current->state = save;
+}
+
+static inline void freeze_process(struct task_struct *p)
+{
+	unsigned long flags;
+
+	if (!freezing(p)) {
+		rmb();
+		if (!frozen(p)) {
+			if (p->state == TASK_STOPPED)
+				force_sig_specific(SIGSTOP, p);
+
+			freeze(p);
+			spin_lock_irqsave(&p->sighand->siglock, flags);
+			signal_wake_up(p, p->state == TASK_STOPPED);
+			spin_unlock_irqrestore(&p->sighand->siglock, flags);
+		}
+	}
+}
+
+static void cancel_freezing(struct task_struct *p)
+{
+	unsigned long flags;
+
+	if (freezing(p)) {
+		pr_debug("  clean up: %s\n", p->comm);
+		do_not_freeze(p);
+		spin_lock_irqsave(&p->sighand->siglock, flags);
+		recalc_sigpending_tsk(p);
+		spin_unlock_irqrestore(&p->sighand->siglock, flags);
+	}
+}
+
+static inline int is_user_space(struct task_struct *p)
+{
+	return p->mm && !(p->flags & PF_BORROWED_MM);
+}
+
+static unsigned int try_to_freeze_tasks(int freeze_user_space)
+{
+	struct task_struct *g, *p;
+	unsigned long end_time;
+	unsigned int todo;
+
+	end_time = jiffies + TIMEOUT;
+	do {
+		todo = 0;
+		read_lock(&tasklist_lock);
+		do_each_thread(g, p) {
+			if (!freezeable(p))
+				continue;
+
+			if (frozen(p))
+				continue;
+
+			if (p->state == TASK_TRACED && frozen(p->parent)) {
+				cancel_freezing(p);
+				continue;
+			}
+			if (is_user_space(p)) {
+				if (!freeze_user_space)
+					continue;
+
+				/* Freeze the task unless there is a vfork
+				 * completion pending
+				 */
+				if (!p->vfork_done)
+					freeze_process(p);
+			} else {
+				if (freeze_user_space)
+					continue;
+
+				freeze_process(p);
+			}
+			todo++;
+		} while_each_thread(g, p);
+		read_unlock(&tasklist_lock);
+		yield();			/* Yield is okay here */
+		if (todo && time_after(jiffies, end_time))
+			break;
+	} while (todo);
+
+	if (todo) {
+		/* This does not unfreeze processes that are already frozen
+		 * (we have slightly ugly calling convention in that respect,
+		 * and caller must call thaw_processes() if something fails),
+		 * but it cleans up leftover PF_FREEZE requests.
+		 */
+		printk("\n");
+		printk(KERN_ERR "Stopping %s timed out after %d seconds "
+				"(%d tasks refusing to freeze):\n",
+				freeze_user_space ? "user space processes" :
+					"kernel threads",
+				TIMEOUT / HZ, todo);
+		read_lock(&tasklist_lock);
+		do_each_thread(g, p) {
+			if (is_user_space(p) == !freeze_user_space)
+				continue;
+
+			if (freezeable(p) && !frozen(p))
+				printk(KERN_ERR " %s\n", p->comm);
+
+			cancel_freezing(p);
+		} while_each_thread(g, p);
+		read_unlock(&tasklist_lock);
+	}
+
+	return todo;
+}
+
+/**
+ *	freeze_processes - tell processes to enter the refrigerator
+ *
+ *	Returns 0 on success, or the number of processes that didn't freeze,
+ *	although they were told to.
+ */
+int freeze_processes(void)
+{
+	unsigned int nr_unfrozen;
+
+	printk("Stopping tasks ... ");
+	nr_unfrozen = try_to_freeze_tasks(FREEZER_USER_SPACE);
+	if (nr_unfrozen)
+		return nr_unfrozen;
+
+	sys_sync();
+	nr_unfrozen = try_to_freeze_tasks(FREEZER_KERNEL_THREADS);
+	if (nr_unfrozen)
+		return nr_unfrozen;
+
+	printk("done.\n");
+	BUG_ON(in_atomic());
+	return 0;
+}
+
+static void thaw_tasks(int thaw_user_space)
+{
+	struct task_struct *g, *p;
+
+	read_lock(&tasklist_lock);
+	do_each_thread(g, p) {
+		if (!freezeable(p))
+			continue;
+
+		if (is_user_space(p) == !thaw_user_space)
+			continue;
+
+		if (!thaw_process(p))
+			printk(KERN_WARNING " Strange, %s not stopped\n",
+				p->comm );
+	} while_each_thread(g, p);
+	read_unlock(&tasklist_lock);
+}
+
+void thaw_processes(void)
+{
+	printk("Restarting tasks ... ");
+	thaw_tasks(FREEZER_KERNEL_THREADS);
+	thaw_tasks(FREEZER_USER_SPACE);
+	schedule();
+	printk("done.\n");
+}
+
+EXPORT_SYMBOL(refrigerator);

kernel/power/swap.c

@@ -0,0 +1,634 @@
+/*
+ * linux/kernel/power/swap.c
+ *
+ * This file provides functions for reading the suspend image from
+ * and writing it to a swap partition.
+ *
+ * Copyright (C) 1998,2001-2005 Pavel Machek <pavel@suse.cz>
+ * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
+ *
+ * This file is released under the GPLv2.
+ *
+ */
+
+#include <linux/module.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/genhd.h>
+#include <linux/device.h>
+#include <linux/buffer_head.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/pm.h>
+
+#include "power.h"
+
+extern char resume_file[];
+
+#define SWSUSP_SIG	"S1SUSPEND"
+
+static struct swsusp_header {
+	char reserved[PAGE_SIZE - 20 - sizeof(sector_t)];
+	sector_t image;
+	char	orig_sig[10];
+	char	sig[10];
+} __attribute__((packed, aligned(PAGE_SIZE))) swsusp_header;
+
+/*
+ * General things
+ */
+
+static unsigned short root_swap = 0xffff;
+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.
+ *	@bio_chain: list of pending biod (for async reading)
+ *
+ *	Straight from the textbook - allocate and initialize the bio.
+ *	If we're reading, make sure the page is marked as dirty.
+ *	Then submit it and, if @bio_chain == NULL, wait.
+ */
+static int submit(int rw, pgoff_t page_off, struct page *page,
+			struct bio **bio_chain)
+{
+	struct bio *bio;
+
+	bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1);
+	if (!bio)
+		return -ENOMEM;
+	bio->bi_sector = page_off * (PAGE_SIZE >> 9);
+	bio->bi_bdev = resume_bdev;
+	bio->bi_end_io = end_swap_bio_read;
+
+	if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
+		printk("swsusp: ERROR: adding page to bio at %ld\n", page_off);
+		bio_put(bio);
+		return -EFAULT;
+	}
+
+	lock_page(page);
+	bio_get(bio);
+
+	if (bio_chain == NULL) {
+		submit_bio(rw | (1 << BIO_RW_SYNC), bio);
+		wait_on_page_locked(page);
+		if (rw == READ)
+			bio_set_pages_dirty(bio);
+		bio_put(bio);
+	} else {
+		if (rw == READ)
+			get_page(page);	/* These pages are freed later */
+		bio->bi_private = *bio_chain;
+		*bio_chain = bio;
+		submit_bio(rw | (1 << BIO_RW_SYNC), bio);
+	}
+	return 0;
+}
+
+static int bio_read_page(pgoff_t page_off, void *addr, struct bio **bio_chain)
+{
+	return submit(READ, page_off, virt_to_page(addr), bio_chain);
+}
+
+static int bio_write_page(pgoff_t page_off, void *addr, struct bio **bio_chain)
+{
+	return submit(WRITE, page_off, virt_to_page(addr), bio_chain);
+}
+
+static int wait_on_bio_chain(struct bio **bio_chain)
+{
+	struct bio *bio;
+	struct bio *next_bio;
+	int ret = 0;
+
+	if (bio_chain == NULL)
+		return 0;
+
+	bio = *bio_chain;
+	if (bio == NULL)
+		return 0;
+	while (bio) {
+		struct page *page;
+
+		next_bio = bio->bi_private;
+		page = bio->bi_io_vec[0].bv_page;
+		wait_on_page_locked(page);
+		if (!PageUptodate(page) || PageError(page))
+			ret = -EIO;
+		put_page(page);
+		bio_put(bio);
+		bio = next_bio;
+	}
+	*bio_chain = NULL;
+	return ret;
+}
+
+/*
+ * Saving part
+ */
+
+static int mark_swapfiles(sector_t start)
+{
+	int error;
+
+	bio_read_page(swsusp_resume_block, &swsusp_header, NULL);
+	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.image = start;
+		error = bio_write_page(swsusp_resume_block,
+					&swsusp_header, NULL);
+	} else {
+		printk(KERN_ERR "swsusp: Swap header not found!\n");
+		error = -ENODEV;
+	}
+	return error;
+}
+
+/**
+ *	swsusp_swap_check - check if the resume device is a swap device
+ *	and get its index (if so)
+ */
+
+static int swsusp_swap_check(void) /* This is called before saving image */
+{
+	int res;
+
+	res = swap_type_of(swsusp_resume_device, swsusp_resume_block,
+			&resume_bdev);
+	if (res < 0)
+		return res;
+
+	root_swap = res;
+	res = blkdev_get(resume_bdev, FMODE_WRITE, O_RDWR);
+	if (res)
+		return res;
+
+	res = set_blocksize(resume_bdev, PAGE_SIZE);
+	if (res < 0)
+		blkdev_put(resume_bdev);
+
+	return res;
+}
+
+/**
+ *	write_page - Write one page to given swap location.
+ *	@buf:		Address we're writing.
+ *	@offset:	Offset of the swap page we're writing to.
+ *	@bio_chain:	Link the next write BIO here
+ */
+
+static int write_page(void *buf, sector_t offset, struct bio **bio_chain)
+{
+	void *src;
+
+	if (!offset)
+		return -ENOSPC;
+
+	if (bio_chain) {
+		src = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
+		if (src) {
+			memcpy(src, buf, PAGE_SIZE);
+		} else {
+			WARN_ON_ONCE(1);
+			bio_chain = NULL;	/* Go synchronous */
+			src = buf;
+		}
+	} else {
+		src = buf;
+	}
+	return bio_write_page(offset, src, bio_chain);
+}
+
+/*
+ *	The swap map is a data structure used for keeping track of each page
+ *	written to a swap partition.  It consists of many swap_map_page
+ *	structures that contain each an array of MAP_PAGE_SIZE swap entries.
+ *	These structures are stored on the swap and linked together with the
+ *	help of the .next_swap member.
+ *
+ *	The swap map is created during suspend.  The swap map pages are
+ *	allocated and populated one at a time, so we only need one memory
+ *	page to set up the entire structure.
+ *
+ *	During resume we also only need to use one swap_map_page structure
+ *	at a time.
+ */
+
+#define MAP_PAGE_ENTRIES	(PAGE_SIZE / sizeof(sector_t) - 1)
+
+struct swap_map_page {
+	sector_t entries[MAP_PAGE_ENTRIES];
+	sector_t next_swap;
+};
+
+/**
+ *	The swap_map_handle structure is used for handling swap in
+ *	a file-alike way
+ */
+
+struct swap_map_handle {
+	struct swap_map_page *cur;
+	sector_t cur_swap;
+	struct bitmap_page *bitmap;
+	unsigned int k;
+};
+
+static void release_swap_writer(struct swap_map_handle *handle)
+{
+	if (handle->cur)
+		free_page((unsigned long)handle->cur);
+	handle->cur = NULL;
+	if (handle->bitmap)
+		free_bitmap(handle->bitmap);
+	handle->bitmap = NULL;
+}
+
+static int get_swap_writer(struct swap_map_handle *handle)
+{
+	handle->cur = (struct swap_map_page *)get_zeroed_page(GFP_KERNEL);
+	if (!handle->cur)
+		return -ENOMEM;
+	handle->bitmap = alloc_bitmap(count_swap_pages(root_swap, 0));
+	if (!handle->bitmap) {
+		release_swap_writer(handle);
+		return -ENOMEM;
+	}
+	handle->cur_swap = alloc_swapdev_block(root_swap, handle->bitmap);
+	if (!handle->cur_swap) {
+		release_swap_writer(handle);
+		return -ENOSPC;
+	}
+	handle->k = 0;
+	return 0;
+}
+
+static int swap_write_page(struct swap_map_handle *handle, void *buf,
+				struct bio **bio_chain)
+{
+	int error = 0;
+	sector_t offset;
+
+	if (!handle->cur)
+		return -EINVAL;
+	offset = alloc_swapdev_block(root_swap, handle->bitmap);
+	error = write_page(buf, offset, bio_chain);
+	if (error)
+		return error;
+	handle->cur->entries[handle->k++] = offset;
+	if (handle->k >= MAP_PAGE_ENTRIES) {
+		error = wait_on_bio_chain(bio_chain);
+		if (error)
+			goto out;
+		offset = alloc_swapdev_block(root_swap, handle->bitmap);
+		if (!offset)
+			return -ENOSPC;
+		handle->cur->next_swap = offset;
+		error = write_page(handle->cur, handle->cur_swap, NULL);
+		if (error)
+			goto out;
+		memset(handle->cur, 0, PAGE_SIZE);
+		handle->cur_swap = offset;
+		handle->k = 0;
+	}
+ out:
+	return error;
+}
+
+static int flush_swap_writer(struct swap_map_handle *handle)
+{
+	if (handle->cur && handle->cur_swap)
+		return write_page(handle->cur, handle->cur_swap, NULL);
+	else
+		return -EINVAL;
+}
+
+/**
+ *	save_image - save the suspend image data
+ */
+
+static int save_image(struct swap_map_handle *handle,
+                      struct snapshot_handle *snapshot,
+                      unsigned int nr_to_write)
+{
+	unsigned int m;
+	int ret;
+	int error = 0;
+	int nr_pages;
+	int err2;
+	struct bio *bio;
+	struct timeval start;
+	struct timeval stop;
+
+	printk("Saving image data pages (%u pages) ...     ", nr_to_write);
+	m = nr_to_write / 100;
+	if (!m)
+		m = 1;
+	nr_pages = 0;
+	bio = NULL;
+	do_gettimeofday(&start);
+	do {
+		ret = snapshot_read_next(snapshot, PAGE_SIZE);
+		if (ret > 0) {
+			error = swap_write_page(handle, data_of(*snapshot),
+						&bio);
+			if (error)
+				break;
+			if (!(nr_pages % m))
+				printk("\b\b\b\b%3d%%", nr_pages / m);
+			nr_pages++;
+		}
+	} while (ret > 0);
+	err2 = wait_on_bio_chain(&bio);
+	do_gettimeofday(&stop);
+	if (!error)
+		error = err2;
+	if (!error)
+		printk("\b\b\b\bdone\n");
+	swsusp_show_speed(&start, &stop, nr_to_write, "Wrote");
+	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 from the resume partition.
+ */
+
+static int enough_swap(unsigned int nr_pages)
+{
+	unsigned int free_swap = count_swap_pages(root_swap, 1);
+
+	pr_debug("swsusp: free swap pages: %u\n", free_swap);
+	return free_swap > nr_pages + PAGES_FOR_IO;
+}
+
+/**
+ *	swsusp_write - Write entire image and metadata.
+ *
+ *	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)
+{
+	struct swap_map_handle handle;
+	struct snapshot_handle snapshot;
+	struct swsusp_info *header;
+	int error;
+
+	error = swsusp_swap_check();
+	if (error) {
+		printk(KERN_ERR "swsusp: Cannot find swap device, try "
+				"swapon -a.\n");
+		return error;
+	}
+	memset(&snapshot, 0, sizeof(struct snapshot_handle));
+	error = snapshot_read_next(&snapshot, PAGE_SIZE);
+	if (error < PAGE_SIZE) {
+		if (error >= 0)
+			error = -EFAULT;
+
+		goto out;
+	}
+	header = (struct swsusp_info *)data_of(snapshot);
+	if (!enough_swap(header->pages)) {
+		printk(KERN_ERR "swsusp: Not enough free swap\n");
+		error = -ENOSPC;
+		goto out;
+	}
+	error = get_swap_writer(&handle);
+	if (!error) {
+		sector_t start = handle.cur_swap;
+
+		error = swap_write_page(&handle, header, NULL);
+		if (!error)
+			error = save_image(&handle, &snapshot,
+					header->pages - 1);
+
+		if (!error) {
+			flush_swap_writer(&handle);
+			printk("S");
+			error = mark_swapfiles(start);
+			printk("|\n");
+		}
+	}
+	if (error)
+		free_all_swap_pages(root_swap, handle.bitmap);
+	release_swap_writer(&handle);
+ out:
+	swsusp_close();
+	return error;
+}
+
+/**
+ *	The following functions allow us to read data using a swap map
+ *	in a file-alike way
+ */
+
+static void release_swap_reader(struct swap_map_handle *handle)
+{
+	if (handle->cur)
+		free_page((unsigned long)handle->cur);
+	handle->cur = NULL;
+}
+
+static int get_swap_reader(struct swap_map_handle *handle, sector_t start)
+{
+	int error;
+
+	if (!start)
+		return -EINVAL;
+
+	handle->cur = (struct swap_map_page *)get_zeroed_page(__GFP_WAIT | __GFP_HIGH);
+	if (!handle->cur)
+		return -ENOMEM;
+
+	error = bio_read_page(start, handle->cur, NULL);
+	if (error) {
+		release_swap_reader(handle);
+		return error;
+	}
+	handle->k = 0;
+	return 0;
+}
+
+static int swap_read_page(struct swap_map_handle *handle, void *buf,
+				struct bio **bio_chain)
+{
+	sector_t offset;
+	int error;
+
+	if (!handle->cur)
+		return -EINVAL;
+	offset = handle->cur->entries[handle->k];
+	if (!offset)
+		return -EFAULT;
+	error = bio_read_page(offset, buf, bio_chain);
+	if (error)
+		return error;
+	if (++handle->k >= MAP_PAGE_ENTRIES) {
+		error = wait_on_bio_chain(bio_chain);
+		handle->k = 0;
+		offset = handle->cur->next_swap;
+		if (!offset)
+			release_swap_reader(handle);
+		else if (!error)
+			error = bio_read_page(offset, handle->cur, NULL);
+	}
+	return error;
+}
+
+/**
+ *	load_image - load the image using the swap map handle
+ *	@handle and the snapshot handle @snapshot
+ *	(assume there are @nr_pages pages to load)
+ */
+
+static int load_image(struct swap_map_handle *handle,
+                      struct snapshot_handle *snapshot,
+                      unsigned int nr_to_read)
+{
+	unsigned int m;
+	int error = 0;
+	struct timeval start;
+	struct timeval stop;
+	struct bio *bio;
+	int err2;
+	unsigned nr_pages;
+
+	printk("Loading image data pages (%u pages) ...     ", nr_to_read);
+	m = nr_to_read / 100;
+	if (!m)
+		m = 1;
+	nr_pages = 0;
+	bio = NULL;
+	do_gettimeofday(&start);
+	for ( ; ; ) {
+		error = snapshot_write_next(snapshot, PAGE_SIZE);
+		if (error <= 0)
+			break;
+		error = swap_read_page(handle, data_of(*snapshot), &bio);
+		if (error)
+			break;
+		if (snapshot->sync_read)
+			error = wait_on_bio_chain(&bio);
+		if (error)
+			break;
+		if (!(nr_pages % m))
+			printk("\b\b\b\b%3d%%", nr_pages / m);
+		nr_pages++;
+	}
+	err2 = wait_on_bio_chain(&bio);
+	do_gettimeofday(&stop);
+	if (!error)
+		error = err2;
+	if (!error) {
+		printk("\b\b\b\bdone\n");
+		snapshot_write_finalize(snapshot);
+		if (!snapshot_image_loaded(snapshot))
+			error = -ENODATA;
+	}
+	swsusp_show_speed(&start, &stop, nr_to_read, "Read");
+	return error;
+}
+
+int swsusp_read(void)
+{
+	int error;
+	struct swap_map_handle handle;
+	struct snapshot_handle snapshot;
+	struct swsusp_info *header;
+
+	if (IS_ERR(resume_bdev)) {
+		pr_debug("swsusp: block device not initialised\n");
+		return PTR_ERR(resume_bdev);
+	}
+
+	memset(&snapshot, 0, sizeof(struct snapshot_handle));
+	error = snapshot_write_next(&snapshot, PAGE_SIZE);
+	if (error < PAGE_SIZE)
+		return error < 0 ? error : -EFAULT;
+	header = (struct swsusp_info *)data_of(snapshot);
+	error = get_swap_reader(&handle, swsusp_header.image);
+	if (!error)
+		error = swap_read_page(&handle, header, NULL);
+	if (!error)
+		error = load_image(&handle, &snapshot, header->pages - 1);
+	release_swap_reader(&handle);
+
+	blkdev_put(resume_bdev);
+
+	if (!error)
+		pr_debug("swsusp: Reading resume file was successful\n");
+	else
+		pr_debug("swsusp: Error %d resuming\n", error);
+	return error;
+}
+
+/**
+ *      swsusp_check - Check for swsusp signature in the resume device
+ */
+
+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);
+		memset(&swsusp_header, 0, sizeof(swsusp_header));
+		error = bio_read_page(swsusp_resume_block,
+					&swsusp_header, NULL);
+		if (error)
+			return error;
+
+		if (!memcmp(SWSUSP_SIG, swsusp_header.sig, 10)) {
+			memcpy(swsusp_header.sig, swsusp_header.orig_sig, 10);
+			/* Reset swap signature now */
+			error = bio_write_page(swsusp_resume_block,
+						&swsusp_header, NULL);
+		} else {
+			return -EINVAL;
+		}
+		if (error)
+			blkdev_put(resume_bdev);
+		else
+			pr_debug("swsusp: Signature found, resuming\n");
+	} else {
+		error = PTR_ERR(resume_bdev);
+	}
+
+	if (error)
+		pr_debug("swsusp: Error %d check for resume file\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);
+}

kernel/power/swsusp.c

@@ -0,0 +1,330 @@
+/*
+ * 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
+ *
+ * Rafael J. Wysocki <rjw@sisk.pl>
+ * Reworked the freeing of memory and the handling of swap
+ *
+ * More state savers are welcome. Especially for the scsi layer...
+ *
+ * For TODOs,FIXMEs also look in Documentation/power/swsusp.txt
+ */
+
+#include <linux/mm.h>
+#include <linux/suspend.h>
+#include <linux/spinlock.h>
+#include <linux/kernel.h>
+#include <linux/major.h>
+#include <linux/swap.h>
+#include <linux/pm.h>
+#include <linux/swapops.h>
+#include <linux/bootmem.h>
+#include <linux/syscalls.h>
+#include <linux/highmem.h>
+#include <linux/time.h>
+
+#include "power.h"
+
+/*
+ * Preferred image size in bytes (tunable via /sys/power/image_size).
+ * When it is set to N, swsusp will do its best to ensure the image
+ * size will not exceed N bytes, but if that is impossible, it will
+ * try to create the smallest image possible.
+ */
+unsigned long image_size = 500 * 1024 * 1024;
+
+int in_suspend __nosavedata = 0;
+
+#ifdef CONFIG_HIGHMEM
+unsigned int count_highmem_pages(void);
+int restore_highmem(void);
+#else
+static inline int restore_highmem(void) { return 0; }
+static inline unsigned int count_highmem_pages(void) { return 0; }
+#endif
+
+/**
+ *	The following functions are used for tracing the allocated
+ *	swap pages, so that they can be freed in case of an error.
+ *
+ *	The functions operate on a linked bitmap structure defined
+ *	in power.h
+ */
+
+void free_bitmap(struct bitmap_page *bitmap)
+{
+	struct bitmap_page *bp;
+
+	while (bitmap) {
+		bp = bitmap->next;
+		free_page((unsigned long)bitmap);
+		bitmap = bp;
+	}
+}
+
+struct bitmap_page *alloc_bitmap(unsigned int nr_bits)
+{
+	struct bitmap_page *bitmap, *bp;
+	unsigned int n;
+
+	if (!nr_bits)
+		return NULL;
+
+	bitmap = (struct bitmap_page *)get_zeroed_page(GFP_KERNEL);
+	bp = bitmap;
+	for (n = BITMAP_PAGE_BITS; n < nr_bits; n += BITMAP_PAGE_BITS) {
+		bp->next = (struct bitmap_page *)get_zeroed_page(GFP_KERNEL);
+		bp = bp->next;
+		if (!bp) {
+			free_bitmap(bitmap);
+			return NULL;
+		}
+	}
+	return bitmap;
+}
+
+static int bitmap_set(struct bitmap_page *bitmap, unsigned long bit)
+{
+	unsigned int n;
+
+	n = BITMAP_PAGE_BITS;
+	while (bitmap && n <= bit) {
+		n += BITMAP_PAGE_BITS;
+		bitmap = bitmap->next;
+	}
+	if (!bitmap)
+		return -EINVAL;
+	n -= BITMAP_PAGE_BITS;
+	bit -= n;
+	n = 0;
+	while (bit >= BITS_PER_CHUNK) {
+		bit -= BITS_PER_CHUNK;
+		n++;
+	}
+	bitmap->chunks[n] |= (1UL << bit);
+	return 0;
+}
+
+sector_t alloc_swapdev_block(int swap, struct bitmap_page *bitmap)
+{
+	unsigned long offset;
+
+	offset = swp_offset(get_swap_page_of_type(swap));
+	if (offset) {
+		if (bitmap_set(bitmap, offset))
+			swap_free(swp_entry(swap, offset));
+		else
+			return swapdev_block(swap, offset);
+	}
+	return 0;
+}
+
+void free_all_swap_pages(int swap, struct bitmap_page *bitmap)
+{
+	unsigned int bit, n;
+	unsigned long test;
+
+	bit = 0;
+	while (bitmap) {
+		for (n = 0; n < BITMAP_PAGE_CHUNKS; n++)
+			for (test = 1UL; test; test <<= 1) {
+				if (bitmap->chunks[n] & test)
+					swap_free(swp_entry(swap, bit));
+				bit++;
+			}
+		bitmap = bitmap->next;
+	}
+}
+
+/**
+ *	swsusp_show_speed - print the time elapsed between two events represented by
+ *	@start and @stop
+ *
+ *	@nr_pages -	number of pages processed between @start and @stop
+ *	@msg -		introductory message to print
+ */
+
+void swsusp_show_speed(struct timeval *start, struct timeval *stop,
+			unsigned nr_pages, char *msg)
+{
+	s64 elapsed_centisecs64;
+	int centisecs;
+	int k;
+	int kps;
+
+	elapsed_centisecs64 = timeval_to_ns(stop) - timeval_to_ns(start);
+	do_div(elapsed_centisecs64, NSEC_PER_SEC / 100);
+	centisecs = elapsed_centisecs64;
+	if (centisecs == 0)
+		centisecs = 1;	/* avoid div-by-zero */
+	k = nr_pages * (PAGE_SIZE / 1024);
+	kps = (k * 100) / centisecs;
+	printk("%s %d kbytes in %d.%02d seconds (%d.%02d MB/s)\n", msg, k,
+			centisecs / 100, centisecs % 100,
+			kps / 1000, (kps % 1000) / 10);
+}
+
+/**
+ *	swsusp_shrink_memory -  Try to free as much memory as needed
+ *
+ *	... but do not OOM-kill anyone
+ *
+ *	Notice: all userland should be stopped before it is called, or
+ *	livelock is possible.
+ */
+
+#define SHRINK_BITE	10000
+static inline unsigned long __shrink_memory(long tmp)
+{
+	if (tmp > SHRINK_BITE)
+		tmp = SHRINK_BITE;
+	return shrink_all_memory(tmp);
+}
+
+int swsusp_shrink_memory(void)
+{
+	long tmp;
+	struct zone *zone;
+	unsigned long pages = 0;
+	unsigned int i = 0;
+	char *p = "-\\|/";
+	struct timeval start, stop;
+
+	printk("Shrinking memory...  ");
+	do_gettimeofday(&start);
+	do {
+		long size, highmem_size;
+
+		highmem_size = count_highmem_pages();
+		size = count_data_pages() + PAGES_FOR_IO;
+		tmp = size;
+		size += highmem_size;
+		for_each_zone (zone)
+			if (populated_zone(zone)) {
+				tmp += snapshot_additional_pages(zone);
+				if (is_highmem(zone)) {
+					highmem_size -=
+					zone_page_state(zone, NR_FREE_PAGES);
+				} else {
+					tmp -= zone_page_state(zone, NR_FREE_PAGES);
+					tmp += zone->lowmem_reserve[ZONE_NORMAL];
+				}
+			}
+
+		if (highmem_size < 0)
+			highmem_size = 0;
+
+		tmp += highmem_size;
+		if (tmp > 0) {
+			tmp = __shrink_memory(tmp);
+			if (!tmp)
+				return -ENOMEM;
+			pages += tmp;
+		} else if (size > image_size / PAGE_SIZE) {
+			tmp = __shrink_memory(size - (image_size / PAGE_SIZE));
+			pages += tmp;
+		}
+		printk("\b%c", p[i++%4]);
+	} while (tmp > 0);
+	do_gettimeofday(&stop);
+	printk("\bdone (%lu pages freed)\n", pages);
+	swsusp_show_speed(&start, &stop, pages, "Freed");
+
+	return 0;
+}
+
+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;
+	}
+
+	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();
+	/* NOTE:  device_power_up() is just a resume() for devices
+	 * that suspended with irqs off ... no overall powerup.
+	 */
+	device_power_up();
+ Enable_irqs:
+	local_irq_enable();
+	return error;
+}
+
+int swsusp_resume(void)
+{
+	int error;
+
+	local_irq_disable();
+	/* NOTE:  device_power_down() is just a suspend() with irqs off;
+	 * it has no special "power things down" semantics
+	 */
+	if (device_power_down(PMSG_PRETHAW))
+		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 = restore_highmem();
+	if (!error) {
+		error = swsusp_arch_resume();
+		/* The code below is only ever reached in case of a failure.
+		 * Otherwise execution continues at place where
+		 * swsusp_arch_suspend() was called
+        	 */
+		BUG_ON(!error);
+		/* This call to restore_highmem() undos the previous one */
+		restore_highmem();
+	}
+	/* 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();
+	touch_softlockup_watchdog();
+	device_power_up();
+	local_irq_enable();
+	return error;
+}

kernel/power/user.c

@@ -0,0 +1,481 @@
+/*
+ * linux/kernel/power/user.c
+ *
+ * This file provides the user space interface for software suspend/resume.
+ *
+ * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
+ *
+ * This file is released under the GPLv2.
+ *
+ */
+
+#include <linux/suspend.h>
+#include <linux/syscalls.h>
+#include <linux/reboot.h>
+#include <linux/string.h>
+#include <linux/device.h>
+#include <linux/miscdevice.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/pm.h>
+#include <linux/fs.h>
+#include <linux/console.h>
+#include <linux/cpu.h>
+#include <linux/freezer.h>
+
+#include <asm/uaccess.h>
+
+#include "power.h"
+
+#define SNAPSHOT_MINOR	231
+
+static struct snapshot_data {
+	struct snapshot_handle handle;
+	int swap;
+	struct bitmap_page *bitmap;
+	int mode;
+	char frozen;
+	char ready;
+	char platform_suspend;
+} snapshot_state;
+
+static atomic_t device_available = ATOMIC_INIT(1);
+
+static int snapshot_open(struct inode *inode, struct file *filp)
+{
+	struct snapshot_data *data;
+
+	if (!atomic_add_unless(&device_available, -1, 0))
+		return -EBUSY;
+
+	if ((filp->f_flags & O_ACCMODE) == O_RDWR)
+		return -ENOSYS;
+
+	nonseekable_open(inode, filp);
+	data = &snapshot_state;
+	filp->private_data = data;
+	memset(&data->handle, 0, sizeof(struct snapshot_handle));
+	if ((filp->f_flags & O_ACCMODE) == O_RDONLY) {
+		data->swap = swsusp_resume_device ?
+			swap_type_of(swsusp_resume_device, 0, NULL) : -1;
+		data->mode = O_RDONLY;
+	} else {
+		data->swap = -1;
+		data->mode = O_WRONLY;
+	}
+	data->bitmap = NULL;
+	data->frozen = 0;
+	data->ready = 0;
+	data->platform_suspend = 0;
+
+	return 0;
+}
+
+static int snapshot_release(struct inode *inode, struct file *filp)
+{
+	struct snapshot_data *data;
+
+	swsusp_free();
+	data = filp->private_data;
+	free_all_swap_pages(data->swap, data->bitmap);
+	free_bitmap(data->bitmap);
+	if (data->frozen) {
+		mutex_lock(&pm_mutex);
+		thaw_processes();
+		enable_nonboot_cpus();
+		mutex_unlock(&pm_mutex);
+	}
+	atomic_inc(&device_available);
+	return 0;
+}
+
+static ssize_t snapshot_read(struct file *filp, char __user *buf,
+                             size_t count, loff_t *offp)
+{
+	struct snapshot_data *data;
+	ssize_t res;
+
+	data = filp->private_data;
+	res = snapshot_read_next(&data->handle, count);
+	if (res > 0) {
+		if (copy_to_user(buf, data_of(data->handle), res))
+			res = -EFAULT;
+		else
+			*offp = data->handle.offset;
+	}
+	return res;
+}
+
+static ssize_t snapshot_write(struct file *filp, const char __user *buf,
+                              size_t count, loff_t *offp)
+{
+	struct snapshot_data *data;
+	ssize_t res;
+
+	data = filp->private_data;
+	res = snapshot_write_next(&data->handle, count);
+	if (res > 0) {
+		if (copy_from_user(data_of(data->handle), buf, res))
+			res = -EFAULT;
+		else
+			*offp = data->handle.offset;
+	}
+	return res;
+}
+
+static inline int platform_prepare(void)
+{
+	int error = 0;
+
+	if (pm_ops && pm_ops->prepare)
+		error = pm_ops->prepare(PM_SUSPEND_DISK);
+
+	return error;
+}
+
+static inline void platform_finish(void)
+{
+	if (pm_ops && pm_ops->finish)
+		pm_ops->finish(PM_SUSPEND_DISK);
+}
+
+static inline int snapshot_suspend(int platform_suspend)
+{
+	int error;
+
+	mutex_lock(&pm_mutex);
+	/* Free memory before shutting down devices. */
+	error = swsusp_shrink_memory();
+	if (error)
+		goto Finish;
+
+	if (platform_suspend) {
+		error = platform_prepare();
+		if (error)
+			goto Finish;
+	}
+	suspend_console();
+	error = device_suspend(PMSG_FREEZE);
+	if (error)
+		goto Resume_devices;
+
+	error = disable_nonboot_cpus();
+	if (!error) {
+		in_suspend = 1;
+		error = swsusp_suspend();
+	}
+	enable_nonboot_cpus();
+ Resume_devices:
+	if (platform_suspend)
+		platform_finish();
+
+	device_resume();
+	resume_console();
+ Finish:
+	mutex_unlock(&pm_mutex);
+	return error;
+}
+
+static inline int snapshot_restore(int platform_suspend)
+{
+	int error;
+
+	mutex_lock(&pm_mutex);
+	pm_prepare_console();
+	if (platform_suspend) {
+		error = platform_prepare();
+		if (error)
+			goto Finish;
+	}
+	suspend_console();
+	error = device_suspend(PMSG_PRETHAW);
+	if (error)
+		goto Resume_devices;
+
+	error = disable_nonboot_cpus();
+	if (!error)
+		error = swsusp_resume();
+
+	enable_nonboot_cpus();
+ Resume_devices:
+	if (platform_suspend)
+		platform_finish();
+
+	device_resume();
+	resume_console();
+ Finish:
+	pm_restore_console();
+	mutex_unlock(&pm_mutex);
+	return error;
+}
+
+static int snapshot_ioctl(struct inode *inode, struct file *filp,
+                          unsigned int cmd, unsigned long arg)
+{
+	int error = 0;
+	struct snapshot_data *data;
+	loff_t avail;
+	sector_t offset;
+
+	if (_IOC_TYPE(cmd) != SNAPSHOT_IOC_MAGIC)
+		return -ENOTTY;
+	if (_IOC_NR(cmd) > SNAPSHOT_IOC_MAXNR)
+		return -ENOTTY;
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	data = filp->private_data;
+
+	switch (cmd) {
+
+	case SNAPSHOT_FREEZE:
+		if (data->frozen)
+			break;
+		mutex_lock(&pm_mutex);
+		if (freeze_processes()) {
+			thaw_processes();
+			error = -EBUSY;
+		}
+		mutex_unlock(&pm_mutex);
+		if (!error)
+			data->frozen = 1;
+		break;
+
+	case SNAPSHOT_UNFREEZE:
+		if (!data->frozen)
+			break;
+		mutex_lock(&pm_mutex);
+		thaw_processes();
+		mutex_unlock(&pm_mutex);
+		data->frozen = 0;
+		break;
+
+	case SNAPSHOT_ATOMIC_SNAPSHOT:
+		if (data->mode != O_RDONLY || !data->frozen  || data->ready) {
+			error = -EPERM;
+			break;
+		}
+		error = snapshot_suspend(data->platform_suspend);
+		if (!error)
+			error = put_user(in_suspend, (unsigned int __user *)arg);
+		if (!error)
+			data->ready = 1;
+		break;
+
+	case SNAPSHOT_ATOMIC_RESTORE:
+		snapshot_write_finalize(&data->handle);
+		if (data->mode != O_WRONLY || !data->frozen ||
+		    !snapshot_image_loaded(&data->handle)) {
+			error = -EPERM;
+			break;
+		}
+		error = snapshot_restore(data->platform_suspend);
+		break;
+
+	case SNAPSHOT_FREE:
+		swsusp_free();
+		memset(&data->handle, 0, sizeof(struct snapshot_handle));
+		data->ready = 0;
+		break;
+
+	case SNAPSHOT_SET_IMAGE_SIZE:
+		image_size = arg;
+		break;
+
+	case SNAPSHOT_AVAIL_SWAP:
+		avail = count_swap_pages(data->swap, 1);
+		avail <<= PAGE_SHIFT;
+		error = put_user(avail, (loff_t __user *)arg);
+		break;
+
+	case SNAPSHOT_GET_SWAP_PAGE:
+		if (data->swap < 0 || data->swap >= MAX_SWAPFILES) {
+			error = -ENODEV;
+			break;
+		}
+		if (!data->bitmap) {
+			data->bitmap = alloc_bitmap(count_swap_pages(data->swap, 0));
+			if (!data->bitmap) {
+				error = -ENOMEM;
+				break;
+			}
+		}
+		offset = alloc_swapdev_block(data->swap, data->bitmap);
+		if (offset) {
+			offset <<= PAGE_SHIFT;
+			error = put_user(offset, (sector_t __user *)arg);
+		} else {
+			error = -ENOSPC;
+		}
+		break;
+
+	case SNAPSHOT_FREE_SWAP_PAGES:
+		if (data->swap < 0 || data->swap >= MAX_SWAPFILES) {
+			error = -ENODEV;
+			break;
+		}
+		free_all_swap_pages(data->swap, data->bitmap);
+		free_bitmap(data->bitmap);
+		data->bitmap = NULL;
+		break;
+
+	case SNAPSHOT_SET_SWAP_FILE:
+		if (!data->bitmap) {
+			/*
+			 * User space encodes device types as two-byte values,
+			 * so we need to recode them
+			 */
+			if (old_decode_dev(arg)) {
+				data->swap = swap_type_of(old_decode_dev(arg),
+							0, NULL);
+				if (data->swap < 0)
+					error = -ENODEV;
+			} else {
+				data->swap = -1;
+				error = -EINVAL;
+			}
+		} else {
+			error = -EPERM;
+		}
+		break;
+
+	case SNAPSHOT_S2RAM:
+		if (!pm_ops) {
+			error = -ENOSYS;
+			break;
+		}
+
+		if (!data->frozen) {
+			error = -EPERM;
+			break;
+		}
+
+		if (!mutex_trylock(&pm_mutex)) {
+			error = -EBUSY;
+			break;
+		}
+
+		if (pm_ops->prepare) {
+			error = pm_ops->prepare(PM_SUSPEND_MEM);
+			if (error)
+				goto OutS3;
+		}
+
+		/* Put devices to sleep */
+		suspend_console();
+		error = device_suspend(PMSG_SUSPEND);
+		if (error) {
+			printk(KERN_ERR "Failed to suspend some devices.\n");
+		} else {
+			error = disable_nonboot_cpus();
+			if (!error) {
+				/* Enter S3, system is already frozen */
+				suspend_enter(PM_SUSPEND_MEM);
+				enable_nonboot_cpus();
+			}
+			/* Wake up devices */
+			device_resume();
+		}
+		resume_console();
+		if (pm_ops->finish)
+			pm_ops->finish(PM_SUSPEND_MEM);
+
+ OutS3:
+		mutex_unlock(&pm_mutex);
+		break;
+
+	case SNAPSHOT_PMOPS:
+		error = -EINVAL;
+
+		switch (arg) {
+
+		case PMOPS_PREPARE:
+			if (pm_ops && pm_ops->enter) {
+				data->platform_suspend = 1;
+				error = 0;
+			} else {
+				error = -ENOSYS;
+			}
+			break;
+
+		case PMOPS_ENTER:
+			if (data->platform_suspend) {
+				kernel_shutdown_prepare(SYSTEM_SUSPEND_DISK);
+				error = pm_ops->enter(PM_SUSPEND_DISK);
+				error = 0;
+			}
+			break;
+
+		case PMOPS_FINISH:
+			if (data->platform_suspend)
+				error = 0;
+
+			break;
+
+		default:
+			printk(KERN_ERR "SNAPSHOT_PMOPS: invalid argument %ld\n", arg);
+
+		}
+		break;
+
+	case SNAPSHOT_SET_SWAP_AREA:
+		if (data->bitmap) {
+			error = -EPERM;
+		} else {
+			struct resume_swap_area swap_area;
+			dev_t swdev;
+
+			error = copy_from_user(&swap_area, (void __user *)arg,
+					sizeof(struct resume_swap_area));
+			if (error) {
+				error = -EFAULT;
+				break;
+			}
+
+			/*
+			 * User space encodes device types as two-byte values,
+			 * so we need to recode them
+			 */
+			swdev = old_decode_dev(swap_area.dev);
+			if (swdev) {
+				offset = swap_area.offset;
+				data->swap = swap_type_of(swdev, offset, NULL);
+				if (data->swap < 0)
+					error = -ENODEV;
+			} else {
+				data->swap = -1;
+				error = -EINVAL;
+			}
+		}
+		break;
+
+	default:
+		error = -ENOTTY;
+
+	}
+
+	return error;
+}
+
+static const struct file_operations snapshot_fops = {
+	.open = snapshot_open,
+	.release = snapshot_release,
+	.read = snapshot_read,
+	.write = snapshot_write,
+	.llseek = no_llseek,
+	.ioctl = snapshot_ioctl,
+};
+
+static struct miscdevice snapshot_device = {
+	.minor = SNAPSHOT_MINOR,
+	.name = "snapshot",
+	.fops = &snapshot_fops,
+};
+
+static int __init snapshot_device_init(void)
+{
+	return misc_register(&snapshot_device);
+};
+
+device_initcall(snapshot_device_init);