Initial import of modified Linux 2.6.28 tree

Original upstream URL:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable.git | branch linux-2.6.28.y

12 files changed, 5685 insertions, 0 deletions

diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
new file mode 100644
index 0000000..23bd4da
--- /dev/null
+++ b/kernel/power/Kconfig
@@ -0,0 +1,206 @@
+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_DEBUG
+	bool "Power Management Debug Support"
+	depends on PM
+	---help---
+	This option enables various debugging support in the Power Management
+	code. This is helpful when debugging and reporting PM bugs, like
+	suspend support.
+
+config PM_VERBOSE
+	bool "Verbose Power Management debugging"
+	depends on PM_DEBUG
+	default n
+	---help---
+	This option enables verbose messages from the Power Management code.
+
+config CAN_PM_TRACE
+	def_bool y
+	depends on PM_DEBUG && PM_SLEEP && EXPERIMENTAL
+
+config PM_TRACE
+	bool
+	help
+	  This enables code to save the last PM event point across
+	  reboot. The architecture needs to support this, x86 for
+	  example does by saving things in the RTC, see below.
+
+	  The architecture specific code must provide the extern
+	  functions from <linux/resume-trace.h> as well as the
+	  <asm/resume-trace.h> header with a TRACE_RESUME() macro.
+
+	  The way the information is presented is architecture-
+	  dependent, x86 will print the information during a
+	  late_initcall.
+
+config PM_TRACE_RTC
+	bool "Suspend/resume event tracing"
+	depends on CAN_PM_TRACE
+	depends on X86
+	select PM_TRACE
+	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, reboot it and 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_SLEEP_SMP
+	bool
+	depends on SMP
+	depends on ARCH_SUSPEND_POSSIBLE || ARCH_HIBERNATION_POSSIBLE
+	depends on PM_SLEEP
+	select HOTPLUG_CPU
+	default y
+
+config PM_SLEEP
+	bool
+	depends on SUSPEND || HIBERNATION || XEN_SAVE_RESTORE
+	default y
+
+config SUSPEND
+	bool "Suspend to RAM and standby"
+	depends on PM && ARCH_SUSPEND_POSSIBLE
+	default y
+	---help---
+	  Allow the system to enter sleep states in which main memory is
+	  powered and thus its contents are preserved, such as the
+	  suspend-to-RAM state (e.g. the ACPI S3 state).
+
+config PM_TEST_SUSPEND
+	bool "Test suspend/resume and wakealarm during bootup"
+	depends on SUSPEND && PM_DEBUG && RTC_CLASS=y
+	---help---
+	This option will let you suspend your machine during bootup, and
+	make it wake up a few seconds later using an RTC wakeup alarm.
+	Enable this with a kernel parameter like "test_suspend=mem".
+
+	You probably want to have your system's RTC driver statically
+	linked, ensuring that it's available when this test runs.
+
+config SUSPEND_FREEZER
+	bool "Enable freezer for suspend to RAM/standby" \
+		if ARCH_WANTS_FREEZER_CONTROL || BROKEN
+	depends on SUSPEND
+	default y
+	help
+	  This allows you to turn off the freezer for suspend. If this is
+	  done, no tasks are frozen for suspend to RAM/standby.
+
+	  Turning OFF this setting is NOT recommended! If in doubt, say Y.
+
+config HIBERNATION
+	bool "Hibernation (aka 'suspend to disk')"
+	depends on PM && SWAP && ARCH_HIBERNATION_POSSIBLE
+	---help---
+	  Enable the suspend to disk (STD) functionality, which is usually
+	  called "hibernation" in user interfaces.  STD checkpoints the
+	  system and powers it off; and restores that checkpoint on reboot.
+
+	  You can suspend your machine with 'echo disk > /sys/power/state'
+	  after placing resume=/dev/swappartition on the kernel command line
+	  in your bootloader's configuration file.
+
+	  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 for the final steps when it is available.  One
+	  of the reasons to use software suspend is that the firmware hooks
+	  for suspend states like suspend-to-RAM (STR) often don't work very
+	  well with Linux.
+
+	  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 HIBERNATION
+	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 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/power/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).
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
new file mode 100644
index 0000000..597823b
--- /dev/null
+++ b/kernel/power/Makefile
@@ -0,0 +1,10 @@
+
+ifeq ($(CONFIG_PM_DEBUG),y)
+EXTRA_CFLAGS	+=	-DDEBUG
+endif
+
+obj-y				:= main.o
+obj-$(CONFIG_PM_SLEEP)		+= process.o console.o
+obj-$(CONFIG_HIBERNATION)	+= swsusp.o disk.o snapshot.o swap.o user.o
+
+obj-$(CONFIG_MAGIC_SYSRQ)	+= poweroff.o
diff --git a/kernel/power/console.c b/kernel/power/console.c
new file mode 100644
index 0000000..b8628be
--- /dev/null
+++ b/kernel/power/console.c
@@ -0,0 +1,83 @@
+/*
+ * 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 <linux/module.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;
+static int disable_vt_switch;
+
+/*
+ * Normally during a suspend, we allocate a new console and switch to it.
+ * When we resume, we switch back to the original console.  This switch
+ * can be slow, so on systems where the framebuffer can handle restoration
+ * of video registers anyways, there's little point in doing the console
+ * switch.  This function allows you to disable it by passing it '0'.
+ */
+void pm_set_vt_switch(int do_switch)
+{
+	acquire_console_sem();
+	disable_vt_switch = !do_switch;
+	release_console_sem();
+}
+EXPORT_SYMBOL(pm_set_vt_switch);
+
+int pm_prepare_console(void)
+{
+	acquire_console_sem();
+
+	if (disable_vt_switch) {
+		release_console_sem();
+		return 0;
+	}
+
+	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();
+	if (disable_vt_switch) {
+		release_console_sem();
+		return;
+	}
+	set_console(orig_fgconsole);
+	release_console_sem();
+	kmsg_redirect = orig_kmsg;
+}
+#endif
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
new file mode 100644
index 0000000..c9d7408
--- /dev/null
+++ b/kernel/power/disk.c
@@ -0,0 +1,901 @@
+/*
+ * 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/kmod.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 <linux/ftrace.h>
+
+#include "power.h"
+
+
+static int noresume = 0;
+static char resume_file[256] = CONFIG_PM_STD_PARTITION;
+dev_t swsusp_resume_device;
+sector_t swsusp_resume_block;
+
+enum {
+	HIBERNATION_INVALID,
+	HIBERNATION_PLATFORM,
+	HIBERNATION_TEST,
+	HIBERNATION_TESTPROC,
+	HIBERNATION_SHUTDOWN,
+	HIBERNATION_REBOOT,
+	/* keep last */
+	__HIBERNATION_AFTER_LAST
+};
+#define HIBERNATION_MAX (__HIBERNATION_AFTER_LAST-1)
+#define HIBERNATION_FIRST (HIBERNATION_INVALID + 1)
+
+static int hibernation_mode = HIBERNATION_SHUTDOWN;
+
+static struct platform_hibernation_ops *hibernation_ops;
+
+/**
+ * hibernation_set_ops - set the global hibernate operations
+ * @ops: the hibernation operations to use in subsequent hibernation transitions
+ */
+
+void hibernation_set_ops(struct platform_hibernation_ops *ops)
+{
+	if (ops && !(ops->begin && ops->end &&  ops->pre_snapshot
+	    && ops->prepare && ops->finish && ops->enter && ops->pre_restore
+	    && ops->restore_cleanup)) {
+		WARN_ON(1);
+		return;
+	}
+	mutex_lock(&pm_mutex);
+	hibernation_ops = ops;
+	if (ops)
+		hibernation_mode = HIBERNATION_PLATFORM;
+	else if (hibernation_mode == HIBERNATION_PLATFORM)
+		hibernation_mode = HIBERNATION_SHUTDOWN;
+
+	mutex_unlock(&pm_mutex);
+}
+
+#ifdef CONFIG_PM_DEBUG
+static void hibernation_debug_sleep(void)
+{
+	printk(KERN_INFO "hibernation debug: Waiting for 5 seconds.\n");
+	mdelay(5000);
+}
+
+static int hibernation_testmode(int mode)
+{
+	if (hibernation_mode == mode) {
+		hibernation_debug_sleep();
+		return 1;
+	}
+	return 0;
+}
+
+static int hibernation_test(int level)
+{
+	if (pm_test_level == level) {
+		hibernation_debug_sleep();
+		return 1;
+	}
+	return 0;
+}
+#else /* !CONFIG_PM_DEBUG */
+static int hibernation_testmode(int mode) { return 0; }
+static int hibernation_test(int level) { return 0; }
+#endif /* !CONFIG_PM_DEBUG */
+
+/**
+ *	platform_begin - tell the platform driver that we're starting
+ *	hibernation
+ */
+
+static int platform_begin(int platform_mode)
+{
+	return (platform_mode && hibernation_ops) ?
+		hibernation_ops->begin() : 0;
+}
+
+/**
+ *	platform_end - tell the platform driver that we've entered the
+ *	working state
+ */
+
+static void platform_end(int platform_mode)
+{
+	if (platform_mode && hibernation_ops)
+		hibernation_ops->end();
+}
+
+/**
+ *	platform_pre_snapshot - prepare the machine for hibernation using the
+ *	platform driver if so configured and return an error code if it fails
+ */
+
+static int platform_pre_snapshot(int platform_mode)
+{
+	return (platform_mode && hibernation_ops) ?
+		hibernation_ops->pre_snapshot() : 0;
+}
+
+/**
+ *	platform_leave - prepare the machine for switching to the normal mode
+ *	of operation using the platform driver (called with interrupts disabled)
+ */
+
+static void platform_leave(int platform_mode)
+{
+	if (platform_mode && hibernation_ops)
+		hibernation_ops->leave();
+}
+
+/**
+ *	platform_finish - switch the machine to the normal mode of operation
+ *	using the platform driver (must be called after platform_prepare())
+ */
+
+static void platform_finish(int platform_mode)
+{
+	if (platform_mode && hibernation_ops)
+		hibernation_ops->finish();
+}
+
+/**
+ *	platform_pre_restore - prepare the platform for the restoration from a
+ *	hibernation image.  If the restore fails after this function has been
+ *	called, platform_restore_cleanup() must be called.
+ */
+
+static int platform_pre_restore(int platform_mode)
+{
+	return (platform_mode && hibernation_ops) ?
+		hibernation_ops->pre_restore() : 0;
+}
+
+/**
+ *	platform_restore_cleanup - switch the platform to the normal mode of
+ *	operation after a failing restore.  If platform_pre_restore() has been
+ *	called before the failing restore, this function must be called too,
+ *	regardless of the result of platform_pre_restore().
+ */
+
+static void platform_restore_cleanup(int platform_mode)
+{
+	if (platform_mode && hibernation_ops)
+		hibernation_ops->restore_cleanup();
+}
+
+/**
+ *	platform_recover - recover the platform from a failure to suspend
+ *	devices.
+ */
+
+static void platform_recover(int platform_mode)
+{
+	if (platform_mode && hibernation_ops && hibernation_ops->recover)
+		hibernation_ops->recover();
+}
+
+/**
+ *	create_image - freeze devices that need to be frozen with interrupts
+ *	off, create the hibernation image and thaw those devices.  Control
+ *	reappears in this routine after a restore.
+ */
+
+static int create_image(int platform_mode)
+{
+	int error;
+
+	error = arch_prepare_suspend();
+	if (error)
+		return error;
+
+	device_pm_lock();
+	local_irq_disable();
+	/* At this point, device_suspend() has been called, but *not*
+	 * device_power_down(). We *must* call 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.
+	 */
+	error = device_power_down(PMSG_FREEZE);
+	if (error) {
+		printk(KERN_ERR "PM: Some devices failed to power down, "
+			"aborting hibernation\n");
+		goto Enable_irqs;
+	}
+
+	if (hibernation_test(TEST_CORE))
+		goto Power_up;
+
+	in_suspend = 1;
+	save_processor_state();
+	error = swsusp_arch_suspend();
+	if (error)
+		printk(KERN_ERR "PM: Error %d creating hibernation image\n",
+			error);
+	/* Restore control flow magically appears here */
+	restore_processor_state();
+	if (!in_suspend)
+		platform_leave(platform_mode);
+ Power_up:
+	/* NOTE:  device_power_up() is just a resume() for devices
+	 * that suspended with irqs off ... no overall powerup.
+	 */
+	device_power_up(in_suspend ?
+		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
+ Enable_irqs:
+	local_irq_enable();
+	device_pm_unlock();
+	return error;
+}
+
+/**
+ *	hibernation_snapshot - quiesce devices and create the hibernation
+ *	snapshot image.
+ *	@platform_mode - if set, use the platform driver, if available, to
+ *			 prepare the platform frimware for the power transition.
+ *
+ *	Must be called with pm_mutex held
+ */
+
+int hibernation_snapshot(int platform_mode)
+{
+	int error, ftrace_save;
+
+	/* Free memory before shutting down devices. */
+	error = swsusp_shrink_memory();
+	if (error)
+		return error;
+
+	error = platform_begin(platform_mode);
+	if (error)
+		goto Close;
+
+	suspend_console();
+	ftrace_save = __ftrace_enabled_save();
+	error = device_suspend(PMSG_FREEZE);
+	if (error)
+		goto Recover_platform;
+
+	if (hibernation_test(TEST_DEVICES))
+		goto Recover_platform;
+
+	error = platform_pre_snapshot(platform_mode);
+	if (error || hibernation_test(TEST_PLATFORM))
+		goto Finish;
+
+	error = disable_nonboot_cpus();
+	if (!error) {
+		if (hibernation_test(TEST_CPUS))
+			goto Enable_cpus;
+
+		if (hibernation_testmode(HIBERNATION_TEST))
+			goto Enable_cpus;
+
+		error = create_image(platform_mode);
+		/* Control returns here after successful restore */
+	}
+ Enable_cpus:
+	enable_nonboot_cpus();
+ Finish:
+	platform_finish(platform_mode);
+ Resume_devices:
+	device_resume(in_suspend ?
+		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
+	__ftrace_enabled_restore(ftrace_save);
+	resume_console();
+ Close:
+	platform_end(platform_mode);
+	return error;
+
+ Recover_platform:
+	platform_recover(platform_mode);
+	goto Resume_devices;
+}
+
+/**
+ *	resume_target_kernel - prepare devices that need to be suspended with
+ *	interrupts off, restore the contents of highmem that have not been
+ *	restored yet from the image and run the low level code that will restore
+ *	the remaining contents of memory and switch to the just restored target
+ *	kernel.
+ */
+
+static int resume_target_kernel(void)
+{
+	int error;
+
+	device_pm_lock();
+	local_irq_disable();
+	error = device_power_down(PMSG_QUIESCE);
+	if (error) {
+		printk(KERN_ERR "PM: Some devices failed to power down, "
+			"aborting resume\n");
+		goto Enable_irqs;
+	}
+	/* 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(PMSG_RECOVER);
+ Enable_irqs:
+	local_irq_enable();
+	device_pm_unlock();
+	return error;
+}
+
+/**
+ *	hibernation_restore - quiesce devices and restore the hibernation
+ *	snapshot image.  If successful, control returns in hibernation_snaphot()
+ *	@platform_mode - if set, use the platform driver, if available, to
+ *			 prepare the platform frimware for the transition.
+ *
+ *	Must be called with pm_mutex held
+ */
+
+int hibernation_restore(int platform_mode)
+{
+	int error, ftrace_save;
+
+	pm_prepare_console();
+	suspend_console();
+	ftrace_save = __ftrace_enabled_save();
+	error = device_suspend(PMSG_QUIESCE);
+	if (error)
+		goto Finish;
+
+	error = platform_pre_restore(platform_mode);
+	if (!error) {
+		error = disable_nonboot_cpus();
+		if (!error)
+			error = resume_target_kernel();
+		enable_nonboot_cpus();
+	}
+	platform_restore_cleanup(platform_mode);
+	device_resume(PMSG_RECOVER);
+ Finish:
+	__ftrace_enabled_restore(ftrace_save);
+	resume_console();
+	pm_restore_console();
+	return error;
+}
+
+/**
+ *	hibernation_platform_enter - enter the hibernation state using the
+ *	platform driver (if available)
+ */
+
+int hibernation_platform_enter(void)
+{
+	int error, ftrace_save;
+
+	if (!hibernation_ops)
+		return -ENOSYS;
+
+	/*
+	 * We have cancelled the power transition by running
+	 * hibernation_ops->finish() before saving the image, so we should let
+	 * the firmware know that we're going to enter the sleep state after all
+	 */
+	error = hibernation_ops->begin();
+	if (error)
+		goto Close;
+
+	suspend_console();
+	ftrace_save = __ftrace_enabled_save();
+	error = device_suspend(PMSG_HIBERNATE);
+	if (error) {
+		if (hibernation_ops->recover)
+			hibernation_ops->recover();
+		goto Resume_devices;
+	}
+
+	error = hibernation_ops->prepare();
+	if (error)
+		goto Resume_devices;
+
+	error = disable_nonboot_cpus();
+	if (error)
+		goto Finish;
+
+	device_pm_lock();
+	local_irq_disable();
+	error = device_power_down(PMSG_HIBERNATE);
+	if (!error) {
+		hibernation_ops->enter();
+		/* We should never get here */
+		while (1);
+	}
+	local_irq_enable();
+	device_pm_unlock();
+
+	/*
+	 * We don't need to reenable the nonboot CPUs or resume consoles, since
+	 * the system is going to be halted anyway.
+	 */
+ Finish:
+	hibernation_ops->finish();
+ Resume_devices:
+	device_resume(PMSG_RESTORE);
+	__ftrace_enabled_restore(ftrace_save);
+	resume_console();
+ Close:
+	hibernation_ops->end();
+	return error;
+}
+
+/**
+ *	power_down - Shut the machine down for hibernation.
+ *
+ *	Use the platform driver, if configured so; otherwise try
+ *	to power off or reboot.
+ */
+
+static void power_down(void)
+{
+	switch (hibernation_mode) {
+	case HIBERNATION_TEST:
+	case HIBERNATION_TESTPROC:
+		break;
+	case HIBERNATION_REBOOT:
+		kernel_restart(NULL);
+		break;
+	case HIBERNATION_PLATFORM:
+		hibernation_platform_enter();
+	case HIBERNATION_SHUTDOWN:
+		kernel_power_off();
+		break;
+	}
+	kernel_halt();
+	/*
+	 * Valid image is on the disk, if we continue we risk serious data
+	 * corruption after resume.
+	 */
+	printk(KERN_CRIT "PM: Please power down manually\n");
+	while(1);
+}
+
+static int prepare_processes(void)
+{
+	int error = 0;
+
+	if (freeze_processes()) {
+		error = -EBUSY;
+		thaw_processes();
+	}
+	return error;
+}
+
+/**
+ *	hibernate - The granpappy of the built-in hibernation management
+ */
+
+int hibernate(void)
+{
+	int error;
+
+	mutex_lock(&pm_mutex);
+	/* The snapshot device should not be opened while we're running */
+	if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
+		error = -EBUSY;
+		goto Unlock;
+	}
+
+	pm_prepare_console();
+	error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE);
+	if (error)
+		goto Exit;
+
+	error = usermodehelper_disable();
+	if (error)
+		goto Exit;
+
+	/* Allocate memory management structures */
+	error = create_basic_memory_bitmaps();
+	if (error)
+		goto Exit;
+
+	printk(KERN_INFO "PM: Syncing filesystems ... ");
+	sys_sync();
+	printk("done.\n");
+
+	error = prepare_processes();
+	if (error)
+		goto Finish;
+
+	if (hibernation_test(TEST_FREEZER))
+		goto Thaw;
+
+	if (hibernation_testmode(HIBERNATION_TESTPROC))
+		goto Thaw;
+
+	error = hibernation_snapshot(hibernation_mode == HIBERNATION_PLATFORM);
+	if (in_suspend && !error) {
+		unsigned int flags = 0;
+
+		if (hibernation_mode == HIBERNATION_PLATFORM)
+			flags |= SF_PLATFORM_MODE;
+		pr_debug("PM: writing image.\n");
+		error = swsusp_write(flags);
+		swsusp_free();
+		if (!error)
+			power_down();
+	} else {
+		pr_debug("PM: Image restored successfully.\n");
+		swsusp_free();
+	}
+ Thaw:
+	thaw_processes();
+ Finish:
+	free_basic_memory_bitmaps();
+	usermodehelper_enable();
+ Exit:
+	pm_notifier_call_chain(PM_POST_HIBERNATION);
+	pm_restore_console();
+	atomic_inc(&snapshot_device_available);
+ Unlock:
+	mutex_unlock(&pm_mutex);
+	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 hibernate() ) if everything goes well.
+ *	Otherwise, we fail gracefully and return to the normally
+ *	scheduled program.
+ *
+ */
+
+static int software_resume(void)
+{
+	int error;
+	unsigned int flags;
+
+	/*
+	 * name_to_dev_t() below takes a sysfs buffer mutex when sysfs
+	 * is configured into the kernel. Since the regular hibernate
+	 * trigger path is via sysfs which takes a buffer mutex before
+	 * calling hibernate functions (which take pm_mutex) this can
+	 * cause lockdep to complain about a possible ABBA deadlock
+	 * which cannot happen since we're in the boot code here and
+	 * sysfs can't be invoked yet. Therefore, we use a subclass
+	 * here to avoid lockdep complaining.
+	 */
+	mutex_lock_nested(&pm_mutex, SINGLE_DEPTH_NESTING);
+	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("PM: Resume from partition %s\n", resume_file);
+	} else {
+		pr_debug("PM: 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 hibernation image.\n");
+	error = swsusp_check();
+	if (error)
+		goto Unlock;
+
+	/* The snapshot device should not be opened while we're running */
+	if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
+		error = -EBUSY;
+		goto Unlock;
+	}
+
+	pm_prepare_console();
+	error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
+	if (error)
+		goto Finish;
+
+	error = usermodehelper_disable();
+	if (error)
+		goto Finish;
+
+	error = create_basic_memory_bitmaps();
+	if (error)
+		goto Finish;
+
+	pr_debug("PM: Preparing processes for restore.\n");
+	error = prepare_processes();
+	if (error) {
+		swsusp_close(FMODE_READ);
+		goto Done;
+	}
+
+	pr_debug("PM: Reading hibernation image.\n");
+
+	error = swsusp_read(&flags);
+	if (!error)
+		hibernation_restore(flags & SF_PLATFORM_MODE);
+
+	printk(KERN_ERR "PM: Restore failed, recovering.\n");
+	swsusp_free();
+	thaw_processes();
+ Done:
+	free_basic_memory_bitmaps();
+	usermodehelper_enable();
+ Finish:
+	pm_notifier_call_chain(PM_POST_RESTORE);
+	pm_restore_console();
+	atomic_inc(&snapshot_device_available);
+	/* For success case, the suspend path will release the lock */
+ Unlock:
+	mutex_unlock(&pm_mutex);
+	pr_debug("PM: Resume from disk failed.\n");
+	return error;
+}
+
+late_initcall(software_resume);
+
+
+static const char * const hibernation_modes[] = {
+	[HIBERNATION_PLATFORM]	= "platform",
+	[HIBERNATION_SHUTDOWN]	= "shutdown",
+	[HIBERNATION_REBOOT]	= "reboot",
+	[HIBERNATION_TEST]	= "test",
+	[HIBERNATION_TESTPROC]	= "testproc",
+};
+
+/**
+ *	disk - Control hibernation mode
+ *
+ *	Suspend-to-disk can be handled in several ways. We have a few options
+ *	for putting the system to sleep - using the platform driver (e.g. ACPI
+ *	or other hibernation_ops), powering off the system or rebooting the
+ *	system (for testing) as well as the two test modes.
+ *
+ *	The system can support 'platform', and that is known a priori (and
+ *	encoded by the presence of hibernation_ops). However, the user may
+ *	choose 'shutdown' or 'reboot' as alternatives, as well as one fo the
+ *	test modes, 'test' or 'testproc'.
+ *
+ *	show() will display what the mode is currently set to.
+ *	store() will accept one of
+ *
+ *	'platform'
+ *	'shutdown'
+ *	'reboot'
+ *	'test'
+ *	'testproc'
+ *
+ *	It will only change to 'platform' if the system
+ *	supports it (as determined by having hibernation_ops).
+ */
+
+static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr,
+			 char *buf)
+{
+	int i;
+	char *start = buf;
+
+	for (i = HIBERNATION_FIRST; i <= HIBERNATION_MAX; i++) {
+		if (!hibernation_modes[i])
+			continue;
+		switch (i) {
+		case HIBERNATION_SHUTDOWN:
+		case HIBERNATION_REBOOT:
+		case HIBERNATION_TEST:
+		case HIBERNATION_TESTPROC:
+			break;
+		case HIBERNATION_PLATFORM:
+			if (hibernation_ops)
+				break;
+			/* not a valid mode, continue with loop */
+			continue;
+		}
+		if (i == hibernation_mode)
+			buf += sprintf(buf, "[%s] ", hibernation_modes[i]);
+		else
+			buf += sprintf(buf, "%s ", hibernation_modes[i]);
+	}
+	buf += sprintf(buf, "\n");
+	return buf-start;
+}
+
+
+static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr,
+			  const char *buf, size_t n)
+{
+	int error = 0;
+	int i;
+	int len;
+	char *p;
+	int mode = HIBERNATION_INVALID;
+
+	p = memchr(buf, '\n', n);
+	len = p ? p - buf : n;
+
+	mutex_lock(&pm_mutex);
+	for (i = HIBERNATION_FIRST; i <= HIBERNATION_MAX; i++) {
+		if (len == strlen(hibernation_modes[i])
+		    && !strncmp(buf, hibernation_modes[i], len)) {
+			mode = i;
+			break;
+		}
+	}
+	if (mode != HIBERNATION_INVALID) {
+		switch (mode) {
+		case HIBERNATION_SHUTDOWN:
+		case HIBERNATION_REBOOT:
+		case HIBERNATION_TEST:
+		case HIBERNATION_TESTPROC:
+			hibernation_mode = mode;
+			break;
+		case HIBERNATION_PLATFORM:
+			if (hibernation_ops)
+				hibernation_mode = mode;
+			else
+				error = -EINVAL;
+		}
+	} else
+		error = -EINVAL;
+
+	if (!error)
+		pr_debug("PM: Hibernation mode set to '%s'\n",
+			 hibernation_modes[mode]);
+	mutex_unlock(&pm_mutex);
+	return error ? error : n;
+}
+
+power_attr(disk);
+
+static ssize_t resume_show(struct kobject *kobj, struct kobj_attribute *attr,
+			   char *buf)
+{
+	return sprintf(buf,"%d:%d\n", MAJOR(swsusp_resume_device),
+		       MINOR(swsusp_resume_device));
+}
+
+static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr,
+			    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(KERN_INFO "PM: Starting manual resume from disk\n");
+	noresume = 0;
+	software_resume();
+	ret = n;
+ out:
+	return ret;
+}
+
+power_attr(resume);
+
+static ssize_t image_size_show(struct kobject *kobj, struct kobj_attribute *attr,
+			       char *buf)
+{
+	return sprintf(buf, "%lu\n", image_size);
+}
+
+static ssize_t image_size_store(struct kobject *kobj, struct kobj_attribute *attr,
+				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_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);
diff --git a/kernel/power/main.c b/kernel/power/main.c
new file mode 100644
index 0000000..b8f7ce9
--- /dev/null
+++ b/kernel/power/main.c
@@ -0,0 +1,732 @@
+/*
+ * 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/kmod.h>
+#include <linux/init.h>
+#include <linux/console.h>
+#include <linux/cpu.h>
+#include <linux/resume-trace.h>
+#include <linux/freezer.h>
+#include <linux/vmstat.h>
+#include <linux/syscalls.h>
+#include <linux/ftrace.h>
+
+#include "power.h"
+
+DEFINE_MUTEX(pm_mutex);
+
+unsigned int pm_flags;
+EXPORT_SYMBOL(pm_flags);
+
+#ifdef CONFIG_PM_SLEEP
+
+/* Routines for PM-transition notifications */
+
+static BLOCKING_NOTIFIER_HEAD(pm_chain_head);
+
+int register_pm_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&pm_chain_head, nb);
+}
+EXPORT_SYMBOL_GPL(register_pm_notifier);
+
+int unregister_pm_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_unregister(&pm_chain_head, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_pm_notifier);
+
+int pm_notifier_call_chain(unsigned long val)
+{
+	return (blocking_notifier_call_chain(&pm_chain_head, val, NULL)
+			== NOTIFY_BAD) ? -EINVAL : 0;
+}
+
+#ifdef CONFIG_PM_DEBUG
+int pm_test_level = TEST_NONE;
+
+static int suspend_test(int level)
+{
+	if (pm_test_level == level) {
+		printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n");
+		mdelay(5000);
+		return 1;
+	}
+	return 0;
+}
+
+static const char * const pm_tests[__TEST_AFTER_LAST] = {
+	[TEST_NONE] = "none",
+	[TEST_CORE] = "core",
+	[TEST_CPUS] = "processors",
+	[TEST_PLATFORM] = "platform",
+	[TEST_DEVICES] = "devices",
+	[TEST_FREEZER] = "freezer",
+};
+
+static ssize_t pm_test_show(struct kobject *kobj, struct kobj_attribute *attr,
+				char *buf)
+{
+	char *s = buf;
+	int level;
+
+	for (level = TEST_FIRST; level <= TEST_MAX; level++)
+		if (pm_tests[level]) {
+			if (level == pm_test_level)
+				s += sprintf(s, "[%s] ", pm_tests[level]);
+			else
+				s += sprintf(s, "%s ", pm_tests[level]);
+		}
+
+	if (s != buf)
+		/* convert the last space to a newline */
+		*(s-1) = '\n';
+
+	return (s - buf);
+}
+
+static ssize_t pm_test_store(struct kobject *kobj, struct kobj_attribute *attr,
+				const char *buf, size_t n)
+{
+	const char * const *s;
+	int level;
+	char *p;
+	int len;
+	int error = -EINVAL;
+
+	p = memchr(buf, '\n', n);
+	len = p ? p - buf : n;
+
+	mutex_lock(&pm_mutex);
+
+	level = TEST_FIRST;
+	for (s = &pm_tests[level]; level <= TEST_MAX; s++, level++)
+		if (*s && len == strlen(*s) && !strncmp(buf, *s, len)) {
+			pm_test_level = level;
+			error = 0;
+			break;
+		}
+
+	mutex_unlock(&pm_mutex);
+
+	return error ? error : n;
+}
+
+power_attr(pm_test);
+#else /* !CONFIG_PM_DEBUG */
+static inline int suspend_test(int level) { return 0; }
+#endif /* !CONFIG_PM_DEBUG */
+
+#endif /* CONFIG_PM_SLEEP */
+
+#ifdef CONFIG_SUSPEND
+
+#ifdef CONFIG_PM_TEST_SUSPEND
+
+/*
+ * We test the system suspend code by setting an RTC wakealarm a short
+ * time in the future, then suspending.  Suspending the devices won't
+ * normally take long ... some systems only need a few milliseconds.
+ *
+ * The time it takes is system-specific though, so when we test this
+ * during system bootup we allow a LOT of time.
+ */
+#define TEST_SUSPEND_SECONDS	5
+
+static unsigned long suspend_test_start_time;
+
+static void suspend_test_start(void)
+{
+	/* FIXME Use better timebase than "jiffies", ideally a clocksource.
+	 * What we want is a hardware counter that will work correctly even
+	 * during the irqs-are-off stages of the suspend/resume cycle...
+	 */
+	suspend_test_start_time = jiffies;
+}
+
+static void suspend_test_finish(const char *label)
+{
+	long nj = jiffies - suspend_test_start_time;
+	unsigned msec;
+
+	msec = jiffies_to_msecs(abs(nj));
+	pr_info("PM: %s took %d.%03d seconds\n", label,
+			msec / 1000, msec % 1000);
+
+	/* Warning on suspend means the RTC alarm period needs to be
+	 * larger -- the system was sooo slooowwww to suspend that the
+	 * alarm (should have) fired before the system went to sleep!
+	 *
+	 * Warning on either suspend or resume also means the system
+	 * has some performance issues.  The stack dump of a WARN_ON
+	 * is more likely to get the right attention than a printk...
+	 */
+	WARN(msec > (TEST_SUSPEND_SECONDS * 1000), "Component: %s\n", label);
+}
+
+#else
+
+static void suspend_test_start(void)
+{
+}
+
+static void suspend_test_finish(const char *label)
+{
+}
+
+#endif
+
+/* This is just an arbitrary number */
+#define FREE_PAGE_NUMBER (100)
+
+static struct platform_suspend_ops *suspend_ops;
+
+/**
+ *	suspend_set_ops - Set the global suspend method table.
+ *	@ops:	Pointer to ops structure.
+ */
+
+void suspend_set_ops(struct platform_suspend_ops *ops)
+{
+	mutex_lock(&pm_mutex);
+	suspend_ops = ops;
+	mutex_unlock(&pm_mutex);
+}
+
+/**
+ * suspend_valid_only_mem - generic memory-only valid callback
+ *
+ * Platform drivers that implement mem suspend only and only need
+ * to check for that in their .valid callback can use this instead
+ * of rolling their own .valid callback.
+ */
+int suspend_valid_only_mem(suspend_state_t state)
+{
+	return state == PM_SUSPEND_MEM;
+}
+
+/**
+ *	suspend_prepare - Do prep work before entering low-power state.
+ *
+ *	This is common code that is called for each state that we're entering.
+ *	Run suspend notifiers, allocate a console and stop all processes.
+ */
+static int suspend_prepare(void)
+{
+	int error;
+	unsigned int free_pages;
+
+	if (!suspend_ops || !suspend_ops->enter)
+		return -EPERM;
+
+	pm_prepare_console();
+
+	error = pm_notifier_call_chain(PM_SUSPEND_PREPARE);
+	if (error)
+		goto Finish;
+
+	error = usermodehelper_disable();
+	if (error)
+		goto Finish;
+
+	if (suspend_freeze_processes()) {
+		error = -EAGAIN;
+		goto Thaw;
+	}
+
+	free_pages = global_page_state(NR_FREE_PAGES);
+	if (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");
+		}
+	}
+	if (!error)
+		return 0;
+
+ Thaw:
+	suspend_thaw_processes();
+	usermodehelper_enable();
+ Finish:
+	pm_notifier_call_chain(PM_POST_SUSPEND);
+	pm_restore_console();
+	return error;
+}
+
+/* default implementation */
+void __attribute__ ((weak)) arch_suspend_disable_irqs(void)
+{
+	local_irq_disable();
+}
+
+/* default implementation */
+void __attribute__ ((weak)) arch_suspend_enable_irqs(void)
+{
+	local_irq_enable();
+}
+
+/**
+ *	suspend_enter - enter the desired system sleep state.
+ *	@state:		state to enter
+ *
+ *	This function should be called after devices have been suspended.
+ */
+static int suspend_enter(suspend_state_t state)
+{
+	int error = 0;
+
+	device_pm_lock();
+	arch_suspend_disable_irqs();
+	BUG_ON(!irqs_disabled());
+
+	if ((error = device_power_down(PMSG_SUSPEND))) {
+		printk(KERN_ERR "PM: Some devices failed to power down\n");
+		goto Done;
+	}
+
+	if (!suspend_test(TEST_CORE))
+		error = suspend_ops->enter(state);
+
+	device_power_up(PMSG_RESUME);
+ Done:
+	arch_suspend_enable_irqs();
+	BUG_ON(irqs_disabled());
+	device_pm_unlock();
+	return error;
+}
+
+/**
+ *	suspend_devices_and_enter - suspend devices and enter the desired system
+ *				    sleep state.
+ *	@state:		  state to enter
+ */
+int suspend_devices_and_enter(suspend_state_t state)
+{
+	int error, ftrace_save;
+
+	if (!suspend_ops)
+		return -ENOSYS;
+
+	if (suspend_ops->begin) {
+		error = suspend_ops->begin(state);
+		if (error)
+			goto Close;
+	}
+	suspend_console();
+	ftrace_save = __ftrace_enabled_save();
+	suspend_test_start();
+	error = device_suspend(PMSG_SUSPEND);
+	if (error) {
+		printk(KERN_ERR "PM: Some devices failed to suspend\n");
+		goto Recover_platform;
+	}
+	suspend_test_finish("suspend devices");
+	if (suspend_test(TEST_DEVICES))
+		goto Recover_platform;
+
+	if (suspend_ops->prepare) {
+		error = suspend_ops->prepare();
+		if (error)
+			goto Resume_devices;
+	}
+
+	if (suspend_test(TEST_PLATFORM))
+		goto Finish;
+
+	error = disable_nonboot_cpus();
+	if (!error && !suspend_test(TEST_CPUS))
+		suspend_enter(state);
+
+	enable_nonboot_cpus();
+ Finish:
+	if (suspend_ops->finish)
+		suspend_ops->finish();
+ Resume_devices:
+	suspend_test_start();
+	device_resume(PMSG_RESUME);
+	suspend_test_finish("resume devices");
+	__ftrace_enabled_restore(ftrace_save);
+	resume_console();
+ Close:
+	if (suspend_ops->end)
+		suspend_ops->end();
+	return error;
+
+ Recover_platform:
+	if (suspend_ops->recover)
+		suspend_ops->recover();
+	goto Resume_devices;
+}
+
+/**
+ *	suspend_finish - Do final work before exiting suspend sequence.
+ *
+ *	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(void)
+{
+	suspend_thaw_processes();
+	usermodehelper_enable();
+	pm_notifier_call_chain(PM_POST_SUSPEND);
+	pm_restore_console();
+}
+
+
+
+
+static const char * const pm_states[PM_SUSPEND_MAX] = {
+	[PM_SUSPEND_STANDBY]	= "standby",
+	[PM_SUSPEND_MEM]	= "mem",
+};
+
+static inline int valid_state(suspend_state_t state)
+{
+	/* All states need lowlevel support and need to be valid
+	 * to the lowlevel implementation, no valid callback
+	 * implies that none are valid. */
+	if (!suspend_ops || !suspend_ops->valid || !suspend_ops->valid(state))
+		return 0;
+	return 1;
+}
+
+
+/**
+ *	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;
+
+	printk(KERN_INFO "PM: Syncing filesystems ... ");
+	sys_sync();
+	printk("done.\n");
+
+	pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]);
+	error = suspend_prepare();
+	if (error)
+		goto Unlock;
+
+	if (suspend_test(TEST_FREEZER))
+		goto Finish;
+
+	pr_debug("PM: Entering %s sleep\n", pm_states[state]);
+	error = suspend_devices_and_enter(state);
+
+ Finish:
+	pr_debug("PM: Finishing wakeup.\n");
+	suspend_finish();
+ Unlock:
+	mutex_unlock(&pm_mutex);
+	return error;
+}
+
+
+/**
+ *	pm_suspend - Externally visible function for suspending system.
+ *	@state:		Enumerated 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);
+
+#endif /* CONFIG_SUSPEND */
+
+struct kobject *power_kobj;
+
+/**
+ *	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 kobject *kobj, struct kobj_attribute *attr,
+			  char *buf)
+{
+	char *s = buf;
+#ifdef CONFIG_SUSPEND
+	int i;
+
+	for (i = 0; i < PM_SUSPEND_MAX; i++) {
+		if (pm_states[i] && valid_state(i))
+			s += sprintf(s,"%s ", pm_states[i]);
+	}
+#endif
+#ifdef CONFIG_HIBERNATION
+	s += sprintf(s, "%s\n", "disk");
+#else
+	if (s != buf)
+		/* convert the last space to a newline */
+		*(s-1) = '\n';
+#endif
+	return (s - buf);
+}
+
+static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr,
+			   const char *buf, size_t n)
+{
+#ifdef CONFIG_SUSPEND
+	suspend_state_t state = PM_SUSPEND_STANDBY;
+	const char * const *s;
+#endif
+	char *p;
+	int len;
+	int error = -EINVAL;
+
+	p = memchr(buf, '\n', n);
+	len = p ? p - buf : n;
+
+	/* First, check if we are requested to hibernate */
+	if (len == 4 && !strncmp(buf, "disk", len)) {
+		error = hibernate();
+  goto Exit;
+	}
+
+#ifdef CONFIG_SUSPEND
+	for (s = &pm_states[state]; state < PM_SUSPEND_MAX; s++, state++) {
+		if (*s && len == strlen(*s) && !strncmp(buf, *s, len))
+			break;
+	}
+	if (state < PM_SUSPEND_MAX && *s)
+		error = enter_state(state);
+#endif
+
+ Exit:
+	return error ? error : n;
+}
+
+power_attr(state);
+
+#ifdef CONFIG_PM_TRACE
+int pm_trace_enabled;
+
+static ssize_t pm_trace_show(struct kobject *kobj, struct kobj_attribute *attr,
+			     char *buf)
+{
+	return sprintf(buf, "%d\n", pm_trace_enabled);
+}
+
+static ssize_t
+pm_trace_store(struct kobject *kobj, struct kobj_attribute *attr,
+	       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);
+#endif /* CONFIG_PM_TRACE */
+
+static struct attribute * g[] = {
+	&state_attr.attr,
+#ifdef CONFIG_PM_TRACE
+	&pm_trace_attr.attr,
+#endif
+#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_PM_DEBUG)
+	&pm_test_attr.attr,
+#endif
+	NULL,
+};
+
+static struct attribute_group attr_group = {
+	.attrs = g,
+};
+
+
+static int __init pm_init(void)
+{
+	power_kobj = kobject_create_and_add("power", NULL);
+	if (!power_kobj)
+		return -ENOMEM;
+	return sysfs_create_group(power_kobj, &attr_group);
+}
+
+core_initcall(pm_init);
+
+
+#ifdef CONFIG_PM_TEST_SUSPEND
+
+#include <linux/rtc.h>
+
+/*
+ * To test system suspend, we need a hands-off mechanism to resume the
+ * system.  RTCs wake alarms are a common self-contained mechanism.
+ */
+
+static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state)
+{
+	static char err_readtime[] __initdata =
+		KERN_ERR "PM: can't read %s time, err %d\n";
+	static char err_wakealarm [] __initdata =
+		KERN_ERR "PM: can't set %s wakealarm, err %d\n";
+	static char err_suspend[] __initdata =
+		KERN_ERR "PM: suspend test failed, error %d\n";
+	static char info_test[] __initdata =
+		KERN_INFO "PM: test RTC wakeup from '%s' suspend\n";
+
+	unsigned long		now;
+	struct rtc_wkalrm	alm;
+	int			status;
+
+	/* this may fail if the RTC hasn't been initialized */
+	status = rtc_read_time(rtc, &alm.time);
+	if (status < 0) {
+		printk(err_readtime, rtc->dev.bus_id, status);
+		return;
+	}
+	rtc_tm_to_time(&alm.time, &now);
+
+	memset(&alm, 0, sizeof alm);
+	rtc_time_to_tm(now + TEST_SUSPEND_SECONDS, &alm.time);
+	alm.enabled = true;
+
+	status = rtc_set_alarm(rtc, &alm);
+	if (status < 0) {
+		printk(err_wakealarm, rtc->dev.bus_id, status);
+		return;
+	}
+
+	if (state == PM_SUSPEND_MEM) {
+		printk(info_test, pm_states[state]);
+		status = pm_suspend(state);
+		if (status == -ENODEV)
+			state = PM_SUSPEND_STANDBY;
+	}
+	if (state == PM_SUSPEND_STANDBY) {
+		printk(info_test, pm_states[state]);
+		status = pm_suspend(state);
+	}
+	if (status < 0)
+		printk(err_suspend, status);
+
+	/* Some platforms can't detect that the alarm triggered the
+	 * wakeup, or (accordingly) disable it after it afterwards.
+	 * It's supposed to give oneshot behavior; cope.
+	 */
+	alm.enabled = false;
+	rtc_set_alarm(rtc, &alm);
+}
+
+static int __init has_wakealarm(struct device *dev, void *name_ptr)
+{
+	struct rtc_device *candidate = to_rtc_device(dev);
+
+	if (!candidate->ops->set_alarm)
+		return 0;
+	if (!device_may_wakeup(candidate->dev.parent))
+		return 0;
+
+	*(char **)name_ptr = dev->bus_id;
+	return 1;
+}
+
+/*
+ * Kernel options like "test_suspend=mem" force suspend/resume sanity tests
+ * at startup time.  They're normally disabled, for faster boot and because
+ * we can't know which states really work on this particular system.
+ */
+static suspend_state_t test_state __initdata = PM_SUSPEND_ON;
+
+static char warn_bad_state[] __initdata =
+	KERN_WARNING "PM: can't test '%s' suspend state\n";
+
+static int __init setup_test_suspend(char *value)
+{
+	unsigned i;
+
+	/* "=mem" ==> "mem" */
+	value++;
+	for (i = 0; i < PM_SUSPEND_MAX; i++) {
+		if (!pm_states[i])
+			continue;
+		if (strcmp(pm_states[i], value) != 0)
+			continue;
+		test_state = (__force suspend_state_t) i;
+		return 0;
+	}
+	printk(warn_bad_state, value);
+	return 0;
+}
+__setup("test_suspend", setup_test_suspend);
+
+static int __init test_suspend(void)
+{
+	static char		warn_no_rtc[] __initdata =
+		KERN_WARNING "PM: no wakealarm-capable RTC driver is ready\n";
+
+	char			*pony = NULL;
+	struct rtc_device	*rtc = NULL;
+
+	/* PM is initialized by now; is that state testable? */
+	if (test_state == PM_SUSPEND_ON)
+		goto done;
+	if (!valid_state(test_state)) {
+		printk(warn_bad_state, pm_states[test_state]);
+		goto done;
+	}
+
+	/* RTCs have initialized by now too ... can we use one? */
+	class_find_device(rtc_class, NULL, &pony, has_wakealarm);
+	if (pony)
+		rtc = rtc_class_open(pony);
+	if (!rtc) {
+		printk(warn_no_rtc);
+		goto done;
+	}
+
+	/* go for it */
+	test_wakealarm(rtc, test_state);
+	rtc_class_close(rtc);
+done:
+	return 0;
+}
+late_initcall(test_suspend);
+
+#endif /* CONFIG_PM_TEST_SUSPEND */
diff --git a/kernel/power/power.h b/kernel/power/power.h
new file mode 100644
index 0000000..46b5ec7
--- /dev/null
+++ b/kernel/power/power.h
@@ -0,0 +1,225 @@
+#include <linux/suspend.h>
+#include <linux/suspend_ioctls.h>
+#include <linux/utsname.h>
+#include <linux/freezer.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_HIBERNATION
+#ifdef CONFIG_ARCH_HIBERNATION_HEADER
+/* Maximum size of architecture specific data in a hibernation header */
+#define MAX_ARCH_HEADER_SIZE	(sizeof(struct new_utsname) + 4)
+
+extern int arch_hibernation_header_save(void *addr, unsigned int max_size);
+extern int arch_hibernation_header_restore(void *addr);
+
+static inline int init_header_complete(struct swsusp_info *info)
+{
+	return arch_hibernation_header_save(info, MAX_ARCH_HEADER_SIZE);
+}
+
+static inline char *check_image_kernel(struct swsusp_info *info)
+{
+	return arch_hibernation_header_restore(info) ?
+			"architecture specific data" : NULL;
+}
+#endif /* CONFIG_ARCH_HIBERNATION_HEADER */
+
+/*
+ * Keep some memory free so that I/O operations can succeed without paging
+ * [Might this be more than 4 MB?]
+ */
+#define PAGES_FOR_IO	((4096 * 1024) >> PAGE_SHIFT)
+
+/*
+ * Keep 1 MB of memory free so that device drivers can allocate some pages in
+ * their .suspend() routines without breaking the suspend to disk.
+ */
+#define SPARE_PAGES	((1024 * 1024) >> PAGE_SHIFT)
+
+/* kernel/power/disk.c */
+extern int hibernation_snapshot(int platform_mode);
+extern int hibernation_restore(int platform_mode);
+extern int hibernation_platform_enter(void);
+#endif
+
+extern int pfn_is_nosave(unsigned long);
+
+#define power_attr(_name) \
+static struct kobj_attribute _name##_attr = {	\
+	.attr	= {				\
+		.name = __stringify(_name),	\
+		.mode = 0644,			\
+	},					\
+	.show	= _name##_show,			\
+	.store	= _name##_store,		\
+}
+
+/* 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 int create_basic_memory_bitmaps(void);
+extern void free_basic_memory_bitmaps(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 unsigned long snapshot_get_image_size(void);
+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);
+
+/* If unset, the snapshot device cannot be open. */
+extern atomic_t snapshot_device_available;
+
+extern sector_t alloc_swapdev_block(int swap);
+extern void free_all_swap_pages(int swap);
+extern int swsusp_swap_in_use(void);
+
+/*
+ * Flags that can be passed from the hibernatig hernel to the "boot" kernel in
+ * the image header.
+ */
+#define SF_PLATFORM_MODE	1
+
+/* kernel/power/disk.c */
+extern int swsusp_check(void);
+extern int swsusp_shrink_memory(void);
+extern void swsusp_free(void);
+extern int swsusp_read(unsigned int *flags_p);
+extern int swsusp_write(unsigned int flags);
+extern void swsusp_close(fmode_t);
+
+struct timeval;
+/* kernel/power/swsusp.c */
+extern void swsusp_show_speed(struct timeval *, struct timeval *,
+				unsigned int, char *);
+
+#ifdef CONFIG_SUSPEND
+/* kernel/power/main.c */
+extern int suspend_devices_and_enter(suspend_state_t state);
+#else /* !CONFIG_SUSPEND */
+static inline int suspend_devices_and_enter(suspend_state_t state)
+{
+	return -ENOSYS;
+}
+#endif /* !CONFIG_SUSPEND */
+
+#ifdef CONFIG_PM_SLEEP
+/* kernel/power/main.c */
+extern int pm_notifier_call_chain(unsigned long val);
+#endif
+
+#ifdef CONFIG_HIGHMEM
+unsigned int count_highmem_pages(void);
+int restore_highmem(void);
+#else
+static inline unsigned int count_highmem_pages(void) { return 0; }
+static inline int restore_highmem(void) { return 0; }
+#endif
+
+/*
+ * Suspend test levels
+ */
+enum {
+	/* keep first */
+	TEST_NONE,
+	TEST_CORE,
+	TEST_CPUS,
+	TEST_PLATFORM,
+	TEST_DEVICES,
+	TEST_FREEZER,
+	/* keep last */
+	__TEST_AFTER_LAST
+};
+
+#define TEST_FIRST	TEST_NONE
+#define TEST_MAX	(__TEST_AFTER_LAST - 1)
+
+extern int pm_test_level;
+
+#ifdef CONFIG_SUSPEND_FREEZER
+static inline int suspend_freeze_processes(void)
+{
+	return freeze_processes();
+}
+
+static inline void suspend_thaw_processes(void)
+{
+	thaw_processes();
+}
+#else
+static inline int suspend_freeze_processes(void)
+{
+	return 0;
+}
+
+static inline void suspend_thaw_processes(void)
+{
+}
+#endif
diff --git a/kernel/power/poweroff.c b/kernel/power/poweroff.c
new file mode 100644
index 0000000..72016f0
--- /dev/null
+++ b/kernel/power/poweroff.c
@@ -0,0 +1,46 @@
+/*
+ * 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>
+#include <linux/cpumask.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)
+{
+	/* run sysrq poweroff on boot cpu */
+	schedule_work_on(first_cpu(cpu_online_map), &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);
diff --git a/kernel/power/process.c b/kernel/power/process.c
new file mode 100644
index 0000000..ca63401
--- /dev/null
+++ b/kernel/power/process.c
@@ -0,0 +1,154 @@
+/*
+ * drivers/power/process.c - Functions for starting/stopping processes on 
+ *                           suspend transitions.
+ *
+ * Originally from swsusp.
+ */
+
+
+#undef DEBUG
+
+#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)
+
+static inline int freezeable(struct task_struct * p)
+{
+	if ((p == current) ||
+	    (p->flags & PF_NOFREEZE) ||
+	    (p->exit_state != 0))
+		return 0;
+	return 1;
+}
+
+static int try_to_freeze_tasks(bool sig_only)
+{
+	struct task_struct *g, *p;
+	unsigned long end_time;
+	unsigned int todo;
+	struct timeval start, end;
+	u64 elapsed_csecs64;
+	unsigned int elapsed_csecs;
+
+	do_gettimeofday(&start);
+
+	end_time = jiffies + TIMEOUT;
+	do {
+		todo = 0;
+		read_lock(&tasklist_lock);
+		do_each_thread(g, p) {
+			if (frozen(p) || !freezeable(p))
+				continue;
+
+			if (!freeze_task(p, sig_only))
+				continue;
+
+			/*
+			 * Now that we've done set_freeze_flag, don't
+			 * perturb a task in TASK_STOPPED or TASK_TRACED.
+			 * It is "frozen enough".  If the task does wake
+			 * up, it will immediately call try_to_freeze.
+			 */
+			if (!task_is_stopped_or_traced(p) &&
+			    !freezer_should_skip(p))
+				todo++;
+		} while_each_thread(g, p);
+		read_unlock(&tasklist_lock);
+		yield();			/* Yield is okay here */
+		if (time_after(jiffies, end_time))
+			break;
+	} while (todo);
+
+	do_gettimeofday(&end);
+	elapsed_csecs64 = timeval_to_ns(&end) - timeval_to_ns(&start);
+	do_div(elapsed_csecs64, NSEC_PER_SEC / 100);
+	elapsed_csecs = elapsed_csecs64;
+
+	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 "Freezing of tasks failed after %d.%02d seconds "
+				"(%d tasks refusing to freeze):\n",
+				elapsed_csecs / 100, elapsed_csecs % 100, todo);
+		show_state();
+		read_lock(&tasklist_lock);
+		do_each_thread(g, p) {
+			task_lock(p);
+			if (freezing(p) && !freezer_should_skip(p))
+				printk(KERN_ERR " %s\n", p->comm);
+			cancel_freezing(p);
+			task_unlock(p);
+		} while_each_thread(g, p);
+		read_unlock(&tasklist_lock);
+	} else {
+		printk("(elapsed %d.%02d seconds) ", elapsed_csecs / 100,
+			elapsed_csecs % 100);
+	}
+
+	return todo ? -EBUSY : 0;
+}
+
+/**
+ *	freeze_processes - tell processes to enter the refrigerator
+ */
+int freeze_processes(void)
+{
+	int error;
+
+	printk("Freezing user space processes ... ");
+	error = try_to_freeze_tasks(true);
+	if (error)
+		goto Exit;
+	printk("done.\n");
+
+	printk("Freezing remaining freezable tasks ... ");
+	error = try_to_freeze_tasks(false);
+	if (error)
+		goto Exit;
+	printk("done.");
+ Exit:
+	BUG_ON(in_atomic());
+	printk("\n");
+	return error;
+}
+
+static void thaw_tasks(bool nosig_only)
+{
+	struct task_struct *g, *p;
+
+	read_lock(&tasklist_lock);
+	do_each_thread(g, p) {
+		if (!freezeable(p))
+			continue;
+
+		if (nosig_only && should_send_signal(p))
+			continue;
+
+		if (cgroup_frozen(p))
+			continue;
+
+		thaw_process(p);
+	} while_each_thread(g, p);
+	read_unlock(&tasklist_lock);
+}
+
+void thaw_processes(void)
+{
+	printk("Restarting tasks ... ");
+	thaw_tasks(true);
+	thaw_tasks(false);
+	schedule();
+	printk("done.\n");
+}
+
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
new file mode 100644
index 0000000..5d2ab83
--- /dev/null
+++ b/kernel/power/snapshot.c
@@ -0,0 +1,1974 @@
+/*
+ * linux/kernel/power/snapshot.c
+ *
+ * This file provides system snapshot/restore functionality for swsusp.
+ *
+ * Copyright (C) 1998-2005 Pavel Machek <pavel@suse.cz>
+ * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
+ *
+ * This file is released under the GPLv2.
+ *
+ */
+
+#include <linux/version.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/suspend.h>
+#include <linux/delay.h>
+#include <linux/bitops.h>
+#include <linux/spinlock.h>
+#include <linux/kernel.h>
+#include <linux/pm.h>
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/syscalls.h>
+#include <linux/console.h>
+#include <linux/highmem.h>
+
+#include <asm/uaccess.h>
+#include <asm/mmu_context.h>
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+#include <asm/io.h>
+
+#include "power.h"
+
+static int swsusp_page_is_free(struct page *);
+static void swsusp_set_page_forbidden(struct page *);
+static void swsusp_unset_page_forbidden(struct page *);
+
+/* List of PBEs needed for restoring the pages that were allocated before
+ * the suspend and included in the suspend image, but have also been
+ * allocated by the "resume" kernel, so their contents cannot be written
+ * directly to their "original" page frames.
+ */
+struct pbe *restore_pblist;
+
+/* Pointer to an auxiliary buffer (1 page) */
+static void *buffer;
+
+/**
+ *	@safe_needed - on resume, for storing the PBE list and the image,
+ *	we can only use memory pages that do not conflict with the pages
+ *	used before suspend.  The unsafe pages have PageNosaveFree set
+ *	and we count them using unsafe_pages.
+ *
+ *	Each allocated image page is marked as PageNosave and PageNosaveFree
+ *	so that swsusp_free() can release it.
+ */
+
+#define PG_ANY		0
+#define PG_SAFE		1
+#define PG_UNSAFE_CLEAR	1
+#define PG_UNSAFE_KEEP	0
+
+static unsigned int allocated_unsafe_pages;
+
+static void *get_image_page(gfp_t gfp_mask, int safe_needed)
+{
+	void *res;
+
+	res = (void *)get_zeroed_page(gfp_mask);
+	if (safe_needed)
+		while (res && swsusp_page_is_free(virt_to_page(res))) {
+			/* The page is unsafe, mark it for swsusp_free() */
+			swsusp_set_page_forbidden(virt_to_page(res));
+			allocated_unsafe_pages++;
+			res = (void *)get_zeroed_page(gfp_mask);
+		}
+	if (res) {
+		swsusp_set_page_forbidden(virt_to_page(res));
+		swsusp_set_page_free(virt_to_page(res));
+	}
+	return res;
+}
+
+unsigned long get_safe_page(gfp_t gfp_mask)
+{
+	return (unsigned long)get_image_page(gfp_mask, PG_SAFE);
+}
+
+static struct page *alloc_image_page(gfp_t gfp_mask)
+{
+	struct page *page;
+
+	page = alloc_page(gfp_mask);
+	if (page) {
+		swsusp_set_page_forbidden(page);
+		swsusp_set_page_free(page);
+	}
+	return page;
+}
+
+/**
+ *	free_image_page - free page represented by @addr, allocated with
+ *	get_image_page (page flags set by it must be cleared)
+ */
+
+static inline void free_image_page(void *addr, int clear_nosave_free)
+{
+	struct page *page;
+
+	BUG_ON(!virt_addr_valid(addr));
+
+	page = virt_to_page(addr);
+
+	swsusp_unset_page_forbidden(page);
+	if (clear_nosave_free)
+		swsusp_unset_page_free(page);
+
+	__free_page(page);
+}
+
+/* struct linked_page is used to build chains of pages */
+
+#define LINKED_PAGE_DATA_SIZE	(PAGE_SIZE - sizeof(void *))
+
+struct linked_page {
+	struct linked_page *next;
+	char data[LINKED_PAGE_DATA_SIZE];
+} __attribute__((packed));
+
+static inline void
+free_list_of_pages(struct linked_page *list, int clear_page_nosave)
+{
+	while (list) {
+		struct linked_page *lp = list->next;
+
+		free_image_page(list, clear_page_nosave);
+		list = lp;
+	}
+}
+
+/**
+  *	struct chain_allocator is used for allocating small objects out of
+  *	a linked list of pages called 'the chain'.
+  *
+  *	The chain grows each time when there is no room for a new object in
+  *	the current page.  The allocated objects cannot be freed individually.
+  *	It is only possible to free them all at once, by freeing the entire
+  *	chain.
+  *
+  *	NOTE: The chain allocator may be inefficient if the allocated objects
+  *	are not much smaller than PAGE_SIZE.
+  */
+
+struct chain_allocator {
+	struct linked_page *chain;	/* the chain */
+	unsigned int used_space;	/* total size of objects allocated out
+					 * of the current page
+					 */
+	gfp_t gfp_mask;		/* mask for allocating pages */
+	int safe_needed;	/* if set, only "safe" pages are allocated */
+};
+
+static void
+chain_init(struct chain_allocator *ca, gfp_t gfp_mask, int safe_needed)
+{
+	ca->chain = NULL;
+	ca->used_space = LINKED_PAGE_DATA_SIZE;
+	ca->gfp_mask = gfp_mask;
+	ca->safe_needed = safe_needed;
+}
+
+static void *chain_alloc(struct chain_allocator *ca, unsigned int size)
+{
+	void *ret;
+
+	if (LINKED_PAGE_DATA_SIZE - ca->used_space < size) {
+		struct linked_page *lp;
+
+		lp = get_image_page(ca->gfp_mask, ca->safe_needed);
+		if (!lp)
+			return NULL;
+
+		lp->next = ca->chain;
+		ca->chain = lp;
+		ca->used_space = 0;
+	}
+	ret = ca->chain->data + ca->used_space;
+	ca->used_space += size;
+	return ret;
+}
+
+static void chain_free(struct chain_allocator *ca, int clear_page_nosave)
+{
+	free_list_of_pages(ca->chain, clear_page_nosave);
+	memset(ca, 0, sizeof(struct chain_allocator));
+}
+
+/**
+ *	Data types related to memory bitmaps.
+ *
+ *	Memory bitmap is a structure consiting of many linked lists of
+ *	objects.  The main list's elements are of type struct zone_bitmap
+ *	and each of them corresonds to one zone.  For each zone bitmap
+ *	object there is a list of objects of type struct bm_block that
+ *	represent each blocks of bitmap in which information is stored.
+ *
+ *	struct memory_bitmap contains a pointer to the main list of zone
+ *	bitmap objects, a struct bm_position used for browsing the bitmap,
+ *	and a pointer to the list of pages used for allocating all of the
+ *	zone bitmap objects and bitmap block objects.
+ *
+ *	NOTE: It has to be possible to lay out the bitmap in memory
+ *	using only allocations of order 0.  Additionally, the bitmap is
+ *	designed to work with arbitrary number of zones (this is over the
+ *	top for now, but let's avoid making unnecessary assumptions ;-).
+ *
+ *	struct zone_bitmap contains a pointer to a list of bitmap block
+ *	objects and a pointer to the bitmap block object that has been
+ *	most recently used for setting bits.  Additionally, it contains the
+ *	pfns that correspond to the start and end of the represented zone.
+ *
+ *	struct bm_block contains a pointer to the memory page in which
+ *	information is stored (in the form of a block of bitmap)
+ *	It also contains the pfns that correspond to the start and end of
+ *	the represented memory area.
+ */
+
+#define BM_END_OF_MAP	(~0UL)
+
+#define BM_BITS_PER_BLOCK	(PAGE_SIZE << 3)
+
+struct bm_block {
+	struct bm_block *next;		/* next element of the list */
+	unsigned long start_pfn;	/* pfn represented by the first bit */
+	unsigned long end_pfn;	/* pfn represented by the last bit plus 1 */
+	unsigned long *data;	/* bitmap representing pages */
+};
+
+static inline unsigned long bm_block_bits(struct bm_block *bb)
+{
+	return bb->end_pfn - bb->start_pfn;
+}
+
+struct zone_bitmap {
+	struct zone_bitmap *next;	/* next element of the list */
+	unsigned long start_pfn;	/* minimal pfn in this zone */
+	unsigned long end_pfn;		/* maximal pfn in this zone plus 1 */
+	struct bm_block *bm_blocks;	/* list of bitmap blocks */
+	struct bm_block *cur_block;	/* recently used bitmap block */
+};
+
+/* strcut bm_position is used for browsing memory bitmaps */
+
+struct bm_position {
+	struct zone_bitmap *zone_bm;
+	struct bm_block *block;
+	int bit;
+};
+
+struct memory_bitmap {
+	struct zone_bitmap *zone_bm_list;	/* list of zone bitmaps */
+	struct linked_page *p_list;	/* list of pages used to store zone
+					 * bitmap objects and bitmap block
+					 * objects
+					 */
+	struct bm_position cur;	/* most recently used bit position */
+};
+
+/* Functions that operate on memory bitmaps */
+
+static void memory_bm_position_reset(struct memory_bitmap *bm)
+{
+	struct zone_bitmap *zone_bm;
+
+	zone_bm = bm->zone_bm_list;
+	bm->cur.zone_bm = zone_bm;
+	bm->cur.block = zone_bm->bm_blocks;
+	bm->cur.bit = 0;
+}
+
+static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free);
+
+/**
+ *	create_bm_block_list - create a list of block bitmap objects
+ */
+
+static inline struct bm_block *
+create_bm_block_list(unsigned int nr_blocks, struct chain_allocator *ca)
+{
+	struct bm_block *bblist = NULL;
+
+	while (nr_blocks-- > 0) {
+		struct bm_block *bb;
+
+		bb = chain_alloc(ca, sizeof(struct bm_block));
+		if (!bb)
+			return NULL;
+
+		bb->next = bblist;
+		bblist = bb;
+	}
+	return bblist;
+}
+
+/**
+ *	create_zone_bm_list - create a list of zone bitmap objects
+ */
+
+static inline struct zone_bitmap *
+create_zone_bm_list(unsigned int nr_zones, struct chain_allocator *ca)
+{
+	struct zone_bitmap *zbmlist = NULL;
+
+	while (nr_zones-- > 0) {
+		struct zone_bitmap *zbm;
+
+		zbm = chain_alloc(ca, sizeof(struct zone_bitmap));
+		if (!zbm)
+			return NULL;
+
+		zbm->next = zbmlist;
+		zbmlist = zbm;
+	}
+	return zbmlist;
+}
+
+/**
+  *	memory_bm_create - allocate memory for a memory bitmap
+  */
+
+static int
+memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed)
+{
+	struct chain_allocator ca;
+	struct zone *zone;
+	struct zone_bitmap *zone_bm;
+	struct bm_block *bb;
+	unsigned int nr;
+
+	chain_init(&ca, gfp_mask, safe_needed);
+
+	/* Compute the number of zones */
+	nr = 0;
+	for_each_zone(zone)
+		if (populated_zone(zone))
+			nr++;
+
+	/* Allocate the list of zones bitmap objects */
+	zone_bm = create_zone_bm_list(nr, &ca);
+	bm->zone_bm_list = zone_bm;
+	if (!zone_bm) {
+		chain_free(&ca, PG_UNSAFE_CLEAR);
+		return -ENOMEM;
+	}
+
+	/* Initialize the zone bitmap objects */
+	for_each_zone(zone) {
+		unsigned long pfn;
+
+		if (!populated_zone(zone))
+			continue;
+
+		zone_bm->start_pfn = zone->zone_start_pfn;
+		zone_bm->end_pfn = zone->zone_start_pfn + zone->spanned_pages;
+		/* Allocate the list of bitmap block objects */
+		nr = DIV_ROUND_UP(zone->spanned_pages, BM_BITS_PER_BLOCK);
+		bb = create_bm_block_list(nr, &ca);
+		zone_bm->bm_blocks = bb;
+		zone_bm->cur_block = bb;
+		if (!bb)
+			goto Free;
+
+		nr = zone->spanned_pages;
+		pfn = zone->zone_start_pfn;
+		/* Initialize the bitmap block objects */
+		while (bb) {
+			unsigned long *ptr;
+
+			ptr = get_image_page(gfp_mask, safe_needed);
+			bb->data = ptr;
+			if (!ptr)
+				goto Free;
+
+			bb->start_pfn = pfn;
+			if (nr >= BM_BITS_PER_BLOCK) {
+				pfn += BM_BITS_PER_BLOCK;
+				nr -= BM_BITS_PER_BLOCK;
+			} else {
+				/* This is executed only once in the loop */
+				pfn += nr;
+			}
+			bb->end_pfn = pfn;
+			bb = bb->next;
+		}
+		zone_bm = zone_bm->next;
+	}
+	bm->p_list = ca.chain;
+	memory_bm_position_reset(bm);
+	return 0;
+
+ Free:
+	bm->p_list = ca.chain;
+	memory_bm_free(bm, PG_UNSAFE_CLEAR);
+	return -ENOMEM;
+}
+
+/**
+  *	memory_bm_free - free memory occupied by the memory bitmap @bm
+  */
+
+static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free)
+{
+	struct zone_bitmap *zone_bm;
+
+	/* Free the list of bit blocks for each zone_bitmap object */
+	zone_bm = bm->zone_bm_list;
+	while (zone_bm) {
+		struct bm_block *bb;
+
+		bb = zone_bm->bm_blocks;
+		while (bb) {
+			if (bb->data)
+				free_image_page(bb->data, clear_nosave_free);
+			bb = bb->next;
+		}
+		zone_bm = zone_bm->next;
+	}
+	free_list_of_pages(bm->p_list, clear_nosave_free);
+	bm->zone_bm_list = NULL;
+}
+
+/**
+ *	memory_bm_find_bit - find the bit in the bitmap @bm that corresponds
+ *	to given pfn.  The cur_zone_bm member of @bm and the cur_block member
+ *	of @bm->cur_zone_bm are updated.
+ */
+
+static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
+				void **addr, unsigned int *bit_nr)
+{
+	struct zone_bitmap *zone_bm;
+	struct bm_block *bb;
+
+	/* Check if the pfn is from the current zone */
+	zone_bm = bm->cur.zone_bm;
+	if (pfn < zone_bm->start_pfn || pfn >= zone_bm->end_pfn) {
+		zone_bm = bm->zone_bm_list;
+		/* We don't assume that the zones are sorted by pfns */
+		while (pfn < zone_bm->start_pfn || pfn >= zone_bm->end_pfn) {
+			zone_bm = zone_bm->next;
+
+			if (!zone_bm)
+				return -EFAULT;
+		}
+		bm->cur.zone_bm = zone_bm;
+	}
+	/* Check if the pfn corresponds to the current bitmap block */
+	bb = zone_bm->cur_block;
+	if (pfn < bb->start_pfn)
+		bb = zone_bm->bm_blocks;
+
+	while (pfn >= bb->end_pfn) {
+		bb = bb->next;
+
+		BUG_ON(!bb);
+	}
+	zone_bm->cur_block = bb;
+	pfn -= bb->start_pfn;
+	*bit_nr = pfn;
+	*addr = bb->data;
+	return 0;
+}
+
+static void memory_bm_set_bit(struct memory_bitmap *bm, unsigned long pfn)
+{
+	void *addr;
+	unsigned int bit;
+	int error;
+
+	error = memory_bm_find_bit(bm, pfn, &addr, &bit);
+	BUG_ON(error);
+	set_bit(bit, addr);
+}
+
+static int mem_bm_set_bit_check(struct memory_bitmap *bm, unsigned long pfn)
+{
+	void *addr;
+	unsigned int bit;
+	int error;
+
+	error = memory_bm_find_bit(bm, pfn, &addr, &bit);
+	if (!error)
+		set_bit(bit, addr);
+	return error;
+}
+
+static void memory_bm_clear_bit(struct memory_bitmap *bm, unsigned long pfn)
+{
+	void *addr;
+	unsigned int bit;
+	int error;
+
+	error = memory_bm_find_bit(bm, pfn, &addr, &bit);
+	BUG_ON(error);
+	clear_bit(bit, addr);
+}
+
+static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn)
+{
+	void *addr;
+	unsigned int bit;
+	int error;
+
+	error = memory_bm_find_bit(bm, pfn, &addr, &bit);
+	BUG_ON(error);
+	return test_bit(bit, addr);
+}
+
+/**
+ *	memory_bm_next_pfn - find the pfn that corresponds to the next set bit
+ *	in the bitmap @bm.  If the pfn cannot be found, BM_END_OF_MAP is
+ *	returned.
+ *
+ *	It is required to run memory_bm_position_reset() before the first call to
+ *	this function.
+ */
+
+static unsigned long memory_bm_next_pfn(struct memory_bitmap *bm)
+{
+	struct zone_bitmap *zone_bm;
+	struct bm_block *bb;
+	int bit;
+
+	do {
+		bb = bm->cur.block;
+		do {
+			bit = bm->cur.bit;
+			bit = find_next_bit(bb->data, bm_block_bits(bb), bit);
+			if (bit < bm_block_bits(bb))
+				goto Return_pfn;
+
+			bb = bb->next;
+			bm->cur.block = bb;
+			bm->cur.bit = 0;
+		} while (bb);
+		zone_bm = bm->cur.zone_bm->next;
+		if (zone_bm) {
+			bm->cur.zone_bm = zone_bm;
+			bm->cur.block = zone_bm->bm_blocks;
+			bm->cur.bit = 0;
+		}
+	} while (zone_bm);
+	memory_bm_position_reset(bm);
+	return BM_END_OF_MAP;
+
+ Return_pfn:
+	bm->cur.bit = bit + 1;
+	return bb->start_pfn + bit;
+}
+
+/**
+ *	This structure represents a range of page frames the contents of which
+ *	should not be saved during the suspend.
+ */
+
+struct nosave_region {
+	struct list_head list;
+	unsigned long start_pfn;
+	unsigned long end_pfn;
+};
+
+static LIST_HEAD(nosave_regions);
+
+/**
+ *	register_nosave_region - register a range of page frames the contents
+ *	of which should not be saved during the suspend (to be used in the early
+ *	initialization code)
+ */
+
+void __init
+__register_nosave_region(unsigned long start_pfn, unsigned long end_pfn,
+			 int use_kmalloc)
+{
+	struct nosave_region *region;
+
+	if (start_pfn >= end_pfn)
+		return;
+
+	if (!list_empty(&nosave_regions)) {
+		/* Try to extend the previous region (they should be sorted) */
+		region = list_entry(nosave_regions.prev,
+					struct nosave_region, list);
+		if (region->end_pfn == start_pfn) {
+			region->end_pfn = end_pfn;
+			goto Report;
+		}
+	}
+	if (use_kmalloc) {
+		/* during init, this shouldn't fail */
+		region = kmalloc(sizeof(struct nosave_region), GFP_KERNEL);
+		BUG_ON(!region);
+	} else
+		/* This allocation cannot fail */
+		region = alloc_bootmem_low(sizeof(struct nosave_region));
+	region->start_pfn = start_pfn;
+	region->end_pfn = end_pfn;
+	list_add_tail(&region->list, &nosave_regions);
+ Report:
+	printk(KERN_INFO "PM: Registered nosave memory: %016lx - %016lx\n",
+		start_pfn << PAGE_SHIFT, end_pfn << PAGE_SHIFT);
+}
+
+/*
+ * Set bits in this map correspond to the page frames the contents of which
+ * should not be saved during the suspend.
+ */
+static struct memory_bitmap *forbidden_pages_map;
+
+/* Set bits in this map correspond to free page frames. */
+static struct memory_bitmap *free_pages_map;
+
+/*
+ * Each page frame allocated for creating the image is marked by setting the
+ * corresponding bits in forbidden_pages_map and free_pages_map simultaneously
+ */
+
+void swsusp_set_page_free(struct page *page)
+{
+	if (free_pages_map)
+		memory_bm_set_bit(free_pages_map, page_to_pfn(page));
+}
+
+static int swsusp_page_is_free(struct page *page)
+{
+	return free_pages_map ?
+		memory_bm_test_bit(free_pages_map, page_to_pfn(page)) : 0;
+}
+
+void swsusp_unset_page_free(struct page *page)
+{
+	if (free_pages_map)
+		memory_bm_clear_bit(free_pages_map, page_to_pfn(page));
+}
+
+static void swsusp_set_page_forbidden(struct page *page)
+{
+	if (forbidden_pages_map)
+		memory_bm_set_bit(forbidden_pages_map, page_to_pfn(page));
+}
+
+int swsusp_page_is_forbidden(struct page *page)
+{
+	return forbidden_pages_map ?
+		memory_bm_test_bit(forbidden_pages_map, page_to_pfn(page)) : 0;
+}
+
+static void swsusp_unset_page_forbidden(struct page *page)
+{
+	if (forbidden_pages_map)
+		memory_bm_clear_bit(forbidden_pages_map, page_to_pfn(page));
+}
+
+/**
+ *	mark_nosave_pages - set bits corresponding to the page frames the
+ *	contents of which should not be saved in a given bitmap.
+ */
+
+static void mark_nosave_pages(struct memory_bitmap *bm)
+{
+	struct nosave_region *region;
+
+	if (list_empty(&nosave_regions))
+		return;
+
+	list_for_each_entry(region, &nosave_regions, list) {
+		unsigned long pfn;
+
+		pr_debug("PM: Marking nosave pages: %016lx - %016lx\n",
+				region->start_pfn << PAGE_SHIFT,
+				region->end_pfn << PAGE_SHIFT);
+
+		for (pfn = region->start_pfn; pfn < region->end_pfn; pfn++)
+			if (pfn_valid(pfn)) {
+				/*
+				 * It is safe to ignore the result of
+				 * mem_bm_set_bit_check() here, since we won't
+				 * touch the PFNs for which the error is
+				 * returned anyway.
+				 */
+				mem_bm_set_bit_check(bm, pfn);
+			}
+	}
+}
+
+/**
+ *	create_basic_memory_bitmaps - create bitmaps needed for marking page
+ *	frames that should not be saved and free page frames.  The pointers
+ *	forbidden_pages_map and free_pages_map are only modified if everything
+ *	goes well, because we don't want the bits to be used before both bitmaps
+ *	are set up.
+ */
+
+int create_basic_memory_bitmaps(void)
+{
+	struct memory_bitmap *bm1, *bm2;
+	int error = 0;
+
+	BUG_ON(forbidden_pages_map || free_pages_map);
+
+	bm1 = kzalloc(sizeof(struct memory_bitmap), GFP_KERNEL);
+	if (!bm1)
+		return -ENOMEM;
+
+	error = memory_bm_create(bm1, GFP_KERNEL, PG_ANY);
+	if (error)
+		goto Free_first_object;
+
+	bm2 = kzalloc(sizeof(struct memory_bitmap), GFP_KERNEL);
+	if (!bm2)
+		goto Free_first_bitmap;
+
+	error = memory_bm_create(bm2, GFP_KERNEL, PG_ANY);
+	if (error)
+		goto Free_second_object;
+
+	forbidden_pages_map = bm1;
+	free_pages_map = bm2;
+	mark_nosave_pages(forbidden_pages_map);
+
+	pr_debug("PM: Basic memory bitmaps created\n");
+
+	return 0;
+
+ Free_second_object:
+	kfree(bm2);
+ Free_first_bitmap:
+ 	memory_bm_free(bm1, PG_UNSAFE_CLEAR);
+ Free_first_object:
+	kfree(bm1);
+	return -ENOMEM;
+}
+
+/**
+ *	free_basic_memory_bitmaps - free memory bitmaps allocated by
+ *	create_basic_memory_bitmaps().  The auxiliary pointers are necessary
+ *	so that the bitmaps themselves are not referred to while they are being
+ *	freed.
+ */
+
+void free_basic_memory_bitmaps(void)
+{
+	struct memory_bitmap *bm1, *bm2;
+
+	BUG_ON(!(forbidden_pages_map && free_pages_map));
+
+	bm1 = forbidden_pages_map;
+	bm2 = free_pages_map;
+	forbidden_pages_map = NULL;
+	free_pages_map = NULL;
+	memory_bm_free(bm1, PG_UNSAFE_CLEAR);
+	kfree(bm1);
+	memory_bm_free(bm2, PG_UNSAFE_CLEAR);
+	kfree(bm2);
+
+	pr_debug("PM: Basic memory bitmaps freed\n");
+}
+
+/**
+ *	snapshot_additional_pages - estimate the number of additional pages
+ *	be needed for setting up the suspend image data structures for given
+ *	zone (usually the returned value is greater than the exact number)
+ */
+
+unsigned int snapshot_additional_pages(struct zone *zone)
+{
+	unsigned int res;
+
+	res = DIV_ROUND_UP(zone->spanned_pages, BM_BITS_PER_BLOCK);
+	res += DIV_ROUND_UP(res * sizeof(struct bm_block), PAGE_SIZE);
+	return 2 * res;
+}
+
+#ifdef CONFIG_HIGHMEM
+/**
+ *	count_free_highmem_pages - compute the total number of free highmem
+ *	pages, system-wide.
+ */
+
+static unsigned int count_free_highmem_pages(void)
+{
+	struct zone *zone;
+	unsigned int cnt = 0;
+
+	for_each_zone(zone)
+		if (populated_zone(zone) && is_highmem(zone))
+			cnt += zone_page_state(zone, NR_FREE_PAGES);
+
+	return cnt;
+}
+
+/**
+ *	saveable_highmem_page - Determine whether a highmem page should be
+ *	included in the suspend image.
+ *
+ *	We should save the page if it isn't Nosave or NosaveFree, or Reserved,
+ *	and it isn't a part of a free chunk of pages.
+ */
+
+static struct page *saveable_highmem_page(unsigned long pfn)
+{
+	struct page *page;
+
+	if (!pfn_valid(pfn))
+		return NULL;
+
+	page = pfn_to_page(pfn);
+
+	BUG_ON(!PageHighMem(page));
+
+	if (swsusp_page_is_forbidden(page) ||  swsusp_page_is_free(page) ||
+	    PageReserved(page))
+		return NULL;
+
+	return page;
+}
+
+/**
+ *	count_highmem_pages - compute the total number of saveable highmem
+ *	pages.
+ */
+
+unsigned int count_highmem_pages(void)
+{
+	struct zone *zone;
+	unsigned int n = 0;
+
+	for_each_zone(zone) {
+		unsigned long pfn, max_zone_pfn;
+
+		if (!is_highmem(zone))
+			continue;
+
+		mark_free_pages(zone);
+		max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
+		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
+			if (saveable_highmem_page(pfn))
+				n++;
+	}
+	return n;
+}
+#else
+static inline void *saveable_highmem_page(unsigned long pfn) { return NULL; }
+#endif /* CONFIG_HIGHMEM */
+
+/**
+ *	saveable_page - Determine whether a non-highmem page should be included
+ *	in the suspend image.
+ *
+ *	We should save the page if it isn't Nosave, and is not in the range
+ *	of pages statically defined as 'unsaveable', and it isn't a part of
+ *	a free chunk of pages.
+ */
+
+static struct page *saveable_page(unsigned long pfn)
+{
+	struct page *page;
+
+	if (!pfn_valid(pfn))
+		return NULL;
+
+	page = pfn_to_page(pfn);
+
+	BUG_ON(PageHighMem(page));
+
+	if (swsusp_page_is_forbidden(page) || swsusp_page_is_free(page))
+		return NULL;
+
+	if (PageReserved(page)
+	    && (!kernel_page_present(page) || pfn_is_nosave(pfn)))
+		return NULL;
+
+	return page;
+}
+
+/**
+ *	count_data_pages - compute the total number of saveable non-highmem
+ *	pages.
+ */
+
+unsigned int count_data_pages(void)
+{
+	struct zone *zone;
+	unsigned long pfn, max_zone_pfn;
+	unsigned int n = 0;
+
+	for_each_zone(zone) {
+		if (is_highmem(zone))
+			continue;
+
+		mark_free_pages(zone);
+		max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
+		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
+			if(saveable_page(pfn))
+				n++;
+	}
+	return n;
+}
+
+/* This is needed, because copy_page and memcpy are not usable for copying
+ * task structs.
+ */
+static inline void do_copy_page(long *dst, long *src)
+{
+	int n;
+
+	for (n = PAGE_SIZE / sizeof(long); n; n--)
+		*dst++ = *src++;
+}
+
+
+/**
+ *	safe_copy_page - check if the page we are going to copy is marked as
+ *		present in the kernel page tables (this always is the case if
+ *		CONFIG_DEBUG_PAGEALLOC is not set and in that case
+ *		kernel_page_present() always returns 'true').
+ */
+static void safe_copy_page(void *dst, struct page *s_page)
+{
+	if (kernel_page_present(s_page)) {
+		do_copy_page(dst, page_address(s_page));
+	} else {
+		kernel_map_pages(s_page, 1, 1);
+		do_copy_page(dst, page_address(s_page));
+		kernel_map_pages(s_page, 1, 0);
+	}
+}
+
+
+#ifdef CONFIG_HIGHMEM
+static inline struct page *
+page_is_saveable(struct zone *zone, unsigned long pfn)
+{
+	return is_highmem(zone) ?
+			saveable_highmem_page(pfn) : saveable_page(pfn);
+}
+
+static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
+{
+	struct page *s_page, *d_page;
+	void *src, *dst;
+
+	s_page = pfn_to_page(src_pfn);
+	d_page = pfn_to_page(dst_pfn);
+	if (PageHighMem(s_page)) {
+		src = kmap_atomic(s_page, KM_USER0);
+		dst = kmap_atomic(d_page, KM_USER1);
+		do_copy_page(dst, src);
+		kunmap_atomic(src, KM_USER0);
+		kunmap_atomic(dst, KM_USER1);
+	} else {
+		if (PageHighMem(d_page)) {
+			/* Page pointed to by src may contain some kernel
+			 * data modified by kmap_atomic()
+			 */
+			safe_copy_page(buffer, s_page);
+			dst = kmap_atomic(pfn_to_page(dst_pfn), KM_USER0);
+			memcpy(dst, buffer, PAGE_SIZE);
+			kunmap_atomic(dst, KM_USER0);
+		} else {
+			safe_copy_page(page_address(d_page), s_page);
+		}
+	}
+}
+#else
+#define page_is_saveable(zone, pfn)	saveable_page(pfn)
+
+static inline void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
+{
+	safe_copy_page(page_address(pfn_to_page(dst_pfn)),
+				pfn_to_page(src_pfn));
+}
+#endif /* CONFIG_HIGHMEM */
+
+static void
+copy_data_pages(struct memory_bitmap *copy_bm, struct memory_bitmap *orig_bm)
+{
+	struct zone *zone;
+	unsigned long pfn;
+
+	for_each_zone(zone) {
+		unsigned long max_zone_pfn;
+
+		mark_free_pages(zone);
+		max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
+		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
+			if (page_is_saveable(zone, pfn))
+				memory_bm_set_bit(orig_bm, pfn);
+	}
+	memory_bm_position_reset(orig_bm);
+	memory_bm_position_reset(copy_bm);
+	for(;;) {
+		pfn = memory_bm_next_pfn(orig_bm);
+		if (unlikely(pfn == BM_END_OF_MAP))
+			break;
+		copy_data_page(memory_bm_next_pfn(copy_bm), pfn);
+	}
+}
+
+/* Total number of image pages */
+static unsigned int nr_copy_pages;
+/* Number of pages needed for saving the original pfns of the image pages */
+static unsigned int nr_meta_pages;
+
+/**
+ *	swsusp_free - free pages allocated for the suspend.
+ *
+ *	Suspend pages are alocated before the atomic copy is made, so we
+ *	need to release them after the resume.
+ */
+
+void swsusp_free(void)
+{
+	struct zone *zone;
+	unsigned long pfn, max_zone_pfn;
+
+	for_each_zone(zone) {
+		max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
+		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
+			if (pfn_valid(pfn)) {
+				struct page *page = pfn_to_page(pfn);
+
+				if (swsusp_page_is_forbidden(page) &&
+				    swsusp_page_is_free(page)) {
+					swsusp_unset_page_forbidden(page);
+					swsusp_unset_page_free(page);
+					__free_page(page);
+				}
+			}
+	}
+	nr_copy_pages = 0;
+	nr_meta_pages = 0;
+	restore_pblist = NULL;
+	buffer = NULL;
+}
+
+#ifdef CONFIG_HIGHMEM
+/**
+  *	count_pages_for_highmem - compute the number of non-highmem pages
+  *	that will be necessary for creating copies of highmem pages.
+  */
+
+static unsigned int count_pages_for_highmem(unsigned int nr_highmem)
+{
+	unsigned int free_highmem = count_free_highmem_pages();
+
+	if (free_highmem >= nr_highmem)
+		nr_highmem = 0;
+	else
+		nr_highmem -= free_highmem;
+
+	return nr_highmem;
+}
+#else
+static unsigned int
+count_pages_for_highmem(unsigned int nr_highmem) { return 0; }
+#endif /* CONFIG_HIGHMEM */
+
+/**
+ *	enough_free_mem - Make sure we have enough free memory for the
+ *	snapshot image.
+ */
+
+static int enough_free_mem(unsigned int nr_pages, unsigned int nr_highmem)
+{
+	struct zone *zone;
+	unsigned int free = 0, meta = 0;
+
+	for_each_zone(zone) {
+		meta += snapshot_additional_pages(zone);
+		if (!is_highmem(zone))
+			free += zone_page_state(zone, NR_FREE_PAGES);
+	}
+
+	nr_pages += count_pages_for_highmem(nr_highmem);
+	pr_debug("PM: Normal pages needed: %u + %u + %u, available pages: %u\n",
+		nr_pages, PAGES_FOR_IO, meta, free);
+
+	return free > nr_pages + PAGES_FOR_IO + meta;
+}
+
+#ifdef CONFIG_HIGHMEM
+/**
+ *	get_highmem_buffer - if there are some highmem pages in the suspend
+ *	image, we may need the buffer to copy them and/or load their data.
+ */
+
+static inline int get_highmem_buffer(int safe_needed)
+{
+	buffer = get_image_page(GFP_ATOMIC | __GFP_COLD, safe_needed);
+	return buffer ? 0 : -ENOMEM;
+}
+
+/**
+ *	alloc_highmem_image_pages - allocate some highmem pages for the image.
+ *	Try to allocate as many pages as needed, but if the number of free
+ *	highmem pages is lesser than that, allocate them all.
+ */
+
+static inline unsigned int
+alloc_highmem_image_pages(struct memory_bitmap *bm, unsigned int nr_highmem)
+{
+	unsigned int to_alloc = count_free_highmem_pages();
+
+	if (to_alloc > nr_highmem)
+		to_alloc = nr_highmem;
+
+	nr_highmem -= to_alloc;
+	while (to_alloc-- > 0) {
+		struct page *page;
+
+		page = alloc_image_page(__GFP_HIGHMEM);
+		memory_bm_set_bit(bm, page_to_pfn(page));
+	}
+	return nr_highmem;
+}
+#else
+static inline int get_highmem_buffer(int safe_needed) { return 0; }
+
+static inline unsigned int
+alloc_highmem_image_pages(struct memory_bitmap *bm, unsigned int n) { return 0; }
+#endif /* CONFIG_HIGHMEM */
+
+/**
+ *	swsusp_alloc - allocate memory for the suspend image
+ *
+ *	We first try to allocate as many highmem pages as there are
+ *	saveable highmem pages in the system.  If that fails, we allocate
+ *	non-highmem pages for the copies of the remaining highmem ones.
+ *
+ *	In this approach it is likely that the copies of highmem pages will
+ *	also be located in the high memory, because of the way in which
+ *	copy_data_pages() works.
+ */
+
+static int
+swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm,
+		unsigned int nr_pages, unsigned int nr_highmem)
+{
+	int error;
+
+	error = memory_bm_create(orig_bm, GFP_ATOMIC | __GFP_COLD, PG_ANY);
+	if (error)
+		goto Free;
+
+	error = memory_bm_create(copy_bm, GFP_ATOMIC | __GFP_COLD, PG_ANY);
+	if (error)
+		goto Free;
+
+	if (nr_highmem > 0) {
+		error = get_highmem_buffer(PG_ANY);
+		if (error)
+			goto Free;
+
+		nr_pages += alloc_highmem_image_pages(copy_bm, nr_highmem);
+	}
+	while (nr_pages-- > 0) {
+		struct page *page = alloc_image_page(GFP_ATOMIC | __GFP_COLD);
+
+		if (!page)
+			goto Free;
+
+		memory_bm_set_bit(copy_bm, page_to_pfn(page));
+	}
+	return 0;
+
+ Free:
+	swsusp_free();
+	return -ENOMEM;
+}
+
+/* Memory bitmap used for marking saveable pages (during suspend) or the
+ * suspend image pages (during resume)
+ */
+static struct memory_bitmap orig_bm;
+/* Memory bitmap used on suspend for marking allocated pages that will contain
+ * the copies of saveable pages.  During resume it is initially used for
+ * marking the suspend image pages, but then its set bits are duplicated in
+ * @orig_bm and it is released.  Next, on systems with high memory, it may be
+ * used for marking "safe" highmem pages, but it has to be reinitialized for
+ * this purpose.
+ */
+static struct memory_bitmap copy_bm;
+
+asmlinkage int swsusp_save(void)
+{
+	unsigned int nr_pages, nr_highmem;
+
+	printk(KERN_INFO "PM: Creating hibernation image: \n");
+
+	drain_local_pages(NULL);
+	nr_pages = count_data_pages();
+	nr_highmem = count_highmem_pages();
+	printk(KERN_INFO "PM: Need to copy %u pages\n", nr_pages + nr_highmem);
+
+	if (!enough_free_mem(nr_pages, nr_highmem)) {
+		printk(KERN_ERR "PM: Not enough free memory\n");
+		return -ENOMEM;
+	}
+
+	if (swsusp_alloc(&orig_bm, &copy_bm, nr_pages, nr_highmem)) {
+		printk(KERN_ERR "PM: Memory allocation failed\n");
+		return -ENOMEM;
+	}
+
+	/* During allocating of suspend pagedir, new cold pages may appear.
+	 * Kill them.
+	 */
+	drain_local_pages(NULL);
+	copy_data_pages(&copy_bm, &orig_bm);
+
+	/*
+	 * End of critical section. From now on, we can write to memory,
+	 * but we should not touch disk. This specially means we must _not_
+	 * touch swap space! Except we must write out our image of course.
+	 */
+
+	nr_pages += nr_highmem;
+	nr_copy_pages = nr_pages;
+	nr_meta_pages = DIV_ROUND_UP(nr_pages * sizeof(long), PAGE_SIZE);
+
+	printk(KERN_INFO "PM: Hibernation image created (%d pages copied)\n",
+		nr_pages);
+
+	return 0;
+}
+
+#ifndef CONFIG_ARCH_HIBERNATION_HEADER
+static int init_header_complete(struct swsusp_info *info)
+{
+	memcpy(&info->uts, init_utsname(), sizeof(struct new_utsname));
+	info->version_code = LINUX_VERSION_CODE;
+	return 0;
+}
+
+static char *check_image_kernel(struct swsusp_info *info)
+{
+	if (info->version_code != LINUX_VERSION_CODE)
+		return "kernel version";
+	if (strcmp(info->uts.sysname,init_utsname()->sysname))
+		return "system type";
+	if (strcmp(info->uts.release,init_utsname()->release))
+		return "kernel release";
+	if (strcmp(info->uts.version,init_utsname()->version))
+		return "version";
+	if (strcmp(info->uts.machine,init_utsname()->machine))
+		return "machine";
+	return NULL;
+}
+#endif /* CONFIG_ARCH_HIBERNATION_HEADER */
+
+unsigned long snapshot_get_image_size(void)
+{
+	return nr_copy_pages + nr_meta_pages + 1;
+}
+
+static int init_header(struct swsusp_info *info)
+{
+	memset(info, 0, sizeof(struct swsusp_info));
+	info->num_physpages = num_physpages;
+	info->image_pages = nr_copy_pages;
+	info->pages = snapshot_get_image_size();
+	info->size = info->pages;
+	info->size <<= PAGE_SHIFT;
+	return init_header_complete(info);
+}
+
+/**
+ *	pack_pfns - pfns corresponding to the set bits found in the bitmap @bm
+ *	are stored in the array @buf[] (1 page at a time)
+ */
+
+static inline void
+pack_pfns(unsigned long *buf, struct memory_bitmap *bm)
+{
+	int j;
+
+	for (j = 0; j < PAGE_SIZE / sizeof(long); j++) {
+		buf[j] = memory_bm_next_pfn(bm);
+		if (unlikely(buf[j] == BM_END_OF_MAP))
+			break;
+	}
+}
+
+/**
+ *	snapshot_read_next - used for reading the system memory snapshot.
+ *
+ *	On the first call to it @handle should point to a zeroed
+ *	snapshot_handle structure.  The structure gets updated and a pointer
+ *	to it should be passed to this function every next time.
+ *
+ *	The @count parameter should contain the number of bytes the caller
+ *	wants to read from the snapshot.  It must not be zero.
+ *
+ *	On success the function returns a positive number.  Then, the caller
+ *	is allowed to read up to the returned number of bytes from the memory
+ *	location computed by the data_of() macro.  The number returned
+ *	may be smaller than @count, but this only happens if the read would
+ *	cross a page boundary otherwise.
+ *
+ *	The function returns 0 to indicate the end of data stream condition,
+ *	and a negative number is returned on error.  In such cases the
+ *	structure pointed to by @handle is not updated and should not be used
+ *	any more.
+ */
+
+int snapshot_read_next(struct snapshot_handle *handle, size_t count)
+{
+	if (handle->cur > nr_meta_pages + nr_copy_pages)
+		return 0;
+
+	if (!buffer) {
+		/* This makes the buffer be freed by swsusp_free() */
+		buffer = get_image_page(GFP_ATOMIC, PG_ANY);
+		if (!buffer)
+			return -ENOMEM;
+	}
+	if (!handle->offset) {
+		int error;
+
+		error = init_header((struct swsusp_info *)buffer);
+		if (error)
+			return error;
+		handle->buffer = buffer;
+		memory_bm_position_reset(&orig_bm);
+		memory_bm_position_reset(&copy_bm);
+	}
+	if (handle->prev < handle->cur) {
+		if (handle->cur <= nr_meta_pages) {
+			memset(buffer, 0, PAGE_SIZE);
+			pack_pfns(buffer, &orig_bm);
+		} else {
+			struct page *page;
+
+			page = pfn_to_page(memory_bm_next_pfn(&copy_bm));
+			if (PageHighMem(page)) {
+				/* Highmem pages are copied to the buffer,
+				 * because we can't return with a kmapped
+				 * highmem page (we may not be called again).
+				 */
+				void *kaddr;
+
+				kaddr = kmap_atomic(page, KM_USER0);
+				memcpy(buffer, kaddr, PAGE_SIZE);
+				kunmap_atomic(kaddr, KM_USER0);
+				handle->buffer = buffer;
+			} else {
+				handle->buffer = page_address(page);
+			}
+		}
+		handle->prev = handle->cur;
+	}
+	handle->buf_offset = handle->cur_offset;
+	if (handle->cur_offset + count >= PAGE_SIZE) {
+		count = PAGE_SIZE - handle->cur_offset;
+		handle->cur_offset = 0;
+		handle->cur++;
+	} else {
+		handle->cur_offset += count;
+	}
+	handle->offset += count;
+	return count;
+}
+
+/**
+ *	mark_unsafe_pages - mark the pages that cannot be used for storing
+ *	the image during resume, because they conflict with the pages that
+ *	had been used before suspend
+ */
+
+static int mark_unsafe_pages(struct memory_bitmap *bm)
+{
+	struct zone *zone;
+	unsigned long pfn, max_zone_pfn;
+
+	/* Clear page flags */
+	for_each_zone(zone) {
+		max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
+		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
+			if (pfn_valid(pfn))
+				swsusp_unset_page_free(pfn_to_page(pfn));
+	}
+
+	/* Mark pages that correspond to the "original" pfns as "unsafe" */
+	memory_bm_position_reset(bm);
+	do {
+		pfn = memory_bm_next_pfn(bm);
+		if (likely(pfn != BM_END_OF_MAP)) {
+			if (likely(pfn_valid(pfn)))
+				swsusp_set_page_free(pfn_to_page(pfn));
+			else
+				return -EFAULT;
+		}
+	} while (pfn != BM_END_OF_MAP);
+
+	allocated_unsafe_pages = 0;
+
+	return 0;
+}
+
+static void
+duplicate_memory_bitmap(struct memory_bitmap *dst, struct memory_bitmap *src)
+{
+	unsigned long pfn;
+
+	memory_bm_position_reset(src);
+	pfn = memory_bm_next_pfn(src);
+	while (pfn != BM_END_OF_MAP) {
+		memory_bm_set_bit(dst, pfn);
+		pfn = memory_bm_next_pfn(src);
+	}
+}
+
+static int check_header(struct swsusp_info *info)
+{
+	char *reason;
+
+	reason = check_image_kernel(info);
+	if (!reason && info->num_physpages != num_physpages)
+		reason = "memory size";
+	if (reason) {
+		printk(KERN_ERR "PM: Image mismatch: %s\n", reason);
+		return -EPERM;
+	}
+	return 0;
+}
+
+/**
+ *	load header - check the image header and copy data from it
+ */
+
+static int
+load_header(struct swsusp_info *info)
+{
+	int error;
+
+	restore_pblist = NULL;
+	error = check_header(info);
+	if (!error) {
+		nr_copy_pages = info->image_pages;
+		nr_meta_pages = info->pages - info->image_pages - 1;
+	}
+	return error;
+}
+
+/**
+ *	unpack_orig_pfns - for each element of @buf[] (1 page at a time) set
+ *	the corresponding bit in the memory bitmap @bm
+ */
+
+static inline void
+unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm)
+{
+	int j;
+
+	for (j = 0; j < PAGE_SIZE / sizeof(long); j++) {
+		if (unlikely(buf[j] == BM_END_OF_MAP))
+			break;
+
+		memory_bm_set_bit(bm, buf[j]);
+	}
+}
+
+/* List of "safe" pages that may be used to store data loaded from the suspend
+ * image
+ */
+static struct linked_page *safe_pages_list;
+
+#ifdef CONFIG_HIGHMEM
+/* struct highmem_pbe is used for creating the list of highmem pages that
+ * should be restored atomically during the resume from disk, because the page
+ * frames they have occupied before the suspend are in use.
+ */
+struct highmem_pbe {
+	struct page *copy_page;	/* data is here now */
+	struct page *orig_page;	/* data was here before the suspend */
+	struct highmem_pbe *next;
+};
+
+/* List of highmem PBEs needed for restoring the highmem pages that were
+ * allocated before the suspend and included in the suspend image, but have
+ * also been allocated by the "resume" kernel, so their contents cannot be
+ * written directly to their "original" page frames.
+ */
+static struct highmem_pbe *highmem_pblist;
+
+/**
+ *	count_highmem_image_pages - compute the number of highmem pages in the
+ *	suspend image.  The bits in the memory bitmap @bm that correspond to the
+ *	image pages are assumed to be set.
+ */
+
+static unsigned int count_highmem_image_pages(struct memory_bitmap *bm)
+{
+	unsigned long pfn;
+	unsigned int cnt = 0;
+
+	memory_bm_position_reset(bm);
+	pfn = memory_bm_next_pfn(bm);
+	while (pfn != BM_END_OF_MAP) {
+		if (PageHighMem(pfn_to_page(pfn)))
+			cnt++;
+
+		pfn = memory_bm_next_pfn(bm);
+	}
+	return cnt;
+}
+
+/**
+ *	prepare_highmem_image - try to allocate as many highmem pages as
+ *	there are highmem image pages (@nr_highmem_p points to the variable
+ *	containing the number of highmem image pages).  The pages that are
+ *	"safe" (ie. will not be overwritten when the suspend image is
+ *	restored) have the corresponding bits set in @bm (it must be
+ *	unitialized).
+ *
+ *	NOTE: This function should not be called if there are no highmem
+ *	image pages.
+ */
+
+static unsigned int safe_highmem_pages;
+
+static struct memory_bitmap *safe_highmem_bm;
+
+static int
+prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p)
+{
+	unsigned int to_alloc;
+
+	if (memory_bm_create(bm, GFP_ATOMIC, PG_SAFE))
+		return -ENOMEM;
+
+	if (get_highmem_buffer(PG_SAFE))
+		return -ENOMEM;
+
+	to_alloc = count_free_highmem_pages();
+	if (to_alloc > *nr_highmem_p)
+		to_alloc = *nr_highmem_p;
+	else
+		*nr_highmem_p = to_alloc;
+
+	safe_highmem_pages = 0;
+	while (to_alloc-- > 0) {
+		struct page *page;
+
+		page = alloc_page(__GFP_HIGHMEM);
+		if (!swsusp_page_is_free(page)) {
+			/* The page is "safe", set its bit the bitmap */
+			memory_bm_set_bit(bm, page_to_pfn(page));
+			safe_highmem_pages++;
+		}
+		/* Mark the page as allocated */
+		swsusp_set_page_forbidden(page);
+		swsusp_set_page_free(page);
+	}
+	memory_bm_position_reset(bm);
+	safe_highmem_bm = bm;
+	return 0;
+}
+
+/**
+ *	get_highmem_page_buffer - for given highmem image page find the buffer
+ *	that suspend_write_next() should set for its caller to write to.
+ *
+ *	If the page is to be saved to its "original" page frame or a copy of
+ *	the page is to be made in the highmem, @buffer is returned.  Otherwise,
+ *	the copy of the page is to be made in normal memory, so the address of
+ *	the copy is returned.
+ *
+ *	If @buffer is returned, the caller of suspend_write_next() will write
+ *	the page's contents to @buffer, so they will have to be copied to the
+ *	right location on the next call to suspend_write_next() and it is done
+ *	with the help of copy_last_highmem_page().  For this purpose, if
+ *	@buffer is returned, @last_highmem page is set to the page to which
+ *	the data will have to be copied from @buffer.
+ */
+
+static struct page *last_highmem_page;
+
+static void *
+get_highmem_page_buffer(struct page *page, struct chain_allocator *ca)
+{
+	struct highmem_pbe *pbe;
+	void *kaddr;
+
+	if (swsusp_page_is_forbidden(page) && swsusp_page_is_free(page)) {
+		/* We have allocated the "original" page frame and we can
+		 * use it directly to store the loaded page.
+		 */
+		last_highmem_page = page;
+		return buffer;
+	}
+	/* The "original" page frame has not been allocated and we have to
+	 * use a "safe" page frame to store the loaded page.
+	 */
+	pbe = chain_alloc(ca, sizeof(struct highmem_pbe));
+	if (!pbe) {
+		swsusp_free();
+		return NULL;
+	}
+	pbe->orig_page = page;
+	if (safe_highmem_pages > 0) {
+		struct page *tmp;
+
+		/* Copy of the page will be stored in high memory */
+		kaddr = buffer;
+		tmp = pfn_to_page(memory_bm_next_pfn(safe_highmem_bm));
+		safe_highmem_pages--;
+		last_highmem_page = tmp;
+		pbe->copy_page = tmp;
+	} else {
+		/* Copy of the page will be stored in normal memory */
+		kaddr = safe_pages_list;
+		safe_pages_list = safe_pages_list->next;
+		pbe->copy_page = virt_to_page(kaddr);
+	}
+	pbe->next = highmem_pblist;
+	highmem_pblist = pbe;
+	return kaddr;
+}
+
+/**
+ *	copy_last_highmem_page - copy the contents of a highmem image from
+ *	@buffer, where the caller of snapshot_write_next() has place them,
+ *	to the right location represented by @last_highmem_page .
+ */
+
+static void copy_last_highmem_page(void)
+{
+	if (last_highmem_page) {
+		void *dst;
+
+		dst = kmap_atomic(last_highmem_page, KM_USER0);
+		memcpy(dst, buffer, PAGE_SIZE);
+		kunmap_atomic(dst, KM_USER0);
+		last_highmem_page = NULL;
+	}
+}
+
+static inline int last_highmem_page_copied(void)
+{
+	return !last_highmem_page;
+}
+
+static inline void free_highmem_data(void)
+{
+	if (safe_highmem_bm)
+		memory_bm_free(safe_highmem_bm, PG_UNSAFE_CLEAR);
+
+	if (buffer)
+		free_image_page(buffer, PG_UNSAFE_CLEAR);
+}
+#else
+static inline int get_safe_write_buffer(void) { return 0; }
+
+static unsigned int
+count_highmem_image_pages(struct memory_bitmap *bm) { return 0; }
+
+static inline int
+prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p)
+{
+	return 0;
+}
+
+static inline void *
+get_highmem_page_buffer(struct page *page, struct chain_allocator *ca)
+{
+	return NULL;
+}
+
+static inline void copy_last_highmem_page(void) {}
+static inline int last_highmem_page_copied(void) { return 1; }
+static inline void free_highmem_data(void) {}
+#endif /* CONFIG_HIGHMEM */
+
+/**
+ *	prepare_image - use the memory bitmap @bm to mark the pages that will
+ *	be overwritten in the process of restoring the system memory state
+ *	from the suspend image ("unsafe" pages) and allocate memory for the
+ *	image.
+ *
+ *	The idea is to allocate a new memory bitmap first and then allocate
+ *	as many pages as needed for the image data, but not to assign these
+ *	pages to specific tasks initially.  Instead, we just mark them as
+ *	allocated and create a lists of "safe" pages that will be used
+ *	later.  On systems with high memory a list of "safe" highmem pages is
+ *	also created.
+ */
+
+#define PBES_PER_LINKED_PAGE	(LINKED_PAGE_DATA_SIZE / sizeof(struct pbe))
+
+static int
+prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm)
+{
+	unsigned int nr_pages, nr_highmem;
+	struct linked_page *sp_list, *lp;
+	int error;
+
+	/* If there is no highmem, the buffer will not be necessary */
+	free_image_page(buffer, PG_UNSAFE_CLEAR);
+	buffer = NULL;
+
+	nr_highmem = count_highmem_image_pages(bm);
+	error = mark_unsafe_pages(bm);
+	if (error)
+		goto Free;
+
+	error = memory_bm_create(new_bm, GFP_ATOMIC, PG_SAFE);
+	if (error)
+		goto Free;
+
+	duplicate_memory_bitmap(new_bm, bm);
+	memory_bm_free(bm, PG_UNSAFE_KEEP);
+	if (nr_highmem > 0) {
+		error = prepare_highmem_image(bm, &nr_highmem);
+		if (error)
+			goto Free;
+	}
+	/* Reserve some safe pages for potential later use.
+	 *
+	 * NOTE: This way we make sure there will be enough safe pages for the
+	 * chain_alloc() in get_buffer().  It is a bit wasteful, but
+	 * nr_copy_pages cannot be greater than 50% of the memory anyway.
+	 */
+	sp_list = NULL;
+	/* nr_copy_pages cannot be lesser than allocated_unsafe_pages */
+	nr_pages = nr_copy_pages - nr_highmem - allocated_unsafe_pages;
+	nr_pages = DIV_ROUND_UP(nr_pages, PBES_PER_LINKED_PAGE);
+	while (nr_pages > 0) {
+		lp = get_image_page(GFP_ATOMIC, PG_SAFE);
+		if (!lp) {
+			error = -ENOMEM;
+			goto Free;
+		}
+		lp->next = sp_list;
+		sp_list = lp;
+		nr_pages--;
+	}
+	/* Preallocate memory for the image */
+	safe_pages_list = NULL;
+	nr_pages = nr_copy_pages - nr_highmem - allocated_unsafe_pages;
+	while (nr_pages > 0) {
+		lp = (struct linked_page *)get_zeroed_page(GFP_ATOMIC);
+		if (!lp) {
+			error = -ENOMEM;
+			goto Free;
+		}
+		if (!swsusp_page_is_free(virt_to_page(lp))) {
+			/* The page is "safe", add it to the list */
+			lp->next = safe_pages_list;
+			safe_pages_list = lp;
+		}
+		/* Mark the page as allocated */
+		swsusp_set_page_forbidden(virt_to_page(lp));
+		swsusp_set_page_free(virt_to_page(lp));
+		nr_pages--;
+	}
+	/* Free the reserved safe pages so that chain_alloc() can use them */
+	while (sp_list) {
+		lp = sp_list->next;
+		free_image_page(sp_list, PG_UNSAFE_CLEAR);
+		sp_list = lp;
+	}
+	return 0;
+
+ Free:
+	swsusp_free();
+	return error;
+}
+
+/**
+ *	get_buffer - compute the address that snapshot_write_next() should
+ *	set for its caller to write to.
+ */
+
+static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca)
+{
+	struct pbe *pbe;
+	struct page *page = pfn_to_page(memory_bm_next_pfn(bm));
+
+	if (PageHighMem(page))
+		return get_highmem_page_buffer(page, ca);
+
+	if (swsusp_page_is_forbidden(page) && swsusp_page_is_free(page))
+		/* We have allocated the "original" page frame and we can
+		 * use it directly to store the loaded page.
+		 */
+		return page_address(page);
+
+	/* The "original" page frame has not been allocated and we have to
+	 * use a "safe" page frame to store the loaded page.
+	 */
+	pbe = chain_alloc(ca, sizeof(struct pbe));
+	if (!pbe) {
+		swsusp_free();
+		return NULL;
+	}
+	pbe->orig_address = page_address(page);
+	pbe->address = safe_pages_list;
+	safe_pages_list = safe_pages_list->next;
+	pbe->next = restore_pblist;
+	restore_pblist = pbe;
+	return pbe->address;
+}
+
+/**
+ *	snapshot_write_next - used for writing the system memory snapshot.
+ *
+ *	On the first call to it @handle should point to a zeroed
+ *	snapshot_handle structure.  The structure gets updated and a pointer
+ *	to it should be passed to this function every next time.
+ *
+ *	The @count parameter should contain the number of bytes the caller
+ *	wants to write to the image.  It must not be zero.
+ *
+ *	On success the function returns a positive number.  Then, the caller
+ *	is allowed to write up to the returned number of bytes to the memory
+ *	location computed by the data_of() macro.  The number returned
+ *	may be smaller than @count, but this only happens if the write would
+ *	cross a page boundary otherwise.
+ *
+ *	The function returns 0 to indicate the "end of file" condition,
+ *	and a negative number is returned on error.  In such cases the
+ *	structure pointed to by @handle is not updated and should not be used
+ *	any more.
+ */
+
+int snapshot_write_next(struct snapshot_handle *handle, size_t count)
+{
+	static struct chain_allocator ca;
+	int error = 0;
+
+	/* Check if we have already loaded the entire image */
+	if (handle->prev && handle->cur > nr_meta_pages + nr_copy_pages)
+		return 0;
+
+	if (handle->offset == 0) {
+		if (!buffer)
+			/* This makes the buffer be freed by swsusp_free() */
+			buffer = get_image_page(GFP_ATOMIC, PG_ANY);
+
+		if (!buffer)
+			return -ENOMEM;
+
+		handle->buffer = buffer;
+	}
+	handle->sync_read = 1;
+	if (handle->prev < handle->cur) {
+		if (handle->prev == 0) {
+			error = load_header(buffer);
+			if (error)
+				return error;
+
+			error = memory_bm_create(&copy_bm, GFP_ATOMIC, PG_ANY);
+			if (error)
+				return error;
+
+		} else if (handle->prev <= nr_meta_pages) {
+			unpack_orig_pfns(buffer, &copy_bm);
+			if (handle->prev == nr_meta_pages) {
+				error = prepare_image(&orig_bm, &copy_bm);
+				if (error)
+					return error;
+
+				chain_init(&ca, GFP_ATOMIC, PG_SAFE);
+				memory_bm_position_reset(&orig_bm);
+				restore_pblist = NULL;
+				handle->buffer = get_buffer(&orig_bm, &ca);
+				handle->sync_read = 0;
+				if (!handle->buffer)
+					return -ENOMEM;
+			}
+		} else {
+			copy_last_highmem_page();
+			handle->buffer = get_buffer(&orig_bm, &ca);
+			if (handle->buffer != buffer)
+				handle->sync_read = 0;
+		}
+		handle->prev = handle->cur;
+	}
+	handle->buf_offset = handle->cur_offset;
+	if (handle->cur_offset + count >= PAGE_SIZE) {
+		count = PAGE_SIZE - handle->cur_offset;
+		handle->cur_offset = 0;
+		handle->cur++;
+	} else {
+		handle->cur_offset += count;
+	}
+	handle->offset += count;
+	return count;
+}
+
+/**
+ *	snapshot_write_finalize - must be called after the last call to
+ *	snapshot_write_next() in case the last page in the image happens
+ *	to be a highmem page and its contents should be stored in the
+ *	highmem.  Additionally, it releases the memory that will not be
+ *	used any more.
+ */
+
+void snapshot_write_finalize(struct snapshot_handle *handle)
+{
+	copy_last_highmem_page();
+	/* Free only if we have loaded the image entirely */
+	if (handle->prev && handle->cur > nr_meta_pages + nr_copy_pages) {
+		memory_bm_free(&orig_bm, PG_UNSAFE_CLEAR);
+		free_highmem_data();
+	}
+}
+
+int snapshot_image_loaded(struct snapshot_handle *handle)
+{
+	return !(!nr_copy_pages || !last_highmem_page_copied() ||
+			handle->cur <= nr_meta_pages + nr_copy_pages);
+}
+
+#ifdef CONFIG_HIGHMEM
+/* Assumes that @buf is ready and points to a "safe" page */
+static inline void
+swap_two_pages_data(struct page *p1, struct page *p2, void *buf)
+{
+	void *kaddr1, *kaddr2;
+
+	kaddr1 = kmap_atomic(p1, KM_USER0);
+	kaddr2 = kmap_atomic(p2, KM_USER1);
+	memcpy(buf, kaddr1, PAGE_SIZE);
+	memcpy(kaddr1, kaddr2, PAGE_SIZE);
+	memcpy(kaddr2, buf, PAGE_SIZE);
+	kunmap_atomic(kaddr1, KM_USER0);
+	kunmap_atomic(kaddr2, KM_USER1);
+}
+
+/**
+ *	restore_highmem - for each highmem page that was allocated before
+ *	the suspend and included in the suspend image, and also has been
+ *	allocated by the "resume" kernel swap its current (ie. "before
+ *	resume") contents with the previous (ie. "before suspend") one.
+ *
+ *	If the resume eventually fails, we can call this function once
+ *	again and restore the "before resume" highmem state.
+ */
+
+int restore_highmem(void)
+{
+	struct highmem_pbe *pbe = highmem_pblist;
+	void *buf;
+
+	if (!pbe)
+		return 0;
+
+	buf = get_image_page(GFP_ATOMIC, PG_SAFE);
+	if (!buf)
+		return -ENOMEM;
+
+	while (pbe) {
+		swap_two_pages_data(pbe->copy_page, pbe->orig_page, buf);
+		pbe = pbe->next;
+	}
+	free_image_page(buf, PG_UNSAFE_CLEAR);
+	return 0;
+}
+#endif /* CONFIG_HIGHMEM */
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
new file mode 100644
index 0000000..6da1435
--- /dev/null
+++ b/kernel/power/swap.c
@@ -0,0 +1,647 @@
+/*
+ * 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/file.h>
+#include <linux/utsname.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"
+
+#define SWSUSP_SIG	"S1SUSPEND"
+
+struct swsusp_header {
+	char reserved[PAGE_SIZE - 20 - sizeof(sector_t) - sizeof(int)];
+	sector_t image;
+	unsigned int flags;	/* Flags to pass to the "boot" kernel */
+	char	orig_sig[10];
+	char	sig[10];
+} __attribute__((packed));
+
+static struct swsusp_header *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(KERN_ERR "PM: Adding page to bio failed 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, unsigned int flags)
+{
+	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;
+		swsusp_header->flags = flags;
+		error = bio_write_page(swsusp_resume_block,
+					swsusp_header, NULL);
+	} else {
+		printk(KERN_ERR "PM: 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);
+	if (res)
+		return res;
+
+	res = set_blocksize(resume_bdev, PAGE_SIZE);
+	if (res < 0)
+		blkdev_put(resume_bdev, FMODE_WRITE);
+
+	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;
+	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;
+}
+
+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->cur_swap = alloc_swapdev_block(root_swap);
+	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);
+	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);
+		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(KERN_INFO "PM: 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("PM: Free swap pages: %u\n", free_swap);
+	return free_swap > nr_pages + PAGES_FOR_IO;
+}
+
+/**
+ *	swsusp_write - Write entire image and metadata.
+ *	@flags: flags to pass to the "boot" kernel in the image header
+ *
+ *	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(unsigned int flags)
+{
+	struct swap_map_handle handle;
+	struct snapshot_handle snapshot;
+	struct swsusp_info *header;
+	int error;
+
+	error = swsusp_swap_check();
+	if (error) {
+		printk(KERN_ERR "PM: 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 "PM: 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(KERN_INFO "PM: S");
+			error = mark_swapfiles(start, flags);
+			printk("|\n");
+		}
+	}
+	if (error)
+		free_all_swap_pages(root_swap);
+
+	release_swap_writer(&handle);
+ out:
+	swsusp_close(FMODE_WRITE);
+	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(KERN_INFO "PM: 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;
+}
+
+/**
+ *	swsusp_read - read the hibernation image.
+ *	@flags_p: flags passed by the "frozen" kernel in the image header should
+ *		  be written into this memeory location
+ */
+
+int swsusp_read(unsigned int *flags_p)
+{
+	int error;
+	struct swap_map_handle handle;
+	struct snapshot_handle snapshot;
+	struct swsusp_info *header;
+
+	*flags_p = swsusp_header->flags;
+	if (IS_ERR(resume_bdev)) {
+		pr_debug("PM: Image 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, FMODE_READ);
+
+	if (!error)
+		pr_debug("PM: Image successfully loaded\n");
+	else
+		pr_debug("PM: 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, PAGE_SIZE);
+		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, FMODE_READ);
+		else
+			pr_debug("PM: Signature found, resuming\n");
+	} else {
+		error = PTR_ERR(resume_bdev);
+	}
+
+	if (error)
+		pr_debug("PM: Error %d checking image file\n", error);
+
+	return error;
+}
+
+/**
+ *	swsusp_close - close swap device.
+ */
+
+void swsusp_close(fmode_t mode)
+{
+	if (IS_ERR(resume_bdev)) {
+		pr_debug("PM: Image device not initialised\n");
+		return;
+	}
+
+	blkdev_put(resume_bdev, mode);
+}
+
+static int swsusp_header_init(void)
+{
+	swsusp_header = (struct swsusp_header*) __get_free_page(GFP_KERNEL);
+	if (!swsusp_header)
+		panic("Could not allocate memory for swsusp_header\n");
+	return 0;
+}
+
+core_initcall(swsusp_header_init);
diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c
new file mode 100644
index 0000000..023ff2a
--- /dev/null
+++ b/kernel/power/swsusp.c
@@ -0,0 +1,264 @@
+/*
+ * 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 <linux/rbtree.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;
+
+/**
+ *	The following functions are used for tracing the allocated
+ *	swap pages, so that they can be freed in case of an error.
+ */
+
+struct swsusp_extent {
+	struct rb_node node;
+	unsigned long start;
+	unsigned long end;
+};
+
+static struct rb_root swsusp_extents = RB_ROOT;
+
+static int swsusp_extents_insert(unsigned long swap_offset)
+{
+	struct rb_node **new = &(swsusp_extents.rb_node);
+	struct rb_node *parent = NULL;
+	struct swsusp_extent *ext;
+
+	/* Figure out where to put the new node */
+	while (*new) {
+		ext = container_of(*new, struct swsusp_extent, node);
+		parent = *new;
+		if (swap_offset < ext->start) {
+			/* Try to merge */
+			if (swap_offset == ext->start - 1) {
+				ext->start--;
+				return 0;
+			}
+			new = &((*new)->rb_left);
+		} else if (swap_offset > ext->end) {
+			/* Try to merge */
+			if (swap_offset == ext->end + 1) {
+				ext->end++;
+				return 0;
+			}
+			new = &((*new)->rb_right);
+		} else {
+			/* It already is in the tree */
+			return -EINVAL;
+		}
+	}
+	/* Add the new node and rebalance the tree. */
+	ext = kzalloc(sizeof(struct swsusp_extent), GFP_KERNEL);
+	if (!ext)
+		return -ENOMEM;
+
+	ext->start = swap_offset;
+	ext->end = swap_offset;
+	rb_link_node(&ext->node, parent, new);
+	rb_insert_color(&ext->node, &swsusp_extents);
+	return 0;
+}
+
+/**
+ *	alloc_swapdev_block - allocate a swap page and register that it has
+ *	been allocated, so that it can be freed in case of an error.
+ */
+
+sector_t alloc_swapdev_block(int swap)
+{
+	unsigned long offset;
+
+	offset = swp_offset(get_swap_page_of_type(swap));
+	if (offset) {
+		if (swsusp_extents_insert(offset))
+			swap_free(swp_entry(swap, offset));
+		else
+			return swapdev_block(swap, offset);
+	}
+	return 0;
+}
+
+/**
+ *	free_all_swap_pages - free swap pages allocated for saving image data.
+ *	It also frees the extents used to register which swap entres had been
+ *	allocated.
+ */
+
+void free_all_swap_pages(int swap)
+{
+	struct rb_node *node;
+
+	while ((node = swsusp_extents.rb_node)) {
+		struct swsusp_extent *ext;
+		unsigned long offset;
+
+		ext = container_of(node, struct swsusp_extent, node);
+		rb_erase(node, &swsusp_extents);
+		for (offset = ext->start; offset <= ext->end; offset++)
+			swap_free(swp_entry(swap, offset));
+
+		kfree(ext);
+	}
+}
+
+int swsusp_swap_in_use(void)
+{
+	return (swsusp_extents.rb_node != NULL);
+}
+
+/**
+ *	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(KERN_INFO "PM: %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(KERN_INFO "PM: Shrinking memory...  ");
+	do_gettimeofday(&start);
+	do {
+		long size, highmem_size;
+
+		highmem_size = count_highmem_pages();
+		size = count_data_pages() + PAGES_FOR_IO + SPARE_PAGES;
+		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;
+}
diff --git a/kernel/power/user.c b/kernel/power/user.c
new file mode 100644
index 0000000..005b93d
--- /dev/null
+++ b/kernel/power/user.c
@@ -0,0 +1,443 @@
+/*
+ * 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 <linux/smp_lock.h>
+
+#include <asm/uaccess.h>
+
+#include "power.h"
+
+/*
+ * NOTE: The SNAPSHOT_SET_SWAP_FILE and SNAPSHOT_PMOPS ioctls are obsolete and
+ * will be removed in the future.  They are only preserved here for
+ * compatibility with existing userland utilities.
+ */
+#define SNAPSHOT_SET_SWAP_FILE	_IOW(SNAPSHOT_IOC_MAGIC, 10, unsigned int)
+#define SNAPSHOT_PMOPS		_IOW(SNAPSHOT_IOC_MAGIC, 12, unsigned int)
+
+#define PMOPS_PREPARE	1
+#define PMOPS_ENTER	2
+#define PMOPS_FINISH	3
+
+/*
+ * NOTE: The following ioctl definitions are wrong and have been replaced with
+ * correct ones.  They are only preserved here for compatibility with existing
+ * userland utilities and will be removed in the future.
+ */
+#define SNAPSHOT_ATOMIC_SNAPSHOT	_IOW(SNAPSHOT_IOC_MAGIC, 3, void *)
+#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_MINOR	231
+
+static struct snapshot_data {
+	struct snapshot_handle handle;
+	int swap;
+	int mode;
+	char frozen;
+	char ready;
+	char platform_support;
+} snapshot_state;
+
+atomic_t snapshot_device_available = ATOMIC_INIT(1);
+
+static int snapshot_open(struct inode *inode, struct file *filp)
+{
+	struct snapshot_data *data;
+	int error;
+
+	mutex_lock(&pm_mutex);
+
+	if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
+		error = -EBUSY;
+		goto Unlock;
+	}
+
+	if ((filp->f_flags & O_ACCMODE) == O_RDWR) {
+		atomic_inc(&snapshot_device_available);
+		error = -ENOSYS;
+		goto Unlock;
+	}
+	if(create_basic_memory_bitmaps()) {
+		atomic_inc(&snapshot_device_available);
+		error = -ENOMEM;
+		goto Unlock;
+	}
+	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;
+		error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
+		if (error)
+			pm_notifier_call_chain(PM_POST_RESTORE);
+	} else {
+		data->swap = -1;
+		data->mode = O_WRONLY;
+		error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE);
+		if (error)
+			pm_notifier_call_chain(PM_POST_HIBERNATION);
+	}
+	if (error)
+		atomic_inc(&snapshot_device_available);
+	data->frozen = 0;
+	data->ready = 0;
+	data->platform_support = 0;
+
+ Unlock:
+	mutex_unlock(&pm_mutex);
+
+	return error;
+}
+
+static int snapshot_release(struct inode *inode, struct file *filp)
+{
+	struct snapshot_data *data;
+
+	mutex_lock(&pm_mutex);
+
+	swsusp_free();
+	free_basic_memory_bitmaps();
+	data = filp->private_data;
+	free_all_swap_pages(data->swap);
+	if (data->frozen)
+		thaw_processes();
+	pm_notifier_call_chain(data->mode == O_WRONLY ?
+			PM_POST_HIBERNATION : PM_POST_RESTORE);
+	atomic_inc(&snapshot_device_available);
+
+	mutex_unlock(&pm_mutex);
+
+	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;
+
+	mutex_lock(&pm_mutex);
+
+	data = filp->private_data;
+	if (!data->ready) {
+		res = -ENODATA;
+		goto Unlock;
+	}
+	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;
+	}
+
+ Unlock:
+	mutex_unlock(&pm_mutex);
+
+	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;
+
+	mutex_lock(&pm_mutex);
+
+	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;
+	}
+
+	mutex_unlock(&pm_mutex);
+
+	return res;
+}
+
+static long snapshot_ioctl(struct file *filp, unsigned int cmd,
+							unsigned long arg)
+{
+	int error = 0;
+	struct snapshot_data *data;
+	loff_t size;
+	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;
+
+	if (!mutex_trylock(&pm_mutex))
+		return -EBUSY;
+
+	data = filp->private_data;
+
+	switch (cmd) {
+
+	case SNAPSHOT_FREEZE:
+		if (data->frozen)
+			break;
+
+		printk("Syncing filesystems ... ");
+		sys_sync();
+		printk("done.\n");
+
+		error = usermodehelper_disable();
+		if (error)
+			break;
+
+		error = freeze_processes();
+		if (error) {
+			thaw_processes();
+			usermodehelper_enable();
+		}
+		if (!error)
+			data->frozen = 1;
+		break;
+
+	case SNAPSHOT_UNFREEZE:
+		if (!data->frozen || data->ready)
+			break;
+		thaw_processes();
+		usermodehelper_enable();
+		data->frozen = 0;
+		break;
+
+	case SNAPSHOT_CREATE_IMAGE:
+	case SNAPSHOT_ATOMIC_SNAPSHOT:
+		if (data->mode != O_RDONLY || !data->frozen  || data->ready) {
+			error = -EPERM;
+			break;
+		}
+		error = hibernation_snapshot(data->platform_support);
+		if (!error)
+			error = put_user(in_suspend, (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 = hibernation_restore(data->platform_support);
+		break;
+
+	case SNAPSHOT_FREE:
+		swsusp_free();
+		memset(&data->handle, 0, sizeof(struct snapshot_handle));
+		data->ready = 0;
+		break;
+
+	case SNAPSHOT_PREF_IMAGE_SIZE:
+	case SNAPSHOT_SET_IMAGE_SIZE:
+		image_size = arg;
+		break;
+
+	case SNAPSHOT_GET_IMAGE_SIZE:
+		if (!data->ready) {
+			error = -ENODATA;
+			break;
+		}
+		size = snapshot_get_image_size();
+		size <<= PAGE_SHIFT;
+		error = put_user(size, (loff_t __user *)arg);
+		break;
+
+	case SNAPSHOT_AVAIL_SWAP_SIZE:
+	case SNAPSHOT_AVAIL_SWAP:
+		size = count_swap_pages(data->swap, 1);
+		size <<= PAGE_SHIFT;
+		error = put_user(size, (loff_t __user *)arg);
+		break;
+
+	case SNAPSHOT_ALLOC_SWAP_PAGE:
+	case SNAPSHOT_GET_SWAP_PAGE:
+		if (data->swap < 0 || data->swap >= MAX_SWAPFILES) {
+			error = -ENODEV;
+			break;
+		}
+		offset = alloc_swapdev_block(data->swap);
+		if (offset) {
+			offset <<= PAGE_SHIFT;
+			error = put_user(offset, (loff_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);
+		break;
+
+	case SNAPSHOT_SET_SWAP_FILE: /* This ioctl is deprecated */
+		if (!swsusp_swap_in_use()) {
+			/*
+			 * 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 (!data->frozen) {
+			error = -EPERM;
+			break;
+		}
+		/*
+		 * Tasks are frozen and the notifiers have been called with
+		 * PM_HIBERNATION_PREPARE
+		 */
+		error = suspend_devices_and_enter(PM_SUSPEND_MEM);
+		break;
+
+	case SNAPSHOT_PLATFORM_SUPPORT:
+		data->platform_support = !!arg;
+		break;
+
+	case SNAPSHOT_POWER_OFF:
+		if (data->platform_support)
+			error = hibernation_platform_enter();
+		break;
+
+	case SNAPSHOT_PMOPS: /* This ioctl is deprecated */
+		error = -EINVAL;
+
+		switch (arg) {
+
+		case PMOPS_PREPARE:
+			data->platform_support = 1;
+			error = 0;
+			break;
+
+		case PMOPS_ENTER:
+			if (data->platform_support)
+				error = hibernation_platform_enter();
+			break;
+
+		case PMOPS_FINISH:
+			if (data->platform_support)
+				error = 0;
+			break;
+
+		default:
+			printk(KERN_ERR "SNAPSHOT_PMOPS: invalid argument %ld\n", arg);
+
+		}
+		break;
+
+	case SNAPSHOT_SET_SWAP_AREA:
+		if (swsusp_swap_in_use()) {
+			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;
+
+	}
+
+	mutex_unlock(&pm_mutex);
+
+	return error;
+}
+
+static const struct file_operations snapshot_fops = {
+	.open = snapshot_open,
+	.release = snapshot_release,
+	.read = snapshot_read,
+	.write = snapshot_write,
+	.llseek = no_llseek,
+	.unlocked_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);