Merge osdl.org:/home/mochel/src/kernel/linux-2.5-virgin

into osdl.org:/home/mochel/src/kernel/linux-2.5-power

10 files changed, 1751 insertions, 469 deletions

diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
new file mode 100644
index 000000000000..c844f7170be1
--- /dev/null
+++ b/kernel/power/Kconfig
@@ -0,0 +1,92 @@
+config PM
+	bool "Power Management support"
+	---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.cs.utexas.edu/users/kharker/linux-laptop/> 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 SOFTWARE_SUSPEND
+	bool "Software Suspend (EXPERIMENTAL)"
+	depends on EXPERIMENTAL && PM && SWAP
+	---help---
+	  Enable the possibilty of suspendig machine. It doesn't need APM.
+	  You may suspend your machine by 'swsusp' or 'shutdown -z <time>' 
+	  (patch for sysvinit needed). 
+
+	  It creates an image which is saved in your active swaps. By the next
+	  booting the, pass 'resume=/dev/swappartition' and kernel will 
+	  detect the saved image, restore the memory from
+	  it and then it continues to run as before you've suspended.
+	  If you don't want the previous state to continue use the 'noresume'
+	  kernel option. However note that your partitions will be fsck'd and
+	  you must re-mkswap your swap partitions. It does not work with swap
+	  files.
+
+	  Right now you may boot without resuming and then later resume but
+	  in meantime you cannot use those swap partitions/files which were
+	  involved in suspending. Also in this case there is a risk that buffers
+	  on disk won't match with saved ones.
+
+	  For more information take a look at Documentation/swsusp.txt.
+
+config PM_DISK
+	bool "Suspend-to-Disk Support"
+	depends on PM && SWAP
+	---help---
+	  Suspend-to-disk is a power management state in which the contents
+	  of memory are stored on disk and the entire system is shut down or
+	  put into a low-power state (e.g. ACPI S4). When the computer is 
+	  turned back on, the stored image is loaded from disk and execution
+	  resumes from where it left off before suspending. 
+
+	  This config option enables the core infrastructure necessary to 
+	  perform the suspend and resume transition. 
+
+	  Currently, this suspend-to-disk implementation is based on a forked
+	  version of the swsusp code base. As such, it's still experimental,
+	  and still relies on CONFIG_SWAP. 
+
+	  More information can be found in Documentation/power/.
+
+	  If unsure, Say N.
+
+config PM_DISK_PARTITION
+	string "Default resume partition"
+	default ""
+	---help---
+	  The default resume partition is the partition that the pmdisk 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:
+
+		pmdisk=/dev/<other device> 
+
+	  which will set the resume partition to the device specified. 
+
+	  One may also do: 
+
+		pmdisk=off
+
+	  to inform the kernel not to perform a resume transition. 
+
+	  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.
+
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index 9640751c4338..d00edd15c0fd 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -1,4 +1,5 @@
 obj-y				:= main.o process.o console.o pm.o
 obj-$(CONFIG_SOFTWARE_SUSPEND)	+= swsusp.o
+obj-$(CONFIG_PM_DISK)		+= disk.o pmdisk.o
 
 obj-$(CONFIG_MAGIC_SYSRQ)	+= poweroff.o
diff --git a/kernel/power/console.c b/kernel/power/console.c
index 35b1f50d97de..c8a48236619b 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -8,7 +8,7 @@
 #include <linux/kbd_kern.h>
 #include "power.h"
 
-static int new_loglevel = 7;
+static int new_loglevel = 10;
 static int orig_loglevel;
 static int orig_fgconsole, orig_kmsg;
 
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
new file mode 100644
index 000000000000..d8c259552344
--- /dev/null
+++ b/kernel/power/disk.c
@@ -0,0 +1,335 @@
+/*
+ * kernel/power/disk.c - Suspend-to-disk support.
+ *
+ * Copyright (c) 2003 Patrick Mochel
+ * Copyright (c) 2003 Open Source Development Lab
+ *
+ * This file is release under the GPLv2
+ *
+ */
+
+#define DEBUG
+
+
+#include <linux/suspend.h>
+#include <linux/reboot.h>
+#include <linux/string.h>
+#include <linux/delay.h>
+#include <linux/fs.h>
+#include "power.h"
+
+
+extern u32 pm_disk_mode;
+extern struct pm_ops * pm_ops;
+
+extern int pmdisk_save(void);
+extern int pmdisk_write(void);
+extern int pmdisk_read(void);
+extern int pmdisk_restore(void);
+extern int pmdisk_free(void);
+
+extern long sys_sync(void);
+
+
+/**
+ *	power_down - Shut machine down for hibernate.
+ *	@mode:		Suspend-to-disk mode
+ *
+ *	Use the platform driver, if configured so, and return gracefully if it
+ *	fails.
+ *	Otherwise, try to power off and reboot. If they fail, halt the machine,
+ *	there ain't no turning back.
+ */
+
+static int power_down(u32 mode)
+{
+	unsigned long flags;
+	int error = 0;
+
+	local_irq_save(flags);
+	device_power_down(PM_SUSPEND_DISK);
+	switch(mode) {
+	case PM_DISK_PLATFORM:
+		error = pm_ops->enter(PM_SUSPEND_DISK);
+		break;
+	case PM_DISK_SHUTDOWN:
+		printk("Powering off system\n");
+		machine_power_off();
+		break;
+	case PM_DISK_REBOOT:
+		machine_restart(NULL);
+		break;
+	}
+	machine_halt();
+	device_power_up();
+	local_irq_restore(flags);
+	return 0;
+}
+
+
+static int in_suspend __nosavedata = 0;
+
+
+/**
+ *	free_some_memory -  Try to free as much memory as possible
+ *
+ *	... but do not OOM-kill anyone
+ *
+ *	Notice: all userland should be stopped at this point, or
+ *	livelock is possible.
+ */
+
+static void free_some_memory(void)
+{
+	printk("Freeing memory: ");
+	while (shrink_all_memory(10000))
+		printk(".");
+	printk("|\n");
+	blk_run_queues();
+}
+
+
+static inline void platform_finish(void)
+{
+	if (pm_disk_mode == PM_DISK_PLATFORM) {
+		if (pm_ops && pm_ops->finish)
+			pm_ops->finish(PM_SUSPEND_DISK);
+	}
+}
+
+static void finish(void)
+{
+	device_resume();
+	platform_finish();
+	thaw_processes();
+	pm_restore_console();
+}
+
+
+static int prepare(void)
+{
+	int error;
+
+	pm_prepare_console();
+
+	sys_sync();
+	if (freeze_processes()) {
+		error = -EBUSY;
+		goto Thaw;
+	}
+
+	if (pm_disk_mode == PM_DISK_PLATFORM) {
+		if (pm_ops && pm_ops->prepare) {
+			if ((error = pm_ops->prepare(PM_SUSPEND_DISK)))
+				goto Thaw;
+		}
+	}
+
+	/* Free memory before shutting down devices. */
+	free_some_memory();
+
+	if ((error = device_suspend(PM_SUSPEND_DISK)))
+		goto Finish;
+
+	return 0;
+ Finish:
+	platform_finish();
+ Thaw:
+	thaw_processes();
+	pm_restore_console();
+	return error;
+}
+
+
+/**
+ *	pm_suspend_disk - The granpappy of power management.
+ *
+ *	If we're going through the firmware, then get it over with quickly.
+ *
+ *	If not, then call pmdis to do it's thing, then figure out how
+ *	to power down the system.
+ */
+
+int pm_suspend_disk(void)
+{
+	int error;
+
+	if ((error = prepare()))
+		return error;
+
+	pr_debug("PM: Attempting to suspend to disk.\n");
+	if (pm_disk_mode == PM_DISK_FIRMWARE)
+		return pm_ops->enter(PM_SUSPEND_DISK);
+
+	pr_debug("PM: snapshotting memory.\n");
+	in_suspend = 1;
+	if ((error = pmdisk_save()))
+		goto Done;
+
+	if (in_suspend) {
+		pr_debug("PM: writing image.\n");
+
+		/*
+		 * FIXME: Leftover from swsusp. Are they necessary?
+		 */
+		mb();
+		barrier();
+
+		error = pmdisk_write();
+		if (!error) {
+			error = power_down(pm_disk_mode);
+			pr_debug("PM: Power down failed.\n");
+		}
+	} else
+		pr_debug("PM: Image restored successfully.\n");
+	pmdisk_free();
+ Done:
+	finish();
+	return error;
+}
+
+
+/**
+ *	pm_resume - Resume from a saved image.
+ *
+ *	Called as a late_initcall (so all devices are discovered and
+ *	initialized), we call pmdisk to see if we have a saved image or not.
+ *	If so, we quiesce devices, the restore the saved image. We will
+ *	return above (in pm_suspend_disk() ) if everything goes well.
+ *	Otherwise, we fail gracefully and return to the normally
+ *	scheduled program.
+ *
+ */
+
+static int pm_resume(void)
+{
+	int error;
+
+	pr_debug("PM: Reading pmdisk image.\n");
+
+	if ((error = pmdisk_read()))
+		goto Done;
+
+	pr_debug("PM: Preparing system for restore.\n");
+
+	if ((error = prepare()))
+		goto Free;
+
+	barrier();
+	mb();
+
+	/* FIXME: The following (comment and mdelay()) are from swsusp.
+	 * Are they really necessary?
+	 *
+	 * We do not want some readahead with DMA to corrupt our memory, right?
+	 * Do it with disabled interrupts for best effect. That way, if some
+	 * driver scheduled DMA, we have good chance for DMA to finish ;-).
+	 */
+	pr_debug("PM: Waiting for DMAs to settle down.\n");
+	mdelay(1000);
+
+	pr_debug("PM: Restoring saved image.\n");
+	pmdisk_restore();
+	pr_debug("PM: Restore failed, recovering.n");
+	finish();
+ Free:
+	pmdisk_free();
+ Done:
+	pr_debug("PM: Resume from disk failed.\n");
+	return 0;
+}
+
+late_initcall(pm_resume);
+
+
+static char * pm_disk_modes[] = {
+	[PM_DISK_FIRMWARE]	= "firmware",
+	[PM_DISK_PLATFORM]	= "platform",
+	[PM_DISK_SHUTDOWN]	= "shutdown",
+	[PM_DISK_REBOOT]	= "reboot",
+};
+
+/**
+ *	disk - Control suspend-to-disk mode
+ *
+ *	Suspend-to-disk can be handled in several ways. The greatest
+ *	distinction is who writes memory to disk - the firmware or the OS.
+ *	If the firmware does it, we assume that it also handles suspending
+ *	the system.
+ *	If the OS does it, then we have three options for putting the system
+ *	to sleep - using the platform driver (e.g. ACPI or other PM registers),
+ *	powering off the system or rebooting the system (for testing).
+ *
+ *	The system will support either 'firmware' or 'platform', and that is
+ *	known a priori (and encoded in pm_ops). But, the user may choose
+ *	'shutdown' or 'reboot' as alternatives.
+ *
+ *	show() will display what the mode is currently set to.
+ *	store() will accept one of
+ *
+ *	'firmware'
+ *	'platform'
+ *	'shutdown'
+ *	'reboot'
+ *
+ *	It will only change to 'firmware' or 'platform' if the system
+ *	supports it (as determined from pm_ops->pm_disk_mode).
+ */
+
+static ssize_t disk_show(struct subsystem * subsys, char * buf)
+{
+	return sprintf(buf,"%s\n",pm_disk_modes[pm_disk_mode]);
+}
+
+
+static ssize_t disk_store(struct subsystem * s, const char * buf, size_t n)
+{
+	int error = 0;
+	int i;
+	u32 mode = 0;
+
+	down(&pm_sem);
+	for (i = PM_DISK_FIRMWARE; i < PM_DISK_MAX; i++) {
+		if (!strcmp(buf,pm_disk_modes[i])) {
+			mode = i;
+			break;
+		}
+	}
+	if (mode) {
+		if (mode == PM_DISK_SHUTDOWN || mode == PM_DISK_REBOOT)
+			pm_disk_mode = mode;
+		else {
+			if (pm_ops && pm_ops->enter &&
+			    (mode == pm_ops->pm_disk_mode))
+				pm_disk_mode = mode;
+			else
+				error = -EINVAL;
+		}
+	} else
+		error = -EINVAL;
+
+	pr_debug("PM: suspend-to-disk mode set to '%s'\n",
+		 pm_disk_modes[mode]);
+	up(&pm_sem);
+	return error ? error : n;
+}
+
+power_attr(disk);
+
+static struct attribute * g[] = {
+	&disk_attr.attr,
+	NULL,
+};
+
+
+static struct attribute_group attr_group = {
+	.attrs = g,
+};
+
+
+static int __init pm_disk_init(void)
+{
+	return sysfs_create_group(&power_subsys.kset.kobj,&attr_group);
+}
+
+core_initcall(pm_disk_init);
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 1b92f13d9a77..fd212e7ecd9f 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -8,32 +8,23 @@
  *
  */
 
+#define DEBUG
+
 #include <linux/suspend.h>
 #include <linux/kobject.h>
-#include <linux/reboot.h>
 #include <linux/string.h>
+#include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/pm.h>
-#include <linux/fs.h>
 
 
 #include "power.h"
 
-static DECLARE_MUTEX(pm_sem);
-
-static struct pm_ops * pm_ops = NULL;
-
-static u32 pm_disk_mode = PM_DISK_SHUTDOWN;
-
-#ifdef CONFIG_SOFTWARE_SUSPEND
-static int have_swsusp = 1;
-#else
-static int have_swsusp = 0;
-#endif
-
-extern long sys_sync(void);
+DECLARE_MUTEX(pm_sem);
 
+struct pm_ops * pm_ops = NULL;
+u32 pm_disk_mode = PM_DISK_SHUTDOWN;
 
 /**
  *	pm_set_ops - Set the global power method table. 
@@ -51,171 +42,6 @@ void pm_set_ops(struct pm_ops * ops)
 
 
 /**
- *	pm_suspend_standby - Enter 'standby' state.
- *	
- *	'standby' is also known as 'Power-On Suspend'. Here, we power down
- *	devices, disable interrupts, and enter the state.
- */
-
-static int pm_suspend_standby(void)
-{
-	int error = 0;
-	unsigned long flags;
-
-	if (!pm_ops || !pm_ops->enter)
-		return -EPERM;
-
-	local_irq_save(flags);
-	if ((error = device_power_down(PM_SUSPEND_STANDBY)))
-		goto Done;
-	error = pm_ops->enter(PM_SUSPEND_STANDBY);
-	local_irq_restore(flags);
-	device_power_up();
- Done:
-	return error;
-}
-
-
-/**
- *	pm_suspend_mem - Enter suspend-to-RAM state.
- *
- *	Identical to pm_suspend_standby() - we power down devices, disable 
- *	interrupts, and enter the low-power state.
- */
-
-static int pm_suspend_mem(void)
-{
-	int error = 0;
-	unsigned long flags;
-
-	if (!pm_ops || !pm_ops->enter)
-		return -EPERM;
-
-	local_irq_save(flags);
-	if ((error = device_power_down(PM_SUSPEND_STANDBY)))
-		goto Done;
-	error = pm_ops->enter(PM_SUSPEND_STANDBY);
-	local_irq_restore(flags);
-	device_power_up();
- Done:
-	return error;
-}
-
-
-/**
- *	power_down - Shut machine down for hibernate.
- *	@mode:		Suspend-to-disk mode
- *
- *	Use the platform driver, if configured so, and return gracefully if it
- *	fails. 
- *	Otherwise, try to power off and reboot. If they fail, halt the machine,
- *	there ain't no turning back.
- */
-
-static int power_down(u32 mode)
-{
-	unsigned long flags;
-	int error = 0;
-
-	local_irq_save(flags);
-	device_power_down(PM_SUSPEND_DISK);
-	switch(mode) {
-	case PM_DISK_PLATFORM:
-		error = pm_ops->enter(PM_SUSPEND_DISK);
-		if (error) {
-			device_power_up();
-			local_irq_restore(flags);
-			return error;
-		}
-	case PM_DISK_SHUTDOWN:
-		machine_power_off();
-		break;
-	case PM_DISK_REBOOT:
-		machine_restart(NULL);
-		break;
-	}
-	machine_halt();
-	return 0;
-}
-
-
-static int in_suspend __nosavedata = 0;
-
-
-/**
- *	free_some_memory -  Try to free as much memory as possible
- *
- *	... but do not OOM-kill anyone
- *
- *	Notice: all userland should be stopped at this point, or 
- *	livelock is possible.
- */
-
-static void free_some_memory(void)
-{
-	printk("Freeing memory: ");
-	while (shrink_all_memory(10000))
-		printk(".");
-	printk("|\n");
-	blk_run_queues();
-}
-
-
-/**
- *	pm_suspend_disk - The granpappy of power management.
- *	
- *	If we're going through the firmware, then get it over with quickly.
- *
- *	If not, then call swsusp to do it's thing, then figure out how
- *	to power down the system.
- */
-
-static int pm_suspend_disk(void)
-{
-	int error;
-
-	pr_debug("PM: Attempting to suspend to disk.\n");
-	if (pm_disk_mode == PM_DISK_FIRMWARE)
-		return pm_ops->enter(PM_SUSPEND_DISK);
-
-	if (!have_swsusp)
-		return -EPERM;
-
-	pr_debug("PM: snapshotting memory.\n");
-	in_suspend = 1;
-	if ((error = swsusp_save()))
-		goto Done;
-
-	if (in_suspend) {
-		pr_debug("PM: writing image.\n");
-		error = swsusp_write();
-		if (!error)
-			error = power_down(pm_disk_mode);
-		pr_debug("PM: Power down failed.\n");
-	} else
-		pr_debug("PM: Image restored successfully.\n");
-	swsusp_free();
- Done:
-	return error;
-}
-
-
-
-#define decl_state(_name) \
-	{ .name = __stringify(_name), .fn = pm_suspend_##_name }
-
-struct pm_state {
-	char * name;
-	int (*fn)(void);
-} pm_states[] = {
-	[PM_SUSPEND_STANDBY]	= decl_state(standby),
-	[PM_SUSPEND_MEM]	= decl_state(mem),
-	[PM_SUSPEND_DISK]	= decl_state(disk),
-	{ NULL },
-};
-
-
-/**
  *	suspend_prepare - Do prep work before entering low-power state.
  *	@state:		State we're entering.
  *
@@ -228,36 +54,47 @@ static int suspend_prepare(u32 state)
 {
 	int error = 0;
 
+	if (!pm_ops || !pm_ops->enter)
+		return -EPERM;
+
 	pm_prepare_console();
 
-	sys_sync();
 	if (freeze_processes()) {
 		error = -EAGAIN;
 		goto Thaw;
 	}
 
-	if (pm_ops && pm_ops->prepare) {
+	if (pm_ops->prepare) {
 		if ((error = pm_ops->prepare(state)))
 			goto Thaw;
 	}
 
-	/* Free memory before shutting down devices. */
-	if (state == PM_SUSPEND_DISK)
-		free_some_memory();
-
 	if ((error = device_suspend(state)))
 		goto Finish;
-
 	return 0;
- Done:
-	pm_restore_console();
-	return error;
  Finish:
-	if (pm_ops && pm_ops->finish)
+	if (pm_ops->finish)
 		pm_ops->finish(state);
  Thaw:
 	thaw_processes();
-	goto Done;
+	pm_restore_console();
+	return error;
+}
+
+
+static int suspend_enter(u32 state)
+{
+	int error = 0;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	if ((error = device_power_down(state)))
+		goto Done;
+	error = pm_ops->enter(state);
+	device_power_up();
+ Done:
+	local_irq_restore(flags);
+	return error;
 }
 
 
@@ -279,6 +116,16 @@ static void suspend_finish(u32 state)
 }
 
 
+
+
+char * pm_states[] = {
+	[PM_SUSPEND_STANDBY]	= "standby",
+	[PM_SUSPEND_MEM]	= "mem",
+	[PM_SUSPEND_DISK]	= "disk",
+	NULL,
+};
+
+
 /**
  *	enter_state - Do common work of entering low-power state.
  *	@state:		pm_state structure for state we're entering.
@@ -293,7 +140,6 @@ static void suspend_finish(u32 state)
 static int enter_state(u32 state)
 {
 	int error;
-	struct pm_state * s = &pm_states[state];
 
 	if (down_trylock(&pm_sem))
 		return -EBUSY;
@@ -304,12 +150,17 @@ static int enter_state(u32 state)
 		goto Unlock;
 	}
 
-	pr_debug("PM: Preparing system for suspend.\n");
+	if (state == PM_SUSPEND_DISK) {
+		error = pm_suspend_disk();
+		goto Unlock;
+	}
+
+	pr_debug("PM: Preparing system for suspend\n");
 	if ((error = suspend_prepare(state)))
 		goto Unlock;
 
 	pr_debug("PM: Entering state.\n");
-	error = s->fn();
+	error = suspend_enter(state);
 
 	pr_debug("PM: Finishing up.\n");
 	suspend_finish(state);
@@ -335,138 +186,10 @@ int pm_suspend(u32 state)
 }
 
 
-/**
- *	pm_resume - Resume from a saved image.
- *
- *	Called as a late_initcall (so all devices are discovered and 
- *	initialized), we call swsusp to see if we have a saved image or not.
- *	If so, we quiesce devices, the restore the saved image. We will 
- *	return above (in pm_suspend_disk() ) if everything goes well. 
- *	Otherwise, we fail gracefully and return to the normally 
- *	scheduled program.
- *
- */
-
-static int pm_resume(void)
-{
-	int error;
-
-	if (!have_swsusp)
-		return 0;
-
-	pr_debug("PM: Reading swsusp image.\n");
-
-	if ((error = swsusp_read()))
-		goto Done;
-
-	pr_debug("PM: Preparing system for restore.\n");
-
-	if ((error = suspend_prepare(PM_SUSPEND_DISK)))
-		goto Free;
-
-	pr_debug("PM: Restoring saved image.\n");
-	swsusp_restore();
-
-	pr_debug("PM: Restore failed, recovering.n");
-	suspend_finish(PM_SUSPEND_DISK);
- Free:
-	swsusp_free();
- Done:
-	pr_debug("PM: Resume from disk failed.\n");
-	return 0;
-}
-
-late_initcall(pm_resume);
-
 
 decl_subsys(power,NULL,NULL);
 
 
-#define power_attr(_name) \
-static struct subsys_attribute _name##_attr = {	\
-	.attr	= {				\
-		.name = __stringify(_name),	\
-		.mode = 0644,			\
-	},					\
-	.show	= _name##_show,			\
-	.store	= _name##_store,		\
-}
-
-
-static char * pm_disk_modes[] = {
-	[PM_DISK_FIRMWARE]	= "firmware",
-	[PM_DISK_PLATFORM]	= "platform",
-	[PM_DISK_SHUTDOWN]	= "shutdown",
-	[PM_DISK_REBOOT]	= "reboot",
-};
-
-/**
- *	disk - Control suspend-to-disk mode
- *
- *	Suspend-to-disk can be handled in several ways. The greatest 
- *	distinction is who writes memory to disk - the firmware or the OS.
- *	If the firmware does it, we assume that it also handles suspending 
- *	the system.
- *	If the OS does it, then we have three options for putting the system
- *	to sleep - using the platform driver (e.g. ACPI or other PM registers),
- *	powering off the system or rebooting the system (for testing). 
- *
- *	The system will support either 'firmware' or 'platform', and that is
- *	known a priori (and encoded in pm_ops). But, the user may choose
- *	'shutdown' or 'reboot' as alternatives.
- *
- *	show() will display what the mode is currently set to. 
- *	store() will accept one of
- *
- *	'firmware'
- *	'platform'
- *	'shutdown'
- *	'reboot'
- *
- *	It will only change to 'firmware' or 'platform' if the system
- *	supports it (as determined from pm_ops->pm_disk_mode).
- */
-
-static ssize_t disk_show(struct subsystem * subsys, char * buf)
-{
-	return sprintf(buf,"%s\n",pm_disk_modes[pm_disk_mode]);
-}
-
-
-static ssize_t disk_store(struct subsystem * s, const char * buf, size_t n)
-{
-	int error = 0;
-	int i;
-	u32 mode = 0;
-
-	down(&pm_sem);
-	for (i = PM_DISK_FIRMWARE; i < PM_DISK_MAX; i++) {
-		if (!strcmp(buf,pm_disk_modes[i])) {
-			mode = i;
-			break;
-		}
-	}
-	if (mode) {
-		if (mode == PM_DISK_SHUTDOWN || mode == PM_DISK_REBOOT)
-			pm_disk_mode = mode;
-		else {
-			if (pm_ops && pm_ops->enter && 
-			    (mode == pm_ops->pm_disk_mode))
-				pm_disk_mode = mode;
-			else
-				error = -EINVAL;
-		}
-	} else
-		error = -EINVAL;
-
-	pr_debug("PM: suspend-to-disk mode set to '%s'\n",
-		 pm_disk_modes[mode]);
-	up(&pm_sem);
-	return error ? error : n;
-}
-
-power_attr(disk);
-
 /**
  *	state - control system power state.
  *
@@ -480,27 +203,28 @@ power_attr(disk);
 
 static ssize_t state_show(struct subsystem * subsys, char * buf)
 {
-	struct pm_state * state;
+	int i;
 	char * s = buf;
 
-	for (state = &pm_states[0]; state->name; state++)
-		s += sprintf(s,"%s ",state->name);
+	for (i = 0; i < PM_SUSPEND_MAX; i++) {
+		if (pm_states[i])
+			s += sprintf(s,"%s ",pm_states[i]);
+	}
 	s += sprintf(s,"\n");
 	return (s - buf);
 }
 
 static ssize_t state_store(struct subsystem * subsys, const char * buf, size_t n)
 {
-	u32 state;
-	struct pm_state * s;
+	u32 state = PM_SUSPEND_STANDBY;
+	char ** s;
 	int error;
 
-	for (state = 0; state < PM_SUSPEND_MAX; state++) {
-		s = &pm_states[state];
-		if (s->name && !strcmp(buf,s->name))
+	for (s = &pm_states[state]; *s; s++, state++) {
+		if (!strcmp(buf,*s))
 			break;
 	}
-	if (s)
+	if (*s)
 		error = enter_state(state);
 	else
 		error = -EINVAL;
@@ -511,7 +235,6 @@ power_attr(state);
 
 static struct attribute * g[] = {
 	&state_attr.attr,
-	&disk_attr.attr,
 	NULL,
 };
 
@@ -520,7 +243,7 @@ static struct attribute_group attr_group = {
 };
 
 
-static int pm_init(void)
+static int __init pm_init(void)
 {
 	int error = subsystem_register(&power_subsys);
 	if (!error)
diff --git a/kernel/power/pmdisk.c b/kernel/power/pmdisk.c
new file mode 100644
index 000000000000..42434427ba5e
--- /dev/null
+++ b/kernel/power/pmdisk.c
@@ -0,0 +1,942 @@
+/*
+ * kernel/power/pmdisk.c - Suspend-to-disk implmentation
+ *
+ * This STD implementation is initially derived from swsusp (suspend-to-swap).
+ * The original copyright on that was: 
+ *
+ * Copyright (C) 1998-2001 Gabor Kuti <seasons@fornax.hu>
+ * Copyright (C) 1998,2001,2002 Pavel Machek <pavel@suse.cz>
+ *
+ * The additional parts are: 
+ * 
+ * Copyright (C) 2003 Patrick Mochel
+ * Copyright (C) 2003 Open Source Development Lab
+ * 
+ * This file is released under the GPLv2. 
+ *
+ * For more information, please see the text files in Documentation/power/
+ *
+ */
+
+#include <linux/mm.h>
+#include <linux/bio.h>
+#include <linux/suspend.h>
+#include <linux/version.h>
+#include <linux/reboot.h>
+#include <linux/device.h>
+#include <linux/swapops.h>
+#include <linux/bootmem.h>
+
+#include <asm/mmu_context.h>
+
+#include "power.h"
+
+
+extern int pmdisk_arch_suspend(int resume);
+
+#define __ADDRESS(x)  ((unsigned long) phys_to_virt(x))
+#define ADDRESS(x) __ADDRESS((x) << PAGE_SHIFT)
+#define ADDRESS2(x) __ADDRESS(__pa(x))		/* Needed for x86-64 where some pages are in memory twice */
+
+/* References to section boundaries */
+extern char __nosave_begin, __nosave_end;
+
+extern int is_head_of_free_region(struct page *);
+
+/* Variables to be preserved over suspend */
+static int pagedir_order_check;
+static int nr_copy_pages_check;
+
+/* For resume= kernel option */
+static char resume_file[256] = CONFIG_PM_DISK_PARTITION;
+
+static dev_t resume_device;
+/* Local variables that should not be affected by save */
+unsigned int pmdisk_pages __nosavedata = 0;
+
+/* Suspend pagedir is allocated before final copy, therefore it
+   must be freed after resume 
+
+   Warning: this is evil. There are actually two pagedirs at time of
+   resume. One is "pagedir_save", which is empty frame allocated at
+   time of suspend, that must be freed. Second is "pagedir_nosave", 
+   allocated at time of resume, that travels through memory not to
+   collide with anything.
+ */
+suspend_pagedir_t *pm_pagedir_nosave __nosavedata = NULL;
+static suspend_pagedir_t *pagedir_save;
+static int pagedir_order __nosavedata = 0;
+
+struct link {
+	char dummy[PAGE_SIZE - sizeof(swp_entry_t)];
+	swp_entry_t next;
+};
+
+union diskpage {
+	union swap_header swh;
+	struct link link;
+	struct suspend_header sh;
+};
+
+/*
+ * XXX: We try to keep some more pages free so that I/O operations succeed
+ * without paging. Might this be more?
+ */
+#define PAGES_FOR_IO	512
+
+static const char name_suspend[] = "Suspend Machine: ";
+static const char name_resume[] = "Resume Machine: ";
+
+/*
+ * Debug
+ */
+#define	DEBUG_DEFAULT
+#undef	DEBUG_PROCESS
+#undef	DEBUG_SLOW
+#define TEST_SWSUSP 0		/* Set to 1 to reboot instead of halt machine after suspension */
+
+#ifdef DEBUG_DEFAULT
+# define PRINTK(f, a...)       printk(f, ## a)
+#else
+# define PRINTK(f, a...)
+#endif
+
+#ifdef DEBUG_SLOW
+#define MDELAY(a) mdelay(a)
+#else
+#define MDELAY(a)
+#endif
+
+/*
+ * Saving part...
+ */
+
+static __inline__ int fill_suspend_header(struct suspend_header *sh)
+{
+	memset((char *)sh, 0, sizeof(*sh));
+
+	sh->version_code = LINUX_VERSION_CODE;
+	sh->num_physpages = num_physpages;
+	strncpy(sh->machine, system_utsname.machine, 8);
+	strncpy(sh->version, system_utsname.version, 20);
+	/* FIXME: Is this bogus? --RR */
+	sh->num_cpus = num_online_cpus();
+	sh->page_size = PAGE_SIZE;
+	sh->suspend_pagedir = pm_pagedir_nosave;
+	BUG_ON (pagedir_save != pm_pagedir_nosave);
+	sh->num_pbes = pmdisk_pages;
+	/* TODO: needed? mounted fs' last mounted date comparison
+	 * [so they haven't been mounted since last suspend.
+	 * Maybe it isn't.] [we'd need to do this for _all_ fs-es]
+	 */
+	return 0;
+}
+
+/* We memorize in swapfile_used what swap devices are used for suspension */
+#define SWAPFILE_UNUSED    0
+#define SWAPFILE_SUSPEND   1	/* This is the suspending device */
+#define SWAPFILE_IGNORED   2	/* Those are other swap devices ignored for suspension */
+
+static unsigned short swapfile_used[MAX_SWAPFILES];
+static unsigned short root_swap;
+#define MARK_SWAP_SUSPEND 0
+#define MARK_SWAP_RESUME 2
+
+static void mark_swapfiles(swp_entry_t prev, int mode)
+{
+	swp_entry_t entry;
+	union diskpage *cur;
+	struct page *page;
+
+	if (root_swap == 0xFFFF)  /* ignored */
+		return;
+
+	page = alloc_page(GFP_ATOMIC);
+	if (!page)
+		panic("Out of memory in mark_swapfiles");
+	cur = page_address(page);
+	/* XXX: this is dirty hack to get first page of swap file */
+	entry = swp_entry(root_swap, 0);
+	rw_swap_page_sync(READ, entry, page);
+
+	if (mode == MARK_SWAP_RESUME) {
+	  	if (!memcmp("S1",cur->swh.magic.magic,2))
+		  	memcpy(cur->swh.magic.magic,"SWAP-SPACE",10);
+		else if (!memcmp("S2",cur->swh.magic.magic,2))
+			memcpy(cur->swh.magic.magic,"SWAPSPACE2",10);
+		else printk("%sUnable to find suspended-data signature (%.10s - misspelled?\n", 
+		      	name_resume, cur->swh.magic.magic);
+	} else {
+	  	if ((!memcmp("SWAP-SPACE",cur->swh.magic.magic,10)))
+		  	memcpy(cur->swh.magic.magic,"S1SUSP....",10);
+		else if ((!memcmp("SWAPSPACE2",cur->swh.magic.magic,10)))
+			memcpy(cur->swh.magic.magic,"S2SUSP....",10);
+		else panic("\nSwapspace is not swapspace (%.10s)\n", cur->swh.magic.magic);
+		cur->link.next = prev; /* prev is the first/last swap page of the resume area */
+		/* link.next lies *no more* in last 4/8 bytes of magic */
+	}
+	rw_swap_page_sync(WRITE, entry, page);
+	__free_page(page);
+}
+
+static void read_swapfiles(void) /* This is called before saving image */
+{
+	int i, len;
+	
+	len=strlen(resume_file);
+	root_swap = 0xFFFF;
+	
+	swap_list_lock();
+	for(i=0; i<MAX_SWAPFILES; i++) {
+		if (swap_info[i].flags == 0) {
+			swapfile_used[i]=SWAPFILE_UNUSED;
+		} else {
+			if(!len) {
+	    			printk(KERN_WARNING "resume= option should be used to set suspend device" );
+				if(root_swap == 0xFFFF) {
+					swapfile_used[i] = SWAPFILE_SUSPEND;
+					root_swap = i;
+				} else
+					swapfile_used[i] = SWAPFILE_IGNORED;				  
+			} else {
+	  			/* we ignore all swap devices that are not the resume_file */
+				if (1) {
+// FIXME				if(resume_device == swap_info[i].swap_device) {
+					swapfile_used[i] = SWAPFILE_SUSPEND;
+					root_swap = i;
+				} else {
+#if 0
+					printk( "Resume: device %s (%x != %x) ignored\n", swap_info[i].swap_file->d_name.name, swap_info[i].swap_device, resume_device );				  
+#endif
+				  	swapfile_used[i] = SWAPFILE_IGNORED;
+				}
+			}
+		}
+	}
+	swap_list_unlock();
+}
+
+static void lock_swapdevices(void) /* This is called after saving image so modification
+				      will be lost after resume... and that's what we want. */
+{
+	int i;
+
+	swap_list_lock();
+	for(i = 0; i< MAX_SWAPFILES; i++)
+		if(swapfile_used[i] == SWAPFILE_IGNORED) {
+			swap_info[i].flags ^= 0xFF; /* we make the device unusable. A new call to
+						       lock_swapdevices can unlock the devices. */
+		}
+	swap_list_unlock();
+}
+
+static int write_suspend_image(void)
+{
+	int i;
+	swp_entry_t entry, prev = { 0 };
+	int nr_pgdir_pages = SUSPEND_PD_PAGES(pmdisk_pages);
+	union diskpage *cur,  *buffer = (union diskpage *)get_zeroed_page(GFP_ATOMIC);
+	unsigned long address;
+	struct page *page;
+
+	printk( "Writing data to swap (%d pages): ", pmdisk_pages );
+	for (i=0; i<pmdisk_pages; i++) {
+		if (!(i%100))
+			printk( "." );
+		if (!(entry = get_swap_page()).val)
+			panic("\nNot enough swapspace when writing data" );
+		
+		if (swapfile_used[swp_type(entry)] != SWAPFILE_SUSPEND)
+			panic("\nPage %d: not enough swapspace on suspend device", i );
+	    
+		address = (pm_pagedir_nosave+i)->address;
+		page = virt_to_page(address);
+		rw_swap_page_sync(WRITE, entry, page);
+		(pm_pagedir_nosave+i)->swap_address = entry;
+	}
+	printk( "|\n" );
+	printk( "Writing pagedir (%d pages): ", nr_pgdir_pages);
+	for (i=0; i<nr_pgdir_pages; i++) {
+		cur = (union diskpage *)((char *) pm_pagedir_nosave)+i;
+		BUG_ON ((char *) cur != (((char *) pm_pagedir_nosave) + i*PAGE_SIZE));
+		printk( "." );
+		if (!(entry = get_swap_page()).val) {
+			printk(KERN_CRIT "Not enough swapspace when writing pgdir\n" );
+			panic("Don't know how to recover");
+			free_page((unsigned long) buffer);
+			return -ENOSPC;
+		}
+
+		if(swapfile_used[swp_type(entry)] != SWAPFILE_SUSPEND)
+			panic("\nNot enough swapspace for pagedir on suspend device" );
+
+		BUG_ON (sizeof(swp_entry_t) != sizeof(long));
+		BUG_ON (PAGE_SIZE % sizeof(struct pbe));
+
+		cur->link.next = prev;				
+		page = virt_to_page((unsigned long)cur);
+		rw_swap_page_sync(WRITE, entry, page);
+		prev = entry;
+	}
+	printk("H");
+	BUG_ON (sizeof(struct suspend_header) > PAGE_SIZE-sizeof(swp_entry_t));
+	BUG_ON (sizeof(union diskpage) != PAGE_SIZE);
+	if (!(entry = get_swap_page()).val)
+		panic( "\nNot enough swapspace when writing header" );
+	if (swapfile_used[swp_type(entry)] != SWAPFILE_SUSPEND)
+		panic("\nNot enough swapspace for header on suspend device" );
+
+	cur = (void *) buffer;
+	if (fill_suspend_header(&cur->sh))
+		panic("\nOut of memory while writing header");
+		
+	cur->link.next = prev;
+
+	page = virt_to_page((unsigned long)cur);
+	rw_swap_page_sync(WRITE, entry, page);
+	prev = entry;
+
+	printk( "S" );
+	mark_swapfiles(prev, MARK_SWAP_SUSPEND);
+	printk( "|\n" );
+
+	MDELAY(1000);
+	free_page((unsigned long) buffer);
+	return 0;
+}
+
+/* if pagedir_p != NULL it also copies the counted pages */
+static int count_and_copy_data_pages(struct pbe *pagedir_p)
+{
+	int chunk_size;
+	int nr_copy_pages = 0;
+	int pfn;
+	struct page *page;
+	
+	BUG_ON (max_pfn != num_physpages);
+
+	for (pfn = 0; pfn < max_pfn; pfn++) {
+		page = pfn_to_page(pfn);
+
+		if (!PageReserved(page)) {
+			if (PageNosave(page))
+				continue;
+
+			if ((chunk_size=is_head_of_free_region(page))!=0) {
+				pfn += chunk_size - 1;
+				continue;
+			}
+		} else if (PageReserved(page)) {
+			BUG_ON (PageNosave(page));
+
+			/*
+			 * Just copy whole code segment. Hopefully it is not that big.
+			 */
+			if ((ADDRESS(pfn) >= (unsigned long) ADDRESS2(&__nosave_begin)) && 
+			    (ADDRESS(pfn) <  (unsigned long) ADDRESS2(&__nosave_end))) {
+				PRINTK("[nosave %lx]", ADDRESS(pfn));
+				continue;
+			}
+			/* Hmm, perhaps copying all reserved pages is not too healthy as they may contain 
+			   critical bios data? */
+		} else	BUG();
+
+		nr_copy_pages++;
+		if (pagedir_p) {
+			pagedir_p->orig_address = ADDRESS(pfn);
+			copy_page((void *) pagedir_p->address, (void *) pagedir_p->orig_address);
+			pagedir_p++;
+		}
+	}
+	return nr_copy_pages;
+}
+
+static void free_suspend_pagedir(unsigned long this_pagedir)
+{
+	struct page *page;
+	int pfn;
+	unsigned long this_pagedir_end = this_pagedir +
+		(PAGE_SIZE << pagedir_order);
+
+	for(pfn = 0; pfn < num_physpages; pfn++) {
+		page = pfn_to_page(pfn);
+		if (!TestClearPageNosave(page))
+			continue;
+
+		if (ADDRESS(pfn) >= this_pagedir && ADDRESS(pfn) < this_pagedir_end)
+			continue; /* old pagedir gets freed in one */
+		
+		free_page(ADDRESS(pfn));
+	}
+	free_pages(this_pagedir, pagedir_order);
+}
+
+static suspend_pagedir_t *create_suspend_pagedir(int nr_copy_pages)
+{
+	int i;
+	suspend_pagedir_t *pagedir;
+	struct pbe *p;
+	struct page *page;
+
+	pagedir_order = get_bitmask_order(SUSPEND_PD_PAGES(nr_copy_pages));
+
+	p = pagedir = (suspend_pagedir_t *)__get_free_pages(GFP_ATOMIC | __GFP_COLD, pagedir_order);
+	if(!pagedir)
+		return NULL;
+
+	page = virt_to_page(pagedir);
+	for(i=0; i < 1<<pagedir_order; i++)
+		SetPageNosave(page++);
+		
+	while(nr_copy_pages--) {
+		p->address = get_zeroed_page(GFP_ATOMIC | __GFP_COLD);
+		if(!p->address) {
+			free_suspend_pagedir((unsigned long) pagedir);
+			return NULL;
+		}
+		SetPageNosave(virt_to_page(p->address));
+		p->orig_address = 0;
+		p++;
+	}
+	return pagedir;
+}
+
+
+int pmdisk_suspend(void)
+{
+	struct sysinfo i;
+	unsigned int nr_needed_pages = 0;
+
+	read_swapfiles();
+	drain_local_pages();
+
+	pm_pagedir_nosave = NULL;
+	printk( "/critical section: Counting pages to copy" );
+	pmdisk_pages = count_and_copy_data_pages(NULL);
+	nr_needed_pages = pmdisk_pages + PAGES_FOR_IO;
+	
+	printk(" (pages needed: %d+%d=%d free: %d)\n",pmdisk_pages,PAGES_FOR_IO,nr_needed_pages,nr_free_pages());
+	if(nr_free_pages() < nr_needed_pages) {
+		printk(KERN_CRIT "%sCouldn't get enough free pages, on %d pages short\n",
+		       name_suspend, nr_needed_pages-nr_free_pages());
+		root_swap = 0xFFFF;
+		return 1;
+	}
+	si_swapinfo(&i);	/* FIXME: si_swapinfo(&i) returns all swap devices information.
+				   We should only consider resume_device. */
+	if (i.freeswap < nr_needed_pages)  {
+		printk(KERN_CRIT "%sThere's not enough swap space available, on %ld pages short\n",
+		       name_suspend, nr_needed_pages-i.freeswap);
+		return 1;
+	}
+
+	PRINTK( "Alloc pagedir\n" ); 
+	pagedir_save = pm_pagedir_nosave = create_suspend_pagedir(pmdisk_pages);
+	if(!pm_pagedir_nosave) {
+		/* Shouldn't happen */
+		printk(KERN_CRIT "%sCouldn't allocate enough pages\n",name_suspend);
+		panic("Really should not happen");
+		return 1;
+	}
+	nr_copy_pages_check = pmdisk_pages;
+	pagedir_order_check = pagedir_order;
+
+	drain_local_pages();	/* During allocating of suspend pagedir, new cold pages may appear. Kill them */
+	if (pmdisk_pages != count_and_copy_data_pages(pm_pagedir_nosave))	/* copy */
+		BUG();
+
+	/*
+	 * 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.
+	 */
+
+	printk( "critical section/: done (%d pages copied)\n", pmdisk_pages );
+	return 0;
+}
+
+
+/**
+ *	suspend_save_image - Prepare and write saved image to swap.
+ *
+ *	IRQs are re-enabled here so we can resume devices and safely write
+ *	to the swap devices. We disable them again before we leave.
+ *
+ *	The second lock_swapdevices() will unlock ignored swap devices since
+ *	writing is finished.
+ *	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.)
+ */
+
+static int suspend_save_image(void)
+{
+	int error;
+	device_resume();
+	lock_swapdevices();
+	error = write_suspend_image();
+	lock_swapdevices();
+	return error;
+}
+
+/*
+ * Magic happens here
+ */
+
+int pmdisk_resume(void)
+{
+	BUG_ON (nr_copy_pages_check != pmdisk_pages);
+	BUG_ON (pagedir_order_check != pagedir_order);
+	
+	/* Even mappings of "global" things (vmalloc) need to be fixed */
+	__flush_tlb_global();
+	return 0;
+}
+
+/* pmdisk_arch_suspend() is implemented in arch/?/power/pmdisk.S,
+   and basically does:
+
+	if (!resume) {
+		save_processor_state();
+		SAVE_REGISTERS
+		return pmdisk_suspend();
+	}
+	GO_TO_SWAPPER_PAGE_TABLES
+	COPY_PAGES_BACK
+	RESTORE_REGISTERS
+	restore_processor_state();
+	return pmdisk_resume();
+
+ */
+
+
+/* More restore stuff */
+
+/* FIXME: Why not memcpy(to, from, 1<<pagedir_order*PAGE_SIZE)? */
+static void __init copy_pagedir(suspend_pagedir_t *to, suspend_pagedir_t *from)
+{
+	int i;
+	char *topointer=(char *)to, *frompointer=(char *)from;
+
+	for(i=0; i < 1 << pagedir_order; i++) {
+		copy_page(topointer, frompointer);
+		topointer += PAGE_SIZE;
+		frompointer += PAGE_SIZE;
+	}
+}
+
+#define does_collide(addr) does_collide_order(pm_pagedir_nosave, addr, 0)
+
+/*
+ * Returns true if given address/order collides with any orig_address 
+ */
+static int __init does_collide_order(suspend_pagedir_t *pagedir, 
+				     unsigned long addr, int order)
+{
+	int i;
+	unsigned long addre = addr + (PAGE_SIZE<<order);
+	
+	for(i=0; i < pmdisk_pages; i++)
+		if((pagedir+i)->orig_address >= addr &&
+			(pagedir+i)->orig_address < addre)
+			return 1;
+
+	return 0;
+}
+
+/*
+ * We check here that pagedir & pages it points to won't collide with pages
+ * where we're going to restore from the loaded pages later
+ */
+static int __init check_pagedir(void)
+{
+	int i;
+
+	for(i=0; i < pmdisk_pages; i++) {
+		unsigned long addr;
+
+		do {
+			addr = get_zeroed_page(GFP_ATOMIC);
+			if(!addr)
+				return -ENOMEM;
+		} while (does_collide(addr));
+
+		(pm_pagedir_nosave+i)->address = addr;
+	}
+	return 0;
+}
+
+static int __init relocate_pagedir(void)
+{
+	/*
+	 * We have to avoid recursion (not to overflow kernel stack),
+	 * and that's why code looks pretty cryptic 
+	 */
+	suspend_pagedir_t *new_pagedir, *old_pagedir = pm_pagedir_nosave;
+	void **eaten_memory = NULL;
+	void **c = eaten_memory, *m, *f;
+
+	printk("Relocating pagedir");
+
+	if(!does_collide_order(old_pagedir, (unsigned long)old_pagedir, pagedir_order)) {
+		printk("not necessary\n");
+		return 0;
+	}
+
+	while ((m = (void *) __get_free_pages(GFP_ATOMIC, pagedir_order))) {
+		memset(m, 0, PAGE_SIZE);
+		if (!does_collide_order(old_pagedir, (unsigned long)m, pagedir_order))
+			break;
+		eaten_memory = m;
+		printk( "." ); 
+		*eaten_memory = c;
+		c = eaten_memory;
+	}
+
+	if (!m)
+		return -ENOMEM;
+
+	pm_pagedir_nosave = new_pagedir = m;
+	copy_pagedir(new_pagedir, old_pagedir);
+
+	c = eaten_memory;
+	while(c) {
+		printk(":");
+		f = *c;
+		c = *c;
+		if (f)
+			free_pages((unsigned long)f, pagedir_order);
+	}
+	printk("|\n");
+	return 0;
+}
+
+/*
+ * Sanity check if this image makes sense with this kernel/swap context
+ * I really don't think that it's foolproof but more than nothing..
+ */
+
+static int __init sanity_check_failed(char *reason)
+{
+	printk(KERN_ERR "%s%s\n",name_resume,reason);
+	return -EPERM;
+}
+
+static int __init sanity_check(struct suspend_header *sh)
+{
+	if(sh->version_code != LINUX_VERSION_CODE)
+		return sanity_check_failed("Incorrect kernel version");
+	if(sh->num_physpages != num_physpages)
+		return sanity_check_failed("Incorrect memory size");
+	if(strncmp(sh->machine, system_utsname.machine, 8))
+		return sanity_check_failed("Incorrect machine type");
+	if(strncmp(sh->version, system_utsname.version, 20))
+		return sanity_check_failed("Incorrect version");
+	if(sh->num_cpus != num_online_cpus())
+		return sanity_check_failed("Incorrect number of cpus");
+	if(sh->page_size != PAGE_SIZE)
+		return sanity_check_failed("Incorrect PAGE_SIZE");
+	return 0;
+}
+
+static struct block_device * resume_bdev;
+
+
+/**
+ *	Using bio to read from swap.
+ *	This code requires a bit more work than just using buffer heads
+ *	but, it is the recommended way for 2.5/2.6.
+ *	The following are to signal the beginning and end of I/O. Bios
+ *	finish asynchronously, while we want them to happen synchronously.
+ *	A simple atomic_t, and a wait loop take care of this problem.
+ */
+
+static atomic_t io_done = ATOMIC_INIT(0);
+
+static void start_io(void)
+{
+	atomic_set(&io_done,1);
+}
+
+static int end_io(struct bio * bio, unsigned int num, int err)
+{
+	atomic_set(&io_done,0);
+	return 0;
+}
+
+static void wait_io(void)
+{
+	blk_run_queues();
+	while(atomic_read(&io_done))
+		io_schedule();
+}
+
+
+/**
+ *	submit - submit BIO request.
+ *	@rw:	READ or WRITE.
+ *	@off	physical offset of page.
+ *	@page:	page we're reading or writing.
+ *
+ *	Straight from the textbook - allocate and initialize the bio.
+ *	If we're writing, make sure the page is marked as dirty.
+ *	Then submit it and wait.
+ */
+
+static int submit(int rw, pgoff_t page_off, void * page)
+{
+	int error = 0;
+	struct bio * bio;
+
+	bio = bio_alloc(GFP_ATOMIC,1);
+	if (!bio)
+		return -ENOMEM;
+	bio->bi_sector = page_off * (PAGE_SIZE >> 9);
+	bio_get(bio);
+	bio->bi_bdev = resume_bdev;
+	bio->bi_end_io = end_io;
+
+	if (bio_add_page(bio, virt_to_page(page), PAGE_SIZE, 0) < PAGE_SIZE) {
+		printk("ERROR: adding page to bio at %ld\n",page_off);
+		error = -EFAULT;
+		goto Done;
+	}
+
+	if (rw == WRITE)
+		bio_set_pages_dirty(bio);
+	start_io();
+	submit_bio(rw,bio);
+	wait_io();
+ Done:
+	bio_put(bio);
+	return error;
+}
+
+static int
+read_page(pgoff_t page_off, void * page)
+{
+	return submit(READ,page_off,page);
+}
+
+static int
+write_page(pgoff_t page_off, void * page)
+{
+	return submit(WRITE,page_off,page);
+}
+
+
+extern dev_t __init name_to_dev_t(const char *line);
+
+
+#define next_entry(diskpage)	diskpage->link.next
+
+static int __init read_suspend_image(void)
+{
+	swp_entry_t next;
+	int i, nr_pgdir_pages;
+	union diskpage *cur;
+	int error = 0;
+
+	cur = (union diskpage *)get_zeroed_page(GFP_ATOMIC);
+	if (!cur)
+		return -ENOMEM;
+
+	if ((error = read_page(0, cur)))
+		goto Done;
+
+	/*
+	 * We have to read next position before we overwrite it
+	 */
+	next = next_entry(cur);
+
+	if (!memcmp("S1",cur->swh.magic.magic,2))
+		memcpy(cur->swh.magic.magic,"SWAP-SPACE",10);
+	else if (!memcmp("S2",cur->swh.magic.magic,2))
+		memcpy(cur->swh.magic.magic,"SWAPSPACE2",10);
+	else if ((!memcmp("SWAP-SPACE",cur->swh.magic.magic,10)) ||
+		 (!memcmp("SWAPSPACE2",cur->swh.magic.magic,10))) {
+		printk(KERN_ERR "pmdisk: Partition is normal swap space\n");
+		error = -EINVAL;
+		goto Done;
+	} else {
+		printk(KERN_ERR "pmdisk: Invalid partition type.\n");
+		error = -EINVAL;
+		goto Done;
+	}
+
+	/*
+	 * Reset swap signature now.
+	 */
+	if ((error = write_page(0,cur)))
+		goto Done;
+
+	printk( "%sSignature found, resuming\n", name_resume );
+	MDELAY(1000);
+
+	if ((error = read_page(swp_offset(next), cur)))
+		goto Done;
+ 	/* Is this same machine? */
+	if ((error = sanity_check(&cur->sh)))
+		goto Done;
+	next = next_entry(cur);
+
+	pagedir_save = cur->sh.suspend_pagedir;
+	pmdisk_pages = cur->sh.num_pbes;
+	nr_pgdir_pages = SUSPEND_PD_PAGES(pmdisk_pages);
+	pagedir_order = get_bitmask_order(nr_pgdir_pages);
+
+	pm_pagedir_nosave = (suspend_pagedir_t *)__get_free_pages(GFP_ATOMIC, pagedir_order);
+	if (!pm_pagedir_nosave) {
+		error = -ENOMEM;
+		goto Done;
+	}
+
+	PRINTK( "%sReading pagedir, ", name_resume );
+
+	/* We get pages in reverse order of saving! */
+	for (i=nr_pgdir_pages-1; i>=0; i--) {
+		BUG_ON (!next.val);
+		cur = (union diskpage *)((char *) pm_pagedir_nosave)+i;
+		error = read_page(swp_offset(next), cur);
+		if (error)
+			goto FreePagedir;
+		next = next_entry(cur);
+	}
+	BUG_ON (next.val);
+
+	if ((error = relocate_pagedir()))
+		goto FreePagedir;
+	if ((error = check_pagedir()))
+		goto FreePagedir;
+
+	printk( "Reading image data (%d pages): ", pmdisk_pages );
+	for(i=0; i < pmdisk_pages; i++) {
+		swp_entry_t swap_address = (pm_pagedir_nosave+i)->swap_address;
+		if (!(i%100))
+			printk( "." );
+		/* You do not need to check for overlaps...
+		   ... check_pagedir already did this work */
+		error = read_page(swp_offset(swap_address),
+				  (char *)((pm_pagedir_nosave+i)->address));
+		if (error)
+			goto FreePagedir;
+	}
+	printk( "|\n" );
+ Done:
+	free_page((unsigned long)cur);
+	return error;
+ FreePagedir:
+	free_pages((unsigned long)pm_pagedir_nosave,pagedir_order);
+	goto Done;
+}
+
+/**
+ *	pmdisk_save - Snapshot memory
+ */
+
+int pmdisk_save(void) 
+{
+	int error;
+
+#if defined (CONFIG_HIGHMEM) || defined (COFNIG_DISCONTIGMEM)
+	printk("pmdisk is not supported with high- or discontig-mem.\n");
+	return -EPERM;
+#endif
+	if ((error = arch_prepare_suspend()))
+		return error;
+	local_irq_disable();
+	error = pmdisk_arch_suspend(0);
+	local_irq_enable();
+	return error;
+}
+
+
+/**
+ *	pmdisk_write - Write saved memory image to swap.
+ *
+ *	pmdisk_arch_suspend(0) returns after system is resumed.
+ *
+ *	pmdisk_arch_suspend() copies all "used" memory to "free" memory,
+ *	then unsuspends all device drivers, and writes memory to disk
+ *	using normal kernel mechanism.
+ */
+
+int pmdisk_write(void)
+{
+	return suspend_save_image();
+}
+
+
+/**
+ *	pmdisk_read - Read saved image from swap.
+ */
+
+int __init pmdisk_read(void)
+{
+	int error;
+	char b[BDEVNAME_SIZE];
+
+	if (!strlen(resume_file))
+		return -ENOENT;
+
+	resume_device = name_to_dev_t(resume_file);
+	printk("pmdisk: Resume From Partition: %s, Device: %s\n", 
+	       resume_file, __bdevname(resume_device, b));
+
+	resume_bdev = open_by_devnum(resume_device, FMODE_READ, BDEV_RAW);
+	if (!IS_ERR(resume_bdev)) {
+		set_blocksize(resume_bdev, PAGE_SIZE);
+		error = read_suspend_image();
+		blkdev_put(resume_bdev, BDEV_RAW);
+	} else
+		error = PTR_ERR(resume_bdev);
+
+	if (!error)
+		PRINTK("Reading resume file was successful\n");
+	else
+		printk( "%sError %d resuming\n", name_resume, error );
+	MDELAY(1000);
+	return error;
+}
+
+
+/**
+ *	pmdisk_restore - Replace running kernel with saved image.
+ */
+
+int __init pmdisk_restore(void)
+{
+	int error;
+	local_irq_disable();
+	error = pmdisk_arch_suspend(1);
+	local_irq_enable();
+	return error;
+}
+
+
+/**
+ *	pmdisk_free - Free memory allocated to hold snapshot.
+ */
+
+int pmdisk_free(void)
+{
+	PRINTK( "Freeing prev allocated pagedir\n" );
+	free_suspend_pagedir((unsigned long) pagedir_save);
+	return 0;
+}
+
+static int __init pmdisk_setup(char *str)
+{
+	if (strlen(str)) {
+		if (!strcmp(str,"off"))
+			resume_file[0] = '\0';
+		else
+			strncpy(resume_file, str, 255);
+	} else
+		resume_file[0] = '\0';
+	return 1;
+}
+
+__setup("pmdisk=", pmdisk_setup);
+
diff --git a/kernel/power/power.h b/kernel/power/power.h
index e98de640155d..d180b0a192cd 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -9,35 +9,28 @@
 #endif
 
 
-#ifdef CONFIG_SOFTWARE_SUSPEND
-extern int swsusp_save(void);
-extern int swsusp_write(void);
-extern int swsusp_read(void);
-extern int swsusp_restore(void);
-extern int swsusp_free(void);
+#ifdef CONFIG_PM_DISK
+extern int pm_suspend_disk(void);
+
 #else
-static inline int swsusp_save(void) 
-{
-	return 0;
-}
-static inline int swsusp_write(void)
+static inline int pm_suspend_disk(void)
 {
-	return 0;
-}
-static inline int swsusp_read(void)
-{
-	return 0;
-}
-static inline int swsusp_restore(void)
-{
-	return 0;
-}
-static inline int swsusp_free(void)
-{
-	return 0;
+	return -EPERM;
 }
 #endif
 
+extern struct semaphore pm_sem;
+#define power_attr(_name) \
+static struct subsys_attribute _name##_attr = {	\
+	.attr	= {				\
+		.name = __stringify(_name),	\
+		.mode = 0644,			\
+	},					\
+	.show	= _name##_show,			\
+	.store	= _name##_store,		\
+}
+
+extern struct subsystem power_subsys;
 
 extern int freeze_processes(void);
 extern void thaw_processes(void);
diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c
index c849a18c45f4..13b1396f317b 100644
--- a/kernel/power/swsusp.c
+++ b/kernel/power/swsusp.c
@@ -65,7 +65,15 @@
 
 #include "power.h"
 
-unsigned char software_suspend_enabled = 1;
+extern long sys_sync(void);
+
+unsigned char software_suspend_enabled = 0;
+
+extern void do_magic(int resume);
+
+#define NORESUME		1
+#define RESUME_SPECIFIED	2
+
 
 #define __ADDRESS(x)  ((unsigned long) phys_to_virt(x))
 #define ADDRESS(x) __ADDRESS((x) << PAGE_SHIFT)
@@ -83,7 +91,8 @@ spinlock_t suspend_pagedir_lock __nosavedata = SPIN_LOCK_UNLOCKED;
 static int pagedir_order_check;
 static int nr_copy_pages_check;
 
-static char resume_file[256];			/* For resume= kernel option */
+static int resume_status;
+static char resume_file[256] = "";			/* For resume= kernel option */
 static dev_t resume_device;
 /* Local variables that should not be affected by save */
 unsigned int nr_copy_pages __nosavedata = 0;
@@ -347,10 +356,15 @@ static int count_and_copy_data_pages(struct pbe *pagedir_p)
 	int pfn;
 	struct page *page;
 	
+#ifdef CONFIG_DISCONTIGMEM
+	panic("Discontingmem not supported");
+#else
 	BUG_ON (max_pfn != num_physpages);
-
+#endif
 	for (pfn = 0; pfn < max_pfn; pfn++) {
 		page = pfn_to_page(pfn);
+		if (PageHighMem(page))
+			panic("Swsusp not supported on highmem boxes. Send 1GB of RAM to <pavel@ucw.cz> and try again ;-).");
 
 		if (!PageReserved(page)) {
 			if (PageNosave(page))
@@ -435,6 +449,56 @@ static suspend_pagedir_t *create_suspend_pagedir(int nr_copy_pages)
 	return pagedir;
 }
 
+static int prepare_suspend_processes(void)
+{
+	sys_sync();	/* Syncing needs pdflushd, so do it before stopping processes */
+	if (freeze_processes()) {
+		printk( KERN_ERR "Suspend failed: Not all processes stopped!\n" );
+		thaw_processes();
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * Try to free as much memory as possible, but do not OOM-kill anyone
+ *
+ * Notice: all userland should be stopped at this point, or livelock is possible.
+ */
+static void free_some_memory(void)
+{
+	printk("Freeing memory: ");
+	while (shrink_all_memory(10000))
+		printk(".");
+	printk("|\n");
+}
+
+/* Make disk drivers accept operations, again */
+static void drivers_unsuspend(void)
+{
+	device_resume();
+}
+
+/* Called from process context */
+static int drivers_suspend(void)
+{
+	return device_suspend(4);
+}
+
+#define RESUME_PHASE1 1 /* Called from interrupts disabled */
+#define RESUME_PHASE2 2 /* Called with interrupts enabled */
+#define RESUME_ALL_PHASES (RESUME_PHASE1 | RESUME_PHASE2)
+static void drivers_resume(int flags)
+{
+	if (flags & RESUME_PHASE1) {
+		device_resume();
+	}
+  	if (flags & RESUME_PHASE2) {
+#ifdef SUSPEND_CONSOLE
+		update_screen(fg_console);	/* Hmm, is this the problem? */
+#endif
+	}
+}
 
 static int suspend_prepare_image(void)
 {
@@ -488,14 +552,12 @@ static int suspend_prepare_image(void)
 	return 0;
 }
 
-static int suspend_save_image(void)
+static void suspend_save_image(void)
 {
-	int error;
-
-	device_resume();
+	drivers_unsuspend();
 
 	lock_swapdevices();
-	error = write_suspend_image();
+	write_suspend_image();
 	lock_swapdevices();	/* This will unlock ignored swap devices since writing is finished */
 
 	/* It is important _NOT_ to umount filesystems at this point. We want
@@ -503,7 +565,29 @@ static int suspend_save_image(void)
 	 * filesystem clean: it is not. (And it does not matter, if we resume
 	 * correctly, we'll mark system clean, anyway.)
 	 */
-	return error;
+}
+
+static void suspend_power_down(void)
+{
+	extern int C_A_D;
+	C_A_D = 0;
+	printk(KERN_EMERG "%s%s Trying to power down.\n", name_suspend, TEST_SWSUSP ? "Disable TEST_SWSUSP. NOT ": "");
+#ifdef CONFIG_VT
+	PRINTK(KERN_EMERG "shift_state: %04x\n", shift_state);
+	mdelay(1000);
+	if (TEST_SWSUSP ^ (!!(shift_state & (1 << KG_CTRL))))
+		machine_restart(NULL);
+	else
+#endif
+	{
+		device_shutdown();
+		machine_power_off();
+	}
+
+	printk(KERN_EMERG "%sProbably not capable for powerdown. System halted.\n", name_suspend);
+	machine_halt();
+	while (1);
+	/* NOTREACHED */
 }
 
 /*
@@ -515,21 +599,32 @@ void do_magic_resume_1(void)
 	barrier();
 	mb();
 	spin_lock_irq(&suspend_pagedir_lock);	/* Done to disable interrupts */ 
+
 	PRINTK( "Waiting for DMAs to settle down...\n");
-	/* We do not want some readahead with DMA to corrupt our memory, right?
-	   Do it with disabled interrupts for best effect. That way, if some
-	   driver scheduled DMA, we have good chance for DMA to finish ;-). */
-	mdelay(1000);
+	mdelay(1000);	/* We do not want some readahead with DMA to corrupt our memory, right?
+			   Do it with disabled interrupts for best effect. That way, if some
+			   driver scheduled DMA, we have good chance for DMA to finish ;-). */
 }
 
 void do_magic_resume_2(void)
 {
 	BUG_ON (nr_copy_pages_check != nr_copy_pages);
 	BUG_ON (pagedir_order_check != pagedir_order);
-	
-	/* Even mappings of "global" things (vmalloc) need to be fixed */
-	__flush_tlb_global();
+
+	__flush_tlb_global();		/* Even mappings of "global" things (vmalloc) need to be fixed */
+
+	PRINTK( "Freeing prev allocated pagedir\n" );
+	free_suspend_pagedir((unsigned long) pagedir_save);
 	spin_unlock_irq(&suspend_pagedir_lock);
+	drivers_resume(RESUME_ALL_PHASES);
+
+	PRINTK( "Fixing swap signatures... " );
+	mark_swapfiles(((swp_entry_t) {0}), MARK_SWAP_RESUME);
+	PRINTK( "ok\n" );
+
+#ifdef SUSPEND_CONSOLE
+	update_screen(fg_console);	/* Hmm, is this the problem? */
+#endif
 }
 
 /* do_magic() is implemented in arch/?/kernel/suspend_asm.S, and basically does:
@@ -554,28 +649,91 @@ void do_magic_suspend_1(void)
 {
 	mb();
 	barrier();
+	BUG_ON(in_atomic());
 	spin_lock_irq(&suspend_pagedir_lock);
 }
 
-int do_magic_suspend_2(void)
+void do_magic_suspend_2(void)
 {
 	int is_problem;
 	read_swapfiles();
 	is_problem = suspend_prepare_image();
 	spin_unlock_irq(&suspend_pagedir_lock);
-	if (!is_problem)
-		return suspend_save_image();
+	if (!is_problem) {
+		kernel_fpu_end();	/* save_processor_state() does kernel_fpu_begin, and we need to revert it in order to pass in_atomic() checks */
+		BUG_ON(in_atomic());
+		suspend_save_image();
+		suspend_power_down();	/* FIXME: if suspend_power_down is commented out, console is lost after few suspends ?! */
+	}
+
 	printk(KERN_EMERG "%sSuspend failed, trying to recover...\n", name_suspend);
+	MDELAY(1000); /* So user can wait and report us messages if armageddon comes :-) */
+
 	barrier();
 	mb();
+	spin_lock_irq(&suspend_pagedir_lock);	/* Done to disable interrupts */ 
 	mdelay(1000);
-	return -EFAULT;
+
+	free_pages((unsigned long) pagedir_nosave, pagedir_order);
+	spin_unlock_irq(&suspend_pagedir_lock);
+	mark_swapfiles(((swp_entry_t) {0}), MARK_SWAP_RESUME);
+}
+
+static void do_software_suspend(void)
+{
+	arch_prepare_suspend();
+	if (pm_prepare_console())
+		printk( "%sCan't allocate a console... proceeding\n", name_suspend);
+	if (!prepare_suspend_processes()) {
+
+		/* At this point, all user processes and "dangerous"
+                   kernel threads are stopped. Free some memory, as we
+                   need half of memory free. */
+
+		free_some_memory();
+		
+		/* No need to invalidate any vfsmnt list -- 
+		 * they will be valid after resume, anyway.
+		 */
+		blk_run_queues();
+
+		/* Save state of all device drivers, and stop them. */		   
+		if(drivers_suspend()==0)
+			/* If stopping device drivers worked, we proceed basically into
+			 * suspend_save_image.
+			 *
+			 * do_magic(0) returns after system is resumed.
+			 *
+			 * do_magic() copies all "used" memory to "free" memory, then
+			 * unsuspends all device drivers, and writes memory to disk
+			 * using normal kernel mechanism.
+			 */
+			do_magic(0);
+		thaw_processes();
+	}
+	software_suspend_enabled = 1;
+	MDELAY(1000);
+	pm_restore_console();
+}
+
+/*
+ * This is main interface to the outside world. It needs to be
+ * called from process context.
+ */
+void software_suspend(void)
+{
+	if(!software_suspend_enabled)
+		return;
+
+	software_suspend_enabled = 0;
+	might_sleep();
+	do_software_suspend();
 }
 
 /* More restore stuff */
 
 /* FIXME: Why not memcpy(to, from, 1<<pagedir_order*PAGE_SIZE)? */
-static void __init copy_pagedir(suspend_pagedir_t *to, suspend_pagedir_t *from)
+static void copy_pagedir(suspend_pagedir_t *to, suspend_pagedir_t *from)
 {
 	int i;
 	char *topointer=(char *)to, *frompointer=(char *)from;
@@ -592,8 +750,8 @@ static void __init copy_pagedir(suspend_pagedir_t *to, suspend_pagedir_t *from)
 /*
  * Returns true if given address/order collides with any orig_address 
  */
-static int __init does_collide_order(suspend_pagedir_t *pagedir, 
-				     unsigned long addr, int order)
+static int does_collide_order(suspend_pagedir_t *pagedir, unsigned long addr,
+		int order)
 {
 	int i;
 	unsigned long addre = addr + (PAGE_SIZE<<order);
@@ -610,7 +768,7 @@ static int __init does_collide_order(suspend_pagedir_t *pagedir,
  * We check here that pagedir & pages it points to won't collide with pages
  * where we're going to restore from the loaded pages later
  */
-static int __init check_pagedir(void)
+static int check_pagedir(void)
 {
 	int i;
 
@@ -628,7 +786,7 @@ static int __init check_pagedir(void)
 	return 0;
 }
 
-static int __init relocate_pagedir(void)
+static int relocate_pagedir(void)
 {
 	/*
 	 * We have to avoid recursion (not to overflow kernel stack),
@@ -678,13 +836,13 @@ static int __init relocate_pagedir(void)
  * I really don't think that it's foolproof but more than nothing..
  */
 
-static int __init sanity_check_failed(char *reason)
+static int sanity_check_failed(char *reason)
 {
 	printk(KERN_ERR "%s%s\n",name_resume,reason);
 	return -EPERM;
 }
 
-static int __init sanity_check(struct suspend_header *sh)
+static int sanity_check(struct suspend_header *sh)
 {
 	if(sh->version_code != LINUX_VERSION_CODE)
 		return sanity_check_failed("Incorrect kernel version");
@@ -701,8 +859,7 @@ static int __init sanity_check(struct suspend_header *sh)
 	return 0;
 }
 
-static int __init bdev_read_page(struct block_device *bdev, 
-				 long pos, void *buf)
+static int bdev_read_page(struct block_device *bdev, long pos, void *buf)
 {
 	struct buffer_head *bh;
 	BUG_ON (pos%PAGE_SIZE);
@@ -716,10 +873,31 @@ static int __init bdev_read_page(struct block_device *bdev,
 	return 0;
 } 
 
+static int bdev_write_page(struct block_device *bdev, long pos, void *buf)
+{
+#if 0
+	struct buffer_head *bh;
+	BUG_ON (pos%PAGE_SIZE);
+	bh = __bread(bdev, pos/PAGE_SIZE, PAGE_SIZE);
+	if (!bh || (!bh->b_data)) {
+		return -1;
+	}
+	memcpy(bh->b_data, buf, PAGE_SIZE);	/* FIXME: may need kmap() */
+	BUG_ON(!buffer_uptodate(bh));
+	generic_make_request(WRITE, bh);
+	if (!buffer_uptodate(bh))
+		printk(KERN_CRIT "%sWarning %s: Fixing swap signatures unsuccessful...\n", name_resume, resume_file);
+	wait_on_buffer(bh);
+	brelse(bh);
+	return 0;
+#endif
+	printk(KERN_CRIT "%sWarning %s: Fixing swap signatures unimplemented...\n", name_resume, resume_file);
+	return 0;
+}
+
 extern dev_t __init name_to_dev_t(const char *line);
 
-static int __init read_suspend_image(struct block_device *bdev, 
-				     union diskpage *cur)
+static int __read_suspend_image(struct block_device *bdev, union diskpage *cur, int noresume)
 {
 	swp_entry_t next;
 	int i, nr_pgdir_pages;
@@ -744,9 +922,18 @@ static int __init read_suspend_image(struct block_device *bdev,
 	else if (!memcmp("S2",cur->swh.magic.magic,2))
 		memcpy(cur->swh.magic.magic,"SWAPSPACE2",10);
 	else {
-		printk("swsusp: %s: Unable to find suspended-data signature (%.10s - misspelled?\n", 
+		if (noresume)
+			return -EINVAL;
+		panic("%sUnable to find suspended-data signature (%.10s - misspelled?\n", 
 			name_resume, cur->swh.magic.magic);
-		return -EFAULT;
+	}
+	if (noresume) {
+		/* We don't do a sanity check here: we want to restore the swap
+		   whatever version of kernel made the suspend image;
+		   We need to write swap, but swap is *not* enabled so
+		   we must write the device directly */
+		printk("%s: Fixing swap signatures %s...\n", name_resume, resume_file);
+		bdev_write_page(bdev, 0, cur);
 	}
 
 	printk( "%sSignature found, resuming\n", name_resume );
@@ -796,115 +983,117 @@ static int __init read_suspend_image(struct block_device *bdev,
 	return 0;
 }
 
-/**
- *	swsusp_save - Snapshot memory
- */
-
-int swsusp_save(void) 
-{
-#if defined (CONFIG_HIGHMEM) || defined (COFNIG_DISCONTIGMEM)
-	printk("swsusp is not supported with high- or discontig-mem.\n");
-	return -EPERM;
-#endif
-	return 0;
-}
-
-
-/**
- *	swsusp_write - Write saved memory image to swap.
- *
- *	do_magic(0) returns after system is resumed.
- *
- *	do_magic() copies all "used" memory to "free" memory, then
- *	unsuspends all device drivers, and writes memory to disk
- *	using normal kernel mechanism.
- */
-
-int swsusp_write(void)
-{
-	arch_prepare_suspend();
-	return do_magic(0);
-}
-
-
-/**
- *	swsusp_read - Read saved image from swap.
- */
-
-int __init swsusp_read(void)
+static int read_suspend_image(const char * specialfile, int noresume)
 {
 	union diskpage *cur;
+	unsigned long scratch_page = 0;
 	int error;
 	char b[BDEVNAME_SIZE];
 
-	if (!strlen(resume_file))
-		return -ENOENT;
-
-	resume_device = name_to_dev_t(resume_file);
-	printk("swsusp: Resume From Partition: %s, Device: %s\n", 
-	       resume_file, __bdevname(resume_device, b));
-
-	cur = (union diskpage *)get_zeroed_page(GFP_ATOMIC);
+	resume_device = name_to_dev_t(specialfile);
+	scratch_page = get_zeroed_page(GFP_ATOMIC);
+	cur = (void *) scratch_page;
 	if (cur) {
 		struct block_device *bdev;
+		printk("Resuming from device %s\n",
+				__bdevname(resume_device, b));
 		bdev = open_by_devnum(resume_device, FMODE_READ, BDEV_RAW);
-		if (!IS_ERR(bdev)) {
+		if (IS_ERR(bdev)) {
+			error = PTR_ERR(bdev);
+		} else {
 			set_blocksize(bdev, PAGE_SIZE);
-			error = read_suspend_image(bdev, cur);
+			error = __read_suspend_image(bdev, cur, noresume);
 			blkdev_put(bdev, BDEV_RAW);
-		} else
-			error = PTR_ERR(bdev);
-		free_page((unsigned long)cur);
-	} else
-		error = -ENOMEM;
+		}
+	} else error = -ENOMEM;
 
-	if (!error)
-		PRINTK("Reading resume file was successful\n");
-	else
-		printk( "%sError %d resuming\n", name_resume, error );
+	if (scratch_page)
+		free_page(scratch_page);
+	switch (error) {
+		case 0:
+			PRINTK("Reading resume file was successful\n");
+			break;
+		case -EINVAL:
+			break;
+		case -EIO:
+			printk( "%sI/O error\n", name_resume);
+			break;
+		case -ENOENT:
+			printk( "%s%s: No such file or directory\n", name_resume, specialfile);
+			break;
+		case -ENOMEM:
+			printk( "%sNot enough memory\n", name_resume);
+			break;
+		default:
+			printk( "%sError %d resuming\n", name_resume, error );
+	}
 	MDELAY(1000);
 	return error;
 }
 
-
-/**
- *	swsusp_restore - Replace running kernel with saved image.
+/*
+ * Called from init kernel_thread.
+ * We check if we have an image and if so we try to resume
  */
 
-int __init swsusp_restore(void)
+void software_resume(void)
 {
-	return do_magic(1);
-}
+	if (num_online_cpus() > 1) {
+		printk(KERN_WARNING "Software Suspend has malfunctioning SMP support. Disabled :(\n");	
+		return;
+	}
+	/* We enable the possibility of machine suspend */
+	software_suspend_enabled = 1;
+	if (!resume_status)
+		return;
 
+	printk( "%s", name_resume );
+	if (resume_status == NORESUME) {
+		if(resume_file[0])
+			read_suspend_image(resume_file, 1);
+		printk( "disabled\n" );
+		return;
+	}
+	MDELAY(1000);
 
-/**
- *	swsusp_free - Free memory allocated to hold snapshot.
- */
+	if (pm_prepare_console())
+		printk("swsusp: Can't allocate a console... proceeding\n");
 
-int swsusp_free(void)
-{
-	PRINTK( "Freeing prev allocated pagedir\n" );
-	free_suspend_pagedir((unsigned long) pagedir_save);
+	if (!resume_file[0] && resume_status == RESUME_SPECIFIED) {
+		printk( "suspension device unspecified\n" );
+		return;
+	}
 
-	PRINTK( "Fixing swap signatures... " );
-	mark_swapfiles(((swp_entry_t) {0}), MARK_SWAP_RESUME);
-	PRINTK( "ok\n" );
-	return 0;
+	printk( "resuming from %s\n", resume_file);
+	if (read_suspend_image(resume_file, 0))
+		goto read_failure;
+	do_magic(1);
+	panic("This never returns");
+
+read_failure:
+	pm_restore_console();
+	return;
 }
 
 static int __init resume_setup(char *str)
 {
-	if (strlen(str))
-		strncpy(resume_file, str, 255);
+	if (resume_status == NORESUME)
+		return 1;
+
+	strncpy( resume_file, str, 255 );
+	resume_status = RESUME_SPECIFIED;
+
 	return 1;
 }
 
 static int __init noresume_setup(char *str)
 {
-	resume_file[0] = '\0';
+	resume_status = NORESUME;
 	return 1;
 }
 
 __setup("noresume", noresume_setup);
 __setup("resume=", resume_setup);
 
+EXPORT_SYMBOL(software_suspend);
+EXPORT_SYMBOL(software_suspend_enabled);
diff --git a/kernel/sched.c b/kernel/sched.c
index 51241d70f924..b98cac028af6 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -28,6 +28,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/security.h>
 #include <linux/notifier.h>
+#include <linux/suspend.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/timer.h>
@@ -2415,6 +2416,9 @@ static int migration_thread(void * data)
 		struct list_head *head;
 		migration_req_t *req;
 
+		if (current->flags & PF_FREEZE)
+			refrigerator(PF_IOTHREAD);
+
 		spin_lock_irq(&rq->lock);
 		head = &rq->migration_queue;
 		current->state = TASK_INTERRUPTIBLE;
diff --git a/kernel/sys.c b/kernel/sys.c
index 02b5a12dfd59..b172afa53be1 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -456,8 +456,11 @@ asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user
 
 #ifdef CONFIG_SOFTWARE_SUSPEND
 	case LINUX_REBOOT_CMD_SW_SUSPEND:
-		if (!pm_suspend(PM_SUSPEND_DISK))
-			break;
+		if (!software_suspend_enabled) {
+			unlock_kernel();
+			return -EAGAIN;
+		}
+		software_suspend();
 		do_exit(0);
 		break;
 #endif