Merge branch 'linus' into tracing/hw-breakpoints

Conflicts:
	arch/x86/Kconfig
	arch/x86/kernel/traps.c
	arch/x86/power/cpu.c
	arch/x86/power/cpu_32.c
	kernel/Makefile

Semantic conflict:
	arch/x86/kernel/hw_breakpoint.c

Merge reason: Resolve the conflicts, move from put_cpu_no_sched() to
              put_cpu() in arch/x86/kernel/hw_breakpoint.c.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

12 files changed, 755 insertions, 771 deletions

diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 23bd4daeb96..72067cbdb37 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -116,9 +116,13 @@ config SUSPEND_FREEZER
 
 	  Turning OFF this setting is NOT recommended! If in doubt, say Y.
 
+config HIBERNATION_NVS
+	bool
+
 config HIBERNATION
 	bool "Hibernation (aka 'suspend to disk')"
 	depends on PM && SWAP && ARCH_HIBERNATION_POSSIBLE
+	select HIBERNATION_NVS if HAS_IOMEM
 	---help---
 	  Enable the suspend to disk (STD) functionality, which is usually
 	  called "hibernation" in user interfaces.  STD checkpoints the
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index 720ea4f781b..c3b81c30e5d 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -6,6 +6,9 @@ endif
 obj-$(CONFIG_PM)		+= main.o
 obj-$(CONFIG_PM_SLEEP)		+= console.o
 obj-$(CONFIG_FREEZER)		+= process.o
-obj-$(CONFIG_HIBERNATION)	+= swsusp.o disk.o snapshot.o swap.o user.o
+obj-$(CONFIG_SUSPEND)		+= suspend.o
+obj-$(CONFIG_PM_TEST_SUSPEND)	+= suspend_test.o
+obj-$(CONFIG_HIBERNATION)	+= swsusp.o hibernate.o snapshot.o swap.o user.o
+obj-$(CONFIG_HIBERNATION_NVS)	+= hibernate_nvs.o
 
 obj-$(CONFIG_MAGIC_SYSRQ)	+= poweroff.o
diff --git a/kernel/power/disk.c b/kernel/power/hibernate.c
index e71ca9cd81b..81d2e746489 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/hibernate.c
@@ -1,12 +1,12 @@
 /*
- * kernel/power/disk.c - Suspend-to-disk support.
+ * kernel/power/hibernate.c - Hibernation (a.k.a suspend-to-disk) support.
  *
  * Copyright (c) 2003 Patrick Mochel
  * Copyright (c) 2003 Open Source Development Lab
  * Copyright (c) 2004 Pavel Machek <pavel@suse.cz>
+ * Copyright (c) 2009 Rafael J. Wysocki, Novell Inc.
  *
  * This file is released under the GPLv2.
- *
  */
 
 #include <linux/suspend.h>
@@ -215,19 +215,17 @@ static int create_image(int platform_mode)
 	if (error)
 		return error;
 
-	device_pm_lock();
-
-	/* At this point, device_suspend() has been called, but *not*
-	 * device_power_down(). We *must* call device_power_down() now.
+	/* At this point, dpm_suspend_start() has been called, but *not*
+	 * dpm_suspend_noirq(). We *must* call dpm_suspend_noirq() 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);
+	error = dpm_suspend_noirq(PMSG_FREEZE);
 	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down, "
 			"aborting hibernation\n");
-		goto Unlock;
+		return error;
 	}
 
 	error = platform_pre_snapshot(platform_mode);
@@ -241,9 +239,9 @@ static int create_image(int platform_mode)
 
 	local_irq_disable();
 
-	sysdev_suspend(PMSG_FREEZE);
+	error = sysdev_suspend(PMSG_FREEZE);
 	if (error) {
-		printk(KERN_ERR "PM: Some devices failed to power down, "
+		printk(KERN_ERR "PM: Some system devices failed to power down, "
 			"aborting hibernation\n");
 		goto Enable_irqs;
 	}
@@ -264,7 +262,7 @@ static int create_image(int platform_mode)
 
  Power_up:
 	sysdev_resume();
-	/* NOTE:  device_power_up() is just a resume() for devices
+	/* NOTE:  dpm_resume_noirq() is just a resume() for devices
 	 * that suspended with irqs off ... no overall powerup.
 	 */
 
@@ -277,12 +275,9 @@ static int create_image(int platform_mode)
  Platform_finish:
 	platform_finish(platform_mode);
 
-	device_power_up(in_suspend ?
+	dpm_resume_noirq(in_suspend ?
 		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
 
- Unlock:
-	device_pm_unlock();
-
 	return error;
 }
 
@@ -309,7 +304,7 @@ int hibernation_snapshot(int platform_mode)
 		goto Close;
 
 	suspend_console();
-	error = device_suspend(PMSG_FREEZE);
+	error = dpm_suspend_start(PMSG_FREEZE);
 	if (error)
 		goto Recover_platform;
 
@@ -320,7 +315,7 @@ int hibernation_snapshot(int platform_mode)
 	/* Control returns here after successful restore */
 
  Resume_devices:
-	device_resume(in_suspend ?
+	dpm_resume_end(in_suspend ?
 		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
 	resume_console();
  Close:
@@ -344,13 +339,11 @@ static int resume_target_kernel(bool platform_mode)
 {
 	int error;
 
-	device_pm_lock();
-
-	error = device_power_down(PMSG_QUIESCE);
+	error = dpm_suspend_noirq(PMSG_QUIESCE);
 	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down, "
 			"aborting resume\n");
-		goto Unlock;
+		return error;
 	}
 
 	error = platform_pre_restore(platform_mode);
@@ -401,10 +394,7 @@ static int resume_target_kernel(bool platform_mode)
  Cleanup:
 	platform_restore_cleanup(platform_mode);
 
-	device_power_up(PMSG_RECOVER);
-
- Unlock:
-	device_pm_unlock();
+	dpm_resume_noirq(PMSG_RECOVER);
 
 	return error;
 }
@@ -424,10 +414,10 @@ int hibernation_restore(int platform_mode)
 
 	pm_prepare_console();
 	suspend_console();
-	error = device_suspend(PMSG_QUIESCE);
+	error = dpm_suspend_start(PMSG_QUIESCE);
 	if (!error) {
 		error = resume_target_kernel(platform_mode);
-		device_resume(PMSG_RECOVER);
+		dpm_resume_end(PMSG_RECOVER);
 	}
 	resume_console();
 	pm_restore_console();
@@ -457,18 +447,16 @@ int hibernation_platform_enter(void)
 
 	entering_platform_hibernation = true;
 	suspend_console();
-	error = device_suspend(PMSG_HIBERNATE);
+	error = dpm_suspend_start(PMSG_HIBERNATE);
 	if (error) {
 		if (hibernation_ops->recover)
 			hibernation_ops->recover();
 		goto Resume_devices;
 	}
 
-	device_pm_lock();
-
-	error = device_power_down(PMSG_HIBERNATE);
+	error = dpm_suspend_noirq(PMSG_HIBERNATE);
 	if (error)
-		goto Unlock;
+		goto Resume_devices;
 
 	error = hibernation_ops->prepare();
 	if (error)
@@ -491,14 +479,11 @@ int hibernation_platform_enter(void)
  Platofrm_finish:
 	hibernation_ops->finish();
 
-	device_power_up(PMSG_RESTORE);
-
- Unlock:
-	device_pm_unlock();
+	dpm_suspend_noirq(PMSG_RESTORE);
 
  Resume_devices:
 	entering_platform_hibernation = false;
-	device_resume(PMSG_RESTORE);
+	dpm_resume_end(PMSG_RESTORE);
 	resume_console();
 
  Close:
diff --git a/kernel/power/hibernate_nvs.c b/kernel/power/hibernate_nvs.c
new file mode 100644
index 00000000000..39ac698ef83
--- /dev/null
+++ b/kernel/power/hibernate_nvs.c
@@ -0,0 +1,135 @@
+/*
+ * linux/kernel/power/hibernate_nvs.c - Routines for handling NVS memory
+ *
+ * Copyright (C) 2008,2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/suspend.h>
+
+/*
+ * Platforms, like ACPI, may want us to save some memory used by them during
+ * hibernation and to restore the contents of this memory during the subsequent
+ * resume.  The code below implements a mechanism allowing us to do that.
+ */
+
+struct nvs_page {
+	unsigned long phys_start;
+	unsigned int size;
+	void *kaddr;
+	void *data;
+	struct list_head node;
+};
+
+static LIST_HEAD(nvs_list);
+
+/**
+ *	hibernate_nvs_register - register platform NVS memory region to save
+ *	@start - physical address of the region
+ *	@size - size of the region
+ *
+ *	The NVS region need not be page-aligned (both ends) and we arrange
+ *	things so that the data from page-aligned addresses in this region will
+ *	be copied into separate RAM pages.
+ */
+int hibernate_nvs_register(unsigned long start, unsigned long size)
+{
+	struct nvs_page *entry, *next;
+
+	while (size > 0) {
+		unsigned int nr_bytes;
+
+		entry = kzalloc(sizeof(struct nvs_page), GFP_KERNEL);
+		if (!entry)
+			goto Error;
+
+		list_add_tail(&entry->node, &nvs_list);
+		entry->phys_start = start;
+		nr_bytes = PAGE_SIZE - (start & ~PAGE_MASK);
+		entry->size = (size < nr_bytes) ? size : nr_bytes;
+
+		start += entry->size;
+		size -= entry->size;
+	}
+	return 0;
+
+ Error:
+	list_for_each_entry_safe(entry, next, &nvs_list, node) {
+		list_del(&entry->node);
+		kfree(entry);
+	}
+	return -ENOMEM;
+}
+
+/**
+ *	hibernate_nvs_free - free data pages allocated for saving NVS regions
+ */
+void hibernate_nvs_free(void)
+{
+	struct nvs_page *entry;
+
+	list_for_each_entry(entry, &nvs_list, node)
+		if (entry->data) {
+			free_page((unsigned long)entry->data);
+			entry->data = NULL;
+			if (entry->kaddr) {
+				iounmap(entry->kaddr);
+				entry->kaddr = NULL;
+			}
+		}
+}
+
+/**
+ *	hibernate_nvs_alloc - allocate memory necessary for saving NVS regions
+ */
+int hibernate_nvs_alloc(void)
+{
+	struct nvs_page *entry;
+
+	list_for_each_entry(entry, &nvs_list, node) {
+		entry->data = (void *)__get_free_page(GFP_KERNEL);
+		if (!entry->data) {
+			hibernate_nvs_free();
+			return -ENOMEM;
+		}
+	}
+	return 0;
+}
+
+/**
+ *	hibernate_nvs_save - save NVS memory regions
+ */
+void hibernate_nvs_save(void)
+{
+	struct nvs_page *entry;
+
+	printk(KERN_INFO "PM: Saving platform NVS memory\n");
+
+	list_for_each_entry(entry, &nvs_list, node)
+		if (entry->data) {
+			entry->kaddr = ioremap(entry->phys_start, entry->size);
+			memcpy(entry->data, entry->kaddr, entry->size);
+		}
+}
+
+/**
+ *	hibernate_nvs_restore - restore NVS memory regions
+ *
+ *	This function is going to be called with interrupts disabled, so it
+ *	cannot iounmap the virtual addresses used to access the NVS region.
+ */
+void hibernate_nvs_restore(void)
+{
+	struct nvs_page *entry;
+
+	printk(KERN_INFO "PM: Restoring platform NVS memory\n");
+
+	list_for_each_entry(entry, &nvs_list, node)
+		if (entry->data)
+			memcpy(entry->kaddr, entry->data, entry->size);
+}
diff --git a/kernel/power/main.c b/kernel/power/main.c
index f99ed6a75ea..f710e36930c 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -8,20 +8,9 @@
  *
  */
 
-#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 "power.h"
 
@@ -119,378 +108,6 @@ power_attr(pm_test);
 
 #endif /* CONFIG_PM_SLEEP */
 
-#ifdef CONFIG_SUSPEND
-
-static int suspend_test(int level)
-{
-#ifdef CONFIG_PM_DEBUG
-	if (pm_test_level == level) {
-		printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n");
-		mdelay(5000);
-		return 1;
-	}
-#endif /* !CONFIG_PM_DEBUG */
-	return 0;
-}
-
-#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;
-
-	device_pm_lock();
-
-	if (suspend_ops->prepare) {
-		error = suspend_ops->prepare();
-		if (error)
-			goto Done;
-	}
-
-	error = device_power_down(PMSG_SUSPEND);
-	if (error) {
-		printk(KERN_ERR "PM: Some devices failed to power down\n");
-		goto Platfrom_finish;
-	}
-
-	if (suspend_ops->prepare_late) {
-		error = suspend_ops->prepare_late();
-		if (error)
-			goto Power_up_devices;
-	}
-
-	if (suspend_test(TEST_PLATFORM))
-		goto Platform_wake;
-
-	error = disable_nonboot_cpus();
-	if (error || suspend_test(TEST_CPUS))
-		goto Enable_cpus;
-
-	arch_suspend_disable_irqs();
-	BUG_ON(!irqs_disabled());
-
-	error = sysdev_suspend(PMSG_SUSPEND);
-	if (!error) {
-		if (!suspend_test(TEST_CORE))
-			error = suspend_ops->enter(state);
-		sysdev_resume();
-	}
-
-	arch_suspend_enable_irqs();
-	BUG_ON(irqs_disabled());
-
- Enable_cpus:
-	enable_nonboot_cpus();
-
- Platform_wake:
-	if (suspend_ops->wake)
-		suspend_ops->wake();
-
- Power_up_devices:
-	device_power_up(PMSG_RESUME);
-
- Platfrom_finish:
-	if (suspend_ops->finish)
-		suspend_ops->finish();
-
- Done:
-	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;
-
-	if (!suspend_ops)
-		return -ENOSYS;
-
-	if (suspend_ops->begin) {
-		error = suspend_ops->begin(state);
-		if (error)
-			goto Close;
-	}
-	suspend_console();
-	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;
-
-	suspend_enter(state);
-
- Resume_devices:
-	suspend_test_start();
-	device_resume(PMSG_RESUME);
-	suspend_test_finish("resume devices");
-	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;
 
 /**
@@ -503,7 +120,6 @@ struct kobject *power_kobj;
  *	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)
 {
@@ -601,7 +217,6 @@ static struct attribute_group attr_group = {
 	.attrs = g,
 };
 
-
 static int __init pm_init(void)
 {
 	power_kobj = kobject_create_and_add("power", NULL);
@@ -611,144 +226,3 @@ static int __init pm_init(void)
 }
 
 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, dev_name(&rtc->dev), 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, dev_name(&rtc->dev), 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;
-
-	*(const char **)name_ptr = dev_name(dev);
-	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
index 46b5ec7a3af..26d5a26f82e 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -45,7 +45,7 @@ static inline char *check_image_kernel(struct swsusp_info *info)
  */
 #define SPARE_PAGES	((1024 * 1024) >> PAGE_SHIFT)
 
-/* kernel/power/disk.c */
+/* kernel/power/hibernate.c */
 extern int hibernation_snapshot(int platform_mode);
 extern int hibernation_restore(int platform_mode);
 extern int hibernation_platform_enter(void);
@@ -74,7 +74,7 @@ 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);
+extern int swsusp_shrink_memory(void);
 
 /**
  *	Auxiliary structure used for reading the snapshot image data and
@@ -147,9 +147,8 @@ extern int swsusp_swap_in_use(void);
  */
 #define SF_PLATFORM_MODE	1
 
-/* kernel/power/disk.c */
+/* kernel/power/hibernate.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);
@@ -161,22 +160,36 @@ extern void swsusp_show_speed(struct timeval *, struct timeval *,
 				unsigned int, char *);
 
 #ifdef CONFIG_SUSPEND
-/* kernel/power/main.c */
+/* kernel/power/suspend.c */
+extern const char *const pm_states[];
+
+extern bool valid_state(suspend_state_t state);
 extern int suspend_devices_and_enter(suspend_state_t state);
+extern int enter_state(suspend_state_t state);
 #else /* !CONFIG_SUSPEND */
 static inline int suspend_devices_and_enter(suspend_state_t state)
 {
 	return -ENOSYS;
 }
+static inline int enter_state(suspend_state_t state) { return -ENOSYS; }
+static inline bool valid_state(suspend_state_t state) { return false; }
 #endif /* !CONFIG_SUSPEND */
 
+#ifdef CONFIG_PM_TEST_SUSPEND
+/* kernel/power/suspend_test.c */
+extern void suspend_test_start(void);
+extern void suspend_test_finish(const char *label);
+#else /* !CONFIG_PM_TEST_SUSPEND */
+static inline void suspend_test_start(void) {}
+static inline void suspend_test_finish(const char *label) {}
+#endif /* !CONFIG_PM_TEST_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; }
diff --git a/kernel/power/poweroff.c b/kernel/power/poweroff.c
index 97890831e1b..e8b33700627 100644
--- a/kernel/power/poweroff.c
+++ b/kernel/power/poweroff.c
@@ -34,7 +34,7 @@ static struct sysrq_key_op	sysrq_poweroff_op = {
 	.handler        = handle_poweroff,
 	.help_msg       = "powerOff",
 	.action_msg     = "Power Off",
- 	.enable_mask	= SYSRQ_ENABLE_BOOT,
+	.enable_mask	= SYSRQ_ENABLE_BOOT,
 };
 
 static int pm_sysrq_init(void)
diff --git a/kernel/power/process.c b/kernel/power/process.c
index ca634019497..da2072d7381 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -117,9 +117,12 @@ int freeze_processes(void)
 	if (error)
 		goto Exit;
 	printk("done.");
+
+	oom_killer_disable();
  Exit:
 	BUG_ON(in_atomic());
 	printk("\n");
+
 	return error;
 }
 
@@ -145,6 +148,8 @@ static void thaw_tasks(bool nosig_only)
 
 void thaw_processes(void)
 {
+	oom_killer_enable();
+
 	printk("Restarting tasks ... ");
 	thaw_tasks(true);
 	thaw_tasks(false);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 33e2e4a819f..523a451b45d 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -39,6 +39,14 @@ static int swsusp_page_is_free(struct page *);
 static void swsusp_set_page_forbidden(struct page *);
 static void swsusp_unset_page_forbidden(struct page *);
 
+/*
+ * 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;
+
 /* 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
@@ -840,7 +848,7 @@ static struct page *saveable_highmem_page(struct zone *zone, unsigned long pfn)
  *	pages.
  */
 
-unsigned int count_highmem_pages(void)
+static unsigned int count_highmem_pages(void)
 {
 	struct zone *zone;
 	unsigned int n = 0;
@@ -902,7 +910,7 @@ static struct page *saveable_page(struct zone *zone, unsigned long pfn)
  *	pages.
  */
 
-unsigned int count_data_pages(void)
+static unsigned int count_data_pages(void)
 {
 	struct zone *zone;
 	unsigned long pfn, max_zone_pfn;
@@ -1058,6 +1066,74 @@ void swsusp_free(void)
 	buffer = NULL;
 }
 
+/**
+ *	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_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;
+}
+
 #ifdef CONFIG_HIGHMEM
 /**
   *	count_pages_for_highmem - compute the number of non-highmem pages
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
new file mode 100644
index 00000000000..6f10dfc2d3e
--- /dev/null
+++ b/kernel/power/suspend.c
@@ -0,0 +1,300 @@
+/*
+ * kernel/power/suspend.c - Suspend to RAM and standby functionality.
+ *
+ * Copyright (c) 2003 Patrick Mochel
+ * Copyright (c) 2003 Open Source Development Lab
+ * Copyright (c) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/string.h>
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/console.h>
+#include <linux/cpu.h>
+#include <linux/syscalls.h>
+
+#include "power.h"
+
+const char *const pm_states[PM_SUSPEND_MAX] = {
+	[PM_SUSPEND_STANDBY]	= "standby",
+	[PM_SUSPEND_MEM]	= "mem",
+};
+
+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);
+}
+
+bool 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.
+	 */
+	return suspend_ops && suspend_ops->valid && suspend_ops->valid(state);
+}
+
+/**
+ * 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;
+}
+
+static int suspend_test(int level)
+{
+#ifdef CONFIG_PM_DEBUG
+	if (pm_test_level == level) {
+		printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n");
+		mdelay(5000);
+		return 1;
+	}
+#endif /* !CONFIG_PM_DEBUG */
+	return 0;
+}
+
+/**
+ *	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;
+
+	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;
+
+	error = suspend_freeze_processes();
+	if (!error)
+		return 0;
+
+	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;
+
+	if (suspend_ops->prepare) {
+		error = suspend_ops->prepare();
+		if (error)
+			return error;
+	}
+
+	error = dpm_suspend_noirq(PMSG_SUSPEND);
+	if (error) {
+		printk(KERN_ERR "PM: Some devices failed to power down\n");
+		goto Platfrom_finish;
+	}
+
+	if (suspend_ops->prepare_late) {
+		error = suspend_ops->prepare_late();
+		if (error)
+			goto Power_up_devices;
+	}
+
+	if (suspend_test(TEST_PLATFORM))
+		goto Platform_wake;
+
+	error = disable_nonboot_cpus();
+	if (error || suspend_test(TEST_CPUS))
+		goto Enable_cpus;
+
+	arch_suspend_disable_irqs();
+	BUG_ON(!irqs_disabled());
+
+	error = sysdev_suspend(PMSG_SUSPEND);
+	if (!error) {
+		if (!suspend_test(TEST_CORE))
+			error = suspend_ops->enter(state);
+		sysdev_resume();
+	}
+
+	arch_suspend_enable_irqs();
+	BUG_ON(irqs_disabled());
+
+ Enable_cpus:
+	enable_nonboot_cpus();
+
+ Platform_wake:
+	if (suspend_ops->wake)
+		suspend_ops->wake();
+
+ Power_up_devices:
+	dpm_resume_noirq(PMSG_RESUME);
+
+ Platfrom_finish:
+	if (suspend_ops->finish)
+		suspend_ops->finish();
+
+	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;
+
+	if (!suspend_ops)
+		return -ENOSYS;
+
+	if (suspend_ops->begin) {
+		error = suspend_ops->begin(state);
+		if (error)
+			goto Close;
+	}
+	suspend_console();
+	suspend_test_start();
+	error = dpm_suspend_start(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;
+
+	suspend_enter(state);
+
+ Resume_devices:
+	suspend_test_start();
+	dpm_resume_end(PMSG_RESUME);
+	suspend_test_finish("resume devices");
+	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();
+}
+
+/**
+ *	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).
+ */
+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);
diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c
new file mode 100644
index 00000000000..17d8bb1acf9
--- /dev/null
+++ b/kernel/power/suspend_test.c
@@ -0,0 +1,187 @@
+/*
+ * kernel/power/suspend_test.c - Suspend to RAM and standby test facility.
+ *
+ * Copyright (c) 2009 Pavel Machek <pavel@ucw.cz>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/init.h>
+#include <linux/rtc.h>
+
+#include "power.h"
+
+/*
+ * 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;
+
+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;
+}
+
+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);
+}
+
+/*
+ * 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, dev_name(&rtc->dev), 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, dev_name(&rtc->dev), 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;
+
+	*(const char **)name_ptr = dev_name(dev);
+	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);
diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c
index 78c35047586..6a07f4dbf2f 100644
--- a/kernel/power/swsusp.c
+++ b/kernel/power/swsusp.c
@@ -55,14 +55,6 @@
 
 #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;
 
 /**
@@ -194,193 +186,3 @@ void swsusp_show_speed(struct timeval *start, struct timeval *stop,
 			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_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;
-}
-
-/*
- * Platforms, like ACPI, may want us to save some memory used by them during
- * hibernation and to restore the contents of this memory during the subsequent
- * resume.  The code below implements a mechanism allowing us to do that.
- */
-
-struct nvs_page {
-	unsigned long phys_start;
-	unsigned int size;
-	void *kaddr;
-	void *data;
-	struct list_head node;
-};
-
-static LIST_HEAD(nvs_list);
-
-/**
- *	hibernate_nvs_register - register platform NVS memory region to save
- *	@start - physical address of the region
- *	@size - size of the region
- *
- *	The NVS region need not be page-aligned (both ends) and we arrange
- *	things so that the data from page-aligned addresses in this region will
- *	be copied into separate RAM pages.
- */
-int hibernate_nvs_register(unsigned long start, unsigned long size)
-{
-	struct nvs_page *entry, *next;
-
-	while (size > 0) {
-		unsigned int nr_bytes;
-
-		entry = kzalloc(sizeof(struct nvs_page), GFP_KERNEL);
-		if (!entry)
-			goto Error;
-
-		list_add_tail(&entry->node, &nvs_list);
-		entry->phys_start = start;
-		nr_bytes = PAGE_SIZE - (start & ~PAGE_MASK);
-		entry->size = (size < nr_bytes) ? size : nr_bytes;
-
-		start += entry->size;
-		size -= entry->size;
-	}
-	return 0;
-
- Error:
-	list_for_each_entry_safe(entry, next, &nvs_list, node) {
-		list_del(&entry->node);
-		kfree(entry);
-	}
-	return -ENOMEM;
-}
-
-/**
- *	hibernate_nvs_free - free data pages allocated for saving NVS regions
- */
-void hibernate_nvs_free(void)
-{
-	struct nvs_page *entry;
-
-	list_for_each_entry(entry, &nvs_list, node)
-		if (entry->data) {
-			free_page((unsigned long)entry->data);
-			entry->data = NULL;
-			if (entry->kaddr) {
-				iounmap(entry->kaddr);
-				entry->kaddr = NULL;
-			}
-		}
-}
-
-/**
- *	hibernate_nvs_alloc - allocate memory necessary for saving NVS regions
- */
-int hibernate_nvs_alloc(void)
-{
-	struct nvs_page *entry;
-
-	list_for_each_entry(entry, &nvs_list, node) {
-		entry->data = (void *)__get_free_page(GFP_KERNEL);
-		if (!entry->data) {
-			hibernate_nvs_free();
-			return -ENOMEM;
-		}
-	}
-	return 0;
-}
-
-/**
- *	hibernate_nvs_save - save NVS memory regions
- */
-void hibernate_nvs_save(void)
-{
-	struct nvs_page *entry;
-
-	printk(KERN_INFO "PM: Saving platform NVS memory\n");
-
-	list_for_each_entry(entry, &nvs_list, node)
-		if (entry->data) {
-			entry->kaddr = ioremap(entry->phys_start, entry->size);
-			memcpy(entry->data, entry->kaddr, entry->size);
-		}
-}
-
-/**
- *	hibernate_nvs_restore - restore NVS memory regions
- *
- *	This function is going to be called with interrupts disabled, so it
- *	cannot iounmap the virtual addresses used to access the NVS region.
- */
-void hibernate_nvs_restore(void)
-{
-	struct nvs_page *entry;
-
-	printk(KERN_INFO "PM: Restoring platform NVS memory\n");
-
-	list_for_each_entry(entry, &nvs_list, node)
-		if (entry->data)
-			memcpy(entry->kaddr, entry->data, entry->size);
-}