Merge commit 'suspend/linux-next'

8 files changed, 448 insertions, 204 deletions

diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 86990011277b..e0dc4071e088 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -50,7 +50,7 @@ static DEFINE_MUTEX(dpm_list_mtx);
 static bool transition_started;
 
 /**
- * device_pm_init - Initialize the PM-related part of a device object
+ * device_pm_init - Initialize the PM-related part of a device object.
  * @dev: Device object being initialized.
  */
 void device_pm_init(struct device *dev)
@@ -60,7 +60,7 @@ void device_pm_init(struct device *dev)
 }
 
 /**
- *	device_pm_lock - lock the list of active devices used by the PM core
+ * device_pm_lock - Lock the list of active devices used by the PM core.
  */
 void device_pm_lock(void)
 {
@@ -68,7 +68,7 @@ void device_pm_lock(void)
 }
 
 /**
- *	device_pm_unlock - unlock the list of active devices used by the PM core
+ * device_pm_unlock - Unlock the list of active devices used by the PM core.
  */
 void device_pm_unlock(void)
 {
@@ -76,8 +76,8 @@ void device_pm_unlock(void)
 }
 
 /**
- *	device_pm_add - add a device to the list of active devices
- *	@dev:	Device to be added to the list
+ * device_pm_add - Add a device to the PM core's list of active devices.
+ * @dev: Device to add to the list.
  */
 void device_pm_add(struct device *dev)
 {
@@ -103,10 +103,8 @@ void device_pm_add(struct device *dev)
 }
 
 /**
- *	device_pm_remove - remove a device from the list of active devices
- *	@dev:	Device to be removed from the list
- *
- *	This function also removes the device's PM-related sysfs attributes.
+ * device_pm_remove - Remove a device from the PM core's list of active devices.
+ * @dev: Device to be removed from the list.
  */
 void device_pm_remove(struct device *dev)
 {
@@ -120,9 +118,9 @@ void device_pm_remove(struct device *dev)
 }
 
 /**
- *	device_pm_move_before - move device in dpm_list
- *	@deva:  Device to move in dpm_list
- *	@devb:  Device @deva should come before
+ * device_pm_move_before - Move device in the PM core's list of active devices.
+ * @deva: Device to move in dpm_list.
+ * @devb: Device @deva should come before.
  */
 void device_pm_move_before(struct device *deva, struct device *devb)
 {
@@ -136,9 +134,9 @@ void device_pm_move_before(struct device *deva, struct device *devb)
 }
 
 /**
- *	device_pm_move_after - move device in dpm_list
- *	@deva:  Device to move in dpm_list
- *	@devb:  Device @deva should come after
+ * device_pm_move_after - Move device in the PM core's list of active devices.
+ * @deva: Device to move in dpm_list.
+ * @devb: Device @deva should come after.
  */
 void device_pm_move_after(struct device *deva, struct device *devb)
 {
@@ -152,8 +150,8 @@ void device_pm_move_after(struct device *deva, struct device *devb)
 }
 
 /**
- * 	device_pm_move_last - move device to end of dpm_list
- * 	@dev:   Device to move in dpm_list
+ * device_pm_move_last - Move device to end of the PM core's list of devices.
+ * @dev: Device to move in dpm_list.
  */
 void device_pm_move_last(struct device *dev)
 {
@@ -164,10 +162,10 @@ void device_pm_move_last(struct device *dev)
 }
 
 /**
- *	pm_op - execute the PM operation appropiate for given PM event
- *	@dev:	Device.
- *	@ops:	PM operations to choose from.
- *	@state:	PM transition of the system being carried out.
+ * pm_op - Execute the PM operation appropriate for given PM event.
+ * @dev: Device to handle.
+ * @ops: PM operations to choose from.
+ * @state: PM transition of the system being carried out.
  */
 static int pm_op(struct device *dev,
 		 const struct dev_pm_ops *ops,
@@ -225,13 +223,13 @@ static int pm_op(struct device *dev,
 }
 
 /**
- *	pm_noirq_op - execute the PM operation appropiate for given PM event
- *	@dev:	Device.
- *	@ops:	PM operations to choose from.
- *	@state: PM transition of the system being carried out.
+ * pm_noirq_op - Execute the PM operation appropriate for given PM event.
+ * @dev: Device to handle.
+ * @ops: PM operations to choose from.
+ * @state: PM transition of the system being carried out.
  *
- *	The operation is executed with interrupts disabled by the only remaining
- *	functional CPU in the system.
+ * The driver of @dev will not receive interrupts while this function is being
+ * executed.
  */
 static int pm_noirq_op(struct device *dev,
 			const struct dev_pm_ops *ops,
@@ -329,11 +327,12 @@ static void pm_dev_err(struct device *dev, pm_message_t state, char *info,
 /*------------------------- Resume routines -------------------------*/
 
 /**
- *	device_resume_noirq - Power on one device (early resume).
- *	@dev:	Device.
- *	@state: PM transition of the system being carried out.
+ * device_resume_noirq - Execute an "early resume" callback for given device.
+ * @dev: Device to handle.
+ * @state: PM transition of the system being carried out.
  *
- *	Must be called with interrupts disabled.
+ * The driver of @dev will not receive interrupts while this function is being
+ * executed.
  */
 static int device_resume_noirq(struct device *dev, pm_message_t state)
 {
@@ -355,20 +354,18 @@ static int device_resume_noirq(struct device *dev, pm_message_t state)
 }
 
 /**
- *	dpm_resume_noirq - Power on all regular (non-sysdev) devices.
- *	@state: PM transition of the system being carried out.
- *
- *	Call the "noirq" resume handlers for all devices marked as
- *	DPM_OFF_IRQ and enable device drivers to receive interrupts.
+ * dpm_resume_noirq - Execute "early resume" callbacks for non-sysdev devices.
+ * @state: PM transition of the system being carried out.
  *
- *	Must be called under dpm_list_mtx.  Device drivers should not receive
- *	interrupts while it's being executed.
+ * Call the "noirq" resume handlers for all devices marked as DPM_OFF_IRQ and
+ * enable device drivers to receive interrupts.
  */
 void dpm_resume_noirq(pm_message_t state)
 {
 	struct device *dev;
 
 	mutex_lock(&dpm_list_mtx);
+	transition_started = false;
 	list_for_each_entry(dev, &dpm_list, power.entry)
 		if (dev->power.status > DPM_OFF) {
 			int error;
@@ -384,9 +381,9 @@ void dpm_resume_noirq(pm_message_t state)
 EXPORT_SYMBOL_GPL(dpm_resume_noirq);
 
 /**
- *	device_resume - Restore state for one device.
- *	@dev:	Device.
- *	@state: PM transition of the system being carried out.
+ * device_resume - Execute "resume" callbacks for given device.
+ * @dev: Device to handle.
+ * @state: PM transition of the system being carried out.
  */
 static int device_resume(struct device *dev, pm_message_t state)
 {
@@ -435,11 +432,11 @@ static int device_resume(struct device *dev, pm_message_t state)
 }
 
 /**
- *	dpm_resume - Resume every device.
- *	@state: PM transition of the system being carried out.
+ * dpm_resume - Execute "resume" callbacks for non-sysdev devices.
+ * @state: PM transition of the system being carried out.
  *
- *	Execute the appropriate "resume" callback for all devices the status of
- *	which indicates that they are inactive.
+ * Execute the appropriate "resume" callback for all devices whose status
+ * indicates that they are suspended.
  */
 static void dpm_resume(pm_message_t state)
 {
@@ -447,7 +444,6 @@ static void dpm_resume(pm_message_t state)
 
 	INIT_LIST_HEAD(&list);
 	mutex_lock(&dpm_list_mtx);
-	transition_started = false;
 	while (!list_empty(&dpm_list)) {
 		struct device *dev = to_device(dpm_list.next);
 
@@ -476,9 +472,9 @@ static void dpm_resume(pm_message_t state)
 }
 
 /**
- *	device_complete - Complete a PM transition for given device
- *	@dev:	Device.
- *	@state: PM transition of the system being carried out.
+ * device_complete - Complete a PM transition for given device.
+ * @dev: Device to handle.
+ * @state: PM transition of the system being carried out.
  */
 static void device_complete(struct device *dev, pm_message_t state)
 {
@@ -503,11 +499,11 @@ static void device_complete(struct device *dev, pm_message_t state)
 }
 
 /**
- *	dpm_complete - Complete a PM transition for all devices.
- *	@state: PM transition of the system being carried out.
+ * dpm_complete - Complete a PM transition for all non-sysdev devices.
+ * @state: PM transition of the system being carried out.
  *
- *	Execute the ->complete() callbacks for all devices that are not marked
- *	as DPM_ON.
+ * Execute the ->complete() callbacks for all devices whose PM status is not
+ * DPM_ON (this allows new devices to be registered).
  */
 static void dpm_complete(pm_message_t state)
 {
@@ -537,11 +533,11 @@ static void dpm_complete(pm_message_t state)
 }
 
 /**
- *	dpm_resume_end - Restore state of each device in system.
- *	@state: PM transition of the system being carried out.
+ * dpm_resume_end - Execute "resume" callbacks and complete system transition.
+ * @state: PM transition of the system being carried out.
  *
- *	Resume all the devices, unlock them all, and allow new
- *	devices to be registered once again.
+ * Execute "resume" callbacks for all devices and complete the PM transition of
+ * the system.
  */
 void dpm_resume_end(pm_message_t state)
 {
@@ -555,9 +551,11 @@ EXPORT_SYMBOL_GPL(dpm_resume_end);
 /*------------------------- Suspend routines -------------------------*/
 
 /**
- *	resume_event - return a PM message representing the resume event
- *	               corresponding to given sleep state.
- *	@sleep_state: PM message representing a sleep state.
+ * resume_event - Return a "resume" message for given "suspend" sleep state.
+ * @sleep_state: PM message representing a sleep state.
+ *
+ * Return a PM message representing the resume event corresponding to given
+ * sleep state.
  */
 static pm_message_t resume_event(pm_message_t sleep_state)
 {
@@ -574,11 +572,12 @@ static pm_message_t resume_event(pm_message_t sleep_state)
 }
 
 /**
- *	device_suspend_noirq - Shut down one device (late suspend).
- *	@dev:	Device.
- *	@state: PM transition of the system being carried out.
+ * device_suspend_noirq - Execute a "late suspend" callback for given device.
+ * @dev: Device to handle.
+ * @state: PM transition of the system being carried out.
  *
- *	This is called with interrupts off and only a single CPU running.
+ * The driver of @dev will not receive interrupts while this function is being
+ * executed.
  */
 static int device_suspend_noirq(struct device *dev, pm_message_t state)
 {
@@ -595,13 +594,11 @@ static int device_suspend_noirq(struct device *dev, pm_message_t state)
 }
 
 /**
- *	dpm_suspend_noirq - Power down all regular (non-sysdev) devices.
- *	@state: PM transition of the system being carried out.
- *
- *	Prevent device drivers from receiving interrupts and call the "noirq"
- *	suspend handlers.
+ * dpm_suspend_noirq - Execute "late suspend" callbacks for non-sysdev devices.
+ * @state: PM transition of the system being carried out.
  *
- *	Must be called under dpm_list_mtx.
+ * Prevent device drivers from receiving interrupts and call the "noirq" suspend
+ * handlers for all non-sysdev devices.
  */
 int dpm_suspend_noirq(pm_message_t state)
 {
@@ -626,9 +623,9 @@ int dpm_suspend_noirq(pm_message_t state)
 EXPORT_SYMBOL_GPL(dpm_suspend_noirq);
 
 /**
- *	device_suspend - Save state of one device.
- *	@dev:	Device.
- *	@state: PM transition of the system being carried out.
+ * device_suspend - Execute "suspend" callbacks for given device.
+ * @dev: Device to handle.
+ * @state: PM transition of the system being carried out.
  */
 static int device_suspend(struct device *dev, pm_message_t state)
 {
@@ -675,10 +672,8 @@ static int device_suspend(struct device *dev, pm_message_t state)
 }
 
 /**
- *	dpm_suspend - Suspend every device.
- *	@state: PM transition of the system being carried out.
- *
- *	Execute the appropriate "suspend" callbacks for all devices.
+ * dpm_suspend - Execute "suspend" callbacks for all non-sysdev devices.
+ * @state: PM transition of the system being carried out.
  */
 static int dpm_suspend(pm_message_t state)
 {
@@ -712,9 +707,12 @@ static int dpm_suspend(pm_message_t state)
 }
 
 /**
- *	device_prepare - Execute the ->prepare() callback(s) for given device.
- *	@dev:	Device.
- *	@state: PM transition of the system being carried out.
+ * device_prepare - Prepare a device for system power transition.
+ * @dev: Device to handle.
+ * @state: PM transition of the system being carried out.
+ *
+ * Execute the ->prepare() callback(s) for given device.  No new children of the
+ * device may be registered after this function has returned.
  */
 static int device_prepare(struct device *dev, pm_message_t state)
 {
@@ -750,10 +748,10 @@ static int device_prepare(struct device *dev, pm_message_t state)
 }
 
 /**
- *	dpm_prepare - Prepare all devices for a PM transition.
- *	@state: PM transition of the system being carried out.
+ * dpm_prepare - Prepare all non-sysdev devices for a system PM transition.
+ * @state: PM transition of the system being carried out.
  *
- *	Execute the ->prepare() callback for all devices.
+ * Execute the ->prepare() callback(s) for all devices.
  */
 static int dpm_prepare(pm_message_t state)
 {
@@ -804,10 +802,11 @@ static int dpm_prepare(pm_message_t state)
 }
 
 /**
- *	dpm_suspend_start - Save state and stop all devices in system.
- *	@state: PM transition of the system being carried out.
+ * dpm_suspend_start - Prepare devices for PM transition and suspend them.
+ * @state: PM transition of the system being carried out.
  *
- *	Prepare and suspend all devices.
+ * Prepare all non-sysdev devices for system PM transition and execute "suspend"
+ * callbacks for them.
  */
 int dpm_suspend_start(pm_message_t state)
 {
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 91b753013780..2b387c2260d8 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -4151,7 +4151,7 @@ static void floppy_device_release(struct device *dev)
 {
 }
 
-static int floppy_resume(struct platform_device *dev)
+static int floppy_resume(struct device *dev)
 {
 	int fdc;
 
@@ -4162,10 +4162,15 @@ static int floppy_resume(struct platform_device *dev)
 	return 0;
 }
 
-static struct platform_driver floppy_driver = {
+static struct dev_pm_ops floppy_pm_ops = {
 	.resume = floppy_resume,
+	.restore = floppy_resume,
+};
+
+static struct platform_driver floppy_driver = {
 	.driver = {
 		.name = "floppy",
+		.pm = &floppy_pm_ops,
 	},
 };
 
diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c
index a2ad53e15874..af04f5b049db 100644
--- a/drivers/platform/x86/hp-wmi.c
+++ b/drivers/platform/x86/hp-wmi.c
@@ -53,7 +53,7 @@ MODULE_ALIAS("wmi:5FB7F034-2C63-45e9-BE91-3D44E2C707E4");
 
 static int __init hp_wmi_bios_setup(struct platform_device *device);
 static int __exit hp_wmi_bios_remove(struct platform_device *device);
-static int hp_wmi_resume_handler(struct platform_device *device);
+static int hp_wmi_resume_handler(struct device *device);
 
 struct bios_args {
 	u32 signature;
@@ -94,14 +94,19 @@ static struct rfkill *wifi_rfkill;
 static struct rfkill *bluetooth_rfkill;
 static struct rfkill *wwan_rfkill;
 
+static struct dev_pm_ops hp_wmi_pm_ops = {
+	.resume  = hp_wmi_resume_handler,
+	.restore  = hp_wmi_resume_handler,
+};
+
 static struct platform_driver hp_wmi_driver = {
 	.driver = {
-		   .name = "hp-wmi",
-		   .owner = THIS_MODULE,
+		.name = "hp-wmi",
+		.owner = THIS_MODULE,
+		.pm = &hp_wmi_pm_ops,
 	},
 	.probe = hp_wmi_bios_setup,
 	.remove = hp_wmi_bios_remove,
-	.resume = hp_wmi_resume_handler,
 };
 
 static int hp_wmi_perform_query(int query, int write, int value)
@@ -512,7 +517,7 @@ static int __exit hp_wmi_bios_remove(struct platform_device *device)
 	return 0;
 }
 
-static int hp_wmi_resume_handler(struct platform_device *device)
+static int hp_wmi_resume_handler(struct device *device)
 {
 	/*
 	 * Hardware state may have changed while suspended, so trigger
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 2b6e20df0e52..3b7e04b95bd2 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -213,6 +213,20 @@ struct dev_pm_ops {
 	int (*runtime_idle)(struct device *dev);
 };
 
+/*
+ * Use this if you want to use the same suspend and resume callbacks for suspend
+ * to RAM and hibernation.
+ */
+#define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \
+struct dev_pm_ops name = { \
+	.suspend = suspend_fn, \
+	.resume = resume_fn, \
+	.freeze = suspend_fn, \
+	.thaw = resume_fn, \
+	.poweroff = suspend_fn, \
+	.restore = resume_fn, \
+}
+
 /**
  * PM_EVENT_ messages
  *
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index 638d8bedec14..a0bb09e79867 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -15,10 +15,10 @@
 /**
  * suspend_device_irqs - disable all currently enabled interrupt lines
  *
- * During system-wide suspend or hibernation device interrupts need to be
- * disabled at the chip level and this function is provided for this purpose.
- * It disables all interrupt lines that are enabled at the moment and sets the
- * IRQ_SUSPENDED flag for them.
+ * During system-wide suspend or hibernation device drivers need to be prevented
+ * from receiving interrupts and this function is provided for this purpose.
+ * It marks all interrupt lines in use, except for the timer ones, as disabled
+ * and sets the IRQ_SUSPENDED flag for each of them.
  */
 void suspend_device_irqs(void)
 {
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 81d2e7464893..04b3a83d686f 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -298,8 +298,8 @@ int hibernation_snapshot(int platform_mode)
 	if (error)
 		return error;
 
-	/* Free memory before shutting down devices. */
-	error = swsusp_shrink_memory();
+	/* Preallocate image memory before shutting down devices. */
+	error = hibernate_preallocate_memory();
 	if (error)
 		goto Close;
 
@@ -315,6 +315,10 @@ int hibernation_snapshot(int platform_mode)
 	/* Control returns here after successful restore */
 
  Resume_devices:
+	/* We may need to release the preallocated image pages here. */
+	if (error || !in_suspend)
+		swsusp_free();
+
 	dpm_resume_end(in_suspend ?
 		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
 	resume_console();
@@ -460,11 +464,11 @@ int hibernation_platform_enter(void)
 
 	error = hibernation_ops->prepare();
 	if (error)
-		goto Platofrm_finish;
+		goto Platform_finish;
 
 	error = disable_nonboot_cpus();
 	if (error)
-		goto Platofrm_finish;
+		goto Platform_finish;
 
 	local_irq_disable();
 	sysdev_suspend(PMSG_HIBERNATE);
@@ -476,7 +480,7 @@ int hibernation_platform_enter(void)
 	 * We don't need to reenable the nonboot CPUs or resume consoles, since
 	 * the system is going to be halted anyway.
 	 */
- Platofrm_finish:
+ Platform_finish:
 	hibernation_ops->finish();
 
 	dpm_suspend_noirq(PMSG_RESTORE);
@@ -578,7 +582,10 @@ int hibernate(void)
 		goto Thaw;
 
 	error = hibernation_snapshot(hibernation_mode == HIBERNATION_PLATFORM);
-	if (in_suspend && !error) {
+	if (error)
+		goto Thaw;
+
+	if (in_suspend) {
 		unsigned int flags = 0;
 
 		if (hibernation_mode == HIBERNATION_PLATFORM)
@@ -590,8 +597,8 @@ int hibernate(void)
 			power_down();
 	} else {
 		pr_debug("PM: Image restored successfully.\n");
-		swsusp_free();
 	}
+
  Thaw:
 	thaw_processes();
  Finish:
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 26d5a26f82e3..46c5a26630a3 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -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 int swsusp_shrink_memory(void);
+extern int hibernate_preallocate_memory(void);
 
 /**
  *	Auxiliary structure used for reading the snapshot image data and
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 523a451b45d3..97955b0e44f4 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -233,7 +233,7 @@ static void *chain_alloc(struct chain_allocator *ca, unsigned int size)
 
 #define BM_END_OF_MAP	(~0UL)
 
-#define BM_BITS_PER_BLOCK	(PAGE_SIZE << 3)
+#define BM_BITS_PER_BLOCK	(PAGE_SIZE * BITS_PER_BYTE)
 
 struct bm_block {
 	struct list_head hook;	/* hook into a list of bitmap blocks */
@@ -275,7 +275,7 @@ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free);
 
 /**
  *	create_bm_block_list - create a list of block bitmap objects
- *	@nr_blocks - number of blocks to allocate
+ *	@pages - number of pages to track
  *	@list - list to put the allocated blocks into
  *	@ca - chain allocator to be used for allocating memory
  */
@@ -853,7 +853,7 @@ static unsigned int count_highmem_pages(void)
 	struct zone *zone;
 	unsigned int n = 0;
 
-	for_each_zone(zone) {
+	for_each_populated_zone(zone) {
 		unsigned long pfn, max_zone_pfn;
 
 		if (!is_highmem(zone))
@@ -916,7 +916,7 @@ static unsigned int count_data_pages(void)
 	unsigned long pfn, max_zone_pfn;
 	unsigned int n = 0;
 
-	for_each_zone(zone) {
+	for_each_populated_zone(zone) {
 		if (is_highmem(zone))
 			continue;
 
@@ -1010,7 +1010,7 @@ copy_data_pages(struct memory_bitmap *copy_bm, struct memory_bitmap *orig_bm)
 	struct zone *zone;
 	unsigned long pfn;
 
-	for_each_zone(zone) {
+	for_each_populated_zone(zone) {
 		unsigned long max_zone_pfn;
 
 		mark_free_pages(zone);
@@ -1033,6 +1033,25 @@ copy_data_pages(struct memory_bitmap *copy_bm, struct memory_bitmap *orig_bm)
 static unsigned int nr_copy_pages;
 /* Number of pages needed for saving the original pfns of the image pages */
 static unsigned int nr_meta_pages;
+/*
+ * Numbers of normal and highmem page frames allocated for hibernation image
+ * before suspending devices.
+ */
+unsigned int alloc_normal, alloc_highmem;
+/*
+ * Memory bitmap used for marking saveable pages (during hibernation) or
+ * hibernation image pages (during restore)
+ */
+static struct memory_bitmap orig_bm;
+/*
+ * Memory bitmap used during hibernation for marking allocated page frames that
+ * will contain copies of saveable pages.  During restore it is initially used
+ * for marking hibernation image pages, but then the set bits from it are
+ * duplicated in @orig_bm and it is released.  On highmem systems it is next
+ * used for marking "safe" highmem pages, but it has to be reinitialized for
+ * this purpose.
+ */
+static struct memory_bitmap copy_bm;
 
 /**
  *	swsusp_free - free pages allocated for the suspend.
@@ -1046,7 +1065,7 @@ void swsusp_free(void)
 	struct zone *zone;
 	unsigned long pfn, max_zone_pfn;
 
-	for_each_zone(zone) {
+	for_each_populated_zone(zone) {
 		max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
 		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
 			if (pfn_valid(pfn)) {
@@ -1064,74 +1083,286 @@ void swsusp_free(void)
 	nr_meta_pages = 0;
 	restore_pblist = NULL;
 	buffer = NULL;
+	alloc_normal = 0;
+	alloc_highmem = 0;
 }
 
+/* Helper functions used for the shrinking of memory. */
+
+#define GFP_IMAGE	(GFP_KERNEL | __GFP_NOWARN)
+
 /**
- *	swsusp_shrink_memory -  Try to free as much memory as needed
- *
- *	... but do not OOM-kill anyone
+ * preallocate_image_pages - Allocate a number of pages for hibernation image
+ * @nr_pages: Number of page frames to allocate.
+ * @mask: GFP flags to use for the allocation.
  *
- *	Notice: all userland should be stopped before it is called, or
- *	livelock is possible.
+ * Return value: Number of page frames actually allocated
+ */
+static unsigned long preallocate_image_pages(unsigned long nr_pages, gfp_t mask)
+{
+	unsigned long nr_alloc = 0;
+
+	while (nr_pages > 0) {
+		struct page *page;
+
+		page = alloc_image_page(mask);
+		if (!page)
+			break;
+		memory_bm_set_bit(&copy_bm, page_to_pfn(page));
+		if (PageHighMem(page))
+			alloc_highmem++;
+		else
+			alloc_normal++;
+		nr_pages--;
+		nr_alloc++;
+	}
+
+	return nr_alloc;
+}
+
+static unsigned long preallocate_image_memory(unsigned long nr_pages)
+{
+	return preallocate_image_pages(nr_pages, GFP_IMAGE);
+}
+
+#ifdef CONFIG_HIGHMEM
+static unsigned long preallocate_image_highmem(unsigned long nr_pages)
+{
+	return preallocate_image_pages(nr_pages, GFP_IMAGE | __GFP_HIGHMEM);
+}
+
+/**
+ *  __fraction - Compute (an approximation of) x * (multiplier / base)
  */
+static unsigned long __fraction(u64 x, u64 multiplier, u64 base)
+{
+	x *= multiplier;
+	do_div(x, base);
+	return (unsigned long)x;
+}
+
+static unsigned long preallocate_highmem_fraction(unsigned long nr_pages,
+						unsigned long highmem,
+						unsigned long total)
+{
+	unsigned long alloc = __fraction(nr_pages, highmem, total);
 
-#define SHRINK_BITE	10000
-static inline unsigned long __shrink_memory(long tmp)
+	return preallocate_image_pages(alloc, GFP_IMAGE | __GFP_HIGHMEM);
+}
+#else /* CONFIG_HIGHMEM */
+static inline unsigned long preallocate_image_highmem(unsigned long nr_pages)
 {
-	if (tmp > SHRINK_BITE)
-		tmp = SHRINK_BITE;
-	return shrink_all_memory(tmp);
+	return 0;
 }
 
-int swsusp_shrink_memory(void)
+static inline unsigned long preallocate_highmem_fraction(unsigned long nr_pages,
+						unsigned long highmem,
+						unsigned long total)
+{
+	return 0;
+}
+#endif /* CONFIG_HIGHMEM */
+
+/**
+ * free_unnecessary_pages - Release preallocated pages not needed for the image
+ */
+static void free_unnecessary_pages(void)
+{
+	unsigned long save_highmem, to_free_normal, to_free_highmem;
+
+	to_free_normal = alloc_normal - count_data_pages();
+	save_highmem = count_highmem_pages();
+	if (alloc_highmem > save_highmem) {
+		to_free_highmem = alloc_highmem - save_highmem;
+	} else {
+		to_free_highmem = 0;
+		to_free_normal -= save_highmem - alloc_highmem;
+	}
+
+	memory_bm_position_reset(&copy_bm);
+
+	while (to_free_normal > 0 && to_free_highmem > 0) {
+		unsigned long pfn = memory_bm_next_pfn(&copy_bm);
+		struct page *page = pfn_to_page(pfn);
+
+		if (PageHighMem(page)) {
+			if (!to_free_highmem)
+				continue;
+			to_free_highmem--;
+			alloc_highmem--;
+		} else {
+			if (!to_free_normal)
+				continue;
+			to_free_normal--;
+			alloc_normal--;
+		}
+		memory_bm_clear_bit(&copy_bm, pfn);
+		swsusp_unset_page_forbidden(page);
+		swsusp_unset_page_free(page);
+		__free_page(page);
+	}
+}
+
+/**
+ * minimum_image_size - Estimate the minimum acceptable size of an image
+ * @saveable: Number of saveable pages in the system.
+ *
+ * We want to avoid attempting to free too much memory too hard, so estimate the
+ * minimum acceptable size of a hibernation image to use as the lower limit for
+ * preallocating memory.
+ *
+ * We assume that the minimum image size should be proportional to
+ *
+ * [number of saveable pages] - [number of pages that can be freed in theory]
+ *
+ * where the second term is the sum of (1) reclaimable slab pages, (2) active
+ * and (3) inactive anonymouns pages, (4) active and (5) inactive file pages,
+ * minus mapped file pages.
+ */
+static unsigned long minimum_image_size(unsigned long saveable)
+{
+	unsigned long size;
+
+	size = global_page_state(NR_SLAB_RECLAIMABLE)
+		+ global_page_state(NR_ACTIVE_ANON)
+		+ global_page_state(NR_INACTIVE_ANON)
+		+ global_page_state(NR_ACTIVE_FILE)
+		+ global_page_state(NR_INACTIVE_FILE)
+		- global_page_state(NR_FILE_MAPPED);
+
+	return saveable <= size ? 0 : saveable - size;
+}
+
+/**
+ * hibernate_preallocate_memory - Preallocate memory for hibernation image
+ *
+ * To create a hibernation image it is necessary to make a copy of every page
+ * frame in use.  We also need a number of page frames to be free during
+ * hibernation for allocations made while saving the image and for device
+ * drivers, in case they need to allocate memory from their hibernation
+ * callbacks (these two numbers are given by PAGES_FOR_IO and SPARE_PAGES,
+ * respectively, both of which are rough estimates).  To make this happen, we
+ * compute the total number of available page frames and allocate at least
+ *
+ * ([page frames total] + PAGES_FOR_IO + [metadata pages]) / 2 + 2 * SPARE_PAGES
+ *
+ * of them, which corresponds to the maximum size of a hibernation image.
+ *
+ * If image_size is set below the number following from the above formula,
+ * the preallocation of memory is continued until the total number of saveable
+ * pages in the system is below the requested image size or the minimum
+ * acceptable image size returned by minimum_image_size(), whichever is greater.
+ */
+int hibernate_preallocate_memory(void)
 {
-	long tmp;
 	struct zone *zone;
-	unsigned long pages = 0;
-	unsigned int i = 0;
-	char *p = "-\\|/";
+	unsigned long saveable, size, max_size, count, highmem, pages = 0;
+	unsigned long alloc, save_highmem, pages_highmem;
 	struct timeval start, stop;
+	int error;
 
-	printk(KERN_INFO "PM: Shrinking memory...  ");
+	printk(KERN_INFO "PM: Preallocating image 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;
+	error = memory_bm_create(&orig_bm, GFP_IMAGE, PG_ANY);
+	if (error)
+		goto err_out;
 
-		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);
+	error = memory_bm_create(&copy_bm, GFP_IMAGE, PG_ANY);
+	if (error)
+		goto err_out;
+
+	alloc_normal = 0;
+	alloc_highmem = 0;
+
+	/* Count the number of saveable data pages. */
+	save_highmem = count_highmem_pages();
+	saveable = count_data_pages();
+
+	/*
+	 * Compute the total number of page frames we can use (count) and the
+	 * number of pages needed for image metadata (size).
+	 */
+	count = saveable;
+	saveable += save_highmem;
+	highmem = save_highmem;
+	size = 0;
+	for_each_populated_zone(zone) {
+		size += snapshot_additional_pages(zone);
+		if (is_highmem(zone))
+			highmem += zone_page_state(zone, NR_FREE_PAGES);
+		else
+			count += zone_page_state(zone, NR_FREE_PAGES);
+	}
+	count += highmem;
+	count -= totalreserve_pages;
+
+	/* Compute the maximum number of saveable pages to leave in memory. */
+	max_size = (count - (size + PAGES_FOR_IO)) / 2 - 2 * SPARE_PAGES;
+	size = DIV_ROUND_UP(image_size, PAGE_SIZE);
+	if (size > max_size)
+		size = max_size;
+	/*
+	 * If the maximum is not less than the current number of saveable pages
+	 * in memory, allocate page frames for the image and we're done.
+	 */
+	if (size >= saveable) {
+		pages = preallocate_image_highmem(save_highmem);
+		pages += preallocate_image_memory(saveable - pages);
+		goto out;
+	}
+
+	/* Estimate the minimum size of the image. */
+	pages = minimum_image_size(saveable);
+	if (size < pages)
+		size = min_t(unsigned long, pages, max_size);
+
+	/*
+	 * Let the memory management subsystem know that we're going to need a
+	 * large number of page frames to allocate and make it free some memory.
+	 * NOTE: If this is not done, performance will be hurt badly in some
+	 * test cases.
+	 */
+	shrink_all_memory(saveable - size);
+
+	/*
+	 * The number of saveable pages in memory was too high, so apply some
+	 * pressure to decrease it.  First, make room for the largest possible
+	 * image and fail if that doesn't work.  Next, try to decrease the size
+	 * of the image as much as indicated by 'size' using allocations from
+	 * highmem and non-highmem zones separately.
+	 */
+	pages_highmem = preallocate_image_highmem(highmem / 2);
+	alloc = (count - max_size) - pages_highmem;
+	pages = preallocate_image_memory(alloc);
+	if (pages < alloc)
+		goto err_out;
+	size = max_size - size;
+	alloc = size;
+	size = preallocate_highmem_fraction(size, highmem, count);
+	pages_highmem += size;
+	alloc -= size;
+	pages += preallocate_image_memory(alloc);
+	pages += pages_highmem;
+
+	/*
+	 * We only need as many page frames for the image as there are saveable
+	 * pages in memory, but we have allocated more.  Release the excessive
+	 * ones now.
+	 */
+	free_unnecessary_pages();
+
+ out:
 	do_gettimeofday(&stop);
-	printk("\bdone (%lu pages freed)\n", pages);
-	swsusp_show_speed(&start, &stop, pages, "Freed");
+	printk(KERN_CONT "done (allocated %lu pages)\n", pages);
+	swsusp_show_speed(&start, &stop, pages, "Allocated");
 
 	return 0;
+
+ err_out:
+	printk(KERN_CONT "\n");
+	swsusp_free();
+	return -ENOMEM;
 }
 
 #ifdef CONFIG_HIGHMEM
@@ -1142,7 +1373,7 @@ int swsusp_shrink_memory(void)
 
 static unsigned int count_pages_for_highmem(unsigned int nr_highmem)
 {
-	unsigned int free_highmem = count_free_highmem_pages();
+	unsigned int free_highmem = count_free_highmem_pages() + alloc_highmem;
 
 	if (free_highmem >= nr_highmem)
 		nr_highmem = 0;
@@ -1164,19 +1395,17 @@ count_pages_for_highmem(unsigned int nr_highmem) { return 0; }
 static int enough_free_mem(unsigned int nr_pages, unsigned int nr_highmem)
 {
 	struct zone *zone;
-	unsigned int free = 0, meta = 0;
+	unsigned int free = alloc_normal;
 
-	for_each_zone(zone) {
-		meta += snapshot_additional_pages(zone);
+	for_each_populated_zone(zone)
 		if (!is_highmem(zone))
 			free += zone_page_state(zone, NR_FREE_PAGES);
-	}
 
 	nr_pages += count_pages_for_highmem(nr_highmem);
-	pr_debug("PM: Normal pages needed: %u + %u + %u, available pages: %u\n",
-		nr_pages, PAGES_FOR_IO, meta, free);
+	pr_debug("PM: Normal pages needed: %u + %u, available pages: %u\n",
+		nr_pages, PAGES_FOR_IO, free);
 
-	return free > nr_pages + PAGES_FOR_IO + meta;
+	return free > nr_pages + PAGES_FOR_IO;
 }
 
 #ifdef CONFIG_HIGHMEM
@@ -1198,7 +1427,7 @@ static inline int get_highmem_buffer(int safe_needed)
  */
 
 static inline unsigned int
-alloc_highmem_image_pages(struct memory_bitmap *bm, unsigned int nr_highmem)
+alloc_highmem_pages(struct memory_bitmap *bm, unsigned int nr_highmem)
 {
 	unsigned int to_alloc = count_free_highmem_pages();
 
@@ -1218,7 +1447,7 @@ alloc_highmem_image_pages(struct memory_bitmap *bm, unsigned int nr_highmem)
 static inline int get_highmem_buffer(int safe_needed) { return 0; }
 
 static inline unsigned int
-alloc_highmem_image_pages(struct memory_bitmap *bm, unsigned int n) { return 0; }
+alloc_highmem_pages(struct memory_bitmap *bm, unsigned int n) { return 0; }
 #endif /* CONFIG_HIGHMEM */
 
 /**
@@ -1237,51 +1466,36 @@ static int
 swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm,
 		unsigned int nr_pages, unsigned int nr_highmem)
 {
-	int error;
-
-	error = memory_bm_create(orig_bm, GFP_ATOMIC | __GFP_COLD, PG_ANY);
-	if (error)
-		goto Free;
-
-	error = memory_bm_create(copy_bm, GFP_ATOMIC | __GFP_COLD, PG_ANY);
-	if (error)
-		goto Free;
+	int error = 0;
 
 	if (nr_highmem > 0) {
 		error = get_highmem_buffer(PG_ANY);
 		if (error)
-			goto Free;
-
-		nr_pages += alloc_highmem_image_pages(copy_bm, nr_highmem);
+			goto err_out;
+		if (nr_highmem > alloc_highmem) {
+			nr_highmem -= alloc_highmem;
+			nr_pages += alloc_highmem_pages(copy_bm, nr_highmem);
+		}
 	}
-	while (nr_pages-- > 0) {
-		struct page *page = alloc_image_page(GFP_ATOMIC | __GFP_COLD);
-
-		if (!page)
-			goto Free;
+	if (nr_pages > alloc_normal) {
+		nr_pages -= alloc_normal;
+		while (nr_pages-- > 0) {
+			struct page *page;
 
-		memory_bm_set_bit(copy_bm, page_to_pfn(page));
+			page = alloc_image_page(GFP_ATOMIC | __GFP_COLD);
+			if (!page)
+				goto err_out;
+			memory_bm_set_bit(copy_bm, page_to_pfn(page));
+		}
 	}
+
 	return 0;
 
- Free:
+ err_out:
 	swsusp_free();
-	return -ENOMEM;
+	return error;
 }
 
-/* Memory bitmap used for marking saveable pages (during suspend) or the
- * suspend image pages (during resume)
- */
-static struct memory_bitmap orig_bm;
-/* Memory bitmap used on suspend for marking allocated pages that will contain
- * the copies of saveable pages.  During resume it is initially used for
- * marking the suspend image pages, but then its set bits are duplicated in
- * @orig_bm and it is released.  Next, on systems with high memory, it may be
- * used for marking "safe" highmem pages, but it has to be reinitialized for
- * this purpose.
- */
-static struct memory_bitmap copy_bm;
-
 asmlinkage int swsusp_save(void)
 {
 	unsigned int nr_pages, nr_highmem;
@@ -1474,7 +1688,7 @@ static int mark_unsafe_pages(struct memory_bitmap *bm)
 	unsigned long pfn, max_zone_pfn;
 
 	/* Clear page flags */
-	for_each_zone(zone) {
+	for_each_populated_zone(zone) {
 		max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
 		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
 			if (pfn_valid(pfn))