Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/suspend-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/suspend-2.6: (23 commits)
  at_hdmac: Rework suspend_late()/resume_early()
  PM: Reset transition_started at dpm_resume_noirq
  PM: Update kerneldoc comments in drivers/base/power/main.c
  PM: Add convenience macro to make switching to dev_pm_ops less error-prone
  hp-wmi: Switch driver to dev_pm_ops
  floppy: Switch driver to dev_pm_ops
  PM: Trivial fixes
  PM / Hibernate / Memory hotplug: Always use for_each_populated_zone()
  PM/Hibernate: Do not try to allocate too much memory too hard (rev. 2)
  PM/Hibernate: Do not release preallocated memory unnecessarily (rev. 2)
  PM/Hibernate: Rework shrinking of memory
  PM: Fix typo in label name s/Platofrm_finish/Platform_finish/
  PM: Run-time PM platform device bus support
  PM: Introduce core framework for run-time PM of I/O devices (rev. 17)
  Driver Core: Make PM operations a const pointer
  PM: Remove platform device suspend_late()/resume_early() V2
  USB: Rework musb suspend()/resume_early()
  I2C: Rework i2c-s3c2410 suspend_late()/resume() V2
  I2C: Rework i2c-pxa suspend_late()/resume_early()
  DMA: Rework txx9dmac suspend_late()/resume_early()
  ...

Fix trivial conflict in drivers/base/platform.c (due to same
constification patch being merged in both sides, along with some other
PM work in the PM branch)

Documentation/power/runtime_pm.txt

+Run-time Power Management Framework for I/O Devices
+
+(C) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+
+1. Introduction
+
+Support for run-time power management (run-time PM) of I/O devices is provided
+at the power management core (PM core) level by means of:
+
+* The power management workqueue pm_wq in which bus types and device drivers can
+  put their PM-related work items.  It is strongly recommended that pm_wq be
+  used for queuing all work items related to run-time PM, because this allows
+  them to be synchronized with system-wide power transitions (suspend to RAM,
+  hibernation and resume from system sleep states).  pm_wq is declared in
+  include/linux/pm_runtime.h and defined in kernel/power/main.c.
+
+* A number of run-time PM fields in the 'power' member of 'struct device' (which
+  is of the type 'struct dev_pm_info', defined in include/linux/pm.h) that can
+  be used for synchronizing run-time PM operations with one another.
+
+* Three device run-time PM callbacks in 'struct dev_pm_ops' (defined in
+  include/linux/pm.h).
+
+* A set of helper functions defined in drivers/base/power/runtime.c that can be
+  used for carrying out run-time PM operations in such a way that the
+  synchronization between them is taken care of by the PM core.  Bus types and
+  device drivers are encouraged to use these functions.
+
+The run-time PM callbacks present in 'struct dev_pm_ops', the device run-time PM
+fields of 'struct dev_pm_info' and the core helper functions provided for
+run-time PM are described below.
+
+2. Device Run-time PM Callbacks
+
+There are three device run-time PM callbacks defined in 'struct dev_pm_ops':
+
+struct dev_pm_ops {
+	...
+	int (*runtime_suspend)(struct device *dev);
+	int (*runtime_resume)(struct device *dev);
+	void (*runtime_idle)(struct device *dev);
+	...
+};
+
+The ->runtime_suspend() callback is executed by the PM core for the bus type of
+the device being suspended.  The bus type's callback is then _entirely_
+_responsible_ for handling the device as appropriate, which may, but need not
+include executing the device driver's own ->runtime_suspend() callback (from the
+PM core's point of view it is not necessary to implement a ->runtime_suspend()
+callback in a device driver as long as the bus type's ->runtime_suspend() knows
+what to do to handle the device).
+
+  * Once the bus type's ->runtime_suspend() callback has completed successfully
+    for given device, the PM core regards the device as suspended, which need
+    not mean that the device has been put into a low power state.  It is
+    supposed to mean, however, that the device will not process data and will
+    not communicate with the CPU(s) and RAM until its bus type's
+    ->runtime_resume() callback is executed for it.  The run-time PM status of
+    a device after successful execution of its bus type's ->runtime_suspend()
+    callback is 'suspended'.
+
+  * If the bus type's ->runtime_suspend() callback returns -EBUSY or -EAGAIN,
+    the device's run-time PM status is supposed to be 'active', which means that
+    the device _must_ be fully operational afterwards.
+
+  * If the bus type's ->runtime_suspend() callback returns an error code
+    different from -EBUSY or -EAGAIN, the PM core regards this as a fatal
+    error and will refuse to run the helper functions described in Section 4
+    for the device, until the status of it is directly set either to 'active'
+    or to 'suspended' (the PM core provides special helper functions for this
+    purpose).
+
+In particular, if the driver requires remote wakeup capability for proper
+functioning and device_may_wakeup() returns 'false' for the device, then
+->runtime_suspend() should return -EBUSY.  On the other hand, if
+device_may_wakeup() returns 'true' for the device and the device is put
+into a low power state during the execution of its bus type's
+->runtime_suspend(), it is expected that remote wake-up (i.e. hardware mechanism
+allowing the device to request a change of its power state, such as PCI PME)
+will be enabled for the device.  Generally, remote wake-up should be enabled
+for all input devices put into a low power state at run time.
+
+The ->runtime_resume() callback is executed by the PM core for the bus type of
+the device being woken up.  The bus type's callback is then _entirely_
+_responsible_ for handling the device as appropriate, which may, but need not
+include executing the device driver's own ->runtime_resume() callback (from the
+PM core's point of view it is not necessary to implement a ->runtime_resume()
+callback in a device driver as long as the bus type's ->runtime_resume() knows
+what to do to handle the device).
+
+  * Once the bus type's ->runtime_resume() callback has completed successfully,
+    the PM core regards the device as fully operational, which means that the
+    device _must_ be able to complete I/O operations as needed.  The run-time
+    PM status of the device is then 'active'.
+
+  * If the bus type's ->runtime_resume() callback returns an error code, the PM
+    core regards this as a fatal error and will refuse to run the helper
+    functions described in Section 4 for the device, until its status is
+    directly set either to 'active' or to 'suspended' (the PM core provides
+    special helper functions for this purpose).
+
+The ->runtime_idle() callback is executed by the PM core for the bus type of
+given device whenever the device appears to be idle, which is indicated to the
+PM core by two counters, the device's usage counter and the counter of 'active'
+children of the device.
+
+  * If any of these counters is decreased using a helper function provided by
+    the PM core and it turns out to be equal to zero, the other counter is
+    checked.  If that counter also is equal to zero, the PM core executes the
+    device bus type's ->runtime_idle() callback (with the device as an
+    argument).
+
+The action performed by a bus type's ->runtime_idle() callback is totally
+dependent on the bus type in question, but the expected and recommended action
+is to check if the device can be suspended (i.e. if all of the conditions
+necessary for suspending the device are satisfied) and to queue up a suspend
+request for the device in that case.
+
+The helper functions provided by the PM core, described in Section 4, guarantee
+that the following constraints are met with respect to the bus type's run-time
+PM callbacks:
+
+(1) The callbacks are mutually exclusive (e.g. it is forbidden to execute
+    ->runtime_suspend() in parallel with ->runtime_resume() or with another
+    instance of ->runtime_suspend() for the same device) with the exception that
+    ->runtime_suspend() or ->runtime_resume() can be executed in parallel with
+    ->runtime_idle() (although ->runtime_idle() will not be started while any
+    of the other callbacks is being executed for the same device).
+
+(2) ->runtime_idle() and ->runtime_suspend() can only be executed for 'active'
+    devices (i.e. the PM core will only execute ->runtime_idle() or
+    ->runtime_suspend() for the devices the run-time PM status of which is
+    'active').
+
+(3) ->runtime_idle() and ->runtime_suspend() can only be executed for a device
+    the usage counter of which is equal to zero _and_ either the counter of
+    'active' children of which is equal to zero, or the 'power.ignore_children'
+    flag of which is set.
+
+(4) ->runtime_resume() can only be executed for 'suspended' devices  (i.e. the
+    PM core will only execute ->runtime_resume() for the devices the run-time
+    PM status of which is 'suspended').
+
+Additionally, the helper functions provided by the PM core obey the following
+rules:
+
+  * If ->runtime_suspend() is about to be executed or there's a pending request
+    to execute it, ->runtime_idle() will not be executed for the same device.
+
+  * A request to execute or to schedule the execution of ->runtime_suspend()
+    will cancel any pending requests to execute ->runtime_idle() for the same
+    device.
+
+  * If ->runtime_resume() is about to be executed or there's a pending request
+    to execute it, the other callbacks will not be executed for the same device.
+
+  * A request to execute ->runtime_resume() will cancel any pending or
+    scheduled requests to execute the other callbacks for the same device.
+
+3. Run-time PM Device Fields
+
+The following device run-time PM fields are present in 'struct dev_pm_info', as
+defined in include/linux/pm.h:
+
+  struct timer_list suspend_timer;
+    - timer used for scheduling (delayed) suspend request
+
+  unsigned long timer_expires;
+    - timer expiration time, in jiffies (if this is different from zero, the
+      timer is running and will expire at that time, otherwise the timer is not
+      running)
+
+  struct work_struct work;
+    - work structure used for queuing up requests (i.e. work items in pm_wq)
+
+  wait_queue_head_t wait_queue;
+    - wait queue used if any of the helper functions needs to wait for another
+      one to complete
+
+  spinlock_t lock;
+    - lock used for synchronisation
+
+  atomic_t usage_count;
+    - the usage counter of the device
+
+  atomic_t child_count;
+    - the count of 'active' children of the device
+
+  unsigned int ignore_children;
+    - if set, the value of child_count is ignored (but still updated)
+
+  unsigned int disable_depth;
+    - used for disabling the helper funcions (they work normally if this is
+      equal to zero); the initial value of it is 1 (i.e. run-time PM is
+      initially disabled for all devices)
+
+  unsigned int runtime_error;
+    - if set, there was a fatal error (one of the callbacks returned error code
+      as described in Section 2), so the helper funtions will not work until
+      this flag is cleared; this is the error code returned by the failing
+      callback
+
+  unsigned int idle_notification;
+    - if set, ->runtime_idle() is being executed
+
+  unsigned int request_pending;
+    - if set, there's a pending request (i.e. a work item queued up into pm_wq)
+
+  enum rpm_request request;
+    - type of request that's pending (valid if request_pending is set)
+
+  unsigned int deferred_resume;
+    - set if ->runtime_resume() is about to be run while ->runtime_suspend() is
+      being executed for that device and it is not practical to wait for the
+      suspend to complete; means "start a resume as soon as you've suspended"
+
+  enum rpm_status runtime_status;
+    - the run-time PM status of the device; this field's initial value is
+      RPM_SUSPENDED, which means that each device is initially regarded by the
+      PM core as 'suspended', regardless of its real hardware status
+
+All of the above fields are members of the 'power' member of 'struct device'.
+
+4. Run-time PM Device Helper Functions
+
+The following run-time PM helper functions are defined in
+drivers/base/power/runtime.c and include/linux/pm_runtime.h:
+
+  void pm_runtime_init(struct device *dev);
+    - initialize the device run-time PM fields in 'struct dev_pm_info'
+
+  void pm_runtime_remove(struct device *dev);
+    - make sure that the run-time PM of the device will be disabled after
+      removing the device from device hierarchy
+
+  int pm_runtime_idle(struct device *dev);
+    - execute ->runtime_idle() for the device's bus type; returns 0 on success
+      or error code on failure, where -EINPROGRESS means that ->runtime_idle()
+      is already being executed
+
+  int pm_runtime_suspend(struct device *dev);
+    - execute ->runtime_suspend() for the device's bus type; returns 0 on
+      success, 1 if the device's run-time PM status was already 'suspended', or
+      error code on failure, where -EAGAIN or -EBUSY means it is safe to attempt
+      to suspend the device again in future
+
+  int pm_runtime_resume(struct device *dev);
+    - execute ->runtime_resume() for the device's bus type; returns 0 on
+      success, 1 if the device's run-time PM status was already 'active' or
+      error code on failure, where -EAGAIN means it may be safe to attempt to
+      resume the device again in future, but 'power.runtime_error' should be
+      checked additionally
+
+  int pm_request_idle(struct device *dev);
+    - submit a request to execute ->runtime_idle() for the device's bus type
+      (the request is represented by a work item in pm_wq); returns 0 on success
+      or error code if the request has not been queued up
+
+  int pm_schedule_suspend(struct device *dev, unsigned int delay);
+    - schedule the execution of ->runtime_suspend() for the device's bus type
+      in future, where 'delay' is the time to wait before queuing up a suspend
+      work item in pm_wq, in milliseconds (if 'delay' is zero, the work item is
+      queued up immediately); returns 0 on success, 1 if the device's PM
+      run-time status was already 'suspended', or error code if the request
+      hasn't been scheduled (or queued up if 'delay' is 0); if the execution of
+      ->runtime_suspend() is already scheduled and not yet expired, the new
+      value of 'delay' will be used as the time to wait
+
+  int pm_request_resume(struct device *dev);
+    - submit a request to execute ->runtime_resume() for the device's bus type
+      (the request is represented by a work item in pm_wq); returns 0 on
+      success, 1 if the device's run-time PM status was already 'active', or
+      error code if the request hasn't been queued up
+
+  void pm_runtime_get_noresume(struct device *dev);
+    - increment the device's usage counter
+
+  int pm_runtime_get(struct device *dev);
+    - increment the device's usage counter, run pm_request_resume(dev) and
+      return its result
+
+  int pm_runtime_get_sync(struct device *dev);
+    - increment the device's usage counter, run pm_runtime_resume(dev) and
+      return its result
+
+  void pm_runtime_put_noidle(struct device *dev);
+    - decrement the device's usage counter
+
+  int pm_runtime_put(struct device *dev);
+    - decrement the device's usage counter, run pm_request_idle(dev) and return
+      its result
+
+  int pm_runtime_put_sync(struct device *dev);
+    - decrement the device's usage counter, run pm_runtime_idle(dev) and return
+      its result
+
+  void pm_runtime_enable(struct device *dev);
+    - enable the run-time PM helper functions to run the device bus type's
+      run-time PM callbacks described in Section 2
+
+  int pm_runtime_disable(struct device *dev);
+    - prevent the run-time PM helper functions from running the device bus
+      type's run-time PM callbacks, make sure that all of the pending run-time
+      PM operations on the device are either completed or canceled; returns
+      1 if there was a resume request pending and it was necessary to execute
+      ->runtime_resume() for the device's bus type to satisfy that request,
+      otherwise 0 is returned
+
+  void pm_suspend_ignore_children(struct device *dev, bool enable);
+    - set/unset the power.ignore_children flag of the device
+
+  int pm_runtime_set_active(struct device *dev);
+    - clear the device's 'power.runtime_error' flag, set the device's run-time
+      PM status to 'active' and update its parent's counter of 'active'
+      children as appropriate (it is only valid to use this function if
+      'power.runtime_error' is set or 'power.disable_depth' is greater than
+      zero); it will fail and return error code if the device has a parent
+      which is not active and the 'power.ignore_children' flag of which is unset
+
+  void pm_runtime_set_suspended(struct device *dev);
+    - clear the device's 'power.runtime_error' flag, set the device's run-time
+      PM status to 'suspended' and update its parent's counter of 'active'
+      children as appropriate (it is only valid to use this function if
+      'power.runtime_error' is set or 'power.disable_depth' is greater than
+      zero)
+
+It is safe to execute the following helper functions from interrupt context:
+
+pm_request_idle()
+pm_schedule_suspend()
+pm_request_resume()
+pm_runtime_get_noresume()
+pm_runtime_get()
+pm_runtime_put_noidle()
+pm_runtime_put()
+pm_suspend_ignore_children()
+pm_runtime_set_active()
+pm_runtime_set_suspended()
+pm_runtime_enable()
+
+5. Run-time PM Initialization, Device Probing and Removal
+
+Initially, the run-time PM is disabled for all devices, which means that the
+majority of the run-time PM helper funtions described in Section 4 will return
+-EAGAIN until pm_runtime_enable() is called for the device.
+
+In addition to that, the initial run-time PM status of all devices is
+'suspended', but it need not reflect the actual physical state of the device.
+Thus, if the device is initially active (i.e. it is able to process I/O), its
+run-time PM status must be changed to 'active', with the help of
+pm_runtime_set_active(), before pm_runtime_enable() is called for the device.
+
+However, if the device has a parent and the parent's run-time PM is enabled,
+calling pm_runtime_set_active() for the device will affect the parent, unless
+the parent's 'power.ignore_children' flag is set.  Namely, in that case the
+parent won't be able to suspend at run time, using the PM core's helper
+functions, as long as the child's status is 'active', even if the child's
+run-time PM is still disabled (i.e. pm_runtime_enable() hasn't been called for
+the child yet or pm_runtime_disable() has been called for it).  For this reason,
+once pm_runtime_set_active() has been called for the device, pm_runtime_enable()
+should be called for it too as soon as reasonably possible or its run-time PM
+status should be changed back to 'suspended' with the help of
+pm_runtime_set_suspended().
+
+If the default initial run-time PM status of the device (i.e. 'suspended')
+reflects the actual state of the device, its bus type's or its driver's
+->probe() callback will likely need to wake it up using one of the PM core's
+helper functions described in Section 4.  In that case, pm_runtime_resume()
+should be used.  Of course, for this purpose the device's run-time PM has to be
+enabled earlier by calling pm_runtime_enable().
+
+If the device bus type's or driver's ->probe() or ->remove() callback runs
+pm_runtime_suspend() or pm_runtime_idle() or their asynchronous counterparts,
+they will fail returning -EAGAIN, because the device's usage counter is
+incremented by the core before executing ->probe() and ->remove().  Still, it
+may be desirable to suspend the device as soon as ->probe() or ->remove() has
+finished, so the PM core uses pm_runtime_idle_sync() to invoke the device bus
+type's ->runtime_idle() callback at that time.

arch/arm/include/asm/device.h

@@ -12,4 +12,7 @@ struct dev_archdata {
 #endif
 };
 
+struct pdev_archdata {
+};
+
 #endif

arch/arm/plat-omap/debug-leds.c

@@ -281,24 +281,27 @@ static int /* __init */ fpga_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int fpga_suspend_late(struct platform_device *pdev, pm_message_t mesg)
+static int fpga_suspend_noirq(struct device *dev)
 {
 	__raw_writew(~0, &fpga->leds);
 	return 0;
 }
 
-static int fpga_resume_early(struct platform_device *pdev)
+static int fpga_resume_noirq(struct device *dev)
 {
 	__raw_writew(~hw_led_state, &fpga->leds);
 	return 0;
 }
 
+static struct dev_pm_ops fpga_dev_pm_ops = {
+	.suspend_noirq = fpga_suspend_noirq,
+	.resume_noirq = fpga_resume_noirq,
+};
 
 static struct platform_driver led_driver = {
 	.driver.name	= "omap_dbg_led",
+	.driver.pm	= &fpga_dev_pm_ops,
 	.probe		= fpga_probe,
-	.suspend_late	= fpga_suspend_late,
-	.resume_early	= fpga_resume_early,
 };
 
 static int __init fpga_init(void)

arch/arm/plat-omap/gpio.c

@@ -1418,8 +1418,9 @@ static struct irq_chip mpuio_irq_chip = {
 
 #include <linux/platform_device.h>
 
-static int omap_mpuio_suspend_late(struct platform_device *pdev, pm_message_t mesg)
+static int omap_mpuio_suspend_noirq(struct device *dev)
 {
+	struct platform_device *pdev = to_platform_device(dev);
 	struct gpio_bank	*bank = platform_get_drvdata(pdev);
 	void __iomem		*mask_reg = bank->base + OMAP_MPUIO_GPIO_MASKIT;
 	unsigned long		flags;
@@ -1432,8 +1433,9 @@ static int omap_mpuio_suspend_late(struct platform_device *pdev, pm_message_t me
 	return 0;
 }
 
-static int omap_mpuio_resume_early(struct platform_device *pdev)
+static int omap_mpuio_resume_noirq(struct device *dev)
 {
+	struct platform_device *pdev = to_platform_device(dev);
 	struct gpio_bank	*bank = platform_get_drvdata(pdev);
 	void __iomem		*mask_reg = bank->base + OMAP_MPUIO_GPIO_MASKIT;
 	unsigned long		flags;
@@ -1445,14 +1447,18 @@ static int omap_mpuio_resume_early(struct platform_device *pdev)
 	return 0;
 }
 
+static struct dev_pm_ops omap_mpuio_dev_pm_ops = {
+	.suspend_noirq = omap_mpuio_suspend_noirq,
+	.resume_noirq = omap_mpuio_resume_noirq,
+};
+
 /* use platform_driver for this, now that there's no longer any
  * point to sys_device (other than not disturbing old code).
  */
 static struct platform_driver omap_mpuio_driver = {
-	.suspend_late	= omap_mpuio_suspend_late,
-	.resume_early	= omap_mpuio_resume_early,
 	.driver		= {
 		.name	= "mpuio",
+		.pm	= &omap_mpuio_dev_pm_ops,
 	},
 };
 

arch/ia64/include/asm/device.h

@@ -15,4 +15,7 @@ struct dev_archdata {
 #endif
 };
 
+struct pdev_archdata {
+};
+
 #endif /* _ASM_IA64_DEVICE_H */

arch/microblaze/include/asm/device.h

@@ -16,6 +16,9 @@ struct dev_archdata {
 	struct device_node	*of_node;
 };
 
+struct pdev_archdata {
+};
+
 #endif /* _ASM_MICROBLAZE_DEVICE_H */
 
 

arch/powerpc/include/asm/device.h

@@ -30,4 +30,7 @@ dev_archdata_get_node(const struct dev_archdata *ad)
 	return ad->of_node;
 }
 
+struct pdev_archdata {
+};
+
 #endif /* _ASM_POWERPC_DEVICE_H */

arch/sparc/include/asm/device.h

@@ -32,4 +32,7 @@ dev_archdata_get_node(const struct dev_archdata *ad)
 	return ad->prom_node;
 }
 
+struct pdev_archdata {
+};
+
 #endif /* _ASM_SPARC_DEVICE_H */

arch/x86/include/asm/device.h

@@ -13,4 +13,7 @@ struct dma_map_ops *dma_ops;
 #endif
 };
 
+struct pdev_archdata {
+};
+
 #endif /* _ASM_X86_DEVICE_H */

drivers/base/dd.c

@@ -23,6 +23,7 @@
 #include <linux/kthread.h>
 #include <linux/wait.h>
 #include <linux/async.h>
+#include <linux/pm_runtime.h>
 
 #include "base.h"
 #include "power/power.h"
@@ -202,7 +203,10 @@ int driver_probe_device(struct device_driver *drv, struct device *dev)
 	pr_debug("bus: '%s': %s: matched device %s with driver %s\n",
 		 drv->bus->name, __func__, dev_name(dev), drv->name);
 
+	pm_runtime_get_noresume(dev);
+	pm_runtime_barrier(dev);
 	ret = really_probe(dev, drv);
+	pm_runtime_put_sync(dev);
 
 	return ret;
 }
@@ -245,7 +249,9 @@ int device_attach(struct device *dev)
 			ret = 0;
 		}
 	} else {
+		pm_runtime_get_noresume(dev);
 		ret = bus_for_each_drv(dev->bus, NULL, dev, __device_attach);
+		pm_runtime_put_sync(dev);
 	}
 	up(&dev->sem);
 	return ret;
@@ -306,6 +312,9 @@ static void __device_release_driver(struct device *dev)
 
 	drv = dev->driver;
 	if (drv) {
+		pm_runtime_get_noresume(dev);
+		pm_runtime_barrier(dev);
+
 		driver_sysfs_remove(dev);
 
 		if (dev->bus)
@@ -324,6 +333,8 @@ static void __device_release_driver(struct device *dev)
 			blocking_notifier_call_chain(&dev->bus->p->bus_notifier,
 						     BUS_NOTIFY_UNBOUND_DRIVER,
 						     dev);
+
+		pm_runtime_put_sync(dev);
 	}
 }
 

drivers/base/platform.c

@@ -17,6 +17,7 @@
 #include <linux/bootmem.h>
 #include <linux/err.h>
 #include <linux/slab.h>
+#include <linux/pm_runtime.h>
 
 #include "base.h"
 
@@ -625,30 +626,6 @@ static int platform_legacy_suspend(struct device *dev, pm_message_t mesg)
 	return ret;
 }
 
-static int platform_legacy_suspend_late(struct device *dev, pm_message_t mesg)
-{
-	struct platform_driver *pdrv = to_platform_driver(dev->driver);
-	struct platform_device *pdev = to_platform_device(dev);
-	int ret = 0;
-
-	if (dev->driver && pdrv->suspend_late)
-		ret = pdrv->suspend_late(pdev, mesg);
-
-	return ret;
-}
-
-static int platform_legacy_resume_early(struct device *dev)
-{
-	struct platform_driver *pdrv = to_platform_driver(dev->driver);
-	struct platform_device *pdev = to_platform_device(dev);
-	int ret = 0;
-
-	if (dev->driver && pdrv->resume_early)
-		ret = pdrv->resume_early(pdev);
-
-	return ret;
-}
-
 static int platform_legacy_resume(struct device *dev)
 {
 	struct platform_driver *pdrv = to_platform_driver(dev->driver);
@@ -680,6 +657,13 @@ static void platform_pm_complete(struct device *dev)
 		drv->pm->complete(dev);
 }
 
+#else /* !CONFIG_PM_SLEEP */
+
+#define platform_pm_prepare		NULL
+#define platform_pm_complete		NULL
+
+#endif /* !CONFIG_PM_SLEEP */
+
 #ifdef CONFIG_SUSPEND
 
 static int platform_pm_suspend(struct device *dev)
@@ -711,8 +695,6 @@ static int platform_pm_suspend_noirq(struct device *dev)
 	if (drv->pm) {
 		if (drv->pm->suspend_noirq)
 			ret = drv->pm->suspend_noirq(dev);
-	} else {
-		ret = platform_legacy_suspend_late(dev, PMSG_SUSPEND);
 	}
 
 	return ret;
@@ -747,8 +729,6 @@ static int platform_pm_resume_noirq(struct device *dev)
 	if (drv->pm) {
 		if (drv->pm->resume_noirq)
 			ret = drv->pm->resume_noirq(dev);
-	} else {
-		ret = platform_legacy_resume_early(dev);
 	}
 
 	return ret;
@@ -794,8 +774,6 @@ static int platform_pm_freeze_noirq(struct device *dev)
 	if (drv->pm) {
 		if (drv->pm->freeze_noirq)
 			ret = drv->pm->freeze_noirq(dev);
-	} else {
-		ret = platform_legacy_suspend_late(dev, PMSG_FREEZE);
 	}
 
 	return ret;
@@ -830,8 +808,6 @@ static int platform_pm_thaw_noirq(struct device *dev)
 	if (drv->pm) {
 		if (drv->pm->thaw_noirq)
 			ret = drv->pm->thaw_noirq(dev);
-	} else {
-		ret = platform_legacy_resume_early(dev);
 	}
 
 	return ret;
@@ -866,8 +842,6 @@ static int platform_pm_poweroff_noirq(struct device *dev)
 	if (drv->pm) {
 		if (drv->pm->poweroff_noirq)
 			ret = drv->pm->poweroff_noirq(dev);
-	} else {
-		ret = platform_legacy_suspend_late(dev, PMSG_HIBERNATE);
 	}
 
 	return ret;
@@ -902,8 +876,6 @@ static int platform_pm_restore_noirq(struct device *dev)
 	if (drv->pm) {
 		if (drv->pm->restore_noirq)
 			ret = drv->pm->restore_noirq(dev);
-	} else {
-		ret = platform_legacy_resume_early(dev);
 	}
 
 	return ret;
@@ -922,6 +894,31 @@ static int platform_pm_restore_noirq(struct device *dev)
 
 #endif /* !CONFIG_HIBERNATION */
 
+#ifdef CONFIG_PM_RUNTIME
+
+int __weak platform_pm_runtime_suspend(struct device *dev)
+{
+	return -ENOSYS;
+};
+
+int __weak platform_pm_runtime_resume(struct device *dev)
+{
+	return -ENOSYS;
+};
+
+int __weak platform_pm_runtime_idle(struct device *dev)
+{
+	return -ENOSYS;
+};
+
+#else /* !CONFIG_PM_RUNTIME */
+
+#define platform_pm_runtime_suspend NULL
+#define platform_pm_runtime_resume NULL
+#define platform_pm_runtime_idle NULL
+
+#endif /* !CONFIG_PM_RUNTIME */
+
 static const struct dev_pm_ops platform_dev_pm_ops = {
 	.prepare = platform_pm_prepare,
 	.complete = platform_pm_complete,
@@ -937,22 +934,17 @@ static const struct dev_pm_ops platform_dev_pm_ops = {
 	.thaw_noirq = platform_pm_thaw_noirq,
 	.poweroff_noirq = platform_pm_poweroff_noirq,
 	.restore_noirq = platform_pm_restore_noirq,
+	.runtime_suspend = platform_pm_runtime_suspend,
+	.runtime_resume = platform_pm_runtime_resume,
+	.runtime_idle = platform_pm_runtime_idle,
 };
 
-#define PLATFORM_PM_OPS_PTR	(&platform_dev_pm_ops)
-
-#else /* !CONFIG_PM_SLEEP */
-
-#define PLATFORM_PM_OPS_PTR	NULL
-
-#endif /* !CONFIG_PM_SLEEP */
-
 struct bus_type platform_bus_type = {
 	.name		= "platform",
 	.dev_attrs	= platform_dev_attrs,
 	.match		= platform_match,
 	.uevent		= platform_uevent,
-	.pm		= PLATFORM_PM_OPS_PTR,
+	.pm		= &platform_dev_pm_ops,
 };
 EXPORT_SYMBOL_GPL(platform_bus_type);
 

drivers/base/power/Makefile

 obj-$(CONFIG_PM)	+= sysfs.o
 obj-$(CONFIG_PM_SLEEP)	+= main.o
+obj-$(CONFIG_PM_RUNTIME)	+= runtime.o
 obj-$(CONFIG_PM_TRACE_RTC)	+= trace.o
 
 ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG

drivers/base/power/main.c

@@ -21,6 +21,7 @@
 #include <linux/kallsyms.h>
 #include <linux/mutex.h>
 #include <linux/pm.h>
+#include <linux/pm_runtime.h>
 #include <linux/resume-trace.h>
 #include <linux/rwsem.h>
 #include <linux/interrupt.h>
@@ -49,7 +50,17 @@ static DEFINE_MUTEX(dpm_list_mtx);
 static bool transition_started;
 
 /**
- *	device_pm_lock - lock the list of active devices used by the PM core
+ * device_pm_init - Initialize the PM-related part of a device object.
+ * @dev: Device object being initialized.
+ */
+void device_pm_init(struct device *dev)
+{
+	dev->power.status = DPM_ON;
+	pm_runtime_init(dev);
+}
+
+/**
+ * device_pm_lock - Lock the list of active devices used by the PM core.
  */
 void device_pm_lock(void)
 {
@@ -57,7 +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)
 {
@@ -65,8 +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)
 {
@@ -92,10 +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)
 {
@@ -105,12 +114,13 @@ void device_pm_remove(struct device *dev)
 	mutex_lock(&dpm_list_mtx);
 	list_del_init(&dev->power.entry);
 	mutex_unlock(&dpm_list_mtx);
+	pm_runtime_remove(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)
 {
@@ -124,9 +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)
 {
@@ -140,8 +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)
 {
@@ -152,10 +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,
@@ -213,13 +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,
@@ -317,11 +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)
 {
@@ -343,20 +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;
@@ -372,9 +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)
 {
@@ -423,11 +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)
 {
@@ -435,7 +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);
 
@@ -464,9 +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)
 {
@@ -491,11 +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)
 {
@@ -512,6 +520,7 @@ static void dpm_complete(pm_message_t state)
 			mutex_unlock(&dpm_list_mtx);
 
 			device_complete(dev, state);
+			pm_runtime_put_noidle(dev);
 
 			mutex_lock(&dpm_list_mtx);
 		}
@@ -524,11 +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)
 {
@@ -542,9 +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)
 {
@@ -561,11 +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)
 {
@@ -582,13 +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)
 {
@@ -613,9 +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)
 {
@@ -662,10 +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)
 {
@@ -699,9 +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)
 {
@@ -737,10 +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)
 {
@@ -757,7 +768,14 @@ static int dpm_prepare(pm_message_t state)
 		dev->power.status = DPM_PREPARING;
 		mutex_unlock(&dpm_list_mtx);
 
-		error = device_prepare(dev, state);
+		pm_runtime_get_noresume(dev);
+		if (pm_runtime_barrier(dev) && device_may_wakeup(dev)) {
+			/* Wake-up requested during system sleep transition. */
+			pm_runtime_put_noidle(dev);
+			error = -EBUSY;
+		} else {
+			error = device_prepare(dev, state);
+		}
 
 		mutex_lock(&dpm_list_mtx);
 		if (error) {
@@ -784,10 +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)
 {

drivers/base/power/power.h

-static inline void device_pm_init(struct device *dev)
-{
-	dev->power.status = DPM_ON;
-}
+#ifdef CONFIG_PM_RUNTIME
+
+extern void pm_runtime_init(struct device *dev);
+extern void pm_runtime_remove(struct device *dev);
+
+#else /* !CONFIG_PM_RUNTIME */
+
+static inline void pm_runtime_init(struct device *dev) {}
+static inline void pm_runtime_remove(struct device *dev) {}
+
+#endif /* !CONFIG_PM_RUNTIME */
 
 #ifdef CONFIG_PM_SLEEP
 
@@ -16,23 +23,33 @@ static inline struct device *to_device(struct list_head *entry)
 	return container_of(entry, struct device, power.entry);
 }
 
+extern void device_pm_init(struct device *dev);
 extern void device_pm_add(struct device *);
 extern void device_pm_remove(struct device *);
 extern void device_pm_move_before(struct device *, struct device *);
 extern void device_pm_move_after(struct device *, struct device *);
 extern void device_pm_move_last(struct device *);
 
-#else /* CONFIG_PM_SLEEP */
+#else /* !CONFIG_PM_SLEEP */
+
+static inline void device_pm_init(struct device *dev)
+{
+	pm_runtime_init(dev);
+}
+
+static inline void device_pm_remove(struct device *dev)
+{
+	pm_runtime_remove(dev);
+}
 
 static inline void device_pm_add(struct device *dev) {}
-static inline void device_pm_remove(struct device *dev) {}
 static inline void device_pm_move_before(struct device *deva,
 					 struct device *devb) {}
 static inline void device_pm_move_after(struct device *deva,
 					struct device *devb) {}
 static inline void device_pm_move_last(struct device *dev) {}
 
-#endif
+#endif /* !CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_PM
 

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,
 	},
 };
 

drivers/dma/at_hdmac.c

@@ -1166,32 +1166,37 @@ static void at_dma_shutdown(struct platform_device *pdev)
 	clk_disable(atdma->clk);
 }
 
-static int at_dma_suspend_late(struct platform_device *pdev, pm_message_t mesg)
+static int at_dma_suspend_noirq(struct device *dev)
 {
-	struct at_dma	*atdma = platform_get_drvdata(pdev);
+	struct platform_device *pdev = to_platform_device(dev);
+	struct at_dma *atdma = platform_get_drvdata(pdev);
 
 	at_dma_off(platform_get_drvdata(pdev));
 	clk_disable(atdma->clk);
 	return 0;
 }
 
-static int at_dma_resume_early(struct platform_device *pdev)
+static int at_dma_resume_noirq(struct device *dev)
 {
-	struct at_dma	*atdma = platform_get_drvdata(pdev);
+	struct platform_device *pdev = to_platform_device(dev);
+	struct at_dma *atdma = platform_get_drvdata(pdev);
 
 	clk_enable(atdma->clk);
 	dma_writel(atdma, EN, AT_DMA_ENABLE);
 	return 0;
-
 }
 
+static struct dev_pm_ops at_dma_dev_pm_ops = {
+	.suspend_noirq = at_dma_suspend_noirq,
+	.resume_noirq = at_dma_resume_noirq,
+};
+
 static struct platform_driver at_dma_driver = {
 	.remove		= __exit_p(at_dma_remove),
 	.shutdown	= at_dma_shutdown,
-	.suspend_late	= at_dma_suspend_late,
-	.resume_early	= at_dma_resume_early,
 	.driver = {
 		.name	= "at_hdmac",
+		.pm	= &at_dma_dev_pm_ops,
 	},
 };
 

drivers/dma/dw_dmac.c

@@ -1399,8 +1399,9 @@ static void dw_shutdown(struct platform_device *pdev)
 	clk_disable(dw->clk);
 }
 
-static int dw_suspend_late(struct platform_device *pdev, pm_message_t mesg)
+static int dw_suspend_noirq(struct device *dev)
 {
+	struct platform_device *pdev = to_platform_device(dev);
 	struct dw_dma	*dw = platform_get_drvdata(pdev);
 
 	dw_dma_off(platform_get_drvdata(pdev));
@@ -1408,23 +1409,27 @@ static int dw_suspend_late(struct platform_device *pdev, pm_message_t mesg)
 	return 0;
 }
 
-static int dw_resume_early(struct platform_device *pdev)
+static int dw_resume_noirq(struct device *dev)
 {
+	struct platform_device *pdev = to_platform_device(dev);
 	struct dw_dma	*dw = platform_get_drvdata(pdev);
 
 	clk_enable(dw->clk);
 	dma_writel(dw, CFG, DW_CFG_DMA_EN);
 	return 0;
-
 }
 
+static struct dev_pm_ops dw_dev_pm_ops = {
+	.suspend_noirq = dw_suspend_noirq,
+	.resume_noirq = dw_resume_noirq,
+};
+
 static struct platform_driver dw_driver = {
 	.remove		= __exit_p(dw_remove),
 	.shutdown	= dw_shutdown,
-	.suspend_late	= dw_suspend_late,
-	.resume_early	= dw_resume_early,
 	.driver = {
 		.name	= "dw_dmac",
+		.pm	= &dw_dev_pm_ops,
 	},
 };
 

drivers/dma/txx9dmac.c

@@ -1291,17 +1291,18 @@ static void txx9dmac_shutdown(struct platform_device *pdev)
 	txx9dmac_off(ddev);
 }
 
-static int txx9dmac_suspend_late(struct platform_device *pdev,
-				 pm_message_t mesg)
+static int txx9dmac_suspend_noirq(struct device *dev)
 {
+	struct platform_device *pdev = to_platform_device(dev);
 	struct txx9dmac_dev *ddev = platform_get_drvdata(pdev);
 
 	txx9dmac_off(ddev);
 	return 0;
 }
 
-static int txx9dmac_resume_early(struct platform_device *pdev)
+static int txx9dmac_resume_noirq(struct device *dev)
 {
+	struct platform_device *pdev = to_platform_device(dev);
 	struct txx9dmac_dev *ddev = platform_get_drvdata(pdev);
 	struct txx9dmac_platform_data *pdata = pdev->dev.platform_data;
 	u32 mcr;
@@ -1314,6 +1315,11 @@ static int txx9dmac_resume_early(struct platform_device *pdev)
 
 }
 
+static struct dev_pm_ops txx9dmac_dev_pm_ops = {
+	.suspend_noirq = txx9dmac_suspend_noirq,
+	.resume_noirq = txx9dmac_resume_noirq,
+};
+
 static struct platform_driver txx9dmac_chan_driver = {
 	.remove		= __exit_p(txx9dmac_chan_remove),
 	.driver = {
@@ -1324,10 +1330,9 @@ static struct platform_driver txx9dmac_chan_driver = {
 static struct platform_driver txx9dmac_driver = {
 	.remove		= __exit_p(txx9dmac_remove),
 	.shutdown	= txx9dmac_shutdown,
-	.suspend_late	= txx9dmac_suspend_late,
-	.resume_early	= txx9dmac_resume_early,
 	.driver = {
 		.name	= "txx9dmac",
+		.pm	= &txx9dmac_dev_pm_ops,
 	},
 };
 

drivers/i2c/busses/i2c-pxa.c

@@ -1134,35 +1134,44 @@ static int __exit i2c_pxa_remove(struct platform_device *dev)
 }
 
 #ifdef CONFIG_PM
-static int i2c_pxa_suspend_late(struct platform_device *dev, pm_message_t state)
+static int i2c_pxa_suspend_noirq(struct device *dev)
 {
-	struct pxa_i2c *i2c = platform_get_drvdata(dev);
+	struct platform_device *pdev = to_platform_device(dev);
+	struct pxa_i2c *i2c = platform_get_drvdata(pdev);
+
 	clk_disable(i2c->clk);
+
 	return 0;
 }
 
-static int i2c_pxa_resume_early(struct platform_device *dev)
+static int i2c_pxa_resume_noirq(struct device *dev)
 {
-	struct pxa_i2c *i2c = platform_get_drvdata(dev);
+	struct platform_device *pdev = to_platform_device(dev);
+	struct pxa_i2c *i2c = platform_get_drvdata(pdev);
 
 	clk_enable(i2c->clk);
 	i2c_pxa_reset(i2c);
 
 	return 0;
 }
+
+static struct dev_pm_ops i2c_pxa_dev_pm_ops = {
+	.suspend_noirq = i2c_pxa_suspend_noirq,
+	.resume_noirq = i2c_pxa_resume_noirq,
+};
+
+#define I2C_PXA_DEV_PM_OPS (&i2c_pxa_dev_pm_ops)
 #else
-#define i2c_pxa_suspend_late NULL
-#define i2c_pxa_resume_early NULL
+#define I2C_PXA_DEV_PM_OPS NULL
 #endif
 
 static struct platform_driver i2c_pxa_driver = {
 	.probe		= i2c_pxa_probe,
 	.remove		= __exit_p(i2c_pxa_remove),
-	.suspend_late	= i2c_pxa_suspend_late,
-	.resume_early	= i2c_pxa_resume_early,
 	.driver		= {
 		.name	= "pxa2xx-i2c",
 		.owner	= THIS_MODULE,
+		.pm	= I2C_PXA_DEV_PM_OPS,
 	},
 	.id_table	= i2c_pxa_id_table,
 };

drivers/i2c/busses/i2c-s3c2410.c

@@ -946,17 +946,20 @@ static int s3c24xx_i2c_remove(struct platform_device *pdev)
 }
 
 #ifdef CONFIG_PM
-static int s3c24xx_i2c_suspend_late(struct platform_device *dev,
-				    pm_message_t msg)
+static int s3c24xx_i2c_suspend_noirq(struct device *dev)
 {
-	struct s3c24xx_i2c *i2c = platform_get_drvdata(dev);
+	struct platform_device *pdev = to_platform_device(dev);
+	struct s3c24xx_i2c *i2c = platform_get_drvdata(pdev);
+
 	i2c->suspended = 1;
+
 	return 0;
 }
 
-static int s3c24xx_i2c_resume(struct platform_device *dev)
+static int s3c24xx_i2c_resume(struct device *dev)
 {
-	struct s3c24xx_i2c *i2c = platform_get_drvdata(dev);
+	struct platform_device *pdev = to_platform_device(dev);
+	struct s3c24xx_i2c *i2c = platform_get_drvdata(pdev);
 
 	i2c->suspended = 0;
 	s3c24xx_i2c_init(i2c);
@@ -964,9 +967,14 @@ static int s3c24xx_i2c_resume(struct platform_device *dev)
 	return 0;
 }
 
+static struct dev_pm_ops s3c24xx_i2c_dev_pm_ops = {
+	.suspend_noirq = s3c24xx_i2c_suspend_noirq,
+	.resume = s3c24xx_i2c_resume,
+};
+
+#define S3C24XX_DEV_PM_OPS (&s3c24xx_i2c_dev_pm_ops)
 #else
-#define s3c24xx_i2c_suspend_late NULL
-#define s3c24xx_i2c_resume NULL
+#define S3C24XX_DEV_PM_OPS NULL
 #endif
 
 /* device driver for platform bus bits */
@@ -985,12 +993,11 @@ MODULE_DEVICE_TABLE(platform, s3c24xx_driver_ids);
 static struct platform_driver s3c24xx_i2c_driver = {
 	.probe		= s3c24xx_i2c_probe,
 	.remove		= s3c24xx_i2c_remove,
-	.suspend_late	= s3c24xx_i2c_suspend_late,
-	.resume		= s3c24xx_i2c_resume,
 	.id_table	= s3c24xx_driver_ids,
 	.driver		= {
 		.owner	= THIS_MODULE,
 		.name	= "s3c-i2c",
+		.pm	= S3C24XX_DEV_PM_OPS,
 	},
 };
 

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

drivers/usb/musb/musb_core.c

@@ -2167,8 +2167,9 @@ static int __devexit musb_remove(struct platform_device *pdev)
 
 #ifdef	CONFIG_PM
 
-static int musb_suspend(struct platform_device *pdev, pm_message_t message)
+static int musb_suspend(struct device *dev)
 {
+	struct platform_device *pdev = to_platform_device(dev);
 	unsigned long	flags;
 	struct musb	*musb = dev_to_musb(&pdev->dev);
 
@@ -2195,8 +2196,9 @@ static int musb_suspend(struct platform_device *pdev, pm_message_t message)
 	return 0;
 }
 
-static int musb_resume_early(struct platform_device *pdev)
+static int musb_resume_noirq(struct device *dev)
 {
+	struct platform_device *pdev = to_platform_device(dev);
 	struct musb	*musb = dev_to_musb(&pdev->dev);
 
 	if (!musb->clock)
@@ -2214,9 +2216,14 @@ static int musb_resume_early(struct platform_device *pdev)
 	return 0;
 }
 
+static struct dev_pm_ops musb_dev_pm_ops = {
+	.suspend	= musb_suspend,
+	.resume_noirq	= musb_resume_noirq,
+};
+
+#define MUSB_DEV_PM_OPS (&musb_dev_pm_ops)
 #else
-#define	musb_suspend	NULL
-#define	musb_resume_early	NULL
+#define	MUSB_DEV_PM_OPS	NULL
 #endif
 
 static struct platform_driver musb_driver = {
@@ -2224,11 +2231,10 @@ static struct platform_driver musb_driver = {
 		.name		= (char *)musb_driver_name,
 		.bus		= &platform_bus_type,
 		.owner		= THIS_MODULE,
+		.pm		= MUSB_DEV_PM_OPS,
 	},
 	.remove		= __devexit_p(musb_remove),
 	.shutdown	= musb_shutdown,
-	.suspend	= musb_suspend,
-	.resume_early	= musb_resume_early,
 };
 
 /*-------------------------------------------------------------------------*/

include/asm-generic/device.h

@@ -9,4 +9,7 @@
 struct dev_archdata {
 };
 
+struct pdev_archdata {
+};
+
 #endif /* _ASM_GENERIC_DEVICE_H */

include/linux/platform_device.h

@@ -22,6 +22,9 @@ struct platform_device {
 	struct resource	* resource;
 
 	struct platform_device_id	*id_entry;
+
+	/* arch specific additions */
+	struct pdev_archdata	archdata;
 };
 
 #define platform_get_device_id(pdev)	((pdev)->id_entry)
@@ -57,8 +60,6 @@ struct platform_driver {
 	int (*remove)(struct platform_device *);
 	void (*shutdown)(struct platform_device *);
 	int (*suspend)(struct platform_device *, pm_message_t state);
-	int (*suspend_late)(struct platform_device *, pm_message_t state);
-	int (*resume_early)(struct platform_device *);
 	int (*resume)(struct platform_device *);
 	struct device_driver driver;
 	struct platform_device_id *id_table;

include/linux/pm.h

@@ -22,6 +22,10 @@
 #define _LINUX_PM_H
 
 #include <linux/list.h>
+#include <linux/workqueue.h>
+#include <linux/spinlock.h>
+#include <linux/wait.h>
+#include <linux/timer.h>
 
 /*
  * Callbacks for platform drivers to implement.
@@ -165,6 +169,28 @@ typedef struct pm_message {
  * It is allowed to unregister devices while the above callbacks are being
  * executed.  However, it is not allowed to unregister a device from within any
  * of its own callbacks.
+ *
+ * There also are the following callbacks related to run-time power management
+ * of devices:
+ *
+ * @runtime_suspend: Prepare the device for a condition in which it won't be
+ *	able to communicate with the CPU(s) and RAM due to power management.
+ *	This need not mean that the device should be put into a low power state.
+ *	For example, if the device is behind a link which is about to be turned
+ *	off, the device may remain at full power.  If the device does go to low
+ *	power and if device_may_wakeup(dev) is true, remote wake-up (i.e., a
+ *	hardware mechanism allowing the device to request a change of its power
+ *	state, such as PCI PME) should be enabled for it.
+ *
+ * @runtime_resume: Put the device into the fully active state in response to a
+ *	wake-up event generated by hardware or at the request of software.  If
+ *	necessary, put the device into the full power state and restore its
+ *	registers, so that it is fully operational.
+ *
+ * @runtime_idle: Device appears to be inactive and it might be put into a low
+ *	power state if all of the necessary conditions are satisfied.  Check
+ *	these conditions and handle the device as appropriate, possibly queueing
+ *	a suspend request for it.  The return value is ignored by the PM core.
  */
 
 struct dev_pm_ops {
@@ -182,8 +208,25 @@ struct dev_pm_ops {
 	int (*thaw_noirq)(struct device *dev);
 	int (*poweroff_noirq)(struct device *dev);
 	int (*restore_noirq)(struct device *dev);
+	int (*runtime_suspend)(struct device *dev);
+	int (*runtime_resume)(struct device *dev);
+	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
  *
@@ -315,14 +358,80 @@ enum dpm_state {
 	DPM_OFF_IRQ,
 };
 
+/**
+ * Device run-time power management status.
+ *
+ * These status labels are used internally by the PM core to indicate the
+ * current status of a device with respect to the PM core operations.  They do
+ * not reflect the actual power state of the device or its status as seen by the
+ * driver.
+ *
+ * RPM_ACTIVE		Device is fully operational.  Indicates that the device
+ *			bus type's ->runtime_resume() callback has completed
+ *			successfully.
+ *
+ * RPM_SUSPENDED	Device bus type's ->runtime_suspend() callback has
+ *			completed successfully.  The device is regarded as
+ *			suspended.
+ *
+ * RPM_RESUMING		Device bus type's ->runtime_resume() callback is being
+ *			executed.
+ *
+ * RPM_SUSPENDING	Device bus type's ->runtime_suspend() callback is being
+ *			executed.
+ */
+
+enum rpm_status {
+	RPM_ACTIVE = 0,
+	RPM_RESUMING,
+	RPM_SUSPENDED,
+	RPM_SUSPENDING,
+};
+
+/**
+ * Device run-time power management request types.
+ *
+ * RPM_REQ_NONE		Do nothing.
+ *
+ * RPM_REQ_IDLE		Run the device bus type's ->runtime_idle() callback
+ *
+ * RPM_REQ_SUSPEND	Run the device bus type's ->runtime_suspend() callback
+ *
+ * RPM_REQ_RESUME	Run the device bus type's ->runtime_resume() callback
+ */
+
+enum rpm_request {
+	RPM_REQ_NONE = 0,
+	RPM_REQ_IDLE,
+	RPM_REQ_SUSPEND,
+	RPM_REQ_RESUME,
+};
+
 struct dev_pm_info {
 	pm_message_t		power_state;
-	unsigned		can_wakeup:1;
-	unsigned		should_wakeup:1;
+	unsigned int		can_wakeup:1;
+	unsigned int		should_wakeup:1;
 	enum dpm_state		status;		/* Owned by the PM core */
-#ifdef	CONFIG_PM_SLEEP
+#ifdef CONFIG_PM_SLEEP
 	struct list_head	entry;
 #endif
+#ifdef CONFIG_PM_RUNTIME
+	struct timer_list	suspend_timer;
+	unsigned long		timer_expires;
+	struct work_struct	work;
+	wait_queue_head_t	wait_queue;
+	spinlock_t		lock;
+	atomic_t		usage_count;
+	atomic_t		child_count;
+	unsigned int		disable_depth:3;
+	unsigned int		ignore_children:1;
+	unsigned int		idle_notification:1;
+	unsigned int		request_pending:1;
+	unsigned int		deferred_resume:1;
+	enum rpm_request	request;
+	enum rpm_status		runtime_status;
+	int			runtime_error;
+#endif
 };
 
 /*

include/linux/pm_runtime.h

+/*
+ * pm_runtime.h - Device run-time power management helper functions.
+ *
+ * Copyright (C) 2009 Rafael J. Wysocki <rjw@sisk.pl>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#ifndef _LINUX_PM_RUNTIME_H
+#define _LINUX_PM_RUNTIME_H
+
+#include <linux/device.h>
+#include <linux/pm.h>
+
+#ifdef CONFIG_PM_RUNTIME
+
+extern struct workqueue_struct *pm_wq;
+
+extern int pm_runtime_idle(struct device *dev);
+extern int pm_runtime_suspend(struct device *dev);
+extern int pm_runtime_resume(struct device *dev);
+extern int pm_request_idle(struct device *dev);
+extern int pm_schedule_suspend(struct device *dev, unsigned int delay);
+extern int pm_request_resume(struct device *dev);
+extern int __pm_runtime_get(struct device *dev, bool sync);
+extern int __pm_runtime_put(struct device *dev, bool sync);
+extern int __pm_runtime_set_status(struct device *dev, unsigned int status);
+extern int pm_runtime_barrier(struct device *dev);
+extern void pm_runtime_enable(struct device *dev);
+extern void __pm_runtime_disable(struct device *dev, bool check_resume);
+
+static inline bool pm_children_suspended(struct device *dev)
+{
+	return dev->power.ignore_children
+		|| !atomic_read(&dev->power.child_count);
+}
+
+static inline void pm_suspend_ignore_children(struct device *dev, bool enable)
+{
+	dev->power.ignore_children = enable;
+}
+
+static inline void pm_runtime_get_noresume(struct device *dev)
+{
+	atomic_inc(&dev->power.usage_count);
+}
+
+static inline void pm_runtime_put_noidle(struct device *dev)
+{
+	atomic_add_unless(&dev->power.usage_count, -1, 0);
+}
+
+#else /* !CONFIG_PM_RUNTIME */
+
+static inline int pm_runtime_idle(struct device *dev) { return -ENOSYS; }
+static inline int pm_runtime_suspend(struct device *dev) { return -ENOSYS; }
+static inline int pm_runtime_resume(struct device *dev) { return 0; }
+static inline int pm_request_idle(struct device *dev) { return -ENOSYS; }
+static inline int pm_schedule_suspend(struct device *dev, unsigned int delay)
+{
+	return -ENOSYS;
+}
+static inline int pm_request_resume(struct device *dev) { return 0; }
+static inline int __pm_runtime_get(struct device *dev, bool sync) { return 1; }
+static inline int __pm_runtime_put(struct device *dev, bool sync) { return 0; }
+static inline int __pm_runtime_set_status(struct device *dev,
+					    unsigned int status) { return 0; }
+static inline int pm_runtime_barrier(struct device *dev) { return 0; }
+static inline void pm_runtime_enable(struct device *dev) {}
+static inline void __pm_runtime_disable(struct device *dev, bool c) {}
+
+static inline bool pm_children_suspended(struct device *dev) { return false; }
+static inline void pm_suspend_ignore_children(struct device *dev, bool en) {}
+static inline void pm_runtime_get_noresume(struct device *dev) {}
+static inline void pm_runtime_put_noidle(struct device *dev) {}
+
+#endif /* !CONFIG_PM_RUNTIME */
+
+static inline int pm_runtime_get(struct device *dev)
+{
+	return __pm_runtime_get(dev, false);
+}
+
+static inline int pm_runtime_get_sync(struct device *dev)
+{
+	return __pm_runtime_get(dev, true);
+}
+
+static inline int pm_runtime_put(struct device *dev)
+{
+	return __pm_runtime_put(dev, false);
+}
+
+static inline int pm_runtime_put_sync(struct device *dev)
+{
+	return __pm_runtime_put(dev, true);
+}
+
+static inline int pm_runtime_set_active(struct device *dev)
+{
+	return __pm_runtime_set_status(dev, RPM_ACTIVE);
+}
+
+static inline void pm_runtime_set_suspended(struct device *dev)
+{
+	__pm_runtime_set_status(dev, RPM_SUSPENDED);
+}
+
+static inline void pm_runtime_disable(struct device *dev)
+{
+	__pm_runtime_disable(dev, true);
+}
+
+#endif

kernel/power/Kconfig

@@ -208,3 +208,17 @@ config APM_EMULATION
 	  random kernel OOPSes or reboots that don't seem to be related to
 	  anything, try disabling/enabling this option (or disabling/enabling
 	  APM in your BIOS).
+
+config PM_RUNTIME
+	bool "Run-time PM core functionality"
+	depends on PM
+	---help---
+	  Enable functionality allowing I/O devices to be put into energy-saving
+	  (low power) states at run time (or autosuspended) after a specified
+	  period of inactivity and woken up in response to a hardware-generated
+	  wake-up event or a driver's request.
+
+	  Hardware support is generally required for this functionality to work
+	  and the bus type drivers of the buses the devices are on are
+	  responsible for the actual handling of the autosuspend requests and
+	  wake-up events.

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:

kernel/power/main.c

@@ -11,6 +11,7 @@
 #include <linux/kobject.h>
 #include <linux/string.h>
 #include <linux/resume-trace.h>
+#include <linux/workqueue.h>
 
 #include "power.h"
 
@@ -217,8 +218,24 @@ static struct attribute_group attr_group = {
 	.attrs = g,
 };
 
+#ifdef CONFIG_PM_RUNTIME
+struct workqueue_struct *pm_wq;
+
+static int __init pm_start_workqueue(void)
+{
+	pm_wq = create_freezeable_workqueue("pm");
+
+	return pm_wq ? 0 : -ENOMEM;
+}
+#else
+static inline int pm_start_workqueue(void) { return 0; }
+#endif
+
 static int __init pm_init(void)
 {
+	int error = pm_start_workqueue();
+	if (error)
+		return error;
 	power_kobj = kobject_create_and_add("power", NULL);
 	if (!power_kobj)
 		return -ENOMEM;

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

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))