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

* 'pm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (63 commits)
  PM / Clocks: Remove redundant NULL checks before kfree()
  PM / Documentation: Update docs about suspend and CPU hotplug
  ACPI / PM: Add Sony VGN-FW21E to nonvs blacklist.
  ARM: mach-shmobile: sh7372 A4R support (v4)
  ARM: mach-shmobile: sh7372 A3SP support (v4)
  PM / Sleep: Mark devices involved in wakeup signaling during suspend
  PM / Hibernate: Improve performance of LZO/plain hibernation, checksum image
  PM / Hibernate: Do not initialize static and extern variables to 0
  PM / Freezer: Make fake_signal_wake_up() wake TASK_KILLABLE tasks too
  PM / Hibernate: Add resumedelay kernel param in addition to resumewait
  MAINTAINERS: Update linux-pm list address
  PM / ACPI: Blacklist Vaio VGN-FW520F machine known to require acpi_sleep=nonvs
  PM / ACPI: Blacklist Sony Vaio known to require acpi_sleep=nonvs
  PM / Hibernate: Add resumewait param to support MMC-like devices as resume file
  PM / Hibernate: Fix typo in a kerneldoc comment
  PM / Hibernate: Freeze kernel threads after preallocating memory
  PM: Update the policy on default wakeup settings
  PM / VT: Cleanup #if defined uglyness and fix compile error
  PM / Suspend: Off by one in pm_suspend()
  PM / Hibernate: Include storage keys in hibernation image on s390
  ...

99 files changed, 4720 insertions, 1044 deletions

diff --git a/Documentation/ABI/testing/sysfs-class-devfreq b/Documentation/ABI/testing/sysfs-class-devfreq
new file mode 100644
index 00000000000..23d78b5aab1
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-devfreq
@@ -0,0 +1,52 @@
+What:           /sys/class/devfreq/.../
+Date:           September 2011
+Contact:        MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+                Provide a place in sysfs for the devfreq objects.
+                This allows accessing various devfreq specific variables.
+                The name of devfreq object denoted as ... is same as the
+                name of device using devfreq.
+
+What:           /sys/class/devfreq/.../governor
+Date:           September 2011
+Contact:        MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+                The /sys/class/devfreq/.../governor shows the name of the
+                governor used by the corresponding devfreq object.
+
+What:           /sys/class/devfreq/.../cur_freq
+Date:           September 2011
+Contact:        MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+                The /sys/class/devfreq/.../cur_freq shows the current
+                frequency of the corresponding devfreq object.
+
+What:           /sys/class/devfreq/.../central_polling
+Date:           September 2011
+Contact:        MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+                The /sys/class/devfreq/.../central_polling shows whether
+                the devfreq ojbect is using devfreq-provided central
+                polling mechanism or not.
+
+What:           /sys/class/devfreq/.../polling_interval
+Date:           September 2011
+Contact:        MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+                The /sys/class/devfreq/.../polling_interval shows and sets
+                the requested polling interval of the corresponding devfreq
+                object. The values are represented in ms. If the value is
+                less than 1 jiffy, it is considered to be 0, which means
+                no polling. This value is meaningless if the governor is
+                not polling; thus. If the governor is not using
+                devfreq-provided central polling
+                (/sys/class/devfreq/.../central_polling is 0), this value
+                may be useless.
+
+What:           /sys/class/devfreq/.../userspace/set_freq
+Date:           September 2011
+Contact:        MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+                The /sys/class/devfreq/.../userspace/set_freq shows and
+                sets the requested frequency for the devfreq object if
+                userspace governor is in effect.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 0e6a1290f04..2af94a23a6a 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2246,6 +2246,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
                         in <PAGE_SIZE> units (needed only for swap files).
                         See  Documentation/power/swsusp-and-swap-files.txt
 
+        resumedelay=    [HIBERNATION] Delay (in seconds) to pause before attempting to
+                        read the resume files
+
+        resumewait      [HIBERNATION] Wait (indefinitely) for resume device to show up.
+                        Useful for devices that are detected asynchronously
+                        (e.g. USB and MMC devices).
+
         hibernate=      [HIBERNATION]
                 noresume        Don't check if there's a hibernation image
                                 present during boot.
diff --git a/Documentation/power/00-INDEX b/Documentation/power/00-INDEX
index 45e9d4a9128..a4d682f5423 100644
--- a/Documentation/power/00-INDEX
+++ b/Documentation/power/00-INDEX
@@ -26,6 +26,8 @@ s2ram.txt
         - How to get suspend to ram working (and debug it when it isn't)
 states.txt
         - System power management states
+suspend-and-cpuhotplug.txt
+        - Explains the interaction between Suspend-to-RAM (S3) and CPU hotplug
 swsusp-and-swap-files.txt
         - Using swap files with software suspend (to disk)
 swsusp-dmcrypt.txt
diff --git a/Documentation/power/basic-pm-debugging.txt b/Documentation/power/basic-pm-debugging.txt
index 05a7fe76232..40a4c65f380 100644
--- a/Documentation/power/basic-pm-debugging.txt
+++ b/Documentation/power/basic-pm-debugging.txt
@@ -201,3 +201,27 @@ case, you may be able to search for failing drivers by following the procedure
 analogous to the one described in section 1.  If you find some failing drivers,
 you will have to unload them every time before an STR transition (ie. before
 you run s2ram), and please report the problems with them.
+
+There is a debugfs entry which shows the suspend to RAM statistics. Here is an
+example of its output.
+        # mount -t debugfs none /sys/kernel/debug
+        # cat /sys/kernel/debug/suspend_stats
+        success: 20
+        fail: 5
+        failed_freeze: 0
+        failed_prepare: 0
+        failed_suspend: 5
+        failed_suspend_noirq: 0
+        failed_resume: 0
+        failed_resume_noirq: 0
+        failures:
+          last_failed_dev:      alarm
+                                adc
+          last_failed_errno:    -16
+                                -16
+          last_failed_step:     suspend
+                                suspend
+Field success means the success number of suspend to RAM, and field fail means
+the failure number. Others are the failure number of different steps of suspend
+to RAM. suspend_stats just lists the last 2 failed devices, error number and
+failed step of suspend.
diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt
index 3384d5996be..646a89e0c07 100644
--- a/Documentation/power/devices.txt
+++ b/Documentation/power/devices.txt
@@ -152,7 +152,9 @@ try to use its wakeup mechanism.  device_set_wakeup_enable() affects this flag;
 for the most part drivers should not change its value.  The initial value of
 should_wakeup is supposed to be false for the majority of devices; the major
 exceptions are power buttons, keyboards, and Ethernet adapters whose WoL
-(wake-on-LAN) feature has been set up with ethtool.
+(wake-on-LAN) feature has been set up with ethtool.  It should also default
+to true for devices that don't generate wakeup requests on their own but merely
+forward wakeup requests from one bus to another (like PCI bridges).
 
 Whether or not a device is capable of issuing wakeup events is a hardware
 matter, and the kernel is responsible for keeping track of it.  By contrast,
@@ -279,10 +281,6 @@ When the system goes into the standby or memory sleep state, the phases are:
         time.)  Unlike the other suspend-related phases, during the prepare
         phase the device tree is traversed top-down.
 
-        In addition to that, if device drivers need to allocate additional
-        memory to be able to hadle device suspend correctly, that should be
-        done in the prepare phase.
-
         After the prepare callback method returns, no new children may be
         registered below the device.  The method may also prepare the device or
         driver in some way for the upcoming system power transition (for
diff --git a/Documentation/power/pm_qos_interface.txt b/Documentation/power/pm_qos_interface.txt
index bfed898a03f..17e130a8034 100644
--- a/Documentation/power/pm_qos_interface.txt
+++ b/Documentation/power/pm_qos_interface.txt
@@ -4,14 +4,19 @@ This interface provides a kernel and user mode interface for registering
 performance expectations by drivers, subsystems and user space applications on
 one of the parameters.
 
-Currently we have {cpu_dma_latency, network_latency, network_throughput} as the
-initial set of pm_qos parameters.
+Two different PM QoS frameworks are available:
+1. PM QoS classes for cpu_dma_latency, network_latency, network_throughput.
+2. the per-device PM QoS framework provides the API to manage the per-device latency
+constraints.
 
 Each parameters have defined units:
  * latency: usec
  * timeout: usec
  * throughput: kbs (kilo bit / sec)
 
+
+1. PM QoS framework
+
 The infrastructure exposes multiple misc device nodes one per implemented
 parameter.  The set of parameters implement is defined by pm_qos_power_init()
 and pm_qos_params.h.  This is done because having the available parameters
@@ -23,14 +28,18 @@ an aggregated target value.  The aggregated target value is updated with
 changes to the request list or elements of the list.  Typically the
 aggregated target value is simply the max or min of the request values held
 in the parameter list elements.
+Note: the aggregated target value is implemented as an atomic variable so that
+reading the aggregated value does not require any locking mechanism.
+
 
 From kernel mode the use of this interface is simple:
 
-handle = pm_qos_add_request(param_class, target_value):
-Will insert an element into the list for that identified PM_QOS class with the
+void pm_qos_add_request(handle, param_class, target_value):
+Will insert an element into the list for that identified PM QoS class with the
 target value.  Upon change to this list the new target is recomputed and any
 registered notifiers are called only if the target value is now different.
-Clients of pm_qos need to save the returned handle.
+Clients of pm_qos need to save the returned handle for future use in other
+pm_qos API functions.
 
 void pm_qos_update_request(handle, new_target_value):
 Will update the list element pointed to by the handle with the new target value
@@ -42,6 +51,20 @@ Will remove the element.  After removal it will update the aggregate target and
 call the notification tree if the target was changed as a result of removing
 the request.
 
+int pm_qos_request(param_class):
+Returns the aggregated value for a given PM QoS class.
+
+int pm_qos_request_active(handle):
+Returns if the request is still active, i.e. it has not been removed from a
+PM QoS class constraints list.
+
+int pm_qos_add_notifier(param_class, notifier):
+Adds a notification callback function to the PM QoS class. The callback is
+called when the aggregated value for the PM QoS class is changed.
+
+int pm_qos_remove_notifier(int param_class, notifier):
+Removes the notification callback function for the PM QoS class.
+
 
 From user mode:
 Only processes can register a pm_qos request.  To provide for automatic
@@ -63,4 +86,63 @@ To remove the user mode request for a target value simply close the device
 node.
 
 
+2. PM QoS per-device latency framework
+
+For each device a list of performance requests is maintained along with
+an aggregated target value.  The aggregated target value is updated with
+changes to the request list or elements of the list.  Typically the
+aggregated target value is simply the max or min of the request values held
+in the parameter list elements.
+Note: the aggregated target value is implemented as an atomic variable so that
+reading the aggregated value does not require any locking mechanism.
+
+
+From kernel mode the use of this interface is the following:
+
+int dev_pm_qos_add_request(device, handle, value):
+Will insert an element into the list for that identified device with the
+target value.  Upon change to this list the new target is recomputed and any
+registered notifiers are called only if the target value is now different.
+Clients of dev_pm_qos need to save the handle for future use in other
+dev_pm_qos API functions.
+
+int dev_pm_qos_update_request(handle, new_value):
+Will update the list element pointed to by the handle with the new target value
+and recompute the new aggregated target, calling the notification trees if the
+target is changed.
+
+int dev_pm_qos_remove_request(handle):
+Will remove the element.  After removal it will update the aggregate target and
+call the notification trees if the target was changed as a result of removing
+the request.
+
+s32 dev_pm_qos_read_value(device):
+Returns the aggregated value for a given device's constraints list.
+
+
+Notification mechanisms:
+The per-device PM QoS framework has 2 different and distinct notification trees:
+a per-device notification tree and a global notification tree.
+
+int dev_pm_qos_add_notifier(device, notifier):
+Adds a notification callback function for the device.
+The callback is called when the aggregated value of the device constraints list
+is changed.
+
+int dev_pm_qos_remove_notifier(device, notifier):
+Removes the notification callback function for the device.
+
+int dev_pm_qos_add_global_notifier(notifier):
+Adds a notification callback function in the global notification tree of the
+framework.
+The callback is called when the aggregated value for any device is changed.
+
+int dev_pm_qos_remove_global_notifier(notifier):
+Removes the notification callback function from the global notification tree
+of the framework.
+
+
+From user mode:
+No API for user space access to the per-device latency constraints is provided
+yet - still under discussion.
 
diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index 6066e3a6b9a..0e856088db7 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -43,13 +43,18 @@ struct dev_pm_ops {
         ...
 };
 
-The ->runtime_suspend(), ->runtime_resume() and ->runtime_idle() callbacks are
-executed by the PM core for either the device type, or the class (if the device
-type's struct dev_pm_ops object does not exist), or the bus type (if the
-device type's and class' struct dev_pm_ops objects do not exist) of the given
-device (this allows device types to override callbacks provided by bus types or
-classes if necessary).  The bus type, device type and class callbacks are
-referred to as subsystem-level callbacks in what follows.
+The ->runtime_suspend(), ->runtime_resume() and ->runtime_idle() callbacks
+are executed by the PM core for either the power domain, or the device type
+(if the device power domain's struct dev_pm_ops does not exist), or the class
+(if the device power domain's and type's struct dev_pm_ops object does not
+exist), or the bus type (if the device power domain's, type's and class'
+struct dev_pm_ops objects do not exist) of the given device, so the priority
+order of callbacks from high to low is that power domain callbacks, device
+type callbacks, class callbacks and bus type callbacks, and the high priority
+one will take precedence over low priority one. The bus type, device type and
+class callbacks are referred to as subsystem-level callbacks in what follows,
+and generally speaking, the power domain callbacks are used for representing
+power domains within a SoC.
 
 By default, the callbacks are always invoked in process context with interrupts
 enabled.  However, subsystems can use the pm_runtime_irq_safe() helper function
@@ -477,12 +482,14 @@ pm_runtime_autosuspend_expiration()
 If pm_runtime_irq_safe() has been called for a device then the following helper
 functions may also be used in interrupt context:
 
+pm_runtime_idle()
 pm_runtime_suspend()
 pm_runtime_autosuspend()
 pm_runtime_resume()
 pm_runtime_get_sync()
 pm_runtime_put_sync()
 pm_runtime_put_sync_suspend()
+pm_runtime_put_sync_autosuspend()
 
 5. Runtime PM Initialization, Device Probing and Removal
 
diff --git a/Documentation/power/suspend-and-cpuhotplug.txt b/Documentation/power/suspend-and-cpuhotplug.txt
new file mode 100644
index 00000000000..f28f9a6f034
--- /dev/null
+++ b/Documentation/power/suspend-and-cpuhotplug.txt
@@ -0,0 +1,275 @@
+Interaction of Suspend code (S3) with the CPU hotplug infrastructure
+
+     (C) 2011 Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
+
+
+I. How does the regular CPU hotplug code differ from how the Suspend-to-RAM
+   infrastructure uses it internally? And where do they share common code?
+
+Well, a picture is worth a thousand words... So ASCII art follows :-)
+
+[This depicts the current design in the kernel, and focusses only on the
+interactions involving the freezer and CPU hotplug and also tries to explain
+the locking involved. It outlines the notifications involved as well.
+But please note that here, only the call paths are illustrated, with the aim
+of describing where they take different paths and where they share code.
+What happens when regular CPU hotplug and Suspend-to-RAM race with each other
+is not depicted here.]
+
+On a high level, the suspend-resume cycle goes like this:
+
+|Freeze| -> |Disable nonboot| -> |Do suspend| -> |Enable nonboot| -> |Thaw |
+|tasks |    |     cpus      |    |          |    |     cpus     |    |tasks|
+
+
+More details follow:
+
+                                Suspend call path
+                                -----------------
+
+                                  Write 'mem' to
+                                /sys/power/state
+                                    syfs file
+                                        |
+                                        v
+                               Acquire pm_mutex lock
+                                        |
+                                        v
+                             Send PM_SUSPEND_PREPARE
+                                   notifications
+                                        |
+                                        v
+                                   Freeze tasks
+                                        |
+                                        |
+                                        v
+                              disable_nonboot_cpus()
+                                   /* start */
+                                        |
+                                        v
+                            Acquire cpu_add_remove_lock
+                                        |
+                                        v
+                             Iterate over CURRENTLY
+                                   online CPUs
+                                        |
+                                        |
+                                        |                ----------
+                                        v                          | L
+             ======>               _cpu_down()                     |
+            |              [This takes cpuhotplug.lock             |
+  Common    |               before taking down the CPU             |
+   code     |               and releases it when done]             | O
+            |            While it is at it, notifications          |
+            |            are sent when notable events occur,       |
+             ======>     by running all registered callbacks.      |
+                                        |                          | O
+                                        |                          |
+                                        |                          |
+                                        v                          |
+                            Note down these cpus in                | P
+                                frozen_cpus mask         ----------
+                                        |
+                                        v
+                           Disable regular cpu hotplug
+                        by setting cpu_hotplug_disabled=1
+                                        |
+                                        v
+                            Release cpu_add_remove_lock
+                                        |
+                                        v
+                       /* disable_nonboot_cpus() complete */
+                                        |
+                                        v
+                                   Do suspend
+
+
+
+Resuming back is likewise, with the counterparts being (in the order of
+execution during resume):
+* enable_nonboot_cpus() which involves:
+   |  Acquire cpu_add_remove_lock
+   |  Reset cpu_hotplug_disabled to 0, thereby enabling regular cpu hotplug
+   |  Call _cpu_up() [for all those cpus in the frozen_cpus mask, in a loop]
+   |  Release cpu_add_remove_lock
+   v
+
+* thaw tasks
+* send PM_POST_SUSPEND notifications
+* Release pm_mutex lock.
+
+
+It is to be noted here that the pm_mutex lock is acquired at the very
+beginning, when we are just starting out to suspend, and then released only
+after the entire cycle is complete (i.e., suspend + resume).
+
+
+
+                          Regular CPU hotplug call path
+                          -----------------------------
+
+                                Write 0 (or 1) to
+                       /sys/devices/system/cpu/cpu*/online
+                                    sysfs file
+                                        |
+                                        |
+                                        v
+                                    cpu_down()
+                                        |
+                                        v
+                           Acquire cpu_add_remove_lock
+                                        |
+                                        v
+                          If cpu_hotplug_disabled is 1
+                                return gracefully
+                                        |
+                                        |
+                                        v
+             ======>                _cpu_down()
+            |              [This takes cpuhotplug.lock
+  Common    |               before taking down the CPU
+   code     |               and releases it when done]
+            |            While it is at it, notifications
+            |           are sent when notable events occur,
+             ======>    by running all registered callbacks.
+                                        |
+                                        |
+                                        v
+                          Release cpu_add_remove_lock
+                               [That's it!, for
+                              regular CPU hotplug]
+
+
+
+So, as can be seen from the two diagrams (the parts marked as "Common code"),
+regular CPU hotplug and the suspend code path converge at the _cpu_down() and
+_cpu_up() functions. They differ in the arguments passed to these functions,
+in that during regular CPU hotplug, 0 is passed for the 'tasks_frozen'
+argument. But during suspend, since the tasks are already frozen by the time
+the non-boot CPUs are offlined or onlined, the _cpu_*() functions are called
+with the 'tasks_frozen' argument set to 1.
+[See below for some known issues regarding this.]
+
+
+Important files and functions/entry points:
+------------------------------------------
+
+kernel/power/process.c : freeze_processes(), thaw_processes()
+kernel/power/suspend.c : suspend_prepare(), suspend_enter(), suspend_finish()
+kernel/cpu.c: cpu_[up|down](), _cpu_[up|down](), [disable|enable]_nonboot_cpus()
+
+
+
+II. What are the issues involved in CPU hotplug?
+    -------------------------------------------
+
+There are some interesting situations involving CPU hotplug and microcode
+update on the CPUs, as discussed below:
+
+[Please bear in mind that the kernel requests the microcode images from
+userspace, using the request_firmware() function defined in
+drivers/base/firmware_class.c]
+
+
+a. When all the CPUs are identical:
+
+   This is the most common situation and it is quite straightforward: we want
+   to apply the same microcode revision to each of the CPUs.
+   To give an example of x86, the collect_cpu_info() function defined in
+   arch/x86/kernel/microcode_core.c helps in discovering the type of the CPU
+   and thereby in applying the correct microcode revision to it.
+   But note that the kernel does not maintain a common microcode image for the
+   all CPUs, in order to handle case 'b' described below.
+
+
+b. When some of the CPUs are different than the rest:
+
+   In this case since we probably need to apply different microcode revisions
+   to different CPUs, the kernel maintains a copy of the correct microcode
+   image for each CPU (after appropriate CPU type/model discovery using
+   functions such as collect_cpu_info()).
+
+
+c. When a CPU is physically hot-unplugged and a new (and possibly different
+   type of) CPU is hot-plugged into the system:
+
+   In the current design of the kernel, whenever a CPU is taken offline during
+   a regular CPU hotplug operation, upon receiving the CPU_DEAD notification
+   (which is sent by the CPU hotplug code), the microcode update driver's
+   callback for that event reacts by freeing the kernel's copy of the
+   microcode image for that CPU.
+
+   Hence, when a new CPU is brought online, since the kernel finds that it
+   doesn't have the microcode image, it does the CPU type/model discovery
+   afresh and then requests the userspace for the appropriate microcode image
+   for that CPU, which is subsequently applied.
+
+   For example, in x86, the mc_cpu_callback() function (which is the microcode
+   update driver's callback registered for CPU hotplug events) calls
+   microcode_update_cpu() which would call microcode_init_cpu() in this case,
+   instead of microcode_resume_cpu() when it finds that the kernel doesn't
+   have a valid microcode image. This ensures that the CPU type/model
+   discovery is performed and the right microcode is applied to the CPU after
+   getting it from userspace.
+
+
+d. Handling microcode update during suspend/hibernate:
+
+   Strictly speaking, during a CPU hotplug operation which does not involve
+   physically removing or inserting CPUs, the CPUs are not actually powered
+   off during a CPU offline. They are just put to the lowest C-states possible.
+   Hence, in such a case, it is not really necessary to re-apply microcode
+   when the CPUs are brought back online, since they wouldn't have lost the
+   image during the CPU offline operation.
+
+   This is the usual scenario encountered during a resume after a suspend.
+   However, in the case of hibernation, since all the CPUs are completely
+   powered off, during restore it becomes necessary to apply the microcode
+   images to all the CPUs.
+
+   [Note that we don't expect someone to physically pull out nodes and insert
+   nodes with a different type of CPUs in-between a suspend-resume or a
+   hibernate/restore cycle.]
+
+   In the current design of the kernel however, during a CPU offline operation
+   as part of the suspend/hibernate cycle (the CPU_DEAD_FROZEN notification),
+   the existing copy of microcode image in the kernel is not freed up.
+   And during the CPU online operations (during resume/restore), since the
+   kernel finds that it already has copies of the microcode images for all the
+   CPUs, it just applies them to the CPUs, avoiding any re-discovery of CPU
+   type/model and the need for validating whether the microcode revisions are
+   right for the CPUs or not (due to the above assumption that physical CPU
+   hotplug will not be done in-between suspend/resume or hibernate/restore
+   cycles).
+
+
+III. Are there any known problems when regular CPU hotplug and suspend race
+     with each other?
+
+Yes, they are listed below:
+
+1. When invoking regular CPU hotplug, the 'tasks_frozen' argument passed to
+   the _cpu_down() and _cpu_up() functions is *always* 0.
+   This might not reflect the true current state of the system, since the
+   tasks could have been frozen by an out-of-band event such as a suspend
+   operation in progress. Hence, it will lead to wrong notifications being
+   sent during the cpu online/offline events (eg, CPU_ONLINE notification
+   instead of CPU_ONLINE_FROZEN) which in turn will lead to execution of
+   inappropriate code by the callbacks registered for such CPU hotplug events.
+
+2. If a regular CPU hotplug stress test happens to race with the freezer due
+   to a suspend operation in progress at the same time, then we could hit the
+   situation described below:
+
+    * A regular cpu online operation continues its journey from userspace
+      into the kernel, since the freezing has not yet begun.
+    * Then freezer gets to work and freezes userspace.
+    * If cpu online has not yet completed the microcode update stuff by now,
+      it will now start waiting on the frozen userspace in the
+      TASK_UNINTERRUPTIBLE state, in order to get the microcode image.
+    * Now the freezer continues and tries to freeze the remaining tasks. But
+      due to this wait mentioned above, the freezer won't be able to freeze
+      the cpu online hotplug task and hence freezing of tasks fails.
+
+   As a result of this task freezing failure, the suspend operation gets
+   aborted.
diff --git a/Documentation/usb/power-management.txt b/Documentation/usb/power-management.txt
index 9d85d96ec6e..12511c98cc4 100644
--- a/Documentation/usb/power-management.txt
+++ b/Documentation/usb/power-management.txt
@@ -439,10 +439,10 @@ cause autosuspends to fail with -EBUSY if the driver needs to use the
 device.
 
 External suspend calls should never be allowed to fail in this way,
-only autosuspend calls.  The driver can tell them apart by checking
-the PM_EVENT_AUTO bit in the message.event argument to the suspend
-method; this bit will be set for internal PM events (autosuspend) and
-clear for external PM events.
+only autosuspend calls.  The driver can tell them apart by applying
+the PMSG_IS_AUTO() macro to the message argument to the suspend
+method; it will return True for internal PM events (autosuspend) and
+False for external PM events.
 
 
         Mutual exclusion
diff --git a/MAINTAINERS b/MAINTAINERS
index 04c0dd8d992..566ab1c23a3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2760,7 +2760,7 @@ F:	fs/freevxfs/
 FREEZER
 M:      Pavel Machek <pavel@ucw.cz>
 M:      "Rafael J. Wysocki" <rjw@sisk.pl>
-L:      linux-pm@lists.linux-foundation.org
+L:      linux-pm@vger.kernel.org
 S:      Supported
 F:      Documentation/power/freezing-of-tasks.txt
 F:      include/linux/freezer.h
@@ -3022,7 +3022,7 @@ F:	drivers/video/hgafb.c
 HIBERNATION (aka Software Suspend, aka swsusp)
 M:      Pavel Machek <pavel@ucw.cz>
 M:      "Rafael J. Wysocki" <rjw@sisk.pl>
-L:      linux-pm@lists.linux-foundation.org
+L:      linux-pm@vger.kernel.org
 S:      Supported
 F:      arch/x86/power/
 F:      drivers/base/power/
@@ -3217,7 +3217,7 @@ F:	drivers/ide/ide-cd*
 
 IDLE-I7300
 M:      Andy Henroid <andrew.d.henroid@intel.com>
-L:      linux-pm@lists.linux-foundation.org
+L:      linux-pm@vger.kernel.org
 S:      Supported
 F:      drivers/idle/i7300_idle.c
 
@@ -3300,7 +3300,7 @@ F:	firmware/isci/
 
 INTEL IDLE DRIVER
 M:      Len Brown <lenb@kernel.org>
-L:      linux-pm@lists.linux-foundation.org
+L:      linux-pm@vger.kernel.org
 T:      git git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-idle-2.6.git
 S:      Supported
 F:      drivers/idle/intel_idle.c
@@ -3397,7 +3397,7 @@ F:	drivers/net/ethernet/intel/
 
 INTEL MRST PMU DRIVER
 M:      Len Brown <len.brown@intel.com>
-L:      linux-pm@lists.linux-foundation.org
+L:      linux-pm@vger.kernel.org
 S:      Supported
 F:      arch/x86/platform/mrst/pmu.*
 
@@ -6338,7 +6338,7 @@ SUSPEND TO RAM
 M:      Len Brown <len.brown@intel.com>
 M:      Pavel Machek <pavel@ucw.cz>
 M:      "Rafael J. Wysocki" <rjw@sisk.pl>
-L:      linux-pm@lists.linux-foundation.org
+L:      linux-pm@vger.kernel.org
 S:      Supported
 F:      Documentation/power/
 F:      arch/x86/kernel/acpi/
diff --git a/arch/arm/mach-msm/clock.c b/arch/arm/mach-msm/clock.c
index 22a53766962..d9145dfc2a3 100644
--- a/arch/arm/mach-msm/clock.c
+++ b/arch/arm/mach-msm/clock.c
@@ -18,7 +18,7 @@
 #include <linux/list.h>
 #include <linux/err.h>
 #include <linux/spinlock.h>
-#include <linux/pm_qos_params.h>
+#include <linux/pm_qos.h>
 #include <linux/mutex.h>
 #include <linux/clk.h>
 #include <linux/string.h>
diff --git a/arch/arm/mach-omap1/pm_bus.c b/arch/arm/mach-omap1/pm_bus.c
index 943072d5a1d..7868e75ad07 100644
--- a/arch/arm/mach-omap1/pm_bus.c
+++ b/arch/arm/mach-omap1/pm_bus.c
@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/io.h>
 #include <linux/pm_runtime.h>
+#include <linux/pm_clock.h>
 #include <linux/platform_device.h>
 #include <linux/mutex.h>
 #include <linux/clk.h>
diff --git a/arch/arm/mach-shmobile/board-ap4evb.c b/arch/arm/mach-shmobile/board-ap4evb.c
index 523f608eb8c..7e90d064ebc 100644
--- a/arch/arm/mach-shmobile/board-ap4evb.c
+++ b/arch/arm/mach-shmobile/board-ap4evb.c
@@ -42,6 +42,7 @@
 #include <linux/leds.h>
 #include <linux/input/sh_keysc.h>
 #include <linux/usb/r8a66597.h>
+#include <linux/pm_clock.h>
 
 #include <media/sh_mobile_ceu.h>
 #include <media/sh_mobile_csi2.h>
@@ -1408,6 +1409,11 @@ static void __init ap4evb_init(void)
         sh7372_add_device_to_domain(&sh7372_a4lc, &lcdc_device);
         sh7372_add_device_to_domain(&sh7372_a4mp, &fsi_device);
 
+        sh7372_add_device_to_domain(&sh7372_a3sp, &sh_mmcif_device);
+        sh7372_add_device_to_domain(&sh7372_a3sp, &sdhi0_device);
+        sh7372_add_device_to_domain(&sh7372_a3sp, &sdhi1_device);
+        sh7372_add_device_to_domain(&sh7372_a4r, &ceu_device);
+
         hdmi_init_pm_clock();
         fsi_init_pm_clock();
         sh7372_pm_init();
diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c
index 802aa58ef9d..00273dad5bf 100644
--- a/arch/arm/mach-shmobile/board-mackerel.c
+++ b/arch/arm/mach-shmobile/board-mackerel.c
@@ -39,7 +39,7 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/physmap.h>
-#include <linux/pm_runtime.h>
+#include <linux/pm_clock.h>
 #include <linux/smsc911x.h>
 #include <linux/sh_intc.h>
 #include <linux/tca6416_keypad.h>
@@ -1589,6 +1589,15 @@ static void __init mackerel_init(void)
         sh7372_add_device_to_domain(&sh7372_a4lc, &lcdc_device);
         sh7372_add_device_to_domain(&sh7372_a4lc, &hdmi_lcdc_device);
         sh7372_add_device_to_domain(&sh7372_a4mp, &fsi_device);
+        sh7372_add_device_to_domain(&sh7372_a3sp, &usbhs0_device);
+        sh7372_add_device_to_domain(&sh7372_a3sp, &usbhs1_device);
+        sh7372_add_device_to_domain(&sh7372_a3sp, &sh_mmcif_device);
+        sh7372_add_device_to_domain(&sh7372_a3sp, &sdhi0_device);
+#if !defined(CONFIG_MMC_SH_MMCIF) && !defined(CONFIG_MMC_SH_MMCIF_MODULE)
+        sh7372_add_device_to_domain(&sh7372_a3sp, &sdhi1_device);
+#endif
+        sh7372_add_device_to_domain(&sh7372_a3sp, &sdhi2_device);
+        sh7372_add_device_to_domain(&sh7372_a4r, &ceu_device);
 
         hdmi_init_pm_clock();
         sh7372_pm_init();
diff --git a/arch/arm/mach-shmobile/include/mach/common.h b/arch/arm/mach-shmobile/include/mach/common.h
index 06aecb31d9c..c0cdbf997c9 100644
--- a/arch/arm/mach-shmobile/include/mach/common.h
+++ b/arch/arm/mach-shmobile/include/mach/common.h
@@ -35,8 +35,8 @@ extern void sh7372_add_standard_devices(void);
 extern void sh7372_clock_init(void);
 extern void sh7372_pinmux_init(void);
 extern void sh7372_pm_init(void);
-extern void sh7372_cpu_suspend(void);
-extern void sh7372_cpu_resume(void);
+extern void sh7372_resume_core_standby_a3sm(void);
+extern int sh7372_do_idle_a3sm(unsigned long unused);
 extern struct clk sh7372_extal1_clk;
 extern struct clk sh7372_extal2_clk;
 
diff --git a/arch/arm/mach-shmobile/include/mach/sh7372.h b/arch/arm/mach-shmobile/include/mach/sh7372.h
index 24e63a85e66..84532f9629b 100644
--- a/arch/arm/mach-shmobile/include/mach/sh7372.h
+++ b/arch/arm/mach-shmobile/include/mach/sh7372.h
@@ -479,7 +479,12 @@ struct platform_device;
 
 struct sh7372_pm_domain {
         struct generic_pm_domain genpd;
+        struct dev_power_governor *gov;
+        void (*suspend)(void);
+        void (*resume)(void);
         unsigned int bit_shift;
+        bool no_debug;
+        bool stay_on;
 };
 
 static inline struct sh7372_pm_domain *to_sh7372_pd(struct generic_pm_domain *d)
@@ -491,16 +496,24 @@ static inline struct sh7372_pm_domain *to_sh7372_pd(struct generic_pm_domain *d)
 extern struct sh7372_pm_domain sh7372_a4lc;
 extern struct sh7372_pm_domain sh7372_a4mp;
 extern struct sh7372_pm_domain sh7372_d4;
+extern struct sh7372_pm_domain sh7372_a4r;
 extern struct sh7372_pm_domain sh7372_a3rv;
 extern struct sh7372_pm_domain sh7372_a3ri;
+extern struct sh7372_pm_domain sh7372_a3sp;
 extern struct sh7372_pm_domain sh7372_a3sg;
 
 extern void sh7372_init_pm_domain(struct sh7372_pm_domain *sh7372_pd);
 extern void sh7372_add_device_to_domain(struct sh7372_pm_domain *sh7372_pd,
                                         struct platform_device *pdev);
+extern void sh7372_pm_add_subdomain(struct sh7372_pm_domain *sh7372_pd,
+                                    struct sh7372_pm_domain *sh7372_sd);
 #else
 #define sh7372_init_pm_domain(pd) do { } while(0)
 #define sh7372_add_device_to_domain(pd, pdev) do { } while(0)
+#define sh7372_pm_add_subdomain(pd, sd) do { } while(0)
 #endif /* CONFIG_PM */
 
+extern void sh7372_intcs_suspend(void);
+extern void sh7372_intcs_resume(void);
+
 #endif /* __ASM_SH7372_H__ */
diff --git a/arch/arm/mach-shmobile/intc-sh7372.c b/arch/arm/mach-shmobile/intc-sh7372.c
index 739315e30eb..29cdc0522d9 100644
--- a/arch/arm/mach-shmobile/intc-sh7372.c
+++ b/arch/arm/mach-shmobile/intc-sh7372.c
@@ -606,9 +606,16 @@ static void intcs_demux(unsigned int irq, struct irq_desc *desc)
         generic_handle_irq(intcs_evt2irq(evtcodeas));
 }
 
+static void __iomem *intcs_ffd2;
+static void __iomem *intcs_ffd5;
+
 void __init sh7372_init_irq(void)
 {
-        void __iomem *intevtsa = ioremap_nocache(0xffd20100, PAGE_SIZE);
+        void __iomem *intevtsa;
+
+        intcs_ffd2 = ioremap_nocache(0xffd20000, PAGE_SIZE);
+        intevtsa = intcs_ffd2 + 0x100;
+        intcs_ffd5 = ioremap_nocache(0xffd50000, PAGE_SIZE);
 
         register_intc_controller(&intca_desc);
         register_intc_controller(&intcs_desc);
@@ -617,3 +624,46 @@ void __init sh7372_init_irq(void)
         irq_set_handler_data(evt2irq(0xf80), (void *)intevtsa);
         irq_set_chained_handler(evt2irq(0xf80), intcs_demux);
 }
+
+static unsigned short ffd2[0x200];
+static unsigned short ffd5[0x100];
+
+void sh7372_intcs_suspend(void)
+{
+        int k;
+
+        for (k = 0x00; k <= 0x30; k += 4)
+                ffd2[k] = __raw_readw(intcs_ffd2 + k);
+
+        for (k = 0x80; k <= 0xb0; k += 4)
+                ffd2[k] = __raw_readb(intcs_ffd2 + k);
+
+        for (k = 0x180; k <= 0x188; k += 4)
+                ffd2[k] = __raw_readb(intcs_ffd2 + k);
+
+        for (k = 0x00; k <= 0x3c; k += 4)
+                ffd5[k] = __raw_readw(intcs_ffd5 + k);
+
+        for (k = 0x80; k <= 0x9c; k += 4)
+                ffd5[k] = __raw_readb(intcs_ffd5 + k);
+}
+
+void sh7372_intcs_resume(void)
+{
+        int k;
+
+        for (k = 0x00; k <= 0x30; k += 4)
+                __raw_writew(ffd2[k], intcs_ffd2 + k);
+
+        for (k = 0x80; k <= 0xb0; k += 4)
+                __raw_writeb(ffd2[k], intcs_ffd2 + k);
+
+        for (k = 0x180; k <= 0x188; k += 4)
+                __raw_writeb(ffd2[k], intcs_ffd2 + k);
+
+        for (k = 0x00; k <= 0x3c; k += 4)
+                __raw_writew(ffd5[k], intcs_ffd5 + k);
+
+        for (k = 0x80; k <= 0x9c; k += 4)
+                __raw_writeb(ffd5[k], intcs_ffd5 + k);
+}
diff --git a/arch/arm/mach-shmobile/pm-sh7372.c b/arch/arm/mach-shmobile/pm-sh7372.c
index 933fb411be0..79612737c5b 100644
--- a/arch/arm/mach-shmobile/pm-sh7372.c
+++ b/arch/arm/mach-shmobile/pm-sh7372.c
@@ -15,23 +15,61 @@
 #include <linux/list.h>
 #include <linux/err.h>
 #include <linux/slab.h>
-#include <linux/pm_runtime.h>
+#include <linux/pm_clock.h>
 #include <linux/platform_device.h>
 #include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/bitrev.h>
 #include <asm/system.h>
 #include <asm/io.h>
 #include <asm/tlbflush.h>
+#include <asm/suspend.h>
 #include <mach/common.h>
 #include <mach/sh7372.h>
 
-#define SMFRAM 0xe6a70000
-#define SYSTBCR 0xe6150024
-#define SBAR 0xe6180020
-#define APARMBAREA 0xe6f10020
+/* DBG */
+#define DBGREG1 0xe6100020
+#define DBGREG9 0xe6100040
 
+/* CPGA */
+#define SYSTBCR 0xe6150024
+#define MSTPSR0 0xe6150030
+#define MSTPSR1 0xe6150038
+#define MSTPSR2 0xe6150040
+#define MSTPSR3 0xe6150048
+#define MSTPSR4 0xe615004c
+#define PLLC01STPCR 0xe61500c8
+
+/* SYSC */
 #define SPDCR 0xe6180008
 #define SWUCR 0xe6180014
+#define SBAR 0xe6180020
+#define WUPRMSK 0xe6180028
+#define WUPSMSK 0xe618002c
+#define WUPSMSK2 0xe6180048
 #define PSTR 0xe6180080
+#define WUPSFAC 0xe6180098
+#define IRQCR 0xe618022c
+#define IRQCR2 0xe6180238
+#define IRQCR3 0xe6180244
+#define IRQCR4 0xe6180248
+#define PDNSEL 0xe6180254
+
+/* INTC */
+#define ICR1A 0xe6900000
+#define ICR2A 0xe6900004
+#define ICR3A 0xe6900008
+#define ICR4A 0xe690000c
+#define INTMSK00A 0xe6900040
+#define INTMSK10A 0xe6900044
+#define INTMSK20A 0xe6900048
+#define INTMSK30A 0xe690004c
+
+/* MFIS */
+#define SMFRAM 0xe6a70000
+
+/* AP-System Core */
+#define APARMBAREA 0xe6f10020
 
 #define PSTR_RETRIES 100
 #define PSTR_DELAY_US 10
@@ -43,6 +81,12 @@ static int pd_power_down(struct generic_pm_domain *genpd)
         struct sh7372_pm_domain *sh7372_pd = to_sh7372_pd(genpd);
         unsigned int mask = 1 << sh7372_pd->bit_shift;
 
+        if (sh7372_pd->suspend)
+                sh7372_pd->suspend();
+
+        if (sh7372_pd->stay_on)
+                return 0;
+
         if (__raw_readl(PSTR) & mask) {
                 unsigned int retry_count;
 
@@ -55,8 +99,9 @@ static int pd_power_down(struct generic_pm_domain *genpd)
                 }
         }
 
-        pr_debug("sh7372 power domain down 0x%08x -> PSTR = 0x%08x\n",
-                 mask, __raw_readl(PSTR));
+        if (!sh7372_pd->no_debug)
+                pr_debug("sh7372 power domain down 0x%08x -> PSTR = 0x%08x\n",
+                         mask, __raw_readl(PSTR));
 
         return 0;
 }
@@ -68,6 +113,9 @@ static int pd_power_up(struct generic_pm_domain *genpd)
         unsigned int retry_count;
         int ret = 0;
 
+        if (sh7372_pd->stay_on)
+                goto out;
+
         if (__raw_readl(PSTR) & mask)
                 goto out;
 
@@ -84,66 +132,48 @@ static int pd_power_up(struct generic_pm_domain *genpd)
         if (__raw_readl(SWUCR) & mask)
                 ret = -EIO;
 
+        if (!sh7372_pd->no_debug)
+                pr_debug("sh7372 power domain up 0x%08x -> PSTR = 0x%08x\n",
+                         mask, __raw_readl(PSTR));
+
  out:
-        pr_debug("sh7372 power domain up 0x%08x -> PSTR = 0x%08x\n",
-                 mask, __raw_readl(PSTR));
+        if (ret == 0 && sh7372_pd->resume)
+                sh7372_pd->resume();
 
         return ret;
 }
 
-static int pd_power_up_a3rv(struct generic_pm_domain *genpd)
+static void sh7372_a4r_suspend(void)
 {
-        int ret = pd_power_up(genpd);
-
-        /* force A4LC on after A3RV has been requested on */
-        pm_genpd_poweron(&sh7372_a4lc.genpd);
-
-        return ret;
+        sh7372_intcs_suspend();
+        __raw_writel(0x300fffff, WUPRMSK); /* avoid wakeup */
 }
 
-static int pd_power_down_a3rv(struct generic_pm_domain *genpd)
+static bool pd_active_wakeup(struct device *dev)
 {
-        int ret = pd_power_down(genpd);
-
-        /* try to power down A4LC after A3RV is requested off */
-        genpd_queue_power_off_work(&sh7372_a4lc.genpd);
-
-        return ret;
+        return true;
 }
 
-static int pd_power_down_a4lc(struct generic_pm_domain *genpd)
+static bool sh7372_power_down_forbidden(struct dev_pm_domain *domain)
 {
-        /* only power down A4LC if A3RV is off */
-        if (!(__raw_readl(PSTR) & (1 << sh7372_a3rv.bit_shift)))
-                return pd_power_down(genpd);
-
-        return -EBUSY;
+        return false;
 }
 
-static bool pd_active_wakeup(struct device *dev)
-{
-        return true;
-}
+struct dev_power_governor sh7372_always_on_gov = {
+        .power_down_ok = sh7372_power_down_forbidden,
+};
 
 void sh7372_init_pm_domain(struct sh7372_pm_domain *sh7372_pd)
 {
         struct generic_pm_domain *genpd = &sh7372_pd->genpd;
 
-        pm_genpd_init(genpd, NULL, false);
+        pm_genpd_init(genpd, sh7372_pd->gov, false);
         genpd->stop_device = pm_clk_suspend;
         genpd->start_device = pm_clk_resume;
+        genpd->dev_irq_safe = true;
         genpd->active_wakeup = pd_active_wakeup;
-
-        if (sh7372_pd == &sh7372_a4lc) {
-                genpd->power_off = pd_power_down_a4lc;
-                genpd->power_on = pd_power_up;
-        } else if (sh7372_pd == &sh7372_a3rv) {
-                genpd->power_off = pd_power_down_a3rv;
-                genpd->power_on = pd_power_up_a3rv;
-        } else {
-                genpd->power_off = pd_power_down;
-                genpd->power_on = pd_power_up;
-        }
+        genpd->power_off = pd_power_down;
+        genpd->power_on = pd_power_up;
         genpd->power_on(&sh7372_pd->genpd);
 }
 
@@ -152,11 +182,15 @@ void sh7372_add_device_to_domain(struct sh7372_pm_domain *sh7372_pd,
 {
         struct device *dev = &pdev->dev;
 
-        if (!dev->power.subsys_data) {
-                pm_clk_init(dev);
-                pm_clk_add(dev, NULL);
-        }
         pm_genpd_add_device(&sh7372_pd->genpd, dev);
+        if (pm_clk_no_clocks(dev))
+                pm_clk_add(dev, NULL);
+}
+
+void sh7372_pm_add_subdomain(struct sh7372_pm_domain *sh7372_pd,
+                             struct sh7372_pm_domain *sh7372_sd)
+{
+        pm_genpd_add_subdomain(&sh7372_pd->genpd, &sh7372_sd->genpd);
 }
 
 struct sh7372_pm_domain sh7372_a4lc = {
@@ -171,6 +205,14 @@ struct sh7372_pm_domain sh7372_d4 = {
         .bit_shift = 3,
 };
 
+struct sh7372_pm_domain sh7372_a4r = {
+        .bit_shift = 5,
+        .gov = &sh7372_always_on_gov,
+        .suspend = sh7372_a4r_suspend,
+        .resume = sh7372_intcs_resume,
+        .stay_on = true,
+};
+
 struct sh7372_pm_domain sh7372_a3rv = {
         .bit_shift = 6,
 };
@@ -179,39 +221,187 @@ struct sh7372_pm_domain sh7372_a3ri = {
         .bit_shift = 8,
 };
 
+struct sh7372_pm_domain sh7372_a3sp = {
+        .bit_shift = 11,
+        .gov = &sh7372_always_on_gov,
+        .no_debug = true,
+};
+
 struct sh7372_pm_domain sh7372_a3sg = {
         .bit_shift = 13,
 };
 
 #endif /* CONFIG_PM */
 
+#if defined(CONFIG_SUSPEND) || defined(CONFIG_CPU_IDLE)
+static int sh7372_do_idle_core_standby(unsigned long unused)
+{
+        cpu_do_idle(); /* WFI when SYSTBCR == 0x10 -> Core Standby */
+        return 0;
+}
+
 static void sh7372_enter_core_standby(void)
 {
-        void __iomem *smfram = (void __iomem *)SMFRAM;
+        /* set reset vector, translate 4k */
+        __raw_writel(__pa(sh7372_resume_core_standby_a3sm), SBAR);
+        __raw_writel(0, APARMBAREA);
 
-        __raw_writel(0, APARMBAREA); /* translate 4k */
-        __raw_writel(__pa(sh7372_cpu_resume), SBAR); /* set reset vector */
-        __raw_writel(0x10, SYSTBCR); /* enable core standby */
+        /* enter sleep mode with SYSTBCR to 0x10 */
+        __raw_writel(0x10, SYSTBCR);
+        cpu_suspend(0, sh7372_do_idle_core_standby);
+        __raw_writel(0, SYSTBCR);
 
-        __raw_writel(0, smfram + 0x3c); /* clear page table address */
+         /* disable reset vector translation */
+        __raw_writel(0, SBAR);
+}
+#endif
+
+#ifdef CONFIG_SUSPEND
+static void sh7372_enter_a3sm_common(int pllc0_on)
+{
+        /* set reset vector, translate 4k */
+        __raw_writel(__pa(sh7372_resume_core_standby_a3sm), SBAR);
+        __raw_writel(0, APARMBAREA);
+
+        if (pllc0_on)
+                __raw_writel(0, PLLC01STPCR);
+        else
+                __raw_writel(1 << 28, PLLC01STPCR);
+
+        __raw_writel(0, PDNSEL); /* power-down A3SM only, not A4S */
+        __raw_readl(WUPSFAC); /* read wakeup int. factor before sleep */
+        cpu_suspend(0, sh7372_do_idle_a3sm);
+        __raw_readl(WUPSFAC); /* read wakeup int. factor after wakeup */
+
+         /* disable reset vector translation */
+        __raw_writel(0, SBAR);
+}
+
+static int sh7372_a3sm_valid(unsigned long *mskp, unsigned long *msk2p)
+{
+        unsigned long mstpsr0, mstpsr1, mstpsr2, mstpsr3, mstpsr4;
+        unsigned long msk, msk2;
+
+        /* check active clocks to determine potential wakeup sources */
+
+        mstpsr0 = __raw_readl(MSTPSR0);
+        if ((mstpsr0 & 0x00000003) != 0x00000003) {
+                pr_debug("sh7372 mstpsr0 0x%08lx\n", mstpsr0);
+                return 0;
+        }
+
+        mstpsr1 = __raw_readl(MSTPSR1);
+        if ((mstpsr1 & 0xff079b7f) != 0xff079b7f) {
+                pr_debug("sh7372 mstpsr1 0x%08lx\n", mstpsr1);
+                return 0;
+        }
 
-        sh7372_cpu_suspend();
-        cpu_init();
+        mstpsr2 = __raw_readl(MSTPSR2);
+        if ((mstpsr2 & 0x000741ff) != 0x000741ff) {
+                pr_debug("sh7372 mstpsr2 0x%08lx\n", mstpsr2);
+                return 0;
+        }
 
-        /* if page table address is non-NULL then we have been powered down */
-        if (__raw_readl(smfram + 0x3c)) {
-                __raw_writel(__raw_readl(smfram + 0x40),
-                             __va(__raw_readl(smfram + 0x3c)));
+        mstpsr3 = __raw_readl(MSTPSR3);
+        if ((mstpsr3 & 0x1a60f010) != 0x1a60f010) {
+                pr_debug("sh7372 mstpsr3 0x%08lx\n", mstpsr3);
+                return 0;
+        }
 
-                flush_tlb_all();
-                set_cr(__raw_readl(smfram + 0x38));
+        mstpsr4 = __raw_readl(MSTPSR4);
+        if ((mstpsr4 & 0x00008cf0) != 0x00008cf0) {
+                pr_debug("sh7372 mstpsr4 0x%08lx\n", mstpsr4);
+                return 0;
         }
 
-        __raw_writel(0, SYSTBCR); /* disable core standby */
-        __raw_writel(0, SBAR); /* disable reset vector translation */
+        msk = 0;
+        msk2 = 0;
+
+        /* make bitmaps of limited number of wakeup sources */
+
+        if ((mstpsr2 & (1 << 23)) == 0) /* SPU2 */
+                msk |= 1 << 31;
+
+        if ((mstpsr2 & (1 << 12)) == 0) /* MFI_MFIM */
+                msk |= 1 << 21;
+
+        if ((mstpsr4 & (1 << 3)) == 0) /* KEYSC */
+                msk |= 1 << 2;
+
+        if ((mstpsr1 & (1 << 24)) == 0) /* CMT0 */
+                msk |= 1 << 1;
+
+        if ((mstpsr3 & (1 << 29)) == 0) /* CMT1 */
+                msk |= 1 << 1;
+
+        if ((mstpsr4 & (1 << 0)) == 0) /* CMT2 */
+                msk |= 1 << 1;
+
+        if ((mstpsr2 & (1 << 13)) == 0) /* MFI_MFIS */
+                msk2 |= 1 << 17;
+
+        *mskp = msk;
+        *msk2p = msk2;
+
+        return 1;
+}
+
+static void sh7372_icr_to_irqcr(unsigned long icr, u16 *irqcr1p, u16 *irqcr2p)
+{
+        u16 tmp, irqcr1, irqcr2;
+        int k;
+
+        irqcr1 = 0;
+        irqcr2 = 0;
+
+        /* convert INTCA ICR register layout to SYSC IRQCR+IRQCR2 */
+        for (k = 0; k <= 7; k++) {
+                tmp = (icr >> ((7 - k) * 4)) & 0xf;
+                irqcr1 |= (tmp & 0x03) << (k * 2);
+                irqcr2 |= (tmp >> 2) << (k * 2);
+        }
+
+        *irqcr1p = irqcr1;
+        *irqcr2p = irqcr2;
+}
+
+static void sh7372_setup_a3sm(unsigned long msk, unsigned long msk2)
+{
+        u16 irqcrx_low, irqcrx_high, irqcry_low, irqcry_high;
+        unsigned long tmp;
+
+        /* read IRQ0A -> IRQ15A mask */
+        tmp = bitrev8(__raw_readb(INTMSK00A));
+        tmp |= bitrev8(__raw_readb(INTMSK10A)) << 8;
+
+        /* setup WUPSMSK from clocks and external IRQ mask */
+        msk = (~msk & 0xc030000f) | (tmp << 4);
+        __raw_writel(msk, WUPSMSK);
+
+        /* propage level/edge trigger for external IRQ 0->15 */
+        sh7372_icr_to_irqcr(__raw_readl(ICR1A), &irqcrx_low, &irqcry_low);
+        sh7372_icr_to_irqcr(__raw_readl(ICR2A), &irqcrx_high, &irqcry_high);
+        __raw_writel((irqcrx_high << 16) | irqcrx_low, IRQCR);
+        __raw_writel((irqcry_high << 16) | irqcry_low, IRQCR2);
+
+        /* read IRQ16A -> IRQ31A mask */
+        tmp = bitrev8(__raw_readb(INTMSK20A));
+        tmp |= bitrev8(__raw_readb(INTMSK30A)) << 8;
+
+        /* setup WUPSMSK2 from clocks and external IRQ mask */
+        msk2 = (~msk2 & 0x00030000) | tmp;
+        __raw_writel(msk2, WUPSMSK2);
+
+        /* propage level/edge trigger for external IRQ 16->31 */
+        sh7372_icr_to_irqcr(__raw_readl(ICR3A), &irqcrx_low, &irqcry_low);
+        sh7372_icr_to_irqcr(__raw_readl(ICR4A), &irqcrx_high, &irqcry_high);
+        __raw_writel((irqcrx_high << 16) | irqcrx_low, IRQCR3);
+        __raw_writel((irqcry_high << 16) | irqcry_low, IRQCR4);
 }
+#endif
 
 #ifdef CONFIG_CPU_IDLE
+
 static void sh7372_cpuidle_setup(struct cpuidle_device *dev)
 {
         struct cpuidle_state *state;
@@ -239,9 +429,25 @@ static void sh7372_cpuidle_init(void) {}
 #endif
 
 #ifdef CONFIG_SUSPEND
+
 static int sh7372_enter_suspend(suspend_state_t suspend_state)
 {
-        sh7372_enter_core_standby();
+        unsigned long msk, msk2;
+
+        /* check active clocks to determine potential wakeup sources */
+        if (sh7372_a3sm_valid(&msk, &msk2)) {
+
+                /* convert INTC mask and sense to SYSC mask and sense */
+                sh7372_setup_a3sm(msk, msk2);
+
+                /* enter A3SM sleep with PLLC0 off */
+                pr_debug("entering A3SM\n");
+                sh7372_enter_a3sm_common(0);
+        } else {
+                /* default to Core Standby that supports all wakeup sources */
+                pr_debug("entering Core Standby\n");
+                sh7372_enter_core_standby();
+        }
         return 0;
 }
 
@@ -253,9 +459,6 @@ static void sh7372_suspend_init(void)
 static void sh7372_suspend_init(void) {}
 #endif
 
-#define DBGREG1 0xe6100020
-#define DBGREG9 0xe6100040
-
 void __init sh7372_pm_init(void)
 {
         /* enable DBG hardware block to kick SYSC */
@@ -263,6 +466,9 @@ void __init sh7372_pm_init(void)
         __raw_writel(0x0000a501, DBGREG9);
         __raw_writel(0x00000000, DBGREG1);
 
+        /* do not convert A3SM, A3SP, A3SG, A4R power down into A4S */
+        __raw_writel(0, PDNSEL);
+
         sh7372_suspend_init();
         sh7372_cpuidle_init();
 }
diff --git a/arch/arm/mach-shmobile/pm_runtime.c b/arch/arm/mach-shmobile/pm_runtime.c
index 6ec454e1e06..bd5c6a3b8c5 100644
--- a/arch/arm/mach-shmobile/pm_runtime.c
+++ b/arch/arm/mach-shmobile/pm_runtime.c
@@ -15,6 +15,7 @@
 #include <linux/io.h>
 #include <linux/pm_runtime.h>
 #include <linux/pm_domain.h>
+#include <linux/pm_clock.h>
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/sh_clk.h>
diff --git a/arch/arm/mach-shmobile/setup-sh7372.c b/arch/arm/mach-shmobile/setup-sh7372.c
index 2d9b1b1a253..2380389e6ac 100644
--- a/arch/arm/mach-shmobile/setup-sh7372.c
+++ b/arch/arm/mach-shmobile/setup-sh7372.c
@@ -30,6 +30,7 @@
 #include <linux/sh_dma.h>
 #include <linux/sh_intc.h>
 #include <linux/sh_timer.h>
+#include <linux/pm_domain.h>
 #include <mach/hardware.h>
 #include <mach/sh7372.h>
 #include <asm/mach-types.h>
@@ -990,9 +991,14 @@ void __init sh7372_add_standard_devices(void)
         sh7372_init_pm_domain(&sh7372_a4lc);
         sh7372_init_pm_domain(&sh7372_a4mp);
         sh7372_init_pm_domain(&sh7372_d4);
+        sh7372_init_pm_domain(&sh7372_a4r);
         sh7372_init_pm_domain(&sh7372_a3rv);
         sh7372_init_pm_domain(&sh7372_a3ri);
         sh7372_init_pm_domain(&sh7372_a3sg);
+        sh7372_init_pm_domain(&sh7372_a3sp);
+
+        sh7372_pm_add_subdomain(&sh7372_a4lc, &sh7372_a3rv);
+        sh7372_pm_add_subdomain(&sh7372_a4r, &sh7372_a4lc);
 
         platform_add_devices(sh7372_early_devices,
                             ARRAY_SIZE(sh7372_early_devices));
@@ -1003,6 +1009,25 @@ void __init sh7372_add_standard_devices(void)
         sh7372_add_device_to_domain(&sh7372_a3rv, &vpu_device);
         sh7372_add_device_to_domain(&sh7372_a4mp, &spu0_device);
         sh7372_add_device_to_domain(&sh7372_a4mp, &spu1_device);
+        sh7372_add_device_to_domain(&sh7372_a3sp, &scif0_device);
+        sh7372_add_device_to_domain(&sh7372_a3sp, &scif1_device);
+        sh7372_add_device_to_domain(&sh7372_a3sp, &scif2_device);
+        sh7372_add_device_to_domain(&sh7372_a3sp, &scif3_device);
+        sh7372_add_device_to_domain(&sh7372_a3sp, &scif4_device);
+        sh7372_add_device_to_domain(&sh7372_a3sp, &scif5_device);
+        sh7372_add_device_to_domain(&sh7372_a3sp, &scif6_device);
+        sh7372_add_device_to_domain(&sh7372_a3sp, &iic1_device);
+        sh7372_add_device_to_domain(&sh7372_a3sp, &dma0_device);
+        sh7372_add_device_to_domain(&sh7372_a3sp, &dma1_device);
+        sh7372_add_device_to_domain(&sh7372_a3sp, &dma2_device);
+        sh7372_add_device_to_domain(&sh7372_a3sp, &usb_dma0_device);
+        sh7372_add_device_to_domain(&sh7372_a3sp, &usb_dma1_device);
+        sh7372_add_device_to_domain(&sh7372_a4r, &iic0_device);
+        sh7372_add_device_to_domain(&sh7372_a4r, &veu0_device);
+        sh7372_add_device_to_domain(&sh7372_a4r, &veu1_device);
+        sh7372_add_device_to_domain(&sh7372_a4r, &veu2_device);
+        sh7372_add_device_to_domain(&sh7372_a4r, &veu3_device);
+        sh7372_add_device_to_domain(&sh7372_a4r, &jpu_device);
 }
 
 void __init sh7372_add_early_devices(void)
diff --git a/arch/arm/mach-shmobile/sleep-sh7372.S b/arch/arm/mach-shmobile/sleep-sh7372.S
index d37d3ca4d18..f3ab3c5810e 100644
--- a/arch/arm/mach-shmobile/sleep-sh7372.S
+++ b/arch/arm/mach-shmobile/sleep-sh7372.S
@@ -30,58 +30,20 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/init.h>
+#include <asm/memory.h>
 #include <asm/assembler.h>
 
-#define SMFRAM 0xe6a70000
-
-        .align
-kernel_flush:
-        .word   v7_flush_dcache_all
-
-        .align  3
-ENTRY(sh7372_cpu_suspend)
-        stmfd   sp!, {r0-r12, lr}       @ save registers on stack
-
-        ldr     r8, =SMFRAM
-
-        mov     r4, sp                  @ Store sp
-        mrs     r5, spsr                @ Store spsr
-        mov     r6, lr                  @ Store lr
-        stmia   r8!, {r4-r6}
-
-        mrc     p15, 0, r4, c1, c0, 2   @ Coprocessor access control register
-        mrc     p15, 0, r5, c2, c0, 0   @ TTBR0
-        mrc     p15, 0, r6, c2, c0, 1   @ TTBR1
-        mrc     p15, 0, r7, c2, c0, 2   @ TTBCR
-        stmia   r8!, {r4-r7}
-
-        mrc     p15, 0, r4, c3, c0, 0   @ Domain access Control Register
-        mrc     p15, 0, r5, c10, c2, 0  @ PRRR
-        mrc     p15, 0, r6, c10, c2, 1  @ NMRR
-        stmia   r8!,{r4-r6}
-
-        mrc     p15, 0, r4, c13, c0, 1  @ Context ID
-        mrc     p15, 0, r5, c13, c0, 2  @ User r/w thread and process ID
-        mrc     p15, 0, r6, c12, c0, 0  @ Secure or NS vector base address
-        mrs     r7, cpsr                @ Store current cpsr
-        stmia   r8!, {r4-r7}
-
-        mrc     p15, 0, r4, c1, c0, 0   @ save control register
-        stmia   r8!, {r4}
-
-        /*
-         * jump out to kernel flush routine
-         *  - reuse that code is better
-         *  - it executes in a cached space so is faster than refetch per-block
-         *  - should be faster and will change with kernel
-         *  - 'might' have to copy address, load and jump to it
-         * Flush all data from the L1 data cache before disabling
-         * SCTLR.C bit.
-         */
-        ldr     r1, kernel_flush
-        mov     lr, pc
-        bx      r1
+#if defined(CONFIG_SUSPEND) || defined(CONFIG_CPU_IDLE)
+        .align  12
+        .text
+        .global sh7372_resume_core_standby_a3sm
+sh7372_resume_core_standby_a3sm:
+        ldr     pc, 1f
+1:      .long   cpu_resume - PAGE_OFFSET + PLAT_PHYS_OFFSET
 
+        .global sh7372_do_idle_a3sm
+sh7372_do_idle_a3sm:
         /*
          * Clear the SCTLR.C bit to prevent further data cache
          * allocation. Clearing SCTLR.C would make all the data accesses
@@ -92,10 +54,13 @@ ENTRY(sh7372_cpu_suspend)
         mcr     p15, 0, r0, c1, c0, 0
         isb
 
+        /* disable L2 cache in the aux control register */
+        mrc     p15, 0, r10, c1, c0, 1
+        bic     r10, r10, #2
+        mcr     p15, 0, r10, c1, c0, 1
+
         /*
-         * Invalidate L1 data cache. Even though only invalidate is
-         * necessary exported flush API is used here. Doing clean
-         * on already clean cache would be almost NOP.
+         * Invalidate data cache again.
          */
         ldr     r1, kernel_flush
         blx     r1
@@ -115,146 +80,16 @@ ENTRY(sh7372_cpu_suspend)
         dsb
         dmb
 
-/*
- * ===================================
- * == WFI instruction => Enter idle ==
- * ===================================
- */
-        wfi                             @ wait for interrupt
-
-/*
- * ===================================
- * == Resume path for non-OFF modes ==
- * ===================================
- */
-        mrc     p15, 0, r0, c1, c0, 0
-        tst     r0, #(1 << 2)           @ Check C bit enabled?
-        orreq   r0, r0, #(1 << 2)       @ Enable the C bit if cleared
-        mcreq   p15, 0, r0, c1, c0, 0
-        isb
-
-/*
- * ===================================
- * == Exit point from non-OFF modes ==
- * ===================================
- */
-        ldmfd   sp!, {r0-r12, pc}       @ restore regs and return
+#define SPDCR 0xe6180008
+#define A3SM (1 << 12)
 
-        .pool
+        /* A3SM power down */
+        ldr     r0, =SPDCR
+        ldr     r1, =A3SM
+        str     r1, [r0]
+1:
+        b      1b
 
-        .align  12
-        .text
-        .global sh7372_cpu_resume
-sh7372_cpu_resume:
-
-        mov     r1, #0
-        /*
-         * Invalidate all instruction caches to PoU
-         * and flush branch target cache
-         */
-        mcr     p15, 0, r1, c7, c5, 0
-
-        ldr     r3, =SMFRAM
-
-        ldmia   r3!, {r4-r6}
-        mov     sp, r4                  @ Restore sp
-        msr     spsr_cxsf, r5           @ Restore spsr
-        mov     lr, r6                  @ Restore lr
-
-        ldmia   r3!, {r4-r7}
-        mcr     p15, 0, r4, c1, c0, 2   @ Coprocessor access Control Register
-        mcr     p15, 0, r5, c2, c0, 0   @ TTBR0
-        mcr     p15, 0, r6, c2, c0, 1   @ TTBR1
-        mcr     p15, 0, r7, c2, c0, 2   @ TTBCR
-
-        ldmia   r3!,{r4-r6}
-        mcr     p15, 0, r4, c3, c0, 0   @ Domain access Control Register
-        mcr     p15, 0, r5, c10, c2, 0  @ PRRR
-        mcr     p15, 0, r6, c10, c2, 1  @ NMRR
-
-        ldmia   r3!,{r4-r7}
-        mcr     p15, 0, r4, c13, c0, 1  @ Context ID
-        mcr     p15, 0, r5, c13, c0, 2  @ User r/w thread and process ID
-        mrc     p15, 0, r6, c12, c0, 0  @ Secure or NS vector base address
-        msr     cpsr, r7                @ store cpsr
-
-        /* Starting to enable MMU here */
-        mrc     p15, 0, r7, c2, c0, 2   @ Read TTBRControl
-        /* Extract N (0:2) bits and decide whether to use TTBR0 or TTBR1 */
-        and     r7, #0x7
-        cmp     r7, #0x0
-        beq     usettbr0
-ttbr_error:
-        /*
-         * More work needs to be done to support N[0:2] value other than 0
-         * So looping here so that the error can be detected
-         */
-        b       ttbr_error
-
-        .align
-cache_pred_disable_mask:
-        .word   0xFFFFE7FB
-ttbrbit_mask:
-        .word   0xFFFFC000
-table_index_mask:
-        .word   0xFFF00000
-table_entry:
-        .word   0x00000C02
-usettbr0:
-
-        mrc     p15, 0, r2, c2, c0, 0
-        ldr     r5, ttbrbit_mask
-        and     r2, r5
-        mov     r4, pc
-        ldr     r5, table_index_mask
-        and     r4, r5                  @ r4 = 31 to 20 bits of pc
-        /* Extract the value to be written to table entry */
-        ldr     r6, table_entry
-        /* r6 has the value to be written to table entry */
-        add     r6, r6, r4
-        /* Getting the address of table entry to modify */
-        lsr     r4, #18
-        /* r2 has the location which needs to be modified */
-        add     r2, r4
-        ldr     r4, [r2]
-        str     r6, [r2] /* modify the table entry */
-
-        mov     r7, r6
-        mov     r5, r2
-        mov     r6, r4
-        /* r5 = original page table address */
-        /* r6 = original page table data */
-
-        mov     r0, #0
-        mcr     p15, 0, r0, c7, c5, 4   @ Flush prefetch buffer
-        mcr     p15, 0, r0, c7, c5, 6   @ Invalidate branch predictor array
-        mcr     p15, 0, r0, c8, c5, 0   @ Invalidate instruction TLB
-        mcr     p15, 0, r0, c8, c6, 0   @ Invalidate data TLB
-
-        /*
-         * Restore control register. This enables the MMU.
-         * The caches and prediction are not enabled here, they
-         * will be enabled after restoring the MMU table entry.
-         */
-        ldmia   r3!, {r4}
-        stmia   r3!, {r5} /* save original page table address */
-        stmia   r3!, {r6} /* save original page table data */
-        stmia   r3!, {r7} /* save modified page table data */
-
-        ldr     r2, cache_pred_disable_mask
-        and     r4, r2
-        mcr     p15, 0, r4, c1, c0, 0
-        dsb
-        isb
-
-        ldr     r0, =restoremmu_on
-        bx      r0
-
-/*
- * ==============================
- * == Exit point from OFF mode ==
- * ==============================
- */
-restoremmu_on:
-
-        ldmfd   sp!, {r0-r12, pc}       @ restore regs and return
+kernel_flush:
+        .word v7_flush_dcache_all
+#endif
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index ed5cb5af528..6b99fc3f9b6 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -91,6 +91,7 @@ config S390
         select HAVE_ARCH_MUTEX_CPU_RELAX
         select HAVE_ARCH_JUMP_LABEL if !MARCH_G5
         select HAVE_RCU_TABLE_FREE if SMP
+        select ARCH_SAVE_PAGE_KEYS if HIBERNATION
         select ARCH_INLINE_SPIN_TRYLOCK
         select ARCH_INLINE_SPIN_TRYLOCK_BH
         select ARCH_INLINE_SPIN_LOCK
diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c
index cf9e5c6d552..b6f9afed74e 100644
--- a/arch/s390/kernel/suspend.c
+++ b/arch/s390/kernel/suspend.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/pfn.h>
+#include <linux/mm.h>
 #include <asm/system.h>
 
 /*
@@ -14,6 +15,123 @@
  */
 extern const void __nosave_begin, __nosave_end;
 
+/*
+ * The restore of the saved pages in an hibernation image will set
+ * the change and referenced bits in the storage key for each page.
+ * Overindication of the referenced bits after an hibernation cycle
+ * does not cause any harm but the overindication of the change bits
+ * would cause trouble.
+ * Use the ARCH_SAVE_PAGE_KEYS hooks to save the storage key of each
+ * page to the most significant byte of the associated page frame
+ * number in the hibernation image.
+ */
+
+/*
+ * Key storage is allocated as a linked list of pages.
+ * The size of the keys array is (PAGE_SIZE - sizeof(long))
+ */
+struct page_key_data {
+        struct page_key_data *next;
+        unsigned char data[];
+};
+
+#define PAGE_KEY_DATA_SIZE      (PAGE_SIZE - sizeof(struct page_key_data *))
+
+static struct page_key_data *page_key_data;
+static struct page_key_data *page_key_rp, *page_key_wp;
+static unsigned long page_key_rx, page_key_wx;
+
+/*
+ * For each page in the hibernation image one additional byte is
+ * stored in the most significant byte of the page frame number.
+ * On suspend no additional memory is required but on resume the
+ * keys need to be memorized until the page data has been restored.
+ * Only then can the storage keys be set to their old state.
+ */
+unsigned long page_key_additional_pages(unsigned long pages)
+{
+        return DIV_ROUND_UP(pages, PAGE_KEY_DATA_SIZE);
+}
+
+/*
+ * Free page_key_data list of arrays.
+ */
+void page_key_free(void)
+{
+        struct page_key_data *pkd;
+
+        while (page_key_data) {
+                pkd = page_key_data;
+                page_key_data = pkd->next;
+                free_page((unsigned long) pkd);
+        }
+}
+
+/*
+ * Allocate page_key_data list of arrays with enough room to store
+ * one byte for each page in the hibernation image.
+ */
+int page_key_alloc(unsigned long pages)
+{
+        struct page_key_data *pk;
+        unsigned long size;
+
+        size = DIV_ROUND_UP(pages, PAGE_KEY_DATA_SIZE);
+        while (size--) {
+                pk = (struct page_key_data *) get_zeroed_page(GFP_KERNEL);
+                if (!pk) {
+                        page_key_free();
+                        return -ENOMEM;
+                }
+                pk->next = page_key_data;
+                page_key_data = pk;
+        }
+        page_key_rp = page_key_wp = page_key_data;
+        page_key_rx = page_key_wx = 0;
+        return 0;
+}
+
+/*
+ * Save the storage key into the upper 8 bits of the page frame number.
+ */
+void page_key_read(unsigned long *pfn)
+{
+        unsigned long addr;
+
+        addr = (unsigned long) page_address(pfn_to_page(*pfn));
+        *(unsigned char *) pfn = (unsigned char) page_get_storage_key(addr);
+}
+
+/*
+ * Extract the storage key from the upper 8 bits of the page frame number
+ * and store it in the page_key_data list of arrays.
+ */
+void page_key_memorize(unsigned long *pfn)
+{
+        page_key_wp->data[page_key_wx] = *(unsigned char *) pfn;
+        *(unsigned char *) pfn = 0;
+        if (++page_key_wx < PAGE_KEY_DATA_SIZE)
+                return;
+        page_key_wp = page_key_wp->next;
+        page_key_wx = 0;
+}
+
+/*
+ * Get the next key from the page_key_data list of arrays and set the
+ * storage key of the page referred by @address. If @address refers to
+ * a "safe" page the swsusp_arch_resume code will transfer the storage
+ * key from the buffer page to the original page.
+ */
+void page_key_write(void *address)
+{
+        page_set_storage_key((unsigned long) address,
+                             page_key_rp->data[page_key_rx], 0);
+        if (++page_key_rx >= PAGE_KEY_DATA_SIZE)
+                return;
+        page_key_rp = page_key_rp->next;
+        page_key_rx = 0;
+}
+
 int pfn_is_nosave(unsigned long pfn)
 {
         unsigned long nosave_begin_pfn = PFN_DOWN(__pa(&__nosave_begin));
diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S
index 51bcdb50a23..acb78cdee89 100644
--- a/arch/s390/kernel/swsusp_asm64.S
+++ b/arch/s390/kernel/swsusp_asm64.S
@@ -136,11 +136,14 @@ ENTRY(swsusp_arch_resume)
 0:
         lg      %r2,8(%r1)
         lg      %r4,0(%r1)
+        iske    %r0,%r4
         lghi    %r3,PAGE_SIZE
         lghi    %r5,PAGE_SIZE
 1:
         mvcle   %r2,%r4,0
         jo      1b
+        lg      %r2,8(%r1)
+        sske    %r0,%r2
         lg      %r1,16(%r1)
         ltgr    %r1,%r1
         jnz     0b
diff --git a/drivers/Kconfig b/drivers/Kconfig
index e73aaaee013..6268167a1bb 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -132,4 +132,6 @@ source "drivers/iommu/Kconfig"
 
 source "drivers/virt/Kconfig"
 
+source "drivers/devfreq/Kconfig"
+
 endmenu
diff --git a/drivers/Makefile b/drivers/Makefile
index e7afb3acbc6..755eaf7a728 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -129,3 +129,5 @@ obj-$(CONFIG_IOMMU_SUPPORT)	+= iommu/
 
 # Virtualization drivers
 obj-$(CONFIG_VIRT_DRIVERS)      += virt/
+
+obj-$(CONFIG_PM_DEVFREQ)        += devfreq/
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 431ab11c8c1..2e69e09ff03 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -37,7 +37,7 @@
 #include <linux/dmi.h>
 #include <linux/moduleparam.h>
 #include <linux/sched.h>        /* need_resched() */
-#include <linux/pm_qos_params.h>
+#include <linux/pm_qos.h>
 #include <linux/clockchips.h>
 #include <linux/cpuidle.h>
 #include <linux/irqflags.h>
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 3ed80b2ca90..0e46faef1d3 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -390,6 +390,14 @@ static struct dmi_system_id __initdata acpisleep_dmi_table[] = {
         },
         {
         .callback = init_nvs_nosave,
+        .ident = "Sony Vaio VGN-FW21E",
+        .matches = {
+                DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
+                DMI_MATCH(DMI_PRODUCT_NAME, "VGN-FW21E"),
+                },
+        },
+        {
+        .callback = init_nvs_nosave,
         .ident = "Sony Vaio VGN-SR11M",
         .matches = {
                 DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
@@ -444,6 +452,22 @@ static struct dmi_system_id __initdata acpisleep_dmi_table[] = {
                 DMI_MATCH(DMI_BOARD_NAME, "A8N-SLI Premium"),
                 },
         },
+        {
+        .callback = init_nvs_nosave,
+        .ident = "Sony Vaio VGN-SR26GN_P",
+        .matches = {
+                DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
+                DMI_MATCH(DMI_PRODUCT_NAME, "VGN-SR26GN_P"),
+                },
+        },
+        {
+        .callback = init_nvs_nosave,
+        .ident = "Sony Vaio VGN-FW520F",
+        .matches = {
+                DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
+                DMI_MATCH(DMI_PRODUCT_NAME, "VGN-FW520F"),
+                },
+        },
         {},
 };
 #endif /* CONFIG_SUSPEND */
diff --git a/drivers/base/power/Makefile b/drivers/base/power/Makefile
index 2639ae79a37..81676dd1790 100644
--- a/drivers/base/power/Makefile
+++ b/drivers/base/power/Makefile
@@ -1,4 +1,4 @@
-obj-$(CONFIG_PM)        += sysfs.o generic_ops.o
+obj-$(CONFIG_PM)        += sysfs.o generic_ops.o common.o qos.o
 obj-$(CONFIG_PM_SLEEP)  += main.o wakeup.o
 obj-$(CONFIG_PM_RUNTIME)        += runtime.o
 obj-$(CONFIG_PM_TRACE_RTC)      += trace.o
@@ -6,4 +6,4 @@ obj-$(CONFIG_PM_OPP)	+= opp.o
 obj-$(CONFIG_PM_GENERIC_DOMAINS)        +=  domain.o
 obj-$(CONFIG_HAVE_CLK)  += clock_ops.o
 
-ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG
\ No newline at end of file
+ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG
diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
index b97294e2d95..5f0f85d5c57 100644
--- a/drivers/base/power/clock_ops.c
+++ b/drivers/base/power/clock_ops.c
@@ -10,18 +10,13 @@
 #include <linux/kernel.h>
 #include <linux/io.h>
 #include <linux/pm.h>
-#include <linux/pm_runtime.h>
+#include <linux/pm_clock.h>
 #include <linux/clk.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 
 #ifdef CONFIG_PM
 
-struct pm_clk_data {
-        struct list_head clock_list;
-        spinlock_t lock;
-};
-
 enum pce_status {
         PCE_STATUS_NONE = 0,
         PCE_STATUS_ACQUIRED,
@@ -36,11 +31,6 @@ struct pm_clock_entry {
         enum pce_status status;
 };
 
-static struct pm_clk_data *__to_pcd(struct device *dev)
-{
-        return dev ? dev->power.subsys_data : NULL;
-}
-
 /**
  * pm_clk_acquire - Acquire a device clock.
  * @dev: Device whose clock is to be acquired.
@@ -67,10 +57,10 @@ static void pm_clk_acquire(struct device *dev, struct pm_clock_entry *ce)
  */
 int pm_clk_add(struct device *dev, const char *con_id)
 {
-        struct pm_clk_data *pcd = __to_pcd(dev);
+        struct pm_subsys_data *psd = dev_to_psd(dev);
         struct pm_clock_entry *ce;
 
-        if (!pcd)
+        if (!psd)
                 return -EINVAL;
 
         ce = kzalloc(sizeof(*ce), GFP_KERNEL);
@@ -91,9 +81,9 @@ int pm_clk_add(struct device *dev, const char *con_id)
 
         pm_clk_acquire(dev, ce);
 
-        spin_lock_irq(&pcd->lock);
-        list_add_tail(&ce->node, &pcd->clock_list);
-        spin_unlock_irq(&pcd->lock);
+        spin_lock_irq(&psd->lock);
+        list_add_tail(&ce->node, &psd->clock_list);
+        spin_unlock_irq(&psd->lock);
         return 0;
 }
 
@@ -114,9 +104,7 @@ static void __pm_clk_remove(struct pm_clock_entry *ce)
                         clk_put(ce->clk);
         }
 
-        if (ce->con_id)
-                kfree(ce->con_id);
-
+        kfree(ce->con_id);
         kfree(ce);
 }
 
@@ -130,15 +118,15 @@ static void __pm_clk_remove(struct pm_clock_entry *ce)
  */
 void pm_clk_remove(struct device *dev, const char *con_id)
 {
-        struct pm_clk_data *pcd = __to_pcd(dev);
+        struct pm_subsys_data *psd = dev_to_psd(dev);
         struct pm_clock_entry *ce;
 
-        if (!pcd)
+        if (!psd)
                 return;
 
-        spin_lock_irq(&pcd->lock);
+        spin_lock_irq(&psd->lock);
 
-        list_for_each_entry(ce, &pcd->clock_list, node) {
+        list_for_each_entry(ce, &psd->clock_list, node) {
                 if (!con_id && !ce->con_id)
                         goto remove;
                 else if (!con_id || !ce->con_id)
@@ -147,12 +135,12 @@ void pm_clk_remove(struct device *dev, const char *con_id)
                         goto remove;
         }
 
-        spin_unlock_irq(&pcd->lock);
+        spin_unlock_irq(&psd->lock);
         return;
 
  remove:
         list_del(&ce->node);
-        spin_unlock_irq(&pcd->lock);
+        spin_unlock_irq(&psd->lock);
 
         __pm_clk_remove(ce);
 }
@@ -161,23 +149,27 @@ void pm_clk_remove(struct device *dev, const char *con_id)
  * pm_clk_init - Initialize a device's list of power management clocks.
  * @dev: Device to initialize the list of PM clocks for.
  *
- * Allocate a struct pm_clk_data object, initialize its lock member and
- * make the @dev's power.subsys_data field point to it.
+ * Initialize the lock and clock_list members of the device's pm_subsys_data
+ * object.
  */
-int pm_clk_init(struct device *dev)
+void pm_clk_init(struct device *dev)
 {
-        struct pm_clk_data *pcd;
-
-        pcd = kzalloc(sizeof(*pcd), GFP_KERNEL);
-        if (!pcd) {
-                dev_err(dev, "Not enough memory for PM clock data.\n");
-                return -ENOMEM;
-        }
+        struct pm_subsys_data *psd = dev_to_psd(dev);
+        if (psd)
+                INIT_LIST_HEAD(&psd->clock_list);
+}
 
-        INIT_LIST_HEAD(&pcd->clock_list);
-        spin_lock_init(&pcd->lock);
-        dev->power.subsys_data = pcd;
-        return 0;
+/**
+ * pm_clk_create - Create and initialize a device's list of PM clocks.
+ * @dev: Device to create and initialize the list of PM clocks for.
+ *
+ * Allocate a struct pm_subsys_data object, initialize its lock and clock_list
+ * members and make the @dev's power.subsys_data field point to it.
+ */
+int pm_clk_create(struct device *dev)
+{
+        int ret = dev_pm_get_subsys_data(dev);
+        return ret < 0 ? ret : 0;
 }
 
 /**
@@ -185,29 +177,28 @@ int pm_clk_init(struct device *dev)
  * @dev: Device to destroy the list of PM clocks for.
  *
  * Clear the @dev's power.subsys_data field, remove the list of clock entries
- * from the struct pm_clk_data object pointed to by it before and free
+ * from the struct pm_subsys_data object pointed to by it before and free
  * that object.
  */
 void pm_clk_destroy(struct device *dev)
 {
-        struct pm_clk_data *pcd = __to_pcd(dev);
+        struct pm_subsys_data *psd = dev_to_psd(dev);
         struct pm_clock_entry *ce, *c;
         struct list_head list;
 
-        if (!pcd)
+        if (!psd)
                 return;
 
-        dev->power.subsys_data = NULL;
         INIT_LIST_HEAD(&list);
 
-        spin_lock_irq(&pcd->lock);
+        spin_lock_irq(&psd->lock);
 
-        list_for_each_entry_safe_reverse(ce, c, &pcd->clock_list, node)
+        list_for_each_entry_safe_reverse(ce, c, &psd->clock_list, node)
                 list_move(&ce->node, &list);
 
-        spin_unlock_irq(&pcd->lock);
+        spin_unlock_irq(&psd->lock);
 
-        kfree(pcd);
+        dev_pm_put_subsys_data(dev);
 
         list_for_each_entry_safe_reverse(ce, c, &list, node) {
                 list_del(&ce->node);
@@ -225,25 +216,25 @@ void pm_clk_destroy(struct device *dev)
  */
 int pm_clk_suspend(struct device *dev)
 {
-        struct pm_clk_data *pcd = __to_pcd(dev);
+        struct pm_subsys_data *psd = dev_to_psd(dev);
         struct pm_clock_entry *ce;
         unsigned long flags;
 
         dev_dbg(dev, "%s()\n", __func__);
 
-        if (!pcd)
+        if (!psd)
                 return 0;
 
-        spin_lock_irqsave(&pcd->lock, flags);
+        spin_lock_irqsave(&psd->lock, flags);
 
-        list_for_each_entry_reverse(ce, &pcd->clock_list, node) {
+        list_for_each_entry_reverse(ce, &psd->clock_list, node) {
                 if (ce->status < PCE_STATUS_ERROR) {
                         clk_disable(ce->clk);
                         ce->status = PCE_STATUS_ACQUIRED;
                 }
         }
 
-        spin_unlock_irqrestore(&pcd->lock, flags);
+        spin_unlock_irqrestore(&psd->lock, flags);
 
         return 0;
 }
@@ -254,25 +245,25 @@ int pm_clk_suspend(struct device *dev)
  */
 int pm_clk_resume(struct device *dev)
 {
-        struct pm_clk_data *pcd = __to_pcd(dev);
+        struct pm_subsys_data *psd = dev_to_psd(dev);
         struct pm_clock_entry *ce;
         unsigned long flags;
 
         dev_dbg(dev, "%s()\n", __func__);
 
-        if (!pcd)
+        if (!psd)
                 return 0;
 
-        spin_lock_irqsave(&pcd->lock, flags);
+        spin_lock_irqsave(&psd->lock, flags);
 
-        list_for_each_entry(ce, &pcd->clock_list, node) {
+        list_for_each_entry(ce, &psd->clock_list, node) {
                 if (ce->status < PCE_STATUS_ERROR) {
                         clk_enable(ce->clk);
                         ce->status = PCE_STATUS_ENABLED;
                 }
         }
 
-        spin_unlock_irqrestore(&pcd->lock, flags);
+        spin_unlock_irqrestore(&psd->lock, flags);
 
         return 0;
 }
@@ -310,7 +301,7 @@ static int pm_clk_notify(struct notifier_block *nb,
                 if (dev->pm_domain)
                         break;
 
-                error = pm_clk_init(dev);
+                error = pm_clk_create(dev);
                 if (error)
                         break;
 
@@ -345,22 +336,22 @@ static int pm_clk_notify(struct notifier_block *nb,
  */
 int pm_clk_suspend(struct device *dev)
 {
-        struct pm_clk_data *pcd = __to_pcd(dev);
+        struct pm_subsys_data *psd = dev_to_psd(dev);
         struct pm_clock_entry *ce;
         unsigned long flags;
 
         dev_dbg(dev, "%s()\n", __func__);
 
         /* If there is no driver, the clocks are already disabled. */
-        if (!pcd || !dev->driver)
+        if (!psd || !dev->driver)
                 return 0;
 
-        spin_lock_irqsave(&pcd->lock, flags);
+        spin_lock_irqsave(&psd->lock, flags);
 
-        list_for_each_entry_reverse(ce, &pcd->clock_list, node)
+        list_for_each_entry_reverse(ce, &psd->clock_list, node)
                 clk_disable(ce->clk);
 
-        spin_unlock_irqrestore(&pcd->lock, flags);
+        spin_unlock_irqrestore(&psd->lock, flags);
 
         return 0;
 }
@@ -371,22 +362,22 @@ int pm_clk_suspend(struct device *dev)
  */
 int pm_clk_resume(struct device *dev)
 {
-        struct pm_clk_data *pcd = __to_pcd(dev);
+        struct pm_subsys_data *psd = dev_to_psd(dev);
         struct pm_clock_entry *ce;
         unsigned long flags;
 
         dev_dbg(dev, "%s()\n", __func__);
 
         /* If there is no driver, the clocks should remain disabled. */
-        if (!pcd || !dev->driver)
+        if (!psd || !dev->driver)
                 return 0;
 
-        spin_lock_irqsave(&pcd->lock, flags);
+        spin_lock_irqsave(&psd->lock, flags);
 
-        list_for_each_entry(ce, &pcd->clock_list, node)
+        list_for_each_entry(ce, &psd->clock_list, node)
                 clk_enable(ce->clk);
 
-        spin_unlock_irqrestore(&pcd->lock, flags);
+        spin_unlock_irqrestore(&psd->lock, flags);
 
         return 0;
 }
diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c
new file mode 100644
index 00000000000..29820c39618
--- /dev/null
+++ b/drivers/base/power/common.c
@@ -0,0 +1,86 @@
+/*
+ * drivers/base/power/common.c - Common device power management code.
+ *
+ * Copyright (C) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Renesas Electronics Corp.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/pm_clock.h>
+
+/**
+ * dev_pm_get_subsys_data - Create or refcount power.subsys_data for device.
+ * @dev: Device to handle.
+ *
+ * If power.subsys_data is NULL, point it to a new object, otherwise increment
+ * its reference counter.  Return 1 if a new object has been created, otherwise
+ * return 0 or error code.
+ */
+int dev_pm_get_subsys_data(struct device *dev)
+{
+        struct pm_subsys_data *psd;
+        int ret = 0;
+
+        psd = kzalloc(sizeof(*psd), GFP_KERNEL);
+        if (!psd)
+                return -ENOMEM;
+
+        spin_lock_irq(&dev->power.lock);
+
+        if (dev->power.subsys_data) {
+                dev->power.subsys_data->refcount++;
+        } else {
+                spin_lock_init(&psd->lock);
+                psd->refcount = 1;
+                dev->power.subsys_data = psd;
+                pm_clk_init(dev);
+                psd = NULL;
+                ret = 1;
+        }
+
+        spin_unlock_irq(&dev->power.lock);
+
+        /* kfree() verifies that its argument is nonzero. */
+        kfree(psd);
+
+        return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_get_subsys_data);
+
+/**
+ * dev_pm_put_subsys_data - Drop reference to power.subsys_data.
+ * @dev: Device to handle.
+ *
+ * If the reference counter of power.subsys_data is zero after dropping the
+ * reference, power.subsys_data is removed.  Return 1 if that happens or 0
+ * otherwise.
+ */
+int dev_pm_put_subsys_data(struct device *dev)
+{
+        struct pm_subsys_data *psd;
+        int ret = 0;
+
+        spin_lock_irq(&dev->power.lock);
+
+        psd = dev_to_psd(dev);
+        if (!psd) {
+                ret = -EINVAL;
+                goto out;
+        }
+
+        if (--psd->refcount == 0) {
+                dev->power.subsys_data = NULL;
+                kfree(psd);
+                ret = 1;
+        }
+
+ out:
+        spin_unlock_irq(&dev->power.lock);
+
+        return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_put_subsys_data);
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 1c374579407..6790cf7eba5 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -29,10 +29,20 @@ static struct generic_pm_domain *dev_to_genpd(struct device *dev)
         return pd_to_genpd(dev->pm_domain);
 }
 
-static void genpd_sd_counter_dec(struct generic_pm_domain *genpd)
+static bool genpd_sd_counter_dec(struct generic_pm_domain *genpd)
 {
-        if (!WARN_ON(genpd->sd_count == 0))
-                        genpd->sd_count--;
+        bool ret = false;
+
+        if (!WARN_ON(atomic_read(&genpd->sd_count) == 0))
+                ret = !!atomic_dec_and_test(&genpd->sd_count);
+
+        return ret;
+}
+
+static void genpd_sd_counter_inc(struct generic_pm_domain *genpd)
+{
+        atomic_inc(&genpd->sd_count);
+        smp_mb__after_atomic_inc();
 }
 
 static void genpd_acquire_lock(struct generic_pm_domain *genpd)
@@ -71,81 +81,119 @@ static void genpd_set_active(struct generic_pm_domain *genpd)
 }
 
 /**
- * pm_genpd_poweron - Restore power to a given PM domain and its parents.
+ * __pm_genpd_poweron - Restore power to a given PM domain and its masters.
  * @genpd: PM domain to power up.
  *
- * Restore power to @genpd and all of its parents so that it is possible to
+ * Restore power to @genpd and all of its masters so that it is possible to
  * resume a device belonging to it.
  */
-int pm_genpd_poweron(struct generic_pm_domain *genpd)
+int __pm_genpd_poweron(struct generic_pm_domain *genpd)
+        __releases(&genpd->lock) __acquires(&genpd->lock)
 {
-        struct generic_pm_domain *parent = genpd->parent;
+        struct gpd_link *link;
+        DEFINE_WAIT(wait);
         int ret = 0;
 
- start:
-        if (parent) {
-                genpd_acquire_lock(parent);
-                mutex_lock_nested(&genpd->lock, SINGLE_DEPTH_NESTING);
-        } else {
+        /* If the domain's master is being waited for, we have to wait too. */
+        for (;;) {
+                prepare_to_wait(&genpd->status_wait_queue, &wait,
+                                TASK_UNINTERRUPTIBLE);
+                if (genpd->status != GPD_STATE_WAIT_MASTER)
+                        break;
+                mutex_unlock(&genpd->lock);
+
+                schedule();
+
                 mutex_lock(&genpd->lock);
         }
+        finish_wait(&genpd->status_wait_queue, &wait);
 
         if (genpd->status == GPD_STATE_ACTIVE
             || (genpd->prepared_count > 0 && genpd->suspend_power_off))
-                goto out;
+                return 0;
 
         if (genpd->status != GPD_STATE_POWER_OFF) {
                 genpd_set_active(genpd);
-                goto out;
+                return 0;
         }
 
-        if (parent && parent->status != GPD_STATE_ACTIVE) {
+        /*
+         * The list is guaranteed not to change while the loop below is being
+         * executed, unless one of the masters' .power_on() callbacks fiddles
+         * with it.
+         */
+        list_for_each_entry(link, &genpd->slave_links, slave_node) {
+                genpd_sd_counter_inc(link->master);
+                genpd->status = GPD_STATE_WAIT_MASTER;
+
                 mutex_unlock(&genpd->lock);
-                genpd_release_lock(parent);
 
-                ret = pm_genpd_poweron(parent);
-                if (ret)
-                        return ret;
+                ret = pm_genpd_poweron(link->master);
 
-                goto start;
+                mutex_lock(&genpd->lock);
+
+                /*
+                 * The "wait for parent" status is guaranteed not to change
+                 * while the master is powering on.
+                 */
+                genpd->status = GPD_STATE_POWER_OFF;
+                wake_up_all(&genpd->status_wait_queue);
+                if (ret) {
+                        genpd_sd_counter_dec(link->master);
+                        goto err;
+                }
         }
 
         if (genpd->power_on) {
                 ret = genpd->power_on(genpd);
                 if (ret)
-                        goto out;
+                        goto err;
         }
 
         genpd_set_active(genpd);
-        if (parent)
-                parent->sd_count++;
 
- out:
-        mutex_unlock(&genpd->lock);
-        if (parent)
-                genpd_release_lock(parent);
+        return 0;
+
+ err:
+        list_for_each_entry_continue_reverse(link, &genpd->slave_links, slave_node)
+                genpd_sd_counter_dec(link->master);
 
         return ret;
 }
 
+/**
+ * pm_genpd_poweron - Restore power to a given PM domain and its masters.
+ * @genpd: PM domain to power up.
+ */
+int pm_genpd_poweron(struct generic_pm_domain *genpd)
+{
+        int ret;
+
+        mutex_lock(&genpd->lock);
+        ret = __pm_genpd_poweron(genpd);
+        mutex_unlock(&genpd->lock);
+        return ret;
+}
+
 #endif /* CONFIG_PM */
 
 #ifdef CONFIG_PM_RUNTIME
 
 /**
  * __pm_genpd_save_device - Save the pre-suspend state of a device.
- * @dle: Device list entry of the device to save the state of.
+ * @pdd: Domain data of the device to save the state of.
  * @genpd: PM domain the device belongs to.
  */
-static int __pm_genpd_save_device(struct dev_list_entry *dle,
+static int __pm_genpd_save_device(struct pm_domain_data *pdd,
                                   struct generic_pm_domain *genpd)
         __releases(&genpd->lock) __acquires(&genpd->lock)
 {
-        struct device *dev = dle->dev;
+        struct generic_pm_domain_data *gpd_data = to_gpd_data(pdd);
+        struct device *dev = pdd->dev;
         struct device_driver *drv = dev->driver;
         int ret = 0;
 
-        if (dle->need_restore)
+        if (gpd_data->need_restore)
                 return 0;
 
         mutex_unlock(&genpd->lock);
@@ -163,24 +211,25 @@ static int __pm_genpd_save_device(struct dev_list_entry *dle,
         mutex_lock(&genpd->lock);
 
         if (!ret)
-                dle->need_restore = true;
+                gpd_data->need_restore = true;
 
         return ret;
 }
 
 /**
  * __pm_genpd_restore_device - Restore the pre-suspend state of a device.
- * @dle: Device list entry of the device to restore the state of.
+ * @pdd: Domain data of the device to restore the state of.
  * @genpd: PM domain the device belongs to.
  */
-static void __pm_genpd_restore_device(struct dev_list_entry *dle,
+static void __pm_genpd_restore_device(struct pm_domain_data *pdd,
                                       struct generic_pm_domain *genpd)
         __releases(&genpd->lock) __acquires(&genpd->lock)
 {
-        struct device *dev = dle->dev;
+        struct generic_pm_domain_data *gpd_data = to_gpd_data(pdd);
+        struct device *dev = pdd->dev;
         struct device_driver *drv = dev->driver;
 
-        if (!dle->need_restore)
+        if (!gpd_data->need_restore)
                 return;
 
         mutex_unlock(&genpd->lock);
@@ -197,7 +246,7 @@ static void __pm_genpd_restore_device(struct dev_list_entry *dle,
 
         mutex_lock(&genpd->lock);
 
-        dle->need_restore = false;
+        gpd_data->need_restore = false;
 }
 
 /**
@@ -211,7 +260,8 @@ static void __pm_genpd_restore_device(struct dev_list_entry *dle,
  */
 static bool genpd_abort_poweroff(struct generic_pm_domain *genpd)
 {
-        return genpd->status == GPD_STATE_ACTIVE || genpd->resume_count > 0;
+        return genpd->status == GPD_STATE_WAIT_MASTER
+                || genpd->status == GPD_STATE_ACTIVE || genpd->resume_count > 0;
 }
 
 /**
@@ -238,8 +288,8 @@ void genpd_queue_power_off_work(struct generic_pm_domain *genpd)
 static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
         __releases(&genpd->lock) __acquires(&genpd->lock)
 {
-        struct generic_pm_domain *parent;
-        struct dev_list_entry *dle;
+        struct pm_domain_data *pdd;
+        struct gpd_link *link;
         unsigned int not_suspended;
         int ret = 0;
 
@@ -247,19 +297,22 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
         /*
          * Do not try to power off the domain in the following situations:
          * (1) The domain is already in the "power off" state.
-         * (2) System suspend is in progress.
+         * (2) The domain is waiting for its master to power up.
          * (3) One of the domain's devices is being resumed right now.
+         * (4) System suspend is in progress.
          */
-        if (genpd->status == GPD_STATE_POWER_OFF || genpd->prepared_count > 0
-            || genpd->resume_count > 0)
+        if (genpd->status == GPD_STATE_POWER_OFF
+            || genpd->status == GPD_STATE_WAIT_MASTER
+            || genpd->resume_count > 0 || genpd->prepared_count > 0)
                 return 0;
 
-        if (genpd->sd_count > 0)
+        if (atomic_read(&genpd->sd_count) > 0)
                 return -EBUSY;
 
         not_suspended = 0;
-        list_for_each_entry(dle, &genpd->dev_list, node)
-                if (dle->dev->driver && !pm_runtime_suspended(dle->dev))
+        list_for_each_entry(pdd, &genpd->dev_list, list_node)
+                if (pdd->dev->driver && (!pm_runtime_suspended(pdd->dev)
+                    || pdd->dev->power.irq_safe))
                         not_suspended++;
 
         if (not_suspended > genpd->in_progress)
@@ -282,54 +335,50 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
         genpd->status = GPD_STATE_BUSY;
         genpd->poweroff_task = current;
 
-        list_for_each_entry_reverse(dle, &genpd->dev_list, node) {
-                ret = __pm_genpd_save_device(dle, genpd);
+        list_for_each_entry_reverse(pdd, &genpd->dev_list, list_node) {
+                ret = atomic_read(&genpd->sd_count) == 0 ?
+                        __pm_genpd_save_device(pdd, genpd) : -EBUSY;
+
+                if (genpd_abort_poweroff(genpd))
+                        goto out;
+
                 if (ret) {
                         genpd_set_active(genpd);
                         goto out;
                 }
 
-                if (genpd_abort_poweroff(genpd))
-                        goto out;
-
                 if (genpd->status == GPD_STATE_REPEAT) {
                         genpd->poweroff_task = NULL;
                         goto start;
                 }
         }
 
-        parent = genpd->parent;
-        if (parent) {
-                mutex_unlock(&genpd->lock);
-
-                genpd_acquire_lock(parent);
-                mutex_lock_nested(&genpd->lock, SINGLE_DEPTH_NESTING);
-
-                if (genpd_abort_poweroff(genpd)) {
-                        genpd_release_lock(parent);
+        if (genpd->power_off) {
+                if (atomic_read(&genpd->sd_count) > 0) {
+                        ret = -EBUSY;
                         goto out;
                 }
-        }
 
-        if (genpd->power_off) {
+                /*
+                 * If sd_count > 0 at this point, one of the subdomains hasn't
+                 * managed to call pm_genpd_poweron() for the master yet after
+                 * incrementing it.  In that case pm_genpd_poweron() will wait
+                 * for us to drop the lock, so we can call .power_off() and let
+                 * the pm_genpd_poweron() restore power for us (this shouldn't
+                 * happen very often).
+                 */
                 ret = genpd->power_off(genpd);
                 if (ret == -EBUSY) {
                         genpd_set_active(genpd);
-                        if (parent)
-                                genpd_release_lock(parent);
-
                         goto out;
                 }
         }
 
         genpd->status = GPD_STATE_POWER_OFF;
 
-        if (parent) {
-                genpd_sd_counter_dec(parent);
-                if (parent->sd_count == 0)
-                        genpd_queue_power_off_work(parent);
-
-                genpd_release_lock(parent);
+        list_for_each_entry(link, &genpd->slave_links, slave_node) {
+                genpd_sd_counter_dec(link->master);
+                genpd_queue_power_off_work(link->master);
         }
 
  out:
@@ -371,12 +420,21 @@ static int pm_genpd_runtime_suspend(struct device *dev)
         if (IS_ERR(genpd))
                 return -EINVAL;
 
+        might_sleep_if(!genpd->dev_irq_safe);
+
         if (genpd->stop_device) {
                 int ret = genpd->stop_device(dev);
                 if (ret)
                         return ret;
         }
 
+        /*
+         * If power.irq_safe is set, this routine will be run with interrupts
+         * off, so it can't use mutexes.
+         */
+        if (dev->power.irq_safe)
+                return 0;
+
         mutex_lock(&genpd->lock);
         genpd->in_progress++;
         pm_genpd_poweroff(genpd);
@@ -387,24 +445,6 @@ static int pm_genpd_runtime_suspend(struct device *dev)
 }
 
 /**
- * __pm_genpd_runtime_resume - Resume a device belonging to I/O PM domain.
- * @dev: Device to resume.
- * @genpd: PM domain the device belongs to.
- */
-static void __pm_genpd_runtime_resume(struct device *dev,
-                                      struct generic_pm_domain *genpd)
-{
-        struct dev_list_entry *dle;
-
-        list_for_each_entry(dle, &genpd->dev_list, node) {
-                if (dle->dev == dev) {
-                        __pm_genpd_restore_device(dle, genpd);
-                        break;
-                }
-        }
-}
-
-/**
  * pm_genpd_runtime_resume - Resume a device belonging to I/O PM domain.
  * @dev: Device to resume.
  *
@@ -424,11 +464,18 @@ static int pm_genpd_runtime_resume(struct device *dev)
         if (IS_ERR(genpd))
                 return -EINVAL;
 
-        ret = pm_genpd_poweron(genpd);
-        if (ret)
-                return ret;
+        might_sleep_if(!genpd->dev_irq_safe);
+
+        /* If power.irq_safe, the PM domain is never powered off. */
+        if (dev->power.irq_safe)
+                goto out;
 
         mutex_lock(&genpd->lock);
+        ret = __pm_genpd_poweron(genpd);
+        if (ret) {
+                mutex_unlock(&genpd->lock);
+                return ret;
+        }
         genpd->status = GPD_STATE_BUSY;
         genpd->resume_count++;
         for (;;) {
@@ -448,12 +495,13 @@ static int pm_genpd_runtime_resume(struct device *dev)
                 mutex_lock(&genpd->lock);
         }
         finish_wait(&genpd->status_wait_queue, &wait);
-        __pm_genpd_runtime_resume(dev, genpd);
+        __pm_genpd_restore_device(dev->power.subsys_data->domain_data, genpd);
         genpd->resume_count--;
         genpd_set_active(genpd);
         wake_up_all(&genpd->status_wait_queue);
         mutex_unlock(&genpd->lock);
 
+ out:
         if (genpd->start_device)
                 genpd->start_device(dev);
 
@@ -478,8 +526,6 @@ void pm_genpd_poweroff_unused(void)
 #else
 
 static inline void genpd_power_off_work_fn(struct work_struct *work) {}
-static inline void __pm_genpd_runtime_resume(struct device *dev,
-                                             struct generic_pm_domain *genpd) {}
 
 #define pm_genpd_runtime_suspend        NULL
 #define pm_genpd_runtime_resume         NULL
@@ -489,11 +535,11 @@ static inline void __pm_genpd_runtime_resume(struct device *dev,
 #ifdef CONFIG_PM_SLEEP
 
 /**
- * pm_genpd_sync_poweroff - Synchronously power off a PM domain and its parents.
+ * pm_genpd_sync_poweroff - Synchronously power off a PM domain and its masters.
  * @genpd: PM domain to power off, if possible.
  *
  * Check if the given PM domain can be powered off (during system suspend or
- * hibernation) and do that if so.  Also, in that case propagate to its parent.
+ * hibernation) and do that if so.  Also, in that case propagate to its masters.
  *
  * This function is only called in "noirq" stages of system power transitions,
  * so it need not acquire locks (all of the "noirq" callbacks are executed
@@ -501,21 +547,23 @@ static inline void __pm_genpd_runtime_resume(struct device *dev,
  */
 static void pm_genpd_sync_poweroff(struct generic_pm_domain *genpd)
 {
-        struct generic_pm_domain *parent = genpd->parent;
+        struct gpd_link *link;
 
         if (genpd->status == GPD_STATE_POWER_OFF)
                 return;
 
-        if (genpd->suspended_count != genpd->device_count || genpd->sd_count > 0)
+        if (genpd->suspended_count != genpd->device_count
+            || atomic_read(&genpd->sd_count) > 0)
                 return;
 
         if (genpd->power_off)
                 genpd->power_off(genpd);
 
         genpd->status = GPD_STATE_POWER_OFF;
-        if (parent) {
-                genpd_sd_counter_dec(parent);
-                pm_genpd_sync_poweroff(parent);
+
+        list_for_each_entry(link, &genpd->slave_links, slave_node) {
+                genpd_sd_counter_dec(link->master);
+                pm_genpd_sync_poweroff(link->master);
         }
 }
 
@@ -666,7 +714,7 @@ static int pm_genpd_suspend_noirq(struct device *dev)
         if (ret)
                 return ret;
 
-        if (device_may_wakeup(dev)
+        if (dev->power.wakeup_path
             && genpd->active_wakeup && genpd->active_wakeup(dev))
                 return 0;
 
@@ -890,7 +938,7 @@ static int pm_genpd_dev_poweroff_noirq(struct device *dev)
         if (ret)
                 return ret;
 
-        if (device_may_wakeup(dev)
+        if (dev->power.wakeup_path
             && genpd->active_wakeup && genpd->active_wakeup(dev))
                 return 0;
 
@@ -1034,7 +1082,8 @@ static void pm_genpd_complete(struct device *dev)
  */
 int pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev)
 {
-        struct dev_list_entry *dle;
+        struct generic_pm_domain_data *gpd_data;
+        struct pm_domain_data *pdd;
         int ret = 0;
 
         dev_dbg(dev, "%s()\n", __func__);
@@ -1054,26 +1103,26 @@ int pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev)
                 goto out;
         }
 
-        list_for_each_entry(dle, &genpd->dev_list, node)
-                if (dle->dev == dev) {
+        list_for_each_entry(pdd, &genpd->dev_list, list_node)
+                if (pdd->dev == dev) {
                         ret = -EINVAL;
                         goto out;
                 }
 
-        dle = kzalloc(sizeof(*dle), GFP_KERNEL);
-        if (!dle) {
+        gpd_data = kzalloc(sizeof(*gpd_data), GFP_KERNEL);
+        if (!gpd_data) {
                 ret = -ENOMEM;
                 goto out;
         }
 
-        dle->dev = dev;
-        dle->need_restore = false;
-        list_add_tail(&dle->node, &genpd->dev_list);
         genpd->device_count++;
 
-        spin_lock_irq(&dev->power.lock);
         dev->pm_domain = &genpd->domain;
-        spin_unlock_irq(&dev->power.lock);
+        dev_pm_get_subsys_data(dev);
+        dev->power.subsys_data->domain_data = &gpd_data->base;
+        gpd_data->base.dev = dev;
+        gpd_data->need_restore = false;
+        list_add_tail(&gpd_data->base.list_node, &genpd->dev_list);
 
  out:
         genpd_release_lock(genpd);
@@ -1089,7 +1138,7 @@ int pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev)
 int pm_genpd_remove_device(struct generic_pm_domain *genpd,
                            struct device *dev)
 {
-        struct dev_list_entry *dle;
+        struct pm_domain_data *pdd;
         int ret = -EINVAL;
 
         dev_dbg(dev, "%s()\n", __func__);
@@ -1104,17 +1153,17 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd,
                 goto out;
         }
 
-        list_for_each_entry(dle, &genpd->dev_list, node) {
-                if (dle->dev != dev)
+        list_for_each_entry(pdd, &genpd->dev_list, list_node) {
+                if (pdd->dev != dev)
                         continue;
 
-                spin_lock_irq(&dev->power.lock);
+                list_del_init(&pdd->list_node);
+                pdd->dev = NULL;
+                dev_pm_put_subsys_data(dev);
                 dev->pm_domain = NULL;
-                spin_unlock_irq(&dev->power.lock);
+                kfree(to_gpd_data(pdd));
 
                 genpd->device_count--;
-                list_del(&dle->node);
-                kfree(dle);
 
                 ret = 0;
                 break;
@@ -1129,48 +1178,55 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 /**
  * pm_genpd_add_subdomain - Add a subdomain to an I/O PM domain.
  * @genpd: Master PM domain to add the subdomain to.
- * @new_subdomain: Subdomain to be added.
+ * @subdomain: Subdomain to be added.
  */
 int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
-                           struct generic_pm_domain *new_subdomain)
+                           struct generic_pm_domain *subdomain)
 {
-        struct generic_pm_domain *subdomain;
+        struct gpd_link *link;
         int ret = 0;
 
-        if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(new_subdomain))
+        if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(subdomain))
                 return -EINVAL;
 
  start:
         genpd_acquire_lock(genpd);
-        mutex_lock_nested(&new_subdomain->lock, SINGLE_DEPTH_NESTING);
+        mutex_lock_nested(&subdomain->lock, SINGLE_DEPTH_NESTING);
 
-        if (new_subdomain->status != GPD_STATE_POWER_OFF
-            && new_subdomain->status != GPD_STATE_ACTIVE) {
-                mutex_unlock(&new_subdomain->lock);
+        if (subdomain->status != GPD_STATE_POWER_OFF
+            && subdomain->status != GPD_STATE_ACTIVE) {
+                mutex_unlock(&subdomain->lock);
                 genpd_release_lock(genpd);
                 goto start;
         }
 
         if (genpd->status == GPD_STATE_POWER_OFF
-            &&  new_subdomain->status != GPD_STATE_POWER_OFF) {
+            &&  subdomain->status != GPD_STATE_POWER_OFF) {
                 ret = -EINVAL;
                 goto out;
         }
 
-        list_for_each_entry(subdomain, &genpd->sd_list, sd_node) {
-                if (subdomain == new_subdomain) {
+        list_for_each_entry(link, &genpd->slave_links, slave_node) {
+                if (link->slave == subdomain && link->master == genpd) {
                         ret = -EINVAL;
                         goto out;
                 }
         }
 
-        list_add_tail(&new_subdomain->sd_node, &genpd->sd_list);
-        new_subdomain->parent = genpd;
+        link = kzalloc(sizeof(*link), GFP_KERNEL);
+        if (!link) {
+                ret = -ENOMEM;
+                goto out;
+        }
+        link->master = genpd;
+        list_add_tail(&link->master_node, &genpd->master_links);
+        link->slave = subdomain;
+        list_add_tail(&link->slave_node, &subdomain->slave_links);
         if (subdomain->status != GPD_STATE_POWER_OFF)
-                genpd->sd_count++;
+                genpd_sd_counter_inc(genpd);
 
  out:
-        mutex_unlock(&new_subdomain->lock);
+        mutex_unlock(&subdomain->lock);
         genpd_release_lock(genpd);
 
         return ret;
@@ -1179,22 +1235,22 @@ int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
 /**
  * pm_genpd_remove_subdomain - Remove a subdomain from an I/O PM domain.
  * @genpd: Master PM domain to remove the subdomain from.
- * @target: Subdomain to be removed.
+ * @subdomain: Subdomain to be removed.
  */
 int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
-                              struct generic_pm_domain *target)
+                              struct generic_pm_domain *subdomain)
 {
-        struct generic_pm_domain *subdomain;
+        struct gpd_link *link;
         int ret = -EINVAL;
 
-        if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(target))
+        if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(subdomain))
                 return -EINVAL;
 
  start:
         genpd_acquire_lock(genpd);
 
-        list_for_each_entry(subdomain, &genpd->sd_list, sd_node) {
-                if (subdomain != target)
+        list_for_each_entry(link, &genpd->master_links, master_node) {
+                if (link->slave != subdomain)
                         continue;
 
                 mutex_lock_nested(&subdomain->lock, SINGLE_DEPTH_NESTING);
@@ -1206,8 +1262,9 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
                         goto start;
                 }
 
-                list_del(&subdomain->sd_node);
-                subdomain->parent = NULL;
+                list_del(&link->master_node);
+                list_del(&link->slave_node);
+                kfree(link);
                 if (subdomain->status != GPD_STATE_POWER_OFF)
                         genpd_sd_counter_dec(genpd);
 
@@ -1234,15 +1291,14 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
         if (IS_ERR_OR_NULL(genpd))
                 return;
 
-        INIT_LIST_HEAD(&genpd->sd_node);
-        genpd->parent = NULL;
+        INIT_LIST_HEAD(&genpd->master_links);
+        INIT_LIST_HEAD(&genpd->slave_links);
         INIT_LIST_HEAD(&genpd->dev_list);
-        INIT_LIST_HEAD(&genpd->sd_list);
         mutex_init(&genpd->lock);
         genpd->gov = gov;
         INIT_WORK(&genpd->power_off_work, genpd_power_off_work_fn);
         genpd->in_progress = 0;
-        genpd->sd_count = 0;
+        atomic_set(&genpd->sd_count, 0);
         genpd->status = is_off ? GPD_STATE_POWER_OFF : GPD_STATE_ACTIVE;
         init_waitqueue_head(&genpd->status_wait_queue);
         genpd->poweroff_task = NULL;
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index a85459126bc..59f8ab23548 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -46,6 +46,7 @@ LIST_HEAD(dpm_prepared_list);
 LIST_HEAD(dpm_suspended_list);
 LIST_HEAD(dpm_noirq_list);
 
+struct suspend_stats suspend_stats;
 static DEFINE_MUTEX(dpm_list_mtx);
 static pm_message_t pm_transition;
 
@@ -65,6 +66,7 @@ void device_pm_init(struct device *dev)
         spin_lock_init(&dev->power.lock);
         pm_runtime_init(dev);
         INIT_LIST_HEAD(&dev->power.entry);
+        dev->power.power_state = PMSG_INVALID;
 }
 
 /**
@@ -96,6 +98,7 @@ void device_pm_add(struct device *dev)
                 dev_warn(dev, "parent %s should not be sleeping\n",
                         dev_name(dev->parent));
         list_add_tail(&dev->power.entry, &dpm_list);
+        dev_pm_qos_constraints_init(dev);
         mutex_unlock(&dpm_list_mtx);
 }
 
@@ -109,6 +112,7 @@ void device_pm_remove(struct device *dev)
                  dev->bus ? dev->bus->name : "No Bus", dev_name(dev));
         complete_all(&dev->power.completion);
         mutex_lock(&dpm_list_mtx);
+        dev_pm_qos_constraints_destroy(dev);
         list_del_init(&dev->power.entry);
         mutex_unlock(&dpm_list_mtx);
         device_wakeup_disable(dev);
@@ -464,8 +468,12 @@ void dpm_resume_noirq(pm_message_t state)
                 mutex_unlock(&dpm_list_mtx);
 
                 error = device_resume_noirq(dev, state);
-                if (error)
+                if (error) {
+                        suspend_stats.failed_resume_noirq++;
+                        dpm_save_failed_step(SUSPEND_RESUME_NOIRQ);
+                        dpm_save_failed_dev(dev_name(dev));
                         pm_dev_err(dev, state, " early", error);
+                }
 
                 mutex_lock(&dpm_list_mtx);
                 put_device(dev);
@@ -626,8 +634,12 @@ void dpm_resume(pm_message_t state)
                         mutex_unlock(&dpm_list_mtx);
 
                         error = device_resume(dev, state, false);
-                        if (error)
+                        if (error) {
+                                suspend_stats.failed_resume++;
+                                dpm_save_failed_step(SUSPEND_RESUME);
+                                dpm_save_failed_dev(dev_name(dev));
                                 pm_dev_err(dev, state, "", error);
+                        }
 
                         mutex_lock(&dpm_list_mtx);
                 }
@@ -802,6 +814,9 @@ int dpm_suspend_noirq(pm_message_t state)
                 mutex_lock(&dpm_list_mtx);
                 if (error) {
                         pm_dev_err(dev, state, " late", error);
+                        suspend_stats.failed_suspend_noirq++;
+                        dpm_save_failed_step(SUSPEND_SUSPEND_NOIRQ);
+                        dpm_save_failed_dev(dev_name(dev));
                         put_device(dev);
                         break;
                 }
@@ -902,7 +917,11 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
         }
 
  End:
-        dev->power.is_suspended = !error;
+        if (!error) {
+                dev->power.is_suspended = true;
+                if (dev->power.wakeup_path && dev->parent)
+                        dev->parent->power.wakeup_path = true;
+        }
 
         device_unlock(dev);
         complete_all(&dev->power.completion);
@@ -923,8 +942,10 @@ static void async_suspend(void *data, async_cookie_t cookie)
         int error;
 
         error = __device_suspend(dev, pm_transition, true);
-        if (error)
+        if (error) {
+                dpm_save_failed_dev(dev_name(dev));
                 pm_dev_err(dev, pm_transition, " async", error);
+        }
 
         put_device(dev);
 }
@@ -967,6 +988,7 @@ int dpm_suspend(pm_message_t state)
                 mutex_lock(&dpm_list_mtx);
                 if (error) {
                         pm_dev_err(dev, state, "", error);
+                        dpm_save_failed_dev(dev_name(dev));
                         put_device(dev);
                         break;
                 }
@@ -980,7 +1002,10 @@ int dpm_suspend(pm_message_t state)
         async_synchronize_full();
         if (!error)
                 error = async_error;
-        if (!error)
+        if (error) {
+                suspend_stats.failed_suspend++;
+                dpm_save_failed_step(SUSPEND_SUSPEND);
+        } else
                 dpm_show_time(starttime, state, NULL);
         return error;
 }
@@ -999,6 +1024,8 @@ static int device_prepare(struct device *dev, pm_message_t state)
 
         device_lock(dev);
 
+        dev->power.wakeup_path = device_may_wakeup(dev);
+
         if (dev->pm_domain) {
                 pm_dev_dbg(dev, state, "preparing power domain ");
                 if (dev->pm_domain->ops.prepare)
@@ -1088,7 +1115,10 @@ int dpm_suspend_start(pm_message_t state)
         int error;
 
         error = dpm_prepare(state);
-        if (!error)
+        if (error) {
+                suspend_stats.failed_prepare++;
+                dpm_save_failed_step(SUSPEND_PREPARE);
+        } else
                 error = dpm_suspend(state);
         return error;
 }
diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c
index b23de185cb0..434a6c01167 100644
--- a/drivers/base/power/opp.c
+++ b/drivers/base/power/opp.c
@@ -73,6 +73,7 @@ struct opp {
  *              RCU usage: nodes are not modified in the list of device_opp,
  *              however addition is possible and is secured by dev_opp_list_lock
  * @dev:        device pointer
+ * @head:       notifier head to notify the OPP availability changes.
  * @opp_list:   list of opps
  *
  * This is an internal data structure maintaining the link to opps attached to
@@ -83,6 +84,7 @@ struct device_opp {
         struct list_head node;
 
         struct device *dev;
+        struct srcu_notifier_head head;
         struct list_head opp_list;
 };
 
@@ -404,6 +406,7 @@ int opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
                 }
 
                 dev_opp->dev = dev;
+                srcu_init_notifier_head(&dev_opp->head);
                 INIT_LIST_HEAD(&dev_opp->opp_list);
 
                 /* Secure the device list modification */
@@ -428,6 +431,11 @@ int opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
         list_add_rcu(&new_opp->node, head);
         mutex_unlock(&dev_opp_list_lock);
 
+        /*
+         * Notify the changes in the availability of the operable
+         * frequency/voltage list.
+         */
+        srcu_notifier_call_chain(&dev_opp->head, OPP_EVENT_ADD, new_opp);
         return 0;
 }
 
@@ -504,6 +512,14 @@ static int opp_set_availability(struct device *dev, unsigned long freq,
         mutex_unlock(&dev_opp_list_lock);
         synchronize_rcu();
 
+        /* Notify the change of the OPP availability */
+        if (availability_req)
+                srcu_notifier_call_chain(&dev_opp->head, OPP_EVENT_ENABLE,
+                                         new_opp);
+        else
+                srcu_notifier_call_chain(&dev_opp->head, OPP_EVENT_DISABLE,
+                                         new_opp);
+
         /* clean up old opp */
         new_opp = opp;
         goto out;
@@ -643,3 +659,17 @@ void opp_free_cpufreq_table(struct device *dev,
         *table = NULL;
 }
 #endif          /* CONFIG_CPU_FREQ */
+
+/**
+ * opp_get_notifier() - find notifier_head of the device with opp
+ * @dev:        device pointer used to lookup device OPPs.
+ */
+struct srcu_notifier_head *opp_get_notifier(struct device *dev)
+{
+        struct device_opp *dev_opp = find_device_opp(dev);
+
+        if (IS_ERR(dev_opp))
+                return ERR_PTR(PTR_ERR(dev_opp)); /* matching type */
+
+        return &dev_opp->head;
+}
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index f2a25f18fde..9bf62323aaf 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -1,3 +1,5 @@
+#include <linux/pm_qos.h>
+
 #ifdef CONFIG_PM_RUNTIME
 
 extern void pm_runtime_init(struct device *dev);
@@ -35,15 +37,21 @@ extern void device_pm_move_last(struct device *);
 static inline void device_pm_init(struct device *dev)
 {
         spin_lock_init(&dev->power.lock);
+        dev->power.power_state = PMSG_INVALID;
         pm_runtime_init(dev);
 }
 
+static inline void device_pm_add(struct device *dev)
+{
+        dev_pm_qos_constraints_init(dev);
+}
+
 static inline void device_pm_remove(struct device *dev)
 {
+        dev_pm_qos_constraints_destroy(dev);
         pm_runtime_remove(dev);
 }
 
-static inline void device_pm_add(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,
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
new file mode 100644
index 00000000000..91e06141738
--- /dev/null
+++ b/drivers/base/power/qos.c
@@ -0,0 +1,419 @@
+/*
+ * Devices PM QoS constraints management
+ *
+ * Copyright (C) 2011 Texas Instruments, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *
+ * This module exposes the interface to kernel space for specifying
+ * per-device PM QoS dependencies. It provides infrastructure for registration
+ * of:
+ *
+ * Dependents on a QoS value : register requests
+ * Watchers of QoS value : get notified when target QoS value changes
+ *
+ * This QoS design is best effort based. Dependents register their QoS needs.
+ * Watchers register to keep track of the current QoS needs of the system.
+ * Watchers can register different types of notification callbacks:
+ *  . a per-device notification callback using the dev_pm_qos_*_notifier API.
+ *    The notification chain data is stored in the per-device constraint
+ *    data struct.
+ *  . a system-wide notification callback using the dev_pm_qos_*_global_notifier
+ *    API. The notification chain data is stored in a static variable.
+ *
+ * Note about the per-device constraint data struct allocation:
+ * . The per-device constraints data struct ptr is tored into the device
+ *    dev_pm_info.
+ * . To minimize the data usage by the per-device constraints, the data struct
+ *   is only allocated at the first call to dev_pm_qos_add_request.
+ * . The data is later free'd when the device is removed from the system.
+ *  . A global mutex protects the constraints users from the data being
+ *     allocated and free'd.
+ */
+
+#include <linux/pm_qos.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/device.h>
+#include <linux/mutex.h>
+
+
+static DEFINE_MUTEX(dev_pm_qos_mtx);
+
+static BLOCKING_NOTIFIER_HEAD(dev_pm_notifiers);
+
+/**
+ * dev_pm_qos_read_value - Get PM QoS constraint for a given device.
+ * @dev: Device to get the PM QoS constraint value for.
+ */
+s32 dev_pm_qos_read_value(struct device *dev)
+{
+        struct pm_qos_constraints *c;
+        unsigned long flags;
+        s32 ret = 0;
+
+        spin_lock_irqsave(&dev->power.lock, flags);
+
+        c = dev->power.constraints;
+        if (c)
+                ret = pm_qos_read_value(c);
+
+        spin_unlock_irqrestore(&dev->power.lock, flags);
+
+        return ret;
+}
+
+/*
+ * apply_constraint
+ * @req: constraint request to apply
+ * @action: action to perform add/update/remove, of type enum pm_qos_req_action
+ * @value: defines the qos request
+ *
+ * Internal function to update the constraints list using the PM QoS core
+ * code and if needed call the per-device and the global notification
+ * callbacks
+ */
+static int apply_constraint(struct dev_pm_qos_request *req,
+                            enum pm_qos_req_action action, int value)
+{
+        int ret, curr_value;
+
+        ret = pm_qos_update_target(req->dev->power.constraints,
+                                   &req->node, action, value);
+
+        if (ret) {
+                /* Call the global callbacks if needed */
+                curr_value = pm_qos_read_value(req->dev->power.constraints);
+                blocking_notifier_call_chain(&dev_pm_notifiers,
+                                             (unsigned long)curr_value,
+                                             req);
+        }
+
+        return ret;
+}
+
+/*
+ * dev_pm_qos_constraints_allocate
+ * @dev: device to allocate data for
+ *
+ * Called at the first call to add_request, for constraint data allocation
+ * Must be called with the dev_pm_qos_mtx mutex held
+ */
+static int dev_pm_qos_constraints_allocate(struct device *dev)
+{
+        struct pm_qos_constraints *c;
+        struct blocking_notifier_head *n;
+
+        c = kzalloc(sizeof(*c), GFP_KERNEL);
+        if (!c)
+                return -ENOMEM;
+
+        n = kzalloc(sizeof(*n), GFP_KERNEL);
+        if (!n) {
+                kfree(c);
+                return -ENOMEM;
+        }
+        BLOCKING_INIT_NOTIFIER_HEAD(n);
+
+        plist_head_init(&c->list);
+        c->target_value = PM_QOS_DEV_LAT_DEFAULT_VALUE;
+        c->default_value = PM_QOS_DEV_LAT_DEFAULT_VALUE;
+        c->type = PM_QOS_MIN;
+        c->notifiers = n;
+
+        spin_lock_irq(&dev->power.lock);
+        dev->power.constraints = c;
+        spin_unlock_irq(&dev->power.lock);
+
+        return 0;
+}
+
+/**
+ * dev_pm_qos_constraints_init - Initalize device's PM QoS constraints pointer.
+ * @dev: target device
+ *
+ * Called from the device PM subsystem during device insertion under
+ * device_pm_lock().
+ */
+void dev_pm_qos_constraints_init(struct device *dev)
+{
+        mutex_lock(&dev_pm_qos_mtx);
+        dev->power.constraints = NULL;
+        dev->power.power_state = PMSG_ON;
+        mutex_unlock(&dev_pm_qos_mtx);
+}
+
+/**
+ * dev_pm_qos_constraints_destroy
+ * @dev: target device
+ *
+ * Called from the device PM subsystem on device removal under device_pm_lock().
+ */
+void dev_pm_qos_constraints_destroy(struct device *dev)
+{
+        struct dev_pm_qos_request *req, *tmp;
+        struct pm_qos_constraints *c;
+
+        mutex_lock(&dev_pm_qos_mtx);
+
+        dev->power.power_state = PMSG_INVALID;
+        c = dev->power.constraints;
+        if (!c)
+                goto out;
+
+        /* Flush the constraints list for the device */
+        plist_for_each_entry_safe(req, tmp, &c->list, node) {
+                /*
+                 * Update constraints list and call the notification
+                 * callbacks if needed
+                 */
+                apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
+                memset(req, 0, sizeof(*req));
+        }
+
+        spin_lock_irq(&dev->power.lock);
+        dev->power.constraints = NULL;
+        spin_unlock_irq(&dev->power.lock);
+
+        kfree(c->notifiers);
+        kfree(c);
+
+ out:
+        mutex_unlock(&dev_pm_qos_mtx);
+}
+
+/**
+ * dev_pm_qos_add_request - inserts new qos request into the list
+ * @dev: target device for the constraint
+ * @req: pointer to a preallocated handle
+ * @value: defines the qos request
+ *
+ * This function inserts a new entry in the device constraints list of
+ * requested qos performance characteristics. It recomputes the aggregate
+ * QoS expectations of parameters and initializes the dev_pm_qos_request
+ * handle.  Caller needs to save this handle for later use in updates and
+ * removal.
+ *
+ * Returns 1 if the aggregated constraint value has changed,
+ * 0 if the aggregated constraint value has not changed,
+ * -EINVAL in case of wrong parameters, -ENOMEM if there's not enough memory
+ * to allocate for data structures, -ENODEV if the device has just been removed
+ * from the system.
+ */
+int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req,
+                           s32 value)
+{
+        int ret = 0;
+
+        if (!dev || !req) /*guard against callers passing in null */
+                return -EINVAL;
+
+        if (dev_pm_qos_request_active(req)) {
+                WARN(1, KERN_ERR "dev_pm_qos_add_request() called for already "
+                        "added request\n");
+                return -EINVAL;
+        }
+
+        req->dev = dev;
+
+        mutex_lock(&dev_pm_qos_mtx);
+
+        if (!dev->power.constraints) {
+                if (dev->power.power_state.event == PM_EVENT_INVALID) {
+                        /* The device has been removed from the system. */
+                        req->dev = NULL;
+                        ret = -ENODEV;
+                        goto out;
+                } else {
+                        /*
+                         * Allocate the constraints data on the first call to
+                         * add_request, i.e. only if the data is not already
+                         * allocated and if the device has not been removed.
+                         */
+                        ret = dev_pm_qos_constraints_allocate(dev);
+                }
+        }
+
+        if (!ret)
+                ret = apply_constraint(req, PM_QOS_ADD_REQ, value);
+
+ out:
+        mutex_unlock(&dev_pm_qos_mtx);
+
+        return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_add_request);
+
+/**
+ * dev_pm_qos_update_request - modifies an existing qos request
+ * @req : handle to list element holding a dev_pm_qos request to use
+ * @new_value: defines the qos request
+ *
+ * Updates an existing dev PM qos request along with updating the
+ * target value.
+ *
+ * Attempts are made to make this code callable on hot code paths.
+ *
+ * Returns 1 if the aggregated constraint value has changed,
+ * 0 if the aggregated constraint value has not changed,
+ * -EINVAL in case of wrong parameters, -ENODEV if the device has been
+ * removed from the system
+ */
+int dev_pm_qos_update_request(struct dev_pm_qos_request *req,
+                              s32 new_value)
+{
+        int ret = 0;
+
+        if (!req) /*guard against callers passing in null */
+                return -EINVAL;
+
+        if (!dev_pm_qos_request_active(req)) {
+                WARN(1, KERN_ERR "dev_pm_qos_update_request() called for "
+                        "unknown object\n");
+                return -EINVAL;
+        }
+
+        mutex_lock(&dev_pm_qos_mtx);
+
+        if (req->dev->power.constraints) {
+                if (new_value != req->node.prio)
+                        ret = apply_constraint(req, PM_QOS_UPDATE_REQ,
+                                               new_value);
+        } else {
+                /* Return if the device has been removed */
+                ret = -ENODEV;
+        }
+
+        mutex_unlock(&dev_pm_qos_mtx);
+        return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_update_request);
+
+/**
+ * dev_pm_qos_remove_request - modifies an existing qos request
+ * @req: handle to request list element
+ *
+ * Will remove pm qos request from the list of constraints and
+ * recompute the current target value. Call this on slow code paths.
+ *
+ * Returns 1 if the aggregated constraint value has changed,
+ * 0 if the aggregated constraint value has not changed,
+ * -EINVAL in case of wrong parameters, -ENODEV if the device has been
+ * removed from the system
+ */
+int dev_pm_qos_remove_request(struct dev_pm_qos_request *req)
+{
+        int ret = 0;
+
+        if (!req) /*guard against callers passing in null */
+                return -EINVAL;
+
+        if (!dev_pm_qos_request_active(req)) {
+                WARN(1, KERN_ERR "dev_pm_qos_remove_request() called for "
+                        "unknown object\n");
+                return -EINVAL;
+        }
+
+        mutex_lock(&dev_pm_qos_mtx);
+
+        if (req->dev->power.constraints) {
+                ret = apply_constraint(req, PM_QOS_REMOVE_REQ,
+                                       PM_QOS_DEFAULT_VALUE);
+                memset(req, 0, sizeof(*req));
+        } else {
+                /* Return if the device has been removed */
+                ret = -ENODEV;
+        }
+
+        mutex_unlock(&dev_pm_qos_mtx);
+        return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_remove_request);
+
+/**
+ * dev_pm_qos_add_notifier - sets notification entry for changes to target value
+ * of per-device PM QoS constraints
+ *
+ * @dev: target device for the constraint
+ * @notifier: notifier block managed by caller.
+ *
+ * Will register the notifier into a notification chain that gets called
+ * upon changes to the target value for the device.
+ */
+int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier)
+{
+        int retval = 0;
+
+        mutex_lock(&dev_pm_qos_mtx);
+
+        /* Silently return if the constraints object is not present. */
+        if (dev->power.constraints)
+                retval = blocking_notifier_chain_register(
+                                dev->power.constraints->notifiers,
+                                notifier);
+
+        mutex_unlock(&dev_pm_qos_mtx);
+        return retval;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_add_notifier);
+
+/**
+ * dev_pm_qos_remove_notifier - deletes notification for changes to target value
+ * of per-device PM QoS constraints
+ *
+ * @dev: target device for the constraint
+ * @notifier: notifier block to be removed.
+ *
+ * Will remove the notifier from the notification chain that gets called
+ * upon changes to the target value.
+ */
+int dev_pm_qos_remove_notifier(struct device *dev,
+                               struct notifier_block *notifier)
+{
+        int retval = 0;
+
+        mutex_lock(&dev_pm_qos_mtx);
+
+        /* Silently return if the constraints object is not present. */
+        if (dev->power.constraints)
+                retval = blocking_notifier_chain_unregister(
+                                dev->power.constraints->notifiers,
+                                notifier);
+
+        mutex_unlock(&dev_pm_qos_mtx);
+        return retval;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_remove_notifier);
+
+/**
+ * dev_pm_qos_add_global_notifier - sets notification entry for changes to
+ * target value of the PM QoS constraints for any device
+ *
+ * @notifier: notifier block managed by caller.
+ *
+ * Will register the notifier into a notification chain that gets called
+ * upon changes to the target value for any device.
+ */
+int dev_pm_qos_add_global_notifier(struct notifier_block *notifier)
+{
+        return blocking_notifier_chain_register(&dev_pm_notifiers, notifier);
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_add_global_notifier);
+
+/**
+ * dev_pm_qos_remove_global_notifier - deletes notification for changes to
+ * target value of PM QoS constraints for any device
+ *
+ * @notifier: notifier block to be removed.
+ *
+ * Will remove the notifier from the notification chain that gets called
+ * upon changes to the target value for any device.
+ */
+int dev_pm_qos_remove_global_notifier(struct notifier_block *notifier)
+{
+        return blocking_notifier_chain_unregister(&dev_pm_notifiers, notifier);
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_remove_global_notifier);
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index acb3f83b807..6bb3aafa85e 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -9,6 +9,7 @@
 
 #include <linux/sched.h>
 #include <linux/pm_runtime.h>
+#include <trace/events/rpm.h>
 #include "power.h"
 
 static int rpm_resume(struct device *dev, int rpmflags);
@@ -155,6 +156,31 @@ static int rpm_check_suspend_allowed(struct device *dev)
 }
 
 /**
+ * __rpm_callback - Run a given runtime PM callback for a given device.
+ * @cb: Runtime PM callback to run.
+ * @dev: Device to run the callback for.
+ */
+static int __rpm_callback(int (*cb)(struct device *), struct device *dev)
+        __releases(&dev->power.lock) __acquires(&dev->power.lock)
+{
+        int retval;
+
+        if (dev->power.irq_safe)
+                spin_unlock(&dev->power.lock);
+        else
+                spin_unlock_irq(&dev->power.lock);
+
+        retval = cb(dev);
+
+        if (dev->power.irq_safe)
+                spin_lock(&dev->power.lock);
+        else
+                spin_lock_irq(&dev->power.lock);
+
+        return retval;
+}
+
+/**
  * rpm_idle - Notify device bus type if the device can be suspended.
  * @dev: Device to notify the bus type about.
  * @rpmflags: Flag bits.
@@ -171,6 +197,7 @@ static int rpm_idle(struct device *dev, int rpmflags)
         int (*callback)(struct device *);
         int retval;
 
+        trace_rpm_idle(dev, rpmflags);
         retval = rpm_check_suspend_allowed(dev);
         if (retval < 0)
                 ;       /* Conditions are wrong. */
@@ -225,24 +252,14 @@ static int rpm_idle(struct device *dev, int rpmflags)
         else
                 callback = NULL;
 
-        if (callback) {
-                if (dev->power.irq_safe)
-                        spin_unlock(&dev->power.lock);
-                else
-                        spin_unlock_irq(&dev->power.lock);
-
-                callback(dev);
-
-                if (dev->power.irq_safe)
-                        spin_lock(&dev->power.lock);
-                else
-                        spin_lock_irq(&dev->power.lock);
-        }
+        if (callback)
+                __rpm_callback(callback, dev);
 
         dev->power.idle_notification = false;
         wake_up_all(&dev->power.wait_queue);
 
  out:
+        trace_rpm_return_int(dev, _THIS_IP_, retval);
         return retval;
 }
 
@@ -252,22 +269,14 @@ static int rpm_idle(struct device *dev, int rpmflags)
  * @dev: Device to run the callback for.
  */
 static int rpm_callback(int (*cb)(struct device *), struct device *dev)
-        __releases(&dev->power.lock) __acquires(&dev->power.lock)
 {
         int retval;
 
         if (!cb)
                 return -ENOSYS;
 
-        if (dev->power.irq_safe) {
-                retval = cb(dev);
-        } else {
-                spin_unlock_irq(&dev->power.lock);
-
-                retval = cb(dev);
+        retval = __rpm_callback(cb, dev);
 
-                spin_lock_irq(&dev->power.lock);
-        }
         dev->power.runtime_error = retval;
         return retval != -EACCES ? retval : -EIO;
 }
@@ -277,14 +286,16 @@ static int rpm_callback(int (*cb)(struct device *), struct device *dev)
  * @dev: Device to suspend.
  * @rpmflags: Flag bits.
  *
- * Check if the device's runtime PM status allows it to be suspended.  If
- * another suspend has been started earlier, either return immediately or wait
- * for it to finish, depending on the RPM_NOWAIT and RPM_ASYNC flags.  Cancel a
- * pending idle notification.  If the RPM_ASYNC flag is set then queue a
- * suspend request; otherwise run the ->runtime_suspend() callback directly.
- * If a deferred resume was requested while the callback was running then carry
- * it out; otherwise send an idle notification for the device (if the suspend
- * failed) or for its parent (if the suspend succeeded).
+ * Check if the device's runtime PM status allows it to be suspended.
+ * Cancel a pending idle notification, autosuspend or suspend. If
+ * another suspend has been started earlier, either return immediately
+ * or wait for it to finish, depending on the RPM_NOWAIT and RPM_ASYNC
+ * flags. If the RPM_ASYNC flag is set then queue a suspend request;
+ * otherwise run the ->runtime_suspend() callback directly. When
+ * ->runtime_suspend succeeded, if a deferred resume was requested while
+ * the callback was running then carry it out, otherwise send an idle
+ * notification for its parent (if the suspend succeeded and both
+ * ignore_children of parent->power and irq_safe of dev->power are not set).
  *
  * This function must be called under dev->power.lock with interrupts disabled.
  */
@@ -295,7 +306,7 @@ static int rpm_suspend(struct device *dev, int rpmflags)
         struct device *parent = NULL;
         int retval;
 
-        dev_dbg(dev, "%s flags 0x%x\n", __func__, rpmflags);
+        trace_rpm_suspend(dev, rpmflags);
 
  repeat:
         retval = rpm_check_suspend_allowed(dev);
@@ -347,6 +358,15 @@ static int rpm_suspend(struct device *dev, int rpmflags)
                         goto out;
                 }
 
+                if (dev->power.irq_safe) {
+                        spin_unlock(&dev->power.lock);
+
+                        cpu_relax();
+
+                        spin_lock(&dev->power.lock);
+                        goto repeat;
+                }
+
                 /* Wait for the other suspend running in parallel with us. */
                 for (;;) {
                         prepare_to_wait(&dev->power.wait_queue, &wait,
@@ -400,15 +420,16 @@ static int rpm_suspend(struct device *dev, int rpmflags)
                         dev->power.runtime_error = 0;
                 else
                         pm_runtime_cancel_pending(dev);
-        } else {
+                wake_up_all(&dev->power.wait_queue);
+                goto out;
+        }
  no_callback:
-                __update_runtime_status(dev, RPM_SUSPENDED);
-                pm_runtime_deactivate_timer(dev);
+        __update_runtime_status(dev, RPM_SUSPENDED);
+        pm_runtime_deactivate_timer(dev);
 
-                if (dev->parent) {
-                        parent = dev->parent;
-                        atomic_add_unless(&parent->power.child_count, -1, 0);
-                }
+        if (dev->parent) {
+                parent = dev->parent;
+                atomic_add_unless(&parent->power.child_count, -1, 0);
         }
         wake_up_all(&dev->power.wait_queue);
 
@@ -430,7 +451,7 @@ static int rpm_suspend(struct device *dev, int rpmflags)
         }
 
  out:
-        dev_dbg(dev, "%s returns %d\n", __func__, retval);
+        trace_rpm_return_int(dev, _THIS_IP_, retval);
 
         return retval;
 }
@@ -459,7 +480,7 @@ static int rpm_resume(struct device *dev, int rpmflags)
         struct device *parent = NULL;
         int retval = 0;
 
-        dev_dbg(dev, "%s flags 0x%x\n", __func__, rpmflags);
+        trace_rpm_resume(dev, rpmflags);
 
  repeat:
         if (dev->power.runtime_error)
@@ -496,6 +517,15 @@ static int rpm_resume(struct device *dev, int rpmflags)
                         goto out;
                 }
 
+                if (dev->power.irq_safe) {
+                        spin_unlock(&dev->power.lock);
+
+                        cpu_relax();
+
+                        spin_lock(&dev->power.lock);
+                        goto repeat;
+                }
+
                 /* Wait for the operation carried out in parallel with us. */
                 for (;;) {
                         prepare_to_wait(&dev->power.wait_queue, &wait,
@@ -615,7 +645,7 @@ static int rpm_resume(struct device *dev, int rpmflags)
                 spin_lock_irq(&dev->power.lock);
         }
 
-        dev_dbg(dev, "%s returns %d\n", __func__, retval);
+        trace_rpm_return_int(dev, _THIS_IP_, retval);
 
         return retval;
 }
@@ -732,13 +762,16 @@ EXPORT_SYMBOL_GPL(pm_schedule_suspend);
  * return immediately if it is larger than zero.  Then carry out an idle
  * notification, either synchronous or asynchronous.
  *
- * This routine may be called in atomic context if the RPM_ASYNC flag is set.
+ * This routine may be called in atomic context if the RPM_ASYNC flag is set,
+ * or if pm_runtime_irq_safe() has been called.
  */
 int __pm_runtime_idle(struct device *dev, int rpmflags)
 {
         unsigned long flags;
         int retval;
 
+        might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
+
         if (rpmflags & RPM_GET_PUT) {
                 if (!atomic_dec_and_test(&dev->power.usage_count))
                         return 0;
@@ -761,13 +794,16 @@ EXPORT_SYMBOL_GPL(__pm_runtime_idle);
  * return immediately if it is larger than zero.  Then carry out a suspend,
  * either synchronous or asynchronous.
  *
- * This routine may be called in atomic context if the RPM_ASYNC flag is set.
+ * This routine may be called in atomic context if the RPM_ASYNC flag is set,
+ * or if pm_runtime_irq_safe() has been called.
  */
 int __pm_runtime_suspend(struct device *dev, int rpmflags)
 {
         unsigned long flags;
         int retval;
 
+        might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
+
         if (rpmflags & RPM_GET_PUT) {
                 if (!atomic_dec_and_test(&dev->power.usage_count))
                         return 0;
@@ -789,13 +825,16 @@ EXPORT_SYMBOL_GPL(__pm_runtime_suspend);
  * If the RPM_GET_PUT flag is set, increment the device's usage count.  Then
  * carry out a resume, either synchronous or asynchronous.
  *
- * This routine may be called in atomic context if the RPM_ASYNC flag is set.
+ * This routine may be called in atomic context if the RPM_ASYNC flag is set,
+ * or if pm_runtime_irq_safe() has been called.
  */
 int __pm_runtime_resume(struct device *dev, int rpmflags)
 {
         unsigned long flags;
         int retval;
 
+        might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
+
         if (rpmflags & RPM_GET_PUT)
                 atomic_inc(&dev->power.usage_count);
 
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index 84f7c7d5a09..14ee07e9cc4 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -276,7 +276,9 @@ EXPORT_SYMBOL_GPL(device_set_wakeup_capable);
  *
  * By default, most devices should leave wakeup disabled.  The exceptions are
  * devices that everyone expects to be wakeup sources: keyboards, power buttons,
- * possibly network interfaces, etc.
+ * possibly network interfaces, etc.  Also, devices that don't generate their
+ * own wakeup requests but merely forward requests from one bus to another
+ * (like PCI bridges) should have wakeup enabled by default.
  */
 int device_init_wakeup(struct device *dev, bool enable)
 {
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 675246a6f7e..f9b726091ad 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -1118,7 +1118,7 @@ static int btusb_suspend(struct usb_interface *intf, pm_message_t message)
                 return 0;
 
         spin_lock_irq(&data->txlock);
-        if (!((message.event & PM_EVENT_AUTO) && data->tx_in_flight)) {
+        if (!(PMSG_IS_AUTO(message) && data->tx_in_flight)) {
                 set_bit(BTUSB_SUSPENDING, &data->flags);
                 spin_unlock_irq(&data->txlock);
         } else {
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index d4c54237288..0df01411009 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -12,7 +12,7 @@
 #include <linux/mutex.h>
 #include <linux/sched.h>
 #include <linux/notifier.h>
-#include <linux/pm_qos_params.h>
+#include <linux/pm_qos.h>
 #include <linux/cpu.h>
 #include <linux/cpuidle.h>
 #include <linux/ktime.h>
diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c
index 12c98900dcf..f62fde21e96 100644
--- a/drivers/cpuidle/governors/ladder.c
+++ b/drivers/cpuidle/governors/ladder.c
@@ -14,7 +14,7 @@
 
 #include <linux/kernel.h>
 #include <linux/cpuidle.h>
-#include <linux/pm_qos_params.h>
+#include <linux/pm_qos.h>
 #include <linux/moduleparam.h>
 #include <linux/jiffies.h>
 
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index c47f3d09c1e..3600f1955e4 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -12,7 +12,7 @@
 
 #include <linux/kernel.h>
 #include <linux/cpuidle.h>
-#include <linux/pm_qos_params.h>
+#include <linux/pm_qos.h>
 #include <linux/time.h>
 #include <linux/ktime.h>
 #include <linux/hrtimer.h>
diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig
new file mode 100644
index 00000000000..643b055ed3c
--- /dev/null
+++ b/drivers/devfreq/Kconfig
@@ -0,0 +1,75 @@
+config ARCH_HAS_DEVFREQ
+        bool
+        depends on ARCH_HAS_OPP
+        help
+          Denotes that the architecture supports DEVFREQ. If the architecture
+          supports multiple OPP entries per device and the frequency of the
+          devices with OPPs may be altered dynamically, the architecture
+          supports DEVFREQ.
+
+menuconfig PM_DEVFREQ
+        bool "Generic Dynamic Voltage and Frequency Scaling (DVFS) support"
+        depends on PM_OPP && ARCH_HAS_DEVFREQ
+        help
+          With OPP support, a device may have a list of frequencies and
+          voltages available. DEVFREQ, a generic DVFS framework can be
+          registered for a device with OPP support in order to let the
+          governor provided to DEVFREQ choose an operating frequency
+          based on the OPP's list and the policy given with DEVFREQ.
+
+          Each device may have its own governor and policy. DEVFREQ can
+          reevaluate the device state periodically and/or based on the
+          OPP list changes (each frequency/voltage pair in OPP may be
+          disabled or enabled).
+
+          Like some CPUs with CPUFREQ, a device may have multiple clocks.
+          However, because the clock frequencies of a single device are
+          determined by the single device's state, an instance of DEVFREQ
+          is attached to a single device and returns a "representative"
+          clock frequency from the OPP of the device, which is also attached
+          to a device by 1-to-1. The device registering DEVFREQ takes the
+          responsiblity to "interpret" the frequency listed in OPP and
+          to set its every clock accordingly with the "target" callback
+          given to DEVFREQ.
+
+if PM_DEVFREQ
+
+comment "DEVFREQ Governors"
+
+config DEVFREQ_GOV_SIMPLE_ONDEMAND
+        bool "Simple Ondemand"
+        help
+          Chooses frequency based on the recent load on the device. Works
+          similar as ONDEMAND governor of CPUFREQ does. A device with
+          Simple-Ondemand should be able to provide busy/total counter
+          values that imply the usage rate. A device may provide tuned
+          values to the governor with data field at devfreq_add_device().
+
+config DEVFREQ_GOV_PERFORMANCE
+        bool "Performance"
+        help
+          Sets the frequency at the maximum available frequency.
+          This governor always returns UINT_MAX as frequency so that
+          the DEVFREQ framework returns the highest frequency available
+          at any time.
+
+config DEVFREQ_GOV_POWERSAVE
+        bool "Powersave"
+        help
+          Sets the frequency at the minimum available frequency.
+          This governor always returns 0 as frequency so that
+          the DEVFREQ framework returns the lowest frequency available
+          at any time.
+
+config DEVFREQ_GOV_USERSPACE
+        bool "Userspace"
+        help
+          Sets the frequency at the user specified one.
+          This governor returns the user configured frequency if there
+          has been an input to /sys/devices/.../power/devfreq_set_freq.
+          Otherwise, the governor does not change the frequnecy
+          given at the initialization.
+
+comment "DEVFREQ Drivers"
+
+endif # PM_DEVFREQ
diff --git a/drivers/devfreq/Makefile b/drivers/devfreq/Makefile
new file mode 100644
index 00000000000..4564a89e970
--- /dev/null
+++ b/drivers/devfreq/Makefile
@@ -0,0 +1,5 @@
+obj-$(CONFIG_PM_DEVFREQ)        += devfreq.o
+obj-$(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND)       += governor_simpleondemand.o
+obj-$(CONFIG_DEVFREQ_GOV_PERFORMANCE)   += governor_performance.o
+obj-$(CONFIG_DEVFREQ_GOV_POWERSAVE)     += governor_powersave.o
+obj-$(CONFIG_DEVFREQ_GOV_USERSPACE)     += governor_userspace.o
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
new file mode 100644
index 00000000000..5d15b812377
--- /dev/null
+++ b/drivers/devfreq/devfreq.c
@@ -0,0 +1,601 @@
+/*
+ * devfreq: Generic Dynamic Voltage and Frequency Scaling (DVFS) Framework
+ *          for Non-CPU Devices.
+ *
+ * Copyright (C) 2011 Samsung Electronics
+ *      MyungJoo Ham <myungjoo.ham@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/opp.h>
+#include <linux/devfreq.h>
+#include <linux/workqueue.h>
+#include <linux/platform_device.h>
+#include <linux/list.h>
+#include <linux/printk.h>
+#include <linux/hrtimer.h>
+#include "governor.h"
+
+struct class *devfreq_class;
+
+/*
+ * devfreq_work periodically monitors every registered device.
+ * The minimum polling interval is one jiffy. The polling interval is
+ * determined by the minimum polling period among all polling devfreq
+ * devices. The resolution of polling interval is one jiffy.
+ */
+static bool polling;
+static struct workqueue_struct *devfreq_wq;
+static struct delayed_work devfreq_work;
+
+/* wait removing if this is to be removed */
+static struct devfreq *wait_remove_device;
+
+/* The list of all device-devfreq */
+static LIST_HEAD(devfreq_list);
+static DEFINE_MUTEX(devfreq_list_lock);
+
+/**
+ * find_device_devfreq() - find devfreq struct using device pointer
+ * @dev:        device pointer used to lookup device devfreq.
+ *
+ * Search the list of device devfreqs and return the matched device's
+ * devfreq info. devfreq_list_lock should be held by the caller.
+ */
+static struct devfreq *find_device_devfreq(struct device *dev)
+{
+        struct devfreq *tmp_devfreq;
+
+        if (unlikely(IS_ERR_OR_NULL(dev))) {
+                pr_err("DEVFREQ: %s: Invalid parameters\n", __func__);
+                return ERR_PTR(-EINVAL);
+        }
+        WARN(!mutex_is_locked(&devfreq_list_lock),
+             "devfreq_list_lock must be locked.");
+
+        list_for_each_entry(tmp_devfreq, &devfreq_list, node) {
+                if (tmp_devfreq->dev.parent == dev)
+                        return tmp_devfreq;
+        }
+
+        return ERR_PTR(-ENODEV);
+}
+
+/**
+ * update_devfreq() - Reevaluate the device and configure frequency.
+ * @devfreq:    the devfreq instance.
+ *
+ * Note: Lock devfreq->lock before calling update_devfreq
+ *       This function is exported for governors.
+ */
+int update_devfreq(struct devfreq *devfreq)
+{
+        unsigned long freq;
+        int err = 0;
+
+        if (!mutex_is_locked(&devfreq->lock)) {
+                WARN(true, "devfreq->lock must be locked by the caller.\n");
+                return -EINVAL;
+        }
+
+        /* Reevaluate the proper frequency */
+        err = devfreq->governor->get_target_freq(devfreq, &freq);
+        if (err)
+                return err;
+
+        err = devfreq->profile->target(devfreq->dev.parent, &freq);
+        if (err)
+                return err;
+
+        devfreq->previous_freq = freq;
+        return err;
+}
+
+/**
+ * devfreq_notifier_call() - Notify that the device frequency requirements
+ *                         has been changed out of devfreq framework.
+ * @nb          the notifier_block (supposed to be devfreq->nb)
+ * @type        not used
+ * @devp        not used
+ *
+ * Called by a notifier that uses devfreq->nb.
+ */
+static int devfreq_notifier_call(struct notifier_block *nb, unsigned long type,
+                                 void *devp)
+{
+        struct devfreq *devfreq = container_of(nb, struct devfreq, nb);
+        int ret;
+
+        mutex_lock(&devfreq->lock);
+        ret = update_devfreq(devfreq);
+        mutex_unlock(&devfreq->lock);
+
+        return ret;
+}
+
+/**
+ * _remove_devfreq() - Remove devfreq from the device.
+ * @devfreq:    the devfreq struct
+ * @skip:       skip calling device_unregister().
+ *
+ * Note that the caller should lock devfreq->lock before calling
+ * this. _remove_devfreq() will unlock it and free devfreq
+ * internally. devfreq_list_lock should be locked by the caller
+ * as well (not relased at return)
+ *
+ * Lock usage:
+ * devfreq->lock: locked before call.
+ *                unlocked at return (and freed)
+ * devfreq_list_lock: locked before call.
+ *                    kept locked at return.
+ *                    if devfreq is centrally polled.
+ *
+ * Freed memory:
+ * devfreq
+ */
+static void _remove_devfreq(struct devfreq *devfreq, bool skip)
+{
+        if (!mutex_is_locked(&devfreq->lock)) {
+                WARN(true, "devfreq->lock must be locked by the caller.\n");
+                return;
+        }
+        if (!devfreq->governor->no_central_polling &&
+            !mutex_is_locked(&devfreq_list_lock)) {
+                WARN(true, "devfreq_list_lock must be locked by the caller.\n");
+                return;
+        }
+
+        if (devfreq->being_removed)
+                return;
+
+        devfreq->being_removed = true;
+
+        if (devfreq->profile->exit)
+                devfreq->profile->exit(devfreq->dev.parent);
+
+        if (devfreq->governor->exit)
+                devfreq->governor->exit(devfreq);
+
+        if (!skip && get_device(&devfreq->dev)) {
+                device_unregister(&devfreq->dev);
+                put_device(&devfreq->dev);
+        }
+
+        if (!devfreq->governor->no_central_polling)
+                list_del(&devfreq->node);
+
+        mutex_unlock(&devfreq->lock);
+        mutex_destroy(&devfreq->lock);
+
+        kfree(devfreq);
+}
+
+/**
+ * devfreq_dev_release() - Callback for struct device to release the device.
+ * @dev:        the devfreq device
+ *
+ * This calls _remove_devfreq() if _remove_devfreq() is not called.
+ * Note that devfreq_dev_release() could be called by _remove_devfreq() as
+ * well as by others unregistering the device.
+ */
+static void devfreq_dev_release(struct device *dev)
+{
+        struct devfreq *devfreq = to_devfreq(dev);
+        bool central_polling = !devfreq->governor->no_central_polling;
+
+        /*
+         * If devfreq_dev_release() was called by device_unregister() of
+         * _remove_devfreq(), we cannot mutex_lock(&devfreq->lock) and
+         * being_removed is already set. This also partially checks the case
+         * where devfreq_dev_release() is called from a thread other than
+         * the one called _remove_devfreq(); however, this case is
+         * dealt completely with another following being_removed check.
+         *
+         * Because being_removed is never being
+         * unset, we do not need to worry about race conditions on
+         * being_removed.
+         */
+        if (devfreq->being_removed)
+                return;
+
+        if (central_polling)
+                mutex_lock(&devfreq_list_lock);
+
+        mutex_lock(&devfreq->lock);
+
+        /*
+         * Check being_removed flag again for the case where
+         * devfreq_dev_release() was called in a thread other than the one
+         * possibly called _remove_devfreq().
+         */
+        if (devfreq->being_removed) {
+                mutex_unlock(&devfreq->lock);
+                goto out;
+        }
+
+        /* devfreq->lock is unlocked and removed in _removed_devfreq() */
+        _remove_devfreq(devfreq, true);
+
+out:
+        if (central_polling)
+                mutex_unlock(&devfreq_list_lock);
+}
+
+/**
+ * devfreq_monitor() - Periodically poll devfreq objects.
+ * @work: the work struct used to run devfreq_monitor periodically.
+ *
+ */
+static void devfreq_monitor(struct work_struct *work)
+{
+        static unsigned long last_polled_at;
+        struct devfreq *devfreq, *tmp;
+        int error;
+        unsigned long jiffies_passed;
+        unsigned long next_jiffies = ULONG_MAX, now = jiffies;
+        struct device *dev;
+
+        /* Initially last_polled_at = 0, polling every device at bootup */
+        jiffies_passed = now - last_polled_at;
+        last_polled_at = now;
+        if (jiffies_passed == 0)
+                jiffies_passed = 1;
+
+        mutex_lock(&devfreq_list_lock);
+        list_for_each_entry_safe(devfreq, tmp, &devfreq_list, node) {
+                mutex_lock(&devfreq->lock);
+                dev = devfreq->dev.parent;
+
+                /* Do not remove tmp for a while */
+                wait_remove_device = tmp;
+
+                if (devfreq->governor->no_central_polling ||
+                    devfreq->next_polling == 0) {
+                        mutex_unlock(&devfreq->lock);
+                        continue;
+                }
+                mutex_unlock(&devfreq_list_lock);
+
+                /*
+                 * Reduce more next_polling if devfreq_wq took an extra
+                 * delay. (i.e., CPU has been idled.)
+                 */
+                if (devfreq->next_polling <= jiffies_passed) {
+                        error = update_devfreq(devfreq);
+
+                        /* Remove a devfreq with an error. */
+                        if (error && error != -EAGAIN) {
+
+                                dev_err(dev, "Due to update_devfreq error(%d), devfreq(%s) is removed from the device\n",
+                                        error, devfreq->governor->name);
+
+                                /*
+                                 * Unlock devfreq before locking the list
+                                 * in order to avoid deadlock with
+                                 * find_device_devfreq or others
+                                 */
+                                mutex_unlock(&devfreq->lock);
+                                mutex_lock(&devfreq_list_lock);
+                                /* Check if devfreq is already removed */
+                                if (IS_ERR(find_device_devfreq(dev)))
+                                        continue;
+                                mutex_lock(&devfreq->lock);
+                                /* This unlocks devfreq->lock and free it */
+                                _remove_devfreq(devfreq, false);
+                                continue;
+                        }
+                        devfreq->next_polling = devfreq->polling_jiffies;
+                } else {
+                        devfreq->next_polling -= jiffies_passed;
+                }
+
+                if (devfreq->next_polling)
+                        next_jiffies = (next_jiffies > devfreq->next_polling) ?
+                                        devfreq->next_polling : next_jiffies;
+
+                mutex_unlock(&devfreq->lock);
+                mutex_lock(&devfreq_list_lock);
+        }
+        wait_remove_device = NULL;
+        mutex_unlock(&devfreq_list_lock);
+
+        if (next_jiffies > 0 && next_jiffies < ULONG_MAX) {
+                polling = true;
+                queue_delayed_work(devfreq_wq, &devfreq_work, next_jiffies);
+        } else {
+                polling = false;
+        }
+}
+
+/**
+ * devfreq_add_device() - Add devfreq feature to the device
+ * @dev:        the device to add devfreq feature.
+ * @profile:    device-specific profile to run devfreq.
+ * @governor:   the policy to choose frequency.
+ * @data:       private data for the governor. The devfreq framework does not
+ *              touch this value.
+ */
+struct devfreq *devfreq_add_device(struct device *dev,
+                                   struct devfreq_dev_profile *profile,
+                                   const struct devfreq_governor *governor,
+                                   void *data)
+{
+        struct devfreq *devfreq;
+        int err = 0;
+
+        if (!dev || !profile || !governor) {
+                dev_err(dev, "%s: Invalid parameters.\n", __func__);
+                return ERR_PTR(-EINVAL);
+        }
+
+
+        if (!governor->no_central_polling) {
+                mutex_lock(&devfreq_list_lock);
+                devfreq = find_device_devfreq(dev);
+                mutex_unlock(&devfreq_list_lock);
+                if (!IS_ERR(devfreq)) {
+                        dev_err(dev, "%s: Unable to create devfreq for the device. It already has one.\n", __func__);
+                        err = -EINVAL;
+                        goto out;
+                }
+        }
+
+        devfreq = kzalloc(sizeof(struct devfreq), GFP_KERNEL);
+        if (!devfreq) {
+                dev_err(dev, "%s: Unable to create devfreq for the device\n",
+                        __func__);
+                err = -ENOMEM;
+                goto out;
+        }
+
+        mutex_init(&devfreq->lock);
+        mutex_lock(&devfreq->lock);
+        devfreq->dev.parent = dev;
+        devfreq->dev.class = devfreq_class;
+        devfreq->dev.release = devfreq_dev_release;
+        devfreq->profile = profile;
+        devfreq->governor = governor;
+        devfreq->previous_freq = profile->initial_freq;
+        devfreq->data = data;
+        devfreq->next_polling = devfreq->polling_jiffies
+                              = msecs_to_jiffies(devfreq->profile->polling_ms);
+        devfreq->nb.notifier_call = devfreq_notifier_call;
+
+        dev_set_name(&devfreq->dev, dev_name(dev));
+        err = device_register(&devfreq->dev);
+        if (err) {
+                put_device(&devfreq->dev);
+                goto err_dev;
+        }
+
+        if (governor->init)
+                err = governor->init(devfreq);
+        if (err)
+                goto err_init;
+
+        mutex_unlock(&devfreq->lock);
+
+        if (governor->no_central_polling)
+                goto out;
+
+        mutex_lock(&devfreq_list_lock);
+
+        list_add(&devfreq->node, &devfreq_list);
+
+        if (devfreq_wq && devfreq->next_polling && !polling) {
+                polling = true;
+                queue_delayed_work(devfreq_wq, &devfreq_work,
+                                   devfreq->next_polling);
+        }
+        mutex_unlock(&devfreq_list_lock);
+        goto out;
+err_init:
+        device_unregister(&devfreq->dev);
+err_dev:
+        mutex_unlock(&devfreq->lock);
+        kfree(devfreq);
+out:
+        if (err)
+                return ERR_PTR(err);
+        else
+                return devfreq;
+}
+
+/**
+ * devfreq_remove_device() - Remove devfreq feature from a device.
+ * @devfreq     the devfreq instance to be removed
+ */
+int devfreq_remove_device(struct devfreq *devfreq)
+{
+        if (!devfreq)
+                return -EINVAL;
+
+        if (!devfreq->governor->no_central_polling) {
+                mutex_lock(&devfreq_list_lock);
+                while (wait_remove_device == devfreq) {
+                        mutex_unlock(&devfreq_list_lock);
+                        schedule();
+                        mutex_lock(&devfreq_list_lock);
+                }
+        }
+
+        mutex_lock(&devfreq->lock);
+        _remove_devfreq(devfreq, false); /* it unlocks devfreq->lock */
+
+        if (!devfreq->governor->no_central_polling)
+                mutex_unlock(&devfreq_list_lock);
+
+        return 0;
+}
+
+static ssize_t show_governor(struct device *dev,
+                             struct device_attribute *attr, char *buf)
+{
+        return sprintf(buf, "%s\n", to_devfreq(dev)->governor->name);
+}
+
+static ssize_t show_freq(struct device *dev,
+                         struct device_attribute *attr, char *buf)
+{
+        return sprintf(buf, "%lu\n", to_devfreq(dev)->previous_freq);
+}
+
+static ssize_t show_polling_interval(struct device *dev,
+                                     struct device_attribute *attr, char *buf)
+{
+        return sprintf(buf, "%d\n", to_devfreq(dev)->profile->polling_ms);
+}
+
+static ssize_t store_polling_interval(struct device *dev,
+                                      struct device_attribute *attr,
+                                      const char *buf, size_t count)
+{
+        struct devfreq *df = to_devfreq(dev);
+        unsigned int value;
+        int ret;
+
+        ret = sscanf(buf, "%u", &value);
+        if (ret != 1)
+                goto out;
+
+        mutex_lock(&df->lock);
+        df->profile->polling_ms = value;
+        df->next_polling = df->polling_jiffies
+                         = msecs_to_jiffies(value);
+        mutex_unlock(&df->lock);
+
+        ret = count;
+
+        if (df->governor->no_central_polling)
+                goto out;
+
+        mutex_lock(&devfreq_list_lock);
+        if (df->next_polling > 0 && !polling) {
+                polling = true;
+                queue_delayed_work(devfreq_wq, &devfreq_work,
+                                   df->next_polling);
+        }
+        mutex_unlock(&devfreq_list_lock);
+out:
+        return ret;
+}
+
+static ssize_t show_central_polling(struct device *dev,
+                                    struct device_attribute *attr, char *buf)
+{
+        return sprintf(buf, "%d\n",
+                       !to_devfreq(dev)->governor->no_central_polling);
+}
+
+static struct device_attribute devfreq_attrs[] = {
+        __ATTR(governor, S_IRUGO, show_governor, NULL),
+        __ATTR(cur_freq, S_IRUGO, show_freq, NULL),
+        __ATTR(central_polling, S_IRUGO, show_central_polling, NULL),
+        __ATTR(polling_interval, S_IRUGO | S_IWUSR, show_polling_interval,
+               store_polling_interval),
+        { },
+};
+
+/**
+ * devfreq_start_polling() - Initialize data structure for devfreq framework and
+ *                         start polling registered devfreq devices.
+ */
+static int __init devfreq_start_polling(void)
+{
+        mutex_lock(&devfreq_list_lock);
+        polling = false;
+        devfreq_wq = create_freezable_workqueue("devfreq_wq");
+        INIT_DELAYED_WORK_DEFERRABLE(&devfreq_work, devfreq_monitor);
+        mutex_unlock(&devfreq_list_lock);
+
+        devfreq_monitor(&devfreq_work.work);
+        return 0;
+}
+late_initcall(devfreq_start_polling);
+
+static int __init devfreq_init(void)
+{
+        devfreq_class = class_create(THIS_MODULE, "devfreq");
+        if (IS_ERR(devfreq_class)) {
+                pr_err("%s: couldn't create class\n", __FILE__);
+                return PTR_ERR(devfreq_class);
+        }
+        devfreq_class->dev_attrs = devfreq_attrs;
+        return 0;
+}
+subsys_initcall(devfreq_init);
+
+static void __exit devfreq_exit(void)
+{
+        class_destroy(devfreq_class);
+}
+module_exit(devfreq_exit);
+
+/*
+ * The followings are helper functions for devfreq user device drivers with
+ * OPP framework.
+ */
+
+/**
+ * devfreq_recommended_opp() - Helper function to get proper OPP for the
+ *                           freq value given to target callback.
+ * @dev         The devfreq user device. (parent of devfreq)
+ * @freq        The frequency given to target function
+ *
+ */
+struct opp *devfreq_recommended_opp(struct device *dev, unsigned long *freq)
+{
+        struct opp *opp = opp_find_freq_ceil(dev, freq);
+
+        if (opp == ERR_PTR(-ENODEV))
+                opp = opp_find_freq_floor(dev, freq);
+        return opp;
+}
+
+/**
+ * devfreq_register_opp_notifier() - Helper function to get devfreq notified
+ *                                 for any changes in the OPP availability
+ *                                 changes
+ * @dev         The devfreq user device. (parent of devfreq)
+ * @devfreq     The devfreq object.
+ */
+int devfreq_register_opp_notifier(struct device *dev, struct devfreq *devfreq)
+{
+        struct srcu_notifier_head *nh = opp_get_notifier(dev);
+
+        if (IS_ERR(nh))
+                return PTR_ERR(nh);
+        return srcu_notifier_chain_register(nh, &devfreq->nb);
+}
+
+/**
+ * devfreq_unregister_opp_notifier() - Helper function to stop getting devfreq
+ *                                   notified for any changes in the OPP
+ *                                   availability changes anymore.
+ * @dev         The devfreq user device. (parent of devfreq)
+ * @devfreq     The devfreq object.
+ *
+ * At exit() callback of devfreq_dev_profile, this must be included if
+ * devfreq_recommended_opp is used.
+ */
+int devfreq_unregister_opp_notifier(struct device *dev, struct devfreq *devfreq)
+{
+        struct srcu_notifier_head *nh = opp_get_notifier(dev);
+
+        if (IS_ERR(nh))
+                return PTR_ERR(nh);
+        return srcu_notifier_chain_unregister(nh, &devfreq->nb);
+}
+
+MODULE_AUTHOR("MyungJoo Ham <myungjoo.ham@samsung.com>");
+MODULE_DESCRIPTION("devfreq class support");
+MODULE_LICENSE("GPL");
diff --git a/drivers/devfreq/governor.h b/drivers/devfreq/governor.h
new file mode 100644
index 00000000000..ea7f13c58de
--- /dev/null
+++ b/drivers/devfreq/governor.h
@@ -0,0 +1,24 @@
+/*
+ * governor.h - internal header for devfreq governors.
+ *
+ * Copyright (C) 2011 Samsung Electronics
+ *      MyungJoo Ham <myungjoo.ham@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This header is for devfreq governors in drivers/devfreq/
+ */
+
+#ifndef _GOVERNOR_H
+#define _GOVERNOR_H
+
+#include <linux/devfreq.h>
+
+#define to_devfreq(DEV) container_of((DEV), struct devfreq, dev)
+
+/* Caution: devfreq->lock must be locked before calling update_devfreq */
+extern int update_devfreq(struct devfreq *devfreq);
+
+#endif /* _GOVERNOR_H */
diff --git a/drivers/devfreq/governor_performance.c b/drivers/devfreq/governor_performance.c
new file mode 100644
index 00000000000..c0596b29176
--- /dev/null
+++ b/drivers/devfreq/governor_performance.c
@@ -0,0 +1,29 @@
+/*
+ *  linux/drivers/devfreq/governor_performance.c
+ *
+ *  Copyright (C) 2011 Samsung Electronics
+ *      MyungJoo Ham <myungjoo.ham@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/devfreq.h>
+
+static int devfreq_performance_func(struct devfreq *df,
+                                    unsigned long *freq)
+{
+        /*
+         * target callback should be able to get floor value as
+         * said in devfreq.h
+         */
+        *freq = UINT_MAX;
+        return 0;
+}
+
+const struct devfreq_governor devfreq_performance = {
+        .name = "performance",
+        .get_target_freq = devfreq_performance_func,
+        .no_central_polling = true,
+};
diff --git a/drivers/devfreq/governor_powersave.c b/drivers/devfreq/governor_powersave.c
new file mode 100644
index 00000000000..2483a85a266
--- /dev/null
+++ b/drivers/devfreq/governor_powersave.c
@@ -0,0 +1,29 @@
+/*
+ *  linux/drivers/devfreq/governor_powersave.c
+ *
+ *  Copyright (C) 2011 Samsung Electronics
+ *      MyungJoo Ham <myungjoo.ham@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/devfreq.h>
+
+static int devfreq_powersave_func(struct devfreq *df,
+                                  unsigned long *freq)
+{
+        /*
+         * target callback should be able to get ceiling value as
+         * said in devfreq.h
+         */
+        *freq = 0;
+        return 0;
+}
+
+const struct devfreq_governor devfreq_powersave = {
+        .name = "powersave",
+        .get_target_freq = devfreq_powersave_func,
+        .no_central_polling = true,
+};
diff --git a/drivers/devfreq/governor_simpleondemand.c b/drivers/devfreq/governor_simpleondemand.c
new file mode 100644
index 00000000000..efad8dcf902
--- /dev/null
+++ b/drivers/devfreq/governor_simpleondemand.c
@@ -0,0 +1,88 @@
+/*
+ *  linux/drivers/devfreq/governor_simpleondemand.c
+ *
+ *  Copyright (C) 2011 Samsung Electronics
+ *      MyungJoo Ham <myungjoo.ham@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/errno.h>
+#include <linux/devfreq.h>
+#include <linux/math64.h>
+
+/* Default constants for DevFreq-Simple-Ondemand (DFSO) */
+#define DFSO_UPTHRESHOLD        (90)
+#define DFSO_DOWNDIFFERENCTIAL  (5)
+static int devfreq_simple_ondemand_func(struct devfreq *df,
+                                        unsigned long *freq)
+{
+        struct devfreq_dev_status stat;
+        int err = df->profile->get_dev_status(df->dev.parent, &stat);
+        unsigned long long a, b;
+        unsigned int dfso_upthreshold = DFSO_UPTHRESHOLD;
+        unsigned int dfso_downdifferential = DFSO_DOWNDIFFERENCTIAL;
+        struct devfreq_simple_ondemand_data *data = df->data;
+
+        if (err)
+                return err;
+
+        if (data) {
+                if (data->upthreshold)
+                        dfso_upthreshold = data->upthreshold;
+                if (data->downdifferential)
+                        dfso_downdifferential = data->downdifferential;
+        }
+        if (dfso_upthreshold > 100 ||
+            dfso_upthreshold < dfso_downdifferential)
+                return -EINVAL;
+
+        /* Assume MAX if it is going to be divided by zero */
+        if (stat.total_time == 0) {
+                *freq = UINT_MAX;
+                return 0;
+        }
+
+        /* Prevent overflow */
+        if (stat.busy_time >= (1 << 24) || stat.total_time >= (1 << 24)) {
+                stat.busy_time >>= 7;
+                stat.total_time >>= 7;
+        }
+
+        /* Set MAX if it's busy enough */
+        if (stat.busy_time * 100 >
+            stat.total_time * dfso_upthreshold) {
+                *freq = UINT_MAX;
+                return 0;
+        }
+
+        /* Set MAX if we do not know the initial frequency */
+        if (stat.current_frequency == 0) {
+                *freq = UINT_MAX;
+                return 0;
+        }
+
+        /* Keep the current frequency */
+        if (stat.busy_time * 100 >
+            stat.total_time * (dfso_upthreshold - dfso_downdifferential)) {
+                *freq = stat.current_frequency;
+                return 0;
+        }
+
+        /* Set the desired frequency based on the load */
+        a = stat.busy_time;
+        a *= stat.current_frequency;
+        b = div_u64(a, stat.total_time);
+        b *= 100;
+        b = div_u64(b, (dfso_upthreshold - dfso_downdifferential / 2));
+        *freq = (unsigned long) b;
+
+        return 0;
+}
+
+const struct devfreq_governor devfreq_simple_ondemand = {
+        .name = "simple_ondemand",
+        .get_target_freq = devfreq_simple_ondemand_func,
+};
diff --git a/drivers/devfreq/governor_userspace.c b/drivers/devfreq/governor_userspace.c
new file mode 100644
index 00000000000..4f8b563da78
--- /dev/null
+++ b/drivers/devfreq/governor_userspace.c
@@ -0,0 +1,116 @@
+/*
+ *  linux/drivers/devfreq/governor_simpleondemand.c
+ *
+ *  Copyright (C) 2011 Samsung Electronics
+ *      MyungJoo Ham <myungjoo.ham@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/slab.h>
+#include <linux/device.h>
+#include <linux/devfreq.h>
+#include <linux/pm.h>
+#include <linux/mutex.h>
+#include "governor.h"
+
+struct userspace_data {
+        unsigned long user_frequency;
+        bool valid;
+};
+
+static int devfreq_userspace_func(struct devfreq *df, unsigned long *freq)
+{
+        struct userspace_data *data = df->data;
+
+        if (!data->valid)
+                *freq = df->previous_freq; /* No user freq specified yet */
+        else
+                *freq = data->user_frequency;
+        return 0;
+}
+
+static ssize_t store_freq(struct device *dev, struct device_attribute *attr,
+                          const char *buf, size_t count)
+{
+        struct devfreq *devfreq = to_devfreq(dev);
+        struct userspace_data *data;
+        unsigned long wanted;
+        int err = 0;
+
+
+        mutex_lock(&devfreq->lock);
+        data = devfreq->data;
+
+        sscanf(buf, "%lu", &wanted);
+        data->user_frequency = wanted;
+        data->valid = true;
+        err = update_devfreq(devfreq);
+        if (err == 0)
+                err = count;
+        mutex_unlock(&devfreq->lock);
+        return err;
+}
+
+static ssize_t show_freq(struct device *dev, struct device_attribute *attr,
+                         char *buf)
+{
+        struct devfreq *devfreq = to_devfreq(dev);
+        struct userspace_data *data;
+        int err = 0;
+
+        mutex_lock(&devfreq->lock);
+        data = devfreq->data;
+
+        if (data->valid)
+                err = sprintf(buf, "%lu\n", data->user_frequency);
+        else
+                err = sprintf(buf, "undefined\n");
+        mutex_unlock(&devfreq->lock);
+        return err;
+}
+
+static DEVICE_ATTR(set_freq, 0644, show_freq, store_freq);
+static struct attribute *dev_entries[] = {
+        &dev_attr_set_freq.attr,
+        NULL,
+};
+static struct attribute_group dev_attr_group = {
+        .name   = "userspace",
+        .attrs  = dev_entries,
+};
+
+static int userspace_init(struct devfreq *devfreq)
+{
+        int err = 0;
+        struct userspace_data *data = kzalloc(sizeof(struct userspace_data),
+                                              GFP_KERNEL);
+
+        if (!data) {
+                err = -ENOMEM;
+                goto out;
+        }
+        data->valid = false;
+        devfreq->data = data;
+
+        err = sysfs_create_group(&devfreq->dev.kobj, &dev_attr_group);
+out:
+        return err;
+}
+
+static void userspace_exit(struct devfreq *devfreq)
+{
+        sysfs_remove_group(&devfreq->dev.kobj, &dev_attr_group);
+        kfree(devfreq->data);
+        devfreq->data = NULL;
+}
+
+const struct devfreq_governor devfreq_userspace = {
+        .name = "userspace",
+        .get_target_freq = devfreq_userspace_func,
+        .init = userspace_init,
+        .exit = userspace_exit,
+        .no_central_polling = true,
+};
diff --git a/drivers/hid/hid-picolcd.c b/drivers/hid/hid-picolcd.c
index 9d8710f8bc7..1782693819f 100644
--- a/drivers/hid/hid-picolcd.c
+++ b/drivers/hid/hid-picolcd.c
@@ -2409,7 +2409,7 @@ static int picolcd_raw_event(struct hid_device *hdev,
 #ifdef CONFIG_PM
 static int picolcd_suspend(struct hid_device *hdev, pm_message_t message)
 {
-        if (message.event & PM_EVENT_AUTO)
+        if (PMSG_IS_AUTO(message))
                 return 0;
 
         picolcd_suspend_backlight(hid_get_drvdata(hdev));
diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index 77e705c2209..b403fcef0b8 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -1332,7 +1332,7 @@ static int hid_suspend(struct usb_interface *intf, pm_message_t message)
         struct usbhid_device *usbhid = hid->driver_data;
         int status;
 
-        if (message.event & PM_EVENT_AUTO) {
+        if (PMSG_IS_AUTO(message)) {
                 spin_lock_irq(&usbhid->lock);   /* Sync with error handler */
                 if (!test_bit(HID_RESET_PENDING, &usbhid->iofl)
                     && !test_bit(HID_CLEAR_HALT, &usbhid->iofl)
@@ -1367,7 +1367,7 @@ static int hid_suspend(struct usb_interface *intf, pm_message_t message)
                         return -EIO;
         }
 
-        if (!ignoreled && (message.event & PM_EVENT_AUTO)) {
+        if (!ignoreled && PMSG_IS_AUTO(message)) {
                 spin_lock_irq(&usbhid->lock);
                 if (test_bit(HID_LED_ON, &usbhid->iofl)) {
                         spin_unlock_irq(&usbhid->lock);
@@ -1380,8 +1380,7 @@ static int hid_suspend(struct usb_interface *intf, pm_message_t message)
         hid_cancel_delayed_stuff(usbhid);
         hid_cease_io(usbhid);
 
-        if ((message.event & PM_EVENT_AUTO) &&
-                        test_bit(HID_KEYS_PRESSED, &usbhid->iofl)) {
+        if (PMSG_IS_AUTO(message) && test_bit(HID_KEYS_PRESSED, &usbhid->iofl)) {
                 /* lost race against keypresses */
                 status = hid_start_in(hid);
                 if (status < 0)
diff --git a/drivers/media/video/via-camera.c b/drivers/media/video/via-camera.c
index bb7f17f2a33..cbf13d09b4a 100644
--- a/drivers/media/video/via-camera.c
+++ b/drivers/media/video/via-camera.c
@@ -21,7 +21,7 @@
 #include <media/videobuf-dma-sg.h>
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
-#include <linux/pm_qos_params.h>
+#include <linux/pm_qos.h>
 #include <linux/via-core.h>
 #include <linux/via-gpio.h>
 #include <linux/via_i2c.h>
@@ -69,7 +69,7 @@ struct via_camera {
         struct mutex lock;
         enum viacam_opstate opstate;
         unsigned long flags;
-        struct pm_qos_request_list qos_request;
+        struct pm_qos_request qos_request;
         /*
          * GPIO info for power/reset management
          */
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 680312710a7..a855db1ad24 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -47,7 +47,7 @@
 #include <linux/if_vlan.h>
 #include <linux/cpu.h>
 #include <linux/smp.h>
-#include <linux/pm_qos_params.h>
+#include <linux/pm_qos.h>
 #include <linux/pm_runtime.h>
 #include <linux/aer.h>
 #include <linux/prefetch.h>
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index cdb958875ba..7d6082160bc 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1476,7 +1476,7 @@ int usbnet_suspend (struct usb_interface *intf, pm_message_t message)
         if (!dev->suspend_count++) {
                 spin_lock_irq(&dev->txq.lock);
                 /* don't autosuspend while transmitting */
-                if (dev->txq.qlen && (message.event & PM_EVENT_AUTO)) {
+                if (dev->txq.qlen && PMSG_IS_AUTO(message)) {
                         spin_unlock_irq(&dev->txq.lock);
                         return -EBUSY;
                 } else {
diff --git a/drivers/net/wimax/i2400m/usb.c b/drivers/net/wimax/i2400m/usb.c
index 298f2b0b631..9a644d052f1 100644
--- a/drivers/net/wimax/i2400m/usb.c
+++ b/drivers/net/wimax/i2400m/usb.c
@@ -599,7 +599,7 @@ void i2400mu_disconnect(struct usb_interface *iface)
  *
  *    As well, the device might refuse going to sleep for whichever
  *    reason. In this case we just fail. For system suspend/hibernate,
- *    we *can't* fail. We check PM_EVENT_AUTO to see if the
+ *    we *can't* fail. We check PMSG_IS_AUTO to see if the
  *    suspend call comes from the USB stack or from the system and act
  *    in consequence.
  *
@@ -615,7 +615,7 @@ int i2400mu_suspend(struct usb_interface *iface, pm_message_t pm_msg)
         struct i2400m *i2400m = &i2400mu->i2400m;
 
 #ifdef CONFIG_PM
-        if (pm_msg.event & PM_EVENT_AUTO)
+        if (PMSG_IS_AUTO(pm_msg))
                 is_autosuspend = 1;
 #endif
 
diff --git a/drivers/net/wireless/ipw2x00/ipw2100.c b/drivers/net/wireless/ipw2x00/ipw2100.c
index ef9ad79d1bf..127e9c63bea 100644
--- a/drivers/net/wireless/ipw2x00/ipw2100.c
+++ b/drivers/net/wireless/ipw2x00/ipw2100.c
@@ -161,7 +161,7 @@ that only one external action is invoked at a time.
 #include <linux/firmware.h>
 #include <linux/acpi.h>
 #include <linux/ctype.h>
-#include <linux/pm_qos_params.h>
+#include <linux/pm_qos.h>
 
 #include <net/lib80211.h>
 
@@ -174,7 +174,7 @@ that only one external action is invoked at a time.
 #define DRV_DESCRIPTION "Intel(R) PRO/Wireless 2100 Network Driver"
 #define DRV_COPYRIGHT   "Copyright(c) 2003-2006 Intel Corporation"
 
-static struct pm_qos_request_list ipw2100_pm_qos_req;
+static struct pm_qos_request ipw2100_pm_qos_req;
 
 /* Debugging stuff */
 #ifdef CONFIG_IPW2100_DEBUG
diff --git a/drivers/tty/Kconfig b/drivers/tty/Kconfig
index f462fa5f937..33175504bb3 100644
--- a/drivers/tty/Kconfig
+++ b/drivers/tty/Kconfig
@@ -60,6 +60,10 @@ config VT_CONSOLE
 
           If unsure, say Y.
 
+config VT_CONSOLE_SLEEP
+        def_bool y
+        depends on VT_CONSOLE && PM_SLEEP
+
 config HW_CONSOLE
         bool
         depends on VT && !UML
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 3ec6699ab72..6960715c506 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1305,7 +1305,7 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message)
         struct acm *acm = usb_get_intfdata(intf);
         int cnt;
 
-        if (message.event & PM_EVENT_AUTO) {
+        if (PMSG_IS_AUTO(message)) {
                 int b;
 
                 spin_lock_irq(&acm->write_lock);
diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c
index 1d26a7135dd..efe684908c1 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -798,11 +798,11 @@ static int wdm_suspend(struct usb_interface *intf, pm_message_t message)
         dev_dbg(&desc->intf->dev, "wdm%d_suspend\n", intf->minor);
 
         /* if this is an autosuspend the caller does the locking */
-        if (!(message.event & PM_EVENT_AUTO))
+        if (!PMSG_IS_AUTO(message))
                 mutex_lock(&desc->lock);
         spin_lock_irq(&desc->iuspin);
 
-        if ((message.event & PM_EVENT_AUTO) &&
+        if (PMSG_IS_AUTO(message) &&
                         (test_bit(WDM_IN_USE, &desc->flags)
                         || test_bit(WDM_RESPONDING, &desc->flags))) {
                 spin_unlock_irq(&desc->iuspin);
@@ -815,7 +815,7 @@ static int wdm_suspend(struct usb_interface *intf, pm_message_t message)
                 kill_urbs(desc);
                 cancel_work_sync(&desc->rxwork);
         }
-        if (!(message.event & PM_EVENT_AUTO))
+        if (!PMSG_IS_AUTO(message))
                 mutex_unlock(&desc->lock);
 
         return rv;
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index adf5ca8a239..3b029a0a478 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -1046,8 +1046,7 @@ static int usb_resume_device(struct usb_device *udev, pm_message_t msg)
         /* Non-root devices on a full/low-speed bus must wait for their
          * companion high-speed root hub, in case a handoff is needed.
          */
-        if (!(msg.event & PM_EVENT_AUTO) && udev->parent &&
-                        udev->bus->hs_companion)
+        if (!PMSG_IS_AUTO(msg) && udev->parent && udev->bus->hs_companion)
                 device_pm_wait_for_dev(&udev->dev,
                                 &udev->bus->hs_companion->root_hub->dev);
 
@@ -1075,7 +1074,7 @@ static int usb_suspend_interface(struct usb_device *udev,
 
         if (driver->suspend) {
                 status = driver->suspend(intf, msg);
-                if (status && !(msg.event & PM_EVENT_AUTO))
+                if (status && !PMSG_IS_AUTO(msg))
                         dev_err(&intf->dev, "%s error %d\n",
                                         "suspend", status);
         } else {
@@ -1189,7 +1188,7 @@ static int usb_suspend_both(struct usb_device *udev, pm_message_t msg)
                         status = usb_suspend_interface(udev, intf, msg);
 
                         /* Ignore errors during system sleep transitions */
-                        if (!(msg.event & PM_EVENT_AUTO))
+                        if (!PMSG_IS_AUTO(msg))
                                 status = 0;
                         if (status != 0)
                                 break;
@@ -1199,7 +1198,7 @@ static int usb_suspend_both(struct usb_device *udev, pm_message_t msg)
                 status = usb_suspend_device(udev, msg);
 
                 /* Again, ignore errors during system sleep transitions */
-                if (!(msg.event & PM_EVENT_AUTO))
+                if (!PMSG_IS_AUTO(msg))
                         status = 0;
         }
 
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index b3b7d062906..13222d352a6 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1975,8 +1975,9 @@ int hcd_bus_suspend(struct usb_device *rhdev, pm_message_t msg)
         int             status;
         int             old_state = hcd->state;
 
-        dev_dbg(&rhdev->dev, "bus %s%s\n",
-                        (msg.event & PM_EVENT_AUTO ? "auto-" : ""), "suspend");
+        dev_dbg(&rhdev->dev, "bus %ssuspend, wakeup %d\n",
+                        (PMSG_IS_AUTO(msg) ? "auto-" : ""),
+                        rhdev->do_remote_wakeup);
         if (HCD_DEAD(hcd)) {
                 dev_dbg(&rhdev->dev, "skipped %s of dead bus\n", "suspend");
                 return 0;
@@ -2011,8 +2012,8 @@ int hcd_bus_resume(struct usb_device *rhdev, pm_message_t msg)
         int             status;
         int             old_state = hcd->state;
 
-        dev_dbg(&rhdev->dev, "usb %s%s\n",
-                        (msg.event & PM_EVENT_AUTO ? "auto-" : ""), "resume");
+        dev_dbg(&rhdev->dev, "usb %sresume\n",
+                        (PMSG_IS_AUTO(msg) ? "auto-" : ""));
         if (HCD_DEAD(hcd)) {
                 dev_dbg(&rhdev->dev, "skipped %s of dead bus\n", "resume");
                 return 0;
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index d6cc8324934..96f05b29c9a 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -2369,8 +2369,6 @@ int usb_port_suspend(struct usb_device *udev, pm_message_t msg)
         int             port1 = udev->portnum;
         int             status;
 
-        // dev_dbg(hub->intfdev, "suspend port %d\n", port1);
-
         /* enable remote wakeup when appropriate; this lets the device
          * wake up the upstream hub (including maybe the root hub).
          *
@@ -2387,7 +2385,7 @@ int usb_port_suspend(struct usb_device *udev, pm_message_t msg)
                         dev_dbg(&udev->dev, "won't remote wakeup, status %d\n",
                                         status);
                         /* bail if autosuspend is requested */
-                        if (msg.event & PM_EVENT_AUTO)
+                        if (PMSG_IS_AUTO(msg))
                                 return status;
                 }
         }
@@ -2416,12 +2414,13 @@ int usb_port_suspend(struct usb_device *udev, pm_message_t msg)
                                 USB_CTRL_SET_TIMEOUT);
 
                 /* System sleep transitions should never fail */
-                if (!(msg.event & PM_EVENT_AUTO))
+                if (!PMSG_IS_AUTO(msg))
                         status = 0;
         } else {
                 /* device has up to 10 msec to fully suspend */
-                dev_dbg(&udev->dev, "usb %ssuspend\n",
-                                (msg.event & PM_EVENT_AUTO ? "auto-" : ""));
+                dev_dbg(&udev->dev, "usb %ssuspend, wakeup %d\n",
+                                (PMSG_IS_AUTO(msg) ? "auto-" : ""),
+                                udev->do_remote_wakeup);
                 usb_set_device_state(udev, USB_STATE_SUSPENDED);
                 msleep(10);
         }
@@ -2572,7 +2571,7 @@ int usb_port_resume(struct usb_device *udev, pm_message_t msg)
         } else {
                 /* drive resume for at least 20 msec */
                 dev_dbg(&udev->dev, "usb %sresume\n",
-                                (msg.event & PM_EVENT_AUTO ? "auto-" : ""));
+                                (PMSG_IS_AUTO(msg) ? "auto-" : ""));
                 msleep(25);
 
                 /* Virtual root hubs can trigger on GET_PORT_STATUS to
@@ -2679,7 +2678,7 @@ static int hub_suspend(struct usb_interface *intf, pm_message_t msg)
                 udev = hdev->children [port1-1];
                 if (udev && udev->can_submit) {
                         dev_warn(&intf->dev, "port %d nyet suspended\n", port1);
-                        if (msg.event & PM_EVENT_AUTO)
+                        if (PMSG_IS_AUTO(msg))
                                 return -EBUSY;
                 }
         }
diff --git a/drivers/usb/serial/sierra.c b/drivers/usb/serial/sierra.c
index d5d136a53b6..b18179bda0d 100644
--- a/drivers/usb/serial/sierra.c
+++ b/drivers/usb/serial/sierra.c
@@ -1009,7 +1009,7 @@ static int sierra_suspend(struct usb_serial *serial, pm_message_t message)
         struct sierra_intf_private *intfdata;
         int b;
 
-        if (message.event & PM_EVENT_AUTO) {
+        if (PMSG_IS_AUTO(message)) {
                 intfdata = serial->private;
                 spin_lock_irq(&intfdata->susp_lock);
                 b = intfdata->in_flight;
diff --git a/drivers/usb/serial/usb_wwan.c b/drivers/usb/serial/usb_wwan.c
index e4fad5e643d..d555ca9567b 100644
--- a/drivers/usb/serial/usb_wwan.c
+++ b/drivers/usb/serial/usb_wwan.c
@@ -651,7 +651,7 @@ int usb_wwan_suspend(struct usb_serial *serial, pm_message_t message)
 
         dbg("%s entered", __func__);
 
-        if (message.event & PM_EVENT_AUTO) {
+        if (PMSG_IS_AUTO(message)) {
                 spin_lock_irq(&intfdata->susp_lock);
                 b = intfdata->in_flight;
                 spin_unlock_irq(&intfdata->susp_lock);
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
new file mode 100644
index 00000000000..afb94583960
--- /dev/null
+++ b/include/linux/devfreq.h
@@ -0,0 +1,238 @@
+/*
+ * devfreq: Generic Dynamic Voltage and Frequency Scaling (DVFS) Framework
+ *          for Non-CPU Devices.
+ *
+ * Copyright (C) 2011 Samsung Electronics
+ *      MyungJoo Ham <myungjoo.ham@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_DEVFREQ_H__
+#define __LINUX_DEVFREQ_H__
+
+#include <linux/device.h>
+#include <linux/notifier.h>
+#include <linux/opp.h>
+
+#define DEVFREQ_NAME_LEN 16
+
+struct devfreq;
+
+/**
+ * struct devfreq_dev_status - Data given from devfreq user device to
+ *                           governors. Represents the performance
+ *                           statistics.
+ * @total_time          The total time represented by this instance of
+ *                      devfreq_dev_status
+ * @busy_time           The time that the device was working among the
+ *                      total_time.
+ * @current_frequency   The operating frequency.
+ * @private_data        An entry not specified by the devfreq framework.
+ *                      A device and a specific governor may have their
+ *                      own protocol with private_data. However, because
+ *                      this is governor-specific, a governor using this
+ *                      will be only compatible with devices aware of it.
+ */
+struct devfreq_dev_status {
+        /* both since the last measure */
+        unsigned long total_time;
+        unsigned long busy_time;
+        unsigned long current_frequency;
+        void *private_date;
+};
+
+/**
+ * struct devfreq_dev_profile - Devfreq's user device profile
+ * @initial_freq        The operating frequency when devfreq_add_device() is
+ *                      called.
+ * @polling_ms          The polling interval in ms. 0 disables polling.
+ * @target              The device should set its operating frequency at
+ *                      freq or lowest-upper-than-freq value. If freq is
+ *                      higher than any operable frequency, set maximum.
+ *                      Before returning, target function should set
+ *                      freq at the current frequency.
+ * @get_dev_status      The device should provide the current performance
+ *                      status to devfreq, which is used by governors.
+ * @exit                An optional callback that is called when devfreq
+ *                      is removing the devfreq object due to error or
+ *                      from devfreq_remove_device() call. If the user
+ *                      has registered devfreq->nb at a notifier-head,
+ *                      this is the time to unregister it.
+ */
+struct devfreq_dev_profile {
+        unsigned long initial_freq;
+        unsigned int polling_ms;
+
+        int (*target)(struct device *dev, unsigned long *freq);
+        int (*get_dev_status)(struct device *dev,
+                              struct devfreq_dev_status *stat);
+        void (*exit)(struct device *dev);
+};
+
+/**
+ * struct devfreq_governor - Devfreq policy governor
+ * @name                Governor's name
+ * @get_target_freq     Returns desired operating frequency for the device.
+ *                      Basically, get_target_freq will run
+ *                      devfreq_dev_profile.get_dev_status() to get the
+ *                      status of the device (load = busy_time / total_time).
+ *                      If no_central_polling is set, this callback is called
+ *                      only with update_devfreq() notified by OPP.
+ * @init                Called when the devfreq is being attached to a device
+ * @exit                Called when the devfreq is being removed from a
+ *                      device. Governor should stop any internal routines
+ *                      before return because related data may be
+ *                      freed after exit().
+ * @no_central_polling  Do not use devfreq's central polling mechanism.
+ *                      When this is set, devfreq will not call
+ *                      get_target_freq with devfreq_monitor(). However,
+ *                      devfreq will call get_target_freq with
+ *                      devfreq_update() notified by OPP framework.
+ *
+ * Note that the callbacks are called with devfreq->lock locked by devfreq.
+ */
+struct devfreq_governor {
+        const char name[DEVFREQ_NAME_LEN];
+        int (*get_target_freq)(struct devfreq *this, unsigned long *freq);
+        int (*init)(struct devfreq *this);
+        void (*exit)(struct devfreq *this);
+        const bool no_central_polling;
+};
+
+/**
+ * struct devfreq - Device devfreq structure
+ * @node        list node - contains the devices with devfreq that have been
+ *              registered.
+ * @lock        a mutex to protect accessing devfreq.
+ * @dev         device registered by devfreq class. dev.parent is the device
+ *              using devfreq.
+ * @profile     device-specific devfreq profile
+ * @governor    method how to choose frequency based on the usage.
+ * @nb          notifier block used to notify devfreq object that it should
+ *              reevaluate operable frequencies. Devfreq users may use
+ *              devfreq.nb to the corresponding register notifier call chain.
+ * @polling_jiffies     interval in jiffies.
+ * @previous_freq       previously configured frequency value.
+ * @next_polling        the number of remaining jiffies to poll with
+ *                      "devfreq_monitor" executions to reevaluate
+ *                      frequency/voltage of the device. Set by
+ *                      profile's polling_ms interval.
+ * @data        Private data of the governor. The devfreq framework does not
+ *              touch this.
+ * @being_removed       a flag to mark that this object is being removed in
+ *                      order to prevent trying to remove the object multiple times.
+ *
+ * This structure stores the devfreq information for a give device.
+ *
+ * Note that when a governor accesses entries in struct devfreq in its
+ * functions except for the context of callbacks defined in struct
+ * devfreq_governor, the governor should protect its access with the
+ * struct mutex lock in struct devfreq. A governor may use this mutex
+ * to protect its own private data in void *data as well.
+ */
+struct devfreq {
+        struct list_head node;
+
+        struct mutex lock;
+        struct device dev;
+        struct devfreq_dev_profile *profile;
+        const struct devfreq_governor *governor;
+        struct notifier_block nb;
+
+        unsigned long polling_jiffies;
+        unsigned long previous_freq;
+        unsigned int next_polling;
+
+        void *data; /* private data for governors */
+
+        bool being_removed;
+};
+
+#if defined(CONFIG_PM_DEVFREQ)
+extern struct devfreq *devfreq_add_device(struct device *dev,
+                                  struct devfreq_dev_profile *profile,
+                                  const struct devfreq_governor *governor,
+                                  void *data);
+extern int devfreq_remove_device(struct devfreq *devfreq);
+
+/* Helper functions for devfreq user device driver with OPP. */
+extern struct opp *devfreq_recommended_opp(struct device *dev,
+                                           unsigned long *freq);
+extern int devfreq_register_opp_notifier(struct device *dev,
+                                         struct devfreq *devfreq);
+extern int devfreq_unregister_opp_notifier(struct device *dev,
+                                           struct devfreq *devfreq);
+
+#ifdef CONFIG_DEVFREQ_GOV_POWERSAVE
+extern const struct devfreq_governor devfreq_powersave;
+#endif
+#ifdef CONFIG_DEVFREQ_GOV_PERFORMANCE
+extern const struct devfreq_governor devfreq_performance;
+#endif
+#ifdef CONFIG_DEVFREQ_GOV_USERSPACE
+extern const struct devfreq_governor devfreq_userspace;
+#endif
+#ifdef CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND
+extern const struct devfreq_governor devfreq_simple_ondemand;
+/**
+ * struct devfreq_simple_ondemand_data - void *data fed to struct devfreq
+ *      and devfreq_add_device
+ * @ upthreshold        If the load is over this value, the frequency jumps.
+ *                      Specify 0 to use the default. Valid value = 0 to 100.
+ * @ downdifferential   If the load is under upthreshold - downdifferential,
+ *                      the governor may consider slowing the frequency down.
+ *                      Specify 0 to use the default. Valid value = 0 to 100.
+ *                      downdifferential < upthreshold must hold.
+ *
+ * If the fed devfreq_simple_ondemand_data pointer is NULL to the governor,
+ * the governor uses the default values.
+ */
+struct devfreq_simple_ondemand_data {
+        unsigned int upthreshold;
+        unsigned int downdifferential;
+};
+#endif
+
+#else /* !CONFIG_PM_DEVFREQ */
+static struct devfreq *devfreq_add_device(struct device *dev,
+                                          struct devfreq_dev_profile *profile,
+                                          struct devfreq_governor *governor,
+                                          void *data);
+{
+        return NULL;
+}
+
+static int devfreq_remove_device(struct devfreq *devfreq);
+{
+        return 0;
+}
+
+static struct opp *devfreq_recommended_opp(struct device *dev,
+                                           unsigned long *freq)
+{
+        return -EINVAL;
+}
+
+static int devfreq_register_opp_notifier(struct device *dev,
+                                         struct devfreq *devfreq)
+{
+        return -EINVAL;
+}
+
+static int devfreq_unregister_opp_notifier(struct device *dev,
+                                           struct devfreq *devfreq)
+{
+        return -EINVAL;
+}
+
+#define devfreq_powersave       NULL
+#define devfreq_performance     NULL
+#define devfreq_userspace       NULL
+#define devfreq_simple_ondemand NULL
+
+#endif /* CONFIG_PM_DEVFREQ */
+
+#endif /* __LINUX_DEVFREQ_H__ */
diff --git a/include/linux/device.h b/include/linux/device.h
index 46751bdb71d..bdcf361ca93 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -638,6 +638,11 @@ static inline void set_dev_node(struct device *dev, int node)
 }
 #endif
 
+static inline struct pm_subsys_data *dev_to_psd(struct device *dev)
+{
+        return dev ? dev->power.subsys_data : NULL;
+}
+
 static inline unsigned int dev_get_uevent_suppress(const struct device *dev)
 {
         return dev->kobj.uevent_suppress;
diff --git a/include/linux/freezer.h b/include/linux/freezer.h
index 1effc8b56b4..aa56cf31f7f 100644
--- a/include/linux/freezer.h
+++ b/include/linux/freezer.h
@@ -49,6 +49,7 @@ extern int thaw_process(struct task_struct *p);
 
 extern void refrigerator(void);
 extern int freeze_processes(void);
+extern int freeze_kernel_threads(void);
 extern void thaw_processes(void);
 
 static inline int try_to_freeze(void)
@@ -171,7 +172,8 @@ static inline void clear_freeze_flag(struct task_struct *p) {}
 static inline int thaw_process(struct task_struct *p) { return 1; }
 
 static inline void refrigerator(void) {}
-static inline int freeze_processes(void) { BUG(); return 0; }
+static inline int freeze_processes(void) { return -ENOSYS; }
+static inline int freeze_kernel_threads(void) { return -ENOSYS; }
 static inline void thaw_processes(void) {}
 
 static inline int try_to_freeze(void) { return 0; }
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c8615cd0b2f..df1c836e694 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -31,7 +31,7 @@
 #include <linux/if_link.h>
 
 #ifdef __KERNEL__
-#include <linux/pm_qos_params.h>
+#include <linux/pm_qos.h>
 #include <linux/timer.h>
 #include <linux/delay.h>
 #include <linux/atomic.h>
@@ -969,7 +969,7 @@ struct net_device {
          */
         char                    name[IFNAMSIZ];
 
-        struct pm_qos_request_list pm_qos_req;
+        struct pm_qos_request   pm_qos_req;
 
         /* device name hash chain */
         struct hlist_node       name_hlist;
diff --git a/include/linux/opp.h b/include/linux/opp.h
index 7020e9736fc..87a9208f8ae 100644
--- a/include/linux/opp.h
+++ b/include/linux/opp.h
@@ -16,9 +16,14 @@
 
 #include <linux/err.h>
 #include <linux/cpufreq.h>
+#include <linux/notifier.h>
 
 struct opp;
 
+enum opp_event {
+        OPP_EVENT_ADD, OPP_EVENT_ENABLE, OPP_EVENT_DISABLE,
+};
+
 #if defined(CONFIG_PM_OPP)
 
 unsigned long opp_get_voltage(struct opp *opp);
@@ -40,6 +45,8 @@ int opp_enable(struct device *dev, unsigned long freq);
 
 int opp_disable(struct device *dev, unsigned long freq);
 
+struct srcu_notifier_head *opp_get_notifier(struct device *dev);
+
 #else
 static inline unsigned long opp_get_voltage(struct opp *opp)
 {
@@ -89,6 +96,11 @@ static inline int opp_disable(struct device *dev, unsigned long freq)
 {
         return 0;
 }
+
+struct srcu_notifier_head *opp_get_notifier(struct device *dev)
+{
+        return ERR_PTR(-EINVAL);
+}
 #endif          /* CONFIG_PM */
 
 #if defined(CONFIG_CPU_FREQ) && defined(CONFIG_PM_OPP)
diff --git a/include/linux/pm.h b/include/linux/pm.h
index f7c84c9abd3..f15acb64681 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -326,6 +326,7 @@ extern struct dev_pm_ops generic_subsys_pm_ops;
  *                      requested by a driver.
  */
 
+#define PM_EVENT_INVALID        (-1)
 #define PM_EVENT_ON             0x0000
 #define PM_EVENT_FREEZE         0x0001
 #define PM_EVENT_SUSPEND        0x0002
@@ -346,6 +347,7 @@ extern struct dev_pm_ops generic_subsys_pm_ops;
 #define PM_EVENT_AUTO_SUSPEND   (PM_EVENT_AUTO | PM_EVENT_SUSPEND)
 #define PM_EVENT_AUTO_RESUME    (PM_EVENT_AUTO | PM_EVENT_RESUME)
 
+#define PMSG_INVALID    ((struct pm_message){ .event = PM_EVENT_INVALID, })
 #define PMSG_ON         ((struct pm_message){ .event = PM_EVENT_ON, })
 #define PMSG_FREEZE     ((struct pm_message){ .event = PM_EVENT_FREEZE, })
 #define PMSG_QUIESCE    ((struct pm_message){ .event = PM_EVENT_QUIESCE, })
@@ -366,6 +368,8 @@ extern struct dev_pm_ops generic_subsys_pm_ops;
 #define PMSG_AUTO_RESUME        ((struct pm_message) \
                                         { .event = PM_EVENT_AUTO_RESUME, })
 
+#define PMSG_IS_AUTO(msg)       (((msg).event & PM_EVENT_AUTO) != 0)
+
 /**
  * Device run-time power management status.
  *
@@ -421,6 +425,22 @@ enum rpm_request {
 
 struct wakeup_source;
 
+struct pm_domain_data {
+        struct list_head list_node;
+        struct device *dev;
+};
+
+struct pm_subsys_data {
+        spinlock_t lock;
+        unsigned int refcount;
+#ifdef CONFIG_PM_CLK
+        struct list_head clock_list;
+#endif
+#ifdef CONFIG_PM_GENERIC_DOMAINS
+        struct pm_domain_data *domain_data;
+#endif
+};
+
 struct dev_pm_info {
         pm_message_t            power_state;
         unsigned int            can_wakeup:1;
@@ -432,6 +452,7 @@ struct dev_pm_info {
         struct list_head        entry;
         struct completion       completion;
         struct wakeup_source    *wakeup;
+        bool                    wakeup_path:1;
 #else
         unsigned int            should_wakeup:1;
 #endif
@@ -462,10 +483,13 @@ struct dev_pm_info {
         unsigned long           suspended_jiffies;
         unsigned long           accounting_timestamp;
 #endif
-        void                    *subsys_data;  /* Owned by the subsystem. */
+        struct pm_subsys_data   *subsys_data;  /* Owned by the subsystem. */
+        struct pm_qos_constraints *constraints;
 };
 
 extern void update_pm_runtime_accounting(struct device *dev);
+extern int dev_pm_get_subsys_data(struct device *dev);
+extern int dev_pm_put_subsys_data(struct device *dev);
 
 /*
  * Power domains provide callbacks that are executed during system suspend,
diff --git a/include/linux/pm_clock.h b/include/linux/pm_clock.h
new file mode 100644
index 00000000000..8348866e7b0
--- /dev/null
+++ b/include/linux/pm_clock.h
@@ -0,0 +1,71 @@
+/*
+ * pm_clock.h - Definitions and headers related to device clocks.
+ *
+ * Copyright (C) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Renesas Electronics Corp.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#ifndef _LINUX_PM_CLOCK_H
+#define _LINUX_PM_CLOCK_H
+
+#include <linux/device.h>
+#include <linux/notifier.h>
+
+struct pm_clk_notifier_block {
+        struct notifier_block nb;
+        struct dev_pm_domain *pm_domain;
+        char *con_ids[];
+};
+
+#ifdef CONFIG_PM_CLK
+static inline bool pm_clk_no_clocks(struct device *dev)
+{
+        return dev && dev->power.subsys_data
+                && list_empty(&dev->power.subsys_data->clock_list);
+}
+
+extern void pm_clk_init(struct device *dev);
+extern int pm_clk_create(struct device *dev);
+extern void pm_clk_destroy(struct device *dev);
+extern int pm_clk_add(struct device *dev, const char *con_id);
+extern void pm_clk_remove(struct device *dev, const char *con_id);
+extern int pm_clk_suspend(struct device *dev);
+extern int pm_clk_resume(struct device *dev);
+#else
+static inline bool pm_clk_no_clocks(struct device *dev)
+{
+        return true;
+}
+static inline void pm_clk_init(struct device *dev)
+{
+}
+static inline int pm_clk_create(struct device *dev)
+{
+        return -EINVAL;
+}
+static inline void pm_clk_destroy(struct device *dev)
+{
+}
+static inline int pm_clk_add(struct device *dev, const char *con_id)
+{
+        return -EINVAL;
+}
+static inline void pm_clk_remove(struct device *dev, const char *con_id)
+{
+}
+#define pm_clk_suspend  NULL
+#define pm_clk_resume   NULL
+#endif
+
+#ifdef CONFIG_HAVE_CLK
+extern void pm_clk_add_notifier(struct bus_type *bus,
+                                        struct pm_clk_notifier_block *clknb);
+#else
+static inline void pm_clk_add_notifier(struct bus_type *bus,
+                                        struct pm_clk_notifier_block *clknb)
+{
+}
+#endif
+
+#endif
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index f9ec1736a11..65633e5a2bc 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -13,6 +13,7 @@
 
 enum gpd_status {
         GPD_STATE_ACTIVE = 0,   /* PM domain is active */
+        GPD_STATE_WAIT_MASTER,  /* PM domain's master is being waited for */
         GPD_STATE_BUSY,         /* Something is happening to the PM domain */
         GPD_STATE_REPEAT,       /* Power off in progress, to be repeated */
         GPD_STATE_POWER_OFF,    /* PM domain is off */
@@ -25,15 +26,14 @@ struct dev_power_governor {
 struct generic_pm_domain {
         struct dev_pm_domain domain;    /* PM domain operations */
         struct list_head gpd_list_node; /* Node in the global PM domains list */
-        struct list_head sd_node;       /* Node in the parent's subdomain list */
-        struct generic_pm_domain *parent;       /* Parent PM domain */
-        struct list_head sd_list;       /* List of dubdomains */
+        struct list_head master_links;  /* Links with PM domain as a master */
+        struct list_head slave_links;   /* Links with PM domain as a slave */
         struct list_head dev_list;      /* List of devices */
         struct mutex lock;
         struct dev_power_governor *gov;
         struct work_struct power_off_work;
         unsigned int in_progress;       /* Number of devices being suspended now */
-        unsigned int sd_count;  /* Number of subdomains with power "on" */
+        atomic_t sd_count;      /* Number of subdomains with power "on" */
         enum gpd_status status; /* Current state of the domain */
         wait_queue_head_t status_wait_queue;
         struct task_struct *poweroff_task;      /* Powering off task */
@@ -42,6 +42,7 @@ struct generic_pm_domain {
         unsigned int suspended_count;   /* System suspend device counter */
         unsigned int prepared_count;    /* Suspend counter of prepared devices */
         bool suspend_power_off; /* Power status before system suspend */
+        bool dev_irq_safe;      /* Device callbacks are IRQ-safe */
         int (*power_off)(struct generic_pm_domain *domain);
         int (*power_on)(struct generic_pm_domain *domain);
         int (*start_device)(struct device *dev);
@@ -54,12 +55,23 @@ static inline struct generic_pm_domain *pd_to_genpd(struct dev_pm_domain *pd)
         return container_of(pd, struct generic_pm_domain, domain);
 }
 
-struct dev_list_entry {
-        struct list_head node;
-        struct device *dev;
+struct gpd_link {
+        struct generic_pm_domain *master;
+        struct list_head master_node;
+        struct generic_pm_domain *slave;
+        struct list_head slave_node;
+};
+
+struct generic_pm_domain_data {
+        struct pm_domain_data base;
         bool need_restore;
 };
 
+static inline struct generic_pm_domain_data *to_gpd_data(struct pm_domain_data *pdd)
+{
+        return container_of(pdd, struct generic_pm_domain_data, base);
+}
+
 #ifdef CONFIG_PM_GENERIC_DOMAINS
 extern int pm_genpd_add_device(struct generic_pm_domain *genpd,
                                struct device *dev);
diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h
new file mode 100644
index 00000000000..83b0ea302a8
--- /dev/null
+++ b/include/linux/pm_qos.h
@@ -0,0 +1,155 @@
+#ifndef _LINUX_PM_QOS_H
+#define _LINUX_PM_QOS_H
+/* interface for the pm_qos_power infrastructure of the linux kernel.
+ *
+ * Mark Gross <mgross@linux.intel.com>
+ */
+#include <linux/plist.h>
+#include <linux/notifier.h>
+#include <linux/miscdevice.h>
+#include <linux/device.h>
+
+#define PM_QOS_RESERVED 0
+#define PM_QOS_CPU_DMA_LATENCY 1
+#define PM_QOS_NETWORK_LATENCY 2
+#define PM_QOS_NETWORK_THROUGHPUT 3
+
+#define PM_QOS_NUM_CLASSES 4
+#define PM_QOS_DEFAULT_VALUE -1
+
+#define PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE        (2000 * USEC_PER_SEC)
+#define PM_QOS_NETWORK_LAT_DEFAULT_VALUE        (2000 * USEC_PER_SEC)
+#define PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE 0
+#define PM_QOS_DEV_LAT_DEFAULT_VALUE            0
+
+struct pm_qos_request {
+        struct plist_node node;
+        int pm_qos_class;
+};
+
+struct dev_pm_qos_request {
+        struct plist_node node;
+        struct device *dev;
+};
+
+enum pm_qos_type {
+        PM_QOS_UNITIALIZED,
+        PM_QOS_MAX,             /* return the largest value */
+        PM_QOS_MIN              /* return the smallest value */
+};
+
+/*
+ * Note: The lockless read path depends on the CPU accessing
+ * target_value atomically.  Atomic access is only guaranteed on all CPU
+ * types linux supports for 32 bit quantites
+ */
+struct pm_qos_constraints {
+        struct plist_head list;
+        s32 target_value;       /* Do not change to 64 bit */
+        s32 default_value;
+        enum pm_qos_type type;
+        struct blocking_notifier_head *notifiers;
+};
+
+/* Action requested to pm_qos_update_target */
+enum pm_qos_req_action {
+        PM_QOS_ADD_REQ,         /* Add a new request */
+        PM_QOS_UPDATE_REQ,      /* Update an existing request */
+        PM_QOS_REMOVE_REQ       /* Remove an existing request */
+};
+
+static inline int dev_pm_qos_request_active(struct dev_pm_qos_request *req)
+{
+        return req->dev != 0;
+}
+
+#ifdef CONFIG_PM
+int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node,
+                         enum pm_qos_req_action action, int value);
+void pm_qos_add_request(struct pm_qos_request *req, int pm_qos_class,
+                        s32 value);
+void pm_qos_update_request(struct pm_qos_request *req,
+                           s32 new_value);
+void pm_qos_remove_request(struct pm_qos_request *req);
+
+int pm_qos_request(int pm_qos_class);
+int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier);
+int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier);
+int pm_qos_request_active(struct pm_qos_request *req);
+s32 pm_qos_read_value(struct pm_qos_constraints *c);
+
+s32 dev_pm_qos_read_value(struct device *dev);
+int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req,
+                           s32 value);
+int dev_pm_qos_update_request(struct dev_pm_qos_request *req, s32 new_value);
+int dev_pm_qos_remove_request(struct dev_pm_qos_request *req);
+int dev_pm_qos_add_notifier(struct device *dev,
+                            struct notifier_block *notifier);
+int dev_pm_qos_remove_notifier(struct device *dev,
+                               struct notifier_block *notifier);
+int dev_pm_qos_add_global_notifier(struct notifier_block *notifier);
+int dev_pm_qos_remove_global_notifier(struct notifier_block *notifier);
+void dev_pm_qos_constraints_init(struct device *dev);
+void dev_pm_qos_constraints_destroy(struct device *dev);
+#else
+static inline int pm_qos_update_target(struct pm_qos_constraints *c,
+                                       struct plist_node *node,
+                                       enum pm_qos_req_action action,
+                                       int value)
+                        { return 0; }
+static inline void pm_qos_add_request(struct pm_qos_request *req,
+                                      int pm_qos_class, s32 value)
+                        { return; }
+static inline void pm_qos_update_request(struct pm_qos_request *req,
+                                         s32 new_value)
+                        { return; }
+static inline void pm_qos_remove_request(struct pm_qos_request *req)
+                        { return; }
+
+static inline int pm_qos_request(int pm_qos_class)
+                        { return 0; }
+static inline int pm_qos_add_notifier(int pm_qos_class,
+                                      struct notifier_block *notifier)
+                        { return 0; }
+static inline int pm_qos_remove_notifier(int pm_qos_class,
+                                         struct notifier_block *notifier)
+                        { return 0; }
+static inline int pm_qos_request_active(struct pm_qos_request *req)
+                        { return 0; }
+static inline s32 pm_qos_read_value(struct pm_qos_constraints *c)
+                        { return 0; }
+
+static inline s32 dev_pm_qos_read_value(struct device *dev)
+                        { return 0; }
+static inline int dev_pm_qos_add_request(struct device *dev,
+                                         struct dev_pm_qos_request *req,
+                                         s32 value)
+                        { return 0; }
+static inline int dev_pm_qos_update_request(struct dev_pm_qos_request *req,
+                                            s32 new_value)
+                        { return 0; }
+static inline int dev_pm_qos_remove_request(struct dev_pm_qos_request *req)
+                        { return 0; }
+static inline int dev_pm_qos_add_notifier(struct device *dev,
+                                          struct notifier_block *notifier)
+                        { return 0; }
+static inline int dev_pm_qos_remove_notifier(struct device *dev,
+                                             struct notifier_block *notifier)
+                        { return 0; }
+static inline int dev_pm_qos_add_global_notifier(
+                                        struct notifier_block *notifier)
+                        { return 0; }
+static inline int dev_pm_qos_remove_global_notifier(
+                                        struct notifier_block *notifier)
+                        { return 0; }
+static inline void dev_pm_qos_constraints_init(struct device *dev)
+{
+        dev->power.power_state = PMSG_ON;
+}
+static inline void dev_pm_qos_constraints_destroy(struct device *dev)
+{
+        dev->power.power_state = PMSG_INVALID;
+}
+#endif
+
+#endif
diff --git a/include/linux/pm_qos_params.h b/include/linux/pm_qos_params.h
deleted file mode 100644
index a7d87f911ca..00000000000
--- a/include/linux/pm_qos_params.h
+++ /dev/null
@@ -1,38 +0,0 @@
-#ifndef _LINUX_PM_QOS_PARAMS_H
-#define _LINUX_PM_QOS_PARAMS_H
-/* interface for the pm_qos_power infrastructure of the linux kernel.
- *
- * Mark Gross <mgross@linux.intel.com>
- */
-#include <linux/plist.h>
-#include <linux/notifier.h>
-#include <linux/miscdevice.h>
-
-#define PM_QOS_RESERVED 0
-#define PM_QOS_CPU_DMA_LATENCY 1
-#define PM_QOS_NETWORK_LATENCY 2
-#define PM_QOS_NETWORK_THROUGHPUT 3
-
-#define PM_QOS_NUM_CLASSES 4
-#define PM_QOS_DEFAULT_VALUE -1
-
-#define PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE        (2000 * USEC_PER_SEC)
-#define PM_QOS_NETWORK_LAT_DEFAULT_VALUE        (2000 * USEC_PER_SEC)
-#define PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE 0
-
-struct pm_qos_request_list {
-        struct plist_node list;
-        int pm_qos_class;
-};
-
-void pm_qos_add_request(struct pm_qos_request_list *l, int pm_qos_class, s32 value);
-void pm_qos_update_request(struct pm_qos_request_list *pm_qos_req,
-                s32 new_value);
-void pm_qos_remove_request(struct pm_qos_request_list *pm_qos_req);
-
-int pm_qos_request(int pm_qos_class);
-int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier);
-int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier);
-int pm_qos_request_active(struct pm_qos_request_list *req);
-
-#endif
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index daac05d751b..70b284024d9 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -251,46 +251,4 @@ static inline void pm_runtime_dont_use_autosuspend(struct device *dev)
         __pm_runtime_use_autosuspend(dev, false);
 }
 
-struct pm_clk_notifier_block {
-        struct notifier_block nb;
-        struct dev_pm_domain *pm_domain;
-        char *con_ids[];
-};
-
-#ifdef CONFIG_PM_CLK
-extern int pm_clk_init(struct device *dev);
-extern void pm_clk_destroy(struct device *dev);
-extern int pm_clk_add(struct device *dev, const char *con_id);
-extern void pm_clk_remove(struct device *dev, const char *con_id);
-extern int pm_clk_suspend(struct device *dev);
-extern int pm_clk_resume(struct device *dev);
-#else
-static inline int pm_clk_init(struct device *dev)
-{
-        return -EINVAL;
-}
-static inline void pm_clk_destroy(struct device *dev)
-{
-}
-static inline int pm_clk_add(struct device *dev, const char *con_id)
-{
-        return -EINVAL;
-}
-static inline void pm_clk_remove(struct device *dev, const char *con_id)
-{
-}
-#define pm_clk_suspend  NULL
-#define pm_clk_resume   NULL
-#endif
-
-#ifdef CONFIG_HAVE_CLK
-extern void pm_clk_add_notifier(struct bus_type *bus,
-                                        struct pm_clk_notifier_block *clknb);
-#else
-static inline void pm_clk_add_notifier(struct bus_type *bus,
-                                        struct pm_clk_notifier_block *clknb)
-{
-}
-#endif
-
 #endif
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 6bbcef22e10..57a692432f8 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -8,15 +8,18 @@
 #include <linux/mm.h>
 #include <asm/errno.h>
 
-#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_VT) && defined(CONFIG_VT_CONSOLE)
+#ifdef CONFIG_VT
 extern void pm_set_vt_switch(int);
-extern int pm_prepare_console(void);
-extern void pm_restore_console(void);
 #else
 static inline void pm_set_vt_switch(int do_switch)
 {
 }
+#endif
 
+#ifdef CONFIG_VT_CONSOLE_SLEEP
+extern int pm_prepare_console(void);
+extern void pm_restore_console(void);
+#else
 static inline int pm_prepare_console(void)
 {
         return 0;
@@ -34,6 +37,58 @@ typedef int __bitwise suspend_state_t;
 #define PM_SUSPEND_MEM          ((__force suspend_state_t) 3)
 #define PM_SUSPEND_MAX          ((__force suspend_state_t) 4)
 
+enum suspend_stat_step {
+        SUSPEND_FREEZE = 1,
+        SUSPEND_PREPARE,
+        SUSPEND_SUSPEND,
+        SUSPEND_SUSPEND_NOIRQ,
+        SUSPEND_RESUME_NOIRQ,
+        SUSPEND_RESUME
+};
+
+struct suspend_stats {
+        int     success;
+        int     fail;
+        int     failed_freeze;
+        int     failed_prepare;
+        int     failed_suspend;
+        int     failed_suspend_noirq;
+        int     failed_resume;
+        int     failed_resume_noirq;
+#define REC_FAILED_NUM  2
+        int     last_failed_dev;
+        char    failed_devs[REC_FAILED_NUM][40];
+        int     last_failed_errno;
+        int     errno[REC_FAILED_NUM];
+        int     last_failed_step;
+        enum suspend_stat_step  failed_steps[REC_FAILED_NUM];
+};
+
+extern struct suspend_stats suspend_stats;
+
+static inline void dpm_save_failed_dev(const char *name)
+{
+        strlcpy(suspend_stats.failed_devs[suspend_stats.last_failed_dev],
+                name,
+                sizeof(suspend_stats.failed_devs[0]));
+        suspend_stats.last_failed_dev++;
+        suspend_stats.last_failed_dev %= REC_FAILED_NUM;
+}
+
+static inline void dpm_save_failed_errno(int err)
+{
+        suspend_stats.errno[suspend_stats.last_failed_errno] = err;
+        suspend_stats.last_failed_errno++;
+        suspend_stats.last_failed_errno %= REC_FAILED_NUM;
+}
+
+static inline void dpm_save_failed_step(enum suspend_stat_step step)
+{
+        suspend_stats.failed_steps[suspend_stats.last_failed_step] = step;
+        suspend_stats.last_failed_step++;
+        suspend_stats.last_failed_step %= REC_FAILED_NUM;
+}
+
 /**
  * struct platform_suspend_ops - Callbacks for managing platform dependent
  *      system sleep states.
@@ -334,4 +389,38 @@ static inline void unlock_system_sleep(void)
 }
 #endif
 
+#ifdef CONFIG_ARCH_SAVE_PAGE_KEYS
+/*
+ * The ARCH_SAVE_PAGE_KEYS functions can be used by an architecture
+ * to save/restore additional information to/from the array of page
+ * frame numbers in the hibernation image. For s390 this is used to
+ * save and restore the storage key for each page that is included
+ * in the hibernation image.
+ */
+unsigned long page_key_additional_pages(unsigned long pages);
+int page_key_alloc(unsigned long pages);
+void page_key_free(void);
+void page_key_read(unsigned long *pfn);
+void page_key_memorize(unsigned long *pfn);
+void page_key_write(void *address);
+
+#else /* !CONFIG_ARCH_SAVE_PAGE_KEYS */
+
+static inline unsigned long page_key_additional_pages(unsigned long pages)
+{
+        return 0;
+}
+
+static inline int  page_key_alloc(unsigned long pages)
+{
+        return 0;
+}
+
+static inline void page_key_free(void) {}
+static inline void page_key_read(unsigned long *pfn) {}
+static inline void page_key_memorize(unsigned long *pfn) {}
+static inline void page_key_write(void *address) {}
+
+#endif /* !CONFIG_ARCH_SAVE_PAGE_KEYS */
+
 #endif /* _LINUX_SUSPEND_H */
diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index 57e71fa33f7..54cb079b7bf 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -29,7 +29,7 @@
 #include <linux/poll.h>
 #include <linux/mm.h>
 #include <linux/bitops.h>
-#include <linux/pm_qos_params.h>
+#include <linux/pm_qos.h>
 
 #define snd_pcm_substream_chip(substream) ((substream)->private_data)
 #define snd_pcm_chip(pcm) ((pcm)->private_data)
@@ -373,7 +373,7 @@ struct snd_pcm_substream {
         int number;
         char name[32];                  /* substream name */
         int stream;                     /* stream (direction) */
-        struct pm_qos_request_list latency_pm_qos_req; /* pm_qos request */
+        struct pm_qos_request latency_pm_qos_req; /* pm_qos request */
         size_t buffer_bytes_max;        /* limit ring buffer size */
         struct snd_dma_buffer dma_buffer;
         unsigned int dma_buf_id;
diff --git a/include/trace/events/rpm.h b/include/trace/events/rpm.h
new file mode 100644
index 00000000000..d62c558bf64
--- /dev/null
+++ b/include/trace/events/rpm.h
@@ -0,0 +1,99 @@
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM rpm
+
+#if !defined(_TRACE_RUNTIME_POWER_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_RUNTIME_POWER_H
+
+#include <linux/ktime.h>
+#include <linux/tracepoint.h>
+#include <linux/device.h>
+
+/*
+ * The rpm_internal events are used for tracing some important
+ * runtime pm internal functions.
+ */
+DECLARE_EVENT_CLASS(rpm_internal,
+
+        TP_PROTO(struct device *dev, int flags),
+
+        TP_ARGS(dev, flags),
+
+        TP_STRUCT__entry(
+                __string(       name,           dev_name(dev)   )
+                __field(        int,            flags           )
+                __field(        int ,           usage_count     )
+                __field(        int ,           disable_depth   )
+                __field(        int ,           runtime_auto    )
+                __field(        int ,           request_pending )
+                __field(        int ,           irq_safe        )
+                __field(        int ,           child_count     )
+        ),
+
+        TP_fast_assign(
+                __assign_str(name, dev_name(dev));
+                __entry->flags = flags;
+                __entry->usage_count = atomic_read(
+                        &dev->power.usage_count);
+                __entry->disable_depth = dev->power.disable_depth;
+                __entry->runtime_auto = dev->power.runtime_auto;
+                __entry->request_pending = dev->power.request_pending;
+                __entry->irq_safe = dev->power.irq_safe;
+                __entry->child_count = atomic_read(
+                        &dev->power.child_count);
+        ),
+
+        TP_printk("%s flags-%x cnt-%-2d dep-%-2d auto-%-1d p-%-1d"
+                        " irq-%-1d child-%d",
+                        __get_str(name), __entry->flags,
+                        __entry->usage_count,
+                        __entry->disable_depth,
+                        __entry->runtime_auto,
+                        __entry->request_pending,
+                        __entry->irq_safe,
+                        __entry->child_count
+                 )
+);
+DEFINE_EVENT(rpm_internal, rpm_suspend,
+
+        TP_PROTO(struct device *dev, int flags),
+
+        TP_ARGS(dev, flags)
+);
+DEFINE_EVENT(rpm_internal, rpm_resume,
+
+        TP_PROTO(struct device *dev, int flags),
+
+        TP_ARGS(dev, flags)
+);
+DEFINE_EVENT(rpm_internal, rpm_idle,
+
+        TP_PROTO(struct device *dev, int flags),
+
+        TP_ARGS(dev, flags)
+);
+
+TRACE_EVENT(rpm_return_int,
+        TP_PROTO(struct device *dev, unsigned long ip, int ret),
+        TP_ARGS(dev, ip, ret),
+
+        TP_STRUCT__entry(
+                __string(       name,           dev_name(dev))
+                __field(        unsigned long,          ip      )
+                __field(        int,                    ret     )
+        ),
+
+        TP_fast_assign(
+                __assign_str(name, dev_name(dev));
+                __entry->ip = ip;
+                __entry->ret = ret;
+        ),
+
+        TP_printk("%pS:%s ret=%d", (void *)__entry->ip, __get_str(name),
+                __entry->ret)
+);
+
+#endif /* _TRACE_RUNTIME_POWER_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/kernel/Makefile b/kernel/Makefile
index eca595e2fd5..2da48d3515e 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -9,7 +9,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
             rcupdate.o extable.o params.o posix-timers.o \
             kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
             hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
-            notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
+            notifier.o ksysfs.o sched_clock.o cred.o \
             async.o range.o
 obj-y += groups.o
 
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 7b01de98bb6..66a594e8ad2 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -67,7 +67,7 @@ static void fake_signal_wake_up(struct task_struct *p)
         unsigned long flags;
 
         spin_lock_irqsave(&p->sighand->siglock, flags);
-        signal_wake_up(p, 0);
+        signal_wake_up(p, 1);
         spin_unlock_irqrestore(&p->sighand->siglock, flags);
 }
 
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 3744c594b19..cedd9982306 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -27,6 +27,7 @@ config HIBERNATION
         select HIBERNATE_CALLBACKS
         select LZO_COMPRESS
         select LZO_DECOMPRESS
+        select CRC32
         ---help---
           Enable the suspend to disk (STD) functionality, which is usually
           called "hibernation" in user interfaces.  STD checkpoints the
@@ -65,6 +66,9 @@ config HIBERNATION
 
           For more information take a look at <file:Documentation/power/swsusp.txt>.
 
+config ARCH_SAVE_PAGE_KEYS
+        bool
+
 config PM_STD_PARTITION
         string "Default resume partition"
         depends on HIBERNATION
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index c5ebc6a9064..07e0e28ffba 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -1,8 +1,8 @@
 
 ccflags-$(CONFIG_PM_DEBUG)      := -DDEBUG
 
-obj-$(CONFIG_PM)                += main.o
-obj-$(CONFIG_PM_SLEEP)          += console.o
+obj-$(CONFIG_PM)                += main.o qos.o
+obj-$(CONFIG_VT_CONSOLE_SLEEP)  += console.o
 obj-$(CONFIG_FREEZER)           += process.o
 obj-$(CONFIG_SUSPEND)           += suspend.o
 obj-$(CONFIG_PM_TEST_SUSPEND)   += suspend_test.o
diff --git a/kernel/power/console.c b/kernel/power/console.c
index 218e5af9015..b1dc456474b 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -1,5 +1,5 @@
 /*
- * drivers/power/process.c - Functions for saving/restoring console.
+ * Functions for saving/restoring console.
  *
  * Originally from swsusp.
  */
@@ -10,7 +10,6 @@
 #include <linux/module.h>
 #include "power.h"
 
-#if defined(CONFIG_VT) && defined(CONFIG_VT_CONSOLE)
 #define SUSPEND_CONSOLE (MAX_NR_CONSOLES-1)
 
 static int orig_fgconsole, orig_kmsg;
@@ -32,4 +31,3 @@ void pm_restore_console(void)
                 vt_kmsg_redirect(orig_kmsg);
         }
 }
-#endif
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 8f7b1db1ece..1c53f7fad5f 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -14,6 +14,7 @@
 #include <linux/reboot.h>
 #include <linux/string.h>
 #include <linux/device.h>
+#include <linux/async.h>
 #include <linux/kmod.h>
 #include <linux/delay.h>
 #include <linux/fs.h>
@@ -29,12 +30,14 @@
 #include "power.h"
 
 
-static int nocompress = 0;
-static int noresume = 0;
+static int nocompress;
+static int noresume;
+static int resume_wait;
+static int resume_delay;
 static char resume_file[256] = CONFIG_PM_STD_PARTITION;
 dev_t swsusp_resume_device;
 sector_t swsusp_resume_block;
-int in_suspend __nosavedata = 0;
+int in_suspend __nosavedata;
 
 enum {
         HIBERNATION_INVALID,
@@ -334,13 +337,17 @@ int hibernation_snapshot(int platform_mode)
         if (error)
                 goto Close;
 
-        error = dpm_prepare(PMSG_FREEZE);
-        if (error)
-                goto Complete_devices;
-
         /* Preallocate image memory before shutting down devices. */
         error = hibernate_preallocate_memory();
         if (error)
+                goto Close;
+
+        error = freeze_kernel_threads();
+        if (error)
+                goto Close;
+
+        error = dpm_prepare(PMSG_FREEZE);
+        if (error)
                 goto Complete_devices;
 
         suspend_console();
@@ -463,7 +470,7 @@ static int resume_target_kernel(bool platform_mode)
  * @platform_mode: If set, use platform driver to prepare for the transition.
  *
  * This routine must be called with pm_mutex held.  If it is successful, control
- * reappears in the restored target kernel in hibernation_snaphot().
+ * reappears in the restored target kernel in hibernation_snapshot().
  */
 int hibernation_restore(int platform_mode)
 {
@@ -650,6 +657,9 @@ int hibernate(void)
                         flags |= SF_PLATFORM_MODE;
                 if (nocompress)
                         flags |= SF_NOCOMPRESS_MODE;
+                else
+                        flags |= SF_CRC32_MODE;
+
                 pr_debug("PM: writing image.\n");
                 error = swsusp_write(flags);
                 swsusp_free();
@@ -724,6 +734,12 @@ static int software_resume(void)
 
         pr_debug("PM: Checking hibernation image partition %s\n", resume_file);
 
+        if (resume_delay) {
+                printk(KERN_INFO "Waiting %dsec before reading resume device...\n",
+                        resume_delay);
+                ssleep(resume_delay);
+        }
+
         /* Check if the device is there */
         swsusp_resume_device = name_to_dev_t(resume_file);
         if (!swsusp_resume_device) {
@@ -732,6 +748,13 @@ static int software_resume(void)
                  * to wait for this to finish.
                  */
                 wait_for_device_probe();
+
+                if (resume_wait) {
+                        while ((swsusp_resume_device = name_to_dev_t(resume_file)) == 0)
+                                msleep(10);
+                        async_synchronize_full();
+                }
+
                 /*
                  * We can't depend on SCSI devices being available after loading
                  * one of their modules until scsi_complete_async_scans() is
@@ -1060,7 +1083,21 @@ static int __init noresume_setup(char *str)
         return 1;
 }
 
+static int __init resumewait_setup(char *str)
+{
+        resume_wait = 1;
+        return 1;
+}
+
+static int __init resumedelay_setup(char *str)
+{
+        resume_delay = simple_strtoul(str, NULL, 0);
+        return 1;
+}
+
 __setup("noresume", noresume_setup);
 __setup("resume_offset=", resume_offset_setup);
 __setup("resume=", resume_setup);
 __setup("hibernate=", hibernate_setup);
+__setup("resumewait", resumewait_setup);
+__setup("resumedelay=", resumedelay_setup);
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 6c601f87196..a52e88425a3 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -12,6 +12,8 @@
 #include <linux/string.h>
 #include <linux/resume-trace.h>
 #include <linux/workqueue.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
 
 #include "power.h"
 
@@ -131,6 +133,101 @@ static ssize_t pm_test_store(struct kobject *kobj, struct kobj_attribute *attr,
 power_attr(pm_test);
 #endif /* CONFIG_PM_DEBUG */
 
+#ifdef CONFIG_DEBUG_FS
+static char *suspend_step_name(enum suspend_stat_step step)
+{
+        switch (step) {
+        case SUSPEND_FREEZE:
+                return "freeze";
+        case SUSPEND_PREPARE:
+                return "prepare";
+        case SUSPEND_SUSPEND:
+                return "suspend";
+        case SUSPEND_SUSPEND_NOIRQ:
+                return "suspend_noirq";
+        case SUSPEND_RESUME_NOIRQ:
+                return "resume_noirq";
+        case SUSPEND_RESUME:
+                return "resume";
+        default:
+                return "";
+        }
+}
+
+static int suspend_stats_show(struct seq_file *s, void *unused)
+{
+        int i, index, last_dev, last_errno, last_step;
+
+        last_dev = suspend_stats.last_failed_dev + REC_FAILED_NUM - 1;
+        last_dev %= REC_FAILED_NUM;
+        last_errno = suspend_stats.last_failed_errno + REC_FAILED_NUM - 1;
+        last_errno %= REC_FAILED_NUM;
+        last_step = suspend_stats.last_failed_step + REC_FAILED_NUM - 1;
+        last_step %= REC_FAILED_NUM;
+        seq_printf(s, "%s: %d\n%s: %d\n%s: %d\n%s: %d\n"
+                        "%s: %d\n%s: %d\n%s: %d\n%s: %d\n",
+                        "success", suspend_stats.success,
+                        "fail", suspend_stats.fail,
+                        "failed_freeze", suspend_stats.failed_freeze,
+                        "failed_prepare", suspend_stats.failed_prepare,
+                        "failed_suspend", suspend_stats.failed_suspend,
+                        "failed_suspend_noirq",
+                                suspend_stats.failed_suspend_noirq,
+                        "failed_resume", suspend_stats.failed_resume,
+                        "failed_resume_noirq",
+                                suspend_stats.failed_resume_noirq);
+        seq_printf(s,   "failures:\n  last_failed_dev:\t%-s\n",
+                        suspend_stats.failed_devs[last_dev]);
+        for (i = 1; i < REC_FAILED_NUM; i++) {
+                index = last_dev + REC_FAILED_NUM - i;
+                index %= REC_FAILED_NUM;
+                seq_printf(s, "\t\t\t%-s\n",
+                        suspend_stats.failed_devs[index]);
+        }
+        seq_printf(s,   "  last_failed_errno:\t%-d\n",
+                        suspend_stats.errno[last_errno]);
+        for (i = 1; i < REC_FAILED_NUM; i++) {
+                index = last_errno + REC_FAILED_NUM - i;
+                index %= REC_FAILED_NUM;
+                seq_printf(s, "\t\t\t%-d\n",
+                        suspend_stats.errno[index]);
+        }
+        seq_printf(s,   "  last_failed_step:\t%-s\n",
+                        suspend_step_name(
+                                suspend_stats.failed_steps[last_step]));
+        for (i = 1; i < REC_FAILED_NUM; i++) {
+                index = last_step + REC_FAILED_NUM - i;
+                index %= REC_FAILED_NUM;
+                seq_printf(s, "\t\t\t%-s\n",
+                        suspend_step_name(
+                                suspend_stats.failed_steps[index]));
+        }
+
+        return 0;
+}
+
+static int suspend_stats_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, suspend_stats_show, NULL);
+}
+
+static const struct file_operations suspend_stats_operations = {
+        .open           = suspend_stats_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+};
+
+static int __init pm_debugfs_init(void)
+{
+        debugfs_create_file("suspend_stats", S_IFREG | S_IRUGO,
+                        NULL, NULL, &suspend_stats_operations);
+        return 0;
+}
+
+late_initcall(pm_debugfs_init);
+#endif /* CONFIG_DEBUG_FS */
+
 #endif /* CONFIG_PM_SLEEP */
 
 struct kobject *power_kobj;
@@ -194,6 +291,11 @@ static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr,
         }
         if (state < PM_SUSPEND_MAX && *s)
                 error = enter_state(state);
+                if (error) {
+                        suspend_stats.fail++;
+                        dpm_save_failed_errno(error);
+                } else
+                        suspend_stats.success++;
 #endif
 
  Exit:
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 9a00a0a2628..23a2db1ec44 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -146,6 +146,7 @@ extern int swsusp_swap_in_use(void);
  */
 #define SF_PLATFORM_MODE        1
 #define SF_NOCOMPRESS_MODE      2
+#define SF_CRC32_MODE           4
 
 /* kernel/power/hibernate.c */
 extern int swsusp_check(void);
@@ -228,7 +229,8 @@ extern int pm_test_level;
 #ifdef CONFIG_SUSPEND_FREEZER
 static inline int suspend_freeze_processes(void)
 {
-        return freeze_processes();
+        int error = freeze_processes();
+        return error ? : freeze_kernel_threads();
 }
 
 static inline void suspend_thaw_processes(void)
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 0cf3a27a6c9..addbbe5531b 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -135,7 +135,7 @@ static int try_to_freeze_tasks(bool sig_only)
 }
 
 /**
- *      freeze_processes - tell processes to enter the refrigerator
+ * freeze_processes - Signal user space processes to enter the refrigerator.
  */
 int freeze_processes(void)
 {
@@ -143,20 +143,30 @@ int freeze_processes(void)
 
         printk("Freezing user space processes ... ");
         error = try_to_freeze_tasks(true);
-        if (error)
-                goto Exit;
-        printk("done.\n");
+        if (!error) {
+                printk("done.");
+                oom_killer_disable();
+        }
+        printk("\n");
+        BUG_ON(in_atomic());
+
+        return error;
+}
+
+/**
+ * freeze_kernel_threads - Make freezable kernel threads go to the refrigerator.
+ */
+int freeze_kernel_threads(void)
+{
+        int error;
 
         printk("Freezing remaining freezable tasks ... ");
         error = try_to_freeze_tasks(false);
-        if (error)
-                goto Exit;
-        printk("done.");
+        if (!error)
+                printk("done.");
 
-        oom_killer_disable();
- Exit:
-        BUG_ON(in_atomic());
         printk("\n");
+        BUG_ON(in_atomic());
 
         return error;
 }
diff --git a/kernel/pm_qos_params.c b/kernel/power/qos.c
index 37f05d0f079..1c1797dd1d1 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/power/qos.c
@@ -29,7 +29,7 @@
 
 /*#define DEBUG*/
 
-#include <linux/pm_qos_params.h>
+#include <linux/pm_qos.h>
 #include <linux/sched.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
@@ -45,62 +45,57 @@
 #include <linux/uaccess.h>
 
 /*
- * locking rule: all changes to requests or notifiers lists
+ * locking rule: all changes to constraints or notifiers lists
  * or pm_qos_object list and pm_qos_objects need to happen with pm_qos_lock
  * held, taken with _irqsave.  One lock to rule them all
  */
-enum pm_qos_type {
-        PM_QOS_MAX,             /* return the largest value */
-        PM_QOS_MIN              /* return the smallest value */
-};
-
-/*
- * Note: The lockless read path depends on the CPU accessing
- * target_value atomically.  Atomic access is only guaranteed on all CPU
- * types linux supports for 32 bit quantites
- */
 struct pm_qos_object {
-        struct plist_head requests;
-        struct blocking_notifier_head *notifiers;
+        struct pm_qos_constraints *constraints;
         struct miscdevice pm_qos_power_miscdev;
         char *name;
-        s32 target_value;       /* Do not change to 64 bit */
-        s32 default_value;
-        enum pm_qos_type type;
 };
 
 static DEFINE_SPINLOCK(pm_qos_lock);
 
 static struct pm_qos_object null_pm_qos;
+
 static BLOCKING_NOTIFIER_HEAD(cpu_dma_lat_notifier);
-static struct pm_qos_object cpu_dma_pm_qos = {
-        .requests = PLIST_HEAD_INIT(cpu_dma_pm_qos.requests),
-        .notifiers = &cpu_dma_lat_notifier,
-        .name = "cpu_dma_latency",
+static struct pm_qos_constraints cpu_dma_constraints = {
+        .list = PLIST_HEAD_INIT(cpu_dma_constraints.list),
         .target_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
         .default_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
         .type = PM_QOS_MIN,
+        .notifiers = &cpu_dma_lat_notifier,
+};
+static struct pm_qos_object cpu_dma_pm_qos = {
+        .constraints = &cpu_dma_constraints,
 };
 
 static BLOCKING_NOTIFIER_HEAD(network_lat_notifier);
-static struct pm_qos_object network_lat_pm_qos = {
-        .requests = PLIST_HEAD_INIT(network_lat_pm_qos.requests),
-        .notifiers = &network_lat_notifier,
-        .name = "network_latency",
+static struct pm_qos_constraints network_lat_constraints = {
+        .list = PLIST_HEAD_INIT(network_lat_constraints.list),
         .target_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
         .default_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
-        .type = PM_QOS_MIN
+        .type = PM_QOS_MIN,
+        .notifiers = &network_lat_notifier,
+};
+static struct pm_qos_object network_lat_pm_qos = {
+        .constraints = &network_lat_constraints,
+        .name = "network_latency",
 };
 
 
 static BLOCKING_NOTIFIER_HEAD(network_throughput_notifier);
-static struct pm_qos_object network_throughput_pm_qos = {
-        .requests = PLIST_HEAD_INIT(network_throughput_pm_qos.requests),
-        .notifiers = &network_throughput_notifier,
-        .name = "network_throughput",
+static struct pm_qos_constraints network_tput_constraints = {
+        .list = PLIST_HEAD_INIT(network_tput_constraints.list),
         .target_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
         .default_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
         .type = PM_QOS_MAX,
+        .notifiers = &network_throughput_notifier,
+};
+static struct pm_qos_object network_throughput_pm_qos = {
+        .constraints = &network_tput_constraints,
+        .name = "network_throughput",
 };
 
 
@@ -127,17 +122,17 @@ static const struct file_operations pm_qos_power_fops = {
 };
 
 /* unlocked internal variant */
-static inline int pm_qos_get_value(struct pm_qos_object *o)
+static inline int pm_qos_get_value(struct pm_qos_constraints *c)
 {
-        if (plist_head_empty(&o->requests))
-                return o->default_value;
+        if (plist_head_empty(&c->list))
+                return c->default_value;
 
-        switch (o->type) {
+        switch (c->type) {
         case PM_QOS_MIN:
-                return plist_first(&o->requests)->prio;
+                return plist_first(&c->list)->prio;
 
         case PM_QOS_MAX:
-                return plist_last(&o->requests)->prio;
+                return plist_last(&c->list)->prio;
 
         default:
                 /* runtime check for not using enum */
@@ -145,69 +140,73 @@ static inline int pm_qos_get_value(struct pm_qos_object *o)
         }
 }
 
-static inline s32 pm_qos_read_value(struct pm_qos_object *o)
+s32 pm_qos_read_value(struct pm_qos_constraints *c)
 {
-        return o->target_value;
+        return c->target_value;
 }
 
-static inline void pm_qos_set_value(struct pm_qos_object *o, s32 value)
+static inline void pm_qos_set_value(struct pm_qos_constraints *c, s32 value)
 {
-        o->target_value = value;
+        c->target_value = value;
 }
 
-static void update_target(struct pm_qos_object *o, struct plist_node *node,
-                          int del, int value)
+/**
+ * pm_qos_update_target - manages the constraints list and calls the notifiers
+ *  if needed
+ * @c: constraints data struct
+ * @node: request to add to the list, to update or to remove
+ * @action: action to take on the constraints list
+ * @value: value of the request to add or update
+ *
+ * This function returns 1 if the aggregated constraint value has changed, 0
+ *  otherwise.
+ */
+int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node,
+                         enum pm_qos_req_action action, int value)
 {
         unsigned long flags;
-        int prev_value, curr_value;
+        int prev_value, curr_value, new_value;
 
         spin_lock_irqsave(&pm_qos_lock, flags);
-        prev_value = pm_qos_get_value(o);
-        /* PM_QOS_DEFAULT_VALUE is a signal that the value is unchanged */
-        if (value != PM_QOS_DEFAULT_VALUE) {
+        prev_value = pm_qos_get_value(c);
+        if (value == PM_QOS_DEFAULT_VALUE)
+                new_value = c->default_value;
+        else
+                new_value = value;
+
+        switch (action) {
+        case PM_QOS_REMOVE_REQ:
+                plist_del(node, &c->list);
+                break;
+        case PM_QOS_UPDATE_REQ:
                 /*
                  * to change the list, we atomically remove, reinit
                  * with new value and add, then see if the extremal
                  * changed
                  */
-                plist_del(node, &o->requests);
-                plist_node_init(node, value);
-                plist_add(node, &o->requests);
-        } else if (del) {
-                plist_del(node, &o->requests);
-        } else {
-                plist_add(node, &o->requests);
+                plist_del(node, &c->list);
+        case PM_QOS_ADD_REQ:
+                plist_node_init(node, new_value);
+                plist_add(node, &c->list);
+                break;
+        default:
+                /* no action */
+                ;
         }
-        curr_value = pm_qos_get_value(o);
-        pm_qos_set_value(o, curr_value);
+
+        curr_value = pm_qos_get_value(c);
+        pm_qos_set_value(c, curr_value);
+
         spin_unlock_irqrestore(&pm_qos_lock, flags);
 
-        if (prev_value != curr_value)
-                blocking_notifier_call_chain(o->notifiers,
+        if (prev_value != curr_value) {
+                blocking_notifier_call_chain(c->notifiers,
                                              (unsigned long)curr_value,
                                              NULL);
-}
-
-static int register_pm_qos_misc(struct pm_qos_object *qos)
-{
-        qos->pm_qos_power_miscdev.minor = MISC_DYNAMIC_MINOR;
-        qos->pm_qos_power_miscdev.name = qos->name;
-        qos->pm_qos_power_miscdev.fops = &pm_qos_power_fops;
-
-        return misc_register(&qos->pm_qos_power_miscdev);
-}
-
-static int find_pm_qos_object_by_minor(int minor)
-{
-        int pm_qos_class;
-
-        for (pm_qos_class = 0;
-                pm_qos_class < PM_QOS_NUM_CLASSES; pm_qos_class++) {
-                if (minor ==
-                        pm_qos_array[pm_qos_class]->pm_qos_power_miscdev.minor)
-                        return pm_qos_class;
+                return 1;
+        } else {
+                return 0;
         }
-        return -1;
 }
 
 /**
@@ -218,11 +217,11 @@ static int find_pm_qos_object_by_minor(int minor)
  */
 int pm_qos_request(int pm_qos_class)
 {
-        return pm_qos_read_value(pm_qos_array[pm_qos_class]);
+        return pm_qos_read_value(pm_qos_array[pm_qos_class]->constraints);
 }
 EXPORT_SYMBOL_GPL(pm_qos_request);
 
-int pm_qos_request_active(struct pm_qos_request_list *req)
+int pm_qos_request_active(struct pm_qos_request *req)
 {
         return req->pm_qos_class != 0;
 }
@@ -230,40 +229,36 @@ EXPORT_SYMBOL_GPL(pm_qos_request_active);
 
 /**
  * pm_qos_add_request - inserts new qos request into the list
- * @dep: pointer to a preallocated handle
+ * @req: pointer to a preallocated handle
  * @pm_qos_class: identifies which list of qos request to use
  * @value: defines the qos request
  *
  * This function inserts a new entry in the pm_qos_class list of requested qos
  * performance characteristics.  It recomputes the aggregate QoS expectations
- * for the pm_qos_class of parameters and initializes the pm_qos_request_list
+ * for the pm_qos_class of parameters and initializes the pm_qos_request
  * handle.  Caller needs to save this handle for later use in updates and
  * removal.
  */
 
-void pm_qos_add_request(struct pm_qos_request_list *dep,
+void pm_qos_add_request(struct pm_qos_request *req,
                         int pm_qos_class, s32 value)
 {
-        struct pm_qos_object *o =  pm_qos_array[pm_qos_class];
-        int new_value;
+        if (!req) /*guard against callers passing in null */
+                return;
 
-        if (pm_qos_request_active(dep)) {
+        if (pm_qos_request_active(req)) {
                 WARN(1, KERN_ERR "pm_qos_add_request() called for already added request\n");
                 return;
         }
-        if (value == PM_QOS_DEFAULT_VALUE)
-                new_value = o->default_value;
-        else
-                new_value = value;
-        plist_node_init(&dep->list, new_value);
-        dep->pm_qos_class = pm_qos_class;
-        update_target(o, &dep->list, 0, PM_QOS_DEFAULT_VALUE);
+        req->pm_qos_class = pm_qos_class;
+        pm_qos_update_target(pm_qos_array[pm_qos_class]->constraints,
+                             &req->node, PM_QOS_ADD_REQ, value);
 }
 EXPORT_SYMBOL_GPL(pm_qos_add_request);
 
 /**
  * pm_qos_update_request - modifies an existing qos request
- * @pm_qos_req : handle to list element holding a pm_qos request to use
+ * @req : handle to list element holding a pm_qos request to use
  * @value: defines the qos request
  *
  * Updates an existing qos request for the pm_qos_class of parameters along
@@ -271,56 +266,47 @@ EXPORT_SYMBOL_GPL(pm_qos_add_request);
  *
  * Attempts are made to make this code callable on hot code paths.
  */
-void pm_qos_update_request(struct pm_qos_request_list *pm_qos_req,
+void pm_qos_update_request(struct pm_qos_request *req,
                            s32 new_value)
 {
-        s32 temp;
-        struct pm_qos_object *o;
-
-        if (!pm_qos_req) /*guard against callers passing in null */
+        if (!req) /*guard against callers passing in null */
                 return;
 
-        if (!pm_qos_request_active(pm_qos_req)) {
+        if (!pm_qos_request_active(req)) {
                 WARN(1, KERN_ERR "pm_qos_update_request() called for unknown object\n");
                 return;
         }
 
-        o = pm_qos_array[pm_qos_req->pm_qos_class];
-
-        if (new_value == PM_QOS_DEFAULT_VALUE)
-                temp = o->default_value;
-        else
-                temp = new_value;
-
-        if (temp != pm_qos_req->list.prio)
-                update_target(o, &pm_qos_req->list, 0, temp);
+        if (new_value != req->node.prio)
+                pm_qos_update_target(
+                        pm_qos_array[req->pm_qos_class]->constraints,
+                        &req->node, PM_QOS_UPDATE_REQ, new_value);
 }
 EXPORT_SYMBOL_GPL(pm_qos_update_request);
 
 /**
  * pm_qos_remove_request - modifies an existing qos request
- * @pm_qos_req: handle to request list element
+ * @req: handle to request list element
  *
- * Will remove pm qos request from the list of requests and
+ * Will remove pm qos request from the list of constraints and
  * recompute the current target value for the pm_qos_class.  Call this
  * on slow code paths.
  */
-void pm_qos_remove_request(struct pm_qos_request_list *pm_qos_req)
+void pm_qos_remove_request(struct pm_qos_request *req)
 {
-        struct pm_qos_object *o;
-
-        if (pm_qos_req == NULL)
+        if (!req) /*guard against callers passing in null */
                 return;
                 /* silent return to keep pcm code cleaner */
 
-        if (!pm_qos_request_active(pm_qos_req)) {
+        if (!pm_qos_request_active(req)) {
                 WARN(1, KERN_ERR "pm_qos_remove_request() called for unknown object\n");
                 return;
         }
 
-        o = pm_qos_array[pm_qos_req->pm_qos_class];
-        update_target(o, &pm_qos_req->list, 1, PM_QOS_DEFAULT_VALUE);
-        memset(pm_qos_req, 0, sizeof(*pm_qos_req));
+        pm_qos_update_target(pm_qos_array[req->pm_qos_class]->constraints,
+                             &req->node, PM_QOS_REMOVE_REQ,
+                             PM_QOS_DEFAULT_VALUE);
+        memset(req, 0, sizeof(*req));
 }
 EXPORT_SYMBOL_GPL(pm_qos_remove_request);
 
@@ -337,7 +323,8 @@ int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier)
         int retval;
 
         retval = blocking_notifier_chain_register(
-                        pm_qos_array[pm_qos_class]->notifiers, notifier);
+                        pm_qos_array[pm_qos_class]->constraints->notifiers,
+                        notifier);
 
         return retval;
 }
@@ -356,19 +343,43 @@ int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier)
         int retval;
 
         retval = blocking_notifier_chain_unregister(
-                        pm_qos_array[pm_qos_class]->notifiers, notifier);
+                        pm_qos_array[pm_qos_class]->constraints->notifiers,
+                        notifier);
 
         return retval;
 }
 EXPORT_SYMBOL_GPL(pm_qos_remove_notifier);
 
+/* User space interface to PM QoS classes via misc devices */
+static int register_pm_qos_misc(struct pm_qos_object *qos)
+{
+        qos->pm_qos_power_miscdev.minor = MISC_DYNAMIC_MINOR;
+        qos->pm_qos_power_miscdev.name = qos->name;
+        qos->pm_qos_power_miscdev.fops = &pm_qos_power_fops;
+
+        return misc_register(&qos->pm_qos_power_miscdev);
+}
+
+static int find_pm_qos_object_by_minor(int minor)
+{
+        int pm_qos_class;
+
+        for (pm_qos_class = 0;
+                pm_qos_class < PM_QOS_NUM_CLASSES; pm_qos_class++) {
+                if (minor ==
+                        pm_qos_array[pm_qos_class]->pm_qos_power_miscdev.minor)
+                        return pm_qos_class;
+        }
+        return -1;
+}
+
 static int pm_qos_power_open(struct inode *inode, struct file *filp)
 {
         long pm_qos_class;
 
         pm_qos_class = find_pm_qos_object_by_minor(iminor(inode));
         if (pm_qos_class >= 0) {
-               struct pm_qos_request_list *req = kzalloc(sizeof(*req), GFP_KERNEL);
+                struct pm_qos_request *req = kzalloc(sizeof(*req), GFP_KERNEL);
                 if (!req)
                         return -ENOMEM;
 
@@ -383,7 +394,7 @@ static int pm_qos_power_open(struct inode *inode, struct file *filp)
 
 static int pm_qos_power_release(struct inode *inode, struct file *filp)
 {
-        struct pm_qos_request_list *req;
+        struct pm_qos_request *req;
 
         req = filp->private_data;
         pm_qos_remove_request(req);
@@ -398,17 +409,15 @@ static ssize_t pm_qos_power_read(struct file *filp, char __user *buf,
 {
         s32 value;
         unsigned long flags;
-        struct pm_qos_object *o;
-        struct pm_qos_request_list *pm_qos_req = filp->private_data;
+        struct pm_qos_request *req = filp->private_data;
 
-        if (!pm_qos_req)
+        if (!req)
                 return -EINVAL;
-        if (!pm_qos_request_active(pm_qos_req))
+        if (!pm_qos_request_active(req))
                 return -EINVAL;
 
-        o = pm_qos_array[pm_qos_req->pm_qos_class];
         spin_lock_irqsave(&pm_qos_lock, flags);
-        value = pm_qos_get_value(o);
+        value = pm_qos_get_value(pm_qos_array[req->pm_qos_class]->constraints);
         spin_unlock_irqrestore(&pm_qos_lock, flags);
 
         return simple_read_from_buffer(buf, count, f_pos, &value, sizeof(s32));
@@ -418,7 +427,7 @@ static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
                 size_t count, loff_t *f_pos)
 {
         s32 value;
-        struct pm_qos_request_list *pm_qos_req;
+        struct pm_qos_request *req;
 
         if (count == sizeof(s32)) {
                 if (copy_from_user(&value, buf, sizeof(s32)))
@@ -449,8 +458,8 @@ static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
                 return -EINVAL;
         }
 
-        pm_qos_req = filp->private_data;
-        pm_qos_update_request(pm_qos_req, value);
+        req = filp->private_data;
+        pm_qos_update_request(req, value);
 
         return count;
 }
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 06efa54f93d..cbe2c144139 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1339,6 +1339,9 @@ int hibernate_preallocate_memory(void)
         count += highmem;
         count -= totalreserve_pages;
 
+        /* Add number of pages required for page keys (s390 only). */
+        size += page_key_additional_pages(saveable);
+
         /* Compute the maximum number of saveable pages to leave in memory. */
         max_size = (count - (size + PAGES_FOR_IO)) / 2
                         - 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE);
@@ -1662,6 +1665,8 @@ pack_pfns(unsigned long *buf, struct memory_bitmap *bm)
                 buf[j] = memory_bm_next_pfn(bm);
                 if (unlikely(buf[j] == BM_END_OF_MAP))
                         break;
+                /* Save page key for data page (s390 only). */
+                page_key_read(buf + j);
         }
 }
 
@@ -1821,6 +1826,9 @@ static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm)
                 if (unlikely(buf[j] == BM_END_OF_MAP))
                         break;
 
+                /* Extract and buffer page key for data page (s390 only). */
+                page_key_memorize(buf + j);
+
                 if (memory_bm_pfn_present(bm, buf[j]))
                         memory_bm_set_bit(bm, buf[j]);
                 else
@@ -2223,6 +2231,11 @@ int snapshot_write_next(struct snapshot_handle *handle)
                 if (error)
                         return error;
 
+                /* Allocate buffer for page keys. */
+                error = page_key_alloc(nr_copy_pages);
+                if (error)
+                        return error;
+
         } else if (handle->cur <= nr_meta_pages + 1) {
                 error = unpack_orig_pfns(buffer, &copy_bm);
                 if (error)
@@ -2243,6 +2256,8 @@ int snapshot_write_next(struct snapshot_handle *handle)
                 }
         } else {
                 copy_last_highmem_page();
+                /* Restore page key for data page (s390 only). */
+                page_key_write(handle->buffer);
                 handle->buffer = get_buffer(&orig_bm, &ca);
                 if (IS_ERR(handle->buffer))
                         return PTR_ERR(handle->buffer);
@@ -2264,6 +2279,9 @@ int snapshot_write_next(struct snapshot_handle *handle)
 void snapshot_write_finalize(struct snapshot_handle *handle)
 {
         copy_last_highmem_page();
+        /* Restore page key for data page (s390 only). */
+        page_key_write(handle->buffer);
+        page_key_free();
         /* Free only if we have loaded the image entirely */
         if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages) {
                 memory_bm_free(&orig_bm, PG_UNSAFE_CLEAR);
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index b6b71ad2208..fdd4263b995 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -104,7 +104,10 @@ static int suspend_prepare(void)
                 goto Finish;
 
         error = suspend_freeze_processes();
-        if (!error)
+        if (error) {
+                suspend_stats.failed_freeze++;
+                dpm_save_failed_step(SUSPEND_FREEZE);
+        } else
                 return 0;
 
         suspend_thaw_processes();
@@ -315,8 +318,16 @@ int enter_state(suspend_state_t state)
  */
 int pm_suspend(suspend_state_t state)
 {
-        if (state > PM_SUSPEND_ON && state <= PM_SUSPEND_MAX)
-                return enter_state(state);
+        int ret;
+        if (state > PM_SUSPEND_ON && state < PM_SUSPEND_MAX) {
+                ret = enter_state(state);
+                if (ret) {
+                        suspend_stats.fail++;
+                        dpm_save_failed_errno(ret);
+                } else
+                        suspend_stats.success++;
+                return ret;
+        }
         return -EINVAL;
 }
 EXPORT_SYMBOL(pm_suspend);
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 7c97c3a0eee..11a594c4ba2 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -27,6 +27,10 @@
 #include <linux/slab.h>
 #include <linux/lzo.h>
 #include <linux/vmalloc.h>
+#include <linux/cpumask.h>
+#include <linux/atomic.h>
+#include <linux/kthread.h>
+#include <linux/crc32.h>
 
 #include "power.h"
 
@@ -43,8 +47,7 @@
  *      allocated and populated one at a time, so we only need one memory
  *      page to set up the entire structure.
  *
- *      During resume we also only need to use one swap_map_page structure
- *      at a time.
+ *      During resume we pick up all swap_map_page structures into a list.
  */
 
 #define MAP_PAGE_ENTRIES        (PAGE_SIZE / sizeof(sector_t) - 1)
@@ -54,6 +57,11 @@ struct swap_map_page {
         sector_t next_swap;
 };
 
+struct swap_map_page_list {
+        struct swap_map_page *map;
+        struct swap_map_page_list *next;
+};
+
 /**
  *      The swap_map_handle structure is used for handling swap in
  *      a file-alike way
@@ -61,13 +69,18 @@ struct swap_map_page {
 
 struct swap_map_handle {
         struct swap_map_page *cur;
+        struct swap_map_page_list *maps;
         sector_t cur_swap;
         sector_t first_sector;
         unsigned int k;
+        unsigned long nr_free_pages, written;
+        u32 crc32;
 };
 
 struct swsusp_header {
-        char reserved[PAGE_SIZE - 20 - sizeof(sector_t) - sizeof(int)];
+        char reserved[PAGE_SIZE - 20 - sizeof(sector_t) - sizeof(int) -
+                      sizeof(u32)];
+        u32     crc32;
         sector_t image;
         unsigned int flags;     /* Flags to pass to the "boot" kernel */
         char    orig_sig[10];
@@ -199,6 +212,8 @@ static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags)
                 memcpy(swsusp_header->sig, HIBERNATE_SIG, 10);
                 swsusp_header->image = handle->first_sector;
                 swsusp_header->flags = flags;
+                if (flags & SF_CRC32_MODE)
+                        swsusp_header->crc32 = handle->crc32;
                 error = hib_bio_write_page(swsusp_resume_block,
                                         swsusp_header, NULL);
         } else {
@@ -245,6 +260,7 @@ static int swsusp_swap_check(void)
 static int write_page(void *buf, sector_t offset, struct bio **bio_chain)
 {
         void *src;
+        int ret;
 
         if (!offset)
                 return -ENOSPC;
@@ -254,9 +270,17 @@ static int write_page(void *buf, sector_t offset, struct bio **bio_chain)
                 if (src) {
                         copy_page(src, buf);
                 } else {
-                        WARN_ON_ONCE(1);
-                        bio_chain = NULL;       /* Go synchronous */
-                        src = buf;
+                        ret = hib_wait_on_bio_chain(bio_chain); /* Free pages */
+                        if (ret)
+                                return ret;
+                        src = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
+                        if (src) {
+                                copy_page(src, buf);
+                        } else {
+                                WARN_ON_ONCE(1);
+                                bio_chain = NULL;       /* Go synchronous */
+                                src = buf;
+                        }
                 }
         } else {
                 src = buf;
@@ -293,6 +317,8 @@ static int get_swap_writer(struct swap_map_handle *handle)
                 goto err_rel;
         }
         handle->k = 0;
+        handle->nr_free_pages = nr_free_pages() >> 1;
+        handle->written = 0;
         handle->first_sector = handle->cur_swap;
         return 0;
 err_rel:
@@ -316,20 +342,23 @@ static int swap_write_page(struct swap_map_handle *handle, void *buf,
                 return error;
         handle->cur->entries[handle->k++] = offset;
         if (handle->k >= MAP_PAGE_ENTRIES) {
-                error = hib_wait_on_bio_chain(bio_chain);
-                if (error)
-                        goto out;
                 offset = alloc_swapdev_block(root_swap);
                 if (!offset)
                         return -ENOSPC;
                 handle->cur->next_swap = offset;
-                error = write_page(handle->cur, handle->cur_swap, NULL);
+                error = write_page(handle->cur, handle->cur_swap, bio_chain);
                 if (error)
                         goto out;
                 clear_page(handle->cur);
                 handle->cur_swap = offset;
                 handle->k = 0;
         }
+        if (bio_chain && ++handle->written > handle->nr_free_pages) {
+                error = hib_wait_on_bio_chain(bio_chain);
+                if (error)
+                        goto out;
+                handle->written = 0;
+        }
  out:
         return error;
 }
@@ -372,6 +401,13 @@ static int swap_writer_finish(struct swap_map_handle *handle,
                                      LZO_HEADER, PAGE_SIZE)
 #define LZO_CMP_SIZE    (LZO_CMP_PAGES * PAGE_SIZE)
 
+/* Maximum number of threads for compression/decompression. */
+#define LZO_THREADS     3
+
+/* Maximum number of pages for read buffering. */
+#define LZO_READ_PAGES  (MAP_PAGE_ENTRIES * 8)
+
+
 /**
  *      save_image - save the suspend image data
  */
@@ -419,6 +455,92 @@ static int save_image(struct swap_map_handle *handle,
         return ret;
 }
 
+/**
+ * Structure used for CRC32.
+ */
+struct crc_data {
+        struct task_struct *thr;                  /* thread */
+        atomic_t ready;                           /* ready to start flag */
+        atomic_t stop;                            /* ready to stop flag */
+        unsigned run_threads;                     /* nr current threads */
+        wait_queue_head_t go;                     /* start crc update */
+        wait_queue_head_t done;                   /* crc update done */
+        u32 *crc32;                               /* points to handle's crc32 */
+        size_t *unc_len[LZO_THREADS];             /* uncompressed lengths */
+        unsigned char *unc[LZO_THREADS];          /* uncompressed data */
+};
+
+/**
+ * CRC32 update function that runs in its own thread.
+ */
+static int crc32_threadfn(void *data)
+{
+        struct crc_data *d = data;
+        unsigned i;
+
+        while (1) {
+                wait_event(d->go, atomic_read(&d->ready) ||
+                                  kthread_should_stop());
+                if (kthread_should_stop()) {
+                        d->thr = NULL;
+                        atomic_set(&d->stop, 1);
+                        wake_up(&d->done);
+                        break;
+                }
+                atomic_set(&d->ready, 0);
+
+                for (i = 0; i < d->run_threads; i++)
+                        *d->crc32 = crc32_le(*d->crc32,
+                                             d->unc[i], *d->unc_len[i]);
+                atomic_set(&d->stop, 1);
+                wake_up(&d->done);
+        }
+        return 0;
+}
+/**
+ * Structure used for LZO data compression.
+ */
+struct cmp_data {
+        struct task_struct *thr;                  /* thread */
+        atomic_t ready;                           /* ready to start flag */
+        atomic_t stop;                            /* ready to stop flag */
+        int ret;                                  /* return code */
+        wait_queue_head_t go;                     /* start compression */
+        wait_queue_head_t done;                   /* compression done */
+        size_t unc_len;                           /* uncompressed length */
+        size_t cmp_len;                           /* compressed length */
+        unsigned char unc[LZO_UNC_SIZE];          /* uncompressed buffer */
+        unsigned char cmp[LZO_CMP_SIZE];          /* compressed buffer */
+        unsigned char wrk[LZO1X_1_MEM_COMPRESS];  /* compression workspace */
+};
+
+/**
+ * Compression function that runs in its own thread.
+ */
+static int lzo_compress_threadfn(void *data)
+{
+        struct cmp_data *d = data;
+
+        while (1) {
+                wait_event(d->go, atomic_read(&d->ready) ||
+                                  kthread_should_stop());
+                if (kthread_should_stop()) {
+                        d->thr = NULL;
+                        d->ret = -1;
+                        atomic_set(&d->stop, 1);
+                        wake_up(&d->done);
+                        break;
+                }
+                atomic_set(&d->ready, 0);
+
+                d->ret = lzo1x_1_compress(d->unc, d->unc_len,
+                                          d->cmp + LZO_HEADER, &d->cmp_len,
+                                          d->wrk);
+                atomic_set(&d->stop, 1);
+                wake_up(&d->done);
+        }
+        return 0;
+}
 
 /**
  * save_image_lzo - Save the suspend image data compressed with LZO.
@@ -437,42 +559,93 @@ static int save_image_lzo(struct swap_map_handle *handle,
         struct bio *bio;
         struct timeval start;
         struct timeval stop;
-        size_t off, unc_len, cmp_len;
-        unsigned char *unc, *cmp, *wrk, *page;
+        size_t off;
+        unsigned thr, run_threads, nr_threads;
+        unsigned char *page = NULL;
+        struct cmp_data *data = NULL;
+        struct crc_data *crc = NULL;
+
+        /*
+         * We'll limit the number of threads for compression to limit memory
+         * footprint.
+         */
+        nr_threads = num_online_cpus() - 1;
+        nr_threads = clamp_val(nr_threads, 1, LZO_THREADS);
 
         page = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
         if (!page) {
                 printk(KERN_ERR "PM: Failed to allocate LZO page\n");
-                return -ENOMEM;
+                ret = -ENOMEM;
+                goto out_clean;
         }
 
-        wrk = vmalloc(LZO1X_1_MEM_COMPRESS);
-        if (!wrk) {
-                printk(KERN_ERR "PM: Failed to allocate LZO workspace\n");
-                free_page((unsigned long)page);
-                return -ENOMEM;
+        data = vmalloc(sizeof(*data) * nr_threads);
+        if (!data) {
+                printk(KERN_ERR "PM: Failed to allocate LZO data\n");
+                ret = -ENOMEM;
+                goto out_clean;
         }
+        for (thr = 0; thr < nr_threads; thr++)
+                memset(&data[thr], 0, offsetof(struct cmp_data, go));
 
-        unc = vmalloc(LZO_UNC_SIZE);
-        if (!unc) {
-                printk(KERN_ERR "PM: Failed to allocate LZO uncompressed\n");
-                vfree(wrk);
-                free_page((unsigned long)page);
-                return -ENOMEM;
+        crc = kmalloc(sizeof(*crc), GFP_KERNEL);
+        if (!crc) {
+                printk(KERN_ERR "PM: Failed to allocate crc\n");
+                ret = -ENOMEM;
+                goto out_clean;
+        }
+        memset(crc, 0, offsetof(struct crc_data, go));
+
+        /*
+         * Start the compression threads.
+         */
+        for (thr = 0; thr < nr_threads; thr++) {
+                init_waitqueue_head(&data[thr].go);
+                init_waitqueue_head(&data[thr].done);
+
+                data[thr].thr = kthread_run(lzo_compress_threadfn,
+                                            &data[thr],
+                                            "image_compress/%u", thr);
+                if (IS_ERR(data[thr].thr)) {
+                        data[thr].thr = NULL;
+                        printk(KERN_ERR
+                               "PM: Cannot start compression threads\n");
+                        ret = -ENOMEM;
+                        goto out_clean;
+                }
         }
 
-        cmp = vmalloc(LZO_CMP_SIZE);
-        if (!cmp) {
-                printk(KERN_ERR "PM: Failed to allocate LZO compressed\n");
-                vfree(unc);
-                vfree(wrk);
-                free_page((unsigned long)page);
-                return -ENOMEM;
+        /*
+         * Adjust number of free pages after all allocations have been done.
+         * We don't want to run out of pages when writing.
+         */
+        handle->nr_free_pages = nr_free_pages() >> 1;
+
+        /*
+         * Start the CRC32 thread.
+         */
+        init_waitqueue_head(&crc->go);
+        init_waitqueue_head(&crc->done);
+
+        handle->crc32 = 0;
+        crc->crc32 = &handle->crc32;
+        for (thr = 0; thr < nr_threads; thr++) {
+                crc->unc[thr] = data[thr].unc;
+                crc->unc_len[thr] = &data[thr].unc_len;
+        }
+
+        crc->thr = kthread_run(crc32_threadfn, crc, "image_crc32");
+        if (IS_ERR(crc->thr)) {
+                crc->thr = NULL;
+                printk(KERN_ERR "PM: Cannot start CRC32 thread\n");
+                ret = -ENOMEM;
+                goto out_clean;
         }
 
         printk(KERN_INFO
+                "PM: Using %u thread(s) for compression.\n"
                 "PM: Compressing and saving image data (%u pages) ...     ",
-                nr_to_write);
+                nr_threads, nr_to_write);
         m = nr_to_write / 100;
         if (!m)
                 m = 1;
@@ -480,55 +653,83 @@ static int save_image_lzo(struct swap_map_handle *handle,
         bio = NULL;
         do_gettimeofday(&start);
         for (;;) {
-                for (off = 0; off < LZO_UNC_SIZE; off += PAGE_SIZE) {
-                        ret = snapshot_read_next(snapshot);
-                        if (ret < 0)
-                                goto out_finish;
-
-                        if (!ret)
+                for (thr = 0; thr < nr_threads; thr++) {
+                        for (off = 0; off < LZO_UNC_SIZE; off += PAGE_SIZE) {
+                                ret = snapshot_read_next(snapshot);
+                                if (ret < 0)
+                                        goto out_finish;
+
+                                if (!ret)
+                                        break;
+
+                                memcpy(data[thr].unc + off,
+                                       data_of(*snapshot), PAGE_SIZE);
+
+                                if (!(nr_pages % m))
+                                        printk(KERN_CONT "\b\b\b\b%3d%%",
+                                               nr_pages / m);
+                                nr_pages++;
+                        }
+                        if (!off)
                                 break;
 
-                        memcpy(unc + off, data_of(*snapshot), PAGE_SIZE);
+                        data[thr].unc_len = off;
 
-                        if (!(nr_pages % m))
-                                printk(KERN_CONT "\b\b\b\b%3d%%", nr_pages / m);
-                        nr_pages++;
+                        atomic_set(&data[thr].ready, 1);
+                        wake_up(&data[thr].go);
                 }
 
-                if (!off)
+                if (!thr)
                         break;
 
-                unc_len = off;
-                ret = lzo1x_1_compress(unc, unc_len,
-                                       cmp + LZO_HEADER, &cmp_len, wrk);
-                if (ret < 0) {
-                        printk(KERN_ERR "PM: LZO compression failed\n");
-                        break;
-                }
+                crc->run_threads = thr;
+                atomic_set(&crc->ready, 1);
+                wake_up(&crc->go);
 
-                if (unlikely(!cmp_len ||
-                             cmp_len > lzo1x_worst_compress(unc_len))) {
-                        printk(KERN_ERR "PM: Invalid LZO compressed length\n");
-                        ret = -1;
-                        break;
-                }
+                for (run_threads = thr, thr = 0; thr < run_threads; thr++) {
+                        wait_event(data[thr].done,
+                                   atomic_read(&data[thr].stop));
+                        atomic_set(&data[thr].stop, 0);
 
-                *(size_t *)cmp = cmp_len;
+                        ret = data[thr].ret;
 
-                /*
-                 * Given we are writing one page at a time to disk, we copy
-                 * that much from the buffer, although the last bit will likely
-                 * be smaller than full page. This is OK - we saved the length
-                 * of the compressed data, so any garbage at the end will be
-                 * discarded when we read it.
-                 */
-                for (off = 0; off < LZO_HEADER + cmp_len; off += PAGE_SIZE) {
-                        memcpy(page, cmp + off, PAGE_SIZE);
+                        if (ret < 0) {
+                                printk(KERN_ERR "PM: LZO compression failed\n");
+                                goto out_finish;
+                        }
 
-                        ret = swap_write_page(handle, page, &bio);
-                        if (ret)
+                        if (unlikely(!data[thr].cmp_len ||
+                                     data[thr].cmp_len >
+                                     lzo1x_worst_compress(data[thr].unc_len))) {
+                                printk(KERN_ERR
+                                       "PM: Invalid LZO compressed length\n");
+                                ret = -1;
                                 goto out_finish;
+                        }
+
+                        *(size_t *)data[thr].cmp = data[thr].cmp_len;
+
+                        /*
+                         * Given we are writing one page at a time to disk, we
+                         * copy that much from the buffer, although the last
+                         * bit will likely be smaller than full page. This is
+                         * OK - we saved the length of the compressed data, so
+                         * any garbage at the end will be discarded when we
+                         * read it.
+                         */
+                        for (off = 0;
+                             off < LZO_HEADER + data[thr].cmp_len;
+                             off += PAGE_SIZE) {
+                                memcpy(page, data[thr].cmp + off, PAGE_SIZE);
+
+                                ret = swap_write_page(handle, page, &bio);
+                                if (ret)
+                                        goto out_finish;
+                        }
                 }
+
+                wait_event(crc->done, atomic_read(&crc->stop));
+                atomic_set(&crc->stop, 0);
         }
 
 out_finish:
@@ -536,16 +737,25 @@ out_finish:
         do_gettimeofday(&stop);
         if (!ret)
                 ret = err2;
-        if (!ret)
+        if (!ret) {
                 printk(KERN_CONT "\b\b\b\bdone\n");
-        else
+        } else {
                 printk(KERN_CONT "\n");
+        }
         swsusp_show_speed(&start, &stop, nr_to_write, "Wrote");
-
-        vfree(cmp);
-        vfree(unc);
-        vfree(wrk);
-        free_page((unsigned long)page);
+out_clean:
+        if (crc) {
+                if (crc->thr)
+                        kthread_stop(crc->thr);
+                kfree(crc);
+        }
+        if (data) {
+                for (thr = 0; thr < nr_threads; thr++)
+                        if (data[thr].thr)
+                                kthread_stop(data[thr].thr);
+                vfree(data);
+        }
+        if (page) free_page((unsigned long)page);
 
         return ret;
 }
@@ -625,8 +835,15 @@ out_finish:
 
 static void release_swap_reader(struct swap_map_handle *handle)
 {
-        if (handle->cur)
-                free_page((unsigned long)handle->cur);
+        struct swap_map_page_list *tmp;
+
+        while (handle->maps) {
+                if (handle->maps->map)
+                        free_page((unsigned long)handle->maps->map);
+                tmp = handle->maps;
+                handle->maps = handle->maps->next;
+                kfree(tmp);
+        }
         handle->cur = NULL;
 }
 
@@ -634,22 +851,46 @@ static int get_swap_reader(struct swap_map_handle *handle,
                 unsigned int *flags_p)
 {
         int error;
+        struct swap_map_page_list *tmp, *last;
+        sector_t offset;
 
         *flags_p = swsusp_header->flags;
 
         if (!swsusp_header->image) /* how can this happen? */
                 return -EINVAL;
 
-        handle->cur = (struct swap_map_page *)get_zeroed_page(__GFP_WAIT | __GFP_HIGH);
-        if (!handle->cur)
-                return -ENOMEM;
+        handle->cur = NULL;
+        last = handle->maps = NULL;
+        offset = swsusp_header->image;
+        while (offset) {
+                tmp = kmalloc(sizeof(*handle->maps), GFP_KERNEL);
+                if (!tmp) {
+                        release_swap_reader(handle);
+                        return -ENOMEM;
+                }
+                memset(tmp, 0, sizeof(*tmp));
+                if (!handle->maps)
+                        handle->maps = tmp;
+                if (last)
+                        last->next = tmp;
+                last = tmp;
+
+                tmp->map = (struct swap_map_page *)
+                           __get_free_page(__GFP_WAIT | __GFP_HIGH);
+                if (!tmp->map) {
+                        release_swap_reader(handle);
+                        return -ENOMEM;
+                }
 
-        error = hib_bio_read_page(swsusp_header->image, handle->cur, NULL);
-        if (error) {
-                release_swap_reader(handle);
-                return error;
+                error = hib_bio_read_page(offset, tmp->map, NULL);
+                if (error) {
+                        release_swap_reader(handle);
+                        return error;
+                }
+                offset = tmp->map->next_swap;
         }
         handle->k = 0;
+        handle->cur = handle->maps->map;
         return 0;
 }
 
@@ -658,6 +899,7 @@ static int swap_read_page(struct swap_map_handle *handle, void *buf,
 {
         sector_t offset;
         int error;
+        struct swap_map_page_list *tmp;
 
         if (!handle->cur)
                 return -EINVAL;
@@ -668,13 +910,15 @@ static int swap_read_page(struct swap_map_handle *handle, void *buf,
         if (error)
                 return error;
         if (++handle->k >= MAP_PAGE_ENTRIES) {
-                error = hib_wait_on_bio_chain(bio_chain);
                 handle->k = 0;
-                offset = handle->cur->next_swap;
-                if (!offset)
+                free_page((unsigned long)handle->maps->map);
+                tmp = handle->maps;
+                handle->maps = handle->maps->next;
+                kfree(tmp);
+                if (!handle->maps)
                         release_swap_reader(handle);
-                else if (!error)
-                        error = hib_bio_read_page(offset, handle->cur, NULL);
+                else
+                        handle->cur = handle->maps->map;
         }
         return error;
 }
@@ -697,7 +941,7 @@ static int load_image(struct swap_map_handle *handle,
                       unsigned int nr_to_read)
 {
         unsigned int m;
-        int error = 0;
+        int ret = 0;
         struct timeval start;
         struct timeval stop;
         struct bio *bio;
@@ -713,15 +957,15 @@ static int load_image(struct swap_map_handle *handle,
         bio = NULL;
         do_gettimeofday(&start);
         for ( ; ; ) {
-                error = snapshot_write_next(snapshot);
-                if (error <= 0)
+                ret = snapshot_write_next(snapshot);
+                if (ret <= 0)
                         break;
-                error = swap_read_page(handle, data_of(*snapshot), &bio);
-                if (error)
+                ret = swap_read_page(handle, data_of(*snapshot), &bio);
+                if (ret)
                         break;
                 if (snapshot->sync_read)
-                        error = hib_wait_on_bio_chain(&bio);
-                if (error)
+                        ret = hib_wait_on_bio_chain(&bio);
+                if (ret)
                         break;
                 if (!(nr_pages % m))
                         printk("\b\b\b\b%3d%%", nr_pages / m);
@@ -729,17 +973,61 @@ static int load_image(struct swap_map_handle *handle,
         }
         err2 = hib_wait_on_bio_chain(&bio);
         do_gettimeofday(&stop);
-        if (!error)
-                error = err2;
-        if (!error) {
+        if (!ret)
+                ret = err2;
+        if (!ret) {
                 printk("\b\b\b\bdone\n");
                 snapshot_write_finalize(snapshot);
                 if (!snapshot_image_loaded(snapshot))
-                        error = -ENODATA;
+                        ret = -ENODATA;
         } else
                 printk("\n");
         swsusp_show_speed(&start, &stop, nr_to_read, "Read");
-        return error;
+        return ret;
+}
+
+/**
+ * Structure used for LZO data decompression.
+ */
+struct dec_data {
+        struct task_struct *thr;                  /* thread */
+        atomic_t ready;                           /* ready to start flag */
+        atomic_t stop;                            /* ready to stop flag */
+        int ret;                                  /* return code */
+        wait_queue_head_t go;                     /* start decompression */
+        wait_queue_head_t done;                   /* decompression done */
+        size_t unc_len;                           /* uncompressed length */
+        size_t cmp_len;                           /* compressed length */
+        unsigned char unc[LZO_UNC_SIZE];          /* uncompressed buffer */
+        unsigned char cmp[LZO_CMP_SIZE];          /* compressed buffer */
+};
+
+/**
+ * Deompression function that runs in its own thread.
+ */
+static int lzo_decompress_threadfn(void *data)
+{
+        struct dec_data *d = data;
+
+        while (1) {
+                wait_event(d->go, atomic_read(&d->ready) ||
+                                  kthread_should_stop());
+                if (kthread_should_stop()) {
+                        d->thr = NULL;
+                        d->ret = -1;
+                        atomic_set(&d->stop, 1);
+                        wake_up(&d->done);
+                        break;
+                }
+                atomic_set(&d->ready, 0);
+
+                d->unc_len = LZO_UNC_SIZE;
+                d->ret = lzo1x_decompress_safe(d->cmp + LZO_HEADER, d->cmp_len,
+                                               d->unc, &d->unc_len);
+                atomic_set(&d->stop, 1);
+                wake_up(&d->done);
+        }
+        return 0;
 }
 
 /**
@@ -753,50 +1041,120 @@ static int load_image_lzo(struct swap_map_handle *handle,
                           unsigned int nr_to_read)
 {
         unsigned int m;
-        int error = 0;
+        int ret = 0;
+        int eof = 0;
         struct bio *bio;
         struct timeval start;
         struct timeval stop;
         unsigned nr_pages;
-        size_t i, off, unc_len, cmp_len;
-        unsigned char *unc, *cmp, *page[LZO_CMP_PAGES];
-
-        for (i = 0; i < LZO_CMP_PAGES; i++) {
-                page[i] = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
-                if (!page[i]) {
-                        printk(KERN_ERR "PM: Failed to allocate LZO page\n");
+        size_t off;
+        unsigned i, thr, run_threads, nr_threads;
+        unsigned ring = 0, pg = 0, ring_size = 0,
+                 have = 0, want, need, asked = 0;
+        unsigned long read_pages;
+        unsigned char **page = NULL;
+        struct dec_data *data = NULL;
+        struct crc_data *crc = NULL;
+
+        /*
+         * We'll limit the number of threads for decompression to limit memory
+         * footprint.
+         */
+        nr_threads = num_online_cpus() - 1;
+        nr_threads = clamp_val(nr_threads, 1, LZO_THREADS);
+
+        page = vmalloc(sizeof(*page) * LZO_READ_PAGES);
+        if (!page) {
+                printk(KERN_ERR "PM: Failed to allocate LZO page\n");
+                ret = -ENOMEM;
+                goto out_clean;
+        }
 
-                        while (i)
-                                free_page((unsigned long)page[--i]);
+        data = vmalloc(sizeof(*data) * nr_threads);
+        if (!data) {
+                printk(KERN_ERR "PM: Failed to allocate LZO data\n");
+                ret = -ENOMEM;
+                goto out_clean;
+        }
+        for (thr = 0; thr < nr_threads; thr++)
+                memset(&data[thr], 0, offsetof(struct dec_data, go));
 
-                        return -ENOMEM;
+        crc = kmalloc(sizeof(*crc), GFP_KERNEL);
+        if (!crc) {
+                printk(KERN_ERR "PM: Failed to allocate crc\n");
+                ret = -ENOMEM;
+                goto out_clean;
+        }
+        memset(crc, 0, offsetof(struct crc_data, go));
+
+        /*
+         * Start the decompression threads.
+         */
+        for (thr = 0; thr < nr_threads; thr++) {
+                init_waitqueue_head(&data[thr].go);
+                init_waitqueue_head(&data[thr].done);
+
+                data[thr].thr = kthread_run(lzo_decompress_threadfn,
+                                            &data[thr],
+                                            "image_decompress/%u", thr);
+                if (IS_ERR(data[thr].thr)) {
+                        data[thr].thr = NULL;
+                        printk(KERN_ERR
+                               "PM: Cannot start decompression threads\n");
+                        ret = -ENOMEM;
+                        goto out_clean;
                 }
         }
 
-        unc = vmalloc(LZO_UNC_SIZE);
-        if (!unc) {
-                printk(KERN_ERR "PM: Failed to allocate LZO uncompressed\n");
-
-                for (i = 0; i < LZO_CMP_PAGES; i++)
-                        free_page((unsigned long)page[i]);
-
-                return -ENOMEM;
+        /*
+         * Start the CRC32 thread.
+         */
+        init_waitqueue_head(&crc->go);
+        init_waitqueue_head(&crc->done);
+
+        handle->crc32 = 0;
+        crc->crc32 = &handle->crc32;
+        for (thr = 0; thr < nr_threads; thr++) {
+                crc->unc[thr] = data[thr].unc;
+                crc->unc_len[thr] = &data[thr].unc_len;
         }
 
-        cmp = vmalloc(LZO_CMP_SIZE);
-        if (!cmp) {
-                printk(KERN_ERR "PM: Failed to allocate LZO compressed\n");
+        crc->thr = kthread_run(crc32_threadfn, crc, "image_crc32");
+        if (IS_ERR(crc->thr)) {
+                crc->thr = NULL;
+                printk(KERN_ERR "PM: Cannot start CRC32 thread\n");
+                ret = -ENOMEM;
+                goto out_clean;
+        }
 
-                vfree(unc);
-                for (i = 0; i < LZO_CMP_PAGES; i++)
-                        free_page((unsigned long)page[i]);
+        /*
+         * Adjust number of pages for read buffering, in case we are short.
+         */
+        read_pages = (nr_free_pages() - snapshot_get_image_size()) >> 1;
+        read_pages = clamp_val(read_pages, LZO_CMP_PAGES, LZO_READ_PAGES);
 
-                return -ENOMEM;
+        for (i = 0; i < read_pages; i++) {
+                page[i] = (void *)__get_free_page(i < LZO_CMP_PAGES ?
+                                                  __GFP_WAIT | __GFP_HIGH :
+                                                  __GFP_WAIT);
+                if (!page[i]) {
+                        if (i < LZO_CMP_PAGES) {
+                                ring_size = i;
+                                printk(KERN_ERR
+                                       "PM: Failed to allocate LZO pages\n");
+                                ret = -ENOMEM;
+                                goto out_clean;
+                        } else {
+                                break;
+                        }
+                }
         }
+        want = ring_size = i;
 
         printk(KERN_INFO
+                "PM: Using %u thread(s) for decompression.\n"
                 "PM: Loading and decompressing image data (%u pages) ...     ",
-                nr_to_read);
+                nr_threads, nr_to_read);
         m = nr_to_read / 100;
         if (!m)
                 m = 1;
@@ -804,85 +1162,189 @@ static int load_image_lzo(struct swap_map_handle *handle,
         bio = NULL;
         do_gettimeofday(&start);
 
-        error = snapshot_write_next(snapshot);
-        if (error <= 0)
+        ret = snapshot_write_next(snapshot);
+        if (ret <= 0)
                 goto out_finish;
 
-        for (;;) {
-                error = swap_read_page(handle, page[0], NULL); /* sync */
-                if (error)
-                        break;
-
-                cmp_len = *(size_t *)page[0];
-                if (unlikely(!cmp_len ||
-                             cmp_len > lzo1x_worst_compress(LZO_UNC_SIZE))) {
-                        printk(KERN_ERR "PM: Invalid LZO compressed length\n");
-                        error = -1;
-                        break;
+        for(;;) {
+                for (i = 0; !eof && i < want; i++) {
+                        ret = swap_read_page(handle, page[ring], &bio);
+                        if (ret) {
+                                /*
+                                 * On real read error, finish. On end of data,
+                                 * set EOF flag and just exit the read loop.
+                                 */
+                                if (handle->cur &&
+                                    handle->cur->entries[handle->k]) {
+                                        goto out_finish;
+                                } else {
+                                        eof = 1;
+                                        break;
+                                }
+                        }
+                        if (++ring >= ring_size)
+                                ring = 0;
                 }
+                asked += i;
+                want -= i;
 
-                for (off = PAGE_SIZE, i = 1;
-                     off < LZO_HEADER + cmp_len; off += PAGE_SIZE, i++) {
-                        error = swap_read_page(handle, page[i], &bio);
-                        if (error)
+                /*
+                 * We are out of data, wait for some more.
+                 */
+                if (!have) {
+                        if (!asked)
+                                break;
+
+                        ret = hib_wait_on_bio_chain(&bio);
+                        if (ret)
                                 goto out_finish;
+                        have += asked;
+                        asked = 0;
+                        if (eof)
+                                eof = 2;
                 }
 
-                error = hib_wait_on_bio_chain(&bio); /* need all data now */
-                if (error)
-                        goto out_finish;
-
-                for (off = 0, i = 0;
-                     off < LZO_HEADER + cmp_len; off += PAGE_SIZE, i++) {
-                        memcpy(cmp + off, page[i], PAGE_SIZE);
+                if (crc->run_threads) {
+                        wait_event(crc->done, atomic_read(&crc->stop));
+                        atomic_set(&crc->stop, 0);
+                        crc->run_threads = 0;
                 }
 
-                unc_len = LZO_UNC_SIZE;
-                error = lzo1x_decompress_safe(cmp + LZO_HEADER, cmp_len,
-                                              unc, &unc_len);
-                if (error < 0) {
-                        printk(KERN_ERR "PM: LZO decompression failed\n");
-                        break;
+                for (thr = 0; have && thr < nr_threads; thr++) {
+                        data[thr].cmp_len = *(size_t *)page[pg];
+                        if (unlikely(!data[thr].cmp_len ||
+                                     data[thr].cmp_len >
+                                     lzo1x_worst_compress(LZO_UNC_SIZE))) {
+                                printk(KERN_ERR
+                                       "PM: Invalid LZO compressed length\n");
+                                ret = -1;
+                                goto out_finish;
+                        }
+
+                        need = DIV_ROUND_UP(data[thr].cmp_len + LZO_HEADER,
+                                            PAGE_SIZE);
+                        if (need > have) {
+                                if (eof > 1) {
+                                        ret = -1;
+                                        goto out_finish;
+                                }
+                                break;
+                        }
+
+                        for (off = 0;
+                             off < LZO_HEADER + data[thr].cmp_len;
+                             off += PAGE_SIZE) {
+                                memcpy(data[thr].cmp + off,
+                                       page[pg], PAGE_SIZE);
+                                have--;
+                                want++;
+                                if (++pg >= ring_size)
+                                        pg = 0;
+                        }
+
+                        atomic_set(&data[thr].ready, 1);
+                        wake_up(&data[thr].go);
                 }
 
-                if (unlikely(!unc_len ||
-                             unc_len > LZO_UNC_SIZE ||
-                             unc_len & (PAGE_SIZE - 1))) {
-                        printk(KERN_ERR "PM: Invalid LZO uncompressed length\n");
-                        error = -1;
-                        break;
+                /*
+                 * Wait for more data while we are decompressing.
+                 */
+                if (have < LZO_CMP_PAGES && asked) {
+                        ret = hib_wait_on_bio_chain(&bio);
+                        if (ret)
+                                goto out_finish;
+                        have += asked;
+                        asked = 0;
+                        if (eof)
+                                eof = 2;
                 }
 
-                for (off = 0; off < unc_len; off += PAGE_SIZE) {
-                        memcpy(data_of(*snapshot), unc + off, PAGE_SIZE);
+                for (run_threads = thr, thr = 0; thr < run_threads; thr++) {
+                        wait_event(data[thr].done,
+                                   atomic_read(&data[thr].stop));
+                        atomic_set(&data[thr].stop, 0);
+
+                        ret = data[thr].ret;
 
-                        if (!(nr_pages % m))
-                                printk("\b\b\b\b%3d%%", nr_pages / m);
-                        nr_pages++;
+                        if (ret < 0) {
+                                printk(KERN_ERR
+                                       "PM: LZO decompression failed\n");
+                                goto out_finish;
+                        }
 
-                        error = snapshot_write_next(snapshot);
-                        if (error <= 0)
+                        if (unlikely(!data[thr].unc_len ||
+                                     data[thr].unc_len > LZO_UNC_SIZE ||
+                                     data[thr].unc_len & (PAGE_SIZE - 1))) {
+                                printk(KERN_ERR
+                                       "PM: Invalid LZO uncompressed length\n");
+                                ret = -1;
                                 goto out_finish;
+                        }
+
+                        for (off = 0;
+                             off < data[thr].unc_len; off += PAGE_SIZE) {
+                                memcpy(data_of(*snapshot),
+                                       data[thr].unc + off, PAGE_SIZE);
+
+                                if (!(nr_pages % m))
+                                        printk("\b\b\b\b%3d%%", nr_pages / m);
+                                nr_pages++;
+
+                                ret = snapshot_write_next(snapshot);
+                                if (ret <= 0) {
+                                        crc->run_threads = thr + 1;
+                                        atomic_set(&crc->ready, 1);
+                                        wake_up(&crc->go);
+                                        goto out_finish;
+                                }
+                        }
                 }
+
+                crc->run_threads = thr;
+                atomic_set(&crc->ready, 1);
+                wake_up(&crc->go);
         }
 
 out_finish:
+        if (crc->run_threads) {
+                wait_event(crc->done, atomic_read(&crc->stop));
+                atomic_set(&crc->stop, 0);
+        }
         do_gettimeofday(&stop);
-        if (!error) {
+        if (!ret) {
                 printk("\b\b\b\bdone\n");
                 snapshot_write_finalize(snapshot);
                 if (!snapshot_image_loaded(snapshot))
-                        error = -ENODATA;
+                        ret = -ENODATA;
+                if (!ret) {
+                        if (swsusp_header->flags & SF_CRC32_MODE) {
+                                if(handle->crc32 != swsusp_header->crc32) {
+                                        printk(KERN_ERR
+                                               "PM: Invalid image CRC32!\n");
+                                        ret = -ENODATA;
+                                }
+                        }
+                }
         } else
                 printk("\n");
         swsusp_show_speed(&start, &stop, nr_to_read, "Read");
-
-        vfree(cmp);
-        vfree(unc);
-        for (i = 0; i < LZO_CMP_PAGES; i++)
+out_clean:
+        for (i = 0; i < ring_size; i++)
                 free_page((unsigned long)page[i]);
+        if (crc) {
+                if (crc->thr)
+                        kthread_stop(crc->thr);
+                kfree(crc);
+        }
+        if (data) {
+                for (thr = 0; thr < nr_threads; thr++)
+                        if (data[thr].thr)
+                                kthread_stop(data[thr].thr);
+                vfree(data);
+        }
+        if (page) vfree(page);
 
-        return error;
+        return ret;
 }
 
 /**
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 761c510a06c..f49405f842f 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -53,6 +53,9 @@ endif
 obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
 obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
 obj-$(CONFIG_TRACEPOINTS) += power-traces.o
+ifeq ($(CONFIG_PM_RUNTIME),y)
+obj-$(CONFIG_TRACEPOINTS) += rpm-traces.o
+endif
 ifeq ($(CONFIG_TRACING),y)
 obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
 endif
diff --git a/kernel/trace/rpm-traces.c b/kernel/trace/rpm-traces.c
new file mode 100644
index 00000000000..4b3b5eaf94d
--- /dev/null
+++ b/kernel/trace/rpm-traces.c
@@ -0,0 +1,20 @@
+/*
+ * Power trace points
+ *
+ * Copyright (C) 2009 Ming Lei <ming.lei@canonical.com>
+ */
+
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/usb.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/rpm.h>
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_return_int);
+EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_idle);
+EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_suspend);
+EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_resume);
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index d4ee6d234a7..d999bf3b84e 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -19,7 +19,7 @@
 #include <linux/if_arp.h>
 #include <linux/rtnetlink.h>
 #include <linux/bitmap.h>
-#include <linux/pm_qos_params.h>
+#include <linux/pm_qos.h>
 #include <linux/inetdevice.h>
 #include <net/net_namespace.h>
 #include <net/cfg80211.h>
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 0e5d8daba1e..ba2da11a997 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -17,7 +17,7 @@
 #include <linux/if_arp.h>
 #include <linux/etherdevice.h>
 #include <linux/rtnetlink.h>
-#include <linux/pm_qos_params.h>
+#include <linux/pm_qos.h>
 #include <linux/crc32.h>
 #include <linux/slab.h>
 #include <net/mac80211.h>
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 397343a5927..83a0b050b37 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -14,7 +14,7 @@
 
 #include <linux/if_arp.h>
 #include <linux/rtnetlink.h>
-#include <linux/pm_qos_params.h>
+#include <linux/pm_qos.h>
 #include <net/sch_generic.h>
 #include <linux/slab.h>
 #include <net/mac80211.h>
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 1c6be91dfb9..c74e228731e 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -23,7 +23,7 @@
 #include <linux/file.h>
 #include <linux/slab.h>
 #include <linux/time.h>
-#include <linux/pm_qos_params.h>
+#include <linux/pm_qos.h>
 #include <linux/uio.h>
 #include <linux/dma-mapping.h>
 #include <sound/core.h>
diff --git a/sound/usb/card.c b/sound/usb/card.c
index d8f2bf40145..3068f043099 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -631,7 +631,7 @@ static int usb_audio_suspend(struct usb_interface *intf, pm_message_t message)
         if (chip == (void *)-1L)
                 return 0;
 
-        if (!(message.event & PM_EVENT_AUTO)) {
+        if (!PMSG_IS_AUTO(message)) {
                 snd_power_change_state(chip->card, SNDRV_CTL_POWER_D3hot);
                 if (!chip->num_suspended_intf++) {
                         list_for_each(p, &chip->pcm_list) {