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

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/suspend-2.6: (26 commits)
  PM / Wakeup: Show wakeup sources statistics in debugfs
  PM: Introduce library for device-specific OPPs (v7)
  PM: Add sysfs attr for rechecking dev hash from PM trace
  PM: Lock PM device list mutex in show_dev_hash()
  PM / Runtime: Remove idle notification after failing suspend
  PM / Hibernate: Modify signature used to mark swap
  PM / Runtime: Reduce code duplication in core helper functions
  PM: Allow wakeup events to abort freezing of tasks
  PM: runtime: add missed pm_request_autosuspend
  PM / Hibernate: Make some boot messages look less scary
  PM / Runtime: Implement autosuspend support
  PM / Runtime: Add no_callbacks flag
  PM / Runtime: Combine runtime PM entry points
  PM / Runtime: Merge synchronous and async runtime routines
  PM / Runtime: Replace boolean arguments with bitflags
  PM / Runtime: Move code in drivers/base/power/runtime.c
  sysfs: Add sysfs_merge_group() and sysfs_unmerge_group()
  PM: Fix potential issue with failing asynchronous suspend
  PM / Wakeup: Introduce wakeup source objects and event statistics (v3)
  PM: Fix signed/unsigned warning in dpm_show_time()
  ...

Documentation/ABI/testing/sysfs-devices-power

@@ -77,3 +77,91 @@ Description:
 		devices this attribute is set to "enabled" by bus type code or
 		device drivers and in that cases it should be safe to leave the
 		default value.
+
+What:		/sys/devices/.../power/wakeup_count
+Date:		September 2010
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_count attribute contains the number
+		of signaled wakeup events associated with the device.  This
+		attribute is read-only.  If the device is not enabled to wake up
+		the system from sleep states, this attribute is empty.
+
+What:		/sys/devices/.../power/wakeup_active_count
+Date:		September 2010
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_active_count attribute contains the
+		number of times the processing of wakeup events associated with
+		the device was completed (at the kernel level).  This attribute
+		is read-only.  If the device is not enabled to wake up the
+		system from sleep states, this attribute is empty.
+
+What:		/sys/devices/.../power/wakeup_hit_count
+Date:		September 2010
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_hit_count attribute contains the
+		number of times the processing of a wakeup event associated with
+		the device might prevent the system from entering a sleep state.
+		This attribute is read-only.  If the device is not enabled to
+		wake up the system from sleep states, this attribute is empty.
+
+What:		/sys/devices/.../power/wakeup_active
+Date:		September 2010
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_active attribute contains either 1,
+		or 0, depending on whether or not a wakeup event associated with
+		the device is being processed (1).  This attribute is read-only.
+		If the device is not enabled to wake up the system from sleep
+		states, this attribute is empty.
+
+What:		/sys/devices/.../power/wakeup_total_time_ms
+Date:		September 2010
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_total_time_ms attribute contains
+		the total time of processing wakeup events associated with the
+		device, in milliseconds.  This attribute is read-only.  If the
+		device is not enabled to wake up the system from sleep states,
+		this attribute is empty.
+
+What:		/sys/devices/.../power/wakeup_max_time_ms
+Date:		September 2010
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_max_time_ms attribute contains
+		the maximum time of processing a single wakeup event associated
+		with the device, in milliseconds.  This attribute is read-only.
+		If the device is not enabled to wake up the system from sleep
+		states, this attribute is empty.
+
+What:		/sys/devices/.../power/wakeup_last_time_ms
+Date:		September 2010
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_last_time_ms attribute contains
+		the value of the monotonic clock corresponding to the time of
+		signaling the last wakeup event associated with the device, in
+		milliseconds.  This attribute is read-only.  If the device is
+		not enabled to wake up the system from sleep states, this
+		attribute is empty.
+
+What:		/sys/devices/.../power/autosuspend_delay_ms
+Date:		September 2010
+Contact:	Alan Stern <stern@rowland.harvard.edu>
+Description:
+		The /sys/devices/.../power/autosuspend_delay_ms attribute
+		contains the autosuspend delay value (in milliseconds).  Some
+		drivers do not want their device to suspend as soon as it
+		becomes idle at run time; they want the device to remain
+		inactive for a certain minimum period of time first.  That
+		period is called the autosuspend delay.  Negative values will
+		prevent the device from being suspended at run time (similar
+		to writing "on" to the power/control attribute).  Values >=
+		1000 will cause the autosuspend timer expiration to be rounded
+		up to the nearest second.
+
+		Not all drivers support this attribute.  If it isn't supported,
+		attempts to read or write it will yield I/O errors.

Documentation/ABI/testing/sysfs-power

@@ -99,9 +99,38 @@ Description:
 
 		dmesg -s 1000000 | grep 'hash matches'
 
+		If you do not get any matches (or they appear to be false
+		positives), it is possible that the last PM event point
+		referred to a device created by a loadable kernel module.  In
+		this case cat /sys/power/pm_trace_dev_match (see below) after
+		your system is started up and the kernel modules are loaded.
+
 		CAUTION: Using it will cause your machine's real-time (CMOS)
 		clock to be set to a random invalid time after a resume.
 
+What;		/sys/power/pm_trace_dev_match
+Date:		October 2010
+Contact:	James Hogan <james@albanarts.com>
+Description:
+		The /sys/power/pm_trace_dev_match file contains the name of the
+		device associated with the last PM event point saved in the RTC
+		across reboots when pm_trace has been used.  More precisely it
+		contains the list of current devices (including those
+		registered by loadable kernel modules since boot) which match
+		the device hash in the RTC at boot, with a newline after each
+		one.
+
+		The advantage of this file over the hash matches printed to the
+		kernel log (see /sys/power/pm_trace), is that it includes
+		devices created after boot by loadable kernel modules.
+
+		Due to the small hash size necessary to fit in the RTC, it is
+		possible that more than one device matches the hash, in which
+		case further investigation is required to determine which
+		device is causing the problem.  Note that genuine RTC clock
+		values (such as when pm_trace has not been used), can still
+		match a device and output it's name here.
+
 What:		/sys/power/pm_async
 Date:		January 2009
 Contact:	Rafael J. Wysocki <rjw@sisk.pl>

Documentation/kernel-parameters.txt

@@ -2170,6 +2170,11 @@ and is between 256 and 4096 characters. It is defined in the file
 			in <PAGE_SIZE> units (needed only for swap files).
 			See  Documentation/power/swsusp-and-swap-files.txt
 
+	hibernate=	[HIBERNATION]
+		noresume	Don't check if there's a hibernation image
+				present during boot.
+		nocompress	Don't compress/decompress hibernation images.
+
 	retain_initrd	[RAM] Keep initrd memory after extraction
 
 	rhash_entries=	[KNL,NET]

Documentation/power/00-INDEX

@@ -14,6 +14,8 @@ interface.txt
 	- Power management user interface in /sys/power
 notifiers.txt
 	- Registering suspend notifiers in device drivers
+opp.txt
+	- Operating Performance Point library
 pci.txt
 	- How the PCI Subsystem Does Power Management
 pm_qos_interface.txt

Documentation/power/interface.txt

@@ -57,7 +57,7 @@ smallest image possible.  In particular, if "0" is written to this file, the
 suspend image will be as small as possible.
 
 Reading from this file will display the current image size limit, which
-is set to 500 MB by default.
+is set to 2/5 of available RAM by default.
 
 /sys/power/pm_trace controls the code which saves the last PM event point in
 the RTC across reboots, so that you can debug a machine that just hangs

Documentation/power/opp.txt

@@ -0,0 +1,375 @@
+*=============*
+* OPP Library *
+*=============*
+
+(C) 2009-2010 Nishanth Menon <nm@ti.com>, Texas Instruments Incorporated
+
+Contents
+--------
+1. Introduction
+2. Initial OPP List Registration
+3. OPP Search Functions
+4. OPP Availability Control Functions
+5. OPP Data Retrieval Functions
+6. Cpufreq Table Generation
+7. Data Structures
+
+1. Introduction
+===============
+Complex SoCs of today consists of a multiple sub-modules working in conjunction.
+In an operational system executing varied use cases, not all modules in the SoC
+need to function at their highest performing frequency all the time. To
+facilitate this, sub-modules in a SoC are grouped into domains, allowing some
+domains to run at lower voltage and frequency while other domains are loaded
+more. The set of discrete tuples consisting of frequency and voltage pairs that
+the device will support per domain are called Operating Performance Points or
+OPPs.
+
+OPP library provides a set of helper functions to organize and query the OPP
+information. The library is located in drivers/base/power/opp.c and the header
+is located in include/linux/opp.h. OPP library can be enabled by enabling
+CONFIG_PM_OPP from power management menuconfig menu. OPP library depends on
+CONFIG_PM as certain SoCs such as Texas Instrument's OMAP framework allows to
+optionally boot at a certain OPP without needing cpufreq.
+
+Typical usage of the OPP library is as follows:
+(users)		-> registers a set of default OPPs		-> (library)
+SoC framework	-> modifies on required cases certain OPPs	-> OPP layer
+		-> queries to search/retrieve information	->
+
+OPP layer expects each domain to be represented by a unique device pointer. SoC
+framework registers a set of initial OPPs per device with the OPP layer. This
+list is expected to be an optimally small number typically around 5 per device.
+This initial list contains a set of OPPs that the framework expects to be safely
+enabled by default in the system.
+
+Note on OPP Availability:
+------------------------
+As the system proceeds to operate, SoC framework may choose to make certain
+OPPs available or not available on each device based on various external
+factors. Example usage: Thermal management or other exceptional situations where
+SoC framework might choose to disable a higher frequency OPP to safely continue
+operations until that OPP could be re-enabled if possible.
+
+OPP library facilitates this concept in it's implementation. The following
+operational functions operate only on available opps:
+opp_find_freq_{ceil, floor}, opp_get_voltage, opp_get_freq, opp_get_opp_count
+and opp_init_cpufreq_table
+
+opp_find_freq_exact is meant to be used to find the opp pointer which can then
+be used for opp_enable/disable functions to make an opp available as required.
+
+WARNING: Users of OPP library should refresh their availability count using
+get_opp_count if opp_enable/disable functions are invoked for a device, the
+exact mechanism to trigger these or the notification mechanism to other
+dependent subsystems such as cpufreq are left to the discretion of the SoC
+specific framework which uses the OPP library. Similar care needs to be taken
+care to refresh the cpufreq table in cases of these operations.
+
+WARNING on OPP List locking mechanism:
+-------------------------------------------------
+OPP library uses RCU for exclusivity. RCU allows the query functions to operate
+in multiple contexts and this synchronization mechanism is optimal for a read
+intensive operations on data structure as the OPP library caters to.
+
+To ensure that the data retrieved are sane, the users such as SoC framework
+should ensure that the section of code operating on OPP queries are locked
+using RCU read locks. The opp_find_freq_{exact,ceil,floor},
+opp_get_{voltage, freq, opp_count} fall into this category.
+
+opp_{add,enable,disable} are updaters which use mutex and implement it's own
+RCU locking mechanisms. opp_init_cpufreq_table acts as an updater and uses
+mutex to implment RCU updater strategy. These functions should *NOT* be called
+under RCU locks and other contexts that prevent blocking functions in RCU or
+mutex operations from working.
+
+2. Initial OPP List Registration
+================================
+The SoC implementation calls opp_add function iteratively to add OPPs per
+device. It is expected that the SoC framework will register the OPP entries
+optimally- typical numbers range to be less than 5. The list generated by
+registering the OPPs is maintained by OPP library throughout the device
+operation. The SoC framework can subsequently control the availability of the
+OPPs dynamically using the opp_enable / disable functions.
+
+opp_add - Add a new OPP for a specific domain represented by the device pointer.
+	The OPP is defined using the frequency and voltage. Once added, the OPP
+	is assumed to be available and control of it's availability can be done
+	with the opp_enable/disable functions. OPP library internally stores
+	and manages this information in the opp struct. This function may be
+	used by SoC framework to define a optimal list as per the demands of
+	SoC usage environment.
+
+	WARNING: Do not use this function in interrupt context.
+
+	Example:
+	 soc_pm_init()
+	 {
+		/* Do things */
+		r = opp_add(mpu_dev, 1000000, 900000);
+		if (!r) {
+			pr_err("%s: unable to register mpu opp(%d)\n", r);
+			goto no_cpufreq;
+		}
+		/* Do cpufreq things */
+	 no_cpufreq:
+		/* Do remaining things */
+	 }
+
+3. OPP Search Functions
+=======================
+High level framework such as cpufreq operates on frequencies. To map the
+frequency back to the corresponding OPP, OPP library provides handy functions
+to search the OPP list that OPP library internally manages. These search
+functions return the matching pointer representing the opp if a match is
+found, else returns error. These errors are expected to be handled by standard
+error checks such as IS_ERR() and appropriate actions taken by the caller.
+
+opp_find_freq_exact - Search for an OPP based on an *exact* frequency and
+	availability. This function is especially useful to enable an OPP which
+	is not available by default.
+	Example: In a case when SoC framework detects a situation where a
+	higher frequency could be made available, it can use this function to
+	find the OPP prior to call the opp_enable to actually make it available.
+	 rcu_read_lock();
+	 opp = opp_find_freq_exact(dev, 1000000000, false);
+	 rcu_read_unlock();
+	 /* dont operate on the pointer.. just do a sanity check.. */
+	 if (IS_ERR(opp)) {
+		pr_err("frequency not disabled!\n");
+		/* trigger appropriate actions.. */
+	 } else {
+		opp_enable(dev,1000000000);
+	 }
+
+	NOTE: This is the only search function that operates on OPPs which are
+	not available.
+
+opp_find_freq_floor - Search for an available OPP which is *at most* the
+	provided frequency. This function is useful while searching for a lesser
+	match OR operating on OPP information in the order of decreasing
+	frequency.
+	Example: To find the highest opp for a device:
+	 freq = ULONG_MAX;
+	 rcu_read_lock();
+	 opp_find_freq_floor(dev, &freq);
+	 rcu_read_unlock();
+
+opp_find_freq_ceil - Search for an available OPP which is *at least* the
+	provided frequency. This function is useful while searching for a
+	higher match OR operating on OPP information in the order of increasing
+	frequency.
+	Example 1: To find the lowest opp for a device:
+	 freq = 0;
+	 rcu_read_lock();
+	 opp_find_freq_ceil(dev, &freq);
+	 rcu_read_unlock();
+	Example 2: A simplified implementation of a SoC cpufreq_driver->target:
+	 soc_cpufreq_target(..)
+	 {
+		/* Do stuff like policy checks etc. */
+		/* Find the best frequency match for the req */
+		rcu_read_lock();
+		opp = opp_find_freq_ceil(dev, &freq);
+		rcu_read_unlock();
+		if (!IS_ERR(opp))
+			soc_switch_to_freq_voltage(freq);
+		else
+			/* do something when we cant satisfy the req */
+		/* do other stuff */
+	 }
+
+4. OPP Availability Control Functions
+=====================================
+A default OPP list registered with the OPP library may not cater to all possible
+situation. The OPP library provides a set of functions to modify the
+availability of a OPP within the OPP list. This allows SoC frameworks to have
+fine grained dynamic control of which sets of OPPs are operationally available.
+These functions are intended to *temporarily* remove an OPP in conditions such
+as thermal considerations (e.g. don't use OPPx until the temperature drops).
+
+WARNING: Do not use these functions in interrupt context.
+
+opp_enable - Make a OPP available for operation.
+	Example: Lets say that 1GHz OPP is to be made available only if the
+	SoC temperature is lower than a certain threshold. The SoC framework
+	implementation might choose to do something as follows:
+	 if (cur_temp < temp_low_thresh) {
+		/* Enable 1GHz if it was disabled */
+		rcu_read_lock();
+		opp = opp_find_freq_exact(dev, 1000000000, false);
+		rcu_read_unlock();
+		/* just error check */
+		if (!IS_ERR(opp))
+			ret = opp_enable(dev, 1000000000);
+		else
+			goto try_something_else;
+	 }
+
+opp_disable - Make an OPP to be not available for operation
+	Example: Lets say that 1GHz OPP is to be disabled if the temperature
+	exceeds a threshold value. The SoC framework implementation might
+	choose to do something as follows:
+	 if (cur_temp > temp_high_thresh) {
+		/* Disable 1GHz if it was enabled */
+		rcu_read_lock();
+		opp = opp_find_freq_exact(dev, 1000000000, true);
+		rcu_read_unlock();
+		/* just error check */
+		if (!IS_ERR(opp))
+			ret = opp_disable(dev, 1000000000);
+		else
+			goto try_something_else;
+	 }
+
+5. OPP Data Retrieval Functions
+===============================
+Since OPP library abstracts away the OPP information, a set of functions to pull
+information from the OPP structure is necessary. Once an OPP pointer is
+retrieved using the search functions, the following functions can be used by SoC
+framework to retrieve the information represented inside the OPP layer.
+
+opp_get_voltage - Retrieve the voltage represented by the opp pointer.
+	Example: At a cpufreq transition to a different frequency, SoC
+	framework requires to set the voltage represented by the OPP using
+	the regulator framework to the Power Management chip providing the
+	voltage.
+	 soc_switch_to_freq_voltage(freq)
+	 {
+		/* do things */
+		rcu_read_lock();
+		opp = opp_find_freq_ceil(dev, &freq);
+		v = opp_get_voltage(opp);
+		rcu_read_unlock();
+		if (v)
+			regulator_set_voltage(.., v);
+		/* do other things */
+	 }
+
+opp_get_freq - Retrieve the freq represented by the opp pointer.
+	Example: Lets say the SoC framework uses a couple of helper functions
+	we could pass opp pointers instead of doing additional parameters to
+	handle quiet a bit of data parameters.
+	 soc_cpufreq_target(..)
+	 {
+		/* do things.. */
+		 max_freq = ULONG_MAX;
+		 rcu_read_lock();
+		 max_opp = opp_find_freq_floor(dev,&max_freq);
+		 requested_opp = opp_find_freq_ceil(dev,&freq);
+		 if (!IS_ERR(max_opp) && !IS_ERR(requested_opp))
+			r = soc_test_validity(max_opp, requested_opp);
+		 rcu_read_unlock();
+		/* do other things */
+	 }
+	 soc_test_validity(..)
+	 {
+		 if(opp_get_voltage(max_opp) < opp_get_voltage(requested_opp))
+			 return -EINVAL;
+		 if(opp_get_freq(max_opp) < opp_get_freq(requested_opp))
+			 return -EINVAL;
+		/* do things.. */
+	 }
+
+opp_get_opp_count - Retrieve the number of available opps for a device
+	Example: Lets say a co-processor in the SoC needs to know the available
+	frequencies in a table, the main processor can notify as following:
+	 soc_notify_coproc_available_frequencies()
+	 {
+		/* Do things */
+		rcu_read_lock();
+		num_available = opp_get_opp_count(dev);
+		speeds = kzalloc(sizeof(u32) * num_available, GFP_KERNEL);
+		/* populate the table in increasing order */
+		freq = 0;
+		while (!IS_ERR(opp = opp_find_freq_ceil(dev, &freq))) {
+			speeds[i] = freq;
+			freq++;
+			i++;
+		}
+		rcu_read_unlock();
+
+		soc_notify_coproc(AVAILABLE_FREQs, speeds, num_available);
+		/* Do other things */
+	 }
+
+6. Cpufreq Table Generation
+===========================
+opp_init_cpufreq_table - cpufreq framework typically is initialized with
+	cpufreq_frequency_table_cpuinfo which is provided with the list of
+	frequencies that are available for operation. This function provides
+	a ready to use conversion routine to translate the OPP layer's internal
+	information about the available frequencies into a format readily
+	providable to cpufreq.
+
+	WARNING: Do not use this function in interrupt context.
+
+	Example:
+	 soc_pm_init()
+	 {
+		/* Do things */
+		r = opp_init_cpufreq_table(dev, &freq_table);
+		if (!r)
+			cpufreq_frequency_table_cpuinfo(policy, freq_table);
+		/* Do other things */
+	 }
+
+	NOTE: This function is available only if CONFIG_CPU_FREQ is enabled in
+	addition to CONFIG_PM as power management feature is required to
+	dynamically scale voltage and frequency in a system.
+
+7. Data Structures
+==================
+Typically an SoC contains multiple voltage domains which are variable. Each
+domain is represented by a device pointer. The relationship to OPP can be
+represented as follows:
+SoC
+ |- device 1
+ |	|- opp 1 (availability, freq, voltage)
+ |	|- opp 2 ..
+ ...	...
+ |	`- opp n ..
+ |- device 2
+ ...
+ `- device m
+
+OPP library maintains a internal list that the SoC framework populates and
+accessed by various functions as described above. However, the structures
+representing the actual OPPs and domains are internal to the OPP library itself
+to allow for suitable abstraction reusable across systems.
+
+struct opp - The internal data structure of OPP library which is used to
+	represent an OPP. In addition to the freq, voltage, availability
+	information, it also contains internal book keeping information required
+	for the OPP library to operate on.  Pointer to this structure is
+	provided back to the users such as SoC framework to be used as a
+	identifier for OPP in the interactions with OPP layer.
+
+	WARNING: The struct opp pointer should not be parsed or modified by the
+	users. The defaults of for an instance is populated by opp_add, but the
+	availability of the OPP can be modified by opp_enable/disable functions.
+
+struct device - This is used to identify a domain to the OPP layer. The
+	nature of the device and it's implementation is left to the user of
+	OPP library such as the SoC framework.
+
+Overall, in a simplistic view, the data structure operations is represented as
+following:
+
+Initialization / modification:
+            +-----+        /- opp_enable
+opp_add --> | opp | <-------
+  |         +-----+        \- opp_disable
+  \-------> domain_info(device)
+
+Search functions:
+             /-- opp_find_freq_ceil  ---\   +-----+
+domain_info<---- opp_find_freq_exact -----> | opp |
+             \-- opp_find_freq_floor ---/   +-----+
+
+Retrieval functions:
++-----+     /- opp_get_voltage
+| opp | <---
++-----+     \- opp_get_freq
+
+domain_info <- opp_get_opp_count

Documentation/power/runtime_pm.txt

@@ -1,6 +1,7 @@
 Run-time Power Management Framework for I/O Devices
 
 (C) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+(C) 2010 Alan Stern <stern@rowland.harvard.edu>
 
 1. Introduction
 
@@ -157,7 +158,8 @@ rules:
     to execute it, the other callbacks will not be executed for the same device.
 
   * A request to execute ->runtime_resume() will cancel any pending or
-    scheduled requests to execute the other callbacks for the same device.
+    scheduled requests to execute the other callbacks for the same device,
+    except for scheduled autosuspends.
 
 3. Run-time PM Device Fields
 
@@ -165,7 +167,7 @@ The following device run-time PM fields are present in 'struct dev_pm_info', as
 defined in include/linux/pm.h:
 
   struct timer_list suspend_timer;
-    - timer used for scheduling (delayed) suspend request
+    - timer used for scheduling (delayed) suspend and autosuspend requests
 
   unsigned long timer_expires;
     - timer expiration time, in jiffies (if this is different from zero, the
@@ -230,6 +232,28 @@ defined in include/linux/pm.h:
       interface; it may only be modified with the help of the pm_runtime_allow()
       and pm_runtime_forbid() helper functions
 
+  unsigned int no_callbacks;
+    - indicates that the device does not use the run-time PM callbacks (see
+      Section 8); it may be modified only by the pm_runtime_no_callbacks()
+      helper function
+
+  unsigned int use_autosuspend;
+    - indicates that the device's driver supports delayed autosuspend (see
+      Section 9); it may be modified only by the
+      pm_runtime{_dont}_use_autosuspend() helper functions
+
+  unsigned int timer_autosuspends;
+    - indicates that the PM core should attempt to carry out an autosuspend
+      when the timer expires rather than a normal suspend
+
+  int autosuspend_delay;
+    - the delay time (in milliseconds) to be used for autosuspend
+
+  unsigned long last_busy;
+    - the time (in jiffies) when the pm_runtime_mark_last_busy() helper
+      function was last called for this device; used in calculating inactivity
+      periods for autosuspend
+
 All of the above fields are members of the 'power' member of 'struct device'.
 
 4. Run-time PM Device Helper Functions
@@ -255,6 +279,12 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
       error code on failure, where -EAGAIN or -EBUSY means it is safe to attempt
       to suspend the device again in future
 
+  int pm_runtime_autosuspend(struct device *dev);
+    - same as pm_runtime_suspend() except that the autosuspend delay is taken
+      into account; if pm_runtime_autosuspend_expiration() says the delay has
+      not yet expired then an autosuspend is scheduled for the appropriate time
+      and 0 is returned
+
   int pm_runtime_resume(struct device *dev);
     - execute the subsystem-level resume callback for the device; returns 0 on
       success, 1 if the device's run-time PM status was already 'active' or
@@ -267,6 +297,11 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
       device (the request is represented by a work item in pm_wq); returns 0 on
       success or error code if the request has not been queued up
 
+  int pm_request_autosuspend(struct device *dev);
+    - schedule the execution of the subsystem-level suspend callback for the
+      device when the autosuspend delay has expired; if the delay has already
+      expired then the work item is queued up immediately
+
   int pm_schedule_suspend(struct device *dev, unsigned int delay);
     - schedule the execution of the subsystem-level suspend callback for the
       device in future, where 'delay' is the time to wait before queuing up a
@@ -298,12 +333,20 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
     - decrement the device's usage counter
 
   int pm_runtime_put(struct device *dev);
-    - decrement the device's usage counter, run pm_request_idle(dev) and return
-      its result
+    - decrement the device's usage counter; if the result is 0 then run
+      pm_request_idle(dev) and return its result
+
+  int pm_runtime_put_autosuspend(struct device *dev);
+    - decrement the device's usage counter; if the result is 0 then run
+      pm_request_autosuspend(dev) and return its result
 
   int pm_runtime_put_sync(struct device *dev);
-    - decrement the device's usage counter, run pm_runtime_idle(dev) and return
-      its result
+    - decrement the device's usage counter; if the result is 0 then run
+      pm_runtime_idle(dev) and return its result
+
+  int pm_runtime_put_sync_autosuspend(struct device *dev);
+    - decrement the device's usage counter; if the result is 0 then run
+      pm_runtime_autosuspend(dev) and return its result
 
   void pm_runtime_enable(struct device *dev);
     - enable the run-time PM helper functions to run the device bus type's
@@ -349,19 +392,51 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
       counter (used by the /sys/devices/.../power/control interface to
       effectively prevent the device from being power managed at run time)
 
+  void pm_runtime_no_callbacks(struct device *dev);
+    - set the power.no_callbacks flag for the device and remove the run-time
+      PM attributes from /sys/devices/.../power (or prevent them from being
+      added when the device is registered)
+
+  void pm_runtime_mark_last_busy(struct device *dev);
+    - set the power.last_busy field to the current time
+
+  void pm_runtime_use_autosuspend(struct device *dev);
+    - set the power.use_autosuspend flag, enabling autosuspend delays
+
+  void pm_runtime_dont_use_autosuspend(struct device *dev);
+    - clear the power.use_autosuspend flag, disabling autosuspend delays
+
+  void pm_runtime_set_autosuspend_delay(struct device *dev, int delay);
+    - set the power.autosuspend_delay value to 'delay' (expressed in
+      milliseconds); if 'delay' is negative then run-time suspends are
+      prevented
+
+  unsigned long pm_runtime_autosuspend_expiration(struct device *dev);
+    - calculate the time when the current autosuspend delay period will expire,
+      based on power.last_busy and power.autosuspend_delay; if the delay time
+      is 1000 ms or larger then the expiration time is rounded up to the
+      nearest second; returns 0 if the delay period has already expired or
+      power.use_autosuspend isn't set, otherwise returns the expiration time
+      in jiffies
+
 It is safe to execute the following helper functions from interrupt context:
 
 pm_request_idle()
+pm_request_autosuspend()
 pm_schedule_suspend()
 pm_request_resume()
 pm_runtime_get_noresume()
 pm_runtime_get()
 pm_runtime_put_noidle()
 pm_runtime_put()
+pm_runtime_put_autosuspend()
+pm_runtime_enable()
 pm_suspend_ignore_children()
 pm_runtime_set_active()
 pm_runtime_set_suspended()
-pm_runtime_enable()
+pm_runtime_suspended()
+pm_runtime_mark_last_busy()
+pm_runtime_autosuspend_expiration()
 
 5. Run-time PM Initialization, Device Probing and Removal
 
@@ -524,3 +599,141 @@ poweroff and run-time suspend callback, and similarly for system resume, thaw,
 restore, and run-time resume, can achieve this with the help of the
 UNIVERSAL_DEV_PM_OPS macro defined in include/linux/pm.h (possibly setting its
 last argument to NULL).
+
+8. "No-Callback" Devices
+
+Some "devices" are only logical sub-devices of their parent and cannot be
+power-managed on their own.  (The prototype example is a USB interface.  Entire
+USB devices can go into low-power mode or send wake-up requests, but neither is
+possible for individual interfaces.)  The drivers for these devices have no
+need of run-time PM callbacks; if the callbacks did exist, ->runtime_suspend()
+and ->runtime_resume() would always return 0 without doing anything else and
+->runtime_idle() would always call pm_runtime_suspend().
+
+Subsystems can tell the PM core about these devices by calling
+pm_runtime_no_callbacks().  This should be done after the device structure is
+initialized and before it is registered (although after device registration is
+also okay).  The routine will set the device's power.no_callbacks flag and
+prevent the non-debugging run-time PM sysfs attributes from being created.
+
+When power.no_callbacks is set, the PM core will not invoke the
+->runtime_idle(), ->runtime_suspend(), or ->runtime_resume() callbacks.
+Instead it will assume that suspends and resumes always succeed and that idle
+devices should be suspended.
+
+As a consequence, the PM core will never directly inform the device's subsystem
+or driver about run-time power changes.  Instead, the driver for the device's
+parent must take responsibility for telling the device's driver when the
+parent's power state changes.
+
+9. Autosuspend, or automatically-delayed suspends
+
+Changing a device's power state isn't free; it requires both time and energy.
+A device should be put in a low-power state only when there's some reason to
+think it will remain in that state for a substantial time.  A common heuristic
+says that a device which hasn't been used for a while is liable to remain
+unused; following this advice, drivers should not allow devices to be suspended
+at run-time until they have been inactive for some minimum period.  Even when
+the heuristic ends up being non-optimal, it will still prevent devices from
+"bouncing" too rapidly between low-power and full-power states.
+
+The term "autosuspend" is an historical remnant.  It doesn't mean that the
+device is automatically suspended (the subsystem or driver still has to call
+the appropriate PM routines); rather it means that run-time suspends will
+automatically be delayed until the desired period of inactivity has elapsed.
+
+Inactivity is determined based on the power.last_busy field.  Drivers should
+call pm_runtime_mark_last_busy() to update this field after carrying out I/O,
+typically just before calling pm_runtime_put_autosuspend().  The desired length
+of the inactivity period is a matter of policy.  Subsystems can set this length
+initially by calling pm_runtime_set_autosuspend_delay(), but after device
+registration the length should be controlled by user space, using the
+/sys/devices/.../power/autosuspend_delay_ms attribute.
+
+In order to use autosuspend, subsystems or drivers must call
+pm_runtime_use_autosuspend() (preferably before registering the device), and
+thereafter they should use the various *_autosuspend() helper functions instead
+of the non-autosuspend counterparts:
+
+	Instead of: pm_runtime_suspend    use: pm_runtime_autosuspend;
+	Instead of: pm_schedule_suspend   use: pm_request_autosuspend;
+	Instead of: pm_runtime_put        use: pm_runtime_put_autosuspend;
+	Instead of: pm_runtime_put_sync   use: pm_runtime_put_sync_autosuspend.
+
+Drivers may also continue to use the non-autosuspend helper functions; they
+will behave normally, not taking the autosuspend delay into account.
+Similarly, if the power.use_autosuspend field isn't set then the autosuspend
+helper functions will behave just like the non-autosuspend counterparts.
+
+The implementation is well suited for asynchronous use in interrupt contexts.
+However such use inevitably involves races, because the PM core can't
+synchronize ->runtime_suspend() callbacks with the arrival of I/O requests.
+This synchronization must be handled by the driver, using its private lock.
+Here is a schematic pseudo-code example:
+
+	foo_read_or_write(struct foo_priv *foo, void *data)
+	{
+		lock(&foo->private_lock);
+		add_request_to_io_queue(foo, data);
+		if (foo->num_pending_requests++ == 0)
+			pm_runtime_get(&foo->dev);
+		if (!foo->is_suspended)
+			foo_process_next_request(foo);
+		unlock(&foo->private_lock);
+	}
+
+	foo_io_completion(struct foo_priv *foo, void *req)
+	{
+		lock(&foo->private_lock);
+		if (--foo->num_pending_requests == 0) {
+			pm_runtime_mark_last_busy(&foo->dev);
+			pm_runtime_put_autosuspend(&foo->dev);
+		} else {
+			foo_process_next_request(foo);
+		}
+		unlock(&foo->private_lock);
+		/* Send req result back to the user ... */
+	}
+
+	int foo_runtime_suspend(struct device *dev)
+	{
+		struct foo_priv foo = container_of(dev, ...);
+		int ret = 0;
+
+		lock(&foo->private_lock);
+		if (foo->num_pending_requests > 0) {
+			ret = -EBUSY;
+		} else {
+			/* ... suspend the device ... */
+			foo->is_suspended = 1;
+		}
+		unlock(&foo->private_lock);
+		return ret;
+	}
+
+	int foo_runtime_resume(struct device *dev)
+	{
+		struct foo_priv foo = container_of(dev, ...);
+
+		lock(&foo->private_lock);
+		/* ... resume the device ... */
+		foo->is_suspended = 0;
+		pm_runtime_mark_last_busy(&foo->dev);
+		if (foo->num_pending_requests > 0)
+			foo_process_requests(foo);
+		unlock(&foo->private_lock);
+		return 0;
+	}
+
+The important point is that after foo_io_completion() asks for an autosuspend,
+the foo_runtime_suspend() callback may race with foo_read_or_write().
+Therefore foo_runtime_suspend() has to check whether there are any pending I/O
+requests (while holding the private lock) before allowing the suspend to
+proceed.
+
+In addition, the power.autosuspend_delay field can be changed by user space at
+any time.  If a driver cares about this, it can call
+pm_runtime_autosuspend_expiration() from within the ->runtime_suspend()
+callback while holding its private lock.  If the function returns a nonzero
+value then the delay has not yet expired and the callback should return
+-EAGAIN.

Documentation/power/s2ram.txt

@@ -49,6 +49,13 @@ machine that doesn't boot) is:
    device (lspci and /sys/devices/pci* is your friend), and see if you can
    fix it, disable it, or trace into its resume function.
 
+   If no device matches the hash (or any matches appear to be false positives),
+   the culprit may be a device from a loadable kernel module that is not loaded
+   until after the hash is checked. You can check the hash against the current
+   devices again after more modules are loaded using sysfs:
+
+	cat /sys/power/pm_trace_dev_match
+
 For example, the above happens to be the VGA device on my EVO, which I
 used to run with "radeonfb" (it's an ATI Radeon mobility). It turns out
 that "radeonfb" simply cannot resume that device - it tries to set the

Documentation/power/swsusp.txt

@@ -66,7 +66,8 @@ swsusp saves the state of the machine into active swaps and then reboots or
 powerdowns.  You must explicitly specify the swap partition to resume from with
 ``resume='' kernel option. If signature is found it loads and restores saved
 state. If the option ``noresume'' is specified as a boot parameter, it skips
-the resuming.
+the resuming.  If the option ``hibernate=nocompress'' is specified as a boot
+parameter, it saves hibernation image without compression.
 
 In the meantime while the system is suspended you should not add/remove any
 of the hardware, write to the filesystems, etc.

drivers/base/power/Makefile

@@ -3,6 +3,7 @@ obj-$(CONFIG_PM_SLEEP)	+= main.o wakeup.o
 obj-$(CONFIG_PM_RUNTIME)	+= runtime.o
 obj-$(CONFIG_PM_OPS)	+= generic_ops.o
 obj-$(CONFIG_PM_TRACE_RTC)	+= trace.o
+obj-$(CONFIG_PM_OPP)	+= opp.o
 
 ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG
 ccflags-$(CONFIG_PM_VERBOSE)   += -DDEBUG

drivers/base/power/generic_ops.c

@@ -46,7 +46,7 @@ int pm_generic_runtime_suspend(struct device *dev)
 	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
 	int ret;
 
-	ret = pm && pm->runtime_suspend ? pm->runtime_suspend(dev) : -EINVAL;
+	ret = pm && pm->runtime_suspend ? pm->runtime_suspend(dev) : 0;
 
 	return ret;
 }
@@ -65,7 +65,7 @@ int pm_generic_runtime_resume(struct device *dev)
 	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
 	int ret;
 
-	ret = pm && pm->runtime_resume ? pm->runtime_resume(dev) : -EINVAL;
+	ret = pm && pm->runtime_resume ? pm->runtime_resume(dev) : 0;
 
 	return ret;
 }

drivers/base/power/main.c

@@ -51,6 +51,8 @@ static pm_message_t pm_transition;
  */
 static bool transition_started;
 
+static int async_error;
+
 /**
  * device_pm_init - Initialize the PM-related part of a device object.
  * @dev: Device object being initialized.
@@ -60,7 +62,8 @@ void device_pm_init(struct device *dev)
 	dev->power.status = DPM_ON;
 	init_completion(&dev->power.completion);
 	complete_all(&dev->power.completion);
-	dev->power.wakeup_count = 0;
+	dev->power.wakeup = NULL;
+	spin_lock_init(&dev->power.lock);
 	pm_runtime_init(dev);
 }
 
@@ -120,6 +123,7 @@ void device_pm_remove(struct device *dev)
 	mutex_lock(&dpm_list_mtx);
 	list_del_init(&dev->power.entry);
 	mutex_unlock(&dpm_list_mtx);
+	device_wakeup_disable(dev);
 	pm_runtime_remove(dev);
 }
 
@@ -407,7 +411,7 @@ static void pm_dev_err(struct device *dev, pm_message_t state, char *info,
 static void dpm_show_time(ktime_t starttime, pm_message_t state, char *info)
 {
 	ktime_t calltime;
-	s64 usecs64;
+	u64 usecs64;
 	int usecs;
 
 	calltime = ktime_get();
@@ -600,6 +604,7 @@ static void dpm_resume(pm_message_t state)
 	INIT_LIST_HEAD(&list);
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
+	async_error = 0;
 
 	list_for_each_entry(dev, &dpm_list, power.entry) {
 		if (dev->power.status < DPM_OFF)
@@ -829,8 +834,6 @@ static int legacy_suspend(struct device *dev, pm_message_t state,
 	return error;
 }
 
-static int async_error;
-
 /**
  * device_suspend - Execute "suspend" callbacks for given device.
  * @dev: Device to handle.
@@ -885,6 +888,9 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 	device_unlock(dev);
 	complete_all(&dev->power.completion);
 
+	if (error)
+		async_error = error;
+
 	return error;
 }
 
@@ -894,10 +900,8 @@ static void async_suspend(void *data, async_cookie_t cookie)
 	int error;
 
 	error = __device_suspend(dev, pm_transition, true);
-	if (error) {
+	if (error)
 		pm_dev_err(dev, pm_transition, " async", error);
-		async_error = error;
-	}
 
 	put_device(dev);
 }
@@ -1085,8 +1089,9 @@ EXPORT_SYMBOL_GPL(__suspend_report_result);
  * @dev: Device to wait for.
  * @subordinate: Device that needs to wait for @dev.
  */
-void device_pm_wait_for_dev(struct device *subordinate, struct device *dev)
+int device_pm_wait_for_dev(struct device *subordinate, struct device *dev)
 {
 	dpm_wait(dev, subordinate->power.async_suspend);
+	return async_error;
 }
 EXPORT_SYMBOL_GPL(device_pm_wait_for_dev);

drivers/base/power/power.h

@@ -34,6 +34,7 @@ extern void device_pm_move_last(struct device *);
 
 static inline void device_pm_init(struct device *dev)
 {
+	spin_lock_init(&dev->power.lock);
 	pm_runtime_init(dev);
 }
 
@@ -59,6 +60,7 @@ static inline void device_pm_move_last(struct device *dev) {}
 
 extern int dpm_sysfs_add(struct device *);
 extern void dpm_sysfs_remove(struct device *);
+extern void rpm_sysfs_remove(struct device *);
 
 #else /* CONFIG_PM */
 

drivers/base/power/sysfs.c

@@ -75,12 +75,27 @@
  *	attribute is set to "enabled" by bus type code or device drivers and in
  *	that cases it should be safe to leave the default value.
  *
+ *	autosuspend_delay_ms - Report/change a device's autosuspend_delay value
+ *
+ *	Some drivers don't want to carry out a runtime suspend as soon as a
+ *	device becomes idle; they want it always to remain idle for some period
+ *	of time before suspending it.  This period is the autosuspend_delay
+ *	value (expressed in milliseconds) and it can be controlled by the user.
+ *	If the value is negative then the device will never be runtime
+ *	suspended.
+ *
+ *	NOTE: The autosuspend_delay_ms attribute and the autosuspend_delay
+ *	value are used only if the driver calls pm_runtime_use_autosuspend().
+ *
  *	wakeup_count - Report the number of wakeup events related to the device
  */
 
 static const char enabled[] = "enabled";
 static const char disabled[] = "disabled";
 
+const char power_group_name[] = "power";
+EXPORT_SYMBOL_GPL(power_group_name);
+
 #ifdef CONFIG_PM_RUNTIME
 static const char ctrl_auto[] = "auto";
 static const char ctrl_on[] = "on";
@@ -170,6 +185,33 @@ static ssize_t rtpm_status_show(struct device *dev,
 }
 
 static DEVICE_ATTR(runtime_status, 0444, rtpm_status_show, NULL);
+
+static ssize_t autosuspend_delay_ms_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	if (!dev->power.use_autosuspend)
+		return -EIO;
+	return sprintf(buf, "%d\n", dev->power.autosuspend_delay);
+}
+
+static ssize_t autosuspend_delay_ms_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t n)
+{
+	long delay;
+
+	if (!dev->power.use_autosuspend)
+		return -EIO;
+
+	if (strict_strtol(buf, 10, &delay) != 0 || delay != (int) delay)
+		return -EINVAL;
+
+	pm_runtime_set_autosuspend_delay(dev, delay);
+	return n;
+}
+
+static DEVICE_ATTR(autosuspend_delay_ms, 0644, autosuspend_delay_ms_show,
+		autosuspend_delay_ms_store);
+
 #endif
 
 static ssize_t
@@ -210,11 +252,122 @@ static DEVICE_ATTR(wakeup, 0644, wake_show, wake_store);
 static ssize_t wakeup_count_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%lu\n", dev->power.wakeup_count);
+	unsigned long count = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		count = dev->power.wakeup->event_count;
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
 }
 
 static DEVICE_ATTR(wakeup_count, 0444, wakeup_count_show, NULL);
-#endif
+
+static ssize_t wakeup_active_count_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	unsigned long count = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		count = dev->power.wakeup->active_count;
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_active_count, 0444, wakeup_active_count_show, NULL);
+
+static ssize_t wakeup_hit_count_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	unsigned long count = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		count = dev->power.wakeup->hit_count;
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_hit_count, 0444, wakeup_hit_count_show, NULL);
+
+static ssize_t wakeup_active_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	unsigned int active = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		active = dev->power.wakeup->active;
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%u\n", active) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_active, 0444, wakeup_active_show, NULL);
+
+static ssize_t wakeup_total_time_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	s64 msec = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		msec = ktime_to_ms(dev->power.wakeup->total_time);
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_total_time_ms, 0444, wakeup_total_time_show, NULL);
+
+static ssize_t wakeup_max_time_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	s64 msec = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		msec = ktime_to_ms(dev->power.wakeup->max_time);
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_max_time_ms, 0444, wakeup_max_time_show, NULL);
+
+static ssize_t wakeup_last_time_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	s64 msec = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		msec = ktime_to_ms(dev->power.wakeup->last_time);
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_last_time_ms, 0444, wakeup_last_time_show, NULL);
+#endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_PM_ADVANCED_DEBUG
 #ifdef CONFIG_PM_RUNTIME
@@ -279,19 +432,20 @@ static DEVICE_ATTR(async, 0644, async_show, async_store);
 #endif /* CONFIG_PM_ADVANCED_DEBUG */
 
 static struct attribute * power_attrs[] = {
-#ifdef CONFIG_PM_RUNTIME
-	&dev_attr_control.attr,
-	&dev_attr_runtime_status.attr,
-	&dev_attr_runtime_suspended_time.attr,
-	&dev_attr_runtime_active_time.attr,
-#endif
 	&dev_attr_wakeup.attr,
 #ifdef CONFIG_PM_SLEEP
 	&dev_attr_wakeup_count.attr,
+	&dev_attr_wakeup_active_count.attr,
+	&dev_attr_wakeup_hit_count.attr,
+	&dev_attr_wakeup_active.attr,
+	&dev_attr_wakeup_total_time_ms.attr,
+	&dev_attr_wakeup_max_time_ms.attr,
+	&dev_attr_wakeup_last_time_ms.attr,
 #endif
 #ifdef CONFIG_PM_ADVANCED_DEBUG
 	&dev_attr_async.attr,
 #ifdef CONFIG_PM_RUNTIME
+	&dev_attr_runtime_status.attr,
 	&dev_attr_runtime_usage.attr,
 	&dev_attr_runtime_active_kids.attr,
 	&dev_attr_runtime_enabled.attr,
@@ -300,10 +454,53 @@ static struct attribute * power_attrs[] = {
 	NULL,
 };
 static struct attribute_group pm_attr_group = {
-	.name	= "power",
+	.name	= power_group_name,
 	.attrs	= power_attrs,
 };
 
+#ifdef CONFIG_PM_RUNTIME
+
+static struct attribute *runtime_attrs[] = {
+#ifndef CONFIG_PM_ADVANCED_DEBUG
+	&dev_attr_runtime_status.attr,
+#endif
+	&dev_attr_control.attr,
+	&dev_attr_runtime_suspended_time.attr,
+	&dev_attr_runtime_active_time.attr,
+	&dev_attr_autosuspend_delay_ms.attr,
+	NULL,
+};
+static struct attribute_group pm_runtime_attr_group = {
+	.name	= power_group_name,
+	.attrs	= runtime_attrs,
+};
+
+int dpm_sysfs_add(struct device *dev)
+{
+	int rc;
+
+	rc = sysfs_create_group(&dev->kobj, &pm_attr_group);
+	if (rc == 0 && !dev->power.no_callbacks) {
+		rc = sysfs_merge_group(&dev->kobj, &pm_runtime_attr_group);
+		if (rc)
+			sysfs_remove_group(&dev->kobj, &pm_attr_group);
+	}
+	return rc;
+}
+
+void rpm_sysfs_remove(struct device *dev)
+{
+	sysfs_unmerge_group(&dev->kobj, &pm_runtime_attr_group);
+}
+
+void dpm_sysfs_remove(struct device *dev)
+{
+	rpm_sysfs_remove(dev);
+	sysfs_remove_group(&dev->kobj, &pm_attr_group);
+}
+
+#else /* CONFIG_PM_RUNTIME */
+
 int dpm_sysfs_add(struct device * dev)
 {
 	return sysfs_create_group(&dev->kobj, &pm_attr_group);
@@ -313,3 +510,5 @@ void dpm_sysfs_remove(struct device * dev)
 {
 	sysfs_remove_group(&dev->kobj, &pm_attr_group);
 }
+
+#endif

drivers/base/power/trace.c

@@ -188,8 +188,10 @@ static int show_file_hash(unsigned int value)
 static int show_dev_hash(unsigned int value)
 {
 	int match = 0;
-	struct list_head *entry = dpm_list.prev;
+	struct list_head *entry;
 
+	device_pm_lock();
+	entry = dpm_list.prev;
 	while (entry != &dpm_list) {
 		struct device * dev = to_device(entry);
 		unsigned int hash = hash_string(DEVSEED, dev_name(dev), DEVHASH);
@@ -199,11 +201,43 @@ static int show_dev_hash(unsigned int value)
 		}
 		entry = entry->prev;
 	}
+	device_pm_unlock();
 	return match;
 }
 
 static unsigned int hash_value_early_read;
 
+int show_trace_dev_match(char *buf, size_t size)
+{
+	unsigned int value = hash_value_early_read / (USERHASH * FILEHASH);
+	int ret = 0;
+	struct list_head *entry;
+
+	/*
+	 * It's possible that multiple devices will match the hash and we can't
+	 * tell which is the culprit, so it's best to output them all.
+	 */
+	device_pm_lock();
+	entry = dpm_list.prev;
+	while (size && entry != &dpm_list) {
+		struct device *dev = to_device(entry);
+		unsigned int hash = hash_string(DEVSEED, dev_name(dev),
+						DEVHASH);
+		if (hash == value) {
+			int len = snprintf(buf, size, "%s\n",
+					    dev_driver_string(dev));
+			if (len > size)
+				len = size;
+			buf += len;
+			ret += len;
+			size -= len;
+		}
+		entry = entry->prev;
+	}
+	device_pm_unlock();
+	return ret;
+}
+
 static int early_resume_init(void)
 {
 	hash_value_early_read = read_magic_time();

fs/sysfs/group.c

@@ -148,6 +148,65 @@ void sysfs_remove_group(struct kobject * kobj,
 	sysfs_put(sd);
 }
 
+/**
+ * sysfs_merge_group - merge files into a pre-existing attribute group.
+ * @kobj:	The kobject containing the group.
+ * @grp:	The files to create and the attribute group they belong to.
+ *
+ * This function returns an error if the group doesn't exist or any of the
+ * files already exist in that group, in which case none of the new files
+ * are created.
+ */
+int sysfs_merge_group(struct kobject *kobj,
+		       const struct attribute_group *grp)
+{
+	struct sysfs_dirent *dir_sd;
+	int error = 0;
+	struct attribute *const *attr;
+	int i;
+
+	if (grp)
+		dir_sd = sysfs_get_dirent(kobj->sd, NULL, grp->name);
+	else
+		dir_sd = sysfs_get(kobj->sd);
+	if (!dir_sd)
+		return -ENOENT;
+
+	for ((i = 0, attr = grp->attrs); *attr && !error; (++i, ++attr))
+		error = sysfs_add_file(dir_sd, *attr, SYSFS_KOBJ_ATTR);
+	if (error) {
+		while (--i >= 0)
+			sysfs_hash_and_remove(dir_sd, NULL, (*--attr)->name);
+	}
+	sysfs_put(dir_sd);
+
+	return error;
+}
+EXPORT_SYMBOL_GPL(sysfs_merge_group);
+
+/**
+ * sysfs_unmerge_group - remove files from a pre-existing attribute group.
+ * @kobj:	The kobject containing the group.
+ * @grp:	The files to remove and the attribute group they belong to.
+ */
+void sysfs_unmerge_group(struct kobject *kobj,
+		       const struct attribute_group *grp)
+{
+	struct sysfs_dirent *dir_sd;
+	struct attribute *const *attr;
+
+	if (grp)
+		dir_sd = sysfs_get_dirent(kobj->sd, NULL, grp->name);
+	else
+		dir_sd = sysfs_get(kobj->sd);
+	if (dir_sd) {
+		for (attr = grp->attrs; *attr; ++attr)
+			sysfs_hash_and_remove(dir_sd, NULL, (*attr)->name);
+		sysfs_put(dir_sd);
+	}
+}
+EXPORT_SYMBOL_GPL(sysfs_unmerge_group);
+
 
 EXPORT_SYMBOL_GPL(sysfs_create_group);
 EXPORT_SYMBOL_GPL(sysfs_update_group);

include/linux/opp.h

@@ -0,0 +1,105 @@
+/*
+ * Generic OPP Interface
+ *
+ * Copyright (C) 2009-2010 Texas Instruments Incorporated.
+ *	Nishanth Menon
+ *	Romit Dasgupta
+ *	Kevin Hilman
+ *
+ * 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_OPP_H__
+#define __LINUX_OPP_H__
+
+#include <linux/err.h>
+#include <linux/cpufreq.h>
+
+struct opp;
+
+#if defined(CONFIG_PM_OPP)
+
+unsigned long opp_get_voltage(struct opp *opp);
+
+unsigned long opp_get_freq(struct opp *opp);
+
+int opp_get_opp_count(struct device *dev);
+
+struct opp *opp_find_freq_exact(struct device *dev, unsigned long freq,
+				bool available);
+
+struct opp *opp_find_freq_floor(struct device *dev, unsigned long *freq);
+
+struct opp *opp_find_freq_ceil(struct device *dev, unsigned long *freq);
+
+int opp_add(struct device *dev, unsigned long freq, unsigned long u_volt);
+
+int opp_enable(struct device *dev, unsigned long freq);
+
+int opp_disable(struct device *dev, unsigned long freq);
+
+#else
+static inline unsigned long opp_get_voltage(struct opp *opp)
+{
+	return 0;
+}
+
+static inline unsigned long opp_get_freq(struct opp *opp)
+{
+	return 0;
+}
+
+static inline int opp_get_opp_count(struct device *dev)
+{
+	return 0;
+}
+
+static inline struct opp *opp_find_freq_exact(struct device *dev,
+					unsigned long freq, bool available)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline struct opp *opp_find_freq_floor(struct device *dev,
+					unsigned long *freq)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline struct opp *opp_find_freq_ceil(struct device *dev,
+					unsigned long *freq)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline int opp_add(struct device *dev, unsigned long freq,
+					unsigned long u_volt)
+{
+	return -EINVAL;
+}
+
+static inline int opp_enable(struct device *dev, unsigned long freq)
+{
+	return 0;
+}
+
+static inline int opp_disable(struct device *dev, unsigned long freq)
+{
+	return 0;
+}
+#endif		/* CONFIG_PM */
+
+#if defined(CONFIG_CPU_FREQ) && defined(CONFIG_PM_OPP)
+int opp_init_cpufreq_table(struct device *dev,
+			    struct cpufreq_frequency_table **table);
+#else
+static inline int opp_init_cpufreq_table(struct device *dev,
+			    struct cpufreq_frequency_table **table)
+{
+	return -EINVAL;
+}
+#endif		/* CONFIG_CPU_FREQ */
+
+#endif		/* __LINUX_OPP_H__ */