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: (21 commits)
  PM / Hibernate: Reduce autotuned default image size
  PM / Core: Introduce struct syscore_ops for core subsystems PM
  PM QoS: Make pm_qos settings readable
  PM / OPP: opp_find_freq_exact() documentation fix
  PM: Documentation/power/states.txt: fix repetition
  PM: Make system-wide PM and runtime PM treat subsystems consistently
  PM: Simplify kernel/power/Kconfig
  PM: Add support for device power domains
  PM: Drop pm_flags that is not necessary
  PM: Allow pm_runtime_suspend() to succeed during system suspend
  PM: Clean up PM_TRACE dependencies and drop unnecessary Kconfig option
  PM: Remove CONFIG_PM_OPS
  PM: Reorder power management Kconfig options
  PM: Make CONFIG_PM depend on (CONFIG_PM_SLEEP || CONFIG_PM_RUNTIME)
  PM / ACPI: Remove references to pm_flags from bus.c
  PM: Do not create wakeup sysfs files for devices that cannot wake up
  USB / Hub: Do not call device_set_wakeup_capable() under spinlock
  PM: Use appropriate printk() priority level in trace.c
  PM / Wakeup: Don't update events_check_enabled in pm_get_wakeup_count()
  PM / Wakeup: Make pm_save_wakeup_count() work as documented
  ...

Documentation/ABI/testing/sysfs-devices-power

@@ -29,9 +29,8 @@ Description:
 		"disabled" to it.
 
 		For the devices that are not capable of generating system wakeup
-		events this file contains "\n".  In that cases the user space
-		cannot modify the contents of this file and the device cannot be
-		enabled to wake up the system.
+		events this file is not present.  In that case the device cannot
+		be enabled to wake up the system from sleep states.
 
 What:		/sys/devices/.../power/control
 Date:		January 2009
@@ -85,7 +84,7 @@ 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.
+		the system from sleep states, this attribute is not present.
 
 What:		/sys/devices/.../power/wakeup_active_count
 Date:		September 2010
@@ -95,7 +94,7 @@ Description:
 		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.
+		system from sleep states, this attribute is not present.
 
 What:		/sys/devices/.../power/wakeup_hit_count
 Date:		September 2010
@@ -105,7 +104,8 @@ Description:
 		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.
+		wake up the system from sleep states, this attribute is not
+		present.
 
 What:		/sys/devices/.../power/wakeup_active
 Date:		September 2010
@@ -115,7 +115,7 @@ Description:
 		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.
+		states, this attribute is not present.
 
 What:		/sys/devices/.../power/wakeup_total_time_ms
 Date:		September 2010
@@ -125,7 +125,7 @@ Description:
 		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.
+		this attribute is not present.
 
 What:		/sys/devices/.../power/wakeup_max_time_ms
 Date:		September 2010
@@ -135,7 +135,7 @@ Description:
 		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.
+		states, this attribute is not present.
 
 What:		/sys/devices/.../power/wakeup_last_time_ms
 Date:		September 2010
@@ -146,7 +146,7 @@ Description:
 		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.
+		attribute is not present.
 
 What:		/sys/devices/.../power/autosuspend_delay_ms
 Date:		September 2010

Documentation/power/devices.txt

@@ -1,6 +1,6 @@
 Device Power Management
 
-Copyright (c) 2010 Rafael J. Wysocki <[email protected]>, Novell Inc.
+Copyright (c) 2010-2011 Rafael J. Wysocki <[email protected]>, Novell Inc.
 Copyright (c) 2010 Alan Stern <[email protected]>
 
 
@@ -159,18 +159,18 @@ matter, and the kernel is responsible for keeping track of it.  By contrast,
 whether or not a wakeup-capable device should issue wakeup events is a policy
 decision, and it is managed by user space through a sysfs attribute: the
 power/wakeup file.  User space can write the strings "enabled" or "disabled" to
-set or clear the should_wakeup flag, respectively.  Reads from the file will
-return the corresponding string if can_wakeup is true, but if can_wakeup is
-false then reads will return an empty string, to indicate that the device
-doesn't support wakeup events.  (But even though the file appears empty, writes
-will still affect the should_wakeup flag.)
+set or clear the "should_wakeup" flag, respectively.  This file is only present
+for wakeup-capable devices (i.e. devices whose "can_wakeup" flags are set)
+and is created (or removed) by device_set_wakeup_capable().  Reads from the
+file will return the corresponding string.
 
 The device_may_wakeup() routine returns true only if both flags are set.
-Drivers should check this routine when putting devices in a low-power state
-during a system sleep transition, to see whether or not to enable the devices'
-wakeup mechanisms.  However for runtime power management, wakeup events should
-be enabled whenever the device and driver both support them, regardless of the
-should_wakeup flag.
+This information is used by subsystems, like the PCI bus type code, to see
+whether or not to enable the devices' wakeup mechanisms.  If device wakeup
+mechanisms are enabled or disabled directly by drivers, they also should use
+device_may_wakeup() to decide what to do during a system sleep transition.
+However for runtime power management, wakeup events should be enabled whenever
+the device and driver both support them, regardless of the should_wakeup flag.
 
 
 /sys/devices/.../power/control files
@@ -249,23 +249,18 @@ various phases always run after tasks have been frozen and before they are
 unfrozen.  Furthermore, the *_noirq phases run at a time when IRQ handlers have
 been disabled (except for those marked with the IRQ_WAKEUP flag).
 
-Most phases use bus, type, and class callbacks (that is, methods defined in
-dev->bus->pm, dev->type->pm, and dev->class->pm).  The prepare and complete
-phases are exceptions; they use only bus callbacks.  When multiple callbacks
-are used in a phase, they are invoked in the order: <class, type, bus> during
-power-down transitions and in the opposite order during power-up transitions.
-For example, during the suspend phase the PM core invokes
-
-	dev->class->pm.suspend(dev);
-	dev->type->pm.suspend(dev);
-	dev->bus->pm.suspend(dev);
-
-before moving on to the next device, whereas during the resume phase the core
-invokes
-
-	dev->bus->pm.resume(dev);
-	dev->type->pm.resume(dev);
-	dev->class->pm.resume(dev);
+All phases use bus, type, or class callbacks (that is, methods defined in
+dev->bus->pm, dev->type->pm, or dev->class->pm).  These callbacks are mutually
+exclusive, so if the device type provides a struct dev_pm_ops object pointed to
+by its pm field (i.e. both dev->type and dev->type->pm are defined), the
+callbacks included in that object (i.e. dev->type->pm) will be used.  Otherwise,
+if the class provides a struct dev_pm_ops object pointed to by its pm field
+(i.e. both dev->class and dev->class->pm are defined), the PM core will use the
+callbacks from that object (i.e. dev->class->pm).  Finally, if the pm fields of
+both the device type and class objects are NULL (or those objects do not exist),
+the callbacks provided by the bus (that is, the callbacks from dev->bus->pm)
+will be used (this allows device types to override callbacks provided by bus
+types or classes if necessary).
 
 These callbacks may in turn invoke device- or driver-specific methods stored in
 dev->driver->pm, but they don't have to.
@@ -507,6 +502,49 @@ routines.  Nevertheless, different callback pointers are used in case there is a
 situation where it actually matters.
 
 
+Device Power Domains
+--------------------
+Sometimes devices share reference clocks or other power resources.  In those
+cases it generally is not possible to put devices into low-power states
+individually.  Instead, a set of devices sharing a power resource can be put
+into a low-power state together at the same time by turning off the shared
+power resource.  Of course, they also need to be put into the full-power state
+together, by turning the shared power resource on.  A set of devices with this
+property is often referred to as a power domain.
+
+Support for power domains is provided through the pwr_domain field of struct
+device.  This field is a pointer to an object of type struct dev_power_domain,
+defined in include/linux/pm.h, providing a set of power management callbacks
+analogous to the subsystem-level and device driver callbacks that are executed
+for the given device during all power transitions, in addition to the respective
+subsystem-level callbacks.  Specifically, the power domain "suspend" callbacks
+(i.e. ->runtime_suspend(), ->suspend(), ->freeze(), ->poweroff(), etc.) are
+executed after the analogous subsystem-level callbacks, while the power domain
+"resume" callbacks (i.e. ->runtime_resume(), ->resume(), ->thaw(), ->restore,
+etc.) are executed before the analogous subsystem-level callbacks.  Error codes
+returned by the "suspend" and "resume" power domain callbacks are ignored.
+
+Power domain ->runtime_idle() callback is executed before the subsystem-level
+->runtime_idle() callback and the result returned by it is not ignored.  Namely,
+if it returns error code, the subsystem-level ->runtime_idle() callback will not
+be called and the helper function rpm_idle() executing it will return error
+code.  This mechanism is intended to help platforms where saving device state
+is a time consuming operation and should only be carried out if all devices
+in the power domain are idle, before turning off the shared power resource(s).
+Namely, the power domain ->runtime_idle() callback may return error code until
+the pm_runtime_idle() helper (or its asychronous version) has been called for
+all devices in the power domain (it is recommended that the returned error code
+be -EBUSY in those cases), preventing the subsystem-level ->runtime_idle()
+callback from being run prematurely.
+
+The support for device power domains is only relevant to platforms needing to
+use the same subsystem-level (e.g. platform bus type) and device driver power
+management callbacks in many different power domain configurations and wanting
+to avoid incorporating the support for power domains into the subsystem-level
+callbacks.  The other platforms need not implement it or take it into account
+in any way.
+
+
 System Devices
 --------------
 System devices (sysdevs) follow a slightly different API, which can be found in

Documentation/power/runtime_pm.txt

@@ -1,6 +1,6 @@
 Run-time Power Management Framework for I/O Devices
 
-(C) 2009 Rafael J. Wysocki <[email protected]>, Novell Inc.
+(C) 2009-2011 Rafael J. Wysocki <[email protected]>, Novell Inc.
 (C) 2010 Alan Stern <[email protected]>
 
 1. Introduction
@@ -44,11 +44,12 @@ struct dev_pm_ops {
 };
 
 The ->runtime_suspend(), ->runtime_resume() and ->runtime_idle() callbacks are
-executed by the PM core for either the bus type, or device type (if the bus
-type's callback is not defined), or device class (if the bus type's and device
-type's callbacks are not defined) of given device.  The bus type, device type
-and device class callbacks are referred to as subsystem-level callbacks in what
-follows.
+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.
 
 By default, the callbacks are always invoked in process context with interrupts
 enabled.  However, subsystems can use the pm_runtime_irq_safe() helper function

Documentation/power/states.txt

@@ -62,12 +62,12 @@ setup via another operating system for it to use. Despite the
 inconvenience, this method requires minimal work by the kernel, since
 the firmware will also handle restoring memory contents on resume. 
 
-For suspend-to-disk, a mechanism called swsusp called 'swsusp' (Swap
-Suspend) is used to write memory contents to free swap space.
-swsusp has some restrictive requirements, but should work in most
-cases. Some, albeit outdated, documentation can be found in
-Documentation/power/swsusp.txt. Alternatively, userspace can do most
-of the actual suspend to disk work, see userland-swsusp.txt.
+For suspend-to-disk, a mechanism called 'swsusp' (Swap Suspend) is used
+to write memory contents to free swap space. swsusp has some restrictive
+requirements, but should work in most cases. Some, albeit outdated,
+documentation can be found in Documentation/power/swsusp.txt.
+Alternatively, userspace can do most of the actual suspend to disk work,
+see userland-swsusp.txt.
 
 Once memory state is written to disk, the system may either enter a
 low-power state (like ACPI S4), or it may simply power down. Powering

arch/x86/kernel/apm_32.c

@@ -227,6 +227,7 @@
 #include <linux/suspend.h>
 #include <linux/kthread.h>
 #include <linux/jiffies.h>
+#include <linux/acpi.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -2331,12 +2332,11 @@ static int __init apm_init(void)
 		apm_info.disabled = 1;
 		return -ENODEV;
 	}
-	if (pm_flags & PM_ACPI) {
+	if (!acpi_disabled) {
 		printk(KERN_NOTICE "apm: overridden by ACPI.\n");
 		apm_info.disabled = 1;
 		return -ENODEV;
 	}
-	pm_flags |= PM_APM;
 
 	/*
 	 * Set up the long jump entry point to the APM BIOS, which is called
@@ -2428,7 +2428,6 @@ static void __exit apm_exit(void)
 		kthread_stop(kapmd_task);
 		kapmd_task = NULL;
 	}
-	pm_flags &= ~PM_APM;
 }
 
 module_init(apm_init);

arch/x86/xen/Kconfig

@@ -38,7 +38,7 @@ config XEN_MAX_DOMAIN_MEMORY
 
 config XEN_SAVE_RESTORE
        bool
-       depends on XEN && PM
+       depends on XEN
        default y
 
 config XEN_DEBUG_FS

drivers/acpi/Kconfig

@@ -7,7 +7,6 @@ menuconfig ACPI
 	depends on !IA64_HP_SIM
 	depends on IA64 || X86
 	depends on PCI
-	depends on PM
 	select PNP
 	default y
 	help

drivers/acpi/bus.c

@@ -40,6 +40,7 @@
 #include <acpi/acpi_bus.h>
 #include <acpi/acpi_drivers.h>
 #include <linux/dmi.h>
+#include <linux/suspend.h>
 
 #include "internal.h"
 
@@ -1006,8 +1007,7 @@ struct kobject *acpi_kobj;
 
 static int __init acpi_init(void)
 {
-	int result = 0;
-
+	int result;
 
 	if (acpi_disabled) {
 		printk(KERN_INFO PREFIX "Interpreter disabled.\n");
@@ -1022,29 +1022,18 @@ static int __init acpi_init(void)
 
 	init_acpi_device_notify();
 	result = acpi_bus_init();
-
-	if (!result) {
-		pci_mmcfg_late_init();
-		if (!(pm_flags & PM_APM))
-			pm_flags |= PM_ACPI;
-		else {
-			printk(KERN_INFO PREFIX
-			       "APM is already active, exiting\n");
-			disable_acpi();
-			result = -ENODEV;
-		}
-	} else
+	if (result) {
 		disable_acpi();
-
-	if (acpi_disabled)
 		return result;
+	}
 
+	pci_mmcfg_late_init();
 	acpi_scan_init();
 	acpi_ec_init();
 	acpi_debugfs_init();
 	acpi_sleep_proc_init();
 	acpi_wakeup_device_init();
-	return result;
+	return 0;
 }
 
 subsys_initcall(acpi_init);

drivers/acpi/sleep.c

@@ -585,7 +585,7 @@ int acpi_suspend(u32 acpi_state)
 	return -EINVAL;
 }
 
-#ifdef CONFIG_PM_OPS
+#ifdef CONFIG_PM
 /**
  *	acpi_pm_device_sleep_state - return preferred power state of ACPI device
  *		in the system sleep state given by %acpi_target_sleep_state
@@ -671,7 +671,7 @@ int acpi_pm_device_sleep_state(struct device *dev, int *d_min_p)
 		*d_min_p = d_min;
 	return d_max;
 }
-#endif /* CONFIG_PM_OPS */
+#endif /* CONFIG_PM */
 
 #ifdef CONFIG_PM_SLEEP
 /**

drivers/base/Makefile

@@ -1,6 +1,6 @@
 # Makefile for the Linux device tree
 
-obj-y			:= core.o sys.o bus.o dd.o \
+obj-y			:= core.o sys.o bus.o dd.o syscore.o \
 			   driver.o class.o platform.o \
 			   cpu.o firmware.o init.o map.o devres.o \
 			   attribute_container.o transport_class.o

drivers/base/power/Makefile

@@ -1,7 +1,6 @@
-obj-$(CONFIG_PM)	+= sysfs.o
+obj-$(CONFIG_PM)	+= sysfs.o generic_ops.o
 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