Merge master.kernel.org:/pub/scm/linux/kernel/git/gregkh/driver-2.6

* master.kernel.org:/pub/scm/linux/kernel/git/gregkh/driver-2.6: (47 commits)
  Driver core: Don't call put methods while holding a spinlock
  Driver core: Remove unneeded routines from driver core
  Driver core: Fix potential deadlock in driver core
  PCI: enable driver multi-threaded probe
  Driver Core: add ability for drivers to do a threaded probe
  sysfs: add proper sysfs_init() prototype
  drivers/base: check errors
  drivers/base: Platform notify needs to occur before drivers attach to the device
  v4l-dev2: handle __must_check
  add CONFIG_ENABLE_MUST_CHECK
  add __must_check to device management code
  Driver core: fixed add_bind_files() definition
  Driver core: fix comments in drivers/base/power/resume.c
  sysfs_remove_bin_file: no return value, dump_stack on error
  kobject: must_check fixes
  Driver core: add ability for devices to create and remove bin files
  Class: add support for class interfaces for devices
  Driver core: create devices/virtual/ tree
  Driver core: add device_rename function
  Driver core: add ability for classes to handle devices properly
  ...

Documentation/ABI/removed/devfs

@@ -1,13 +1,12 @@
 What:		devfs
-Date:		July 2005
+Date:		July 2005 (scheduled), finally removed in kernel v2.6.18
 Contact:	Greg Kroah-Hartman <gregkh@suse.de>
 Description:
 	devfs has been unmaintained for a number of years, has unfixable
 	races, contains a naming policy within the kernel that is
 	against the LSB, and can be replaced by using udev.
-	The files fs/devfs/*, include/linux/devfs_fs*.h will be removed,
+	The files fs/devfs/*, include/linux/devfs_fs*.h were removed,
 	along with the the assorted devfs function calls throughout the
 	kernel tree.
 
 Users:
-

Documentation/ABI/testing/sysfs-power

@@ -0,0 +1,88 @@
+What:		/sys/power/
+Date:		August 2006
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/power directory will contain files that will
+		provide a unified interface to the power management
+		subsystem.
+
+What:		/sys/power/state
+Date:		August 2006
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/power/state file controls the system power state.
+		Reading from this file returns what states are supported,
+		which is hard-coded to 'standby' (Power-On Suspend), 'mem'
+		(Suspend-to-RAM), and 'disk' (Suspend-to-Disk).
+
+		Writing to this file one of these strings causes the system to
+		transition into that state. Please see the file
+		Documentation/power/states.txt for a description of each of
+		these states.
+
+What:		/sys/power/disk
+Date:		August 2006
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/power/disk file controls the operating mode of the
+		suspend-to-disk mechanism.  Reading from this file returns
+		the name of the method by which the system will be put to
+		sleep on the next suspend.  There are four methods supported:
+		'firmware' - means that the memory image will be saved to disk
+		by some firmware, in which case we also assume that the
+		firmware will handle the system suspend.
+		'platform' - the memory image will be saved by the kernel and
+		the system will be put to sleep by the platform driver (e.g.
+		ACPI or other PM registers).
+		'shutdown' - the memory image will be saved by the kernel and
+		the system will be powered off.
+		'reboot' - the memory image will be saved by the kernel and
+		the system will be rebooted.
+
+		The suspend-to-disk method may be chosen by writing to this
+		file one of the accepted strings:
+
+		'firmware'
+		'platform'
+		'shutdown'
+		'reboot'
+
+		It will only change to 'firmware' or 'platform' if the system
+		supports that.
+
+What:		/sys/power/image_size
+Date:		August 2006
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/power/image_size file controls the size of the image
+		created by the suspend-to-disk mechanism.  It can be written a
+		string representing a non-negative integer that will be used
+		as an upper limit of the image size, in bytes.  The kernel's
+		suspend-to-disk code will do its best to ensure the image size
+		will not exceed this number.  However, if it turns out to be
+		impossible, the kernel will try to suspend anyway using the
+		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.
+
+What:		/sys/power/pm_trace
+Date:		August 2006
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/power/pm_trace file 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 during suspend (or more
+		commonly, during resume).  Namely, the RTC is only used to save
+		the last PM event point if this file contains '1'.  Initially
+		it contains '0' which may be changed to '1' by writing a
+		string representing a nonzero integer into it.
+
+		To use this debugging feature you should attempt to suspend
+		the machine, then reboot it and run
+
+		dmesg -s 1000000 | grep 'hash matches'
+
+		CAUTION: Using it will cause your machine's real-time (CMOS)
+		clock to be set to a random invalid time after a resume.

Documentation/feature-removal-schedule.txt

@@ -6,6 +6,21 @@ be removed from this file.
 
 ---------------------------
 
+What:	/sys/devices/.../power/state
+	dev->power.power_state
+	dpm_runtime_{suspend,resume)()
+When:	July 2007
+Why:	Broken design for runtime control over driver power states, confusing
+	driver-internal runtime power management with:  mechanisms to support
+	system-wide sleep state transitions; event codes that distinguish
+	different phases of swsusp "sleep" transitions; and userspace policy
+	inputs.  This framework was never widely used, and most attempts to
+	use it were broken.  Drivers should instead be exposing domain-specific
+	interfaces either to kernel or to userspace.
+Who:	Pavel Machek <pavel@suse.cz>
+
+---------------------------
+
 What:	RAW driver (CONFIG_RAW_DRIVER)
 When:	December 2005
 Why:	declared obsolete since kernel 2.6.3
@@ -294,3 +309,15 @@ Why:	The frame diverter is included in most distribution kernels, but is
 	It is not clear if anyone is still using it.
 Who:	Stephen Hemminger <shemminger@osdl.org>
 
+---------------------------
+
+
+What:	PHYSDEVPATH, PHYSDEVBUS, PHYSDEVDRIVER in the uevent environment
+When:	Oktober 2008
+Why:	The stacking of class devices makes these values misleading and
+	inconsistent.
+	Class devices should not carry any of these properties, and bus
+	devices have SUBSYTEM and DRIVER as a replacement.
+Who:	Kay Sievers <kay.sievers@suse.de>
+
+---------------------------

Documentation/power/devices.txt

@@ -1,208 +1,553 @@
+Most of the code in Linux is device drivers, so most of the Linux power
+management code is also driver-specific.  Most drivers will do very little;
+others, especially for platforms with small batteries (like cell phones),
+will do a lot.
 
-Device Power Management
+This writeup gives an overview of how drivers interact with system-wide
+power management goals, emphasizing the models and interfaces that are
+shared by everything that hooks up to the driver model core.  Read it as
+background for the domain-specific work you'd do with any specific driver.
 
 
-Device power management encompasses two areas - the ability to save
+Two Models for Device Power Management
-state and transition a device to a low-power state when the system is
+======================================
-entering a low-power state; and the ability to transition a device to
+Drivers will use one or both of these models to put devices into low-power
-a low-power state while the system is running (and independently of
+states:
-any other power management activity). 
+
+    System Sleep model:
+	Drivers can enter low power states as part of entering system-wide
+	low-power states like "suspend-to-ram", or (mostly for systems with
+	disks) "hibernate" (suspend-to-disk).
+
+	This is something that device, bus, and class drivers collaborate on
+	by implementing various role-specific suspend and resume methods to
+	cleanly power down hardware and software subsystems, then reactivate
+	them without loss of data.
+
+	Some drivers can manage hardware wakeup events, which make the system
+	leave that low-power state.  This feature may be disabled using the
+	relevant /sys/devices/.../power/wakeup file; enabling it may cost some
+	power usage, but let the whole system enter low power states more often.
+
+    Runtime Power Management model:
+	Drivers may also enter low power states while the system is running,
+	independently of other power management activity.  Upstream drivers
+	will normally not know (or care) if the device is in some low power
+	state when issuing requests; the driver will auto-resume anything
+	that's needed when it gets a request.
+
+	This doesn't have, or need much infrastructure; it's just something you
+	should do when writing your drivers.  For example, clk_disable() unused
+	clocks as part of minimizing power drain for currently-unused hardware.
+	Of course, sometimes clusters of drivers will collaborate with each
+	other, which could involve task-specific power management.
+
+There's not a lot to be said about those low power states except that they
+are very system-specific, and often device-specific.  Also, that if enough
+drivers put themselves into low power states (at "runtime"), the effect may be
+the same as entering some system-wide low-power state (system sleep) ... and
+that synergies exist, so that several drivers using runtime pm might put the
+system into a state where even deeper power saving options are available.
+
+Most suspended devices will have quiesced all I/O:  no more DMA or irqs, no
+more data read or written, and requests from upstream drivers are no longer
+accepted.  A given bus or platform may have different requirements though.
+
+Examples of hardware wakeup events include an alarm from a real time clock,
+network wake-on-LAN packets, keyboard or mouse activity, and media insertion
+or removal (for PCMCIA, MMC/SD, USB, and so on).
 
 
-Methods
+Interfaces for Entering System Sleep States
+===========================================
+Most of the programming interfaces a device driver needs to know about
+relate to that first model:  entering a system-wide low power state,
+rather than just minimizing power consumption by one device.
 
-The methods to suspend and resume devices reside in struct bus_type: 
+
+Bus Driver Methods
+------------------
+The core methods to suspend and resume devices reside in struct bus_type.
+These are mostly of interest to people writing infrastructure for busses
+like PCI or USB, or because they define the primitives that device drivers
+may need to apply in domain-specific ways to their devices:
 
 struct bus_type {
-       ...
+	...
-       int             (*suspend)(struct device * dev, pm_message_t state);
+	int  (*suspend)(struct device *dev, pm_message_t state);
-       int             (*resume)(struct device * dev);
+	int  (*suspend_late)(struct device *dev, pm_message_t state);
+
+	int  (*resume_early)(struct device *dev);
+	int  (*resume)(struct device *dev);
 };
 
-Each bus driver is responsible implementing these methods, translating
+Bus drivers implement those methods as appropriate for the hardware and
-the call into a bus-specific request and forwarding the call to the
+the drivers using it; PCI works differently from USB, and so on.  Not many
-bus-specific drivers. For example, PCI drivers implement suspend() and
+people write bus drivers; most driver code is a "device driver" that
-resume() methods in struct pci_driver. The PCI core is simply
+builds on top of bus-specific framework code.
-responsible for translating the pointers to PCI-specific ones and
-calling the low-level driver.
 
-This is done to a) ease transition to the new power management methods
+For more information on these driver calls, see the description later;
-and leverage the existing PM code in various bus drivers; b) allow
+they are called in phases for every device, respecting the parent-child
-buses to implement generic and default PM routines for devices, and c)
+sequencing in the driver model tree.  Note that as this is being written,
-make the flow of execution obvious to the reader. 
+only the suspend() and resume() are widely available; not many bus drivers
+leverage all of those phases, or pass them down to lower driver levels.
 
 
-System Power Management
+/sys/devices/.../power/wakeup files
+-----------------------------------
+All devices in the driver model have two flags to control handling of
+wakeup events, which are hardware signals that can force the device and/or
+system out of a low power state.  These are initialized by bus or device
+driver code using device_init_wakeup(dev,can_wakeup).
 
-When the system enters a low-power state, the device tree is walked in
+The "can_wakeup" flag just records whether the device (and its driver) can
-a depth-first fashion to transition each device into a low-power
+physically support wakeup events.  When that flag is clear, the sysfs
-state. The ordering of the device tree is guaranteed by the order in
+"wakeup" file is empty, and device_may_wakeup() returns false.
-which devices get registered - children are never registered before
-their ancestors, and devices are placed at the back of the list when
-registered. By walking the list in reverse order, we are guaranteed to
-suspend devices in the proper order. 
 
-Devices are suspended once with interrupts enabled. Drivers are
+For devices that can issue wakeup events, a separate flag controls whether
-expected to stop I/O transactions, save device state, and place the
+that device should try to use its wakeup mechanism.  The initial value of
-device into a low-power state. Drivers may sleep, allocate memory,
+device_may_wakeup() will be true, so that the device's "wakeup" file holds
-etc. at will. 
+the value "enabled".  Userspace can change that to "disabled" so that
+device_may_wakeup() returns false; or change it back to "enabled" (so that
+it returns true again).
 
-Some devices are broken and will inevitably have problems powering
-down or disabling themselves with interrupts enabled. For these
-special cases, they may return -EAGAIN. This will put the device on a
-list to be taken care of later. When interrupts are disabled, before
-we enter the low-power state, their drivers are called again to put
-their device to sleep. 
 
-On resume, the devices that returned -EAGAIN will be called to power
+EXAMPLE:  PCI Device Driver Methods
-themselves back on with interrupts disabled. Once interrupts have been
+-----------------------------------
-re-enabled, the rest of the drivers will be called to resume their
+PCI framework software calls these methods when the PCI device driver bound
-devices. On resume, a driver is responsible for powering back on each
+to a device device has provided them:
-device, restoring state, and re-enabling I/O transactions for that
-device. 
 
+struct pci_driver {
+	...
+	int  (*suspend)(struct pci_device *pdev, pm_message_t state);
+	int  (*suspend_late)(struct pci_device *pdev, pm_message_t state);
+
+	int  (*resume_early)(struct pci_device *pdev);
+	int  (*resume)(struct pci_device *pdev);
+};
+
+Drivers will implement those methods, and call PCI-specific procedures
+like pci_set_power_state(), pci_enable_wake(), pci_save_state(), and
+pci_restore_state() to manage PCI-specific mechanisms.  (PCI config space
+could be saved during driver probe, if it weren't for the fact that some
+systems rely on userspace tweaking using setpci.)  Devices are suspended
+before their bridges enter low power states, and likewise bridges resume
+before their devices.
+
+
+Upper Layers of Driver Stacks
+-----------------------------
+Device drivers generally have at least two interfaces, and the methods
+sketched above are the ones which apply to the lower level (nearer PCI, USB,
+or other bus hardware).  The network and block layers are examples of upper
+level interfaces, as is a character device talking to userspace.
+
+Power management requests normally need to flow through those upper levels,
+which often use domain-oriented requests like "blank that screen".  In
+some cases those upper levels will have power management intelligence that
+relates to end-user activity, or other devices that work in cooperation.
+
+When those interfaces are structured using class interfaces, there is a
+standard way to have the upper layer stop issuing requests to a given
+class device (and restart later):
+
+struct class {
+	...
+	int  (*suspend)(struct device *dev, pm_message_t state);
+	int  (*resume)(struct device *dev);
+};
+
+Those calls are issued in specific phases of the process by which the
+system enters a low power "suspend" state, or resumes from it.
+
+
+Calling Drivers to Enter System Sleep States
+============================================
+When the system enters a low power state, each device's driver is asked
+to suspend the device by putting it into state compatible with the target
+system state.  That's usually some version of "off", but the details are
+system-specific.  Also, wakeup-enabled devices will usually stay partly
+functional in order to wake the system.
+
+When the system leaves that low power state, the device's driver is asked
+to resume it.  The suspend and resume operations always go together, and
+both are multi-phase operations.
+
+For simple drivers, suspend might quiesce the device using the class code
+and then turn its hardware as "off" as possible with late_suspend.  The
+matching resume calls would then completely reinitialize the hardware
+before reactivating its class I/O queues.
+
+More power-aware drivers drivers will use more than one device low power
+state, either at runtime or during system sleep states, and might trigger
+system wakeup events.
+
+
+Call Sequence Guarantees
+------------------------
+To ensure that bridges and similar links needed to talk to a device are
+available when the device is suspended or resumed, the device tree is
+walked in a bottom-up order to suspend devices.  A top-down order is
+used to resume those devices.
+
+The ordering of the device tree is defined by the order in which devices
+get registered:  a child can never be registered, probed or resumed before
+its parent; and can't be removed or suspended after that parent.
+
+The policy is that the device tree should match hardware bus topology.
+(Or at least the control bus, for devices which use multiple busses.)
+
+
+Suspending Devices
+------------------
+Suspending a given device is done in several phases.  Suspending the
+system always includes every phase, executing calls for every device
+before the next phase begins.  Not all busses or classes support all
+these callbacks; and not all drivers use all the callbacks.
+
+The phases are seen by driver notifications issued in this order:
+
+   1	class.suspend(dev, message) is called after tasks are frozen, for
+	devices associated with a class that has such a method.  This
+	method may sleep.
+
+	Since I/O activity usually comes from such higher layers, this is
+	a good place to quiesce all drivers of a given type (and keep such
+	code out of those drivers).
+
+   2	bus.suspend(dev, message) is called next.  This method may sleep,
+	and is often morphed into a device driver call with bus-specific
+	parameters and/or rules.
+
+	This call should handle parts of device suspend logic that require
+	sleeping.  It probably does work to quiesce the device which hasn't
+	been abstracted into class.suspend() or bus.suspend_late().
+
+   3	bus.suspend_late(dev, message) is called with IRQs disabled, and
+	with only one CPU active.  Until the bus.resume_early() phase
+	completes (see later), IRQs are not enabled again.  This method
+	won't be exposed by all busses; for message based busses like USB,
+	I2C, or SPI, device interactions normally require IRQs.  This bus
+	call may be morphed into a driver call with bus-specific parameters.
+
+	This call might save low level hardware state that might otherwise
+	be lost in the upcoming low power state, and actually put the
+	device into a low power state ... so that in some cases the device
+	may stay partly usable until this late.  This "late" call may also
+	help when coping with hardware that behaves badly.
+
+The pm_message_t parameter is currently used to refine those semantics
+(described later).
+
+At the end of those phases, drivers should normally have stopped all I/O
+transactions (DMA, IRQs), saved enough state that they can re-initialize
+or restore previous state (as needed by the hardware), and placed the
+device into a low-power state.  On many platforms they will also use
+clk_disable() to gate off one or more clock sources; sometimes they will
+also switch off power supplies, or reduce voltages.  Drivers which have
+runtime PM support may already have performed some or all of the steps
+needed to prepare for the upcoming system sleep state.
+
+When any driver sees that its device_can_wakeup(dev), it should make sure
+to use the relevant hardware signals to trigger a system wakeup event.
+For example, enable_irq_wake() might identify GPIO signals hooked up to
+a switch or other external hardware, and pci_enable_wake() does something
+similar for PCI's PME# signal.
+
+If a driver (or bus, or class) fails it suspend method, the system won't
+enter the desired low power state; it will resume all the devices it's
+suspended so far.
+
+Note that drivers may need to perform different actions based on the target
+system lowpower/sleep state.  At this writing, there are only platform
+specific APIs through which drivers could determine those target states.
+
+
+Device Low Power (suspend) States
+---------------------------------
+Device low-power states aren't very standard.  One device might only handle
+"on" and "off, while another might support a dozen different versions of
+"on" (how many engines are active?), plus a state that gets back to "on"
+faster than from a full "off".
+
+Some busses define rules about what different suspend states mean.  PCI
+gives one example:  after the suspend sequence completes, a non-legacy
+PCI device may not perform DMA or issue IRQs, and any wakeup events it
+issues would be issued through the PME# bus signal.  Plus, there are
+several PCI-standard device states, some of which are optional.
+
+In contrast, integrated system-on-chip processors often use irqs as the
+wakeup event sources (so drivers would call enable_irq_wake) and might
+be able to treat DMA completion as a wakeup event (sometimes DMA can stay
+active too, it'd only be the CPU and some peripherals that sleep).
+
+Some details here may be platform-specific.  Systems may have devices that
+can be fully active in certain sleep states, such as an LCD display that's
+refreshed using DMA while most of the system is sleeping lightly ... and
+its frame buffer might even be updated by a DSP or other non-Linux CPU while
+the Linux control processor stays idle.
+
+Moreover, the specific actions taken may depend on the target system state.
+One target system state might allow a given device to be very operational;
+another might require a hard shut down with re-initialization on resume.
+And two different target systems might use the same device in different
+ways; the aforementioned LCD might be active in one product's "standby",
+but a different product using the same SOC might work differently.
+
+
+Meaning of pm_message_t.event
+-----------------------------
+Parameters to suspend calls include the device affected and a message of
+type pm_message_t, which has one field:  the event.  If driver does not
+recognize the event code, suspend calls may abort the request and return
+a negative errno.  However, most drivers will be fine if they implement
+PM_EVENT_SUSPEND semantics for all messages.
+
+The event codes are used to refine the goal of suspending the device, and
+mostly matter when creating or resuming system memory image snapshots, as
+used with suspend-to-disk:
+
+    PM_EVENT_SUSPEND -- quiesce the driver and put hardware into a low-power
+	state.  When used with system sleep states like "suspend-to-RAM" or
+	"standby", the upcoming resume() call will often be able to rely on
+	state kept in hardware, or issue system wakeup events.  When used
+	instead with suspend-to-disk, few devices support this capability;
+	most are completely powered off.
+
+    PM_EVENT_FREEZE -- quiesce the driver, but don't necessarily change into
+	any low power mode.  A system snapshot is about to be taken, often
+	followed by a call to the driver's resume() method.  Neither wakeup
+	events nor DMA are allowed.
+
+    PM_EVENT_PRETHAW -- quiesce the driver, knowing that the upcoming resume()
+	will restore a suspend-to-disk snapshot from a different kernel image.
+	Drivers that are smart enough to look at their hardware state during
+	resume() processing need that state to be correct ... a PRETHAW could
+	be used to invalidate that state (by resetting the device), like a
+	shutdown() invocation would before a kexec() or system halt.  Other
+	drivers might handle this the same way as PM_EVENT_FREEZE.  Neither
+	wakeup events nor DMA are allowed.
+
+To enter "standby" (ACPI S1) or "Suspend to RAM" (STR, ACPI S3) states, or
+the similarly named APM states, only PM_EVENT_SUSPEND is used; for "Suspend
+to Disk" (STD, hibernate, ACPI S4), all of those event codes are used.
+
+There's also PM_EVENT_ON, a value which never appears as a suspend event
+but is sometimes used to record the "not suspended" device state.
+
+
+Resuming Devices
+----------------
+Resuming is done in multiple phases, much like suspending, with all
+devices processing each phase's calls before the next phase begins.
+
+The phases are seen by driver notifications issued in this order:
+
+   1	bus.resume_early(dev) is called with IRQs disabled, and with
+   	only one CPU active.  As with bus.suspend_late(), this method
+	won't be supported on busses that require IRQs in order to
+	interact with devices.
+
+	This reverses the effects of bus.suspend_late().
+
+   2	bus.resume(dev) is called next.  This may be morphed into a device
+   	driver call with bus-specific parameters; implementations may sleep.
+
+	This reverses the effects of bus.suspend().
+
+   3	class.resume(dev) is called for devices associated with a class
+	that has such a method.  Implementations may sleep.
+
+	This reverses the effects of class.suspend(), and would usually
+	reactivate the device's I/O queue.
+
+At the end of those phases, drivers should normally be as functional as
+they were before suspending:  I/O can be performed using DMA and IRQs, and
+the relevant clocks are gated on.  The device need not be "fully on"; it
+might be in a runtime lowpower/suspend state that acts as if it were.
+
+However, the details here may again be platform-specific.  For example,
+some systems support multiple "run" states, and the mode in effect at
+the end of resume() might not be the one which preceded suspension.
+That means availability of certain clocks or power supplies changed,
+which could easily affect how a driver works.
+
+
+Drivers need to be able to handle hardware which has been reset since the
+suspend methods were called, for example by complete reinitialization.
+This may be the hardest part, and the one most protected by NDA'd documents
+and chip errata.  It's simplest if the hardware state hasn't changed since
+the suspend() was called, but that can't always be guaranteed.
+
+Drivers must also be prepared to notice that the device has been removed
+while the system was powered off, whenever that's physically possible.
+PCMCIA, MMC, USB, Firewire, SCSI, and even IDE are common examples of busses
+where common Linux platforms will see such removal.  Details of how drivers
+will notice and handle such removals are currently bus-specific, and often
+involve a separate thread.
+
+
+Note that the bus-specific runtime PM wakeup mechanism can exist, and might
+be defined to share some of the same driver code as for system wakeup.  For
+example, a bus-specific device driver's resume() method might be used there,
+so it wouldn't only be called from bus.resume() during system-wide wakeup.
+See bus-specific information about how runtime wakeup events are handled.
+
+
+System Devices
+--------------
 System devices follow a slightly different API, which can be found in
 
 	include/linux/sysdev.h
 	drivers/base/sys.c
 
-System devices will only be suspended with interrupts disabled, and
+System devices will only be suspended with interrupts disabled, and after
-after all other devices have been suspended. On resume, they will be
+all other devices have been suspended.  On resume, they will be resumed
-resumed before any other devices, and also with interrupts disabled.
+before any other devices, and also with interrupts disabled.
+
+That is, IRQs are disabled, the suspend_late() phase begins, then the
+sysdev_driver.suspend() phase, and the system enters a sleep state.  Then
+the sysdev_driver.resume() phase begins, followed by the resume_early()
+phase, after which IRQs are enabled.
+
+Code to actually enter and exit the system-wide low power state sometimes
+involves hardware details that are only known to the boot firmware, and
+may leave a CPU running software (from SRAM or flash memory) that monitors
+the system and manages its wakeup sequence.
 
 
 Runtime Power Management
+========================
+Many devices are able to dynamically power down while the system is still
+running. This feature is useful for devices that are not being used, and
+can offer significant power savings on a running system.  These devices
+often support a range of runtime power states, which might use names such
+as "off", "sleep", "idle", "active", and so on.  Those states will in some
+cases (like PCI) be partially constrained by a bus the device uses, and will
+usually include hardware states that are also used in system sleep states.
 
-Many devices are able to dynamically power down while the system is
+However, note that if a driver puts a device into a runtime low power state
-still running. This feature is useful for devices that are not being
+and the system then goes into a system-wide sleep state, it normally ought
-used, and can offer significant power savings on a running system. 
+to resume into that runtime low power state rather than "full on".  Such
+distinctions would be part of the driver-internal state machine for that
+hardware; the whole point of runtime power management is to be sure that
+drivers are decoupled in that way from the state machine governing phases
+of the system-wide power/sleep state transitions.
 
-In each device's directory, there is a 'power' directory, which
-contains at least a 'state' file. Reading from this file displays what
-power state the device is currently in. Writing to this file initiates
-a transition to the specified power state, which must be a decimal in
-the range 1-3, inclusive; or 0 for 'On'.
 
-The PM core will call the ->suspend() method in the bus_type object
+Power Saving Techniques
-that the device belongs to if the specified state is not 0, or
+-----------------------
-->resume() if it is. 
+Normally runtime power management is handled by the drivers without specific
+userspace or kernel intervention, by device-aware use of techniques like:
 
-Nothing will happen if the specified state is the same state the
+    Using information provided by other system layers
-device is currently in. 
+	- stay deeply "off" except between open() and close()
+	- if transceiver/PHY indicates "nobody connected", stay "off"
+	- application protocols may include power commands or hints
 
-If the device is already in a low-power state, and the specified state
+    Using fewer CPU cycles
-is another, but different, low-power state, the ->resume() method will
+	- using DMA instead of PIO
-first be called to power the device back on, then ->suspend() will be
+	- removing timers, or making them lower frequency
-called again with the new state. 
+	- shortening "hot" code paths
+	- eliminating cache misses
+	- (sometimes) offloading work to device firmware
 
-The driver is responsible for saving the working state of the device
+    Reducing other resource costs
-and putting it into the low-power state specified. If this was
+	- gating off unused clocks in software (or hardware)
-successful, it returns 0, and the device's power_state field is
+	- switching off unused power supplies
-updated. 
+	- eliminating (or delaying/merging) IRQs
+	- tuning DMA to use word and/or burst modes
 
-The driver must take care to know whether or not it is able to
+    Using device-specific low power states
-properly resume the device, including all step of reinitialization
+	- using lower voltages
-necessary. (This is the hardest part, and the one most protected by
+	- avoiding needless DMA transfers
-NDA'd documents). 
 
-The driver must also take care not to suspend a device that is
+Read your hardware documentation carefully to see the opportunities that
-currently in use. It is their responsibility to provide their own
+may be available.  If you can, measure the actual power usage and check
-exclusion mechanisms.
+it against the budget established for your project.
 
-The runtime power transition happens with interrupts enabled. If a
-device cannot support being powered down with interrupts, it may
-return -EAGAIN (as it would during a system power management
-transition),  but it will _not_ be called again, and the transaction
-will fail.
 
-There is currently no way to know what states a device or driver
+Examples:  USB hosts, system timer, system CPU
-supports a priori. This will change in the future. 
+----------------------------------------------
+USB host controllers make interesting, if complex, examples.  In many cases
+these have no work to do:  no USB devices are connected, or all of them are
+in the USB "suspend" state.  Linux host controller drivers can then disable
+periodic DMA transfers that would otherwise be a constant power drain on the
+memory subsystem, and enter a suspend state.  In power-aware controllers,
+entering that suspend state may disable the clock used with USB signaling,
+saving a certain amount of power.
 
-pm_message_t meaning
+The controller will be woken from that state (with an IRQ) by changes to the
+signal state on the data lines of a given port, for example by an existing
+peripheral requesting "remote wakeup" or by plugging a new peripheral.  The
+same wakeup mechanism usually works from "standby" sleep states, and on some
+systems also from "suspend to RAM" (or even "suspend to disk") states.
+(Except that ACPI may be involved instead of normal IRQs, on some hardware.)
 
-pm_message_t has two fields. event ("major"), and flags.  If driver
+System devices like timers and CPUs may have special roles in the platform
-does not know event code, it aborts the request, returning error. Some
+power management scheme.  For example, system timers using a "dynamic tick"
-drivers may need to deal with special cases based on the actual type
+approach don't just save CPU cycles (by eliminating needless timer IRQs),
-of suspend operation being done at the system level. This is why
+but they may also open the door to using lower power CPU "idle" states that
-there are flags.
+cost more than a jiffie to enter and exit.  On x86 systems these are states
+like "C3"; note that periodic DMA transfers from a USB host controller will
+also prevent entry to a C3 state, much like a periodic timer IRQ.
 
-Event codes are:
+That kind of runtime mechanism interaction is common.  "System On Chip" (SOC)
+processors often have low power idle modes that can't be entered unless
+certain medium-speed clocks (often 12 or 48 MHz) are gated off.  When the
+drivers gate those clocks effectively, then the system idle task may be able
+to use the lower power idle modes and thereby increase battery life.
 
-ON -- no need to do anything except special cases like broken
+If the CPU can have a "cpufreq" driver, there also may be opportunities
-HW.
+to shift to lower voltage settings and reduce the power cost of executing
+a given number of instructions.  (Without voltage adjustment, it's rare
+for cpufreq to save much power; the cost-per-instruction must go down.)
 
-# NOTIFICATION -- pretty much same as ON?
 
-FREEZE -- stop DMA and interrupts, and be prepared to reinit HW from
+/sys/devices/.../power/state files
-scratch. That probably means stop accepting upstream requests, the
+==================================
-actual policy of what to do with them being specific to a given
+For now you can also test some of this functionality using sysfs.
-driver. It's acceptable for a network driver to just drop packets
-while a block driver is expected to block the queue so no request is
-lost. (Use IDE as an example on how to do that). FREEZE requires no
-power state change, and it's expected for drivers to be able to
-quickly transition back to operating state.
 
-SUSPEND -- like FREEZE, but also put hardware into low-power state. If
+	DEPRECATED:  USE "power/state" ONLY FOR DRIVER TESTING, AND
-there's need to distinguish several levels of sleep, additional flag
+	AVOID USING dev->power.power_state IN DRIVERS.
-is probably best way to do that.
 
-Transitions are only from a resumed state to a suspended state, never
+	THESE WILL BE REMOVED.  IF THE "power/state" FILE GETS REPLACED,
-between 2 suspended states. (ON -> FREEZE or ON -> SUSPEND can happen,
+	IT WILL BECOME SOMETHING COUPLED TO THE BUS OR DRIVER.
-FREEZE -> SUSPEND or SUSPEND -> FREEZE can not).
 
-All events are:
+In each device's directory, there is a 'power' directory, which contains
+at least a 'state' file.  The value of this field is effectively boolean,
+PM_EVENT_ON or PM_EVENT_SUSPEND.
 
-[NOTE NOTE NOTE: If you are driver author, you should not care; you
+   *	Reading from this file displays a value corresponding to
-should only look at event, and ignore flags.]
+	the power.power_state.event field.  All nonzero values are
+	displayed as "2", corresponding to a low power state; zero
+	is displayed as "0", corresponding to normal operation.
 
-#Prepare for suspend -- userland is still running but we are going to
+   *	Writing to this file initiates a transition using the
-#enter suspend state. This gives drivers chance to load firmware from
+   	specified event code number; only '0', '2', and '3' are
-#disk and store it in memory, or do other activities taht require
+	accepted (without a newline); '2' and '3' are both
-#operating userland, ability to kmalloc GFP_KERNEL, etc... All of these
+	mapped to PM_EVENT_SUSPEND.
-#are forbiden once the suspend dance is started.. event = ON, flags =
-#PREPARE_TO_SUSPEND
 
-Apm standby -- prepare for APM event. Quiesce devices to make life
+On writes, the PM core relies on that recorded event code and the device/bus
-easier for APM BIOS. event = FREEZE, flags = APM_STANDBY
+capabilities to determine whether it uses a partial suspend() or resume()
+sequence to change things so that the recorded event corresponds to the
+numeric parameter.
 
-Apm suspend -- same as APM_STANDBY, but it we should probably avoid
+   -	If the bus requires the irqs-disabled suspend_late()/resume_early()
-spinning down disks. event = FREEZE, flags = APM_SUSPEND
+	phases, writes fail because those operations are not supported here.
 
-System halt, reboot -- quiesce devices to make life easier for BIOS. event
+   -	If the recorded value is the expected value, nothing is done.
-= FREEZE, flags = SYSTEM_HALT or SYSTEM_REBOOT
 
-System shutdown -- at least disks need to be spun down, or data may be
+   -	If the recorded value is nonzero, the device is partially resumed,
-lost. Quiesce devices, just to make life easier for BIOS. event =
+	using the bus.resume() and/or class.resume() methods.
-FREEZE, flags = SYSTEM_SHUTDOWN
 
-Kexec    -- turn off DMAs and put hardware into some state where new
+   -	If the target value is nonzero, the device is partially suspended,
-kernel can take over. event = FREEZE, flags = KEXEC
+	using the class.suspend() and/or bus.suspend() methods and the
+	PM_EVENT_SUSPEND message.
 
-Powerdown at end of swsusp -- very similar to SYSTEM_SHUTDOWN, except wake
+Drivers have no way to tell whether their suspend() and resume() calls
-may need to be enabled on some devices. This actually has at least 3
+have come through the sysfs power/state file or as part of entering a
-subtypes, system can reboot, enter S4 and enter S5 at the end of
+system sleep state, except that when accessed through sysfs the normal
-swsusp. event = FREEZE, flags = SWSUSP and one of SYSTEM_REBOOT,
+parent/child sequencing rules are ignored.  Drivers (such as bus, bridge,
-SYSTEM_SHUTDOWN, SYSTEM_S4
+or hub drivers) which expose child devices may need to enforce those rules
-
+on their own.
-Suspend to ram  -- put devices into low power state. event = SUSPEND,
-flags = SUSPEND_TO_RAM
-
-Freeze for swsusp snapshot -- stop DMA and interrupts. No need to put
-devices into low power mode, but you must be able to reinitialize
-device from scratch in resume method. This has two flavors, its done
-once on suspending kernel, once on resuming kernel. event = FREEZE,
-flags = DURING_SUSPEND or DURING_RESUME
-
-Device detach requested from /sys -- deinitialize device; proably same as
-SYSTEM_SHUTDOWN, I do not understand this one too much. probably event
-= FREEZE, flags = DEV_DETACH.
-
-#These are not really events sent:
-#
-#System fully on -- device is working normally; this is probably never
-#passed to suspend() method... event = ON, flags = 0
-#
-#Ready after resume -- userland is now running, again. Time to free any
-#memory you ate during prepare to suspend... event = ON, flags =
-#READY_AFTER_RESUME
-#

drivers/base/base.h

@@ -16,7 +16,7 @@ extern int cpu_dev_init(void);
 extern int attribute_container_init(void);
 
 extern int bus_add_device(struct device * dev);
-extern void bus_attach_device(struct device * dev);
+extern int bus_attach_device(struct device * dev);
 extern void bus_remove_device(struct device * dev);
 extern struct bus_type *get_bus(struct bus_type * bus);
 extern void put_bus(struct bus_type * bus);

drivers/base/bus.c

@@ -371,12 +371,20 @@ int bus_add_device(struct device * dev)
 	if (bus) {
 		pr_debug("bus %s: add device %s\n", bus->name, dev->bus_id);
 		error = device_add_attrs(bus, dev);
-		if (!error) {
+		if (error)
-			sysfs_create_link(&bus->devices.kobj, &dev->kobj, dev->bus_id);
+			goto out;
-			sysfs_create_link(&dev->kobj, &dev->bus->subsys.kset.kobj, "subsystem");
+		error = sysfs_create_link(&bus->devices.kobj,
-			sysfs_create_link(&dev->kobj, &dev->bus->subsys.kset.kobj, "bus");
+						&dev->kobj, dev->bus_id);
-		}
+		if (error)
+			goto out;
+		error = sysfs_create_link(&dev->kobj,
+				&dev->bus->subsys.kset.kobj, "subsystem");
+		if (error)
+			goto out;
+		error = sysfs_create_link(&dev->kobj,
+				&dev->bus->subsys.kset.kobj, "bus");
 	}
+out:
 	return error;
 }
 
@@ -384,16 +392,24 @@ int bus_add_device(struct device * dev)
  *	bus_attach_device - add device to bus
  *	@dev:	device tried to attach to a driver
  *
+ *	- Add device to bus's list of devices.
  *	- Try to attach to driver.
  */
-void bus_attach_device(struct device * dev)
+int bus_attach_device(struct device * dev)
 {
-	struct bus_type * bus = dev->bus;
+	struct bus_type *bus = dev->bus;
+	int ret = 0;
 
 	if (bus) {
-		device_attach(dev);
+		dev->is_registered = 1;
-		klist_add_tail(&dev->knode_bus, &bus->klist_devices);
+		ret = device_attach(dev);
+		if (ret >= 0) {
+			klist_add_tail(&dev->knode_bus, &bus->klist_devices);
+			ret = 0;
+		} else
+			dev->is_registered = 0;
 	}
+	return ret;
 }
 
 /**
@@ -412,7 +428,8 @@ void bus_remove_device(struct device * dev)
 		sysfs_remove_link(&dev->kobj, "bus");
 		sysfs_remove_link(&dev->bus->devices.kobj, dev->bus_id);
 		device_remove_attrs(dev->bus, dev);
-		klist_remove(&dev->knode_bus);
+		dev->is_registered = 0;
+		klist_del(&dev->knode_bus);
 		pr_debug("bus %s: remove device %s\n", dev->bus->name, dev->bus_id);
 		device_release_driver(dev);
 		put_bus(dev->bus);
@@ -455,10 +472,17 @@ static void driver_remove_attrs(struct bus_type * bus, struct device_driver * dr
  * Thanks to drivers making their tables __devinit, we can't allow manual
  * bind and unbind from userspace unless CONFIG_HOTPLUG is enabled.
  */
-static void add_bind_files(struct device_driver *drv)
+static int __must_check add_bind_files(struct device_driver *drv)
 {
-	driver_create_file(drv, &driver_attr_unbind);
+	int ret;
-	driver_create_file(drv, &driver_attr_bind);
+
+	ret = driver_create_file(drv, &driver_attr_unbind);
+	if (ret == 0) {
+		ret = driver_create_file(drv, &driver_attr_bind);
+		if (ret)
+			driver_remove_file(drv, &driver_attr_unbind);
+	}
+	return ret;
 }
 
 static void remove_bind_files(struct device_driver *drv)
@@ -467,7 +491,7 @@ static void remove_bind_files(struct device_driver *drv)
 	driver_remove_file(drv, &driver_attr_unbind);
 }
 #else
-static inline void add_bind_files(struct device_driver *drv) {}
+static inline int add_bind_files(struct device_driver *drv) { return 0; }
 static inline void remove_bind_files(struct device_driver *drv) {}
 #endif
 
@@ -476,7 +500,7 @@ static inline void remove_bind_files(struct device_driver *drv) {}
  *	@drv:	driver.
  *
  */
-int bus_add_driver(struct device_driver * drv)
+int bus_add_driver(struct device_driver *drv)
 {
 	struct bus_type * bus = get_bus(drv->bus);
 	int error = 0;
@@ -484,27 +508,39 @@ int bus_add_driver(struct device_driver * drv)
 	if (bus) {
 		pr_debug("bus %s: add driver %s\n", bus->name, drv->name);
 		error = kobject_set_name(&drv->kobj, "%s", drv->name);
-		if (error) {
+		if (error)
-			put_bus(bus);
+			goto out_put_bus;
-			return error;
-		}
 		drv->kobj.kset = &bus->drivers;
-		if ((error = kobject_register(&drv->kobj))) {
+		if ((error = kobject_register(&drv->kobj)))
-			put_bus(bus);
+			goto out_put_bus;
-			return error;
-		}
 
-		driver_attach(drv);
+		error = driver_attach(drv);
+		if (error)
+			goto out_unregister;
 		klist_add_tail(&drv->knode_bus, &bus->klist_drivers);
 		module_add_driver(drv->owner, drv);
 
-		driver_add_attrs(bus, drv);
+		error = driver_add_attrs(bus, drv);
-		add_bind_files(drv);
+		if (error) {
+			/* How the hell do we get out of this pickle? Give up */
+			printk(KERN_ERR "%s: driver_add_attrs(%s) failed\n",
+				__FUNCTION__, drv->name);
+		}
+		error = add_bind_files(drv);
+		if (error) {
+			/* Ditto */
+			printk(KERN_ERR "%s: add_bind_files(%s) failed\n",
+				__FUNCTION__, drv->name);
+		}
 	}
 	return error;
+out_unregister:
+	kobject_unregister(&drv->kobj);
+out_put_bus:
+	put_bus(bus);
+	return error;
 }
 
-
 /**
  *	bus_remove_driver - delete driver from bus's knowledge.
  *	@drv:	driver.
@@ -530,16 +566,21 @@ void bus_remove_driver(struct device_driver * drv)
 
 
 /* Helper for bus_rescan_devices's iter */
-static int bus_rescan_devices_helper(struct device *dev, void *data)
+static int __must_check bus_rescan_devices_helper(struct device *dev,
+						void *data)
 {
+	int ret = 0;
+
 	if (!dev->driver) {
 		if (dev->parent)	/* Needed for USB */
 			down(&dev->parent->sem);
-		device_attach(dev);
+		ret = device_attach(dev);
 		if (dev->parent)
 			up(&dev->parent->sem);
+		if (ret > 0)
+			ret = 0;
 	}
-	return 0;
+	return ret < 0 ? ret : 0;
 }
 
 /**
@@ -550,9 +591,9 @@ static int bus_rescan_devices_helper(struct device *dev, void *data)
  * attached and rescan it against existing drivers to see if it matches
  * any by calling device_attach() for the unbound devices.
  */
-void bus_rescan_devices(struct bus_type * bus)
+int bus_rescan_devices(struct bus_type * bus)
 {
-	bus_for_each_dev(bus, NULL, NULL, bus_rescan_devices_helper);
+	return bus_for_each_dev(bus, NULL, NULL, bus_rescan_devices_helper);
 }
 
 /**
@@ -564,7 +605,7 @@ void bus_rescan_devices(struct bus_type * bus)
  * to use if probing criteria changed during a devices lifetime and
  * driver attachment should change accordingly.
  */
-void device_reprobe(struct device *dev)
+int device_reprobe(struct device *dev)
 {
 	if (dev->driver) {
 		if (dev->parent)        /* Needed for USB */
@@ -573,14 +614,14 @@ void device_reprobe(struct device *dev)
 		if (dev->parent)
 			up(&dev->parent->sem);
 	}
-
+	return bus_rescan_devices_helper(dev, NULL);
-	bus_rescan_devices_helper(dev, NULL);
 }
 EXPORT_SYMBOL_GPL(device_reprobe);
 
-struct bus_type * get_bus(struct bus_type * bus)
+struct bus_type *get_bus(struct bus_type *bus)
 {
-	return bus ? container_of(subsys_get(&bus->subsys), struct bus_type, subsys) : NULL;
+	return bus ? container_of(subsys_get(&bus->subsys),
+				struct bus_type, subsys) : NULL;
 }
 
 void put_bus(struct bus_type * bus)
@@ -655,22 +696,6 @@ static void klist_devices_put(struct klist_node *n)
 	put_device(dev);
 }
 
-static void klist_drivers_get(struct klist_node *n)
-{
-	struct device_driver *drv = container_of(n, struct device_driver,
-						 knode_bus);
-
-	get_driver(drv);
-}
-
-static void klist_drivers_put(struct klist_node *n)
-{
-	struct device_driver *drv = container_of(n, struct device_driver,
-						 knode_bus);
-
-	put_driver(drv);
-}
-
 /**
  *	bus_register - register a bus with the system.
  *	@bus:	bus.
@@ -706,7 +731,7 @@ int bus_register(struct bus_type * bus)
 		goto bus_drivers_fail;
 
 	klist_init(&bus->klist_devices, klist_devices_get, klist_devices_put);
-	klist_init(&bus->klist_drivers, klist_drivers_get, klist_drivers_put);
+	klist_init(&bus->klist_drivers, NULL, NULL);
 	bus_add_attrs(bus);
 
 	pr_debug("bus type '%s' registered\n", bus->name);

drivers/base/class.c

@@ -19,6 +19,8 @@
 #include <linux/slab.h>
 #include "base.h"
 
+extern struct subsystem devices_subsys;
+
 #define to_class_attr(_attr) container_of(_attr, struct class_attribute, attr)
 #define to_class(obj) container_of(obj, struct class, subsys.kset.kobj)
 
@@ -197,7 +199,7 @@ static int class_device_create_uevent(struct class_device *class_dev,
  * Note, the pointer created here is to be destroyed when finished by
  * making a call to class_destroy().
  */
-struct class *class_create(struct module *owner, char *name)
+struct class *class_create(struct module *owner, const char *name)
 {
 	struct class *cls;
 	int retval;
@@ -361,7 +363,7 @@ static int class_uevent(struct kset *kset, struct kobject *kobj, char **envp,
 	pr_debug("%s - name = %s\n", __FUNCTION__, class_dev->class_id);
 
 	if (class_dev->dev) {
-		/* add physical device, backing this device  */
+		/* add device, backing this class device (deprecated) */
 		struct device *dev = class_dev->dev;
 		char *path = kobject_get_path(&dev->kobj, GFP_KERNEL);
 
@@ -679,7 +681,8 @@ int class_device_register(struct class_device *class_dev)
 struct class_device *class_device_create(struct class *cls,
 					 struct class_device *parent,
 					 dev_t devt,
-					 struct device *device, char *fmt, ...)
+					 struct device *device,
+					 const char *fmt, ...)
 {
 	va_list args;
 	struct class_device *class_dev = NULL;
@@ -839,6 +842,7 @@ int class_interface_register(struct class_interface *class_intf)
 {
 	struct class *parent;
 	struct class_device *class_dev;
+	struct device *dev;
 
 	if (!class_intf || !class_intf->class)
 		return -ENODEV;
@@ -853,6 +857,10 @@ int class_interface_register(struct class_interface *class_intf)
 		list_for_each_entry(class_dev, &parent->children, node)
 			class_intf->add(class_dev, class_intf);
 	}
+	if (class_intf->add_dev) {
+		list_for_each_entry(dev, &parent->devices, node)
+			class_intf->add_dev(dev, class_intf);
+	}
 	up(&parent->sem);
 
 	return 0;
@@ -862,6 +870,7 @@ void class_interface_unregister(struct class_interface *class_intf)
 {
 	struct class * parent = class_intf->class;
 	struct class_device *class_dev;
+	struct device *dev;
 
 	if (!parent)
 		return;
@@ -872,12 +881,31 @@ void class_interface_unregister(struct class_interface *class_intf)
 		list_for_each_entry(class_dev, &parent->children, node)
 			class_intf->remove(class_dev, class_intf);
 	}
+	if (class_intf->remove_dev) {
+		list_for_each_entry(dev, &parent->devices, node)
+			class_intf->remove_dev(dev, class_intf);
+	}
 	up(&parent->sem);
 
 	class_put(parent);
 }
 
+int virtual_device_parent(struct device *dev)
+{
+	if (!dev->class)
+		return -ENODEV;
 
+	if (!dev->class->virtual_dir) {
+		static struct kobject *virtual_dir = NULL;
+
+		if (!virtual_dir)
+			virtual_dir = kobject_add_dir(&devices_subsys.kset.kobj, "virtual");
+		dev->class->virtual_dir = kobject_add_dir(virtual_dir, dev->class->name);
+	}
+
+	dev->kobj.parent = dev->class->virtual_dir;
+	return 0;
+}
 
 int __init classes_init(void)
 {

drivers/base/core.c

@@ -3,6 +3,8 @@
  *
  * Copyright (c) 2002-3 Patrick Mochel
  * Copyright (c) 2002-3 Open Source Development Labs
+ * Copyright (c) 2006 Greg Kroah-Hartman <gregkh@suse.de>
+ * Copyright (c) 2006 Novell, Inc.
  *
  * This file is released under the GPLv2
  *
@@ -92,6 +94,8 @@ static void device_release(struct kobject * kobj)
 
 	if (dev->release)
 		dev->release(dev);
+	else if (dev->class && dev->class->dev_release)
+		dev->class->dev_release(dev);
 	else {
 		printk(KERN_ERR "Device '%s' does not have a release() function, "
 			"it is broken and must be fixed.\n",
@@ -149,17 +153,21 @@ static int dev_uevent(struct kset *kset, struct kobject *kobj, char **envp,
 			       "MINOR=%u", MINOR(dev->devt));
 	}
 
-	/* add bus name of physical device */
+	/* add bus name (same as SUBSYSTEM, deprecated) */
 	if (dev->bus)
 		add_uevent_var(envp, num_envp, &i,
 			       buffer, buffer_size, &length,
 			       "PHYSDEVBUS=%s", dev->bus->name);
 
-	/* add driver name of physical device */
+	/* add driver name (PHYSDEV* values are deprecated)*/
-	if (dev->driver)
+	if (dev->driver) {
+		add_uevent_var(envp, num_envp, &i,
+			       buffer, buffer_size, &length,
+			       "DRIVER=%s", dev->driver->name);
 		add_uevent_var(envp, num_envp, &i,
 			       buffer, buffer_size, &length,
 			       "PHYSDEVDRIVER=%s", dev->driver->name);
+	}
 
 	/* terminate, set to next free slot, shrink available space */
 	envp[i] = NULL;
@@ -177,6 +185,15 @@ static int dev_uevent(struct kset *kset, struct kobject *kobj, char **envp,
 		}
 	}
 
+	if (dev->class && dev->class->dev_uevent) {
+		/* have the class specific function add its stuff */
+		retval = dev->class->dev_uevent(dev, envp, num_envp, buffer, buffer_size);
+			if (retval) {
+				pr_debug("%s - dev_uevent() returned %d\n",
+					 __FUNCTION__, retval);
+		}
+	}
+
 	return retval;
 }
 
@@ -193,6 +210,72 @@ static ssize_t store_uevent(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
+static int device_add_groups(struct device *dev)
+{
+	int i;
+	int error = 0;
+
+	if (dev->groups) {
+		for (i = 0; dev->groups[i]; i++) {
+			error = sysfs_create_group(&dev->kobj, dev->groups[i]);
+			if (error) {
+				while (--i >= 0)
+					sysfs_remove_group(&dev->kobj, dev->groups[i]);
+				goto out;
+			}
+		}
+	}
+out:
+	return error;
+}
+
+static void device_remove_groups(struct device *dev)
+{
+	int i;
+	if (dev->groups) {
+		for (i = 0; dev->groups[i]; i++) {
+			sysfs_remove_group(&dev->kobj, dev->groups[i]);
+		}
+	}
+}
+
+static int device_add_attrs(struct device *dev)
+{
+	struct class *class = dev->class;
+	int error = 0;
+	int i;
+
+	if (!class)
+		return 0;
+
+	if (class->dev_attrs) {
+		for (i = 0; attr_name(class->dev_attrs[i]); i++) {
+			error = device_create_file(dev, &class->dev_attrs[i]);
+			if (error)
+				break;
+		}
+	}
+	if (error)
+		while (--i >= 0)
+			device_remove_file(dev, &class->dev_attrs[i]);
+	return error;
+}
+
+static void device_remove_attrs(struct device *dev)
+{
+	struct class *class = dev->class;
+	int i;
+
+	if (!class)
+		return;
+
+	if (class->dev_attrs) {
+		for (i = 0; attr_name(class->dev_attrs[i]); i++)
+			device_remove_file(dev, &class->dev_attrs[i]);
+	}
+}
+
+
 static ssize_t show_dev(struct device *dev, struct device_attribute *attr,
 			char *buf)
 {
@@ -236,6 +319,32 @@ void device_remove_file(struct device * dev, struct device_attribute * attr)
 	}
 }
 
+/**
+ * device_create_bin_file - create sysfs binary attribute file for device.
+ * @dev: device.
+ * @attr: device binary attribute descriptor.
+ */
+int device_create_bin_file(struct device *dev, struct bin_attribute *attr)
+{
+	int error = -EINVAL;
+	if (dev)
+		error = sysfs_create_bin_file(&dev->kobj, attr);
+	return error;
+}
+EXPORT_SYMBOL_GPL(device_create_bin_file);
+
+/**
+ * device_remove_bin_file - remove sysfs binary attribute file
+ * @dev: device.
+ * @attr: device binary attribute descriptor.
+ */
+void device_remove_bin_file(struct device *dev, struct bin_attribute *attr)
+{
+	if (dev)
+		sysfs_remove_bin_file(&dev->kobj, attr);
+}
+EXPORT_SYMBOL_GPL(device_remove_bin_file);
+
 static void klist_children_get(struct klist_node *n)
 {
 	struct device *dev = container_of(n, struct device, knode_parent);
@@ -289,12 +398,20 @@ int device_add(struct device *dev)
 {
 	struct device *parent = NULL;
 	char *class_name = NULL;
+	struct class_interface *class_intf;
 	int error = -EINVAL;
 
 	dev = get_device(dev);
 	if (!dev || !strlen(dev->bus_id))
 		goto Error;
 
+	/* if this is a class device, and has no parent, create one */
+	if ((dev->class) && (dev->parent == NULL)) {
+		error = virtual_device_parent(dev);
+		if (error)
+			goto Error;
+	}
+
 	parent = get_device(dev->parent);
 
 	pr_debug("DEV: registering device: ID = '%s'\n", dev->bus_id);
@@ -307,6 +424,10 @@ int device_add(struct device *dev)
 	if ((error = kobject_add(&dev->kobj)))
 		goto Error;
 
+	/* notify platform of device entry */
+	if (platform_notify)
+		platform_notify(dev);
+
 	dev->uevent_attr.attr.name = "uevent";
 	dev->uevent_attr.attr.mode = S_IWUSR;
 	if (dev->driver)
@@ -340,12 +461,17 @@ int device_add(struct device *dev)
 				  "subsystem");
 		sysfs_create_link(&dev->class->subsys.kset.kobj, &dev->kobj,
 				  dev->bus_id);
-
+		if (parent) {
-		sysfs_create_link(&dev->kobj, &dev->parent->kobj, "device");
+			sysfs_create_link(&dev->kobj, &dev->parent->kobj, "device");
-		class_name = make_class_name(dev->class->name, &dev->kobj);
+			class_name = make_class_name(dev->class->name, &dev->kobj);
-		sysfs_create_link(&dev->parent->kobj, &dev->kobj, class_name);
+			sysfs_create_link(&dev->parent->kobj, &dev->kobj, class_name);
+		}
 	}
 
+	if ((error = device_add_attrs(dev)))
+		goto AttrsError;
+	if ((error = device_add_groups(dev)))
+		goto GroupError;
 	if ((error = device_pm_add(dev)))
 		goto PMError;
 	if ((error = bus_add_device(dev)))
@@ -356,15 +482,16 @@ int device_add(struct device *dev)
 		klist_add_tail(&dev->knode_parent, &parent->klist_children);
 
 	if (dev->class) {
-		/* tie the class to the device */
 		down(&dev->class->sem);
+		/* tie the class to the device */
 		list_add_tail(&dev->node, &dev->class->devices);
+
+		/* notify any interfaces that the device is here */
+		list_for_each_entry(class_intf, &dev->class->interfaces, node)
+			if (class_intf->add_dev)
+				class_intf->add_dev(dev, class_intf);
 		up(&dev->class->sem);
 	}
-
-	/* notify platform of device entry */
-	if (platform_notify)
-		platform_notify(dev);
  Done:
  	kfree(class_name);
 	put_device(dev);
@@ -372,6 +499,10 @@ int device_add(struct device *dev)
  BusError:
 	device_pm_remove(dev);
  PMError:
+	device_remove_groups(dev);
+ GroupError:
+ 	device_remove_attrs(dev);
+ AttrsError:
 	if (dev->devt_attr) {
 		device_remove_file(dev, dev->devt_attr);
 		kfree(dev->devt_attr);
@@ -449,6 +580,7 @@ void device_del(struct device * dev)
 {
 	struct device * parent = dev->parent;
 	char *class_name = NULL;
+	struct class_interface *class_intf;
 
 	if (parent)
 		klist_del(&dev->knode_parent);
@@ -458,14 +590,23 @@ void device_del(struct device * dev)
 		sysfs_remove_link(&dev->kobj, "subsystem");
 		sysfs_remove_link(&dev->class->subsys.kset.kobj, dev->bus_id);
 		class_name = make_class_name(dev->class->name, &dev->kobj);
-		sysfs_remove_link(&dev->kobj, "device");
+		if (parent) {
-		sysfs_remove_link(&dev->parent->kobj, class_name);
+			sysfs_remove_link(&dev->kobj, "device");
+			sysfs_remove_link(&dev->parent->kobj, class_name);
+		}
 		kfree(class_name);
 		down(&dev->class->sem);
+		/* notify any interfaces that the device is now gone */
+		list_for_each_entry(class_intf, &dev->class->interfaces, node)
+			if (class_intf->remove_dev)
+				class_intf->remove_dev(dev, class_intf);
+		/* remove the device from the class list */
 		list_del_init(&dev->node);
 		up(&dev->class->sem);
 	}
 	device_remove_file(dev, &dev->uevent_attr);
+	device_remove_groups(dev);
+	device_remove_attrs(dev);
 
 	/* Notify the platform of the removal, in case they
 	 * need to do anything...
@@ -579,7 +720,7 @@ static void device_create_release(struct device *dev)
  * been created with a call to class_create().
  */
 struct device *device_create(struct class *class, struct device *parent,
-			     dev_t devt, char *fmt, ...)
+			     dev_t devt, const char *fmt, ...)
 {
 	va_list args;
 	struct device *dev = NULL;
@@ -587,10 +728,6 @@ struct device *device_create(struct class *class, struct device *parent,
 
 	if (class == NULL || IS_ERR(class))
 		goto error;
-	if (parent == NULL) {
-		printk(KERN_WARNING "%s does not work yet for NULL parents\n", __FUNCTION__);
-		goto error;
-	}
 
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 	if (!dev) {
@@ -644,3 +781,58 @@ void device_destroy(struct class *class, dev_t devt)
 		device_unregister(dev);
 }
 EXPORT_SYMBOL_GPL(device_destroy);
+
+/**
+ * device_rename - renames a device
+ * @dev: the pointer to the struct device to be renamed
+ * @new_name: the new name of the device
+ */
+int device_rename(struct device *dev, char *new_name)
+{
+	char *old_class_name = NULL;
+	char *new_class_name = NULL;
+	char *old_symlink_name = NULL;
+	int error;
+
+	dev = get_device(dev);
+	if (!dev)
+		return -EINVAL;
+
+	pr_debug("DEVICE: renaming '%s' to '%s'\n", dev->bus_id, new_name);
+
+	if ((dev->class) && (dev->parent))
+		old_class_name = make_class_name(dev->class->name, &dev->kobj);
+
+	if (dev->class) {
+		old_symlink_name = kmalloc(BUS_ID_SIZE, GFP_KERNEL);
+		if (!old_symlink_name)
+			return -ENOMEM;
+		strlcpy(old_symlink_name, dev->bus_id, BUS_ID_SIZE);
+	}
+
+	strlcpy(dev->bus_id, new_name, BUS_ID_SIZE);
+
+	error = kobject_rename(&dev->kobj, new_name);
+
+	if (old_class_name) {
+		new_class_name = make_class_name(dev->class->name, &dev->kobj);
+		if (new_class_name) {
+			sysfs_create_link(&dev->parent->kobj, &dev->kobj,
+					  new_class_name);
+			sysfs_remove_link(&dev->parent->kobj, old_class_name);
+		}
+	}
+	if (dev->class) {
+		sysfs_remove_link(&dev->class->subsys.kset.kobj,
+				  old_symlink_name);
+		sysfs_create_link(&dev->class->subsys.kset.kobj, &dev->kobj,
+				  dev->bus_id);
+	}
+	put_device(dev);
+
+	kfree(old_class_name);
+	kfree(new_class_name);
+	kfree(old_symlink_name);
+
+	return error;
+}

drivers/base/dd.c

@@ -17,6 +17,7 @@
 
 #include <linux/device.h>
 #include <linux/module.h>
+#include <linux/kthread.h>
 
 #include "base.h"
 #include "power/power.h"
@@ -38,66 +39,73 @@
  *
  *	This function must be called with @dev->sem held.
  */
-void device_bind_driver(struct device * dev)
+int device_bind_driver(struct device *dev)
 {
-	if (klist_node_attached(&dev->knode_driver))
+	int ret;
-		return;
+
+	if (klist_node_attached(&dev->knode_driver)) {
+		printk(KERN_WARNING "%s: device %s already bound\n",
+			__FUNCTION__, kobject_name(&dev->kobj));
+		return 0;
+	}
 
 	pr_debug("bound device '%s' to driver '%s'\n",
 		 dev->bus_id, dev->driver->name);
 	klist_add_tail(&dev->knode_driver, &dev->driver->klist_devices);
-	sysfs_create_link(&dev->driver->kobj, &dev->kobj,
+	ret = sysfs_create_link(&dev->driver->kobj, &dev->kobj,
 			  kobject_name(&dev->kobj));
-	sysfs_create_link(&dev->kobj, &dev->driver->kobj, "driver");
+	if (ret == 0) {
+		ret = sysfs_create_link(&dev->kobj, &dev->driver->kobj,
+					"driver");
+		if (ret)
+			sysfs_remove_link(&dev->driver->kobj,
+					kobject_name(&dev->kobj));
+	}
+	return ret;
 }
 
-/**
+struct stupid_thread_structure {
- *	driver_probe_device - attempt to bind device & driver.
+	struct device_driver *drv;
- *	@drv:	driver.
+	struct device *dev;
- *	@dev:	device.
+};
- *
+
- *	First, we call the bus's match function, if one present, which
+static atomic_t probe_count = ATOMIC_INIT(0);
- *	should compare the device IDs the driver supports with the
+static int really_probe(void *void_data)
- *	device IDs of the device. Note we don't do this ourselves
- *	because we don't know the format of the ID structures, nor what
- *	is to be considered a match and what is not.
- *
- *	This function returns 1 if a match is found, an error if one
- *	occurs (that is not -ENODEV or -ENXIO), and 0 otherwise.
- *
- *	This function must be called with @dev->sem held.  When called
- *	for a USB interface, @dev->parent->sem must be held as well.
- */
-int driver_probe_device(struct device_driver * drv, struct device * dev)
 {
+	struct stupid_thread_structure *data = void_data;
+	struct device_driver *drv = data->drv;
+	struct device *dev = data->dev;
 	int ret = 0;
 
-	if (drv->bus->match && !drv->bus->match(dev, drv))
+	atomic_inc(&probe_count);
-		goto Done;
+	pr_debug("%s: Probing driver %s with device %s\n",
+		 drv->bus->name, drv->name, dev->bus_id);
 
-	pr_debug("%s: Matched Device %s with Driver %s\n",
-		 drv->bus->name, dev->bus_id, drv->name);
 	dev->driver = drv;
 	if (dev->bus->probe) {
 		ret = dev->bus->probe(dev);
 		if (ret) {
 			dev->driver = NULL;
-			goto ProbeFailed;
+			goto probe_failed;
 		}
 	} else if (drv->probe) {
 		ret = drv->probe(dev);
 		if (ret) {
 			dev->driver = NULL;
-			goto ProbeFailed;
+			goto probe_failed;
 		}
 	}
-	device_bind_driver(dev);
+	if (device_bind_driver(dev)) {
+		printk(KERN_ERR "%s: device_bind_driver(%s) failed\n",
+			__FUNCTION__, dev->bus_id);
+		/* How does undo a ->probe?  We're screwed. */
+	}
 	ret = 1;
 	pr_debug("%s: Bound Device %s to Driver %s\n",
 		 drv->bus->name, dev->bus_id, drv->name);
-	goto Done;
+	goto done;
 
- ProbeFailed:
+probe_failed:
 	if (ret == -ENODEV || ret == -ENXIO) {
 		/* Driver matched, but didn't support device
 		 * or device not found.
@@ -110,7 +118,71 @@ int driver_probe_device(struct device_driver * drv, struct device * dev)
 		       "%s: probe of %s failed with error %d\n",
 		       drv->name, dev->bus_id, ret);
 	}
- Done:
+done:
+	kfree(data);
+	atomic_dec(&probe_count);
+	return ret;
+}
+
+/**
+ * driver_probe_done
+ * Determine if the probe sequence is finished or not.
+ *
+ * Should somehow figure out how to use a semaphore, not an atomic variable...
+ */
+int driver_probe_done(void)
+{
+	pr_debug("%s: probe_count = %d\n", __FUNCTION__,
+		 atomic_read(&probe_count));
+	if (atomic_read(&probe_count))
+		return -EBUSY;
+	return 0;
+}
+
+/**
+ * driver_probe_device - attempt to bind device & driver together
+ * @drv: driver to bind a device to
+ * @dev: device to try to bind to the driver
+ *
+ * First, we call the bus's match function, if one present, which should
+ * compare the device IDs the driver supports with the device IDs of the
+ * device. Note we don't do this ourselves because we don't know the
+ * format of the ID structures, nor what is to be considered a match and
+ * what is not.
+ *
+ * This function returns 1 if a match is found, an error if one occurs
+ * (that is not -ENODEV or -ENXIO), and 0 otherwise.
+ *
+ * This function must be called with @dev->sem held.  When called for a
+ * USB interface, @dev->parent->sem must be held as well.
+ */
+int driver_probe_device(struct device_driver * drv, struct device * dev)
+{
+	struct stupid_thread_structure *data;
+	struct task_struct *probe_task;
+	int ret = 0;
+
+	if (!device_is_registered(dev))
+		return -ENODEV;
+	if (drv->bus->match && !drv->bus->match(dev, drv))
+		goto done;
+
+	pr_debug("%s: Matched Device %s with Driver %s\n",
+		 drv->bus->name, dev->bus_id, drv->name);
+
+	data = kmalloc(sizeof(*data), GFP_KERNEL);
+	data->drv = drv;
+	data->dev = dev;
+
+	if (drv->multithread_probe) {
+		probe_task = kthread_run(really_probe, data,
+					 "probe-%s", dev->bus_id);
+		if (IS_ERR(probe_task))
+			ret = PTR_ERR(probe_task);
+	} else
+		ret = really_probe(data);
+
+done:
 	return ret;
 }
 
@@ -139,8 +211,9 @@ int device_attach(struct device * dev)
 
 	down(&dev->sem);
 	if (dev->driver) {
-		device_bind_driver(dev);
+		ret = device_bind_driver(dev);
-		ret = 1;
+		if (ret == 0)
+			ret = 1;
 	} else
 		ret = bus_for_each_drv(dev->bus, NULL, dev, __device_attach);
 	up(&dev->sem);
@@ -182,9 +255,9 @@ static int __driver_attach(struct device * dev, void * data)
  *	returns 0 and the @dev->driver is set, we've found a
  *	compatible pair.
  */
-void driver_attach(struct device_driver * drv)
+int driver_attach(struct device_driver * drv)
 {
-	bus_for_each_dev(drv->bus, NULL, drv, __driver_attach);
+	return bus_for_each_dev(drv->bus, NULL, drv, __driver_attach);
 }
 
 /**

drivers/base/driver.c

@@ -142,20 +142,6 @@ void put_driver(struct device_driver * drv)
 	kobject_put(&drv->kobj);
 }
 
-static void klist_devices_get(struct klist_node *n)
-{
-	struct device *dev = container_of(n, struct device, knode_driver);
-
-	get_device(dev);
-}
-
-static void klist_devices_put(struct klist_node *n)
-{
-	struct device *dev = container_of(n, struct device, knode_driver);
-
-	put_device(dev);
-}
-
 /**
  *	driver_register - register driver with bus
  *	@drv:	driver to register
@@ -175,7 +161,7 @@ int driver_register(struct device_driver * drv)
 	    (drv->bus->shutdown && drv->shutdown)) {
 		printk(KERN_WARNING "Driver '%s' needs updating - please use bus_type methods\n", drv->name);
 	}
-	klist_init(&drv->klist_devices, klist_devices_get, klist_devices_put);
+	klist_init(&drv->klist_devices, NULL, NULL);
 	init_completion(&drv->unloaded);
 	return bus_add_driver(drv);
 }

drivers/base/platform.c

@@ -505,12 +505,36 @@ static int platform_match(struct device * dev, struct device_driver * drv)
 	return (strncmp(pdev->name, drv->name, BUS_ID_SIZE) == 0);
 }
 
-static int platform_suspend(struct device * dev, pm_message_t state)
+static int platform_suspend(struct device *dev, pm_message_t mesg)
 {
 	int ret = 0;
 
 	if (dev->driver && dev->driver->suspend)
-		ret = dev->driver->suspend(dev, state);
+		ret = dev->driver->suspend(dev, mesg);
+
+	return ret;
+}
+
+static int platform_suspend_late(struct device *dev, pm_message_t mesg)
+{
+	struct platform_driver *drv = to_platform_driver(dev->driver);
+	struct platform_device *pdev = container_of(dev, struct platform_device, dev);
+	int ret = 0;
+
+	if (dev->driver && drv->suspend_late)
+		ret = drv->suspend_late(pdev, mesg);
+
+	return ret;
+}
+
+static int platform_resume_early(struct device *dev)
+{
+	struct platform_driver *drv = to_platform_driver(dev->driver);
+	struct platform_device *pdev = container_of(dev, struct platform_device, dev);
+	int ret = 0;
+
+	if (dev->driver && drv->resume_early)
+		ret = drv->resume_early(pdev);
 
 	return ret;
 }
@@ -531,6 +555,8 @@ struct bus_type platform_bus_type = {
 	.match		= platform_match,
 	.uevent		= platform_uevent,
 	.suspend	= platform_suspend,
+	.suspend_late	= platform_suspend_late,
+	.resume_early	= platform_resume_early,
 	.resume		= platform_resume,
 };
 EXPORT_SYMBOL_GPL(platform_bus_type);

drivers/base/power/resume.c

@@ -38,13 +38,35 @@ int resume_device(struct device * dev)
 		dev_dbg(dev,"resuming\n");
 		error = dev->bus->resume(dev);
 	}
+	if (dev->class && dev->class->resume) {
+		dev_dbg(dev,"class resume\n");
+		error = dev->class->resume(dev);
+	}
 	up(&dev->sem);
 	TRACE_RESUME(error);
 	return error;
 }
 
 
+static int resume_device_early(struct device * dev)
+{
+	int error = 0;
 
+	TRACE_DEVICE(dev);
+	TRACE_RESUME(0);
+	if (dev->bus && dev->bus->resume_early) {
+		dev_dbg(dev,"EARLY resume\n");
+		error = dev->bus->resume_early(dev);
+	}
+	TRACE_RESUME(error);
+	return error;
+}
+
+/*
+ * Resume the devices that have either not gone through
+ * the late suspend, or that did go through it but also
+ * went through the early resume
+ */
 void dpm_resume(void)
 {
 	down(&dpm_list_sem);
@@ -74,6 +96,7 @@ void dpm_resume(void)
 
 void device_resume(void)
 {
+	might_sleep();
 	down(&dpm_sem);
 	dpm_resume();
 	up(&dpm_sem);
@@ -83,12 +106,12 @@ EXPORT_SYMBOL_GPL(device_resume);
 
 
 /**
- *	device_power_up_irq - Power on some devices.
+ *	dpm_power_up - Power on some devices.
  *
  *	Walk the dpm_off_irq list and power each device up. This
  *	is used for devices that required they be powered down with
- *	interrupts disabled. As devices are powered on, they are moved to
+ *	interrupts disabled. As devices are powered on, they are moved
- *	the dpm_suspended list.
+ *	to the dpm_active list.
  *
  *	Interrupts must be disabled when calling this.
  */
@@ -99,16 +122,14 @@ void dpm_power_up(void)
 		struct list_head * entry = dpm_off_irq.next;
 		struct device * dev = to_device(entry);
 
-		get_device(dev);
+		list_move_tail(entry, &dpm_off);
-		list_move_tail(entry, &dpm_active);
+		resume_device_early(dev);
-		resume_device(dev);
-		put_device(dev);
 	}
 }
 
 
 /**
- *	device_pm_power_up - Turn on all devices that need special attention.
+ *	device_power_up - Turn on all devices that need special attention.
  *
  *	Power on system devices then devices that required we shut them down
  *	with interrupts disabled.

drivers/base/power/suspend.c

@@ -34,6 +34,7 @@ static inline char *suspend_verb(u32 event)
 	switch (event) {
 	case PM_EVENT_SUSPEND:	return "suspend";
 	case PM_EVENT_FREEZE:	return "freeze";
+	case PM_EVENT_PRETHAW:	return "prethaw";
 	default:		return "(unknown suspend event)";
 	}
 }
@@ -65,7 +66,19 @@ int suspend_device(struct device * dev, pm_message_t state)
 
 	dev->power.prev_state = dev->power.power_state;
 
-	if (dev->bus && dev->bus->suspend && !dev->power.power_state.event) {
+	if (dev->class && dev->class->suspend && !dev->power.power_state.event) {
+		dev_dbg(dev, "class %s%s\n",
+			suspend_verb(state.event),
+			((state.event == PM_EVENT_SUSPEND)
+					&& device_may_wakeup(dev))
+				? ", may wakeup"
+				: ""
+			);
+		error = dev->class->suspend(dev, state);
+		suspend_report_result(dev->class->suspend, error);
+	}
+
+	if (!error && dev->bus && dev->bus->suspend && !dev->power.power_state.event) {
 		dev_dbg(dev, "%s%s\n",
 			suspend_verb(state.event),
 			((state.event == PM_EVENT_SUSPEND)
@@ -81,15 +94,42 @@ int suspend_device(struct device * dev, pm_message_t state)
 }
 
 
+/*
+ * This is called with interrupts off, only a single CPU
+ * running. We can't do down() on a semaphore (and we don't
+ * need the protection)
+ */
+static int suspend_device_late(struct device *dev, pm_message_t state)
+{
+	int error = 0;
+
+	if (dev->bus && dev->bus->suspend_late && !dev->power.power_state.event) {
+		dev_dbg(dev, "LATE %s%s\n",
+			suspend_verb(state.event),
+			((state.event == PM_EVENT_SUSPEND)
+					&& device_may_wakeup(dev))
+				? ", may wakeup"
+				: ""
+			);
+		error = dev->bus->suspend_late(dev, state);
+		suspend_report_result(dev->bus->suspend_late, error);
+	}
+	return error;
+}
+
 /**
  *	device_suspend - Save state and stop all devices in system.
  *	@state:		Power state to put each device in.
  *
  *	Walk the dpm_active list, call ->suspend() for each device, and move
- *	it to dpm_off.
+ *	it to the dpm_off list.
- *	Check the return value for each. If it returns 0, then we move the
+ *
- *	the device to the dpm_off list. If it returns -EAGAIN, we move it to
+ *	(For historical reasons, if it returns -EAGAIN, that used to mean
- *	the dpm_off_irq list. If we get a different error, try and back out.
+ *	that the device would be called again with interrupts disabled.
+ *	These days, we use the "suspend_late()" callback for that, so we
+ *	print a warning and consider it an error).
+ *
+ *	If we get a different error, try and back out.
  *
  *	If we hit a failure with any of the devices, call device_resume()
  *	above to bring the suspended devices back to life.
@@ -100,6 +140,7 @@ int device_suspend(pm_message_t state)
 {
 	int error = 0;
 
+	might_sleep();
 	down(&dpm_sem);
 	down(&dpm_list_sem);
 	while (!list_empty(&dpm_active) && error == 0) {
@@ -115,39 +156,27 @@ int device_suspend(pm_message_t state)
 
 		/* Check if the device got removed */
 		if (!list_empty(&dev->power.entry)) {
-			/* Move it to the dpm_off or dpm_off_irq list */
+			/* Move it to the dpm_off list */
 			if (!error)
 				list_move(&dev->power.entry, &dpm_off);
-			else if (error == -EAGAIN) {
-				list_move(&dev->power.entry, &dpm_off_irq);
-				error = 0;
-			}
 		}
 		if (error)
 			printk(KERN_ERR "Could not suspend device %s: "
-				"error %d\n", kobject_name(&dev->kobj), error);
+				"error %d%s\n",
+				kobject_name(&dev->kobj), error,
+				error == -EAGAIN ? " (please convert to suspend_late)" : "");
 		put_device(dev);
 	}
 	up(&dpm_list_sem);
-	if (error) {
+	if (error)
-		/* we failed... before resuming, bring back devices from
-		 * dpm_off_irq list back to main dpm_off list, we do want
-		 * to call resume() on them, in case they partially suspended
-		 * despite returning -EAGAIN
-		 */
-		while (!list_empty(&dpm_off_irq)) {
-			struct list_head * entry = dpm_off_irq.next;
-			list_move(entry, &dpm_off);
-		}
 		dpm_resume();
-	}
+
 	up(&dpm_sem);
 	return error;
 }
 
 EXPORT_SYMBOL_GPL(device_suspend);
 
-
 /**
  *	device_power_down - Shut down special devices.
  *	@state:		Power state to enter.
@@ -162,14 +191,17 @@ int device_power_down(pm_message_t state)
 	int error = 0;
 	struct device * dev;
 
-	list_for_each_entry_reverse(dev, &dpm_off_irq, power.entry) {
+	while (!list_empty(&dpm_off)) {
-		if ((error = suspend_device(dev, state)))
+		struct list_head * entry = dpm_off.prev;
-			break;
+
+		dev = to_device(entry);
+		error = suspend_device_late(dev, state);
+		if (error)
+			goto Error;
+		list_move(&dev->power.entry, &dpm_off_irq);
 	}
-	if (error)
+
-		goto Error;
+	error = sysdev_suspend(state);
-	if ((error = sysdev_suspend(state)))
-		goto Error;
  Done:
 	return error;
  Error:

drivers/base/power/sysfs.c

@@ -7,22 +7,29 @@
 #include "power.h"
 
 
+#ifdef	CONFIG_PM_SYSFS_DEPRECATED
+
 /**
  *	state - Control current power state of device
  *
  *	show() returns the current power state of the device. '0' indicates
- *	the device is on. Other values (1-3) indicate the device is in a low
+ *	the device is on. Other values (2) indicate the device is in some low
  *	power state.
  *
- *	store() sets the current power state, which is an integer value
+ *	store() sets the current power state, which is an integer valued
- *	between 0-3. If the device is on ('0'), and the value written is
+ *	0, 2, or 3.  Devices with bus.suspend_late(), or bus.resume_early()
- *	greater than 0, then the device is placed directly into the low-power
+ *	methods fail this operation; those methods couldn't be called.
- *	state (via its driver's ->suspend() method).
+ *	Otherwise,
- *	If the device is currently in a low-power state, and the value is 0,
+ *
- *	the device is powered back on (via the ->resume() method).
+ *	- If the recorded dev->power.power_state.event matches the
- *	If the device is in a low-power state, and a different low-power state
+ *	  target value, nothing is done.
- *	is requested, the device is first resumed, then suspended into the new
+ *	- If the recorded event code is nonzero, the device is reactivated
- *	low-power state.
+ *	  by calling bus.resume() and/or class.resume().
+ *	- If the target value is nonzero, the device is suspended by
+ *	  calling class.suspend() and/or bus.suspend() with event code
+ *	  PM_EVENT_SUSPEND.
+ *
+ *	This mechanism is DEPRECATED and should only be used for testing.
  */
 
 static ssize_t state_show(struct device * dev, struct device_attribute *attr, char * buf)
@@ -38,6 +45,10 @@ static ssize_t state_store(struct device * dev, struct device_attribute *attr, c
 	pm_message_t state;
 	int error = -EINVAL;
 
+	/* disallow incomplete suspend sequences */
+	if (dev->bus && (dev->bus->suspend_late || dev->bus->resume_early))
+		return error;
+
 	state.event = PM_EVENT_SUSPEND;
 	/* Older apps expected to write "3" here - confused with PCI D3 */
 	if ((n == 1) && !strcmp(buf, "3"))
@@ -57,6 +68,8 @@ static ssize_t state_store(struct device * dev, struct device_attribute *attr, c
 static DEVICE_ATTR(state, 0644, state_show, state_store);
 
 
+#endif	/* CONFIG_PM_SYSFS_DEPRECATED */
+
 /*
  *	wakeup - Report/change current wakeup option for device
  *
@@ -130,7 +143,9 @@ static DEVICE_ATTR(wakeup, 0644, wake_show, wake_store);
 
 
 static struct attribute * power_attrs[] = {
+#ifdef	CONFIG_PM_SYSFS_DEPRECATED
 	&dev_attr_state.attr,
+#endif
 	&dev_attr_wakeup.attr,
 	NULL,
 };

drivers/ide/ide.c

@@ -1207,7 +1207,7 @@ int system_bus_clock (void)
 
 EXPORT_SYMBOL(system_bus_clock);
 
-static int generic_ide_suspend(struct device *dev, pm_message_t state)
+static int generic_ide_suspend(struct device *dev, pm_message_t mesg)
 {
 	ide_drive_t *drive = dev->driver_data;
 	struct request rq;
@@ -1221,7 +1221,9 @@ static int generic_ide_suspend(struct device *dev, pm_message_t state)
 	rq.special = &args;
 	rq.end_io_data = &rqpm;
 	rqpm.pm_step = ide_pm_state_start_suspend;
-	rqpm.pm_state = state.event;
+	if (mesg.event == PM_EVENT_PRETHAW)
+		mesg.event = PM_EVENT_FREEZE;
+	rqpm.pm_state = mesg.event;
 
 	return ide_do_drive_cmd(drive, &rq, ide_wait);
 }

drivers/ide/ppc/pmac.c

@@ -1369,15 +1369,16 @@ pmac_ide_macio_attach(struct macio_dev *mdev, const struct of_device_id *match)
 }
 
 static int
-pmac_ide_macio_suspend(struct macio_dev *mdev, pm_message_t state)
+pmac_ide_macio_suspend(struct macio_dev *mdev, pm_message_t mesg)
 {
 	ide_hwif_t	*hwif = (ide_hwif_t *)dev_get_drvdata(&mdev->ofdev.dev);
 	int		rc = 0;
 
-	if (state.event != mdev->ofdev.dev.power.power_state.event && state.event >= PM_EVENT_SUSPEND) {
+	if (mesg.event != mdev->ofdev.dev.power.power_state.event
+			&& mesg.event == PM_EVENT_SUSPEND) {
 		rc = pmac_ide_do_suspend(hwif);
 		if (rc == 0)
-			mdev->ofdev.dev.power.power_state = state;
+			mdev->ofdev.dev.power.power_state = mesg;
 	}
 
 	return rc;
@@ -1473,15 +1474,16 @@ pmac_ide_pci_attach(struct pci_dev *pdev, const struct pci_device_id *id)
 }
 
 static int
-pmac_ide_pci_suspend(struct pci_dev *pdev, pm_message_t state)
+pmac_ide_pci_suspend(struct pci_dev *pdev, pm_message_t mesg)
 {
 	ide_hwif_t	*hwif = (ide_hwif_t *)pci_get_drvdata(pdev);
 	int		rc = 0;
 	
-	if (state.event != pdev->dev.power.power_state.event && state.event >= 2) {
+	if (mesg.event != pdev->dev.power.power_state.event
+			&& mesg.event == PM_EVENT_SUSPEND) {
 		rc = pmac_ide_do_suspend(hwif);
 		if (rc == 0)
-			pdev->dev.power.power_state = state;
+			pdev->dev.power.power_state = mesg;
 	}
 
 	return rc;

drivers/media/dvb/cinergyT2/cinergyT2.c

@@ -981,7 +981,7 @@ static int cinergyt2_suspend (struct usb_interface *intf, pm_message_t state)
 	if (cinergyt2->disconnect_pending || mutex_lock_interruptible(&cinergyt2->sem))
 		return -ERESTARTSYS;
 
-	if (state.event > PM_EVENT_ON) {
+	if (1) {
 		struct cinergyt2 *cinergyt2 = usb_get_intfdata (intf);
 
 		cinergyt2_suspend_rc(cinergyt2);

drivers/pci/Kconfig

@@ -17,6 +17,31 @@ config PCI_MSI
 
 	   If you don't know what to do here, say N.
 
+config PCI_MULTITHREAD_PROBE
+	bool "PCI Multi-threaded probe (EXPERIMENTAL)"
+	depends on PCI && EXPERIMENTAL
+	help
+	  Say Y here if you want the PCI core to spawn a new thread for
+	  every PCI device that is probed.  This can cause a huge
+	  speedup in boot times on multiprocessor machines, and even a
+	  smaller speedup on single processor machines.
+
+	  But it can also cause lots of bad things to happen.  A number
+	  of PCI drivers can not properly handle running in this way,
+	  some will just not work properly at all, while others might
+	  decide to blow up power supplies with a huge load all at once,
+	  so use this option at your own risk.
+
+	  It is very unwise to use this option if you are not using a
+	  boot process that can handle devices being created in any
+	  order.  A program that can create persistant block and network
+	  device names (like udev) is a good idea if you wish to use
+	  this option.
+
+	  Again, use this option at your own risk, you have been warned!
+
+	  When in doubt, say N.
+
 config PCI_DEBUG
 	bool "PCI Debugging"
 	depends on PCI && DEBUG_KERNEL

drivers/pci/hotplug/acpiphp_ibm.c

@@ -487,9 +487,7 @@ static void __exit ibm_acpiphp_exit(void)
 	if (ACPI_FAILURE(status))
 		err("%s: Notification handler removal failed\n", __FUNCTION__);
 	/* remove the /sys entries */
-	if (sysfs_remove_bin_file(sysdir, &ibm_apci_table_attr))
+	sysfs_remove_bin_file(sysdir, &ibm_apci_table_attr);
-		err("%s: removal of sysfs file apci_table failed\n",
-				__FUNCTION__);
 }
 
 module_init(ibm_acpiphp_init);

drivers/pci/pci-driver.c

@@ -17,6 +17,16 @@
  *  Registration of PCI drivers and handling of hot-pluggable devices.
  */
 
+/* multithreaded probe logic */
+static int pci_multithread_probe =
+#ifdef CONFIG_PCI_MULTITHREAD_PROBE
+	1;
+#else
+	0;
+#endif
+__module_param_call("", pci_multithread_probe, param_set_bool, param_get_bool, &pci_multithread_probe, 0644);
+
+
 /*
  * Dynamic device IDs are disabled for !CONFIG_HOTPLUG
  */
@@ -279,6 +289,18 @@ static int pci_device_suspend(struct device * dev, pm_message_t state)
 	return i;
 }
 
+static int pci_device_suspend_late(struct device * dev, pm_message_t state)
+{
+	struct pci_dev * pci_dev = to_pci_dev(dev);
+	struct pci_driver * drv = pci_dev->driver;
+	int i = 0;
+
+	if (drv && drv->suspend_late) {
+		i = drv->suspend_late(pci_dev, state);
+		suspend_report_result(drv->suspend_late, i);
+	}
+	return i;
+}
 
 /*
  * Default resume method for devices that have no driver provided resume,
@@ -313,6 +335,17 @@ static int pci_device_resume(struct device * dev)
 	return error;
 }
 
+static int pci_device_resume_early(struct device * dev)
+{
+	int error = 0;
+	struct pci_dev * pci_dev = to_pci_dev(dev);
+	struct pci_driver * drv = pci_dev->driver;
+
+	if (drv && drv->resume_early)
+		error = drv->resume_early(pci_dev);
+	return error;
+}
+
 static void pci_device_shutdown(struct device *dev)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
@@ -385,6 +418,7 @@ int __pci_register_driver(struct pci_driver *drv, struct module *owner)
 	drv->driver.bus = &pci_bus_type;
 	drv->driver.owner = owner;
 	drv->driver.kobj.ktype = &pci_driver_kobj_type;
+	drv->driver.multithread_probe = pci_multithread_probe;
 
 	spin_lock_init(&drv->dynids.lock);
 	INIT_LIST_HEAD(&drv->dynids.list);
@@ -509,8 +543,10 @@ struct bus_type pci_bus_type = {
 	.probe		= pci_device_probe,
 	.remove		= pci_device_remove,
 	.suspend	= pci_device_suspend,
-	.shutdown	= pci_device_shutdown,
+	.suspend_late	= pci_device_suspend_late,
+	.resume_early	= pci_device_resume_early,
 	.resume		= pci_device_resume,
+	.shutdown	= pci_device_shutdown,
 	.dev_attrs	= pci_dev_attrs,
 };
 

drivers/pci/pci.c

@@ -432,10 +432,12 @@ pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state)
 	case PM_EVENT_ON:
 		return PCI_D0;
 	case PM_EVENT_FREEZE:
+	case PM_EVENT_PRETHAW:
+		/* REVISIT both freeze and pre-thaw "should" use D0 */
 	case PM_EVENT_SUSPEND:
 		return PCI_D3hot;
 	default:
-		printk("They asked me for state %d\n", state.event);
+		printk("Unrecognized suspend event %d\n", state.event);
 		BUG();
 	}
 	return PCI_D0;

drivers/scsi/mesh.c

@@ -1756,16 +1756,23 @@ static void set_mesh_power(struct mesh_state *ms, int state)
 		pmac_call_feature(PMAC_FTR_MESH_ENABLE, macio_get_of_node(ms->mdev), 0, 0);
 		msleep(10);
 	}
-}			
+}
 
 
 #ifdef CONFIG_PM
-static int mesh_suspend(struct macio_dev *mdev, pm_message_t state)
+static int mesh_suspend(struct macio_dev *mdev, pm_message_t mesg)
 {
 	struct mesh_state *ms = (struct mesh_state *)macio_get_drvdata(mdev);
 	unsigned long flags;
 
-	if (state.event == mdev->ofdev.dev.power.power_state.event || state.event < 2)
+	switch (mesg.event) {
+	case PM_EVENT_SUSPEND:
+	case PM_EVENT_FREEZE:
+		break;
+	default:
+		return 0;
+	}
+	if (mesg.event == mdev->ofdev.dev.power.power_state.event)
 		return 0;
 
 	scsi_block_requests(ms->host);
@@ -1780,7 +1787,7 @@ static int mesh_suspend(struct macio_dev *mdev, pm_message_t state)
 	disable_irq(ms->meshintr);
 	set_mesh_power(ms, 0);
 
-	mdev->ofdev.dev.power.power_state = state;
+	mdev->ofdev.dev.power.power_state = mesg;
 
 	return 0;
 }

drivers/usb/core/hcd-pci.c

@@ -281,7 +281,7 @@ int usb_hcd_pci_suspend (struct pci_dev *dev, pm_message_t message)
 			(void) usb_hcd_pci_resume (dev);
 		}
 
-	} else {
+	} else if (hcd->state != HC_STATE_HALT) {
 		dev_dbg (hcd->self.controller, "hcd state %d; not suspended\n",
 			hcd->state);
 		WARN_ON(1);

drivers/usb/host/ehci-pci.c

@@ -238,6 +238,12 @@ static int ehci_pci_suspend(struct usb_hcd *hcd, pm_message_t message)
 	writel (0, &ehci->regs->intr_enable);
 	(void)readl(&ehci->regs->intr_enable);
 
+	/* make sure snapshot being resumed re-enumerates everything */
+	if (message.event == PM_EVENT_PRETHAW) {
+		ehci_halt(ehci);
+		ehci_reset(ehci);
+	}
+
 	clear_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags);
  bail:
 	spin_unlock_irqrestore (&ehci->lock, flags);

drivers/usb/host/ohci-pci.c

@@ -135,6 +135,11 @@ static int ohci_pci_suspend (struct usb_hcd *hcd, pm_message_t message)
 	}
 	ohci_writel(ohci, OHCI_INTR_MIE, &ohci->regs->intrdisable);
 	(void)ohci_readl(ohci, &ohci->regs->intrdisable);
+
+	/* make sure snapshot being resumed re-enumerates everything */
+	if (message.event == PM_EVENT_PRETHAW)
+		ohci_usb_reset(ohci);
+
 	clear_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags);
  bail:
 	spin_unlock_irqrestore (&ohci->lock, flags);

drivers/usb/host/sl811-hcd.c

@@ -1783,10 +1783,15 @@ sl811h_suspend(struct platform_device *dev, pm_message_t state)
 	struct sl811	*sl811 = hcd_to_sl811(hcd);
 	int		retval = 0;
 
-	if (state.event == PM_EVENT_FREEZE)
+	switch (state.event) {
+	case PM_EVENT_FREEZE:
 		retval = sl811h_bus_suspend(hcd);
-	else if (state.event == PM_EVENT_SUSPEND)
+		break;
+	case PM_EVENT_SUSPEND:
+	case PM_EVENT_PRETHAW:		/* explicitly discard hw state */
 		port_power(sl811, 0);
+		break;
+	}
 	if (retval == 0)
 		dev->dev.power.power_state = state;
 	return retval;

drivers/usb/host/uhci-hcd.c

@@ -734,6 +734,10 @@ static int uhci_suspend(struct usb_hcd *hcd, pm_message_t message)
 
 	/* FIXME: Enable non-PME# remote wakeup? */
 
+	/* make sure snapshot being resumed re-enumerates everything */
+	if (message.event == PM_EVENT_PRETHAW)
+		uhci_hc_died(uhci);
+
 done_okay:
 	clear_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags);
 done:

drivers/video/aty/radeon_pm.c

@@ -2621,25 +2621,28 @@ static int radeon_restore_pci_cfg(struct radeonfb_info *rinfo)
 }
 
 
-int radeonfb_pci_suspend(struct pci_dev *pdev, pm_message_t state)
+int radeonfb_pci_suspend(struct pci_dev *pdev, pm_message_t mesg)
 {
         struct fb_info *info = pci_get_drvdata(pdev);
         struct radeonfb_info *rinfo = info->par;
 	int i;
 
-	if (state.event == pdev->dev.power.power_state.event)
+	if (mesg.event == pdev->dev.power.power_state.event)
 		return 0;
 
-	printk(KERN_DEBUG "radeonfb (%s): suspending to state: %d...\n",
+	printk(KERN_DEBUG "radeonfb (%s): suspending for event: %d...\n",
-	       pci_name(pdev), state.event);
+	       pci_name(pdev), mesg.event);
 
 	/* For suspend-to-disk, we cheat here. We don't suspend anything and
 	 * let fbcon continue drawing until we are all set. That shouldn't
 	 * really cause any problem at this point, provided that the wakeup
 	 * code knows that any state in memory may not match the HW
 	 */
-	if (state.event == PM_EVENT_FREEZE)
+	switch (mesg.event) {
+	case PM_EVENT_FREEZE:		/* about to take snapshot */
+	case PM_EVENT_PRETHAW:		/* before restoring snapshot */
 		goto done;
+	}
 
 	acquire_console_sem();
 
@@ -2706,7 +2709,7 @@ int radeonfb_pci_suspend(struct pci_dev *pdev, pm_message_t state)
 	release_console_sem();
 
  done:
-	pdev->dev.power.power_state = state;
+	pdev->dev.power.power_state = mesg;
 
 	return 0;
 }

drivers/video/i810/i810_main.c

@@ -1554,15 +1554,17 @@ static struct fb_ops i810fb_ops __devinitdata = {
 /***********************************************************************
  *                         Power Management                            *
  ***********************************************************************/
-static int i810fb_suspend(struct pci_dev *dev, pm_message_t state)
+static int i810fb_suspend(struct pci_dev *dev, pm_message_t mesg)
 {
 	struct fb_info *info = pci_get_drvdata(dev);
 	struct i810fb_par *par = info->par;
 
-	par->cur_state = state.event;
+	par->cur_state = mesg.event;
 
-	if (state.event == PM_EVENT_FREEZE) {
+	switch (mesg.event) {
-		dev->dev.power.power_state = state;
+	case PM_EVENT_FREEZE:
+	case PM_EVENT_PRETHAW:
+		dev->dev.power.power_state = mesg;
 		return 0;
 	}
 
@@ -1578,7 +1580,7 @@ static int i810fb_suspend(struct pci_dev *dev, pm_message_t state)
 
 	pci_save_state(dev);
 	pci_disable_device(dev);
-	pci_set_power_state(dev, pci_choose_state(dev, state));
+	pci_set_power_state(dev, pci_choose_state(dev, mesg));
 	release_console_sem();
 
 	return 0;

drivers/video/nvidia/nvidia.c

@@ -950,24 +950,25 @@ static struct fb_ops nvidia_fb_ops = {
 };
 
 #ifdef CONFIG_PM
-static int nvidiafb_suspend(struct pci_dev *dev, pm_message_t state)
+static int nvidiafb_suspend(struct pci_dev *dev, pm_message_t mesg)
 {
 	struct fb_info *info = pci_get_drvdata(dev);
 	struct nvidia_par *par = info->par;
 
+	if (mesg.event == PM_EVENT_PRETHAW)
+		mesg.event = PM_EVENT_FREEZE;
 	acquire_console_sem();
-	par->pm_state = state.event;
+	par->pm_state = mesg.event;
 
-	if (state.event == PM_EVENT_FREEZE) {
+	if (mesg.event == PM_EVENT_SUSPEND) {
-		dev->dev.power.power_state = state;
-	} else {
 		fb_set_suspend(info, 1);
 		nvidiafb_blank(FB_BLANK_POWERDOWN, info);
 		nvidia_write_regs(par, &par->SavedReg);
 		pci_save_state(dev);
 		pci_disable_device(dev);
-		pci_set_power_state(dev, pci_choose_state(dev, state));
+		pci_set_power_state(dev, pci_choose_state(dev, mesg));
 	}
+	dev->dev.power.power_state = mesg;
 
 	release_console_sem();
 	return 0;

drivers/video/savage/savagefb_driver.c

@@ -2323,24 +2323,24 @@ static void __devexit savagefb_remove(struct pci_dev *dev)
 	}
 }
 
-static int savagefb_suspend(struct pci_dev* dev, pm_message_t state)
+static int savagefb_suspend(struct pci_dev *dev, pm_message_t mesg)
 {
 	struct fb_info *info = pci_get_drvdata(dev);
 	struct savagefb_par *par = info->par;
 
 	DBG("savagefb_suspend");
 
-
+	if (mesg.event == PM_EVENT_PRETHAW)
-	par->pm_state = state.event;
+		mesg.event = PM_EVENT_FREEZE;
+	par->pm_state = mesg.event;
+	dev->dev.power.power_state = mesg;
 
 	/*
 	 * For PM_EVENT_FREEZE, do not power down so the console
 	 * can remain active.
 	 */
-	if (state.event == PM_EVENT_FREEZE) {
+	if (mesg.event == PM_EVENT_FREEZE)
-		dev->dev.power.power_state = state;
 		return 0;
-	}
 
 	acquire_console_sem();
 	fb_set_suspend(info, 1);
@@ -2353,7 +2353,7 @@ static int savagefb_suspend(struct pci_dev* dev, pm_message_t state)
 	savage_disable_mmio(par);
 	pci_save_state(dev);
 	pci_disable_device(dev);
-	pci_set_power_state(dev, pci_choose_state(dev, state));
+	pci_set_power_state(dev, pci_choose_state(dev, mesg));
 	release_console_sem();
 
 	return 0;

fs/debugfs/file.c

@@ -55,12 +55,11 @@ static u64 debugfs_u8_get(void *data)
 DEFINE_SIMPLE_ATTRIBUTE(fops_u8, debugfs_u8_get, debugfs_u8_set, "%llu\n");
 
 /**
- * debugfs_create_u8 - create a file in the debugfs filesystem that is used to read and write an unsigned 8 bit value.
+ * debugfs_create_u8 - create a debugfs file that is used to read and write an unsigned 8-bit value
- *
  * @name: a pointer to a string containing the name of the file to create.
  * @mode: the permission that the file should have
  * @parent: a pointer to the parent dentry for this file.  This should be a
- *          directory dentry if set.  If this paramater is NULL, then the
+ *          directory dentry if set.  If this parameter is %NULL, then the
  *          file will be created in the root of the debugfs filesystem.
  * @value: a pointer to the variable that the file should read to and write
  *         from.
@@ -72,11 +71,11 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_u8, debugfs_u8_get, debugfs_u8_set, "%llu\n");
  * This function will return a pointer to a dentry if it succeeds.  This
  * pointer must be passed to the debugfs_remove() function when the file is
  * to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.)  If an error occurs, NULL will be returned.
+ * you are responsible here.)  If an error occurs, %NULL will be returned.
  *
- * If debugfs is not enabled in the kernel, the value -ENODEV will be
+ * If debugfs is not enabled in the kernel, the value -%ENODEV will be
  * returned.  It is not wise to check for this value, but rather, check for
- * NULL or !NULL instead as to eliminate the need for #ifdef in the calling
+ * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling
  * code.
  */
 struct dentry *debugfs_create_u8(const char *name, mode_t mode,
@@ -97,12 +96,11 @@ static u64 debugfs_u16_get(void *data)
 DEFINE_SIMPLE_ATTRIBUTE(fops_u16, debugfs_u16_get, debugfs_u16_set, "%llu\n");
 
 /**
- * debugfs_create_u16 - create a file in the debugfs filesystem that is used to read and write an unsigned 16 bit value.
+ * debugfs_create_u16 - create a debugfs file that is used to read and write an unsigned 16-bit value
- *
  * @name: a pointer to a string containing the name of the file to create.
  * @mode: the permission that the file should have
  * @parent: a pointer to the parent dentry for this file.  This should be a
- *          directory dentry if set.  If this paramater is NULL, then the
+ *          directory dentry if set.  If this parameter is %NULL, then the
  *          file will be created in the root of the debugfs filesystem.
  * @value: a pointer to the variable that the file should read to and write
  *         from.
@@ -114,11 +112,11 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_u16, debugfs_u16_get, debugfs_u16_set, "%llu\n");
  * This function will return a pointer to a dentry if it succeeds.  This
  * pointer must be passed to the debugfs_remove() function when the file is
  * to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.)  If an error occurs, NULL will be returned.
+ * you are responsible here.)  If an error occurs, %NULL will be returned.
  *
- * If debugfs is not enabled in the kernel, the value -ENODEV will be
+ * If debugfs is not enabled in the kernel, the value -%ENODEV will be
  * returned.  It is not wise to check for this value, but rather, check for
- * NULL or !NULL instead as to eliminate the need for #ifdef in the calling
+ * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling
  * code.
  */
 struct dentry *debugfs_create_u16(const char *name, mode_t mode,
@@ -139,12 +137,11 @@ static u64 debugfs_u32_get(void *data)
 DEFINE_SIMPLE_ATTRIBUTE(fops_u32, debugfs_u32_get, debugfs_u32_set, "%llu\n");
 
 /**
- * debugfs_create_u32 - create a file in the debugfs filesystem that is used to read and write an unsigned 32 bit value.
+ * debugfs_create_u32 - create a debugfs file that is used to read and write an unsigned 32-bit value
- *
  * @name: a pointer to a string containing the name of the file to create.
  * @mode: the permission that the file should have
  * @parent: a pointer to the parent dentry for this file.  This should be a
- *          directory dentry if set.  If this paramater is NULL, then the
+ *          directory dentry if set.  If this parameter is %NULL, then the
  *          file will be created in the root of the debugfs filesystem.
  * @value: a pointer to the variable that the file should read to and write
  *         from.
@@ -156,11 +153,11 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_u32, debugfs_u32_get, debugfs_u32_set, "%llu\n");
  * This function will return a pointer to a dentry if it succeeds.  This
  * pointer must be passed to the debugfs_remove() function when the file is
  * to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.)  If an error occurs, NULL will be returned.
+ * you are responsible here.)  If an error occurs, %NULL will be returned.
  *
- * If debugfs is not enabled in the kernel, the value -ENODEV will be
+ * If debugfs is not enabled in the kernel, the value -%ENODEV will be
  * returned.  It is not wise to check for this value, but rather, check for
- * NULL or !NULL instead as to eliminate the need for #ifdef in the calling
+ * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling
  * code.
  */
 struct dentry *debugfs_create_u32(const char *name, mode_t mode,
@@ -219,12 +216,11 @@ static const struct file_operations fops_bool = {
 };
 
 /**
- * debugfs_create_bool - create a file in the debugfs filesystem that is used to read and write a boolean value.
+ * debugfs_create_bool - create a debugfs file that is used to read and write a boolean value
- *
  * @name: a pointer to a string containing the name of the file to create.
  * @mode: the permission that the file should have
  * @parent: a pointer to the parent dentry for this file.  This should be a
- *          directory dentry if set.  If this paramater is NULL, then the
+ *          directory dentry if set.  If this parameter is %NULL, then the
  *          file will be created in the root of the debugfs filesystem.
  * @value: a pointer to the variable that the file should read to and write
  *         from.
@@ -236,11 +232,11 @@ static const struct file_operations fops_bool = {
  * This function will return a pointer to a dentry if it succeeds.  This
  * pointer must be passed to the debugfs_remove() function when the file is
  * to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.)  If an error occurs, NULL will be returned.
+ * you are responsible here.)  If an error occurs, %NULL will be returned.
  *
- * If debugfs is not enabled in the kernel, the value -ENODEV will be
+ * If debugfs is not enabled in the kernel, the value -%ENODEV will be
  * returned.  It is not wise to check for this value, but rather, check for
- * NULL or !NULL instead as to eliminate the need for #ifdef in the calling
+ * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling
  * code.
  */
 struct dentry *debugfs_create_bool(const char *name, mode_t mode,
@@ -264,13 +260,11 @@ static struct file_operations fops_blob = {
 };
 
 /**
- * debugfs_create_blob - create a file in the debugfs filesystem that is
+ * debugfs_create_blob - create a debugfs file that is used to read and write a binary blob
- * used to read and write a binary blob.
- *
  * @name: a pointer to a string containing the name of the file to create.
  * @mode: the permission that the file should have
  * @parent: a pointer to the parent dentry for this file.  This should be a
- *          directory dentry if set.  If this paramater is NULL, then the
+ *          directory dentry if set.  If this parameter is %NULL, then the
  *          file will be created in the root of the debugfs filesystem.
  * @blob: a pointer to a struct debugfs_blob_wrapper which contains a pointer
  *        to the blob data and the size of the data.
@@ -282,11 +276,11 @@ static struct file_operations fops_blob = {
  * This function will return a pointer to a dentry if it succeeds.  This
  * pointer must be passed to the debugfs_remove() function when the file is
  * to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.)  If an error occurs, NULL will be returned.
+ * you are responsible here.)  If an error occurs, %NULL will be returned.
  *
- * If debugfs is not enabled in the kernel, the value -ENODEV will be
+ * If debugfs is not enabled in the kernel, the value -%ENODEV will be
  * returned.  It is not wise to check for this value, but rather, check for
- * NULL or !NULL instead as to eliminate the need for #ifdef in the calling
+ * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling
  * code.
  */
 struct dentry *debugfs_create_blob(const char *name, mode_t mode,

fs/debugfs/inode.c

@@ -162,7 +162,6 @@ static int debugfs_create_by_name(const char *name, mode_t mode,
 
 /**
  * debugfs_create_file - create a file in the debugfs filesystem
- *
  * @name: a pointer to a string containing the name of the file to create.
  * @mode: the permission that the file should have
  * @parent: a pointer to the parent dentry for this file.  This should be a
@@ -182,11 +181,11 @@ static int debugfs_create_by_name(const char *name, mode_t mode,
  * This function will return a pointer to a dentry if it succeeds.  This
  * pointer must be passed to the debugfs_remove() function when the file is
  * to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.)  If an error occurs, NULL will be returned.
+ * you are responsible here.)  If an error occurs, %NULL will be returned.
  *
- * If debugfs is not enabled in the kernel, the value -ENODEV will be
+ * If debugfs is not enabled in the kernel, the value -%ENODEV will be
  * returned.  It is not wise to check for this value, but rather, check for
- * NULL or !NULL instead as to eliminate the need for #ifdef in the calling
+ * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling
  * code.
  */
 struct dentry *debugfs_create_file(const char *name, mode_t mode,
@@ -221,7 +220,6 @@ EXPORT_SYMBOL_GPL(debugfs_create_file);
 
 /**
  * debugfs_create_dir - create a directory in the debugfs filesystem
- *
  * @name: a pointer to a string containing the name of the directory to
  *        create.
  * @parent: a pointer to the parent dentry for this file.  This should be a
@@ -233,11 +231,11 @@ EXPORT_SYMBOL_GPL(debugfs_create_file);
  * This function will return a pointer to a dentry if it succeeds.  This
  * pointer must be passed to the debugfs_remove() function when the file is
  * to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.)  If an error occurs, NULL will be returned.
+ * you are responsible here.)  If an error occurs, %NULL will be returned.
  *
- * If debugfs is not enabled in the kernel, the value -ENODEV will be
+ * If debugfs is not enabled in the kernel, the value -%ENODEV will be
  * returned.  It is not wise to check for this value, but rather, check for
- * NULL or !NULL instead as to eliminate the need for #ifdef in the calling
+ * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling
  * code.
  */
 struct dentry *debugfs_create_dir(const char *name, struct dentry *parent)
@@ -250,7 +248,6 @@ EXPORT_SYMBOL_GPL(debugfs_create_dir);
 
 /**
  * debugfs_remove - removes a file or directory from the debugfs filesystem
- *
  * @dentry: a pointer to a the dentry of the file or directory to be
  *          removed.
  *

fs/namespace.c

@@ -17,6 +17,7 @@
 #include <linux/acct.h>
 #include <linux/capability.h>
 #include <linux/module.h>
+#include <linux/sysfs.h>
 #include <linux/seq_file.h>
 #include <linux/namespace.h>
 #include <linux/namei.h>
@@ -28,15 +29,6 @@
 
 extern int __init init_rootfs(void);
 
-#ifdef CONFIG_SYSFS
-extern int __init sysfs_init(void);
-#else
-static inline int sysfs_init(void)
-{
-	return 0;
-}
-#endif
-
 /* spinlock for vfsmount related operations, inplace of dcache_lock */
 __cacheline_aligned_in_smp DEFINE_SPINLOCK(vfsmount_lock);
 

fs/sysfs/bin.c

@@ -10,6 +10,7 @@
 
 #include <linux/errno.h>
 #include <linux/fs.h>
+#include <linux/kernel.h>
 #include <linux/kobject.h>
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -176,7 +177,6 @@ const struct file_operations bin_fops = {
  *	sysfs_create_bin_file - create binary file for object.
  *	@kobj:	object.
  *	@attr:	attribute descriptor.
- *
  */
 
 int sysfs_create_bin_file(struct kobject * kobj, struct bin_attribute * attr)
@@ -191,13 +191,16 @@ int sysfs_create_bin_file(struct kobject * kobj, struct bin_attribute * attr)
  *	sysfs_remove_bin_file - remove binary file for object.
  *	@kobj:	object.
  *	@attr:	attribute descriptor.
- *
  */
 
-int sysfs_remove_bin_file(struct kobject * kobj, struct bin_attribute * attr)
+void sysfs_remove_bin_file(struct kobject * kobj, struct bin_attribute * attr)
 {
-	sysfs_hash_and_remove(kobj->dentry,attr->attr.name);
+	if (sysfs_hash_and_remove(kobj->dentry, attr->attr.name) < 0) {
-	return 0;
+		printk(KERN_ERR "%s: "
+			"bad dentry or inode or no such file: \"%s\"\n",
+			__FUNCTION__, attr->attr.name);
+		dump_stack();
+	}
 }
 
 EXPORT_SYMBOL_GPL(sysfs_create_bin_file);

fs/sysfs/dir.c

@@ -43,7 +43,7 @@ static struct sysfs_dirent * sysfs_new_dirent(struct sysfs_dirent * parent_sd,
 
 	memset(sd, 0, sizeof(*sd));
 	atomic_set(&sd->s_count, 1);
-	atomic_set(&sd->s_event, 0);
+	atomic_set(&sd->s_event, 1);
 	INIT_LIST_HEAD(&sd->s_children);
 	list_add(&sd->s_sibling, &parent_sd->s_children);
 	sd->s_element = element;

fs/sysfs/inode.c

@@ -12,6 +12,7 @@
 #include <linux/namei.h>
 #include <linux/backing-dev.h>
 #include <linux/capability.h>
+#include <linux/errno.h>
 #include "sysfs.h"
 
 extern struct super_block * sysfs_sb;
@@ -234,17 +235,18 @@ void sysfs_drop_dentry(struct sysfs_dirent * sd, struct dentry * parent)
 	}
 }
 
-void sysfs_hash_and_remove(struct dentry * dir, const char * name)
+int sysfs_hash_and_remove(struct dentry * dir, const char * name)
 {
 	struct sysfs_dirent * sd;
 	struct sysfs_dirent * parent_sd;
+	int found = 0;
 
 	if (!dir)
-		return;
+		return -ENOENT;
 
 	if (dir->d_inode == NULL)
 		/* no inode means this hasn't been made visible yet */
-		return;
+		return -ENOENT;
 
 	parent_sd = dir->d_fsdata;
 	mutex_lock(&dir->d_inode->i_mutex);
@@ -255,8 +257,11 @@ void sysfs_hash_and_remove(struct dentry * dir, const char * name)
 			list_del_init(&sd->s_sibling);
 			sysfs_drop_dentry(sd, dir);
 			sysfs_put(sd);
+			found = 1;
 			break;
 		}
 	}
 	mutex_unlock(&dir->d_inode->i_mutex);
+
+	return found ? 0 : -ENOENT;
 }

fs/sysfs/symlink.c

@@ -3,6 +3,7 @@
  */
 
 #include <linux/fs.h>
+#include <linux/mount.h>
 #include <linux/module.h>
 #include <linux/kobject.h>
 #include <linux/namei.h>
@@ -82,10 +83,19 @@ exit1:
  */
 int sysfs_create_link(struct kobject * kobj, struct kobject * target, const char * name)
 {
-	struct dentry * dentry = kobj->dentry;
+	struct dentry *dentry = NULL;
 	int error = -EEXIST;
 
-	BUG_ON(!kobj || !kobj->dentry || !name);
+	BUG_ON(!name);
+
+	if (!kobj) {
+		if (sysfs_mount && sysfs_mount->mnt_sb)
+			dentry = sysfs_mount->mnt_sb->s_root;
+	} else
+		dentry = kobj->dentry;
+
+	if (!dentry)
+		return -EFAULT;
 
 	mutex_lock(&dentry->d_inode->i_mutex);
 	if (!sysfs_dirent_exist(dentry->d_fsdata, name))

fs/sysfs/sysfs.h

@@ -10,7 +10,7 @@ extern int sysfs_make_dirent(struct sysfs_dirent *, struct dentry *, void *,
 				umode_t, int);
 
 extern int sysfs_add_file(struct dentry *, const struct attribute *, int);
-extern void sysfs_hash_and_remove(struct dentry * dir, const char * name);
+extern int sysfs_hash_and_remove(struct dentry * dir, const char * name);
 extern struct sysfs_dirent *sysfs_find(struct sysfs_dirent *dir, const char * name);
 
 extern int sysfs_create_subdir(struct kobject *, const char *, struct dentry **);

include/linux/compiler.h

@@ -99,6 +99,11 @@ extern void __chk_io_ptr(void __iomem *);
 #define __must_check
 #endif
 
+#ifndef CONFIG_ENABLE_MUST_CHECK
+#undef __must_check
+#define __must_check
+#endif
+
 /*
  * Allow us to avoid 'defined but not used' warnings on functions and data,
  * as well as force them to be emitted to the assembly file.

include/linux/device.h

@@ -15,6 +15,7 @@
 #include <linux/kobject.h>
 #include <linux/klist.h>
 #include <linux/list.h>
+#include <linux/compiler.h>
 #include <linux/types.h>
 #include <linux/module.h>
 #include <linux/pm.h>
@@ -51,14 +52,17 @@ struct bus_type {
 	int		(*probe)(struct device * dev);
 	int		(*remove)(struct device * dev);
 	void		(*shutdown)(struct device * dev);
-	int		(*suspend)(struct device * dev, pm_message_t state);
+
-	int		(*resume)(struct device * dev);
+	int (*suspend)(struct device * dev, pm_message_t state);
+	int (*suspend_late)(struct device * dev, pm_message_t state);
+	int (*resume_early)(struct device * dev);
+	int (*resume)(struct device * dev);
 };
 
-extern int bus_register(struct bus_type * bus);
+extern int __must_check bus_register(struct bus_type * bus);
 extern void bus_unregister(struct bus_type * bus);
 
-extern void bus_rescan_devices(struct bus_type * bus);
+extern int __must_check bus_rescan_devices(struct bus_type * bus);
 
 /* iterator helpers for buses */
 
@@ -67,9 +71,9 @@ int bus_for_each_dev(struct bus_type * bus, struct device * start, void * data,
 struct device * bus_find_device(struct bus_type *bus, struct device *start,
 				void *data, int (*match)(struct device *, void *));
 
-int bus_for_each_drv(struct bus_type * bus, struct device_driver * start, 
+int __must_check bus_for_each_drv(struct bus_type *bus,
-		     void * data, int (*fn)(struct device_driver *, void *));
+		struct device_driver *start, void *data,
-
+		int (*fn)(struct device_driver *, void *));
 
 /* driverfs interface for exporting bus attributes */
 
@@ -82,7 +86,8 @@ struct bus_attribute {
 #define BUS_ATTR(_name,_mode,_show,_store)	\
 struct bus_attribute bus_attr_##_name = __ATTR(_name,_mode,_show,_store)
 
-extern int bus_create_file(struct bus_type *, struct bus_attribute *);
+extern int __must_check bus_create_file(struct bus_type *,
+					struct bus_attribute *);
 extern void bus_remove_file(struct bus_type *, struct bus_attribute *);
 
 struct device_driver {
@@ -101,16 +106,18 @@ struct device_driver {
 	void	(*shutdown)	(struct device * dev);
 	int	(*suspend)	(struct device * dev, pm_message_t state);
 	int	(*resume)	(struct device * dev);
+
+	unsigned int multithread_probe:1;
 };
 
 
-extern int driver_register(struct device_driver * drv);
+extern int __must_check driver_register(struct device_driver * drv);
 extern void driver_unregister(struct device_driver * drv);
 
 extern struct device_driver * get_driver(struct device_driver * drv);
 extern void put_driver(struct device_driver * drv);
 extern struct device_driver *driver_find(const char *name, struct bus_type *bus);
-
+extern int driver_probe_done(void);
 
 /* driverfs interface for exporting driver attributes */
 
@@ -123,16 +130,17 @@ struct driver_attribute {
 #define DRIVER_ATTR(_name,_mode,_show,_store)	\
 struct driver_attribute driver_attr_##_name = __ATTR(_name,_mode,_show,_store)
 
-extern int driver_create_file(struct device_driver *, struct driver_attribute *);
+extern int __must_check driver_create_file(struct device_driver *,
+					struct driver_attribute *);
 extern void driver_remove_file(struct device_driver *, struct driver_attribute *);
 
-extern int driver_for_each_device(struct device_driver * drv, struct device * start,
+extern int __must_check driver_for_each_device(struct device_driver * drv,
-				  void * data, int (*fn)(struct device *, void *));
+		struct device *start, void *data,
+		int (*fn)(struct device *, void *));
 struct device * driver_find_device(struct device_driver *drv,
 				   struct device *start, void *data,
 				   int (*match)(struct device *, void *));
 
-
 /*
  * device classes
  */
@@ -146,17 +154,26 @@ struct class {
 	struct list_head	interfaces;
 	struct semaphore	sem;	/* locks both the children and interfaces lists */
 
+	struct kobject		*virtual_dir;
+
 	struct class_attribute		* class_attrs;
 	struct class_device_attribute	* class_dev_attrs;
+	struct device_attribute		* dev_attrs;
 
 	int	(*uevent)(struct class_device *dev, char **envp,
 			   int num_envp, char *buffer, int buffer_size);
+	int	(*dev_uevent)(struct device *dev, char **envp, int num_envp,
+				char *buffer, int buffer_size);
 
 	void	(*release)(struct class_device *dev);
 	void	(*class_release)(struct class *class);
+	void	(*dev_release)(struct device *dev);
+
+	int	(*suspend)(struct device *, pm_message_t state);
+	int	(*resume)(struct device *);
 };
 
-extern int class_register(struct class *);
+extern int __must_check class_register(struct class *);
 extern void class_unregister(struct class *);
 
 
@@ -169,7 +186,8 @@ struct class_attribute {
 #define CLASS_ATTR(_name,_mode,_show,_store)			\
 struct class_attribute class_attr_##_name = __ATTR(_name,_mode,_show,_store) 
 
-extern int class_create_file(struct class *, const struct class_attribute *);
+extern int __must_check class_create_file(struct class *,
+					const struct class_attribute *);
 extern void class_remove_file(struct class *, const struct class_attribute *);
 
 struct class_device_attribute {
@@ -182,7 +200,7 @@ struct class_device_attribute {
 struct class_device_attribute class_device_attr_##_name = 	\
 	__ATTR(_name,_mode,_show,_store)
 
-extern int class_device_create_file(struct class_device *,
+extern int __must_check class_device_create_file(struct class_device *,
 				    const struct class_device_attribute *);
 
 /**
@@ -242,10 +260,10 @@ class_set_devdata (struct class_device *dev, void *data)
 }
 
 
-extern int class_device_register(struct class_device *);
+extern int __must_check class_device_register(struct class_device *);
 extern void class_device_unregister(struct class_device *);
 extern void class_device_initialize(struct class_device *);
-extern int class_device_add(struct class_device *);
+extern int __must_check class_device_add(struct class_device *);
 extern void class_device_del(struct class_device *);
 
 extern int class_device_rename(struct class_device *, char *);
@@ -255,7 +273,7 @@ extern void class_device_put(struct class_device *);
 
 extern void class_device_remove_file(struct class_device *, 
 				     const struct class_device_attribute *);
-extern int class_device_create_bin_file(struct class_device *,
+extern int __must_check class_device_create_bin_file(struct class_device *,
 					struct bin_attribute *);
 extern void class_device_remove_bin_file(struct class_device *,
 					 struct bin_attribute *);
@@ -266,22 +284,23 @@ struct class_interface {
 
 	int (*add)	(struct class_device *, struct class_interface *);
 	void (*remove)	(struct class_device *, struct class_interface *);
+	int (*add_dev)		(struct device *, struct class_interface *);
+	void (*remove_dev)	(struct device *, struct class_interface *);
 };
 
-extern int class_interface_register(struct class_interface *);
+extern int __must_check class_interface_register(struct class_interface *);
 extern void class_interface_unregister(struct class_interface *);
 
-extern struct class *class_create(struct module *owner, char *name);
+extern struct class *class_create(struct module *owner, const char *name);
 extern void class_destroy(struct class *cls);
 extern struct class_device *class_device_create(struct class *cls,
 						struct class_device *parent,
 						dev_t devt,
 						struct device *device,
-						char *fmt, ...)
+						const char *fmt, ...)
 					__attribute__((format(printf,5,6)));
 extern void class_device_destroy(struct class *cls, dev_t devt);
 
-
 /* interface for exporting device attributes */
 struct device_attribute {
 	struct attribute	attr;
@@ -294,8 +313,13 @@ struct device_attribute {
 #define DEVICE_ATTR(_name,_mode,_show,_store) \
 struct device_attribute dev_attr_##_name = __ATTR(_name,_mode,_show,_store)
 
-extern int device_create_file(struct device *device, struct device_attribute * entry);
+extern int __must_check device_create_file(struct device *device,
+					struct device_attribute * entry);
 extern void device_remove_file(struct device * dev, struct device_attribute * attr);
+extern int __must_check device_create_bin_file(struct device *dev,
+					       struct bin_attribute *attr);
+extern void device_remove_bin_file(struct device *dev,
+				   struct bin_attribute *attr);
 struct device {
 	struct klist		klist_children;
 	struct klist_node	knode_parent;		/* node in sibling list */
@@ -305,6 +329,7 @@ struct device {
 
 	struct kobject kobj;
 	char	bus_id[BUS_ID_SIZE];	/* position on parent bus */
+	unsigned		is_registered:1;
 	struct device_attribute uevent_attr;
 	struct device_attribute *devt_attr;
 
@@ -338,6 +363,7 @@ struct device {
 	struct list_head	node;
 	struct class		*class;		/* optional*/
 	dev_t			devt;		/* dev_t, creates the sysfs "dev" */
+	struct attribute_group	**groups;	/* optional groups */
 
 	void	(*release)(struct device * dev);
 };
@@ -356,38 +382,41 @@ dev_set_drvdata (struct device *dev, void *data)
 
 static inline int device_is_registered(struct device *dev)
 {
-	return klist_node_attached(&dev->knode_bus);
+	return dev->is_registered;
 }
 
 /*
  * High level routines for use by the bus drivers
  */
-extern int device_register(struct device * dev);
+extern int __must_check device_register(struct device * dev);
 extern void device_unregister(struct device * dev);
 extern void device_initialize(struct device * dev);
-extern int device_add(struct device * dev);
+extern int __must_check device_add(struct device * dev);
 extern void device_del(struct device * dev);
-extern int device_for_each_child(struct device *, void *,
+extern int __must_check device_for_each_child(struct device *, void *,
 		     int (*fn)(struct device *, void *));
+extern int device_rename(struct device *dev, char *new_name);
 
 /*
  * Manual binding of a device to driver. See drivers/base/bus.c
  * for information on use.
  */
-extern void device_bind_driver(struct device * dev);
+extern int __must_check device_bind_driver(struct device *dev);
 extern void device_release_driver(struct device * dev);
-extern int  device_attach(struct device * dev);
+extern int  __must_check device_attach(struct device * dev);
-extern void driver_attach(struct device_driver * drv);
+extern int __must_check driver_attach(struct device_driver *drv);
-extern void device_reprobe(struct device *dev);
+extern int __must_check device_reprobe(struct device *dev);
 
 /*
  * Easy functions for dynamically creating devices on the fly
  */
 extern struct device *device_create(struct class *cls, struct device *parent,
-				    dev_t devt, char *fmt, ...)
+				    dev_t devt, const char *fmt, ...)
 				    __attribute__((format(printf,4,5)));
 extern void device_destroy(struct class *cls, dev_t devt);
 
+extern int virtual_device_parent(struct device *dev);
+
 /*
  * Platform "fixup" functions - allow the platform to have their say
  * about devices and actions that the general device layer doesn't
@@ -412,7 +441,7 @@ extern void device_shutdown(void);
 
 
 /* drivers/base/firmware.c */
-extern int firmware_register(struct subsystem *);
+extern int __must_check firmware_register(struct subsystem *);
 extern void firmware_unregister(struct subsystem *);
 
 /* debugging and troubleshooting/diagnostic helpers. */

include/linux/kobject.h

@@ -20,6 +20,7 @@
 #include <linux/types.h>
 #include <linux/list.h>
 #include <linux/sysfs.h>
+#include <linux/compiler.h>
 #include <linux/spinlock.h>
 #include <linux/rwsem.h>
 #include <linux/kref.h>
@@ -71,12 +72,12 @@ static inline const char * kobject_name(const struct kobject * kobj)
 extern void kobject_init(struct kobject *);
 extern void kobject_cleanup(struct kobject *);
 
-extern int kobject_add(struct kobject *);
+extern int __must_check kobject_add(struct kobject *);
 extern void kobject_del(struct kobject *);
 
-extern int kobject_rename(struct kobject *, const char *new_name);
+extern int __must_check kobject_rename(struct kobject *, const char *new_name);
 
-extern int kobject_register(struct kobject *);
+extern int __must_check kobject_register(struct kobject *);
 extern void kobject_unregister(struct kobject *);
 
 extern struct kobject * kobject_get(struct kobject *);
@@ -128,8 +129,8 @@ struct kset {
 
 
 extern void kset_init(struct kset * k);
-extern int kset_add(struct kset * k);
+extern int __must_check kset_add(struct kset * k);
-extern int kset_register(struct kset * k);
+extern int __must_check kset_register(struct kset * k);
 extern void kset_unregister(struct kset * k);
 
 static inline struct kset * to_kset(struct kobject * kobj)
@@ -239,7 +240,7 @@ extern struct subsystem hypervisor_subsys;
 	(obj)->subsys.kset.kobj.kset = &(_subsys).kset
 
 extern void subsystem_init(struct subsystem *);
-extern int subsystem_register(struct subsystem *);
+extern int __must_check subsystem_register(struct subsystem *);
 extern void subsystem_unregister(struct subsystem *);
 
 static inline struct subsystem * subsys_get(struct subsystem * s)
@@ -258,7 +259,8 @@ struct subsys_attribute {
 	ssize_t (*store)(struct subsystem *, const char *, size_t); 
 };
 
-extern int subsys_create_file(struct subsystem * , struct subsys_attribute *);
+extern int __must_check subsys_create_file(struct subsystem * ,
+					struct subsys_attribute *);
 
 #if defined(CONFIG_HOTPLUG)
 void kobject_uevent(struct kobject *kobj, enum kobject_action action);

include/linux/pci.h

@@ -49,6 +49,7 @@
 #include <linux/types.h>
 #include <linux/ioport.h>
 #include <linux/list.h>
+#include <linux/compiler.h>
 #include <linux/errno.h>
 #include <linux/device.h>
 
@@ -346,6 +347,8 @@ struct pci_driver {
 	int  (*probe)  (struct pci_dev *dev, const struct pci_device_id *id);	/* New device inserted */
 	void (*remove) (struct pci_dev *dev);	/* Device removed (NULL if not a hot-plug capable driver) */
 	int  (*suspend) (struct pci_dev *dev, pm_message_t state);	/* Device suspended */
+	int  (*suspend_late) (struct pci_dev *dev, pm_message_t state);
+	int  (*resume_early) (struct pci_dev *dev);
 	int  (*resume) (struct pci_dev *dev);	                /* Device woken up */
 	int  (*enable_wake) (struct pci_dev *dev, pci_power_t state, int enable);   /* Enable wake event */
 	void (*shutdown) (struct pci_dev *dev);
@@ -401,7 +404,7 @@ extern struct list_head pci_root_buses;	/* list of all known PCI buses */
 extern struct list_head pci_devices;	/* list of all devices */
 
 void pcibios_fixup_bus(struct pci_bus *);
-int pcibios_enable_device(struct pci_dev *, int mask);
+int __must_check pcibios_enable_device(struct pci_dev *, int mask);
 char *pcibios_setup (char *str);
 
 /* Used only when drivers/pci/setup.c is used */
@@ -488,19 +491,19 @@ static inline int pci_write_config_dword(struct pci_dev *dev, int where, u32 val
 	return pci_bus_write_config_dword (dev->bus, dev->devfn, where, val);
 }
 
-int pci_enable_device(struct pci_dev *dev);
+int __must_check pci_enable_device(struct pci_dev *dev);
-int pci_enable_device_bars(struct pci_dev *dev, int mask);
+int __must_check pci_enable_device_bars(struct pci_dev *dev, int mask);
 void pci_disable_device(struct pci_dev *dev);
 void pci_set_master(struct pci_dev *dev);
 #define HAVE_PCI_SET_MWI
-int pci_set_mwi(struct pci_dev *dev);
+int __must_check pci_set_mwi(struct pci_dev *dev);
 void pci_clear_mwi(struct pci_dev *dev);
 void pci_intx(struct pci_dev *dev, int enable);
 int pci_set_dma_mask(struct pci_dev *dev, u64 mask);
 int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask);
 void pci_update_resource(struct pci_dev *dev, struct resource *res, int resno);
-int pci_assign_resource(struct pci_dev *dev, int i);
+int __must_check pci_assign_resource(struct pci_dev *dev, int i);
-int pci_assign_resource_fixed(struct pci_dev *dev, int i);
+int __must_check pci_assign_resource_fixed(struct pci_dev *dev, int i);
 void pci_restore_bars(struct pci_dev *dev);
 
 /* ROM control related routines */
@@ -526,23 +529,24 @@ void pdev_sort_resources(struct pci_dev *, struct resource_list *);
 void pci_fixup_irqs(u8 (*)(struct pci_dev *, u8 *),
 		    int (*)(struct pci_dev *, u8, u8));
 #define HAVE_PCI_REQ_REGIONS	2
-int pci_request_regions(struct pci_dev *, const char *);
+int __must_check pci_request_regions(struct pci_dev *, const char *);
 void pci_release_regions(struct pci_dev *);
-int pci_request_region(struct pci_dev *, int, const char *);
+int __must_check pci_request_region(struct pci_dev *, int, const char *);
 void pci_release_region(struct pci_dev *, int);
 
 /* drivers/pci/bus.c */
-int pci_bus_alloc_resource(struct pci_bus *bus, struct resource *res,
+int __must_check pci_bus_alloc_resource(struct pci_bus *bus,
-			   resource_size_t size, resource_size_t align,
+			struct resource *res, resource_size_t size,
-			   resource_size_t min, unsigned int type_mask,
+			resource_size_t align, resource_size_t min,
-			   void (*alignf)(void *, struct resource *,
+			unsigned int type_mask,
-					  resource_size_t, resource_size_t),
+			void (*alignf)(void *, struct resource *,
-			   void *alignf_data);
+				resource_size_t, resource_size_t),
+			void *alignf_data);
 void pci_enable_bridges(struct pci_bus *bus);
 
 /* Proper probing supporting hot-pluggable devices */
-int __pci_register_driver(struct pci_driver *, struct module *);
+int __must_check __pci_register_driver(struct pci_driver *, struct module *);
-static inline int pci_register_driver(struct pci_driver *driver)
+static inline int __must_check pci_register_driver(struct pci_driver *driver)
 {
 	return __pci_register_driver(driver, THIS_MODULE);
 }

include/linux/platform_device.h

@@ -49,6 +49,8 @@ struct platform_driver {
 	int (*remove)(struct platform_device *);
 	void (*shutdown)(struct platform_device *);
 	int (*suspend)(struct platform_device *, pm_message_t state);
+	int (*suspend_late)(struct platform_device *, pm_message_t state);
+	int (*resume_early)(struct platform_device *);
 	int (*resume)(struct platform_device *);
 	struct device_driver driver;
 };

include/linux/pm.h

@@ -142,29 +142,61 @@ typedef struct pm_message {
 } pm_message_t;
 
 /*
- * There are 4 important states driver can be in:
+ * Several driver power state transitions are externally visible, affecting
- * ON     -- driver is working
+ * the state of pending I/O queues and (for drivers that touch hardware)
- * FREEZE -- stop operations and apply whatever policy is applicable to a
+ * interrupts, wakeups, DMA, and other hardware state.  There may also be
- *           suspended driver of that class, freeze queues for block like IDE
+ * internal transitions to various low power modes, which are transparent
- *           does, drop packets for ethernet, etc... stop DMA engine too etc...
+ * to the rest of the driver stack (such as a driver that's ON gating off
- *           so a consistent image can be saved; but do not power any hardware
+ * clocks which are not in active use).
- *           down.
- * SUSPEND - like FREEZE, but hardware is doing as much powersaving as
- *           possible. Roughly pci D3.
  *
- * Unfortunately, current drivers only recognize numeric values 0 (ON) and 3
+ * One transition is triggered by resume(), after a suspend() call; the
- * (SUSPEND).  We'll need to fix the drivers. So yes, putting 3 to all different
+ * message is implicit:
- * defines is intentional, and will go away as soon as drivers are fixed.  Also
+ *
- * note that typedef is neccessary, we'll probably want to switch to
+ * ON		Driver starts working again, responding to hardware events
- *   typedef struct pm_message_t { int event; int flags; } pm_message_t
+ * 		and software requests.  The hardware may have gone through
- * or something similar soon.
+ * 		a power-off reset, or it may have maintained state from the
+ * 		previous suspend() which the driver will rely on while
+ * 		resuming.  On most platforms, there are no restrictions on
+ * 		availability of resources like clocks during resume().
+ *
+ * Other transitions are triggered by messages sent using suspend().  All
+ * these transitions quiesce the driver, so that I/O queues are inactive.
+ * That commonly entails turning off IRQs and DMA; there may be rules
+ * about how to quiesce that are specific to the bus or the device's type.
+ * (For example, network drivers mark the link state.)  Other details may
+ * differ according to the message:
+ *
+ * SUSPEND	Quiesce, enter a low power device state appropriate for
+ * 		the upcoming system state (such as PCI_D3hot), and enable
+ * 		wakeup events as appropriate.
+ *
+ * FREEZE	Quiesce operations so that a consistent image can be saved;
+ * 		but do NOT otherwise enter a low power device state, and do
+ * 		NOT emit system wakeup events.
+ *
+ * PRETHAW	Quiesce as if for FREEZE; additionally, prepare for restoring
+ * 		the system from a snapshot taken after an earlier FREEZE.
+ * 		Some drivers will need to reset their hardware state instead
+ * 		of preserving it, to ensure that it's never mistaken for the
+ * 		state which that earlier snapshot had set up.
+ *
+ * A minimally power-aware driver treats all messages as SUSPEND, fully
+ * reinitializes its device during resume() -- whether or not it was reset
+ * during the suspend/resume cycle -- and can't issue wakeup events.
+ *
+ * More power-aware drivers may also use low power states at runtime as
+ * well as during system sleep states like PM_SUSPEND_STANDBY.  They may
+ * be able to use wakeup events to exit from runtime low-power states,
+ * or from system low-power states such as standby or suspend-to-RAM.
  */
 
 #define PM_EVENT_ON 0
 #define PM_EVENT_FREEZE 1
 #define PM_EVENT_SUSPEND 2
+#define PM_EVENT_PRETHAW 3
 
 #define PMSG_FREEZE	((struct pm_message){ .event = PM_EVENT_FREEZE, })
+#define PMSG_PRETHAW	((struct pm_message){ .event = PM_EVENT_PRETHAW, })
 #define PMSG_SUSPEND	((struct pm_message){ .event = PM_EVENT_SUSPEND, })
 #define PMSG_ON		((struct pm_message){ .event = PM_EVENT_ON, })
 
@@ -190,6 +222,7 @@ extern void device_resume(void);
 extern suspend_disk_method_t pm_disk_mode;
 
 extern int device_suspend(pm_message_t state);
+extern int device_prepare_suspend(pm_message_t state);
 
 #define device_set_wakeup_enable(dev,val) \
 	((dev)->power.should_wakeup = !!(val))

include/linux/sysfs.h

@@ -10,6 +10,7 @@
 #ifndef _SYSFS_H_
 #define _SYSFS_H_
 
+#include <linux/compiler.h>
 #include <asm/atomic.h>
 
 struct kobject;
@@ -86,40 +87,44 @@ struct sysfs_dirent {
 
 #ifdef CONFIG_SYSFS
 
-extern int
+extern int __must_check
 sysfs_create_dir(struct kobject *);
 
 extern void
 sysfs_remove_dir(struct kobject *);
 
-extern int
+extern int __must_check
 sysfs_rename_dir(struct kobject *, const char *new_name);
 
-extern int
+extern int __must_check
 sysfs_create_file(struct kobject *, const struct attribute *);
 
-extern int
+extern int __must_check
 sysfs_update_file(struct kobject *, const struct attribute *);
 
-extern int
+extern int __must_check
 sysfs_chmod_file(struct kobject *kobj, struct attribute *attr, mode_t mode);
 
 extern void
 sysfs_remove_file(struct kobject *, const struct attribute *);
 
-extern int
+extern int __must_check
 sysfs_create_link(struct kobject * kobj, struct kobject * target, const char * name);
 
 extern void
 sysfs_remove_link(struct kobject *, const char * name);
 
-int sysfs_create_bin_file(struct kobject * kobj, struct bin_attribute * attr);
+int __must_check sysfs_create_bin_file(struct kobject *kobj,
-int sysfs_remove_bin_file(struct kobject * kobj, struct bin_attribute * attr);
+					struct bin_attribute *attr);
+void sysfs_remove_bin_file(struct kobject *kobj, struct bin_attribute *attr);
 
-int sysfs_create_group(struct kobject *, const struct attribute_group *);
+int __must_check sysfs_create_group(struct kobject *,
+					const struct attribute_group *);
 void sysfs_remove_group(struct kobject *, const struct attribute_group *);
 void sysfs_notify(struct kobject * k, char *dir, char *attr);
 
+extern int __must_check sysfs_init(void);
+
 #else /* CONFIG_SYSFS */
 
 static inline int sysfs_create_dir(struct kobject * k)
@@ -191,6 +196,11 @@ static inline void sysfs_notify(struct kobject * k, char *dir, char *attr)
 {
 }
 
+static inline int __must_check sysfs_init(void)
+{
+	return 0;
+}
+
 #endif /* CONFIG_SYSFS */
 
 #endif /* _SYSFS_H_ */

include/media/v4l2-dev.h

@@ -341,7 +341,7 @@ extern int video_usercopy(struct inode *inode, struct file *file,
 extern struct video_device* video_devdata(struct file*);
 
 #define to_video_device(cd) container_of(cd, struct video_device, class_dev)
-static inline int
+static inline int __must_check
 video_device_create_file(struct video_device *vfd,
 			 struct class_device_attribute *attr)
 {

init/do_mounts.c

@@ -8,6 +8,7 @@
 #include <linux/security.h>
 #include <linux/delay.h>
 #include <linux/mount.h>
+#include <linux/device.h>
 
 #include <linux/nfs_fs.h>
 #include <linux/nfs_fs_sb.h>
@@ -403,6 +404,10 @@ void __init prepare_namespace(void)
 		ssleep(root_delay);
 	}
 
+	/* wait for the known devices to complete their probing */
+	while (driver_probe_done() != 0)
+		msleep(100);
+
 	md_run_setup();
 
 	if (saved_root_name[0]) {

kernel/power/Kconfig

@@ -64,6 +64,17 @@ config PM_TRACE
 	CAUTION: this option will cause your machine's real-time clock to be
 	set to an invalid time after a resume.
 
+config PM_SYSFS_DEPRECATED
+	bool "Driver model /sys/devices/.../power/state files (DEPRECATED)"
+	depends on PM && SYSFS
+	default n
+	help
+	  The driver model started out with a sysfs file intended to provide
+	  a userspace hook for device power management.  This feature has never
+	  worked very well, except for limited testing purposes, and so it will
+	  be removed.   It's not clear that a generic mechanism could really
+	  handle the wide variability of device power states; any replacements
+	  are likely to be bus or driver specific.
 
 config SOFTWARE_SUSPEND
 	bool "Software Suspend"

kernel/power/disk.c

@@ -103,7 +103,7 @@ static void unprepare_processes(void)
 }
 
 /**
- *	pm_suspend_disk - The granpappy of power management.
+ *	pm_suspend_disk - The granpappy of hibernation power management.
  *
  *	If we're going through the firmware, then get it over with quickly.
  *
@@ -212,7 +212,7 @@ static int software_resume(void)
 
 	pr_debug("PM: Preparing devices for restore.\n");
 
-	if ((error = device_suspend(PMSG_FREEZE))) {
+	if ((error = device_suspend(PMSG_PRETHAW))) {
 		printk("Some devices failed to suspend\n");
 		swsusp_free();
 		goto Thaw;

kernel/power/swsusp.c

@@ -247,6 +247,9 @@ int swsusp_suspend(void)
 	restore_processor_state();
 Restore_highmem:
 	restore_highmem();
+	/* NOTE:  device_power_up() is just a resume() for devices
+	 * that suspended with irqs off ... no overall powerup.
+	 */
 	device_power_up();
 Enable_irqs:
 	local_irq_enable();
@@ -256,8 +259,12 @@ Enable_irqs:
 int swsusp_resume(void)
 {
 	int error;
+
 	local_irq_disable();
-	if (device_power_down(PMSG_FREEZE))
+	/* NOTE:  device_power_down() is just a suspend() with irqs off;
+	 * it has no special "power things down" semantics
+	 */
+	if (device_power_down(PMSG_PRETHAW))
 		printk(KERN_ERR "Some devices failed to power down, very bad\n");
 	/* We'll ignore saved state, but this gets preempt count (etc) right */
 	save_processor_state();

kernel/power/user.c

@@ -196,7 +196,7 @@ static int snapshot_ioctl(struct inode *inode, struct file *filp,
 		snapshot_free_unused_memory(&data->handle);
 		down(&pm_sem);
 		pm_prepare_console();
-		error = device_suspend(PMSG_FREEZE);
+		error = device_suspend(PMSG_PRETHAW);
 		if (!error) {
 			error = swsusp_resume();
 			device_resume();

lib/Kconfig.debug

@@ -8,6 +8,13 @@ config PRINTK_TIME
 	  operations.  This is useful for identifying long delays
 	  in kernel startup.
 
+config ENABLE_MUST_CHECK
+	bool "Enable __must_check logic"
+	default y
+	help
+	  Enable the __must_check logic in the kernel build.  Disable this to
+	  suppress the "warning: ignoring return value of 'foo', declared with
+	  attribute warn_unused_result" messages.
 
 config MAGIC_SYSRQ
 	bool "Magic SysRq key"

lib/klist.c

@@ -123,12 +123,10 @@ EXPORT_SYMBOL_GPL(klist_add_tail);
 static void klist_release(struct kref * kref)
 {
 	struct klist_node * n = container_of(kref, struct klist_node, n_ref);
-	void (*put)(struct klist_node *) = n->n_klist->put;
+
 	list_del(&n->n_node);
 	complete(&n->n_removed);
 	n->n_klist = NULL;
-	if (put)
-		put(n);
 }
 
 static int klist_dec_and_del(struct klist_node * n)
@@ -145,10 +143,14 @@ static int klist_dec_and_del(struct klist_node * n)
 void klist_del(struct klist_node * n)
 {
 	struct klist * k = n->n_klist;
+	void (*put)(struct klist_node *) = k->put;
 
 	spin_lock(&k->k_lock);
-	klist_dec_and_del(n);
+	if (!klist_dec_and_del(n))
+		put = NULL;
 	spin_unlock(&k->k_lock);
+	if (put)
+		put(n);
 }
 
 EXPORT_SYMBOL_GPL(klist_del);
@@ -161,10 +163,7 @@ EXPORT_SYMBOL_GPL(klist_del);
 
 void klist_remove(struct klist_node * n)
 {
-	struct klist * k = n->n_klist;
+	klist_del(n);
-	spin_lock(&k->k_lock);
-	klist_dec_and_del(n);
-	spin_unlock(&k->k_lock);
 	wait_for_completion(&n->n_removed);
 }
 
@@ -260,12 +259,15 @@ static struct klist_node * to_klist_node(struct list_head * n)
 struct klist_node * klist_next(struct klist_iter * i)
 {
 	struct list_head * next;
+	struct klist_node * lnode = i->i_cur;
 	struct klist_node * knode = NULL;
+	void (*put)(struct klist_node *) = i->i_klist->put;
 
 	spin_lock(&i->i_klist->k_lock);
-	if (i->i_cur) {
+	if (lnode) {
-		next = i->i_cur->n_node.next;
+		next = lnode->n_node.next;
-		klist_dec_and_del(i->i_cur);
+		if (!klist_dec_and_del(lnode))
+			put = NULL;
 	} else
 		next = i->i_head->next;
 
@@ -275,6 +277,8 @@ struct klist_node * klist_next(struct klist_iter * i)
 	}
 	i->i_cur = knode;
 	spin_unlock(&i->i_klist->k_lock);
+	if (put && lnode)
+		put(lnode);
 	return knode;
 }
 

lib/kobject.c

@@ -407,6 +407,7 @@ static struct kobj_type dir_ktype = {
 struct kobject *kobject_add_dir(struct kobject *parent, const char *name)
 {
 	struct kobject *k;
+	int ret;
 
 	if (!parent)
 		return NULL;
@@ -418,7 +419,13 @@ struct kobject *kobject_add_dir(struct kobject *parent, const char *name)
 	k->parent = parent;
 	k->ktype = &dir_ktype;
 	kobject_set_name(k, name);
-	kobject_register(k);
+	ret = kobject_register(k);
+	if (ret < 0) {
+		printk(KERN_WARNING "kobject_add_dir: "
+			"kobject_register error: %d\n", ret);
+		kobject_del(k);
+		return NULL;
+	}
 
 	return k;
 }