Merge branch 'pm-sleep' into pm-for-linus

* pm-sleep: (51 commits)
  PM: Drop generic_subsys_pm_ops
  PM / Sleep: Remove forward-only callbacks from AMBA bus type
  PM / Sleep: Remove forward-only callbacks from platform bus type
  PM: Run the driver callback directly if the subsystem one is not there
  PM / Sleep: Make pm_op() and pm_noirq_op() return callback pointers
  PM / Sleep: Merge internal functions in generic_ops.c
  PM / Sleep: Simplify generic system suspend callbacks
  PM / Hibernate: Remove deprecated hibernation snapshot ioctls
  PM / Sleep: Fix freezer failures due to racy usermodehelper_is_disabled()
  PM / Sleep: Recommend [un]lock_system_sleep() over using pm_mutex directly
  PM / Sleep: Replace mutex_[un]lock(&pm_mutex) with [un]lock_system_sleep()
  PM / Sleep: Make [un]lock_system_sleep() generic
  PM / Sleep: Use the freezer_count() functions in [un]lock_system_sleep() APIs
  PM / Freezer: Remove the "userspace only" constraint from freezer[_do_not]_count()
  PM / Hibernate: Replace unintuitive 'if' condition in kernel/power/user.c with 'else'
  Freezer / sunrpc / NFS: don't allow TASK_KILLABLE sleeps to block the freezer
  PM / Sleep: Unify diagnostic messages from device suspend/resume
  ACPI / PM: Do not save/restore NVS on Asus K54C/K54HR
  PM / Hibernate: Remove deprecated hibernation test modes
  PM / Hibernate: Thaw processes in SNAPSHOT_CREATE_IMAGE ioctl test path
  ...

Conflicts:
	kernel/kmod.c

Documentation/feature-removal-schedule.txt

@@ -85,17 +85,6 @@ Who:	Robin Getz <rgetz@blackfin.uclinux.org> & Matt Mackall <mpm@selenic.com>
 
 ---------------------------
 
-What:	Deprecated snapshot ioctls
-When:	2.6.36
-
-Why:	The ioctls in kernel/power/user.c were marked as deprecated long time
-	ago. Now they notify users about that so that they need to replace
-	their userspace. After some more time, remove them completely.
-
-Who:	Jiri Slaby <jirislaby@gmail.com>
-
----------------------------
-
 What:	The ieee80211_regdom module parameter
 When:	March 2010 / desktop catchup
 

Documentation/power/devices.txt

@@ -126,7 +126,9 @@ The core methods to suspend and resume devices reside in struct dev_pm_ops
 pointed to by the ops member of struct dev_pm_domain, or by the pm member of
 struct bus_type, struct device_type and struct class.  They are mostly of
 interest to the people writing infrastructure for platforms and buses, like PCI
-or USB, or device type and device class drivers.
+or USB, or device type and device class drivers.  They also are relevant to the
+writers of device drivers whose subsystems (PM domains, device types, device
+classes and bus types) don't provide all power management methods.
 
 Bus drivers implement these methods as appropriate for the hardware and the
 drivers using it; PCI works differently from USB, and so on.  Not many people
@@ -268,32 +270,35 @@ various phases always run after tasks have been frozen and before they are
 unfrozen.  Furthermore, the *_noirq phases run at a time when IRQ handlers have
 been disabled (except for those marked with the IRQF_NO_SUSPEND flag).
 
-All phases use PM domain, bus, type, or class callbacks (that is, methods
-defined in dev->pm_domain->ops, dev->bus->pm, dev->type->pm, or dev->class->pm).
-These callbacks are regarded by the PM core as mutually exclusive.  Moreover,
-PM domain callbacks always take precedence over bus, type and class callbacks,
-while type callbacks take precedence over bus and class callbacks, and class
-callbacks take precedence over bus callbacks.  To be precise, the following
-rules are used to determine which callback to execute in the given phase:
+All phases use PM domain, bus, type, class or driver callbacks (that is, methods
+defined in dev->pm_domain->ops, dev->bus->pm, dev->type->pm, dev->class->pm or
+dev->driver->pm).  These callbacks are regarded by the PM core as mutually
+exclusive.  Moreover, PM domain callbacks always take precedence over all of the
+other callbacks and, for example, type callbacks take precedence over bus, class
+and driver callbacks.  To be precise, the following rules are used to determine
+which callback to execute in the given phase:
 
-    1.	If dev->pm_domain is present, the PM core will attempt to execute the
-	callback included in dev->pm_domain->ops.  If that callback is not
-	present, no action will be carried out for the given device.
+    1.	If dev->pm_domain is present, the PM core will choose the callback
+	included in dev->pm_domain->ops for execution
 
     2.	Otherwise, if both dev->type and dev->type->pm are present, the callback
-	included in dev->type->pm will be executed.
+	included in dev->type->pm will be chosen for execution.
 
     3.	Otherwise, if both dev->class and dev->class->pm are present, the
-	callback included in dev->class->pm will be executed.
+	callback included in dev->class->pm will be chosen for execution.
 
     4.	Otherwise, if both dev->bus and dev->bus->pm are present, the callback
-	included in dev->bus->pm will be executed.
+	included in dev->bus->pm will be chosen for execution.
 
 This allows PM domains and device types to override callbacks provided by bus
 types or device classes if necessary.
 
-These callbacks may in turn invoke device- or driver-specific methods stored in
-dev->driver->pm, but they don't have to.
+The PM domain, type, class and bus callbacks may in turn invoke device- or
+driver-specific methods stored in dev->driver->pm, but they don't have to do
+that.
+
+If the subsystem callback chosen for execution is not present, the PM core will
+execute the corresponding method from dev->driver->pm instead if there is one.
 
 
 Entering System Suspend

Documentation/power/freezing-of-tasks.txt

@@ -21,7 +21,7 @@ freeze_processes() (defined in kernel/power/process.c) is called.  It executes
 try_to_freeze_tasks() that sets TIF_FREEZE for all of the freezable tasks and
 either wakes them up, if they are kernel threads, or sends fake signals to them,
 if they are user space processes.  A task that has TIF_FREEZE set, should react
-to it by calling the function called refrigerator() (defined in
+to it by calling the function called __refrigerator() (defined in
 kernel/freezer.c), which sets the task's PF_FROZEN flag, changes its state
 to TASK_UNINTERRUPTIBLE and makes it loop until PF_FROZEN is cleared for it.
 Then, we say that the task is 'frozen' and therefore the set of functions
@@ -29,10 +29,10 @@ handling this mechanism is referred to as 'the freezer' (these functions are
 defined in kernel/power/process.c, kernel/freezer.c & include/linux/freezer.h).
 User space processes are generally frozen before kernel threads.
 
-It is not recommended to call refrigerator() directly.  Instead, it is
-recommended to use the try_to_freeze() function (defined in
-include/linux/freezer.h), that checks the task's TIF_FREEZE flag and makes the
-task enter refrigerator() if the flag is set.
+__refrigerator() must not be called directly.  Instead, use the
+try_to_freeze() function (defined in include/linux/freezer.h), that checks
+the task's TIF_FREEZE flag and makes the task enter __refrigerator() if the
+flag is set.
 
 For user space processes try_to_freeze() is called automatically from the
 signal-handling code, but the freezable kernel threads need to call it
@@ -61,13 +61,13 @@ wait_event_freezable() and wait_event_freezable_timeout() macros.
 After the system memory state has been restored from a hibernation image and
 devices have been reinitialized, the function thaw_processes() is called in
 order to clear the PF_FROZEN flag for each frozen task.  Then, the tasks that
-have been frozen leave refrigerator() and continue running.
+have been frozen leave __refrigerator() and continue running.
 
 III. Which kernel threads are freezable?
 
 Kernel threads are not freezable by default.  However, a kernel thread may clear
 PF_NOFREEZE for itself by calling set_freezable() (the resetting of PF_NOFREEZE
-directly is strongly discouraged).  From this point it is regarded as freezable
+directly is not allowed).  From this point it is regarded as freezable
 and must call try_to_freeze() in a suitable place.
 
 IV. Why do we do that?
@@ -176,3 +176,28 @@ tasks, since it generally exists anyway.
 A driver must have all firmwares it may need in RAM before suspend() is called.
 If keeping them is not practical, for example due to their size, they must be
 requested early enough using the suspend notifier API described in notifiers.txt.
+
+VI. Are there any precautions to be taken to prevent freezing failures?
+
+Yes, there are.
+
+First of all, grabbing the 'pm_mutex' lock to mutually exclude a piece of code
+from system-wide sleep such as suspend/hibernation is not encouraged.
+If possible, that piece of code must instead hook onto the suspend/hibernation
+notifiers to achieve mutual exclusion. Look at the CPU-Hotplug code
+(kernel/cpu.c) for an example.
+
+However, if that is not feasible, and grabbing 'pm_mutex' is deemed necessary,
+it is strongly discouraged to directly call mutex_[un]lock(&pm_mutex) since
+that could lead to freezing failures, because if the suspend/hibernate code
+successfully acquired the 'pm_mutex' lock, and hence that other entity failed
+to acquire the lock, then that task would get blocked in TASK_UNINTERRUPTIBLE
+state. As a consequence, the freezer would not be able to freeze that task,
+leading to freezing failure.
+
+However, the [un]lock_system_sleep() APIs are safe to use in this scenario,
+since they ask the freezer to skip freezing this task, since it is anyway
+"frozen enough" as it is blocked on 'pm_mutex', which will be released
+only after the entire suspend/hibernation sequence is complete.
+So, to summarize, use [un]lock_system_sleep() instead of directly using
+mutex_[un]lock(&pm_mutex). That would prevent freezing failures.

Documentation/power/runtime_pm.txt

@@ -57,6 +57,10 @@ the following:
 
   4. Bus type of the device, if both dev->bus and dev->bus->pm are present.
 
+If the subsystem chosen by applying the above rules doesn't provide the relevant
+callback, the PM core will invoke the corresponding driver callback stored in
+dev->driver->pm directly (if present).
+
 The PM core always checks which callback to use in the order given above, so the
 priority order of callbacks from high to low is: PM domain, device type, class
 and bus type.  Moreover, the high-priority one will always take precedence over
@@ -64,86 +68,88 @@ a low-priority one.  The PM domain, bus type, device type and class callbacks
 are referred to as subsystem-level callbacks in what follows.
 
 By default, the callbacks are always invoked in process context with interrupts
-enabled.  However, subsystems can use the pm_runtime_irq_safe() helper function
-to tell the PM core that their ->runtime_suspend(), ->runtime_resume() and
-->runtime_idle() callbacks may be invoked in atomic context with interrupts
-disabled for a given device.  This implies that the callback routines in
-question must not block or sleep, but it also means that the synchronous helper
-functions listed at the end of Section 4 may be used for that device within an
-interrupt handler or generally in an atomic context.
-
-The subsystem-level suspend callback is _entirely_ _responsible_ for handling
-the suspend of the device as appropriate, which may, but need not include
-executing the device driver's own ->runtime_suspend() callback (from the
+enabled.  However, the pm_runtime_irq_safe() helper function can be used to tell
+the PM core that it is safe to run the ->runtime_suspend(), ->runtime_resume()
+and ->runtime_idle() callbacks for the given device in atomic context with
+interrupts disabled.  This implies that the callback routines in question must
+not block or sleep, but it also means that the synchronous helper functions
+listed at the end of Section 4 may be used for that device within an interrupt
+handler or generally in an atomic context.
+
+The subsystem-level suspend callback, if present, is _entirely_ _responsible_
+for handling the suspend of the device as appropriate, which may, but need not
+include executing the device driver's own ->runtime_suspend() callback (from the
 PM core's point of view it is not necessary to implement a ->runtime_suspend()
 callback in a device driver as long as the subsystem-level suspend callback
 knows what to do to handle the device).
 
-  * Once the subsystem-level suspend callback has completed successfully
-    for given device, the PM core regards the device as suspended, which need
-    not mean that the device has been put into a low power state.  It is
-    supposed to mean, however, that the device will not process data and will
-    not communicate with the CPU(s) and RAM until the subsystem-level resume
-    callback is executed for it.  The runtime PM status of a device after
-    successful execution of the subsystem-level suspend callback is 'suspended'.
-
-  * If the subsystem-level suspend callback returns -EBUSY or -EAGAIN,
-    the device's runtime PM status is 'active', which means that the device
-    _must_ be fully operational afterwards.
-
-  * If the subsystem-level suspend callback returns an error code different
-    from -EBUSY or -EAGAIN, the PM core regards this as a fatal error and will
-    refuse to run the helper functions described in Section 4 for the device,
-    until the status of it is directly set either to 'active', or to 'suspended'
-    (the PM core provides special helper functions for this purpose).
-
-In particular, if the driver requires remote wake-up capability (i.e. hardware
+  * Once the subsystem-level suspend callback (or the driver suspend callback,
+    if invoked directly) has completed successfully for the given device, the PM
+    core regards the device as suspended, which need not mean that it has been
+    put into a low power state.  It is supposed to mean, however, that the
+    device will not process data and will not communicate with the CPU(s) and
+    RAM until the appropriate resume callback is executed for it.  The runtime
+    PM status of a device after successful execution of the suspend callback is
+    'suspended'.
+
+  * If the suspend callback returns -EBUSY or -EAGAIN, the device's runtime PM
+    status remains 'active', which means that the device _must_ be fully
+    operational afterwards.
+
+  * If the suspend callback returns an error code different from -EBUSY and
+    -EAGAIN, the PM core regards this as a fatal error and will refuse to run
+    the helper functions described in Section 4 for the device until its status
+    is directly set to  either'active', or 'suspended' (the PM core provides
+    special helper functions for this purpose).
+
+In particular, if the driver requires remote wakeup capability (i.e. hardware
 mechanism allowing the device to request a change of its power state, such as
 PCI PME) for proper functioning and device_run_wake() returns 'false' for the
 device, then ->runtime_suspend() should return -EBUSY.  On the other hand, if
-device_run_wake() returns 'true' for the device and the device is put into a low
-power state during the execution of the subsystem-level suspend callback, it is
-expected that remote wake-up will be enabled for the device.  Generally, remote
-wake-up should be enabled for all input devices put into a low power state at
-run time.
-
-The subsystem-level resume callback is _entirely_ _responsible_ for handling the
-resume of the device as appropriate, which may, but need not include executing
-the device driver's own ->runtime_resume() callback (from the PM core's point of
-view it is not necessary to implement a ->runtime_resume() callback in a device
-driver as long as the subsystem-level resume callback knows what to do to handle
-the device).
-
-  * Once the subsystem-level resume callback has completed successfully, the PM
-    core regards the device as fully operational, which means that the device
-    _must_ be able to complete I/O operations as needed.  The runtime PM status
-    of the device is then 'active'.
-
-  * If the subsystem-level resume callback returns an error code, the PM core
-    regards this as a fatal error and will refuse to run the helper functions
-    described in Section 4 for the device, until its status is directly set
-    either to 'active' or to 'suspended' (the PM core provides special helper
-    functions for this purpose).
-
-The subsystem-level idle callback is executed by the PM core whenever the device
-appears to be idle, which is indicated to the PM core by two counters, the
-device's usage counter and the counter of 'active' children of the device.
+device_run_wake() returns 'true' for the device and the device is put into a
+low-power state during the execution of the suspend callback, it is expected
+that remote wakeup will be enabled for the device.  Generally, remote wakeup
+should be enabled for all input devices put into low-power states at run time.
+
+The subsystem-level resume callback, if present, is _entirely_ _responsible_ for
+handling the resume of the device as appropriate, which may, but need not
+include executing the device driver's own ->runtime_resume() callback (from the
+PM core's point of view it is not necessary to implement a ->runtime_resume()
+callback in a device driver as long as the subsystem-level resume callback knows
+what to do to handle the device).
+
+  * Once the subsystem-level resume callback (or the driver resume callback, if
+    invoked directly) has completed successfully, the PM core regards the device
+    as fully operational, which means that the device _must_ be able to complete
+    I/O operations as needed.  The runtime PM status of the device is then
+    'active'.
+
+  * If the resume callback returns an error code, the PM core regards this as a
+    fatal error and will refuse to run the helper functions described in Section
+    4 for the device, until its status is directly set to either 'active', or
+    'suspended' (by means of special helper functions provided by the PM core
+    for this purpose).
+
+The idle callback (a subsystem-level one, if present, or the driver one) is
+executed by the PM core whenever the device appears to be idle, which is
+indicated to the PM core by two counters, the device's usage counter and the
+counter of 'active' children of the device.
 
   * If any of these counters is decreased using a helper function provided by
     the PM core and it turns out to be equal to zero, the other counter is
     checked.  If that counter also is equal to zero, the PM core executes the
-    subsystem-level idle callback with the device as an argument.
+    idle callback with the device as its argument.
 
-The action performed by a subsystem-level idle callback is totally dependent on
-the subsystem in question, but the expected and recommended action is to check
+The action performed by the idle callback is totally dependent on the subsystem
+(or driver) in question, but the expected and recommended action is to check
 if the device can be suspended (i.e. if all of the conditions necessary for
 suspending the device are satisfied) and to queue up a suspend request for the
 device in that case.  The value returned by this callback is ignored by the PM
 core.
 
 The helper functions provided by the PM core, described in Section 4, guarantee
-that the following constraints are met with respect to the bus type's runtime
-PM callbacks:
+that the following constraints are met with respect to runtime PM callbacks for
+one device:
 
 (1) The callbacks are mutually exclusive (e.g. it is forbidden to execute
     ->runtime_suspend() in parallel with ->runtime_resume() or with another

arch/alpha/include/asm/thread_info.h

@@ -79,7 +79,6 @@ register struct thread_info *__current_thread_info __asm__("$8");
 #define TIF_UAC_SIGBUS		12	/* ! userspace part of 'osf_sysinfo' */
 #define TIF_MEMDIE		13	/* is terminating due to OOM killer */
 #define TIF_RESTORE_SIGMASK	14	/* restore signal mask in do_signal */
-#define TIF_FREEZE		16	/* is freezing for suspend */
 
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
@@ -87,7 +86,6 @@ register struct thread_info *__current_thread_info __asm__("$8");
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_RESTORE_SIGMASK	(1<<TIF_RESTORE_SIGMASK)
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
-#define _TIF_FREEZE		(1<<TIF_FREEZE)
 
 /* Work to do on interrupt/exception return.  */
 #define _TIF_WORK_MASK		(_TIF_SIGPENDING | _TIF_NEED_RESCHED | \

arch/arm/include/asm/thread_info.h

@@ -142,7 +142,6 @@ extern void vfp_flush_hwstate(struct thread_info *);
 #define TIF_POLLING_NRFLAG	16
 #define TIF_USING_IWMMXT	17
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
-#define TIF_FREEZE		19
 #define TIF_RESTORE_SIGMASK	20
 #define TIF_SECCOMP		21
 
@@ -152,7 +151,6 @@ extern void vfp_flush_hwstate(struct thread_info *);
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
 #define _TIF_USING_IWMMXT	(1 << TIF_USING_IWMMXT)
-#define _TIF_FREEZE		(1 << TIF_FREEZE)
 #define _TIF_RESTORE_SIGMASK	(1 << TIF_RESTORE_SIGMASK)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
 

arch/avr32/include/asm/thread_info.h

@@ -85,7 +85,6 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_RESTORE_SIGMASK	7	/* restore signal mask in do_signal */
 #define TIF_CPU_GOING_TO_SLEEP	8	/* CPU is entering sleep 0 mode */
 #define TIF_NOTIFY_RESUME	9	/* callback before returning to user */
-#define TIF_FREEZE		29
 #define TIF_DEBUG		30	/* debugging enabled */
 #define TIF_USERSPACE		31      /* true if FS sets userspace */
 
@@ -98,7 +97,6 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_RESTORE_SIGMASK	(1 << TIF_RESTORE_SIGMASK)
 #define _TIF_CPU_GOING_TO_SLEEP (1 << TIF_CPU_GOING_TO_SLEEP)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
-#define _TIF_FREEZE		(1 << TIF_FREEZE)
 
 /* Note: The masks below must never span more than 16 bits! */
 

arch/blackfin/include/asm/thread_info.h

@@ -100,7 +100,6 @@ static inline struct thread_info *current_thread_info(void)
 					   TIF_NEED_RESCHED */
 #define TIF_MEMDIE		4	/* is terminating due to OOM killer */
 #define TIF_RESTORE_SIGMASK	5	/* restore signal mask in do_signal() */
-#define TIF_FREEZE		6	/* is freezing for suspend */
 #define TIF_IRQ_SYNC		7	/* sync pipeline stage */
 #define TIF_NOTIFY_RESUME	8	/* callback before returning to user */
 #define TIF_SINGLESTEP		9
@@ -111,7 +110,6 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_RESTORE_SIGMASK	(1<<TIF_RESTORE_SIGMASK)
-#define _TIF_FREEZE		(1<<TIF_FREEZE)
 #define _TIF_IRQ_SYNC		(1<<TIF_IRQ_SYNC)
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
 #define _TIF_SINGLESTEP		(1<<TIF_SINGLESTEP)

arch/cris/include/asm/thread_info.h

@@ -86,7 +86,6 @@ struct thread_info {
 #define TIF_RESTORE_SIGMASK	9	/* restore signal mask in do_signal() */
 #define TIF_POLLING_NRFLAG	16	/* true if poll_idle() is polling TIF_NEED_RESCHED */
 #define TIF_MEMDIE		17	/* is terminating due to OOM killer */
-#define TIF_FREEZE		18	/* is freezing for suspend */
 
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
@@ -94,7 +93,6 @@ struct thread_info {
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
 #define _TIF_RESTORE_SIGMASK	(1<<TIF_RESTORE_SIGMASK)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
-#define _TIF_FREEZE		(1<<TIF_FREEZE)
 
 #define _TIF_WORK_MASK		0x0000FFFE	/* work to do on interrupt/exception return */
 #define _TIF_ALLWORK_MASK	0x0000FFFF	/* work to do on any return to u-space */

arch/frv/include/asm/thread_info.h

@@ -111,7 +111,6 @@ register struct thread_info *__current_thread_info asm("gr15");
 #define TIF_RESTORE_SIGMASK	5	/* restore signal mask in do_signal() */
 #define TIF_POLLING_NRFLAG	16	/* true if poll_idle() is polling TIF_NEED_RESCHED */
 #define TIF_MEMDIE		17	/* is terminating due to OOM killer */
-#define TIF_FREEZE		18	/* freezing for suspend */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
@@ -120,7 +119,6 @@ register struct thread_info *__current_thread_info asm("gr15");
 #define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
 #define _TIF_RESTORE_SIGMASK	(1 << TIF_RESTORE_SIGMASK)
 #define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
-#define _TIF_FREEZE		(1 << TIF_FREEZE)
 
 #define _TIF_WORK_MASK		0x0000FFFE	/* work to do on interrupt/exception return */
 #define _TIF_ALLWORK_MASK	0x0000FFFF	/* work to do on any return to u-space */

arch/h8300/include/asm/thread_info.h

@@ -90,7 +90,6 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_MEMDIE		4	/* is terminating due to OOM killer */
 #define TIF_RESTORE_SIGMASK	5	/* restore signal mask in do_signal() */
 #define TIF_NOTIFY_RESUME	6	/* callback before returning to user */
-#define TIF_FREEZE		16	/* is freezing for suspend */
 
 /* as above, but as bit values */
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
@@ -99,7 +98,6 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_RESTORE_SIGMASK	(1<<TIF_RESTORE_SIGMASK)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
-#define _TIF_FREEZE		(1<<TIF_FREEZE)
 
 #define _TIF_WORK_MASK		0x0000FFFE	/* work to do on interrupt/exception return */
 

arch/ia64/include/asm/thread_info.h

@@ -113,7 +113,6 @@ struct thread_info {
 #define TIF_MEMDIE		17	/* is terminating due to OOM killer */
 #define TIF_MCA_INIT		18	/* this task is processing MCA or INIT */
 #define TIF_DB_DISABLED		19	/* debug trap disabled for fsyscall */
-#define TIF_FREEZE		20	/* is freezing for suspend */
 #define TIF_RESTORE_RSE		21	/* user RBS is newer than kernel RBS */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
@@ -126,7 +125,6 @@ struct thread_info {
 #define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
 #define _TIF_MCA_INIT		(1 << TIF_MCA_INIT)
 #define _TIF_DB_DISABLED	(1 << TIF_DB_DISABLED)
-#define _TIF_FREEZE		(1 << TIF_FREEZE)
 #define _TIF_RESTORE_RSE	(1 << TIF_RESTORE_RSE)
 
 /* "work to do on user-return" bits */

arch/m32r/include/asm/thread_info.h

@@ -138,7 +138,6 @@ static inline unsigned int get_thread_fault_code(void)
 #define TIF_USEDFPU		16	/* FPU was used by this task this quantum (SMP) */
 #define TIF_POLLING_NRFLAG	17	/* true if poll_idle() is polling TIF_NEED_RESCHED */
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
-#define TIF_FREEZE		19	/* is freezing for suspend */
 
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
@@ -149,7 +148,6 @@ static inline unsigned int get_thread_fault_code(void)
 #define _TIF_RESTORE_SIGMASK	(1<<TIF_RESTORE_SIGMASK)
 #define _TIF_USEDFPU		(1<<TIF_USEDFPU)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
-#define _TIF_FREEZE		(1<<TIF_FREEZE)
 
 #define _TIF_WORK_MASK		0x0000FFFE	/* work to do on interrupt/exception return */
 #define _TIF_ALLWORK_MASK	0x0000FFFF	/* work to do on any return to u-space */

arch/m68k/include/asm/thread_info.h

@@ -103,7 +103,6 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_DELAYED_TRACE	14	/* single step a syscall */
 #define TIF_SYSCALL_TRACE	15	/* syscall trace active */
 #define TIF_MEMDIE		16	/* is terminating due to OOM killer */
-#define TIF_FREEZE		17	/* thread is freezing for suspend */
 #define TIF_RESTORE_SIGMASK	18	/* restore signal mask in do_signal */
 
 #endif	/* _ASM_M68K_THREAD_INFO_H */

arch/microblaze/include/asm/thread_info.h

@@ -125,7 +125,6 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_MEMDIE		6	/* is terminating due to OOM killer */
 #define TIF_SYSCALL_AUDIT	9       /* syscall auditing active */
 #define TIF_SECCOMP		10      /* secure computing */
-#define TIF_FREEZE		14	/* Freezing for suspend */
 
 /* true if poll_idle() is polling TIF_NEED_RESCHED */
 #define TIF_POLLING_NRFLAG	16
@@ -137,7 +136,6 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
 #define _TIF_IRET		(1 << TIF_IRET)
 #define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
-#define _TIF_FREEZE		(1 << TIF_FREEZE)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
 

arch/mips/include/asm/thread_info.h

@@ -117,7 +117,6 @@ register struct thread_info *__current_thread_info __asm__("$28");
 #define TIF_USEDFPU		16	/* FPU was used by this task this quantum (SMP) */
 #define TIF_POLLING_NRFLAG	17	/* true if poll_idle() is polling TIF_NEED_RESCHED */
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
-#define TIF_FREEZE		19
 #define TIF_FIXADE		20	/* Fix address errors in software */
 #define TIF_LOGADE		21	/* Log address errors to syslog */
 #define TIF_32BIT_REGS		22	/* also implies 16/32 fprs */
@@ -141,7 +140,6 @@ register struct thread_info *__current_thread_info __asm__("$28");
 #define _TIF_RESTORE_SIGMASK	(1<<TIF_RESTORE_SIGMASK)
 #define _TIF_USEDFPU		(1<<TIF_USEDFPU)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
-#define _TIF_FREEZE		(1<<TIF_FREEZE)
 #define _TIF_FIXADE		(1<<TIF_FIXADE)
 #define _TIF_LOGADE		(1<<TIF_LOGADE)
 #define _TIF_32BIT_REGS		(1<<TIF_32BIT_REGS)

arch/mn10300/include/asm/thread_info.h

@@ -165,7 +165,6 @@ extern void free_thread_info(struct thread_info *);
 #define TIF_RESTORE_SIGMASK	5	/* restore signal mask in do_signal() */
 #define TIF_POLLING_NRFLAG	16	/* true if poll_idle() is polling TIF_NEED_RESCHED */
 #define TIF_MEMDIE		17	/* is terminating due to OOM killer */
-#define TIF_FREEZE		18	/* freezing for suspend */
 
 #define _TIF_SYSCALL_TRACE	+(1 << TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	+(1 << TIF_NOTIFY_RESUME)
@@ -174,7 +173,6 @@ extern void free_thread_info(struct thread_info *);
 #define _TIF_SINGLESTEP		+(1 << TIF_SINGLESTEP)
 #define _TIF_RESTORE_SIGMASK	+(1 << TIF_RESTORE_SIGMASK)
 #define _TIF_POLLING_NRFLAG	+(1 << TIF_POLLING_NRFLAG)
-#define _TIF_FREEZE		+(1 << TIF_FREEZE)
 
 #define _TIF_WORK_MASK		0x0000FFFE	/* work to do on interrupt/exception return */
 #define _TIF_ALLWORK_MASK	0x0000FFFF	/* work to do on any return to u-space */

arch/parisc/include/asm/thread_info.h

@@ -58,7 +58,6 @@ struct thread_info {
 #define TIF_32BIT               4       /* 32 bit binary */
 #define TIF_MEMDIE		5	/* is terminating due to OOM killer */
 #define TIF_RESTORE_SIGMASK	6	/* restore saved signal mask */
-#define TIF_FREEZE		7	/* is freezing for suspend */
 #define TIF_NOTIFY_RESUME	8	/* callback before returning to user */
 #define TIF_SINGLESTEP		9	/* single stepping? */
 #define TIF_BLOCKSTEP		10	/* branch stepping? */
@@ -69,7 +68,6 @@ struct thread_info {
 #define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
 #define _TIF_32BIT		(1 << TIF_32BIT)
 #define _TIF_RESTORE_SIGMASK	(1 << TIF_RESTORE_SIGMASK)
-#define _TIF_FREEZE		(1 << TIF_FREEZE)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
 #define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
 #define _TIF_BLOCKSTEP		(1 << TIF_BLOCKSTEP)

arch/powerpc/include/asm/thread_info.h

@@ -109,7 +109,6 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_RESTOREALL		11	/* Restore all regs (implies NOERROR) */
 #define TIF_NOERROR		12	/* Force successful syscall return */
 #define TIF_NOTIFY_RESUME	13	/* callback before returning to user */
-#define TIF_FREEZE		14	/* Freezing for suspend */
 #define TIF_SYSCALL_TRACEPOINT	15	/* syscall tracepoint instrumentation */
 #define TIF_RUNLATCH		16	/* Is the runlatch enabled? */
 
@@ -127,7 +126,6 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_RESTOREALL		(1<<TIF_RESTOREALL)
 #define _TIF_NOERROR		(1<<TIF_NOERROR)
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
-#define _TIF_FREEZE		(1<<TIF_FREEZE)
 #define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
 #define _TIF_RUNLATCH		(1<<TIF_RUNLATCH)
 #define _TIF_SYSCALL_T_OR_A	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \

arch/powerpc/kernel/vio.c

@@ -1406,7 +1406,6 @@ static struct bus_type vio_bus_type = {
 	.match = vio_bus_match,
 	.probe = vio_bus_probe,
 	.remove = vio_bus_remove,
-	.pm = GENERIC_SUBSYS_PM_OPS,
 };
 
 /**

arch/s390/include/asm/thread_info.h

@@ -102,7 +102,6 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
 #define TIF_RESTORE_SIGMASK	19	/* restore signal mask in do_signal() */
 #define TIF_SINGLE_STEP		20	/* This task is single stepped */
-#define TIF_FREEZE		21	/* thread is freezing for suspend */
 
 #define _TIF_SYSCALL		(1<<TIF_SYSCALL)
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
@@ -119,7 +118,6 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_31BIT		(1<<TIF_31BIT)
 #define _TIF_SINGLE_STEP	(1<<TIF_SINGLE_STEP)
-#define _TIF_FREEZE		(1<<TIF_FREEZE)
 
 #ifdef CONFIG_64BIT
 #define is_32bit_task()		(test_thread_flag(TIF_31BIT))

arch/sh/include/asm/thread_info.h

@@ -122,7 +122,6 @@ extern void init_thread_xstate(void);
 #define TIF_SYSCALL_TRACEPOINT	8	/* for ftrace syscall instrumentation */
 #define TIF_POLLING_NRFLAG	17	/* true if poll_idle() is polling TIF_NEED_RESCHED */
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
-#define TIF_FREEZE		19	/* Freezing for suspend */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
@@ -133,7 +132,6 @@ extern void init_thread_xstate(void);
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
 #define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
-#define _TIF_FREEZE		(1 << TIF_FREEZE)
 
 /*
  * _TIF_ALLWORK_MASK and _TIF_WORK_MASK need to fit within 2 bytes, or we

arch/sparc/include/asm/thread_info_32.h

@@ -133,7 +133,6 @@ BTFIXUPDEF_CALL(void, free_thread_info, struct thread_info *)
 #define TIF_POLLING_NRFLAG	9	/* true if poll_idle() is polling
 					 * TIF_NEED_RESCHED */
 #define TIF_MEMDIE		10	/* is terminating due to OOM killer */
-#define TIF_FREEZE		11	/* is freezing for suspend */
 
 /* as above, but as bit values */
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
@@ -147,7 +146,6 @@ BTFIXUPDEF_CALL(void, free_thread_info, struct thread_info *)
 #define _TIF_DO_NOTIFY_RESUME_MASK	(_TIF_NOTIFY_RESUME | \
 					 _TIF_SIGPENDING | \
 					 _TIF_RESTORE_SIGMASK)
-#define _TIF_FREEZE		(1<<TIF_FREEZE)
 
 #endif /* __KERNEL__ */
 

arch/sparc/include/asm/thread_info_64.h

@@ -225,7 +225,6 @@ register struct thread_info *current_thread_info_reg asm("g6");
 /* flag bit 12 is available */
 #define TIF_MEMDIE		13	/* is terminating due to OOM killer */
 #define TIF_POLLING_NRFLAG	14
-#define TIF_FREEZE		15	/* is freezing for suspend */
 
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
@@ -237,7 +236,6 @@ register struct thread_info *current_thread_info_reg asm("g6");
 #define _TIF_SYSCALL_AUDIT	(1<<TIF_SYSCALL_AUDIT)
 #define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
-#define _TIF_FREEZE		(1<<TIF_FREEZE)
 
 #define _TIF_USER_WORK_MASK	((0xff << TI_FLAG_WSAVED_SHIFT) | \
 				 _TIF_DO_NOTIFY_RESUME_MASK | \

arch/um/include/asm/thread_info.h

@@ -71,7 +71,6 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_MEMDIE		5	/* is terminating due to OOM killer */
 #define TIF_SYSCALL_AUDIT	6
 #define TIF_RESTORE_SIGMASK	7
-#define TIF_FREEZE		16	/* is freezing for suspend */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
@@ -80,6 +79,5 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_MEMDIE		(1 << TIF_MEMDIE)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_RESTORE_SIGMASK	(1 << TIF_RESTORE_SIGMASK)
-#define _TIF_FREEZE		(1 << TIF_FREEZE)
 
 #endif

arch/unicore32/include/asm/thread_info.h

@@ -135,14 +135,12 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_NOTIFY_RESUME	2	/* callback before returning to user */
 #define TIF_SYSCALL_TRACE	8
 #define TIF_MEMDIE		18
-#define TIF_FREEZE		19
 #define TIF_RESTORE_SIGMASK	20
 
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
-#define _TIF_FREEZE		(1 << TIF_FREEZE)
 #define _TIF_RESTORE_SIGMASK	(1 << TIF_RESTORE_SIGMASK)
 
 /*

arch/x86/include/asm/thread_info.h

@@ -90,7 +90,6 @@ struct thread_info {
 #define TIF_MEMDIE		20	/* is terminating due to OOM killer */
 #define TIF_DEBUG		21	/* uses debug registers */
 #define TIF_IO_BITMAP		22	/* uses I/O bitmap */
-#define TIF_FREEZE		23	/* is freezing for suspend */
 #define TIF_FORCED_TF		24	/* true if TF in eflags artificially */
 #define TIF_BLOCKSTEP		25	/* set when we want DEBUGCTLMSR_BTF */
 #define TIF_LAZY_MMU_UPDATES	27	/* task is updating the mmu lazily */
@@ -112,7 +111,6 @@ struct thread_info {
 #define _TIF_FORK		(1 << TIF_FORK)
 #define _TIF_DEBUG		(1 << TIF_DEBUG)
 #define _TIF_IO_BITMAP		(1 << TIF_IO_BITMAP)
-#define _TIF_FREEZE		(1 << TIF_FREEZE)
 #define _TIF_FORCED_TF		(1 << TIF_FORCED_TF)
 #define _TIF_BLOCKSTEP		(1 << TIF_BLOCKSTEP)
 #define _TIF_LAZY_MMU_UPDATES	(1 << TIF_LAZY_MMU_UPDATES)

arch/xtensa/include/asm/thread_info.h

@@ -132,7 +132,6 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_MEMDIE		5	/* is terminating due to OOM killer */
 #define TIF_RESTORE_SIGMASK	6	/* restore signal mask in do_signal() */
 #define TIF_POLLING_NRFLAG	16	/* true if poll_idle() is polling TIF_NEED_RESCHED */
-#define TIF_FREEZE		17	/* is freezing for suspend */
 
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
@@ -141,7 +140,6 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_IRET		(1<<TIF_IRET)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_RESTORE_SIGMASK	(1<<TIF_RESTORE_SIGMASK)
-#define _TIF_FREEZE		(1<<TIF_FREEZE)
 
 #define _TIF_WORK_MASK		0x0000FFFE	/* work to do on interrupt/exception return */
 #define _TIF_ALLWORK_MASK	0x0000FFFF	/* work to do on any return to u-space */

drivers/acpi/sleep.c

@@ -476,6 +476,22 @@ static struct dmi_system_id __initdata acpisleep_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "VGN-FW520F"),
 		},
 	},
+	{
+	.callback = init_nvs_nosave,
+	.ident = "Asus K54C",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "K54C"),
+		},
+	},
+	{
+	.callback = init_nvs_nosave,
+	.ident = "Asus K54HR",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "K54HR"),
+		},
+	},
 	{},
 };
 #endif /* CONFIG_SUSPEND */

drivers/amba/bus.c

@@ -109,31 +109,7 @@ static int amba_legacy_resume(struct device *dev)
 	return ret;
 }
 
-static int amba_pm_prepare(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (drv && drv->pm && drv->pm->prepare)
-		ret = drv->pm->prepare(dev);
-
-	return ret;
-}
-
-static void amba_pm_complete(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-
-	if (drv && drv->pm && drv->pm->complete)
-		drv->pm->complete(dev);
-}
-
-#else /* !CONFIG_PM_SLEEP */
-
-#define amba_pm_prepare		NULL
-#define amba_pm_complete		NULL
-
-#endif /* !CONFIG_PM_SLEEP */
+#endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_SUSPEND
 
@@ -155,22 +131,6 @@ static int amba_pm_suspend(struct device *dev)
 	return ret;
 }
 
-static int amba_pm_suspend_noirq(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->suspend_noirq)
-			ret = drv->pm->suspend_noirq(dev);
-	}
-
-	return ret;
-}
-
 static int amba_pm_resume(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
@@ -189,28 +149,10 @@ static int amba_pm_resume(struct device *dev)
 	return ret;
 }
 
-static int amba_pm_resume_noirq(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->resume_noirq)
-			ret = drv->pm->resume_noirq(dev);
-	}
-
-	return ret;
-}
-
 #else /* !CONFIG_SUSPEND */
 
 #define amba_pm_suspend		NULL
 #define amba_pm_resume		NULL
-#define amba_pm_suspend_noirq	NULL
-#define amba_pm_resume_noirq	NULL
 
 #endif /* !CONFIG_SUSPEND */
 
@@ -234,22 +176,6 @@ static int amba_pm_freeze(struct device *dev)
 	return ret;
 }
 
-static int amba_pm_freeze_noirq(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->freeze_noirq)
-			ret = drv->pm->freeze_noirq(dev);
-	}
-
-	return ret;
-}
-
 static int amba_pm_thaw(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
@@ -268,22 +194,6 @@ static int amba_pm_thaw(struct device *dev)
 	return ret;
 }
 
-static int amba_pm_thaw_noirq(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->thaw_noirq)
-			ret = drv->pm->thaw_noirq(dev);
-	}
-
-	return ret;
-}
-
 static int amba_pm_poweroff(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
@@ -302,22 +212,6 @@ static int amba_pm_poweroff(struct device *dev)
 	return ret;
 }
 
-static int amba_pm_poweroff_noirq(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->poweroff_noirq)
-			ret = drv->pm->poweroff_noirq(dev);
-	}
-
-	return ret;
-}
-
 static int amba_pm_restore(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
@@ -336,32 +230,12 @@ static int amba_pm_restore(struct device *dev)
 	return ret;
 }
 
-static int amba_pm_restore_noirq(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->restore_noirq)
-			ret = drv->pm->restore_noirq(dev);
-	}
-
-	return ret;
-}
-
 #else /* !CONFIG_HIBERNATE_CALLBACKS */
 
 #define amba_pm_freeze		NULL
 #define amba_pm_thaw		NULL
 #define amba_pm_poweroff		NULL
 #define amba_pm_restore		NULL
-#define amba_pm_freeze_noirq	NULL
-#define amba_pm_thaw_noirq		NULL
-#define amba_pm_poweroff_noirq	NULL
-#define amba_pm_restore_noirq	NULL
 
 #endif /* !CONFIG_HIBERNATE_CALLBACKS */
 
@@ -402,20 +276,12 @@ static int amba_pm_runtime_resume(struct device *dev)
 #ifdef CONFIG_PM
 
 static const struct dev_pm_ops amba_pm = {
-	.prepare	= amba_pm_prepare,
-	.complete	= amba_pm_complete,
 	.suspend	= amba_pm_suspend,
 	.resume		= amba_pm_resume,
 	.freeze		= amba_pm_freeze,
 	.thaw		= amba_pm_thaw,
 	.poweroff	= amba_pm_poweroff,
 	.restore	= amba_pm_restore,
-	.suspend_noirq	= amba_pm_suspend_noirq,
-	.resume_noirq	= amba_pm_resume_noirq,
-	.freeze_noirq	= amba_pm_freeze_noirq,
-	.thaw_noirq	= amba_pm_thaw_noirq,
-	.poweroff_noirq	= amba_pm_poweroff_noirq,
-	.restore_noirq	= amba_pm_restore_noirq,
 	SET_RUNTIME_PM_OPS(
 		amba_pm_runtime_suspend,
 		amba_pm_runtime_resume,

drivers/base/firmware_class.c

@@ -534,6 +534,8 @@ static int _request_firmware(const struct firmware **firmware_p,
 		return 0;
 	}
 
+	read_lock_usermodehelper();
+
 	if (WARN_ON(usermodehelper_is_disabled())) {
 		dev_err(device, "firmware: %s will not be loaded\n", name);
 		retval = -EBUSY;
@@ -572,6 +574,8 @@ static int _request_firmware(const struct firmware **firmware_p,
 	fw_destroy_instance(fw_priv);
 
 out:
+	read_unlock_usermodehelper();
+
 	if (retval) {
 		release_firmware(firmware);
 		*firmware_p = NULL;

drivers/base/platform.c

@@ -700,25 +700,6 @@ static int platform_legacy_resume(struct device *dev)
 	return ret;
 }
 
-int platform_pm_prepare(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (drv && drv->pm && drv->pm->prepare)
-		ret = drv->pm->prepare(dev);
-
-	return ret;
-}
-
-void platform_pm_complete(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-
-	if (drv && drv->pm && drv->pm->complete)
-		drv->pm->complete(dev);
-}
-
 #endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_SUSPEND
@@ -741,22 +722,6 @@ int platform_pm_suspend(struct device *dev)
 	return ret;
 }
 
-int platform_pm_suspend_noirq(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->suspend_noirq)
-			ret = drv->pm->suspend_noirq(dev);
-	}
-
-	return ret;
-}
-
 int platform_pm_resume(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
@@ -775,22 +740,6 @@ int platform_pm_resume(struct device *dev)
 	return ret;
 }
 
-int platform_pm_resume_noirq(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->resume_noirq)
-			ret = drv->pm->resume_noirq(dev);
-	}
-
-	return ret;
-}
-
 #endif /* CONFIG_SUSPEND */
 
 #ifdef CONFIG_HIBERNATE_CALLBACKS
@@ -813,22 +762,6 @@ int platform_pm_freeze(struct device *dev)
 	return ret;
 }
 
-int platform_pm_freeze_noirq(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->freeze_noirq)
-			ret = drv->pm->freeze_noirq(dev);
-	}
-
-	return ret;
-}
-
 int platform_pm_thaw(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
@@ -847,22 +780,6 @@ int platform_pm_thaw(struct device *dev)
 	return ret;
 }
 
-int platform_pm_thaw_noirq(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->thaw_noirq)
-			ret = drv->pm->thaw_noirq(dev);
-	}
-
-	return ret;
-}
-
 int platform_pm_poweroff(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
@@ -881,22 +798,6 @@ int platform_pm_poweroff(struct device *dev)
 	return ret;
 }
 
-int platform_pm_poweroff_noirq(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->poweroff_noirq)
-			ret = drv->pm->poweroff_noirq(dev);
-	}
-
-	return ret;
-}
-
 int platform_pm_restore(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
@@ -915,22 +816,6 @@ int platform_pm_restore(struct device *dev)
 	return ret;
 }
 
-int platform_pm_restore_noirq(struct device *dev)
-{
-	struct device_driver *drv = dev->driver;
-	int ret = 0;
-
-	if (!drv)
-		return 0;
-
-	if (drv->pm) {
-		if (drv->pm->restore_noirq)
-			ret = drv->pm->restore_noirq(dev);
-	}
-
-	return ret;
-}
-
 #endif /* CONFIG_HIBERNATE_CALLBACKS */
 
 static const struct dev_pm_ops platform_dev_pm_ops = {

drivers/base/power/generic_ops.c

@@ -97,16 +97,16 @@ int pm_generic_prepare(struct device *dev)
  * @event: PM transition of the system under way.
  * @bool: Whether or not this is the "noirq" stage.
  *
- * If the device has not been suspended at run time, execute the
- * suspend/freeze/poweroff/thaw callback provided by its driver, if defined, and
- * return its error code.  Otherwise, return zero.
+ * Execute the PM callback corresponding to @event provided by the driver of
+ * @dev, if defined, and return its error code.    Return 0 if the callback is
+ * not present.
  */
 static int __pm_generic_call(struct device *dev, int event, bool noirq)
 {
 	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
 	int (*callback)(struct device *);
 
-	if (!pm || pm_runtime_suspended(dev))
+	if (!pm)
 		return 0;
 
 	switch (event) {
@@ -119,9 +119,15 @@ static int __pm_generic_call(struct device *dev, int event, bool noirq)
 	case PM_EVENT_HIBERNATE:
 		callback = noirq ? pm->poweroff_noirq : pm->poweroff;
 		break;
+	case PM_EVENT_RESUME:
+		callback = noirq ? pm->resume_noirq : pm->resume;
+		break;
 	case PM_EVENT_THAW:
 		callback = noirq ? pm->thaw_noirq : pm->thaw;
 		break;
+	case PM_EVENT_RESTORE:
+		callback = noirq ? pm->restore_noirq : pm->restore;
+		break;
 	default:
 		callback = NULL;
 		break;
@@ -210,57 +216,13 @@ int pm_generic_thaw(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(pm_generic_thaw);
 
-/**
- * __pm_generic_resume - Generic resume/restore callback for subsystems.
- * @dev: Device to handle.
- * @event: PM transition of the system under way.
- * @bool: Whether or not this is the "noirq" stage.
- *
- * Execute the resume/resotre callback provided by the @dev's driver, if
- * defined.  If it returns 0, change the device's runtime PM status to 'active'.
- * Return the callback's error code.
- */
-static int __pm_generic_resume(struct device *dev, int event, bool noirq)
-{
-	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
-	int (*callback)(struct device *);
-	int ret;
-
-	if (!pm)
-		return 0;
-
-	switch (event) {
-	case PM_EVENT_RESUME:
-		callback = noirq ? pm->resume_noirq : pm->resume;
-		break;
-	case PM_EVENT_RESTORE:
-		callback = noirq ? pm->restore_noirq : pm->restore;
-		break;
-	default:
-		callback = NULL;
-		break;
-	}
-
-	if (!callback)
-		return 0;
-
-	ret = callback(dev);
-	if (!ret && !noirq && pm_runtime_enabled(dev)) {
-		pm_runtime_disable(dev);
-		pm_runtime_set_active(dev);
-		pm_runtime_enable(dev);
-	}
-
-	return ret;
-}
-
 /**
  * pm_generic_resume_noirq - Generic resume_noirq callback for subsystems.
  * @dev: Device to resume.
  */
 int pm_generic_resume_noirq(struct device *dev)
 {
-	return __pm_generic_resume(dev, PM_EVENT_RESUME, true);
+	return __pm_generic_call(dev, PM_EVENT_RESUME, true);
 }
 EXPORT_SYMBOL_GPL(pm_generic_resume_noirq);
 
@@ -270,7 +232,7 @@ EXPORT_SYMBOL_GPL(pm_generic_resume_noirq);
  */
 int pm_generic_resume(struct device *dev)
 {
-	return __pm_generic_resume(dev, PM_EVENT_RESUME, false);
+	return __pm_generic_call(dev, PM_EVENT_RESUME, false);
 }
 EXPORT_SYMBOL_GPL(pm_generic_resume);
 
@@ -280,7 +242,7 @@ EXPORT_SYMBOL_GPL(pm_generic_resume);
  */
 int pm_generic_restore_noirq(struct device *dev)
 {
-	return __pm_generic_resume(dev, PM_EVENT_RESTORE, true);
+	return __pm_generic_call(dev, PM_EVENT_RESTORE, true);
 }
 EXPORT_SYMBOL_GPL(pm_generic_restore_noirq);
 
@@ -290,7 +252,7 @@ EXPORT_SYMBOL_GPL(pm_generic_restore_noirq);
  */
 int pm_generic_restore(struct device *dev)
 {
-	return __pm_generic_resume(dev, PM_EVENT_RESTORE, false);
+	return __pm_generic_call(dev, PM_EVENT_RESTORE, false);
 }
 EXPORT_SYMBOL_GPL(pm_generic_restore);
 
@@ -314,28 +276,3 @@ void pm_generic_complete(struct device *dev)
 	pm_runtime_idle(dev);
 }
 #endif /* CONFIG_PM_SLEEP */
-
-struct dev_pm_ops generic_subsys_pm_ops = {
-#ifdef CONFIG_PM_SLEEP
-	.prepare = pm_generic_prepare,
-	.suspend = pm_generic_suspend,
-	.suspend_noirq = pm_generic_suspend_noirq,
-	.resume = pm_generic_resume,
-	.resume_noirq = pm_generic_resume_noirq,
-	.freeze = pm_generic_freeze,
-	.freeze_noirq = pm_generic_freeze_noirq,
-	.thaw = pm_generic_thaw,
-	.thaw_noirq = pm_generic_thaw_noirq,
-	.poweroff = pm_generic_poweroff,
-	.poweroff_noirq = pm_generic_poweroff_noirq,
-	.restore = pm_generic_restore,
-	.restore_noirq = pm_generic_restore_noirq,
-	.complete = pm_generic_complete,
-#endif
-#ifdef CONFIG_PM_RUNTIME
-	.runtime_suspend = pm_generic_runtime_suspend,
-	.runtime_resume = pm_generic_runtime_resume,
-	.runtime_idle = pm_generic_runtime_idle,
-#endif
-};
-EXPORT_SYMBOL_GPL(generic_subsys_pm_ops);

drivers/base/power/main.c

@@ -32,6 +32,8 @@
 #include "../base.h"
 #include "power.h"
 
+typedef int (*pm_callback_t)(struct device *);
+
 /*
  * The entries in the dpm_list list are in a depth first order, simply
  * because children are guaranteed to be discovered after parents, and
@@ -164,8 +166,9 @@ static ktime_t initcall_debug_start(struct device *dev)
 	ktime_t calltime = ktime_set(0, 0);
 
 	if (initcall_debug) {
-		pr_info("calling  %s+ @ %i\n",
-				dev_name(dev), task_pid_nr(current));
+		pr_info("calling  %s+ @ %i, parent: %s\n",
+			dev_name(dev), task_pid_nr(current),
+			dev->parent ? dev_name(dev->parent) : "none");
 		calltime = ktime_get();
 	}
 
@@ -211,151 +214,69 @@ static void dpm_wait_for_children(struct device *dev, bool async)
 }
 
 /**
- * pm_op - Execute the PM operation appropriate for given PM event.
- * @dev: Device to handle.
+ * pm_op - Return the PM operation appropriate for given PM event.
  * @ops: PM operations to choose from.
  * @state: PM transition of the system being carried out.
  */
-static int pm_op(struct device *dev,
-		 const struct dev_pm_ops *ops,
-		 pm_message_t state)
+static pm_callback_t pm_op(const struct dev_pm_ops *ops, pm_message_t state)
 {
-	int error = 0;
-	ktime_t calltime;
-
-	calltime = initcall_debug_start(dev);
-
 	switch (state.event) {
 #ifdef CONFIG_SUSPEND
 	case PM_EVENT_SUSPEND:
-		if (ops->suspend) {
-			error = ops->suspend(dev);
-			suspend_report_result(ops->suspend, error);
-		}
-		break;
+		return ops->suspend;
 	case PM_EVENT_RESUME:
-		if (ops->resume) {
-			error = ops->resume(dev);
-			suspend_report_result(ops->resume, error);
-		}
-		break;
+		return ops->resume;
 #endif /* CONFIG_SUSPEND */
 #ifdef CONFIG_HIBERNATE_CALLBACKS
 	case PM_EVENT_FREEZE:
 	case PM_EVENT_QUIESCE:
-		if (ops->freeze) {
-			error = ops->freeze(dev);
-			suspend_report_result(ops->freeze, error);
-		}
-		break;
+		return ops->freeze;
 	case PM_EVENT_HIBERNATE:
-		if (ops->poweroff) {
-			error = ops->poweroff(dev);
-			suspend_report_result(ops->poweroff, error);
-		}
-		break;
+		return ops->poweroff;
 	case PM_EVENT_THAW:
 	case PM_EVENT_RECOVER:
-		if (ops->thaw) {
-			error = ops->thaw(dev);
-			suspend_report_result(ops->thaw, error);
-		}
+		return ops->thaw;
 		break;
 	case PM_EVENT_RESTORE:
-		if (ops->restore) {
-			error = ops->restore(dev);
-			suspend_report_result(ops->restore, error);
-		}
-		break;
+		return ops->restore;
 #endif /* CONFIG_HIBERNATE_CALLBACKS */
-	default:
-		error = -EINVAL;
 	}
 
-	initcall_debug_report(dev, calltime, error);
-
-	return error;
+	return NULL;
 }
 
 /**
- * pm_noirq_op - Execute the PM operation appropriate for given PM event.
- * @dev: Device to handle.
+ * pm_noirq_op - Return the PM operation appropriate for given PM event.
  * @ops: PM operations to choose from.
  * @state: PM transition of the system being carried out.
  *
  * The driver of @dev will not receive interrupts while this function is being
  * executed.
  */
-static int pm_noirq_op(struct device *dev,
-			const struct dev_pm_ops *ops,
-			pm_message_t state)
+static pm_callback_t pm_noirq_op(const struct dev_pm_ops *ops, pm_message_t state)
 {
-	int error = 0;
-	ktime_t calltime = ktime_set(0, 0), delta, rettime;
-
-	if (initcall_debug) {
-		pr_info("calling  %s+ @ %i, parent: %s\n",
-				dev_name(dev), task_pid_nr(current),
-				dev->parent ? dev_name(dev->parent) : "none");
-		calltime = ktime_get();
-	}
-
 	switch (state.event) {
 #ifdef CONFIG_SUSPEND
 	case PM_EVENT_SUSPEND:
-		if (ops->suspend_noirq) {
-			error = ops->suspend_noirq(dev);
-			suspend_report_result(ops->suspend_noirq, error);
-		}
-		break;
+		return ops->suspend_noirq;
 	case PM_EVENT_RESUME:
-		if (ops->resume_noirq) {
-			error = ops->resume_noirq(dev);
-			suspend_report_result(ops->resume_noirq, error);
-		}
-		break;
+		return ops->resume_noirq;
 #endif /* CONFIG_SUSPEND */
 #ifdef CONFIG_HIBERNATE_CALLBACKS
 	case PM_EVENT_FREEZE:
 	case PM_EVENT_QUIESCE:
-		if (ops->freeze_noirq) {
-			error = ops->freeze_noirq(dev);
-			suspend_report_result(ops->freeze_noirq, error);
-		}
-		break;
+		return ops->freeze_noirq;
 	case PM_EVENT_HIBERNATE:
-		if (ops->poweroff_noirq) {
-			error = ops->poweroff_noirq(dev);
-			suspend_report_result(ops->poweroff_noirq, error);
-		}
-		break;
+		return ops->poweroff_noirq;
 	case PM_EVENT_THAW:
 	case PM_EVENT_RECOVER:
-		if (ops->thaw_noirq) {
-			error = ops->thaw_noirq(dev);
-			suspend_report_result(ops->thaw_noirq, error);
-		}
-		break;
+		return ops->thaw_noirq;
 	case PM_EVENT_RESTORE:
-		if (ops->restore_noirq) {
-			error = ops->restore_noirq(dev);
-			suspend_report_result(ops->restore_noirq, error);
-		}
-		break;
+		return ops->restore_noirq;
 #endif /* CONFIG_HIBERNATE_CALLBACKS */
-	default:
-		error = -EINVAL;
-	}
-
-	if (initcall_debug) {
-		rettime = ktime_get();
-		delta = ktime_sub(rettime, calltime);
-		printk("initcall %s_i+ returned %d after %Ld usecs\n",
-			dev_name(dev), error,
-			(unsigned long long)ktime_to_ns(delta) >> 10);
 	}
 
-	return error;
+	return NULL;
 }
 
 static char *pm_verb(int event)
@@ -413,6 +334,26 @@ static void dpm_show_time(ktime_t starttime, pm_message_t state, char *info)
 		usecs / USEC_PER_MSEC, usecs % USEC_PER_MSEC);
 }
 
+static int dpm_run_callback(pm_callback_t cb, struct device *dev,
+			    pm_message_t state, char *info)
+{
+	ktime_t calltime;
+	int error;
+
+	if (!cb)
+		return 0;
+
+	calltime = initcall_debug_start(dev);
+
+	pm_dev_dbg(dev, state, info);
+	error = cb(dev);
+	suspend_report_result(cb, error);
+
+	initcall_debug_report(dev, calltime, error);
+
+	return error;
+}
+
 /*------------------------- Resume routines -------------------------*/
 
 /**
@@ -425,25 +366,34 @@ static void dpm_show_time(ktime_t starttime, pm_message_t state, char *info)
  */
 static int device_resume_noirq(struct device *dev, pm_message_t state)
 {
+	pm_callback_t callback = NULL;
+	char *info = NULL;
 	int error = 0;
 
 	TRACE_DEVICE(dev);
 	TRACE_RESUME(0);
 
 	if (dev->pm_domain) {
-		pm_dev_dbg(dev, state, "EARLY power domain ");
-		error = pm_noirq_op(dev, &dev->pm_domain->ops, state);
+		info = "EARLY power domain ";
+		callback = pm_noirq_op(&dev->pm_domain->ops, state);
 	} else if (dev->type && dev->type->pm) {
-		pm_dev_dbg(dev, state, "EARLY type ");
-		error = pm_noirq_op(dev, dev->type->pm, state);
+		info = "EARLY type ";
+		callback = pm_noirq_op(dev->type->pm, state);
 	} else if (dev->class && dev->class->pm) {
-		pm_dev_dbg(dev, state, "EARLY class ");
-		error = pm_noirq_op(dev, dev->class->pm, state);
+		info = "EARLY class ";
+		callback = pm_noirq_op(dev->class->pm, state);
 	} else if (dev->bus && dev->bus->pm) {
-		pm_dev_dbg(dev, state, "EARLY ");
-		error = pm_noirq_op(dev, dev->bus->pm, state);
+		info = "EARLY bus ";
+		callback = pm_noirq_op(dev->bus->pm, state);
 	}
 
+	if (!callback && dev->driver && dev->driver->pm) {
+		info = "EARLY driver ";
+		callback = pm_noirq_op(dev->driver->pm, state);
+	}
+
+	error = dpm_run_callback(callback, dev, state, info);
+
 	TRACE_RESUME(error);
 	return error;
 }
@@ -485,26 +435,6 @@ void dpm_resume_noirq(pm_message_t state)
 }
 EXPORT_SYMBOL_GPL(dpm_resume_noirq);
 
-/**
- * legacy_resume - Execute a legacy (bus or class) resume callback for device.
- * @dev: Device to resume.
- * @cb: Resume callback to execute.
- */
-static int legacy_resume(struct device *dev, int (*cb)(struct device *dev))
-{
-	int error;
-	ktime_t calltime;
-
-	calltime = initcall_debug_start(dev);
-
-	error = cb(dev);
-	suspend_report_result(cb, error);
-
-	initcall_debug_report(dev, calltime, error);
-
-	return error;
-}
-
 /**
  * device_resume - Execute "resume" callbacks for given device.
  * @dev: Device to handle.
@@ -513,6 +443,8 @@ static int legacy_resume(struct device *dev, int (*cb)(struct device *dev))
  */
 static int device_resume(struct device *dev, pm_message_t state, bool async)
 {
+	pm_callback_t callback = NULL;
+	char *info = NULL;
 	int error = 0;
 	bool put = false;
 
@@ -535,40 +467,48 @@ static int device_resume(struct device *dev, pm_message_t state, bool async)
 	put = true;
 
 	if (dev->pm_domain) {
-		pm_dev_dbg(dev, state, "power domain ");
-		error = pm_op(dev, &dev->pm_domain->ops, state);
-		goto End;
+		info = "power domain ";
+		callback = pm_op(&dev->pm_domain->ops, state);
+		goto Driver;
 	}
 
 	if (dev->type && dev->type->pm) {
-		pm_dev_dbg(dev, state, "type ");
-		error = pm_op(dev, dev->type->pm, state);
-		goto End;
+		info = "type ";
+		callback = pm_op(dev->type->pm, state);
+		goto Driver;
 	}
 
 	if (dev->class) {
 		if (dev->class->pm) {
-			pm_dev_dbg(dev, state, "class ");
-			error = pm_op(dev, dev->class->pm, state);
-			goto End;
+			info = "class ";
+			callback = pm_op(dev->class->pm, state);
+			goto Driver;
 		} else if (dev->class->resume) {
-			pm_dev_dbg(dev, state, "legacy class ");
-			error = legacy_resume(dev, dev->class->resume);
+			info = "legacy class ";
+			callback = dev->class->resume;
 			goto End;
 		}
 	}
 
 	if (dev->bus) {
 		if (dev->bus->pm) {
-			pm_dev_dbg(dev, state, "");
-			error = pm_op(dev, dev->bus->pm, state);
+			info = "bus ";
+			callback = pm_op(dev->bus->pm, state);
 		} else if (dev->bus->resume) {
-			pm_dev_dbg(dev, state, "legacy ");
-			error = legacy_resume(dev, dev->bus->resume);
+			info = "legacy bus ";
+			callback = dev->bus->resume;
+			goto End;
 		}
 	}
 
+ Driver:
+	if (!callback && dev->driver && dev->driver->pm) {
+		info = "driver ";
+		callback = pm_op(dev->driver->pm, state);
+	}
+
  End:
+	error = dpm_run_callback(callback, dev, state, info);
 	dev->power.is_suspended = false;
 
  Unlock:
@@ -660,24 +600,33 @@ void dpm_resume(pm_message_t state)
  */
 static void device_complete(struct device *dev, pm_message_t state)
 {
+	void (*callback)(struct device *) = NULL;
+	char *info = NULL;
+
 	device_lock(dev);
 
 	if (dev->pm_domain) {
-		pm_dev_dbg(dev, state, "completing power domain ");
-		if (dev->pm_domain->ops.complete)
-			dev->pm_domain->ops.complete(dev);
+		info = "completing power domain ";
+		callback = dev->pm_domain->ops.complete;
 	} else if (dev->type && dev->type->pm) {
-		pm_dev_dbg(dev, state, "completing type ");
-		if (dev->type->pm->complete)
-			dev->type->pm->complete(dev);
+		info = "completing type ";
+		callback = dev->type->pm->complete;
 	} else if (dev->class && dev->class->pm) {
-		pm_dev_dbg(dev, state, "completing class ");
-		if (dev->class->pm->complete)
-			dev->class->pm->complete(dev);
+		info = "completing class ";
+		callback = dev->class->pm->complete;
 	} else if (dev->bus && dev->bus->pm) {
-		pm_dev_dbg(dev, state, "completing ");
-		if (dev->bus->pm->complete)
-			dev->bus->pm->complete(dev);
+		info = "completing bus ";
+		callback = dev->bus->pm->complete;
+	}
+
+	if (!callback && dev->driver && dev->driver->pm) {
+		info = "completing driver ";
+		callback = dev->driver->pm->complete;
+	}
+
+	if (callback) {
+		pm_dev_dbg(dev, state, info);
+		callback(dev);
 	}
 
 	device_unlock(dev);
@@ -763,31 +712,29 @@ static pm_message_t resume_event(pm_message_t sleep_state)
  */
 static int device_suspend_noirq(struct device *dev, pm_message_t state)
 {
-	int error;
+	pm_callback_t callback = NULL;
+	char *info = NULL;
 
 	if (dev->pm_domain) {
-		pm_dev_dbg(dev, state, "LATE power domain ");
-		error = pm_noirq_op(dev, &dev->pm_domain->ops, state);
-		if (error)
-			return error;
+		info = "LATE power domain ";
+		callback = pm_noirq_op(&dev->pm_domain->ops, state);
 	} else if (dev->type && dev->type->pm) {
-		pm_dev_dbg(dev, state, "LATE type ");
-		error = pm_noirq_op(dev, dev->type->pm, state);
-		if (error)
-			return error;
+		info = "LATE type ";
+		callback = pm_noirq_op(dev->type->pm, state);
 	} else if (dev->class && dev->class->pm) {
-		pm_dev_dbg(dev, state, "LATE class ");
-		error = pm_noirq_op(dev, dev->class->pm, state);
-		if (error)
-			return error;
+		info = "LATE class ";
+		callback = pm_noirq_op(dev->class->pm, state);
 	} else if (dev->bus && dev->bus->pm) {
-		pm_dev_dbg(dev, state, "LATE ");
-		error = pm_noirq_op(dev, dev->bus->pm, state);
-		if (error)
-			return error;
+		info = "LATE bus ";
+		callback = pm_noirq_op(dev->bus->pm, state);
 	}
 
-	return 0;
+	if (!callback && dev->driver && dev->driver->pm) {
+		info = "LATE driver ";
+		callback = pm_noirq_op(dev->driver->pm, state);
+	}
+
+	return dpm_run_callback(callback, dev, state, info);
 }
 
 /**
@@ -864,6 +811,8 @@ static int legacy_suspend(struct device *dev, pm_message_t state,
  */
 static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 {
+	pm_callback_t callback = NULL;
+	char *info = NULL;
 	int error = 0;
 
 	dpm_wait_for_children(dev, async);
@@ -884,22 +833,22 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 	device_lock(dev);
 
 	if (dev->pm_domain) {
-		pm_dev_dbg(dev, state, "power domain ");
-		error = pm_op(dev, &dev->pm_domain->ops, state);
-		goto End;
+		info = "power domain ";
+		callback = pm_op(&dev->pm_domain->ops, state);
+		goto Run;
 	}
 
 	if (dev->type && dev->type->pm) {
-		pm_dev_dbg(dev, state, "type ");
-		error = pm_op(dev, dev->type->pm, state);
-		goto End;
+		info = "type ";
+		callback = pm_op(dev->type->pm, state);
+		goto Run;
 	}
 
 	if (dev->class) {
 		if (dev->class->pm) {
-			pm_dev_dbg(dev, state, "class ");
-			error = pm_op(dev, dev->class->pm, state);
-			goto End;
+			info = "class ";
+			callback = pm_op(dev->class->pm, state);
+			goto Run;
 		} else if (dev->class->suspend) {
 			pm_dev_dbg(dev, state, "legacy class ");
 			error = legacy_suspend(dev, state, dev->class->suspend);
@@ -909,14 +858,23 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 
 	if (dev->bus) {
 		if (dev->bus->pm) {
-			pm_dev_dbg(dev, state, "");
-			error = pm_op(dev, dev->bus->pm, state);
+			info = "bus ";
+			callback = pm_op(dev->bus->pm, state);
 		} else if (dev->bus->suspend) {
-			pm_dev_dbg(dev, state, "legacy ");
+			pm_dev_dbg(dev, state, "legacy bus ");
 			error = legacy_suspend(dev, state, dev->bus->suspend);
+			goto End;
 		}
 	}
 
+ Run:
+	if (!callback && dev->driver && dev->driver->pm) {
+		info = "driver ";
+		callback = pm_op(dev->driver->pm, state);
+	}
+
+	error = dpm_run_callback(callback, dev, state, info);
+
  End:
 	if (!error) {
 		dev->power.is_suspended = true;
@@ -1022,6 +980,8 @@ int dpm_suspend(pm_message_t state)
  */
 static int device_prepare(struct device *dev, pm_message_t state)
 {
+	int (*callback)(struct device *) = NULL;
+	char *info = NULL;
 	int error = 0;
 
 	device_lock(dev);
@@ -1029,34 +989,29 @@ static int device_prepare(struct device *dev, pm_message_t state)
 	dev->power.wakeup_path = device_may_wakeup(dev);
 
 	if (dev->pm_domain) {
-		pm_dev_dbg(dev, state, "preparing power domain ");
-		if (dev->pm_domain->ops.prepare)
-			error = dev->pm_domain->ops.prepare(dev);
-		suspend_report_result(dev->pm_domain->ops.prepare, error);
-		if (error)
-			goto End;
+		info = "preparing power domain ";
+		callback = dev->pm_domain->ops.prepare;
 	} else if (dev->type && dev->type->pm) {
-		pm_dev_dbg(dev, state, "preparing type ");
-		if (dev->type->pm->prepare)
-			error = dev->type->pm->prepare(dev);
-		suspend_report_result(dev->type->pm->prepare, error);
-		if (error)
-			goto End;
+		info = "preparing type ";
+		callback = dev->type->pm->prepare;
 	} else if (dev->class && dev->class->pm) {
-		pm_dev_dbg(dev, state, "preparing class ");
-		if (dev->class->pm->prepare)
-			error = dev->class->pm->prepare(dev);
-		suspend_report_result(dev->class->pm->prepare, error);
-		if (error)
-			goto End;
+		info = "preparing class ";
+		callback = dev->class->pm->prepare;
 	} else if (dev->bus && dev->bus->pm) {
-		pm_dev_dbg(dev, state, "preparing ");
-		if (dev->bus->pm->prepare)
-			error = dev->bus->pm->prepare(dev);
-		suspend_report_result(dev->bus->pm->prepare, error);
+		info = "preparing bus ";
+		callback = dev->bus->pm->prepare;
+	}
+
+	if (!callback && dev->driver && dev->driver->pm) {
+		info = "preparing driver ";
+		callback = dev->driver->pm->prepare;
+	}
+
+	if (callback) {
+		error = callback(dev);
+		suspend_report_result(callback, error);
 	}
 
- End:
 	device_unlock(dev);
 
 	return error;

drivers/base/power/runtime.c

@@ -250,6 +250,9 @@ static int rpm_idle(struct device *dev, int rpmflags)
 	else
 		callback = NULL;
 
+	if (!callback && dev->driver && dev->driver->pm)
+		callback = dev->driver->pm->runtime_idle;
+
 	if (callback)
 		__rpm_callback(callback, dev);
 
@@ -413,6 +416,9 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 	else
 		callback = NULL;
 
+	if (!callback && dev->driver && dev->driver->pm)
+		callback = dev->driver->pm->runtime_suspend;
+
 	retval = rpm_callback(callback, dev);
 	if (retval) {
 		__update_runtime_status(dev, RPM_ACTIVE);
@@ -633,6 +639,9 @@ static int rpm_resume(struct device *dev, int rpmflags)
 	else
 		callback = NULL;
 
+	if (!callback && dev->driver && dev->driver->pm)
+		callback = dev->driver->pm->runtime_resume;
+
 	retval = rpm_callback(callback, dev);
 	if (retval) {
 		__update_runtime_status(dev, RPM_SUSPENDED);

drivers/bluetooth/btmrvl_main.c

@@ -475,8 +475,6 @@ static int btmrvl_service_main_thread(void *data)
 
 	init_waitqueue_entry(&wait, current);
 
-	current->flags |= PF_NOFREEZE;
-
 	for (;;) {
 		add_wait_queue(&thread->wait_q, &wait);
 

drivers/dma/dmatest.c

@@ -214,9 +214,18 @@ static unsigned int dmatest_verify(u8 **bufs, unsigned int start,
 	return error_count;
 }
 
-static void dmatest_callback(void *completion)
+/* poor man's completion - we want to use wait_event_freezable() on it */
+struct dmatest_done {
+	bool			done;
+	wait_queue_head_t	*wait;
+};
+
+static void dmatest_callback(void *arg)
 {
-	complete(completion);
+	struct dmatest_done *done = arg;
+
+	done->done = true;
+	wake_up_all(done->wait);
 }
 
 /*
@@ -235,7 +244,9 @@ static void dmatest_callback(void *completion)
  */
 static int dmatest_func(void *data)
 {
+	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(done_wait);
 	struct dmatest_thread	*thread = data;
+	struct dmatest_done	done = { .wait = &done_wait };
 	struct dma_chan		*chan;
 	const char		*thread_name;
 	unsigned int		src_off, dst_off, len;
@@ -252,7 +263,7 @@ static int dmatest_func(void *data)
 	int			i;
 
 	thread_name = current->comm;
-	set_freezable_with_signal();
+	set_freezable();
 
 	ret = -ENOMEM;
 
@@ -306,9 +317,6 @@ static int dmatest_func(void *data)
 		struct dma_async_tx_descriptor *tx = NULL;
 		dma_addr_t dma_srcs[src_cnt];
 		dma_addr_t dma_dsts[dst_cnt];
-		struct completion cmp;
-		unsigned long start, tmo, end = 0 /* compiler... */;
-		bool reload = true;
 		u8 align = 0;
 
 		total_tests++;
@@ -391,9 +399,9 @@ static int dmatest_func(void *data)
 			continue;
 		}
 
-		init_completion(&cmp);
+		done.done = false;
 		tx->callback = dmatest_callback;
-		tx->callback_param = &cmp;
+		tx->callback_param = &done;
 		cookie = tx->tx_submit(tx);
 
 		if (dma_submit_error(cookie)) {
@@ -407,20 +415,20 @@ static int dmatest_func(void *data)
 		}
 		dma_async_issue_pending(chan);
 
-		do {
-			start = jiffies;
-			if (reload)
-				end = start + msecs_to_jiffies(timeout);
-			else if (end <= start)
-				end = start + 1;
-			tmo = wait_for_completion_interruptible_timeout(&cmp,
-								end - start);
-			reload = try_to_freeze();
-		} while (tmo == -ERESTARTSYS);
+		wait_event_freezable_timeout(done_wait, done.done,
+					     msecs_to_jiffies(timeout));
 
 		status = dma_async_is_tx_complete(chan, cookie, NULL, NULL);
 
-		if (tmo == 0) {
+		if (!done.done) {
+			/*
+			 * We're leaving the timed out dma operation with
+			 * dangling pointer to done_wait.  To make this
+			 * correct, we'll need to allocate wait_done for
+			 * each test iteration and perform "who's gonna
+			 * free it this time?" dancing.  For now, just
+			 * leave it dangling.
+			 */
 			pr_warning("%s: #%u: test timed out\n",
 				   thread_name, total_tests - 1);
 			failed_tests++;

drivers/mfd/twl6030-irq.c

@@ -138,8 +138,6 @@ static int twl6030_irq_thread(void *data)
 	static const unsigned max_i2c_errors = 100;
 	int ret;
 
-	current->flags |= PF_NOFREEZE;
-
 	while (!kthread_should_stop()) {
 		int i;
 		union {

drivers/net/irda/stir4200.c

@@ -750,7 +750,7 @@ static int stir_transmit_thread(void *arg)
 
 			write_reg(stir, REG_CTRL1, CTRL1_TXPWD|CTRL1_RXPWD);
 
-			refrigerator();
+			try_to_freeze();
 
 			if (change_speed(stir, stir->speed))
 				break;

drivers/platform/x86/thinkpad_acpi.c

@@ -2456,8 +2456,9 @@ static int hotkey_kthread(void *data)
 	u32 poll_mask, event_mask;
 	unsigned int si, so;
 	unsigned long t;
-	unsigned int change_detector, must_reset;
+	unsigned int change_detector;
 	unsigned int poll_freq;
+	bool was_frozen;
 
 	mutex_lock(&hotkey_thread_mutex);
 
@@ -2488,14 +2489,14 @@ static int hotkey_kthread(void *data)
 				t = 100;	/* should never happen... */
 		}
 		t = msleep_interruptible(t);
-		if (unlikely(kthread_should_stop()))
+		if (unlikely(kthread_freezable_should_stop(&was_frozen)))
 			break;
-		must_reset = try_to_freeze();
-		if (t > 0 && !must_reset)
+
+		if (t > 0 && !was_frozen)
 			continue;
 
 		mutex_lock(&hotkey_thread_data_mutex);
-		if (must_reset || hotkey_config_change != change_detector) {
+		if (was_frozen || hotkey_config_change != change_detector) {
 			/* forget old state on thaw or config change */
 			si = so;
 			t = 0;
@@ -2528,10 +2529,6 @@ exit:
 static void hotkey_poll_stop_sync(void)
 {
 	if (tpacpi_hotkey_task) {
-		if (frozen(tpacpi_hotkey_task) ||
-		    freezing(tpacpi_hotkey_task))
-			thaw_process(tpacpi_hotkey_task);
-
 		kthread_stop(tpacpi_hotkey_task);
 		tpacpi_hotkey_task = NULL;
 		mutex_lock(&hotkey_thread_mutex);

drivers/staging/rts_pstor/rtsx.c

@@ -466,8 +466,6 @@ static int rtsx_control_thread(void *__dev)
 	struct rtsx_chip *chip = dev->chip;
 	struct Scsi_Host *host = rtsx_to_host(dev);
 
-	current->flags |= PF_NOFREEZE;
-
 	for (;;) {
 		if (wait_for_completion_interruptible(&dev->cmnd_ready))
 			break;

drivers/usb/storage/usb.c

@@ -831,7 +831,8 @@ static int usb_stor_scan_thread(void * __us)
 
 	dev_dbg(dev, "device found\n");
 
-	set_freezable_with_signal();
+	set_freezable();
+
 	/*
 	 * Wait for the timeout to expire or for a disconnect
 	 *
@@ -839,16 +840,16 @@ static int usb_stor_scan_thread(void * __us)
 	 * fail to freeze, but we can't be non-freezable either. Nor can
 	 * khubd freeze while waiting for scanning to complete as it may
 	 * hold the device lock, causing a hang when suspending devices.
-	 * So we request a fake signal when freezing and use
-	 * interruptible sleep to kick us out of our wait early when
-	 * freezing happens.
+	 * So instead of using wait_event_freezable(), explicitly test
+	 * for (DONT_SCAN || freezing) in interruptible wait and proceed
+	 * if any of DONT_SCAN, freezing or timeout has happened.
 	 */
 	if (delay_use > 0) {
 		dev_dbg(dev, "waiting for device to settle "
 				"before scanning\n");
 		wait_event_interruptible_timeout(us->delay_wait,
-				test_bit(US_FLIDX_DONT_SCAN, &us->dflags),
-				delay_use * HZ);
+				test_bit(US_FLIDX_DONT_SCAN, &us->dflags) ||
+				freezing(current), delay_use * HZ);
 	}
 
 	/* If the device is still connected, perform the scanning */

fs/btrfs/async-thread.c

@@ -334,7 +334,7 @@ again:
 		if (freezing(current)) {
 			worker->working = 0;
 			spin_unlock_irq(&worker->lock);
-			refrigerator();
+			try_to_freeze();
 		} else {
 			spin_unlock_irq(&worker->lock);
 			if (!kthread_should_stop()) {

fs/btrfs/disk-io.c

@@ -1579,9 +1579,7 @@ static int cleaner_kthread(void *arg)
 			btrfs_run_defrag_inodes(root->fs_info);
 		}
 
-		if (freezing(current)) {
-			refrigerator();
-		} else {
+		if (!try_to_freeze()) {
 			set_current_state(TASK_INTERRUPTIBLE);
 			if (!kthread_should_stop())
 				schedule();
@@ -1635,9 +1633,7 @@ sleep:
 		wake_up_process(root->fs_info->cleaner_kthread);
 		mutex_unlock(&root->fs_info->transaction_kthread_mutex);
 
-		if (freezing(current)) {
-			refrigerator();
-		} else {
+		if (!try_to_freeze()) {
 			set_current_state(TASK_INTERRUPTIBLE);
 			if (!kthread_should_stop() &&
 			    !btrfs_transaction_blocked(root->fs_info))

fs/ext4/super.c

@@ -2883,8 +2883,7 @@ cont_thread:
 		}
 		mutex_unlock(&eli->li_list_mtx);
 
-		if (freezing(current))
-			refrigerator();
+		try_to_freeze();
 
 		cur = jiffies;
 		if ((time_after_eq(cur, next_wakeup)) ||

fs/fs-writeback.c

@@ -937,7 +937,7 @@ int bdi_writeback_thread(void *data)
 
 	trace_writeback_thread_start(bdi);
 
-	while (!kthread_should_stop()) {
+	while (!kthread_freezable_should_stop(NULL)) {
 		/*
 		 * Remove own delayed wake-up timer, since we are already awake
 		 * and we'll take care of the preriodic write-back.
@@ -967,8 +967,6 @@ int bdi_writeback_thread(void *data)
 			 */
 			schedule();
 		}
-
-		try_to_freeze();
 	}
 
 	/* Flush any work that raced with us exiting */

fs/gfs2/log.c

@@ -951,8 +951,8 @@ int gfs2_logd(void *data)
 			wake_up(&sdp->sd_log_waitq);
 
 		t = gfs2_tune_get(sdp, gt_logd_secs) * HZ;
-		if (freezing(current))
-			refrigerator();
+
+		try_to_freeze();
 
 		do {
 			prepare_to_wait(&sdp->sd_logd_waitq, &wait,

fs/gfs2/quota.c

@@ -1427,8 +1427,8 @@ int gfs2_quotad(void *data)
 		/* Check for & recover partially truncated inodes */
 		quotad_check_trunc_list(sdp);
 
-		if (freezing(current))
-			refrigerator();
+		try_to_freeze();
+
 		t = min(quotad_timeo, statfs_timeo);
 
 		prepare_to_wait(&sdp->sd_quota_wait, &wait, TASK_INTERRUPTIBLE);

fs/jbd/journal.c

@@ -166,7 +166,7 @@ loop:
 		 */
 		jbd_debug(1, "Now suspending kjournald\n");
 		spin_unlock(&journal->j_state_lock);
-		refrigerator();
+		try_to_freeze();
 		spin_lock(&journal->j_state_lock);
 	} else {
 		/*

fs/jbd2/journal.c

@@ -173,7 +173,7 @@ loop:
 		 */
 		jbd_debug(1, "Now suspending kjournald2\n");
 		write_unlock(&journal->j_state_lock);
-		refrigerator();
+		try_to_freeze();
 		write_lock(&journal->j_state_lock);
 	} else {
 		/*

fs/jfs/jfs_logmgr.c

@@ -2349,7 +2349,7 @@ int jfsIOWait(void *arg)
 
 		if (freezing(current)) {
 			spin_unlock_irq(&log_redrive_lock);
-			refrigerator();
+			try_to_freeze();
 		} else {
 			set_current_state(TASK_INTERRUPTIBLE);
 			spin_unlock_irq(&log_redrive_lock);

fs/jfs/jfs_txnmgr.c

@@ -2800,7 +2800,7 @@ int jfs_lazycommit(void *arg)
 
 		if (freezing(current)) {
 			LAZY_UNLOCK(flags);
-			refrigerator();
+			try_to_freeze();
 		} else {
 			DECLARE_WAITQUEUE(wq, current);
 
@@ -2994,7 +2994,7 @@ int jfs_sync(void *arg)
 
 		if (freezing(current)) {
 			TXN_UNLOCK();
-			refrigerator();
+			try_to_freeze();
 		} else {
 			set_current_state(TASK_INTERRUPTIBLE);
 			TXN_UNLOCK();

fs/nfs/inode.c

@@ -38,6 +38,7 @@
 #include <linux/nfs_xdr.h>
 #include <linux/slab.h>
 #include <linux/compat.h>
+#include <linux/freezer.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -77,7 +78,7 @@ int nfs_wait_bit_killable(void *word)
 {
 	if (fatal_signal_pending(current))
 		return -ERESTARTSYS;
-	schedule();
+	freezable_schedule();
 	return 0;
 }
 

fs/nfs/nfs3proc.c

@@ -17,6 +17,7 @@
 #include <linux/nfs_page.h>
 #include <linux/lockd/bind.h>
 #include <linux/nfs_mount.h>
+#include <linux/freezer.h>
 
 #include "iostat.h"
 #include "internal.h"
@@ -32,7 +33,7 @@ nfs3_rpc_wrapper(struct rpc_clnt *clnt, struct rpc_message *msg, int flags)
 		res = rpc_call_sync(clnt, msg, flags);
 		if (res != -EJUKEBOX && res != -EKEYEXPIRED)
 			break;
-		schedule_timeout_killable(NFS_JUKEBOX_RETRY_TIME);
+		freezable_schedule_timeout_killable(NFS_JUKEBOX_RETRY_TIME);
 		res = -ERESTARTSYS;
 	} while (!fatal_signal_pending(current));
 	return res;

fs/nfs/nfs4proc.c

@@ -55,6 +55,7 @@
 #include <linux/sunrpc/bc_xprt.h>
 #include <linux/xattr.h>
 #include <linux/utsname.h>
+#include <linux/freezer.h>
 
 #include "nfs4_fs.h"
 #include "delegation.h"
@@ -243,7 +244,7 @@ static int nfs4_delay(struct rpc_clnt *clnt, long *timeout)
 		*timeout = NFS4_POLL_RETRY_MIN;
 	if (*timeout > NFS4_POLL_RETRY_MAX)
 		*timeout = NFS4_POLL_RETRY_MAX;
-	schedule_timeout_killable(*timeout);
+	freezable_schedule_timeout_killable(*timeout);
 	if (fatal_signal_pending(current))
 		res = -ERESTARTSYS;
 	*timeout <<= 1;
@@ -3958,7 +3959,7 @@ int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4
 static unsigned long
 nfs4_set_lock_task_retry(unsigned long timeout)
 {
-	schedule_timeout_killable(timeout);
+	freezable_schedule_timeout_killable(timeout);
 	timeout <<= 1;
 	if (timeout > NFS4_LOCK_MAXTIMEOUT)
 		return NFS4_LOCK_MAXTIMEOUT;

fs/nfs/proc.c

@@ -41,6 +41,7 @@
 #include <linux/nfs_fs.h>
 #include <linux/nfs_page.h>
 #include <linux/lockd/bind.h>
+#include <linux/freezer.h>
 #include "internal.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PROC
@@ -59,7 +60,7 @@ nfs_rpc_wrapper(struct rpc_clnt *clnt, struct rpc_message *msg, int flags)
 		res = rpc_call_sync(clnt, msg, flags);
 		if (res != -EKEYEXPIRED)
 			break;
-		schedule_timeout_killable(NFS_JUKEBOX_RETRY_TIME);
+		freezable_schedule_timeout_killable(NFS_JUKEBOX_RETRY_TIME);
 		res = -ERESTARTSYS;
 	} while (!fatal_signal_pending(current));
 	return res;

fs/nilfs2/segment.c

@@ -2470,7 +2470,7 @@ static int nilfs_segctor_thread(void *arg)
 
 	if (freezing(current)) {
 		spin_unlock(&sci->sc_state_lock);
-		refrigerator();
+		try_to_freeze();
 		spin_lock(&sci->sc_state_lock);
 	} else {
 		DEFINE_WAIT(wait);

fs/xfs/xfs_buf.c

@@ -1703,7 +1703,7 @@ xfsbufd(
 
 		if (unlikely(freezing(current))) {
 			set_bit(XBT_FORCE_SLEEP, &target->bt_flags);
-			refrigerator();
+			try_to_freeze();
 		} else {
 			clear_bit(XBT_FORCE_SLEEP, &target->bt_flags);
 		}

include/linux/freezer.h

@@ -5,71 +5,58 @@
 
 #include <linux/sched.h>
 #include <linux/wait.h>
+#include <linux/atomic.h>
 
 #ifdef CONFIG_FREEZER
+extern atomic_t system_freezing_cnt;	/* nr of freezing conds in effect */
+extern bool pm_freezing;		/* PM freezing in effect */
+extern bool pm_nosig_freezing;		/* PM nosig freezing in effect */
+
 /*
  * Check if a process has been frozen
  */
-static inline int frozen(struct task_struct *p)
+static inline bool frozen(struct task_struct *p)
 {
 	return p->flags & PF_FROZEN;
 }
 
-/*
- * Check if there is a request to freeze a process
- */
-static inline int freezing(struct task_struct *p)
-{
-	return test_tsk_thread_flag(p, TIF_FREEZE);
-}
+extern bool freezing_slow_path(struct task_struct *p);
 
 /*
- * Request that a process be frozen
- */
-static inline void set_freeze_flag(struct task_struct *p)
-{
-	set_tsk_thread_flag(p, TIF_FREEZE);
-}
-
-/*
- * Sometimes we may need to cancel the previous 'freeze' request
+ * Check if there is a request to freeze a process
  */
-static inline void clear_freeze_flag(struct task_struct *p)
-{
-	clear_tsk_thread_flag(p, TIF_FREEZE);
-}
-
-static inline bool should_send_signal(struct task_struct *p)
+static inline bool freezing(struct task_struct *p)
 {
-	return !(p->flags & PF_FREEZER_NOSIG);
+	if (likely(!atomic_read(&system_freezing_cnt)))
+		return false;
+	return freezing_slow_path(p);
 }
 
 /* Takes and releases task alloc lock using task_lock() */
-extern int thaw_process(struct task_struct *p);
+extern void __thaw_task(struct task_struct *t);
 
-extern void refrigerator(void);
+extern bool __refrigerator(bool check_kthr_stop);
 extern int freeze_processes(void);
 extern int freeze_kernel_threads(void);
 extern void thaw_processes(void);
 
-static inline int try_to_freeze(void)
+static inline bool try_to_freeze(void)
 {
-	if (freezing(current)) {
-		refrigerator();
-		return 1;
-	} else
-		return 0;
+	might_sleep();
+	if (likely(!freezing(current)))
+		return false;
+	return __refrigerator(false);
 }
 
-extern bool freeze_task(struct task_struct *p, bool sig_only);
-extern void cancel_freezing(struct task_struct *p);
+extern bool freeze_task(struct task_struct *p);
+extern bool set_freezable(void);
 
 #ifdef CONFIG_CGROUP_FREEZER
-extern int cgroup_freezing_or_frozen(struct task_struct *task);
+extern bool cgroup_freezing(struct task_struct *task);
 #else /* !CONFIG_CGROUP_FREEZER */
-static inline int cgroup_freezing_or_frozen(struct task_struct *task)
+static inline bool cgroup_freezing(struct task_struct *task)
 {
-	return 0;
+	return false;
 }
 #endif /* !CONFIG_CGROUP_FREEZER */
 
@@ -80,33 +67,27 @@ static inline int cgroup_freezing_or_frozen(struct task_struct *task)
  * appropriately in case the child has exited before the freezing of tasks is
  * complete.  However, we don't want kernel threads to be frozen in unexpected
  * places, so we allow them to block freeze_processes() instead or to set
- * PF_NOFREEZE if needed and PF_FREEZER_SKIP is only set for userland vfork
- * parents.  Fortunately, in the ____call_usermodehelper() case the parent won't
- * really block freeze_processes(), since ____call_usermodehelper() (the child)
- * does a little before exec/exit and it can't be frozen before waking up the
- * parent.
+ * PF_NOFREEZE if needed. Fortunately, in the ____call_usermodehelper() case the
+ * parent won't really block freeze_processes(), since ____call_usermodehelper()
+ * (the child) does a little before exec/exit and it can't be frozen before
+ * waking up the parent.
  */
 
-/*
- * If the current task is a user space one, tell the freezer not to count it as
- * freezable.
- */
+
+/* Tell the freezer not to count the current task as freezable. */
 static inline void freezer_do_not_count(void)
 {
-	if (current->mm)
-		current->flags |= PF_FREEZER_SKIP;
+	current->flags |= PF_FREEZER_SKIP;
 }
 
 /*
- * If the current task is a user space one, tell the freezer to count it as
- * freezable again and try to freeze it.
+ * Tell the freezer to count the current task as freezable again and try to
+ * freeze it.
  */
 static inline void freezer_count(void)
 {
-	if (current->mm) {
-		current->flags &= ~PF_FREEZER_SKIP;
-		try_to_freeze();
-	}
+	current->flags &= ~PF_FREEZER_SKIP;
+	try_to_freeze();
 }
 
 /*
@@ -118,21 +99,27 @@ static inline int freezer_should_skip(struct task_struct *p)
 }
 
 /*
- * Tell the freezer that the current task should be frozen by it
+ * These macros are intended to be used whenever you want allow a task that's
+ * sleeping in TASK_UNINTERRUPTIBLE or TASK_KILLABLE state to be frozen. Note
+ * that neither return any clear indication of whether a freeze event happened
+ * while in this function.
  */
-static inline void set_freezable(void)
-{
-	current->flags &= ~PF_NOFREEZE;
-}
 
-/*
- * Tell the freezer that the current task should be frozen by it and that it
- * should send a fake signal to the task to freeze it.
- */
-static inline void set_freezable_with_signal(void)
-{
-	current->flags &= ~(PF_NOFREEZE | PF_FREEZER_NOSIG);
-}
+/* Like schedule(), but should not block the freezer. */
+#define freezable_schedule()						\
+({									\
+	freezer_do_not_count();						\
+	schedule();							\
+	freezer_count();						\
+})
+
+/* Like schedule_timeout_killable(), but should not block the freezer. */
+#define freezable_schedule_timeout_killable(timeout)			\
+({									\
+	freezer_do_not_count();						\
+	schedule_timeout_killable(timeout);				\
+	freezer_count();						\
+})
 
 /*
  * Freezer-friendly wrappers around wait_event_interruptible(),
@@ -152,47 +139,51 @@ static inline void set_freezable_with_signal(void)
 #define wait_event_freezable(wq, condition)				\
 ({									\
 	int __retval;							\
-	do {								\
+	for (;;) {							\
 		__retval = wait_event_interruptible(wq, 		\
 				(condition) || freezing(current));	\
-		if (__retval && !freezing(current))			\
+		if (__retval || (condition))				\
 			break;						\
-		else if (!(condition))					\
-			__retval = -ERESTARTSYS;			\
-	} while (try_to_freeze());					\
+		try_to_freeze();					\
+	}								\
 	__retval;							\
 })
 
-
 #define wait_event_freezable_timeout(wq, condition, timeout)		\
 ({									\
 	long __retval = timeout;					\
-	do {								\
+	for (;;) {							\
 		__retval = wait_event_interruptible_timeout(wq,		\
 				(condition) || freezing(current),	\
 				__retval); 				\
-	} while (try_to_freeze());					\
+		if (__retval <= 0 || (condition))			\
+			break;						\
+		try_to_freeze();					\
+	}								\
 	__retval;							\
 })
+
 #else /* !CONFIG_FREEZER */
-static inline int frozen(struct task_struct *p) { return 0; }
-static inline int freezing(struct task_struct *p) { return 0; }
-static inline void set_freeze_flag(struct task_struct *p) {}
-static inline void clear_freeze_flag(struct task_struct *p) {}
-static inline int thaw_process(struct task_struct *p) { return 1; }
+static inline bool frozen(struct task_struct *p) { return false; }
+static inline bool freezing(struct task_struct *p) { return false; }
+static inline void __thaw_task(struct task_struct *t) {}
 
-static inline void refrigerator(void) {}
+static inline bool __refrigerator(bool check_kthr_stop) { return false; }
 static inline int freeze_processes(void) { return -ENOSYS; }
 static inline int freeze_kernel_threads(void) { return -ENOSYS; }
 static inline void thaw_processes(void) {}
 
-static inline int try_to_freeze(void) { return 0; }
+static inline bool try_to_freeze(void) { return false; }
 
 static inline void freezer_do_not_count(void) {}
 static inline void freezer_count(void) {}
 static inline int freezer_should_skip(struct task_struct *p) { return 0; }
 static inline void set_freezable(void) {}
-static inline void set_freezable_with_signal(void) {}
+
+#define freezable_schedule()  schedule()
+
+#define freezable_schedule_timeout_killable(timeout)			\
+	schedule_timeout_killable(timeout)
 
 #define wait_event_freezable(wq, condition)				\
 		wait_event_interruptible(wq, condition)

include/linux/kmod.h

@@ -117,5 +117,7 @@ extern void usermodehelper_init(void);
 extern int usermodehelper_disable(void);
 extern void usermodehelper_enable(void);
 extern bool usermodehelper_is_disabled(void);
+extern void read_lock_usermodehelper(void);
+extern void read_unlock_usermodehelper(void);
 
 #endif /* __LINUX_KMOD_H__ */

include/linux/kthread.h

@@ -35,6 +35,7 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
 void kthread_bind(struct task_struct *k, unsigned int cpu);
 int kthread_stop(struct task_struct *k);
 int kthread_should_stop(void);
+bool kthread_freezable_should_stop(bool *was_frozen);
 void *kthread_data(struct task_struct *k);
 
 int kthreadd(void *unused);

include/linux/platform_device.h

@@ -264,62 +264,34 @@ static inline char *early_platform_driver_setup_func(void)		\
 }
 #endif /* MODULE */
 
-#ifdef CONFIG_PM_SLEEP
-extern int platform_pm_prepare(struct device *dev);
-extern void platform_pm_complete(struct device *dev);
-#else
-#define platform_pm_prepare	NULL
-#define platform_pm_complete	NULL
-#endif
-
 #ifdef CONFIG_SUSPEND
 extern int platform_pm_suspend(struct device *dev);
-extern int platform_pm_suspend_noirq(struct device *dev);
 extern int platform_pm_resume(struct device *dev);
-extern int platform_pm_resume_noirq(struct device *dev);
 #else
 #define platform_pm_suspend		NULL
 #define platform_pm_resume		NULL
-#define platform_pm_suspend_noirq	NULL
-#define platform_pm_resume_noirq	NULL
 #endif
 
 #ifdef CONFIG_HIBERNATE_CALLBACKS
 extern int platform_pm_freeze(struct device *dev);
-extern int platform_pm_freeze_noirq(struct device *dev);
 extern int platform_pm_thaw(struct device *dev);
-extern int platform_pm_thaw_noirq(struct device *dev);
 extern int platform_pm_poweroff(struct device *dev);
-extern int platform_pm_poweroff_noirq(struct device *dev);
 extern int platform_pm_restore(struct device *dev);
-extern int platform_pm_restore_noirq(struct device *dev);
 #else
 #define platform_pm_freeze		NULL
 #define platform_pm_thaw		NULL
 #define platform_pm_poweroff		NULL
 #define platform_pm_restore		NULL
-#define platform_pm_freeze_noirq	NULL
-#define platform_pm_thaw_noirq		NULL
-#define platform_pm_poweroff_noirq	NULL
-#define platform_pm_restore_noirq	NULL
 #endif
 
 #ifdef CONFIG_PM_SLEEP
 #define USE_PLATFORM_PM_SLEEP_OPS \
-	.prepare = platform_pm_prepare, \
-	.complete = platform_pm_complete, \
 	.suspend = platform_pm_suspend, \
 	.resume = platform_pm_resume, \
 	.freeze = platform_pm_freeze, \
 	.thaw = platform_pm_thaw, \
 	.poweroff = platform_pm_poweroff, \
-	.restore = platform_pm_restore, \
-	.suspend_noirq = platform_pm_suspend_noirq, \
-	.resume_noirq = platform_pm_resume_noirq, \
-	.freeze_noirq = platform_pm_freeze_noirq, \
-	.thaw_noirq = platform_pm_thaw_noirq, \
-	.poweroff_noirq = platform_pm_poweroff_noirq, \
-	.restore_noirq = platform_pm_restore_noirq,
+	.restore = platform_pm_restore,
 #else
 #define USE_PLATFORM_PM_SLEEP_OPS
 #endif

include/linux/pm.h

@@ -300,19 +300,6 @@ const struct dev_pm_ops name = { \
 	SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \
 }
 
-/*
- * Use this for subsystems (bus types, device types, device classes) that don't
- * need any special suspend/resume handling in addition to invoking the PM
- * callbacks provided by device drivers supporting both the system sleep PM and
- * runtime PM, make the pm member point to generic_subsys_pm_ops.
- */
-#ifdef CONFIG_PM
-extern struct dev_pm_ops generic_subsys_pm_ops;
-#define GENERIC_SUBSYS_PM_OPS	(&generic_subsys_pm_ops)
-#else
-#define GENERIC_SUBSYS_PM_OPS	NULL
-#endif
-
 /**
  * PM_EVENT_ messages
  *

include/linux/sched.h

@@ -220,7 +220,7 @@ extern char ___assert_task_state[1 - 2*!!(
 			((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
 #define task_contributes_to_load(task)	\
 				((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
-				 (task->flags & PF_FREEZING) == 0)
+				 (task->flags & PF_FROZEN) == 0)
 
 #define __set_task_state(tsk, state_value)		\
 	do { (tsk)->state = (state_value); } while (0)
@@ -1772,7 +1772,6 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 #define PF_MEMALLOC	0x00000800	/* Allocating memory */
 #define PF_NPROC_EXCEEDED 0x00001000	/* set_user noticed that RLIMIT_NPROC was exceeded */
 #define PF_USED_MATH	0x00002000	/* if unset the fpu must be initialized before use */
-#define PF_FREEZING	0x00004000	/* freeze in progress. do not account to load */
 #define PF_NOFREEZE	0x00008000	/* this thread should not be frozen */
 #define PF_FROZEN	0x00010000	/* frozen for system suspend */
 #define PF_FSTRANS	0x00020000	/* inside a filesystem transaction */
@@ -1788,7 +1787,6 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 #define PF_MEMPOLICY	0x10000000	/* Non-default NUMA mempolicy */
 #define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */
 #define PF_FREEZER_SKIP	0x40000000	/* Freezer should not count it as freezable */
-#define PF_FREEZER_NOSIG 0x80000000	/* Freezer won't send signals to it */
 
 /*
  * Only the _current_ task can read/write to tsk->flags, but other

include/linux/suspend.h

@@ -6,6 +6,7 @@
 #include <linux/init.h>
 #include <linux/pm.h>
 #include <linux/mm.h>
+#include <linux/freezer.h>
 #include <asm/errno.h>
 
 #ifdef CONFIG_VT
@@ -331,6 +332,8 @@ static inline bool system_entering_hibernation(void) { return false; }
 #define PM_RESTORE_PREPARE	0x0005 /* Going to restore a saved image */
 #define PM_POST_RESTORE		0x0006 /* Restore failed */
 
+extern struct mutex pm_mutex;
+
 #ifdef CONFIG_PM_SLEEP
 void save_processor_state(void);
 void restore_processor_state(void);
@@ -351,6 +354,19 @@ extern bool events_check_enabled;
 extern bool pm_wakeup_pending(void);
 extern bool pm_get_wakeup_count(unsigned int *count);
 extern bool pm_save_wakeup_count(unsigned int count);
+
+static inline void lock_system_sleep(void)
+{
+	freezer_do_not_count();
+	mutex_lock(&pm_mutex);
+}
+
+static inline void unlock_system_sleep(void)
+{
+	mutex_unlock(&pm_mutex);
+	freezer_count();
+}
+
 #else /* !CONFIG_PM_SLEEP */
 
 static inline int register_pm_notifier(struct notifier_block *nb)
@@ -366,28 +382,11 @@ static inline int unregister_pm_notifier(struct notifier_block *nb)
 #define pm_notifier(fn, pri)	do { (void)(fn); } while (0)
 
 static inline bool pm_wakeup_pending(void) { return false; }
-#endif /* !CONFIG_PM_SLEEP */
-
-extern struct mutex pm_mutex;
 
-#ifndef CONFIG_HIBERNATE_CALLBACKS
 static inline void lock_system_sleep(void) {}
 static inline void unlock_system_sleep(void) {}
 
-#else
-
-/* Let some subsystems like memory hotadd exclude hibernation */
-
-static inline void lock_system_sleep(void)
-{
-	mutex_lock(&pm_mutex);
-}
-
-static inline void unlock_system_sleep(void)
-{
-	mutex_unlock(&pm_mutex);
-}
-#endif
+#endif /* !CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_ARCH_SAVE_PAGE_KEYS
 /*

kernel/cgroup_freezer.c

@@ -48,19 +48,17 @@ static inline struct freezer *task_freezer(struct task_struct *task)
 			    struct freezer, css);
 }
 
-static inline int __cgroup_freezing_or_frozen(struct task_struct *task)
+bool cgroup_freezing(struct task_struct *task)
 {
-	enum freezer_state state = task_freezer(task)->state;
-	return (state == CGROUP_FREEZING) || (state == CGROUP_FROZEN);
-}
+	enum freezer_state state;
+	bool ret;
 
-int cgroup_freezing_or_frozen(struct task_struct *task)
-{
-	int result;
-	task_lock(task);
-	result = __cgroup_freezing_or_frozen(task);
-	task_unlock(task);
-	return result;
+	rcu_read_lock();
+	state = task_freezer(task)->state;
+	ret = state == CGROUP_FREEZING || state == CGROUP_FROZEN;
+	rcu_read_unlock();
+
+	return ret;
 }
 
 /*
@@ -102,9 +100,6 @@ struct cgroup_subsys freezer_subsys;
  * freezer_can_attach():
  * cgroup_mutex (held by caller of can_attach)
  *
- * cgroup_freezing_or_frozen():
- * task->alloc_lock (to get task's cgroup)
- *
  * freezer_fork() (preserving fork() performance means can't take cgroup_mutex):
  * freezer->lock
  *  sighand->siglock (if the cgroup is freezing)
@@ -130,7 +125,7 @@ struct cgroup_subsys freezer_subsys;
  *   write_lock css_set_lock (cgroup iterator start)
  *    task->alloc_lock
  *   read_lock css_set_lock (cgroup iterator start)
- *    task->alloc_lock (inside thaw_process(), prevents race with refrigerator())
+ *    task->alloc_lock (inside __thaw_task(), prevents race with refrigerator())
  *     sighand->siglock
  */
 static struct cgroup_subsys_state *freezer_create(struct cgroup_subsys *ss,
@@ -150,7 +145,11 @@ static struct cgroup_subsys_state *freezer_create(struct cgroup_subsys *ss,
 static void freezer_destroy(struct cgroup_subsys *ss,
 			    struct cgroup *cgroup)
 {
-	kfree(cgroup_freezer(cgroup));
+	struct freezer *freezer = cgroup_freezer(cgroup);
+
+	if (freezer->state != CGROUP_THAWED)
+		atomic_dec(&system_freezing_cnt);
+	kfree(freezer);
 }
 
 /* task is frozen or will freeze immediately when next it gets woken */
@@ -184,13 +183,7 @@ static int freezer_can_attach(struct cgroup_subsys *ss,
 
 static int freezer_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 {
-	rcu_read_lock();
-	if (__cgroup_freezing_or_frozen(tsk)) {
-		rcu_read_unlock();
-		return -EBUSY;
-	}
-	rcu_read_unlock();
-	return 0;
+	return cgroup_freezing(tsk) ? -EBUSY : 0;
 }
 
 static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task)
@@ -220,7 +213,7 @@ static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task)
 
 	/* Locking avoids race with FREEZING -> THAWED transitions. */
 	if (freezer->state == CGROUP_FREEZING)
-		freeze_task(task, true);
+		freeze_task(task);
 	spin_unlock_irq(&freezer->lock);
 }
 
@@ -238,7 +231,7 @@ static void update_if_frozen(struct cgroup *cgroup,
 	cgroup_iter_start(cgroup, &it);
 	while ((task = cgroup_iter_next(cgroup, &it))) {
 		ntotal++;
-		if (is_task_frozen_enough(task))
+		if (freezing(task) && is_task_frozen_enough(task))
 			nfrozen++;
 	}
 
@@ -286,10 +279,9 @@ static int try_to_freeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
 	struct task_struct *task;
 	unsigned int num_cant_freeze_now = 0;
 
-	freezer->state = CGROUP_FREEZING;
 	cgroup_iter_start(cgroup, &it);
 	while ((task = cgroup_iter_next(cgroup, &it))) {
-		if (!freeze_task(task, true))
+		if (!freeze_task(task))
 			continue;
 		if (is_task_frozen_enough(task))
 			continue;
@@ -307,12 +299,9 @@ static void unfreeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
 	struct task_struct *task;
 
 	cgroup_iter_start(cgroup, &it);
-	while ((task = cgroup_iter_next(cgroup, &it))) {
-		thaw_process(task);
-	}
+	while ((task = cgroup_iter_next(cgroup, &it)))
+		__thaw_task(task);
 	cgroup_iter_end(cgroup, &it);
-
-	freezer->state = CGROUP_THAWED;
 }
 
 static int freezer_change_state(struct cgroup *cgroup,
@@ -326,20 +315,24 @@ static int freezer_change_state(struct cgroup *cgroup,
 	spin_lock_irq(&freezer->lock);
 
 	update_if_frozen(cgroup, freezer);
-	if (goal_state == freezer->state)
-		goto out;
 
 	switch (goal_state) {
 	case CGROUP_THAWED:
+		if (freezer->state != CGROUP_THAWED)
+			atomic_dec(&system_freezing_cnt);
+		freezer->state = CGROUP_THAWED;
 		unfreeze_cgroup(cgroup, freezer);
 		break;
 	case CGROUP_FROZEN:
+		if (freezer->state == CGROUP_THAWED)
+			atomic_inc(&system_freezing_cnt);
+		freezer->state = CGROUP_FREEZING;
 		retval = try_to_freeze_cgroup(cgroup, freezer);
 		break;
 	default:
 		BUG();
 	}
-out:
+
 	spin_unlock_irq(&freezer->lock);
 
 	return retval;

kernel/exit.c

@@ -679,8 +679,6 @@ static void exit_mm(struct task_struct * tsk)
 	tsk->mm = NULL;
 	up_read(&mm->mmap_sem);
 	enter_lazy_tlb(mm, current);
-	/* We don't want this task to be frozen prematurely */
-	clear_freeze_flag(tsk);
 	task_unlock(tsk);
 	mm_update_next_owner(mm);
 	mmput(mm);
@@ -1040,6 +1038,7 @@ NORET_TYPE void do_exit(long code)
 	exit_rcu();
 	/* causes final put_task_struct in finish_task_switch(). */
 	tsk->state = TASK_DEAD;
+	tsk->flags |= PF_NOFREEZE;	/* tell freezer to ignore us */
 	schedule();
 	BUG();
 	/* Avoid "noreturn function does return".  */

kernel/fork.c

@@ -992,7 +992,6 @@ static void copy_flags(unsigned long clone_flags, struct task_struct *p)
 	new_flags |= PF_FORKNOEXEC;
 	new_flags |= PF_STARTING;
 	p->flags = new_flags;
-	clear_freeze_flag(p);
 }
 
 SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr)

kernel/freezer.c

@@ -9,101 +9,114 @@
 #include <linux/export.h>
 #include <linux/syscalls.h>
 #include <linux/freezer.h>
+#include <linux/kthread.h>
 
-/*
- * freezing is complete, mark current process as frozen
+/* total number of freezing conditions in effect */
+atomic_t system_freezing_cnt = ATOMIC_INIT(0);
+EXPORT_SYMBOL(system_freezing_cnt);
+
+/* indicate whether PM freezing is in effect, protected by pm_mutex */
+bool pm_freezing;
+bool pm_nosig_freezing;
+
+/* protects freezing and frozen transitions */
+static DEFINE_SPINLOCK(freezer_lock);
+
+/**
+ * freezing_slow_path - slow path for testing whether a task needs to be frozen
+ * @p: task to be tested
+ *
+ * This function is called by freezing() if system_freezing_cnt isn't zero
+ * and tests whether @p needs to enter and stay in frozen state.  Can be
+ * called under any context.  The freezers are responsible for ensuring the
+ * target tasks see the updated state.
  */
-static inline void frozen_process(void)
+bool freezing_slow_path(struct task_struct *p)
 {
-	if (!unlikely(current->flags & PF_NOFREEZE)) {
-		current->flags |= PF_FROZEN;
-		smp_wmb();
-	}
-	clear_freeze_flag(current);
+	if (p->flags & PF_NOFREEZE)
+		return false;
+
+	if (pm_nosig_freezing || cgroup_freezing(p))
+		return true;
+
+	if (pm_freezing && !(p->flags & PF_KTHREAD))
+		return true;
+
+	return false;
 }
+EXPORT_SYMBOL(freezing_slow_path);
 
 /* Refrigerator is place where frozen processes are stored :-). */
-void refrigerator(void)
+bool __refrigerator(bool check_kthr_stop)
 {
 	/* Hmm, should we be allowed to suspend when there are realtime
 	   processes around? */
-	long save;
+	bool was_frozen = false;
+	long save = current->state;
 
-	task_lock(current);
-	if (freezing(current)) {
-		frozen_process();
-		task_unlock(current);
-	} else {
-		task_unlock(current);
-		return;
-	}
-	save = current->state;
 	pr_debug("%s entered refrigerator\n", current->comm);
 
-	spin_lock_irq(&current->sighand->siglock);
-	recalc_sigpending(); /* We sent fake signal, clean it up */
-	spin_unlock_irq(&current->sighand->siglock);
-
-	/* prevent accounting of that task to load */
-	current->flags |= PF_FREEZING;
-
 	for (;;) {
 		set_current_state(TASK_UNINTERRUPTIBLE);
-		if (!frozen(current))
+
+		spin_lock_irq(&freezer_lock);
+		current->flags |= PF_FROZEN;
+		if (!freezing(current) ||
+		    (check_kthr_stop && kthread_should_stop()))
+			current->flags &= ~PF_FROZEN;
+		spin_unlock_irq(&freezer_lock);
+
+		if (!(current->flags & PF_FROZEN))
 			break;
+		was_frozen = true;
 		schedule();
 	}
 
-	/* Remove the accounting blocker */
-	current->flags &= ~PF_FREEZING;
-
 	pr_debug("%s left refrigerator\n", current->comm);
-	__set_current_state(save);
+
+	/*
+	 * Restore saved task state before returning.  The mb'd version
+	 * needs to be used; otherwise, it might silently break
+	 * synchronization which depends on ordered task state change.
+	 */
+	set_current_state(save);
+
+	return was_frozen;
 }
-EXPORT_SYMBOL(refrigerator);
+EXPORT_SYMBOL(__refrigerator);
 
 static void fake_signal_wake_up(struct task_struct *p)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&p->sighand->siglock, flags);
-	signal_wake_up(p, 0);
-	spin_unlock_irqrestore(&p->sighand->siglock, flags);
+	if (lock_task_sighand(p, &flags)) {
+		signal_wake_up(p, 0);
+		unlock_task_sighand(p, &flags);
+	}
 }
 
 /**
- *	freeze_task - send a freeze request to given task
- *	@p: task to send the request to
- *	@sig_only: if set, the request will only be sent if the task has the
- *		PF_FREEZER_NOSIG flag unset
- *	Return value: 'false', if @sig_only is set and the task has
- *		PF_FREEZER_NOSIG set or the task is frozen, 'true', otherwise
+ * freeze_task - send a freeze request to given task
+ * @p: task to send the request to
+ *
+ * If @p is freezing, the freeze request is sent by setting %TIF_FREEZE
+ * flag and either sending a fake signal to it or waking it up, depending
+ * on whether it has %PF_FREEZER_NOSIG set.
  *
- *	The freeze request is sent by setting the tasks's TIF_FREEZE flag and
- *	either sending a fake signal to it or waking it up, depending on whether
- *	or not it has PF_FREEZER_NOSIG set.  If @sig_only is set and the task
- *	has PF_FREEZER_NOSIG set (ie. it is a typical kernel thread), its
- *	TIF_FREEZE flag will not be set.
+ * RETURNS:
+ * %false, if @p is not freezing or already frozen; %true, otherwise
  */
-bool freeze_task(struct task_struct *p, bool sig_only)
+bool freeze_task(struct task_struct *p)
 {
-	/*
-	 * We first check if the task is freezing and next if it has already
-	 * been frozen to avoid the race with frozen_process() which first marks
-	 * the task as frozen and next clears its TIF_FREEZE.
-	 */
-	if (!freezing(p)) {
-		smp_rmb();
-		if (frozen(p))
-			return false;
-
-		if (!sig_only || should_send_signal(p))
-			set_freeze_flag(p);
-		else
-			return false;
+	unsigned long flags;
+
+	spin_lock_irqsave(&freezer_lock, flags);
+	if (!freezing(p) || frozen(p)) {
+		spin_unlock_irqrestore(&freezer_lock, flags);
+		return false;
 	}
 
-	if (should_send_signal(p)) {
+	if (!(p->flags & PF_KTHREAD)) {
 		fake_signal_wake_up(p);
 		/*
 		 * fake_signal_wake_up() goes through p's scheduler
@@ -111,56 +124,48 @@ bool freeze_task(struct task_struct *p, bool sig_only)
 		 * TASK_RUNNING transition can't race with task state
 		 * testing in try_to_freeze_tasks().
 		 */
-	} else if (sig_only) {
-		return false;
 	} else {
 		wake_up_state(p, TASK_INTERRUPTIBLE);
 	}
 
+	spin_unlock_irqrestore(&freezer_lock, flags);
 	return true;
 }
 
-void cancel_freezing(struct task_struct *p)
+void __thaw_task(struct task_struct *p)
 {
 	unsigned long flags;
 
-	if (freezing(p)) {
-		pr_debug("  clean up: %s\n", p->comm);
-		clear_freeze_flag(p);
-		spin_lock_irqsave(&p->sighand->siglock, flags);
-		recalc_sigpending_and_wake(p);
-		spin_unlock_irqrestore(&p->sighand->siglock, flags);
-	}
-}
-
-static int __thaw_process(struct task_struct *p)
-{
-	if (frozen(p)) {
-		p->flags &= ~PF_FROZEN;
-		return 1;
-	}
-	clear_freeze_flag(p);
-	return 0;
+	/*
+	 * Clear freezing and kick @p if FROZEN.  Clearing is guaranteed to
+	 * be visible to @p as waking up implies wmb.  Waking up inside
+	 * freezer_lock also prevents wakeups from leaking outside
+	 * refrigerator.
+	 */
+	spin_lock_irqsave(&freezer_lock, flags);
+	if (frozen(p))
+		wake_up_process(p);
+	spin_unlock_irqrestore(&freezer_lock, flags);
 }
 
-/*
- * Wake up a frozen process
+/**
+ * set_freezable - make %current freezable
  *
- * task_lock() is needed to prevent the race with refrigerator() which may
- * occur if the freezing of tasks fails.  Namely, without the lock, if the
- * freezing of tasks failed, thaw_tasks() might have run before a task in
- * refrigerator() could call frozen_process(), in which case the task would be
- * frozen and no one would thaw it.
+ * Mark %current freezable and enter refrigerator if necessary.
  */
-int thaw_process(struct task_struct *p)
+bool set_freezable(void)
 {
-	task_lock(p);
-	if (__thaw_process(p) == 1) {
-		task_unlock(p);
-		wake_up_process(p);
-		return 1;
-	}
-	task_unlock(p);
-	return 0;
+	might_sleep();
+
+	/*
+	 * Modify flags while holding freezer_lock.  This ensures the
+	 * freezer notices that we aren't frozen yet or the freezing
+	 * condition is visible to try_to_freeze() below.
+	 */
+	spin_lock_irq(&freezer_lock);
+	current->flags &= ~PF_NOFREEZE;
+	spin_unlock_irq(&freezer_lock);
+
+	return try_to_freeze();
 }
-EXPORT_SYMBOL(thaw_process);
+EXPORT_SYMBOL(set_freezable);

kernel/kexec.c

@@ -1523,7 +1523,7 @@ int kernel_kexec(void)
 
 #ifdef CONFIG_KEXEC_JUMP
 	if (kexec_image->preserve_context) {
-		mutex_lock(&pm_mutex);
+		lock_system_sleep();
 		pm_prepare_console();
 		error = freeze_processes();
 		if (error) {
@@ -1576,7 +1576,7 @@ int kernel_kexec(void)
 		thaw_processes();
  Restore_console:
 		pm_restore_console();
-		mutex_unlock(&pm_mutex);
+		unlock_system_sleep();
 	}
 #endif
 

kernel/kmod.c

@@ -34,6 +34,9 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/resource.h>
+#include <linux/notifier.h>
+#include <linux/suspend.h>
+#include <linux/rwsem.h>
 #include <asm/uaccess.h>
 
 #include <trace/events/module.h>
@@ -48,6 +51,7 @@ static struct workqueue_struct *khelper_wq;
 static kernel_cap_t usermodehelper_bset = CAP_FULL_SET;
 static kernel_cap_t usermodehelper_inheritable = CAP_FULL_SET;
 static DEFINE_SPINLOCK(umh_sysctl_lock);
+static DECLARE_RWSEM(umhelper_sem);
 
 #ifdef CONFIG_MODULES
 
@@ -273,6 +277,7 @@ static void __call_usermodehelper(struct work_struct *work)
  * If set, call_usermodehelper_exec() will exit immediately returning -EBUSY
  * (used for preventing user land processes from being created after the user
  * land has been frozen during a system-wide hibernation or suspend operation).
+ * Should always be manipulated under umhelper_sem acquired for write.
  */
 static int usermodehelper_disabled = 1;
 
@@ -291,6 +296,18 @@ static DECLARE_WAIT_QUEUE_HEAD(running_helpers_waitq);
  */
 #define RUNNING_HELPERS_TIMEOUT	(5 * HZ)
 
+void read_lock_usermodehelper(void)
+{
+	down_read(&umhelper_sem);
+}
+EXPORT_SYMBOL_GPL(read_lock_usermodehelper);
+
+void read_unlock_usermodehelper(void)
+{
+	up_read(&umhelper_sem);
+}
+EXPORT_SYMBOL_GPL(read_unlock_usermodehelper);
+
 /**
  * usermodehelper_disable - prevent new helpers from being started
  */
@@ -298,8 +315,10 @@ int usermodehelper_disable(void)
 {
 	long retval;
 
+	down_write(&umhelper_sem);
 	usermodehelper_disabled = 1;
-	smp_mb();
+	up_write(&umhelper_sem);
+
 	/*
 	 * From now on call_usermodehelper_exec() won't start any new
 	 * helpers, so it is sufficient if running_helpers turns out to
@@ -312,7 +331,9 @@ int usermodehelper_disable(void)
 	if (retval)
 		return 0;
 
+	down_write(&umhelper_sem);
 	usermodehelper_disabled = 0;
+	up_write(&umhelper_sem);
 	return -EAGAIN;
 }
 
@@ -321,7 +342,9 @@ int usermodehelper_disable(void)
  */
 void usermodehelper_enable(void)
 {
+	down_write(&umhelper_sem);
 	usermodehelper_disabled = 0;
+	up_write(&umhelper_sem);
 }
 
 /**

kernel/kthread.c

@@ -58,6 +58,31 @@ int kthread_should_stop(void)
 }
 EXPORT_SYMBOL(kthread_should_stop);
 
+/**
+ * kthread_freezable_should_stop - should this freezable kthread return now?
+ * @was_frozen: optional out parameter, indicates whether %current was frozen
+ *
+ * kthread_should_stop() for freezable kthreads, which will enter
+ * refrigerator if necessary.  This function is safe from kthread_stop() /
+ * freezer deadlock and freezable kthreads should use this function instead
+ * of calling try_to_freeze() directly.
+ */
+bool kthread_freezable_should_stop(bool *was_frozen)
+{
+	bool frozen = false;
+
+	might_sleep();
+
+	if (unlikely(freezing(current)))
+		frozen = __refrigerator(true);
+
+	if (was_frozen)
+		*was_frozen = frozen;
+
+	return kthread_should_stop();
+}
+EXPORT_SYMBOL_GPL(kthread_freezable_should_stop);
+
 /**
  * kthread_data - return data value specified on kthread creation
  * @task: kthread task in question
@@ -257,7 +282,7 @@ int kthreadd(void *unused)
 	set_cpus_allowed_ptr(tsk, cpu_all_mask);
 	set_mems_allowed(node_states[N_HIGH_MEMORY]);
 
-	current->flags |= PF_NOFREEZE | PF_FREEZER_NOSIG;
+	current->flags |= PF_NOFREEZE;
 
 	for (;;) {
 		set_current_state(TASK_INTERRUPTIBLE);

kernel/power/hibernate.c

@@ -43,8 +43,6 @@ int in_suspend __nosavedata;
 enum {
 	HIBERNATION_INVALID,
 	HIBERNATION_PLATFORM,
-	HIBERNATION_TEST,
-	HIBERNATION_TESTPROC,
 	HIBERNATION_SHUTDOWN,
 	HIBERNATION_REBOOT,
 	/* keep last */
@@ -55,7 +53,7 @@ enum {
 
 static int hibernation_mode = HIBERNATION_SHUTDOWN;
 
-static bool freezer_test_done;
+bool freezer_test_done;
 
 static const struct platform_hibernation_ops *hibernation_ops;
 
@@ -71,14 +69,14 @@ void hibernation_set_ops(const struct platform_hibernation_ops *ops)
 		WARN_ON(1);
 		return;
 	}
-	mutex_lock(&pm_mutex);
+	lock_system_sleep();
 	hibernation_ops = ops;
 	if (ops)
 		hibernation_mode = HIBERNATION_PLATFORM;
 	else if (hibernation_mode == HIBERNATION_PLATFORM)
 		hibernation_mode = HIBERNATION_SHUTDOWN;
 
-	mutex_unlock(&pm_mutex);
+	unlock_system_sleep();
 }
 
 static bool entering_platform_hibernation;
@@ -96,15 +94,6 @@ static void hibernation_debug_sleep(void)
 	mdelay(5000);
 }
 
-static int hibernation_testmode(int mode)
-{
-	if (hibernation_mode == mode) {
-		hibernation_debug_sleep();
-		return 1;
-	}
-	return 0;
-}
-
 static int hibernation_test(int level)
 {
 	if (pm_test_level == level) {
@@ -114,7 +103,6 @@ static int hibernation_test(int level)
 	return 0;
 }
 #else /* !CONFIG_PM_DEBUG */
-static int hibernation_testmode(int mode) { return 0; }
 static int hibernation_test(int level) { return 0; }
 #endif /* !CONFIG_PM_DEBUG */
 
@@ -278,8 +266,7 @@ static int create_image(int platform_mode)
 		goto Platform_finish;
 
 	error = disable_nonboot_cpus();
-	if (error || hibernation_test(TEST_CPUS)
-	    || hibernation_testmode(HIBERNATION_TEST))
+	if (error || hibernation_test(TEST_CPUS))
 		goto Enable_cpus;
 
 	local_irq_disable();
@@ -333,7 +320,7 @@ static int create_image(int platform_mode)
  */
 int hibernation_snapshot(int platform_mode)
 {
-	pm_message_t msg = PMSG_RECOVER;
+	pm_message_t msg;
 	int error;
 
 	error = platform_begin(platform_mode);
@@ -349,8 +336,7 @@ int hibernation_snapshot(int platform_mode)
 	if (error)
 		goto Cleanup;
 
-	if (hibernation_test(TEST_FREEZER) ||
-		hibernation_testmode(HIBERNATION_TESTPROC)) {
+	if (hibernation_test(TEST_FREEZER)) {
 
 		/*
 		 * Indicate to the caller that we are returning due to a
@@ -362,26 +348,26 @@ int hibernation_snapshot(int platform_mode)
 
 	error = dpm_prepare(PMSG_FREEZE);
 	if (error) {
-		dpm_complete(msg);
+		dpm_complete(PMSG_RECOVER);
 		goto Cleanup;
 	}
 
 	suspend_console();
 	pm_restrict_gfp_mask();
+
 	error = dpm_suspend(PMSG_FREEZE);
-	if (error)
-		goto Recover_platform;
 
-	if (hibernation_test(TEST_DEVICES))
-		goto Recover_platform;
+	if (error || hibernation_test(TEST_DEVICES))
+		platform_recover(platform_mode);
+	else
+		error = create_image(platform_mode);
 
-	error = create_image(platform_mode);
 	/*
-	 * Control returns here (1) after the image has been created or the
+	 * In the case that we call create_image() above, the control
+	 * returns here (1) after the image has been created or the
 	 * image creation has failed and (2) after a successful restore.
 	 */
 
- Resume_devices:
 	/* We may need to release the preallocated image pages here. */
 	if (error || !in_suspend)
 		swsusp_free();
@@ -399,10 +385,6 @@ int hibernation_snapshot(int platform_mode)
 	platform_end(platform_mode);
 	return error;
 
- Recover_platform:
-	platform_recover(platform_mode);
-	goto Resume_devices;
-
  Cleanup:
 	swsusp_free();
 	goto Close;
@@ -590,9 +572,6 @@ int hibernation_platform_enter(void)
 static void power_down(void)
 {
 	switch (hibernation_mode) {
-	case HIBERNATION_TEST:
-	case HIBERNATION_TESTPROC:
-		break;
 	case HIBERNATION_REBOOT:
 		kernel_restart(NULL);
 		break;
@@ -611,17 +590,6 @@ static void power_down(void)
 	while(1);
 }
 
-static int prepare_processes(void)
-{
-	int error = 0;
-
-	if (freeze_processes()) {
-		error = -EBUSY;
-		thaw_processes();
-	}
-	return error;
-}
-
 /**
  * hibernate - Carry out system hibernation, including saving the image.
  */
@@ -629,7 +597,7 @@ int hibernate(void)
 {
 	int error;
 
-	mutex_lock(&pm_mutex);
+	lock_system_sleep();
 	/* The snapshot device should not be opened while we're running */
 	if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
 		error = -EBUSY;
@@ -654,7 +622,7 @@ int hibernate(void)
 	sys_sync();
 	printk("done.\n");
 
-	error = prepare_processes();
+	error = freeze_processes();
 	if (error)
 		goto Finish;
 
@@ -697,7 +665,7 @@ int hibernate(void)
 	pm_restore_console();
 	atomic_inc(&snapshot_device_available);
  Unlock:
-	mutex_unlock(&pm_mutex);
+	unlock_system_sleep();
 	return error;
 }
 
@@ -811,11 +779,13 @@ static int software_resume(void)
 		goto close_finish;
 
 	error = create_basic_memory_bitmaps();
-	if (error)
+	if (error) {
+		usermodehelper_enable();
 		goto close_finish;
+	}
 
 	pr_debug("PM: Preparing processes for restore.\n");
-	error = prepare_processes();
+	error = freeze_processes();
 	if (error) {
 		swsusp_close(FMODE_READ);
 		goto Done;
@@ -855,8 +825,6 @@ static const char * const hibernation_modes[] = {
 	[HIBERNATION_PLATFORM]	= "platform",
 	[HIBERNATION_SHUTDOWN]	= "shutdown",
 	[HIBERNATION_REBOOT]	= "reboot",
-	[HIBERNATION_TEST]	= "test",
-	[HIBERNATION_TESTPROC]	= "testproc",
 };
 
 /*
@@ -865,17 +833,15 @@ static const char * const hibernation_modes[] = {
  * Hibernation can be handled in several ways.  There are a few different ways
  * to put the system into the sleep state: using the platform driver (e.g. ACPI
  * or other hibernation_ops), powering it off or rebooting it (for testing
- * mostly), or using one of the two available test modes.
+ * mostly).
  *
  * The sysfs file /sys/power/disk provides an interface for selecting the
  * hibernation mode to use.  Reading from this file causes the available modes
- * to be printed.  There are 5 modes that can be supported:
+ * to be printed.  There are 3 modes that can be supported:
  *
  *	'platform'
  *	'shutdown'
  *	'reboot'
- *	'test'
- *	'testproc'
  *
  * If a platform hibernation driver is in use, 'platform' will be supported
  * and will be used by default.  Otherwise, 'shutdown' will be used by default.
@@ -899,8 +865,6 @@ static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr,
 		switch (i) {
 		case HIBERNATION_SHUTDOWN:
 		case HIBERNATION_REBOOT:
-		case HIBERNATION_TEST:
-		case HIBERNATION_TESTPROC:
 			break;
 		case HIBERNATION_PLATFORM:
 			if (hibernation_ops)
@@ -929,7 +893,7 @@ static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr,
 	p = memchr(buf, '\n', n);
 	len = p ? p - buf : n;
 
-	mutex_lock(&pm_mutex);
+	lock_system_sleep();
 	for (i = HIBERNATION_FIRST; i <= HIBERNATION_MAX; i++) {
 		if (len == strlen(hibernation_modes[i])
 		    && !strncmp(buf, hibernation_modes[i], len)) {
@@ -941,8 +905,6 @@ static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr,
 		switch (mode) {
 		case HIBERNATION_SHUTDOWN:
 		case HIBERNATION_REBOOT:
-		case HIBERNATION_TEST:
-		case HIBERNATION_TESTPROC:
 			hibernation_mode = mode;
 			break;
 		case HIBERNATION_PLATFORM:
@@ -957,7 +919,7 @@ static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr,
 	if (!error)
 		pr_debug("PM: Hibernation mode set to '%s'\n",
 			 hibernation_modes[mode]);
-	mutex_unlock(&pm_mutex);
+	unlock_system_sleep();
 	return error ? error : n;
 }
 
@@ -984,9 +946,9 @@ static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr,
 	if (maj != MAJOR(res) || min != MINOR(res))
 		goto out;
 
-	mutex_lock(&pm_mutex);
+	lock_system_sleep();
 	swsusp_resume_device = res;
-	mutex_unlock(&pm_mutex);
+	unlock_system_sleep();
 	printk(KERN_INFO "PM: Starting manual resume from disk\n");
 	noresume = 0;
 	software_resume();

kernel/power/main.c

@@ -3,7 +3,7 @@
  *
  * Copyright (c) 2003 Patrick Mochel
  * Copyright (c) 2003 Open Source Development Lab
- * 
+ *
  * This file is released under the GPLv2
  *
  */
@@ -116,7 +116,7 @@ static ssize_t pm_test_store(struct kobject *kobj, struct kobj_attribute *attr,
 	p = memchr(buf, '\n', n);
 	len = p ? p - buf : n;
 
-	mutex_lock(&pm_mutex);
+	lock_system_sleep();
 
 	level = TEST_FIRST;
 	for (s = &pm_tests[level]; level <= TEST_MAX; s++, level++)
@@ -126,7 +126,7 @@ static ssize_t pm_test_store(struct kobject *kobj, struct kobj_attribute *attr,
 			break;
 		}
 
-	mutex_unlock(&pm_mutex);
+	unlock_system_sleep();
 
 	return error ? error : n;
 }
@@ -240,7 +240,7 @@ struct kobject *power_kobj;
  *	'standby' (Power-On Suspend), 'mem' (Suspend-to-RAM), and
  *	'disk' (Suspend-to-Disk).
  *
- *	store() accepts one of those strings, translates it into the 
+ *	store() accepts one of those strings, translates it into the
  *	proper enumerated value, and initiates a suspend transition.
  */
 static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr,
@@ -282,7 +282,7 @@ static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr,
 	/* First, check if we are requested to hibernate */
 	if (len == 4 && !strncmp(buf, "disk", len)) {
 		error = hibernate();
-  goto Exit;
+		goto Exit;
 	}
 
 #ifdef CONFIG_SUSPEND

kernel/power/power.h

@@ -50,6 +50,8 @@ static inline char *check_image_kernel(struct swsusp_info *info)
 #define SPARE_PAGES	((1024 * 1024) >> PAGE_SHIFT)
 
 /* kernel/power/hibernate.c */
+extern bool freezer_test_done;
+
 extern int hibernation_snapshot(int platform_mode);
 extern int hibernation_restore(int platform_mode);
 extern int hibernation_platform_enter(void);

kernel/power/process.c

@@ -22,16 +22,7 @@
  */
 #define TIMEOUT	(20 * HZ)
 
-static inline int freezable(struct task_struct * p)
-{
-	if ((p == current) ||
-	    (p->flags & PF_NOFREEZE) ||
-	    (p->exit_state != 0))
-		return 0;
-	return 1;
-}
-
-static int try_to_freeze_tasks(bool sig_only)
+static int try_to_freeze_tasks(bool user_only)
 {
 	struct task_struct *g, *p;
 	unsigned long end_time;
@@ -46,17 +37,14 @@ static int try_to_freeze_tasks(bool sig_only)
 
 	end_time = jiffies + TIMEOUT;
 
-	if (!sig_only)
+	if (!user_only)
 		freeze_workqueues_begin();
 
 	while (true) {
 		todo = 0;
 		read_lock(&tasklist_lock);
 		do_each_thread(g, p) {
-			if (frozen(p) || !freezable(p))
-				continue;
-
-			if (!freeze_task(p, sig_only))
+			if (p == current || !freeze_task(p))
 				continue;
 
 			/*
@@ -77,7 +65,7 @@ static int try_to_freeze_tasks(bool sig_only)
 		} while_each_thread(g, p);
 		read_unlock(&tasklist_lock);
 
-		if (!sig_only) {
+		if (!user_only) {
 			wq_busy = freeze_workqueues_busy();
 			todo += wq_busy;
 		}
@@ -103,11 +91,6 @@ static int try_to_freeze_tasks(bool sig_only)
 	elapsed_csecs = elapsed_csecs64;
 
 	if (todo) {
-		/* This does not unfreeze processes that are already frozen
-		 * (we have slightly ugly calling convention in that respect,
-		 * and caller must call thaw_processes() if something fails),
-		 * but it cleans up leftover PF_FREEZE requests.
-		 */
 		printk("\n");
 		printk(KERN_ERR "Freezing of tasks %s after %d.%02d seconds "
 		       "(%d tasks refusing to freeze, wq_busy=%d):\n",
@@ -115,15 +98,11 @@ static int try_to_freeze_tasks(bool sig_only)
 		       elapsed_csecs / 100, elapsed_csecs % 100,
 		       todo - wq_busy, wq_busy);
 
-		thaw_workqueues();
-
 		read_lock(&tasklist_lock);
 		do_each_thread(g, p) {
-			task_lock(p);
-			if (!wakeup && freezing(p) && !freezer_should_skip(p))
+			if (!wakeup && !freezer_should_skip(p) &&
+			    p != current && freezing(p) && !frozen(p))
 				sched_show_task(p);
-			cancel_freezing(p);
-			task_unlock(p);
 		} while_each_thread(g, p);
 		read_unlock(&tasklist_lock);
 	} else {
@@ -136,12 +115,18 @@ static int try_to_freeze_tasks(bool sig_only)
 
 /**
  * freeze_processes - Signal user space processes to enter the refrigerator.
+ *
+ * On success, returns 0.  On failure, -errno and system is fully thawed.
  */
 int freeze_processes(void)
 {
 	int error;
 
+	if (!pm_freezing)
+		atomic_inc(&system_freezing_cnt);
+
 	printk("Freezing user space processes ... ");
+	pm_freezing = true;
 	error = try_to_freeze_tasks(true);
 	if (!error) {
 		printk("done.");
@@ -150,17 +135,22 @@ int freeze_processes(void)
 	printk("\n");
 	BUG_ON(in_atomic());
 
+	if (error)
+		thaw_processes();
 	return error;
 }
 
 /**
  * freeze_kernel_threads - Make freezable kernel threads go to the refrigerator.
+ *
+ * On success, returns 0.  On failure, -errno and system is fully thawed.
  */
 int freeze_kernel_threads(void)
 {
 	int error;
 
 	printk("Freezing remaining freezable tasks ... ");
+	pm_nosig_freezing = true;
 	error = try_to_freeze_tasks(false);
 	if (!error)
 		printk("done.");
@@ -168,37 +158,32 @@ int freeze_kernel_threads(void)
 	printk("\n");
 	BUG_ON(in_atomic());
 
+	if (error)
+		thaw_processes();
 	return error;
 }
 
-static void thaw_tasks(bool nosig_only)
+void thaw_processes(void)
 {
 	struct task_struct *g, *p;
 
-	read_lock(&tasklist_lock);
-	do_each_thread(g, p) {
-		if (!freezable(p))
-			continue;
+	if (pm_freezing)
+		atomic_dec(&system_freezing_cnt);
+	pm_freezing = false;
+	pm_nosig_freezing = false;
 
-		if (nosig_only && should_send_signal(p))
-			continue;
+	oom_killer_enable();
+
+	printk("Restarting tasks ... ");
 
-		if (cgroup_freezing_or_frozen(p))
-			continue;
+	thaw_workqueues();
 
-		thaw_process(p);
+	read_lock(&tasklist_lock);
+	do_each_thread(g, p) {
+		__thaw_task(p);
 	} while_each_thread(g, p);
 	read_unlock(&tasklist_lock);
-}
 
-void thaw_processes(void)
-{
-	oom_killer_enable();
-
-	printk("Restarting tasks ... ");
-	thaw_workqueues();
-	thaw_tasks(true);
-	thaw_tasks(false);
 	schedule();
 	printk("done.\n");
 }

kernel/power/suspend.c

@@ -42,9 +42,9 @@ static const struct platform_suspend_ops *suspend_ops;
  */
 void suspend_set_ops(const struct platform_suspend_ops *ops)
 {
-	mutex_lock(&pm_mutex);
+	lock_system_sleep();
 	suspend_ops = ops;
-	mutex_unlock(&pm_mutex);
+	unlock_system_sleep();
 }
 EXPORT_SYMBOL_GPL(suspend_set_ops);
 
@@ -106,13 +106,11 @@ static int suspend_prepare(void)
 		goto Finish;
 
 	error = suspend_freeze_processes();
-	if (error) {
-		suspend_stats.failed_freeze++;
-		dpm_save_failed_step(SUSPEND_FREEZE);
-	} else
+	if (!error)
 		return 0;
 
-	suspend_thaw_processes();
+	suspend_stats.failed_freeze++;
+	dpm_save_failed_step(SUSPEND_FREEZE);
 	usermodehelper_enable();
  Finish:
 	pm_notifier_call_chain(PM_POST_SUSPEND);

kernel/power/user.c

@@ -30,28 +30,6 @@
 
 #include "power.h"
 
-/*
- * NOTE: The SNAPSHOT_SET_SWAP_FILE and SNAPSHOT_PMOPS ioctls are obsolete and
- * will be removed in the future.  They are only preserved here for
- * compatibility with existing userland utilities.
- */
-#define SNAPSHOT_SET_SWAP_FILE	_IOW(SNAPSHOT_IOC_MAGIC, 10, unsigned int)
-#define SNAPSHOT_PMOPS		_IOW(SNAPSHOT_IOC_MAGIC, 12, unsigned int)
-
-#define PMOPS_PREPARE	1
-#define PMOPS_ENTER	2
-#define PMOPS_FINISH	3
-
-/*
- * NOTE: The following ioctl definitions are wrong and have been replaced with
- * correct ones.  They are only preserved here for compatibility with existing
- * userland utilities and will be removed in the future.
- */
-#define SNAPSHOT_ATOMIC_SNAPSHOT	_IOW(SNAPSHOT_IOC_MAGIC, 3, void *)
-#define SNAPSHOT_SET_IMAGE_SIZE		_IOW(SNAPSHOT_IOC_MAGIC, 6, unsigned long)
-#define SNAPSHOT_AVAIL_SWAP		_IOR(SNAPSHOT_IOC_MAGIC, 7, void *)
-#define SNAPSHOT_GET_SWAP_PAGE		_IOR(SNAPSHOT_IOC_MAGIC, 8, void *)
-
 
 #define SNAPSHOT_MINOR	231
 
@@ -71,7 +49,7 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 	struct snapshot_data *data;
 	int error;
 
-	mutex_lock(&pm_mutex);
+	lock_system_sleep();
 
 	if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
 		error = -EBUSY;
@@ -123,7 +101,7 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 	data->platform_support = 0;
 
  Unlock:
-	mutex_unlock(&pm_mutex);
+	unlock_system_sleep();
 
 	return error;
 }
@@ -132,7 +110,7 @@ static int snapshot_release(struct inode *inode, struct file *filp)
 {
 	struct snapshot_data *data;
 
-	mutex_lock(&pm_mutex);
+	lock_system_sleep();
 
 	swsusp_free();
 	free_basic_memory_bitmaps();
@@ -146,7 +124,7 @@ static int snapshot_release(struct inode *inode, struct file *filp)
 			PM_POST_HIBERNATION : PM_POST_RESTORE);
 	atomic_inc(&snapshot_device_available);
 
-	mutex_unlock(&pm_mutex);
+	unlock_system_sleep();
 
 	return 0;
 }
@@ -158,7 +136,7 @@ static ssize_t snapshot_read(struct file *filp, char __user *buf,
 	ssize_t res;
 	loff_t pg_offp = *offp & ~PAGE_MASK;
 
-	mutex_lock(&pm_mutex);
+	lock_system_sleep();
 
 	data = filp->private_data;
 	if (!data->ready) {
@@ -179,7 +157,7 @@ static ssize_t snapshot_read(struct file *filp, char __user *buf,
 		*offp += res;
 
  Unlock:
-	mutex_unlock(&pm_mutex);
+	unlock_system_sleep();
 
 	return res;
 }
@@ -191,7 +169,7 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf,
 	ssize_t res;
 	loff_t pg_offp = *offp & ~PAGE_MASK;
 
-	mutex_lock(&pm_mutex);
+	lock_system_sleep();
 
 	data = filp->private_data;
 
@@ -208,20 +186,11 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf,
 	if (res > 0)
 		*offp += res;
 unlock:
-	mutex_unlock(&pm_mutex);
+	unlock_system_sleep();
 
 	return res;
 }
 
-static void snapshot_deprecated_ioctl(unsigned int cmd)
-{
-	if (printk_ratelimit())
-		printk(KERN_NOTICE "%pf: ioctl '%.8x' is deprecated and will "
-				"be removed soon, update your suspend-to-disk "
-				"utilities\n",
-				__builtin_return_address(0), cmd);
-}
-
 static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 							unsigned long arg)
 {
@@ -257,11 +226,9 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 			break;
 
 		error = freeze_processes();
-		if (error) {
-			thaw_processes();
+		if (error)
 			usermodehelper_enable();
-		}
-		if (!error)
+		else
 			data->frozen = 1;
 		break;
 
@@ -274,8 +241,6 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 		data->frozen = 0;
 		break;
 
-	case SNAPSHOT_ATOMIC_SNAPSHOT:
-		snapshot_deprecated_ioctl(cmd);
 	case SNAPSHOT_CREATE_IMAGE:
 		if (data->mode != O_RDONLY || !data->frozen  || data->ready) {
 			error = -EPERM;
@@ -283,10 +248,15 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 		}
 		pm_restore_gfp_mask();
 		error = hibernation_snapshot(data->platform_support);
-		if (!error)
+		if (!error) {
 			error = put_user(in_suspend, (int __user *)arg);
-		if (!error)
-			data->ready = 1;
+			if (!error && !freezer_test_done)
+				data->ready = 1;
+			if (freezer_test_done) {
+				freezer_test_done = false;
+				thaw_processes();
+			}
+		}
 		break;
 
 	case SNAPSHOT_ATOMIC_RESTORE:
@@ -305,8 +275,6 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 		data->ready = 0;
 		break;
 
-	case SNAPSHOT_SET_IMAGE_SIZE:
-		snapshot_deprecated_ioctl(cmd);
 	case SNAPSHOT_PREF_IMAGE_SIZE:
 		image_size = arg;
 		break;
@@ -321,16 +289,12 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 		error = put_user(size, (loff_t __user *)arg);
 		break;
 
-	case SNAPSHOT_AVAIL_SWAP:
-		snapshot_deprecated_ioctl(cmd);
 	case SNAPSHOT_AVAIL_SWAP_SIZE:
 		size = count_swap_pages(data->swap, 1);
 		size <<= PAGE_SHIFT;
 		error = put_user(size, (loff_t __user *)arg);
 		break;
 
-	case SNAPSHOT_GET_SWAP_PAGE:
-		snapshot_deprecated_ioctl(cmd);
 	case SNAPSHOT_ALLOC_SWAP_PAGE:
 		if (data->swap < 0 || data->swap >= MAX_SWAPFILES) {
 			error = -ENODEV;
@@ -353,27 +317,6 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 		free_all_swap_pages(data->swap);
 		break;
 
-	case SNAPSHOT_SET_SWAP_FILE: /* This ioctl is deprecated */
-		snapshot_deprecated_ioctl(cmd);
-		if (!swsusp_swap_in_use()) {
-			/*
-			 * User space encodes device types as two-byte values,
-			 * so we need to recode them
-			 */
-			if (old_decode_dev(arg)) {
-				data->swap = swap_type_of(old_decode_dev(arg),
-							0, NULL);
-				if (data->swap < 0)
-					error = -ENODEV;
-			} else {
-				data->swap = -1;
-				error = -EINVAL;
-			}
-		} else {
-			error = -EPERM;
-		}
-		break;
-
 	case SNAPSHOT_S2RAM:
 		if (!data->frozen) {
 			error = -EPERM;
@@ -396,33 +339,6 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 			error = hibernation_platform_enter();
 		break;
 
-	case SNAPSHOT_PMOPS: /* This ioctl is deprecated */
-		snapshot_deprecated_ioctl(cmd);
-		error = -EINVAL;
-
-		switch (arg) {
-
-		case PMOPS_PREPARE:
-			data->platform_support = 1;
-			error = 0;
-			break;
-
-		case PMOPS_ENTER:
-			if (data->platform_support)
-				error = hibernation_platform_enter();
-			break;
-
-		case PMOPS_FINISH:
-			if (data->platform_support)
-				error = 0;
-			break;
-
-		default:
-			printk(KERN_ERR "SNAPSHOT_PMOPS: invalid argument %ld\n", arg);
-
-		}
-		break;
-
 	case SNAPSHOT_SET_SWAP_AREA:
 		if (swsusp_swap_in_use()) {
 			error = -EPERM;

mm/backing-dev.c

@@ -600,14 +600,10 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 
 	/*
 	 * Finally, kill the kernel thread. We don't need to be RCU
-	 * safe anymore, since the bdi is gone from visibility. Force
-	 * unfreeze of the thread before calling kthread_stop(), otherwise
-	 * it would never exet if it is currently stuck in the refrigerator.
+	 * safe anymore, since the bdi is gone from visibility.
 	 */
-	if (bdi->wb.task) {
-		thaw_process(bdi->wb.task);
+	if (bdi->wb.task)
 		kthread_stop(bdi->wb.task);
-	}
 }
 
 /*

mm/oom_kill.c

@@ -328,7 +328,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 		 */
 		if (test_tsk_thread_flag(p, TIF_MEMDIE)) {
 			if (unlikely(frozen(p)))
-				thaw_process(p);
+				__thaw_task(p);
 			return ERR_PTR(-1UL);
 		}
 		if (!p->mm)

net/sunrpc/sched.c

@@ -18,6 +18,7 @@
 #include <linux/smp.h>
 #include <linux/spinlock.h>
 #include <linux/mutex.h>
+#include <linux/freezer.h>
 
 #include <linux/sunrpc/clnt.h>
 
@@ -231,7 +232,7 @@ static int rpc_wait_bit_killable(void *word)
 {
 	if (fatal_signal_pending(current))
 		return -ERESTARTSYS;
-	schedule();
+	freezable_schedule();
 	return 0;
 }