Most of these files were implicitly getting EXPORT_SYMBOL via
device.h which was including module.h, but that path will be broken
soon.

[ with input from Stephen Rothwell <sfr@canb.auug.org.au> ]
Signed-off-by: NPaul Gortmaker <paul.gortmaker@windriver.com>

Since kfree() checks it its argument is not NULL, it is not necessary
to duplicate this check in __pm_clk_remove().

[rjw: Added the changelog.]
Signed-off-by: NJonghwan Choi <jhbird.choi@samsung.com>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

The generic PM domains code in drivers/base/power/domain.c has
to avoid powering off domains that provide power to wakeup devices
during system suspend.  Currently, however, this only works for
wakeup devices directly belonging to the given domain and not for
their children (or the children of their children and so on).
Thus, if there's a wakeup device whose parent belongs to a power
domain handled by the generic PM domains code, the domain will be
powered off during system suspend preventing the device from
signaling wakeup.

To address this problem introduce a device flag, power.wakeup_path,
that will be set during system suspend for all wakeup devices,
their parents, the parents of their parents and so on.  This way,
all wakeup paths in the device hierarchy will be marked and the
generic PM domains code will only need to avoid powering off
domains containing devices whose power.wakeup_path is set.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

This patch (as1485) documents a change to the kernel's default wakeup
policy.  Devices that forward wakeup requests between buses should be
enabled for wakeup by default.
Signed-off-by: NAlan Stern <stern@rowland.harvard.edu>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

Record S3 failure time about each reason and the latest two failed
devices' names in S3 progress.
We can check it through 'suspend_stats' entry in debugfs.

The motivation of the patch:

We are enabling power features on Medfield. Comparing with PC/notebook,
a mobile enters/exits suspend-2-ram (we call it s3 on Medfield) far
more frequently. If it can't enter suspend-2-ram in time, the power
might be used up soon.

We often find sometimes, a device suspend fails. Then, system retries
s3 over and over again. As display is off, testers and developers
don't know what happens.

Some testers and developers complain they don't know if system
tries suspend-2-ram, and what device fails to suspend. They need
such info for a quick check. The patch adds suspend_stats under
debugfs for users to check suspend to RAM statistics quickly.

If not using this patch, we have other methods to get info about
what device fails. One is to turn on  CONFIG_PM_DEBUG, but users
would get too much info and testers need recompile the system.

In addition, dynamic debug is another good tool to dump debug info.
But it still doesn't match our utilization scenario closely.
1) user need write a user space parser to process the syslog output;
2) Our testing scenario is we leave the mobile for at least hours.
   Then, check its status. No serial console available during the
   testing. One is because console would be suspended, and the other
   is serial console connecting with spi or HSU devices would consume
   power. These devices are powered off at suspend-2-ram.
Signed-off-by: NShuoX Liu <shuox.liu@intel.com>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

If .runtime_suspend() returns -EAGAIN or -EBUSY, the device should
still be in ACTIVE state, so it is not necessary to send an idle
notification to its parent.  If .runtime_suspend() returns other
fatal failure, it doesn't make sense to send idle notification to
its parent.

Skip parent idle notification when failure is returned from
.runtime_suspend() and update comments in rpm_suspend() to reflect
that change.

[rjw: Modified the subject and changelog slightly.]
Signed-off-by: NMing Lei <ming.lei@canonical.com>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

This patch fix kerneldoc comments for rpm_suspend():

 - 'Cancel a pending idle notification' should be put before, also
   should be changed to 'Cancel a pending idle notification,
   autosuspend or suspend'.

 - idle notification for the device after succeeding suspend has
   been removed, so update the comment accordingly.

[rjw: Modified the subject and changelog slightly.]
Signed-off-by: NMing Lei <ming.lei@canonical.com>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

To read the current PM QoS value for a given device we need to
make sure that the device's power.constraints object won't be
removed while we're doing that.  For this reason, put the
operation under dev->power.lock and acquire the lock
around the initialization and removal of power.constraints.

Moreover, since we're using the value of power.constraints to
determine whether or not the object is present, the
power.constraints_state field isn't necessary any more and may be
removed.  However, dev_pm_qos_add_request() needs to check if the
device is being removed from the system before allocating a new
PM QoS constraints object for it, so make it use the
power.power_state field of struct device for this purpose.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

The patch enables to register notifier_block for an OPP-device in order
to get notified for any changes in the availability of OPPs of the
device. For example, if a new OPP is inserted or enable/disable status
of an OPP is changed, the notifier is executed.

This enables the usage of opp_add, opp_enable, and opp_disable to
directly take effect with any connected entities such as cpufreq or
devfreq.
Signed-off-by: NMyungJoo Ham <myungjoo.ham@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Reviewed-by: NMike Turquette <mturquette@ti.com>
Reviewed-by: NKevin Hilman <khilman@ti.com>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

This patch replaces dev_dbg with trace_rpm_* inside
the three important functions:

	rpm_idle
	rpm_suspend
	rpm_resume

Trace points have the below advantages compared with dev_dbg:

	- trace points include much runtime information(such as
	running cpu, current task, ...)

	- most of linux distributions may disable "verbose debug"
	driver debug compile switch, so it is very difficult to
	report/debug runtime pm related problems from distribution
	users without this kind of debug information.

	- for upstream kernel users, enableing the debug switch will
	produce many useless "rpm_resume" output, and it is very noise.

	- dev_dbg inside rpm_suspend/rpm_resume may have some effects
	on runtime pm behaviour of console devicer
Signed-off-by: NMing Lei <ming.lei@canonical.com>
Acked-by: NSteven Rostedt <rostedt@goodmis.org>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

The rpm_suspend() and rpm_resume() routines execute subsystem or PM
domain callbacks under power.lock if power.irq_safe is set for the
given device.  This is inconsistent with that rpm_idle() does after
commit 02b26774 (PM / Runtime: Allow _put_sync() from
interrupts-disabled context) and is problematic for subsystems and PM
domains wanting to use power.lock for synchronization in their
runtime PM callbacks.

This change requires the code checking if the device's runtime PM
status is RPM_SUSPENDING or RPM_RESUMING to be modified too, to take
the power.irq_safe set case into account (that code wasn't reachable
before with power.irq_safe set, because it's executed with the
device's power.lock held).
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>
Reviewed-by: NMing Lei <tom.leiming@gmail.com>
Reviewed-by: NKevin Hilman <khilman@ti.com>

The struct pm_domain_data data type is defined in such a way that
adding new fields specific to the generic PM domains code will
require include/linux/pm.h to be modified.  As a result, data types
used only by the generic PM domains code will be defined in two
headers, although they all should be defined in pm_domain.h and
pm.h will need to include more headers, which won't be very nice.

For this reason change the definition of struct pm_subsys_data
so that its domain_data member is a pointer, which will allow
struct pm_domain_data to be subclassed by various PM domains
implementations.  Remove the need_restore member from
struct pm_domain_data and make the generic PM domains code
subclass it by adding the need_restore member to the new data type.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

Commit b7ab83ed (PM: Use spinlock instead of mutex in clock
management functions) introduced a regression causing clocks_mutex
to be acquired under a spinlock.  This happens because
pm_clk_suspend() and pm_clk_resume() call pm_clk_acquire() under
pcd->lock, but pm_clk_acquire() executes clk_get() which causes
clocks_mutex to be acquired.  Similarly, __pm_clk_remove(),
executed under pcd->lock, calls clk_put(), which also causes
clocks_mutex to be acquired.

To fix those problems make pm_clk_add() call pm_clk_acquire(), so
that pm_clk_suspend() and pm_clk_resume() don't have to do that.
Change pm_clk_remove() and pm_clk_destroy() to separate
modifications of the pcd->clock_list list from the actual removal of
PM clock entry objects done by __pm_clk_remove().
Reported-and-tested-by: NGuennadi Liakhovetski <g.liakhovetski@gmx.de>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>
Acked-by: NRussell King <rmk+kernel@arm.linux.org.uk>

The generic PM domains framework currently doesn't work with devices
whose power.irq_safe flag is set, because runtime PM callbacks for
such devices are run with interrupts disabled and the callbacks
provided by the generic PM domains framework use domain mutexes
and may sleep.  However, such devices very well may belong to
power domains on some systems, so the generic PM domains framework
should take them into account.

For this reason, modify the generic PM domains framework so that the
domain .power_off() and .power_on() callbacks are never executed for
a domain containing devices with power.irq_safe set, although the
.stop_device() and .start_device() callbacks are still run for them.

Additionally, introduce a flag allowing the creator of a
struct generic_pm_domain object to indicate that its .stop_device()
and .start_device() callbacks may be run in interrupt context
(might_sleep_if() triggers if that flag is not set and one of those
callbacks is run in interrupt context).
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

Add a global notification chain that gets called upon changes to the
aggregated constraint value for any device.
The notification callbacks are passing the full constraint request data
in order for the callees to have access to it. The current use is for the
platform low-level code to access the target device of the constraint.
Signed-off-by: NJean Pihet <j-pihet@ti.com>
Reviewed-by: NKevin Hilman <khilman@ti.com>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

Implement the per-device PM QoS constraints by creating a device
PM QoS API, which calls the PM QoS constraints management core code.

The per-device latency constraints data strctures are stored
in the device dev_pm_info struct.

The device PM code calls the init and destroy of the per-device constraints
data struct in order to support the dynamic insertion and removal of the
devices in the system.

To minimize the data usage by the per-device constraints, the data struct
is only allocated at the first call to dev_pm_qos_add_request.
The data is later free'd when the device is removed from the system.
A global mutex protects the constraints users from the data being
allocated and free'd.
Signed-off-by: NJean Pihet <j-pihet@ti.com>
Reviewed-by: NKevin Hilman <khilman@ti.com>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

Since the PM clock management code in drivers/base/power/clock_ops.c
is used for both runtime PM and system suspend/hibernation, the
definitions of data structures and headers related to it should not
be located in include/linux/pm_rumtime.h.  Move them to a separate
header file.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

Currently pm_genpd_runtime_resume() has to walk the list of devices
from the device's PM domain to find the corresponding device list
object containing the need_restore field to check if the driver's
.runtime_resume() callback should be executed for the device.
This is suboptimal and can be simplified by using power.sybsys_data
to store device information used by the generic PM domains code.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

Since the power.subsys_data device field will be used by multiple
filesystems, introduce a reference counting mechanism for it to avoid
freeing it prematurely or changing its value at a wrong time.

Make the PM clocks management code that currently is the only user of
power.subsys_data use the new reference counting.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

Introduce struct pm_subsys_data that may be subclassed by subsystems
to store subsystem-specific information related to the device.  Move
the clock management fields accessed through the power.subsys_data
pointer in struct device to the new strucutre.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

Change the name of the second argument of pm_genpd_add_subdomain()
so that it is (a) shorter and (b) in agreement with the name of
the second argument of pm_genpd_add_subdomain().
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

Since it is now possible for a PM domain to have multiple masters
instead of one parent, rename the "wait for parent" status to reflect
the new situation.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

Currently, for a given generic PM domain there may be only one parent
domain (i.e. a PM domain it depends on).  However, there is at least
one real-life case in which there should be two parents (masters) for
one PM domain (the A3RV domain on SH7372 turns out to depend on the
A4LC domain and it depends on the A4R domain and the same time). For
this reason, allow a PM domain to have multiple parents (masters) by
introducing objects representing links between PM domains.

The (logical) links between PM domains represent relationships in
which one domain is a master (i.e. it is depended on) and another
domain is a slave (i.e. it depends on the master) with the rule that
the slave cannot be powered on if the master is not powered on and
the master cannot be powered off if the slave is not powered off.
Each struct generic_pm_domain object representing a PM domain has
two lists of links, a list of links in which it is a master and
a list of links in which it is a slave.  The first of these lists
replaces the list of subdomains and the second one is used in place
of the parent pointer.

Each link is represented by struct gpd_link object containing
pointers to the master and the slave and two struct list_head
members allowing it to hook into two lists (the master's list
of "master" links and the slave's list of "slave" links).  This
allows the code to get to the link from each side (either from
the master or from the slave) and follow it in each direction.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

The next patch will make it possible for a generic PM domain to have
multiple parents (i.e. multiple PM domains it depends on).  To
prepare for that change it is necessary to change pm_genpd_poweron()
so that it doesn't jump to the start label after running itself
recursively for the parent domain.  For this purpose, introduce a new
PM domain status value GPD_STATE_WAIT_PARENT that will be set by
pm_genpd_poweron() before calling itself recursively for the parent
domain and modify the code in drivers/base/power/domain.c so that
the GPD_STATE_WAIT_PARENT status is guaranteed to be preserved during
the execution of pm_genpd_poweron() for the parent.

This change also causes pm_genpd_add_subdomain() and
pm_genpd_remove_subdomain() to wait for started pm_genpd_poweron() to
complete and allows pm_genpd_runtime_resume() to avoid dropping the
lock after powering on the PM domain.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

If pm_genpd_remove_subdomain() is called to remove a PM domain's
subdomain and pm_genpd_poweron() is called for that subdomain at
the same time, and the pm_genpd_poweron() called by it recursively
for the parent returns an error, the first pm_genpd_poweron()'s
error code path will attempt to decrement the subdomain counter of
a PM domain that it's not a subdomain of any more.

Rearrange the code in pm_genpd_poweron() to prevent this from
happening.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

After the subdomain counter in struct generic_pm_domain has been
changed into an atomic_t field, it is possible to modify
pm_genpd_poweron() and pm_genpd_poweroff() so that they don't take
the parents locks.  This requires pm_genpd_poweron() to increment
the parent's subdomain counter before calling itself recursively
for the parent and to decrement it if an error is to be returned.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

Currently, pm_genpd_poweron() and pm_genpd_poweroff() need to take
the parent PM domain's lock in order to modify the parent's counter
of active subdomains in a nonracy way.  This causes the locking to be
considerably complex and in fact is not necessary, because the
subdomain counters may be implemented as atomic fields and they
won't have to be modified under a lock.

Replace the unsigned in sd_count field in struct generic_pm_domain
by an atomic_t one and modify the code in drivers/base/power/domain.c
to take this change into account.

This patch doesn't change the locking yet, that is going to be done
in a separate subsequent patch.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

The lock member of struct pm_clk_data is of type struct mutex,
which is a problem, because the suspend and resume routines
defined in drivers/base/power/clock_ops.c cannot be executed
with interrupts disabled for this reason.  Modify
struct pm_clk_data so that its lock member is a spinlock.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>
Acked-by: NMagnus Damm <damm@opensource.se>

Some of the entry points to pm runtime are not safe to
call in atomic context unless pm_runtime_irq_safe() has
been called.  Inspecting the code, it is not immediately
obvious that the functions sleep at all, as they run
inside a spin_lock_irqsave, but under some conditions
they can drop the lock and turn on irqs.

If a driver incorrectly calls the pm_runtime apis, it can
cause sleeping and irq processing when it expects to stay
in atomic context.

Add might_sleep_if to the majority of the __pm_runtime_* entry points
to enforce correct usage.

Add pm_runtime_put_sync_autosuspend to the list of
functions that can be called in atomic context.
Signed-off-by: NColin Cross <ccross@android.com>
Reviewed-by: NKevin Hilman <khilman@ti.com>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

Function genpd_queue_power_off_work() is not defined for
CONFIG_PM_RUNTIME, so pm_genpd_poweroff_unused() causes a build
error to happen in that case.  Fix the problem by making
pm_genpd_poweroff_unused() depend on CONFIG_PM_RUNTIME too.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

Currently the use of pm_runtime_put_sync() is not safe from
interrupts-disabled context because rpm_idle() will release the
spinlock and enable interrupts for the idle callbacks.  This enables
interrupts during a time where interrupts were expected to be
disabled, and can have strange side effects on drivers that expected
interrupts to be disabled.

This is not a bug since the documentation clearly states that only
_put_sync_suspend() is safe in IRQ-safe mode.

However, pm_runtime_put_sync() could be made safe when in IRQ-safe
mode by releasing the spinlock but not re-enabling interrupts, which
is what this patch aims to do.

Problem was found when using some buggy drivers that set
pm_runtime_irq_safe() and used _put_sync() in interrupts-disabled
context.
Reported-by: NColin Cross <ccross@google.com>
Tested-by: NNishanth Menon <nm@ti.com>
Signed-off-by: NKevin Hilman <khilman@ti.com>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

The local variable ret is defined twice in pm_genpd_poweron(), which
causes this function to always return 0, even if the PM domain's
.power_on() callback fails, in which case an error code should be
returned.

Remove the wrong second definition of ret and additionally remove an
unnecessary definition of wait from pm_genpd_poweron().
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

This allows us to move duplicated code in <asm/atomic.h>
(atomic_inc_not_zero() for now) to <linux/atomic.h>
Signed-off-by: NArun Sharma <asharma@fb.com>
Reviewed-by: NEric Dumazet <eric.dumazet@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: David Miller <davem@davemloft.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: NMike Frysinger <vapier@gentoo.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Dev_opp initial value shoule be ERR_PTR(), IS_ERR() is used to check
error.
Signed-off-by: NJonghwan Choi <jhbird.choi@samsung.com>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Some users are apparently confused by dmesg output from
read_magic_time(), which looks like "real" time and date.
Add the "RTC" string to time stamps printed by read_magic_time() to
avoid that confusion.
Reported-by: NJustin P. Mattock <justinmattock@gmail.com>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

cpufreq table allocated by opp_init_cpufreq_table is better
freed by OPP layer itself. This allows future modifications to
the table handling to be transparent to the users.
Signed-off-by: NNishanth Menon <nm@ti.com>
Acked-by: NKevin Hilman <khilman@ti.com>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

Currently pm_genpd_poweroff() discards error codes returned by
the PM domain's .power_off() callback, because it's safer to always
regard the domain as inaccessible to drivers after a failing
.power_off().  Still, there are situations in which the low-level
code may want to indicate that it doesn't want to power off the
domain, so allow it to do that by returning -EBUSY from .power_off().
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>
Acked-by: NMagnus Damm <damm@opensource.se>

Make pd_power_down_a3rv() use genpd_queue_power_off_work() to queue
up the powering off of the A4LC domain to avoid queuing it up when
it is pending.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>
Acked-by: NMagnus Damm <damm@opensource.se>

Add a new function pm_genpd_poweroff_unused() queuing up the
execution of pm_genpd_poweroff() for every initialized generic PM
domain.  Calling it will cause every generic PM domain without
devices in use to be powered off.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>
Acked-by: NMagnus Damm <damm@opensource.se>

In theory it is possible that pm_genpd_poweroff() for two different
subdomains of the same parent domain will attempt to queue up the
execution of pm_genpd_poweroff() for the parent twice in a row.  This
would lead to unpleasant consequences, so prevent it from happening
by checking if genpd->power_off_work is pending before attempting to
queue it up.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>