The invocation of the ->setpolicy() cpufreq driver callback should
be equivalent to calling cpufreq_governor_limits(policy) for drivers
with internal governors, but in fact it isn't so, because the
temporary new_policy object is passed to it instead of the updated
policy.

That is a bit confusing, so make cpufreq_set_policy() pass the
updated policy to the driver ->setpolicy() callback.

No intentional changes of behavior.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>

Remove the redundant "cpufreq:" prefix from two debug messages in
cpufreq_set_policy().
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>

In cpufreq_update_policy(), instead of updating new_policy.cur
separately, which is kind of confusing, because cpufreq_set_policy()
doesn't take that value into account directly anyway, make the copy
of the existing policy after calling cpufreq_update_current_freq().

No intentional changes of behavior.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>

Add kerneldoc comments describing cpufreq_set_policy() and
cpufreq_update_policy() as they have not been properly documented
so far and they really need to be documented.

While at it, fix white space around the cpufreq_set_policy() header.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>

Merge branch 'cpufreq/arm/linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm into pm-cpufreq

Pull cpufreq drivers material for v5.1 from Viresh Kumar:

"This contains:

- Minor cleanups for pcc, longhaul, powerenv and speedstep drivers (Yangtao Li).
- Moving configuration data out of mach directory for davinci (Bartosz Golaszewski)."

* 'cpufreq/arm/linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm:
  cpufreq: davinci: move configuration to include/linux/platform_data
  cpufreq: speedstep: convert BUG() to BUG_ON()
  cpufreq: powernv: fix missing check of return value in init_powernv_pstates()
  cpufreq: longhaul: remove unneeded semicolon
  cpufreq: pcc-cpufreq: remove unneeded semicolon

The current iowait boosting mechanism in intel_pstate_update_util()
is quite aggressive, as it goes to the maximum P-state right away,
and may cause excessive amounts of energy to be used, which is not
desirable and arguably isn't necessary too.

Follow commit a5a0809b ("cpufreq: schedutil: Make iowait boost
more energy efficient") that reworked the analogous iowait boost
mechanism in the schedutil governor and make the iowait boosting
in intel_pstate_update_util() work along the same lines.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

There is only one caller of intel_pstate_get_base_pstate() and it is
more straightforward to carry out the computation directly in the
caller, so do that and drop intel_pstate_get_base_pstate().

No intentional changes of behavior.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

After commit 1a4fe38a ("cpufreq: intel_pstate: Remove max/min
fractions to limit performance") the initial value of the pstate local
variable in intel_pstate_max_within_limits() and the initial value of
the max_pstate local variable in intel_pstate_prepare_request() are
both immediately discarded, so initialize both these variables to
their target values upfront.

No intentional changes of behavior.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

Hisilicon chips do not support delivered performance counter register
and reference performance counter register. But the platform can
calculate the real performance using its own method. We reuse the
desired performance register to store the real performance calculated by
the platform. After the platform finished the frequency adjust, it gets
the real performance and writes it into desired performance register. Os
can use it to calculate the real frequency.
Signed-off-by: Xiongfeng Wang <wangxiongfeng2@huawei.com>
[ rjw: Drop unnecessary braces ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

This patch add a helper to get the value of desired performance
register.
Signed-off-by: Xiongfeng Wang <wangxiongfeng2@huawei.com>
[ rjw: More white space ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

The header containing the configuration structure for davinci cpufreq
driver lives in mach-davinci/include/mach/. This is fine for now but
if we want to make davinci part of the multi_v5 build, no code external
to mach-davinci should include machine-specific headers.

Move the configuration structure to include/linux/platform_data.

While we're at it: convert the GPL-2.0 boilerplate to a proper SPDX
license identifier.
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Acked-by: Sekhar Nori <nsekhar@ti.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>

To fix coccinelle WARNING.

WARNING: Use BUG_ON instead of if condition followed by BUG.
Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>

kmalloc() could fail, so insert a check of its return value. And
if it fails, returns -ENOMEM.

And remove (struct pstate_idx_revmap_data *) to fix coccinelle WARNING
by the way.

WARNING: casting value returned by memory allocation function to (struct
pstate_idx_revmap_data *) is useless.
Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>

The semicolon is unneeded, so remove it.
Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>

The semicolon is unneeded, so remove it.
Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>

Double NOT (!!) operation is normally done to convert a non-zero value
to 1 and keep zero as is, but that isn't the requirement in this case.
All we wanted was to make sure that only one of the two routines isn't
set, i.e. either both function pointers are set or both are unset.

This can be done with a single NOT (!) operation as well.
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

The init code path has several exceptions where the driver can
decide not to load.

As CONFIG_X86_INTEL_PSTATE is generally set to Y, the return code is
not reachable.  The initialization code is neither verbose of the
reason why it did choose to prematurely exit, so it is difficult for
a user to determine, on a given platform, why the driver didn't load
properly.

This patch is about reporting to the user the reason/context of why
the driver failed to load.  That is a precious hint when debugging
a platform.
Signed-off-by: Erwan Velu <e.velu@criteo.com>
[ rjw: Subject & changelog, minor fixups ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

Merge branch 'cpufreq/arm/linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm into pm-cpufreq

Pull ARM cpufreq driver updates for v5.1 from Viresh Kumar:

"This pull request contains following changes:

 - New Armada 8k cpufreq driver (Gregory CLEMENT).
 - qcom driver cleanups (Amit Kucheria, Taniya Das, Yangtao Li).
 - s5pv210 driver cleanup (Paweł Chmiel).
 - tegra driver cleanup (Yangtao Li).
 - Minor update to MAINTAINERS file (Baruch Siach)."

* 'cpufreq/arm/linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm:
  cpufreq: qcom-hw: Register an Energy Model
  cpufreq: qcom: Read voltage LUT and populate OPP
  cpufreq: qcom-hw: Move to device_initcall
  cpufreq: tegra124: add missing of_node_put()
  cpufreq: qcom-kryo: make some variables static
  MAINTAINERS: Update the active pm tree for ARM
  cpufreq: ap806: add cpufreq driver for Armada 8K
  MAINTAINERS: add new entries for Armada 8K cpufreq driver
  cpufreq: s5pv210: Defer probe if getting regulators fail
  MAINTAINERS: use common indentation
  PM / OPP: Introduce a power estimation helper
  PM / OPP: Remove unused parameter of _generic_set_opp_clk_only()

Implement the light-weight tear down and bring up helpers to reduce the
amount of work to do on CPU offline/online operation.
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

The cpufreq core doesn't remove the cpufreq policy anymore on CPU
offline operation, rather that happens when the CPU device gets
unregistered from the kernel. This allows faster recovery when the CPU
comes back online. This is also very useful during system wide
suspend/resume where we offline all non-boot CPUs during suspend and
then bring them back on resume.

This commit takes the same idea a step ahead to allow drivers to do
light weight tear-down and bring-up during CPU offline and online
operations.

A new set of callbacks is introduced, online/offline(). online() gets
called when the first CPU of an inactive policy is brought up and
offline() gets called when all the CPUs of a policy are offlined.

The existing init/exit() callback get called on policy
creation/destruction. They also get called instead of online/offline()
callbacks if the online/offline() callbacks aren't provided.

This also moves around some code to get executed only for the new-policy
case going forward.
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

Try and register an Energy Model from qcom-cpufreq-hw to allow
interested sub-systems like the task scheduler to use the provided
information.
Signed-off-by: Matthias Kaehlcke <mka@chromium.org>
[ Viresh: Rebased over cpufreq related changes ]
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>

Add support to read the voltage look up table and populate OPP for all
corresponding CPUS for consumers like the energy model could use the
frequency and voltage from the OPP tables. Also update the logic to not add
duplicate OPPs.
Tested-by: Matthias Kaehlcke <mka@chromium.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Taniya Das <tdas@codeaurora.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>

subsys_initcall causes problems registering the driver as a thermal
cooling device.

If "faster boot" is the main reason for doing subsys_initcall, this
should be handled in the bootloader or another boot constraint
framework.
Signed-off-by: Amit Kucheria <amit.kucheria@linaro.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>

of_cpu_device_node_get() will increase the refcount of device_node,
it is necessary to call of_node_put() at the end to release the
refcount.

Fixes: 9eb15dbb ("cpufreq: Add cpufreq driver for Tegra124")
Cc: <stable@vger.kernel.org> # 4.4+
Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>

The variables are local to the source and do not
need to be in global scope, so make them static.
Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>

The Linaro hosted git tree is no longer active. Update the cpufreq
entry.
Signed-off-by: Baruch Siach <baruch@tkos.co.il>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>

Add cpufreq driver for Marvell AP-806 found on Aramda 8K.
The AP-806 has DFS (Dynamic Frequency Scaling) with coupled
clock domain for two clusters, so this driver will directly
use generic cpufreq-dt driver as backend.

Based on the work of Omri Itach <omrii@marvell.com>.
Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>

This new driver belongs to the mvebu family, update the MAINTAINER file
to document it.
Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>

There is possibility, that when probing driver, regulators are not yet
initialized. In this case we should return EPROBE_DEFER and wait till
they're initialized, since they're required currently for cpufreq driver
to work. Also move regulator initialization code at beginning of probe,
so we can defer as fast as posibble.
Signed-off-by: Paweł Chmiel <pawel.mikolaj.chmiel@gmail.com>
Reviewed-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>

Commit 46e2856b ("cpufreq: Add Kryo CPU scaling driver") slips in
some formatting with spaces instead of tabs, which are used in the common
format for the MAINTAINERS file.

Also update to Ilia's new email address, as Ilia requested.

Fixes: 46e2856b ("cpufreq: Add Kryo CPU scaling driver")
Signed-off-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>

The Energy Model (EM) framework provides an API to let drivers register
the active power of CPUs. The drivers are expected to provide a callback
method which estimates the power consumed by a CPU at each available
performance levels. How exactly this should be implemented, however,
depends on the platform.

On some systems, PM_OPP knows the voltage and frequency at which CPUs
can run. When coupled with the CPU 'capacitance' (as provided by the
'dynamic-power-coefficient' devicetree binding), it is possible to
estimate the dynamic power consumption of a CPU as P = C * V^2 * f, with
C its capacitance and V and f respectively the voltage and frequency of
the OPP. The Intelligent Power Allocator (IPA) thermal governor already
implements that estimation method, in the thermal framework.

However, this power estimation method can be applied to any platform
where all the parameters are known (C, V and f), and not only those
suffering thermal issues. As such, the code implementing this feature
can be re-used to also populate the EM framework now used by EAS.

As a first step, introduce in PM_OPP a helper function which CPUFreq
drivers can use to register into the EM framework. This duplicates the
power estimation done in IPA until it can be migrated to using the EM
framework. This will be done later, once the EM framework has support
for at least all platforms currently supported by IPA.
Signed-off-by: Quentin Perret <quentin.perret@arm.com>
Tested-by: Matthias Kaehlcke <mka@chromium.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>

The previous frequency value isn't getting used in the routine
_generic_set_opp_clk_only(), drop it.
Reviewed-by: Stephen Boyd <sboyd@kernel.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>

It is possible for cpufreq_stats_clear_table() and
cpufreq_stats_record_transition() to get called concurrently and they
will try to update same variables simultaneously and may lead to
corruption of data.

Prevent that with the help of existing spinlock.
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

Freq attribute for "trans_table" is defined right after its callback
(without any blank line between them), but the others are defined
separately later on. Keep this consistent and define all attributes
right after their callbacks.
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

Use the CPUFREQ_IS_COOLING_DEV flag to allow cpufreq core to
automatically register as a thermal cooling device.

This allows removal of boiler plate code from the driver.
Signed-off-by: Amit Kucheria <amit.kucheria@linaro.org>
Acked-by: Sudeep Holla <sudeep.holla@arm.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

Use the CPUFREQ_IS_COOLING_DEV flag to allow cpufreq core to
automatically register as a thermal cooling device.

This allows removal of boiler plate code from the driver.
Signed-off-by: Amit Kucheria <amit.kucheria@linaro.org>
Acked-by: Sudeep Holla <sudeep.holla@arm.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

Use the CPUFREQ_IS_COOLING_DEV flag to allow cpufreq core to
automatically register as a thermal cooling device.

This allows removal of boiler plate code from the driver.
Signed-off-by: Amit Kucheria <amit.kucheria@linaro.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

Use the CPUFREQ_IS_COOLING_DEV flag to allow cpufreq core to
automatically register as a thermal cooling device.

This allows removal of boiler plate code from the driver.
Signed-off-by: Amit Kucheria <amit.kucheria@linaro.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>