Merge tag 'pm-5.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
"These clean up and rework the PM QoS API, address a suspend-to-idle
wakeup regression on some ACPI-based platforms, clean up and extend a
few cpuidle drivers, update multiple cpufreq drivers and cpufreq
documentation, and fix a number of issues in devfreq and several other
things all over.

Specifics:

- Clean up and rework the PM QoS API to simplify the code and reduce
the size of it (Rafael Wysocki).

- Fix a suspend-to-idle wakeup regression on Dell XPS13 9370 and
similar platforms where the USB plug/unplug events are handled by
the EC (Rafael Wysocki).

- CLean up the intel_idle and PSCI cpuidle drivers (Rafael Wysocki,
Ulf Hansson).

- Extend the haltpoll cpuidle driver so that it can be forced to run
on some systems where it refused to load (Maciej Szmigiero).

- Convert several cpufreq documents to the .rst format and move the
legacy driver documentation into one common file (Mauro Carvalho
Chehab, Rafael Wysocki).

- Update several cpufreq drivers:

* Extend and fix the imx-cpufreq-dt driver (Anson Huang).

* Improve the -EPROBE_DEFER handling and fix unwanted CPU
overclocking on i.MX6ULL in imx6q-cpufreq (Anson Huang,
Christoph Niedermaier).

* Add support for Krait based SoCs to the qcom driver (Ansuel
Smith).

* Add support for OPP_PLUS to ti-cpufreq (Lokesh Vutla).

* Add platform specific intermediate callbacks support to
cpufreq-dt and update the imx6q driver (Peng Fan).

* Simplify and consolidate some pieces of the intel_pstate
driver and update its documentation (Rafael Wysocki, Alex
Hung).

- Fix several devfreq issues:

* Remove unneeded extern keyword from a devfreq header file and
use the DEVFREQ_GOV_UPDATE_INTERNAL event name instead of
DEVFREQ_GOV_INTERNAL (Chanwoo Choi).

* Fix the handling of dev_pm_qos_remove_request() result
(Leonard Crestez).

* Use constant name for userspace governor (Pierre Kuo).

* Get rid of doc warnings and fix a typo (Christophe JAILLET).

- Use built-in RCU list checking in some places in the PM core to
avoid false-positive RCU usage warnings (Madhuparna Bhowmik).

- Add explicit READ_ONCE()/WRITE_ONCE() annotations to low-level PM
QoS routines (Qian Cai).

- Fix removal of wakeup sources to avoid NULL pointer dereferences in
a corner case (Neeraj Upadhyay).

- Clean up the handling of hibernate compat ioctls and fix the
related documentation (Eric Biggers).

- Update the idle_inject power capping driver to use variable-length
arrays instead of zero-length arrays (Gustavo Silva).

- Fix list format in a PM QoS document (Randy Dunlap).

- Make the cpufreq stats module use scnprintf() to avoid potential
buffer overflows (Takashi Iwai).

- Add pm_runtime_get_if_active() to PM-runtime API (Sakari Ailus).

- Allow no domain-idle-states DT property in generic PM domains (Ulf
Hansson).

- Fix a broken y-axis scale in the intel_pstate_tracer utility (Doug
Smythies)"

* tag 'pm-5.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (78 commits)
cpufreq: intel_pstate: Simplify intel_pstate_cpu_init()
tools/power/x86/intel_pstate_tracer: fix a broken y-axis scale
ACPI: PM: s2idle: Refine active GPEs check
ACPICA: Allow acpi_any_gpe_status_set() to skip one GPE
PM: sleep: wakeup: Skip wakeup_source_sysfs_remove() if device is not there
PM / devfreq: Get rid of some doc warnings
PM / devfreq: Fix handling dev_pm_qos_remove_request result
PM / devfreq: Fix a typo in a comment
PM / devfreq: Change to DEVFREQ_GOV_UPDATE_INTERVAL event name
PM / devfreq: Remove unneeded extern keyword
PM / devfreq: Use constant name of userspace governor
ACPI: PM: s2idle: Fix comment in acpi_s2idle_prepare_late()
cpufreq: qcom: Add support for krait based socs
cpufreq: imx6q-cpufreq: Improve the logic of -EPROBE_DEFER handling
cpufreq: Use scnprintf() for avoiding potential buffer overflow
cpuidle: psci: Split psci_dt_cpu_init_idle()
PM / Domains: Allow no domain-idle-states DT property in genpd when parsing
PM / hibernate: Remove unnecessary compat ioctl overrides
PM: hibernate: fix docs for ioctls that return loff_t via pointer
Documentation: intel_pstate: update links for references
...

Documentation/admin-guide/pm/cpufreq_drivers.rst

···
+.. SPDX-License-Identifier: GPL-2.0
+
+=======================================================
+Legacy Documentation of CPU Performance Scaling Drivers
+=======================================================
+
+Included below are historic documents describing assorted
+:doc:`CPU performance scaling <cpufreq>` drivers.  They are reproduced verbatim,
+with the original white space formatting and indentation preserved, except for
+the added leading space character in every line of text.
+
+
+AMD PowerNow! Drivers
+=====================
+
+::
+
+ PowerNow! and Cool'n'Quiet are AMD names for frequency
+ management capabilities in AMD processors. As the hardware
+ implementation changes in new generations of the processors,
+ there is a different cpu-freq driver for each generation.
+
+ Note that the driver's will not load on the "wrong" hardware,
+ so it is safe to try each driver in turn when in doubt as to
+ which is the correct driver.
+
+ Note that the functionality to change frequency (and voltage)
+ is not available in all processors. The drivers will refuse
+ to load on processors without this capability. The capability
+ is detected with the cpuid instruction.
+
+ The drivers use BIOS supplied tables to obtain frequency and
+ voltage information appropriate for a particular platform.
+ Frequency transitions will be unavailable if the BIOS does
+ not supply these tables.
+
+ 6th Generation: powernow-k6
+
+ 7th Generation: powernow-k7: Athlon, Duron, Geode.
+
+ 8th Generation: powernow-k8: Athlon, Athlon 64, Opteron, Sempron.
+ Documentation on this functionality in 8th generation processors
+ is available in the "BIOS and Kernel Developer's Guide", publication
+ 26094, in chapter 9, available for download from www.amd.com.
+
+ BIOS supplied data, for powernow-k7 and for powernow-k8, may be
+ from either the PSB table or from ACPI objects. The ACPI support
+ is only available if the kernel config sets CONFIG_ACPI_PROCESSOR.
+ The powernow-k8 driver will attempt to use ACPI if so configured,
+ and fall back to PST if that fails.
+ The powernow-k7 driver will try to use the PSB support first, and
+ fall back to ACPI if the PSB support fails. A module parameter,
+ acpi_force, is provided to force ACPI support to be used instead
+ of PSB support.
+
+
+``cpufreq-nforce2``
+===================
+
+::
+
+ The cpufreq-nforce2 driver changes the FSB on nVidia nForce2 platforms.
+
+ This works better than on other platforms, because the FSB of the CPU
+ can be controlled independently from the PCI/AGP clock.
+
+ The module has two options:
+
+ 	fid: 	 multiplier * 10 (for example 8.5 = 85)
+ 	min_fsb: minimum FSB
+
+ If not set, fid is calculated from the current CPU speed and the FSB.
+ min_fsb defaults to FSB at boot time - 50 MHz.
+
+ IMPORTANT: The available range is limited downwards!
+            Also the minimum available FSB can differ, for systems
+            booting with 200 MHz, 150 should always work.
+
+
+``pcc-cpufreq``
+===============
+
+::
+
+ /*
+  *  pcc-cpufreq.txt - PCC interface documentation
+  *
+  *  Copyright (C) 2009 Red Hat, Matthew Garrett <[e-mail]>
+  *  Copyright (C) 2009 Hewlett-Packard Development Company, L.P.
+  *      Nagananda Chumbalkar <[e-mail]>
+  */
+
+
+ 			Processor Clocking Control Driver
+ 			---------------------------------
+
+ Contents:
+ ---------
+ 1.	Introduction
+ 1.1	PCC interface
+ 1.1.1	Get Average Frequency
+ 1.1.2	Set Desired Frequency
+ 1.2	Platforms affected
+ 2.	Driver and /sys details
+ 2.1	scaling_available_frequencies
+ 2.2	cpuinfo_transition_latency
+ 2.3	cpuinfo_cur_freq
+ 2.4	related_cpus
+ 3.	Caveats
+
+ 1. Introduction:
+ ----------------
+ Processor Clocking Control (PCC) is an interface between the platform
+ firmware and OSPM. It is a mechanism for coordinating processor
+ performance (ie: frequency) between the platform firmware and the OS.
+
+ The PCC driver (pcc-cpufreq) allows OSPM to take advantage of the PCC
+ interface.
+
+ OS utilizes the PCC interface to inform platform firmware what frequency the
+ OS wants for a logical processor. The platform firmware attempts to achieve
+ the requested frequency. If the request for the target frequency could not be
+ satisfied by platform firmware, then it usually means that power budget
+ conditions are in place, and "power capping" is taking place.
+
+ 1.1 PCC interface:
+ ------------------
+ The complete PCC specification is available here:
+ https://acpica.org/sites/acpica/files/Processor-Clocking-Control-v1p0.pdf
+
+ PCC relies on a shared memory region that provides a channel for communication
+ between the OS and platform firmware. PCC also implements a "doorbell" that
+ is used by the OS to inform the platform firmware that a command has been
+ sent.
+
+ The ACPI PCCH() method is used to discover the location of the PCC shared
+ memory region. The shared memory region header contains the "command" and
+ "status" interface. PCCH() also contains details on how to access the platform
+ doorbell.
+
+ The following commands are supported by the PCC interface:
+ * Get Average Frequency
+ * Set Desired Frequency
+
+ The ACPI PCCP() method is implemented for each logical processor and is
+ used to discover the offsets for the input and output buffers in the shared
+ memory region.
+
+ When PCC mode is enabled, the platform will not expose processor performance
+ or throttle states (_PSS, _TSS and related ACPI objects) to OSPM. Therefore,
+ the native P-state driver (such as acpi-cpufreq for Intel, powernow-k8 for
+ AMD) will not load.
+
+ However, OSPM remains in control of policy. The governor (eg: "ondemand")
+ computes the required performance for each processor based on server workload.
+ The PCC driver fills in the command interface, and the input buffer and
+ communicates the request to the platform firmware. The platform firmware is
+ responsible for delivering the requested performance.
+
+ Each PCC command is "global" in scope and can affect all the logical CPUs in
+ the system. Therefore, PCC is capable of performing "group" updates. With PCC
+ the OS is capable of getting/setting the frequency of all the logical CPUs in
+ the system with a single call to the BIOS.
+
+ 1.1.1 Get Average Frequency:
+ ----------------------------
+ This command is used by the OSPM to query the running frequency of the
+ processor since the last time this command was completed. The output buffer
+ indicates the average unhalted frequency of the logical processor expressed as
+ a percentage of the nominal (ie: maximum) CPU frequency. The output buffer
+ also signifies if the CPU frequency is limited by a power budget condition.
+
+ 1.1.2 Set Desired Frequency:
+ ----------------------------
+ This command is used by the OSPM to communicate to the platform firmware the
+ desired frequency for a logical processor. The output buffer is currently
+ ignored by OSPM. The next invocation of "Get Average Frequency" will inform
+ OSPM if the desired frequency was achieved or not.
+
+ 1.2 Platforms affected:
+ -----------------------
+ The PCC driver will load on any system where the platform firmware:
+ * supports the PCC interface, and the associated PCCH() and PCCP() methods
+ * assumes responsibility for managing the hardware clocking controls in order
+ to deliver the requested processor performance
+
+ Currently, certain HP ProLiant platforms implement the PCC interface. On those
+ platforms PCC is the "default" choice.
+
+ However, it is possible to disable this interface via a BIOS setting. In
+ such an instance, as is also the case on platforms where the PCC interface
+ is not implemented, the PCC driver will fail to load silently.
+
+ 2. Driver and /sys details:
+ ---------------------------
+ When the driver loads, it merely prints the lowest and the highest CPU
+ frequencies supported by the platform firmware.
+
+ The PCC driver loads with a message such as:
+ pcc-cpufreq: (v1.00.00) driver loaded with frequency limits: 1600 MHz, 2933
+ MHz
+
+ This means that the OPSM can request the CPU to run at any frequency in
+ between the limits (1600 MHz, and 2933 MHz) specified in the message.
+
+ Internally, there is no need for the driver to convert the "target" frequency
+ to a corresponding P-state.
+
+ The VERSION number for the driver will be of the format v.xy.ab.
+ eg: 1.00.02
+    ----- --
+     |    |
+     |    -- this will increase with bug fixes/enhancements to the driver
+     |-- this is the version of the PCC specification the driver adheres to
+
+
+ The following is a brief discussion on some of the fields exported via the
+ /sys filesystem and how their values are affected by the PCC driver:
+
+ 2.1 scaling_available_frequencies:
+ ----------------------------------
+ scaling_available_frequencies is not created in /sys. No intermediate
+ frequencies need to be listed because the BIOS will try to achieve any
+ frequency, within limits, requested by the governor. A frequency does not have
+ to be strictly associated with a P-state.
+
+ 2.2 cpuinfo_transition_latency:
+ -------------------------------
+ The cpuinfo_transition_latency field is 0. The PCC specification does
+ not include a field to expose this value currently.
+
+ 2.3 cpuinfo_cur_freq:
+ ---------------------
+ A) Often cpuinfo_cur_freq will show a value different than what is declared
+ in the scaling_available_frequencies or scaling_cur_freq, or scaling_max_freq.
+ This is due to "turbo boost" available on recent Intel processors. If certain
+ conditions are met the BIOS can achieve a slightly higher speed than requested
+ by OSPM. An example:
+
+ scaling_cur_freq	: 2933000
+ cpuinfo_cur_freq	: 3196000
+
+ B) There is a round-off error associated with the cpuinfo_cur_freq value.
+ Since the driver obtains the current frequency as a "percentage" (%) of the
+ nominal frequency from the BIOS, sometimes, the values displayed by
+ scaling_cur_freq and cpuinfo_cur_freq may not match. An example:
+
+ scaling_cur_freq	: 1600000
+ cpuinfo_cur_freq	: 1583000
+
+ In this example, the nominal frequency is 2933 MHz. The driver obtains the
+ current frequency, cpuinfo_cur_freq, as 54% of the nominal frequency:
+
+ 	54% of 2933 MHz = 1583 MHz
+
+ Nominal frequency is the maximum frequency of the processor, and it usually
+ corresponds to the frequency of the P0 P-state.
+
+ 2.4 related_cpus:
+ -----------------
+ The related_cpus field is identical to affected_cpus.
+
+ affected_cpus	: 4
+ related_cpus	: 4
+
+ Currently, the PCC driver does not evaluate _PSD. The platforms that support
+ PCC do not implement SW_ALL. So OSPM doesn't need to perform any coordination
+ to ensure that the same frequency is requested of all dependent CPUs.
+
+ 3. Caveats:
+ -----------
+ The "cpufreq_stats" module in its present form cannot be loaded and
+ expected to work with the PCC driver. Since the "cpufreq_stats" module
+ provides information wrt each P-state, it is not applicable to the PCC driver.

Documentation/admin-guide/pm/cpuidle.rst

···
 The power management quality of service (PM QoS) framework in the Linux kernel
 allows kernel code and user space processes to set constraints on various
 energy-efficiency features of the kernel to prevent performance from dropping
-below a required level.  The PM QoS constraints can be set globally, in
-predefined categories referred to as PM QoS classes, or against individual
-devices.
+below a required level.
 
 CPU idle time management can be affected by PM QoS in two ways, through the
-global constraint in the ``PM_QOS_CPU_DMA_LATENCY`` class and through the
-resume latency constraints for individual CPUs.  Kernel code (e.g. device
-drivers) can set both of them with the help of special internal interfaces
-provided by the PM QoS framework.  User space can modify the former by opening
-the :file:`cpu_dma_latency` special device file under :file:`/dev/` and writing
-a binary value (interpreted as a signed 32-bit integer) to it.  In turn, the
-resume latency constraint for a CPU can be modified by user space by writing a
-string (representing a signed 32-bit integer) to the
-:file:`power/pm_qos_resume_latency_us` file under
+global CPU latency limit and through the resume latency constraints for
+individual CPUs.  Kernel code (e.g. device drivers) can set both of them with
+the help of special internal interfaces provided by the PM QoS framework.  User
+space can modify the former by opening the :file:`cpu_dma_latency` special
+device file under :file:`/dev/` and writing a binary value (interpreted as a
+signed 32-bit integer) to it.  In turn, the resume latency constraint for a CPU
+can be modified from user space by writing a string (representing a signed
+32-bit integer) to the :file:`power/pm_qos_resume_latency_us` file under
 :file:`/sys/devices/system/cpu/cpu<N>/` in ``sysfs``, where the CPU number
 ``<N>`` is allocated at the system initialization time.  Negative values
 will be rejected in both cases and, also in both cases, the written integer
···
 The requested value is not automatically applied as a new constraint, however,
 as it may be less restrictive (greater in this particular case) than another
 constraint previously requested by someone else.  For this reason, the PM QoS
-framework maintains a list of requests that have been made so far in each
-global class and for each device, aggregates them and applies the effective
-(minimum in this particular case) value as the new constraint.
+framework maintains a list of requests that have been made so far for the
+global CPU latency limit and for each individual CPU, aggregates them and
+applies the effective (minimum in this particular case) value as the new
+constraint.
 
 In fact, opening the :file:`cpu_dma_latency` special device file causes a new
-PM QoS request to be created and added to the priority list of requests in the
-``PM_QOS_CPU_DMA_LATENCY`` class and the file descriptor coming from the
-"open" operation represents that request.  If that file descriptor is then
-used for writing, the number written to it will be associated with the PM QoS
-request represented by it as a new requested constraint value.  Next, the
-priority list mechanism will be used to determine the new effective value of
-the entire list of requests and that effective value will be set as a new
-constraint.  Thus setting a new requested constraint value will only change the
-real constraint if the effective "list" value is affected by it.  In particular,
-for the ``PM_QOS_CPU_DMA_LATENCY`` class it only affects the real constraint if
-it is the minimum of the requested constraints in the list.  The process holding
-a file descriptor obtained by opening the :file:`cpu_dma_latency` special device
-file controls the PM QoS request associated with that file descriptor, but it
-controls this particular PM QoS request only.
+PM QoS request to be created and added to a global priority list of CPU latency
+limit requests and the file descriptor coming from the "open" operation
+represents that request.  If that file descriptor is then used for writing, the
+number written to it will be associated with the PM QoS request represented by
+it as a new requested limit value.  Next, the priority list mechanism will be
+used to determine the new effective value of the entire list of requests and
+that effective value will be set as a new CPU latency limit.  Thus requesting a
+new limit value will only change the real limit if the effective "list" value is
+affected by it, which is the case if it is the minimum of the requested values
+in the list.
+
+The process holding a file descriptor obtained by opening the
+:file:`cpu_dma_latency` special device file controls the PM QoS request
+associated with that file descriptor, but it controls this particular PM QoS
+request only.
 
 Closing the :file:`cpu_dma_latency` special device file or, more precisely, the
 file descriptor obtained while opening it, causes the PM QoS request associated
-with that file descriptor to be removed from the ``PM_QOS_CPU_DMA_LATENCY``
-class priority list and destroyed.  If that happens, the priority list mechanism
-will be used, again, to determine the new effective value for the whole list
-and that value will become the new real constraint.
+with that file descriptor to be removed from the global priority list of CPU
+latency limit requests and destroyed.  If that happens, the priority list
+mechanism will be used again, to determine the new effective value for the whole
+list and that value will become the new limit.
 
 In turn, for each CPU there is one resume latency PM QoS request associated with
 the :file:`power/pm_qos_resume_latency_us` file under
···
 (there may be other requests coming from kernel code in that list).
 
 CPU idle time governors are expected to regard the minimum of the global
-effective ``PM_QOS_CPU_DMA_LATENCY`` class constraint and the effective
-resume latency constraint for the given CPU as the upper limit for the exit
-latency of the idle states they can select for that CPU.  They should never
-select any idle states with exit latency beyond that limit.
+(effective) CPU latency limit and the effective resume latency constraint for
+the given CPU as the upper limit for the exit latency of the idle states that
+they are allowed to select for that CPU.  They should never select any idle
+states with exit latency beyond that limit.
 
 
 Idle States Control Via Kernel Command Line

Documentation/admin-guide/pm/intel_pstate.rst

···
 ==========
 
 .. [1] Kristen Accardi, *Balancing Power and Performance in the Linux Kernel*,
-       http://events.linuxfoundation.org/sites/events/files/slides/LinuxConEurope_2015.pdf
+       https://events.static.linuxfound.org/sites/events/files/slides/LinuxConEurope_2015.pdf
 
 .. [2] *Intel® 64 and IA-32 Architectures Software Developer’s Manual Volume 3: System Programming Guide*,
-       http://www.intel.com/content/www/us/en/architecture-and-technology/64-ia-32-architectures-software-developer-system-programming-manual-325384.html
+       https://www.intel.com/content/www/us/en/architecture-and-technology/64-ia-32-architectures-software-developer-system-programming-manual-325384.html
 
 .. [3] *Advanced Configuration and Power Interface Specification*,
        https://uefi.org/sites/default/files/resources/ACPI_6_3_final_Jan30.pdf

Documentation/admin-guide/pm/working-state.rst

···
    intel_idle
    cpufreq
    intel_pstate
+   cpufreq_drivers
    intel_epb

Documentation/cpu-freq/amd-powernow.txt

···
-
-PowerNow! and Cool'n'Quiet are AMD names for frequency
-management capabilities in AMD processors. As the hardware
-implementation changes in new generations of the processors,
-there is a different cpu-freq driver for each generation.
-
-Note that the driver's will not load on the "wrong" hardware,
-so it is safe to try each driver in turn when in doubt as to
-which is the correct driver.
-
-Note that the functionality to change frequency (and voltage)
-is not available in all processors. The drivers will refuse
-to load on processors without this capability. The capability
-is detected with the cpuid instruction.
-
-The drivers use BIOS supplied tables to obtain frequency and
-voltage information appropriate for a particular platform.
-Frequency transitions will be unavailable if the BIOS does
-not supply these tables.
-
-6th Generation: powernow-k6
-
-7th Generation: powernow-k7: Athlon, Duron, Geode.
-
-8th Generation: powernow-k8: Athlon, Athlon 64, Opteron, Sempron.
-Documentation on this functionality in 8th generation processors
-is available in the "BIOS and Kernel Developer's Guide", publication
-26094, in chapter 9, available for download from www.amd.com. 
-
-BIOS supplied data, for powernow-k7 and for powernow-k8, may be
-from either the PSB table or from ACPI objects. The ACPI support
-is only available if the kernel config sets CONFIG_ACPI_PROCESSOR.
-The powernow-k8 driver will attempt to use ACPI if so configured,
-and fall back to PST if that fails.
-The powernow-k7 driver will try to use the PSB support first, and
-fall back to ACPI if the PSB support fails. A module parameter,
-acpi_force, is provided to force ACPI support to be used instead 
-of PSB support.

Documentation/cpu-freq/core.txt Documentation/cpu-freq/core.rst

···
-     CPU frequency and voltage scaling code in the Linux(TM) kernel
+.. SPDX-License-Identifier: GPL-2.0
 
+=============================================================
+General description of the CPUFreq core and CPUFreq notifiers
+=============================================================
 
-		         L i n u x    C P U F r e q
+Authors:
+	- Dominik Brodowski  <[e-mail]>
+	- David Kimdon <[e-mail]>
+	- Rafael J. Wysocki <[e-mail]>
+	- Viresh Kumar <[e-mail]>
 
-			  C P U F r e q    C o r e
+.. Contents:
 
-
-		    Dominik Brodowski  <[e-mail]>
-		     David Kimdon <[e-mail]>
-		Rafael J. Wysocki <[e-mail]>
-		   Viresh Kumar <[e-mail]>
-
-
-
-   Clock scaling allows you to change the clock speed of the CPUs on the
-    fly. This is a nice method to save battery power, because the lower
-            the clock speed, the less power the CPU consumes.
-
-
-Contents:
----------
-1.  CPUFreq core and interfaces
-2.  CPUFreq notifiers
-3.  CPUFreq Table Generation with Operating Performance Point (OPP)
+   1.  CPUFreq core and interfaces
+   2.  CPUFreq notifiers
+   3.  CPUFreq Table Generation with Operating Performance Point (OPP)
 
 1. General Information
-=======================
+======================
 
 The CPUFreq core code is located in drivers/cpufreq/cpufreq.c. This
 cpufreq code offers a standardized interface for the CPUFreq
···
 CPUFREQ_CREATE_POLICY when the policy is first created and it is
 CPUFREQ_REMOVE_POLICY when the policy is removed.
 
-The third argument, a void *pointer, points to a struct cpufreq_policy
+The third argument, a ``void *pointer``, points to a struct cpufreq_policy
 consisting of several values, including min, max (the lower and upper
 frequencies (in kHz) of the new policy).
 
···
 
 The third argument is a struct cpufreq_freqs with the following
 values:
-cpu	- number of the affected CPU
-old	- old frequency
-new	- new frequency
-flags	- flags of the cpufreq driver
+
+=====	===========================
+cpu	number of the affected CPU
+old	old frequency
+new	new frequency
+flags	flags of the cpufreq driver
+=====	===========================
 
 3. CPUFreq Table Generation with Operating Performance Point (OPP)
 ==================================================================
···
 	the OPP layer's internal information about the available frequencies
 	into a format readily providable to cpufreq.
 
-	WARNING: Do not use this function in interrupt context.
+	.. Warning::
 
-	Example:
+	   Do not use this function in interrupt context.
+
+	Example::
+
 	 soc_pm_init()
 	 {
 		/* Do things */
···
 		/* Do other things */
 	 }
 
-	NOTE: This function is available only if CONFIG_CPU_FREQ is enabled in
-	addition to CONFIG_PM_OPP.
+	.. note::
 
-dev_pm_opp_free_cpufreq_table - Free up the table allocated by dev_pm_opp_init_cpufreq_table
+	   This function is available only if CONFIG_CPU_FREQ is enabled in
+	   addition to CONFIG_PM_OPP.
+
+dev_pm_opp_free_cpufreq_table
+	Free up the table allocated by dev_pm_opp_init_cpufreq_table

Documentation/cpu-freq/cpu-drivers.txt Documentation/cpu-freq/cpu-drivers.rst

···
-     CPU frequency and voltage scaling code in the Linux(TM) kernel
+.. SPDX-License-Identifier: GPL-2.0
+
+===============================================
+How to Implement a new CPUFreq Processor Driver
+===============================================
+
+Authors:
 
 
-		         L i n u x    C P U F r e q
+	- Dominik Brodowski  <[e-mail]>
+	- Rafael J. Wysocki <[e-mail]>
+	- Viresh Kumar <[e-mail]>
 
-			   C P U   D r i v e r s 
+.. Contents
 
-		       - information for developers -
-
-
-		    Dominik Brodowski  <[e-mail]>
-		Rafael J. Wysocki <[e-mail]>
-		   Viresh Kumar <[e-mail]>
-
-
-
-   Clock scaling allows you to change the clock speed of the CPUs on the
-    fly. This is a nice method to save battery power, because the lower
-            the clock speed, the less power the CPU consumes.
-
-
-Contents:
----------
-1.   What To Do?
-1.1  Initialization
-1.2  Per-CPU Initialization
-1.3  verify
-1.4  target/target_index or setpolicy?
-1.5  target/target_index
-1.6  setpolicy
-1.7  get_intermediate and target_intermediate
-2.   Frequency Table Helpers
+   1.   What To Do?
+   1.1  Initialization
+   1.2  Per-CPU Initialization
+   1.3  verify
+   1.4  target/target_index or setpolicy?
+   1.5  target/target_index
+   1.6  setpolicy
+   1.7  get_intermediate and target_intermediate
+   2.   Frequency Table Helpers
 
 
 
···
 chipset. If so, register a struct cpufreq_driver with the CPUfreq core
 using cpufreq_register_driver()
 
-What shall this struct cpufreq_driver contain? 
+What shall this struct cpufreq_driver contain?
 
  .name - The name of this driver.
 
···
 cpufreq driver registers itself, the per-policy initialization function
 cpufreq_driver.init is called if no cpufreq policy existed for the CPU.
 Note that the .init() and .exit() routines are called only once for the
-policy and not for each CPU managed by the policy. It takes a struct
-cpufreq_policy *policy as argument. What to do now?
+policy and not for each CPU managed by the policy. It takes a ``struct
+cpufreq_policy *policy`` as argument. What to do now?
 
 If necessary, activate the CPUfreq support on your CPU.
 
 Then, the driver must fill in the following values:
 
-policy->cpuinfo.min_freq _and_
-policy->cpuinfo.max_freq -	the minimum and maximum frequency 
-				(in kHz) which is supported by 
-				this CPU
-policy->cpuinfo.transition_latency   the time it takes on this CPU to
-				switch between two frequencies in
-				nanoseconds (if appropriate, else
-				specify CPUFREQ_ETERNAL)
-
-policy->cur			The current operating frequency of
-				this CPU (if appropriate)
-policy->min, 
-policy->max, 
-policy->policy and, if necessary,
-policy->governor		must contain the "default policy" for
-				this CPU. A few moments later,
-				cpufreq_driver.verify and either
-				cpufreq_driver.setpolicy or
-				cpufreq_driver.target/target_index is called
-				with these values.
-policy->cpus			Update this with the masks of the
-				(online + offline) CPUs that do DVFS
-				along with this CPU (i.e.  that share
-				clock/voltage rails with it).
++-----------------------------------+--------------------------------------+
+|policy->cpuinfo.min_freq _and_	    |					   |
+|policy->cpuinfo.max_freq	    | the minimum and maximum frequency	   |
+|				    | (in kHz) which is supported by	   |
+|				    | this CPU				   |
++-----------------------------------+--------------------------------------+
+|policy->cpuinfo.transition_latency | the time it takes on this CPU to	   |
+|				    | switch between two frequencies in	   |
+|				    | nanoseconds (if appropriate, else	   |
+|				    | specify CPUFREQ_ETERNAL)		   |
++-----------------------------------+--------------------------------------+
+|policy->cur			    | The current operating frequency of   |
+|				    | this CPU (if appropriate)		   |
++-----------------------------------+--------------------------------------+
+|policy->min,			    |					   |
+|policy->max,			    |					   |
+|policy->policy and, if necessary,  |					   |
+|policy->governor		    | must contain the "default policy" for|
+|				    | this CPU. A few moments later,       |
+|				    | cpufreq_driver.verify and either     |
+|				    | cpufreq_driver.setpolicy or          |
+|				    | cpufreq_driver.target/target_index is|
+|				    | called with these values.		   |
++-----------------------------------+--------------------------------------+
+|policy->cpus			    | Update this with the masks of the	   |
+|				    | (online + offline) CPUs that do DVFS |
+|				    | along with this CPU (i.e.  that share|
+|				    | clock/voltage rails with it).	   |
++-----------------------------------+--------------------------------------+
 
 For setting some of these values (cpuinfo.min[max]_freq, policy->min[max]), the
 frequency table helpers might be helpful. See the section 2 for more information
···
 When the user decides a new policy (consisting of
 "policy,governor,min,max") shall be set, this policy must be validated
 so that incompatible values can be corrected. For verifying these
-values cpufreq_verify_within_limits(struct cpufreq_policy *policy,
-unsigned int min_freq, unsigned int max_freq) function might be helpful.
+values cpufreq_verify_within_limits(``struct cpufreq_policy *policy``,
+``unsigned int min_freq``, ``unsigned int max_freq``) function might be helpful.
 See section 2 for details on frequency table helpers.
 
 You need to make sure that at least one valid frequency (or operating
···
 1.4 target or target_index or setpolicy or fast_switch?
 -------------------------------------------------------
 
-Most cpufreq drivers or even most cpu frequency scaling algorithms 
+Most cpufreq drivers or even most cpu frequency scaling algorithms
 only allow the CPU frequency to be set to predefined fixed values. For
 these, you use the ->target(), ->target_index() or ->fast_switch()
 callbacks.
···
 1.5. target/target_index
 ------------------------
 
-The target_index call has two arguments: struct cpufreq_policy *policy,
-and unsigned int index (into the exposed frequency table).
+The target_index call has two arguments: ``struct cpufreq_policy *policy``,
+and ``unsigned int`` index (into the exposed frequency table).
 
 The CPUfreq driver must set the new frequency when called here. The
 actual frequency must be determined by freq_table[index].frequency.
···
 It should always restore to earlier frequency (i.e. policy->restore_freq) in
 case of errors, even if we switched to intermediate frequency earlier.
 
-Deprecated:
+Deprecated
 ----------
-The target call has three arguments: struct cpufreq_policy *policy,
+The target call has three arguments: ``struct cpufreq_policy *policy``,
 unsigned int target_frequency, unsigned int relation.
 
 The CPUfreq driver must set the new frequency when called here. The
···
 this callback isn't allowed. This callback must be highly optimized to
 do switching as fast as possible.
 
-This function has two arguments: struct cpufreq_policy *policy and
-unsigned int target_frequency.
+This function has two arguments: ``struct cpufreq_policy *policy`` and
+``unsigned int target_frequency``.
 
 
 1.7 setpolicy
 -------------
 
-The setpolicy call only takes a struct cpufreq_policy *policy as
+The setpolicy call only takes a ``struct cpufreq_policy *policy`` as
 argument. You need to set the lower limit of the in-processor or
 in-chipset dynamic frequency switching to policy->min, the upper limit
 to policy->max, and -if supported- select a performance-oriented
···
 
 cpufreq_for_each_valid_entry(pos, table) - iterates over all entries,
 excluding CPUFREQ_ENTRY_INVALID frequencies.
-Use arguments "pos" - a cpufreq_frequency_table * as a loop cursor and
-"table" - the cpufreq_frequency_table * you want to iterate over.
+Use arguments "pos" - a ``cpufreq_frequency_table *`` as a loop cursor and
+"table" - the ``cpufreq_frequency_table *`` you want to iterate over.
 
-For example:
+For example::
 
 	struct cpufreq_frequency_table *pos, *driver_freq_table;
 

Documentation/cpu-freq/cpufreq-nforce2.txt

···
-
-The cpufreq-nforce2 driver changes the FSB on nVidia nForce2 platforms.
-
-This works better than on other platforms, because the FSB of the CPU
-can be controlled independently from the PCI/AGP clock.
-
-The module has two options:
-
-	fid: 	 multiplier * 10 (for example 8.5 = 85)
-	min_fsb: minimum FSB
-
-If not set, fid is calculated from the current CPU speed and the FSB.
-min_fsb defaults to FSB at boot time - 50 MHz.
-
-IMPORTANT: The available range is limited downwards!
-           Also the minimum available FSB can differ, for systems 
-           booting with 200 MHz, 150 should always work.
-
-

Documentation/cpu-freq/cpufreq-stats.rst

···
+.. SPDX-License-Identifier: GPL-2.0
+
+==========================================
+General Description of sysfs CPUFreq Stats
+==========================================
+
+information for users
+
+
+Author: Venkatesh Pallipadi <[e-mail]>
+
+.. Contents
+
+   1. Introduction
+   2. Statistics Provided (with example)
+   3. Configuring cpufreq-stats
+
+
+1. Introduction
+===============
+
+cpufreq-stats is a driver that provides CPU frequency statistics for each CPU.
+These statistics are provided in /sysfs as a bunch of read_only interfaces. This
+interface (when configured) will appear in a separate directory under cpufreq
+in /sysfs (<sysfs root>/devices/system/cpu/cpuX/cpufreq/stats/) for each CPU.
+Various statistics will form read_only files under this directory.
+
+This driver is designed to be independent of any particular cpufreq_driver
+that may be running on your CPU. So, it will work with any cpufreq_driver.
+
+
+2. Statistics Provided (with example)
+=====================================
+
+cpufreq stats provides following statistics (explained in detail below).
+
+-  time_in_state
+-  total_trans
+-  trans_table
+
+All the statistics will be from the time the stats driver has been inserted
+(or the time the stats were reset) to the time when a read of a particular
+statistic is done. Obviously, stats driver will not have any information
+about the frequency transitions before the stats driver insertion.
+
+::
+
+    <mysystem>:/sys/devices/system/cpu/cpu0/cpufreq/stats # ls -l
+    total 0
+    drwxr-xr-x  2 root root    0 May 14 16:06 .
+    drwxr-xr-x  3 root root    0 May 14 15:58 ..
+    --w-------  1 root root 4096 May 14 16:06 reset
+    -r--r--r--  1 root root 4096 May 14 16:06 time_in_state
+    -r--r--r--  1 root root 4096 May 14 16:06 total_trans
+    -r--r--r--  1 root root 4096 May 14 16:06 trans_table
+
+- **reset**
+
+Write-only attribute that can be used to reset the stat counters. This can be
+useful for evaluating system behaviour under different governors without the
+need for a reboot.
+
+- **time_in_state**
+
+This gives the amount of time spent in each of the frequencies supported by
+this CPU. The cat output will have "<frequency> <time>" pair in each line, which
+will mean this CPU spent <time> usertime units of time at <frequency>. Output
+will have one line for each of the supported frequencies. usertime units here
+is 10mS (similar to other time exported in /proc).
+
+::
+
+    <mysystem>:/sys/devices/system/cpu/cpu0/cpufreq/stats # cat time_in_state
+    3600000 2089
+    3400000 136
+    3200000 34
+    3000000 67
+    2800000 172488
+
+
+- **total_trans**
+
+This gives the total number of frequency transitions on this CPU. The cat
+output will have a single count which is the total number of frequency
+transitions.
+
+::
+
+    <mysystem>:/sys/devices/system/cpu/cpu0/cpufreq/stats # cat total_trans
+    20
+
+- **trans_table**
+
+This will give a fine grained information about all the CPU frequency
+transitions. The cat output here is a two dimensional matrix, where an entry
+<i,j> (row i, column j) represents the count of number of transitions from
+Freq_i to Freq_j. Freq_i rows and Freq_j columns follow the sorting order in
+which the driver has provided the frequency table initially to the cpufreq core
+and so can be sorted (ascending or descending) or unsorted.  The output here
+also contains the actual freq values for each row and column for better
+readability.
+
+If the transition table is bigger than PAGE_SIZE, reading this will
+return an -EFBIG error.
+
+::
+
+    <mysystem>:/sys/devices/system/cpu/cpu0/cpufreq/stats # cat trans_table
+    From  :    To
+	    :   3600000   3400000   3200000   3000000   2800000
+    3600000:         0         5         0         0         0
+    3400000:         4         0         2         0         0
+    3200000:         0         1         0         2         0
+    3000000:         0         0         1         0         3
+    2800000:         0         0         0         2         0
+
+3. Configuring cpufreq-stats
+============================
+
+To configure cpufreq-stats in your kernel::
+
+	Config Main Menu
+		Power management options (ACPI, APM)  --->
+			CPU Frequency scaling  --->
+				[*] CPU Frequency scaling
+				[*]   CPU frequency translation statistics
+
+
+"CPU Frequency scaling" (CONFIG_CPU_FREQ) should be enabled to configure
+cpufreq-stats.
+
+"CPU frequency translation statistics" (CONFIG_CPU_FREQ_STAT) provides the
+statistics which includes time_in_state, total_trans and trans_table.
+
+Once this option is enabled and your CPU supports cpufrequency, you
+will be able to see the CPU frequency statistics in /sysfs.

Documentation/cpu-freq/cpufreq-stats.txt

···
-
-     CPU frequency and voltage scaling statistics in the Linux(TM) kernel
-
-
-             L i n u x    c p u f r e q - s t a t s   d r i v e r
-
-                       - information for users -
-
-
-             Venkatesh Pallipadi <[e-mail]>
-
-Contents
-1. Introduction
-2. Statistics Provided (with example)
-3. Configuring cpufreq-stats
-
-
-1. Introduction
-
-cpufreq-stats is a driver that provides CPU frequency statistics for each CPU.
-These statistics are provided in /sysfs as a bunch of read_only interfaces. This
-interface (when configured) will appear in a separate directory under cpufreq
-in /sysfs (<sysfs root>/devices/system/cpu/cpuX/cpufreq/stats/) for each CPU.
-Various statistics will form read_only files under this directory.
-
-This driver is designed to be independent of any particular cpufreq_driver
-that may be running on your CPU. So, it will work with any cpufreq_driver.
-
-
-2. Statistics Provided (with example)
-
-cpufreq stats provides following statistics (explained in detail below).
--  time_in_state
--  total_trans
--  trans_table
-
-All the statistics will be from the time the stats driver has been inserted
-(or the time the stats were reset) to the time when a read of a particular
-statistic is done. Obviously, stats driver will not have any information
-about the frequency transitions before the stats driver insertion.
-
---------------------------------------------------------------------------------
-<mysystem>:/sys/devices/system/cpu/cpu0/cpufreq/stats # ls -l
-total 0
-drwxr-xr-x  2 root root    0 May 14 16:06 .
-drwxr-xr-x  3 root root    0 May 14 15:58 ..
---w-------  1 root root 4096 May 14 16:06 reset
--r--r--r--  1 root root 4096 May 14 16:06 time_in_state
--r--r--r--  1 root root 4096 May 14 16:06 total_trans
--r--r--r--  1 root root 4096 May 14 16:06 trans_table
---------------------------------------------------------------------------------
-
--  reset
-Write-only attribute that can be used to reset the stat counters. This can be
-useful for evaluating system behaviour under different governors without the
-need for a reboot.
-
--  time_in_state
-This gives the amount of time spent in each of the frequencies supported by
-this CPU. The cat output will have "<frequency> <time>" pair in each line, which
-will mean this CPU spent <time> usertime units of time at <frequency>. Output
-will have one line for each of the supported frequencies. usertime units here 
-is 10mS (similar to other time exported in /proc).
-
---------------------------------------------------------------------------------
-<mysystem>:/sys/devices/system/cpu/cpu0/cpufreq/stats # cat time_in_state 
-3600000 2089
-3400000 136
-3200000 34
-3000000 67
-2800000 172488
---------------------------------------------------------------------------------
-
-
--  total_trans
-This gives the total number of frequency transitions on this CPU. The cat 
-output will have a single count which is the total number of frequency
-transitions.
-
---------------------------------------------------------------------------------
-<mysystem>:/sys/devices/system/cpu/cpu0/cpufreq/stats # cat total_trans
-20
---------------------------------------------------------------------------------
-
--  trans_table
-This will give a fine grained information about all the CPU frequency
-transitions. The cat output here is a two dimensional matrix, where an entry
-<i,j> (row i, column j) represents the count of number of transitions from 
-Freq_i to Freq_j. Freq_i rows and Freq_j columns follow the sorting order in
-which the driver has provided the frequency table initially to the cpufreq core
-and so can be sorted (ascending or descending) or unsorted.  The output here
-also contains the actual freq values for each row and column for better
-readability.
-
-If the transition table is bigger than PAGE_SIZE, reading this will
-return an -EFBIG error.
-
---------------------------------------------------------------------------------
-<mysystem>:/sys/devices/system/cpu/cpu0/cpufreq/stats # cat trans_table
-   From  :    To
-         :   3600000   3400000   3200000   3000000   2800000 
-  3600000:         0         5         0         0         0 
-  3400000:         4         0         2         0         0 
-  3200000:         0         1         0         2         0 
-  3000000:         0         0         1         0         3 
-  2800000:         0         0         0         2         0 
---------------------------------------------------------------------------------
-
-
-3. Configuring cpufreq-stats
-
-To configure cpufreq-stats in your kernel
-Config Main Menu
-	Power management options (ACPI, APM)  --->
-		CPU Frequency scaling  --->
-			[*] CPU Frequency scaling
-			[*]   CPU frequency translation statistics
-
-
-"CPU Frequency scaling" (CONFIG_CPU_FREQ) should be enabled to configure
-cpufreq-stats.
-
-"CPU frequency translation statistics" (CONFIG_CPU_FREQ_STAT) provides the
-statistics which includes time_in_state, total_trans and trans_table.
-
-Once this option is enabled and your CPU supports cpufrequency, you
-will be able to see the CPU frequency statistics in /sysfs.

Documentation/cpu-freq/index.rst

···
+.. SPDX-License-Identifier: GPL-2.0
+
+==============================================================================
+Linux CPUFreq - CPU frequency and voltage scaling code in the Linux(TM) kernel
+==============================================================================
+
+Author: Dominik Brodowski  <[e-mail]>
+
+   Clock scaling allows you to change the clock speed of the CPUs on the
+   fly. This is a nice method to save battery power, because the lower
+   the clock speed, the less power the CPU consumes.
+
+
+.. toctree::
+   :maxdepth: 1
+
+   core
+   cpu-drivers
+   cpufreq-stats
+
+Mailing List
+------------
+There is a CPU frequency changing CVS commit and general list where
+you can report bugs, problems or submit patches. To post a message,
+send an email to [e-mail].
+
+Links
+-----
+the FTP archives:
+* ftp://ftp.linux.org.uk/pub/linux/cpufreq/
+
+how to access the CVS repository:
+* http://cvs.arm.linux.org.uk/
+
+the CPUFreq Mailing list:
+* http://vger.kernel.org/vger-lists.html#linux-pm
+
+Clock and voltage scaling for the SA-1100:
+* http://www.lartmaker.nl/projects/scaling

Documentation/cpu-freq/index.txt

···
-     CPU frequency and voltage scaling code in the Linux(TM) kernel
-
-
-		         L i n u x    C P U F r e q
-
-
-
-
-		    Dominik Brodowski  <[e-mail]>
-
-
-
-   Clock scaling allows you to change the clock speed of the CPUs on the
-    fly. This is a nice method to save battery power, because the lower
-            the clock speed, the less power the CPU consumes.
-
-
-
-Documents in this directory:
-----------------------------
-
-amd-powernow.txt -	AMD powernow driver specific file.
-
-core.txt	-	General description of the CPUFreq core and
-			of CPUFreq notifiers.
-
-cpu-drivers.txt -	How to implement a new cpufreq processor driver.
-
-cpufreq-nforce2.txt -	nVidia nForce2 platform specific file.
-
-cpufreq-stats.txt -	General description of sysfs cpufreq stats.
-
-index.txt	-	File index, Mailing list and Links (this document)
-
-pcc-cpufreq.txt -	PCC cpufreq driver specific file.
-
-
-Mailing List
-------------
-There is a CPU frequency changing CVS commit and general list where
-you can report bugs, problems or submit patches. To post a message,
-send an email to [e-mail].
-
-Links
------
-the FTP archives:
-* ftp://ftp.linux.org.uk/pub/linux/cpufreq/
-
-how to access the CVS repository:
-* http://cvs.arm.linux.org.uk/
-
-the CPUFreq Mailing list:
-* http://vger.kernel.org/vger-lists.html#linux-pm
-
-Clock and voltage scaling for the SA-1100:
-* http://www.lartmaker.nl/projects/scaling

Documentation/cpu-freq/pcc-cpufreq.txt

···
-/*
- *  pcc-cpufreq.txt - PCC interface documentation
- *
- *  Copyright (C) 2009 Red Hat, Matthew Garrett <[e-mail]>
- *  Copyright (C) 2009 Hewlett-Packard Development Company, L.P.
- *      Nagananda Chumbalkar <[e-mail]>
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; version 2 of the License.
- *
- *  This program is distributed in the hope that it will be useful, but
- *  WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or NON
- *  INFRINGEMENT. See the GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- */
-
-
-			Processor Clocking Control Driver
-			---------------------------------
-
-Contents:
----------
-1.	Introduction
-1.1	PCC interface
-1.1.1   Get Average Frequency
-1.1.2	Set Desired Frequency
-1.2	Platforms affected
-2.	Driver and /sys details
-2.1	scaling_available_frequencies
-2.2	cpuinfo_transition_latency
-2.3	cpuinfo_cur_freq
-2.4	related_cpus
-3.	Caveats
-
-1. Introduction:
-----------------
-Processor Clocking Control (PCC) is an interface between the platform
-firmware and OSPM. It is a mechanism for coordinating processor
-performance (ie: frequency) between the platform firmware and the OS.
-
-The PCC driver (pcc-cpufreq) allows OSPM to take advantage of the PCC
-interface.
-
-OS utilizes the PCC interface to inform platform firmware what frequency the
-OS wants for a logical processor. The platform firmware attempts to achieve
-the requested frequency. If the request for the target frequency could not be
-satisfied by platform firmware, then it usually means that power budget
-conditions are in place, and "power capping" is taking place.
-
-1.1 PCC interface:
-------------------
-The complete PCC specification is available here:
-http://www.acpica.org/download/Processor-Clocking-Control-v1p0.pdf
-
-PCC relies on a shared memory region that provides a channel for communication
-between the OS and platform firmware. PCC also implements a "doorbell" that
-is used by the OS to inform the platform firmware that a command has been
-sent.
-
-The ACPI PCCH() method is used to discover the location of the PCC shared
-memory region. The shared memory region header contains the "command" and
-"status" interface. PCCH() also contains details on how to access the platform
-doorbell.
-
-The following commands are supported by the PCC interface:
-* Get Average Frequency
-* Set Desired Frequency
-
-The ACPI PCCP() method is implemented for each logical processor and is
-used to discover the offsets for the input and output buffers in the shared
-memory region.
-
-When PCC mode is enabled, the platform will not expose processor performance
-or throttle states (_PSS, _TSS and related ACPI objects) to OSPM. Therefore,
-the native P-state driver (such as acpi-cpufreq for Intel, powernow-k8 for
-AMD) will not load.
-
-However, OSPM remains in control of policy. The governor (eg: "ondemand")
-computes the required performance for each processor based on server workload.
-The PCC driver fills in the command interface, and the input buffer and
-communicates the request to the platform firmware. The platform firmware is
-responsible for delivering the requested performance.
-
-Each PCC command is "global" in scope and can affect all the logical CPUs in
-the system. Therefore, PCC is capable of performing "group" updates. With PCC
-the OS is capable of getting/setting the frequency of all the logical CPUs in
-the system with a single call to the BIOS.
-
-1.1.1 Get Average Frequency:
-----------------------------
-This command is used by the OSPM to query the running frequency of the
-processor since the last time this command was completed. The output buffer
-indicates the average unhalted frequency of the logical processor expressed as
-a percentage of the nominal (ie: maximum) CPU frequency. The output buffer
-also signifies if the CPU frequency is limited by a power budget condition.
-
-1.1.2 Set Desired Frequency:
-----------------------------
-This command is used by the OSPM to communicate to the platform firmware the
-desired frequency for a logical processor. The output buffer is currently
-ignored by OSPM. The next invocation of "Get Average Frequency" will inform
-OSPM if the desired frequency was achieved or not.
-
-1.2 Platforms affected:
------------------------
-The PCC driver will load on any system where the platform firmware:
-* supports the PCC interface, and the associated PCCH() and PCCP() methods
-* assumes responsibility for managing the hardware clocking controls in order
-to deliver the requested processor performance
-
-Currently, certain HP ProLiant platforms implement the PCC interface. On those
-platforms PCC is the "default" choice.
-
-However, it is possible to disable this interface via a BIOS setting. In
-such an instance, as is also the case on platforms where the PCC interface
-is not implemented, the PCC driver will fail to load silently.
-
-2. Driver and /sys details:
----------------------------
-When the driver loads, it merely prints the lowest and the highest CPU
-frequencies supported by the platform firmware.
-
-The PCC driver loads with a message such as:
-pcc-cpufreq: (v1.00.00) driver loaded with frequency limits: 1600 MHz, 2933
-MHz
-
-This means that the OPSM can request the CPU to run at any frequency in
-between the limits (1600 MHz, and 2933 MHz) specified in the message.
-
-Internally, there is no need for the driver to convert the "target" frequency
-to a corresponding P-state.
-
-The VERSION number for the driver will be of the format v.xy.ab.
-eg: 1.00.02
-   ----- --
-    |    |
-    |    -- this will increase with bug fixes/enhancements to the driver
-    |-- this is the version of the PCC specification the driver adheres to
-
-
-The following is a brief discussion on some of the fields exported via the
-/sys filesystem and how their values are affected by the PCC driver:
-
-2.1 scaling_available_frequencies:
-----------------------------------
-scaling_available_frequencies is not created in /sys. No intermediate
-frequencies need to be listed because the BIOS will try to achieve any
-frequency, within limits, requested by the governor. A frequency does not have
-to be strictly associated with a P-state.
-
-2.2 cpuinfo_transition_latency:
--------------------------------
-The cpuinfo_transition_latency field is 0. The PCC specification does
-not include a field to expose this value currently.
-
-2.3 cpuinfo_cur_freq:
----------------------
-A) Often cpuinfo_cur_freq will show a value different than what is declared
-in the scaling_available_frequencies or scaling_cur_freq, or scaling_max_freq.
-This is due to "turbo boost" available on recent Intel processors. If certain
-conditions are met the BIOS can achieve a slightly higher speed than requested
-by OSPM. An example:
-
-scaling_cur_freq	: 2933000
-cpuinfo_cur_freq	: 3196000
-
-B) There is a round-off error associated with the cpuinfo_cur_freq value.
-Since the driver obtains the current frequency as a "percentage" (%) of the
-nominal frequency from the BIOS, sometimes, the values displayed by
-scaling_cur_freq and cpuinfo_cur_freq may not match. An example:
-
-scaling_cur_freq	: 1600000
-cpuinfo_cur_freq	: 1583000
-
-In this example, the nominal frequency is 2933 MHz. The driver obtains the
-current frequency, cpuinfo_cur_freq, as 54% of the nominal frequency:
-
-	54% of 2933 MHz = 1583 MHz
-
-Nominal frequency is the maximum frequency of the processor, and it usually
-corresponds to the frequency of the P0 P-state.
-
-2.4 related_cpus:
------------------
-The related_cpus field is identical to affected_cpus.
-
-affected_cpus	: 4
-related_cpus	: 4
-
-Currently, the PCC driver does not evaluate _PSD. The platforms that support
-PCC do not implement SW_ALL. So OSPM doesn't need to perform any coordination
-to ensure that the same frequency is requested of all dependent CPUs.
-
-3. Caveats:
------------
-The "cpufreq_stats" module in its present form cannot be loaded and
-expected to work with the PCC driver. Since the "cpufreq_stats" module
-provides information wrt each P-state, it is not applicable to the PCC driver.

Documentation/devicetree/bindings/opp/qcom-nvmem-cpufreq.txt

···
 
 In 'operating-points-v2' table:
 - compatible: Should be
-	- 'operating-points-v2-kryo-cpu' for apq8096 and msm8996.
+	- 'operating-points-v2-kryo-cpu' for apq8096, msm8996, msm8974,
+					     apq8064, ipq8064, msm8960 and ipq8074.
 
 Optional properties:
 --------------------

Documentation/index.rst

···
    accounting/index
    block/index
    cdrom/index
+   cpu-freq/index
    ide/index
    fb/index
    fpga/index

Documentation/power/pm_qos_interface.rst

···
 one of the parameters.
 
 Two different PM QoS frameworks are available:
-1. PM QoS classes for cpu_dma_latency
-2. The per-device PM QoS framework provides the API to manage the
+ * CPU latency QoS.
+ * The per-device PM QoS framework provides the API to manage the
    per-device latency constraints and PM QoS flags.
 
-Each parameters have defined units:
-
- * latency: usec
- * timeout: usec
- * throughput: kbs (kilo bit / sec)
- * memory bandwidth: mbs (mega bit / sec)
+The latency unit used in the PM QoS framework is the microsecond (usec).
 
 
 1. PM QoS framework
 ===================
 
-The infrastructure exposes multiple misc device nodes one per implemented
-parameter.  The set of parameters implement is defined by pm_qos_power_init()
-and pm_qos_params.h.  This is done because having the available parameters
-being runtime configurable or changeable from a driver was seen as too easy to
-abuse.
+A global list of CPU latency QoS requests is maintained along with an aggregated
+(effective) target value.  The aggregated target value is updated with changes
+to the request list or elements of the list.  For CPU latency QoS, the
+aggregated target value is simply the min of the request values held in the list
+elements.
 
-For each parameter a list of performance requests is maintained along with
-an aggregated target value.  The aggregated target value is updated with
-changes to the request list or elements of the list.  Typically the
-aggregated target value is simply the max or min of the request values held
-in the parameter list elements.
 Note: the aggregated target value is implemented as an atomic variable so that
 reading the aggregated value does not require any locking mechanism.
 
+From kernel space the use of this interface is simple:
 
-From kernel mode the use of this interface is simple:
+void cpu_latency_qos_add_request(handle, target_value):
+  Will insert an element into the CPU latency QoS list with the target value.
+  Upon change to this list the new target is recomputed and any registered
+  notifiers are called only if the target value is now different.
+  Clients of PM QoS need to save the returned handle for future use in other
+  PM QoS API functions.
 
-void pm_qos_add_request(handle, param_class, target_value):
-  Will insert an element into the list for that identified PM QoS class with the
-  target value.  Upon change to this list the new target is recomputed and any
-  registered notifiers are called only if the target value is now different.
-  Clients of pm_qos need to save the returned handle for future use in other
-  pm_qos API functions.
-
-void pm_qos_update_request(handle, new_target_value):
+void cpu_latency_qos_update_request(handle, new_target_value):
   Will update the list element pointed to by the handle with the new target
   value and recompute the new aggregated target, calling the notification tree
   if the target is changed.
 
-void pm_qos_remove_request(handle):
+void cpu_latency_qos_remove_request(handle):
   Will remove the element.  After removal it will update the aggregate target
   and call the notification tree if the target was changed as a result of
   removing the request.
 
-int pm_qos_request(param_class):
-  Returns the aggregated value for a given PM QoS class.
+int cpu_latency_qos_limit():
+  Returns the aggregated value for the CPU latency QoS.
 
-int pm_qos_request_active(handle):
-  Returns if the request is still active, i.e. it has not been removed from a
-  PM QoS class constraints list.
+int cpu_latency_qos_request_active(handle):
+  Returns if the request is still active, i.e. it has not been removed from the
+  CPU latency QoS list.
 
-int pm_qos_add_notifier(param_class, notifier):
-  Adds a notification callback function to the PM QoS class. The callback is
-  called when the aggregated value for the PM QoS class is changed.
+int cpu_latency_qos_add_notifier(notifier):
+  Adds a notification callback function to the CPU latency QoS. The callback is
+  called when the aggregated value for the CPU latency QoS is changed.
 
-int pm_qos_remove_notifier(int param_class, notifier):
-  Removes the notification callback function for the PM QoS class.
+int cpu_latency_qos_remove_notifier(notifier):
+  Removes the notification callback function from the CPU latency QoS.
 
 
-From user mode:
+From user space:
 
-Only processes can register a pm_qos request.  To provide for automatic
+The infrastructure exposes one device node, /dev/cpu_dma_latency, for the CPU
+latency QoS.
+
+Only processes can register a PM QoS request.  To provide for automatic
 cleanup of a process, the interface requires the process to register its
-parameter requests in the following way:
+parameter requests as follows.
 
-To register the default pm_qos target for the specific parameter, the process
-must open /dev/cpu_dma_latency
+To register the default PM QoS target for the CPU latency QoS, the process must
+open /dev/cpu_dma_latency.
 
 As long as the device node is held open that process has a registered
 request on the parameter.
 
-To change the requested target value the process needs to write an s32 value to
-the open device node.  Alternatively the user mode program could write a hex
-string for the value using 10 char long format e.g. "0x12345678".  This
-translates to a pm_qos_update_request call.
+To change the requested target value, the process needs to write an s32 value to
+the open device node.  Alternatively, it can write a hex string for the value
+using the 10 char long format e.g. "0x12345678".  This translates to a
+cpu_latency_qos_update_request() call.
 
 To remove the user mode request for a target value simply close the device
 node.

Documentation/power/runtime_pm.rst

···
       nonzero, increment the counter and return 1; otherwise return 0 without
       changing the counter
 
+  `int pm_runtime_get_if_active(struct device *dev, bool ign_usage_count);`
+    - return -EINVAL if 'power.disable_depth' is nonzero; otherwise, if the
+      runtime PM status is RPM_ACTIVE, and either ign_usage_count is true
+      or the device's usage_count is non-zero, increment the counter and
+      return 1; otherwise return 0 without changing the counter
+
   `void pm_runtime_put_noidle(struct device *dev);`
     - decrement the device's usage counter
 

Documentation/power/userland-swsusp.rst

···
 
 SNAPSHOT_GET_IMAGE_SIZE
 	return the actual size of the hibernation image
+	(the last argument should be a pointer to a loff_t variable that
+	will contain the result if the call is successful)
 
 SNAPSHOT_AVAIL_SWAP_SIZE
-	return the amount of available swap in bytes (the
-	last argument should be a pointer to an unsigned int variable that will
-	contain the result if the call is successful).
+	return the amount of available swap in bytes
+	(the last argument should be a pointer to a loff_t variable that
+	will contain the result if the call is successful)
 
 SNAPSHOT_ALLOC_SWAP_PAGE
 	allocate a swap page from the resume partition

Documentation/trace/events-power.rst

···
 target/flags update.
 ::
 
-  pm_qos_add_request                 "pm_qos_class=%s value=%d"
-  pm_qos_update_request              "pm_qos_class=%s value=%d"
-  pm_qos_remove_request              "pm_qos_class=%s value=%d"
-  pm_qos_update_request_timeout      "pm_qos_class=%s value=%d, timeout_us=%ld"
-
-The first parameter gives the QoS class name (e.g. "CPU_DMA_LATENCY").
-The second parameter is value to be added/updated/removed.
-The third parameter is timeout value in usec.
-::
-
   pm_qos_update_target               "action=%s prev_value=%d curr_value=%d"
   pm_qos_update_flags                "action=%s prev_value=0x%x curr_value=0x%x"
 
···
 The second parameter is the previous QoS value.
 The third parameter is the current QoS value to update.
 
-And, there are also events used for device PM QoS add/update/remove request.
+There are also events used for device PM QoS add/update/remove request.
 ::
 
   dev_pm_qos_add_request             "device=%s type=%s new_value=%d"
···
 QoS requests.
 The second parameter gives the request type (e.g. "DEV_PM_QOS_RESUME_LATENCY").
 The third parameter is value to be added/updated/removed.
+
+And, there are events used for CPU latency QoS add/update/remove request.
+::
+
+  pm_qos_add_request        "value=%d"
+  pm_qos_update_request     "value=%d"
+  pm_qos_remove_request     "value=%d"
+
+The parameter is the value to be added/updated/removed.

arch/x86/platform/intel/iosf_mbi.c

···
 			    iosf_mbi_sem_address, 0, PUNIT_SEMAPHORE_BIT))
 		dev_err(&mbi_pdev->dev, "Error P-Unit semaphore reset failed\n");
 
-	pm_qos_update_request(&iosf_mbi_pm_qos, PM_QOS_DEFAULT_VALUE);
+	cpu_latency_qos_update_request(&iosf_mbi_pm_qos, PM_QOS_DEFAULT_VALUE);
 
 	blocking_notifier_call_chain(&iosf_mbi_pmic_bus_access_notifier,
 				     MBI_PMIC_BUS_ACCESS_END, NULL);
···
  * 4) When CPU cores enter C6 or C7 the P-Unit needs to talk to the PMIC
  *    if this happens while the kernel itself is accessing the PMIC I2C bus
  *    the SoC hangs.
- *    As the third step we call pm_qos_update_request() to disallow the CPU
- *    to enter C6 or C7.
+ *    As the third step we call cpu_latency_qos_update_request() to disallow the
+ *    CPU to enter C6 or C7.
  *
  * 5) The P-Unit has a PMIC bus semaphore which we can request to stop
  *    autonomous P-Unit tasks from accessing the PMIC I2C bus while we hold it.
···
 	 * requires the P-Unit to talk to the PMIC and if this happens while
 	 * we're holding the semaphore, the SoC hangs.
 	 */
-	pm_qos_update_request(&iosf_mbi_pm_qos, 0);
+	cpu_latency_qos_update_request(&iosf_mbi_pm_qos, 0);
 
 	/* host driver writes to side band semaphore register */
 	ret = iosf_mbi_write(BT_MBI_UNIT_PMC, MBI_REG_WRITE,
···
 {
 	iosf_debugfs_init();
 
-	pm_qos_add_request(&iosf_mbi_pm_qos, PM_QOS_CPU_DMA_LATENCY,
-			   PM_QOS_DEFAULT_VALUE);
+	cpu_latency_qos_add_request(&iosf_mbi_pm_qos, PM_QOS_DEFAULT_VALUE);
 
 	return pci_register_driver(&iosf_mbi_pci_driver);
 }
···
 	pci_dev_put(mbi_pdev);
 	mbi_pdev = NULL;
 
-	pm_qos_remove_request(&iosf_mbi_pm_qos);
+	cpu_latency_qos_remove_request(&iosf_mbi_pm_qos);
 }
 
 module_init(iosf_mbi_init);

drivers/acpi/acpica/achware.h

···
 
 acpi_status acpi_hw_enable_all_wakeup_gpes(void);
 
-u8 acpi_hw_check_all_gpes(void);
+u8 acpi_hw_check_all_gpes(acpi_handle gpe_skip_device, u32 gpe_skip_number);
 
 acpi_status
 acpi_hw_enable_runtime_gpe_block(struct acpi_gpe_xrupt_info *gpe_xrupt_info,

drivers/acpi/acpica/evxfgpe.c

···
  *
  * FUNCTION:    acpi_any_gpe_status_set
  *
- * PARAMETERS:  None
+ * PARAMETERS:  gpe_skip_number      - Number of the GPE to skip
  *
  * RETURN:      Whether or not the status bit is set for any GPE
  *
- * DESCRIPTION: Check the status bits of all enabled GPEs and return TRUE if any
- *              of them is set or FALSE otherwise.
+ * DESCRIPTION: Check the status bits of all enabled GPEs, except for the one
+ *              represented by the "skip" argument, and return TRUE if any of
+ *              them is set or FALSE otherwise.
  *
  ******************************************************************************/
-u32 acpi_any_gpe_status_set(void)
+u32 acpi_any_gpe_status_set(u32 gpe_skip_number)
 {
 	acpi_status status;
+	acpi_handle gpe_device;
 	u8 ret;
 
 	ACPI_FUNCTION_TRACE(acpi_any_gpe_status_set);
···
 		return (FALSE);
 	}
 
-	ret = acpi_hw_check_all_gpes();
+	status = acpi_get_gpe_device(gpe_skip_number, &gpe_device);
+	if (ACPI_FAILURE(status)) {
+		gpe_device = NULL;
+	}
+
+	ret = acpi_hw_check_all_gpes(gpe_device, gpe_skip_number);
 	(void)acpi_ut_release_mutex(ACPI_MTX_EVENTS);
 
 	return (ret);

drivers/acpi/acpica/hwgpe.c

···
 	return (AE_OK);
 }
 
+struct acpi_gpe_block_status_context {
+	struct acpi_gpe_register_info *gpe_skip_register_info;
+	u8 gpe_skip_mask;
+	u8 retval;
+};
+
 /******************************************************************************
  *
  * FUNCTION:    acpi_hw_get_gpe_block_status
  *
  * PARAMETERS:  gpe_xrupt_info      - GPE Interrupt info
  *              gpe_block           - Gpe Block info
+ *              context             - GPE list walk context data
  *
  * RETURN:      Success
  *
···
 static acpi_status
 acpi_hw_get_gpe_block_status(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
 			     struct acpi_gpe_block_info *gpe_block,
-			     void *ret_ptr)
+			     void *context)
 {
+	struct acpi_gpe_block_status_context *c = context;
 	struct acpi_gpe_register_info *gpe_register_info;
 	u64 in_enable, in_status;
 	acpi_status status;
-	u8 *ret = ret_ptr;
+	u8 ret_mask;
 	u32 i;
 
 	/* Examine each GPE Register within the block */
···
 			continue;
 		}
 
-		*ret |= in_enable & in_status;
+		ret_mask = in_enable & in_status;
+		if (ret_mask && c->gpe_skip_register_info == gpe_register_info) {
+			ret_mask &= ~c->gpe_skip_mask;
+		}
+		c->retval |= ret_mask;
 	}
 
 	return (AE_OK);
···
  *
  * FUNCTION:    acpi_hw_check_all_gpes
  *
- * PARAMETERS:  None
+ * PARAMETERS:  gpe_skip_device      - GPE devoce of the GPE to skip
+ *              gpe_skip_number      - Number of the GPE to skip
  *
  * RETURN:      Combined status of all GPEs
  *
- * DESCRIPTION: Check all enabled GPEs in all GPE blocks and return TRUE if the
+ * DESCRIPTION: Check all enabled GPEs in all GPE blocks, except for the one
+ *              represented by the "skip" arguments, and return TRUE if the
  *              status bit is set for at least one of them of FALSE otherwise.
  *
  ******************************************************************************/
 
-u8 acpi_hw_check_all_gpes(void)
+u8 acpi_hw_check_all_gpes(acpi_handle gpe_skip_device, u32 gpe_skip_number)
 {
-	u8 ret = 0;
+	struct acpi_gpe_block_status_context context = {
+		.gpe_skip_register_info = NULL,
+		.retval = 0,
+	};
+	struct acpi_gpe_event_info *gpe_event_info;
+	acpi_cpu_flags flags;
 
 	ACPI_FUNCTION_TRACE(acpi_hw_check_all_gpes);
 
-	(void)acpi_ev_walk_gpe_list(acpi_hw_get_gpe_block_status, &ret);
+	flags = acpi_os_acquire_lock(acpi_gbl_gpe_lock);
 
-	return (ret != 0);
+	gpe_event_info = acpi_ev_get_gpe_event_info(gpe_skip_device,
+						    gpe_skip_number);
+	if (gpe_event_info) {
+		context.gpe_skip_register_info = gpe_event_info->register_info;
+		context.gpe_skip_mask = acpi_hw_get_gpe_register_bit(gpe_event_info);
+	}
+
+	acpi_os_release_lock(acpi_gbl_gpe_lock, flags);
+
+	(void)acpi_ev_walk_gpe_list(acpi_hw_get_gpe_block_status, &context);
+	return (context.retval != 0);
 }
 
 #endif				/* !ACPI_REDUCED_HARDWARE */

drivers/acpi/ec.c

···
 		acpi_set_gpe_wake_mask(NULL, first_ec->gpe, action);
 }
 
+bool acpi_ec_other_gpes_active(void)
+{
+	return acpi_any_gpe_status_set(first_ec ? first_ec->gpe : U32_MAX);
+}
+
 bool acpi_ec_dispatch_gpe(void)
 {
 	u32 ret;

drivers/acpi/internal.h

···
 
 #ifdef CONFIG_PM_SLEEP
 void acpi_ec_flush_work(void);
+bool acpi_ec_other_gpes_active(void);
 bool acpi_ec_dispatch_gpe(void);
 #endif
 

drivers/acpi/sleep.c

···
 
 static void acpi_s2idle_sync(void)
 {
-	/*
-	 * The EC driver uses the system workqueue and an additional special
-	 * one, so those need to be flushed too.
-	 */
+	/* The EC driver uses special workqueues that need to be flushed. */
 	acpi_ec_flush_work();
 	acpi_os_wait_events_complete(); /* synchronize Notify handling */
 }
···
 			return true;
 
 		/*
-		 * If there are no EC events to process and at least one of the
-		 * other enabled GPEs is active, the wakeup is regarded as a
-		 * genuine one.
-		 *
-		 * Note that the checks below must be carried out in this order
-		 * to avoid returning prematurely due to a change of the EC GPE
-		 * status bit from unset to set between the checks with the
-		 * status bits of all the other GPEs unset.
+		 * If the status bit is set for any enabled GPE other than the
+		 * EC one, the wakeup is regarded as a genuine one.
 		 */
-		if (acpi_any_gpe_status_set() && !acpi_ec_dispatch_gpe())
+		if (acpi_ec_other_gpes_active())
 			return true;
+
+		/*
+		 * If the EC GPE status bit has not been set, the wakeup is
+		 * regarded as a spurious one.
+		 */
+		if (!acpi_ec_dispatch_gpe())
+			return false;
 
 		/*
 		 * Cancel the wakeup and process all pending events in case

drivers/base/power/domain.c

···
 
 	ret = of_count_phandle_with_args(dn, "domain-idle-states", NULL);
 	if (ret <= 0)
-		return ret;
+		return ret == -ENOENT ? 0 : ret;
 
 	/* Loop over the phandles until all the requested entry is found */
 	of_for_each_phandle(&it, ret, dn, "domain-idle-states", NULL, 0) {

drivers/base/power/main.c

···
 
 typedef int (*pm_callback_t)(struct device *);
 
+#define list_for_each_entry_rcu_locked(pos, head, member) \
+	list_for_each_entry_rcu(pos, head, member, \
+			device_links_read_lock_held())
+
 /*
  * The entries in the dpm_list list are in a depth first order, simply
  * because children are guaranteed to be discovered after parents, and
···
 	 * callbacks freeing the link objects for the links in the list we're
 	 * walking.
 	 */
-	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node)
+	list_for_each_entry_rcu_locked(link, &dev->links.suppliers, c_node)
 		if (READ_ONCE(link->status) != DL_STATE_DORMANT)
 			dpm_wait(link->supplier, async);
 
···
 	 * continue instead of trying to continue in parallel with its
 	 * unregistration).
 	 */
-	list_for_each_entry_rcu(link, &dev->links.consumers, s_node)
+	list_for_each_entry_rcu_locked(link, &dev->links.consumers, s_node)
 		if (READ_ONCE(link->status) != DL_STATE_DORMANT)
 			dpm_wait(link->consumer, async);
 
···
 
 	idx = device_links_read_lock();
 
-	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node)
+	list_for_each_entry_rcu_locked(link, &dev->links.suppliers, c_node)
 		link->supplier->power.must_resume = true;
 
 	device_links_read_unlock(idx);
···
 
 	idx = device_links_read_lock();
 
-	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) {
+	list_for_each_entry_rcu_locked(link, &dev->links.suppliers, c_node) {
 		spin_lock_irq(&link->supplier->power.lock);
 		link->supplier->power.direct_complete = false;
 		spin_unlock_irq(&link->supplier->power.lock);

drivers/base/power/runtime.c

···
 EXPORT_SYMBOL_GPL(__pm_runtime_resume);
 
 /**
- * pm_runtime_get_if_in_use - Conditionally bump up the device's usage counter.
+ * pm_runtime_get_if_active - Conditionally bump up the device's usage counter.
  * @dev: Device to handle.
  *
  * Return -EINVAL if runtime PM is disabled for the device.
  *
- * If that's not the case and if the device's runtime PM status is RPM_ACTIVE
- * and the runtime PM usage counter is nonzero, increment the counter and
- * return 1.  Otherwise return 0 without changing the counter.
+ * Otherwise, if the device's runtime PM status is RPM_ACTIVE and either
+ * ign_usage_count is true or the device's usage_count is non-zero, increment
+ * the counter and return 1. Otherwise return 0 without changing the counter.
+ *
+ * If ign_usage_count is true, the function can be used to prevent suspending
+ * the device when its runtime PM status is RPM_ACTIVE.
+ *
+ * If ign_usage_count is false, the function can be used to prevent suspending
+ * the device when both its runtime PM status is RPM_ACTIVE and its usage_count
+ * is non-zero.
+ *
+ * The caller is resposible for putting the device's usage count when ther
+ * return value is greater than zero.
  */
-int pm_runtime_get_if_in_use(struct device *dev)
+int pm_runtime_get_if_active(struct device *dev, bool ign_usage_count)
 {
 	unsigned long flags;
 	int retval;
 
 	spin_lock_irqsave(&dev->power.lock, flags);
-	retval = dev->power.disable_depth > 0 ? -EINVAL :
-		dev->power.runtime_status == RPM_ACTIVE
-			&& atomic_inc_not_zero(&dev->power.usage_count);
+	if (dev->power.disable_depth > 0) {
+		retval = -EINVAL;
+	} else if (dev->power.runtime_status != RPM_ACTIVE) {
+		retval = 0;
+	} else if (ign_usage_count) {
+		retval = 1;
+		atomic_inc(&dev->power.usage_count);
+	} else {
+		retval = atomic_inc_not_zero(&dev->power.usage_count);
+	}
 	trace_rpm_usage_rcuidle(dev, 0);
 	spin_unlock_irqrestore(&dev->power.lock, flags);
+
 	return retval;
 }
-EXPORT_SYMBOL_GPL(pm_runtime_get_if_in_use);
+EXPORT_SYMBOL_GPL(pm_runtime_get_if_active);
 
 /**
  * __pm_runtime_set_status - Set runtime PM status of a device.

drivers/base/power/wakeup.c

···
 #define pm_suspend_target_state	(PM_SUSPEND_ON)
 #endif
 
+#define list_for_each_entry_rcu_locked(pos, head, member) \
+	list_for_each_entry_rcu(pos, head, member, \
+		srcu_read_lock_held(&wakeup_srcu))
 /*
  * If set, the suspend/hibernate code will abort transitions to a sleep state
  * if wakeup events are registered during or immediately before the transition.
···
 {
 	if (ws) {
 		wakeup_source_remove(ws);
-		wakeup_source_sysfs_remove(ws);
+		if (ws->dev)
+			wakeup_source_sysfs_remove(ws);
+
 		wakeup_source_destroy(ws);
 	}
 }
···
 	int srcuidx;
 
 	srcuidx = srcu_read_lock(&wakeup_srcu);
-	list_for_each_entry_rcu(ws, &wakeup_sources, entry)
+	list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry)
 		dev_pm_arm_wake_irq(ws->wakeirq);
 	srcu_read_unlock(&wakeup_srcu, srcuidx);
 }
···
 	int srcuidx;
 
 	srcuidx = srcu_read_lock(&wakeup_srcu);
-	list_for_each_entry_rcu(ws, &wakeup_sources, entry)
+	list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry)
 		dev_pm_disarm_wake_irq(ws->wakeirq);
 	srcu_read_unlock(&wakeup_srcu, srcuidx);
 }
···
 	struct wakeup_source *last_activity_ws = NULL;
 
 	srcuidx = srcu_read_lock(&wakeup_srcu);
-	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+	list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) {
 		if (ws->active) {
 			pm_pr_dbg("active wakeup source: %s\n", ws->name);
 			active = 1;
···
 	int srcuidx;
 
 	srcuidx = srcu_read_lock(&wakeup_srcu);
-	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+	list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) {
 		spin_lock_irq(&ws->lock);
 		if (ws->autosleep_enabled != set) {
 			ws->autosleep_enabled = set;
···
 	}
 
 	*srcuidx = srcu_read_lock(&wakeup_srcu);
-	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+	list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) {
 		if (n-- <= 0)
 			return ws;
 	}

drivers/cpufreq/Kconfig.arm

···
 
 config ARM_QCOM_CPUFREQ_NVMEM
 	tristate "Qualcomm nvmem based CPUFreq"
-	depends on ARM64
+	depends on ARCH_QCOM
 	depends on QCOM_QFPROM
 	depends on QCOM_SMEM
 	select PM_OPP

drivers/cpufreq/Kconfig.x86

···
 	  This driver adds support for the PCC interface.
 
 	  For details, take a look at:
-	  <file:Documentation/cpu-freq/pcc-cpufreq.txt>.
+	  <file:Documentation/admin-guide/pm/cpufreq_drivers.rst>.
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called pcc-cpufreq.

drivers/cpufreq/cpufreq-dt-platdev.c

···
 	{ .compatible = "ti,dra7", },
 	{ .compatible = "ti,omap3", },
 
+	{ .compatible = "qcom,ipq8064", },
+	{ .compatible = "qcom,apq8064", },
+	{ .compatible = "qcom,msm8974", },
+	{ .compatible = "qcom,msm8960", },
+
 	{ }
 };
 

drivers/cpufreq/cpufreq-dt.c

···
 		dt_cpufreq_driver.resume = data->resume;
 		if (data->suspend)
 			dt_cpufreq_driver.suspend = data->suspend;
+		if (data->get_intermediate) {
+			dt_cpufreq_driver.target_intermediate = data->target_intermediate;
+			dt_cpufreq_driver.get_intermediate = data->get_intermediate;
+		}
 	}
 
 	ret = cpufreq_register_driver(&dt_cpufreq_driver);

drivers/cpufreq/cpufreq-dt.h

···
 struct cpufreq_dt_platform_data {
 	bool have_governor_per_policy;
 
+	unsigned int	(*get_intermediate)(struct cpufreq_policy *policy,
+					    unsigned int index);
+	int		(*target_intermediate)(struct cpufreq_policy *policy,
+					       unsigned int index);
 	int (*suspend)(struct cpufreq_policy *policy);
 	int (*resume)(struct cpufreq_policy *policy);
 };

drivers/cpufreq/cpufreq_stats.c

···
 	if (policy->fast_switch_enabled)
 		return 0;
 
-	len += snprintf(buf + len, PAGE_SIZE - len, "   From  :    To\n");
-	len += snprintf(buf + len, PAGE_SIZE - len, "         : ");
+	len += scnprintf(buf + len, PAGE_SIZE - len, "   From  :    To\n");
+	len += scnprintf(buf + len, PAGE_SIZE - len, "         : ");
 	for (i = 0; i < stats->state_num; i++) {
 		if (len >= PAGE_SIZE)
 			break;
-		len += snprintf(buf + len, PAGE_SIZE - len, "%9u ",
+		len += scnprintf(buf + len, PAGE_SIZE - len, "%9u ",
 				stats->freq_table[i]);
 	}
 	if (len >= PAGE_SIZE)
 		return PAGE_SIZE;
 
-	len += snprintf(buf + len, PAGE_SIZE - len, "\n");
+	len += scnprintf(buf + len, PAGE_SIZE - len, "\n");
 
 	for (i = 0; i < stats->state_num; i++) {
 		if (len >= PAGE_SIZE)
 			break;
 
-		len += snprintf(buf + len, PAGE_SIZE - len, "%9u: ",
+		len += scnprintf(buf + len, PAGE_SIZE - len, "%9u: ",
 				stats->freq_table[i]);
 
 		for (j = 0; j < stats->state_num; j++) {
 			if (len >= PAGE_SIZE)
 				break;
-			len += snprintf(buf + len, PAGE_SIZE - len, "%9u ",
+			len += scnprintf(buf + len, PAGE_SIZE - len, "%9u ",
 					stats->trans_table[i*stats->max_state+j]);
 		}
 		if (len >= PAGE_SIZE)
 			break;
-		len += snprintf(buf + len, PAGE_SIZE - len, "\n");
+		len += scnprintf(buf + len, PAGE_SIZE - len, "\n");
 	}
 
 	if (len >= PAGE_SIZE) {

drivers/cpufreq/imx-cpufreq-dt.c

···
 #define IMX8MN_OCOTP_CFG3_SPEED_GRADE_MASK	(0xf << 8)
 #define OCOTP_CFG3_MKT_SEGMENT_SHIFT    6
 #define OCOTP_CFG3_MKT_SEGMENT_MASK     (0x3 << 6)
+#define IMX8MP_OCOTP_CFG3_MKT_SEGMENT_SHIFT    5
+#define IMX8MP_OCOTP_CFG3_MKT_SEGMENT_MASK     (0x3 << 5)
 
 /* cpufreq-dt device registered by imx-cpufreq-dt */
 static struct platform_device *cpufreq_dt_pdev;
···
 	int speed_grade, mkt_segment;
 	int ret;
 
+	if (!of_find_property(cpu_dev->of_node, "cpu-supply", NULL))
+		return -ENODEV;
+
 	ret = nvmem_cell_read_u32(cpu_dev, "speed_grade", &cell_value);
 	if (ret)
 		return ret;
···
 	else
 		speed_grade = (cell_value & OCOTP_CFG3_SPEED_GRADE_MASK)
 			      >> OCOTP_CFG3_SPEED_GRADE_SHIFT;
-	mkt_segment = (cell_value & OCOTP_CFG3_MKT_SEGMENT_MASK) >> OCOTP_CFG3_MKT_SEGMENT_SHIFT;
+
+	if (of_machine_is_compatible("fsl,imx8mp"))
+		mkt_segment = (cell_value & IMX8MP_OCOTP_CFG3_MKT_SEGMENT_MASK)
+			       >> IMX8MP_OCOTP_CFG3_MKT_SEGMENT_SHIFT;
+	else
+		mkt_segment = (cell_value & OCOTP_CFG3_MKT_SEGMENT_MASK)
+			       >> OCOTP_CFG3_MKT_SEGMENT_SHIFT;
 
 	/*
 	 * Early samples without fuses written report "0 0" which may NOT

drivers/cpufreq/imx6q-cpufreq.c

···
 #define OCOTP_CFG3_SPEED_996MHZ		0x2
 #define OCOTP_CFG3_SPEED_852MHZ		0x1
 
-static void imx6q_opp_check_speed_grading(struct device *dev)
+static int imx6q_opp_check_speed_grading(struct device *dev)
 {
 	struct device_node *np;
 	void __iomem *base;
 	u32 val;
+	int ret;
 
-	np = of_find_compatible_node(NULL, NULL, "fsl,imx6q-ocotp");
-	if (!np)
-		return;
+	if (of_find_property(dev->of_node, "nvmem-cells", NULL)) {
+		ret = nvmem_cell_read_u32(dev, "speed_grade", &val);
+		if (ret)
+			return ret;
+	} else {
+		np = of_find_compatible_node(NULL, NULL, "fsl,imx6q-ocotp");
+		if (!np)
+			return -ENOENT;
 
-	base = of_iomap(np, 0);
-	if (!base) {
-		dev_err(dev, "failed to map ocotp\n");
-		goto put_node;
+		base = of_iomap(np, 0);
+		of_node_put(np);
+		if (!base) {
+			dev_err(dev, "failed to map ocotp\n");
+			return -EFAULT;
+		}
+
+		/*
+		 * SPEED_GRADING[1:0] defines the max speed of ARM:
+		 * 2b'11: 1200000000Hz;
+		 * 2b'10: 996000000Hz;
+		 * 2b'01: 852000000Hz; -- i.MX6Q Only, exclusive with 996MHz.
+		 * 2b'00: 792000000Hz;
+		 * We need to set the max speed of ARM according to fuse map.
+		 */
+		val = readl_relaxed(base + OCOTP_CFG3);
+		iounmap(base);
 	}
 
-	/*
-	 * SPEED_GRADING[1:0] defines the max speed of ARM:
-	 * 2b'11: 1200000000Hz;
-	 * 2b'10: 996000000Hz;
-	 * 2b'01: 852000000Hz; -- i.MX6Q Only, exclusive with 996MHz.
-	 * 2b'00: 792000000Hz;
-	 * We need to set the max speed of ARM according to fuse map.
-	 */
-	val = readl_relaxed(base + OCOTP_CFG3);
 	val >>= OCOTP_CFG3_SPEED_SHIFT;
 	val &= 0x3;
 
···
 			if (dev_pm_opp_disable(dev, 1200000000))
 				dev_warn(dev, "failed to disable 1.2GHz OPP\n");
 	}
-	iounmap(base);
-put_node:
-	of_node_put(np);
+
+	return 0;
 }
 
 #define OCOTP_CFG3_6UL_SPEED_696MHZ	0x2
···
 		void __iomem *base;
 
 		np = of_find_compatible_node(NULL, NULL, "fsl,imx6ul-ocotp");
+		if (!np)
+			np = of_find_compatible_node(NULL, NULL,
+						     "fsl,imx6ull-ocotp");
 		if (!np)
 			return -ENOENT;
 
···
 		goto put_reg;
 	}
 
+	/* Because we have added the OPPs here, we must free them */
+	free_opp = true;
+
 	if (of_machine_is_compatible("fsl,imx6ul") ||
 	    of_machine_is_compatible("fsl,imx6ull")) {
 		ret = imx6ul_opp_check_speed_grading(cpu_dev);
-		if (ret) {
-			if (ret == -EPROBE_DEFER)
-				goto put_node;
-
+	} else {
+		ret = imx6q_opp_check_speed_grading(cpu_dev);
+	}
+	if (ret) {
+		if (ret != -EPROBE_DEFER)
 			dev_err(cpu_dev, "failed to read ocotp: %d\n",
 				ret);
-			goto put_node;
-		}
-	} else {
-		imx6q_opp_check_speed_grading(cpu_dev);
+		goto out_free_opp;
 	}
 
-	/* Because we have added the OPPs here, we must free them */
-	free_opp = true;
 	num = dev_pm_opp_get_opp_count(cpu_dev);
 	if (num < 0) {
 		ret = num;

drivers/cpufreq/intel_pstate.c

···
 	}
 }
 
-static int intel_pstate_verify_policy(struct cpufreq_policy_data *policy)
+static void intel_pstate_verify_cpu_policy(struct cpudata *cpu,
+					   struct cpufreq_policy_data *policy)
 {
-	struct cpudata *cpu = all_cpu_data[policy->cpu];
-
 	update_turbo_state();
 	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
 				     intel_pstate_get_max_freq(cpu));
 
 	intel_pstate_adjust_policy_max(cpu, policy);
+}
+
+static int intel_pstate_verify_policy(struct cpufreq_policy_data *policy)
+{
+	intel_pstate_verify_cpu_policy(all_cpu_data[policy->cpu], policy);
 
 	return 0;
 }
···
 	if (ret)
 		return ret;
 
-	if (IS_ENABLED(CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE))
-		policy->policy = CPUFREQ_POLICY_PERFORMANCE;
-	else
-		policy->policy = CPUFREQ_POLICY_POWERSAVE;
+	/*
+	 * Set the policy to powersave to provide a valid fallback value in case
+	 * the default cpufreq governor is neither powersave nor performance.
+	 */
+	policy->policy = CPUFREQ_POLICY_POWERSAVE;
 
 	return 0;
 }
···
 {
 	struct cpudata *cpu = all_cpu_data[policy->cpu];
 
-	update_turbo_state();
-	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
-				     intel_pstate_get_max_freq(cpu));
-
-	intel_pstate_adjust_policy_max(cpu, policy);
-
+	intel_pstate_verify_cpu_policy(cpu, policy);
 	intel_pstate_update_perf_limits(cpu, policy->min, policy->max);
 
 	return 0;

drivers/cpufreq/qcom-cpufreq-nvmem.c

···
 struct qcom_cpufreq_match_data {
 	int (*get_version)(struct device *cpu_dev,
 			   struct nvmem_cell *speedbin_nvmem,
+			   char **pvs_name,
 			   struct qcom_cpufreq_drv *drv);
 	const char **genpd_names;
 };
 
 struct qcom_cpufreq_drv {
-	struct opp_table **opp_tables;
+	struct opp_table **names_opp_tables;
+	struct opp_table **hw_opp_tables;
 	struct opp_table **genpd_opp_tables;
 	u32 versions;
 	const struct qcom_cpufreq_match_data *data;
 };
 
 static struct platform_device *cpufreq_dt_pdev, *cpufreq_pdev;
+
+static void get_krait_bin_format_a(struct device *cpu_dev,
+					  int *speed, int *pvs, int *pvs_ver,
+					  struct nvmem_cell *pvs_nvmem, u8 *buf)
+{
+	u32 pte_efuse;
+
+	pte_efuse = *((u32 *)buf);
+
+	*speed = pte_efuse & 0xf;
+	if (*speed == 0xf)
+		*speed = (pte_efuse >> 4) & 0xf;
+
+	if (*speed == 0xf) {
+		*speed = 0;
+		dev_warn(cpu_dev, "Speed bin: Defaulting to %d\n", *speed);
+	} else {
+		dev_dbg(cpu_dev, "Speed bin: %d\n", *speed);
+	}
+
+	*pvs = (pte_efuse >> 10) & 0x7;
+	if (*pvs == 0x7)
+		*pvs = (pte_efuse >> 13) & 0x7;
+
+	if (*pvs == 0x7) {
+		*pvs = 0;
+		dev_warn(cpu_dev, "PVS bin: Defaulting to %d\n", *pvs);
+	} else {
+		dev_dbg(cpu_dev, "PVS bin: %d\n", *pvs);
+	}
+}
+
+static void get_krait_bin_format_b(struct device *cpu_dev,
+					  int *speed, int *pvs, int *pvs_ver,
+					  struct nvmem_cell *pvs_nvmem, u8 *buf)
+{
+	u32 pte_efuse, redundant_sel;
+
+	pte_efuse = *((u32 *)buf);
+	redundant_sel = (pte_efuse >> 24) & 0x7;
+
+	*pvs_ver = (pte_efuse >> 4) & 0x3;
+
+	switch (redundant_sel) {
+	case 1:
+		*pvs = ((pte_efuse >> 28) & 0x8) | ((pte_efuse >> 6) & 0x7);
+		*speed = (pte_efuse >> 27) & 0xf;
+		break;
+	case 2:
+		*pvs = (pte_efuse >> 27) & 0xf;
+		*speed = pte_efuse & 0x7;
+		break;
+	default:
+		/* 4 bits of PVS are in efuse register bits 31, 8-6. */
+		*pvs = ((pte_efuse >> 28) & 0x8) | ((pte_efuse >> 6) & 0x7);
+		*speed = pte_efuse & 0x7;
+	}
+
+	/* Check SPEED_BIN_BLOW_STATUS */
+	if (pte_efuse & BIT(3)) {
+		dev_dbg(cpu_dev, "Speed bin: %d\n", *speed);
+	} else {
+		dev_warn(cpu_dev, "Speed bin not set. Defaulting to 0!\n");
+		*speed = 0;
+	}
+
+	/* Check PVS_BLOW_STATUS */
+	pte_efuse = *(((u32 *)buf) + 4);
+	pte_efuse &= BIT(21);
+	if (pte_efuse) {
+		dev_dbg(cpu_dev, "PVS bin: %d\n", *pvs);
+	} else {
+		dev_warn(cpu_dev, "PVS bin not set. Defaulting to 0!\n");
+		*pvs = 0;
+	}
+
+	dev_dbg(cpu_dev, "PVS version: %d\n", *pvs_ver);
+}
 
 static enum _msm8996_version qcom_cpufreq_get_msm_id(void)
 {
···
 
 static int qcom_cpufreq_kryo_name_version(struct device *cpu_dev,
 					  struct nvmem_cell *speedbin_nvmem,
+					  char **pvs_name,
 					  struct qcom_cpufreq_drv *drv)
 {
 	size_t len;
 	u8 *speedbin;
 	enum _msm8996_version msm8996_version;
+	*pvs_name = NULL;
 
 	msm8996_version = qcom_cpufreq_get_msm_id();
 	if (NUM_OF_MSM8996_VERSIONS == msm8996_version) {
···
 	return 0;
 }
 
+static int qcom_cpufreq_krait_name_version(struct device *cpu_dev,
+					   struct nvmem_cell *speedbin_nvmem,
+					   char **pvs_name,
+					   struct qcom_cpufreq_drv *drv)
+{
+	int speed = 0, pvs = 0, pvs_ver = 0;
+	u8 *speedbin;
+	size_t len;
+
+	speedbin = nvmem_cell_read(speedbin_nvmem, &len);
+
+	if (IS_ERR(speedbin))
+		return PTR_ERR(speedbin);
+
+	switch (len) {
+	case 4:
+		get_krait_bin_format_a(cpu_dev, &speed, &pvs, &pvs_ver,
+				       speedbin_nvmem, speedbin);
+		break;
+	case 8:
+		get_krait_bin_format_b(cpu_dev, &speed, &pvs, &pvs_ver,
+				       speedbin_nvmem, speedbin);
+		break;
+	default:
+		dev_err(cpu_dev, "Unable to read nvmem data. Defaulting to 0!\n");
+		return -ENODEV;
+	}
+
+	snprintf(*pvs_name, sizeof("speedXX-pvsXX-vXX"), "speed%d-pvs%d-v%d",
+		 speed, pvs, pvs_ver);
+
+	drv->versions = (1 << speed);
+
+	kfree(speedbin);
+	return 0;
+}
+
 static const struct qcom_cpufreq_match_data match_data_kryo = {
 	.get_version = qcom_cpufreq_kryo_name_version,
+};
+
+static const struct qcom_cpufreq_match_data match_data_krait = {
+	.get_version = qcom_cpufreq_krait_name_version,
 };
 
 static const char *qcs404_genpd_names[] = { "cpr", NULL };
···
 	struct nvmem_cell *speedbin_nvmem;
 	struct device_node *np;
 	struct device *cpu_dev;
+	char *pvs_name = "speedXX-pvsXX-vXX";
 	unsigned cpu;
 	const struct of_device_id *match;
 	int ret;
···
 	if (!np)
 		return -ENOENT;
 
-	ret = of_device_is_compatible(np, "operating-points-v2-kryo-cpu");
+	ret = of_device_is_compatible(np, "operating-points-v2-qcom-cpu");
 	if (!ret) {
 		of_node_put(np);
 		return -ENOENT;
···
 			goto free_drv;
 		}
 
-		ret = drv->data->get_version(cpu_dev, speedbin_nvmem, drv);
+		ret = drv->data->get_version(cpu_dev,
+							speedbin_nvmem, &pvs_name, drv);
 		if (ret) {
 			nvmem_cell_put(speedbin_nvmem);
 			goto free_drv;
···
 	}
 	of_node_put(np);
 
-	drv->opp_tables = kcalloc(num_possible_cpus(), sizeof(*drv->opp_tables),
+	drv->names_opp_tables = kcalloc(num_possible_cpus(),
+				  sizeof(*drv->names_opp_tables),
 				  GFP_KERNEL);
-	if (!drv->opp_tables) {
+	if (!drv->names_opp_tables) {
 		ret = -ENOMEM;
 		goto free_drv;
+	}
+	drv->hw_opp_tables = kcalloc(num_possible_cpus(),
+				  sizeof(*drv->hw_opp_tables),
+				  GFP_KERNEL);
+	if (!drv->hw_opp_tables) {
+		ret = -ENOMEM;
+		goto free_opp_names;
 	}
 
 	drv->genpd_opp_tables = kcalloc(num_possible_cpus(),
···
 		}
 
 		if (drv->data->get_version) {
-			drv->opp_tables[cpu] =
-				dev_pm_opp_set_supported_hw(cpu_dev,
-							    &drv->versions, 1);
-			if (IS_ERR(drv->opp_tables[cpu])) {
-				ret = PTR_ERR(drv->opp_tables[cpu]);
+
+			if (pvs_name) {
+				drv->names_opp_tables[cpu] = dev_pm_opp_set_prop_name(
+								     cpu_dev,
+								     pvs_name);
+				if (IS_ERR(drv->names_opp_tables[cpu])) {
+					ret = PTR_ERR(drv->names_opp_tables[cpu]);
+					dev_err(cpu_dev, "Failed to add OPP name %s\n",
+						pvs_name);
+					goto free_opp;
+				}
+			}
+
+			drv->hw_opp_tables[cpu] = dev_pm_opp_set_supported_hw(
+									 cpu_dev, &drv->versions, 1);
+			if (IS_ERR(drv->hw_opp_tables[cpu])) {
+				ret = PTR_ERR(drv->hw_opp_tables[cpu]);
 				dev_err(cpu_dev,
 					"Failed to set supported hardware\n");
 				goto free_genpd_opp;
···
 	kfree(drv->genpd_opp_tables);
 free_opp:
 	for_each_possible_cpu(cpu) {
-		if (IS_ERR_OR_NULL(drv->opp_tables[cpu]))
+		if (IS_ERR_OR_NULL(drv->names_opp_tables[cpu]))
 			break;
-		dev_pm_opp_put_supported_hw(drv->opp_tables[cpu]);
+		dev_pm_opp_put_prop_name(drv->names_opp_tables[cpu]);
 	}
-	kfree(drv->opp_tables);
+	for_each_possible_cpu(cpu) {
+		if (IS_ERR_OR_NULL(drv->hw_opp_tables[cpu]))
+			break;
+		dev_pm_opp_put_supported_hw(drv->hw_opp_tables[cpu]);
+	}
+	kfree(drv->hw_opp_tables);
+free_opp_names:
+	kfree(drv->names_opp_tables);
 free_drv:
 	kfree(drv);
 
···
 	platform_device_unregister(cpufreq_dt_pdev);
 
 	for_each_possible_cpu(cpu) {
-		if (drv->opp_tables[cpu])
-			dev_pm_opp_put_supported_hw(drv->opp_tables[cpu]);
+		if (drv->names_opp_tables[cpu])
+			dev_pm_opp_put_supported_hw(drv->names_opp_tables[cpu]);
+		if (drv->hw_opp_tables[cpu])
+			dev_pm_opp_put_supported_hw(drv->hw_opp_tables[cpu]);
 		if (drv->genpd_opp_tables[cpu])
 			dev_pm_opp_detach_genpd(drv->genpd_opp_tables[cpu]);
 	}
 
-	kfree(drv->opp_tables);
+	kfree(drv->names_opp_tables);
+	kfree(drv->hw_opp_tables);
 	kfree(drv->genpd_opp_tables);
 	kfree(drv);
 
···
 	{ .compatible = "qcom,apq8096", .data = &match_data_kryo },
 	{ .compatible = "qcom,msm8996", .data = &match_data_kryo },
 	{ .compatible = "qcom,qcs404", .data = &match_data_qcs404 },
+	{ .compatible = "qcom,ipq8064", .data = &match_data_krait },
+	{ .compatible = "qcom,apq8064", .data = &match_data_krait },
+	{ .compatible = "qcom,msm8974", .data = &match_data_krait },
+	{ .compatible = "qcom,msm8960", .data = &match_data_krait },
 	{},
 };
 

drivers/cpufreq/ti-cpufreq.c

···
 
 #define DRA7_EFUSE_HAS_OD_MPU_OPP		11
 #define DRA7_EFUSE_HAS_HIGH_MPU_OPP		15
+#define DRA76_EFUSE_HAS_PLUS_MPU_OPP		18
 #define DRA7_EFUSE_HAS_ALL_MPU_OPP		23
+#define DRA76_EFUSE_HAS_ALL_MPU_OPP		24
 
 #define DRA7_EFUSE_NOM_MPU_OPP			BIT(0)
 #define DRA7_EFUSE_OD_MPU_OPP			BIT(1)
 #define DRA7_EFUSE_HIGH_MPU_OPP			BIT(2)
+#define DRA76_EFUSE_PLUS_MPU_OPP		BIT(3)
 
 #define OMAP3_CONTROL_DEVICE_STATUS		0x4800244C
 #define OMAP3_CONTROL_IDCODE			0x4830A204
···
 	 */
 
 	switch (efuse) {
+	case DRA76_EFUSE_HAS_PLUS_MPU_OPP:
+	case DRA76_EFUSE_HAS_ALL_MPU_OPP:
+		calculated_efuse |= DRA76_EFUSE_PLUS_MPU_OPP;
+		/* Fall through */
 	case DRA7_EFUSE_HAS_ALL_MPU_OPP:
 	case DRA7_EFUSE_HAS_HIGH_MPU_OPP:
 		calculated_efuse |= DRA7_EFUSE_HIGH_MPU_OPP;

drivers/cpuidle/cpuidle-haltpoll.c

···
 #include <linux/kvm_para.h>
 #include <linux/cpuidle_haltpoll.h>
 
+static bool force __read_mostly;
+module_param(force, bool, 0444);
+MODULE_PARM_DESC(force, "Load unconditionally");
+
 static struct cpuidle_device __percpu *haltpoll_cpuidle_devices;
 static enum cpuhp_state haltpoll_hp_state;
 
···
 	haltpoll_cpuidle_devices = NULL;
 }
 
+static bool haltpool_want(void)
+{
+	return kvm_para_has_hint(KVM_HINTS_REALTIME) || force;
+}
+
 static int __init haltpoll_init(void)
 {
 	int ret;
···
 
 	cpuidle_poll_state_init(drv);
 
-	if (!kvm_para_available() ||
-		!kvm_para_has_hint(KVM_HINTS_REALTIME))
+	if (!kvm_para_available() || !haltpool_want())
 		return -ENODEV;
 
 	ret = cpuidle_register_driver(drv);

drivers/cpuidle/cpuidle-psci.c

···
 	return 0;
 }
 
+static int __init psci_dt_cpu_init_topology(struct cpuidle_driver *drv,
+					    struct psci_cpuidle_data *data,
+					    unsigned int state_count, int cpu)
+{
+	/* Currently limit the hierarchical topology to be used in OSI mode. */
+	if (!psci_has_osi_support())
+		return 0;
+
+	data->dev = psci_dt_attach_cpu(cpu);
+	if (IS_ERR_OR_NULL(data->dev))
+		return PTR_ERR_OR_ZERO(data->dev);
+
+	/*
+	 * Using the deepest state for the CPU to trigger a potential selection
+	 * of a shared state for the domain, assumes the domain states are all
+	 * deeper states.
+	 */
+	drv->states[state_count - 1].enter = psci_enter_domain_idle_state;
+	psci_cpuidle_use_cpuhp = true;
+
+	return 0;
+}
+
 static int __init psci_dt_cpu_init_idle(struct cpuidle_driver *drv,
 					struct device_node *cpu_node,
 					unsigned int state_count, int cpu)
···
 		goto free_mem;
 	}
 
-	/* Currently limit the hierarchical topology to be used in OSI mode. */
-	if (psci_has_osi_support()) {
-		data->dev = psci_dt_attach_cpu(cpu);
-		if (IS_ERR(data->dev)) {
-			ret = PTR_ERR(data->dev);
-			goto free_mem;
-		}
-
-		/*
-		 * Using the deepest state for the CPU to trigger a potential
-		 * selection of a shared state for the domain, assumes the
-		 * domain states are all deeper states.
-		 */
-		if (data->dev) {
-			drv->states[state_count - 1].enter =
-				psci_enter_domain_idle_state;
-			psci_cpuidle_use_cpuhp = true;
-		}
-	}
+	/* Initialize optional data, used for the hierarchical topology. */
+	ret = psci_dt_cpu_init_topology(drv, data, state_count, cpu);
+	if (ret < 0)
+		goto free_mem;
 
 	/* Idle states parsed correctly, store them in the per-cpu struct. */
 	data->psci_states = psci_states;

drivers/cpuidle/cpuidle.c

···
 }
 EXPORT_SYMBOL_GPL(cpuidle_register);
 
-#ifdef CONFIG_SMP
-
-/*
- * This function gets called when a part of the kernel has a new latency
- * requirement.  This means we need to get all processors out of their C-state,
- * and then recalculate a new suitable C-state. Just do a cross-cpu IPI; that
- * wakes them all right up.
- */
-static int cpuidle_latency_notify(struct notifier_block *b,
-		unsigned long l, void *v)
-{
-	wake_up_all_idle_cpus();
-	return NOTIFY_OK;
-}
-
-static struct notifier_block cpuidle_latency_notifier = {
-	.notifier_call = cpuidle_latency_notify,
-};
-
-static inline void latency_notifier_init(struct notifier_block *n)
-{
-	pm_qos_add_notifier(PM_QOS_CPU_DMA_LATENCY, n);
-}
-
-#else /* CONFIG_SMP */
-
-#define latency_notifier_init(x) do { } while (0)
-
-#endif /* CONFIG_SMP */
-
 /**
  * cpuidle_init - core initializer
  */
 static int __init cpuidle_init(void)
 {
-	int ret;
-
 	if (cpuidle_disabled())
 		return -ENODEV;
 
-	ret = cpuidle_add_interface(cpu_subsys.dev_root);
-	if (ret)
-		return ret;
-
-	latency_notifier_init(&cpuidle_latency_notifier);
-
-	return 0;
+	return cpuidle_add_interface(cpu_subsys.dev_root);
 }
 
 module_param(off, int, 0444);

drivers/cpuidle/governor.c

···
  */
 s64 cpuidle_governor_latency_req(unsigned int cpu)
 {
-	int global_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
 	struct device *device = get_cpu_device(cpu);
 	int device_req = dev_pm_qos_raw_resume_latency(device);
+	int global_req = cpu_latency_qos_limit();
 
 	if (device_req > global_req)
 		device_req = global_req;

drivers/devfreq/devfreq.c

···
 EXPORT_SYMBOL(devfreq_monitor_resume);
 
 /**
- * devfreq_interval_update() - Update device devfreq monitoring interval
+ * devfreq_update_interval() - Update device devfreq monitoring interval
  * @devfreq:    the devfreq instance.
  * @delay:      new polling interval to be set.
  *
  * Helper function to set new load monitoring polling interval. Function
- * to be called from governor in response to DEVFREQ_GOV_INTERVAL event.
+ * to be called from governor in response to DEVFREQ_GOV_UPDATE_INTERVAL event.
  */
-void devfreq_interval_update(struct devfreq *devfreq, unsigned int *delay)
+void devfreq_update_interval(struct devfreq *devfreq, unsigned int *delay)
 {
 	unsigned int cur_delay = devfreq->profile->polling_ms;
 	unsigned int new_delay = *delay;
···
 out:
 	mutex_unlock(&devfreq->lock);
 }
-EXPORT_SYMBOL(devfreq_interval_update);
+EXPORT_SYMBOL(devfreq_update_interval);
 
 /**
  * devfreq_notifier_call() - Notify that the device frequency requirements
···
 
 	if (dev_pm_qos_request_active(&devfreq->user_max_freq_req)) {
 		err = dev_pm_qos_remove_request(&devfreq->user_max_freq_req);
-		if (err)
+		if (err < 0)
 			dev_warn(dev->parent,
 				"Failed to remove max_freq request: %d\n", err);
 	}
 	if (dev_pm_qos_request_active(&devfreq->user_min_freq_req)) {
 		err = dev_pm_qos_remove_request(&devfreq->user_min_freq_req);
-		if (err)
+		if (err < 0)
 			dev_warn(dev->parent,
 				"Failed to remove min_freq request: %d\n", err);
 	}
···
 	if (ret != 1)
 		return -EINVAL;
 
-	df->governor->event_handler(df, DEVFREQ_GOV_INTERVAL, &value);
+	df->governor->event_handler(df, DEVFREQ_GOV_UPDATE_INTERVAL, &value);
 	ret = count;
 
 	return ret;

drivers/devfreq/governor.h

···
 /* Devfreq events */
 #define DEVFREQ_GOV_START			0x1
 #define DEVFREQ_GOV_STOP			0x2
-#define DEVFREQ_GOV_INTERVAL			0x3
+#define DEVFREQ_GOV_UPDATE_INTERVAL		0x3
 #define DEVFREQ_GOV_SUSPEND			0x4
 #define DEVFREQ_GOV_RESUME			0x5
 
···
  * @node:		list node - contains registered devfreq governors
  * @name:		Governor's name
  * @immutable:		Immutable flag for governor. If the value is 1,
- *			this govenror is never changeable to other governor.
+ *			this governor is never changeable to other governor.
  * @interrupt_driven:	Devfreq core won't schedule polling work for this
  *			governor if value is set to 1.
  * @get_target_freq:	Returns desired operating frequency for the device.
···
 				unsigned int event, void *data);
 };
 
-extern void devfreq_monitor_start(struct devfreq *devfreq);
-extern void devfreq_monitor_stop(struct devfreq *devfreq);
-extern void devfreq_monitor_suspend(struct devfreq *devfreq);
-extern void devfreq_monitor_resume(struct devfreq *devfreq);
-extern void devfreq_interval_update(struct devfreq *devfreq,
-					unsigned int *delay);
+void devfreq_monitor_start(struct devfreq *devfreq);
+void devfreq_monitor_stop(struct devfreq *devfreq);
+void devfreq_monitor_suspend(struct devfreq *devfreq);
+void devfreq_monitor_resume(struct devfreq *devfreq);
+void devfreq_update_interval(struct devfreq *devfreq, unsigned int *delay);
 
-extern int devfreq_add_governor(struct devfreq_governor *governor);
-extern int devfreq_remove_governor(struct devfreq_governor *governor);
+int devfreq_add_governor(struct devfreq_governor *governor);
+int devfreq_remove_governor(struct devfreq_governor *governor);
 
-extern int devfreq_update_status(struct devfreq *devfreq, unsigned long freq);
+int devfreq_update_status(struct devfreq *devfreq, unsigned long freq);
 
 static inline int devfreq_update_stats(struct devfreq *df)
 {

drivers/devfreq/governor_simpleondemand.c

···
 		devfreq_monitor_stop(devfreq);
 		break;
 
-	case DEVFREQ_GOV_INTERVAL:
-		devfreq_interval_update(devfreq, (unsigned int *)data);
+	case DEVFREQ_GOV_UPDATE_INTERVAL:
+		devfreq_update_interval(devfreq, (unsigned int *)data);
 		break;
 
 	case DEVFREQ_GOV_SUSPEND:

drivers/devfreq/governor_userspace.c

···
 }
 
 static struct devfreq_governor devfreq_userspace = {
-	.name = "userspace",
+	.name = DEVFREQ_GOV_USERSPACE,
 	.get_target_freq = devfreq_userspace_func,
 	.event_handler = devfreq_userspace_handler,
 };

drivers/devfreq/tegra30-devfreq.c

···
 		devfreq_monitor_stop(devfreq);
 		break;
 
-	case DEVFREQ_GOV_INTERVAL:
+	case DEVFREQ_GOV_UPDATE_INTERVAL:
 		/*
 		 * ACTMON hardware supports up to 256 milliseconds for the
 		 * sampling period.
···
 		}
 
 		tegra_actmon_pause(tegra);
-		devfreq_interval_update(devfreq, new_delay);
+		devfreq_update_interval(devfreq, new_delay);
 		ret = tegra_actmon_resume(tegra);
 		break;
 

drivers/gpu/drm/i915/display/intel_dp.c

···
 	 * lowest possible wakeup latency and so prevent the cpu from going into
 	 * deep sleep states.
 	 */
-	pm_qos_update_request(&i915->pm_qos, 0);
+	cpu_latency_qos_update_request(&i915->pm_qos, 0);
 
 	intel_dp_check_edp(intel_dp);
 
···
 
 	ret = recv_bytes;
 out:
-	pm_qos_update_request(&i915->pm_qos, PM_QOS_DEFAULT_VALUE);
+	cpu_latency_qos_update_request(&i915->pm_qos, PM_QOS_DEFAULT_VALUE);
 
 	if (vdd)
 		edp_panel_vdd_off(intel_dp, false);

drivers/gpu/drm/i915/i915_drv.c

···
 	mutex_init(&dev_priv->backlight_lock);
 
 	mutex_init(&dev_priv->sb_lock);
-	pm_qos_add_request(&dev_priv->sb_qos,
-			   PM_QOS_CPU_DMA_LATENCY, PM_QOS_DEFAULT_VALUE);
+	cpu_latency_qos_add_request(&dev_priv->sb_qos, PM_QOS_DEFAULT_VALUE);
 
 	mutex_init(&dev_priv->av_mutex);
 	mutex_init(&dev_priv->wm.wm_mutex);
···
 	vlv_free_s0ix_state(dev_priv);
 	i915_workqueues_cleanup(dev_priv);
 
-	pm_qos_remove_request(&dev_priv->sb_qos);
+	cpu_latency_qos_remove_request(&dev_priv->sb_qos);
 	mutex_destroy(&dev_priv->sb_lock);
 }
 
···
 		}
 	}
 
-	pm_qos_add_request(&dev_priv->pm_qos, PM_QOS_CPU_DMA_LATENCY,
-			   PM_QOS_DEFAULT_VALUE);
+	cpu_latency_qos_add_request(&dev_priv->pm_qos, PM_QOS_DEFAULT_VALUE);
 
 	intel_gt_init_workarounds(dev_priv);
 
···
 err_msi:
 	if (pdev->msi_enabled)
 		pci_disable_msi(pdev);
-	pm_qos_remove_request(&dev_priv->pm_qos);
+	cpu_latency_qos_remove_request(&dev_priv->pm_qos);
 err_mem_regions:
 	intel_memory_regions_driver_release(dev_priv);
 err_ggtt:
···
 	if (pdev->msi_enabled)
 		pci_disable_msi(pdev);
 
-	pm_qos_remove_request(&dev_priv->pm_qos);
+	cpu_latency_qos_remove_request(&dev_priv->pm_qos);
 }
 
 /**

drivers/gpu/drm/i915/intel_sideband.c

···
 	 * to the Valleyview P-unit and not all sideband communications.
 	 */
 	if (IS_VALLEYVIEW(i915)) {
-		pm_qos_update_request(&i915->sb_qos, 0);
+		cpu_latency_qos_update_request(&i915->sb_qos, 0);
 		on_each_cpu(ping, NULL, 1);
 	}
 }
···
 static void __vlv_punit_put(struct drm_i915_private *i915)
 {
 	if (IS_VALLEYVIEW(i915))
-		pm_qos_update_request(&i915->sb_qos, PM_QOS_DEFAULT_VALUE);
+		cpu_latency_qos_update_request(&i915->sb_qos,
+					       PM_QOS_DEFAULT_VALUE);
 
 	iosf_mbi_punit_release();
 }

drivers/hsi/clients/cmt_speech.c

···
 
 	if (old_state != hi->iface_state) {
 		if (hi->iface_state == CS_STATE_CONFIGURED) {
-			pm_qos_add_request(&hi->pm_qos_req,
-				PM_QOS_CPU_DMA_LATENCY,
+			cpu_latency_qos_add_request(&hi->pm_qos_req,
 				CS_QOS_LATENCY_FOR_DATA_USEC);
 			local_bh_disable();
 			cs_hsi_read_on_data(hi);
 			local_bh_enable();
 		} else if (old_state == CS_STATE_CONFIGURED) {
-			pm_qos_remove_request(&hi->pm_qos_req);
+			cpu_latency_qos_remove_request(&hi->pm_qos_req);
 		}
 	}
 	return r;
···
 	WARN_ON(!cs_state_idle(hi->control_state));
 	WARN_ON(!cs_state_idle(hi->data_state));
 
-	if (pm_qos_request_active(&hi->pm_qos_req))
-		pm_qos_remove_request(&hi->pm_qos_req);
+	if (cpu_latency_qos_request_active(&hi->pm_qos_req))
+		cpu_latency_qos_remove_request(&hi->pm_qos_req);
 
 	spin_lock_bh(&hi->lock);
 	cs_hsi_free_data(hi);

drivers/idle/intel_idle.c

···
 /*
  * intel_idle.c - native hardware idle loop for modern Intel processors
  *
- * Copyright (c) 2013, Intel Corporation.
+ * Copyright (c) 2013 - 2020, Intel Corporation.
  * Len Brown <[e-mail]>
+ * Rafael J. Wysocki <[e-mail]>
  */
 
 /*
···
 
 /*
  * Known limitations
- *
- * The driver currently initializes for_each_online_cpu() upon modprobe.
- * It it unaware of subsequent processors hot-added to the system.
- * This means that if you boot with maxcpus=n and later online
- * processors above n, those processors will use C1 only.
  *
  * ACPI has a .suspend hack to turn off deep c-statees during suspend
  * to avoid complications with the lapic timer workaround.
···
 #include <asm/mwait.h>
 #include <asm/msr.h>
 
-#define INTEL_IDLE_VERSION "0.4.1"
+#define INTEL_IDLE_VERSION "0.5.1"
 
 static struct cpuidle_driver intel_idle_driver = {
 	.name = "intel_idle",
···
 static int max_cstate = CPUIDLE_STATE_MAX - 1;
 static unsigned int disabled_states_mask;
 
-static unsigned int mwait_substates;
+static struct cpuidle_device __percpu *intel_idle_cpuidle_devices;
 
-#define LAPIC_TIMER_ALWAYS_RELIABLE 0xFFFFFFFF
-/* Reliable LAPIC Timer States, bit 1 for C1 etc.  */
-static unsigned int lapic_timer_reliable_states = (1 << 1);	 /* Default to only C1 */
+static unsigned long auto_demotion_disable_flags;
+static bool disable_promotion_to_c1e;
+
+static bool lapic_timer_always_reliable;
 
 struct idle_cpu {
 	struct cpuidle_state *state_table;
···
 	bool use_acpi;
 };
 
-static const struct idle_cpu *icpu;
-static struct cpuidle_device __percpu *intel_idle_cpuidle_devices;
-static int intel_idle(struct cpuidle_device *dev,
-			struct cpuidle_driver *drv, int index);
-static void intel_idle_s2idle(struct cpuidle_device *dev,
-			      struct cpuidle_driver *drv, int index);
-static struct cpuidle_state *cpuidle_state_table;
+static const struct idle_cpu *icpu __initdata;
+static struct cpuidle_state *cpuidle_state_table __initdata;
+
+static unsigned int mwait_substates __initdata;
 
 /*
  * Enable this state by default even if the ACPI _CST does not list it.
···
  * If this flag is set, SW flushes the TLB, so even if the
  * HW doesn't do the flushing, this flag is safe to use.
  */
-#define CPUIDLE_FLAG_TLB_FLUSHED	0x10000
+#define CPUIDLE_FLAG_TLB_FLUSHED	BIT(16)
 
 /*
  * MWAIT takes an 8-bit "hint" in EAX "suggesting"
···
 #define flg2MWAIT(flags) (((flags) >> 24) & 0xFF)
 #define MWAIT2flg(eax) ((eax & 0xFF) << 24)
 
+/**
+ * intel_idle - Ask the processor to enter the given idle state.
+ * @dev: cpuidle device of the target CPU.
+ * @drv: cpuidle driver (assumed to point to intel_idle_driver).
+ * @index: Target idle state index.
+ *
+ * Use the MWAIT instruction to notify the processor that the CPU represented by
+ * @dev is idle and it can try to enter the idle state corresponding to @index.
+ *
+ * If the local APIC timer is not known to be reliable in the target idle state,
+ * enable one-shot tick broadcasting for the target CPU before executing MWAIT.
+ *
+ * Optionally call leave_mm() for the target CPU upfront to avoid wakeups due to
+ * flushing user TLBs.
+ *
+ * Must be called under local_irq_disable().
+ */
+static __cpuidle int intel_idle(struct cpuidle_device *dev,
+				struct cpuidle_driver *drv, int index)
+{
+	struct cpuidle_state *state = &drv->states[index];
+	unsigned long eax = flg2MWAIT(state->flags);
+	unsigned long ecx = 1; /* break on interrupt flag */
+	bool uninitialized_var(tick);
+	int cpu = smp_processor_id();
+
+	/*
+	 * leave_mm() to avoid costly and often unnecessary wakeups
+	 * for flushing the user TLB's associated with the active mm.
+	 */
+	if (state->flags & CPUIDLE_FLAG_TLB_FLUSHED)
+		leave_mm(cpu);
+
+	if (!static_cpu_has(X86_FEATURE_ARAT) && !lapic_timer_always_reliable) {
+		/*
+		 * Switch over to one-shot tick broadcast if the target C-state
+		 * is deeper than C1.
+		 */
+		if ((eax >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK) {
+			tick = true;
+			tick_broadcast_enter();
+		} else {
+			tick = false;
+		}
+	}
+
+	mwait_idle_with_hints(eax, ecx);
+
+	if (!static_cpu_has(X86_FEATURE_ARAT) && tick)
+		tick_broadcast_exit();
+
+	return index;
+}
+
+/**
+ * intel_idle_s2idle - Ask the processor to enter the given idle state.
+ * @dev: cpuidle device of the target CPU.
+ * @drv: cpuidle driver (assumed to point to intel_idle_driver).
+ * @index: Target idle state index.
+ *
+ * Use the MWAIT instruction to notify the processor that the CPU represented by
+ * @dev is idle and it can try to enter the idle state corresponding to @index.
+ *
+ * Invoked as a suspend-to-idle callback routine with frozen user space, frozen
+ * scheduler tick and suspended scheduler clock on the target CPU.
+ */
+static __cpuidle void intel_idle_s2idle(struct cpuidle_device *dev,
+					struct cpuidle_driver *drv, int index)
+{
+	unsigned long eax = flg2MWAIT(drv->states[index].flags);
+	unsigned long ecx = 1; /* break on interrupt flag */
+
+	mwait_idle_with_hints(eax, ecx);
+}
+
 /*
  * States are indexed by the cstate number,
  * which is also the index into the MWAIT hint array.
  * Thus C0 is a dummy.
  */
-static struct cpuidle_state nehalem_cstates[] = {
+static struct cpuidle_state nehalem_cstates[] __initdata = {
 	{
 		.name = "C1",
 		.desc = "MWAIT 0x00",
···
 		.enter = NULL }
 };
 
-static struct cpuidle_state snb_cstates[] = {
+static struct cpuidle_state snb_cstates[] __initdata = {
 	{
 		.name = "C1",
 		.desc = "MWAIT 0x00",
···
 		.enter = NULL }
 };
 
-static struct cpuidle_state byt_cstates[] = {
+static struct cpuidle_state byt_cstates[] __initdata = {
 	{
 		.name = "C1",
 		.desc = "MWAIT 0x00",
···
 		.enter = NULL }
 };
 
-static struct cpuidle_state cht_cstates[] = {
+static struct cpuidle_state cht_cstates[] __initdata = {
 	{
 		.name = "C1",
 		.desc = "MWAIT 0x00",
···
 		.enter = NULL }
 };
 
-static struct cpuidle_state ivb_cstates[] = {
+static struct cpuidle_state ivb_cstates[] __initdata = {
 	{
 		.name = "C1",
 		.desc = "MWAIT 0x00",
···
 		.enter = NULL }
 };
 
-static struct cpuidle_state ivt_cstates[] = {
+static struct cpuidle_state ivt_cstates[] __initdata = {
 	{
 		.name = "C1",
 		.desc = "MWAIT 0x00",
···
 		.enter = NULL }
 };
 
-static struct cpuidle_state ivt_cstates_4s[] = {
+static struct cpuidle_state ivt_cstates_4s[] __initdata = {
 	{
 		.name = "C1",
 		.desc = "MWAIT 0x00",
···
 		.enter = NULL }
 };
 
-static struct cpuidle_state ivt_cstates_8s[] = {
+static struct cpuidle_state ivt_cstates_8s[] __initdata = {
 	{
 		.name = "C1",
 		.desc = "MWAIT 0x00",
···
 		.enter = NULL }
 };
 
-static struct cpuidle_state hsw_cstates[] = {
+static struct cpuidle_state hsw_cstates[] __initdata = {
 	{
 		.name = "C1",
 		.desc = "MWAIT 0x00",
···
 	{
 		.enter = NULL }
 };
-static struct cpuidle_state bdw_cstates[] = {
+static struct cpuidle_state bdw_cstates[] __initdata = {
 	{
 		.name = "C1",
 		.desc = "MWAIT 0x00",
···
 		.enter = NULL }
 };
 
-static struct cpuidle_state skl_cstates[] = {
+static struct cpuidle_state skl_cstates[] __initdata = {
 	{
 		.name = "C1",
 		.desc = "MWAIT 0x00",
···
 		.enter = NULL }
 };
 
-static struct cpuidle_state skx_cstates[] = {
+static struct cpuidle_state skx_cstates[] __initdata = {
 	{
 		.name = "C1",
 		.desc = "MWAIT 0x00",
···
 		.enter = NULL }
 };
 
-static struct cpuidle_state atom_cstates[] = {
+static struct cpuidle_state atom_cstates[] __initdata = {
 	{
 		.name = "C1E",
 		.desc = "MWAIT 0x00",
···
 	{
 		.enter = NULL }
 };
-static struct cpuidle_state tangier_cstates[] = {
+static struct cpuidle_state tangier_cstates[] __initdata = {
 	{
 		.name = "C1",
 		.desc = "MWAIT 0x00",
···
 	{
 		.enter = NULL }
 };
-static struct cpuidle_state avn_cstates[] = {
+static struct cpuidle_state avn_cstates[] __initdata = {
 	{
 		.name = "C1",
 		.desc = "MWAIT 0x00",
···
 	{
 		.enter = NULL }
 };
-static struct cpuidle_state knl_cstates[] = {
+static struct cpuidle_state knl_cstates[] __initdata = {
 	{
 		.name = "C1",
 		.desc = "MWAIT 0x00",
···
 		.enter = NULL }
 };
 
-static struct cpuidle_state bxt_cstates[] = {
+static struct cpuidle_state bxt_cstates[] __initdata = {
 	{
 		.name = "C1",
 		.desc = "MWAIT 0x00",
···
 		.enter = NULL }
 };
 
-static struct cpuidle_state dnv_cstates[] = {
+static struct cpuidle_state dnv_cstates[] __initdata = {
 	{
 		.name = "C1",
 		.desc = "MWAIT 0x00",
···
 		.enter = NULL }
 };
 
-/**
- * intel_idle
- * @dev: cpuidle_device
- * @drv: cpuidle driver
- * @index: index of cpuidle state
- *
- * Must be called under local_irq_disable().
- */
-static __cpuidle int intel_idle(struct cpuidle_device *dev,
-				struct cpuidle_driver *drv, int index)
-{
-	unsigned long ecx = 1; /* break on interrupt flag */
-	struct cpuidle_state *state = &drv->states[index];
-	unsigned long eax = flg2MWAIT(state->flags);
-	unsigned int cstate;
-	bool uninitialized_var(tick);
-	int cpu = smp_processor_id();
-
-	/*
-	 * leave_mm() to avoid costly and often unnecessary wakeups
-	 * for flushing the user TLB's associated with the active mm.
-	 */
-	if (state->flags & CPUIDLE_FLAG_TLB_FLUSHED)
-		leave_mm(cpu);
-
-	if (!static_cpu_has(X86_FEATURE_ARAT)) {
-		cstate = (((eax) >> MWAIT_SUBSTATE_SIZE) &
-				MWAIT_CSTATE_MASK) + 1;
-		tick = false;
-		if (!(lapic_timer_reliable_states & (1 << (cstate)))) {
-			tick = true;
-			tick_broadcast_enter();
-		}
-	}
-
-	mwait_idle_with_hints(eax, ecx);
-
-	if (!static_cpu_has(X86_FEATURE_ARAT) && tick)
-		tick_broadcast_exit();
-
-	return index;
-}
-
-/**
- * intel_idle_s2idle - simplified "enter" callback routine for suspend-to-idle
- * @dev: cpuidle_device
- * @drv: cpuidle driver
- * @index: state index
- */
-static void intel_idle_s2idle(struct cpuidle_device *dev,
-			     struct cpuidle_driver *drv, int index)
-{
-	unsigned long ecx = 1; /* break on interrupt flag */
-	unsigned long eax = flg2MWAIT(drv->states[index].flags);
-
-	mwait_idle_with_hints(eax, ecx);
-}
-
-static const struct idle_cpu idle_cpu_nehalem = {
+static const struct idle_cpu idle_cpu_nehalem __initconst = {
 	.state_table = nehalem_cstates,
 	.auto_demotion_disable_flags = NHM_C1_AUTO_DEMOTE | NHM_C3_AUTO_DEMOTE,
 	.disable_promotion_to_c1e = true,
 };
 
-static const struct idle_cpu idle_cpu_nhx = {
+static const struct idle_cpu idle_cpu_nhx __initconst = {
 	.state_table = nehalem_cstates,
 	.auto_demotion_disable_flags = NHM_C1_AUTO_DEMOTE | NHM_C3_AUTO_DEMOTE,
 	.disable_promotion_to_c1e = true,
 	.use_acpi = true,
 };
 
-static const struct idle_cpu idle_cpu_atom = {
+static const struct idle_cpu idle_cpu_atom __initconst = {
 	.state_table = atom_cstates,
 };
 
-static const struct idle_cpu idle_cpu_tangier = {
+static const struct idle_cpu idle_cpu_tangier __initconst = {
 	.state_table = tangier_cstates,
 };
 
-static const struct idle_cpu idle_cpu_lincroft = {
+static const struct idle_cpu idle_cpu_lincroft __initconst = {
 	.state_table = atom_cstates,
 	.auto_demotion_disable_flags = ATM_LNC_C6_AUTO_DEMOTE,
 };
 
-static const struct idle_cpu idle_cpu_snb = {
+static const struct idle_cpu idle_cpu_snb __initconst = {
 	.state_table = snb_cstates,
 	.disable_promotion_to_c1e = true,
 };
 
-static const struct idle_cpu idle_cpu_snx = {
+static const struct idle_cpu idle_cpu_snx __initconst = {
 	.state_table = snb_cstates,
 	.disable_promotion_to_c1e = true,
 	.use_acpi = true,
 };
 
-static const struct idle_cpu idle_cpu_byt = {
+static const struct idle_cpu idle_cpu_byt __initconst = {
 	.state_table = byt_cstates,
 	.disable_promotion_to_c1e = true,
 	.byt_auto_demotion_disable_flag = true,
 };
 
-static const struct idle_cpu idle_cpu_cht = {
+static const struct idle_cpu idle_cpu_cht __initconst = {
 	.state_table = cht_cstates,
 	.disable_promotion_to_c1e = true,
 	.byt_auto_demotion_disable_flag = true,
 };
 
-static const struct idle_cpu idle_cpu_ivb = {
+static const struct idle_cpu idle_cpu_ivb __initconst = {
 	.state_table = ivb_cstates,
 	.disable_promotion_to_c1e = true,
 };
 
-static const struct idle_cpu idle_cpu_ivt = {
+static const struct idle_cpu idle_cpu_ivt __initconst = {
 	.state_table = ivt_cstates,
 	.disable_promotion_to_c1e = true,
 	.use_acpi = true,
 };
 
-static const struct idle_cpu idle_cpu_hsw = {
+static const struct idle_cpu idle_cpu_hsw __initconst = {
 	.state_table = hsw_cstates,
 	.disable_promotion_to_c1e = true,
 };
 
-static const struct idle_cpu idle_cpu_hsx = {
+static const struct idle_cpu idle_cpu_hsx __initconst = {
 	.state_table = hsw_cstates,
 	.disable_promotion_to_c1e = true,
 	.use_acpi = true,
 };
 
-static const struct idle_cpu idle_cpu_bdw = {
+static const struct idle_cpu idle_cpu_bdw __initconst = {
 	.state_table = bdw_cstates,
 	.disable_promotion_to_c1e = true,
 };
 
-static const struct idle_cpu idle_cpu_bdx = {
+static const struct idle_cpu idle_cpu_bdx __initconst = {
 	.state_table = bdw_cstates,
 	.disable_promotion_to_c1e = true,
 	.use_acpi = true,
 };
 
-static const struct idle_cpu idle_cpu_skl = {
+static const struct idle_cpu idle_cpu_skl __initconst = {
 	.state_table = skl_cstates,
 	.disable_promotion_to_c1e = true,
 };
 
-static const struct idle_cpu idle_cpu_skx = {
+static const struct idle_cpu idle_cpu_skx __initconst = {
 	.state_table = skx_cstates,
 	.disable_promotion_to_c1e = true,
 	.use_acpi = true,
 };
 
-static const struct idle_cpu idle_cpu_avn = {
+static const struct idle_cpu idle_cpu_avn __initconst = {
 	.state_table = avn_cstates,
 	.disable_promotion_to_c1e = true,
 	.use_acpi = true,
 };
 
-static const struct idle_cpu idle_cpu_knl = {
+static const struct idle_cpu idle_cpu_knl __initconst = {
 	.state_table = knl_cstates,
 	.use_acpi = true,
 };
 
-static const struct idle_cpu idle_cpu_bxt = {
+static const struct idle_cpu idle_cpu_bxt __initconst = {
 	.state_table = bxt_cstates,
 	.disable_promotion_to_c1e = true,
 };
 
-static const struct idle_cpu idle_cpu_dnv = {
+static const struct idle_cpu idle_cpu_dnv __initconst = {
 	.state_table = dnv_cstates,
 	.disable_promotion_to_c1e = true,
 	.use_acpi = true,
···
 static inline bool intel_idle_off_by_default(u32 mwait_hint) { return false; }
 #endif /* !CONFIG_ACPI_PROCESSOR_CSTATE */
 
-/*
- * ivt_idle_state_table_update(void)
+/**
+ * ivt_idle_state_table_update - Tune the idle states table for Ivy Town.
  *
- * Tune IVT multi-socket targets
- * Assumption: num_sockets == (max_package_num + 1)
+ * Tune IVT multi-socket targets.
+ * Assumption: num_sockets == (max_package_num + 1).
  */
 static void __init ivt_idle_state_table_update(void)
 {
···
 	return div_u64((irtl & 0x3FF) * ns, NSEC_PER_USEC);
 }
 
-/*
- * bxt_idle_state_table_update(void)
+/**
+ * bxt_idle_state_table_update - Fix up the Broxton idle states table.
  *
- * On BXT, we trust the IRTL to show the definitive maximum latency
- * We use the same value for target_residency.
+ * On BXT, trust the IRTL (Interrupt Response Time Limit) MSR to show the
+ * definitive maximum latency and use the same value for target_residency.
  */
 static void __init bxt_idle_state_table_update(void)
 {
···
 	}
 
 }
-/*
- * sklh_idle_state_table_update(void)
+
+/**
+ * sklh_idle_state_table_update - Fix up the Sky Lake idle states table.
  *
- * On SKL-H (model 0x5e) disable C8 and C9 if:
- * C10 is enabled and SGX disabled
+ * On SKL-H (model 0x5e) skip C8 and C9 if C10 is enabled and SGX disabled.
  */
 static void __init sklh_idle_state_table_update(void)
 {
···
 	}
 }
 
-/*
- * intel_idle_cpuidle_driver_init()
- * allocate, initialize cpuidle_states
+/**
+ * intel_idle_cpuidle_driver_init - Create the list of available idle states.
+ * @drv: cpuidle driver structure to initialize.
  */
 static void __init intel_idle_cpuidle_driver_init(struct cpuidle_driver *drv)
 {
···
 	unsigned long long msr_bits;
 
 	rdmsrl(MSR_PKG_CST_CONFIG_CONTROL, msr_bits);
-	msr_bits &= ~(icpu->auto_demotion_disable_flags);
+	msr_bits &= ~auto_demotion_disable_flags;
 	wrmsrl(MSR_PKG_CST_CONFIG_CONTROL, msr_bits);
 }
 
···
 	wrmsrl(MSR_IA32_POWER_CTL, msr_bits);
 }
 
-/*
- * intel_idle_cpu_init()
- * allocate, initialize, register cpuidle_devices
- * @cpu: cpu/core to initialize
+/**
+ * intel_idle_cpu_init - Register the target CPU with the cpuidle core.
+ * @cpu: CPU to initialize.
+ *
+ * Register a cpuidle device object for @cpu and update its MSRs in accordance
+ * with the processor model flags.
  */
 static int intel_idle_cpu_init(unsigned int cpu)
 {
···
 		return -EIO;
 	}
 
-	if (!icpu)
-		return 0;
-
-	if (icpu->auto_demotion_disable_flags)
+	if (auto_demotion_disable_flags)
 		auto_demotion_disable();
 
-	if (icpu->disable_promotion_to_c1e)
+	if (disable_promotion_to_c1e)
 		c1e_promotion_disable();
 
 	return 0;
···
 {
 	struct cpuidle_device *dev;
 
-	if (lapic_timer_reliable_states != LAPIC_TIMER_ALWAYS_RELIABLE)
+	if (!lapic_timer_always_reliable)
 		tick_broadcast_enable();
 
 	/*
···
 	icpu = (const struct idle_cpu *)id->driver_data;
 	if (icpu) {
 		cpuidle_state_table = icpu->state_table;
+		auto_demotion_disable_flags = icpu->auto_demotion_disable_flags;
+		disable_promotion_to_c1e = icpu->disable_promotion_to_c1e;
 		if (icpu->use_acpi || force_use_acpi)
 			intel_idle_acpi_cst_extract();
 	} else if (!intel_idle_acpi_cst_extract()) {
···
 	}
 
 	if (boot_cpu_has(X86_FEATURE_ARAT))	/* Always Reliable APIC Timer */
-		lapic_timer_reliable_states = LAPIC_TIMER_ALWAYS_RELIABLE;
+		lapic_timer_always_reliable = true;
 
 	retval = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "idle/intel:online",
 				   intel_idle_cpu_online, NULL);
 	if (retval < 0)
 		goto hp_setup_fail;
 
-	pr_debug("lapic_timer_reliable_states 0x%x\n",
-		 lapic_timer_reliable_states);
+	pr_debug("Local APIC timer is reliable in %s\n",
+		 lapic_timer_always_reliable ? "all C-states" : "C1");
 
 	return 0;
 

drivers/media/pci/saa7134/saa7134-video.c

···
 	 */
 	if ((dmaq == &dev->video_q && !vb2_is_streaming(&dev->vbi_vbq)) ||
 	    (dmaq == &dev->vbi_q && !vb2_is_streaming(&dev->video_vbq)))
-		pm_qos_add_request(&dev->qos_request,
-			PM_QOS_CPU_DMA_LATENCY, 20);
+		cpu_latency_qos_add_request(&dev->qos_request, 20);
 	dmaq->seq_nr = 0;
 
 	return 0;
···
 
 	if ((dmaq == &dev->video_q && !vb2_is_streaming(&dev->vbi_vbq)) ||
 	    (dmaq == &dev->vbi_q && !vb2_is_streaming(&dev->video_vbq)))
-		pm_qos_remove_request(&dev->qos_request);
+		cpu_latency_qos_remove_request(&dev->qos_request);
 }
 
 static const struct vb2_ops vb2_qops = {

drivers/media/platform/via-camera.c

···
 	 * requirement which will keep the CPU out of the deeper sleep
 	 * states.
 	 */
-	pm_qos_add_request(&cam->qos_request, PM_QOS_CPU_DMA_LATENCY, 50);
+	cpu_latency_qos_add_request(&cam->qos_request, 50);
 	viacam_start_engine(cam);
 	return 0;
 out:
···
 	struct via_camera *cam = vb2_get_drv_priv(vq);
 	struct via_buffer *buf, *tmp;
 
-	pm_qos_remove_request(&cam->qos_request);
+	cpu_latency_qos_remove_request(&cam->qos_request);
 	viacam_stop_engine(cam);
 
 	list_for_each_entry_safe(buf, tmp, &cam->buffer_queue, queue) {

drivers/mmc/host/sdhci-esdhc-imx.c

···
 						  pdev->id_entry->driver_data;
 
 	if (imx_data->socdata->flags & ESDHC_FLAG_PMQOS)
-		pm_qos_add_request(&imx_data->pm_qos_req,
-			PM_QOS_CPU_DMA_LATENCY, 0);
+		cpu_latency_qos_add_request(&imx_data->pm_qos_req, 0);
 
 	imx_data->clk_ipg = devm_clk_get(&pdev->dev, "ipg");
 	if (IS_ERR(imx_data->clk_ipg)) {
···
 	clk_disable_unprepare(imx_data->clk_per);
 free_sdhci:
 	if (imx_data->socdata->flags & ESDHC_FLAG_PMQOS)
-		pm_qos_remove_request(&imx_data->pm_qos_req);
+		cpu_latency_qos_remove_request(&imx_data->pm_qos_req);
 	sdhci_pltfm_free(pdev);
 	return err;
 }
···
 	clk_disable_unprepare(imx_data->clk_ahb);
 
 	if (imx_data->socdata->flags & ESDHC_FLAG_PMQOS)
-		pm_qos_remove_request(&imx_data->pm_qos_req);
+		cpu_latency_qos_remove_request(&imx_data->pm_qos_req);
 
 	sdhci_pltfm_free(pdev);
 
···
 	clk_disable_unprepare(imx_data->clk_ahb);
 
 	if (imx_data->socdata->flags & ESDHC_FLAG_PMQOS)
-		pm_qos_remove_request(&imx_data->pm_qos_req);
+		cpu_latency_qos_remove_request(&imx_data->pm_qos_req);
 
 	return ret;
 }
···
 	int err;
 
 	if (imx_data->socdata->flags & ESDHC_FLAG_PMQOS)
-		pm_qos_add_request(&imx_data->pm_qos_req,
-			PM_QOS_CPU_DMA_LATENCY, 0);
+		cpu_latency_qos_add_request(&imx_data->pm_qos_req, 0);
 
 	err = clk_prepare_enable(imx_data->clk_ahb);
 	if (err)
···
 	clk_disable_unprepare(imx_data->clk_ahb);
 remove_pm_qos_request:
 	if (imx_data->socdata->flags & ESDHC_FLAG_PMQOS)
-		pm_qos_remove_request(&imx_data->pm_qos_req);
+		cpu_latency_qos_remove_request(&imx_data->pm_qos_req);
 	return err;
 }
 #endif

drivers/net/ethernet/intel/e1000e/netdev.c

···
 
 		dev_info(&adapter->pdev->dev,
 			 "Some CPU C-states have been disabled in order to enable jumbo frames\n");
-		pm_qos_update_request(&adapter->pm_qos_req, lat);
+		cpu_latency_qos_update_request(&adapter->pm_qos_req, lat);
 	} else {
-		pm_qos_update_request(&adapter->pm_qos_req,
-				      PM_QOS_DEFAULT_VALUE);
+		cpu_latency_qos_update_request(&adapter->pm_qos_req,
+					       PM_QOS_DEFAULT_VALUE);
 	}
 
 	/* Enable Receives */
···
 		e1000_update_mng_vlan(adapter);
 
 	/* DMA latency requirement to workaround jumbo issue */
-	pm_qos_add_request(&adapter->pm_qos_req, PM_QOS_CPU_DMA_LATENCY,
-			   PM_QOS_DEFAULT_VALUE);
+	cpu_latency_qos_add_request(&adapter->pm_qos_req, PM_QOS_DEFAULT_VALUE);
 
 	/* before we allocate an interrupt, we must be ready to handle it.
 	 * Setting DEBUG_SHIRQ in the kernel makes it fire an interrupt
···
 	return 0;
 
 err_req_irq:
-	pm_qos_remove_request(&adapter->pm_qos_req);
+	cpu_latency_qos_remove_request(&adapter->pm_qos_req);
 	e1000e_release_hw_control(adapter);
 	e1000_power_down_phy(adapter);
 	e1000e_free_rx_resources(adapter->rx_ring);
···
 	    !test_bit(__E1000_TESTING, &adapter->state))
 		e1000e_release_hw_control(adapter);
 
-	pm_qos_remove_request(&adapter->pm_qos_req);
+	cpu_latency_qos_remove_request(&adapter->pm_qos_req);
 
 	pm_runtime_put_sync(&pdev->dev);
 

drivers/net/wireless/ath/ath10k/core.c

···
 	}
 
 	memset(&latency_qos, 0, sizeof(latency_qos));
-	pm_qos_add_request(&latency_qos, PM_QOS_CPU_DMA_LATENCY, 0);
+	cpu_latency_qos_add_request(&latency_qos, 0);
 
 	ret = ath10k_bmi_fast_download(ar, address, data, data_len);
 
-	pm_qos_remove_request(&latency_qos);
+	cpu_latency_qos_remove_request(&latency_qos);
 
 	return ret;
 }

drivers/net/wireless/intel/ipw2x00/ipw2100.c

···
 	/* the ipw2100 hardware really doesn't want power management delays
 	 * longer than 175usec
 	 */
-	pm_qos_update_request(&ipw2100_pm_qos_req, 175);
+	cpu_latency_qos_update_request(&ipw2100_pm_qos_req, 175);
 
 	/* If the interrupt is enabled, turn it off... */
 	spin_lock_irqsave(&priv->low_lock, flags);
···
 	ipw2100_disable_interrupts(priv);
 	spin_unlock_irqrestore(&priv->low_lock, flags);
 
-	pm_qos_update_request(&ipw2100_pm_qos_req, PM_QOS_DEFAULT_VALUE);
+	cpu_latency_qos_update_request(&ipw2100_pm_qos_req,
+				       PM_QOS_DEFAULT_VALUE);
 
 	/* We have to signal any supplicant if we are disassociating */
 	if (associated)
···
 	printk(KERN_INFO DRV_NAME ": %s, %s\n", DRV_DESCRIPTION, DRV_VERSION);
 	printk(KERN_INFO DRV_NAME ": %s\n", DRV_COPYRIGHT);
 
-	pm_qos_add_request(&ipw2100_pm_qos_req, PM_QOS_CPU_DMA_LATENCY,
-			   PM_QOS_DEFAULT_VALUE);
+	cpu_latency_qos_add_request(&ipw2100_pm_qos_req, PM_QOS_DEFAULT_VALUE);
 
 	ret = pci_register_driver(&ipw2100_pci_driver);
 	if (ret)
···
 			   &driver_attr_debug_level);
 #endif
 	pci_unregister_driver(&ipw2100_pci_driver);
-	pm_qos_remove_request(&ipw2100_pm_qos_req);
+	cpu_latency_qos_remove_request(&ipw2100_pm_qos_req);
 }
 
 module_init(ipw2100_init);

drivers/powercap/idle_inject.c

···
 	struct hrtimer timer;
 	unsigned int idle_duration_us;
 	unsigned int run_duration_us;
-	unsigned long int cpumask[0];
+	unsigned long cpumask[];
 };
 
 static DEFINE_PER_CPU(struct idle_inject_thread, idle_inject_thread);

drivers/spi/spi-fsl-qspi.c

···
 	}
 
 	if (needs_wakeup_wait_mode(q))
-		pm_qos_add_request(&q->pm_qos_req, PM_QOS_CPU_DMA_LATENCY, 0);
+		cpu_latency_qos_add_request(&q->pm_qos_req, 0);
 
 	return 0;
 }
···
 static void fsl_qspi_clk_disable_unprep(struct fsl_qspi *q)
 {
 	if (needs_wakeup_wait_mode(q))
-		pm_qos_remove_request(&q->pm_qos_req);
+		cpu_latency_qos_remove_request(&q->pm_qos_req);
 
 	clk_disable_unprepare(q->clk);
 	clk_disable_unprepare(q->clk_en);

drivers/tty/serial/8250/8250_omap.c

···
 	struct omap8250_priv *priv;
 
 	priv = container_of(work, struct omap8250_priv, qos_work);
-	pm_qos_update_request(&priv->pm_qos_request, priv->latency);
+	cpu_latency_qos_update_request(&priv->pm_qos_request, priv->latency);
 }
 
 #ifdef CONFIG_SERIAL_8250_DMA
···
 			 DEFAULT_CLK_SPEED);
 	}
 
-	priv->latency = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE;
-	priv->calc_latency = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE;
-	pm_qos_add_request(&priv->pm_qos_request, PM_QOS_CPU_DMA_LATENCY,
-			   priv->latency);
+	priv->latency = PM_QOS_CPU_LATENCY_DEFAULT_VALUE;
+	priv->calc_latency = PM_QOS_CPU_LATENCY_DEFAULT_VALUE;
+	cpu_latency_qos_add_request(&priv->pm_qos_request, priv->latency);
 	INIT_WORK(&priv->qos_work, omap8250_uart_qos_work);
 
 	spin_lock_init(&priv->rx_dma_lock);
···
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	serial8250_unregister_port(priv->line);
-	pm_qos_remove_request(&priv->pm_qos_request);
+	cpu_latency_qos_remove_request(&priv->pm_qos_request);
 	device_init_wakeup(&pdev->dev, false);
 	return 0;
 }
···
 	if (up->dma && up->dma->rxchan)
 		omap_8250_rx_dma_flush(up);
 
-	priv->latency = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE;
+	priv->latency = PM_QOS_CPU_LATENCY_DEFAULT_VALUE;
 	schedule_work(&priv->qos_work);
 
 	return 0;

drivers/tty/serial/omap-serial.c

···
 	struct uart_omap_port *up = container_of(work, struct uart_omap_port,
 						qos_work);
 
-	pm_qos_update_request(&up->pm_qos_request, up->latency);
+	cpu_latency_qos_update_request(&up->pm_qos_request, up->latency);
 }
 
 static void
···
 			 DEFAULT_CLK_SPEED);
 	}
 
-	up->latency = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE;
-	up->calc_latency = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE;
-	pm_qos_add_request(&up->pm_qos_request,
-		PM_QOS_CPU_DMA_LATENCY, up->latency);
+	up->latency = PM_QOS_CPU_LATENCY_DEFAULT_VALUE;
+	up->calc_latency = PM_QOS_CPU_LATENCY_DEFAULT_VALUE;
+	cpu_latency_qos_add_request(&up->pm_qos_request, up->latency);
 	INIT_WORK(&up->qos_work, serial_omap_uart_qos_work);
 
 	platform_set_drvdata(pdev, up);
···
 	pm_runtime_dont_use_autosuspend(&pdev->dev);
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-	pm_qos_remove_request(&up->pm_qos_request);
+	cpu_latency_qos_remove_request(&up->pm_qos_request);
 	device_init_wakeup(up->dev, false);
 err_rs485:
 err_port_line:
···
 	pm_runtime_dont_use_autosuspend(up->dev);
 	pm_runtime_put_sync(up->dev);
 	pm_runtime_disable(up->dev);
-	pm_qos_remove_request(&up->pm_qos_request);
+	cpu_latency_qos_remove_request(&up->pm_qos_request);
 	device_init_wakeup(&dev->dev, false);
 
 	return 0;
···
 
 	serial_omap_enable_wakeup(up, true);
 
-	up->latency = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE;
+	up->latency = PM_QOS_CPU_LATENCY_DEFAULT_VALUE;
 	schedule_work(&up->qos_work);
 
 	return 0;

drivers/usb/chipidea/ci_hdrc_imx.c

···
 	}
 
 	if (pdata.flags & CI_HDRC_PMQOS)
-		pm_qos_add_request(&data->pm_qos_req,
-			PM_QOS_CPU_DMA_LATENCY, 0);
+		cpu_latency_qos_add_request(&data->pm_qos_req, 0);
 
 	ret = imx_get_clks(dev);
 	if (ret)
···
 		/* don't overwrite original ret (cf. EPROBE_DEFER) */
 		regulator_disable(data->hsic_pad_regulator);
 	if (pdata.flags & CI_HDRC_PMQOS)
-		pm_qos_remove_request(&data->pm_qos_req);
+		cpu_latency_qos_remove_request(&data->pm_qos_req);
 	data->ci_pdev = NULL;
 	return ret;
 }
···
 	if (data->ci_pdev) {
 		imx_disable_unprepare_clks(&pdev->dev);
 		if (data->plat_data->flags & CI_HDRC_PMQOS)
-			pm_qos_remove_request(&data->pm_qos_req);
+			cpu_latency_qos_remove_request(&data->pm_qos_req);
 		if (data->hsic_pad_regulator)
 			regulator_disable(data->hsic_pad_regulator);
 	}
···
 
 	imx_disable_unprepare_clks(dev);
 	if (data->plat_data->flags & CI_HDRC_PMQOS)
-		pm_qos_remove_request(&data->pm_qos_req);
+		cpu_latency_qos_remove_request(&data->pm_qos_req);
 
 	data->in_lpm = true;
 
···
 	}
 
 	if (data->plat_data->flags & CI_HDRC_PMQOS)
-		pm_qos_add_request(&data->pm_qos_req,
-			PM_QOS_CPU_DMA_LATENCY, 0);
+		cpu_latency_qos_add_request(&data->pm_qos_req, 0);
 
 	ret = imx_prepare_enable_clks(dev);
 	if (ret)

include/acpi/acpixf.h

···
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_disable_all_gpes(void))
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_runtime_gpes(void))
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_wakeup_gpes(void))
-ACPI_HW_DEPENDENT_RETURN_UINT32(u32 acpi_any_gpe_status_set(void))
+ACPI_HW_DEPENDENT_RETURN_UINT32(u32 acpi_any_gpe_status_set(u32 gpe_skip_number))
 ACPI_HW_DEPENDENT_RETURN_UINT32(u32 acpi_any_fixed_event_status_set(void))
 
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status

include/linux/devfreq.h

···
  * functions except for the context of callbacks defined in struct
  * devfreq_governor, the governor should protect its access with the
  * struct mutex lock in struct devfreq. A governor may use this mutex
- * to protect its own private data in void *data as well.
+ * to protect its own private data in ``void *data`` as well.
  */
 struct devfreq {
 	struct list_head node;
···
 };
 
 #if defined(CONFIG_PM_DEVFREQ)
-extern struct devfreq *devfreq_add_device(struct device *dev,
-				  struct devfreq_dev_profile *profile,
-				  const char *governor_name,
-				  void *data);
-extern int devfreq_remove_device(struct devfreq *devfreq);
-extern struct devfreq *devm_devfreq_add_device(struct device *dev,
-				  struct devfreq_dev_profile *profile,
-				  const char *governor_name,
-				  void *data);
-extern void devm_devfreq_remove_device(struct device *dev,
-				  struct devfreq *devfreq);
+struct devfreq *devfreq_add_device(struct device *dev,
+				struct devfreq_dev_profile *profile,
+				const char *governor_name,
+				void *data);
+int devfreq_remove_device(struct devfreq *devfreq);
+struct devfreq *devm_devfreq_add_device(struct device *dev,
+				struct devfreq_dev_profile *profile,
+				const char *governor_name,
+				void *data);
+void devm_devfreq_remove_device(struct device *dev, struct devfreq *devfreq);
 
 /* Supposed to be called by PM callbacks */
-extern int devfreq_suspend_device(struct devfreq *devfreq);
-extern int devfreq_resume_device(struct devfreq *devfreq);
+int devfreq_suspend_device(struct devfreq *devfreq);
+int devfreq_resume_device(struct devfreq *devfreq);
 
-extern void devfreq_suspend(void);
-extern void devfreq_resume(void);
+void devfreq_suspend(void);
+void devfreq_resume(void);
 
 /**
  * update_devfreq() - Reevaluate the device and configure frequency
···
  *
  * Note: devfreq->lock must be held
  */
-extern int update_devfreq(struct devfreq *devfreq);
+int update_devfreq(struct devfreq *devfreq);
 
 /* Helper functions for devfreq user device driver with OPP. */
-extern struct dev_pm_opp *devfreq_recommended_opp(struct device *dev,
-					   unsigned long *freq, u32 flags);
-extern int devfreq_register_opp_notifier(struct device *dev,
-					 struct devfreq *devfreq);
-extern int devfreq_unregister_opp_notifier(struct device *dev,
-					   struct devfreq *devfreq);
-extern int devm_devfreq_register_opp_notifier(struct device *dev,
-					      struct devfreq *devfreq);
-extern void devm_devfreq_unregister_opp_notifier(struct device *dev,
-						struct devfreq *devfreq);
-extern int devfreq_register_notifier(struct devfreq *devfreq,
-					struct notifier_block *nb,
-					unsigned int list);
-extern int devfreq_unregister_notifier(struct devfreq *devfreq,
-					struct notifier_block *nb,
-					unsigned int list);
-extern int devm_devfreq_register_notifier(struct device *dev,
+struct dev_pm_opp *devfreq_recommended_opp(struct device *dev,
+				unsigned long *freq, u32 flags);
+int devfreq_register_opp_notifier(struct device *dev,
+				struct devfreq *devfreq);
+int devfreq_unregister_opp_notifier(struct device *dev,
+				struct devfreq *devfreq);
+int devm_devfreq_register_opp_notifier(struct device *dev,
+				struct devfreq *devfreq);
+void devm_devfreq_unregister_opp_notifier(struct device *dev,
+				struct devfreq *devfreq);
+int devfreq_register_notifier(struct devfreq *devfreq,
+				struct notifier_block *nb,
+				unsigned int list);
+int devfreq_unregister_notifier(struct devfreq *devfreq,
+				struct notifier_block *nb,
+				unsigned int list);
+int devm_devfreq_register_notifier(struct device *dev,
 				struct devfreq *devfreq,
 				struct notifier_block *nb,
 				unsigned int list);
-extern void devm_devfreq_unregister_notifier(struct device *dev,
+void devm_devfreq_unregister_notifier(struct device *dev,
 				struct devfreq *devfreq,
 				struct notifier_block *nb,
 				unsigned int list);
-extern struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev,
-						int index);
+struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index);
 
 #if IS_ENABLED(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND)
 /**
- * struct devfreq_simple_ondemand_data - void *data fed to struct devfreq
+ * struct devfreq_simple_ondemand_data - ``void *data`` fed to struct devfreq
  *	and devfreq_add_device
  * @upthreshold:	If the load is over this value, the frequency jumps.
  *			Specify 0 to use the default. Valid value = 0 to 100.
···
 
 #if IS_ENABLED(CONFIG_DEVFREQ_GOV_PASSIVE)
 /**
- * struct devfreq_passive_data - void *data fed to struct devfreq
+ * struct devfreq_passive_data - ``void *data`` fed to struct devfreq
  *	and devfreq_add_device
  * @parent:	the devfreq instance of parent device.
  * @get_target_freq:	Optional callback, Returns desired operating frequency
···
 
 #else /* !CONFIG_PM_DEVFREQ */
 static inline struct devfreq *devfreq_add_device(struct device *dev,
-					  struct devfreq_dev_profile *profile,
-					  const char *governor_name,
-					  void *data)
+					struct devfreq_dev_profile *profile,
+					const char *governor_name,
+					void *data)
 {
 	return ERR_PTR(-ENOSYS);
 }
···
 static inline void devfreq_resume(void) {}
 
 static inline struct dev_pm_opp *devfreq_recommended_opp(struct device *dev,
-					   unsigned long *freq, u32 flags)
+					unsigned long *freq, u32 flags)
 {
 	return ERR_PTR(-EINVAL);
 }
 
 static inline int devfreq_register_opp_notifier(struct device *dev,
-					 struct devfreq *devfreq)
+					struct devfreq *devfreq)
 {
 	return -EINVAL;
 }
 
 static inline int devfreq_unregister_opp_notifier(struct device *dev,
-					   struct devfreq *devfreq)
+					struct devfreq *devfreq)
 {
 	return -EINVAL;
 }
 
 static inline int devm_devfreq_register_opp_notifier(struct device *dev,
-						     struct devfreq *devfreq)
+					struct devfreq *devfreq)
 {
 	return -EINVAL;
 }
 
 static inline void devm_devfreq_unregister_opp_notifier(struct device *dev,
-							struct devfreq *devfreq)
+					struct devfreq *devfreq)
 {
 }
 
···
 }
 
 static inline int devm_devfreq_register_notifier(struct device *dev,
-				struct devfreq *devfreq,
-				struct notifier_block *nb,
-				unsigned int list)
+					struct devfreq *devfreq,
+					struct notifier_block *nb,
+					unsigned int list)
 {
 	return 0;
 }
 
 static inline void devm_devfreq_unregister_notifier(struct device *dev,
-				struct devfreq *devfreq,
-				struct notifier_block *nb,
-				unsigned int list)
+					struct devfreq *devfreq,
+					struct notifier_block *nb,
+					unsigned int list)
 {
 }
 
 static inline struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev,
-							int index)
+					int index)
 {
 	return ERR_PTR(-ENODEV);
 }

include/linux/pm_qos.h

···
 /* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Definitions related to Power Management Quality of Service (PM QoS).
+ *
+ * Copyright (C) 2020 Intel Corporation
+ *
+ * Authors:
+ *	Mark Gross <[e-mail]>
+ *	Rafael J. Wysocki <[e-mail]>
+ */
+
 #ifndef _LINUX_PM_QOS_H
 #define _LINUX_PM_QOS_H
-/* interface for the pm_qos_power infrastructure of the linux kernel.
- *
- * Mark Gross <[e-mail]>
- */
+
 #include <linux/plist.h>
 #include <linux/notifier.h>
 #include <linux/device.h>
-#include <linux/workqueue.h>
-
-enum {
-	PM_QOS_RESERVED = 0,
-	PM_QOS_CPU_DMA_LATENCY,
-
-	/* insert new class ID */
-	PM_QOS_NUM_CLASSES,
-};
 
 enum pm_qos_flags_status {
 	PM_QOS_FLAGS_UNDEFINED = -1,
···
 #define PM_QOS_LATENCY_ANY	S32_MAX
 #define PM_QOS_LATENCY_ANY_NS	((s64)PM_QOS_LATENCY_ANY * NSEC_PER_USEC)
 
-#define PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE	(2000 * USEC_PER_SEC)
+#define PM_QOS_CPU_LATENCY_DEFAULT_VALUE	(2000 * USEC_PER_SEC)
 #define PM_QOS_RESUME_LATENCY_DEFAULT_VALUE	PM_QOS_LATENCY_ANY
 #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT	PM_QOS_LATENCY_ANY
 #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS	PM_QOS_LATENCY_ANY_NS
···
 
 #define PM_QOS_FLAG_NO_POWER_OFF	(1 << 0)
 
-struct pm_qos_request {
-	struct plist_node node;
-	int pm_qos_class;
-	struct delayed_work work; /* for pm_qos_update_request_timeout */
-};
-
-struct pm_qos_flags_request {
-	struct list_head node;
-	s32 flags;	/* Do not change to 64 bit */
-};
-
 enum pm_qos_type {
 	PM_QOS_UNITIALIZED,
 	PM_QOS_MAX,		/* return the largest value */
 	PM_QOS_MIN,		/* return the smallest value */
-	PM_QOS_SUM		/* return the sum */
 };
 
 /*
···
 	s32 no_constraint_value;
 	enum pm_qos_type type;
 	struct blocking_notifier_head *notifiers;
+};
+
+struct pm_qos_request {
+	struct plist_node node;
+	struct pm_qos_constraints *qos;
+};
+
+struct pm_qos_flags_request {
+	struct list_head node;
+	s32 flags;	/* Do not change to 64 bit */
 };
 
 struct pm_qos_flags {
···
 	return req->dev != NULL;
 }
 
+s32 pm_qos_read_value(struct pm_qos_constraints *c);
 int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node,
 			 enum pm_qos_req_action action, int value);
 bool pm_qos_update_flags(struct pm_qos_flags *pqf,
 			 struct pm_qos_flags_request *req,
 			 enum pm_qos_req_action action, s32 val);
-void pm_qos_add_request(struct pm_qos_request *req, int pm_qos_class,
-			s32 value);
-void pm_qos_update_request(struct pm_qos_request *req,
-			   s32 new_value);
-void pm_qos_update_request_timeout(struct pm_qos_request *req,
-				   s32 new_value, unsigned long timeout_us);
-void pm_qos_remove_request(struct pm_qos_request *req);
 
-int pm_qos_request(int pm_qos_class);
-int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier);
-int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier);
-int pm_qos_request_active(struct pm_qos_request *req);
-s32 pm_qos_read_value(struct pm_qos_constraints *c);
+#ifdef CONFIG_CPU_IDLE
+s32 cpu_latency_qos_limit(void);
+bool cpu_latency_qos_request_active(struct pm_qos_request *req);
+void cpu_latency_qos_add_request(struct pm_qos_request *req, s32 value);
+void cpu_latency_qos_update_request(struct pm_qos_request *req, s32 new_value);
+void cpu_latency_qos_remove_request(struct pm_qos_request *req);
+#else
+static inline s32 cpu_latency_qos_limit(void) { return INT_MAX; }
+static inline bool cpu_latency_qos_request_active(struct pm_qos_request *req)
+{
+	return false;
+}
+static inline void cpu_latency_qos_add_request(struct pm_qos_request *req,
+					       s32 value) {}
+static inline void cpu_latency_qos_update_request(struct pm_qos_request *req,
+						  s32 new_value) {}
+static inline void cpu_latency_qos_remove_request(struct pm_qos_request *req) {}
+#endif
 
 #ifdef CONFIG_PM
 enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev, s32 mask);

include/linux/pm_runtime.h

···
 extern int __pm_runtime_idle(struct device *dev, int rpmflags);
 extern int __pm_runtime_suspend(struct device *dev, int rpmflags);
 extern int __pm_runtime_resume(struct device *dev, int rpmflags);
-extern int pm_runtime_get_if_in_use(struct device *dev);
+extern int pm_runtime_get_if_active(struct device *dev, bool ign_usage_count);
 extern int pm_schedule_suspend(struct device *dev, unsigned int delay);
 extern int __pm_runtime_set_status(struct device *dev, unsigned int status);
 extern int pm_runtime_barrier(struct device *dev);
···
 extern void pm_runtime_put_suppliers(struct device *dev);
 extern void pm_runtime_new_link(struct device *dev);
 extern void pm_runtime_drop_link(struct device *dev);
+
+static inline int pm_runtime_get_if_in_use(struct device *dev)
+{
+	return pm_runtime_get_if_active(dev, false);
+}
 
 static inline void pm_suspend_ignore_children(struct device *dev, bool enable)
 {
···
 	return -ENOSYS;
 }
 static inline int pm_runtime_get_if_in_use(struct device *dev)
+{
+	return -EINVAL;
+}
+static inline int pm_runtime_get_if_active(struct device *dev,
+					   bool ign_usage_count)
 {
 	return -EINVAL;
 }

include/trace/events/power.h

···
 );
 
 /*
- * The pm qos events are used for pm qos update
+ * CPU latency QoS events used for global CPU latency QoS list updates
  */
-DECLARE_EVENT_CLASS(pm_qos_request,
+DECLARE_EVENT_CLASS(cpu_latency_qos_request,
 
-	TP_PROTO(int pm_qos_class, s32 value),
+	TP_PROTO(s32 value),
 
-	TP_ARGS(pm_qos_class, value),
+	TP_ARGS(value),
 
 	TP_STRUCT__entry(
-		__field( int,                    pm_qos_class   )
 		__field( s32,                    value          )
 	),
 
 	TP_fast_assign(
-		__entry->pm_qos_class = pm_qos_class;
 		__entry->value = value;
 	),
 
-	TP_printk("pm_qos_class=%s value=%d",
-		  __print_symbolic(__entry->pm_qos_class,
-			{ PM_QOS_CPU_DMA_LATENCY,	"CPU_DMA_LATENCY" }),
+	TP_printk("CPU_DMA_LATENCY value=%d",
 		  __entry->value)
 );
 
-DEFINE_EVENT(pm_qos_request, pm_qos_add_request,
+DEFINE_EVENT(cpu_latency_qos_request, pm_qos_add_request,
 
-	TP_PROTO(int pm_qos_class, s32 value),
+	TP_PROTO(s32 value),
 
-	TP_ARGS(pm_qos_class, value)
+	TP_ARGS(value)
 );
 
-DEFINE_EVENT(pm_qos_request, pm_qos_update_request,
+DEFINE_EVENT(cpu_latency_qos_request, pm_qos_update_request,
 
-	TP_PROTO(int pm_qos_class, s32 value),
+	TP_PROTO(s32 value),
 
-	TP_ARGS(pm_qos_class, value)
+	TP_ARGS(value)
 );
 
-DEFINE_EVENT(pm_qos_request, pm_qos_remove_request,
+DEFINE_EVENT(cpu_latency_qos_request, pm_qos_remove_request,
 
-	TP_PROTO(int pm_qos_class, s32 value),
+	TP_PROTO(s32 value),
 
-	TP_ARGS(pm_qos_class, value)
+	TP_ARGS(value)
 );
 
-TRACE_EVENT(pm_qos_update_request_timeout,
-
-	TP_PROTO(int pm_qos_class, s32 value, unsigned long timeout_us),
-
-	TP_ARGS(pm_qos_class, value, timeout_us),
-
-	TP_STRUCT__entry(
-		__field( int,                    pm_qos_class   )
-		__field( s32,                    value          )
-		__field( unsigned long,          timeout_us     )
-	),
-
-	TP_fast_assign(
-		__entry->pm_qos_class = pm_qos_class;
-		__entry->value = value;
-		__entry->timeout_us = timeout_us;
-	),
-
-	TP_printk("pm_qos_class=%s value=%d, timeout_us=%ld",
-		  __print_symbolic(__entry->pm_qos_class,
-			{ PM_QOS_CPU_DMA_LATENCY,	"CPU_DMA_LATENCY" }),
-		  __entry->value, __entry->timeout_us)
-);
-
+/*
+ * General PM QoS events used for updates of PM QoS request lists
+ */
 DECLARE_EVENT_CLASS(pm_qos_update,
 
 	TP_PROTO(enum pm_qos_req_action action, int prev_value, int curr_value),

kernel/power/qos.c

···
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * This module exposes the interface to kernel space for specifying
- * QoS dependencies.  It provides infrastructure for registration of:
+ * Power Management Quality of Service (PM QoS) support base.
  *
- * Dependents on a QoS value : register requests
- * Watchers of QoS value : get notified when target QoS value changes
+ * Copyright (C) 2020 Intel Corporation
  *
- * This QoS design is best effort based.  Dependents register their QoS needs.
- * Watchers register to keep track of the current QoS needs of the system.
+ * Authors:
+ *	Mark Gross <[e-mail]>
+ *	Rafael J. Wysocki <[e-mail]>
  *
- * There are 3 basic classes of QoS parameter: latency, timeout, throughput
- * each have defined units:
- * latency: usec
- * timeout: usec <-- currently not used.
- * throughput: kbs (kilo byte / sec)
+ * Provided here is an interface for specifying PM QoS dependencies.  It allows
+ * entities depending on QoS constraints to register their requests which are
+ * aggregated as appropriate to produce effective constraints (target values)
+ * that can be monitored by entities needing to respect them, either by polling
+ * or through a built-in notification mechanism.
  *
- * There are lists of pm_qos_objects each one wrapping requests, notifiers
- *
- * User mode requests on a QOS parameter register themselves to the
- * subsystem by opening the device node /dev/... and writing there request to
- * the node.  As long as the process holds a file handle open to the node the
- * client continues to be accounted for.  Upon file release the usermode
- * request is removed and a new qos target is computed.  This way when the
- * request that the application has is cleaned up when closes the file
- * pointer or exits the pm_qos_object will get an opportunity to clean up.
- *
- * Mark Gross <[e-mail]>
+ * In addition to the basic functionality, more specific interfaces for managing
+ * global CPU latency QoS requests and frequency QoS requests are provided.
  */
 
 /*#define DEBUG*/
···
  * or pm_qos_object list and pm_qos_objects need to happen with pm_qos_lock
  * held, taken with _irqsave.  One lock to rule them all
  */
-struct pm_qos_object {
-	struct pm_qos_constraints *constraints;
-	struct miscdevice pm_qos_power_miscdev;
-	char *name;
-};
-
 static DEFINE_SPINLOCK(pm_qos_lock);
 
-static struct pm_qos_object null_pm_qos;
-
-static BLOCKING_NOTIFIER_HEAD(cpu_dma_lat_notifier);
-static struct pm_qos_constraints cpu_dma_constraints = {
-	.list = PLIST_HEAD_INIT(cpu_dma_constraints.list),
-	.target_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
-	.default_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
-	.no_constraint_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
-	.type = PM_QOS_MIN,
-	.notifiers = &cpu_dma_lat_notifier,
-};
-static struct pm_qos_object cpu_dma_pm_qos = {
-	.constraints = &cpu_dma_constraints,
-	.name = "cpu_dma_latency",
-};
-
-static struct pm_qos_object *pm_qos_array[] = {
-	&null_pm_qos,
-	&cpu_dma_pm_qos,
-};
-
-static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
-		size_t count, loff_t *f_pos);
-static ssize_t pm_qos_power_read(struct file *filp, char __user *buf,
-		size_t count, loff_t *f_pos);
-static int pm_qos_power_open(struct inode *inode, struct file *filp);
-static int pm_qos_power_release(struct inode *inode, struct file *filp);
-
-static const struct file_operations pm_qos_power_fops = {
-	.write = pm_qos_power_write,
-	.read = pm_qos_power_read,
-	.open = pm_qos_power_open,
-	.release = pm_qos_power_release,
-	.llseek = noop_llseek,
-};
-
-/* unlocked internal variant */
-static inline int pm_qos_get_value(struct pm_qos_constraints *c)
+/**
+ * pm_qos_read_value - Return the current effective constraint value.
+ * @c: List of PM QoS constraint requests.
+ */
+s32 pm_qos_read_value(struct pm_qos_constraints *c)
 {
-	struct plist_node *node;
-	int total_value = 0;
+	return READ_ONCE(c->target_value);
+}
 
+static int pm_qos_get_value(struct pm_qos_constraints *c)
+{
 	if (plist_head_empty(&c->list))
 		return c->no_constraint_value;
 
···
 	case PM_QOS_MAX:
 		return plist_last(&c->list)->prio;
 
-	case PM_QOS_SUM:
-		plist_for_each(node, &c->list)
-			total_value += node->prio;
-
-		return total_value;
-
 	default:
-		/* runtime check for not using enum */
-		BUG();
+		WARN(1, "Unknown PM QoS type in %s\n", __func__);
 		return PM_QOS_DEFAULT_VALUE;
 	}
 }
 
-s32 pm_qos_read_value(struct pm_qos_constraints *c)
+static void pm_qos_set_value(struct pm_qos_constraints *c, s32 value)
 {
-	return c->target_value;
+	WRITE_ONCE(c->target_value, value);
 }
-
-static inline void pm_qos_set_value(struct pm_qos_constraints *c, s32 value)
-{
-	c->target_value = value;
-}
-
-static int pm_qos_debug_show(struct seq_file *s, void *unused)
-{
-	struct pm_qos_object *qos = (struct pm_qos_object *)s->private;
-	struct pm_qos_constraints *c;
-	struct pm_qos_request *req;
-	char *type;
-	unsigned long flags;
-	int tot_reqs = 0;
-	int active_reqs = 0;
-
-	if (IS_ERR_OR_NULL(qos)) {
-		pr_err("%s: bad qos param!\n", __func__);
-		return -EINVAL;
-	}
-	c = qos->constraints;
-	if (IS_ERR_OR_NULL(c)) {
-		pr_err("%s: Bad constraints on qos?\n", __func__);
-		return -EINVAL;
-	}
-
-	/* Lock to ensure we have a snapshot */
-	spin_lock_irqsave(&pm_qos_lock, flags);
-	if (plist_head_empty(&c->list)) {
-		seq_puts(s, "Empty!\n");
-		goto out;
-	}
-
-	switch (c->type) {
-	case PM_QOS_MIN:
-		type = "Minimum";
-		break;
-	case PM_QOS_MAX:
-		type = "Maximum";
-		break;
-	case PM_QOS_SUM:
-		type = "Sum";
-		break;
-	default:
-		type = "Unknown";
-	}
-
-	plist_for_each_entry(req, &c->list, node) {
-		char *state = "Default";
-
-		if ((req->node).prio != c->default_value) {
-			active_reqs++;
-			state = "Active";
-		}
-		tot_reqs++;
-		seq_printf(s, "%d: %d: %s\n", tot_reqs,
-			   (req->node).prio, state);
-	}
-
-	seq_printf(s, "Type=%s, Value=%d, Requests: active=%d / total=%d\n",
-		   type, pm_qos_get_value(c), active_reqs, tot_reqs);
-
-out:
-	spin_unlock_irqrestore(&pm_qos_lock, flags);
-	return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(pm_qos_debug);
 
 /**
- * pm_qos_update_target - manages the constraints list and calls the notifiers
- *  if needed
- * @c: constraints data struct
- * @node: request to add to the list, to update or to remove
- * @action: action to take on the constraints list
- * @value: value of the request to add or update
+ * pm_qos_update_target - Update a list of PM QoS constraint requests.
+ * @c: List of PM QoS requests.
+ * @node: Target list entry.
+ * @action: Action to carry out (add, update or remove).
+ * @value: New request value for the target list entry.
  *
- * This function returns 1 if the aggregated constraint value has changed, 0
- *  otherwise.
+ * Update the given list of PM QoS constraint requests, @c, by carrying an
+ * @action involving the @node list entry and @value on it.
+ *
+ * The recognized values of @action are PM_QOS_ADD_REQ (store @value in @node
+ * and add it to the list), PM_QOS_UPDATE_REQ (remove @node from the list, store
+ * @value in it and add it to the list again), and PM_QOS_REMOVE_REQ (remove
+ * @node from the list, ignore @value).
+ *
+ * Return: 1 if the aggregate constraint value has changed, 0  otherwise.
  */
 int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node,
 			 enum pm_qos_req_action action, int value)
 {
-	unsigned long flags;
 	int prev_value, curr_value, new_value;
-	int ret;
+	unsigned long flags;
 
 	spin_lock_irqsave(&pm_qos_lock, flags);
+
 	prev_value = pm_qos_get_value(c);
 	if (value == PM_QOS_DEFAULT_VALUE)
 		new_value = c->default_value;
···
 		break;
 	case PM_QOS_UPDATE_REQ:
 		/*
-		 * to change the list, we atomically remove, reinit
-		 * with new value and add, then see if the extremal
-		 * changed
+		 * To change the list, atomically remove, reinit with new value
+		 * and add, then see if the aggregate has changed.
 		 */
 		plist_del(node, &c->list);
 		/* fall through */
···
 	spin_unlock_irqrestore(&pm_qos_lock, flags);
 
 	trace_pm_qos_update_target(action, prev_value, curr_value);
-	if (prev_value != curr_value) {
-		ret = 1;
-		if (c->notifiers)
-			blocking_notifier_call_chain(c->notifiers,
-						     (unsigned long)curr_value,
-						     NULL);
-	} else {
-		ret = 0;
-	}
-	return ret;
+
+	if (prev_value == curr_value)
+		return 0;
+
+	if (c->notifiers)
+		blocking_notifier_call_chain(c->notifiers, curr_value, NULL);
+
+	return 1;
 }
 
 /**
···
 
 /**
  * pm_qos_update_flags - Update a set of PM QoS flags.
- * @pqf: Set of flags to update.
+ * @pqf: Set of PM QoS flags to update.
  * @req: Request to add to the set, to modify, or to remove from the set.
  * @action: Action to take on the set.
  * @val: Value of the request to add or modify.
  *
- * Update the given set of PM QoS flags and call notifiers if the aggregate
- * value has changed.  Returns 1 if the aggregate constraint value has changed,
- * 0 otherwise.
+ * Return: 1 if the aggregate constraint value has changed, 0 otherwise.
  */
 bool pm_qos_update_flags(struct pm_qos_flags *pqf,
 			 struct pm_qos_flags_request *req,
···
 	spin_unlock_irqrestore(&pm_qos_lock, irqflags);
 
 	trace_pm_qos_update_flags(action, prev_value, curr_value);
+
 	return prev_value != curr_value;
 }
 
+#ifdef CONFIG_CPU_IDLE
+/* Definitions related to the CPU latency QoS. */
+
+static struct pm_qos_constraints cpu_latency_constraints = {
+	.list = PLIST_HEAD_INIT(cpu_latency_constraints.list),
+	.target_value = PM_QOS_CPU_LATENCY_DEFAULT_VALUE,
+	.default_value = PM_QOS_CPU_LATENCY_DEFAULT_VALUE,
+	.no_constraint_value = PM_QOS_CPU_LATENCY_DEFAULT_VALUE,
+	.type = PM_QOS_MIN,
+};
+
 /**
- * pm_qos_request - returns current system wide qos expectation
- * @pm_qos_class: identification of which qos value is requested
- *
- * This function returns the current target value.
+ * cpu_latency_qos_limit - Return current system-wide CPU latency QoS limit.
  */
-int pm_qos_request(int pm_qos_class)
+s32 cpu_latency_qos_limit(void)
 {
-	return pm_qos_read_value(pm_qos_array[pm_qos_class]->constraints);
-}
-EXPORT_SYMBOL_GPL(pm_qos_request);
-
-int pm_qos_request_active(struct pm_qos_request *req)
-{
-	return req->pm_qos_class != 0;
-}
-EXPORT_SYMBOL_GPL(pm_qos_request_active);
-
-static void __pm_qos_update_request(struct pm_qos_request *req,
-			   s32 new_value)
-{
-	trace_pm_qos_update_request(req->pm_qos_class, new_value);
-
-	if (new_value != req->node.prio)
-		pm_qos_update_target(
-			pm_qos_array[req->pm_qos_class]->constraints,
-			&req->node, PM_QOS_UPDATE_REQ, new_value);
+	return pm_qos_read_value(&cpu_latency_constraints);
 }
 
 /**
- * pm_qos_work_fn - the timeout handler of pm_qos_update_request_timeout
- * @work: work struct for the delayed work (timeout)
+ * cpu_latency_qos_request_active - Check the given PM QoS request.
+ * @req: PM QoS request to check.
  *
- * This cancels the timeout request by falling back to the default at timeout.
+ * Return: 'true' if @req has been added to the CPU latency QoS list, 'false'
+ * otherwise.
  */
-static void pm_qos_work_fn(struct work_struct *work)
+bool cpu_latency_qos_request_active(struct pm_qos_request *req)
 {
-	struct pm_qos_request *req = container_of(to_delayed_work(work),
-						  struct pm_qos_request,
-						  work);
+	return req->qos == &cpu_latency_constraints;
+}
+EXPORT_SYMBOL_GPL(cpu_latency_qos_request_active);
 
-	__pm_qos_update_request(req, PM_QOS_DEFAULT_VALUE);
+static void cpu_latency_qos_apply(struct pm_qos_request *req,
+				  enum pm_qos_req_action action, s32 value)
+{
+	int ret = pm_qos_update_target(req->qos, &req->node, action, value);
+	if (ret > 0)
+		wake_up_all_idle_cpus();
 }
 
 /**
- * pm_qos_add_request - inserts new qos request into the list
- * @req: pointer to a preallocated handle
- * @pm_qos_class: identifies which list of qos request to use
- * @value: defines the qos request
+ * cpu_latency_qos_add_request - Add new CPU latency QoS request.
+ * @req: Pointer to a preallocated handle.
+ * @value: Requested constraint value.
  *
- * This function inserts a new entry in the pm_qos_class list of requested qos
- * performance characteristics.  It recomputes the aggregate QoS expectations
- * for the pm_qos_class of parameters and initializes the pm_qos_request
- * handle.  Caller needs to save this handle for later use in updates and
- * removal.
+ * Use @value to initialize the request handle pointed to by @req, insert it as
+ * a new entry to the CPU latency QoS list and recompute the effective QoS
+ * constraint for that list.
+ *
+ * Callers need to save the handle for later use in updates and removal of the
+ * QoS request represented by it.
  */
-
-void pm_qos_add_request(struct pm_qos_request *req,
-			int pm_qos_class, s32 value)
-{
-	if (!req) /*guard against callers passing in null */
-		return;
-
-	if (pm_qos_request_active(req)) {
-		WARN(1, KERN_ERR "pm_qos_add_request() called for already added request\n");
-		return;
-	}
-	req->pm_qos_class = pm_qos_class;
-	INIT_DELAYED_WORK(&req->work, pm_qos_work_fn);
-	trace_pm_qos_add_request(pm_qos_class, value);
-	pm_qos_update_target(pm_qos_array[pm_qos_class]->constraints,
-			     &req->node, PM_QOS_ADD_REQ, value);
-}
-EXPORT_SYMBOL_GPL(pm_qos_add_request);
-
-/**
- * pm_qos_update_request - modifies an existing qos request
- * @req : handle to list element holding a pm_qos request to use
- * @value: defines the qos request
- *
- * Updates an existing qos request for the pm_qos_class of parameters along
- * with updating the target pm_qos_class value.
- *
- * Attempts are made to make this code callable on hot code paths.
- */
-void pm_qos_update_request(struct pm_qos_request *req,
-			   s32 new_value)
-{
-	if (!req) /*guard against callers passing in null */
-		return;
-
-	if (!pm_qos_request_active(req)) {
-		WARN(1, KERN_ERR "pm_qos_update_request() called for unknown object\n");
-		return;
-	}
-
-	cancel_delayed_work_sync(&req->work);
-	__pm_qos_update_request(req, new_value);
-}
-EXPORT_SYMBOL_GPL(pm_qos_update_request);
-
-/**
- * pm_qos_update_request_timeout - modifies an existing qos request temporarily.
- * @req : handle to list element holding a pm_qos request to use
- * @new_value: defines the temporal qos request
- * @timeout_us: the effective duration of this qos request in usecs.
- *
- * After timeout_us, this qos request is cancelled automatically.
- */
-void pm_qos_update_request_timeout(struct pm_qos_request *req, s32 new_value,
-				   unsigned long timeout_us)
+void cpu_latency_qos_add_request(struct pm_qos_request *req, s32 value)
 {
 	if (!req)
 		return;
-	if (WARN(!pm_qos_request_active(req),
-		 "%s called for unknown object.", __func__))
-		return;
 
-	cancel_delayed_work_sync(&req->work);
-
-	trace_pm_qos_update_request_timeout(req->pm_qos_class,
-					    new_value, timeout_us);
-	if (new_value != req->node.prio)
-		pm_qos_update_target(
-			pm_qos_array[req->pm_qos_class]->constraints,
-			&req->node, PM_QOS_UPDATE_REQ, new_value);
-
-	schedule_delayed_work(&req->work, usecs_to_jiffies(timeout_us));
-}
-
-/**
- * pm_qos_remove_request - modifies an existing qos request
- * @req: handle to request list element
- *
- * Will remove pm qos request from the list of constraints and
- * recompute the current target value for the pm_qos_class.  Call this
- * on slow code paths.
- */
-void pm_qos_remove_request(struct pm_qos_request *req)
-{
-	if (!req) /*guard against callers passing in null */
-		return;
-		/* silent return to keep pcm code cleaner */
-
-	if (!pm_qos_request_active(req)) {
-		WARN(1, KERN_ERR "pm_qos_remove_request() called for unknown object\n");
+	if (cpu_latency_qos_request_active(req)) {
+		WARN(1, KERN_ERR "%s called for already added request\n", __func__);
 		return;
 	}
 
-	cancel_delayed_work_sync(&req->work);
+	trace_pm_qos_add_request(value);
 
-	trace_pm_qos_remove_request(req->pm_qos_class, PM_QOS_DEFAULT_VALUE);
-	pm_qos_update_target(pm_qos_array[req->pm_qos_class]->constraints,
-			     &req->node, PM_QOS_REMOVE_REQ,
-			     PM_QOS_DEFAULT_VALUE);
+	req->qos = &cpu_latency_constraints;
+	cpu_latency_qos_apply(req, PM_QOS_ADD_REQ, value);
+}
+EXPORT_SYMBOL_GPL(cpu_latency_qos_add_request);
+
+/**
+ * cpu_latency_qos_update_request - Modify existing CPU latency QoS request.
+ * @req : QoS request to update.
+ * @new_value: New requested constraint value.
+ *
+ * Use @new_value to update the QoS request represented by @req in the CPU
+ * latency QoS list along with updating the effective constraint value for that
+ * list.
+ */
+void cpu_latency_qos_update_request(struct pm_qos_request *req, s32 new_value)
+{
+	if (!req)
+		return;
+
+	if (!cpu_latency_qos_request_active(req)) {
+		WARN(1, KERN_ERR "%s called for unknown object\n", __func__);
+		return;
+	}
+
+	trace_pm_qos_update_request(new_value);
+
+	if (new_value == req->node.prio)
+		return;
+
+	cpu_latency_qos_apply(req, PM_QOS_UPDATE_REQ, new_value);
+}
+EXPORT_SYMBOL_GPL(cpu_latency_qos_update_request);
+
+/**
+ * cpu_latency_qos_remove_request - Remove existing CPU latency QoS request.
+ * @req: QoS request to remove.
+ *
+ * Remove the CPU latency QoS request represented by @req from the CPU latency
+ * QoS list along with updating the effective constraint value for that list.
+ */
+void cpu_latency_qos_remove_request(struct pm_qos_request *req)
+{
+	if (!req)
+		return;
+
+	if (!cpu_latency_qos_request_active(req)) {
+		WARN(1, KERN_ERR "%s called for unknown object\n", __func__);
+		return;
+	}
+
+	trace_pm_qos_remove_request(PM_QOS_DEFAULT_VALUE);
+
+	cpu_latency_qos_apply(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
 	memset(req, 0, sizeof(*req));
 }
-EXPORT_SYMBOL_GPL(pm_qos_remove_request);
+EXPORT_SYMBOL_GPL(cpu_latency_qos_remove_request);
 
-/**
- * pm_qos_add_notifier - sets notification entry for changes to target value
- * @pm_qos_class: identifies which qos target changes should be notified.
- * @notifier: notifier block managed by caller.
- *
- * will register the notifier into a notification chain that gets called
- * upon changes to the pm_qos_class target value.
- */
-int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier)
-{
-	int retval;
+/* User space interface to the CPU latency QoS via misc device. */
 
-	retval = blocking_notifier_chain_register(
-			pm_qos_array[pm_qos_class]->constraints->notifiers,
-			notifier);
-
-	return retval;
-}
-EXPORT_SYMBOL_GPL(pm_qos_add_notifier);
-
-/**
- * pm_qos_remove_notifier - deletes notification entry from chain.
- * @pm_qos_class: identifies which qos target changes are notified.
- * @notifier: notifier block to be removed.
- *
- * will remove the notifier from the notification chain that gets called
- * upon changes to the pm_qos_class target value.
- */
-int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier)
-{
-	int retval;
-
-	retval = blocking_notifier_chain_unregister(
-			pm_qos_array[pm_qos_class]->constraints->notifiers,
-			notifier);
-
-	return retval;
-}
-EXPORT_SYMBOL_GPL(pm_qos_remove_notifier);
-
-/* User space interface to PM QoS classes via misc devices */
-static int register_pm_qos_misc(struct pm_qos_object *qos, struct dentry *d)
-{
-	qos->pm_qos_power_miscdev.minor = MISC_DYNAMIC_MINOR;
-	qos->pm_qos_power_miscdev.name = qos->name;
-	qos->pm_qos_power_miscdev.fops = &pm_qos_power_fops;
-
-	debugfs_create_file(qos->name, S_IRUGO, d, (void *)qos,
-			    &pm_qos_debug_fops);
-
-	return misc_register(&qos->pm_qos_power_miscdev);
-}
-
-static int find_pm_qos_object_by_minor(int minor)
-{
-	int pm_qos_class;
-
-	for (pm_qos_class = PM_QOS_CPU_DMA_LATENCY;
-		pm_qos_class < PM_QOS_NUM_CLASSES; pm_qos_class++) {
-		if (minor ==
-			pm_qos_array[pm_qos_class]->pm_qos_power_miscdev.minor)
-			return pm_qos_class;
-	}
-	return -1;
-}
-
-static int pm_qos_power_open(struct inode *inode, struct file *filp)
-{
-	long pm_qos_class;
-
-	pm_qos_class = find_pm_qos_object_by_minor(iminor(inode));
-	if (pm_qos_class >= PM_QOS_CPU_DMA_LATENCY) {
-		struct pm_qos_request *req = kzalloc(sizeof(*req), GFP_KERNEL);
-		if (!req)
-			return -ENOMEM;
-
-		pm_qos_add_request(req, pm_qos_class, PM_QOS_DEFAULT_VALUE);
-		filp->private_data = req;
-
-		return 0;
-	}
-	return -EPERM;
-}
-
-static int pm_qos_power_release(struct inode *inode, struct file *filp)
+static int cpu_latency_qos_open(struct inode *inode, struct file *filp)
 {
 	struct pm_qos_request *req;
 
-	req = filp->private_data;
-	pm_qos_remove_request(req);
+	req = kzalloc(sizeof(*req), GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
+
+	cpu_latency_qos_add_request(req, PM_QOS_DEFAULT_VALUE);
+	filp->private_data = req;
+
+	return 0;
+}
+
+static int cpu_latency_qos_release(struct inode *inode, struct file *filp)
+{
+	struct pm_qos_request *req = filp->private_data;
+
+	filp->private_data = NULL;
+
+	cpu_latency_qos_remove_request(req);
 	kfree(req);
 
 	return 0;
 }
 
-
-static ssize_t pm_qos_power_read(struct file *filp, char __user *buf,
-		size_t count, loff_t *f_pos)
+static ssize_t cpu_latency_qos_read(struct file *filp, char __user *buf,
+				    size_t count, loff_t *f_pos)
 {
-	s32 value;
-	unsigned long flags;
 	struct pm_qos_request *req = filp->private_data;
+	unsigned long flags;
+	s32 value;
 
-	if (!req)
-		return -EINVAL;
-	if (!pm_qos_request_active(req))
+	if (!req || !cpu_latency_qos_request_active(req))
 		return -EINVAL;
 
 	spin_lock_irqsave(&pm_qos_lock, flags);
-	value = pm_qos_get_value(pm_qos_array[req->pm_qos_class]->constraints);
+	value = pm_qos_get_value(&cpu_latency_constraints);
 	spin_unlock_irqrestore(&pm_qos_lock, flags);
 
 	return simple_read_from_buffer(buf, count, f_pos, &value, sizeof(s32));
 }
 
-static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
-		size_t count, loff_t *f_pos)
+static ssize_t cpu_latency_qos_write(struct file *filp, const char __user *buf,
+				     size_t count, loff_t *f_pos)
 {
 	s32 value;
-	struct pm_qos_request *req;
 
 	if (count == sizeof(s32)) {
 		if (copy_from_user(&value, buf, sizeof(s32)))
···
 			return ret;
 	}
 
-	req = filp->private_data;
-	pm_qos_update_request(req, value);
+	cpu_latency_qos_update_request(filp->private_data, value);
 
 	return count;
 }
 
+static const struct file_operations cpu_latency_qos_fops = {
+	.write = cpu_latency_qos_write,
+	.read = cpu_latency_qos_read,
+	.open = cpu_latency_qos_open,
+	.release = cpu_latency_qos_release,
+	.llseek = noop_llseek,
+};
 
-static int __init pm_qos_power_init(void)
+static struct miscdevice cpu_latency_qos_miscdev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "cpu_dma_latency",
+	.fops = &cpu_latency_qos_fops,
+};
+
+static int __init cpu_latency_qos_init(void)
 {
-	int ret = 0;
-	int i;
-	struct dentry *d;
+	int ret;
 
-	BUILD_BUG_ON(ARRAY_SIZE(pm_qos_array) != PM_QOS_NUM_CLASSES);
-
-	d = debugfs_create_dir("pm_qos", NULL);
-
-	for (i = PM_QOS_CPU_DMA_LATENCY; i < PM_QOS_NUM_CLASSES; i++) {
-		ret = register_pm_qos_misc(pm_qos_array[i], d);
-		if (ret < 0) {
-			pr_err("%s: %s setup failed\n",
-			       __func__, pm_qos_array[i]->name);
-			return ret;
-		}
-	}
+	ret = misc_register(&cpu_latency_qos_miscdev);
+	if (ret < 0)
+		pr_err("%s: %s setup failed\n", __func__,
+		       cpu_latency_qos_miscdev.name);
 
 	return ret;
 }
-
-late_initcall(pm_qos_power_init);
+late_initcall(cpu_latency_qos_init);
+#endif /* CONFIG_CPU_IDLE */
 
 /* Definitions related to the frequency QoS below. */
 

kernel/power/user.c

···
 	switch (cmd) {
 	case SNAPSHOT_GET_IMAGE_SIZE:
 	case SNAPSHOT_AVAIL_SWAP_SIZE:
-	case SNAPSHOT_ALLOC_SWAP_PAGE: {
-		compat_loff_t __user *uoffset = compat_ptr(arg);
-		loff_t offset;
-		mm_segment_t old_fs;
-		int err;
-
-		old_fs = get_fs();
-		set_fs(KERNEL_DS);
-		err = snapshot_ioctl(file, cmd, (unsigned long) &offset);
-		set_fs(old_fs);
-		if (!err && put_user(offset, uoffset))
-			err = -EFAULT;
-		return err;
-	}
-
+	case SNAPSHOT_ALLOC_SWAP_PAGE:
 	case SNAPSHOT_CREATE_IMAGE:
 		return snapshot_ioctl(file, cmd,
 				      (unsigned long) compat_ptr(arg));

sound/core/pcm_native.c

···
 	snd_pcm_timer_resolution_change(substream);
 	snd_pcm_set_state(substream, SNDRV_PCM_STATE_SETUP);
 
-	if (pm_qos_request_active(&substream->latency_pm_qos_req))
-		pm_qos_remove_request(&substream->latency_pm_qos_req);
+	if (cpu_latency_qos_request_active(&substream->latency_pm_qos_req))
+		cpu_latency_qos_remove_request(&substream->latency_pm_qos_req);
 	if ((usecs = period_to_usecs(runtime)) >= 0)
-		pm_qos_add_request(&substream->latency_pm_qos_req,
-				   PM_QOS_CPU_DMA_LATENCY, usecs);
+		cpu_latency_qos_add_request(&substream->latency_pm_qos_req,
+					    usecs);
 	return 0;
  _error:
 	/* hardware might be unusable from this time,
···
 		return -EBADFD;
 	result = do_hw_free(substream);
 	snd_pcm_set_state(substream, SNDRV_PCM_STATE_OPEN);
-	pm_qos_remove_request(&substream->latency_pm_qos_req);
+	cpu_latency_qos_remove_request(&substream->latency_pm_qos_req);
 	return result;
 }
 
···
 		substream->ops->close(substream);
 		substream->hw_opened = 0;
 	}
-	if (pm_qos_request_active(&substream->latency_pm_qos_req))
-		pm_qos_remove_request(&substream->latency_pm_qos_req);
+	if (cpu_latency_qos_request_active(&substream->latency_pm_qos_req))
+		cpu_latency_qos_remove_request(&substream->latency_pm_qos_req);
 	if (substream->pcm_release) {
 		substream->pcm_release(substream);
 		substream->pcm_release = NULL;

sound/soc/intel/atom/sst/sst.c

···
 		ret = -ENOMEM;
 		goto do_free_mem;
 	}
-	pm_qos_add_request(ctx->qos, PM_QOS_CPU_DMA_LATENCY,
-				PM_QOS_DEFAULT_VALUE);
+	cpu_latency_qos_add_request(ctx->qos, PM_QOS_DEFAULT_VALUE);
 
 	dev_dbg(ctx->dev, "Requesting FW %s now...\n", ctx->firmware_name);
 	ret = request_firmware_nowait(THIS_MODULE, true, ctx->firmware_name,
···
 	sysfs_remove_group(&ctx->dev->kobj, &sst_fw_version_attr_group);
 	flush_scheduled_work();
 	destroy_workqueue(ctx->post_msg_wq);
-	pm_qos_remove_request(ctx->qos);
+	cpu_latency_qos_remove_request(ctx->qos);
 	kfree(ctx->fw_sg_list.src);
 	kfree(ctx->fw_sg_list.dst);
 	ctx->fw_sg_list.list_len = 0;

sound/soc/intel/atom/sst/sst_loader.c

···
 		return -ENOMEM;
 
 	/* Prevent C-states beyond C6 */
-	pm_qos_update_request(sst_drv_ctx->qos, 0);
+	cpu_latency_qos_update_request(sst_drv_ctx->qos, 0);
 
 	sst_drv_ctx->sst_state = SST_FW_LOADING;
 
···
 
 restore:
 	/* Re-enable Deeper C-states beyond C6 */
-	pm_qos_update_request(sst_drv_ctx->qos, PM_QOS_DEFAULT_VALUE);
+	cpu_latency_qos_update_request(sst_drv_ctx->qos, PM_QOS_DEFAULT_VALUE);
 	sst_free_block(sst_drv_ctx, block);
 	dev_dbg(sst_drv_ctx->dev, "fw load successful!!!\n");
 

sound/soc/ti/omap-dmic.c

···
 
 	mutex_lock(&dmic->mutex);
 
-	pm_qos_remove_request(&dmic->pm_qos_req);
+	cpu_latency_qos_remove_request(&dmic->pm_qos_req);
 
 	if (!dai->active)
 		dmic->active = 0;
···
 	struct omap_dmic *dmic = snd_soc_dai_get_drvdata(dai);
 	u32 ctrl;
 
-	if (pm_qos_request_active(&dmic->pm_qos_req))
-		pm_qos_update_request(&dmic->pm_qos_req, dmic->latency);
+	if (cpu_latency_qos_request_active(&dmic->pm_qos_req))
+		cpu_latency_qos_update_request(&dmic->pm_qos_req,
+					       dmic->latency);
 
 	/* Configure uplink threshold */
 	omap_dmic_write(dmic, OMAP_DMIC_FIFO_CTRL_REG, dmic->threshold);

sound/soc/ti/omap-mcbsp.c

···
 	int stream2 = tx ? SNDRV_PCM_STREAM_CAPTURE : SNDRV_PCM_STREAM_PLAYBACK;
 
 	if (mcbsp->latency[stream2])
-		pm_qos_update_request(&mcbsp->pm_qos_req,
-				      mcbsp->latency[stream2]);
+		cpu_latency_qos_update_request(&mcbsp->pm_qos_req,
+					       mcbsp->latency[stream2]);
 	else if (mcbsp->latency[stream1])
-		pm_qos_remove_request(&mcbsp->pm_qos_req);
+		cpu_latency_qos_remove_request(&mcbsp->pm_qos_req);
 
 	mcbsp->latency[stream1] = 0;
 
···
 	if (!latency || mcbsp->latency[stream1] < latency)
 		latency = mcbsp->latency[stream1];
 
-	if (pm_qos_request_active(pm_qos_req))
-		pm_qos_update_request(pm_qos_req, latency);
+	if (cpu_latency_qos_request_active(pm_qos_req))
+		cpu_latency_qos_update_request(pm_qos_req, latency);
 	else if (latency)
-		pm_qos_add_request(pm_qos_req, PM_QOS_CPU_DMA_LATENCY, latency);
+		cpu_latency_qos_add_request(pm_qos_req, latency);
 
 	return 0;
 }
···
 	if (mcbsp->pdata->ops && mcbsp->pdata->ops->free)
 		mcbsp->pdata->ops->free(mcbsp->id);
 
-	if (pm_qos_request_active(&mcbsp->pm_qos_req))
-		pm_qos_remove_request(&mcbsp->pm_qos_req);
+	if (cpu_latency_qos_request_active(&mcbsp->pm_qos_req))
+		cpu_latency_qos_remove_request(&mcbsp->pm_qos_req);
 
 	if (mcbsp->pdata->buffer_size)
 		sysfs_remove_group(&mcbsp->dev->kobj, &additional_attr_group);

sound/soc/ti/omap-mcpdm.c

···
 	}
 
 	if (mcpdm->latency[stream2])
-		pm_qos_update_request(&mcpdm->pm_qos_req,
-				      mcpdm->latency[stream2]);
+		cpu_latency_qos_update_request(&mcpdm->pm_qos_req,
+					       mcpdm->latency[stream2]);
 	else if (mcpdm->latency[stream1])
-		pm_qos_remove_request(&mcpdm->pm_qos_req);
+		cpu_latency_qos_remove_request(&mcpdm->pm_qos_req);
 
 	mcpdm->latency[stream1] = 0;
 
···
 	if (!latency || mcpdm->latency[stream1] < latency)
 		latency = mcpdm->latency[stream1];
 
-	if (pm_qos_request_active(pm_qos_req))
-		pm_qos_update_request(pm_qos_req, latency);
+	if (cpu_latency_qos_request_active(pm_qos_req))
+		cpu_latency_qos_update_request(pm_qos_req, latency);
 	else if (latency)
-		pm_qos_add_request(pm_qos_req, PM_QOS_CPU_DMA_LATENCY, latency);
+		cpu_latency_qos_add_request(pm_qos_req, latency);
 
 	if (!omap_mcpdm_active(mcpdm)) {
 		omap_mcpdm_start(mcpdm);
···
 	free_irq(mcpdm->irq, (void *)mcpdm);
 	pm_runtime_disable(mcpdm->dev);
 
-	if (pm_qos_request_active(&mcpdm->pm_qos_req))
-		pm_qos_remove_request(&mcpdm->pm_qos_req);
+	if (cpu_latency_qos_request_active(&mcpdm->pm_qos_req))
+		cpu_latency_qos_remove_request(&mcpdm->pm_qos_req);
 
 	return 0;
 }

tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py

···
     output_png = 'all_cpu_durations.png'
     g_plot = common_all_gnuplot_settings(output_png)
 #   autoscale this one, no set y range
-    g_plot('set ytics 0, 500')
     g_plot('set ylabel "Timer Duration (MilliSeconds)"')
     g_plot('set title "{} : cpu durations : {:%F %H:%M}"'.format(testname, datetime.now()))