Merge tag 'pm-5.15-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull more power management updates from Rafael Wysocki:
 "These are mostly ARM cpufreq driver updates, including one new
  MediaTek driver that has just passed all of the reviews, with the
  addition of a revert of a recent intel_pstate commit, some core
  cpufreq changes and a DT-related update of the operating performance
  points (OPP) support code.

  Specifics:

   - Add new cpufreq driver for the MediaTek MT6779 platform called
     mediatek-hw along with corresponding DT bindings (Hector.Yuan).

   - Add DCVS interrupt support to the qcom-cpufreq-hw driver (Thara
     Gopinath).

   - Make the qcom-cpufreq-hw driver set the dvfs_possible_from_any_cpu
     policy flag (Taniya Das).

   - Blocklist more Qualcomm platforms in cpufreq-dt-platdev (Bjorn
     Andersson).

   - Make the vexpress cpufreq driver set the CPUFREQ_IS_COOLING_DEV
     flag (Viresh Kumar).

   - Add new cpufreq driver callback to allow drivers to register with
     the Energy Model in a consistent way and make several drivers use
     it (Viresh Kumar).

   - Change the remaining users of the .ready() cpufreq driver callback
     to move the code from it elsewhere and drop it from the cpufreq
     core (Viresh Kumar).

   - Revert recent intel_pstate change adding HWP guaranteed performance
     change notification support to it that led to problems, because the
     notification in question is triggered prematurely on some systems
     (Rafael Wysocki).

   - Convert the OPP DT bindings to DT schema and clean them up while at
     it (Rob Herring)"

* tag 'pm-5.15-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (23 commits)
  Revert "cpufreq: intel_pstate: Process HWP Guaranteed change notification"
  cpufreq: mediatek-hw: Add support for CPUFREQ HW
  cpufreq: Add of_perf_domain_get_sharing_cpumask
  dt-bindings: cpufreq: add bindings for MediaTek cpufreq HW
  cpufreq: Remove ready() callback
  cpufreq: sh: Remove sh_cpufreq_cpu_ready()
  cpufreq: acpi: Remove acpi_cpufreq_cpu_ready()
  cpufreq: qcom-hw: Set dvfs_possible_from_any_cpu cpufreq driver flag
  cpufreq: blocklist more Qualcomm platforms in cpufreq-dt-platdev
  cpufreq: qcom-cpufreq-hw: Add dcvs interrupt support
  cpufreq: scmi: Use .register_em() to register with energy model
  cpufreq: vexpress: Use .register_em() to register with energy model
  cpufreq: scpi: Use .register_em() to register with energy model
  dt-bindings: opp: Convert to DT schema
  dt-bindings: Clean-up OPP binding node names in examples
  ARM: dts: omap: Drop references to opp.txt
  cpufreq: qcom-cpufreq-hw: Use .register_em() to register with energy model
  cpufreq: omap: Use .register_em() to register with energy model
  cpufreq: mediatek: Use .register_em() to register with energy model
  cpufreq: imx6q: Use .register_em() to register with energy model
  ...

Documentation/cpu-freq/cpu-drivers.rst

@@ -75,9 +75,6 @@ And optionally
  .resume - A pointer to a per-policy resume function which is called
  with interrupts disabled and _before_ the governor is started again.
 
- .ready - A pointer to a per-policy ready function which is called after
- the policy is fully initialized.
-
  .attr - A pointer to a NULL-terminated list of "struct freq_attr" which
  allow to export values to sysfs.
 

Documentation/devicetree/bindings/cpufreq/cpufreq-dt.txt

@@ -11,7 +11,7 @@ Required properties:
 - None
 
 Optional properties:
-- operating-points: Refer to Documentation/devicetree/bindings/opp/opp.txt for
+- operating-points: Refer to Documentation/devicetree/bindings/opp/opp-v1.yaml for
   details. OPPs *must* be supplied either via DT, i.e. this property, or
   populated at runtime.
 - clock-latency: Specify the possible maximum transition latency for clock,

Documentation/devicetree/bindings/cpufreq/cpufreq-mediatek-hw.yaml

+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/cpufreq/cpufreq-mediatek-hw.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: MediaTek's CPUFREQ Bindings
+
+maintainers:
+  - Hector Yuan <hector.yuan@mediatek.com>
+
+description:
+  CPUFREQ HW is a hardware engine used by MediaTek SoCs to
+  manage frequency in hardware. It is capable of controlling
+  frequency for multiple clusters.
+
+properties:
+  compatible:
+    const: mediatek,cpufreq-hw
+
+  reg:
+    minItems: 1
+    maxItems: 2
+    description:
+      Addresses and sizes for the memory of the HW bases in
+      each frequency domain. Each entry corresponds to
+      a register bank for each frequency domain present.
+
+  "#performance-domain-cells":
+    description:
+      Number of cells in a performance domain specifier.
+      Set const to 1 here for nodes providing multiple
+      performance domains.
+    const: 1
+
+required:
+  - compatible
+  - reg
+  - "#performance-domain-cells"
+
+additionalProperties: false
+
+examples:
+  - |
+    cpus {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            cpu0: cpu@0 {
+                device_type = "cpu";
+                compatible = "arm,cortex-a55";
+                enable-method = "psci";
+                performance-domains = <&performance 0>;
+                reg = <0x000>;
+            };
+    };
+
+    /* ... */
+
+    soc {
+        #address-cells = <2>;
+        #size-cells = <2>;
+
+        performance: performance-controller@11bc00 {
+            compatible = "mediatek,cpufreq-hw";
+            reg = <0 0x0011bc10 0 0x120>, <0 0x0011bd30 0 0x120>;
+
+            #performance-domain-cells = <1>;
+        };
+    };

Documentation/devicetree/bindings/cpufreq/cpufreq-mediatek.txt

@@ -10,7 +10,7 @@ Required properties:
 			  transition and not stable yet.
 	Please refer to Documentation/devicetree/bindings/clock/clock-bindings.txt for
 	generic clock consumer properties.
-- operating-points-v2: Please refer to Documentation/devicetree/bindings/opp/opp.txt
+- operating-points-v2: Please refer to Documentation/devicetree/bindings/opp/opp-v2.yaml
 	for detail.
 - proc-supply: Regulator for Vproc of CPU cluster.
 

Documentation/devicetree/bindings/cpufreq/cpufreq-st.txt

@@ -6,8 +6,6 @@ from the SoC, then supplies the OPP framework with 'prop' and 'supported
 hardware' information respectively.  The framework is then able to read
 the DT and operate in the usual way.
 
-For more information about the expected DT format [See: ../opp/opp.txt].
-
 Frequency Scaling only
 ----------------------
 
@@ -15,7 +13,7 @@ No vendor specific driver required for this.
 
 Located in CPU's node:
 
-- operating-points		: [See: ../power/opp.txt]
+- operating-points		: [See: ../power/opp-v1.yaml]
 
 Example [safe]
 --------------
@@ -37,7 +35,7 @@ This requires the ST CPUFreq driver to supply 'process' and 'version' info.
 
 Located in CPU's node:
 
-- operating-points-v2		: [See ../power/opp.txt]
+- operating-points-v2		: [See ../power/opp-v2.yaml]
 
 Example [unsafe]
 ----------------

Documentation/devicetree/bindings/cpufreq/nvidia,tegra20-cpufreq.txt

@@ -4,7 +4,7 @@ Binding for NVIDIA Tegra20 CPUFreq
 Required properties:
 - clocks: Must contain an entry for the CPU clock.
   See ../clocks/clock-bindings.txt for details.
-- operating-points-v2: See ../bindings/opp/opp.txt for details.
+- operating-points-v2: See ../bindings/opp/opp-v2.yaml for details.
 - #cooling-cells: Should be 2. See ../thermal/thermal-cooling-devices.yaml for details.
 
 For each opp entry in 'operating-points-v2' table:

Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt

@@ -8,7 +8,7 @@ Required properties:
 - clocks:		 Phandles for clock specified in "clock-names" property
 - clock-names :		 The name of clock used by the DFI, must be
 			 "pclk_ddr_mon";
-- operating-points-v2:	 Refer to Documentation/devicetree/bindings/opp/opp.txt
+- operating-points-v2:	 Refer to Documentation/devicetree/bindings/opp/opp-v2.yaml
 			 for details.
 - center-supply:	 DMC supply node.
 - status:		 Marks the node enabled/disabled.

Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml

@@ -137,7 +137,7 @@ examples:
       resets = <&reset 0>, <&reset 1>;
     };
 
-    gpu_opp_table: opp_table0 {
+    gpu_opp_table: opp-table {
       compatible = "operating-points-v2";
 
       opp-533000000 {

Documentation/devicetree/bindings/gpu/arm,mali-midgard.yaml

@@ -160,7 +160,7 @@ examples:
       #cooling-cells = <2>;
     };
 
-    gpu_opp_table: opp_table0 {
+    gpu_opp_table: opp-table {
       compatible = "operating-points-v2";
 
       opp-533000000 {

Documentation/devicetree/bindings/interconnect/fsl,imx8m-noc.yaml

@@ -81,10 +81,10 @@ examples:
         noc_opp_table: opp-table {
             compatible = "operating-points-v2";
 
-            opp-133M {
+            opp-133333333 {
                 opp-hz = /bits/ 64 <133333333>;
             };
-            opp-800M {
+            opp-800000000 {
                 opp-hz = /bits/ 64 <800000000>;
             };
         };

Documentation/devicetree/bindings/opp/allwinner,sun50i-h6-operating-points.yaml

@@ -18,6 +18,9 @@ description: |
   sun50i-cpufreq-nvmem driver reads the efuse value from the SoC to
   provide the OPP framework with required information.
 
+allOf:
+  - $ref: opp-v2-base.yaml#
+
 properties:
   compatible:
     const: allwinner,sun50i-h6-operating-points
@@ -43,6 +46,7 @@ patternProperties:
 
     properties:
       opp-hz: true
+      clock-latency-ns: true
 
     patternProperties:
       "opp-microvolt-.*": true

Documentation/devicetree/bindings/opp/opp-v1.yaml

+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/opp/opp-v1.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Generic OPP (Operating Performance Points) v1 Bindings
+
+maintainers:
+  - Viresh Kumar <viresh.kumar@linaro.org>
+
+description: |+
+  Devices work at voltage-current-frequency combinations and some implementations
+  have the liberty of choosing these. These combinations are called Operating
+  Performance Points aka OPPs. This document defines bindings for these OPPs
+  applicable across wide range of devices. For illustration purpose, this document
+  uses CPU as a device.
+
+  This binding only supports voltage-frequency pairs.
+
+select: true
+
+properties:
+  operating-points:
+    $ref: /schemas/types.yaml#/definitions/uint32-matrix
+    items:
+      items:
+        - description: Frequency in kHz
+        - description: Voltage for OPP in uV
+
+
+additionalProperties: true
+examples:
+  - |
+    cpus {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        cpu@0 {
+            compatible = "arm,cortex-a9";
+            device_type = "cpu";
+            reg = <0>;
+            next-level-cache = <&L2>;
+            operating-points =
+                /* kHz    uV */
+                <792000 1100000>,
+                <396000 950000>,
+                <198000 850000>;
+        };
+    };
+...

Documentation/devicetree/bindings/opp/opp-v2-base.yaml

+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/opp/opp-v2-base.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Generic OPP (Operating Performance Points) Common Binding
+
+maintainers:
+  - Viresh Kumar <viresh.kumar@linaro.org>
+
+description: |
+  Devices work at voltage-current-frequency combinations and some implementations
+  have the liberty of choosing these. These combinations are called Operating
+  Performance Points aka OPPs. This document defines bindings for these OPPs
+  applicable across wide range of devices. For illustration purpose, this document
+  uses CPU as a device.
+
+  This describes the OPPs belonging to a device.
+
+select: false
+
+properties:
+  $nodename:
+    pattern: '^opp-table(-[a-z0-9]+)?$'
+
+  opp-shared:
+    description:
+      Indicates that device nodes using this OPP Table Node's phandle switch
+      their DVFS state together, i.e. they share clock/voltage/current lines.
+      Missing property means devices have independent clock/voltage/current
+      lines, but they share OPP tables.
+    type: boolean
+
+patternProperties:
+  '^opp-?[0-9]+$':
+    type: object
+    description:
+      One or more OPP nodes describing voltage-current-frequency combinations.
+      Their name isn't significant but their phandle can be used to reference an
+      OPP. These are mandatory except for the case where the OPP table is
+      present only to indicate dependency between devices using the opp-shared
+      property.
+
+    properties:
+      opp-hz:
+        description:
+          Frequency in Hz, expressed as a 64-bit big-endian integer. This is a
+          required property for all device nodes, unless another "required"
+          property to uniquely identify the OPP nodes exists. Devices like power
+          domains must have another (implementation dependent) property.
+
+      opp-microvolt:
+        description: |
+          Voltage for the OPP
+
+          A single regulator's voltage is specified with an array of size one or three.
+          Single entry is for target voltage and three entries are for <target min max>
+          voltages.
+
+          Entries for multiple regulators shall be provided in the same field separated
+          by angular brackets <>. The OPP binding doesn't provide any provisions to
+          relate the values to their power supplies or the order in which the supplies
+          need to be configured and that is left for the implementation specific
+          binding.
+
+          Entries for all regulators shall be of the same size, i.e. either all use a
+          single value or triplets.
+        minItems: 1
+        maxItems: 8   # Should be enough regulators
+        items:
+          minItems: 1
+          maxItems: 3
+
+      opp-microamp:
+        description: |
+          The maximum current drawn by the device in microamperes considering
+          system specific parameters (such as transients, process, aging,
+          maximum operating temperature range etc.) as necessary. This may be
+          used to set the most efficient regulator operating mode.
+
+          Should only be set if opp-microvolt or opp-microvolt-<name> is set for
+          the OPP.
+
+          Entries for multiple regulators shall be provided in the same field
+          separated by angular brackets <>. If current values aren't required
+          for a regulator, then it shall be filled with 0. If current values
+          aren't required for any of the regulators, then this field is not
+          required. The OPP binding doesn't provide any provisions to relate the
+          values to their power supplies or the order in which the supplies need
+          to be configured and that is left for the implementation specific
+          binding.
+        minItems: 1
+        maxItems: 8   # Should be enough regulators
+
+      opp-level:
+        description:
+          A value representing the performance level of the device.
+        $ref: /schemas/types.yaml#/definitions/uint32
+
+      opp-peak-kBps:
+        description:
+          Peak bandwidth in kilobytes per second, expressed as an array of
+          32-bit big-endian integers. Each element of the array represents the
+          peak bandwidth value of each interconnect path. The number of elements
+          should match the number of interconnect paths.
+        minItems: 1
+        maxItems: 32  # Should be enough
+
+      opp-avg-kBps:
+        description:
+          Average bandwidth in kilobytes per second, expressed as an array
+          of 32-bit big-endian integers. Each element of the array represents the
+          average bandwidth value of each interconnect path. The number of elements
+          should match the number of interconnect paths. This property is only
+          meaningful in OPP tables where opp-peak-kBps is present.
+        minItems: 1
+        maxItems: 32  # Should be enough
+
+      clock-latency-ns:
+        description:
+          Specifies the maximum possible transition latency (in nanoseconds) for
+          switching to this OPP from any other OPP.
+
+      turbo-mode:
+        description:
+          Marks the OPP to be used only for turbo modes. Turbo mode is available
+          on some platforms, where the device can run over its operating
+          frequency for a short duration of time limited by the device's power,
+          current and thermal limits.
+        type: boolean
+
+      opp-suspend:
+        description:
+          Marks the OPP to be used during device suspend. If multiple OPPs in
+          the table have this, the OPP with highest opp-hz will be used.
+        type: boolean
+
+      opp-supported-hw:
+        description: |
+          This property allows a platform to enable only a subset of the OPPs
+          from the larger set present in the OPP table, based on the current
+          version of the hardware (already known to the operating system).
+
+          Each block present in the array of blocks in this property, represents
+          a sub-group of hardware versions supported by the OPP. i.e. <sub-group
+          A>, <sub-group B>, etc. The OPP will be enabled if _any_ of these
+          sub-groups match the hardware's version.
+
+          Each sub-group is a platform defined array representing the hierarchy
+          of hardware versions supported by the platform. For a platform with
+          three hierarchical levels of version (X.Y.Z), this field shall look
+          like
+
+          opp-supported-hw = <X1 Y1 Z1>, <X2 Y2 Z2>, <X3 Y3 Z3>.
+
+          Each level (eg. X1) in version hierarchy is represented by a 32 bit
+          value, one bit per version and so there can be maximum 32 versions per
+          level. Logical AND (&) operation is performed for each level with the
+          hardware's level version and a non-zero output for _all_ the levels in
+          a sub-group means the OPP is supported by hardware. A value of
+          0xFFFFFFFF for each level in the sub-group will enable the OPP for all
+          versions for the hardware.
+        $ref: /schemas/types.yaml#/definitions/uint32-matrix
+        maxItems: 32
+        items:
+          minItems: 1
+          maxItems: 4
+
+      required-opps:
+        description:
+          This contains phandle to an OPP node in another device's OPP table. It
+          may contain an array of phandles, where each phandle points to an OPP
+          of a different device. It should not contain multiple phandles to the
+          OPP nodes in the same OPP table. This specifies the minimum required
+          OPP of the device(s), whose OPP's phandle is present in this property,
+          for the functioning of the current device at the current OPP (where
+          this property is present).
+        $ref: /schemas/types.yaml#/definitions/phandle-array
+
+    patternProperties:
+      '^opp-microvolt-':
+        description:
+          Named opp-microvolt property. This is exactly similar to the above
+          opp-microvolt property, but allows multiple voltage ranges to be
+          provided for the same OPP. At runtime, the platform can pick a <name>
+          and matching opp-microvolt-<name> property will be enabled for all
+          OPPs. If the platform doesn't pick a specific <name> or the <name>
+          doesn't match with any opp-microvolt-<name> properties, then
+          opp-microvolt property shall be used, if present.
+        $ref: /schemas/types.yaml#/definitions/uint32-matrix
+        minItems: 1
+        maxItems: 8   # Should be enough regulators
+        items:
+          minItems: 1
+          maxItems: 3
+
+      '^opp-microamp-':
+        description:
+          Named opp-microamp property. Similar to opp-microvolt-<name> property,
+          but for microamp instead.
+        $ref: /schemas/types.yaml#/definitions/uint32-array
+        minItems: 1
+        maxItems: 8   # Should be enough regulators
+
+    dependencies:
+      opp-avg-kBps: [ opp-peak-kBps ]
+
+required:
+  - compatible
+
+additionalProperties: true
+
+...

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

 Qualcomm OPP bindings to describe OPP nodes
 
 The bindings are based on top of the operating-points-v2 bindings
-described in Documentation/devicetree/bindings/opp/opp.txt
+described in Documentation/devicetree/bindings/opp/opp-v2-base.yaml
 Additional properties are described below.
 
 * OPP Table Node

Documentation/devicetree/bindings/opp/ti-omap5-opp-supply.txt

@@ -13,7 +13,7 @@ regulators to the device that will undergo OPP transitions we can make use
 of the multi regulator binding that is part of the OPP core described here [1]
 to describe both regulators needed by the platform.
 
-[1] Documentation/devicetree/bindings/opp/opp.txt
+[1] Documentation/devicetree/bindings/opp/opp-v2.yaml
 
 Required Properties for Device Node:
 - vdd-supply: phandle to regulator controlling VDD supply

Documentation/devicetree/bindings/power/power-domain.yaml

@@ -46,7 +46,7 @@ properties:
       Phandles to the OPP tables of power domains provided by a power domain
       provider. If the provider provides a single power domain only or all
       the power domains provided by the provider have identical OPP tables,
-      then this shall contain a single phandle. Refer to ../opp/opp.txt
+      then this shall contain a single phandle. Refer to ../opp/opp-v2-base.yaml
       for more information.
 
   "#power-domain-cells":

Documentation/translations/zh_CN/cpu-freq/cpu-drivers.rst

@@ -82,8 +82,6 @@ CPUfreq核心层注册一个cpufreq_driver结构体。
  .resume - 一个指向per-policy恢复函数的指针，该函数在关中断且在调节器再一次开始前被
  调用。
 
- .ready - 一个指向per-policy准备函数的指针，该函数在策略完全初始化之后被调用。
-
  .attr - 一个指向NULL结尾的"struct freq_attr"列表的指针，该函数允许导出值到
  sysfs。
 

arch/arm/boot/dts/omap34xx.dtsi

@@ -24,7 +24,6 @@ cpu: cpu@0 {
 		};
 	};
 
-	/* see Documentation/devicetree/bindings/opp/opp.txt */
 	cpu0_opp_table: opp-table {
 		compatible = "operating-points-v2-ti-cpu";
 		syscon = <&scm_conf>;

arch/arm/boot/dts/omap36xx.dtsi

@@ -29,7 +29,6 @@ cpu: cpu@0 {
 		};
 	};
 
-	/* see Documentation/devicetree/bindings/opp/opp.txt */
 	cpu0_opp_table: opp-table {
 		compatible = "operating-points-v2-ti-cpu";
 		syscon = <&scm_conf>;

drivers/base/arch_topology.c

@@ -149,6 +149,7 @@ void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq,
 }
 
 DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
+EXPORT_PER_CPU_SYMBOL_GPL(cpu_scale);
 
 void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity)
 {
@@ -165,6 +166,7 @@ void topology_set_thermal_pressure(const struct cpumask *cpus,
 	for_each_cpu(cpu, cpus)
 		WRITE_ONCE(per_cpu(thermal_pressure, cpu), th_pressure);
 }
+EXPORT_SYMBOL_GPL(topology_set_thermal_pressure);
 
 static ssize_t cpu_capacity_show(struct device *dev,
 				 struct device_attribute *attr,

drivers/cpufreq/Kconfig.arm

@@ -133,6 +133,18 @@ config ARM_MEDIATEK_CPUFREQ
 	help
 	  This adds the CPUFreq driver support for MediaTek SoCs.
 
+config ARM_MEDIATEK_CPUFREQ_HW
+	tristate "MediaTek CPUFreq HW driver"
+	depends on ARCH_MEDIATEK || COMPILE_TEST
+	default m
+	help
+	  Support for the CPUFreq HW driver.
+	  Some MediaTek chipsets have a HW engine to offload the steps
+	  necessary for changing the frequency of the CPUs. Firmware loaded
+	  in this engine exposes a programming interface to the OS.
+	  The driver implements the cpufreq interface for this HW engine.
+	  Say Y if you want to support CPUFreq HW.
+
 config ARM_OMAP2PLUS_CPUFREQ
 	bool "TI OMAP2+"
 	depends on ARCH_OMAP2PLUS

drivers/cpufreq/Makefile

@@ -56,6 +56,7 @@ obj-$(CONFIG_ARM_IMX6Q_CPUFREQ)		+= imx6q-cpufreq.o
 obj-$(CONFIG_ARM_IMX_CPUFREQ_DT)	+= imx-cpufreq-dt.o
 obj-$(CONFIG_ARM_KIRKWOOD_CPUFREQ)	+= kirkwood-cpufreq.o
 obj-$(CONFIG_ARM_MEDIATEK_CPUFREQ)	+= mediatek-cpufreq.o
+obj-$(CONFIG_ARM_MEDIATEK_CPUFREQ_HW)	+= mediatek-cpufreq-hw.o
 obj-$(CONFIG_MACH_MVEBU_V7)		+= mvebu-cpufreq.o
 obj-$(CONFIG_ARM_OMAP2PLUS_CPUFREQ)	+= omap-cpufreq.o
 obj-$(CONFIG_ARM_PXA2xx_CPUFREQ)	+= pxa2xx-cpufreq.o

drivers/cpufreq/acpi-cpufreq.c

@@ -889,6 +889,9 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	policy->fast_switch_possible = !acpi_pstate_strict &&
 		!(policy_is_shared(policy) && policy->shared_type != CPUFREQ_SHARED_TYPE_ANY);
 
+	if (perf->states[0].core_frequency * 1000 != freq_table[0].frequency)
+		pr_warn(FW_WARN "P-state 0 is not max freq\n");
+
 	return result;
 
 err_unreg:
@@ -918,16 +921,6 @@ static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 	return 0;
 }
 
-static void acpi_cpufreq_cpu_ready(struct cpufreq_policy *policy)
-{
-	struct acpi_processor_performance *perf = per_cpu_ptr(acpi_perf_data,
-							      policy->cpu);
-	unsigned int freq = policy->freq_table[0].frequency;
-
-	if (perf->states[0].core_frequency * 1000 != freq)
-		pr_warn(FW_WARN "P-state 0 is not max freq\n");
-}
-
 static int acpi_cpufreq_resume(struct cpufreq_policy *policy)
 {
 	struct acpi_cpufreq_data *data = policy->driver_data;
@@ -955,7 +948,6 @@ static struct cpufreq_driver acpi_cpufreq_driver = {
 	.bios_limit	= acpi_processor_get_bios_limit,
 	.init		= acpi_cpufreq_cpu_init,
 	.exit		= acpi_cpufreq_cpu_exit,
-	.ready		= acpi_cpufreq_cpu_ready,
 	.resume		= acpi_cpufreq_resume,
 	.name		= "acpi-cpufreq",
 	.attr		= acpi_cpufreq_attr,

drivers/cpufreq/cpufreq-dt-platdev.c

@@ -137,11 +137,15 @@ static const struct of_device_id blocklist[] __initconst = {
 	{ .compatible = "qcom,apq8096", },
 	{ .compatible = "qcom,msm8996", },
 	{ .compatible = "qcom,qcs404", },
+	{ .compatible = "qcom,sa8155p" },
 	{ .compatible = "qcom,sc7180", },
 	{ .compatible = "qcom,sc7280", },
 	{ .compatible = "qcom,sc8180x", },
 	{ .compatible = "qcom,sdm845", },
+	{ .compatible = "qcom,sm6350", },
 	{ .compatible = "qcom,sm8150", },
+	{ .compatible = "qcom,sm8250", },
+	{ .compatible = "qcom,sm8350", },
 
 	{ .compatible = "st,stih407", },
 	{ .compatible = "st,stih410", },

drivers/cpufreq/cpufreq-dt.c

@@ -143,8 +143,6 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		cpufreq_dt_attr[1] = &cpufreq_freq_attr_scaling_boost_freqs;
 	}
 
-	dev_pm_opp_of_register_em(cpu_dev, policy->cpus);
-
 	return 0;
 
 out_clk_put:
@@ -184,6 +182,7 @@ static struct cpufreq_driver dt_cpufreq_driver = {
 	.exit = cpufreq_exit,
 	.online = cpufreq_online,
 	.offline = cpufreq_offline,
+	.register_em = cpufreq_register_em_with_opp,
 	.name = "cpufreq-dt",
 	.attr = cpufreq_dt_attr,
 	.suspend = cpufreq_generic_suspend,

drivers/cpufreq/cpufreq.c

@@ -1491,6 +1491,19 @@ static int cpufreq_online(unsigned int cpu)
 		write_lock_irqsave(&cpufreq_driver_lock, flags);
 		list_add(&policy->policy_list, &cpufreq_policy_list);
 		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+
+		/*
+		 * Register with the energy model before
+		 * sched_cpufreq_governor_change() is called, which will result
+		 * in rebuilding of the sched domains, which should only be done
+		 * once the energy model is properly initialized for the policy
+		 * first.
+		 *
+		 * Also, this should be called before the policy is registered
+		 * with cooling framework.
+		 */
+		if (cpufreq_driver->register_em)
+			cpufreq_driver->register_em(policy);
 	}
 
 	ret = cpufreq_init_policy(policy);
@@ -1504,10 +1517,6 @@ static int cpufreq_online(unsigned int cpu)
 
 	kobject_uevent(&policy->kobj, KOBJ_ADD);
 
-	/* Callback for handling stuff after policy is ready */
-	if (cpufreq_driver->ready)
-		cpufreq_driver->ready(policy);
-
 	if (cpufreq_thermal_control_enabled(cpufreq_driver))
 		policy->cdev = of_cpufreq_cooling_register(policy);
 

drivers/cpufreq/imx6q-cpufreq.c

@@ -192,7 +192,6 @@ static int imx6q_cpufreq_init(struct cpufreq_policy *policy)
 	policy->clk = clks[ARM].clk;
 	cpufreq_generic_init(policy, freq_table, transition_latency);
 	policy->suspend_freq = max_freq;
-	dev_pm_opp_of_register_em(cpu_dev, policy->cpus);
 
 	return 0;
 }
@@ -204,6 +203,7 @@ static struct cpufreq_driver imx6q_cpufreq_driver = {
 	.target_index = imx6q_set_target,
 	.get = cpufreq_generic_get,
 	.init = imx6q_cpufreq_init,
+	.register_em = cpufreq_register_em_with_opp,
 	.name = "imx6q-cpufreq",
 	.attr = cpufreq_generic_attr,
 	.suspend = cpufreq_generic_suspend,

drivers/cpufreq/intel_pstate.c

@@ -32,7 +32,6 @@
 #include <asm/cpu_device_id.h>
 #include <asm/cpufeature.h>
 #include <asm/intel-family.h>
-#include "../drivers/thermal/intel/thermal_interrupt.h"
 
 #define INTEL_PSTATE_SAMPLING_INTERVAL	(10 * NSEC_PER_MSEC)
 
@@ -220,7 +219,6 @@ struct global_params {
  * @sched_flags:	Store scheduler flags for possible cross CPU update
  * @hwp_boost_min:	Last HWP boosted min performance
  * @suspended:		Whether or not the driver has been suspended.
- * @hwp_notify_work:	workqueue for HWP notifications.
  *
  * This structure stores per CPU instance data for all CPUs.
  */
@@ -259,7 +257,6 @@ struct cpudata {
 	unsigned int sched_flags;
 	u32 hwp_boost_min;
 	bool suspended;
-	struct delayed_work hwp_notify_work;
 };
 
 static struct cpudata **all_cpu_data;
@@ -1628,40 +1625,6 @@ static void intel_pstate_sysfs_hide_hwp_dynamic_boost(void)
 
 /************************** sysfs end ************************/
 
-static void intel_pstate_notify_work(struct work_struct *work)
-{
-	mutex_lock(&intel_pstate_driver_lock);
-	cpufreq_update_policy(smp_processor_id());
-	wrmsrl(MSR_HWP_STATUS, 0);
-	mutex_unlock(&intel_pstate_driver_lock);
-}
-
-void notify_hwp_interrupt(void)
-{
-	unsigned int this_cpu = smp_processor_id();
-	struct cpudata *cpudata;
-	u64 value;
-
-	if (!hwp_active || !boot_cpu_has(X86_FEATURE_HWP_NOTIFY))
-		return;
-
-	rdmsrl(MSR_HWP_STATUS, value);
-	if (!(value & 0x01))
-		return;
-
-	cpudata = all_cpu_data[this_cpu];
-	schedule_delayed_work_on(this_cpu, &cpudata->hwp_notify_work, msecs_to_jiffies(10));
-}
-
-static void intel_pstate_enable_hwp_interrupt(struct cpudata *cpudata)
-{
-	/* Enable HWP notification interrupt for guaranteed performance change */
-	if (boot_cpu_has(X86_FEATURE_HWP_NOTIFY)) {
-		INIT_DELAYED_WORK(&cpudata->hwp_notify_work, intel_pstate_notify_work);
-		wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x01);
-	}
-}
-
 static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 {
 	/* First disable HWP notification interrupt as we don't process them */
@@ -1671,8 +1634,6 @@ static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 	wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1);
 	if (cpudata->epp_default == -EINVAL)
 		cpudata->epp_default = intel_pstate_get_epp(cpudata, 0);
-
-	intel_pstate_enable_hwp_interrupt(cpudata);
 }
 
 static int atom_get_min_pstate(void)

drivers/cpufreq/mediatek-cpufreq-hw.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2020 MediaTek Inc.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/cpufreq.h>
+#include <linux/energy_model.h>
+#include <linux/init.h>
+#include <linux/iopoll.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/slab.h>
+
+#define LUT_MAX_ENTRIES			32U
+#define LUT_FREQ			GENMASK(11, 0)
+#define LUT_ROW_SIZE			0x4
+#define CPUFREQ_HW_STATUS		BIT(0)
+#define SVS_HW_STATUS			BIT(1)
+#define POLL_USEC			1000
+#define TIMEOUT_USEC			300000
+
+enum {
+	REG_FREQ_LUT_TABLE,
+	REG_FREQ_ENABLE,
+	REG_FREQ_PERF_STATE,
+	REG_FREQ_HW_STATE,
+	REG_EM_POWER_TBL,
+	REG_FREQ_LATENCY,
+
+	REG_ARRAY_SIZE,
+};
+
+struct mtk_cpufreq_data {
+	struct cpufreq_frequency_table *table;
+	void __iomem *reg_bases[REG_ARRAY_SIZE];
+	int nr_opp;
+};
+
+static const u16 cpufreq_mtk_offsets[REG_ARRAY_SIZE] = {
+	[REG_FREQ_LUT_TABLE]	= 0x0,
+	[REG_FREQ_ENABLE]	= 0x84,
+	[REG_FREQ_PERF_STATE]	= 0x88,
+	[REG_FREQ_HW_STATE]	= 0x8c,
+	[REG_EM_POWER_TBL]	= 0x90,
+	[REG_FREQ_LATENCY]	= 0x110,
+};
+
+static int __maybe_unused
+mtk_cpufreq_get_cpu_power(unsigned long *mW,
+			  unsigned long *KHz, struct device *cpu_dev)
+{
+	struct mtk_cpufreq_data *data;
+	struct cpufreq_policy *policy;
+	int i;
+
+	policy = cpufreq_cpu_get_raw(cpu_dev->id);
+	if (!policy)
+		return 0;
+
+	data = policy->driver_data;
+
+	for (i = 0; i < data->nr_opp; i++) {
+		if (data->table[i].frequency < *KHz)
+			break;
+	}
+	i--;
+
+	*KHz = data->table[i].frequency;
+	*mW = readl_relaxed(data->reg_bases[REG_EM_POWER_TBL] +
+			    i * LUT_ROW_SIZE) / 1000;
+
+	return 0;
+}
+
+static int mtk_cpufreq_hw_target_index(struct cpufreq_policy *policy,
+				       unsigned int index)
+{
+	struct mtk_cpufreq_data *data = policy->driver_data;
+
+	writel_relaxed(index, data->reg_bases[REG_FREQ_PERF_STATE]);
+
+	return 0;
+}
+
+static unsigned int mtk_cpufreq_hw_get(unsigned int cpu)
+{
+	struct mtk_cpufreq_data *data;
+	struct cpufreq_policy *policy;
+	unsigned int index;
+
+	policy = cpufreq_cpu_get_raw(cpu);
+	if (!policy)
+		return 0;
+
+	data = policy->driver_data;
+
+	index = readl_relaxed(data->reg_bases[REG_FREQ_PERF_STATE]);
+	index = min(index, LUT_MAX_ENTRIES - 1);
+
+	return data->table[index].frequency;
+}
+
+static unsigned int mtk_cpufreq_hw_fast_switch(struct cpufreq_policy *policy,
+					       unsigned int target_freq)
+{
+	struct mtk_cpufreq_data *data = policy->driver_data;
+	unsigned int index;
+
+	index = cpufreq_table_find_index_dl(policy, target_freq);
+
+	writel_relaxed(index, data->reg_bases[REG_FREQ_PERF_STATE]);
+
+	return policy->freq_table[index].frequency;
+}
+
+static int mtk_cpu_create_freq_table(struct platform_device *pdev,
+				     struct mtk_cpufreq_data *data)
+{
+	struct device *dev = &pdev->dev;
+	u32 temp, i, freq, prev_freq = 0;
+	void __iomem *base_table;
+
+	data->table = devm_kcalloc(dev, LUT_MAX_ENTRIES + 1,
+				   sizeof(*data->table), GFP_KERNEL);
+	if (!data->table)
+		return -ENOMEM;
+
+	base_table = data->reg_bases[REG_FREQ_LUT_TABLE];
+
+	for (i = 0; i < LUT_MAX_ENTRIES; i++) {
+		temp = readl_relaxed(base_table + (i * LUT_ROW_SIZE));
+		freq = FIELD_GET(LUT_FREQ, temp) * 1000;
+
+		if (freq == prev_freq)
+			break;
+
+		data->table[i].frequency = freq;
+
+		dev_dbg(dev, "index=%d freq=%d\n", i, data->table[i].frequency);
+
+		prev_freq = freq;
+	}
+
+	data->table[i].frequency = CPUFREQ_TABLE_END;
+	data->nr_opp = i;
+
+	return 0;
+}
+
+static int mtk_cpu_resources_init(struct platform_device *pdev,
+				  struct cpufreq_policy *policy,
+				  const u16 *offsets)
+{
+	struct mtk_cpufreq_data *data;
+	struct device *dev = &pdev->dev;
+	void __iomem *base;
+	int ret, i;
+	int index;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	index = of_perf_domain_get_sharing_cpumask(policy->cpu, "performance-domains",
+						   "#performance-domain-cells",
+						   policy->cpus);
+	if (index < 0)
+		return index;
+
+	base = devm_platform_ioremap_resource(pdev, index);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	for (i = REG_FREQ_LUT_TABLE; i < REG_ARRAY_SIZE; i++)
+		data->reg_bases[i] = base + offsets[i];
+
+	ret = mtk_cpu_create_freq_table(pdev, data);
+	if (ret) {
+		dev_info(dev, "Domain-%d failed to create freq table\n", index);
+		return ret;
+	}
+
+	policy->freq_table = data->table;
+	policy->driver_data = data;
+
+	return 0;
+}
+
+static int mtk_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
+{
+	struct platform_device *pdev = cpufreq_get_driver_data();
+	int sig, pwr_hw = CPUFREQ_HW_STATUS | SVS_HW_STATUS;
+	struct mtk_cpufreq_data *data;
+	unsigned int latency;
+	int ret;
+
+	/* Get the bases of cpufreq for domains */
+	ret = mtk_cpu_resources_init(pdev, policy, platform_get_drvdata(pdev));
+	if (ret) {
+		dev_info(&pdev->dev, "CPUFreq resource init failed\n");
+		return ret;
+	}
+
+	data = policy->driver_data;
+
+	latency = readl_relaxed(data->reg_bases[REG_FREQ_LATENCY]) * 1000;
+	if (!latency)
+		latency = CPUFREQ_ETERNAL;
+
+	policy->cpuinfo.transition_latency = latency;
+	policy->fast_switch_possible = true;
+
+	/* HW should be in enabled state to proceed now */
+	writel_relaxed(0x1, data->reg_bases[REG_FREQ_ENABLE]);
+	if (readl_poll_timeout(data->reg_bases[REG_FREQ_HW_STATE], sig,
+			       (sig & pwr_hw) == pwr_hw, POLL_USEC,
+			       TIMEOUT_USEC)) {
+		if (!(sig & CPUFREQ_HW_STATUS)) {
+			pr_info("cpufreq hardware of CPU%d is not enabled\n",
+				policy->cpu);
+			return -ENODEV;
+		}
+
+		pr_info("SVS of CPU%d is not enabled\n", policy->cpu);
+	}
+
+	return 0;
+}
+
+static int mtk_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy)
+{
+	struct mtk_cpufreq_data *data = policy->driver_data;
+
+	/* HW should be in paused state now */
+	writel_relaxed(0x0, data->reg_bases[REG_FREQ_ENABLE]);
+
+	return 0;
+}
+
+static void mtk_cpufreq_register_em(struct cpufreq_policy *policy)
+{
+	struct em_data_callback em_cb = EM_DATA_CB(mtk_cpufreq_get_cpu_power);
+	struct mtk_cpufreq_data *data = policy->driver_data;
+
+	em_dev_register_perf_domain(get_cpu_device(policy->cpu), data->nr_opp,
+				    &em_cb, policy->cpus, true);
+}
+
+static struct cpufreq_driver cpufreq_mtk_hw_driver = {
+	.flags		= CPUFREQ_NEED_INITIAL_FREQ_CHECK |
+			  CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
+			  CPUFREQ_IS_COOLING_DEV,
+	.verify		= cpufreq_generic_frequency_table_verify,
+	.target_index	= mtk_cpufreq_hw_target_index,
+	.get		= mtk_cpufreq_hw_get,
+	.init		= mtk_cpufreq_hw_cpu_init,
+	.exit		= mtk_cpufreq_hw_cpu_exit,
+	.register_em	= mtk_cpufreq_register_em,
+	.fast_switch	= mtk_cpufreq_hw_fast_switch,
+	.name		= "mtk-cpufreq-hw",
+	.attr		= cpufreq_generic_attr,
+};
+
+static int mtk_cpufreq_hw_driver_probe(struct platform_device *pdev)
+{
+	const void *data;
+	int ret;
+
+	data = of_device_get_match_data(&pdev->dev);
+	if (!data)
+		return -EINVAL;
+
+	platform_set_drvdata(pdev, (void *) data);
+	cpufreq_mtk_hw_driver.driver_data = pdev;
+
+	ret = cpufreq_register_driver(&cpufreq_mtk_hw_driver);
+	if (ret)
+		dev_err(&pdev->dev, "CPUFreq HW driver failed to register\n");
+
+	return ret;
+}
+
+static int mtk_cpufreq_hw_driver_remove(struct platform_device *pdev)
+{
+	return cpufreq_unregister_driver(&cpufreq_mtk_hw_driver);
+}
+
+static const struct of_device_id mtk_cpufreq_hw_match[] = {
+	{ .compatible = "mediatek,cpufreq-hw", .data = &cpufreq_mtk_offsets },
+	{}
+};
+
+static struct platform_driver mtk_cpufreq_hw_driver = {
+	.probe = mtk_cpufreq_hw_driver_probe,
+	.remove = mtk_cpufreq_hw_driver_remove,
+	.driver = {
+		.name = "mtk-cpufreq-hw",
+		.of_match_table = mtk_cpufreq_hw_match,
+	},
+};
+module_platform_driver(mtk_cpufreq_hw_driver);
+
+MODULE_AUTHOR("Hector Yuan <hector.yuan@mediatek.com>");
+MODULE_DESCRIPTION("Mediatek cpufreq-hw driver");
+MODULE_LICENSE("GPL v2");

drivers/cpufreq/mediatek-cpufreq.c

@@ -448,8 +448,6 @@ static int mtk_cpufreq_init(struct cpufreq_policy *policy)
 	policy->driver_data = info;
 	policy->clk = info->cpu_clk;
 
-	dev_pm_opp_of_register_em(info->cpu_dev, policy->cpus);
-
 	return 0;
 }
 
@@ -471,6 +469,7 @@ static struct cpufreq_driver mtk_cpufreq_driver = {
 	.get = cpufreq_generic_get,
 	.init = mtk_cpufreq_init,
 	.exit = mtk_cpufreq_exit,
+	.register_em = cpufreq_register_em_with_opp,
 	.name = "mtk-cpufreq",
 	.attr = cpufreq_generic_attr,
 };

drivers/cpufreq/omap-cpufreq.c

@@ -131,7 +131,6 @@ static int omap_cpu_init(struct cpufreq_policy *policy)
 
 	/* FIXME: what's the actual transition time? */
 	cpufreq_generic_init(policy, freq_table, 300 * 1000);
-	dev_pm_opp_of_register_em(mpu_dev, policy->cpus);
 
 	return 0;
 }
@@ -150,6 +149,7 @@ static struct cpufreq_driver omap_driver = {
 	.get		= cpufreq_generic_get,
 	.init		= omap_cpu_init,
 	.exit		= omap_cpu_exit,
+	.register_em	= cpufreq_register_em_with_opp,
 	.name		= "omap",
 	.attr		= cpufreq_generic_attr,
 };

drivers/cpufreq/qcom-cpufreq-hw.c

@@ -7,12 +7,14 @@
 #include <linux/cpufreq.h>
 #include <linux/init.h>
 #include <linux/interconnect.h>
+#include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
 #include <linux/pm_opp.h>
 #include <linux/slab.h>
+#include <linux/spinlock.h>
 
 #define LUT_MAX_ENTRIES			40U
 #define LUT_SRC				GENMASK(31, 30)
@@ -22,10 +24,13 @@
 #define CLK_HW_DIV			2
 #define LUT_TURBO_IND			1
 
+#define HZ_PER_KHZ			1000
+
 struct qcom_cpufreq_soc_data {
 	u32 reg_enable;
 	u32 reg_freq_lut;
 	u32 reg_volt_lut;
+	u32 reg_current_vote;
 	u32 reg_perf_state;
 	u8 lut_row_size;
 };
@@ -34,6 +39,16 @@ struct qcom_cpufreq_data {
 	void __iomem *base;
 	struct resource *res;
 	const struct qcom_cpufreq_soc_data *soc_data;
+
+	/*
+	 * Mutex to synchronize between de-init sequence and re-starting LMh
+	 * polling/interrupts
+	 */
+	struct mutex throttle_lock;
+	int throttle_irq;
+	bool cancel_throttle;
+	struct delayed_work throttle_work;
+	struct cpufreq_policy *policy;
 };
 
 static unsigned long cpu_hw_rate, xo_rate;
@@ -251,10 +266,92 @@ static void qcom_get_related_cpus(int index, struct cpumask *m)
 	}
 }
 
+static unsigned int qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data)
+{
+	unsigned int val = readl_relaxed(data->base + data->soc_data->reg_current_vote);
+
+	return (val & 0x3FF) * 19200;
+}
+
+static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data)
+{
+	unsigned long max_capacity, capacity, freq_hz, throttled_freq;
+	struct cpufreq_policy *policy = data->policy;
+	int cpu = cpumask_first(policy->cpus);
+	struct device *dev = get_cpu_device(cpu);
+	struct dev_pm_opp *opp;
+	unsigned int freq;
+
+	/*
+	 * Get the h/w throttled frequency, normalize it using the
+	 * registered opp table and use it to calculate thermal pressure.
+	 */
+	freq = qcom_lmh_get_throttle_freq(data);
+	freq_hz = freq * HZ_PER_KHZ;
+
+	opp = dev_pm_opp_find_freq_floor(dev, &freq_hz);
+	if (IS_ERR(opp) && PTR_ERR(opp) == -ERANGE)
+		dev_pm_opp_find_freq_ceil(dev, &freq_hz);
+
+	throttled_freq = freq_hz / HZ_PER_KHZ;
+
+	/* Update thermal pressure */
+
+	max_capacity = arch_scale_cpu_capacity(cpu);
+	capacity = mult_frac(max_capacity, throttled_freq, policy->cpuinfo.max_freq);
+
+	/* Don't pass boost capacity to scheduler */
+	if (capacity > max_capacity)
+		capacity = max_capacity;
+
+	arch_set_thermal_pressure(policy->cpus, max_capacity - capacity);
+
+	/*
+	 * In the unlikely case policy is unregistered do not enable
+	 * polling or h/w interrupt
+	 */
+	mutex_lock(&data->throttle_lock);
+	if (data->cancel_throttle)
+		goto out;
+
+	/*
+	 * If h/w throttled frequency is higher than what cpufreq has requested
+	 * for, then stop polling and switch back to interrupt mechanism.
+	 */
+	if (throttled_freq >= qcom_cpufreq_hw_get(cpu))
+		enable_irq(data->throttle_irq);
+	else
+		mod_delayed_work(system_highpri_wq, &data->throttle_work,
+				 msecs_to_jiffies(10));
+
+out:
+	mutex_unlock(&data->throttle_lock);
+}
+
+static void qcom_lmh_dcvs_poll(struct work_struct *work)
+{
+	struct qcom_cpufreq_data *data;
+
+	data = container_of(work, struct qcom_cpufreq_data, throttle_work.work);
+	qcom_lmh_dcvs_notify(data);
+}
+
+static irqreturn_t qcom_lmh_dcvs_handle_irq(int irq, void *data)
+{
+	struct qcom_cpufreq_data *c_data = data;
+
+	/* Disable interrupt and enable polling */
+	disable_irq_nosync(c_data->throttle_irq);
+	qcom_lmh_dcvs_notify(c_data);
+
+	return 0;
+}
+
 static const struct qcom_cpufreq_soc_data qcom_soc_data = {
 	.reg_enable = 0x0,
 	.reg_freq_lut = 0x110,
 	.reg_volt_lut = 0x114,
+	.reg_current_vote = 0x704,
 	.reg_perf_state = 0x920,
 	.lut_row_size = 32,
 };
@@ -274,6 +371,51 @@ static const struct of_device_id qcom_cpufreq_hw_match[] = {
 };
 MODULE_DEVICE_TABLE(of, qcom_cpufreq_hw_match);
 
+static int qcom_cpufreq_hw_lmh_init(struct cpufreq_policy *policy, int index)
+{
+	struct qcom_cpufreq_data *data = policy->driver_data;
+	struct platform_device *pdev = cpufreq_get_driver_data();
+	char irq_name[15];
+	int ret;
+
+	/*
+	 * Look for LMh interrupt. If no interrupt line is specified /
+	 * if there is an error, allow cpufreq to be enabled as usual.
+	 */
+	data->throttle_irq = platform_get_irq(pdev, index);
+	if (data->throttle_irq <= 0)
+		return data->throttle_irq == -EPROBE_DEFER ? -EPROBE_DEFER : 0;
+
+	data->cancel_throttle = false;
+	data->policy = policy;
+
+	mutex_init(&data->throttle_lock);
+	INIT_DEFERRABLE_WORK(&data->throttle_work, qcom_lmh_dcvs_poll);
+
+	snprintf(irq_name, sizeof(irq_name), "dcvsh-irq-%u", policy->cpu);
+	ret = request_threaded_irq(data->throttle_irq, NULL, qcom_lmh_dcvs_handle_irq,
+				   IRQF_ONESHOT, irq_name, data);
+	if (ret) {
+		dev_err(&pdev->dev, "Error registering %s: %d\n", irq_name, ret);
+		return 0;
+	}
+
+	return 0;
+}
+
+static void qcom_cpufreq_hw_lmh_exit(struct qcom_cpufreq_data *data)
+{
+	if (data->throttle_irq <= 0)
+		return;
+
+	mutex_lock(&data->throttle_lock);
+	data->cancel_throttle = true;
+	mutex_unlock(&data->throttle_lock);
+
+	cancel_delayed_work_sync(&data->throttle_work);
+	free_irq(data->throttle_irq, data);
+}
+
 static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 {
 	struct platform_device *pdev = cpufreq_get_driver_data();
@@ -348,6 +490,7 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 	}
 
 	policy->driver_data = data;
+	policy->dvfs_possible_from_any_cpu = true;
 
 	ret = qcom_cpufreq_hw_read_lut(cpu_dev, policy);
 	if (ret) {
@@ -362,14 +505,16 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 		goto error;
 	}
 
-	dev_pm_opp_of_register_em(cpu_dev, policy->cpus);
-
 	if (policy_has_boost_freq(policy)) {
 		ret = cpufreq_enable_boost_support();
 		if (ret)
 			dev_warn(cpu_dev, "failed to enable boost: %d\n", ret);
 	}
 
+	ret = qcom_cpufreq_hw_lmh_init(policy, index);
+	if (ret)
+		goto error;
+
 	return 0;
 error:
 	kfree(data);
@@ -389,6 +534,7 @@ static int qcom_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy)
 
 	dev_pm_opp_remove_all_dynamic(cpu_dev);
 	dev_pm_opp_of_cpumask_remove_table(policy->related_cpus);
+	qcom_cpufreq_hw_lmh_exit(data);
 	kfree(policy->freq_table);
 	kfree(data);
 	iounmap(base);
@@ -412,6 +558,7 @@ static struct cpufreq_driver cpufreq_qcom_hw_driver = {
 	.get		= qcom_cpufreq_hw_get,
 	.init		= qcom_cpufreq_hw_cpu_init,
 	.exit		= qcom_cpufreq_hw_cpu_exit,
+	.register_em	= cpufreq_register_em_with_opp,
 	.fast_switch    = qcom_cpufreq_hw_fast_switch,
 	.name		= "qcom-cpufreq-hw",
 	.attr		= qcom_cpufreq_hw_attr,

drivers/cpufreq/scmi-cpufreq.c

@@ -22,7 +22,9 @@
 
 struct scmi_data {
 	int domain_id;
+	int nr_opp;
 	struct device *cpu_dev;
+	cpumask_var_t opp_shared_cpus;
 };
 
 static struct scmi_protocol_handle *ph;
@@ -123,9 +125,6 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 	struct device *cpu_dev;
 	struct scmi_data *priv;
 	struct cpufreq_frequency_table *freq_table;
-	struct em_data_callback em_cb = EM_DATA_CB(scmi_get_cpu_power);
-	cpumask_var_t opp_shared_cpus;
-	bool power_scale_mw;
 
 	cpu_dev = get_cpu_device(policy->cpu);
 	if (!cpu_dev) {
@@ -133,9 +132,15 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 		return -ENODEV;
 	}
 
-	if (!zalloc_cpumask_var(&opp_shared_cpus, GFP_KERNEL))
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
 		return -ENOMEM;
 
+	if (!zalloc_cpumask_var(&priv->opp_shared_cpus, GFP_KERNEL)) {
+		ret = -ENOMEM;
+		goto out_free_priv;
+	}
+
 	/* Obtain CPUs that share SCMI performance controls */
 	ret = scmi_get_sharing_cpus(cpu_dev, policy->cpus);
 	if (ret) {
@@ -148,14 +153,14 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 	 * The OPP 'sharing cpus' info may come from DT through an empty opp
 	 * table and opp-shared.
 	 */
-	ret = dev_pm_opp_of_get_sharing_cpus(cpu_dev, opp_shared_cpus);
-	if (ret || !cpumask_weight(opp_shared_cpus)) {
+	ret = dev_pm_opp_of_get_sharing_cpus(cpu_dev, priv->opp_shared_cpus);
+	if (ret || !cpumask_weight(priv->opp_shared_cpus)) {
 		/*
 		 * Either opp-table is not set or no opp-shared was found.
 		 * Use the CPU mask from SCMI to designate CPUs sharing an OPP
 		 * table.
 		 */
-		cpumask_copy(opp_shared_cpus, policy->cpus);
+		cpumask_copy(priv->opp_shared_cpus, policy->cpus);
 	}
 
 	 /*
@@ -180,7 +185,7 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 			goto out_free_opp;
 		}
 
-		ret = dev_pm_opp_set_sharing_cpus(cpu_dev, opp_shared_cpus);
+		ret = dev_pm_opp_set_sharing_cpus(cpu_dev, priv->opp_shared_cpus);
 		if (ret) {
 			dev_err(cpu_dev, "%s: failed to mark OPPs as shared: %d\n",
 				__func__, ret);
@@ -188,21 +193,13 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 			goto out_free_opp;
 		}
 
-		power_scale_mw = perf_ops->power_scale_mw_get(ph);
-		em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb,
-					    opp_shared_cpus, power_scale_mw);
-	}
-
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv) {
-		ret = -ENOMEM;
-		goto out_free_opp;
+		priv->nr_opp = nr_opp;
 	}
 
 	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table);
 	if (ret) {
 		dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret);
-		goto out_free_priv;
+		goto out_free_opp;
 	}
 
 	priv->cpu_dev = cpu_dev;
@@ -223,17 +220,16 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 	policy->fast_switch_possible =
 		perf_ops->fast_switch_possible(ph, cpu_dev);
 
-	free_cpumask_var(opp_shared_cpus);
 	return 0;
 
-out_free_priv:
-	kfree(priv);
-
 out_free_opp:
 	dev_pm_opp_remove_all_dynamic(cpu_dev);
 
 out_free_cpumask:
-	free_cpumask_var(opp_shared_cpus);
+	free_cpumask_var(priv->opp_shared_cpus);
+
+out_free_priv:
+	kfree(priv);
 
 	return ret;
 }
@@ -244,11 +240,33 @@ static int scmi_cpufreq_exit(struct cpufreq_policy *policy)
 
 	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
 	dev_pm_opp_remove_all_dynamic(priv->cpu_dev);
+	free_cpumask_var(priv->opp_shared_cpus);
 	kfree(priv);
 
 	return 0;
 }
 
+static void scmi_cpufreq_register_em(struct cpufreq_policy *policy)
+{
+	struct em_data_callback em_cb = EM_DATA_CB(scmi_get_cpu_power);
+	bool power_scale_mw = perf_ops->power_scale_mw_get(ph);
+	struct scmi_data *priv = policy->driver_data;
+
+	/*
+	 * This callback will be called for each policy, but we don't need to
+	 * register with EM every time. Despite not being part of the same
+	 * policy, some CPUs may still share their perf-domains, and a CPU from
+	 * another policy may already have registered with EM on behalf of CPUs
+	 * of this policy.
+	 */
+	if (!priv->nr_opp)
+		return;
+
+	em_dev_register_perf_domain(get_cpu_device(policy->cpu), priv->nr_opp,
+				    &em_cb, priv->opp_shared_cpus,
+				    power_scale_mw);
+}
+
 static struct cpufreq_driver scmi_cpufreq_driver = {
 	.name	= "scmi",
 	.flags	= CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
@@ -261,6 +279,7 @@ static struct cpufreq_driver scmi_cpufreq_driver = {
 	.get	= scmi_cpufreq_get_rate,
 	.init	= scmi_cpufreq_init,
 	.exit	= scmi_cpufreq_exit,
+	.register_em	= scmi_cpufreq_register_em,
 };
 
 static int scmi_cpufreq_probe(struct scmi_device *sdev)

drivers/cpufreq/scpi-cpufreq.c

@@ -163,8 +163,6 @@ static int scpi_cpufreq_init(struct cpufreq_policy *policy)
 
 	policy->fast_switch_possible = false;
 
-	dev_pm_opp_of_register_em(cpu_dev, policy->cpus);
-
 	return 0;
 
 out_free_cpufreq_table:
@@ -200,6 +198,7 @@ static struct cpufreq_driver scpi_cpufreq_driver = {
 	.init	= scpi_cpufreq_init,
 	.exit	= scpi_cpufreq_exit,
 	.target_index	= scpi_cpufreq_set_target,
+	.register_em	= cpufreq_register_em_with_opp,
 };
 
 static int scpi_cpufreq_probe(struct platform_device *pdev)

drivers/cpufreq/sh-cpufreq.c

@@ -145,16 +145,6 @@ static int sh_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 	return 0;
 }
 
-static void sh_cpufreq_cpu_ready(struct cpufreq_policy *policy)
-{
-	struct device *dev = get_cpu_device(policy->cpu);
-
-	dev_info(dev, "CPU Frequencies - Minimum %u.%03u MHz, "
-	       "Maximum %u.%03u MHz.\n",
-	       policy->min / 1000, policy->min % 1000,
-	       policy->max / 1000, policy->max % 1000);
-}
-
 static struct cpufreq_driver sh_cpufreq_driver = {
 	.name		= "sh",
 	.flags		= CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING,
@@ -163,7 +153,6 @@ static struct cpufreq_driver sh_cpufreq_driver = {
 	.verify		= sh_cpufreq_verify,
 	.init		= sh_cpufreq_cpu_init,
 	.exit		= sh_cpufreq_cpu_exit,
-	.ready		= sh_cpufreq_cpu_ready,
 	.attr		= cpufreq_generic_attr,
 };
 

drivers/cpufreq/vexpress-spc-cpufreq.c

@@ -15,7 +15,6 @@
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/cpumask.h>
-#include <linux/cpu_cooling.h>
 #include <linux/device.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
@@ -47,7 +46,6 @@ static bool bL_switching_enabled;
 #define ACTUAL_FREQ(cluster, freq)  ((cluster == A7_CLUSTER) ? freq << 1 : freq)
 #define VIRT_FREQ(cluster, freq)    ((cluster == A7_CLUSTER) ? freq >> 1 : freq)
 
-static struct thermal_cooling_device *cdev[MAX_CLUSTERS];
 static struct clk *clk[MAX_CLUSTERS];
 static struct cpufreq_frequency_table *freq_table[MAX_CLUSTERS + 1];
 static atomic_t cluster_usage[MAX_CLUSTERS + 1];
@@ -442,8 +440,6 @@ static int ve_spc_cpufreq_init(struct cpufreq_policy *policy)
 	policy->freq_table = freq_table[cur_cluster];
 	policy->cpuinfo.transition_latency = 1000000; /* 1 ms */
 
-	dev_pm_opp_of_register_em(cpu_dev, policy->cpus);
-
 	if (is_bL_switching_enabled())
 		per_cpu(cpu_last_req_freq, policy->cpu) =
 						clk_get_cpu_rate(policy->cpu);
@@ -457,11 +453,6 @@ static int ve_spc_cpufreq_exit(struct cpufreq_policy *policy)
 	struct device *cpu_dev;
 	int cur_cluster = cpu_to_cluster(policy->cpu);
 
-	if (cur_cluster < MAX_CLUSTERS) {
-		cpufreq_cooling_unregister(cdev[cur_cluster]);
-		cdev[cur_cluster] = NULL;
-	}
-
 	cpu_dev = get_cpu_device(policy->cpu);
 	if (!cpu_dev) {
 		pr_err("%s: failed to get cpu%d device\n", __func__,
@@ -473,17 +464,6 @@ static int ve_spc_cpufreq_exit(struct cpufreq_policy *policy)
 	return 0;
 }
 
-static void ve_spc_cpufreq_ready(struct cpufreq_policy *policy)
-{
-	int cur_cluster = cpu_to_cluster(policy->cpu);
-
-	/* Do not register a cpu_cooling device if we are in IKS mode */
-	if (cur_cluster >= MAX_CLUSTERS)
-		return;
-
-	cdev[cur_cluster] = of_cpufreq_cooling_register(policy);
-}
-
 static struct cpufreq_driver ve_spc_cpufreq_driver = {
 	.name			= "vexpress-spc",
 	.flags			= CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
@@ -493,7 +473,7 @@ static struct cpufreq_driver ve_spc_cpufreq_driver = {
 	.get			= ve_spc_cpufreq_get_rate,
 	.init			= ve_spc_cpufreq_init,
 	.exit			= ve_spc_cpufreq_exit,
-	.ready			= ve_spc_cpufreq_ready,
+	.register_em		= cpufreq_register_em_with_opp,
 	.attr			= cpufreq_generic_attr,
 };
 
@@ -553,6 +533,9 @@ static int ve_spc_cpufreq_probe(struct platform_device *pdev)
 	for (i = 0; i < MAX_CLUSTERS; i++)
 		mutex_init(&cluster_lock[i]);
 
+	if (!is_bL_switching_enabled())
+		ve_spc_cpufreq_driver.flags |= CPUFREQ_IS_COOLING_DEV;
+
 	ret = cpufreq_register_driver(&ve_spc_cpufreq_driver);
 	if (ret) {
 		pr_info("%s: Failed registering platform driver: %s, err: %d\n",

include/linux/cpufreq.h

@@ -9,10 +9,14 @@
 #define _LINUX_CPUFREQ_H
 
 #include <linux/clk.h>
+#include <linux/cpu.h>
 #include <linux/cpumask.h>
 #include <linux/completion.h>
 #include <linux/kobject.h>
 #include <linux/notifier.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/pm_opp.h>
 #include <linux/pm_qos.h>
 #include <linux/spinlock.h>
 #include <linux/sysfs.h>
@@ -365,14 +369,17 @@ struct cpufreq_driver {
 	int		(*suspend)(struct cpufreq_policy *policy);
 	int		(*resume)(struct cpufreq_policy *policy);
 
-	/* Will be called after the driver is fully initialized */
-	void		(*ready)(struct cpufreq_policy *policy);
-
 	struct freq_attr **attr;
 
 	/* platform specific boost support code */
 	bool		boost_enabled;
 	int		(*set_boost)(struct cpufreq_policy *policy, int state);
+
+	/*
+	 * Set by drivers that want to register with the energy model after the
+	 * policy is properly initialized, but before the governor is started.
+	 */
+	void		(*register_em)(struct cpufreq_policy *policy);
 };
 
 /* flags */
@@ -995,6 +1002,55 @@ static inline int cpufreq_table_count_valid_entries(const struct cpufreq_policy
 
 	return count;
 }
+
+static inline int parse_perf_domain(int cpu, const char *list_name,
+				    const char *cell_name)
+{
+	struct device_node *cpu_np;
+	struct of_phandle_args args;
+	int ret;
+
+	cpu_np = of_cpu_device_node_get(cpu);
+	if (!cpu_np)
+		return -ENODEV;
+
+	ret = of_parse_phandle_with_args(cpu_np, list_name, cell_name, 0,
+					 &args);
+	if (ret < 0)
+		return ret;
+
+	of_node_put(cpu_np);
+
+	return args.args[0];
+}
+
+static inline int of_perf_domain_get_sharing_cpumask(int pcpu, const char *list_name,
+						     const char *cell_name, struct cpumask *cpumask)
+{
+	int target_idx;
+	int cpu, ret;
+
+	ret = parse_perf_domain(pcpu, list_name, cell_name);
+	if (ret < 0)
+		return ret;
+
+	target_idx = ret;
+	cpumask_set_cpu(pcpu, cpumask);
+
+	for_each_possible_cpu(cpu) {
+		if (cpu == pcpu)
+			continue;
+
+		ret = parse_perf_domain(pcpu, list_name, cell_name);
+		if (ret < 0)
+			continue;
+
+		if (target_idx == ret)
+			cpumask_set_cpu(cpu, cpumask);
+	}
+
+	return target_idx;
+}
 #else
 static inline int cpufreq_boost_trigger_state(int state)
 {
@@ -1014,6 +1070,12 @@ static inline bool policy_has_boost_freq(struct cpufreq_policy *policy)
 {
 	return false;
 }
+
+static inline int of_perf_domain_get_sharing_cpumask(int pcpu, const char *list_name,
+						     const char *cell_name, struct cpumask *cpumask)
+{
+	return -EOPNOTSUPP;
+}
 #endif
 
 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
@@ -1035,7 +1097,6 @@ void arch_set_freq_scale(const struct cpumask *cpus,
 {
 }
 #endif
-
 /* the following are really really optional */
 extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs;
 extern struct freq_attr cpufreq_freq_attr_scaling_boost_freqs;
@@ -1046,4 +1107,10 @@ unsigned int cpufreq_generic_get(unsigned int cpu);
 void cpufreq_generic_init(struct cpufreq_policy *policy,
 		struct cpufreq_frequency_table *table,
 		unsigned int transition_latency);
+
+static inline void cpufreq_register_em_with_opp(struct cpufreq_policy *policy)
+{
+	dev_pm_opp_of_register_em(get_cpu_device(policy->cpu),
+				  policy->related_cpus);
+}
 #endif /* _LINUX_CPUFREQ_H */