Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/evalenti/linux-soc-thermal into thermal-soc

Documentation/devicetree/bindings/thermal/hisilicon-thermal.txt

@@ -0,0 +1,23 @@
+* Temperature Sensor on hisilicon SoCs
+
+** Required properties :
+
+- compatible: "hisilicon,tsensor".
+- reg: physical base address of thermal sensor and length of memory mapped
+  region.
+- interrupt: The interrupt number to the cpu. Defines the interrupt used
+  by /SOCTHERM/tsensor.
+- clock-names: Input clock name, should be 'thermal_clk'.
+- clocks: phandles for clock specified in "clock-names" property.
+- #thermal-sensor-cells: Should be 1. See ./thermal.txt for a description.
+
+Example :
+
+	tsensor: tsensor@0,f7030700 {
+		compatible = "hisilicon,tsensor";
+		reg = <0x0 0xf7030700 0x0 0x1000>;
+		interrupts = <0 7 0x4>;
+		clocks = <&sys_ctrl HI6220_TSENSOR_CLK>;
+		clock-names = "thermal_clk";
+		#thermal-sensor-cells = <1>;
+	}

Documentation/devicetree/bindings/thermal/qcom-spmi-temp-alarm.txt

@@ -0,0 +1,57 @@
+Qualcomm QPNP PMIC Temperature Alarm
+
+QPNP temperature alarm peripherals are found inside of Qualcomm PMIC chips
+that utilize the Qualcomm SPMI implementation. These peripherals provide an
+interrupt signal and status register to identify high PMIC die temperature.
+
+Required properties:
+- compatible:      Should contain "qcom,spmi-temp-alarm".
+- reg:             Specifies the SPMI address and length of the controller's
+                   registers.
+- interrupts:      PMIC temperature alarm interrupt.
+- #thermal-sensor-cells: Should be 0. See thermal.txt for a description.
+
+Optional properties:
+- io-channels:     Should contain IIO channel specifier for the ADC channel,
+                   which report chip die temperature.
+- io-channel-names: Should contain "thermal".
+
+Example:
+
+	pm8941_temp: thermal-alarm@2400 {
+		compatible = "qcom,spmi-temp-alarm";
+		reg = <0x2400 0x100>;
+		interrupts = <0 0x24 0 IRQ_TYPE_EDGE_RISING>;
+		#thermal-sensor-cells = <0>;
+
+		io-channels = <&pm8941_vadc VADC_DIE_TEMP>;
+		io-channel-names = "thermal";
+	};
+
+	thermal-zones {
+		pm8941 {
+			polling-delay-passive = <250>;
+			polling-delay = <1000>;
+
+			thermal-sensors = <&pm8941_temp>;
+
+			trips {
+				passive {
+					temperature = <1050000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+				alert {
+					temperature = <125000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+				crit {
+					temperature = <145000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+		};
+	};
+

Documentation/devicetree/bindings/thermal/thermal.txt

@@ -167,6 +167,13 @@ Optional property:
 			by means of sensor ID. Additional coefficients are
 			interpreted as constant offset.
 
+- sustainable-power:	An estimate of the sustainable power (in mW) that the
+  Type: unsigned	thermal zone can dissipate at the desired
+  Size: one cell	control temperature.  For reference, the
+			sustainable power of a 4'' phone is typically
+			2000mW, while on a 10'' tablet is around
+			4500mW.
+
 Note: The delay properties are bound to the maximum dT/dt (temperature
 derivative over time) in two situations for a thermal zone:
 (i)  - when passive cooling is activated (polling-delay-passive); and
@@ -546,6 +553,8 @@ thermal-zones {
 		 */
 		coefficients =		<1200	-345	890>;
 
+		sustainable-power = <2500>;
+
 		trips {
 			/* Trips are based on resulting linear equation */
 			cpu_trip: cpu-trip {

Documentation/thermal/cpu-cooling-api.txt

@@ -36,8 +36,162 @@ the user. The registration APIs returns the cooling device pointer.
     np: pointer to the cooling device device tree node
     clip_cpus: cpumask of cpus where the frequency constraints will happen.
 
-1.1.3 void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
+1.1.3 struct thermal_cooling_device *cpufreq_power_cooling_register(
+    const struct cpumask *clip_cpus, u32 capacitance,
+    get_static_t plat_static_func)
+
+Similar to cpufreq_cooling_register, this function registers a cpufreq
+cooling device.  Using this function, the cooling device will
+implement the power extensions by using a simple cpu power model.  The
+cpus must have registered their OPPs using the OPP library.
+
+The additional parameters are needed for the power model (See 2. Power
+models).  "capacitance" is the dynamic power coefficient (See 2.1
+Dynamic power).  "plat_static_func" is a function to calculate the
+static power consumed by these cpus (See 2.2 Static power).
+
+1.1.4 struct thermal_cooling_device *of_cpufreq_power_cooling_register(
+    struct device_node *np, const struct cpumask *clip_cpus, u32 capacitance,
+    get_static_t plat_static_func)
+
+Similar to cpufreq_power_cooling_register, this function register a
+cpufreq cooling device with power extensions using the device tree
+information supplied by the np parameter.
+
+1.1.5 void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 
     This interface function unregisters the "thermal-cpufreq-%x" cooling device.
 
     cdev: Cooling device pointer which has to be unregistered.
+
+2. Power models
+
+The power API registration functions provide a simple power model for
+CPUs.  The current power is calculated as dynamic + (optionally)
+static power.  This power model requires that the operating-points of
+the CPUs are registered using the kernel's opp library and the
+`cpufreq_frequency_table` is assigned to the `struct device` of the
+cpu.  If you are using CONFIG_CPUFREQ_DT then the
+`cpufreq_frequency_table` should already be assigned to the cpu
+device.
+
+The `plat_static_func` parameter of `cpufreq_power_cooling_register()`
+and `of_cpufreq_power_cooling_register()` is optional.  If you don't
+provide it, only dynamic power will be considered.
+
+2.1 Dynamic power
+
+The dynamic power consumption of a processor depends on many factors.
+For a given processor implementation the primary factors are:
+
+- The time the processor spends running, consuming dynamic power, as
+  compared to the time in idle states where dynamic consumption is
+  negligible.  Herein we refer to this as 'utilisation'.
+- The voltage and frequency levels as a result of DVFS.  The DVFS
+  level is a dominant factor governing power consumption.
+- In running time the 'execution' behaviour (instruction types, memory
+  access patterns and so forth) causes, in most cases, a second order
+  variation.  In pathological cases this variation can be significant,
+  but typically it is of a much lesser impact than the factors above.
+
+A high level dynamic power consumption model may then be represented as:
+
+Pdyn = f(run) * Voltage^2 * Frequency * Utilisation
+
+f(run) here represents the described execution behaviour and its
+result has a units of Watts/Hz/Volt^2 (this often expressed in
+mW/MHz/uVolt^2)
+
+The detailed behaviour for f(run) could be modelled on-line.  However,
+in practice, such an on-line model has dependencies on a number of
+implementation specific processor support and characterisation
+factors.  Therefore, in initial implementation that contribution is
+represented as a constant coefficient.  This is a simplification
+consistent with the relative contribution to overall power variation.
+
+In this simplified representation our model becomes:
+
+Pdyn = Capacitance * Voltage^2 * Frequency * Utilisation
+
+Where `capacitance` is a constant that represents an indicative
+running time dynamic power coefficient in fundamental units of
+mW/MHz/uVolt^2.  Typical values for mobile CPUs might lie in range
+from 100 to 500.  For reference, the approximate values for the SoC in
+ARM's Juno Development Platform are 530 for the Cortex-A57 cluster and
+140 for the Cortex-A53 cluster.
+
+
+2.2 Static power
+
+Static leakage power consumption depends on a number of factors.  For a
+given circuit implementation the primary factors are:
+
+- Time the circuit spends in each 'power state'
+- Temperature
+- Operating voltage
+- Process grade
+
+The time the circuit spends in each 'power state' for a given
+evaluation period at first order means OFF or ON.  However,
+'retention' states can also be supported that reduce power during
+inactive periods without loss of context.
+
+Note: The visibility of state entries to the OS can vary, according to
+platform specifics, and this can then impact the accuracy of a model
+based on OS state information alone.  It might be possible in some
+cases to extract more accurate information from system resources.
+
+The temperature, operating voltage and process 'grade' (slow to fast)
+of the circuit are all significant factors in static leakage power
+consumption.  All of these have complex relationships to static power.
+
+Circuit implementation specific factors include the chosen silicon
+process as well as the type, number and size of transistors in both
+the logic gates and any RAM elements included.
+
+The static power consumption modelling must take into account the
+power managed regions that are implemented.  Taking the example of an
+ARM processor cluster, the modelling would take into account whether
+each CPU can be powered OFF separately or if only a single power
+region is implemented for the complete cluster.
+
+In one view, there are others, a static power consumption model can
+then start from a set of reference values for each power managed
+region (e.g. CPU, Cluster/L2) in each state (e.g. ON, OFF) at an
+arbitrary process grade, voltage and temperature point.  These values
+are then scaled for all of the following: the time in each state, the
+process grade, the current temperature and the operating voltage.
+However, since both implementation specific and complex relationships
+dominate the estimate, the appropriate interface to the model from the
+cpu cooling device is to provide a function callback that calculates
+the static power in this platform.  When registering the cpu cooling
+device pass a function pointer that follows the `get_static_t`
+prototype:
+
+    int plat_get_static(cpumask_t *cpumask, int interval,
+                        unsigned long voltage, u32 &power);
+
+`cpumask` is the cpumask of the cpus involved in the calculation.
+`voltage` is the voltage at which they are operating.  The function
+should calculate the average static power for the last `interval`
+milliseconds.  It returns 0 on success, -E* on error.  If it
+succeeds, it should store the static power in `power`.  Reading the
+temperature of the cpus described by `cpumask` is left for
+plat_get_static() to do as the platform knows best which thermal
+sensor is closest to the cpu.
+
+If `plat_static_func` is NULL, static power is considered to be
+negligible for this platform and only dynamic power is considered.
+
+The platform specific callback can then use any combination of tables
+and/or equations to permute the estimated value.  Process grade
+information is not passed to the model since access to such data, from
+on-chip measurement capability or manufacture time data, is platform
+specific.
+
+Note: the significance of static power for CPUs in comparison to
+dynamic power is highly dependent on implementation.  Given the
+potential complexity in implementation, the importance and accuracy of
+its inclusion when using cpu cooling devices should be assessed on a
+case by case basis.
+

Documentation/thermal/power_allocator.txt

@@ -0,0 +1,247 @@
+Power allocator governor tunables
+=================================
+
+Trip points
+-----------
+
+The governor requires the following two passive trip points:
+
+1.  "switch on" trip point: temperature above which the governor
+    control loop starts operating.  This is the first passive trip
+    point of the thermal zone.
+
+2.  "desired temperature" trip point: it should be higher than the
+    "switch on" trip point.  This the target temperature the governor
+    is controlling for.  This is the last passive trip point of the
+    thermal zone.
+
+PID Controller
+--------------
+
+The power allocator governor implements a
+Proportional-Integral-Derivative controller (PID controller) with
+temperature as the control input and power as the controlled output:
+
+    P_max = k_p * e + k_i * err_integral + k_d * diff_err + sustainable_power
+
+where
+    e = desired_temperature - current_temperature
+    err_integral is the sum of previous errors
+    diff_err = e - previous_error
+
+It is similar to the one depicted below:
+
+                                      k_d
+                                       |
+current_temp                           |
+     |                                 v
+     |                +----------+   +---+
+     |         +----->| diff_err |-->| X |------+
+     |         |      +----------+   +---+      |
+     |         |                                |      tdp        actor
+     |         |                      k_i       |       |  get_requested_power()
+     |         |                       |        |       |        |     |
+     |         |                       |        |       |        |     | ...
+     v         |                       v        v       v        v     v
+   +---+       |      +-------+      +---+    +---+   +---+   +----------+
+   | S |-------+----->| sum e |----->| X |--->| S |-->| S |-->|power     |
+   +---+       |      +-------+      +---+    +---+   +---+   |allocation|
+     ^         |                                ^             +----------+
+     |         |                                |                |     |
+     |         |        +---+                   |                |     |
+     |         +------->| X |-------------------+                v     v
+     |                  +---+                               granted performance
+desired_temperature       ^
+                          |
+                          |
+                      k_po/k_pu
+
+Sustainable power
+-----------------
+
+An estimate of the sustainable dissipatable power (in mW) should be
+provided while registering the thermal zone.  This estimates the
+sustained power that can be dissipated at the desired control
+temperature.  This is the maximum sustained power for allocation at
+the desired maximum temperature.  The actual sustained power can vary
+for a number of reasons.  The closed loop controller will take care of
+variations such as environmental conditions, and some factors related
+to the speed-grade of the silicon.  `sustainable_power` is therefore
+simply an estimate, and may be tuned to affect the aggressiveness of
+the thermal ramp. For reference, the sustainable power of a 4" phone
+is typically 2000mW, while on a 10" tablet is around 4500mW (may vary
+depending on screen size).
+
+If you are using device tree, do add it as a property of the
+thermal-zone.  For example:
+
+	thermal-zones {
+		soc_thermal {
+			polling-delay = <1000>;
+			polling-delay-passive = <100>;
+			sustainable-power = <2500>;
+			...
+
+Instead, if the thermal zone is registered from the platform code, pass a
+`thermal_zone_params` that has a `sustainable_power`.  If no
+`thermal_zone_params` were being passed, then something like below
+will suffice:
+
+	static const struct thermal_zone_params tz_params = {
+		.sustainable_power = 3500,
+	};
+
+and then pass `tz_params` as the 5th parameter to
+`thermal_zone_device_register()`
+
+k_po and k_pu
+-------------
+
+The implementation of the PID controller in the power allocator
+thermal governor allows the configuration of two proportional term
+constants: `k_po` and `k_pu`.  `k_po` is the proportional term
+constant during temperature overshoot periods (current temperature is
+above "desired temperature" trip point).  Conversely, `k_pu` is the
+proportional term constant during temperature undershoot periods
+(current temperature below "desired temperature" trip point).
+
+These controls are intended as the primary mechanism for configuring
+the permitted thermal "ramp" of the system.  For instance, a lower
+`k_pu` value will provide a slower ramp, at the cost of capping
+available capacity at a low temperature.  On the other hand, a high
+value of `k_pu` will result in the governor granting very high power
+whilst temperature is low, and may lead to temperature overshooting.
+
+The default value for `k_pu` is:
+
+    2 * sustainable_power / (desired_temperature - switch_on_temp)
+
+This means that at `switch_on_temp` the output of the controller's
+proportional term will be 2 * `sustainable_power`.  The default value
+for `k_po` is:
+
+    sustainable_power / (desired_temperature - switch_on_temp)
+
+Focusing on the proportional and feed forward values of the PID
+controller equation we have:
+
+    P_max = k_p * e + sustainable_power
+
+The proportional term is proportional to the difference between the
+desired temperature and the current one.  When the current temperature
+is the desired one, then the proportional component is zero and
+`P_max` = `sustainable_power`.  That is, the system should operate in
+thermal equilibrium under constant load.  `sustainable_power` is only
+an estimate, which is the reason for closed-loop control such as this.
+
+Expanding `k_pu` we get:
+    P_max = 2 * sustainable_power * (T_set - T) / (T_set - T_on) +
+        sustainable_power
+
+where
+    T_set is the desired temperature
+    T is the current temperature
+    T_on is the switch on temperature
+
+When the current temperature is the switch_on temperature, the above
+formula becomes:
+
+    P_max = 2 * sustainable_power * (T_set - T_on) / (T_set - T_on) +
+        sustainable_power = 2 * sustainable_power + sustainable_power =
+        3 * sustainable_power
+
+Therefore, the proportional term alone linearly decreases power from
+3 * `sustainable_power` to `sustainable_power` as the temperature
+rises from the switch on temperature to the desired temperature.
+
+k_i and integral_cutoff
+-----------------------
+
+`k_i` configures the PID loop's integral term constant.  This term
+allows the PID controller to compensate for long term drift and for
+the quantized nature of the output control: cooling devices can't set
+the exact power that the governor requests.  When the temperature
+error is below `integral_cutoff`, errors are accumulated in the
+integral term.  This term is then multiplied by `k_i` and the result
+added to the output of the controller.  Typically `k_i` is set low (1
+or 2) and `integral_cutoff` is 0.
+
+k_d
+---
+
+`k_d` configures the PID loop's derivative term constant.  It's
+recommended to leave it as the default: 0.
+
+Cooling device power API
+========================
+
+Cooling devices controlled by this governor must supply the additional
+"power" API in their `cooling_device_ops`.  It consists on three ops:
+
+1. int get_requested_power(struct thermal_cooling_device *cdev,
+	struct thermal_zone_device *tz, u32 *power);
+@cdev: The `struct thermal_cooling_device` pointer
+@tz: thermal zone in which we are currently operating
+@power: pointer in which to store the calculated power
+
+`get_requested_power()` calculates the power requested by the device
+in milliwatts and stores it in @power .  It should return 0 on
+success, -E* on failure.  This is currently used by the power
+allocator governor to calculate how much power to give to each cooling
+device.
+
+2. int state2power(struct thermal_cooling_device *cdev, struct
+        thermal_zone_device *tz, unsigned long state, u32 *power);
+@cdev: The `struct thermal_cooling_device` pointer
+@tz: thermal zone in which we are currently operating
+@state: A cooling device state
+@power: pointer in which to store the equivalent power
+
+Convert cooling device state @state into power consumption in
+milliwatts and store it in @power.  It should return 0 on success, -E*
+on failure.  This is currently used by thermal core to calculate the
+maximum power that an actor can consume.
+
+3. int power2state(struct thermal_cooling_device *cdev, u32 power,
+	unsigned long *state);
+@cdev: The `struct thermal_cooling_device` pointer
+@power: power in milliwatts
+@state: pointer in which to store the resulting state
+
+Calculate a cooling device state that would make the device consume at
+most @power mW and store it in @state.  It should return 0 on success,
+-E* on failure.  This is currently used by the thermal core to convert
+a given power set by the power allocator governor to a state that the
+cooling device can set.  It is a function because this conversion may
+depend on external factors that may change so this function should the
+best conversion given "current circumstances".
+
+Cooling device weights
+----------------------
+
+Weights are a mechanism to bias the allocation among cooling
+devices.  They express the relative power efficiency of different
+cooling devices.  Higher weight can be used to express higher power
+efficiency.  Weighting is relative such that if each cooling device
+has a weight of one they are considered equal.  This is particularly
+useful in heterogeneous systems where two cooling devices may perform
+the same kind of compute, but with different efficiency.  For example,
+a system with two different types of processors.
+
+If the thermal zone is registered using
+`thermal_zone_device_register()` (i.e., platform code), then weights
+are passed as part of the thermal zone's `thermal_bind_parameters`.
+If the platform is registered using device tree, then they are passed
+as the `contribution` property of each map in the `cooling-maps` node.
+
+Limitations of the power allocator governor
+===========================================
+
+The power allocator governor's PID controller works best if there is a
+periodic tick.  If you have a driver that calls
+`thermal_zone_device_update()` (or anything that ends up calling the
+governor's `throttle()` function) repetitively, the governor response
+won't be very good.  Note that this is not particular to this
+governor, step-wise will also misbehave if you call its throttle()
+faster than the normal thermal framework tick (due to interrupts for
+example) as it will overreact.

Documentation/thermal/sysfs-api.txt

@@ -95,7 +95,7 @@ temperature) and throttle appropriate devices.
 1.3 interface for binding a thermal zone device with a thermal cooling device
 1.3.1 int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz,
 	int trip, struct thermal_cooling_device *cdev,
-	unsigned long upper, unsigned long lower);
+	unsigned long upper, unsigned long lower, unsigned int weight);
 
     This interface function bind a thermal cooling device to the certain trip
     point of a thermal zone device.
@@ -110,6 +110,8 @@ temperature) and throttle appropriate devices.
     lower:the Minimum cooling state can be used for this trip point.
           THERMAL_NO_LIMIT means no lower limit,
 	  and the cooling device can be in cooling state 0.
+    weight: the influence of this cooling device in this thermal
+            zone.  See 1.4.1 below for more information.
 
 1.3.2 int thermal_zone_unbind_cooling_device(struct thermal_zone_device *tz,
 		int trip, struct thermal_cooling_device *cdev);
@@ -127,9 +129,15 @@ temperature) and throttle appropriate devices.
     This structure defines the following parameters that are used to bind
     a zone with a cooling device for a particular trip point.
     .cdev: The cooling device pointer
-    .weight: The 'influence' of a particular cooling device on this zone.
-             This is on a percentage scale. The sum of all these weights
-             (for a particular zone) cannot exceed 100.
+    .weight: The 'influence' of a particular cooling device on this
+             zone. This is relative to the rest of the cooling
+             devices. For example, if all cooling devices have a
+             weight of 1, then they all contribute the same. You can
+             use percentages if you want, but it's not mandatory. A
+             weight of 0 means that this cooling device doesn't
+             contribute to the cooling of this zone unless all cooling
+             devices have a weight of 0. If all weights are 0, then
+             they all contribute the same.
     .trip_mask:This is a bit mask that gives the binding relation between
                this thermal zone and cdev, for a particular trip point.
                If nth bit is set, then the cdev and thermal zone are bound
@@ -176,6 +184,14 @@ Thermal zone device sys I/F, created once it's registered:
     |---trip_point_[0-*]_type:	Trip point type
     |---trip_point_[0-*]_hyst:	Hysteresis value for this trip point
     |---emul_temp:		Emulated temperature set node
+    |---sustainable_power:      Sustainable dissipatable power
+    |---k_po:                   Proportional term during temperature overshoot
+    |---k_pu:                   Proportional term during temperature undershoot
+    |---k_i:                    PID's integral term in the power allocator gov
+    |---k_d:                    PID's derivative term in the power allocator
+    |---integral_cutoff:        Offset above which errors are accumulated
+    |---slope:                  Slope constant applied as linear extrapolation
+    |---offset:                 Offset constant applied as linear extrapolation
 
 Thermal cooling device sys I/F, created once it's registered:
 /sys/class/thermal/cooling_device[0-*]:
@@ -192,6 +208,8 @@ thermal_zone_bind_cooling_device/thermal_zone_unbind_cooling_device.
 /sys/class/thermal/thermal_zone[0-*]:
     |---cdev[0-*]:		[0-*]th cooling device in current thermal zone
     |---cdev[0-*]_trip_point:	Trip point that cdev[0-*] is associated with
+    |---cdev[0-*]_weight:       Influence of the cooling device in
+                                this thermal zone
 
 Besides the thermal zone device sysfs I/F and cooling device sysfs I/F,
 the generic thermal driver also creates a hwmon sysfs I/F for each _type_
@@ -265,6 +283,14 @@ cdev[0-*]_trip_point
 	point.
 	RO, Optional
 
+cdev[0-*]_weight
+        The influence of cdev[0-*] in this thermal zone. This value
+        is relative to the rest of cooling devices in the thermal
+        zone. For example, if a cooling device has a weight double
+        than that of other, it's twice as effective in cooling the
+        thermal zone.
+        RW, Optional
+
 passive
 	Attribute is only present for zones in which the passive cooling
 	policy is not supported by native thermal driver. Default is zero
@@ -289,6 +315,66 @@ emul_temp
 	  because userland can easily disable the thermal policy by simply
 	  flooding this sysfs node with low temperature values.
 
+sustainable_power
+	An estimate of the sustained power that can be dissipated by
+	the thermal zone. Used by the power allocator governor. For
+	more information see Documentation/thermal/power_allocator.txt
+	Unit: milliwatts
+	RW, Optional
+
+k_po
+	The proportional term of the power allocator governor's PID
+	controller during temperature overshoot. Temperature overshoot
+	is when the current temperature is above the "desired
+	temperature" trip point. For more information see
+	Documentation/thermal/power_allocator.txt
+	RW, Optional
+
+k_pu
+	The proportional term of the power allocator governor's PID
+	controller during temperature undershoot. Temperature undershoot
+	is when the current temperature is below the "desired
+	temperature" trip point. For more information see
+	Documentation/thermal/power_allocator.txt
+	RW, Optional
+
+k_i
+	The integral term of the power allocator governor's PID
+	controller. This term allows the PID controller to compensate
+	for long term drift. For more information see
+	Documentation/thermal/power_allocator.txt
+	RW, Optional
+
+k_d
+	The derivative term of the power allocator governor's PID
+	controller. For more information see
+	Documentation/thermal/power_allocator.txt
+	RW, Optional
+
+integral_cutoff
+	Temperature offset from the desired temperature trip point
+	above which the integral term of the power allocator
+	governor's PID controller starts accumulating errors. For
+	example, if integral_cutoff is 0, then the integral term only
+	accumulates error when temperature is above the desired
+	temperature trip point. For more information see
+	Documentation/thermal/power_allocator.txt
+	RW, Optional
+
+slope
+	The slope constant used in a linear extrapolation model
+	to determine a hotspot temperature based off the sensor's
+	raw readings. It is up to the device driver to determine
+	the usage of these values.
+	RW, Optional
+
+offset
+	The offset constant used in a linear extrapolation model
+	to determine a hotspot temperature based off the sensor's
+	raw readings. It is up to the device driver to determine
+	the usage of these values.
+	RW, Optional
+
 *****************************
 * Cooling device attributes *
 *****************************
@@ -318,7 +404,8 @@ passive, active. If an ACPI thermal zone supports critical, passive,
 active[0] and active[1] at the same time, it may register itself as a
 thermal_zone_device (thermal_zone1) with 4 trip points in all.
 It has one processor and one fan, which are both registered as
-thermal_cooling_device.
+thermal_cooling_device. Both are considered to have the same
+effectiveness in cooling the thermal zone.
 
 If the processor is listed in _PSL method, and the fan is listed in _AL0
 method, the sys I/F structure will be built like this:
@@ -340,8 +427,10 @@ method, the sys I/F structure will be built like this:
     |---trip_point_3_type:	active1
     |---cdev0:			--->/sys/class/thermal/cooling_device0
     |---cdev0_trip_point:	1	/* cdev0 can be used for passive */
+    |---cdev0_weight:           1024
     |---cdev1:			--->/sys/class/thermal/cooling_device3
     |---cdev1_trip_point:	2	/* cdev1 can be used for active[0]*/
+    |---cdev1_weight:           1024
 
 |cooling_device0:
     |---type:			Processor

drivers/acpi/thermal.c

@@ -800,7 +800,8 @@ static int acpi_thermal_cooling_device_cb(struct thermal_zone_device *thermal,
 				result =
 					thermal_zone_bind_cooling_device
 					(thermal, trip, cdev,
-					 THERMAL_NO_LIMIT, THERMAL_NO_LIMIT);
+					 THERMAL_NO_LIMIT, THERMAL_NO_LIMIT,
+					 THERMAL_WEIGHT_DEFAULT);
 			else
 				result =
 					thermal_zone_unbind_cooling_device
@@ -824,7 +825,8 @@ static int acpi_thermal_cooling_device_cb(struct thermal_zone_device *thermal,
 			if (bind)
 				result = thermal_zone_bind_cooling_device
 					(thermal, trip, cdev,
-					 THERMAL_NO_LIMIT, THERMAL_NO_LIMIT);
+					 THERMAL_NO_LIMIT, THERMAL_NO_LIMIT,
+					 THERMAL_WEIGHT_DEFAULT);
 			else
 				result = thermal_zone_unbind_cooling_device
 					(thermal, trip, cdev);
@@ -841,7 +843,8 @@ static int acpi_thermal_cooling_device_cb(struct thermal_zone_device *thermal,
 				result = thermal_zone_bind_cooling_device
 						(thermal, THERMAL_TRIPS_NONE,
 						 cdev, THERMAL_NO_LIMIT,
-						 THERMAL_NO_LIMIT);
+						 THERMAL_NO_LIMIT,
+						 THERMAL_WEIGHT_DEFAULT);
 			else
 				result = thermal_zone_unbind_cooling_device
 						(thermal, THERMAL_TRIPS_NONE,

drivers/platform/x86/acerhdf.c

@@ -372,7 +372,8 @@ static int acerhdf_bind(struct thermal_zone_device *thermal,
 		return 0;
 
 	if (thermal_zone_bind_cooling_device(thermal, 0, cdev,
-			THERMAL_NO_LIMIT, THERMAL_NO_LIMIT)) {
+			THERMAL_NO_LIMIT, THERMAL_NO_LIMIT,
+			THERMAL_WEIGHT_DEFAULT)) {
 		pr_err("error binding cooling dev\n");
 		return -EINVAL;
 	}

drivers/thermal/Kconfig

@@ -42,6 +42,17 @@ config THERMAL_OF
 	  Say 'Y' here if you need to build thermal infrastructure
 	  based on device tree.
 
+config THERMAL_WRITABLE_TRIPS
+	bool "Enable writable trip points"
+	help
+	  This option allows the system integrator to choose whether
+	  trip temperatures can be changed from userspace. The
+	  writable trips need to be specified when setting up the
+	  thermal zone but the choice here takes precedence.
+
+	  Say 'Y' here if you would like to allow userspace tools to
+	  change trip temperatures.
+
 choice
 	prompt "Default Thermal governor"
 	default THERMAL_DEFAULT_GOV_STEP_WISE
@@ -71,6 +82,14 @@ config THERMAL_DEFAULT_GOV_USER_SPACE
 	  Select this if you want to let the user space manage the
 	  platform thermals.
 
+config THERMAL_DEFAULT_GOV_POWER_ALLOCATOR
+	bool "power_allocator"
+	select THERMAL_GOV_POWER_ALLOCATOR
+	help
+	  Select this if you want to control temperature based on
+	  system and device power allocation. This governor can only
+	  operate on cooling devices that implement the power API.
+
 endchoice
 
 config THERMAL_GOV_FAIR_SHARE
@@ -99,6 +118,12 @@ config THERMAL_GOV_USER_SPACE
 	help
 	  Enable this to let the user space manage the platform thermals.
 
+config THERMAL_GOV_POWER_ALLOCATOR
+	bool "Power allocator thermal governor"
+	help
+	  Enable this to manage platform thermals by dynamically
+	  allocating and limiting power to devices.
+
 config CPU_THERMAL
 	bool "generic cpu cooling support"
 	depends on CPU_FREQ
@@ -136,6 +161,14 @@ config THERMAL_EMULATION
 	  because userland can easily disable the thermal policy by simply
 	  flooding this sysfs node with low temperature values.
 
+config HISI_THERMAL
+	tristate "Hisilicon thermal driver"
+	depends on ARCH_HISI && CPU_THERMAL && OF
+	help
+	  Enable this to plug hisilicon's thermal sensor driver into the Linux
+	  thermal framework. cpufreq is used as the cooling device to throttle
+	  CPUs when the passive trip is crossed.
+
 config IMX_THERMAL
 	tristate "Temperature sensor driver for Freescale i.MX SoCs"
 	depends on CPU_THERMAL
@@ -299,4 +332,15 @@ depends on ARCH_STI && OF
 source "drivers/thermal/st/Kconfig"
 endmenu
 
+config QCOM_SPMI_TEMP_ALARM
+	tristate "Qualcomm SPMI PMIC Temperature Alarm"
+	depends on OF && SPMI && IIO
+	select REGMAP_SPMI
+	help
+	  This enables a thermal sysfs driver for Qualcomm plug-and-play (QPNP)
+	  PMIC devices. It shows up in sysfs as a thermal sensor with multiple
+	  trip points. The temperature reported by the thermal sensor reflects the
+	  real time die temperature if an ADC is present or an estimate of the
+	  temperature based upon the over temperature stage value.
+
 endif

drivers/thermal/Makefile

@@ -14,6 +14,7 @@ thermal_sys-$(CONFIG_THERMAL_GOV_FAIR_SHARE)	+= fair_share.o
 thermal_sys-$(CONFIG_THERMAL_GOV_BANG_BANG)	+= gov_bang_bang.o
 thermal_sys-$(CONFIG_THERMAL_GOV_STEP_WISE)	+= step_wise.o
 thermal_sys-$(CONFIG_THERMAL_GOV_USER_SPACE)	+= user_space.o
+thermal_sys-$(CONFIG_THERMAL_GOV_POWER_ALLOCATOR)	+= power_allocator.o
 
 # cpufreq cooling
 thermal_sys-$(CONFIG_CPU_THERMAL)	+= cpu_cooling.o
@@ -22,6 +23,7 @@ thermal_sys-$(CONFIG_CPU_THERMAL)	+= cpu_cooling.o
 thermal_sys-$(CONFIG_CLOCK_THERMAL)	+= clock_cooling.o
 
 # platform thermal drivers
+obj-$(CONFIG_QCOM_SPMI_TEMP_ALARM)	+= qcom-spmi-temp-alarm.o
 obj-$(CONFIG_SPEAR_THERMAL)	+= spear_thermal.o
 obj-$(CONFIG_ROCKCHIP_THERMAL)	+= rockchip_thermal.o
 obj-$(CONFIG_RCAR_THERMAL)	+= rcar_thermal.o
@@ -39,3 +41,4 @@ obj-$(CONFIG_TI_SOC_THERMAL)	+= ti-soc-thermal/
 obj-$(CONFIG_INT340X_THERMAL)  += int340x_thermal/
 obj-$(CONFIG_ST_THERMAL)	+= st/
 obj-$(CONFIG_TEGRA_SOCTHERM)	+= tegra_soctherm.o
+obj-$(CONFIG_HISI_THERMAL)     += hisi_thermal.o

drivers/thermal/cpu_cooling.c

@@ -26,10 +26,13 @@
 #include <linux/thermal.h>
 #include <linux/cpufreq.h>
 #include <linux/err.h>
+#include <linux/pm_opp.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/cpu_cooling.h>
 
+#include <trace/events/thermal.h>
+
 /*
  * Cooling state <-> CPUFreq frequency
  *
@@ -44,6 +47,19 @@
  *	...
  */
 
+/**
+ * struct power_table - frequency to power conversion
+ * @frequency:	frequency in KHz
+ * @power:	power in mW
+ *
+ * This structure is built when the cooling device registers and helps
+ * in translating frequency to power and viceversa.
+ */
+struct power_table {
+	u32 frequency;
+	u32 power;
+};
+
 /**
  * struct cpufreq_cooling_device - data for cooling device with cpufreq
  * @id: unique integer value corresponding to each cpufreq_cooling_device
@@ -58,6 +74,15 @@
  *	cpufreq frequencies.
  * @allowed_cpus: all the cpus involved for this cpufreq_cooling_device.
  * @node: list_head to link all cpufreq_cooling_device together.
+ * @last_load: load measured by the latest call to cpufreq_get_actual_power()
+ * @time_in_idle: previous reading of the absolute time that this cpu was idle
+ * @time_in_idle_timestamp: wall time of the last invocation of
+ *	get_cpu_idle_time_us()
+ * @dyn_power_table: array of struct power_table for frequency to power
+ *	conversion, sorted in ascending order.
+ * @dyn_power_table_entries: number of entries in the @dyn_power_table array
+ * @cpu_dev: the first cpu_device from @allowed_cpus that has OPPs registered
+ * @plat_get_static_power: callback to calculate the static power
  *
  * This structure is required for keeping information of each registered
  * cpufreq_cooling_device.
@@ -71,6 +96,13 @@ struct cpufreq_cooling_device {
 	unsigned int *freq_table;	/* In descending order */
 	struct cpumask allowed_cpus;
 	struct list_head node;
+	u32 last_load;
+	u64 *time_in_idle;
+	u64 *time_in_idle_timestamp;
+	struct power_table *dyn_power_table;
+	int dyn_power_table_entries;
+	struct device *cpu_dev;
+	get_static_t plat_get_static_power;
 };
 static DEFINE_IDR(cpufreq_idr);
 static DEFINE_MUTEX(cooling_cpufreq_lock);
@@ -186,23 +218,237 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb,
 	unsigned long max_freq = 0;
 	struct cpufreq_cooling_device *cpufreq_dev;
 
-	if (event != CPUFREQ_ADJUST)
-		return 0;
+	switch (event) {
 
-	mutex_lock(&cooling_cpufreq_lock);
-	list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) {
-		if (!cpumask_test_cpu(policy->cpu,
-					&cpufreq_dev->allowed_cpus))
+	case CPUFREQ_ADJUST:
+		mutex_lock(&cooling_cpufreq_lock);
+		list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) {
+			if (!cpumask_test_cpu(policy->cpu,
+					      &cpufreq_dev->allowed_cpus))
+				continue;
+
+			max_freq = cpufreq_dev->cpufreq_val;
+
+			if (policy->max != max_freq)
+				cpufreq_verify_within_limits(policy, 0,
+							     max_freq);
+		}
+		mutex_unlock(&cooling_cpufreq_lock);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
+/**
+ * build_dyn_power_table() - create a dynamic power to frequency table
+ * @cpufreq_device:	the cpufreq cooling device in which to store the table
+ * @capacitance: dynamic power coefficient for these cpus
+ *
+ * Build a dynamic power to frequency table for this cpu and store it
+ * in @cpufreq_device.  This table will be used in cpu_power_to_freq() and
+ * cpu_freq_to_power() to convert between power and frequency
+ * efficiently.  Power is stored in mW, frequency in KHz.  The
+ * resulting table is in ascending order.
+ *
+ * Return: 0 on success, -E* on error.
+ */
+static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
+				 u32 capacitance)
+{
+	struct power_table *power_table;
+	struct dev_pm_opp *opp;
+	struct device *dev = NULL;
+	int num_opps = 0, cpu, i, ret = 0;
+	unsigned long freq;
+
+	rcu_read_lock();
+
+	for_each_cpu(cpu, &cpufreq_device->allowed_cpus) {
+		dev = get_cpu_device(cpu);
+		if (!dev) {
+			dev_warn(&cpufreq_device->cool_dev->device,
+				 "No cpu device for cpu %d\n", cpu);
 			continue;
+		}
+
+		num_opps = dev_pm_opp_get_opp_count(dev);
+		if (num_opps > 0) {
+			break;
+		} else if (num_opps < 0) {
+			ret = num_opps;
+			goto unlock;
+		}
+	}
 
-		max_freq = cpufreq_dev->cpufreq_val;
+	if (num_opps == 0) {
+		ret = -EINVAL;
+		goto unlock;
+	}
 
-		if (policy->max != max_freq)
-			cpufreq_verify_within_limits(policy, 0, max_freq);
+	power_table = kcalloc(num_opps, sizeof(*power_table), GFP_KERNEL);
+	if (!power_table) {
+		ret = -ENOMEM;
+		goto unlock;
 	}
-	mutex_unlock(&cooling_cpufreq_lock);
 
-	return 0;
+	for (freq = 0, i = 0;
+	     opp = dev_pm_opp_find_freq_ceil(dev, &freq), !IS_ERR(opp);
+	     freq++, i++) {
+		u32 freq_mhz, voltage_mv;
+		u64 power;
+
+		freq_mhz = freq / 1000000;
+		voltage_mv = dev_pm_opp_get_voltage(opp) / 1000;
+
+		/*
+		 * Do the multiplication with MHz and millivolt so as
+		 * to not overflow.
+		 */
+		power = (u64)capacitance * freq_mhz * voltage_mv * voltage_mv;
+		do_div(power, 1000000000);
+
+		/* frequency is stored in power_table in KHz */
+		power_table[i].frequency = freq / 1000;
+
+		/* power is stored in mW */
+		power_table[i].power = power;
+	}
+
+	if (i == 0) {
+		ret = PTR_ERR(opp);
+		goto unlock;
+	}
+
+	cpufreq_device->cpu_dev = dev;
+	cpufreq_device->dyn_power_table = power_table;
+	cpufreq_device->dyn_power_table_entries = i;
+
+unlock:
+	rcu_read_unlock();
+	return ret;
+}
+
+static u32 cpu_freq_to_power(struct cpufreq_cooling_device *cpufreq_device,
+			     u32 freq)
+{
+	int i;
+	struct power_table *pt = cpufreq_device->dyn_power_table;
+
+	for (i = 1; i < cpufreq_device->dyn_power_table_entries; i++)
+		if (freq < pt[i].frequency)
+			break;
+
+	return pt[i - 1].power;
+}
+
+static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_device,
+			     u32 power)
+{
+	int i;
+	struct power_table *pt = cpufreq_device->dyn_power_table;
+
+	for (i = 1; i < cpufreq_device->dyn_power_table_entries; i++)
+		if (power < pt[i].power)
+			break;
+
+	return pt[i - 1].frequency;
+}
+
+/**
+ * get_load() - get load for a cpu since last updated
+ * @cpufreq_device:	&struct cpufreq_cooling_device for this cpu
+ * @cpu:	cpu number
+ *
+ * Return: The average load of cpu @cpu in percentage since this
+ * function was last called.
+ */
+static u32 get_load(struct cpufreq_cooling_device *cpufreq_device, int cpu)
+{
+	u32 load;
+	u64 now, now_idle, delta_time, delta_idle;
+
+	now_idle = get_cpu_idle_time(cpu, &now, 0);
+	delta_idle = now_idle - cpufreq_device->time_in_idle[cpu];
+	delta_time = now - cpufreq_device->time_in_idle_timestamp[cpu];
+
+	if (delta_time <= delta_idle)
+		load = 0;
+	else
+		load = div64_u64(100 * (delta_time - delta_idle), delta_time);
+
+	cpufreq_device->time_in_idle[cpu] = now_idle;
+	cpufreq_device->time_in_idle_timestamp[cpu] = now;
+
+	return load;
+}
+
+/**
+ * get_static_power() - calculate the static power consumed by the cpus
+ * @cpufreq_device:	struct &cpufreq_cooling_device for this cpu cdev
+ * @tz:		thermal zone device in which we're operating
+ * @freq:	frequency in KHz
+ * @power:	pointer in which to store the calculated static power
+ *
+ * Calculate the static power consumed by the cpus described by
+ * @cpu_actor running at frequency @freq.  This function relies on a
+ * platform specific function that should have been provided when the
+ * actor was registered.  If it wasn't, the static power is assumed to
+ * be negligible.  The calculated static power is stored in @power.
+ *
+ * Return: 0 on success, -E* on failure.
+ */
+static int get_static_power(struct cpufreq_cooling_device *cpufreq_device,
+			    struct thermal_zone_device *tz, unsigned long freq,
+			    u32 *power)
+{
+	struct dev_pm_opp *opp;
+	unsigned long voltage;
+	struct cpumask *cpumask = &cpufreq_device->allowed_cpus;
+	unsigned long freq_hz = freq * 1000;
+
+	if (!cpufreq_device->plat_get_static_power ||
+	    !cpufreq_device->cpu_dev) {
+		*power = 0;
+		return 0;
+	}
+
+	rcu_read_lock();
+
+	opp = dev_pm_opp_find_freq_exact(cpufreq_device->cpu_dev, freq_hz,
+					 true);
+	voltage = dev_pm_opp_get_voltage(opp);
+
+	rcu_read_unlock();
+
+	if (voltage == 0) {
+		dev_warn_ratelimited(cpufreq_device->cpu_dev,
+				     "Failed to get voltage for frequency %lu: %ld\n",
+				     freq_hz, IS_ERR(opp) ? PTR_ERR(opp) : 0);
+		return -EINVAL;
+	}
+
+	return cpufreq_device->plat_get_static_power(cpumask, tz->passive_delay,
+						     voltage, power);
+}
+
+/**
+ * get_dynamic_power() - calculate the dynamic power
+ * @cpufreq_device:	&cpufreq_cooling_device for this cdev
+ * @freq:	current frequency
+ *
+ * Return: the dynamic power consumed by the cpus described by
+ * @cpufreq_device.
+ */
+static u32 get_dynamic_power(struct cpufreq_cooling_device *cpufreq_device,
+			     unsigned long freq)
+{
+	u32 raw_cpu_power;
+
+	raw_cpu_power = cpu_freq_to_power(cpufreq_device, freq);
+	return (raw_cpu_power * cpufreq_device->last_load) / 100;
 }
 
 /* cpufreq cooling device callback functions are defined below */
@@ -280,8 +526,205 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev,
 	return 0;
 }
 
+/**
+ * cpufreq_get_requested_power() - get the current power
+ * @cdev:	&thermal_cooling_device pointer
+ * @tz:		a valid thermal zone device pointer
+ * @power:	pointer in which to store the resulting power
+ *
+ * Calculate the current power consumption of the cpus in milliwatts
+ * and store it in @power.  This function should actually calculate
+ * the requested power, but it's hard to get the frequency that
+ * cpufreq would have assigned if there were no thermal limits.
+ * Instead, we calculate the current power on the assumption that the
+ * immediate future will look like the immediate past.
+ *
+ * We use the current frequency and the average load since this
+ * function was last called.  In reality, there could have been
+ * multiple opps since this function was last called and that affects
+ * the load calculation.  While it's not perfectly accurate, this
+ * simplification is good enough and works.  REVISIT this, as more
+ * complex code may be needed if experiments show that it's not
+ * accurate enough.
+ *
+ * Return: 0 on success, -E* if getting the static power failed.
+ */
+static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev,
+				       struct thermal_zone_device *tz,
+				       u32 *power)
+{
+	unsigned long freq;
+	int i = 0, cpu, ret;
+	u32 static_power, dynamic_power, total_load = 0;
+	struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
+	u32 *load_cpu = NULL;
+
+	cpu = cpumask_any_and(&cpufreq_device->allowed_cpus, cpu_online_mask);
+
+	/*
+	 * All the CPUs are offline, thus the requested power by
+	 * the cdev is 0
+	 */
+	if (cpu >= nr_cpu_ids) {
+		*power = 0;
+		return 0;
+	}
+
+	freq = cpufreq_quick_get(cpu);
+
+	if (trace_thermal_power_cpu_get_power_enabled()) {
+		u32 ncpus = cpumask_weight(&cpufreq_device->allowed_cpus);
+
+		load_cpu = devm_kcalloc(&cdev->device, ncpus, sizeof(*load_cpu),
+					GFP_KERNEL);
+	}
+
+	for_each_cpu(cpu, &cpufreq_device->allowed_cpus) {
+		u32 load;
+
+		if (cpu_online(cpu))
+			load = get_load(cpufreq_device, cpu);
+		else
+			load = 0;
+
+		total_load += load;
+		if (trace_thermal_power_cpu_limit_enabled() && load_cpu)
+			load_cpu[i] = load;
+
+		i++;
+	}
+
+	cpufreq_device->last_load = total_load;
+
+	dynamic_power = get_dynamic_power(cpufreq_device, freq);
+	ret = get_static_power(cpufreq_device, tz, freq, &static_power);
+	if (ret) {
+		if (load_cpu)
+			devm_kfree(&cdev->device, load_cpu);
+		return ret;
+	}
+
+	if (load_cpu) {
+		trace_thermal_power_cpu_get_power(
+			&cpufreq_device->allowed_cpus,
+			freq, load_cpu, i, dynamic_power, static_power);
+
+		devm_kfree(&cdev->device, load_cpu);
+	}
+
+	*power = static_power + dynamic_power;
+	return 0;
+}
+
+/**
+ * cpufreq_state2power() - convert a cpu cdev state to power consumed
+ * @cdev:	&thermal_cooling_device pointer
+ * @tz:		a valid thermal zone device pointer
+ * @state:	cooling device state to be converted
+ * @power:	pointer in which to store the resulting power
+ *
+ * Convert cooling device state @state into power consumption in
+ * milliwatts assuming 100% load.  Store the calculated power in
+ * @power.
+ *
+ * Return: 0 on success, -EINVAL if the cooling device state could not
+ * be converted into a frequency or other -E* if there was an error
+ * when calculating the static power.
+ */
+static int cpufreq_state2power(struct thermal_cooling_device *cdev,
+			       struct thermal_zone_device *tz,
+			       unsigned long state, u32 *power)
+{
+	unsigned int freq, num_cpus;
+	cpumask_t cpumask;
+	u32 static_power, dynamic_power;
+	int ret;
+	struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
+
+	cpumask_and(&cpumask, &cpufreq_device->allowed_cpus, cpu_online_mask);
+	num_cpus = cpumask_weight(&cpumask);
+
+	/* None of our cpus are online, so no power */
+	if (num_cpus == 0) {
+		*power = 0;
+		return 0;
+	}
+
+	freq = cpufreq_device->freq_table[state];
+	if (!freq)
+		return -EINVAL;
+
+	dynamic_power = cpu_freq_to_power(cpufreq_device, freq) * num_cpus;
+	ret = get_static_power(cpufreq_device, tz, freq, &static_power);
+	if (ret)
+		return ret;
+
+	*power = static_power + dynamic_power;
+	return 0;
+}
+
+/**
+ * cpufreq_power2state() - convert power to a cooling device state
+ * @cdev:	&thermal_cooling_device pointer
+ * @tz:		a valid thermal zone device pointer
+ * @power:	power in milliwatts to be converted
+ * @state:	pointer in which to store the resulting state
+ *
+ * Calculate a cooling device state for the cpus described by @cdev
+ * that would allow them to consume at most @power mW and store it in
+ * @state.  Note that this calculation depends on external factors
+ * such as the cpu load or the current static power.  Calling this
+ * function with the same power as input can yield different cooling
+ * device states depending on those external factors.
+ *
+ * Return: 0 on success, -ENODEV if no cpus are online or -EINVAL if
+ * the calculated frequency could not be converted to a valid state.
+ * The latter should not happen unless the frequencies available to
+ * cpufreq have changed since the initialization of the cpu cooling
+ * device.
+ */
+static int cpufreq_power2state(struct thermal_cooling_device *cdev,
+			       struct thermal_zone_device *tz, u32 power,
+			       unsigned long *state)
+{
+	unsigned int cpu, cur_freq, target_freq;
+	int ret;
+	s32 dyn_power;
+	u32 last_load, normalised_power, static_power;
+	struct cpufreq_cooling_device *cpufreq_device = cdev->devdata;
+
+	cpu = cpumask_any_and(&cpufreq_device->allowed_cpus, cpu_online_mask);
+
+	/* None of our cpus are online */
+	if (cpu >= nr_cpu_ids)
+		return -ENODEV;
+
+	cur_freq = cpufreq_quick_get(cpu);
+	ret = get_static_power(cpufreq_device, tz, cur_freq, &static_power);
+	if (ret)
+		return ret;
+
+	dyn_power = power - static_power;
+	dyn_power = dyn_power > 0 ? dyn_power : 0;
+	last_load = cpufreq_device->last_load ?: 1;
+	normalised_power = (dyn_power * 100) / last_load;
+	target_freq = cpu_power_to_freq(cpufreq_device, normalised_power);
+
+	*state = cpufreq_cooling_get_level(cpu, target_freq);
+	if (*state == THERMAL_CSTATE_INVALID) {
+		dev_warn_ratelimited(&cdev->device,
+				     "Failed to convert %dKHz for cpu %d into a cdev state\n",
+				     target_freq, cpu);
+		return -EINVAL;
+	}
+
+	trace_thermal_power_cpu_limit(&cpufreq_device->allowed_cpus,
+				      target_freq, *state, power);
+	return 0;
+}
+
 /* Bind cpufreq callbacks to thermal cooling device ops */
-static struct thermal_cooling_device_ops const cpufreq_cooling_ops = {
+static struct thermal_cooling_device_ops cpufreq_cooling_ops = {
 	.get_max_state = cpufreq_get_max_state,
 	.get_cur_state = cpufreq_get_cur_state,
 	.set_cur_state = cpufreq_set_cur_state,
@@ -311,6 +754,9 @@ static unsigned int find_next_max(struct cpufreq_frequency_table *table,
  * @np: a valid struct device_node to the cooling device device tree node
  * @clip_cpus: cpumask of cpus where the frequency constraints will happen.
  * Normally this should be same as cpufreq policy->related_cpus.
+ * @capacitance: dynamic power coefficient for these cpus
+ * @plat_static_func: function to calculate the static power consumed by these
+ *                    cpus (optional)
  *
  * This interface function registers the cpufreq cooling device with the name
  * "thermal-cpufreq-%x". This api can support multiple instances of cpufreq
@@ -322,13 +768,14 @@ static unsigned int find_next_max(struct cpufreq_frequency_table *table,
  */
 static struct thermal_cooling_device *
 __cpufreq_cooling_register(struct device_node *np,
-			   const struct cpumask *clip_cpus)
+			const struct cpumask *clip_cpus, u32 capacitance,
+			get_static_t plat_static_func)
 {
 	struct thermal_cooling_device *cool_dev;
 	struct cpufreq_cooling_device *cpufreq_dev;
 	char dev_name[THERMAL_NAME_LENGTH];
 	struct cpufreq_frequency_table *pos, *table;
-	unsigned int freq, i;
+	unsigned int freq, i, num_cpus;
 	int ret;
 
 	table = cpufreq_frequency_get_table(cpumask_first(clip_cpus));
@@ -341,6 +788,23 @@ __cpufreq_cooling_register(struct device_node *np,
 	if (!cpufreq_dev)
 		return ERR_PTR(-ENOMEM);
 
+	num_cpus = cpumask_weight(clip_cpus);
+	cpufreq_dev->time_in_idle = kcalloc(num_cpus,
+					    sizeof(*cpufreq_dev->time_in_idle),
+					    GFP_KERNEL);
+	if (!cpufreq_dev->time_in_idle) {
+		cool_dev = ERR_PTR(-ENOMEM);
+		goto free_cdev;
+	}
+
+	cpufreq_dev->time_in_idle_timestamp =
+		kcalloc(num_cpus, sizeof(*cpufreq_dev->time_in_idle_timestamp),
+			GFP_KERNEL);
+	if (!cpufreq_dev->time_in_idle_timestamp) {
+		cool_dev = ERR_PTR(-ENOMEM);
+		goto free_time_in_idle;
+	}
+
 	/* Find max levels */
 	cpufreq_for_each_valid_entry(pos, table)
 		cpufreq_dev->max_level++;
@@ -349,7 +813,7 @@ __cpufreq_cooling_register(struct device_node *np,
 					  cpufreq_dev->max_level, GFP_KERNEL);
 	if (!cpufreq_dev->freq_table) {
 		cool_dev = ERR_PTR(-ENOMEM);
-		goto free_cdev;
+		goto free_time_in_idle_timestamp;
 	}
 
 	/* max_level is an index, not a counter */
@@ -357,6 +821,20 @@ __cpufreq_cooling_register(struct device_node *np,
 
 	cpumask_copy(&cpufreq_dev->allowed_cpus, clip_cpus);
 
+	if (capacitance) {
+		cpufreq_cooling_ops.get_requested_power =
+			cpufreq_get_requested_power;
+		cpufreq_cooling_ops.state2power = cpufreq_state2power;
+		cpufreq_cooling_ops.power2state = cpufreq_power2state;
+		cpufreq_dev->plat_get_static_power = plat_static_func;
+
+		ret = build_dyn_power_table(cpufreq_dev, capacitance);
+		if (ret) {
+			cool_dev = ERR_PTR(ret);
+			goto free_table;
+		}
+	}
+
 	ret = get_idr(&cpufreq_idr, &cpufreq_dev->id);
 	if (ret) {
 		cool_dev = ERR_PTR(ret);
@@ -402,6 +880,10 @@ remove_idr:
 	release_idr(&cpufreq_idr, cpufreq_dev->id);
 free_table:
 	kfree(cpufreq_dev->freq_table);
+free_time_in_idle_timestamp:
+	kfree(cpufreq_dev->time_in_idle_timestamp);
+free_time_in_idle:
+	kfree(cpufreq_dev->time_in_idle);
 free_cdev:
 	kfree(cpufreq_dev);
 
@@ -422,7 +904,7 @@ free_cdev:
 struct thermal_cooling_device *
 cpufreq_cooling_register(const struct cpumask *clip_cpus)
 {
-	return __cpufreq_cooling_register(NULL, clip_cpus);
+	return __cpufreq_cooling_register(NULL, clip_cpus, 0, NULL);
 }
 EXPORT_SYMBOL_GPL(cpufreq_cooling_register);
 
@@ -446,10 +928,77 @@ of_cpufreq_cooling_register(struct device_node *np,
 	if (!np)
 		return ERR_PTR(-EINVAL);
 
-	return __cpufreq_cooling_register(np, clip_cpus);
+	return __cpufreq_cooling_register(np, clip_cpus, 0, NULL);
 }
 EXPORT_SYMBOL_GPL(of_cpufreq_cooling_register);
 
+/**
+ * cpufreq_power_cooling_register() - create cpufreq cooling device with power extensions
+ * @clip_cpus:	cpumask of cpus where the frequency constraints will happen
+ * @capacitance:	dynamic power coefficient for these cpus
+ * @plat_static_func:	function to calculate the static power consumed by these
+ *			cpus (optional)
+ *
+ * This interface function registers the cpufreq cooling device with
+ * the name "thermal-cpufreq-%x".  This api can support multiple
+ * instances of cpufreq cooling devices.  Using this function, the
+ * cooling device will implement the power extensions by using a
+ * simple cpu power model.  The cpus must have registered their OPPs
+ * using the OPP library.
+ *
+ * An optional @plat_static_func may be provided to calculate the
+ * static power consumed by these cpus.  If the platform's static
+ * power consumption is unknown or negligible, make it NULL.
+ *
+ * Return: a valid struct thermal_cooling_device pointer on success,
+ * on failure, it returns a corresponding ERR_PTR().
+ */
+struct thermal_cooling_device *
+cpufreq_power_cooling_register(const struct cpumask *clip_cpus, u32 capacitance,
+			       get_static_t plat_static_func)
+{
+	return __cpufreq_cooling_register(NULL, clip_cpus, capacitance,
+				plat_static_func);
+}
+EXPORT_SYMBOL(cpufreq_power_cooling_register);
+
+/**
+ * of_cpufreq_power_cooling_register() - create cpufreq cooling device with power extensions
+ * @np:	a valid struct device_node to the cooling device device tree node
+ * @clip_cpus:	cpumask of cpus where the frequency constraints will happen
+ * @capacitance:	dynamic power coefficient for these cpus
+ * @plat_static_func:	function to calculate the static power consumed by these
+ *			cpus (optional)
+ *
+ * This interface function registers the cpufreq cooling device with
+ * the name "thermal-cpufreq-%x".  This api can support multiple
+ * instances of cpufreq cooling devices.  Using this API, the cpufreq
+ * cooling device will be linked to the device tree node provided.
+ * Using this function, the cooling device will implement the power
+ * extensions by using a simple cpu power model.  The cpus must have
+ * registered their OPPs using the OPP library.
+ *
+ * An optional @plat_static_func may be provided to calculate the
+ * static power consumed by these cpus.  If the platform's static
+ * power consumption is unknown or negligible, make it NULL.
+ *
+ * Return: a valid struct thermal_cooling_device pointer on success,
+ * on failure, it returns a corresponding ERR_PTR().
+ */
+struct thermal_cooling_device *
+of_cpufreq_power_cooling_register(struct device_node *np,
+				  const struct cpumask *clip_cpus,
+				  u32 capacitance,
+				  get_static_t plat_static_func)
+{
+	if (!np)
+		return ERR_PTR(-EINVAL);
+
+	return __cpufreq_cooling_register(np, clip_cpus, capacitance,
+				plat_static_func);
+}
+EXPORT_SYMBOL(of_cpufreq_power_cooling_register);
+
 /**
  * cpufreq_cooling_unregister - function to remove cpufreq cooling device.
  * @cdev: thermal cooling device pointer.
@@ -475,6 +1024,8 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 
 	thermal_cooling_device_unregister(cpufreq_dev->cool_dev);
 	release_idr(&cpufreq_idr, cpufreq_dev->id);
+	kfree(cpufreq_dev->time_in_idle_timestamp);
+	kfree(cpufreq_dev->time_in_idle);
 	kfree(cpufreq_dev->freq_table);
 	kfree(cpufreq_dev);
 }

drivers/thermal/db8500_thermal.c

@@ -76,7 +76,7 @@ static int db8500_cdev_bind(struct thermal_zone_device *thermal,
 		upper = lower = i > max_state ? max_state : i;
 
 		ret = thermal_zone_bind_cooling_device(thermal, i, cdev,
-			upper, lower);
+			upper, lower, THERMAL_WEIGHT_DEFAULT);
 
 		dev_info(&cdev->device, "%s bind to %d: %d-%s\n", cdev->type,
 			i, ret, ret ? "fail" : "succeed");

drivers/thermal/fair_share.c

@@ -59,17 +59,17 @@ static int get_trip_level(struct thermal_zone_device *tz)
 }
 
 static long get_target_state(struct thermal_zone_device *tz,
-		struct thermal_cooling_device *cdev, int weight, int level)
+		struct thermal_cooling_device *cdev, int percentage, int level)
 {
 	unsigned long max_state;
 
 	cdev->ops->get_max_state(cdev, &max_state);
 
-	return (long)(weight * level * max_state) / (100 * tz->trips);
+	return (long)(percentage * level * max_state) / (100 * tz->trips);
 }
 
 /**
- * fair_share_throttle - throttles devices asscciated with the given zone
+ * fair_share_throttle - throttles devices associated with the given zone
  * @tz - thermal_zone_device
  *
  * Throttling Logic: This uses three parameters to calculate the new
@@ -77,7 +77,7 @@ static long get_target_state(struct thermal_zone_device *tz,
  *
  * Parameters used for Throttling:
  * P1. max_state: Maximum throttle state exposed by the cooling device.
- * P2. weight[i]/100:
+ * P2. percentage[i]/100:
  *	How 'effective' the 'i'th device is, in cooling the given zone.
  * P3. cur_trip_level/max_no_of_trips:
  *	This describes the extent to which the devices should be throttled.
@@ -88,28 +88,33 @@ static long get_target_state(struct thermal_zone_device *tz,
  */
 static int fair_share_throttle(struct thermal_zone_device *tz, int trip)
 {
-	const struct thermal_zone_params *tzp;
-	struct thermal_cooling_device *cdev;
 	struct thermal_instance *instance;
-	int i;
+	int total_weight = 0;
+	int total_instance = 0;
 	int cur_trip_level = get_trip_level(tz);
 
-	if (!tz->tzp || !tz->tzp->tbp)
-		return -EINVAL;
+	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+		if (instance->trip != trip)
+			continue;
+
+		total_weight += instance->weight;
+		total_instance++;
+	}
 
-	tzp = tz->tzp;
+	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+		int percentage;
+		struct thermal_cooling_device *cdev = instance->cdev;
 
-	for (i = 0; i < tzp->num_tbps; i++) {
-		if (!tzp->tbp[i].cdev)
+		if (instance->trip != trip)
 			continue;
 
-		cdev = tzp->tbp[i].cdev;
-		instance = get_thermal_instance(tz, cdev, trip);
-		if (!instance)
-			continue;
+		if (!total_weight)
+			percentage = 100 / total_instance;
+		else
+			percentage = (instance->weight * 100) / total_weight;
 
-		instance->target = get_target_state(tz, cdev,
-					tzp->tbp[i].weight, cur_trip_level);
+		instance->target = get_target_state(tz, cdev, percentage,
+						    cur_trip_level);
 
 		instance->cdev->updated = false;
 		thermal_cdev_update(cdev);

drivers/thermal/hisi_thermal.c

@@ -0,0 +1,421 @@
+/*
+ * Hisilicon thermal sensor driver
+ *
+ * Copyright (c) 2014-2015 Hisilicon Limited.
+ * Copyright (c) 2014-2015 Linaro Limited.
+ *
+ * Xinwei Kong <kong.kongxinwei@hisilicon.com>
+ * Leo Yan <leo.yan@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/cpufreq.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+
+#include "thermal_core.h"
+
+#define TEMP0_TH			(0x4)
+#define TEMP0_RST_TH			(0x8)
+#define TEMP0_CFG			(0xC)
+#define TEMP0_EN			(0x10)
+#define TEMP0_INT_EN			(0x14)
+#define TEMP0_INT_CLR			(0x18)
+#define TEMP0_RST_MSK			(0x1C)
+#define TEMP0_VALUE			(0x28)
+
+#define HISI_TEMP_BASE			(-60)
+#define HISI_TEMP_RESET			(100000)
+
+#define HISI_MAX_SENSORS		4
+
+struct hisi_thermal_sensor {
+	struct hisi_thermal_data *thermal;
+	struct thermal_zone_device *tzd;
+
+	long sensor_temp;
+	uint32_t id;
+	uint32_t thres_temp;
+};
+
+struct hisi_thermal_data {
+	struct mutex thermal_lock;    /* protects register data */
+	struct platform_device *pdev;
+	struct clk *clk;
+	struct hisi_thermal_sensor sensors[HISI_MAX_SENSORS];
+
+	int irq, irq_bind_sensor;
+	bool irq_enabled;
+
+	void __iomem *regs;
+};
+
+/* in millicelsius */
+static inline int _step_to_temp(int step)
+{
+	/*
+	 * Every step equals (1 * 200) / 255 celsius, and finally
+	 * need convert to millicelsius.
+	 */
+	return (HISI_TEMP_BASE + (step * 200 / 255)) * 1000;
+}
+
+static inline long _temp_to_step(long temp)
+{
+	return ((temp / 1000 - HISI_TEMP_BASE) * 255 / 200);
+}
+
+static long hisi_thermal_get_sensor_temp(struct hisi_thermal_data *data,
+					 struct hisi_thermal_sensor *sensor)
+{
+	long val;
+
+	mutex_lock(&data->thermal_lock);
+
+	/* disable interrupt */
+	writel(0x0, data->regs + TEMP0_INT_EN);
+	writel(0x1, data->regs + TEMP0_INT_CLR);
+
+	/* disable module firstly */
+	writel(0x0, data->regs + TEMP0_EN);
+
+	/* select sensor id */
+	writel((sensor->id << 12), data->regs + TEMP0_CFG);
+
+	/* enable module */
+	writel(0x1, data->regs + TEMP0_EN);
+
+	usleep_range(3000, 5000);
+
+	val = readl(data->regs + TEMP0_VALUE);
+	val = _step_to_temp(val);
+
+	mutex_unlock(&data->thermal_lock);
+
+	return val;
+}
+
+static void hisi_thermal_enable_bind_irq_sensor
+			(struct hisi_thermal_data *data)
+{
+	struct hisi_thermal_sensor *sensor;
+
+	mutex_lock(&data->thermal_lock);
+
+	sensor = &data->sensors[data->irq_bind_sensor];
+
+	/* setting the hdak time */
+	writel(0x0, data->regs + TEMP0_CFG);
+
+	/* disable module firstly */
+	writel(0x0, data->regs + TEMP0_RST_MSK);
+	writel(0x0, data->regs + TEMP0_EN);
+
+	/* select sensor id */
+	writel((sensor->id << 12), data->regs + TEMP0_CFG);
+
+	/* enable for interrupt */
+	writel(_temp_to_step(sensor->thres_temp) | 0x0FFFFFF00,
+	       data->regs + TEMP0_TH);
+
+	writel(_temp_to_step(HISI_TEMP_RESET), data->regs + TEMP0_RST_TH);
+
+	/* enable module */
+	writel(0x1, data->regs + TEMP0_RST_MSK);
+	writel(0x1, data->regs + TEMP0_EN);
+
+	writel(0x0, data->regs + TEMP0_INT_CLR);
+	writel(0x1, data->regs + TEMP0_INT_EN);
+
+	usleep_range(3000, 5000);
+
+	mutex_unlock(&data->thermal_lock);
+}
+
+static void hisi_thermal_disable_sensor(struct hisi_thermal_data *data)
+{
+	mutex_lock(&data->thermal_lock);
+
+	/* disable sensor module */
+	writel(0x0, data->regs + TEMP0_INT_EN);
+	writel(0x0, data->regs + TEMP0_RST_MSK);
+	writel(0x0, data->regs + TEMP0_EN);
+
+	mutex_unlock(&data->thermal_lock);
+}
+
+static int hisi_thermal_get_temp(void *_sensor, long *temp)
+{
+	struct hisi_thermal_sensor *sensor = _sensor;
+	struct hisi_thermal_data *data = sensor->thermal;
+
+	int sensor_id = 0, i;
+	long max_temp = 0;
+
+	*temp = hisi_thermal_get_sensor_temp(data, sensor);
+
+	sensor->sensor_temp = *temp;
+
+	for (i = 0; i < HISI_MAX_SENSORS; i++) {
+		if (data->sensors[i].sensor_temp >= max_temp) {
+			max_temp = data->sensors[i].sensor_temp;
+			sensor_id = i;
+		}
+	}
+
+	mutex_lock(&data->thermal_lock);
+	data->irq_bind_sensor = sensor_id;
+	mutex_unlock(&data->thermal_lock);
+
+	dev_dbg(&data->pdev->dev, "id=%d, irq=%d, temp=%ld, thres=%d\n",
+		sensor->id, data->irq_enabled, *temp, sensor->thres_temp);
+	/*
+	 * Bind irq to sensor for two cases:
+	 *   Reenable alarm IRQ if temperature below threshold;
+	 *   if irq has been enabled, always set it;
+	 */
+	if (data->irq_enabled) {
+		hisi_thermal_enable_bind_irq_sensor(data);
+		return 0;
+	}
+
+	if (max_temp < sensor->thres_temp) {
+		data->irq_enabled = true;
+		hisi_thermal_enable_bind_irq_sensor(data);
+		enable_irq(data->irq);
+	}
+
+	return 0;
+}
+
+static struct thermal_zone_of_device_ops hisi_of_thermal_ops = {
+	.get_temp = hisi_thermal_get_temp,
+};
+
+static irqreturn_t hisi_thermal_alarm_irq(int irq, void *dev)
+{
+	struct hisi_thermal_data *data = dev;
+
+	disable_irq_nosync(irq);
+	data->irq_enabled = false;
+
+	return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t hisi_thermal_alarm_irq_thread(int irq, void *dev)
+{
+	struct hisi_thermal_data *data = dev;
+	struct hisi_thermal_sensor *sensor;
+	int i;
+
+	mutex_lock(&data->thermal_lock);
+	sensor = &data->sensors[data->irq_bind_sensor];
+
+	dev_crit(&data->pdev->dev, "THERMAL ALARM: T > %d\n",
+		 sensor->thres_temp / 1000);
+	mutex_unlock(&data->thermal_lock);
+
+	for (i = 0; i < HISI_MAX_SENSORS; i++)
+		thermal_zone_device_update(data->sensors[i].tzd);
+
+	return IRQ_HANDLED;
+}
+
+static int hisi_thermal_register_sensor(struct platform_device *pdev,
+					struct hisi_thermal_data *data,
+					struct hisi_thermal_sensor *sensor,
+					int index)
+{
+	int ret, i;
+	const struct thermal_trip *trip;
+
+	sensor->id = index;
+	sensor->thermal = data;
+
+	sensor->tzd = thermal_zone_of_sensor_register(&pdev->dev, sensor->id,
+				sensor, &hisi_of_thermal_ops);
+	if (IS_ERR(sensor->tzd)) {
+		ret = PTR_ERR(sensor->tzd);
+		dev_err(&pdev->dev, "failed to register sensor id %d: %d\n",
+			sensor->id, ret);
+		return ret;
+	}
+
+	trip = of_thermal_get_trip_points(sensor->tzd);
+
+	for (i = 0; i < of_thermal_get_ntrips(sensor->tzd); i++) {
+		if (trip[i].type == THERMAL_TRIP_PASSIVE) {
+			sensor->thres_temp = trip[i].temperature;
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static const struct of_device_id of_hisi_thermal_match[] = {
+	{ .compatible = "hisilicon,tsensor" },
+	{ /* end */ }
+};
+MODULE_DEVICE_TABLE(of, of_hisi_thermal_match);
+
+static void hisi_thermal_toggle_sensor(struct hisi_thermal_sensor *sensor,
+				       bool on)
+{
+	struct thermal_zone_device *tzd = sensor->tzd;
+
+	tzd->ops->set_mode(tzd,
+		on ? THERMAL_DEVICE_ENABLED : THERMAL_DEVICE_DISABLED);
+}
+
+static int hisi_thermal_probe(struct platform_device *pdev)
+{
+	struct hisi_thermal_data *data;
+	struct resource *res;
+	int i;
+	int ret;
+
+	data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	mutex_init(&data->thermal_lock);
+	data->pdev = pdev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	data->regs = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(data->regs)) {
+		dev_err(&pdev->dev, "failed to get io address\n");
+		return PTR_ERR(data->regs);
+	}
+
+	data->irq = platform_get_irq(pdev, 0);
+	if (data->irq < 0)
+		return data->irq;
+
+	ret = devm_request_threaded_irq(&pdev->dev, data->irq,
+					hisi_thermal_alarm_irq,
+					hisi_thermal_alarm_irq_thread,
+					0, "hisi_thermal", data);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "failed to request alarm irq: %d\n", ret);
+		return ret;
+	}
+
+	platform_set_drvdata(pdev, data);
+
+	data->clk = devm_clk_get(&pdev->dev, "thermal_clk");
+	if (IS_ERR(data->clk)) {
+		ret = PTR_ERR(data->clk);
+		if (ret != -EPROBE_DEFER)
+			dev_err(&pdev->dev,
+				"failed to get thermal clk: %d\n", ret);
+		return ret;
+	}
+
+	/* enable clock for thermal */
+	ret = clk_prepare_enable(data->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to enable thermal clk: %d\n", ret);
+		return ret;
+	}
+
+	for (i = 0; i < HISI_MAX_SENSORS; ++i) {
+		ret = hisi_thermal_register_sensor(pdev, data,
+						   &data->sensors[i], i);
+		if (ret) {
+			dev_err(&pdev->dev,
+				"failed to register thermal sensor: %d\n", ret);
+			goto err_get_sensor_data;
+		}
+	}
+
+	hisi_thermal_enable_bind_irq_sensor(data);
+	data->irq_enabled = true;
+
+	for (i = 0; i < HISI_MAX_SENSORS; i++)
+		hisi_thermal_toggle_sensor(&data->sensors[i], true);
+
+	return 0;
+
+err_get_sensor_data:
+	clk_disable_unprepare(data->clk);
+
+	return ret;
+}
+
+static int hisi_thermal_remove(struct platform_device *pdev)
+{
+	struct hisi_thermal_data *data = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < HISI_MAX_SENSORS; i++) {
+		struct hisi_thermal_sensor *sensor = &data->sensors[i];
+
+		hisi_thermal_toggle_sensor(sensor, false);
+		thermal_zone_of_sensor_unregister(&pdev->dev, sensor->tzd);
+	}
+
+	hisi_thermal_disable_sensor(data);
+	clk_disable_unprepare(data->clk);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int hisi_thermal_suspend(struct device *dev)
+{
+	struct hisi_thermal_data *data = dev_get_drvdata(dev);
+
+	hisi_thermal_disable_sensor(data);
+	data->irq_enabled = false;
+
+	clk_disable_unprepare(data->clk);
+
+	return 0;
+}
+
+static int hisi_thermal_resume(struct device *dev)
+{
+	struct hisi_thermal_data *data = dev_get_drvdata(dev);
+
+	clk_prepare_enable(data->clk);
+
+	data->irq_enabled = true;
+	hisi_thermal_enable_bind_irq_sensor(data);
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(hisi_thermal_pm_ops,
+			 hisi_thermal_suspend, hisi_thermal_resume);
+
+static struct platform_driver hisi_thermal_driver = {
+	.driver = {
+		.name		= "hisi_thermal",
+		.owner		= THIS_MODULE,
+		.pm		= &hisi_thermal_pm_ops,
+		.of_match_table = of_hisi_thermal_match,
+	},
+	.probe	= hisi_thermal_probe,
+	.remove	= hisi_thermal_remove,
+};
+
+module_platform_driver(hisi_thermal_driver);
+
+MODULE_AUTHOR("Xinwei Kong <kong.kongxinwei@hisilicon.com>");
+MODULE_AUTHOR("Leo Yan <leo.yan@linaro.org>");
+MODULE_DESCRIPTION("Hisilicon thermal driver");
+MODULE_LICENSE("GPL v2");

drivers/thermal/imx_thermal.c

@@ -306,7 +306,8 @@ static int imx_bind(struct thermal_zone_device *tz,
 
 	ret = thermal_zone_bind_cooling_device(tz, IMX_TRIP_PASSIVE, cdev,
 					       THERMAL_NO_LIMIT,
-					       THERMAL_NO_LIMIT);
+					       THERMAL_NO_LIMIT,
+					       THERMAL_WEIGHT_DEFAULT);
 	if (ret) {
 		dev_err(&tz->device,
 			"binding zone %s with cdev %s failed:%d\n",

drivers/thermal/of-thermal.c

@@ -58,6 +58,8 @@ struct __thermal_bind_params {
  * @mode: current thermal zone device mode (enabled/disabled)
  * @passive_delay: polling interval while passive cooling is activated
  * @polling_delay: zone polling interval
+ * @slope: slope of the temperature adjustment curve
+ * @offset: offset of the temperature adjustment curve
  * @ntrips: number of trip points
  * @trips: an array of trip points (0..ntrips - 1)
  * @num_tbps: number of thermal bind params
@@ -70,6 +72,8 @@ struct __thermal_zone {
 	enum thermal_device_mode mode;
 	int passive_delay;
 	int polling_delay;
+	int slope;
+	int offset;
 
 	/* trip data */
 	int ntrips;
@@ -227,7 +231,8 @@ static int of_thermal_bind(struct thermal_zone_device *thermal,
 			ret = thermal_zone_bind_cooling_device(thermal,
 						tbp->trip_id, cdev,
 						tbp->max,
-						tbp->min);
+						tbp->min,
+						tbp->usage);
 			if (ret)
 				return ret;
 		}
@@ -581,7 +586,7 @@ static int thermal_of_populate_bind_params(struct device_node *np,
 	u32 prop;
 
 	/* Default weight. Usage is optional */
-	__tbp->usage = 0;
+	__tbp->usage = THERMAL_WEIGHT_DEFAULT;
 	ret = of_property_read_u32(np, "contribution", &prop);
 	if (ret == 0)
 		__tbp->usage = prop;
@@ -715,7 +720,7 @@ static int thermal_of_populate_trip(struct device_node *np,
  * @np parameter and fills the read data into a __thermal_zone data structure
  * and return this pointer.
  *
- * TODO: Missing properties to parse: thermal-sensor-names and coefficients
+ * TODO: Missing properties to parse: thermal-sensor-names
  *
  * Return: On success returns a valid struct __thermal_zone,
  * otherwise, it returns a corresponding ERR_PTR(). Caller must
@@ -727,7 +732,7 @@ thermal_of_build_thermal_zone(struct device_node *np)
 	struct device_node *child = NULL, *gchild;
 	struct __thermal_zone *tz;
 	int ret, i;
-	u32 prop;
+	u32 prop, coef[2];
 
 	if (!np) {
 		pr_err("no thermal zone np\n");
@@ -752,6 +757,20 @@ thermal_of_build_thermal_zone(struct device_node *np)
 	}
 	tz->polling_delay = prop;
 
+	/*
+	 * REVIST: for now, the thermal framework supports only
+	 * one sensor per thermal zone. Thus, we are considering
+	 * only the first two values as slope and offset.
+	 */
+	ret = of_property_read_u32_array(np, "coefficients", coef, 2);
+	if (ret == 0) {
+		tz->slope = coef[0];
+		tz->offset = coef[1];
+	} else {
+		tz->slope = 1;
+		tz->offset = 0;
+	}
+
 	/* trips */
 	child = of_get_child_by_name(np, "trips");
 
@@ -865,6 +884,8 @@ int __init of_parse_thermal_zones(void)
 	for_each_child_of_node(np, child) {
 		struct thermal_zone_device *zone;
 		struct thermal_zone_params *tzp;
+		int i, mask = 0;
+		u32 prop;
 
 		/* Check whether child is enabled or not */
 		if (!of_device_is_available(child))
@@ -891,8 +912,18 @@ int __init of_parse_thermal_zones(void)
 		/* No hwmon because there might be hwmon drivers registering */
 		tzp->no_hwmon = true;
 
+		if (!of_property_read_u32(child, "sustainable-power", &prop))
+			tzp->sustainable_power = prop;
+
+		for (i = 0; i < tz->ntrips; i++)
+			mask |= 1 << i;
+
+		/* these two are left for temperature drivers to use */
+		tzp->slope = tz->slope;
+		tzp->offset = tz->offset;
+
 		zone = thermal_zone_device_register(child->name, tz->ntrips,
-						    0, tz,
+						    mask, tz,
 						    ops, tzp,
 						    tz->passive_delay,
 						    tz->polling_delay);

drivers/thermal/power_allocator.c

@@ -0,0 +1,539 @@
+/*
+ * A power allocator to manage temperature
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt) "Power allocator: " fmt
+
+#include <linux/rculist.h>
+#include <linux/slab.h>
+#include <linux/thermal.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/thermal_power_allocator.h>
+
+#include "thermal_core.h"
+
+#define FRAC_BITS 10
+#define int_to_frac(x) ((x) << FRAC_BITS)
+#define frac_to_int(x) ((x) >> FRAC_BITS)
+
+/**
+ * mul_frac() - multiply two fixed-point numbers
+ * @x:	first multiplicand
+ * @y:	second multiplicand
+ *
+ * Return: the result of multiplying two fixed-point numbers.  The
+ * result is also a fixed-point number.
+ */
+static inline s64 mul_frac(s64 x, s64 y)
+{
+	return (x * y) >> FRAC_BITS;
+}
+
+/**
+ * div_frac() - divide two fixed-point numbers
+ * @x:	the dividend
+ * @y:	the divisor
+ *
+ * Return: the result of dividing two fixed-point numbers.  The
+ * result is also a fixed-point number.
+ */
+static inline s64 div_frac(s64 x, s64 y)
+{
+	return div_s64(x << FRAC_BITS, y);
+}
+
+/**
+ * struct power_allocator_params - parameters for the power allocator governor
+ * @err_integral:	accumulated error in the PID controller.
+ * @prev_err:	error in the previous iteration of the PID controller.
+ *		Used to calculate the derivative term.
+ * @trip_switch_on:	first passive trip point of the thermal zone.  The
+ *			governor switches on when this trip point is crossed.
+ * @trip_max_desired_temperature:	last passive trip point of the thermal
+ *					zone.  The temperature we are
+ *					controlling for.
+ */
+struct power_allocator_params {
+	s64 err_integral;
+	s32 prev_err;
+	int trip_switch_on;
+	int trip_max_desired_temperature;
+};
+
+/**
+ * pid_controller() - PID controller
+ * @tz:	thermal zone we are operating in
+ * @current_temp:	the current temperature in millicelsius
+ * @control_temp:	the target temperature in millicelsius
+ * @max_allocatable_power:	maximum allocatable power for this thermal zone
+ *
+ * This PID controller increases the available power budget so that the
+ * temperature of the thermal zone gets as close as possible to
+ * @control_temp and limits the power if it exceeds it.  k_po is the
+ * proportional term when we are overshooting, k_pu is the
+ * proportional term when we are undershooting.  integral_cutoff is a
+ * threshold below which we stop accumulating the error.  The
+ * accumulated error is only valid if the requested power will make
+ * the system warmer.  If the system is mostly idle, there's no point
+ * in accumulating positive error.
+ *
+ * Return: The power budget for the next period.
+ */
+static u32 pid_controller(struct thermal_zone_device *tz,
+			  unsigned long current_temp,
+			  unsigned long control_temp,
+			  u32 max_allocatable_power)
+{
+	s64 p, i, d, power_range;
+	s32 err, max_power_frac;
+	struct power_allocator_params *params = tz->governor_data;
+
+	max_power_frac = int_to_frac(max_allocatable_power);
+
+	err = ((s32)control_temp - (s32)current_temp);
+	err = int_to_frac(err);
+
+	/* Calculate the proportional term */
+	p = mul_frac(err < 0 ? tz->tzp->k_po : tz->tzp->k_pu, err);
+
+	/*
+	 * Calculate the integral term
+	 *
+	 * if the error is less than cut off allow integration (but
+	 * the integral is limited to max power)
+	 */
+	i = mul_frac(tz->tzp->k_i, params->err_integral);
+
+	if (err < int_to_frac(tz->tzp->integral_cutoff)) {
+		s64 i_next = i + mul_frac(tz->tzp->k_i, err);
+
+		if (abs64(i_next) < max_power_frac) {
+			i = i_next;
+			params->err_integral += err;
+		}
+	}
+
+	/*
+	 * Calculate the derivative term
+	 *
+	 * We do err - prev_err, so with a positive k_d, a decreasing
+	 * error (i.e. driving closer to the line) results in less
+	 * power being applied, slowing down the controller)
+	 */
+	d = mul_frac(tz->tzp->k_d, err - params->prev_err);
+	d = div_frac(d, tz->passive_delay);
+	params->prev_err = err;
+
+	power_range = p + i + d;
+
+	/* feed-forward the known sustainable dissipatable power */
+	power_range = tz->tzp->sustainable_power + frac_to_int(power_range);
+
+	power_range = clamp(power_range, (s64)0, (s64)max_allocatable_power);
+
+	trace_thermal_power_allocator_pid(tz, frac_to_int(err),
+					  frac_to_int(params->err_integral),
+					  frac_to_int(p), frac_to_int(i),
+					  frac_to_int(d), power_range);
+
+	return power_range;
+}
+
+/**
+ * divvy_up_power() - divvy the allocated power between the actors
+ * @req_power:	each actor's requested power
+ * @max_power:	each actor's maximum available power
+ * @num_actors:	size of the @req_power, @max_power and @granted_power's array
+ * @total_req_power: sum of @req_power
+ * @power_range:	total allocated power
+ * @granted_power:	output array: each actor's granted power
+ * @extra_actor_power:	an appropriately sized array to be used in the
+ *			function as temporary storage of the extra power given
+ *			to the actors
+ *
+ * This function divides the total allocated power (@power_range)
+ * fairly between the actors.  It first tries to give each actor a
+ * share of the @power_range according to how much power it requested
+ * compared to the rest of the actors.  For example, if only one actor
+ * requests power, then it receives all the @power_range.  If
+ * three actors each requests 1mW, each receives a third of the
+ * @power_range.
+ *
+ * If any actor received more than their maximum power, then that
+ * surplus is re-divvied among the actors based on how far they are
+ * from their respective maximums.
+ *
+ * Granted power for each actor is written to @granted_power, which
+ * should've been allocated by the calling function.
+ */
+static void divvy_up_power(u32 *req_power, u32 *max_power, int num_actors,
+			   u32 total_req_power, u32 power_range,
+			   u32 *granted_power, u32 *extra_actor_power)
+{
+	u32 extra_power, capped_extra_power;
+	int i;
+
+	/*
+	 * Prevent division by 0 if none of the actors request power.
+	 */
+	if (!total_req_power)
+		total_req_power = 1;
+
+	capped_extra_power = 0;
+	extra_power = 0;
+	for (i = 0; i < num_actors; i++) {
+		u64 req_range = req_power[i] * power_range;
+
+		granted_power[i] = DIV_ROUND_CLOSEST_ULL(req_range,
+							 total_req_power);
+
+		if (granted_power[i] > max_power[i]) {
+			extra_power += granted_power[i] - max_power[i];
+			granted_power[i] = max_power[i];
+		}
+
+		extra_actor_power[i] = max_power[i] - granted_power[i];
+		capped_extra_power += extra_actor_power[i];
+	}
+
+	if (!extra_power)
+		return;
+
+	/*
+	 * Re-divvy the reclaimed extra among actors based on
+	 * how far they are from the max
+	 */
+	extra_power = min(extra_power, capped_extra_power);
+	if (capped_extra_power > 0)
+		for (i = 0; i < num_actors; i++)
+			granted_power[i] += (extra_actor_power[i] *
+					extra_power) / capped_extra_power;
+}
+
+static int allocate_power(struct thermal_zone_device *tz,
+			  unsigned long current_temp,
+			  unsigned long control_temp)
+{
+	struct thermal_instance *instance;
+	struct power_allocator_params *params = tz->governor_data;
+	u32 *req_power, *max_power, *granted_power, *extra_actor_power;
+	u32 total_req_power, max_allocatable_power;
+	u32 total_granted_power, power_range;
+	int i, num_actors, total_weight, ret = 0;
+	int trip_max_desired_temperature = params->trip_max_desired_temperature;
+
+	mutex_lock(&tz->lock);
+
+	num_actors = 0;
+	total_weight = 0;
+	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+		if ((instance->trip == trip_max_desired_temperature) &&
+		    cdev_is_power_actor(instance->cdev)) {
+			num_actors++;
+			total_weight += instance->weight;
+		}
+	}
+
+	/*
+	 * We need to allocate three arrays of the same size:
+	 * req_power, max_power and granted_power.  They are going to
+	 * be needed until this function returns.  Allocate them all
+	 * in one go to simplify the allocation and deallocation
+	 * logic.
+	 */
+	BUILD_BUG_ON(sizeof(*req_power) != sizeof(*max_power));
+	BUILD_BUG_ON(sizeof(*req_power) != sizeof(*granted_power));
+	BUILD_BUG_ON(sizeof(*req_power) != sizeof(*extra_actor_power));
+	req_power = devm_kcalloc(&tz->device, num_actors * 4,
+				 sizeof(*req_power), GFP_KERNEL);
+	if (!req_power) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	max_power = &req_power[num_actors];
+	granted_power = &req_power[2 * num_actors];
+	extra_actor_power = &req_power[3 * num_actors];
+
+	i = 0;
+	total_req_power = 0;
+	max_allocatable_power = 0;
+
+	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+		int weight;
+		struct thermal_cooling_device *cdev = instance->cdev;
+
+		if (instance->trip != trip_max_desired_temperature)
+			continue;
+
+		if (!cdev_is_power_actor(cdev))
+			continue;
+
+		if (cdev->ops->get_requested_power(cdev, tz, &req_power[i]))
+			continue;
+
+		if (!total_weight)
+			weight = 1 << FRAC_BITS;
+		else
+			weight = instance->weight;
+
+		req_power[i] = frac_to_int(weight * req_power[i]);
+
+		if (power_actor_get_max_power(cdev, tz, &max_power[i]))
+			continue;
+
+		total_req_power += req_power[i];
+		max_allocatable_power += max_power[i];
+
+		i++;
+	}
+
+	power_range = pid_controller(tz, current_temp, control_temp,
+				     max_allocatable_power);
+
+	divvy_up_power(req_power, max_power, num_actors, total_req_power,
+		       power_range, granted_power, extra_actor_power);
+
+	total_granted_power = 0;
+	i = 0;
+	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+		if (instance->trip != trip_max_desired_temperature)
+			continue;
+
+		if (!cdev_is_power_actor(instance->cdev))
+			continue;
+
+		power_actor_set_power(instance->cdev, instance,
+				      granted_power[i]);
+		total_granted_power += granted_power[i];
+
+		i++;
+	}
+
+	trace_thermal_power_allocator(tz, req_power, total_req_power,
+				      granted_power, total_granted_power,
+				      num_actors, power_range,
+				      max_allocatable_power, current_temp,
+				      (s32)control_temp - (s32)current_temp);
+
+	devm_kfree(&tz->device, req_power);
+unlock:
+	mutex_unlock(&tz->lock);
+
+	return ret;
+}
+
+static int get_governor_trips(struct thermal_zone_device *tz,
+			      struct power_allocator_params *params)
+{
+	int i, ret, last_passive;
+	bool found_first_passive;
+
+	found_first_passive = false;
+	last_passive = -1;
+	ret = -EINVAL;
+
+	for (i = 0; i < tz->trips; i++) {
+		enum thermal_trip_type type;
+
+		ret = tz->ops->get_trip_type(tz, i, &type);
+		if (ret)
+			return ret;
+
+		if (!found_first_passive) {
+			if (type == THERMAL_TRIP_PASSIVE) {
+				params->trip_switch_on = i;
+				found_first_passive = true;
+			}
+		} else if (type == THERMAL_TRIP_PASSIVE) {
+			last_passive = i;
+		} else {
+			break;
+		}
+	}
+
+	if (last_passive != -1) {
+		params->trip_max_desired_temperature = last_passive;
+		ret = 0;
+	} else {
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static void reset_pid_controller(struct power_allocator_params *params)
+{
+	params->err_integral = 0;
+	params->prev_err = 0;
+}
+
+static void allow_maximum_power(struct thermal_zone_device *tz)
+{
+	struct thermal_instance *instance;
+	struct power_allocator_params *params = tz->governor_data;
+
+	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+		if ((instance->trip != params->trip_max_desired_temperature) ||
+		    (!cdev_is_power_actor(instance->cdev)))
+			continue;
+
+		instance->target = 0;
+		instance->cdev->updated = false;
+		thermal_cdev_update(instance->cdev);
+	}
+}
+
+/**
+ * power_allocator_bind() - bind the power_allocator governor to a thermal zone
+ * @tz:	thermal zone to bind it to
+ *
+ * Check that the thermal zone is valid for this governor, that is, it
+ * has two thermal trips.  If so, initialize the PID controller
+ * parameters and bind it to the thermal zone.
+ *
+ * Return: 0 on success, -EINVAL if the trips were invalid or -ENOMEM
+ * if we ran out of memory.
+ */
+static int power_allocator_bind(struct thermal_zone_device *tz)
+{
+	int ret;
+	struct power_allocator_params *params;
+	unsigned long switch_on_temp, control_temp;
+	u32 temperature_threshold;
+
+	if (!tz->tzp || !tz->tzp->sustainable_power) {
+		dev_err(&tz->device,
+			"power_allocator: missing sustainable_power\n");
+		return -EINVAL;
+	}
+
+	params = devm_kzalloc(&tz->device, sizeof(*params), GFP_KERNEL);
+	if (!params)
+		return -ENOMEM;
+
+	ret = get_governor_trips(tz, params);
+	if (ret) {
+		dev_err(&tz->device,
+			"thermal zone %s has wrong trip setup for power allocator\n",
+			tz->type);
+		goto free;
+	}
+
+	ret = tz->ops->get_trip_temp(tz, params->trip_switch_on,
+				     &switch_on_temp);
+	if (ret)
+		goto free;
+
+	ret = tz->ops->get_trip_temp(tz, params->trip_max_desired_temperature,
+				     &control_temp);
+	if (ret)
+		goto free;
+
+	temperature_threshold = control_temp - switch_on_temp;
+
+	tz->tzp->k_po = tz->tzp->k_po ?:
+		int_to_frac(tz->tzp->sustainable_power) / temperature_threshold;
+	tz->tzp->k_pu = tz->tzp->k_pu ?:
+		int_to_frac(2 * tz->tzp->sustainable_power) /
+		temperature_threshold;
+	tz->tzp->k_i = tz->tzp->k_i ?: int_to_frac(10) / 1000;
+	/*
+	 * The default for k_d and integral_cutoff is 0, so we can
+	 * leave them as they are.
+	 */
+
+	reset_pid_controller(params);
+
+	tz->governor_data = params;
+
+	return 0;
+
+free:
+	devm_kfree(&tz->device, params);
+	return ret;
+}
+
+static void power_allocator_unbind(struct thermal_zone_device *tz)
+{
+	dev_dbg(&tz->device, "Unbinding from thermal zone %d\n", tz->id);
+	devm_kfree(&tz->device, tz->governor_data);
+	tz->governor_data = NULL;
+}
+
+static int power_allocator_throttle(struct thermal_zone_device *tz, int trip)
+{
+	int ret;
+	unsigned long switch_on_temp, control_temp, current_temp;
+	struct power_allocator_params *params = tz->governor_data;
+
+	/*
+	 * We get called for every trip point but we only need to do
+	 * our calculations once
+	 */
+	if (trip != params->trip_max_desired_temperature)
+		return 0;
+
+	ret = thermal_zone_get_temp(tz, &current_temp);
+	if (ret) {
+		dev_warn(&tz->device, "Failed to get temperature: %d\n", ret);
+		return ret;
+	}
+
+	ret = tz->ops->get_trip_temp(tz, params->trip_switch_on,
+				     &switch_on_temp);
+	if (ret) {
+		dev_warn(&tz->device,
+			 "Failed to get switch on temperature: %d\n", ret);
+		return ret;
+	}
+
+	if (current_temp < switch_on_temp) {
+		tz->passive = 0;
+		reset_pid_controller(params);
+		allow_maximum_power(tz);
+		return 0;
+	}
+
+	tz->passive = 1;
+
+	ret = tz->ops->get_trip_temp(tz, params->trip_max_desired_temperature,
+				&control_temp);
+	if (ret) {
+		dev_warn(&tz->device,
+			 "Failed to get the maximum desired temperature: %d\n",
+			 ret);
+		return ret;
+	}
+
+	return allocate_power(tz, current_temp, control_temp);
+}
+
+static struct thermal_governor thermal_gov_power_allocator = {
+	.name		= "power_allocator",
+	.bind_to_tz	= power_allocator_bind,
+	.unbind_from_tz	= power_allocator_unbind,
+	.throttle	= power_allocator_throttle,
+};
+
+int thermal_gov_power_allocator_register(void)
+{
+	return thermal_register_governor(&thermal_gov_power_allocator);
+}
+
+void thermal_gov_power_allocator_unregister(void)
+{
+	thermal_unregister_governor(&thermal_gov_power_allocator);
+}

drivers/thermal/qcom-spmi-temp-alarm.c

@@ -0,0 +1,309 @@
+/*
+ * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * 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.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/iio/consumer.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/thermal.h>
+
+#define QPNP_TM_REG_TYPE		0x04
+#define QPNP_TM_REG_SUBTYPE		0x05
+#define QPNP_TM_REG_STATUS		0x08
+#define QPNP_TM_REG_SHUTDOWN_CTRL1	0x40
+#define QPNP_TM_REG_ALARM_CTRL		0x46
+
+#define QPNP_TM_TYPE			0x09
+#define QPNP_TM_SUBTYPE			0x08
+
+#define STATUS_STAGE_MASK		0x03
+
+#define SHUTDOWN_CTRL1_THRESHOLD_MASK	0x03
+
+#define ALARM_CTRL_FORCE_ENABLE		0x80
+
+/*
+ * Trip point values based on threshold control
+ * 0 = {105 C, 125 C, 145 C}
+ * 1 = {110 C, 130 C, 150 C}
+ * 2 = {115 C, 135 C, 155 C}
+ * 3 = {120 C, 140 C, 160 C}
+*/
+#define TEMP_STAGE_STEP			20000	/* Stage step: 20.000 C */
+#define TEMP_STAGE_HYSTERESIS		2000
+
+#define TEMP_THRESH_MIN			105000	/* Threshold Min: 105 C */
+#define TEMP_THRESH_STEP		5000	/* Threshold step: 5 C */
+
+#define THRESH_MIN			0
+
+/* Temperature in Milli Celsius reported during stage 0 if no ADC is present */
+#define DEFAULT_TEMP			37000
+
+struct qpnp_tm_chip {
+	struct regmap			*map;
+	struct thermal_zone_device	*tz_dev;
+	long				temp;
+	unsigned int			thresh;
+	unsigned int			stage;
+	unsigned int			prev_stage;
+	unsigned int			base;
+	struct iio_channel		*adc;
+};
+
+static int qpnp_tm_read(struct qpnp_tm_chip *chip, u16 addr, u8 *data)
+{
+	unsigned int val;
+	int ret;
+
+	ret = regmap_read(chip->map, chip->base + addr, &val);
+	if (ret < 0)
+		return ret;
+
+	*data = val;
+	return 0;
+}
+
+static int qpnp_tm_write(struct qpnp_tm_chip *chip, u16 addr, u8 data)
+{
+	return regmap_write(chip->map, chip->base + addr, data);
+}
+
+/*
+ * This function updates the internal temp value based on the
+ * current thermal stage and threshold as well as the previous stage
+ */
+static int qpnp_tm_update_temp_no_adc(struct qpnp_tm_chip *chip)
+{
+	unsigned int stage;
+	int ret;
+	u8 reg = 0;
+
+	ret = qpnp_tm_read(chip, QPNP_TM_REG_STATUS, &reg);
+	if (ret < 0)
+		return ret;
+
+	stage = reg & STATUS_STAGE_MASK;
+
+	if (stage > chip->stage) {
+		/* increasing stage, use lower bound */
+		chip->temp = (stage - 1) * TEMP_STAGE_STEP +
+			     chip->thresh * TEMP_THRESH_STEP +
+			     TEMP_STAGE_HYSTERESIS + TEMP_THRESH_MIN;
+	} else if (stage < chip->stage) {
+		/* decreasing stage, use upper bound */
+		chip->temp = stage * TEMP_STAGE_STEP +
+			     chip->thresh * TEMP_THRESH_STEP -
+			     TEMP_STAGE_HYSTERESIS + TEMP_THRESH_MIN;
+	}
+
+	chip->stage = stage;
+
+	return 0;
+}
+
+static int qpnp_tm_get_temp(void *data, long *temp)
+{
+	struct qpnp_tm_chip *chip = data;
+	int ret, mili_celsius;
+
+	if (!temp)
+		return -EINVAL;
+
+	if (IS_ERR(chip->adc)) {
+		ret = qpnp_tm_update_temp_no_adc(chip);
+		if (ret < 0)
+			return ret;
+	} else {
+		ret = iio_read_channel_processed(chip->adc, &mili_celsius);
+		if (ret < 0)
+			return ret;
+
+		chip->temp = mili_celsius;
+	}
+
+	*temp = chip->temp < 0 ? 0 : chip->temp;
+
+	return 0;
+}
+
+static const struct thermal_zone_of_device_ops qpnp_tm_sensor_ops = {
+	.get_temp = qpnp_tm_get_temp,
+};
+
+static irqreturn_t qpnp_tm_isr(int irq, void *data)
+{
+	struct qpnp_tm_chip *chip = data;
+
+	thermal_zone_device_update(chip->tz_dev);
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * This function initializes the internal temp value based on only the
+ * current thermal stage and threshold. Setup threshold control and
+ * disable shutdown override.
+ */
+static int qpnp_tm_init(struct qpnp_tm_chip *chip)
+{
+	int ret;
+	u8 reg;
+
+	chip->thresh = THRESH_MIN;
+	chip->temp = DEFAULT_TEMP;
+
+	ret = qpnp_tm_read(chip, QPNP_TM_REG_STATUS, &reg);
+	if (ret < 0)
+		return ret;
+
+	chip->stage = reg & STATUS_STAGE_MASK;
+
+	if (chip->stage)
+		chip->temp = chip->thresh * TEMP_THRESH_STEP +
+			     (chip->stage - 1) * TEMP_STAGE_STEP +
+			     TEMP_THRESH_MIN;
+
+	/*
+	 * Set threshold and disable software override of stage 2 and 3
+	 * shutdowns.
+	 */
+	reg = chip->thresh & SHUTDOWN_CTRL1_THRESHOLD_MASK;
+	ret = qpnp_tm_write(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, reg);
+	if (ret < 0)
+		return ret;
+
+	/* Enable the thermal alarm PMIC module in always-on mode. */
+	reg = ALARM_CTRL_FORCE_ENABLE;
+	ret = qpnp_tm_write(chip, QPNP_TM_REG_ALARM_CTRL, reg);
+
+	return ret;
+}
+
+static int qpnp_tm_probe(struct platform_device *pdev)
+{
+	struct qpnp_tm_chip *chip;
+	struct device_node *node;
+	u8 type, subtype;
+	u32 res[2];
+	int ret, irq;
+
+	node = pdev->dev.of_node;
+
+	chip = devm_kzalloc(&pdev->dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	dev_set_drvdata(&pdev->dev, chip);
+
+	chip->map = dev_get_regmap(pdev->dev.parent, NULL);
+	if (!chip->map)
+		return -ENXIO;
+
+	ret = of_property_read_u32_array(node, "reg", res, 2);
+	if (ret < 0)
+		return ret;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	/* ADC based measurements are optional */
+	chip->adc = iio_channel_get(&pdev->dev, "thermal");
+	if (PTR_ERR(chip->adc) == -EPROBE_DEFER)
+		return PTR_ERR(chip->adc);
+
+	chip->base = res[0];
+
+	ret = qpnp_tm_read(chip, QPNP_TM_REG_TYPE, &type);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "could not read type\n");
+		goto fail;
+	}
+
+	ret = qpnp_tm_read(chip, QPNP_TM_REG_SUBTYPE, &subtype);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "could not read subtype\n");
+		goto fail;
+	}
+
+	if (type != QPNP_TM_TYPE || subtype != QPNP_TM_SUBTYPE) {
+		dev_err(&pdev->dev, "invalid type 0x%02x or subtype 0x%02x\n",
+			type, subtype);
+		ret = -ENODEV;
+		goto fail;
+	}
+
+	ret = qpnp_tm_init(chip);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "init failed\n");
+		goto fail;
+	}
+
+	ret = devm_request_threaded_irq(&pdev->dev, irq, NULL, qpnp_tm_isr,
+					IRQF_ONESHOT, node->name, chip);
+	if (ret < 0)
+		goto fail;
+
+	chip->tz_dev = thermal_zone_of_sensor_register(&pdev->dev, 0, chip,
+							&qpnp_tm_sensor_ops);
+	if (IS_ERR(chip->tz_dev)) {
+		dev_err(&pdev->dev, "failed to register sensor\n");
+		ret = PTR_ERR(chip->tz_dev);
+		goto fail;
+	}
+
+	return 0;
+
+fail:
+	if (!IS_ERR(chip->adc))
+		iio_channel_release(chip->adc);
+
+	return ret;
+}
+
+static int qpnp_tm_remove(struct platform_device *pdev)
+{
+	struct qpnp_tm_chip *chip = dev_get_drvdata(&pdev->dev);
+
+	thermal_zone_of_sensor_unregister(&pdev->dev, chip->tz_dev);
+	if (!IS_ERR(chip->adc))
+		iio_channel_release(chip->adc);
+
+	return 0;
+}
+
+static const struct of_device_id qpnp_tm_match_table[] = {
+	{ .compatible = "qcom,spmi-temp-alarm" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, qpnp_tm_match_table);
+
+static struct platform_driver qpnp_tm_driver = {
+	.driver = {
+		.name = "spmi-temp-alarm",
+		.of_match_table = qpnp_tm_match_table,
+	},
+	.probe  = qpnp_tm_probe,
+	.remove = qpnp_tm_remove,
+};
+module_platform_driver(qpnp_tm_driver);
+
+MODULE_ALIAS("platform:spmi-temp-alarm");
+MODULE_DESCRIPTION("QPNP PMIC Temperature Alarm driver");
+MODULE_LICENSE("GPL v2");

drivers/thermal/samsung/exynos_tmu.c

@@ -97,6 +97,32 @@
 #define EXYNOS4412_MUX_ADDR_VALUE          6
 #define EXYNOS4412_MUX_ADDR_SHIFT          20
 
+/* Exynos5433 specific registers */
+#define EXYNOS5433_TMU_REG_CONTROL1		0x024
+#define EXYNOS5433_TMU_SAMPLING_INTERVAL	0x02c
+#define EXYNOS5433_TMU_COUNTER_VALUE0		0x030
+#define EXYNOS5433_TMU_COUNTER_VALUE1		0x034
+#define EXYNOS5433_TMU_REG_CURRENT_TEMP1	0x044
+#define EXYNOS5433_THD_TEMP_RISE3_0		0x050
+#define EXYNOS5433_THD_TEMP_RISE7_4		0x054
+#define EXYNOS5433_THD_TEMP_FALL3_0		0x060
+#define EXYNOS5433_THD_TEMP_FALL7_4		0x064
+#define EXYNOS5433_TMU_REG_INTEN		0x0c0
+#define EXYNOS5433_TMU_REG_INTPEND		0x0c8
+#define EXYNOS5433_TMU_EMUL_CON			0x110
+#define EXYNOS5433_TMU_PD_DET_EN		0x130
+
+#define EXYNOS5433_TRIMINFO_SENSOR_ID_SHIFT	16
+#define EXYNOS5433_TRIMINFO_CALIB_SEL_SHIFT	23
+#define EXYNOS5433_TRIMINFO_SENSOR_ID_MASK	\
+			(0xf << EXYNOS5433_TRIMINFO_SENSOR_ID_SHIFT)
+#define EXYNOS5433_TRIMINFO_CALIB_SEL_MASK	BIT(23)
+
+#define EXYNOS5433_TRIMINFO_ONE_POINT_TRIMMING	0
+#define EXYNOS5433_TRIMINFO_TWO_POINT_TRIMMING	1
+
+#define EXYNOS5433_PD_DET_EN			1
+
 /*exynos5440 specific registers*/
 #define EXYNOS5440_TMU_S0_7_TRIM		0x000
 #define EXYNOS5440_TMU_S0_7_CTRL		0x020
@@ -484,6 +510,101 @@ out:
 	return ret;
 }
 
+static int exynos5433_tmu_initialize(struct platform_device *pdev)
+{
+	struct exynos_tmu_data *data = platform_get_drvdata(pdev);
+	struct exynos_tmu_platform_data *pdata = data->pdata;
+	struct thermal_zone_device *tz = data->tzd;
+	unsigned int status, trim_info;
+	unsigned int rising_threshold = 0, falling_threshold = 0;
+	unsigned long temp, temp_hist;
+	int ret = 0, threshold_code, i, sensor_id, cal_type;
+
+	status = readb(data->base + EXYNOS_TMU_REG_STATUS);
+	if (!status) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	trim_info = readl(data->base + EXYNOS_TMU_REG_TRIMINFO);
+	sanitize_temp_error(data, trim_info);
+
+	/* Read the temperature sensor id */
+	sensor_id = (trim_info & EXYNOS5433_TRIMINFO_SENSOR_ID_MASK)
+				>> EXYNOS5433_TRIMINFO_SENSOR_ID_SHIFT;
+	dev_info(&pdev->dev, "Temperature sensor ID: 0x%x\n", sensor_id);
+
+	/* Read the calibration mode */
+	writel(trim_info, data->base + EXYNOS_TMU_REG_TRIMINFO);
+	cal_type = (trim_info & EXYNOS5433_TRIMINFO_CALIB_SEL_MASK)
+				>> EXYNOS5433_TRIMINFO_CALIB_SEL_SHIFT;
+
+	switch (cal_type) {
+	case EXYNOS5433_TRIMINFO_ONE_POINT_TRIMMING:
+		pdata->cal_type = TYPE_ONE_POINT_TRIMMING;
+		break;
+	case EXYNOS5433_TRIMINFO_TWO_POINT_TRIMMING:
+		pdata->cal_type = TYPE_TWO_POINT_TRIMMING;
+		break;
+	default:
+		pdata->cal_type = TYPE_ONE_POINT_TRIMMING;
+		break;
+	};
+
+	dev_info(&pdev->dev, "Calibration type is %d-point calibration\n",
+			cal_type ?  2 : 1);
+
+	/* Write temperature code for rising and falling threshold */
+	for (i = 0; i < of_thermal_get_ntrips(tz); i++) {
+		int rising_reg_offset, falling_reg_offset;
+		int j = 0;
+
+		switch (i) {
+		case 0:
+		case 1:
+		case 2:
+		case 3:
+			rising_reg_offset = EXYNOS5433_THD_TEMP_RISE3_0;
+			falling_reg_offset = EXYNOS5433_THD_TEMP_FALL3_0;
+			j = i;
+			break;
+		case 4:
+		case 5:
+		case 6:
+		case 7:
+			rising_reg_offset = EXYNOS5433_THD_TEMP_RISE7_4;
+			falling_reg_offset = EXYNOS5433_THD_TEMP_FALL7_4;
+			j = i - 4;
+			break;
+		default:
+			continue;
+		}
+
+		/* Write temperature code for rising threshold */
+		tz->ops->get_trip_temp(tz, i, &temp);
+		temp /= MCELSIUS;
+		threshold_code = temp_to_code(data, temp);
+
+		rising_threshold = readl(data->base + rising_reg_offset);
+		rising_threshold |= (threshold_code << j * 8);
+		writel(rising_threshold, data->base + rising_reg_offset);
+
+		/* Write temperature code for falling threshold */
+		tz->ops->get_trip_hyst(tz, i, &temp_hist);
+		temp_hist = temp - (temp_hist / MCELSIUS);
+		threshold_code = temp_to_code(data, temp_hist);
+
+		falling_threshold = readl(data->base + falling_reg_offset);
+		falling_threshold &= ~(0xff << j * 8);
+		falling_threshold |= (threshold_code << j * 8);
+		writel(falling_threshold, data->base + falling_reg_offset);
+	}
+
+	data->tmu_clear_irqs(data);
+out:
+	return ret;
+}
+
 static int exynos5440_tmu_initialize(struct platform_device *pdev)
 {
 	struct exynos_tmu_data *data = platform_get_drvdata(pdev);
@@ -643,6 +764,48 @@ static void exynos4210_tmu_control(struct platform_device *pdev, bool on)
 	writel(con, data->base + EXYNOS_TMU_REG_CONTROL);
 }
 
+static void exynos5433_tmu_control(struct platform_device *pdev, bool on)
+{
+	struct exynos_tmu_data *data = platform_get_drvdata(pdev);
+	struct thermal_zone_device *tz = data->tzd;
+	unsigned int con, interrupt_en, pd_det_en;
+
+	con = get_con_reg(data, readl(data->base + EXYNOS_TMU_REG_CONTROL));
+
+	if (on) {
+		con |= (1 << EXYNOS_TMU_CORE_EN_SHIFT);
+		interrupt_en =
+			(of_thermal_is_trip_valid(tz, 7)
+			<< EXYNOS7_TMU_INTEN_RISE7_SHIFT) |
+			(of_thermal_is_trip_valid(tz, 6)
+			<< EXYNOS7_TMU_INTEN_RISE6_SHIFT) |
+			(of_thermal_is_trip_valid(tz, 5)
+			<< EXYNOS7_TMU_INTEN_RISE5_SHIFT) |
+			(of_thermal_is_trip_valid(tz, 4)
+			<< EXYNOS7_TMU_INTEN_RISE4_SHIFT) |
+			(of_thermal_is_trip_valid(tz, 3)
+			<< EXYNOS7_TMU_INTEN_RISE3_SHIFT) |
+			(of_thermal_is_trip_valid(tz, 2)
+			<< EXYNOS7_TMU_INTEN_RISE2_SHIFT) |
+			(of_thermal_is_trip_valid(tz, 1)
+			<< EXYNOS7_TMU_INTEN_RISE1_SHIFT) |
+			(of_thermal_is_trip_valid(tz, 0)
+			<< EXYNOS7_TMU_INTEN_RISE0_SHIFT);
+
+		interrupt_en |=
+			interrupt_en << EXYNOS_TMU_INTEN_FALL0_SHIFT;
+	} else {
+		con &= ~(1 << EXYNOS_TMU_CORE_EN_SHIFT);
+		interrupt_en = 0; /* Disable all interrupts */
+	}
+
+	pd_det_en = on ? EXYNOS5433_PD_DET_EN : 0;
+
+	writel(pd_det_en, data->base + EXYNOS5433_TMU_PD_DET_EN);
+	writel(interrupt_en, data->base + EXYNOS5433_TMU_REG_INTEN);
+	writel(con, data->base + EXYNOS_TMU_REG_CONTROL);
+}
+
 static void exynos5440_tmu_control(struct platform_device *pdev, bool on)
 {
 	struct exynos_tmu_data *data = platform_get_drvdata(pdev);
@@ -770,6 +933,8 @@ static void exynos4412_tmu_set_emulation(struct exynos_tmu_data *data,
 
 	if (data->soc == SOC_ARCH_EXYNOS5260)
 		emul_con = EXYNOS5260_EMUL_CON;
+	if (data->soc == SOC_ARCH_EXYNOS5433)
+		emul_con = EXYNOS5433_TMU_EMUL_CON;
 	else if (data->soc == SOC_ARCH_EXYNOS7)
 		emul_con = EXYNOS7_TMU_REG_EMUL_CON;
 	else
@@ -882,6 +1047,9 @@ static void exynos4210_tmu_clear_irqs(struct exynos_tmu_data *data)
 	} else if (data->soc == SOC_ARCH_EXYNOS7) {
 		tmu_intstat = EXYNOS7_TMU_REG_INTPEND;
 		tmu_intclear = EXYNOS7_TMU_REG_INTPEND;
+	} else if (data->soc == SOC_ARCH_EXYNOS5433) {
+		tmu_intstat = EXYNOS5433_TMU_REG_INTPEND;
+		tmu_intclear = EXYNOS5433_TMU_REG_INTPEND;
 	} else {
 		tmu_intstat = EXYNOS_TMU_REG_INTSTAT;
 		tmu_intclear = EXYNOS_TMU_REG_INTCLEAR;
@@ -926,6 +1094,7 @@ static const struct of_device_id exynos_tmu_match[] = {
 	{ .compatible = "samsung,exynos5260-tmu", },
 	{ .compatible = "samsung,exynos5420-tmu", },
 	{ .compatible = "samsung,exynos5420-tmu-ext-triminfo", },
+	{ .compatible = "samsung,exynos5433-tmu", },
 	{ .compatible = "samsung,exynos5440-tmu", },
 	{ .compatible = "samsung,exynos7-tmu", },
 	{ /* sentinel */ },
@@ -949,6 +1118,8 @@ static int exynos_of_get_soc_type(struct device_node *np)
 	else if (of_device_is_compatible(np,
 					 "samsung,exynos5420-tmu-ext-triminfo"))
 		return SOC_ARCH_EXYNOS5420_TRIMINFO;
+	else if (of_device_is_compatible(np, "samsung,exynos5433-tmu"))
+		return SOC_ARCH_EXYNOS5433;
 	else if (of_device_is_compatible(np, "samsung,exynos5440-tmu"))
 		return SOC_ARCH_EXYNOS5440;
 	else if (of_device_is_compatible(np, "samsung,exynos7-tmu"))
@@ -1069,6 +1240,13 @@ static int exynos_map_dt_data(struct platform_device *pdev)
 		data->tmu_set_emulation = exynos4412_tmu_set_emulation;
 		data->tmu_clear_irqs = exynos4210_tmu_clear_irqs;
 		break;
+	case SOC_ARCH_EXYNOS5433:
+		data->tmu_initialize = exynos5433_tmu_initialize;
+		data->tmu_control = exynos5433_tmu_control;
+		data->tmu_read = exynos4412_tmu_read;
+		data->tmu_set_emulation = exynos4412_tmu_set_emulation;
+		data->tmu_clear_irqs = exynos4210_tmu_clear_irqs;
+		break;
 	case SOC_ARCH_EXYNOS5440:
 		data->tmu_initialize = exynos5440_tmu_initialize;
 		data->tmu_control = exynos5440_tmu_control;
@@ -1172,7 +1350,9 @@ static int exynos_tmu_probe(struct platform_device *pdev)
 		goto err_clk_sec;
 	}
 
-	if (data->soc == SOC_ARCH_EXYNOS7) {
+	switch (data->soc) {
+	case SOC_ARCH_EXYNOS5433:
+	case SOC_ARCH_EXYNOS7:
 		data->sclk = devm_clk_get(&pdev->dev, "tmu_sclk");
 		if (IS_ERR(data->sclk)) {
 			dev_err(&pdev->dev, "Failed to get sclk\n");
@@ -1184,7 +1364,10 @@ static int exynos_tmu_probe(struct platform_device *pdev)
 				goto err_clk;
 			}
 		}
-	}
+		break;
+	default:
+		break;
+	};
 
 	ret = exynos_tmu_initialize(pdev);
 	if (ret) {

drivers/thermal/samsung/exynos_tmu.h

@@ -33,6 +33,7 @@ enum soc_type {
 	SOC_ARCH_EXYNOS5260,
 	SOC_ARCH_EXYNOS5420,
 	SOC_ARCH_EXYNOS5420_TRIMINFO,
+	SOC_ARCH_EXYNOS5433,
 	SOC_ARCH_EXYNOS5440,
 	SOC_ARCH_EXYNOS7,
 };

drivers/thermal/thermal_core.c

@@ -75,6 +75,58 @@ static struct thermal_governor *__find_governor(const char *name)
 	return NULL;
 }
 
+/**
+ * bind_previous_governor() - bind the previous governor of the thermal zone
+ * @tz:		a valid pointer to a struct thermal_zone_device
+ * @failed_gov_name:	the name of the governor that failed to register
+ *
+ * Register the previous governor of the thermal zone after a new
+ * governor has failed to be bound.
+ */
+static void bind_previous_governor(struct thermal_zone_device *tz,
+				   const char *failed_gov_name)
+{
+	if (tz->governor && tz->governor->bind_to_tz) {
+		if (tz->governor->bind_to_tz(tz)) {
+			dev_err(&tz->device,
+				"governor %s failed to bind and the previous one (%s) failed to bind again, thermal zone %s has no governor\n",
+				failed_gov_name, tz->governor->name, tz->type);
+			tz->governor = NULL;
+		}
+	}
+}
+
+/**
+ * thermal_set_governor() - Switch to another governor
+ * @tz:		a valid pointer to a struct thermal_zone_device
+ * @new_gov:	pointer to the new governor
+ *
+ * Change the governor of thermal zone @tz.
+ *
+ * Return: 0 on success, an error if the new governor's bind_to_tz() failed.
+ */
+static int thermal_set_governor(struct thermal_zone_device *tz,
+				struct thermal_governor *new_gov)
+{
+	int ret = 0;
+
+	if (tz->governor && tz->governor->unbind_from_tz)
+		tz->governor->unbind_from_tz(tz);
+
+	if (new_gov && new_gov->bind_to_tz) {
+		ret = new_gov->bind_to_tz(tz);
+		if (ret) {
+			bind_previous_governor(tz, new_gov->name);
+
+			return ret;
+		}
+	}
+
+	tz->governor = new_gov;
+
+	return ret;
+}
+
 int thermal_register_governor(struct thermal_governor *governor)
 {
 	int err;
@@ -107,8 +159,15 @@ int thermal_register_governor(struct thermal_governor *governor)
 
 		name = pos->tzp->governor_name;
 
-		if (!strncasecmp(name, governor->name, THERMAL_NAME_LENGTH))
-			pos->governor = governor;
+		if (!strncasecmp(name, governor->name, THERMAL_NAME_LENGTH)) {
+			int ret;
+
+			ret = thermal_set_governor(pos, governor);
+			if (ret)
+				dev_err(&pos->device,
+					"Failed to set governor %s for thermal zone %s: %d\n",
+					governor->name, pos->type, ret);
+		}
 	}
 
 	mutex_unlock(&thermal_list_lock);
@@ -134,7 +193,7 @@ void thermal_unregister_governor(struct thermal_governor *governor)
 	list_for_each_entry(pos, &thermal_tz_list, node) {
 		if (!strncasecmp(pos->governor->name, governor->name,
 						THERMAL_NAME_LENGTH))
-			pos->governor = NULL;
+			thermal_set_governor(pos, NULL);
 	}
 
 	mutex_unlock(&thermal_list_lock);
@@ -218,7 +277,8 @@ static void print_bind_err_msg(struct thermal_zone_device *tz,
 
 static void __bind(struct thermal_zone_device *tz, int mask,
 			struct thermal_cooling_device *cdev,
-			unsigned long *limits)
+			unsigned long *limits,
+			unsigned int weight)
 {
 	int i, ret;
 
@@ -233,7 +293,8 @@ static void __bind(struct thermal_zone_device *tz, int mask,
 				upper = limits[i * 2 + 1];
 			}
 			ret = thermal_zone_bind_cooling_device(tz, i, cdev,
-							       upper, lower);
+							       upper, lower,
+							       weight);
 			if (ret)
 				print_bind_err_msg(tz, cdev, ret);
 		}
@@ -280,7 +341,8 @@ static void bind_cdev(struct thermal_cooling_device *cdev)
 				continue;
 			tzp->tbp[i].cdev = cdev;
 			__bind(pos, tzp->tbp[i].trip_mask, cdev,
-			       tzp->tbp[i].binding_limits);
+			       tzp->tbp[i].binding_limits,
+			       tzp->tbp[i].weight);
 		}
 	}
 
@@ -319,7 +381,8 @@ static void bind_tz(struct thermal_zone_device *tz)
 				continue;
 			tzp->tbp[i].cdev = pos;
 			__bind(tz, tzp->tbp[i].trip_mask, pos,
-			       tzp->tbp[i].binding_limits);
+			       tzp->tbp[i].binding_limits,
+			       tzp->tbp[i].weight);
 		}
 	}
 exit:
@@ -713,7 +776,8 @@ passive_store(struct device *dev, struct device_attribute *attr,
 				thermal_zone_bind_cooling_device(tz,
 						THERMAL_TRIPS_NONE, cdev,
 						THERMAL_NO_LIMIT,
-						THERMAL_NO_LIMIT);
+						THERMAL_NO_LIMIT,
+						THERMAL_WEIGHT_DEFAULT);
 		}
 		mutex_unlock(&thermal_list_lock);
 		if (!tz->passive_delay)
@@ -765,8 +829,9 @@ policy_store(struct device *dev, struct device_attribute *attr,
 	if (!gov)
 		goto exit;
 
-	tz->governor = gov;
-	ret = count;
+	ret = thermal_set_governor(tz, gov);
+	if (!ret)
+		ret = count;
 
 exit:
 	mutex_unlock(&tz->lock);
@@ -810,6 +875,158 @@ emul_temp_store(struct device *dev, struct device_attribute *attr,
 static DEVICE_ATTR(emul_temp, S_IWUSR, NULL, emul_temp_store);
 #endif/*CONFIG_THERMAL_EMULATION*/
 
+static ssize_t
+sustainable_power_show(struct device *dev, struct device_attribute *devattr,
+		       char *buf)
+{
+	struct thermal_zone_device *tz = to_thermal_zone(dev);
+
+	if (tz->tzp)
+		return sprintf(buf, "%u\n", tz->tzp->sustainable_power);
+	else
+		return -EIO;
+}
+
+static ssize_t
+sustainable_power_store(struct device *dev, struct device_attribute *devattr,
+			const char *buf, size_t count)
+{
+	struct thermal_zone_device *tz = to_thermal_zone(dev);
+	u32 sustainable_power;
+
+	if (!tz->tzp)
+		return -EIO;
+
+	if (kstrtou32(buf, 10, &sustainable_power))
+		return -EINVAL;
+
+	tz->tzp->sustainable_power = sustainable_power;
+
+	return count;
+}
+static DEVICE_ATTR(sustainable_power, S_IWUSR | S_IRUGO, sustainable_power_show,
+		sustainable_power_store);
+
+#define create_s32_tzp_attr(name)					\
+	static ssize_t							\
+	name##_show(struct device *dev, struct device_attribute *devattr, \
+		char *buf)						\
+	{								\
+	struct thermal_zone_device *tz = to_thermal_zone(dev);		\
+									\
+	if (tz->tzp)							\
+		return sprintf(buf, "%u\n", tz->tzp->name);		\
+	else								\
+		return -EIO;						\
+	}								\
+									\
+	static ssize_t							\
+	name##_store(struct device *dev, struct device_attribute *devattr, \
+		const char *buf, size_t count)				\
+	{								\
+		struct thermal_zone_device *tz = to_thermal_zone(dev);	\
+		s32 value;						\
+									\
+		if (!tz->tzp)						\
+			return -EIO;					\
+									\
+		if (kstrtos32(buf, 10, &value))				\
+			return -EINVAL;					\
+									\
+		tz->tzp->name = value;					\
+									\
+		return count;						\
+	}								\
+	static DEVICE_ATTR(name, S_IWUSR | S_IRUGO, name##_show, name##_store)
+
+create_s32_tzp_attr(k_po);
+create_s32_tzp_attr(k_pu);
+create_s32_tzp_attr(k_i);
+create_s32_tzp_attr(k_d);
+create_s32_tzp_attr(integral_cutoff);
+create_s32_tzp_attr(slope);
+create_s32_tzp_attr(offset);
+#undef create_s32_tzp_attr
+
+static struct device_attribute *dev_tzp_attrs[] = {
+	&dev_attr_sustainable_power,
+	&dev_attr_k_po,
+	&dev_attr_k_pu,
+	&dev_attr_k_i,
+	&dev_attr_k_d,
+	&dev_attr_integral_cutoff,
+	&dev_attr_slope,
+	&dev_attr_offset,
+};
+
+static int create_tzp_attrs(struct device *dev)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(dev_tzp_attrs); i++) {
+		int ret;
+		struct device_attribute *dev_attr = dev_tzp_attrs[i];
+
+		ret = device_create_file(dev, dev_attr);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * power_actor_get_max_power() - get the maximum power that a cdev can consume
+ * @cdev:	pointer to &thermal_cooling_device
+ * @tz:		a valid thermal zone device pointer
+ * @max_power:	pointer in which to store the maximum power
+ *
+ * Calculate the maximum power consumption in milliwats that the
+ * cooling device can currently consume and store it in @max_power.
+ *
+ * Return: 0 on success, -EINVAL if @cdev doesn't support the
+ * power_actor API or -E* on other error.
+ */
+int power_actor_get_max_power(struct thermal_cooling_device *cdev,
+			      struct thermal_zone_device *tz, u32 *max_power)
+{
+	if (!cdev_is_power_actor(cdev))
+		return -EINVAL;
+
+	return cdev->ops->state2power(cdev, tz, 0, max_power);
+}
+
+/**
+ * power_actor_set_power() - limit the maximum power that a cooling device can consume
+ * @cdev:	pointer to &thermal_cooling_device
+ * @instance:	thermal instance to update
+ * @power:	the power in milliwatts
+ *
+ * Set the cooling device to consume at most @power milliwatts.
+ *
+ * Return: 0 on success, -EINVAL if the cooling device does not
+ * implement the power actor API or -E* for other failures.
+ */
+int power_actor_set_power(struct thermal_cooling_device *cdev,
+			  struct thermal_instance *instance, u32 power)
+{
+	unsigned long state;
+	int ret;
+
+	if (!cdev_is_power_actor(cdev))
+		return -EINVAL;
+
+	ret = cdev->ops->power2state(cdev, instance->tz, power, &state);
+	if (ret)
+		return ret;
+
+	instance->target = state;
+	cdev->updated = false;
+	thermal_cdev_update(cdev);
+
+	return 0;
+}
+
 static DEVICE_ATTR(type, 0444, type_show, NULL);
 static DEVICE_ATTR(temp, 0444, temp_show, NULL);
 static DEVICE_ATTR(mode, 0644, mode_show, mode_store);
@@ -917,6 +1134,34 @@ static const struct attribute_group *cooling_device_attr_groups[] = {
 	NULL,
 };
 
+static ssize_t
+thermal_cooling_device_weight_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct thermal_instance *instance;
+
+	instance = container_of(attr, struct thermal_instance, weight_attr);
+
+	return sprintf(buf, "%d\n", instance->weight);
+}
+
+static ssize_t
+thermal_cooling_device_weight_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t count)
+{
+	struct thermal_instance *instance;
+	int ret, weight;
+
+	ret = kstrtoint(buf, 0, &weight);
+	if (ret)
+		return ret;
+
+	instance = container_of(attr, struct thermal_instance, weight_attr);
+	instance->weight = weight;
+
+	return count;
+}
 /* Device management */
 
 /**
@@ -931,6 +1176,9 @@ static const struct attribute_group *cooling_device_attr_groups[] = {
  * @lower:	the Minimum cooling state can be used for this trip point.
  *		THERMAL_NO_LIMIT means no lower limit,
  *		and the cooling device can be in cooling state 0.
+ * @weight:	The weight of the cooling device to be bound to the
+ *		thermal zone. Use THERMAL_WEIGHT_DEFAULT for the
+ *		default value
  *
  * This interface function bind a thermal cooling device to the certain trip
  * point of a thermal zone device.
@@ -941,7 +1189,8 @@ static const struct attribute_group *cooling_device_attr_groups[] = {
 int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz,
 				     int trip,
 				     struct thermal_cooling_device *cdev,
-				     unsigned long upper, unsigned long lower)
+				     unsigned long upper, unsigned long lower,
+				     unsigned int weight)
 {
 	struct thermal_instance *dev;
 	struct thermal_instance *pos;
@@ -986,6 +1235,7 @@ int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz,
 	dev->upper = upper;
 	dev->lower = lower;
 	dev->target = THERMAL_NO_TARGET;
+	dev->weight = weight;
 
 	result = get_idr(&tz->idr, &tz->lock, &dev->id);
 	if (result)
@@ -1006,6 +1256,16 @@ int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz,
 	if (result)
 		goto remove_symbol_link;
 
+	sprintf(dev->weight_attr_name, "cdev%d_weight", dev->id);
+	sysfs_attr_init(&dev->weight_attr.attr);
+	dev->weight_attr.attr.name = dev->weight_attr_name;
+	dev->weight_attr.attr.mode = S_IWUSR | S_IRUGO;
+	dev->weight_attr.show = thermal_cooling_device_weight_show;
+	dev->weight_attr.store = thermal_cooling_device_weight_store;
+	result = device_create_file(&tz->device, &dev->weight_attr);
+	if (result)
+		goto remove_trip_file;
+
 	mutex_lock(&tz->lock);
 	mutex_lock(&cdev->lock);
 	list_for_each_entry(pos, &tz->thermal_instances, tz_node)
@@ -1023,6 +1283,8 @@ int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz,
 	if (!result)
 		return 0;
 
+	device_remove_file(&tz->device, &dev->weight_attr);
+remove_trip_file:
 	device_remove_file(&tz->device, &dev->attr);
 remove_symbol_link:
 	sysfs_remove_link(&tz->device.kobj, dev->name);
@@ -1377,7 +1639,8 @@ static int create_trip_attrs(struct thermal_zone_device *tz, int mask)
 						tz->trip_temp_attrs[indx].name;
 		tz->trip_temp_attrs[indx].attr.attr.mode = S_IRUGO;
 		tz->trip_temp_attrs[indx].attr.show = trip_point_temp_show;
-		if (mask & (1 << indx)) {
+		if (IS_ENABLED(CONFIG_THERMAL_WRITABLE_TRIPS) &&
+		    mask & (1 << indx)) {
 			tz->trip_temp_attrs[indx].attr.attr.mode |= S_IWUSR;
 			tz->trip_temp_attrs[indx].attr.store =
 							trip_point_temp_store;
@@ -1454,7 +1717,7 @@ static void remove_trip_attrs(struct thermal_zone_device *tz)
 struct thermal_zone_device *thermal_zone_device_register(const char *type,
 	int trips, int mask, void *devdata,
 	struct thermal_zone_device_ops *ops,
-	const struct thermal_zone_params *tzp,
+	struct thermal_zone_params *tzp,
 	int passive_delay, int polling_delay)
 {
 	struct thermal_zone_device *tz;
@@ -1462,6 +1725,7 @@ struct thermal_zone_device *thermal_zone_device_register(const char *type,
 	int result;
 	int count;
 	int passive = 0;
+	struct thermal_governor *governor;
 
 	if (type && strlen(type) >= THERMAL_NAME_LENGTH)
 		return ERR_PTR(-EINVAL);
@@ -1548,13 +1812,24 @@ struct thermal_zone_device *thermal_zone_device_register(const char *type,
 	if (result)
 		goto unregister;
 
+	/* Add thermal zone params */
+	result = create_tzp_attrs(&tz->device);
+	if (result)
+		goto unregister;
+
 	/* Update 'this' zone's governor information */
 	mutex_lock(&thermal_governor_lock);
 
 	if (tz->tzp)
-		tz->governor = __find_governor(tz->tzp->governor_name);
+		governor = __find_governor(tz->tzp->governor_name);
 	else
-		tz->governor = def_governor;
+		governor = def_governor;
+
+	result = thermal_set_governor(tz, governor);
+	if (result) {
+		mutex_unlock(&thermal_governor_lock);
+		goto unregister;
+	}
 
 	mutex_unlock(&thermal_governor_lock);
 
@@ -1643,7 +1918,7 @@ void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 		device_remove_file(&tz->device, &dev_attr_mode);
 	device_remove_file(&tz->device, &dev_attr_policy);
 	remove_trip_attrs(tz);
-	tz->governor = NULL;
+	thermal_set_governor(tz, NULL);
 
 	thermal_remove_hwmon_sysfs(tz);
 	release_idr(&thermal_tz_idr, &thermal_idr_lock, tz->id);
@@ -1799,7 +2074,11 @@ static int __init thermal_register_governors(void)
 	if (result)
 		return result;
 
-	return thermal_gov_user_space_register();
+	result = thermal_gov_user_space_register();
+	if (result)
+		return result;
+
+	return thermal_gov_power_allocator_register();
 }
 
 static void thermal_unregister_governors(void)
@@ -1808,6 +2087,7 @@ static void thermal_unregister_governors(void)
 	thermal_gov_fair_share_unregister();
 	thermal_gov_bang_bang_unregister();
 	thermal_gov_user_space_unregister();
+	thermal_gov_power_allocator_unregister();
 }
 
 static int __init thermal_init(void)

drivers/thermal/thermal_core.h

@@ -46,8 +46,11 @@ struct thermal_instance {
 	unsigned long target;	/* expected cooling state */
 	char attr_name[THERMAL_NAME_LENGTH];
 	struct device_attribute attr;
+	char weight_attr_name[THERMAL_NAME_LENGTH];
+	struct device_attribute weight_attr;
 	struct list_head tz_node; /* node in tz->thermal_instances */
 	struct list_head cdev_node; /* node in cdev->thermal_instances */
+	unsigned int weight; /* The weight of the cooling device */
 };
 
 int thermal_register_governor(struct thermal_governor *);
@@ -85,6 +88,14 @@ static inline int thermal_gov_user_space_register(void) { return 0; }
 static inline void thermal_gov_user_space_unregister(void) {}
 #endif /* CONFIG_THERMAL_GOV_USER_SPACE */
 
+#ifdef CONFIG_THERMAL_GOV_POWER_ALLOCATOR
+int thermal_gov_power_allocator_register(void);
+void thermal_gov_power_allocator_unregister(void);
+#else
+static inline int thermal_gov_power_allocator_register(void) { return 0; }
+static inline void thermal_gov_power_allocator_unregister(void) {}
+#endif /* CONFIG_THERMAL_GOV_POWER_ALLOCATOR */
+
 /* device tree support */
 #ifdef CONFIG_THERMAL_OF
 int of_parse_thermal_zones(void);

drivers/thermal/ti-soc-thermal/ti-bandgap.c

@@ -43,6 +43,8 @@
 
 #include "ti-bandgap.h"
 
+static int ti_bandgap_force_single_read(struct ti_bandgap *bgp, int id);
+
 /***   Helper functions to access registers and their bitfields   ***/
 
 /**
@@ -103,19 +105,15 @@ do {								\
  */
 static int ti_bandgap_power(struct ti_bandgap *bgp, bool on)
 {
-	int i, ret = 0;
+	int i;
 
-	if (!TI_BANDGAP_HAS(bgp, POWER_SWITCH)) {
-		ret = -ENOTSUPP;
-		goto exit;
-	}
+	if (!TI_BANDGAP_HAS(bgp, POWER_SWITCH))
+		return -ENOTSUPP;
 
 	for (i = 0; i < bgp->conf->sensor_count; i++)
 		/* active on 0 */
 		RMW_BITS(bgp, i, temp_sensor_ctrl, bgap_tempsoff_mask, !on);
-
-exit:
-	return ret;
+	return 0;
 }
 
 /**
@@ -263,18 +261,13 @@ static
 int ti_bandgap_adc_to_mcelsius(struct ti_bandgap *bgp, int adc_val, int *t)
 {
 	const struct ti_bandgap_data *conf = bgp->conf;
-	int ret = 0;
 
 	/* look up for temperature in the table and return the temperature */
-	if (adc_val < conf->adc_start_val || adc_val > conf->adc_end_val) {
-		ret = -ERANGE;
-		goto exit;
-	}
+	if (adc_val < conf->adc_start_val || adc_val > conf->adc_end_val)
+		return -ERANGE;
 
 	*t = bgp->conf->conv_table[adc_val - conf->adc_start_val];
-
-exit:
-	return ret;
+	return 0;
 }
 
 /**
@@ -295,16 +288,14 @@ int ti_bandgap_mcelsius_to_adc(struct ti_bandgap *bgp, long temp, int *adc)
 {
 	const struct ti_bandgap_data *conf = bgp->conf;
 	const int *conv_table = bgp->conf->conv_table;
-	int high, low, mid, ret = 0;
+	int high, low, mid;
 
 	low = 0;
 	high = conf->adc_end_val - conf->adc_start_val;
 	mid = (high + low) / 2;
 
-	if (temp < conv_table[low] || temp > conv_table[high]) {
-		ret = -ERANGE;
-		goto exit;
-	}
+	if (temp < conv_table[low] || temp > conv_table[high])
+		return -ERANGE;
 
 	while (low < high) {
 		if (temp < conv_table[mid])
@@ -315,9 +306,7 @@ int ti_bandgap_mcelsius_to_adc(struct ti_bandgap *bgp, long temp, int *adc)
 	}
 
 	*adc = conf->adc_start_val + low;
-
-exit:
-	return ret;
+	return 0;
 }
 
 /**
@@ -343,13 +332,11 @@ int ti_bandgap_add_hyst(struct ti_bandgap *bgp, int adc_val, int hyst_val,
 	 */
 	ret = ti_bandgap_adc_to_mcelsius(bgp, adc_val, &temp);
 	if (ret < 0)
-		goto exit;
+		return ret;
 
 	temp += hyst_val;
 
 	ret = ti_bandgap_mcelsius_to_adc(bgp, temp, sum);
-
-exit:
 	return ret;
 }
 
@@ -468,22 +455,18 @@ exit:
  */
 static inline int ti_bandgap_validate(struct ti_bandgap *bgp, int id)
 {
-	int ret = 0;
-
 	if (!bgp || IS_ERR(bgp)) {
 		pr_err("%s: invalid bandgap pointer\n", __func__);
-		ret = -EINVAL;
-		goto exit;
+		return -EINVAL;
 	}
 
 	if ((id < 0) || (id >= bgp->conf->sensor_count)) {
 		dev_err(bgp->dev, "%s: sensor id out of range (%d)\n",
 			__func__, id);
-		ret = -ERANGE;
+		return -ERANGE;
 	}
 
-exit:
-	return ret;
+	return 0;
 }
 
 /**
@@ -511,12 +494,10 @@ static int _ti_bandgap_write_threshold(struct ti_bandgap *bgp, int id, int val,
 
 	ret = ti_bandgap_validate(bgp, id);
 	if (ret)
-		goto exit;
+		return ret;
 
-	if (!TI_BANDGAP_HAS(bgp, TALERT)) {
-		ret = -ENOTSUPP;
-		goto exit;
-	}
+	if (!TI_BANDGAP_HAS(bgp, TALERT))
+		return -ENOTSUPP;
 
 	ts_data = bgp->conf->sensors[id].ts_data;
 	tsr = bgp->conf->sensors[id].registers;
@@ -529,17 +510,15 @@ static int _ti_bandgap_write_threshold(struct ti_bandgap *bgp, int id, int val,
 	}
 
 	if (ret)
-		goto exit;
+		return ret;
 
 	ret = ti_bandgap_mcelsius_to_adc(bgp, val, &adc_val);
 	if (ret < 0)
-		goto exit;
+		return ret;
 
 	spin_lock(&bgp->lock);
 	ret = ti_bandgap_update_alert_threshold(bgp, id, adc_val, hot);
 	spin_unlock(&bgp->lock);
-
-exit:
 	return ret;
 }
 
@@ -582,7 +561,7 @@ static int _ti_bandgap_read_threshold(struct ti_bandgap *bgp, int id,
 
 	temp = ti_bandgap_readl(bgp, tsr->bgap_threshold);
 	temp = (temp & mask) >> __ffs(mask);
-	ret |= ti_bandgap_adc_to_mcelsius(bgp, temp, &temp);
+	ret = ti_bandgap_adc_to_mcelsius(bgp, temp, &temp);
 	if (ret) {
 		dev_err(bgp->dev, "failed to read thot\n");
 		ret = -EIO;
@@ -852,11 +831,17 @@ int ti_bandgap_read_temperature(struct ti_bandgap *bgp, int id,
 	if (ret)
 		return ret;
 
+	if (!TI_BANDGAP_HAS(bgp, MODE_CONFIG)) {
+		ret = ti_bandgap_force_single_read(bgp, id);
+		if (ret)
+			return ret;
+	}
+
 	spin_lock(&bgp->lock);
 	temp = ti_bandgap_read_temp(bgp, id);
 	spin_unlock(&bgp->lock);
 
-	ret |= ti_bandgap_adc_to_mcelsius(bgp, temp, &temp);
+	ret = ti_bandgap_adc_to_mcelsius(bgp, temp, &temp);
 	if (ret)
 		return -EIO;
 
@@ -917,7 +902,8 @@ void *ti_bandgap_get_sensor_data(struct ti_bandgap *bgp, int id)
 static int
 ti_bandgap_force_single_read(struct ti_bandgap *bgp, int id)
 {
-	u32 temp = 0, counter = 1000;
+	u32 counter = 1000;
+	struct temp_sensor_registers *tsr;
 
 	/* Select single conversion mode */
 	if (TI_BANDGAP_HAS(bgp, MODE_CONFIG))
@@ -925,16 +911,27 @@ ti_bandgap_force_single_read(struct ti_bandgap *bgp, int id)
 
 	/* Start of Conversion = 1 */
 	RMW_BITS(bgp, id, temp_sensor_ctrl, bgap_soc_mask, 1);
-	/* Wait until DTEMP is updated */
-	temp = ti_bandgap_read_temp(bgp, id);
 
-	while ((temp == 0) && --counter)
-		temp = ti_bandgap_read_temp(bgp, id);
-	/* REVISIT: Check correct condition for end of conversion */
+	/* Wait for EOCZ going up */
+	tsr = bgp->conf->sensors[id].registers;
+
+	while (--counter) {
+		if (ti_bandgap_readl(bgp, tsr->temp_sensor_ctrl) &
+		    tsr->bgap_eocz_mask)
+			break;
+	}
 
 	/* Start of Conversion = 0 */
 	RMW_BITS(bgp, id, temp_sensor_ctrl, bgap_soc_mask, 0);
 
+	/* Wait for EOCZ going down */
+	counter = 1000;
+	while (--counter) {
+		if (!(ti_bandgap_readl(bgp, tsr->temp_sensor_ctrl) &
+		      tsr->bgap_eocz_mask))
+			break;
+	}
+
 	return 0;
 }
 
@@ -1220,11 +1217,10 @@ int ti_bandgap_probe(struct platform_device *pdev)
 		goto free_irqs;
 	}
 
-	bgp->div_clk = clk_get(NULL,  bgp->conf->div_ck_name);
+	bgp->div_clk = clk_get(NULL, bgp->conf->div_ck_name);
 	ret = IS_ERR(bgp->div_clk);
 	if (ret) {
-		dev_err(&pdev->dev,
-			"failed to request div_ts_ck clock ref\n");
+		dev_err(&pdev->dev, "failed to request div_ts_ck clock ref\n");
 		ret = PTR_ERR(bgp->div_clk);
 		goto free_irqs;
 	}

drivers/thermal/ti-soc-thermal/ti-thermal-common.c

@@ -75,7 +75,7 @@ static inline int ti_thermal_hotspot_temperature(int t, int s, int c)
 }
 
 /* thermal zone ops */
-/* Get temperature callback function for thermal zone*/
+/* Get temperature callback function for thermal zone */
 static inline int __ti_thermal_get_temp(void *devdata, long *temp)
 {
 	struct thermal_zone_device *pcb_tz = NULL;
@@ -146,7 +146,8 @@ static int ti_thermal_bind(struct thermal_zone_device *thermal,
 	return thermal_zone_bind_cooling_device(thermal, 0, cdev,
 	/* bind with min and max states defined by cpu_cooling */
 						THERMAL_NO_LIMIT,
-						THERMAL_NO_LIMIT);
+						THERMAL_NO_LIMIT,
+						THERMAL_WEIGHT_DEFAULT);
 }
 
 /* Unbind callback functions for thermal zone */

drivers/thermal/x86_pkg_temp_thermal.c

@@ -68,7 +68,7 @@ struct phy_dev_entry {
 	struct thermal_zone_device *tzone;
 };
 
-static const struct thermal_zone_params pkg_temp_tz_params = {
+static struct thermal_zone_params pkg_temp_tz_params = {
 	.no_hwmon	= true,
 };
 

include/linux/cpu_cooling.h

@@ -28,6 +28,9 @@
 #include <linux/thermal.h>
 #include <linux/cpumask.h>
 
+typedef int (*get_static_t)(cpumask_t *cpumask, int interval,
+			    unsigned long voltage, u32 *power);
+
 #ifdef CONFIG_CPU_THERMAL
 /**
  * cpufreq_cooling_register - function to create cpufreq cooling device.
@@ -36,6 +39,10 @@
 struct thermal_cooling_device *
 cpufreq_cooling_register(const struct cpumask *clip_cpus);
 
+struct thermal_cooling_device *
+cpufreq_power_cooling_register(const struct cpumask *clip_cpus,
+			       u32 capacitance, get_static_t plat_static_func);
+
 /**
  * of_cpufreq_cooling_register - create cpufreq cooling device based on DT.
  * @np: a valid struct device_node to the cooling device device tree node.
@@ -45,6 +52,12 @@ cpufreq_cooling_register(const struct cpumask *clip_cpus);
 struct thermal_cooling_device *
 of_cpufreq_cooling_register(struct device_node *np,
 			    const struct cpumask *clip_cpus);
+
+struct thermal_cooling_device *
+of_cpufreq_power_cooling_register(struct device_node *np,
+				  const struct cpumask *clip_cpus,
+				  u32 capacitance,
+				  get_static_t plat_static_func);
 #else
 static inline struct thermal_cooling_device *
 of_cpufreq_cooling_register(struct device_node *np,
@@ -52,6 +65,15 @@ of_cpufreq_cooling_register(struct device_node *np,
 {
 	return ERR_PTR(-ENOSYS);
 }
+
+static inline struct thermal_cooling_device *
+of_cpufreq_power_cooling_register(struct device_node *np,
+				  const struct cpumask *clip_cpus,
+				  u32 capacitance,
+				  get_static_t plat_static_func)
+{
+	return NULL;
+}
 #endif
 
 /**
@@ -67,12 +89,29 @@ cpufreq_cooling_register(const struct cpumask *clip_cpus)
 {
 	return ERR_PTR(-ENOSYS);
 }
+static inline struct thermal_cooling_device *
+cpufreq_power_cooling_register(const struct cpumask *clip_cpus,
+			       u32 capacitance, get_static_t plat_static_func)
+{
+	return NULL;
+}
+
 static inline struct thermal_cooling_device *
 of_cpufreq_cooling_register(struct device_node *np,
 			    const struct cpumask *clip_cpus)
 {
 	return ERR_PTR(-ENOSYS);
 }
+
+static inline struct thermal_cooling_device *
+of_cpufreq_power_cooling_register(struct device_node *np,
+				  const struct cpumask *clip_cpus,
+				  u32 capacitance,
+				  get_static_t plat_static_func)
+{
+	return NULL;
+}
+
 static inline
 void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 {

include/linux/thermal.h

@@ -40,6 +40,9 @@
 /* No upper/lower limit requirement */
 #define THERMAL_NO_LIMIT	((u32)~0)
 
+/* Default weight of a bound cooling device */
+#define THERMAL_WEIGHT_DEFAULT 0
+
 /* Unit conversion macros */
 #define KELVIN_TO_CELSIUS(t)	(long)(((long)t-2732 >= 0) ?	\
 				((long)t-2732+5)/10 : ((long)t-2732-5)/10)
@@ -56,10 +59,13 @@
 #define DEFAULT_THERMAL_GOVERNOR       "fair_share"
 #elif defined(CONFIG_THERMAL_DEFAULT_GOV_USER_SPACE)
 #define DEFAULT_THERMAL_GOVERNOR       "user_space"
+#elif defined(CONFIG_THERMAL_DEFAULT_GOV_POWER_ALLOCATOR)
+#define DEFAULT_THERMAL_GOVERNOR       "power_allocator"
 #endif
 
 struct thermal_zone_device;
 struct thermal_cooling_device;
+struct thermal_instance;
 
 enum thermal_device_mode {
 	THERMAL_DEVICE_DISABLED = 0,
@@ -113,6 +119,12 @@ struct thermal_cooling_device_ops {
 	int (*get_max_state) (struct thermal_cooling_device *, unsigned long *);
 	int (*get_cur_state) (struct thermal_cooling_device *, unsigned long *);
 	int (*set_cur_state) (struct thermal_cooling_device *, unsigned long);
+	int (*get_requested_power)(struct thermal_cooling_device *,
+				   struct thermal_zone_device *, u32 *);
+	int (*state2power)(struct thermal_cooling_device *,
+			   struct thermal_zone_device *, unsigned long, u32 *);
+	int (*power2state)(struct thermal_cooling_device *,
+			   struct thermal_zone_device *, u32, unsigned long *);
 };
 
 struct thermal_cooling_device {
@@ -144,8 +156,7 @@ struct thermal_attr {
  * @devdata:	private pointer for device private data
  * @trips:	number of trip points the thermal zone supports
  * @passive_delay:	number of milliseconds to wait between polls when
- *			performing passive cooling.  Currenty only used by the
- *			step-wise governor
+ *			performing passive cooling.
  * @polling_delay:	number of milliseconds to wait between polls when
  *			checking whether trip points have been crossed (0 for
  *			interrupt driven systems)
@@ -155,13 +166,13 @@ struct thermal_attr {
  * @last_temperature:	previous temperature read
  * @emul_temperature:	emulated temperature when using CONFIG_THERMAL_EMULATION
  * @passive:		1 if you've crossed a passive trip point, 0 otherwise.
- *			Currenty only used by the step-wise governor.
  * @forced_passive:	If > 0, temperature at which to switch on all ACPI
  *			processor cooling devices.  Currently only used by the
  *			step-wise governor.
  * @ops:	operations this &thermal_zone_device supports
  * @tzp:	thermal zone parameters
  * @governor:	pointer to the governor for this thermal zone
+ * @governor_data:	private pointer for governor data
  * @thermal_instances:	list of &struct thermal_instance of this thermal zone
  * @idr:	&struct idr to generate unique id for this zone's cooling
  *		devices
@@ -186,8 +197,9 @@ struct thermal_zone_device {
 	int passive;
 	unsigned int forced_passive;
 	struct thermal_zone_device_ops *ops;
-	const struct thermal_zone_params *tzp;
+	struct thermal_zone_params *tzp;
 	struct thermal_governor *governor;
+	void *governor_data;
 	struct list_head thermal_instances;
 	struct idr idr;
 	struct mutex lock;
@@ -198,12 +210,19 @@ struct thermal_zone_device {
 /**
  * struct thermal_governor - structure that holds thermal governor information
  * @name:	name of the governor
+ * @bind_to_tz: callback called when binding to a thermal zone.  If it
+ *		returns 0, the governor is bound to the thermal zone,
+ *		otherwise it fails.
+ * @unbind_from_tz:	callback called when a governor is unbound from a
+ *			thermal zone.
  * @throttle:	callback called for every trip point even if temperature is
  *		below the trip point temperature
  * @governor_list:	node in thermal_governor_list (in thermal_core.c)
  */
 struct thermal_governor {
 	char name[THERMAL_NAME_LENGTH];
+	int (*bind_to_tz)(struct thermal_zone_device *tz);
+	void (*unbind_from_tz)(struct thermal_zone_device *tz);
 	int (*throttle)(struct thermal_zone_device *tz, int trip);
 	struct list_head	governor_list;
 };
@@ -214,9 +233,12 @@ struct thermal_bind_params {
 
 	/*
 	 * This is a measure of 'how effectively these devices can
-	 * cool 'this' thermal zone. The shall be determined by platform
-	 * characterization. This is on a 'percentage' scale.
-	 * See Documentation/thermal/sysfs-api.txt for more information.
+	 * cool 'this' thermal zone. It shall be determined by
+	 * platform characterization. This value is relative to the
+	 * rest of the weights so a cooling device whose weight is
+	 * double that of another cooling device is twice as
+	 * effective. See Documentation/thermal/sysfs-api.txt for more
+	 * information.
 	 */
 	int weight;
 
@@ -253,6 +275,44 @@ struct thermal_zone_params {
 
 	int num_tbps;	/* Number of tbp entries */
 	struct thermal_bind_params *tbp;
+
+	/*
+	 * Sustainable power (heat) that this thermal zone can dissipate in
+	 * mW
+	 */
+	u32 sustainable_power;
+
+	/*
+	 * Proportional parameter of the PID controller when
+	 * overshooting (i.e., when temperature is below the target)
+	 */
+	s32 k_po;
+
+	/*
+	 * Proportional parameter of the PID controller when
+	 * undershooting
+	 */
+	s32 k_pu;
+
+	/* Integral parameter of the PID controller */
+	s32 k_i;
+
+	/* Derivative parameter of the PID controller */
+	s32 k_d;
+
+	/* threshold below which the error is no longer accumulated */
+	s32 integral_cutoff;
+
+	/*
+	 * @slope:	slope of a linear temperature adjustment curve.
+	 * 		Used by thermal zone drivers.
+	 */
+	int slope;
+	/*
+	 * @offset:	offset of a linear temperature adjustment curve.
+	 * 		Used by thermal zone drivers (default 0).
+	 */
+	int offset;
 };
 
 struct thermal_genl_event {
@@ -316,14 +376,25 @@ void thermal_zone_of_sensor_unregister(struct device *dev,
 #endif
 
 #if IS_ENABLED(CONFIG_THERMAL)
+static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev)
+{
+	return cdev->ops->get_requested_power && cdev->ops->state2power &&
+		cdev->ops->power2state;
+}
+
+int power_actor_get_max_power(struct thermal_cooling_device *,
+			      struct thermal_zone_device *tz, u32 *max_power);
+int power_actor_set_power(struct thermal_cooling_device *,
+			  struct thermal_instance *, u32);
 struct thermal_zone_device *thermal_zone_device_register(const char *, int, int,
 		void *, struct thermal_zone_device_ops *,
-		const struct thermal_zone_params *, int, int);
+		struct thermal_zone_params *, int, int);
 void thermal_zone_device_unregister(struct thermal_zone_device *);
 
 int thermal_zone_bind_cooling_device(struct thermal_zone_device *, int,
 				     struct thermal_cooling_device *,
-				     unsigned long, unsigned long);
+				     unsigned long, unsigned long,
+				     unsigned int);
 int thermal_zone_unbind_cooling_device(struct thermal_zone_device *, int,
 				       struct thermal_cooling_device *);
 void thermal_zone_device_update(struct thermal_zone_device *);
@@ -343,6 +414,14 @@ struct thermal_instance *get_thermal_instance(struct thermal_zone_device *,
 void thermal_cdev_update(struct thermal_cooling_device *);
 void thermal_notify_framework(struct thermal_zone_device *, int);
 #else
+static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev)
+{ return false; }
+static inline int power_actor_get_max_power(struct thermal_cooling_device *cdev,
+			      struct thermal_zone_device *tz, u32 *max_power)
+{ return 0; }
+static inline int power_actor_set_power(struct thermal_cooling_device *cdev,
+			  struct thermal_instance *tz, u32 power)
+{ return 0; }
 static inline struct thermal_zone_device *thermal_zone_device_register(
 	const char *type, int trips, int mask, void *devdata,
 	struct thermal_zone_device_ops *ops,

include/trace/events/thermal.h

@@ -77,6 +77,64 @@ TRACE_EVENT(thermal_zone_trip,
 		__entry->trip_type)
 );
 
+TRACE_EVENT(thermal_power_cpu_get_power,
+	TP_PROTO(const struct cpumask *cpus, unsigned long freq, u32 *load,
+		size_t load_len, u32 dynamic_power, u32 static_power),
+
+	TP_ARGS(cpus, freq, load, load_len, dynamic_power, static_power),
+
+	TP_STRUCT__entry(
+		__bitmask(cpumask, num_possible_cpus())
+		__field(unsigned long, freq          )
+		__dynamic_array(u32,   load, load_len)
+		__field(size_t,        load_len      )
+		__field(u32,           dynamic_power )
+		__field(u32,           static_power  )
+	),
+
+	TP_fast_assign(
+		__assign_bitmask(cpumask, cpumask_bits(cpus),
+				num_possible_cpus());
+		__entry->freq = freq;
+		memcpy(__get_dynamic_array(load), load,
+			load_len * sizeof(*load));
+		__entry->load_len = load_len;
+		__entry->dynamic_power = dynamic_power;
+		__entry->static_power = static_power;
+	),
+
+	TP_printk("cpus=%s freq=%lu load={%s} dynamic_power=%d static_power=%d",
+		__get_bitmask(cpumask), __entry->freq,
+		__print_array(__get_dynamic_array(load), __entry->load_len, 4),
+		__entry->dynamic_power, __entry->static_power)
+);
+
+TRACE_EVENT(thermal_power_cpu_limit,
+	TP_PROTO(const struct cpumask *cpus, unsigned int freq,
+		unsigned long cdev_state, u32 power),
+
+	TP_ARGS(cpus, freq, cdev_state, power),
+
+	TP_STRUCT__entry(
+		__bitmask(cpumask, num_possible_cpus())
+		__field(unsigned int,  freq      )
+		__field(unsigned long, cdev_state)
+		__field(u32,           power     )
+	),
+
+	TP_fast_assign(
+		__assign_bitmask(cpumask, cpumask_bits(cpus),
+				num_possible_cpus());
+		__entry->freq = freq;
+		__entry->cdev_state = cdev_state;
+		__entry->power = power;
+	),
+
+	TP_printk("cpus=%s freq=%u cdev_state=%lu power=%u",
+		__get_bitmask(cpumask), __entry->freq, __entry->cdev_state,
+		__entry->power)
+);
+
 #endif /* _TRACE_THERMAL_H */
 
 /* This part must be outside protection */

include/trace/events/thermal_power_allocator.h

@@ -0,0 +1,87 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM thermal_power_allocator
+
+#if !defined(_TRACE_THERMAL_POWER_ALLOCATOR_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_THERMAL_POWER_ALLOCATOR_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(thermal_power_allocator,
+	TP_PROTO(struct thermal_zone_device *tz, u32 *req_power,
+		 u32 total_req_power, u32 *granted_power,
+		 u32 total_granted_power, size_t num_actors,
+		 u32 power_range, u32 max_allocatable_power,
+		 unsigned long current_temp, s32 delta_temp),
+	TP_ARGS(tz, req_power, total_req_power, granted_power,
+		total_granted_power, num_actors, power_range,
+		max_allocatable_power, current_temp, delta_temp),
+	TP_STRUCT__entry(
+		__field(int,           tz_id          )
+		__dynamic_array(u32,   req_power, num_actors    )
+		__field(u32,           total_req_power          )
+		__dynamic_array(u32,   granted_power, num_actors)
+		__field(u32,           total_granted_power      )
+		__field(size_t,        num_actors               )
+		__field(u32,           power_range              )
+		__field(u32,           max_allocatable_power    )
+		__field(unsigned long, current_temp             )
+		__field(s32,           delta_temp               )
+	),
+	TP_fast_assign(
+		__entry->tz_id = tz->id;
+		memcpy(__get_dynamic_array(req_power), req_power,
+			num_actors * sizeof(*req_power));
+		__entry->total_req_power = total_req_power;
+		memcpy(__get_dynamic_array(granted_power), granted_power,
+			num_actors * sizeof(*granted_power));
+		__entry->total_granted_power = total_granted_power;
+		__entry->num_actors = num_actors;
+		__entry->power_range = power_range;
+		__entry->max_allocatable_power = max_allocatable_power;
+		__entry->current_temp = current_temp;
+		__entry->delta_temp = delta_temp;
+	),
+
+	TP_printk("thermal_zone_id=%d req_power={%s} total_req_power=%u granted_power={%s} total_granted_power=%u power_range=%u max_allocatable_power=%u current_temperature=%lu delta_temperature=%d",
+		__entry->tz_id,
+		__print_array(__get_dynamic_array(req_power),
+                              __entry->num_actors, 4),
+		__entry->total_req_power,
+		__print_array(__get_dynamic_array(granted_power),
+                              __entry->num_actors, 4),
+		__entry->total_granted_power, __entry->power_range,
+		__entry->max_allocatable_power, __entry->current_temp,
+		__entry->delta_temp)
+);
+
+TRACE_EVENT(thermal_power_allocator_pid,
+	TP_PROTO(struct thermal_zone_device *tz, s32 err, s32 err_integral,
+		 s64 p, s64 i, s64 d, s32 output),
+	TP_ARGS(tz, err, err_integral, p, i, d, output),
+	TP_STRUCT__entry(
+		__field(int, tz_id       )
+		__field(s32, err         )
+		__field(s32, err_integral)
+		__field(s64, p           )
+		__field(s64, i           )
+		__field(s64, d           )
+		__field(s32, output      )
+	),
+	TP_fast_assign(
+		__entry->tz_id = tz->id;
+		__entry->err = err;
+		__entry->err_integral = err_integral;
+		__entry->p = p;
+		__entry->i = i;
+		__entry->d = d;
+		__entry->output = output;
+	),
+
+	TP_printk("thermal_zone_id=%d err=%d err_integral=%d p=%lld i=%lld d=%lld output=%d",
+		  __entry->tz_id, __entry->err, __entry->err_integral,
+		  __entry->p, __entry->i, __entry->d, __entry->output)
+);
+#endif /* _TRACE_THERMAL_POWER_ALLOCATOR_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>