Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux

Pull thermal management updates from Zhang Rui:
 "Specifics:

   - enhance Thermal Framework with several new capabilities:

       * use power estimates
       * compute weights with relative integers instead of percentages
       * allow governors to have private data in thermal zones
       * export thermal zone parameters through sysfs

     Thanks to the ARM thermal team (Javi, Punit, KP).

   - introduce a new thermal governor: power allocator.  First in kernel
     closed loop PI(D) controller for thermal control.  Thanks to ARM
     thermal team.

   - enhance OF thermal to allow thermal zones to have sustainable power
     HW specification.  Thanks to Punit.

   - introduce thermal driver for Intel Quark SoC x1000platform.  Thanks
     to Ong, Boon Leong.

   - introduce QPNP PMIC temperature alarm driver.  Thanks to Ivan T. I.

   - introduce thermal driver for Hisilicon hi6220.  Thanks to
     kongxinwei.

   - enhance Exynos thermal driver to handle Exynos5433 TMU.  Thanks to
     Chanwoo C.

   - TI thermal driver now has a better implementation for EOCZ bit.
     From Pavel M.

   - add id for Skylake processors in int340x processor thermal driver.

   - a couple of small fixes and cleanups."

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux: (36 commits)
  thermal: hisilicon: add new hisilicon thermal sensor driver
  dt-bindings: Document the hi6220 thermal sensor bindings
  thermal: of-thermal: add support for reading coefficients property
  thermal: support slope and offset coefficients
  thermal: power_allocator: round the division when divvying up power
  thermal: exynos: Add the support for Exynos5433 TMU
  thermal: cpu_cooling: Fix power calculation when CPUs are offline
  thermal: cpu_cooling: Remove cpu_dev update on policy CPU update
  thermal: export thermal_zone_parameters to sysfs
  thermal: cpu_cooling: Check memory allocation of power_table
  ti-soc-thermal: request temperature periodically if hw can't do that itself
  ti-soc-thermal: implement eocz bit to make driver useful on omap3
  cleanup ti-soc-thermal
  thermal: remove stale THERMAL_POWER_ACTOR select
  thermal: Default OF created trip points to writable
  thermal: core: Add Kconfig option to enable writable trips
  thermal: x86_pkg_temp: drop const for thermal_zone_parameters
  of: thermal: Introduce sustainable power for a thermal zone
  thermal: add trace events to the power allocator governor
  thermal: introduce the Power Allocator governor
  ...

4 files changed, 272 insertions, 9 deletions

diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h
index bd955270d5aa..c156f5082758 100644
--- a/include/linux/cpu_cooling.h
+++ b/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
 
 /**
@@ -68,11 +90,28 @@ 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)
 {
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 5eac316490ea..037e9df2f610 100644
--- a/include/linux/thermal.h
+++ b/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,
diff --git a/include/trace/events/thermal.h b/include/trace/events/thermal.h
index 0f4f95d63c03..8b1f80682b80 100644
--- a/include/trace/events/thermal.h
+++ b/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 */
diff --git a/include/trace/events/thermal_power_allocator.h b/include/trace/events/thermal_power_allocator.h
new file mode 100644
index 000000000000..12e1321c4e0c
--- /dev/null
+++ b/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>