thermal: add trace events to the power allocator governor

Add trace events for the power allocator governor and the power actor
interface of the cpu cooling device.

Cc: Zhang Rui <rui.zhang@intel.com>
Cc: Eduardo Valentin <edubezval@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Javi Merino <javi.merino@arm.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>

drivers/thermal/cpu_cooling.c

@@ -31,6 +31,8 @@
 #include <linux/cpu.h>
 #include <linux/cpu_cooling.h>
 
+#include <trace/events/thermal.h>
+
 /*
  * Cooling state <-> CPUFreq frequency
  *
@@ -588,12 +590,20 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev,
 				       u32 *power)
 {
 	unsigned long freq;
-	int cpu, ret;
+	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;
 
 	freq = cpufreq_quick_get(cpumask_any(&cpufreq_device->allowed_cpus));
 
+	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;
 
@@ -603,14 +613,29 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev,
 			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 (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;
@@ -718,6 +743,8 @@ static int cpufreq_power2state(struct thermal_cooling_device *cdev,
 		return -EINVAL;
 	}
 
+	trace_thermal_power_cpu_limit(&cpufreq_device->allowed_cpus,
+				      target_freq, *state, power);
 	return 0;
 }
 

drivers/thermal/power_allocator.c

@@ -19,6 +19,9 @@
 #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
@@ -138,7 +141,14 @@ static u32 pid_controller(struct thermal_zone_device *tz,
 	/* feed-forward the known sustainable dissipatable power */
 	power_range = tz->tzp->sustainable_power + frac_to_int(power_range);
 
-	return clamp(power_range, (s64)0, (s64)max_allocatable_power);
+	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;
 }
 
 /**
@@ -219,7 +229,7 @@ static int allocate_power(struct thermal_zone_device *tz,
 	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 power_range;
+	u32 total_granted_power, power_range;
 	int i, num_actors, total_weight, ret = 0;
 	int trip_max_desired_temperature = params->trip_max_desired_temperature;
 
@@ -295,6 +305,7 @@ static int allocate_power(struct thermal_zone_device *tz,
 	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)
@@ -305,10 +316,17 @@ static int allocate_power(struct thermal_zone_device *tz,
 
 		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);

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>