Re: [RFC PATCH v5 09/10] thermal: add trace events to the power allocator governor

From: Steven Rostedt
Date: Thu Jul 10 2014 - 11:44:59 EST

On Thu, 10 Jul 2014 15:18:47 +0100
"Javi Merino" <javi.merino@xxxxxxx> wrote:

> Add trace events for the power allocator governor and the power actor
> interface of the cpu cooling device.
>
> Cc: Zhang Rui <rui.zhang@xxxxxxxxx>
> Cc: Eduardo Valentin <edubezval@xxxxxxxxx>
> Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
> Cc: Frederic Weisbecker <fweisbec@xxxxxxxxx>
> Cc: Ingo Molnar <mingo@xxxxxxxxxx>
> Signed-off-by: Javi Merino <javi.merino@xxxxxxx>
> ---
> drivers/thermal/cpu_actor.c | 17 ++-
> drivers/thermal/power_allocator.c | 22 +++-
> include/trace/events/thermal_power_allocator.h | 138 +++++++++++++++++++++++++
> 3 files changed, 173 insertions(+), 4 deletions(-)
> create mode 100644 include/trace/events/thermal_power_allocator.h
>
> diff --git a/drivers/thermal/cpu_actor.c b/drivers/thermal/cpu_actor.c
> index 45ea4fa92ea0..b5ed2e80e288 100644
> --- a/drivers/thermal/cpu_actor.c
> +++ b/drivers/thermal/cpu_actor.c
> @@ -28,6 +28,8 @@
> #include <linux/printk.h>
> #include <linux/slab.h>
>
> +#include <trace/events/thermal_power_allocator.h>
> +
> /**
> * struct power_table - frequency to power conversion
> * @frequency: frequency in KHz
> @@ -184,11 +186,12 @@ static u32 get_static_power(struct cpu_actor *cpu_actor,
> */
> static u32 get_dynamic_power(struct cpu_actor *cpu_actor, unsigned long freq)
> {
> - int cpu;
> - u32 power = 0, raw_cpu_power, total_load = 0;
> + int i, cpu;
> + u32 power = 0, raw_cpu_power, total_load = 0, load_cpu[NR_CPUS];

When NR_CPUS == 1024, you just killed the stack, as you added 4K to it.
We upped the stack recently to 16k, but still.

>
> raw_cpu_power = cpu_freq_to_power(cpu_actor, freq);
>
> + i = 0;
> for_each_cpu(cpu, &cpu_actor->cpumask) {
> u32 load;
>
> @@ -198,8 +201,15 @@ static u32 get_dynamic_power(struct cpu_actor *cpu_actor, unsigned long freq)
> load = get_load(cpu_actor, cpu);
> power += (raw_cpu_power * load) / 100;
> total_load += load;
> + load_cpu[i] = load;
> +
> + i++;
> }
>
> + trace_thermal_power_actor_cpu_get_dyn_power(&cpu_actor->cpumask, freq,
> + raw_cpu_power, load_cpu, i,
> + power);

How many CPUs are you saving load_cpu on? A trace event can't be bigger
than a page. And the data is actually a little less than that with the
required headers.

-- Steve

> +
> cpu_actor->last_load = total_load;
>
> return power;
> @@ -296,6 +306,9 @@ static int cpu_set_power(struct power_actor *actor,
> return -EINVAL;
> }
>
> + trace_thermal_power_actor_cpu_limit(&cpu_actor->cpumask, target_freq,
> + cdev_state, power);
> +
> return cdev->ops->set_cur_state(cdev, cdev_state);
> }
>
> diff --git a/drivers/thermal/power_allocator.c b/drivers/thermal/power_allocator.c
> index eb1797cd859b..e6793d6d1288 100644
> --- a/drivers/thermal/power_allocator.c
> +++ b/drivers/thermal/power_allocator.c
> @@ -20,6 +20,9 @@
> #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 8
> @@ -133,7 +136,14 @@ 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(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;
> }
>
> /**
> @@ -214,7 +224,7 @@ static int allocate_power(struct thermal_zone_device *tz,
> struct power_actor *actor;
> u32 *req_power, *max_power, *granted_power;
> u32 total_req_power, max_allocatable_power;
> - u32 power_range;
> + u32 total_granted_power, power_range;
> int i, num_actors, ret = 0;
>
> mutex_lock(&tz->lock);
> @@ -265,12 +275,20 @@ 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);
>
> + total_granted_power = 0;
> i = 0;
> list_for_each_entry_rcu(actor, &actor_list, actor_node) {
> actor->ops->set_power(actor, tz, granted_power[i]);
> + total_granted_power += granted_power[i];
> +
> i++;
> }
>
> + trace_thermal_power_allocator(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, granted_power);
> free_max_power:
> devm_kfree(&tz->device, max_power);
> diff --git a/include/trace/events/thermal_power_allocator.h b/include/trace/events/thermal_power_allocator.h
> new file mode 100644
> index 000000000000..9140cec55c63
> --- /dev/null
> +++ b/include/trace/events/thermal_power_allocator.h
> @@ -0,0 +1,138 @@
> +#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(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(req_power, total_req_power, granted_power, total_granted_power,
> + num_actors, power_range, max_allocatable_power, current_temp,
> + delta_temp),
> + TP_STRUCT__entry(
> + __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(
> + 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("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",
> + __print_u32_array(__get_dynamic_array(req_power),
> + __entry->num_actors),
> + __entry->total_req_power,
> + __print_u32_array(__get_dynamic_array(granted_power),
> + __entry->num_actors),
> + __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(s32 err, s32 err_integral, s64 p, s64 i, s64 d, s32 output),
> + TP_ARGS(err, err_integral, p, i, d, output),
> + TP_STRUCT__entry(
> + __field(s32, err )
> + __field(s32, err_integral)
> + __field(s64, p )
> + __field(s64, i )
> + __field(s64, d )
> + __field(s32, output )
> + ),
> + TP_fast_assign(
> + __entry->err = err;
> + __entry->err_integral = err_integral;
> + __entry->p = p;
> + __entry->i = i;
> + __entry->d = d;
> + __entry->output = output;
> + ),
> +
> + TP_printk("err=%d err_integral=%d p=%lld i=%lld d=%lld output=%d",
> + __entry->err, __entry->err_integral,
> + __entry->p, __entry->i, __entry->d, __entry->output)
> +);
> +
> +TRACE_EVENT(thermal_power_actor_cpu_get_dyn_power,
> + TP_PROTO(const struct cpumask *cpus, unsigned long freq,
> + u32 raw_cpu_power, u32 *load, size_t load_len, u32 power),
> +
> + TP_ARGS(cpus, freq, raw_cpu_power, load, load_len, power),
> +
> + TP_STRUCT__entry(
> + __bitmask(cpumask, num_possible_cpus())
> + __field(unsigned long, freq )
> + __field(u32, raw_cpu_power )
> + __dynamic_array(u32, load, load_len)
> + __field(size_t, load_len )
> + __field(u32, power )
> + ),
> +
> + TP_fast_assign(
> + __assign_bitmask(cpumask, cpumask_bits(cpus),
> + num_possible_cpus());
> + __entry->freq = freq;
> + __entry->raw_cpu_power = raw_cpu_power;
> + memcpy(__get_dynamic_array(load), load,
> + load_len * sizeof(*load));
> + __entry->load_len = load_len;
> + __entry->power = power;
> + ),
> +
> + TP_printk("cpus=%s freq=%lu raw_cpu_power=%d load={%s} power=%d",
> + __get_bitmask(cpumask), __entry->freq, __entry->raw_cpu_power,
> + __print_u32_array(__get_dynamic_array(load), __entry->load_len),
> + __entry->power)
> +);
> +
> +TRACE_EVENT(thermal_power_actor_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_POWER_ALLOCATOR_H */
> +
> +/* This part must be outside protection */
> +#include <trace/define_trace.h>

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/