Re: [PATCH 1/3] thermal/cpu-cooling, sched/core: Cleanup thermal pressure definition

[Vincent Guittot]

On Sun, 14 Jun 2020 at 03:10, Valentin Schneider
<valentin.schneider@xxxxxxx> wrote:
>
> The following commit:
>
>   14533a16c46d ("thermal/cpu-cooling, sched/core: Move the arch_set_thermal_pressure() API to generic scheduler code")
>
> moved the definition of arch_set_thermal_pressure() to sched/core.c, but
> kept its declaration in linux/arch_topology.h. When building e.g. an x86
> kernel with CONFIG_SCHED_THERMAL_PRESSURE=y, cpufreq_cooling.c ends up
> getting the declaration of arch_set_thermal_pressure() from
> include/linux/arch_topology.h, which is somewhat awkward.
>
> On top of this, the public setter, arch_set_thermal_pressure(), is defined
> unconditionally in sched/core.c while the public getter,
> arch_scale_thermal_pressure(), is hardcoded to return 0 unless it has been
> redefined by the architecture. arch_*() functions are meant to be defined
> by architectures, so revert the aforementioned commit and re-implement it
> in a way that keeps arch_set_thermal_pressure() architecture-definable.
>
> Signed-off-by: Valentin Schneider <valentin.schneider@xxxxxxx>
> ---
>  drivers/base/arch_topology.c      | 11 +++++++++++
>  drivers/thermal/cpufreq_cooling.c |  5 +++++
>  include/linux/arch_topology.h     |  3 ---
>  kernel/sched/core.c               | 11 -----------
>  4 files changed, 16 insertions(+), 14 deletions(-)
>
> diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
> index 4d0a0038b476..d14cab7dfa3c 100644
> --- a/drivers/base/arch_topology.c
> +++ b/drivers/base/arch_topology.c
> @@ -54,6 +54,17 @@ void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity)
>         per_cpu(cpu_scale, cpu) = capacity;
>  }
>
> +DEFINE_PER_CPU(unsigned long, thermal_pressure);
> +
> +void arch_set_thermal_pressure(const struct cpumask *cpus,
> +                              unsigned long th_pressure)
> +{
> +       int cpu;
> +
> +       for_each_cpu(cpu, cpus)
> +               WRITE_ONCE(per_cpu(thermal_pressure, cpu), th_pressure);
> +}
> +
>  static ssize_t cpu_capacity_show(struct device *dev,
>                                  struct device_attribute *attr,
>                                  char *buf)
> diff --git a/drivers/thermal/cpufreq_cooling.c b/drivers/thermal/cpufreq_cooling.c
> index e297e135c031..a1efd379b683 100644
> --- a/drivers/thermal/cpufreq_cooling.c
> +++ b/drivers/thermal/cpufreq_cooling.c
> @@ -417,6 +417,11 @@ static int cpufreq_get_cur_state(struct thermal_cooling_device *cdev,
>         return 0;
>  }
>
> +__weak void
> +arch_set_thermal_pressure(const struct cpumask *cpus, unsigned long th_pressure)
> +{
> +}

Having this weak function declared in cpufreq_cooling is weird. This
means that we will have to do so for each one that wants to use it.

Can't you declare an empty function in a common header file ?

> +
>  /**
>   * cpufreq_set_cur_state - callback function to set the current cooling state.
>   * @cdev: thermal cooling device pointer.
> diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
> index 0566cb3314ef..81bd1c627195 100644
> --- a/include/linux/arch_topology.h
> +++ b/include/linux/arch_topology.h
> @@ -39,9 +39,6 @@ static inline unsigned long topology_get_thermal_pressure(int cpu)
>         return per_cpu(thermal_pressure, cpu);
>  }
>
> -void arch_set_thermal_pressure(struct cpumask *cpus,
> -                              unsigned long th_pressure);
> -
>  struct cpu_topology {
>         int thread_id;
>         int core_id;
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 43ba2d4a8eca..7861d21f3c2b 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -3628,17 +3628,6 @@ unsigned long long task_sched_runtime(struct task_struct *p)
>         return ns;
>  }
>
> -DEFINE_PER_CPU(unsigned long, thermal_pressure);
> -
> -void arch_set_thermal_pressure(struct cpumask *cpus,
> -                              unsigned long th_pressure)
> -{
> -       int cpu;
> -
> -       for_each_cpu(cpu, cpus)
> -               WRITE_ONCE(per_cpu(thermal_pressure, cpu), th_pressure);
> -}
> -
>  /*
>   * This function gets called by the timer code, with HZ frequency.
>   * We call it with interrupts disabled.
> --
> 2.27.0
>