Hi Vincent,
On 9/1/23 14:03, Vincent Guittot wrote:
> Create a new method to get a unique and fixed max frequency. Currently
> cpuinfo.max_freq or last item of performance domain are used as the max
> frequency when computing the frequency for a level of utilization but:
> - cpuinfo_max_freq can change at runtime. boost is one example of
> such change.
> - cpuinfo.max_freq and last item of the PD can be different leading to
> different results betwen cpufreq and energy model.
>
> We need to save the max frequency that has been used when computing the
> CPUs capacity and use this fixed and coherent value to convert between
> frequency and CPU's capacity.
>
> In fact, we already save the frequency that has been used when computing
> the capacity of each CPU. We extend the precision to save khZ instead of
> Mhz currently and we modify the type to be aligned with other variables
> used when converting frequency to capacity and the other way.
I do like this 'kHz' change. We also use kHz in the EM, so better
aligned now.
>
> Signed-off-by: Vincent Guittot <[email protected]>
> ---
> arch/arm/include/asm/topology.h | 1 +
> arch/arm64/include/asm/topology.h | 1 +
> arch/riscv/include/asm/topology.h | 1 +
> drivers/base/arch_topology.c | 9 +++------
> include/linux/arch_topology.h | 7 +++++++
> 5 files changed, 13 insertions(+), 6 deletions(-)
>
> diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
> index c7d2510e5a78..853c4f81ba4a 100644
> --- a/arch/arm/include/asm/topology.h
> +++ b/arch/arm/include/asm/topology.h
> @@ -13,6 +13,7 @@
> #define arch_set_freq_scale topology_set_freq_scale
> #define arch_scale_freq_capacity topology_get_freq_scale
> #define arch_scale_freq_invariant topology_scale_freq_invariant
> +#define arch_scale_freq_ref topology_get_freq_ref
> #endif
>
> /* Replace task scheduler's default cpu-invariant accounting */
> diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
> index 9fab663dd2de..a323b109b9c4 100644
> --- a/arch/arm64/include/asm/topology.h
> +++ b/arch/arm64/include/asm/topology.h
> @@ -23,6 +23,7 @@ void update_freq_counters_refs(void);
> #define arch_set_freq_scale topology_set_freq_scale
> #define arch_scale_freq_capacity topology_get_freq_scale
> #define arch_scale_freq_invariant topology_scale_freq_invariant
> +#define arch_scale_freq_ref topology_get_freq_ref
>
> #ifdef CONFIG_ACPI_CPPC_LIB
> #define arch_init_invariance_cppc topology_init_cpu_capacity_cppc
> diff --git a/arch/riscv/include/asm/topology.h b/arch/riscv/include/asm/topology.h
> index e316ab3b77f3..61183688bdd5 100644
> --- a/arch/riscv/include/asm/topology.h
> +++ b/arch/riscv/include/asm/topology.h
> @@ -9,6 +9,7 @@
> #define arch_set_freq_scale topology_set_freq_scale
> #define arch_scale_freq_capacity topology_get_freq_scale
> #define arch_scale_freq_invariant topology_scale_freq_invariant
> +#define arch_scale_freq_ref topology_get_freq_ref
>
> /* Replace task scheduler's default cpu-invariant accounting */
> #define arch_scale_cpu_capacity topology_get_cpu_scale
> diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
> index b741b5ba82bd..75fa67477a9d 100644
> --- a/drivers/base/arch_topology.c
> +++ b/drivers/base/arch_topology.c
> @@ -26,7 +26,7 @@
> static DEFINE_PER_CPU(struct scale_freq_data __rcu *, sft_data);
> static struct cpumask scale_freq_counters_mask;
> static bool scale_freq_invariant;
> -static DEFINE_PER_CPU(u32, freq_factor) = 1;
> +DEFINE_PER_CPU(unsigned long, freq_factor) = 1;
Why it's not static now?
>
> static bool supports_scale_freq_counters(const struct cpumask *cpus)
> {
> @@ -183,10 +183,7 @@ void topology_update_thermal_pressure(const struct cpumask *cpus,
>
> cpu = cpumask_first(cpus);
> max_capacity = arch_scale_cpu_capacity(cpu);
> - max_freq = per_cpu(freq_factor, cpu);
> -
> - /* Convert to MHz scale which is used in 'freq_factor' */
> - capped_freq /= 1000;
> + max_freq = arch_scale_freq_ref(cpu);
>
> /*
> * Handle properly the boost frequencies, which should simply clean
> @@ -411,7 +408,7 @@ init_cpu_capacity_callback(struct notifier_block *nb,
> cpumask_andnot(cpus_to_visit, cpus_to_visit, policy->related_cpus);
>
> for_each_cpu(cpu, policy->related_cpus)
> - per_cpu(freq_factor, cpu) = policy->cpuinfo.max_freq / 1000;
> + per_cpu(freq_factor, cpu) = policy->cpuinfo.max_freq;
>
> if (cpumask_empty(cpus_to_visit)) {
> topology_normalize_cpu_scale();
> diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
> index a07b510e7dc5..7a2dba9c3dc0 100644
> --- a/include/linux/arch_topology.h
> +++ b/include/linux/arch_topology.h
> @@ -27,6 +27,13 @@ static inline unsigned long topology_get_cpu_scale(int cpu)
>
> void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity);
>
> +DECLARE_PER_CPU(unsigned long, freq_factor);
> +
> +static inline unsigned long topology_get_freq_ref(int cpu)
> +{
> + return per_cpu(freq_factor, cpu);
> +}
> +
> DECLARE_PER_CPU(unsigned long, arch_freq_scale);
>
> static inline unsigned long topology_get_freq_scale(int cpu)
Apart from that 'static' missing, that looks good.
Regards,
Lukasz
On Mon, 4 Sept 2023 at 14:34, Lukasz Luba <[email protected]> wrote:
>
> Hi Vincent,
>
>
> On 9/1/23 14:03, Vincent Guittot wrote:
> > Create a new method to get a unique and fixed max frequency. Currently
> > cpuinfo.max_freq or last item of performance domain are used as the max
> > frequency when computing the frequency for a level of utilization but:
> > - cpuinfo_max_freq can change at runtime. boost is one example of
> > such change.
> > - cpuinfo.max_freq and last item of the PD can be different leading to
> > different results betwen cpufreq and energy model.
> >
> > We need to save the max frequency that has been used when computing the
> > CPUs capacity and use this fixed and coherent value to convert between
> > frequency and CPU's capacity.
> >
> > In fact, we already save the frequency that has been used when computing
> > the capacity of each CPU. We extend the precision to save khZ instead of
> > Mhz currently and we modify the type to be aligned with other variables
> > used when converting frequency to capacity and the other way.
>
> I do like this 'kHz' change. We also use kHz in the EM, so better
> aligned now.
>
> >
> > Signed-off-by: Vincent Guittot <[email protected]>
> > ---
> > arch/arm/include/asm/topology.h | 1 +
> > arch/arm64/include/asm/topology.h | 1 +
> > arch/riscv/include/asm/topology.h | 1 +
> > drivers/base/arch_topology.c | 9 +++------
> > include/linux/arch_topology.h | 7 +++++++
> > 5 files changed, 13 insertions(+), 6 deletions(-)
> >
> > diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
> > index c7d2510e5a78..853c4f81ba4a 100644
> > --- a/arch/arm/include/asm/topology.h
> > +++ b/arch/arm/include/asm/topology.h
> > @@ -13,6 +13,7 @@
> > #define arch_set_freq_scale topology_set_freq_scale
> > #define arch_scale_freq_capacity topology_get_freq_scale
> > #define arch_scale_freq_invariant topology_scale_freq_invariant
> > +#define arch_scale_freq_ref topology_get_freq_ref
> > #endif
> >
> > /* Replace task scheduler's default cpu-invariant accounting */
> > diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
> > index 9fab663dd2de..a323b109b9c4 100644
> > --- a/arch/arm64/include/asm/topology.h
> > +++ b/arch/arm64/include/asm/topology.h
> > @@ -23,6 +23,7 @@ void update_freq_counters_refs(void);
> > #define arch_set_freq_scale topology_set_freq_scale
> > #define arch_scale_freq_capacity topology_get_freq_scale
> > #define arch_scale_freq_invariant topology_scale_freq_invariant
> > +#define arch_scale_freq_ref topology_get_freq_ref
> >
> > #ifdef CONFIG_ACPI_CPPC_LIB
> > #define arch_init_invariance_cppc topology_init_cpu_capacity_cppc
> > diff --git a/arch/riscv/include/asm/topology.h b/arch/riscv/include/asm/topology.h
> > index e316ab3b77f3..61183688bdd5 100644
> > --- a/arch/riscv/include/asm/topology.h
> > +++ b/arch/riscv/include/asm/topology.h
> > @@ -9,6 +9,7 @@
> > #define arch_set_freq_scale topology_set_freq_scale
> > #define arch_scale_freq_capacity topology_get_freq_scale
> > #define arch_scale_freq_invariant topology_scale_freq_invariant
> > +#define arch_scale_freq_ref topology_get_freq_ref
> >
> > /* Replace task scheduler's default cpu-invariant accounting */
> > #define arch_scale_cpu_capacity topology_get_cpu_scale
> > diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
> > index b741b5ba82bd..75fa67477a9d 100644
> > --- a/drivers/base/arch_topology.c
> > +++ b/drivers/base/arch_topology.c
> > @@ -26,7 +26,7 @@
> > static DEFINE_PER_CPU(struct scale_freq_data __rcu *, sft_data);
> > static struct cpumask scale_freq_counters_mask;
> > static bool scale_freq_invariant;
> > -static DEFINE_PER_CPU(u32, freq_factor) = 1;
> > +DEFINE_PER_CPU(unsigned long, freq_factor) = 1;
>
> Why it's not static now?
it can be accessed outside with inline function like cpu_scale and
arch_freq_scale
>
> >
> > static bool supports_scale_freq_counters(const struct cpumask *cpus)
> > {
> > @@ -183,10 +183,7 @@ void topology_update_thermal_pressure(const struct cpumask *cpus,
> >
> > cpu = cpumask_first(cpus);
> > max_capacity = arch_scale_cpu_capacity(cpu);
> > - max_freq = per_cpu(freq_factor, cpu);
> > -
> > - /* Convert to MHz scale which is used in 'freq_factor' */
> > - capped_freq /= 1000;
> > + max_freq = arch_scale_freq_ref(cpu);
> >
> > /*
> > * Handle properly the boost frequencies, which should simply clean
> > @@ -411,7 +408,7 @@ init_cpu_capacity_callback(struct notifier_block *nb,
> > cpumask_andnot(cpus_to_visit, cpus_to_visit, policy->related_cpus);
> >
> > for_each_cpu(cpu, policy->related_cpus)
> > - per_cpu(freq_factor, cpu) = policy->cpuinfo.max_freq / 1000;
> > + per_cpu(freq_factor, cpu) = policy->cpuinfo.max_freq;
> >
> > if (cpumask_empty(cpus_to_visit)) {
> > topology_normalize_cpu_scale();
> > diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
> > index a07b510e7dc5..7a2dba9c3dc0 100644
> > --- a/include/linux/arch_topology.h
> > +++ b/include/linux/arch_topology.h
> > @@ -27,6 +27,13 @@ static inline unsigned long topology_get_cpu_scale(int cpu)
> >
> > void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity);
> >
> > +DECLARE_PER_CPU(unsigned long, freq_factor);
> > +
> > +static inline unsigned long topology_get_freq_ref(int cpu)
> > +{
> > + return per_cpu(freq_factor, cpu);
> > +}
> > +
> > DECLARE_PER_CPU(unsigned long, arch_freq_scale);
> >
> > static inline unsigned long topology_get_freq_scale(int cpu)
>
> Apart from that 'static' missing, that looks good.
>
> Regards,
> Lukasz