Re: [RFCv5, 18/46] arm: topology: Define TC2 energy and provide it to the scheduler

[Leo Yan <leo.yan@linaro.org>]

Hi Morten,

On Tue, Jul 07, 2015 at 07:24:01PM +0100, Morten Rasmussen wrote:
> From: Dietmar Eggemann <dietmar.eggemann@arm.com>
> 
> This patch is only here to be able to test provisioning of energy related
> data from an arch topology shim layer to the scheduler. Since there is no
> code today which deals with extracting energy related data from the dtb or
> acpi, and process it in the topology shim layer, the content of the
> sched_group_energy structures as well as the idle_state and capacity_state
> arrays are hard-coded here.
> 
> This patch defines the sched_group_energy structure as well as the
> idle_state and capacity_state array for the cluster (relates to sched
> groups (sgs) in DIE sched domain level) and for the core (relates to sgs
> in MC sd level) for a Cortex A7 as well as for a Cortex A15.
> It further provides related implementations of the sched_domain_energy_f
> functions (cpu_cluster_energy() and cpu_core_energy()).
> 
> To be able to propagate this information from the topology shim layer to
> the scheduler, the elements of the arm_topology[] table have been
> provisioned with the appropriate sched_domain_energy_f functions.
> 
> cc: Russell King <linux@arm.linux.org.uk>
> 
> Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
> 
> ---
> arch/arm/kernel/topology.c | 118 +++++++++++++++++++++++++++++++++++++++++++--
>  1 file changed, 115 insertions(+), 3 deletions(-)
> 
> diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
> index b35d3e5..bbe20c7 100644
> --- a/arch/arm/kernel/topology.c
> +++ b/arch/arm/kernel/topology.c
> @@ -274,6 +274,119 @@ void store_cpu_topology(unsigned int cpuid)
>  		cpu_topology[cpuid].socket_id, mpidr);
>  }
>  
> +/*
> + * ARM TC2 specific energy cost model data. There are no unit requirements for
> + * the data. Data can be normalized to any reference point, but the
> + * normalization must be consistent. That is, one bogo-joule/watt must be the
> + * same quantity for all data, but we don't care what it is.
> + */
> +static struct idle_state idle_states_cluster_a7[] = {
> +	 { .power = 25 }, /* WFI */

This state is confused. Is this state corresponding to all CPUs have been
powered off but L2 cache RAM array and SCU are still power on?

> +	 { .power = 10 }, /* cluster-sleep-l */

Is this status means all CPU and cluster have been powered off, if so
then it will have no power consumption anymore...

> +	};
> +
> +static struct idle_state idle_states_cluster_a15[] = {
> +	 { .power = 70 }, /* WFI */
> +	 { .power = 25 }, /* cluster-sleep-b */
> +	};
> +
> +static struct capacity_state cap_states_cluster_a7[] = {
> +	/* Cluster only power */
> +	 { .cap =  150, .power = 2967, }, /*  350 MHz */

For cluster level's capacity, does it mean need run benchmark on all
CPUs within cluster?

> +	 { .cap =  172, .power = 2792, }, /*  400 MHz */
> +	 { .cap =  215, .power = 2810, }, /*  500 MHz */
> +	 { .cap =  258, .power = 2815, }, /*  600 MHz */
> +	 { .cap =  301, .power = 2919, }, /*  700 MHz */
> +	 { .cap =  344, .power = 2847, }, /*  800 MHz */
> +	 { .cap =  387, .power = 3917, }, /*  900 MHz */
> +	 { .cap =  430, .power = 4905, }, /* 1000 MHz */
> +	};
> +
> +static struct capacity_state cap_states_cluster_a15[] = {
> +	/* Cluster only power */
> +	 { .cap =  426, .power =  7920, }, /*  500 MHz */
> +	 { .cap =  512, .power =  8165, }, /*  600 MHz */
> +	 { .cap =  597, .power =  8172, }, /*  700 MHz */
> +	 { .cap =  682, .power =  8195, }, /*  800 MHz */
> +	 { .cap =  768, .power =  8265, }, /*  900 MHz */
> +	 { .cap =  853, .power =  8446, }, /* 1000 MHz */
> +	 { .cap =  938, .power = 11426, }, /* 1100 MHz */
> +	 { .cap = 1024, .power = 15200, }, /* 1200 MHz */
> +	};
> +
> +static struct sched_group_energy energy_cluster_a7 = {
> +	  .nr_idle_states = ARRAY_SIZE(idle_states_cluster_a7),
> +	  .idle_states    = idle_states_cluster_a7,
> +	  .nr_cap_states  = ARRAY_SIZE(cap_states_cluster_a7),
> +	  .cap_states     = cap_states_cluster_a7,
> +};
> +
> +static struct sched_group_energy energy_cluster_a15 = {
> +	  .nr_idle_states = ARRAY_SIZE(idle_states_cluster_a15),
> +	  .idle_states    = idle_states_cluster_a15,
> +	  .nr_cap_states  = ARRAY_SIZE(cap_states_cluster_a15),
> +	  .cap_states     = cap_states_cluster_a15,
> +};
> +
> +static struct idle_state idle_states_core_a7[] = {
> +	 { .power = 0 }, /* WFI */

Should have two idle states for CPU level (WFI and CPU's power off)?

> +	};
> +
> +static struct idle_state idle_states_core_a15[] = {
> +	 { .power = 0 }, /* WFI */
> +	};
> +
> +static struct capacity_state cap_states_core_a7[] = {
> +	/* Power per cpu */
> +	 { .cap =  150, .power =  187, }, /*  350 MHz */
> +	 { .cap =  172, .power =  275, }, /*  400 MHz */
> +	 { .cap =  215, .power =  334, }, /*  500 MHz */
> +	 { .cap =  258, .power =  407, }, /*  600 MHz */
> +	 { .cap =  301, .power =  447, }, /*  700 MHz */
> +	 { .cap =  344, .power =  549, }, /*  800 MHz */
> +	 { .cap =  387, .power =  761, }, /*  900 MHz */
> +	 { .cap =  430, .power = 1024, }, /* 1000 MHz */
> +	};
> +
> +static struct capacity_state cap_states_core_a15[] = {
> +	/* Power per cpu */
> +	 { .cap =  426, .power = 2021, }, /*  500 MHz */
> +	 { .cap =  512, .power = 2312, }, /*  600 MHz */
> +	 { .cap =  597, .power = 2756, }, /*  700 MHz */
> +	 { .cap =  682, .power = 3125, }, /*  800 MHz */
> +	 { .cap =  768, .power = 3524, }, /*  900 MHz */
> +	 { .cap =  853, .power = 3846, }, /* 1000 MHz */
> +	 { .cap =  938, .power = 5177, }, /* 1100 MHz */
> +	 { .cap = 1024, .power = 6997, }, /* 1200 MHz */
> +	};
> +
> +static struct sched_group_energy energy_core_a7 = {
> +	  .nr_idle_states = ARRAY_SIZE(idle_states_core_a7),
> +	  .idle_states    = idle_states_core_a7,
> +	  .nr_cap_states  = ARRAY_SIZE(cap_states_core_a7),
> +	  .cap_states     = cap_states_core_a7,
> +};
> +
> +static struct sched_group_energy energy_core_a15 = {
> +	  .nr_idle_states = ARRAY_SIZE(idle_states_core_a15),
> +	  .idle_states    = idle_states_core_a15,
> +	  .nr_cap_states  = ARRAY_SIZE(cap_states_core_a15),
> +	  .cap_states     = cap_states_core_a15,
> +};
> +
> +/* sd energy functions */
> +static inline const struct sched_group_energy *cpu_cluster_energy(int cpu)
> +{
> +	return cpu_topology[cpu].socket_id ? &energy_cluster_a7 :
> +			&energy_cluster_a15;
> +}
> +
> +static inline const struct sched_group_energy *cpu_core_energy(int cpu)
> +{
> +	return cpu_topology[cpu].socket_id ? &energy_core_a7 :
> +			&energy_core_a15;
> +}
> +
>  static inline int cpu_corepower_flags(void)
>  {
>  	return SD_SHARE_PKG_RESOURCES  | SD_SHARE_POWERDOMAIN | \
> @@ -282,10 +395,9 @@ static inline int cpu_corepower_flags(void)
>  
>  static struct sched_domain_topology_level arm_topology[] = {
>  #ifdef CONFIG_SCHED_MC
> -	{ cpu_corepower_mask, cpu_corepower_flags, SD_INIT_NAME(GMC) },
> -	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
> +	{ cpu_coregroup_mask, cpu_corepower_flags, cpu_core_energy, SD_INIT_NAME(MC) },
>  #endif
> -	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
> +	{ cpu_cpu_mask, 0, cpu_cluster_energy, SD_INIT_NAME(DIE) },
>  	{ NULL, },
>  };
>