mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-27 16:15:06 +07:00
27871f7a8a
Several subsystems in the kernel (task scheduler and/or thermal at the time of writing) can benefit from knowing about the energy consumed by CPUs. Yet, this information can come from different sources (DT or firmware for example), in different formats, hence making it hard to exploit without a standard API. As an attempt to address this, introduce a centralized Energy Model (EM) management framework which aggregates the power values provided by drivers into a table for each performance domain in the system. The power cost tables are made available to interested clients (e.g. task scheduler or thermal) via platform-agnostic APIs. The overall design is represented by the diagram below (focused on Arm-related drivers as an example, but applicable to any architecture): +---------------+ +-----------------+ +-------------+ | Thermal (IPA) | | Scheduler (EAS) | | Other | +---------------+ +-----------------+ +-------------+ | | em_pd_energy() | | | em_cpu_get() | +-----------+ | +--------+ | | | v v v +---------------------+ | | | Energy Model | | | | Framework | | | +---------------------+ ^ ^ ^ | | | em_register_perf_domain() +----------+ | +---------+ | | | +---------------+ +---------------+ +--------------+ | cpufreq-dt | | arm_scmi | | Other | +---------------+ +---------------+ +--------------+ ^ ^ ^ | | | +--------------+ +---------------+ +--------------+ | Device Tree | | Firmware | | ? | +--------------+ +---------------+ +--------------+ Drivers (typically, but not limited to, CPUFreq drivers) can register data in the EM framework using the em_register_perf_domain() API. The calling driver must provide a callback function with a standardized signature that will be used by the EM framework to build the power cost tables of the performance domain. This design should offer a lot of flexibility to calling drivers which are free of reading information from any location and to use any technique to compute power costs. Moreover, the capacity states registered by drivers in the EM framework are not required to match real performance states of the target. This is particularly important on targets where the performance states are not known by the OS. The power cost coefficients managed by the EM framework are specified in milli-watts. Although the two potential users of those coefficients (IPA and EAS) only need relative correctness, IPA specifically needs to compare the power of CPUs with the power of other components (GPUs, for example), which are still expressed in absolute terms in their respective subsystems. Hence, specifying the power of CPUs in milli-watts should help transitioning IPA to using the EM framework without introducing new problems by keeping units comparable across sub-systems. On the longer term, the EM of other devices than CPUs could also be managed by the EM framework, which would enable to remove the absolute unit. However, this is not absolutely required as a first step, so this extension of the EM framework is left for later. On the client side, the EM framework offers APIs to access the power cost tables of a CPU (em_cpu_get()), and to estimate the energy consumed by the CPUs of a performance domain (em_pd_energy()). Clients such as the task scheduler can then use these APIs to access the shared data structures holding the Energy Model of CPUs. Signed-off-by: Quentin Perret <quentin.perret@arm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rafael J. Wysocki <rjw@rjwysocki.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: adharmap@codeaurora.org Cc: chris.redpath@arm.com Cc: currojerez@riseup.net Cc: dietmar.eggemann@arm.com Cc: edubezval@gmail.com Cc: gregkh@linuxfoundation.org Cc: javi.merino@kernel.org Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: morten.rasmussen@arm.com Cc: patrick.bellasi@arm.com Cc: pkondeti@codeaurora.org Cc: skannan@codeaurora.org Cc: smuckle@google.com Cc: srinivas.pandruvada@linux.intel.com Cc: thara.gopinath@linaro.org Cc: tkjos@google.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Cc: viresh.kumar@linaro.org Link: https://lkml.kernel.org/r/20181203095628.11858-4-quentin.perret@arm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
188 lines
5.9 KiB
C
188 lines
5.9 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_ENERGY_MODEL_H
|
|
#define _LINUX_ENERGY_MODEL_H
|
|
#include <linux/cpumask.h>
|
|
#include <linux/jump_label.h>
|
|
#include <linux/kobject.h>
|
|
#include <linux/rcupdate.h>
|
|
#include <linux/sched/cpufreq.h>
|
|
#include <linux/sched/topology.h>
|
|
#include <linux/types.h>
|
|
|
|
#ifdef CONFIG_ENERGY_MODEL
|
|
/**
|
|
* em_cap_state - Capacity state of a performance domain
|
|
* @frequency: The CPU frequency in KHz, for consistency with CPUFreq
|
|
* @power: The power consumed by 1 CPU at this level, in milli-watts
|
|
* @cost: The cost coefficient associated with this level, used during
|
|
* energy calculation. Equal to: power * max_frequency / frequency
|
|
*/
|
|
struct em_cap_state {
|
|
unsigned long frequency;
|
|
unsigned long power;
|
|
unsigned long cost;
|
|
};
|
|
|
|
/**
|
|
* em_perf_domain - Performance domain
|
|
* @table: List of capacity states, in ascending order
|
|
* @nr_cap_states: Number of capacity states
|
|
* @cpus: Cpumask covering the CPUs of the domain
|
|
*
|
|
* A "performance domain" represents a group of CPUs whose performance is
|
|
* scaled together. All CPUs of a performance domain must have the same
|
|
* micro-architecture. Performance domains often have a 1-to-1 mapping with
|
|
* CPUFreq policies.
|
|
*/
|
|
struct em_perf_domain {
|
|
struct em_cap_state *table;
|
|
int nr_cap_states;
|
|
unsigned long cpus[0];
|
|
};
|
|
|
|
#define EM_CPU_MAX_POWER 0xFFFF
|
|
|
|
struct em_data_callback {
|
|
/**
|
|
* active_power() - Provide power at the next capacity state of a CPU
|
|
* @power : Active power at the capacity state in mW (modified)
|
|
* @freq : Frequency at the capacity state in kHz (modified)
|
|
* @cpu : CPU for which we do this operation
|
|
*
|
|
* active_power() must find the lowest capacity state of 'cpu' above
|
|
* 'freq' and update 'power' and 'freq' to the matching active power
|
|
* and frequency.
|
|
*
|
|
* The power is the one of a single CPU in the domain, expressed in
|
|
* milli-watts. It is expected to fit in the [0, EM_CPU_MAX_POWER]
|
|
* range.
|
|
*
|
|
* Return 0 on success.
|
|
*/
|
|
int (*active_power)(unsigned long *power, unsigned long *freq, int cpu);
|
|
};
|
|
#define EM_DATA_CB(_active_power_cb) { .active_power = &_active_power_cb }
|
|
|
|
struct em_perf_domain *em_cpu_get(int cpu);
|
|
int em_register_perf_domain(cpumask_t *span, unsigned int nr_states,
|
|
struct em_data_callback *cb);
|
|
|
|
/**
|
|
* em_pd_energy() - Estimates the energy consumed by the CPUs of a perf. domain
|
|
* @pd : performance domain for which energy has to be estimated
|
|
* @max_util : highest utilization among CPUs of the domain
|
|
* @sum_util : sum of the utilization of all CPUs in the domain
|
|
*
|
|
* Return: the sum of the energy consumed by the CPUs of the domain assuming
|
|
* a capacity state satisfying the max utilization of the domain.
|
|
*/
|
|
static inline unsigned long em_pd_energy(struct em_perf_domain *pd,
|
|
unsigned long max_util, unsigned long sum_util)
|
|
{
|
|
unsigned long freq, scale_cpu;
|
|
struct em_cap_state *cs;
|
|
int i, cpu;
|
|
|
|
/*
|
|
* In order to predict the capacity state, map the utilization of the
|
|
* most utilized CPU of the performance domain to a requested frequency,
|
|
* like schedutil.
|
|
*/
|
|
cpu = cpumask_first(to_cpumask(pd->cpus));
|
|
scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
|
|
cs = &pd->table[pd->nr_cap_states - 1];
|
|
freq = map_util_freq(max_util, cs->frequency, scale_cpu);
|
|
|
|
/*
|
|
* Find the lowest capacity state of the Energy Model above the
|
|
* requested frequency.
|
|
*/
|
|
for (i = 0; i < pd->nr_cap_states; i++) {
|
|
cs = &pd->table[i];
|
|
if (cs->frequency >= freq)
|
|
break;
|
|
}
|
|
|
|
/*
|
|
* The capacity of a CPU in the domain at that capacity state (cs)
|
|
* can be computed as:
|
|
*
|
|
* cs->freq * scale_cpu
|
|
* cs->cap = -------------------- (1)
|
|
* cpu_max_freq
|
|
*
|
|
* So, ignoring the costs of idle states (which are not available in
|
|
* the EM), the energy consumed by this CPU at that capacity state is
|
|
* estimated as:
|
|
*
|
|
* cs->power * cpu_util
|
|
* cpu_nrg = -------------------- (2)
|
|
* cs->cap
|
|
*
|
|
* since 'cpu_util / cs->cap' represents its percentage of busy time.
|
|
*
|
|
* NOTE: Although the result of this computation actually is in
|
|
* units of power, it can be manipulated as an energy value
|
|
* over a scheduling period, since it is assumed to be
|
|
* constant during that interval.
|
|
*
|
|
* By injecting (1) in (2), 'cpu_nrg' can be re-expressed as a product
|
|
* of two terms:
|
|
*
|
|
* cs->power * cpu_max_freq cpu_util
|
|
* cpu_nrg = ------------------------ * --------- (3)
|
|
* cs->freq scale_cpu
|
|
*
|
|
* The first term is static, and is stored in the em_cap_state struct
|
|
* as 'cs->cost'.
|
|
*
|
|
* Since all CPUs of the domain have the same micro-architecture, they
|
|
* share the same 'cs->cost', and the same CPU capacity. Hence, the
|
|
* total energy of the domain (which is the simple sum of the energy of
|
|
* all of its CPUs) can be factorized as:
|
|
*
|
|
* cs->cost * \Sum cpu_util
|
|
* pd_nrg = ------------------------ (4)
|
|
* scale_cpu
|
|
*/
|
|
return cs->cost * sum_util / scale_cpu;
|
|
}
|
|
|
|
/**
|
|
* em_pd_nr_cap_states() - Get the number of capacity states of a perf. domain
|
|
* @pd : performance domain for which this must be done
|
|
*
|
|
* Return: the number of capacity states in the performance domain table
|
|
*/
|
|
static inline int em_pd_nr_cap_states(struct em_perf_domain *pd)
|
|
{
|
|
return pd->nr_cap_states;
|
|
}
|
|
|
|
#else
|
|
struct em_perf_domain {};
|
|
struct em_data_callback {};
|
|
#define EM_DATA_CB(_active_power_cb) { }
|
|
|
|
static inline int em_register_perf_domain(cpumask_t *span,
|
|
unsigned int nr_states, struct em_data_callback *cb)
|
|
{
|
|
return -EINVAL;
|
|
}
|
|
static inline struct em_perf_domain *em_cpu_get(int cpu)
|
|
{
|
|
return NULL;
|
|
}
|
|
static inline unsigned long em_pd_energy(struct em_perf_domain *pd,
|
|
unsigned long max_util, unsigned long sum_util)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline int em_pd_nr_cap_states(struct em_perf_domain *pd)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
#endif
|