android_kernel_xiaomi_sm8350/include/linux/energy_model.h
Lukasz Luba 156eaacba3 PM: EM: Increase energy calculation precision
[ Upstream commit 7fcc17d0cb12938d2b3507973a6f93fc9ed2c7a1 ]

The Energy Model (EM) provides useful information about device power in
each performance state to other subsystems like: Energy Aware Scheduler
(EAS). The energy calculation in EAS does arithmetic operation based on
the EM em_cpu_energy(). Current implementation of that function uses
em_perf_state::cost as a pre-computed cost coefficient equal to:
cost = power * max_frequency / frequency.
The 'power' is expressed in milli-Watts (or in abstract scale).

There are corner cases when the EAS energy calculation for two Performance
Domains (PDs) return the same value. The EAS compares these values to
choose smaller one. It might happen that this values are equal due to
rounding error. In such scenario, we need better resolution, e.g. 1000
times better. To provide this possibility increase the resolution in the
em_perf_state::cost for 64-bit architectures. The cost of increasing
resolution on 32-bit is pretty high (64-bit division) and is not justified
since there are no new 32bit big.LITTLE EAS systems expected which would
benefit from this higher resolution.

This patch allows to avoid the rounding to milli-Watt errors, which might
occur in EAS energy estimation for each PD. The rounding error is common
for small tasks which have small utilization value.

There are two places in the code where it makes a difference:
1. In the find_energy_efficient_cpu() where we are searching for
best_delta. We might suffer there when two PDs return the same result,
like in the example below.

Scenario:
Low utilized system e.g. ~200 sum_util for PD0 and ~220 for PD1. There
are quite a few small tasks ~10-15 util. These tasks would suffer for
the rounding error. These utilization values are typical when running games
on Android. One of our partners has reported 5..10mA less battery drain
when running with increased resolution.

Some details:
We have two PDs: PD0 (big) and PD1 (little)
Let's compare w/o patch set ('old') and w/ patch set ('new')
We are comparing energy w/ task and w/o task placed in the PDs

a) 'old' w/o patch set, PD0
task_util = 13
cost = 480
sum_util_w/o_task = 215
sum_util_w_task = 228
scale_cpu = 1024
energy_w/o_task = 480 * 215 / 1024 = 100.78 => 100
energy_w_task = 480 * 228 / 1024 = 106.87 => 106
energy_diff = 106 - 100 = 6
(this is equal to 'old' PD1's energy_diff in 'c)')

b) 'new' w/ patch set, PD0
task_util = 13
cost = 480 * 1000 = 480000
sum_util_w/o_task = 215
sum_util_w_task = 228
energy_w/o_task = 480000 * 215 / 1024 = 100781
energy_w_task = 480000 * 228 / 1024  = 106875
energy_diff = 106875 - 100781 = 6094
(this is not equal to 'new' PD1's energy_diff in 'd)')

c) 'old' w/o patch set, PD1
task_util = 13
cost = 160
sum_util_w/o_task = 283
sum_util_w_task = 293
scale_cpu = 355
energy_w/o_task = 160 * 283 / 355 = 127.55 => 127
energy_w_task = 160 * 296 / 355 = 133.41 => 133
energy_diff = 133 - 127 = 6
(this is equal to 'old' PD0's energy_diff in 'a)')

d) 'new' w/ patch set, PD1
task_util = 13
cost = 160 * 1000 = 160000
sum_util_w/o_task = 283
sum_util_w_task = 293
scale_cpu = 355
energy_w/o_task = 160000 * 283 / 355 = 127549
energy_w_task = 160000 * 296 / 355 =   133408
energy_diff = 133408 - 127549 = 5859
(this is not equal to 'new' PD0's energy_diff in 'b)')

2. Difference in the 6% energy margin filter at the end of
find_energy_efficient_cpu(). With this patch the margin comparison also
has better resolution, so it's possible to have better task placement
thanks to that.

Fixes: 27871f7a8a ("PM: Introduce an Energy Model management framework")
Reported-by: CCJ Yeh <CCj.Yeh@mediatek.com>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
2021-09-15 09:47:33 +02:00

204 lines
6.5 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
/*
* Increase resolution of energy estimation calculations for 64-bit
* architectures. The extra resolution improves decision made by EAS for the
* task placement when two Performance Domains might provide similar energy
* estimation values (w/o better resolution the values could be equal).
*
* We increase resolution only if we have enough bits to allow this increased
* resolution (i.e. 64-bit). The costs for increasing resolution when 32-bit
* are pretty high and the returns do not justify the increased costs.
*/
#ifdef CONFIG_64BIT
#define em_scale_power(p) ((p) * 1000)
#else
#define em_scale_power(p) (p)
#endif
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(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