Provide to the scheduler a feedback about the temporary max available
capacity. Unlike arch_update_thermal_pressure, this doesn't need to be
filtered as the pressure will happen for dozens ms or more.
Signed-off-by: Vincent Guittot <[email protected]>
Acked-by: Rafael J. Wysocki <[email protected]>
Acked-by: Viresh Kumar <[email protected]>
Reviewed-by: Qais Yousef <[email protected]>
Reviewed-by: Lukasz Luba <[email protected]>
Tested-by: Lukasz Luba <[email protected]>
---
drivers/cpufreq/cpufreq.c | 36 ++++++++++++++++++++++++++++++++++++
include/linux/cpufreq.h | 10 ++++++++++
2 files changed, 46 insertions(+)
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 66e10a19d76a..1de8bd105934 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2582,6 +2582,40 @@ int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu)
}
EXPORT_SYMBOL(cpufreq_get_policy);
+DEFINE_PER_CPU(unsigned long, cpufreq_pressure);
+
+/**
+ * cpufreq_update_pressure() - Update cpufreq pressure for CPUs
+ * @policy: cpufreq policy of the CPUs.
+ *
+ * Update the value of cpufreq pressure for all @cpus in the policy.
+ */
+static void cpufreq_update_pressure(struct cpufreq_policy *policy)
+{
+ unsigned long max_capacity, capped_freq, pressure;
+ u32 max_freq;
+ int cpu;
+
+ cpu = cpumask_first(policy->related_cpus);
+ max_freq = arch_scale_freq_ref(cpu);
+ capped_freq = policy->max;
+
+ /*
+ * Handle properly the boost frequencies, which should simply clean
+ * the cpufreq pressure value.
+ */
+ if (max_freq <= capped_freq) {
+ pressure = 0;
+ } else {
+ max_capacity = arch_scale_cpu_capacity(cpu);
+ pressure = max_capacity -
+ mult_frac(max_capacity, capped_freq, max_freq);
+ }
+
+ for_each_cpu(cpu, policy->related_cpus)
+ WRITE_ONCE(per_cpu(cpufreq_pressure, cpu), pressure);
+}
+
/**
* cpufreq_set_policy - Modify cpufreq policy parameters.
* @policy: Policy object to modify.
@@ -2637,6 +2671,8 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
policy->max = __resolve_freq(policy, policy->max, CPUFREQ_RELATION_H);
trace_cpu_frequency_limits(policy);
+ cpufreq_update_pressure(policy);
+
policy->cached_target_freq = UINT_MAX;
pr_debug("new min and max freqs are %u - %u kHz\n",
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 9956afb9acc2..20f7e98ee8af 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -241,6 +241,12 @@ struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy);
void cpufreq_enable_fast_switch(struct cpufreq_policy *policy);
void cpufreq_disable_fast_switch(struct cpufreq_policy *policy);
bool has_target_index(void);
+
+DECLARE_PER_CPU(unsigned long, cpufreq_pressure);
+static inline unsigned long cpufreq_get_pressure(int cpu)
+{
+ return READ_ONCE(per_cpu(cpufreq_pressure, cpu));
+}
#else
static inline unsigned int cpufreq_get(unsigned int cpu)
{
@@ -264,6 +270,10 @@ static inline bool cpufreq_supports_freq_invariance(void)
}
static inline void disable_cpufreq(void) { }
static inline void cpufreq_update_limits(unsigned int cpu) { }
+static inline unsigned long cpufreq_get_pressure(int cpu)
+{
+ return 0;
+}
#endif
#ifdef CONFIG_CPU_FREQ_STAT
--
2.34.1
Hi,
On Mar 26, 2024 at 10:16:12 +0100, Vincent Guittot wrote:
> Provide to the scheduler a feedback about the temporary max available
> capacity. Unlike arch_update_thermal_pressure, this doesn't need to be
> filtered as the pressure will happen for dozens ms or more.
>
> Signed-off-by: Vincent Guittot <[email protected]>
> Acked-by: Rafael J. Wysocki <[email protected]>
> Acked-by: Viresh Kumar <[email protected]>
> Reviewed-by: Qais Yousef <[email protected]>
> Reviewed-by: Lukasz Luba <[email protected]>
> Tested-by: Lukasz Luba <[email protected]>
> ---
LGTM,
Reviewed-by: Dhruva Gole <[email protected]>
--
Best regards,
Dhruva
The following commit has been merged into the sched/core branch of tip:
Commit-ID: 75d659317bb136d849a10a30ffe7e0462c982d29
Gitweb: https://git.kernel.org/tip/75d659317bb136d849a10a30ffe7e0462c982d29
Author: Vincent Guittot <[email protected]>
AuthorDate: Tue, 26 Mar 2024 10:16:12 +01:00
Committer: Ingo Molnar <[email protected]>
CommitterDate: Wed, 24 Apr 2024 12:07:58 +02:00
cpufreq: Add a cpufreq pressure feedback for the scheduler
Provide to the scheduler a feedback about the temporary max available
capacity. Unlike arch_update_thermal_pressure(), this doesn't need to be
filtered as the pressure will happen for dozens of ms or more.
Signed-off-by: Vincent Guittot <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Tested-by: Lukasz Luba <[email protected]>
Reviewed-by: Qais Yousef <[email protected]>
Reviewed-by: Lukasz Luba <[email protected]>
Reviewed-by: Dhruva Gole <[email protected]>
Acked-by: Rafael J. Wysocki <[email protected]>
Acked-by: Viresh Kumar <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
---
drivers/cpufreq/cpufreq.c | 36 ++++++++++++++++++++++++++++++++++++
include/linux/cpufreq.h | 10 ++++++++++
2 files changed, 46 insertions(+)
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 66e10a1..1de8bd1 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2582,6 +2582,40 @@ int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu)
}
EXPORT_SYMBOL(cpufreq_get_policy);
+DEFINE_PER_CPU(unsigned long, cpufreq_pressure);
+
+/**
+ * cpufreq_update_pressure() - Update cpufreq pressure for CPUs
+ * @policy: cpufreq policy of the CPUs.
+ *
+ * Update the value of cpufreq pressure for all @cpus in the policy.
+ */
+static void cpufreq_update_pressure(struct cpufreq_policy *policy)
+{
+ unsigned long max_capacity, capped_freq, pressure;
+ u32 max_freq;
+ int cpu;
+
+ cpu = cpumask_first(policy->related_cpus);
+ max_freq = arch_scale_freq_ref(cpu);
+ capped_freq = policy->max;
+
+ /*
+ * Handle properly the boost frequencies, which should simply clean
+ * the cpufreq pressure value.
+ */
+ if (max_freq <= capped_freq) {
+ pressure = 0;
+ } else {
+ max_capacity = arch_scale_cpu_capacity(cpu);
+ pressure = max_capacity -
+ mult_frac(max_capacity, capped_freq, max_freq);
+ }
+
+ for_each_cpu(cpu, policy->related_cpus)
+ WRITE_ONCE(per_cpu(cpufreq_pressure, cpu), pressure);
+}
+
/**
* cpufreq_set_policy - Modify cpufreq policy parameters.
* @policy: Policy object to modify.
@@ -2637,6 +2671,8 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
policy->max = __resolve_freq(policy, policy->max, CPUFREQ_RELATION_H);
trace_cpu_frequency_limits(policy);
+ cpufreq_update_pressure(policy);
+
policy->cached_target_freq = UINT_MAX;
pr_debug("new min and max freqs are %u - %u kHz\n",
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 9956afb..20f7e98 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -241,6 +241,12 @@ struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy);
void cpufreq_enable_fast_switch(struct cpufreq_policy *policy);
void cpufreq_disable_fast_switch(struct cpufreq_policy *policy);
bool has_target_index(void);
+
+DECLARE_PER_CPU(unsigned long, cpufreq_pressure);
+static inline unsigned long cpufreq_get_pressure(int cpu)
+{
+ return READ_ONCE(per_cpu(cpufreq_pressure, cpu));
+}
#else
static inline unsigned int cpufreq_get(unsigned int cpu)
{
@@ -264,6 +270,10 @@ static inline bool cpufreq_supports_freq_invariance(void)
}
static inline void disable_cpufreq(void) { }
static inline void cpufreq_update_limits(unsigned int cpu) { }
+static inline unsigned long cpufreq_get_pressure(int cpu)
+{
+ return 0;
+}
#endif
#ifdef CONFIG_CPU_FREQ_STAT