[v5,1/5] cpufreq: Add a cpufreq pressure feedback for the scheduler

Commit Message

Vincent Guittot Feb. 20, 2024, 2:59 p.m. UTC

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 <[e-mail]>
Acked-by: Rafael J. Wysocki <[e-mail]>
Acked-by: Viresh Kumar <[e-mail]>
Reviewed-by: Qais Yousef <[e-mail]>
---
 drivers/cpufreq/cpufreq.c | 36 ++++++++++++++++++++++++++++++++++++
 include/linux/cpufreq.h   | 10 ++++++++++
 2 files changed, 46 insertions(+)

Patch

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 44db4f59c4cc..f4eee3d107f1 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2563,6 +2563,40 @@  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.
@@ -2618,6 +2652,8 @@  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 afda5f24d3dd..13b69a816747 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)
 {
@@ -263,6 +269,10 @@  static inline bool cpufreq_supports_freq_invariance(void)
 	return false;
 }
 static inline void disable_cpufreq(void) { }
+static inline unsigned long cpufreq_get_pressure(int cpu)
+{
+	return 0;
+}
 #endif
 
 #ifdef CONFIG_CPU_FREQ_STAT