Merge tag 'sched-core-2024-05-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Add cpufreq pressure feedback for the scheduler

 - Rework misfit load-balancing wrt affinity restrictions

 - Clean up and simplify the code around ::overutilized and
   ::overload access.

 - Simplify sched_balance_newidle()

 - Bump SCHEDSTAT_VERSION to 16 due to a cleanup of CPU_MAX_IDLE_TYPES
   handling that changed the output.

 - Rework & clean up <asm/vtime.h> interactions wrt arch_vtime_task_switch()

 - Reorganize, clean up and unify most of the higher level
   scheduler balancing function names around the sched_balance_*()
   prefix

 - Simplify the balancing flag code (sched_balance_running)

 - Miscellaneous cleanups & fixes

* tag 'sched-core-2024-05-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (50 commits)
  sched/pelt: Remove shift of thermal clock
  sched/cpufreq: Rename arch_update_thermal_pressure() => arch_update_hw_pressure()
  thermal/cpufreq: Remove arch_update_thermal_pressure()
  sched/cpufreq: Take cpufreq feedback into account
  cpufreq: Add a cpufreq pressure feedback for the scheduler
  sched/fair: Fix update of rd->sg_overutilized
  sched/vtime: Do not include <asm/vtime.h> header
  s390/irq,nmi: Include <asm/vtime.h> header directly
  s390/vtime: Remove unused __ARCH_HAS_VTIME_TASK_SWITCH leftover
  sched/vtime: Get rid of generic vtime_task_switch() implementation
  sched/vtime: Remove confusing arch_vtime_task_switch() declaration
  sched/balancing: Simplify the sg_status bitmask and use separate ->overloaded and ->overutilized flags
  sched/fair: Rename set_rd_overutilized_status() to set_rd_overutilized()
  sched/fair: Rename SG_OVERLOAD to SG_OVERLOADED
  sched/fair: Rename {set|get}_rd_overload() to {set|get}_rd_overloaded()
  sched/fair: Rename root_domain::overload to ::overloaded
  sched/fair: Use helper functions to access root_domain::overload
  sched/fair: Check root_domain::overload value before update
  sched/fair: Combine EAS check with root_domain::overutilized access
  sched/fair: Simplify the continue_balancing logic in sched_balance_newidle()
  ...

1 files changed, 36 insertions, 0 deletions

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",