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()
  ...

4 files changed, 51 insertions, 18 deletions

diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 024b78a0cfc1..0248912ff687 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -22,7 +22,7 @@
 #include <linux/units.h>
 
 #define CREATE_TRACE_POINTS
-#include <trace/events/thermal_pressure.h>
+#include <trace/events/hw_pressure.h>
 
 static DEFINE_PER_CPU(struct scale_freq_data __rcu *, sft_data);
 static struct cpumask scale_freq_counters_mask;
@@ -160,26 +160,26 @@ void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity)
 	per_cpu(cpu_scale, cpu) = capacity;
 }
 
-DEFINE_PER_CPU(unsigned long, thermal_pressure);
+DEFINE_PER_CPU(unsigned long, hw_pressure);
 
 /**
- * topology_update_thermal_pressure() - Update thermal pressure for CPUs
+ * topology_update_hw_pressure() - Update HW pressure for CPUs
  * @cpus        : The related CPUs for which capacity has been reduced
  * @capped_freq : The maximum allowed frequency that CPUs can run at
  *
- * Update the value of thermal pressure for all @cpus in the mask. The
+ * Update the value of HW pressure for all @cpus in the mask. The
  * cpumask should include all (online+offline) affected CPUs, to avoid
  * operating on stale data when hot-plug is used for some CPUs. The
  * @capped_freq reflects the currently allowed max CPUs frequency due to
- * thermal capping. It might be also a boost frequency value, which is bigger
+ * HW capping. It might be also a boost frequency value, which is bigger
  * than the internal 'capacity_freq_ref' max frequency. In such case the
  * pressure value should simply be removed, since this is an indication that
- * there is no thermal throttling. The @capped_freq must be provided in kHz.
+ * there is no HW throttling. The @capped_freq must be provided in kHz.
  */
-void topology_update_thermal_pressure(const struct cpumask *cpus,
+void topology_update_hw_pressure(const struct cpumask *cpus,
 				      unsigned long capped_freq)
 {
-	unsigned long max_capacity, capacity, th_pressure;
+	unsigned long max_capacity, capacity, hw_pressure;
 	u32 max_freq;
 	int cpu;
 
@@ -189,21 +189,21 @@ void topology_update_thermal_pressure(const struct cpumask *cpus,
 
 	/*
 	 * Handle properly the boost frequencies, which should simply clean
-	 * the thermal pressure value.
+	 * the HW pressure value.
 	 */
 	if (max_freq <= capped_freq)
 		capacity = max_capacity;
 	else
 		capacity = mult_frac(max_capacity, capped_freq, max_freq);
 
-	th_pressure = max_capacity - capacity;
+	hw_pressure = max_capacity - capacity;
 
-	trace_thermal_pressure_update(cpu, th_pressure);
+	trace_hw_pressure_update(cpu, hw_pressure);
 
 	for_each_cpu(cpu, cpus)
-		WRITE_ONCE(per_cpu(thermal_pressure, cpu), th_pressure);
+		WRITE_ONCE(per_cpu(hw_pressure, cpu), hw_pressure);
 }
-EXPORT_SYMBOL_GPL(topology_update_thermal_pressure);
+EXPORT_SYMBOL_GPL(topology_update_hw_pressure);
 
 static ssize_t cpu_capacity_show(struct device *dev,
 				 struct device_attribute *attr,
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/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index 70b0f21968a0..ec8df5496a0c 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -347,8 +347,8 @@ static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data)
 
 	throttled_freq = freq_hz / HZ_PER_KHZ;
 
-	/* Update thermal pressure (the boost frequencies are accepted) */
-	arch_update_thermal_pressure(policy->related_cpus, throttled_freq);
+	/* Update HW pressure (the boost frequencies are accepted) */
+	arch_update_hw_pressure(policy->related_cpus, throttled_freq);
 
 	/*
 	 * In the unlikely case policy is unregistered do not enable
diff --git a/drivers/thermal/cpufreq_cooling.c b/drivers/thermal/cpufreq_cooling.c
index 9d1b1459700d..280071be30b1 100644
--- a/drivers/thermal/cpufreq_cooling.c
+++ b/drivers/thermal/cpufreq_cooling.c
@@ -477,7 +477,6 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev,
 				 unsigned long state)
 {
 	struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
-	struct cpumask *cpus;
 	unsigned int frequency;
 	int ret;
 
@@ -494,8 +493,6 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev,
 	ret = freq_qos_update_request(&cpufreq_cdev->qos_req, frequency);
 	if (ret >= 0) {
 		cpufreq_cdev->cpufreq_state = state;
-		cpus = cpufreq_cdev->policy->related_cpus;
-		arch_update_thermal_pressure(cpus, frequency);
 		ret = 0;
 	}