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()
  ...

9 files changed, 30 insertions, 25 deletions

diff --git a/include/asm-generic/vtime.h b/include/asm-generic/vtime.h
deleted file mode 100644
index b1a49677fe25..000000000000
--- a/include/asm-generic/vtime.h
+++ /dev/null
@@ -1 +0,0 @@
-/* no content, but patch(1) dislikes empty files */
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index a63d61ca55af..b721f360d759 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -60,14 +60,14 @@ void topology_scale_freq_tick(void);
 void topology_set_scale_freq_source(struct scale_freq_data *data, const struct cpumask *cpus);
 void topology_clear_scale_freq_source(enum scale_freq_source source, const struct cpumask *cpus);
 
-DECLARE_PER_CPU(unsigned long, thermal_pressure);
+DECLARE_PER_CPU(unsigned long, hw_pressure);
 
-static inline unsigned long topology_get_thermal_pressure(int cpu)
+static inline unsigned long topology_get_hw_pressure(int cpu)
 {
-	return per_cpu(thermal_pressure, cpu);
+	return per_cpu(hw_pressure, cpu);
 }
 
-void topology_update_thermal_pressure(const struct cpumask *cpus,
+void topology_update_hw_pressure(const struct cpumask *cpus,
 				      unsigned long capped_freq);
 
 struct cpu_topology {
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
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3c2abbc587b4..c75fd46506df 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -301,7 +301,7 @@ enum {
 	TASK_COMM_LEN = 16,
 };
 
-extern void scheduler_tick(void);
+extern void sched_tick(void);
 
 #define	MAX_SCHEDULE_TIMEOUT		LONG_MAX
 
@@ -835,6 +835,7 @@ struct task_struct {
 #endif
 
 	unsigned int			policy;
+	unsigned long			max_allowed_capacity;
 	int				nr_cpus_allowed;
 	const cpumask_t			*cpus_ptr;
 	cpumask_t			*user_cpus_ptr;
diff --git a/include/linux/sched/idle.h b/include/linux/sched/idle.h
index 478084f9105e..e670ac282333 100644
--- a/include/linux/sched/idle.h
+++ b/include/linux/sched/idle.h
@@ -5,8 +5,8 @@
 #include <linux/sched.h>
 
 enum cpu_idle_type {
+	__CPU_NOT_IDLE = 0,
 	CPU_IDLE,
-	CPU_NOT_IDLE,
 	CPU_NEWLY_IDLE,
 	CPU_MAX_IDLE_TYPES
 };
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 18572c9ea724..4237daa5ac7a 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -110,7 +110,7 @@ struct sched_domain {
 	unsigned long last_decay_max_lb_cost;
 
 #ifdef CONFIG_SCHEDSTATS
-	/* load_balance() stats */
+	/* sched_balance_rq() stats */
 	unsigned int lb_count[CPU_MAX_IDLE_TYPES];
 	unsigned int lb_failed[CPU_MAX_IDLE_TYPES];
 	unsigned int lb_balanced[CPU_MAX_IDLE_TYPES];
@@ -270,17 +270,17 @@ unsigned long arch_scale_cpu_capacity(int cpu)
 }
 #endif
 
-#ifndef arch_scale_thermal_pressure
+#ifndef arch_scale_hw_pressure
 static __always_inline
-unsigned long arch_scale_thermal_pressure(int cpu)
+unsigned long arch_scale_hw_pressure(int cpu)
 {
 	return 0;
 }
 #endif
 
-#ifndef arch_update_thermal_pressure
+#ifndef arch_update_hw_pressure
 static __always_inline
-void arch_update_thermal_pressure(const struct cpumask *cpus,
+void arch_update_hw_pressure(const struct cpumask *cpus,
 				  unsigned long capped_frequency)
 { }
 #endif
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index 3684487d01e1..29dd5b91dd7d 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -5,10 +5,6 @@
 #include <linux/context_tracking_state.h>
 #include <linux/sched.h>
 
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-#include <asm/vtime.h>
-#endif
-
 /*
  * Common vtime APIs
  */
@@ -18,7 +14,6 @@ extern void vtime_account_idle(struct task_struct *tsk);
 #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-extern void arch_vtime_task_switch(struct task_struct *tsk);
 extern void vtime_user_enter(struct task_struct *tsk);
 extern void vtime_user_exit(struct task_struct *tsk);
 extern void vtime_guest_enter(struct task_struct *tsk);
diff --git a/include/trace/events/thermal_pressure.h b/include/trace/events/hw_pressure.h
index b68680201360..b9cd68854128 100644
--- a/include/trace/events/thermal_pressure.h
+++ b/include/trace/events/hw_pressure.h
@@ -1,27 +1,27 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #undef TRACE_SYSTEM
-#define TRACE_SYSTEM thermal_pressure
+#define TRACE_SYSTEM hw_pressure
 
 #if !defined(_TRACE_THERMAL_PRESSURE_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_THERMAL_PRESSURE_H
 
 #include <linux/tracepoint.h>
 
-TRACE_EVENT(thermal_pressure_update,
-	TP_PROTO(int cpu, unsigned long thermal_pressure),
-	TP_ARGS(cpu, thermal_pressure),
+TRACE_EVENT(hw_pressure_update,
+	TP_PROTO(int cpu, unsigned long hw_pressure),
+	TP_ARGS(cpu, hw_pressure),
 
 	TP_STRUCT__entry(
-		__field(unsigned long, thermal_pressure)
+		__field(unsigned long, hw_pressure)
 		__field(int, cpu)
 	),
 
 	TP_fast_assign(
-		__entry->thermal_pressure = thermal_pressure;
+		__entry->hw_pressure = hw_pressure;
 		__entry->cpu = cpu;
 	),
 
-	TP_printk("cpu=%d thermal_pressure=%lu", __entry->cpu, __entry->thermal_pressure)
+	TP_printk("cpu=%d hw_pressure=%lu", __entry->cpu, __entry->hw_pressure)
 );
 #endif /* _TRACE_THERMAL_PRESSURE_H */
 
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 226f47c6939c..68973f650c26 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -787,7 +787,7 @@ DECLARE_TRACE(pelt_dl_tp,
 	TP_PROTO(struct rq *rq),
 	TP_ARGS(rq));
 
-DECLARE_TRACE(pelt_thermal_tp,
+DECLARE_TRACE(pelt_hw_tp,
 	TP_PROTO(struct rq *rq),
 	TP_ARGS(rq));