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, 31 insertions, 23 deletions

diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index 853c4f81ba4a..ad36b6570067 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -22,9 +22,9 @@
 /* Enable topology flag updates */
 #define arch_update_cpu_topology topology_update_cpu_topology
 
-/* Replace task scheduler's default thermal pressure API */
-#define arch_scale_thermal_pressure topology_get_thermal_pressure
-#define arch_update_thermal_pressure	topology_update_thermal_pressure
+/* Replace task scheduler's default HW pressure API */
+#define arch_scale_hw_pressure topology_get_hw_pressure
+#define arch_update_hw_pressure	topology_update_hw_pressure
 
 #else
 
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index ef0058de432b..2336ee2aa44a 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -42,7 +42,7 @@
  * can take this difference into account during load balance. A per cpu
  * structure is preferred because each CPU updates its own cpu_capacity field
  * during the load balance except for idle cores. One idle core is selected
- * to run the rebalance_domains for all idle cores and the cpu_capacity can be
+ * to run the sched_balance_domains for all idle cores and the cpu_capacity can be
  * updated during this sequence.
  */
 
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index a323b109b9c4..0f6ef432fb84 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -35,9 +35,9 @@ void update_freq_counters_refs(void);
 /* Enable topology flag updates */
 #define arch_update_cpu_topology topology_update_cpu_topology
 
-/* Replace task scheduler's default thermal pressure API */
-#define arch_scale_thermal_pressure topology_get_thermal_pressure
-#define arch_update_thermal_pressure	topology_update_thermal_pressure
+/* Replace task scheduler's default HW pressure API */
+#define arch_scale_hw_pressure topology_get_hw_pressure
+#define arch_update_hw_pressure	topology_update_hw_pressure
 
 #include <asm-generic/topology.h>
 
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index 61a8d5555cd7..e5fdc336c9b2 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -6,5 +6,4 @@ generic-y += agp.h
 generic-y += kvm_types.h
 generic-y += mcs_spinlock.h
 generic-y += qrwlock.h
-generic-y += vtime.h
 generic-y += early_ioremap.h
diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index 4961fb38e438..aff858ca99c0 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -32,23 +32,10 @@
 #ifdef CONFIG_PPC64
 #define get_accounting(tsk)	(&get_paca()->accounting)
 #define raw_get_accounting(tsk)	(&local_paca->accounting)
-static inline void arch_vtime_task_switch(struct task_struct *tsk) { }
 
 #else
 #define get_accounting(tsk)	(&task_thread_info(tsk)->accounting)
 #define raw_get_accounting(tsk)	get_accounting(tsk)
-/*
- * Called from the context switch with interrupts disabled, to charge all
- * accumulated times to the current process, and to prepare accounting on
- * the next process.
- */
-static inline void arch_vtime_task_switch(struct task_struct *prev)
-{
-	struct cpu_accounting_data *acct = get_accounting(current);
-	struct cpu_accounting_data *acct0 = get_accounting(prev);
-
-	acct->starttime = acct0->starttime;
-}
 #endif
 
 /*
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index df20cf201f74..c0fdc6d94fee 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -354,6 +354,28 @@ void vtime_flush(struct task_struct *tsk)
 	acct->hardirq_time = 0;
 	acct->softirq_time = 0;
 }
+
+/*
+ * Called from the context switch with interrupts disabled, to charge all
+ * accumulated times to the current process, and to prepare accounting on
+ * the next process.
+ */
+void vtime_task_switch(struct task_struct *prev)
+{
+	if (is_idle_task(prev))
+		vtime_account_idle(prev);
+	else
+		vtime_account_kernel(prev);
+
+	vtime_flush(prev);
+
+	if (!IS_ENABLED(CONFIG_PPC64)) {
+		struct cpu_accounting_data *acct = get_accounting(current);
+		struct cpu_accounting_data *acct0 = get_accounting(prev);
+
+		acct->starttime = acct0->starttime;
+	}
+}
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 void __no_kcsan __delay(unsigned long loops)
diff --git a/arch/s390/include/asm/vtime.h b/arch/s390/include/asm/vtime.h
index fe17e448c0c5..561c91c1a87c 100644
--- a/arch/s390/include/asm/vtime.h
+++ b/arch/s390/include/asm/vtime.h
@@ -2,8 +2,6 @@
 #ifndef _S390_VTIME_H
 #define _S390_VTIME_H
 
-#define __ARCH_HAS_VTIME_TASK_SWITCH
-
 static inline void update_timer_sys(void)
 {
 	S390_lowcore.system_timer += S390_lowcore.last_update_timer - S390_lowcore.exit_timer;
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 6f71b0ce1068..259496fe0ef9 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -29,6 +29,7 @@
 #include <asm/hw_irq.h>
 #include <asm/stacktrace.h>
 #include <asm/softirq_stack.h>
+#include <asm/vtime.h>
 #include "entry.h"
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_stat, irq_stat);
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index c77382a67325..230d010bac9b 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -31,6 +31,7 @@
 #include <asm/crw.h>
 #include <asm/asm-offsets.h>
 #include <asm/pai.h>
+#include <asm/vtime.h>
 
 struct mcck_struct {
 	unsigned int kill_task : 1;