From 14ff4dbd34f46cc6b6105f549983321241ccbba9 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 8 Mar 2024 12:18:10 +0100 Subject: sched/balancing: Rename rebalance_domains() => sched_balance_domains() Standardize scheduler load-balancing function names on the sched_balance_() prefix. Signed-off-by: Ingo Molnar Reviewed-by: Shrikanth Hegde Link: https://lore.kernel.org/r/20240308111819.1101550-5-mingo@kernel.org --- arch/arm/kernel/topology.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') 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. */ -- cgit v1.2.3-70-g09d2 From 89d6910cc562ab34d1f1c08f3cf0a9700b8bf2c4 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 10 Apr 2024 17:09:45 +0200 Subject: sched/vtime: Get rid of generic vtime_task_switch() implementation The generic vtime_task_switch() implementation gets built only if __ARCH_HAS_VTIME_TASK_SWITCH is not defined, but requires an architecture to implement arch_vtime_task_switch() callback at the same time, which is confusing. Further, arch_vtime_task_switch() is implemented for 32-bit PowerPC architecture only and vtime_task_switch() generic variant is rather superfluous. Simplify the whole vtime_task_switch() wiring by moving the existing generic implementation to PowerPC. Signed-off-by: Alexander Gordeev Signed-off-by: Ingo Molnar Reviewed-by: Frederic Weisbecker Reviewed-by: Nicholas Piggin Acked-by: Michael Ellerman Link: https://lore.kernel.org/r/2cb6e3caada93623f6d4f78ad938ac6cd0e2fda8.1712760275.git.agordeev@linux.ibm.com --- arch/powerpc/include/asm/cputime.h | 13 ------------- arch/powerpc/kernel/time.c | 22 ++++++++++++++++++++++ kernel/sched/cputime.c | 13 ------------- 3 files changed, 22 insertions(+), 26 deletions(-) (limited to 'arch') 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/kernel/sched/cputime.c b/kernel/sched/cputime.c index af7952f12e6c..aa48b2ec879d 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -424,19 +424,6 @@ static inline void irqtime_account_process_tick(struct task_struct *p, int user_ */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -# ifndef __ARCH_HAS_VTIME_TASK_SWITCH -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); - arch_vtime_task_switch(prev); -} -# endif - void vtime_account_irq(struct task_struct *tsk, unsigned int offset) { unsigned int pc = irq_count() - offset; -- cgit v1.2.3-70-g09d2 From 60b8edba142e4ba3c3060431760dd803bd90ffa1 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 10 Apr 2024 17:09:46 +0200 Subject: s390/vtime: Remove unused __ARCH_HAS_VTIME_TASK_SWITCH leftover __ARCH_HAS_VTIME_TASK_SWITCH macro is not used anymore. Signed-off-by: Alexander Gordeev Signed-off-by: Ingo Molnar Reviewed-by: Frederic Weisbecker Acked-by: Heiko Carstens Acked-by: Nicholas Piggin Link: https://lore.kernel.org/r/b1055852eab0ffea33ad16c92d6a825c83037c3e.1712760275.git.agordeev@linux.ibm.com --- arch/s390/include/asm/vtime.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch') 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; -- cgit v1.2.3-70-g09d2 From 036cbbafbd1eb2a7437912c2fe5fdefc9d52c309 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 10 Apr 2024 17:09:47 +0200 Subject: s390/irq,nmi: Include header directly update_timer_sys() and update_timer_mcck() are inlines used for CPU time accounting from the interrupt and machine-check handlers. These routines are specific to s390 architecture, but included via header implicitly. Avoid the extra loop and include header directly. Signed-off-by: Alexander Gordeev Signed-off-by: Ingo Molnar Acked-by: Heiko Carstens Link: https://lore.kernel.org/r/3fb696637c0eb7e9d6ffd6cbf9e647d7c5986b3d.1712760275.git.agordeev@linux.ibm.com --- arch/s390/kernel/irq.c | 1 + arch/s390/kernel/nmi.c | 1 + 2 files changed, 2 insertions(+) (limited to 'arch') 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 #include #include +#include #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 #include #include +#include struct mcck_struct { unsigned int kill_task : 1; -- cgit v1.2.3-70-g09d2 From 08a36a48544d73bf153960245aec6c5fa23960de Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 10 Apr 2024 17:09:48 +0200 Subject: sched/vtime: Do not include header There is no architecture-specific code or data left that generic needs to know about. Thus, avoid the inclusion of header. Signed-off-by: Alexander Gordeev Signed-off-by: Ingo Molnar Reviewed-by: Frederic Weisbecker Acked-by: Nicholas Piggin Link: https://lore.kernel.org/r/f7cd245668b9ae61a55184871aec494ec9199c4a.1712760275.git.agordeev@linux.ibm.com --- arch/powerpc/include/asm/Kbuild | 1 - include/asm-generic/vtime.h | 1 - include/linux/vtime.h | 4 ---- 3 files changed, 6 deletions(-) delete mode 100644 include/asm-generic/vtime.h (limited to 'arch') 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/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/vtime.h b/include/linux/vtime.h index 593466ceebed..29dd5b91dd7d 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -5,10 +5,6 @@ #include #include -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -#include -#endif - /* * Common vtime APIs */ -- cgit v1.2.3-70-g09d2 From d4dbc991714eefcbd8d54a3204bd77a0a52bd32d Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Tue, 26 Mar 2024 10:16:15 +0100 Subject: sched/cpufreq: Rename arch_update_thermal_pressure() => arch_update_hw_pressure() Now that cpufreq provides a pressure value to the scheduler, rename arch_update_thermal_pressure into HW pressure to reflect that it returns a pressure applied by HW (i.e. with a high frequency change) and not always related to thermal mitigation but also generated by max current limitation as an example. Such high frequency signal needs filtering to be smoothed and provide an value that reflects the average available capacity into the scheduler time scale. Signed-off-by: Vincent Guittot Signed-off-by: Ingo Molnar Tested-by: Lukasz Luba Reviewed-by: Qais Yousef Reviewed-by: Lukasz Luba Link: https://lore.kernel.org/r/20240326091616.3696851-5-vincent.guittot@linaro.org --- arch/arm/include/asm/topology.h | 6 +++--- arch/arm64/include/asm/topology.h | 6 +++--- drivers/base/arch_topology.c | 26 +++++++++++++------------- drivers/cpufreq/qcom-cpufreq-hw.c | 4 ++-- include/linux/arch_topology.h | 8 ++++---- include/linux/sched/topology.h | 8 ++++---- include/trace/events/hw_pressure.h | 29 +++++++++++++++++++++++++++++ include/trace/events/sched.h | 2 +- include/trace/events/thermal_pressure.h | 29 ----------------------------- init/Kconfig | 12 ++++++------ kernel/sched/core.c | 8 ++++---- kernel/sched/fair.c | 16 ++++++++-------- kernel/sched/pelt.c | 18 +++++++++--------- kernel/sched/pelt.h | 16 ++++++++-------- kernel/sched/sched.h | 10 +++++----- 15 files changed, 99 insertions(+), 99 deletions(-) create mode 100644 include/trace/events/hw_pressure.h delete mode 100644 include/trace/events/thermal_pressure.h (limited to 'arch') 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/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 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 #define CREATE_TRACE_POINTS -#include +#include 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/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/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/sched/topology.h b/include/linux/sched/topology.h index c8fe9bab981b..4237daa5ac7a 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -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/trace/events/hw_pressure.h b/include/trace/events/hw_pressure.h new file mode 100644 index 000000000000..b9cd68854128 --- /dev/null +++ b/include/trace/events/hw_pressure.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM hw_pressure + +#if !defined(_TRACE_THERMAL_PRESSURE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_THERMAL_PRESSURE_H + +#include + +TRACE_EVENT(hw_pressure_update, + TP_PROTO(int cpu, unsigned long hw_pressure), + TP_ARGS(cpu, hw_pressure), + + TP_STRUCT__entry( + __field(unsigned long, hw_pressure) + __field(int, cpu) + ), + + TP_fast_assign( + __entry->hw_pressure = hw_pressure; + __entry->cpu = cpu; + ), + + TP_printk("cpu=%d hw_pressure=%lu", __entry->cpu, __entry->hw_pressure) +); +#endif /* _TRACE_THERMAL_PRESSURE_H */ + +/* This part must be outside protection */ +#include diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index dbb01b4b7451..d115d64c4011 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -752,7 +752,7 @@ 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)); diff --git a/include/trace/events/thermal_pressure.h b/include/trace/events/thermal_pressure.h deleted file mode 100644 index b68680201360..000000000000 --- a/include/trace/events/thermal_pressure.h +++ /dev/null @@ -1,29 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#undef TRACE_SYSTEM -#define TRACE_SYSTEM thermal_pressure - -#if !defined(_TRACE_THERMAL_PRESSURE_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_THERMAL_PRESSURE_H - -#include - -TRACE_EVENT(thermal_pressure_update, - TP_PROTO(int cpu, unsigned long thermal_pressure), - TP_ARGS(cpu, thermal_pressure), - - TP_STRUCT__entry( - __field(unsigned long, thermal_pressure) - __field(int, cpu) - ), - - TP_fast_assign( - __entry->thermal_pressure = thermal_pressure; - __entry->cpu = cpu; - ), - - TP_printk("cpu=%d thermal_pressure=%lu", __entry->cpu, __entry->thermal_pressure) -); -#endif /* _TRACE_THERMAL_PRESSURE_H */ - -/* This part must be outside protection */ -#include diff --git a/init/Kconfig b/init/Kconfig index aa02aec6aa7d..f0c9117962ec 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -547,24 +547,24 @@ config HAVE_SCHED_AVG_IRQ depends on IRQ_TIME_ACCOUNTING || PARAVIRT_TIME_ACCOUNTING depends on SMP -config SCHED_THERMAL_PRESSURE +config SCHED_HW_PRESSURE bool default y if ARM && ARM_CPU_TOPOLOGY default y if ARM64 depends on SMP depends on CPU_FREQ_THERMAL help - Select this option to enable thermal pressure accounting in the - scheduler. Thermal pressure is the value conveyed to the scheduler + Select this option to enable HW pressure accounting in the + scheduler. HW pressure is the value conveyed to the scheduler that reflects the reduction in CPU compute capacity resulted from - thermal throttling. Thermal throttling occurs when the performance of - a CPU is capped due to high operating temperatures. + HW throttling. HW throttling occurs when the performance of + a CPU is capped due to high operating temperatures as an example. If selected, the scheduler will be able to balance tasks accordingly, i.e. put less load on throttled CPUs than on non/less throttled ones. This requires the architecture to implement - arch_update_thermal_pressure() and arch_scale_thermal_pressure(). + arch_update_hw_pressure() and arch_scale_thermal_pressure(). config BSD_PROCESS_ACCT bool "BSD Process Accounting" diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0621e4ee31de..67a8302c3131 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -108,7 +108,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_rt_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_dl_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp); -EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_thermal_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_hw_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_cpu_capacity_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp); @@ -5668,7 +5668,7 @@ void sched_tick(void) struct rq *rq = cpu_rq(cpu); struct task_struct *curr = rq->curr; struct rq_flags rf; - unsigned long thermal_pressure; + unsigned long hw_pressure; u64 resched_latency; if (housekeeping_cpu(cpu, HK_TYPE_TICK)) @@ -5679,8 +5679,8 @@ void sched_tick(void) rq_lock(rq, &rf); update_rq_clock(rq); - thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq)); - update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure); + hw_pressure = arch_scale_hw_pressure(cpu_of(rq)); + update_hw_load_avg(rq_clock_hw(rq), rq, hw_pressure); curr->sched_class->task_tick(rq, curr, 0); if (sched_feat(LATENCY_WARN)) resched_latency = cpu_resched_latency(rq); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 19199c119829..eef39ae3efcf 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -78,7 +78,7 @@ static unsigned int normalized_sysctl_sched_base_slice = 750000ULL; const_debug unsigned int sysctl_sched_migration_cost = 500000UL; -int sched_thermal_decay_shift; +int sched_hw_decay_shift; static int __init setup_sched_thermal_decay_shift(char *str) { int _shift = 0; @@ -86,7 +86,7 @@ static int __init setup_sched_thermal_decay_shift(char *str) if (kstrtoint(str, 0, &_shift)) pr_warn("Unable to set scheduler thermal pressure decay shift parameter\n"); - sched_thermal_decay_shift = clamp(_shift, 0, 10); + sched_hw_decay_shift = clamp(_shift, 0, 10); return 1; } __setup("sched_thermal_decay_shift=", setup_sched_thermal_decay_shift); @@ -4969,7 +4969,7 @@ static inline unsigned long get_actual_cpu_capacity(int cpu) { unsigned long capacity = arch_scale_cpu_capacity(cpu); - capacity -= max(thermal_load_avg(cpu_rq(cpu)), cpufreq_get_pressure(cpu)); + capacity -= max(hw_load_avg(cpu_rq(cpu)), cpufreq_get_pressure(cpu)); return capacity; } @@ -5002,7 +5002,7 @@ static inline int util_fits_cpu(unsigned long util, * Similarly if a task is capped to arch_scale_cpu_capacity(little_cpu), it * should fit a little cpu even if there's some pressure. * - * Only exception is for thermal pressure since it has a direct impact + * Only exception is for HW or cpufreq pressure since it has a direct impact * on available OPP of the system. * * We honour it for uclamp_min only as a drop in performance level @@ -9324,7 +9324,7 @@ static inline bool others_have_blocked(struct rq *rq) if (cpu_util_dl(rq)) return true; - if (thermal_load_avg(rq)) + if (hw_load_avg(rq)) return true; if (cpu_util_irq(rq)) @@ -9354,7 +9354,7 @@ static bool __update_blocked_others(struct rq *rq, bool *done) { const struct sched_class *curr_class; u64 now = rq_clock_pelt(rq); - unsigned long thermal_pressure; + unsigned long hw_pressure; bool decayed; /* @@ -9363,11 +9363,11 @@ static bool __update_blocked_others(struct rq *rq, bool *done) */ curr_class = rq->curr->sched_class; - thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq)); + hw_pressure = arch_scale_hw_pressure(cpu_of(rq)); decayed = update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) | update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) | - update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure) | + update_hw_load_avg(rq_clock_hw(rq), rq, hw_pressure) | update_irq_load_avg(rq, 0); if (others_have_blocked(rq)) diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c index 3a96da25b67c..ef00382de595 100644 --- a/kernel/sched/pelt.c +++ b/kernel/sched/pelt.c @@ -384,30 +384,30 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running) return 0; } -#ifdef CONFIG_SCHED_THERMAL_PRESSURE +#ifdef CONFIG_SCHED_HW_PRESSURE /* - * thermal: + * hardware: * * load_sum = \Sum se->avg.load_sum but se->avg.load_sum is not tracked * * util_avg and runnable_load_avg are not supported and meaningless. * * Unlike rt/dl utilization tracking that track time spent by a cpu - * running a rt/dl task through util_avg, the average thermal pressure is - * tracked through load_avg. This is because thermal pressure signal is + * running a rt/dl task through util_avg, the average HW pressure is + * tracked through load_avg. This is because HW pressure signal is * time weighted "delta" capacity unlike util_avg which is binary. * "delta capacity" = actual capacity - - * capped capacity a cpu due to a thermal event. + * capped capacity a cpu due to a HW event. */ -int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity) +int update_hw_load_avg(u64 now, struct rq *rq, u64 capacity) { - if (___update_load_sum(now, &rq->avg_thermal, + if (___update_load_sum(now, &rq->avg_hw, capacity, capacity, capacity)) { - ___update_load_avg(&rq->avg_thermal, 1); - trace_pelt_thermal_tp(rq); + ___update_load_avg(&rq->avg_hw, 1); + trace_pelt_hw_tp(rq); return 1; } diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h index 9e1083465fbc..2150062949d4 100644 --- a/kernel/sched/pelt.h +++ b/kernel/sched/pelt.h @@ -7,21 +7,21 @@ int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq); int update_rt_rq_load_avg(u64 now, struct rq *rq, int running); int update_dl_rq_load_avg(u64 now, struct rq *rq, int running); -#ifdef CONFIG_SCHED_THERMAL_PRESSURE -int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity); +#ifdef CONFIG_SCHED_HW_PRESSURE +int update_hw_load_avg(u64 now, struct rq *rq, u64 capacity); -static inline u64 thermal_load_avg(struct rq *rq) +static inline u64 hw_load_avg(struct rq *rq) { - return READ_ONCE(rq->avg_thermal.load_avg); + return READ_ONCE(rq->avg_hw.load_avg); } #else static inline int -update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity) +update_hw_load_avg(u64 now, struct rq *rq, u64 capacity) { return 0; } -static inline u64 thermal_load_avg(struct rq *rq) +static inline u64 hw_load_avg(struct rq *rq) { return 0; } @@ -202,12 +202,12 @@ update_dl_rq_load_avg(u64 now, struct rq *rq, int running) } static inline int -update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity) +update_hw_load_avg(u64 now, struct rq *rq, u64 capacity) { return 0; } -static inline u64 thermal_load_avg(struct rq *rq) +static inline u64 hw_load_avg(struct rq *rq) { return 0; } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 7c39dbf31f75..993edb02fb0d 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1108,8 +1108,8 @@ struct rq { #ifdef CONFIG_HAVE_SCHED_AVG_IRQ struct sched_avg avg_irq; #endif -#ifdef CONFIG_SCHED_THERMAL_PRESSURE - struct sched_avg avg_thermal; +#ifdef CONFIG_SCHED_HW_PRESSURE + struct sched_avg avg_hw; #endif u64 idle_stamp; u64 avg_idle; @@ -1561,11 +1561,11 @@ static inline u64 rq_clock_task(struct rq *rq) * 3 256 * 4 512 */ -extern int sched_thermal_decay_shift; +extern int sched_hw_decay_shift; -static inline u64 rq_clock_thermal(struct rq *rq) +static inline u64 rq_clock_hw(struct rq *rq) { - return rq_clock_task(rq) >> sched_thermal_decay_shift; + return rq_clock_task(rq) >> sched_hw_decay_shift; } static inline void rq_clock_skip_update(struct rq *rq) -- cgit v1.2.3-70-g09d2