Commit bb447999 authored by Dietmar Eggemann's avatar Dietmar Eggemann Committed by Peter Zijlstra
Browse files

sched, drivers: Remove max param from effective_cpu_util()/sched_cpu_util() 



effective_cpu_util() already has a `int cpu' parameter which allows to
retrieve the CPU capacity scale factor (or maximum CPU capacity) inside
this function via an arch_scale_cpu_capacity(cpu).

A lot of code calling effective_cpu_util() (or the shim
sched_cpu_util()) needs the maximum CPU capacity, i.e. it will call
arch_scale_cpu_capacity() already.
But not having to pass it into effective_cpu_util() will make the EAS
wake-up code easier, especially when the maximum CPU capacity reduced
by the thermal pressure is passed through the EAS wake-up functions.

Due to the asymmetric CPU capacity support of arm/arm64 architectures,
arch_scale_cpu_capacity(int cpu) is a per-CPU variable read access via
per_cpu(cpu_scale, cpu) on such a system.
On all other architectures it is a a compile-time constant
(SCHED_CAPACITY_SCALE).

Signed-off-by: default avatarDietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: default avatarVincent Guittot <vincent.guittot@linaro.org>
Tested-by: default avatarLukasz Luba <lukasz.luba@arm.com>
Link: https://lkml.kernel.org/r/20220621090414.433602-4-vdonnefort@google.com
parent e2f3e35f

drivers/powercap/dtpm_cpu.c

+9 −24
Original line number Diff line number Diff line
@@ -71,34 +71,19 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit) 


static u64 scale_pd_power_uw(struct cpumask *pd_mask, u64 power)

{

	unsigned long max = 0, sum_util = 0;

	unsigned long max, sum_util = 0;

	int cpu;



	for_each_cpu_and(cpu, pd_mask, cpu_online_mask) {



	/*

	 * The capacity is the same for all CPUs belonging to

		 * the same perf domain, so a single call to

		 * arch_scale_cpu_capacity() is enough. However, we

		 * need the CPU parameter to be initialized by the

		 * loop, so the call ends up in this block.

		 *

		 * We can initialize 'max' with a cpumask_first() call

		 * before the loop but the bits computation is not

		 * worth given the arch_scale_cpu_capacity() just

		 * returns a value where the resulting assembly code

		 * will be optimized by the compiler.

	 * the same perf domain.

	 */

		max = arch_scale_cpu_capacity(cpu);

		sum_util += sched_cpu_util(cpu, max);

	}

	max = arch_scale_cpu_capacity(cpumask_first(pd_mask));



	/*

	 * In the improbable case where all the CPUs of the perf

	 * domain are offline, 'max' will be zero and will lead to an

	 * illegal operation with a zero division.

	 */

	return max ? (power * ((sum_util << 10) / max)) >> 10 : 0;

	for_each_cpu_and(cpu, pd_mask, cpu_online_mask)

		sum_util += sched_cpu_util(cpu);



	return (power * ((sum_util << 10) / max)) >> 10;

}



static u64 get_pd_power_uw(struct dtpm *dtpm)

drivers/thermal/cpufreq_cooling.c

+2 −4
Original line number Diff line number Diff line
@@ -137,11 +137,9 @@ static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_cdev, 
static u32 get_load(struct cpufreq_cooling_device *cpufreq_cdev, int cpu,

		    int cpu_idx)

{

	unsigned long max = arch_scale_cpu_capacity(cpu);

	unsigned long util;

	unsigned long util = sched_cpu_util(cpu);



	util = sched_cpu_util(cpu, max);

	return (util * 100) / max;

	return (util * 100) / arch_scale_cpu_capacity(cpu);

}

#else /* !CONFIG_SMP */

static u32 get_load(struct cpufreq_cooling_device *cpufreq_cdev, int cpu,

include/linux/sched.h

+1 −1
Original line number Diff line number Diff line
@@ -2257,7 +2257,7 @@ static inline bool owner_on_cpu(struct task_struct *owner) 
}



/* Returns effective CPU energy utilization, as seen by the scheduler */

unsigned long sched_cpu_util(int cpu, unsigned long max);

unsigned long sched_cpu_util(int cpu);

#endif /* CONFIG_SMP */



#ifdef CONFIG_RSEQ

kernel/sched/core.c

+6 −5
Original line number Diff line number Diff line
@@ -7125,12 +7125,14 @@ struct task_struct *idle_task(int cpu) 
 * required to meet deadlines.

 */

unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,

				 unsigned long max, enum cpu_util_type type,

				 enum cpu_util_type type,

				 struct task_struct *p)

{

	unsigned long dl_util, util, irq;

	unsigned long dl_util, util, irq, max;

	struct rq *rq = cpu_rq(cpu);



	max = arch_scale_cpu_capacity(cpu);



	if (!uclamp_is_used() &&

	    type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) {

		return max;
@@ -7210,10 +7212,9 @@ unsigned long effective_cpu_util(int cpu, unsigned long util_cfs, 
	return min(max, util);

}



unsigned long sched_cpu_util(int cpu, unsigned long max)

unsigned long sched_cpu_util(int cpu)

{

	return effective_cpu_util(cpu, cpu_util_cfs(cpu), max,

				  ENERGY_UTIL, NULL);

	return effective_cpu_util(cpu, cpu_util_cfs(cpu), ENERGY_UTIL, NULL);

}

#endif /* CONFIG_SMP */

kernel/sched/cpufreq_schedutil.c

+2 −3
Original line number Diff line number Diff line
@@ -157,11 +157,10 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, 
static void sugov_get_util(struct sugov_cpu *sg_cpu)

{

	struct rq *rq = cpu_rq(sg_cpu->cpu);

	unsigned long max = arch_scale_cpu_capacity(sg_cpu->cpu);



	sg_cpu->max = max;

	sg_cpu->max = arch_scale_cpu_capacity(sg_cpu->cpu);

	sg_cpu->bw_dl = cpu_bw_dl(rq);

	sg_cpu->util = effective_cpu_util(sg_cpu->cpu, cpu_util_cfs(sg_cpu->cpu), max,

	sg_cpu->util = effective_cpu_util(sg_cpu->cpu, cpu_util_cfs(sg_cpu->cpu),

					  FREQUENCY_UTIL, NULL);

}