From bb4479994945e9170534389a7762eb56149320ac Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Tue, 21 Jun 2022 10:04:10 +0100 Subject: 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: Dietmar Eggemann Signed-off-by: Peter Zijlstra (Intel) Acked-by: Vincent Guittot Tested-by: Lukasz Luba Link: https://lkml.kernel.org/r/20220621090414.433602-4-vdonnefort@google.com --- drivers/powercap/dtpm_cpu.c | 33 +++++++++------------------------ drivers/thermal/cpufreq_cooling.c | 6 ++---- 2 files changed, 11 insertions(+), 28 deletions(-) (limited to 'drivers') diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c index f5eced0842b3..6a88eb7e9f75 100644 --- a/drivers/powercap/dtpm_cpu.c +++ b/drivers/powercap/dtpm_cpu.c @@ -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. - */ - max = arch_scale_cpu_capacity(cpu); - sum_util += sched_cpu_util(cpu, max); - } - /* - * 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. + * The capacity is the same for all CPUs belonging to + * the same perf domain. */ - return max ? (power * ((sum_util << 10) / max)) >> 10 : 0; + max = arch_scale_cpu_capacity(cpumask_first(pd_mask)); + + 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) diff --git a/drivers/thermal/cpufreq_cooling.c b/drivers/thermal/cpufreq_cooling.c index b8151d95a806..b263b0fde03c 100644 --- a/drivers/thermal/cpufreq_cooling.c +++ b/drivers/thermal/cpufreq_cooling.c @@ -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, -- cgit v1.2.3