diff options
-rw-r--r-- | include/linux/energy_model.h | 16 | ||||
-rw-r--r-- | include/linux/sched/cpufreq.h | 2 | ||||
-rw-r--r-- | kernel/sched/cpufreq_schedutil.c | 1 | ||||
-rw-r--r-- | kernel/sched/fair.c | 2 |
4 files changed, 16 insertions, 5 deletions
diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 757fc60658fa..3f221dbf5f95 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -91,6 +91,8 @@ void em_dev_unregister_perf_domain(struct device *dev); * @pd : performance domain for which energy has to be estimated * @max_util : highest utilization among CPUs of the domain * @sum_util : sum of the utilization of all CPUs in the domain + * @allowed_cpu_cap : maximum allowed CPU capacity for the @pd, which + might reflect reduced frequency (due to thermal) * * This function must be used only for CPU devices. There is no validation, * i.e. if the EM is a CPU type and has cpumask allocated. It is called from @@ -100,7 +102,8 @@ void em_dev_unregister_perf_domain(struct device *dev); * a capacity state satisfying the max utilization of the domain. */ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, - unsigned long max_util, unsigned long sum_util) + unsigned long max_util, unsigned long sum_util, + unsigned long allowed_cpu_cap) { unsigned long freq, scale_cpu; struct em_perf_state *ps; @@ -112,11 +115,17 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, /* * In order to predict the performance state, map the utilization of * the most utilized CPU of the performance domain to a requested - * frequency, like schedutil. + * frequency, like schedutil. Take also into account that the real + * frequency might be set lower (due to thermal capping). Thus, clamp + * max utilization to the allowed CPU capacity before calculating + * effective frequency. */ cpu = cpumask_first(to_cpumask(pd->cpus)); scale_cpu = arch_scale_cpu_capacity(cpu); ps = &pd->table[pd->nr_perf_states - 1]; + + max_util = map_util_perf(max_util); + max_util = min(max_util, allowed_cpu_cap); freq = map_util_freq(max_util, ps->frequency, scale_cpu); /* @@ -209,7 +218,8 @@ static inline struct em_perf_domain *em_pd_get(struct device *dev) return NULL; } static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, - unsigned long max_util, unsigned long sum_util) + unsigned long max_util, unsigned long sum_util, + unsigned long allowed_cpu_cap) { return 0; } diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h index 6205578ab6ee..bdd31ab93bc5 100644 --- a/include/linux/sched/cpufreq.h +++ b/include/linux/sched/cpufreq.h @@ -26,7 +26,7 @@ bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy); static inline unsigned long map_util_freq(unsigned long util, unsigned long freq, unsigned long cap) { - return (freq + (freq >> 2)) * util / cap; + return freq * util / cap; } static inline unsigned long map_util_perf(unsigned long util) diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 4f09afd2f321..57124614363d 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -151,6 +151,7 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, unsigned int freq = arch_scale_freq_invariant() ? policy->cpuinfo.max_freq : policy->cur; + util = map_util_perf(util); freq = map_util_freq(util, freq, max); if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 0d6d190accb0..ed7df1b9cba9 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6592,7 +6592,7 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) max_util = max(max_util, min(cpu_util, _cpu_cap)); } - return em_cpu_energy(pd->em_pd, max_util, sum_util); + return em_cpu_energy(pd->em_pd, max_util, sum_util, _cpu_cap); } /* |