@@ -68,27 +68,59 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit)
return power_limit;
}
+static u64 scale_pd_power_uw(struct cpumask *pd_mask, u64 power)
+{
+ unsigned long max = 0, 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.
+ */
+ return max ? (power * ((sum_util << 10) / max)) >> 10 : 0;
+}
+
static u64 get_pd_power_uw(struct dtpm *dtpm)
{
struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm);
struct em_perf_domain *pd;
- struct cpumask cpus;
+ struct cpumask *pd_mask;
unsigned long freq;
- int i, nr_cpus;
+ int i;
pd = em_cpu_get(dtpm_cpu->cpu);
- freq = cpufreq_quick_get(dtpm_cpu->cpu);
- cpumask_and(&cpus, cpu_online_mask, to_cpumask(pd->cpus));
- nr_cpus = cpumask_weight(&cpus);
+ pd_mask = em_span_cpus(pd);
+
+ freq = cpufreq_quick_get(dtpm_cpu->cpu);
for (i = 0; i < pd->nr_perf_states; i++) {
if (pd->table[i].frequency < freq)
continue;
- return pd->table[i].power *
- MICROWATT_PER_MILLIWATT * nr_cpus;
+ return scale_pd_power_uw(pd_mask, pd->table[i].power *
+ MICROWATT_PER_MILLIWATT);
}
return 0;