@@ -20,6 +20,12 @@ void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data,
void (*func)(struct update_util_data *data, u64 time,
unsigned int flags));
void cpufreq_remove_update_util_hook(int cpu);
+
+static inline unsigned long map_util_freq(unsigned long util,
+ unsigned long freq, unsigned long cap)
+{
+ return (freq + (freq >> 2)) * util / cap;
+}
#endif /* CONFIG_CPU_FREQ */
#endif /* _LINUX_SCHED_CPUFREQ_H */
@@ -13,6 +13,7 @@
#include "sched.h"
+#include <linux/sched/cpufreq.h>
#include <trace/events/power.h>
struct sugov_tunables {
@@ -167,7 +168,7 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
unsigned int freq = arch_scale_freq_invariant() ?
policy->cpuinfo.max_freq : policy->cur;
- freq = (freq + (freq >> 2)) * util / max;
+ freq = map_util_freq(util, freq, max);
if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update)
return sg_policy->next_freq;
@@ -197,15 +198,13 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
* based on the task model parameters and gives the minimal utilization
* required to meet deadlines.
*/
-static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
+unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs,
+ unsigned long max, enum schedutil_type type)
{
- struct rq *rq = cpu_rq(sg_cpu->cpu);
- unsigned long util, irq, max;
-
- sg_cpu->max = max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
- sg_cpu->bw_dl = cpu_bw_dl(rq);
+ struct rq *rq = cpu_rq(cpu);
+ unsigned long util, irq;
- if (rt_rq_is_runnable(&rq->rt))
+ if (type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt))
return max;
/*
@@ -223,20 +222,33 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
* utilization (PELT windows are synchronized) we can directly add them
* to obtain the CPU's actual utilization.
*/
- util = cpu_util_cfs(rq);
+ util = util_cfs;
util += cpu_util_rt(rq);
- /*
- * We do not make cpu_util_dl() a permanent part of this sum because we
- * want to use cpu_bw_dl() later on, but we need to check if the
- * CFS+RT+DL sum is saturated (ie. no idle time) such that we select
- * f_max when there is no idle time.
- *
- * NOTE: numerical errors or stop class might cause us to not quite hit
- * saturation when we should -- something for later.
- */
- if ((util + cpu_util_dl(rq)) >= max)
- return max;
+ if (type == FREQUENCY_UTIL) {
+ /*
+ * For frequency selection we do not make cpu_util_dl() a
+ * permanent part of this sum because we want to use
+ * cpu_bw_dl() later on, but we need to check if the
+ * CFS+RT+DL sum is saturated (ie. no idle time) such
+ * that we select f_max when there is no idle time.
+ *
+ * NOTE: numerical errors or stop class might cause us
+ * to not quite hit saturation when we should --
+ * something for later.
+ */
+
+ if ((util + cpu_util_dl(rq)) >= max)
+ return max;
+ } else {
+ /*
+ * OTOH, for energy computation we need the estimated
+ * running time, so include util_dl and ignore dl_bw.
+ */
+ util += cpu_util_dl(rq);
+ if (util >= max)
+ return max;
+ }
/*
* There is still idle time; further improve the number by using the
@@ -250,17 +262,35 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
util = scale_irq_capacity(util, irq, max);
util += irq;
- /*
- * Bandwidth required by DEADLINE must always be granted while, for
- * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism
- * to gracefully reduce the frequency when no tasks show up for longer
- * periods of time.
- *
- * Ideally we would like to set bw_dl as min/guaranteed freq and util +
- * bw_dl as requested freq. However, cpufreq is not yet ready for such
- * an interface. So, we only do the latter for now.
- */
- return min(max, util + sg_cpu->bw_dl);
+ if (type == FREQUENCY_UTIL) {
+ /*
+ * Bandwidth required by DEADLINE must always be granted
+ * while, for FAIR and RT, we use blocked utilization of
+ * IDLE CPUs as a mechanism to gracefully reduce the
+ * frequency when no tasks show up for longer periods of
+ * time.
+ *
+ * Ideally we would like to set bw_dl as min/guaranteed
+ * freq and util + bw_dl as requested freq. However,
+ * cpufreq is not yet ready for such an interface. So,
+ * we only do the latter for now.
+ */
+ util += cpu_bw_dl(rq);
+ }
+
+ return min(max, util);
+}
+
+static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
+{
+ struct rq *rq = cpu_rq(sg_cpu->cpu);
+ unsigned long util = cpu_util_cfs(rq);
+ unsigned long max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
+
+ sg_cpu->max = max;
+ sg_cpu->bw_dl = cpu_bw_dl(rq);
+
+ return schedutil_freq_util(sg_cpu->cpu, util, max, FREQUENCY_UTIL);
}
/**
@@ -2173,6 +2173,31 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
#endif
#ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
+/**
+ * enum schedutil_type - CPU utilization type
+ * @FREQUENCY_UTIL: Utilization used to select frequency
+ * @ENERGY_UTIL: Utilization used during energy calculation
+ *
+ * The utilization signals of all scheduling classes (CFS/RT/DL) and IRQ time
+ * need to be aggregated differently depending on the usage made of them. This
+ * enum is used within schedutil_freq_util() to differentiate the types of
+ * utilization expected by the callers, and adjust the aggregation accordingly.
+ */
+enum schedutil_type {
+ FREQUENCY_UTIL,
+ ENERGY_UTIL,
+};
+
+unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs,
+ unsigned long max, enum schedutil_type type);
+
+static inline unsigned long schedutil_energy_util(int cpu, unsigned long cfs)
+{
+ unsigned long max = arch_scale_cpu_capacity(NULL, cpu);
+
+ return schedutil_freq_util(cpu, cfs, max, ENERGY_UTIL);
+}
+
static inline unsigned long cpu_bw_dl(struct rq *rq)
{
return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT;
@@ -2199,6 +2224,11 @@ static inline unsigned long cpu_util_rt(struct rq *rq)
{
return READ_ONCE(rq->avg_rt.util_avg);
}
+#else /* CONFIG_CPU_FREQ_GOV_SCHEDUTIL */
+static inline unsigned long schedutil_energy_util(int cpu, unsigned long cfs)
+{
+ return cfs;
+}
#endif
#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
Schedutil requests frequency by aggregating utilization signals from the scheduler (CFS, RT, DL, IRQ) and applying a 25% margin on top of them. Since Energy Aware Scheduling (EAS) needs to be able to predict the frequency requests, it needs to forecast the decisions made by the governor. In order to prepare the introduction of EAS, introduce schedutil_freq_util() to centralize the aforementioned signal aggregation and make it available to both schedutil and EAS. Since frequency selection and energy estimation still need to deal with RT and DL signals slightly differently, schedutil_freq_util() is called with a different 'type' parameter in those two contexts, and returns an aggregated utilization signal accordingly. While at it, introduce the map_util_freq() function which is designed to make schedutil's 25% margin usable easily for both sugov and EAS. As EAS will be able to predict schedutil's frequency requests more accurately than any other governor by design, it'd be sensible to make sure EAS cannot be used without schedutil. This will be done later, once EAS has actually been introduced. Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Suggested-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Quentin Perret <quentin.perret@arm.com> --- include/linux/sched/cpufreq.h | 6 +++ kernel/sched/cpufreq_schedutil.c | 92 +++++++++++++++++++++----------- kernel/sched/sched.h | 30 +++++++++++ 3 files changed, 97 insertions(+), 31 deletions(-)