[PATCH 1/4] sched: cpufreq: Rename map_util_perf to apply_dvfs_headroom

[Qais Yousef]

We are providing headroom for the utilization to grow until the next
decision point to pick the next frequency. Give the function a better
name and give it some documentation. It is not really mapping anything.

Provide a dummy definition for !CONFIG_CPUFREQ which will be required
for later patches.

Signed-off-by: Qais Yousef (Google) <qyousef@xxxxxxxxxxx>
---
 include/linux/energy_model.h     |  2 +-
 include/linux/sched/cpufreq.h    | 27 ++++++++++++++++++++++++++-
 kernel/sched/cpufreq_schedutil.c |  6 +++---
 3 files changed, 30 insertions(+), 5 deletions(-)

diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index b9caa01dfac4..6ebde4e69e98 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -243,7 +243,7 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
 	scale_cpu = arch_scale_cpu_capacity(cpu);
 	ps = &pd->table[pd->nr_perf_states - 1];
 
-	max_util = map_util_perf(max_util);
+	max_util = apply_dvfs_headroom(max_util);
 	max_util = min(max_util, allowed_cpu_cap);
 	freq = map_util_freq(max_util, ps->frequency, scale_cpu);
 
diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h
index bdd31ab93bc5..f0069b354ac8 100644
--- a/include/linux/sched/cpufreq.h
+++ b/include/linux/sched/cpufreq.h
@@ -29,10 +29,35 @@ static inline unsigned long map_util_freq(unsigned long util,
 	return freq * util / cap;
 }
 
-static inline unsigned long map_util_perf(unsigned long util)
+/*
+ * DVFS decision are made at discrete points. If CPU stays busy, the util will
+ * continue to grow, which means it could need to run at a higher frequency
+ * before the next decision point was reached. IOW, we can't follow the util as
+ * it grows immediately, but there's a delay before we issue a request to go to
+ * higher frequency. The headroom caters for this delay so the system continues
+ * to run at adequate performance point.
+ *
+ * This function provides enough headroom to provide adequate performance
+ * assuming the CPU continues to be busy.
+ *
+ * At the moment it is a constant multiplication with 1.25.
+ *
+ * TODO: The headroom should be a function of the delay. 25% is too high
+ * especially on powerful systems. For example, if the delay is 500us, it makes
+ * more sense to give a small headroom as the next decision point is not far
+ * away and will follow the util if it continues to rise. On the other hand if
+ * the delay is 10ms, then we need a bigger headroom so the CPU won't struggle
+ * at a lower frequency if it never goes to idle until then.
+ */
+static inline unsigned long apply_dvfs_headroom(unsigned long util)
 {
 	return util + (util >> 2);
 }
+#else
+static inline unsigned long apply_dvfs_headroom(unsigned long util)
+{
+	return util;
+}
 #endif /* CONFIG_CPU_FREQ */
 
 #endif /* _LINUX_SCHED_CPUFREQ_H */
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 4492608b7d7f..916c4d3d6192 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -143,7 +143,7 @@ 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);
+	util = apply_dvfs_headroom(util);
 	freq = map_util_freq(util, freq, max);
 
 	if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update)
@@ -406,8 +406,8 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
 	    sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
 		sg_cpu->util = prev_util;
 
-	cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
-				   map_util_perf(sg_cpu->util), max_cap);
+	cpufreq_driver_adjust_perf(sg_cpu->cpu, apply_dvfs_headroom(sg_cpu->bw_dl),
+				   apply_dvfs_headroom(sg_cpu->util), max_cap);
 
 	sg_cpu->sg_policy->last_freq_update_time = time;
 }
-- 
2.34.1