[PATCH 6/7] sched/cpufreq: uclamp: add utilization clamping for FAIR tasks

[Patrick Bellasi]

Each time a frequency update is required via schedutil, a frequency is
selected to (possibly) satisfy the utilization reported by the CFS
class. However, when utilization clamping is in use, the frequency
selection should consider the requirements suggested by userspace, for
example, to:

 - boost tasks which are directly affecting the user experience
   by running them at least at a minimum "required" frequency

 - cap low priority tasks not directly affecting the user experience
   by running them only up to a maximum "allowed" frequency

These constraints are meant to support a per-task based tuning of the
operating frequency selection thus allowing to have a fine grained
definition of performance boosting vs energy saving strategies in kernel
space.

Let's add the required support to clamp the utilization generated by
FAIR tasks within the boundaries defined by their aggregated utilization
clamp constraints.
On each CPU the aggregated clamp values are obtained by considering the
maximum of the {min,max}_util values for each task. This max aggregation
responds to the goal of not penalizing, for example, high boosted (i.e.
more important for the user-experience) CFS tasks which happens to be
co-scheduled with high capped (i.e. less important for the
user-experience) CFS tasks.

For FAIR tasks both the utilization as well as the IOWait boot values
are clamped according to the CPU aggregated utilization clamp
constraints.

The default values for boosting and capping are defined to be:
 - util_min: 0
 - util_max: SCHED_CAPACITY_SCALE
which means that by default no boosting/capping is enforced on FAIR
tasks, and thus the frequency will be selected considering the actual
utilization value of each CPU.

Signed-off-by: Patrick Bellasi <patrick.bellasi@xxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
Cc: Viresh Kumar <viresh.kumar@xxxxxxxxxx>
Cc: Joel Fernandes <joelaf@xxxxxxxxxx>
Cc: Juri Lelli <juri.lelli@xxxxxxxxxx>
Cc: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
Cc: Morten Rasmussen <morten.rasmussen@xxxxxxx>
Cc: linux-kernel@xxxxxxxxxxxxxxx
Cc: linux-pm@xxxxxxxxxxxxxxx
---
 kernel/sched/cpufreq_schedutil.c | 29 ++++++++++++++------
 kernel/sched/sched.h             | 59 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 80 insertions(+), 8 deletions(-)

diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index e021db562308..fe53984d06a0 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -190,7 +190,7 @@ static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
 	} else {
 		util = sg_cpu->util_dl;
 		if (rq->cfs.h_nr_running)
-			util += sg_cpu->util_cfs;
+			util += uclamp_util(sg_cpu->cpu, sg_cpu->util_cfs);
 	}
 
 	/*
@@ -213,6 +213,7 @@ static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
  */
 static void sugov_set_iowait_boost(struct sugov_cpu *sg_cpu, unsigned int flags)
 {
+	unsigned int max_boost;
 
 	/* Boost only tasks waking up after IO */
 	if (!(flags & SCHED_CPUFREQ_IOWAIT))
@@ -223,16 +224,28 @@ static void sugov_set_iowait_boost(struct sugov_cpu *sg_cpu, unsigned int flags)
 		return;
 	sg_cpu->iowait_boost_pending = true;
 
-	/* Double the IO boost at each frequency increase */
-	if (sg_cpu->iowait_boost) {
-		sg_cpu->iowait_boost <<= 1;
-		if (sg_cpu->iowait_boost > sg_cpu->iowait_boost_max)
-			sg_cpu->iowait_boost = sg_cpu->iowait_boost_max;
+	/* At first wakeup after IO, start with minimum boost */
+	if (!sg_cpu->iowait_boost) {
+		sg_cpu->iowait_boost = sg_cpu->sg_policy->policy->min;
 		return;
 	}
 
-	/* At first wakeup after IO, start with minimum boost */
-	sg_cpu->iowait_boost = sg_cpu->sg_policy->policy->min;
+	/*
+	 * Boost only up to the current max CPU clamped utilization.
+	 *
+	 * Since DL tasks have a much more advanced bandwidth control, it's
+	 * safe to assume that IO boost does not apply to those tasks.
+	 * Instead, since for RT tasks we are going to max, we don't want to
+	 * clamp the IO boost max value.
+	 */
+	max_boost = sg_cpu->iowait_boost_max;
+	if (!cpu_rq(sg_cpu->cpu)->rt.rt_nr_running)
+		max_boost = uclamp_util(sg_cpu->cpu, max_boost);
+
+	/* Double the IO boost at each frequency increase */
+	sg_cpu->iowait_boost <<= 1;
+	if (sg_cpu->iowait_boost > max_boost)
+		sg_cpu->iowait_boost = max_boost;
 }
 
 /**
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index a91b9cd162a3..1aa5d9b93fa5 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2268,6 +2268,65 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
 static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #endif /* CONFIG_CPU_FREQ */
 
+#ifdef CONFIG_UCLAMP_TASK
+/**
+ * uclamp_value: get the current CPU's utilization clamp value
+ * @cpu: the CPU to consider
+ * @clamp_id: the utilization clamp index (i.e. min or max utilization)
+ *
+ * The utilization clamp value for a CPU depends on its set of currently
+ * active tasks and their specific util_{min,max} constraints.
+ * A max aggregated value is tracked for each CPU and returned by this
+ * function. An IDLE CPU never enforces a clamp value.
+ *
+ * Return: the current value for the specified CPU and clamp index
+ */
+static inline unsigned int uclamp_value(unsigned int cpu, int clamp_id)
+{
+	struct uclamp_cpu *uc_cpu = &cpu_rq(cpu)->uclamp[clamp_id];
+	int clamp_value = uclamp_none(clamp_id);
+
+	/* Update min utilization clamp */
+	if (uc_cpu->value != UCLAMP_NONE)
+		clamp_value = uc_cpu->value;
+
+	return clamp_value;
+}
+
+/**
+ * clamp_util: clamp a utilization value for a specified CPU
+ * @cpu: the CPU to get the clamp values from
+ * @util: the utilization signal to clamp
+ *
+ * Each CPU tracks util_{min,max} clamp values depending on the set of its
+ * currently active tasks. Given a utilization signal, i.e a signal in the
+ * [0..SCHED_CAPACITY_SCALE] range, this function returns a clamped
+ * utilization signal considering the current clamp values for the
+ * specified CPU.
+ *
+ * Return: a clamped utilization signal for a given CPU.
+ */
+static inline unsigned int uclamp_util(unsigned int cpu, unsigned int util)
+{
+	unsigned int min_util = uclamp_value(cpu, UCLAMP_MIN);
+	unsigned int max_util = uclamp_value(cpu, UCLAMP_MAX);
+
+	return clamp(util, min_util, max_util);
+}
+#else /* CONFIG_UCLAMP_TASK */
+static inline unsigned int uclamp_value(unsigned int cpu, int clamp_id)
+{
+	if (clamp_id == UCLAMP_MIN)
+		return 0;
+	return SCHED_CAPACITY_SCALE;
+}
+
+static inline unsigned int uclamp_util(unsigned int cpu, unsigned int util)
+{
+	return util;
+}
+#endif /* CONFIG_UCLAMP_TASK */
+
 #ifdef arch_scale_freq_capacity
 # ifndef arch_scale_freq_invariant
 #  define arch_scale_freq_invariant()	true
-- 
2.15.1