sched/uclamp: Add uclamp_util_with()

So far uclamp_util() allows to clamp a specified utilization considering
the clamp values requested by RUNNABLE tasks in a CPU. For the Energy
Aware Scheduler (EAS) it is interesting to test how clamp values will
change when a task is becoming RUNNABLE on a given CPU.
For example, EAS is interested in comparing the energy impact of
different scheduling decisions and the clamp values can play a role on
that.

Add uclamp_util_with() which allows to clamp a given utilization by
considering the possible impact on CPU clamp values of a specified task.

Signed-off-by: Patrick Bellasi <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Cc: Alessio Balsini <[email protected]>
Cc: Dietmar Eggemann <[email protected]>
Cc: Joel Fernandes <[email protected]>
Cc: Juri Lelli <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Morten Rasmussen <[email protected]>
Cc: Paul Turner <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Quentin Perret <[email protected]>
Cc: Rafael J . Wysocki <[email protected]>
Cc: Steve Muckle <[email protected]>
Cc: Suren Baghdasaryan <[email protected]>
Cc: Tejun Heo <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Todd Kjos <[email protected]>
Cc: Vincent Guittot <[email protected]>
Cc: Viresh Kumar <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

kernel/sched/core.c

@@ -880,6 +880,19 @@ uclamp_eff_get(struct task_struct *p, unsigned int clamp_id)
 	return uc_req;
 }
 
+unsigned int uclamp_eff_value(struct task_struct *p, unsigned int clamp_id)
+{
+	struct uclamp_se uc_eff;
+
+	/* Task currently refcounted: use back-annotated (effective) value */
+	if (p->uclamp[clamp_id].active)
+		return p->uclamp[clamp_id].value;
+
+	uc_eff = uclamp_eff_get(p, clamp_id);
+
+	return uc_eff.value;
+}
+
 /*
  * When a task is enqueued on a rq, the clamp bucket currently defined by the
  * task's uclamp::bucket_id is refcounted on that rq. This also immediately

kernel/sched/sched.h

@@ -2266,11 +2266,20 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #endif /* CONFIG_CPU_FREQ */
 
 #ifdef CONFIG_UCLAMP_TASK
-static inline unsigned int uclamp_util(struct rq *rq, unsigned int util)
+unsigned int uclamp_eff_value(struct task_struct *p, unsigned int clamp_id);
+
+static __always_inline
+unsigned int uclamp_util_with(struct rq *rq, unsigned int util,
+			      struct task_struct *p)
 {
 	unsigned int min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value);
 	unsigned int max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value);
 
+	if (p) {
+		min_util = max(min_util, uclamp_eff_value(p, UCLAMP_MIN));
+		max_util = max(max_util, uclamp_eff_value(p, UCLAMP_MAX));
+	}
+
 	/*
 	 * Since CPU's {min,max}_util clamps are MAX aggregated considering
 	 * RUNNABLE tasks with _different_ clamps, we can end up with an
@@ -2281,7 +2290,17 @@ static inline unsigned int uclamp_util(struct rq *rq, unsigned int util)
 
 	return clamp(util, min_util, max_util);
 }
+
+static inline unsigned int uclamp_util(struct rq *rq, unsigned int util)
+{
+	return uclamp_util_with(rq, util, NULL);
+}
 #else /* CONFIG_UCLAMP_TASK */
+static inline unsigned int uclamp_util_with(struct rq *rq, unsigned int util,
+					    struct task_struct *p)
+{
+	return util;
+}
 static inline unsigned int uclamp_util(struct rq *rq, unsigned int util)
 {
 	return util;