sched/debug: Add new tracepoint to track compute energy computation

It was useful to track feec() placement decision and debug the spare
capacity and optimization issues vs uclamp_max.
Signed-off-by: Qais Yousef (Google) <qyousef@layalina.io>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230916232955.2099394-4-qyousef@layalina.io

include/trace/events/sched.h

@@ -735,6 +735,11 @@ DECLARE_TRACE(sched_update_nr_running_tp,
 	TP_PROTO(struct rq *rq, int change),
 	TP_ARGS(rq, change));
 
+DECLARE_TRACE(sched_compute_energy_tp,
+	TP_PROTO(struct task_struct *p, int dst_cpu, unsigned long energy,
+		 unsigned long max_util, unsigned long busy_time),
+	TP_ARGS(p, dst_cpu, energy, max_util, busy_time));
+
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */

kernel/sched/core.c

@@ -114,6 +114,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_compute_energy_tp);
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 

kernel/sched/fair.c

@@ -7600,11 +7600,16 @@ compute_energy(struct energy_env *eenv, struct perf_domain *pd,
 {
 	unsigned long max_util = eenv_pd_max_util(eenv, pd_cpus, p, dst_cpu);
 	unsigned long busy_time = eenv->pd_busy_time;
+	unsigned long energy;
 
 	if (dst_cpu >= 0)
 		busy_time = min(eenv->pd_cap, busy_time + eenv->task_busy_time);
 
-	return em_cpu_energy(pd->em_pd, max_util, busy_time, eenv->cpu_cap);
+	energy = em_cpu_energy(pd->em_pd, max_util, busy_time, eenv->cpu_cap);
+
+	trace_sched_compute_energy_tp(p, dst_cpu, energy, max_util, busy_time);
+
+	return energy;
 }
 
 /*