[tip:sched/core] sched/pelt: Skip updating util_est when utilization is higher than CPU's capacity

[tip-bot for Vincent Guittot]

Commit-ID:  10a35e6812aa0953f02a956c499d23fe4e68af4a
Gitweb:     https://git.kernel.org/tip/10a35e6812aa0953f02a956c499d23fe4e68af4a
Author:     Vincent Guittot <vincent.guittot@xxxxxxxxxx>
AuthorDate: Wed, 23 Jan 2019 16:26:54 +0100
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Mon, 4 Feb 2019 09:13:21 +0100

sched/pelt: Skip updating util_est when utilization is higher than CPU's capacity

util_est is mainly meant to be a lower-bound for tasks utilization.
That's why task_util_est() returns the actual util_avg when it's higher
than the estimated utilization.

With new invaraince signal and without any special check on samples
collection, if a task is limited because of thermal capping for
example, we could end up overestimating its utilization and thus
perhaps generating an unwanted frequency spike when the capping is
relaxed... and (even worst) it will take some more activations for the
estimated utilization to converge back to the actual utilization.

Since we cannot easily know if there is idle time in a CPU when a task
completes an activation with a utilization higher then the CPU capacity,
we skip the sampling when utilization is higher than CPU's capacity.

Suggested-by: Patrick Bellasi <patrick.bellasi@xxxxxxx>
Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Mike Galbraith <efault@xxxxxx>
Cc: Morten.Rasmussen@xxxxxxx
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: bsegall@xxxxxxxxxx
Cc: dietmar.eggemann@xxxxxxx
Cc: pjt@xxxxxxxxxx
Cc: pkondeti@xxxxxxxxxxxxxx
Cc: quentin.perret@xxxxxxx
Cc: rjw@xxxxxxxxxxxxx
Cc: srinivas.pandruvada@xxxxxxxxxxxxxxx
Cc: thara.gopinath@xxxxxxxxxx
Link: https://lkml.kernel.org/r/1548257214-13745-4-git-send-email-vincent.guittot@xxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 kernel/sched/fair.c  | 14 +++++++++-----
 kernel/sched/sched.h |  7 +++++++
 2 files changed, 16 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f41f2eec6186..8c165f0d33b3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3638,6 +3638,7 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
 {
 	long last_ewma_diff;
 	struct util_est ue;
+	int cpu;
 
 	if (!sched_feat(UTIL_EST))
 		return;
@@ -3671,6 +3672,14 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
 	if (within_margin(last_ewma_diff, (SCHED_CAPACITY_SCALE / 100)))
 		return;
 
+	/*
+	 * To avoid overestimation of actual task utilization, skip updates if
+	 * we cannot grant there is idle time in this CPU.
+	 */
+	cpu = cpu_of(rq_of(cfs_rq));
+	if (task_util(p) > capacity_orig_of(cpu))
+		return;
+
 	/*
 	 * Update Task's estimated utilization
 	 *
@@ -5542,11 +5551,6 @@ static unsigned long capacity_of(int cpu)
 	return cpu_rq(cpu)->cpu_capacity;
 }
 
-static unsigned long capacity_orig_of(int cpu)
-{
-	return cpu_rq(cpu)->cpu_capacity_orig;
-}
-
 static unsigned long cpu_avg_load_per_task(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index fe31bc472f3e..99e2a7772d16 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2230,6 +2230,13 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 # define arch_scale_freq_invariant()	false
 #endif
 
+#ifdef CONFIG_SMP
+static inline unsigned long capacity_orig_of(int cpu)
+{
+	return cpu_rq(cpu)->cpu_capacity_orig;
+}
+#endif
+
 #ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
 /**
  * enum schedutil_type - CPU utilization type