sched/fair: jump to max OPP when crossing UP threshold

Since the true utilization of a long running task is not detectable
while it is running and might be bigger than the current cpu capacity,
create the maximum cpu capacity head room by requesting the maximum
cpu capacity once the cpu usage plus the capacity margin exceeds the
current capacity. This is also done to try to harm the performance of
a task the least.

Original fair-class only version authored by Juri Lelli
<juri.lelli@arm.com>.

cc: Ingo Molnar <mingo@redhat.com>
cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
Signed-off-by: Steve Muckle <smuckle@linaro.org>

1 files changed, 41 insertions, 0 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 569a2f0f01e4..573dcb62b3b3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2854,6 +2854,45 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 	return ns;
 }
 
+#ifdef CONFIG_CPU_FREQ_GOV_SCHED
+static unsigned long sum_capacity_reqs(unsigned long cfs_cap,
+				       struct sched_capacity_reqs *scr)
+{
+	unsigned long total = cfs_cap + scr->rt;
+
+	total = total * capacity_margin;
+	total /= SCHED_CAPACITY_SCALE;
+	total += scr->dl;
+	return total;
+}
+
+static void sched_freq_tick(int cpu)
+{
+	struct sched_capacity_reqs *scr;
+	unsigned long capacity_orig, capacity_curr;
+
+	if (!sched_freq())
+		return;
+
+	capacity_orig = capacity_orig_of(cpu);
+	capacity_curr = capacity_curr_of(cpu);
+	if (capacity_curr == capacity_orig)
+		return;
+
+	/*
+	 * To make free room for a task that is building up its "real"
+	 * utilization and to harm its performance the least, request
+	 * a jump to max OPP as soon as the margin of free capacity is
+	 * impacted (specified by capacity_margin).
+	 */
+	scr = &per_cpu(cpu_sched_capacity_reqs, cpu);
+	if (capacity_curr < sum_capacity_reqs(cpu_util(cpu), scr))
+		set_cfs_cpu_capacity(cpu, true, capacity_max);
+}
+#else
+static inline void sched_freq_tick(int cpu) { }
+#endif
+
 /*
  * This function gets called by the timer code, with HZ frequency.
  * We call it with interrupts disabled.
@@ -2880,6 +2919,8 @@ void scheduler_tick(void)
 	trigger_load_balance(rq);
 #endif
 	rq_last_tick_reset(rq);
+
+	sched_freq_tick(cpu);
 }
 
 #ifdef CONFIG_NO_HZ_FULL