sched/fair: Decay task PELT values during wakeup migration

Before being migrated to a new CPU, a task sees its PELT values
synchronized with rq last_update_time. Once done, that same task will also
have its sched_avg last_update_time reset. This means the time between
the migration and the last clock update will not be accounted for in
util_avg and a discontinuity will appear. This issue is amplified by the
PELT clock scaling. It takes currently one tick after the CPU being idle
to let clock_pelt catching up clock_task.

This is especially problematic for asymmetric CPU capacity systems which
need stable util_avg signals for task placement and energy estimation.

Ideally, this problem would be solved by updating the runqueue clocks
before the migration. But that would require taking the runqueue lock
which is quite expensive [1]. Instead estimate the missing time and update
the task util_avg with that value.

To that end, we need sched_clock_cpu() but it is a costly function. Limit
the usage to the case where the source CPU is idle as we know this is when
the clock is having the biggest risk of being outdated.

See comment in migrate_se_pelt_lag() for more details about how the PELT
value is estimated. Notice though this estimation doesn't take into account
IRQ and Paravirt time.

[1] https://lkml.kernel.org/r/20190709115759.10451-1-chris.redpath@arm.com

Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://lkml.kernel.org/r/20220621090414.433602-3-vdonnefort@google.com

1 files changed, 33 insertions, 7 deletions

diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
index 4ff2ed4f8fa1..3a0e0dc28721 100644
--- a/kernel/sched/pelt.h
+++ b/kernel/sched/pelt.h
@@ -61,6 +61,25 @@ static inline void cfs_se_util_change(struct sched_avg *avg)
 	WRITE_ONCE(avg->util_est.enqueued, enqueued);
 }
 
+static inline u64 rq_clock_pelt(struct rq *rq)
+{
+	lockdep_assert_rq_held(rq);
+	assert_clock_updated(rq);
+
+	return rq->clock_pelt - rq->lost_idle_time;
+}
+
+/* The rq is idle, we can sync to clock_task */
+static inline void _update_idle_rq_clock_pelt(struct rq *rq)
+{
+	rq->clock_pelt  = rq_clock_task(rq);
+
+	u64_u32_store(rq->clock_idle, rq_clock(rq));
+	/* Paired with smp_rmb in migrate_se_pelt_lag() */
+	smp_wmb();
+	u64_u32_store(rq->clock_pelt_idle, rq_clock_pelt(rq));
+}
+
 /*
  * The clock_pelt scales the time to reflect the effective amount of
  * computation done during the running delta time but then sync back to
@@ -76,8 +95,7 @@ static inline void cfs_se_util_change(struct sched_avg *avg)
 static inline void update_rq_clock_pelt(struct rq *rq, s64 delta)
 {
 	if (unlikely(is_idle_task(rq->curr))) {
-		/* The rq is idle, we can sync to clock_task */
-		rq->clock_pelt  = rq_clock_task(rq);
+		_update_idle_rq_clock_pelt(rq);
 		return;
 	}
 
@@ -130,17 +148,23 @@ static inline void update_idle_rq_clock_pelt(struct rq *rq)
 	 */
 	if (util_sum >= divider)
 		rq->lost_idle_time += rq_clock_task(rq) - rq->clock_pelt;
+
+	_update_idle_rq_clock_pelt(rq);
 }
 
-static inline u64 rq_clock_pelt(struct rq *rq)
+#ifdef CONFIG_CFS_BANDWIDTH
+static inline void update_idle_cfs_rq_clock_pelt(struct cfs_rq *cfs_rq)
 {
-	lockdep_assert_rq_held(rq);
-	assert_clock_updated(rq);
+	u64 throttled;
 
-	return rq->clock_pelt - rq->lost_idle_time;
+	if (unlikely(cfs_rq->throttle_count))
+		throttled = U64_MAX;
+	else
+		throttled = cfs_rq->throttled_clock_pelt_time;
+
+	u64_u32_store(cfs_rq->throttled_pelt_idle, throttled);
 }
 
-#ifdef CONFIG_CFS_BANDWIDTH
 /* rq->task_clock normalized against any time this cfs_rq has spent throttled */
 static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq)
 {
@@ -150,6 +174,7 @@ static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq)
 	return rq_clock_pelt(rq_of(cfs_rq)) - cfs_rq->throttled_clock_pelt_time;
 }
 #else
+static inline void update_idle_cfs_rq_clock_pelt(struct cfs_rq *cfs_rq) { }
 static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq)
 {
 	return rq_clock_pelt(rq_of(cfs_rq));
@@ -204,6 +229,7 @@ update_rq_clock_pelt(struct rq *rq, s64 delta) { }
 static inline void
 update_idle_rq_clock_pelt(struct rq *rq) { }
 
+static inline void update_idle_cfs_rq_clock_pelt(struct cfs_rq *cfs_rq) { }
 #endif