}
#ifdef CONFIG_SMP
+static inline bool load_avg_is_decayed(struct sched_avg *sa)
+{
+ if (sa->load_sum)
+ return false;
+
+ if (sa->util_sum)
+ return false;
+
+ if (sa->runnable_sum)
+ return false;
+
+ /*
+ * _avg must be null when _sum are null because _avg = _sum / divider
+ * Make sure that rounding and/or propagation of PELT values never
+ * break this.
+ */
+ SCHED_WARN_ON(sa->load_avg ||
+ sa->util_avg ||
+ sa->runnable_avg);
+
+ return true;
+}
+
static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
{
return u64_u32_load_copy(cfs_rq->avg.last_update_time,
if (cfs_rq->load.weight)
return false;
- if (cfs_rq->avg.load_sum)
- return false;
-
- if (cfs_rq->avg.util_sum)
- return false;
-
- if (cfs_rq->avg.runnable_sum)
+ if (!load_avg_is_decayed(&cfs_rq->avg))
return false;
if (child_cfs_rq_on_list(cfs_rq))
return false;
- /*
- * _avg must be null when _sum are null because _avg = _sum / divider
- * Make sure that rounding and/or propagation of PELT values never
- * break this.
- */
- SCHED_WARN_ON(cfs_rq->avg.load_avg ||
- cfs_rq->avg.util_avg ||
- cfs_rq->avg.runnable_avg);
-
return true;
}
#endif /* CONFIG_FAIR_GROUP_SCHED */
+#ifdef CONFIG_NO_HZ_COMMON
+static inline void migrate_se_pelt_lag(struct sched_entity *se)
+{
+ u64 throttled = 0, now, lut;
+ struct cfs_rq *cfs_rq;
+ struct rq *rq;
+ bool is_idle;
+
+ if (load_avg_is_decayed(&se->avg))
+ return;
+
+ cfs_rq = cfs_rq_of(se);
+ rq = rq_of(cfs_rq);
+
+ rcu_read_lock();
+ is_idle = is_idle_task(rcu_dereference(rq->curr));
+ rcu_read_unlock();
+
+ /*
+ * The lag estimation comes with a cost we don't want to pay all the
+ * time. Hence, limiting to the case where the source CPU is idle and
+ * we know we are at the greatest risk to have an outdated clock.
+ */
+ if (!is_idle)
+ return;
+
+ /*
+ * Estimated "now" is: last_update_time + cfs_idle_lag + rq_idle_lag, where:
+ *
+ * last_update_time (the cfs_rq's last_update_time)
+ * = cfs_rq_clock_pelt()@cfs_rq_idle
+ * = rq_clock_pelt()@cfs_rq_idle
+ * - cfs->throttled_clock_pelt_time@cfs_rq_idle
+ *
+ * cfs_idle_lag (delta between rq's update and cfs_rq's update)
+ * = rq_clock_pelt()@rq_idle - rq_clock_pelt()@cfs_rq_idle
+ *
+ * rq_idle_lag (delta between now and rq's update)
+ * = sched_clock_cpu() - rq_clock()@rq_idle
+ *
+ * We can then write:
+ *
+ * now = rq_clock_pelt()@rq_idle - cfs->throttled_clock_pelt_time +
+ * sched_clock_cpu() - rq_clock()@rq_idle
+ * Where:
+ * rq_clock_pelt()@rq_idle is rq->clock_pelt_idle
+ * rq_clock()@rq_idle is rq->clock_idle
+ * cfs->throttled_clock_pelt_time@cfs_rq_idle
+ * is cfs_rq->throttled_pelt_idle
+ */
+
+#ifdef CONFIG_CFS_BANDWIDTH
+ throttled = u64_u32_load(cfs_rq->throttled_pelt_idle);
+ /* The clock has been stopped for throttling */
+ if (throttled == U64_MAX)
+ return;
+#endif
+ now = u64_u32_load(rq->clock_pelt_idle);
+ /*
+ * Paired with _update_idle_rq_clock_pelt(). It ensures at the worst case
+ * is observed the old clock_pelt_idle value and the new clock_idle,
+ * which lead to an underestimation. The opposite would lead to an
+ * overestimation.
+ */
+ smp_rmb();
+ lut = cfs_rq_last_update_time(cfs_rq);
+
+ now -= throttled;
+ if (now < lut)
+ /*
+ * cfs_rq->avg.last_update_time is more recent than our
+ * estimation, let's use it.
+ */
+ now = lut;
+ else
+ now += sched_clock_cpu(cpu_of(rq)) - u64_u32_load(rq->clock_idle);
+
+ __update_load_avg_blocked_se(now, se);
+}
+#else
+static void migrate_se_pelt_lag(struct sched_entity *se) {}
+#endif
+
/**
* update_cfs_rq_load_avg - update the cfs_rq's load/util averages
* @now: current time, as per cfs_rq_clock_pelt()
*/
if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) != DEQUEUE_SAVE)
update_min_vruntime(cfs_rq);
+
+ if (cfs_rq->nr_running == 0)
+ update_idle_cfs_rq_clock_pelt(cfs_rq);
}
/*
*/
static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
{
+ struct sched_entity *se = &p->se;
+
/*
* As blocked tasks retain absolute vruntime the migration needs to
* deal with this by subtracting the old and adding the new
* the task on the new runqueue.
*/
if (READ_ONCE(p->__state) == TASK_WAKING) {
- struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
se->vruntime -= u64_u32_load(cfs_rq->min_vruntime);
* rq->lock and can modify state directly.
*/
lockdep_assert_rq_held(task_rq(p));
- detach_entity_cfs_rq(&p->se);
+ detach_entity_cfs_rq(se);
} else {
+ remove_entity_load_avg(se);
+
/*
- * We are supposed to update the task to "current" time, then
- * its up to date and ready to go to new CPU/cfs_rq. But we
- * have difficulty in getting what current time is, so simply
- * throw away the out-of-date time. This will result in the
- * wakee task is less decayed, but giving the wakee more load
- * sounds not bad.
+ * Here, the task's PELT values have been updated according to
+ * the current rq's clock. But if that clock hasn't been
+ * updated in a while, a substantial idle time will be missed,
+ * leading to an inflation after wake-up on the new rq.
+ *
+ * Estimate the missing time from the cfs_rq last_update_time
+ * and update sched_avg to improve the PELT continuity after
+ * migration.
*/
- remove_entity_load_avg(&p->se);
+ migrate_se_pelt_lag(se);
}
/* Tell new CPU we are migrated */
- p->se.avg.last_update_time = 0;
+ se->avg.last_update_time = 0;
/* We have migrated, no longer consider this task hot */
- p->se.exec_start = 0;
+ se->exec_start = 0;
update_scan_period(p, new_cpu);
}
if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq)) {
update_tg_load_avg(cfs_rq);
+ if (cfs_rq->nr_running == 0)
+ update_idle_cfs_rq_clock_pelt(cfs_rq);
+
if (cfs_rq == &rq->cfs)
decayed = true;
}
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
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;
}
*/
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)
{
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));
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
projects / platform / kernel / linux-starfive.git / commitdiff