static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
#endif /* CONFIG_FAIR_GROUP_SCHED */
+static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
+{
+ if (&this_rq()->cfs == cfs_rq) {
+ /*
+ * There are a few boundary cases this might miss but it should
+ * get called often enough that that should (hopefully) not be
+ * a real problem -- added to that it only calls on the local
+ * CPU, so if we enqueue remotely we'll miss an update, but
+ * the next tick/schedule should update.
+ *
+ * It will not get called when we go idle, because the idle
+ * thread is a different class (!fair), nor will the utilization
+ * number include things like RT tasks.
+ *
+ * As is, the util number is not freq-invariant (we'd have to
+ * implement arch_scale_freq_capacity() for that).
+ *
+ * See cpu_util().
+ */
+ cpufreq_update_util(rq_of(cfs_rq), 0);
+ }
+}
+
static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
/*
} while (0)
/* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */
-static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
+static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq,
+ bool update_freq)
{
struct sched_avg *sa = &cfs_rq->avg;
- int decayed, removed = 0;
+ int decayed, removed = 0, removed_util = 0;
if (atomic_long_read(&cfs_rq->removed_load_avg)) {
s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0);
sub_positive(&sa->util_avg, r);
sub_positive(&sa->util_sum, r * LOAD_AVG_MAX);
+ removed_util = 1;
}
decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
if (cfs_rq == &rq_of(cfs_rq)->cfs)
trace_sched_load_avg_cpu(cpu_of(rq_of(cfs_rq)), cfs_rq);
+ if (update_freq && (decayed || removed_util))
+ cfs_rq_util_change(cfs_rq);
+
return decayed || removed;
}
se->on_rq * scale_load_down(se->load.weight),
cfs_rq->curr == se, NULL);
- if (update_cfs_rq_load_avg(now, cfs_rq) && update_tg)
+ if (update_cfs_rq_load_avg(now, cfs_rq, true) && update_tg)
update_tg_load_avg(cfs_rq, 0);
if (entity_is_task(se))
cfs_rq->avg.load_sum += se->avg.load_sum;
cfs_rq->avg.util_avg += se->avg.util_avg;
cfs_rq->avg.util_sum += se->avg.util_sum;
+
+ cfs_rq_util_change(cfs_rq);
}
static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum);
sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
+
+ cfs_rq_util_change(cfs_rq);
}
/* Add the load generated by se into cfs_rq's load average */
cfs_rq->curr == se, NULL);
}
- decayed = update_cfs_rq_load_avg(now, cfs_rq);
+ decayed = update_cfs_rq_load_avg(now, cfs_rq, !migrated);
cfs_rq->runnable_load_avg += sa->load_avg;
cfs_rq->runnable_load_sum += sa->load_sum;
#else /* CONFIG_SMP */
-static inline void update_load_avg(struct sched_entity *se, int update_tg) {}
+static inline void update_load_avg(struct sched_entity *se, int update_tg)
+{
+ cpufreq_update_util(rq_of(cfs_rq_of(se)), 0);
+}
+
static inline void
enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
static inline void
if (!cfs_bandwidth_used())
return;
+ /* Synchronize hierarchical throttle counter: */
+ if (unlikely(!cfs_rq->throttle_uptodate)) {
+ struct rq *rq = rq_of(cfs_rq);
+ struct cfs_rq *pcfs_rq;
+ struct task_group *tg;
+
+ cfs_rq->throttle_uptodate = 1;
+
+ /* Get closest up-to-date node, because leaves go first: */
+ for (tg = cfs_rq->tg->parent; tg; tg = tg->parent) {
+ pcfs_rq = tg->cfs_rq[cpu_of(rq)];
+ if (pcfs_rq->throttle_uptodate)
+ break;
+ }
+ if (tg) {
+ cfs_rq->throttle_count = pcfs_rq->throttle_count;
+ cfs_rq->throttled_clock_task = rq_clock_task(rq);
+ }
+ }
+
/* an active group must be handled by the update_curr()->put() path */
if (!cfs_rq->runtime_enabled || cfs_rq->curr)
return;
#ifdef CONFIG_SMP
static bool cpu_overutilized(int cpu);
-static inline unsigned long boosted_cpu_util(int cpu);
+unsigned long boosted_cpu_util(int cpu);
#else
#define boosted_cpu_util(cpu) cpu_util(cpu)
#endif
int task_wakeup = flags & ENQUEUE_WAKEUP;
#endif
+ /*
+ * If in_iowait is set, the code below may not trigger any cpufreq
+ * utilization updates, so do it here explicitly with the IOWAIT flag
+ * passed.
+ */
+ if (p->in_iowait)
+ cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_IOWAIT);
+
for_each_sched_entity(se) {
if (se->on_rq)
break;
/* Don't dequeue parent if it has other entities besides us */
if (cfs_rq->load.weight) {
+ /* Avoid re-evaluating load for this entity: */
+ se = parent_entity(se);
/*
* Bias pick_next to pick a task from this cfs_rq, as
* p is sleeping when it is within its sched_slice.
*/
- if (task_sleep && parent_entity(se))
- set_next_buddy(parent_entity(se));
-
- /* avoid re-evaluating load for this entity */
- se = parent_entity(se);
+ if (task_sleep && se && !throttled_hierarchy(cfs_rq))
+ set_next_buddy(se);
break;
}
flags |= DEQUEUE_SLEEP;
return __task_fits(p, cpu, 0);
}
-static inline bool task_fits_spare(struct task_struct *p, int cpu)
-{
- return __task_fits(p, cpu, cpu_util(cpu));
-}
-
static bool cpu_overutilized(int cpu)
{
return (capacity_of(cpu) * 1024) < (cpu_util(cpu) * capacity_margin);
#endif /* CONFIG_SCHED_TUNE */
-static inline unsigned long
+unsigned long
boosted_cpu_util(int cpu)
{
unsigned long util = cpu_util(cpu);
int this_cpu, int sd_flag)
{
struct sched_group *idlest = NULL, *group = sd->groups;
- struct sched_group *fit_group = NULL, *spare_group = NULL;
unsigned long min_load = ULONG_MAX, this_load = 0;
- unsigned long fit_capacity = ULONG_MAX;
- unsigned long max_spare_capacity = capacity_margin - SCHED_LOAD_SCALE;
int load_idx = sd->forkexec_idx;
int imbalance = 100 + (sd->imbalance_pct-100)/2;
load_idx = sd->wake_idx;
do {
- unsigned long load, avg_load, spare_capacity;
+ unsigned long load, avg_load;
int local_group;
int i;
load = target_load(i, load_idx);
avg_load += load;
-
- /*
- * Look for most energy-efficient group that can fit
- * that can fit the task.
- */
- if (capacity_of(i) < fit_capacity && task_fits_spare(p, i)) {
- fit_capacity = capacity_of(i);
- fit_group = group;
- }
-
- /*
- * Look for group which has most spare capacity on a
- * single cpu.
- */
- spare_capacity = capacity_of(i) - cpu_util(i);
- if (spare_capacity > max_spare_capacity) {
- max_spare_capacity = spare_capacity;
- spare_group = group;
- }
}
/* Adjust by relative CPU capacity of the group */
}
} while (group = group->next, group != sd->groups);
- if (fit_group)
- return fit_group;
-
- if (spare_group)
- return spare_group;
-
if (!idlest || 100*this_load < imbalance*min_load)
return NULL;
return idlest;
/* Traverse only the allowed CPUs */
for_each_cpu_and(i, sched_group_cpus(group), tsk_cpus_allowed(p)) {
- if (task_fits_spare(p, i)) {
+ if (idle_cpu(i)) {
struct rq *rq = cpu_rq(i);
struct cpuidle_state *idle = idle_get_state(rq);
if (idle && idle->exit_latency < min_exit_latency) {
min_exit_latency = idle->exit_latency;
latest_idle_timestamp = rq->idle_stamp;
shallowest_idle_cpu = i;
- } else if (idle_cpu(i) &&
- (!idle || idle->exit_latency == min_exit_latency) &&
+ } else if ((!idle || idle->exit_latency == min_exit_latency) &&
rq->idle_stamp > latest_idle_timestamp) {
/*
* If equal or no active idle state, then
*/
latest_idle_timestamp = rq->idle_stamp;
shallowest_idle_cpu = i;
- } else if (shallowest_idle_cpu == -1) {
- /*
- * If we haven't found an idle CPU yet
- * pick a non-idle one that can fit the task as
- * fallback.
- */
- shallowest_idle_cpu = i;
}
} else if (shallowest_idle_cpu == -1) {
load = weighted_cpuload(i);
int sync = wake_flags & WF_SYNC;
if (sd_flag & SD_BALANCE_WAKE)
- want_affine = (!wake_wide(p) && task_fits_max(p, cpu) &&
- cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) ||
+ want_affine = (!wake_wide(p) && cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) ||
energy_aware();
rcu_read_lock();
if (throttled_hierarchy(cfs_rq))
continue;
- if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq))
+ if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq,
+ true))
update_tg_load_avg(cfs_rq, 0);
}
raw_spin_unlock_irqrestore(&rq->lock, flags);
raw_spin_lock_irqsave(&rq->lock, flags);
update_rq_clock(rq);
- update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq);
+ update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq, true);
raw_spin_unlock_irqrestore(&rq->lock, flags);
}