static struct numa_group *deref_task_numa_group(struct task_struct *p)
{
return rcu_dereference_check(p->numa_group, p == current ||
- (lockdep_is_held(&task_rq(p)->lock) && !READ_ONCE(p->on_cpu)));
+ (lockdep_is_held(__rq_lockp(task_rq(p))) && !READ_ONCE(p->on_cpu)));
}
static struct numa_group *deref_curr_numa_group(struct task_struct *p)
{
struct task_group *tg;
- lockdep_assert_held(&rq->lock);
+ lockdep_assert_rq_held(rq);
rcu_read_lock();
list_for_each_entry_rcu(tg, &task_groups, list) {
{
struct task_group *tg;
- lockdep_assert_held(&rq->lock);
+ lockdep_assert_rq_held(rq);
rcu_read_lock();
list_for_each_entry_rcu(tg, &task_groups, list) {
}
if (has_idle_core)
- set_idle_cores(this, false);
+ set_idle_cores(target, false);
if (sched_feat(SIS_PROP) && !has_idle_core) {
time = cpu_clock(this) - time;
task_util = uclamp_task_util(p);
}
+ /*
+ * per-cpu select_idle_mask usage
+ */
+ lockdep_assert_irqs_disabled();
+
if ((available_idle_cpu(target) || sched_idle_cpu(target)) &&
asym_fits_capacity(task_util, target))
return target;
{
unsigned long prev_delta = ULONG_MAX, best_delta = ULONG_MAX;
struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
+ int cpu, best_energy_cpu = prev_cpu, target = -1;
unsigned long cpu_cap, util, base_energy = 0;
- int cpu, best_energy_cpu = prev_cpu;
struct sched_domain *sd;
struct perf_domain *pd;
rcu_read_lock();
pd = rcu_dereference(rd->pd);
if (!pd || READ_ONCE(rd->overutilized))
- goto fail;
+ goto unlock;
/*
* Energy-aware wake-up happens on the lowest sched_domain starting
while (sd && !cpumask_test_cpu(prev_cpu, sched_domain_span(sd)))
sd = sd->parent;
if (!sd)
- goto fail;
+ goto unlock;
+
+ target = prev_cpu;
sync_entity_load_avg(&p->se);
if (!task_util_est(p))
for (; pd; pd = pd->next) {
unsigned long cur_delta, spare_cap, max_spare_cap = 0;
+ bool compute_prev_delta = false;
unsigned long base_energy_pd;
int max_spare_cap_cpu = -1;
- /* Compute the 'base' energy of the pd, without @p */
- base_energy_pd = compute_energy(p, -1, pd);
- base_energy += base_energy_pd;
-
for_each_cpu_and(cpu, perf_domain_span(pd), sched_domain_span(sd)) {
if (!cpumask_test_cpu(cpu, p->cpus_ptr))
continue;
if (!fits_capacity(util, cpu_cap))
continue;
- /* Always use prev_cpu as a candidate. */
if (cpu == prev_cpu) {
- prev_delta = compute_energy(p, prev_cpu, pd);
- prev_delta -= base_energy_pd;
- best_delta = min(best_delta, prev_delta);
- }
-
- /*
- * Find the CPU with the maximum spare capacity in
- * the performance domain
- */
- if (spare_cap > max_spare_cap) {
+ /* Always use prev_cpu as a candidate. */
+ compute_prev_delta = true;
+ } else if (spare_cap > max_spare_cap) {
+ /*
+ * Find the CPU with the maximum spare capacity
+ * in the performance domain.
+ */
max_spare_cap = spare_cap;
max_spare_cap_cpu = cpu;
}
}
- /* Evaluate the energy impact of using this CPU. */
- if (max_spare_cap_cpu >= 0 && max_spare_cap_cpu != prev_cpu) {
+ if (max_spare_cap_cpu < 0 && !compute_prev_delta)
+ continue;
+
+ /* Compute the 'base' energy of the pd, without @p */
+ base_energy_pd = compute_energy(p, -1, pd);
+ base_energy += base_energy_pd;
+
+ /* Evaluate the energy impact of using prev_cpu. */
+ if (compute_prev_delta) {
+ prev_delta = compute_energy(p, prev_cpu, pd);
+ if (prev_delta < base_energy_pd)
+ goto unlock;
+ prev_delta -= base_energy_pd;
+ best_delta = min(best_delta, prev_delta);
+ }
+
+ /* Evaluate the energy impact of using max_spare_cap_cpu. */
+ if (max_spare_cap_cpu >= 0) {
cur_delta = compute_energy(p, max_spare_cap_cpu, pd);
+ if (cur_delta < base_energy_pd)
+ goto unlock;
cur_delta -= base_energy_pd;
if (cur_delta < best_delta) {
best_delta = cur_delta;
}
}
}
-unlock:
rcu_read_unlock();
/*
* Pick the best CPU if prev_cpu cannot be used, or if it saves at
* least 6% of the energy used by prev_cpu.
*/
- if (prev_delta == ULONG_MAX)
- return best_energy_cpu;
-
- if ((prev_delta - best_delta) > ((prev_delta + base_energy) >> 4))
- return best_energy_cpu;
+ if ((prev_delta == ULONG_MAX) ||
+ (prev_delta - best_delta) > ((prev_delta + base_energy) >> 4))
+ target = best_energy_cpu;
- return prev_cpu;
+ return target;
-fail:
+unlock:
rcu_read_unlock();
- return -1;
+ return target;
}
/*
* certain conditions an idle sibling CPU if the domain has SD_WAKE_AFFINE set.
*
* Returns the target CPU number.
- *
- * preempt must be disabled.
*/
static int
select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags)
/* SD_flags and WF_flags share the first nibble */
int sd_flag = wake_flags & 0xF;
+ /*
+ * required for stable ->cpus_allowed
+ */
+ lockdep_assert_held(&p->pi_lock);
if (wake_flags & WF_TTWU) {
record_wakee(p);
* In case of TASK_ON_RQ_MIGRATING we in fact hold the 'old'
* rq->lock and can modify state directly.
*/
- lockdep_assert_held(&task_rq(p)->lock);
+ lockdep_assert_rq_held(task_rq(p));
detach_entity_cfs_rq(&p->se);
} else {
{
s64 delta;
- lockdep_assert_held(&env->src_rq->lock);
+ lockdep_assert_rq_held(env->src_rq);
if (p->sched_class != &fair_sched_class)
return 0;
{
int tsk_cache_hot;
- lockdep_assert_held(&env->src_rq->lock);
+ lockdep_assert_rq_held(env->src_rq);
/*
* We do not migrate tasks that are:
*/
static void detach_task(struct task_struct *p, struct lb_env *env)
{
- lockdep_assert_held(&env->src_rq->lock);
+ lockdep_assert_rq_held(env->src_rq);
deactivate_task(env->src_rq, p, DEQUEUE_NOCLOCK);
set_task_cpu(p, env->dst_cpu);
{
struct task_struct *p;
- lockdep_assert_held(&env->src_rq->lock);
+ lockdep_assert_rq_held(env->src_rq);
list_for_each_entry_reverse(p,
&env->src_rq->cfs_tasks, se.group_node) {
struct task_struct *p;
int detached = 0;
- lockdep_assert_held(&env->src_rq->lock);
+ lockdep_assert_rq_held(env->src_rq);
/*
* Source run queue has been emptied by another CPU, clear
*/
static void attach_task(struct rq *rq, struct task_struct *p)
{
- lockdep_assert_held(&rq->lock);
+ lockdep_assert_rq_held(rq);
BUG_ON(task_rq(p) != rq);
activate_task(rq, p, ENQUEUE_NOCLOCK);
if (need_active_balance(&env)) {
unsigned long flags;
- raw_spin_lock_irqsave(&busiest->lock, flags);
+ raw_spin_rq_lock_irqsave(busiest, flags);
/*
* Don't kick the active_load_balance_cpu_stop,
* moved to this_cpu:
*/
if (!cpumask_test_cpu(this_cpu, busiest->curr->cpus_ptr)) {
- raw_spin_unlock_irqrestore(&busiest->lock,
- flags);
+ raw_spin_rq_unlock_irqrestore(busiest, flags);
goto out_one_pinned;
}
busiest->push_cpu = this_cpu;
active_balance = 1;
}
- raw_spin_unlock_irqrestore(&busiest->lock, flags);
+ raw_spin_rq_unlock_irqrestore(busiest, flags);
if (active_balance) {
stop_one_cpu_nowait(cpu_of(busiest),
u64 curr_cost = 0;
update_misfit_status(NULL, this_rq);
+
+ /*
+ * There is a task waiting to run. No need to search for one.
+ * Return 0; the task will be enqueued when switching to idle.
+ */
+ if (this_rq->ttwu_pending)
+ return 0;
+
/*
* We must set idle_stamp _before_ calling idle_balance(), such that we
* measure the duration of idle_balance() as idle time.
goto out;
}
- raw_spin_unlock(&this_rq->lock);
+ raw_spin_rq_unlock(this_rq);
update_blocked_averages(this_cpu);
rcu_read_lock();
* Stop searching for tasks to pull if there are
* now runnable tasks on this rq.
*/
- if (pulled_task || this_rq->nr_running > 0)
+ if (pulled_task || this_rq->nr_running > 0 ||
+ this_rq->ttwu_pending)
break;
}
rcu_read_unlock();
- raw_spin_lock(&this_rq->lock);
+ raw_spin_rq_lock(this_rq);
if (curr_cost > this_rq->max_idle_balance_cost)
this_rq->max_idle_balance_cost = curr_cost;
{
struct cfs_rq *cfs_rq;
+ list_add_leaf_cfs_rq(cfs_rq_of(se));
+
/* Start to propagate at parent */
se = se->parent;
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
- if (cfs_rq_throttled(cfs_rq))
- break;
+ if (!cfs_rq_throttled(cfs_rq)){
+ update_load_avg(cfs_rq, se, UPDATE_TG);
+ list_add_leaf_cfs_rq(cfs_rq);
+ continue;
+ }
- update_load_avg(cfs_rq, se, UPDATE_TG);
+ if (list_add_leaf_cfs_rq(cfs_rq))
+ break;
}
}
#else
rq = cpu_rq(cpu);
- raw_spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_rq_lock_irqsave(rq, flags);
list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
- raw_spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_rq_unlock_irqrestore(rq, flags);
}
}