*/
static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- return calc_delta_mine(__sched_period(cfs_rq->nr_running),
- se->load.weight, &cfs_rq->load);
+ u64 slice = __sched_period(cfs_rq->nr_running);
+
+ for_each_sched_entity(se) {
+ cfs_rq = cfs_rq_of(se);
+
+ slice *= se->load.weight;
+ do_div(slice, cfs_rq->load.weight);
+ }
+
+
+ return slice;
}
/*
- * We calculate the vruntime slice.
+ * We calculate the vruntime slice of a to be inserted task
*
* vs = s/w = p/rw
*/
-static u64 __sched_vslice(unsigned long rq_weight, unsigned long nr_running)
+static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- u64 vslice = __sched_period(nr_running);
+ unsigned long nr_running = cfs_rq->nr_running;
+ unsigned long weight;
+ u64 vslice;
- vslice *= NICE_0_LOAD;
- do_div(vslice, rq_weight);
+ if (!se->on_rq)
+ nr_running++;
- return vslice;
-}
+ vslice = __sched_period(nr_running);
-static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
- return __sched_vslice(cfs_rq->load.weight + se->load.weight,
- cfs_rq->nr_running + 1);
+ for_each_sched_entity(se) {
+ cfs_rq = cfs_rq_of(se);
+
+ weight = cfs_rq->load.weight;
+ if (!se->on_rq)
+ weight += se->load.weight;
+
+ vslice *= NICE_0_LOAD;
+ do_div(vslice, weight);
+ }
+
+ return vslice;
}
/*
update_load_add(&cfs_rq->load, se->load.weight);
cfs_rq->nr_running++;
se->on_rq = 1;
+ list_add(&se->group_node, &cfs_rq->tasks);
}
static void
update_load_sub(&cfs_rq->load, se->load.weight);
cfs_rq->nr_running--;
se->on_rq = 0;
+ list_del_init(&se->group_node);
}
static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
if (!initial) {
/* sleeps upto a single latency don't count. */
- if (sched_feat(NEW_FAIR_SLEEPERS)) {
- if (sched_feat(NORMALIZED_SLEEPER))
- vruntime -= calc_delta_fair(sysctl_sched_latency,
- &cfs_rq->load);
- else
- vruntime -= sysctl_sched_latency;
- }
+ if (sched_feat(NEW_FAIR_SLEEPERS))
+ vruntime -= sysctl_sched_latency;
/* ensure we never gain time by being placed backwards. */
vruntime = max_vruntime(se->vruntime, vruntime);
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
+ account_entity_enqueue(cfs_rq, se);
if (wakeup) {
place_entity(cfs_rq, se, 0);
check_spread(cfs_rq, se);
if (se != cfs_rq->curr)
__enqueue_entity(cfs_rq, se);
- account_entity_enqueue(cfs_rq, se);
}
static void update_avg(u64 *avg, u64 sample)
* queued ticks are scheduled to match the slice, so don't bother
* validating it and just reschedule.
*/
- if (queued)
- return resched_task(rq_of(cfs_rq)->curr);
+ if (queued) {
+ resched_task(rq_of(cfs_rq)->curr);
+ return;
+ }
/*
* don't let the period tick interfere with the hrtick preemption
*/
return;
if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {
- __update_rq_clock(rq);
+ update_rq_clock(rq);
/*
* Update run-time statistics of the 'current'.
*/
* sibling runqueue info. This will avoid the checks and cache miss
* penalities associated with that.
*/
- if (idle_cpu(cpu) || cpu_rq(cpu)->nr_running > 1)
+ if (idle_cpu(cpu) || cpu_rq(cpu)->cfs.nr_running > 1)
return cpu;
for_each_domain(cpu, sd) {
struct task_struct *curr = this_rq->curr;
unsigned long tl = this_load;
unsigned long tl_per_task;
+ int balanced;
- if (!(this_sd->flags & SD_WAKE_AFFINE))
+ if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS))
return 0;
+ /*
+ * If sync wakeup then subtract the (maximum possible)
+ * effect of the currently running task from the load
+ * of the current CPU:
+ */
+ if (sync)
+ tl -= current->se.load.weight;
+
+ balanced = 100*(tl + p->se.load.weight) <= imbalance*load;
+
/*
* If the currently running task will sleep within
* a reasonable amount of time then attract this newly
* woken task:
*/
- if (sync && curr->sched_class == &fair_sched_class) {
+ if (sync && balanced && curr->sched_class == &fair_sched_class) {
if (curr->se.avg_overlap < sysctl_sched_migration_cost &&
p->se.avg_overlap < sysctl_sched_migration_cost)
return 1;
schedstat_inc(p, se.nr_wakeups_affine_attempts);
tl_per_task = cpu_avg_load_per_task(this_cpu);
- /*
- * If sync wakeup then subtract the (maximum possible)
- * effect of the currently running task from the load
- * of the current CPU:
- */
- if (sync)
- tl -= current->se.load.weight;
-
if ((tl <= load && tl + target_load(prev_cpu, idx) <= tl_per_task) ||
- 100*(tl + p->se.load.weight) <= imbalance*load) {
+ balanced) {
/*
* This domain has SD_WAKE_AFFINE and
* p is cache cold in this domain, and
* the current task:
*/
static struct task_struct *
-__load_balance_iterator(struct cfs_rq *cfs_rq, struct rb_node *curr)
+__load_balance_iterator(struct cfs_rq *cfs_rq, struct list_head *next)
{
struct task_struct *p = NULL;
struct sched_entity *se;
- if (!curr)
+ if (next == &cfs_rq->tasks)
return NULL;
/* Skip over entities that are not tasks */
do {
- se = rb_entry(curr, struct sched_entity, run_node);
- curr = rb_next(curr);
- } while (curr && !entity_is_task(se));
+ se = list_entry(next, struct sched_entity, group_node);
+ next = next->next;
+ } while (next != &cfs_rq->tasks && !entity_is_task(se));
+
+ if (next == &cfs_rq->tasks)
+ return NULL;
- cfs_rq->rb_load_balance_curr = curr;
+ cfs_rq->balance_iterator = next;
if (entity_is_task(se))
p = task_of(se);
{
struct cfs_rq *cfs_rq = arg;
- return __load_balance_iterator(cfs_rq, first_fair(cfs_rq));
+ return __load_balance_iterator(cfs_rq, cfs_rq->tasks.next);
}
static struct task_struct *load_balance_next_fair(void *arg)
{
struct cfs_rq *cfs_rq = arg;
- return __load_balance_iterator(cfs_rq, cfs_rq->rb_load_balance_curr);
+ return __load_balance_iterator(cfs_rq, cfs_rq->balance_iterator);
}
#ifdef CONFIG_FAIR_GROUP_SCHED