sched: fix: move the CPU check into ->task_new_fair()

noticed by Peter Zijlstra:

fix: move the CPU check into ->task_new_fair(), this way we
can call place_entity() and get child ->vruntime right at
initial wakeup time.

(without this there can be large latencies)

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>

2 files changed, 3 insertions, 5 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index f2b8db4d6802..b41ef663b993 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1660,17 +1660,14 @@ void fastcall wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 {
         unsigned long flags;
         struct rq *rq;
-        int this_cpu;
 
         rq = task_rq_lock(p, &flags);
         BUG_ON(p->state != TASK_RUNNING);
-        this_cpu = smp_processor_id(); /* parent's CPU */
         update_rq_clock(rq);
 
         p->prio = effective_prio(p);
 
-        if (task_cpu(p) != this_cpu || !p->sched_class->task_new ||
-                                                        !current->se.on_rq) {
+        if (!p->sched_class->task_new || !current->se.on_rq || !rq->cfs.curr) {
                 activate_task(rq, p, 0);
         } else {
                 /*
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index a9dfb7746c5c..f5f491762e35 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1007,13 +1007,14 @@ static void task_new_fair(struct rq *rq, struct task_struct *p)
 {
         struct cfs_rq *cfs_rq = task_cfs_rq(p);
         struct sched_entity *se = &p->se, *curr = cfs_rq->curr;
+        int this_cpu = smp_processor_id();
 
         sched_info_queued(p);
 
         update_curr(cfs_rq);
         place_entity(cfs_rq, se, 1);
 
-        if (sysctl_sched_child_runs_first &&
+        if (sysctl_sched_child_runs_first && this_cpu == task_cpu(p) &&
                         curr->vruntime < se->vruntime) {
                 /*
                  * Upon rescheduling, sched_class::put_prev_task() will place