The task_fork_fair() callback already calls __set_task_cpu() and takes
rq->lock.

If we move the sched_class::task_fork callback in sched_fork() under
the existing p->pi_lock, right after its set_task_cpu() call, we can
avoid doing two such calls and omit the IRQ disabling on the rq->lock.

Change to __set_task_cpu() to skip the migration bits, this is a new
task, not a migration.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/sched/core.c |    7 +++----
 kernel/sched/fair.c |   27 ++++++---------------------
 2 files changed, 9 insertions(+), 25 deletions(-)

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2381,9 +2381,6 @@ int sched_fork(unsigned long clone_flags
 		p->sched_class = &fair_sched_class;
 	}
 
-	if (p->sched_class->task_fork)
-		p->sched_class->task_fork(p);
-
 	/*
 	 * The child is not yet in the pid-hash so no cgroup attach races,
 	 * and the cgroup is pinned to this child due to cgroup_fork()
@@ -2392,7 +2389,9 @@ int sched_fork(unsigned long clone_flags
 	 * Silence PROVE_RCU.
 	 */
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
-	set_task_cpu(p, cpu);
+	__set_task_cpu(p, cpu);
+	if (p->sched_class->task_fork)
+		p->sched_class->task_fork(p);
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
 #ifdef CONFIG_SCHED_INFO
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4418,7 +4418,7 @@ enqueue_task_fair(struct rq *rq, struct
 		 *
 		 * note: in the case of encountering a throttled cfs_rq we will
 		 * post the final h_nr_running increment below.
-		*/
+		 */
 		if (cfs_rq_throttled(cfs_rq))
 			break;
 		cfs_rq->h_nr_running++;
@@ -8255,31 +8255,17 @@ static void task_fork_fair(struct task_s
 {
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se, *curr;
-	int this_cpu = smp_processor_id();
 	struct rq *rq = this_rq();
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&rq->lock, flags);
 
+	raw_spin_lock(&rq->lock);
 	update_rq_clock(rq);
 
 	cfs_rq = task_cfs_rq(current);
 	curr = cfs_rq->curr;
-
-	/*
-	 * Not only the cpu but also the task_group of the parent might have
-	 * been changed after parent->se.parent,cfs_rq were copied to
-	 * child->se.parent,cfs_rq. So call __set_task_cpu() to make those
-	 * of child point to valid ones.
-	 */
-	rcu_read_lock();
-	__set_task_cpu(p, this_cpu);
-	rcu_read_unlock();
-
-	update_curr(cfs_rq);
-
-	if (curr)
+	if (curr) {
+		update_curr(cfs_rq);
 		se->vruntime = curr->vruntime;
+	}
 	place_entity(cfs_rq, se, 1);
 
 	if (sysctl_sched_child_runs_first && curr && entity_before(curr, se)) {
@@ -8292,8 +8278,7 @@ static void task_fork_fair(struct task_s
 	}
 
 	se->vruntime -= cfs_rq->min_vruntime;
-
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	raw_spin_unlock(&rq->lock);
 }
 
 /*