Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "The main changes in this cycle were:

   - refcount conversions

   - Solve the rq->leaf_cfs_rq_list can of worms for real.

   - improve power-aware scheduling

   - add sysctl knob for Energy Aware Scheduling

   - documentation updates

   - misc other changes"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (34 commits)
  kthread: Do not use TIMER_IRQSAFE
  kthread: Convert worker lock to raw spinlock
  sched/fair: Use non-atomic cpumask_{set,clear}_cpu()
  sched/fair: Remove unused 'sd' parameter from select_idle_smt()
  sched/wait: Use freezable_schedule() when possible
  sched/fair: Prune, fix and simplify the nohz_balancer_kick() comment block
  sched/fair: Explain LLC nohz kick condition
  sched/fair: Simplify nohz_balancer_kick()
  sched/topology: Fix percpu data types in struct sd_data & struct s_data
  sched/fair: Simplify post_init_entity_util_avg() by calling it with a task_struct pointer argument
  sched/fair: Fix O(nr_cgroups) in the load balancing path
  sched/fair: Optimize update_blocked_averages()
  sched/fair: Fix insertion in rq->leaf_cfs_rq_list
  sched/fair: Add tmp_alone_branch assertion
  sched/core: Use READ_ONCE()/WRITE_ONCE() in move_queued_task()/task_rq_lock()
  sched/debug: Initialize sd_sysctl_cpus if !CONFIG_CPUMASK_OFFSTACK
  sched/pelt: Skip updating util_est when utilization is higher than CPU's capacity
  sched/fair: Update scale invariance of PELT
  sched/fair: Move the rq_of() helper function
  sched/core: Convert task_struct.stack_refcount to refcount_t
  ...

1 files changed, 7 insertions, 5 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0002995570db..f3901b84d217 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -107,11 +107,12 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 		 *					[L] ->on_rq
 		 *	RELEASE (rq->lock)
 		 *
-		 * If we observe the old CPU in task_rq_lock, the acquire of
+		 * If we observe the old CPU in task_rq_lock(), the acquire of
 		 * the old rq->lock will fully serialize against the stores.
 		 *
-		 * If we observe the new CPU in task_rq_lock, the acquire will
-		 * pair with the WMB to ensure we must then also see migrating.
+		 * If we observe the new CPU in task_rq_lock(), the address
+		 * dependency headed by '[L] rq = task_rq()' and the acquire
+		 * will pair with the WMB to ensure we then also see migrating.
 		 */
 		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
 			rq_pin_lock(rq, rf);
@@ -180,6 +181,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 	if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
 		update_irq_load_avg(rq, irq_delta + steal);
 #endif
+	update_rq_clock_pelt(rq, delta);
 }
 
 void update_rq_clock(struct rq *rq)
@@ -956,7 +958,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
 {
 	lockdep_assert_held(&rq->lock);
 
-	p->on_rq = TASK_ON_RQ_MIGRATING;
+	WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING);
 	dequeue_task(rq, p, DEQUEUE_NOCLOCK);
 	set_task_cpu(p, new_cpu);
 	rq_unlock(rq, rf);
@@ -2459,7 +2461,7 @@ void wake_up_new_task(struct task_struct *p)
 #endif
 	rq = __task_rq_lock(p, &rf);
 	update_rq_clock(rq);
-	post_init_entity_util_avg(&p->se);
+	post_init_entity_util_avg(p);
 
 	activate_task(rq, p, ENQUEUE_NOCLOCK);
 	p->on_rq = TASK_ON_RQ_QUEUED;