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, 31 insertions, 2 deletions

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 7d905f55e7fa..ab7f371a3a17 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -201,11 +201,37 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 	return 1;
 }
 
-DEFINE_STATIC_KEY_FALSE(sched_energy_present);
 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
+DEFINE_STATIC_KEY_FALSE(sched_energy_present);
+unsigned int sysctl_sched_energy_aware = 1;
 DEFINE_MUTEX(sched_energy_mutex);
 bool sched_energy_update;
 
+#ifdef CONFIG_PROC_SYSCTL
+int sched_energy_aware_handler(struct ctl_table *table, int write,
+			 void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	int ret, state;
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	if (!ret && write) {
+		state = static_branch_unlikely(&sched_energy_present);
+		if (state != sysctl_sched_energy_aware) {
+			mutex_lock(&sched_energy_mutex);
+			sched_energy_update = 1;
+			rebuild_sched_domains();
+			sched_energy_update = 0;
+			mutex_unlock(&sched_energy_mutex);
+		}
+	}
+
+	return ret;
+}
+#endif
+
 static void free_pd(struct perf_domain *pd)
 {
 	struct perf_domain *tmp;
@@ -322,6 +348,9 @@ static bool build_perf_domains(const struct cpumask *cpu_map)
 	struct cpufreq_policy *policy;
 	struct cpufreq_governor *gov;
 
+	if (!sysctl_sched_energy_aware)
+		goto free;
+
 	/* EAS is enabled for asymmetric CPU capacity topologies. */
 	if (!per_cpu(sd_asym_cpucapacity, cpu)) {
 		if (sched_debug()) {
@@ -676,7 +705,7 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 }
 
 struct s_data {
-	struct sched_domain ** __percpu sd;
+	struct sched_domain * __percpu *sd;
 	struct root_domain	*rd;
 };