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

Pull scheduler fixes from Ingo Molnar:
 "Misc fixes: a cgroup fix, a fair-scheduler migration accounting fix, a
  cputime fix and two cpuacct cleanups"

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/cpuacct: Simplify the cpuacct code
  sched/cpuacct: Rename parameter in cpuusage_write() for readability
  sched/fair: Add comments to explain select_idle_sibling()
  sched/fair: Fix fairness issue on migration
  sched/cgroup: Fix/cleanup cgroup teardown/init
  sched/cputime: Fix steal time accounting vs. CPU hotplug

5 files changed, 72 insertions, 55 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 44db0fffa8be..d8465eeab8b3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5371,6 +5371,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 
 	case CPU_UP_PREPARE:
 		rq->calc_load_update = calc_load_update;
+		account_reset_rq(rq);
 		break;
 
 	case CPU_ONLINE:
@@ -7537,7 +7538,7 @@ void set_curr_task(int cpu, struct task_struct *p)
 /* task_group_lock serializes the addition/removal of task groups */
 static DEFINE_SPINLOCK(task_group_lock);
 
-static void free_sched_group(struct task_group *tg)
+static void sched_free_group(struct task_group *tg)
 {
 	free_fair_sched_group(tg);
 	free_rt_sched_group(tg);
@@ -7563,7 +7564,7 @@ struct task_group *sched_create_group(struct task_group *parent)
 	return tg;
 
 err:
-	free_sched_group(tg);
+	sched_free_group(tg);
 	return ERR_PTR(-ENOMEM);
 }
 
@@ -7583,17 +7584,16 @@ void sched_online_group(struct task_group *tg, struct task_group *parent)
 }
 
 /* rcu callback to free various structures associated with a task group */
-static void free_sched_group_rcu(struct rcu_head *rhp)
+static void sched_free_group_rcu(struct rcu_head *rhp)
 {
 	/* now it should be safe to free those cfs_rqs */
-	free_sched_group(container_of(rhp, struct task_group, rcu));
+	sched_free_group(container_of(rhp, struct task_group, rcu));
 }
 
-/* Destroy runqueue etc associated with a task group */
 void sched_destroy_group(struct task_group *tg)
 {
 	/* wait for possible concurrent references to cfs_rqs complete */
-	call_rcu(&tg->rcu, free_sched_group_rcu);
+	call_rcu(&tg->rcu, sched_free_group_rcu);
 }
 
 void sched_offline_group(struct task_group *tg)
@@ -8052,31 +8052,26 @@ cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	if (IS_ERR(tg))
 		return ERR_PTR(-ENOMEM);
 
+	sched_online_group(tg, parent);
+
 	return &tg->css;
 }
 
-static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
+static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
 {
 	struct task_group *tg = css_tg(css);
-	struct task_group *parent = css_tg(css->parent);
 
-	if (parent)
-		sched_online_group(tg, parent);
-	return 0;
+	sched_offline_group(tg);
 }
 
 static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
 {
 	struct task_group *tg = css_tg(css);
 
-	sched_destroy_group(tg);
-}
-
-static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css)
-{
-	struct task_group *tg = css_tg(css);
-
-	sched_offline_group(tg);
+	/*
+	 * Relies on the RCU grace period between css_released() and this.
+	 */
+	sched_free_group(tg);
 }
 
 static void cpu_cgroup_fork(struct task_struct *task)
@@ -8436,9 +8431,8 @@ static struct cftype cpu_files[] = {
 
 struct cgroup_subsys cpu_cgrp_subsys = {
 	.css_alloc	= cpu_cgroup_css_alloc,
+	.css_released	= cpu_cgroup_css_released,
 	.css_free	= cpu_cgroup_css_free,
-	.css_online	= cpu_cgroup_css_online,
-	.css_offline	= cpu_cgroup_css_offline,
 	.fork		= cpu_cgroup_fork,
 	.can_attach	= cpu_cgroup_can_attach,
 	.attach		= cpu_cgroup_attach,
diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index 2ddaebf7469a..4a811203c04a 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -145,13 +145,16 @@ static u64 cpuusage_read(struct cgroup_subsys_state *css, struct cftype *cft)
 }
 
 static int cpuusage_write(struct cgroup_subsys_state *css, struct cftype *cft,
-			  u64 reset)
+			  u64 val)
 {
 	struct cpuacct *ca = css_ca(css);
 	int err = 0;
 	int i;
 
-	if (reset) {
+	/*
+	 * Only allow '0' here to do a reset.
+	 */
+	if (val) {
 		err = -EINVAL;
 		goto out;
 	}
@@ -235,23 +238,10 @@ static struct cftype files[] = {
 void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 {
 	struct cpuacct *ca;
-	int cpu;
-
-	cpu = task_cpu(tsk);
 
 	rcu_read_lock();
-
-	ca = task_ca(tsk);
-
-	while (true) {
-		u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
-		*cpuusage += cputime;
-
-		ca = parent_ca(ca);
-		if (!ca)
-			break;
-	}
-
+	for (ca = task_ca(tsk); ca; ca = parent_ca(ca))
+		*this_cpu_ptr(ca->cpuusage) += cputime;
 	rcu_read_unlock();
 }
 
@@ -260,18 +250,13 @@ void cpuacct_charge(struct task_struct *tsk, u64 cputime)
  *
  * Note: it's the caller that updates the account of the root cgroup.
  */
-void cpuacct_account_field(struct task_struct *p, int index, u64 val)
+void cpuacct_account_field(struct task_struct *tsk, int index, u64 val)
 {
-	struct kernel_cpustat *kcpustat;
 	struct cpuacct *ca;
 
 	rcu_read_lock();
-	ca = task_ca(p);
-	while (ca != &root_cpuacct) {
-		kcpustat = this_cpu_ptr(ca->cpustat);
-		kcpustat->cpustat[index] += val;
-		ca = parent_ca(ca);
-	}
+	for (ca = task_ca(tsk); ca != &root_cpuacct; ca = parent_ca(ca))
+		this_cpu_ptr(ca->cpustat)->cpustat[index] += val;
 	rcu_read_unlock();
 }
 
diff --git a/kernel/sched/cpuacct.h b/kernel/sched/cpuacct.h
index ed605624a5e7..ba72807c73d4 100644
--- a/kernel/sched/cpuacct.h
+++ b/kernel/sched/cpuacct.h
@@ -1,7 +1,7 @@
 #ifdef CONFIG_CGROUP_CPUACCT
 
 extern void cpuacct_charge(struct task_struct *tsk, u64 cputime);
-extern void cpuacct_account_field(struct task_struct *p, int index, u64 val);
+extern void cpuacct_account_field(struct task_struct *tsk, int index, u64 val);
 
 #else
 
@@ -10,7 +10,7 @@ static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 }
 
 static inline void
-cpuacct_account_field(struct task_struct *p, int index, u64 val)
+cpuacct_account_field(struct task_struct *tsk, int index, u64 val)
 {
 }
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 46d64e4ccfde..0fe30e66aff1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3181,17 +3181,25 @@ static inline void check_schedstat_required(void)
 static void
 enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
+	bool renorm = !(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING);
+	bool curr = cfs_rq->curr == se;
+
 	/*
-	 * Update the normalized vruntime before updating min_vruntime
-	 * through calling update_curr().
+	 * If we're the current task, we must renormalise before calling
+	 * update_curr().
 	 */
-	if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING))
+	if (renorm && curr)
 		se->vruntime += cfs_rq->min_vruntime;
 
+	update_curr(cfs_rq);
+
 	/*
-	 * Update run-time statistics of the 'current'.
+	 * Otherwise, renormalise after, such that we're placed at the current
+	 * moment in time, instead of some random moment in the past.
 	 */
-	update_curr(cfs_rq);
+	if (renorm && !curr)
+		se->vruntime += cfs_rq->min_vruntime;
+
 	enqueue_entity_load_avg(cfs_rq, se);
 	account_entity_enqueue(cfs_rq, se);
 	update_cfs_shares(cfs_rq);
@@ -3207,7 +3215,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		update_stats_enqueue(cfs_rq, se);
 		check_spread(cfs_rq, se);
 	}
-	if (se != cfs_rq->curr)
+	if (!curr)
 		__enqueue_entity(cfs_rq, se);
 	se->on_rq = 1;
 
@@ -5071,7 +5079,19 @@ static int select_idle_sibling(struct task_struct *p, int target)
 		return i;
 
 	/*
-	 * Otherwise, iterate the domains and find an elegible idle cpu.
+	 * Otherwise, iterate the domains and find an eligible idle cpu.
+	 *
+	 * A completely idle sched group at higher domains is more
+	 * desirable than an idle group at a lower level, because lower
+	 * domains have smaller groups and usually share hardware
+	 * resources which causes tasks to contend on them, e.g. x86
+	 * hyperthread siblings in the lowest domain (SMT) can contend
+	 * on the shared cpu pipeline.
+	 *
+	 * However, while we prefer idle groups at higher domains
+	 * finding an idle cpu at the lowest domain is still better than
+	 * returning 'target', which we've already established, isn't
+	 * idle.
 	 */
 	sd = rcu_dereference(per_cpu(sd_llc, target));
 	for_each_lower_domain(sd) {
@@ -5081,11 +5101,16 @@ static int select_idle_sibling(struct task_struct *p, int target)
 						tsk_cpus_allowed(p)))
 				goto next;
 
+			/* Ensure the entire group is idle */
 			for_each_cpu(i, sched_group_cpus(sg)) {
 				if (i == target || !idle_cpu(i))
 					goto next;
 			}
 
+			/*
+			 * It doesn't matter which cpu we pick, the
+			 * whole group is idle.
+			 */
 			target = cpumask_first_and(sched_group_cpus(sg),
 					tsk_cpus_allowed(p));
 			goto done;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 382848a24ed9..ec2e8d23527e 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1841,3 +1841,16 @@ static inline void cpufreq_trigger_update(u64 time)
 static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max) {}
 static inline void cpufreq_trigger_update(u64 time) {}
 #endif /* CONFIG_CPU_FREQ */
+
+static inline void account_reset_rq(struct rq *rq)
+{
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+	rq->prev_irq_time = 0;
+#endif
+#ifdef CONFIG_PARAVIRT
+	rq->prev_steal_time = 0;
+#endif
+#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
+	rq->prev_steal_time_rq = 0;
+#endif
+}