Merge commit '8700c95adb03' into timers/nohz

The full dynticks tree needs the latest RCU and sched
upstream updates in order to fix some dependencies.

Merge a common upstream merge point that has these
updates.

Conflicts:
	include/linux/perf_event.h
	kernel/rcutree.h
	kernel/rcutree_plugin.h

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>

10 files changed, 464 insertions, 410 deletions

diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index f06d249e103b..deaf90e4a1de 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -16,3 +16,4 @@ obj-$(CONFIG_SMP) += cpupri.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
+obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index c685e31492df..c3ae1446461c 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -176,10 +176,36 @@ static u64 sched_clock_remote(struct sched_clock_data *scd)
 	u64 this_clock, remote_clock;
 	u64 *ptr, old_val, val;
 
+#if BITS_PER_LONG != 64
+again:
+	/*
+	 * Careful here: The local and the remote clock values need to
+	 * be read out atomic as we need to compare the values and
+	 * then update either the local or the remote side. So the
+	 * cmpxchg64 below only protects one readout.
+	 *
+	 * We must reread via sched_clock_local() in the retry case on
+	 * 32bit as an NMI could use sched_clock_local() via the
+	 * tracer and hit between the readout of
+	 * the low32bit and the high 32bit portion.
+	 */
+	this_clock = sched_clock_local(my_scd);
+	/*
+	 * We must enforce atomic readout on 32bit, otherwise the
+	 * update on the remote cpu can hit inbetween the readout of
+	 * the low32bit and the high 32bit portion.
+	 */
+	remote_clock = cmpxchg64(&scd->clock, 0, 0);
+#else
+	/*
+	 * On 64bit the read of [my]scd->clock is atomic versus the
+	 * update, so we can avoid the above 32bit dance.
+	 */
 	sched_clock_local(my_scd);
 again:
 	this_clock = my_scd->clock;
 	remote_clock = scd->clock;
+#endif
 
 	/*
 	 * Use the opportunity that we have both locks
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index dd09def88567..e94842d4400c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -512,11 +512,6 @@ static inline void init_hrtick(void)
  * the target CPU.
  */
 #ifdef CONFIG_SMP
-
-#ifndef tsk_is_polling
-#define tsk_is_polling(t) 0
-#endif
-
 void resched_task(struct task_struct *p)
 {
 	int cpu;
@@ -1536,8 +1531,10 @@ static void try_to_wake_up_local(struct task_struct *p)
 {
 	struct rq *rq = task_rq(p);
 
-	BUG_ON(rq != this_rq());
-	BUG_ON(p == current);
+	if (WARN_ON_ONCE(rq != this_rq()) ||
+	    WARN_ON_ONCE(p == current))
+		return;
+
 	lockdep_assert_held(&rq->lock);
 
 	if (!raw_spin_trylock(&p->pi_lock)) {
@@ -3037,51 +3034,6 @@ void __sched schedule_preempt_disabled(void)
 	preempt_disable();
 }
 
-#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
-
-static inline bool owner_running(struct mutex *lock, struct task_struct *owner)
-{
-	if (lock->owner != owner)
-		return false;
-
-	/*
-	 * Ensure we emit the owner->on_cpu, dereference _after_ checking
-	 * lock->owner still matches owner, if that fails, owner might
-	 * point to free()d memory, if it still matches, the rcu_read_lock()
-	 * ensures the memory stays valid.
-	 */
-	barrier();
-
-	return owner->on_cpu;
-}
-
-/*
- * Look out! "owner" is an entirely speculative pointer
- * access and not reliable.
- */
-int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
-{
-	if (!sched_feat(OWNER_SPIN))
-		return 0;
-
-	rcu_read_lock();
-	while (owner_running(lock, owner)) {
-		if (need_resched())
-			break;
-
-		arch_mutex_cpu_relax();
-	}
-	rcu_read_unlock();
-
-	/*
-	 * We break out the loop above on need_resched() and when the
-	 * owner changed, which is a sign for heavy contention. Return
-	 * success only when lock->owner is NULL.
-	 */
-	return lock->owner == NULL;
-}
-#endif
-
 #ifdef CONFIG_PREEMPT
 /*
  * this is the entry point to schedule() from in-kernel preemption
@@ -4170,6 +4122,10 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	get_task_struct(p);
 	rcu_read_unlock();
 
+	if (p->flags & PF_NO_SETAFFINITY) {
+		retval = -EINVAL;
+		goto out_put_task;
+	}
 	if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
 		retval = -ENOMEM;
 		goto out_put_task;
@@ -4817,11 +4773,6 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 		goto out;
 	}
 
-	if (unlikely((p->flags & PF_THREAD_BOUND) && p != current)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
 	do_set_cpus_allowed(p, new_mask);
 
 	/* Can the task run on the task's current CPU? If so, we're done */
@@ -5043,7 +4994,7 @@ static void sd_free_ctl_entry(struct ctl_table **tablep)
 }
 
 static int min_load_idx = 0;
-static int max_load_idx = CPU_LOAD_IDX_MAX;
+static int max_load_idx = CPU_LOAD_IDX_MAX-1;
 
 static void
 set_table_entry(struct ctl_table *entry,
@@ -6292,7 +6243,7 @@ static void sched_init_numa(void)
 	 * 'level' contains the number of unique distances, excluding the
 	 * identity distance node_distance(i,i).
 	 *
-	 * The sched_domains_nume_distance[] array includes the actual distance
+	 * The sched_domains_numa_distance[] array includes the actual distance
 	 * numbers.
 	 */
 
@@ -6913,7 +6864,7 @@ struct task_group root_task_group;
 LIST_HEAD(task_groups);
 #endif
 
-DECLARE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
+DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
 
 void __init sched_init(void)
 {
@@ -6950,7 +6901,7 @@ void __init sched_init(void)
 #endif /* CONFIG_RT_GROUP_SCHED */
 #ifdef CONFIG_CPUMASK_OFFSTACK
 		for_each_possible_cpu(i) {
-			per_cpu(load_balance_tmpmask, i) = (void *)ptr;
+			per_cpu(load_balance_mask, i) = (void *)ptr;
 			ptr += cpumask_size();
 		}
 #endif /* CONFIG_CPUMASK_OFFSTACK */
@@ -6976,12 +6927,6 @@ void __init sched_init(void)
 
 #endif /* CONFIG_CGROUP_SCHED */
 
-#ifdef CONFIG_CGROUP_CPUACCT
-	root_cpuacct.cpustat = &kernel_cpustat;
-	root_cpuacct.cpuusage = alloc_percpu(u64);
-	/* Too early, not expected to fail */
-	BUG_ON(!root_cpuacct.cpuusage);
-#endif
 	for_each_possible_cpu(i) {
 		struct rq *rq;
 
@@ -8083,226 +8028,6 @@ struct cgroup_subsys cpu_cgroup_subsys = {
 
 #endif	/* CONFIG_CGROUP_SCHED */
 
-#ifdef CONFIG_CGROUP_CPUACCT
-
-/*
- * CPU accounting code for task groups.
- *
- * Based on the work by Paul Menage (menage@google.com) and Balbir Singh
- * (balbir@in.ibm.com).
- */
-
-struct cpuacct root_cpuacct;
-
-/* create a new cpu accounting group */
-static struct cgroup_subsys_state *cpuacct_css_alloc(struct cgroup *cgrp)
-{
-	struct cpuacct *ca;
-
-	if (!cgrp->parent)
-		return &root_cpuacct.css;
-
-	ca = kzalloc(sizeof(*ca), GFP_KERNEL);
-	if (!ca)
-		goto out;
-
-	ca->cpuusage = alloc_percpu(u64);
-	if (!ca->cpuusage)
-		goto out_free_ca;
-
-	ca->cpustat = alloc_percpu(struct kernel_cpustat);
-	if (!ca->cpustat)
-		goto out_free_cpuusage;
-
-	return &ca->css;
-
-out_free_cpuusage:
-	free_percpu(ca->cpuusage);
-out_free_ca:
-	kfree(ca);
-out:
-	return ERR_PTR(-ENOMEM);
-}
-
-/* destroy an existing cpu accounting group */
-static void cpuacct_css_free(struct cgroup *cgrp)
-{
-	struct cpuacct *ca = cgroup_ca(cgrp);
-
-	free_percpu(ca->cpustat);
-	free_percpu(ca->cpuusage);
-	kfree(ca);
-}
-
-static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
-{
-	u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
-	u64 data;
-
-#ifndef CONFIG_64BIT
-	/*
-	 * Take rq->lock to make 64-bit read safe on 32-bit platforms.
-	 */
-	raw_spin_lock_irq(&cpu_rq(cpu)->lock);
-	data = *cpuusage;
-	raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
-#else
-	data = *cpuusage;
-#endif
-
-	return data;
-}
-
-static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
-{
-	u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
-
-#ifndef CONFIG_64BIT
-	/*
-	 * Take rq->lock to make 64-bit write safe on 32-bit platforms.
-	 */
-	raw_spin_lock_irq(&cpu_rq(cpu)->lock);
-	*cpuusage = val;
-	raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
-#else
-	*cpuusage = val;
-#endif
-}
-
-/* return total cpu usage (in nanoseconds) of a group */
-static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft)
-{
-	struct cpuacct *ca = cgroup_ca(cgrp);
-	u64 totalcpuusage = 0;
-	int i;
-
-	for_each_present_cpu(i)
-		totalcpuusage += cpuacct_cpuusage_read(ca, i);
-
-	return totalcpuusage;
-}
-
-static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype,
-								u64 reset)
-{
-	struct cpuacct *ca = cgroup_ca(cgrp);
-	int err = 0;
-	int i;
-
-	if (reset) {
-		err = -EINVAL;
-		goto out;
-	}
-
-	for_each_present_cpu(i)
-		cpuacct_cpuusage_write(ca, i, 0);
-
-out:
-	return err;
-}
-
-static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft,
-				   struct seq_file *m)
-{
-	struct cpuacct *ca = cgroup_ca(cgroup);
-	u64 percpu;
-	int i;
-
-	for_each_present_cpu(i) {
-		percpu = cpuacct_cpuusage_read(ca, i);
-		seq_printf(m, "%llu ", (unsigned long long) percpu);
-	}
-	seq_printf(m, "\n");
-	return 0;
-}
-
-static const char *cpuacct_stat_desc[] = {
-	[CPUACCT_STAT_USER] = "user",
-	[CPUACCT_STAT_SYSTEM] = "system",
-};
-
-static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft,
-			      struct cgroup_map_cb *cb)
-{
-	struct cpuacct *ca = cgroup_ca(cgrp);
-	int cpu;
-	s64 val = 0;
-
-	for_each_online_cpu(cpu) {
-		struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu);
-		val += kcpustat->cpustat[CPUTIME_USER];
-		val += kcpustat->cpustat[CPUTIME_NICE];
-	}
-	val = cputime64_to_clock_t(val);
-	cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_USER], val);
-
-	val = 0;
-	for_each_online_cpu(cpu) {
-		struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu);
-		val += kcpustat->cpustat[CPUTIME_SYSTEM];
-		val += kcpustat->cpustat[CPUTIME_IRQ];
-		val += kcpustat->cpustat[CPUTIME_SOFTIRQ];
-	}
-
-	val = cputime64_to_clock_t(val);
-	cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val);
-
-	return 0;
-}
-
-static struct cftype files[] = {
-	{
-		.name = "usage",
-		.read_u64 = cpuusage_read,
-		.write_u64 = cpuusage_write,
-	},
-	{
-		.name = "usage_percpu",
-		.read_seq_string = cpuacct_percpu_seq_read,
-	},
-	{
-		.name = "stat",
-		.read_map = cpuacct_stats_show,
-	},
-	{ }	/* terminate */
-};
-
-/*
- * charge this task's execution time to its accounting group.
- *
- * called with rq->lock held.
- */
-void cpuacct_charge(struct task_struct *tsk, u64 cputime)
-{
-	struct cpuacct *ca;
-	int cpu;
-
-	if (unlikely(!cpuacct_subsys.active))
-		return;
-
-	cpu = task_cpu(tsk);
-
-	rcu_read_lock();
-
-	ca = task_ca(tsk);
-
-	for (; ca; ca = parent_ca(ca)) {
-		u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
-		*cpuusage += cputime;
-	}
-
-	rcu_read_unlock();
-}
-
-struct cgroup_subsys cpuacct_subsys = {
-	.name = "cpuacct",
-	.css_alloc = cpuacct_css_alloc,
-	.css_free = cpuacct_css_free,
-	.subsys_id = cpuacct_subsys_id,
-	.base_cftypes = files,
-};
-#endif	/* CONFIG_CGROUP_CPUACCT */
-
 void dump_cpu_task(int cpu)
 {
 	pr_info("Task dump for CPU %d:\n", cpu);
diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
new file mode 100644
index 000000000000..dbb7e2cd95eb
--- /dev/null
+++ b/kernel/sched/cpuacct.c
@@ -0,0 +1,296 @@
+#include <linux/cgroup.h>
+#include <linux/slab.h>
+#include <linux/percpu.h>
+#include <linux/spinlock.h>
+#include <linux/cpumask.h>
+#include <linux/seq_file.h>
+#include <linux/rcupdate.h>
+#include <linux/kernel_stat.h>
+#include <linux/err.h>
+
+#include "sched.h"
+
+/*
+ * CPU accounting code for task groups.
+ *
+ * Based on the work by Paul Menage (menage@google.com) and Balbir Singh
+ * (balbir@in.ibm.com).
+ */
+
+/* Time spent by the tasks of the cpu accounting group executing in ... */
+enum cpuacct_stat_index {
+	CPUACCT_STAT_USER,	/* ... user mode */
+	CPUACCT_STAT_SYSTEM,	/* ... kernel mode */
+
+	CPUACCT_STAT_NSTATS,
+};
+
+/* track cpu usage of a group of tasks and its child groups */
+struct cpuacct {
+	struct cgroup_subsys_state css;
+	/* cpuusage holds pointer to a u64-type object on every cpu */
+	u64 __percpu *cpuusage;
+	struct kernel_cpustat __percpu *cpustat;
+};
+
+/* return cpu accounting group corresponding to this container */
+static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp)
+{
+	return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id),
+			    struct cpuacct, css);
+}
+
+/* return cpu accounting group to which this task belongs */
+static inline struct cpuacct *task_ca(struct task_struct *tsk)
+{
+	return container_of(task_subsys_state(tsk, cpuacct_subsys_id),
+			    struct cpuacct, css);
+}
+
+static inline struct cpuacct *__parent_ca(struct cpuacct *ca)
+{
+	return cgroup_ca(ca->css.cgroup->parent);
+}
+
+static inline struct cpuacct *parent_ca(struct cpuacct *ca)
+{
+	if (!ca->css.cgroup->parent)
+		return NULL;
+	return cgroup_ca(ca->css.cgroup->parent);
+}
+
+static DEFINE_PER_CPU(u64, root_cpuacct_cpuusage);
+static struct cpuacct root_cpuacct = {
+	.cpustat	= &kernel_cpustat,
+	.cpuusage	= &root_cpuacct_cpuusage,
+};
+
+/* create a new cpu accounting group */
+static struct cgroup_subsys_state *cpuacct_css_alloc(struct cgroup *cgrp)
+{
+	struct cpuacct *ca;
+
+	if (!cgrp->parent)
+		return &root_cpuacct.css;
+
+	ca = kzalloc(sizeof(*ca), GFP_KERNEL);
+	if (!ca)
+		goto out;
+
+	ca->cpuusage = alloc_percpu(u64);
+	if (!ca->cpuusage)
+		goto out_free_ca;
+
+	ca->cpustat = alloc_percpu(struct kernel_cpustat);
+	if (!ca->cpustat)
+		goto out_free_cpuusage;
+
+	return &ca->css;
+
+out_free_cpuusage:
+	free_percpu(ca->cpuusage);
+out_free_ca:
+	kfree(ca);
+out:
+	return ERR_PTR(-ENOMEM);
+}
+
+/* destroy an existing cpu accounting group */
+static void cpuacct_css_free(struct cgroup *cgrp)
+{
+	struct cpuacct *ca = cgroup_ca(cgrp);
+
+	free_percpu(ca->cpustat);
+	free_percpu(ca->cpuusage);
+	kfree(ca);
+}
+
+static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
+{
+	u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
+	u64 data;
+
+#ifndef CONFIG_64BIT
+	/*
+	 * Take rq->lock to make 64-bit read safe on 32-bit platforms.
+	 */
+	raw_spin_lock_irq(&cpu_rq(cpu)->lock);
+	data = *cpuusage;
+	raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
+#else
+	data = *cpuusage;
+#endif
+
+	return data;
+}
+
+static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
+{
+	u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
+
+#ifndef CONFIG_64BIT
+	/*
+	 * Take rq->lock to make 64-bit write safe on 32-bit platforms.
+	 */
+	raw_spin_lock_irq(&cpu_rq(cpu)->lock);
+	*cpuusage = val;
+	raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
+#else
+	*cpuusage = val;
+#endif
+}
+
+/* return total cpu usage (in nanoseconds) of a group */
+static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft)
+{
+	struct cpuacct *ca = cgroup_ca(cgrp);
+	u64 totalcpuusage = 0;
+	int i;
+
+	for_each_present_cpu(i)
+		totalcpuusage += cpuacct_cpuusage_read(ca, i);
+
+	return totalcpuusage;
+}
+
+static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype,
+								u64 reset)
+{
+	struct cpuacct *ca = cgroup_ca(cgrp);
+	int err = 0;
+	int i;
+
+	if (reset) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	for_each_present_cpu(i)
+		cpuacct_cpuusage_write(ca, i, 0);
+
+out:
+	return err;
+}
+
+static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft,
+				   struct seq_file *m)
+{
+	struct cpuacct *ca = cgroup_ca(cgroup);
+	u64 percpu;
+	int i;
+
+	for_each_present_cpu(i) {
+		percpu = cpuacct_cpuusage_read(ca, i);
+		seq_printf(m, "%llu ", (unsigned long long) percpu);
+	}
+	seq_printf(m, "\n");
+	return 0;
+}
+
+static const char * const cpuacct_stat_desc[] = {
+	[CPUACCT_STAT_USER] = "user",
+	[CPUACCT_STAT_SYSTEM] = "system",
+};
+
+static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft,
+			      struct cgroup_map_cb *cb)
+{
+	struct cpuacct *ca = cgroup_ca(cgrp);
+	int cpu;
+	s64 val = 0;
+
+	for_each_online_cpu(cpu) {
+		struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu);
+		val += kcpustat->cpustat[CPUTIME_USER];
+		val += kcpustat->cpustat[CPUTIME_NICE];
+	}
+	val = cputime64_to_clock_t(val);
+	cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_USER], val);
+
+	val = 0;
+	for_each_online_cpu(cpu) {
+		struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu);
+		val += kcpustat->cpustat[CPUTIME_SYSTEM];
+		val += kcpustat->cpustat[CPUTIME_IRQ];
+		val += kcpustat->cpustat[CPUTIME_SOFTIRQ];
+	}
+
+	val = cputime64_to_clock_t(val);
+	cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val);
+
+	return 0;
+}
+
+static struct cftype files[] = {
+	{
+		.name = "usage",
+		.read_u64 = cpuusage_read,
+		.write_u64 = cpuusage_write,
+	},
+	{
+		.name = "usage_percpu",
+		.read_seq_string = cpuacct_percpu_seq_read,
+	},
+	{
+		.name = "stat",
+		.read_map = cpuacct_stats_show,
+	},
+	{ }	/* terminate */
+};
+
+/*
+ * charge this task's execution time to its accounting group.
+ *
+ * called with rq->lock held.
+ */
+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;
+	}
+
+	rcu_read_unlock();
+}
+
+/*
+ * Add user/system time to cpuacct.
+ *
+ * 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)
+{
+	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);
+	}
+	rcu_read_unlock();
+}
+
+struct cgroup_subsys cpuacct_subsys = {
+	.name		= "cpuacct",
+	.css_alloc	= cpuacct_css_alloc,
+	.css_free	= cpuacct_css_free,
+	.subsys_id	= cpuacct_subsys_id,
+	.base_cftypes	= files,
+	.early_init	= 1,
+};
diff --git a/kernel/sched/cpuacct.h b/kernel/sched/cpuacct.h
new file mode 100644
index 000000000000..ed605624a5e7
--- /dev/null
+++ b/kernel/sched/cpuacct.h
@@ -0,0 +1,17 @@
+#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);
+
+#else
+
+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)
+{
+}
+
+#endif
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 699d59756ece..ea32f02bf2c3 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -115,10 +115,6 @@ static int irqtime_account_si_update(void)
 static inline void task_group_account_field(struct task_struct *p, int index,
 					    u64 tmp)
 {
-#ifdef CONFIG_CGROUP_CPUACCT
-	struct kernel_cpustat *kcpustat;
-	struct cpuacct *ca;
-#endif
 	/*
 	 * Since all updates are sure to touch the root cgroup, we
 	 * get ourselves ahead and touch it first. If the root cgroup
@@ -127,19 +123,7 @@ static inline void task_group_account_field(struct task_struct *p, int index,
 	 */
 	__get_cpu_var(kernel_cpustat).cpustat[index] += tmp;
 
-#ifdef CONFIG_CGROUP_CPUACCT
-	if (unlikely(!cpuacct_subsys.active))
-		return;
-
-	rcu_read_lock();
-	ca = task_ca(p);
-	while (ca && (ca != &root_cpuacct)) {
-		kcpustat = this_cpu_ptr(ca->cpustat);
-		kcpustat->cpustat[index] += tmp;
-		ca = parent_ca(ca);
-	}
-	rcu_read_unlock();
-#endif
+	cpuacct_account_field(p, index, tmp);
 }
 
 /*
@@ -310,7 +294,7 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
 
 	t = tsk;
 	do {
-		task_cputime(tsk, &utime, &stime);
+		task_cputime(t, &utime, &stime);
 		times->utime += utime;
 		times->stime += stime;
 		times->sum_exec_runtime += task_sched_runtime(t);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5c97fca091a7..c61a614465c8 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1563,6 +1563,27 @@ static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq,
 		se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
 	} /* migrations, e.g. sleep=0 leave decay_count == 0 */
 }
+
+/*
+ * Update the rq's load with the elapsed running time before entering
+ * idle. if the last scheduled task is not a CFS task, idle_enter will
+ * be the only way to update the runnable statistic.
+ */
+void idle_enter_fair(struct rq *this_rq)
+{
+	update_rq_runnable_avg(this_rq, 1);
+}
+
+/*
+ * Update the rq's load with the elapsed idle time before a task is
+ * scheduled. if the newly scheduled task is not a CFS task, idle_exit will
+ * be the only way to update the runnable statistic.
+ */
+void idle_exit_fair(struct rq *this_rq)
+{
+	update_rq_runnable_avg(this_rq, 0);
+}
+
 #else
 static inline void update_entity_load_avg(struct sched_entity *se,
 					  int update_cfs_rq) {}
@@ -3875,12 +3896,16 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	int tsk_cache_hot = 0;
 	/*
 	 * We do not migrate tasks that are:
-	 * 1) running (obviously), or
+	 * 1) throttled_lb_pair, or
 	 * 2) cannot be migrated to this CPU due to cpus_allowed, or
-	 * 3) are cache-hot on their current CPU.
+	 * 3) running (obviously), or
+	 * 4) are cache-hot on their current CPU.
 	 */
+	if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu))
+		return 0;
+
 	if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) {
-		int new_dst_cpu;
+		int cpu;
 
 		schedstat_inc(p, se.statistics.nr_failed_migrations_affine);
 
@@ -3895,12 +3920,15 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 		if (!env->dst_grpmask || (env->flags & LBF_SOME_PINNED))
 			return 0;
 
-		new_dst_cpu = cpumask_first_and(env->dst_grpmask,
-						tsk_cpus_allowed(p));
-		if (new_dst_cpu < nr_cpu_ids) {
-			env->flags |= LBF_SOME_PINNED;
-			env->new_dst_cpu = new_dst_cpu;
+		/* Prevent to re-select dst_cpu via env's cpus */
+		for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) {
+			if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) {
+				env->flags |= LBF_SOME_PINNED;
+				env->new_dst_cpu = cpu;
+				break;
+			}
 		}
+
 		return 0;
 	}
 
@@ -3921,20 +3949,17 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	tsk_cache_hot = task_hot(p, env->src_rq->clock_task, env->sd);
 	if (!tsk_cache_hot ||
 		env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
-#ifdef CONFIG_SCHEDSTATS
+
 		if (tsk_cache_hot) {
 			schedstat_inc(env->sd, lb_hot_gained[env->idle]);
 			schedstat_inc(p, se.statistics.nr_forced_migrations);
 		}
-#endif
+
 		return 1;
 	}
 
-	if (tsk_cache_hot) {
-		schedstat_inc(p, se.statistics.nr_failed_migrations_hot);
-		return 0;
-	}
-	return 1;
+	schedstat_inc(p, se.statistics.nr_failed_migrations_hot);
+	return 0;
 }
 
 /*
@@ -3949,9 +3974,6 @@ static int move_one_task(struct lb_env *env)
 	struct task_struct *p, *n;
 
 	list_for_each_entry_safe(p, n, &env->src_rq->cfs_tasks, se.group_node) {
-		if (throttled_lb_pair(task_group(p), env->src_rq->cpu, env->dst_cpu))
-			continue;
-
 		if (!can_migrate_task(p, env))
 			continue;
 
@@ -4003,7 +4025,7 @@ static int move_tasks(struct lb_env *env)
 			break;
 		}
 
-		if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu))
+		if (!can_migrate_task(p, env))
 			goto next;
 
 		load = task_h_load(p);
@@ -4014,9 +4036,6 @@ static int move_tasks(struct lb_env *env)
 		if ((load / 2) > env->imbalance)
 			goto next;
 
-		if (!can_migrate_task(p, env))
-			goto next;
-
 		move_task(p, env);
 		pulled++;
 		env->imbalance -= load;
@@ -4961,7 +4980,7 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 #define MAX_PINNED_INTERVAL	512
 
 /* Working cpumask for load_balance and load_balance_newidle. */
-DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
+DEFINE_PER_CPU(cpumask_var_t, load_balance_mask);
 
 static int need_active_balance(struct lb_env *env)
 {
@@ -4992,11 +5011,10 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 			int *balance)
 {
 	int ld_moved, cur_ld_moved, active_balance = 0;
-	int lb_iterations, max_lb_iterations;
 	struct sched_group *group;
 	struct rq *busiest;
 	unsigned long flags;
-	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
+	struct cpumask *cpus = __get_cpu_var(load_balance_mask);
 
 	struct lb_env env = {
 		.sd		= sd,
@@ -5008,8 +5026,14 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 		.cpus		= cpus,
 	};
 
+	/*
+	 * For NEWLY_IDLE load_balancing, we don't need to consider
+	 * other cpus in our group
+	 */
+	if (idle == CPU_NEWLY_IDLE)
+		env.dst_grpmask = NULL;
+
 	cpumask_copy(cpus, cpu_active_mask);
-	max_lb_iterations = cpumask_weight(env.dst_grpmask);
 
 	schedstat_inc(sd, lb_count[idle]);
 
@@ -5035,7 +5059,6 @@ redo:
 	schedstat_add(sd, lb_imbalance[idle], env.imbalance);
 
 	ld_moved = 0;
-	lb_iterations = 1;
 	if (busiest->nr_running > 1) {
 		/*
 		 * Attempt to move tasks. If find_busiest_group has found
@@ -5062,17 +5085,17 @@ more_balance:
 		double_rq_unlock(env.dst_rq, busiest);
 		local_irq_restore(flags);
 
-		if (env.flags & LBF_NEED_BREAK) {
-			env.flags &= ~LBF_NEED_BREAK;
-			goto more_balance;
-		}
-
 		/*
 		 * some other cpu did the load balance for us.
 		 */
 		if (cur_ld_moved && env.dst_cpu != smp_processor_id())
 			resched_cpu(env.dst_cpu);
 
+		if (env.flags & LBF_NEED_BREAK) {
+			env.flags &= ~LBF_NEED_BREAK;
+			goto more_balance;
+		}
+
 		/*
 		 * Revisit (affine) tasks on src_cpu that couldn't be moved to
 		 * us and move them to an alternate dst_cpu in our sched_group
@@ -5092,14 +5115,17 @@ more_balance:
 		 * moreover subsequent load balance cycles should correct the
 		 * excess load moved.
 		 */
-		if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0 &&
-				lb_iterations++ < max_lb_iterations) {
+		if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0) {
 
 			env.dst_rq	 = cpu_rq(env.new_dst_cpu);
 			env.dst_cpu	 = env.new_dst_cpu;
 			env.flags	&= ~LBF_SOME_PINNED;
 			env.loop	 = 0;
 			env.loop_break	 = sched_nr_migrate_break;
+
+			/* Prevent to re-select dst_cpu via env's cpus */
+			cpumask_clear_cpu(env.dst_cpu, env.cpus);
+
 			/*
 			 * Go back to "more_balance" rather than "redo" since we
 			 * need to continue with same src_cpu.
@@ -5220,8 +5246,6 @@ void idle_balance(int this_cpu, struct rq *this_rq)
 	if (this_rq->avg_idle < sysctl_sched_migration_cost)
 		return;
 
-	update_rq_runnable_avg(this_rq, 1);
-
 	/*
 	 * Drop the rq->lock, but keep IRQ/preempt disabled.
 	 */
@@ -5396,13 +5420,16 @@ static inline void set_cpu_sd_state_busy(void)
 	struct sched_domain *sd;
 	int cpu = smp_processor_id();
 
-	if (!test_bit(NOHZ_IDLE, nohz_flags(cpu)))
-		return;
-	clear_bit(NOHZ_IDLE, nohz_flags(cpu));
-
 	rcu_read_lock();
-	for_each_domain(cpu, sd)
+	sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd);
+
+	if (!sd || !sd->nohz_idle)
+		goto unlock;
+	sd->nohz_idle = 0;
+
+	for (; sd; sd = sd->parent)
 		atomic_inc(&sd->groups->sgp->nr_busy_cpus);
+unlock:
 	rcu_read_unlock();
 }
 
@@ -5411,13 +5438,16 @@ void set_cpu_sd_state_idle(void)
 	struct sched_domain *sd;
 	int cpu = smp_processor_id();
 
-	if (test_bit(NOHZ_IDLE, nohz_flags(cpu)))
-		return;
-	set_bit(NOHZ_IDLE, nohz_flags(cpu));
-
 	rcu_read_lock();
-	for_each_domain(cpu, sd)
+	sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd);
+
+	if (!sd || sd->nohz_idle)
+		goto unlock;
+	sd->nohz_idle = 1;
+
+	for (; sd; sd = sd->parent)
 		atomic_dec(&sd->groups->sgp->nr_busy_cpus);
+unlock:
 	rcu_read_unlock();
 }
 
@@ -5469,7 +5499,7 @@ void update_max_interval(void)
  * It checks each scheduling domain to see if it is due to be balanced,
  * and initiates a balancing operation if so.
  *
- * Balancing parameters are set up in arch_init_sched_domains.
+ * Balancing parameters are set up in init_sched_domains.
  */
 static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 {
@@ -5507,10 +5537,11 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 		if (time_after_eq(jiffies, sd->last_balance + interval)) {
 			if (load_balance(cpu, rq, sd, idle, &balance)) {
 				/*
-				 * We've pulled tasks over so either we're no
-				 * longer idle.
+				 * The LBF_SOME_PINNED logic could have changed
+				 * env->dst_cpu, so we can't know our idle
+				 * state even if we migrated tasks. Update it.
 				 */
-				idle = CPU_NOT_IDLE;
+				idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE;
 			}
 			sd->last_balance = jiffies;
 		}
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 1ad1d2b5395f..99399f8e4799 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -46,13 +46,6 @@ SCHED_FEAT(DOUBLE_TICK, false)
 SCHED_FEAT(LB_BIAS, true)
 
 /*
- * Spin-wait on mutex acquisition when the mutex owner is running on
- * another cpu -- assumes that when the owner is running, it will soon
- * release the lock. Decreases scheduling overhead.
- */
-SCHED_FEAT(OWNER_SPIN, true)
-
-/*
  * Decrement CPU power based on time not spent running tasks
  */
 SCHED_FEAT(NONTASK_POWER, true)
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index b6baf370cae9..b8ce77328341 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -13,6 +13,16 @@ select_task_rq_idle(struct task_struct *p, int sd_flag, int flags)
 {
 	return task_cpu(p); /* IDLE tasks as never migrated */
 }
+
+static void pre_schedule_idle(struct rq *rq, struct task_struct *prev)
+{
+	idle_exit_fair(rq);
+}
+
+static void post_schedule_idle(struct rq *rq)
+{
+	idle_enter_fair(rq);
+}
 #endif /* CONFIG_SMP */
 /*
  * Idle tasks are unconditionally rescheduled:
@@ -25,6 +35,10 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
 static struct task_struct *pick_next_task_idle(struct rq *rq)
 {
 	schedstat_inc(rq, sched_goidle);
+#ifdef CONFIG_SMP
+	/* Trigger the post schedule to do an idle_enter for CFS */
+	rq->post_schedule = 1;
+#endif
 	return rq->idle;
 }
 
@@ -86,6 +100,8 @@ const struct sched_class idle_sched_class = {
 
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_idle,
+	.pre_schedule		= pre_schedule_idle,
+	.post_schedule		= post_schedule_idle,
 #endif
 
 	.set_curr_task          = set_curr_task_idle,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index eb363aa5d83c..24dc29897749 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -8,6 +8,7 @@
 #include <linux/tick.h>
 
 #include "cpupri.h"
+#include "cpuacct.h"
 
 extern __read_mostly int scheduler_running;
 
@@ -951,14 +952,6 @@ static const u32 prio_to_wmult[40] = {
  /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
 };
 
-/* Time spent by the tasks of the cpu accounting group executing in ... */
-enum cpuacct_stat_index {
-	CPUACCT_STAT_USER,	/* ... user mode */
-	CPUACCT_STAT_SYSTEM,	/* ... kernel mode */
-
-	CPUACCT_STAT_NSTATS,
-};
-
 #define ENQUEUE_WAKEUP		1
 #define ENQUEUE_HEAD		2
 #ifdef CONFIG_SMP
@@ -1032,6 +1025,18 @@ extern void update_group_power(struct sched_domain *sd, int cpu);
 extern void trigger_load_balance(struct rq *rq, int cpu);
 extern void idle_balance(int this_cpu, struct rq *this_rq);
 
+/*
+ * Only depends on SMP, FAIR_GROUP_SCHED may be removed when runnable_avg
+ * becomes useful in lb
+ */
+#if defined(CONFIG_FAIR_GROUP_SCHED)
+extern void idle_enter_fair(struct rq *this_rq);
+extern void idle_exit_fair(struct rq *this_rq);
+#else
+static inline void idle_enter_fair(struct rq *this_rq) {}
+static inline void idle_exit_fair(struct rq *this_rq) {}
+#endif
+
 #else	/* CONFIG_SMP */
 
 static inline void idle_balance(int cpu, struct rq *rq)
@@ -1055,45 +1060,6 @@ extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime
 
 extern void update_idle_cpu_load(struct rq *this_rq);
 
-#ifdef CONFIG_CGROUP_CPUACCT
-#include <linux/cgroup.h>
-/* track cpu usage of a group of tasks and its child groups */
-struct cpuacct {
-	struct cgroup_subsys_state css;
-	/* cpuusage holds pointer to a u64-type object on every cpu */
-	u64 __percpu *cpuusage;
-	struct kernel_cpustat __percpu *cpustat;
-};
-
-extern struct cgroup_subsys cpuacct_subsys;
-extern struct cpuacct root_cpuacct;
-
-/* return cpu accounting group corresponding to this container */
-static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp)
-{
-	return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id),
-			    struct cpuacct, css);
-}
-
-/* return cpu accounting group to which this task belongs */
-static inline struct cpuacct *task_ca(struct task_struct *tsk)
-{
-	return container_of(task_subsys_state(tsk, cpuacct_subsys_id),
-			    struct cpuacct, css);
-}
-
-static inline struct cpuacct *parent_ca(struct cpuacct *ca)
-{
-	if (!ca || !ca->css.cgroup->parent)
-		return NULL;
-	return cgroup_ca(ca->css.cgroup->parent);
-}
-
-extern void cpuacct_charge(struct task_struct *tsk, u64 cputime);
-#else
-static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
-#endif
-
 #ifdef CONFIG_PARAVIRT
 static inline u64 steal_ticks(u64 steal)
 {
@@ -1348,7 +1314,6 @@ extern void account_cfs_bandwidth_used(int enabled, int was_enabled);
 enum rq_nohz_flag_bits {
 	NOHZ_TICK_STOPPED,
 	NOHZ_BALANCE_KICK,
-	NOHZ_IDLE,
 };
 
 #define nohz_flags(cpu)	(&cpu_rq(cpu)->nohz_flags)