25 files changed, 477 insertions, 84 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index eca595e2fd5..988cb3da703 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -101,6 +101,7 @@ obj-$(CONFIG_RING_BUFFER) += trace/
 obj-$(CONFIG_TRACEPOINTS) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
 obj-$(CONFIG_IRQ_WORK) += irq_work.o
+obj-$(CONFIG_CPU_PM) += cpu_pm.o
 
 obj-$(CONFIG_PERF_EVENTS) += events/
 
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index e691818d7e4..a3f638ac3de 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -153,6 +153,13 @@ static void freezer_destroy(struct cgroup_subsys *ss,
 	kfree(cgroup_freezer(cgroup));
 }
 
+/* task is frozen or will freeze immediately when next it gets woken */
+static bool is_task_frozen_enough(struct task_struct *task)
+{
+	return frozen(task) ||
+		(task_is_stopped_or_traced(task) && freezing(task));
+}
+
 /*
  * The call to cgroup_lock() in the freezer.state write method prevents
  * a write to that file racing against an attach, and hence the
@@ -231,7 +238,7 @@ static void update_if_frozen(struct cgroup *cgroup,
 	cgroup_iter_start(cgroup, &it);
 	while ((task = cgroup_iter_next(cgroup, &it))) {
 		ntotal++;
-		if (frozen(task))
+		if (is_task_frozen_enough(task))
 			nfrozen++;
 	}
 
@@ -284,7 +291,7 @@ static int try_to_freeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
 	while ((task = cgroup_iter_next(cgroup, &it))) {
 		if (!freeze_task(task, true))
 			continue;
-		if (frozen(task))
+		if (is_task_frozen_enough(task))
 			continue;
 		if (!freezing(task) && !freezer_should_skip(task))
 			num_cant_freeze_now++;
diff --git a/kernel/cpu_pm.c b/kernel/cpu_pm.c
new file mode 100644
index 00000000000..249152e1530
--- /dev/null
+++ b/kernel/cpu_pm.c
@@ -0,0 +1,233 @@
+/*
+ * Copyright (C) 2011 Google, Inc.
+ *
+ * Author:
+ *	Colin Cross <ccross@android.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/cpu_pm.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+#include <linux/spinlock.h>
+#include <linux/syscore_ops.h>
+
+static DEFINE_RWLOCK(cpu_pm_notifier_lock);
+static RAW_NOTIFIER_HEAD(cpu_pm_notifier_chain);
+
+static int cpu_pm_notify(enum cpu_pm_event event, int nr_to_call, int *nr_calls)
+{
+	int ret;
+
+	ret = __raw_notifier_call_chain(&cpu_pm_notifier_chain, event, NULL,
+		nr_to_call, nr_calls);
+
+	return notifier_to_errno(ret);
+}
+
+/**
+ * cpu_pm_register_notifier - register a driver with cpu_pm
+ * @nb: notifier block to register
+ *
+ * Add a driver to a list of drivers that are notified about
+ * CPU and CPU cluster low power entry and exit.
+ *
+ * This function may sleep, and has the same return conditions as
+ * raw_notifier_chain_register.
+ */
+int cpu_pm_register_notifier(struct notifier_block *nb)
+{
+	unsigned long flags;
+	int ret;
+
+	write_lock_irqsave(&cpu_pm_notifier_lock, flags);
+	ret = raw_notifier_chain_register(&cpu_pm_notifier_chain, nb);
+	write_unlock_irqrestore(&cpu_pm_notifier_lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cpu_pm_register_notifier);
+
+/**
+ * cpu_pm_unregister_notifier - unregister a driver with cpu_pm
+ * @nb: notifier block to be unregistered
+ *
+ * Remove a driver from the CPU PM notifier list.
+ *
+ * This function may sleep, and has the same return conditions as
+ * raw_notifier_chain_unregister.
+ */
+int cpu_pm_unregister_notifier(struct notifier_block *nb)
+{
+	unsigned long flags;
+	int ret;
+
+	write_lock_irqsave(&cpu_pm_notifier_lock, flags);
+	ret = raw_notifier_chain_unregister(&cpu_pm_notifier_chain, nb);
+	write_unlock_irqrestore(&cpu_pm_notifier_lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cpu_pm_unregister_notifier);
+
+/**
+ * cpm_pm_enter - CPU low power entry notifier
+ *
+ * Notifies listeners that a single CPU is entering a low power state that may
+ * cause some blocks in the same power domain as the cpu to reset.
+ *
+ * Must be called on the affected CPU with interrupts disabled.  Platform is
+ * responsible for ensuring that cpu_pm_enter is not called twice on the same
+ * CPU before cpu_pm_exit is called. Notified drivers can include VFP
+ * co-processor, interrupt controller and it's PM extensions, local CPU
+ * timers context save/restore which shouldn't be interrupted. Hence it
+ * must be called with interrupts disabled.
+ *
+ * Return conditions are same as __raw_notifier_call_chain.
+ */
+int cpu_pm_enter(void)
+{
+	int nr_calls;
+	int ret = 0;
+
+	read_lock(&cpu_pm_notifier_lock);
+	ret = cpu_pm_notify(CPU_PM_ENTER, -1, &nr_calls);
+	if (ret)
+		/*
+		 * Inform listeners (nr_calls - 1) about failure of CPU PM
+		 * PM entry who are notified earlier to prepare for it.
+		 */
+		cpu_pm_notify(CPU_PM_ENTER_FAILED, nr_calls - 1, NULL);
+	read_unlock(&cpu_pm_notifier_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cpu_pm_enter);
+
+/**
+ * cpm_pm_exit - CPU low power exit notifier
+ *
+ * Notifies listeners that a single CPU is exiting a low power state that may
+ * have caused some blocks in the same power domain as the cpu to reset.
+ *
+ * Notified drivers can include VFP co-processor, interrupt controller
+ * and it's PM extensions, local CPU timers context save/restore which
+ * shouldn't be interrupted. Hence it must be called with interrupts disabled.
+ *
+ * Return conditions are same as __raw_notifier_call_chain.
+ */
+int cpu_pm_exit(void)
+{
+	int ret;
+
+	read_lock(&cpu_pm_notifier_lock);
+	ret = cpu_pm_notify(CPU_PM_EXIT, -1, NULL);
+	read_unlock(&cpu_pm_notifier_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cpu_pm_exit);
+
+/**
+ * cpm_cluster_pm_enter - CPU cluster low power entry notifier
+ *
+ * Notifies listeners that all cpus in a power domain are entering a low power
+ * state that may cause some blocks in the same power domain to reset.
+ *
+ * Must be called after cpu_pm_enter has been called on all cpus in the power
+ * domain, and before cpu_pm_exit has been called on any cpu in the power
+ * domain. Notified drivers can include VFP co-processor, interrupt controller
+ * and it's PM extensions, local CPU timers context save/restore which
+ * shouldn't be interrupted. Hence it must be called with interrupts disabled.
+ *
+ * Must be called with interrupts disabled.
+ *
+ * Return conditions are same as __raw_notifier_call_chain.
+ */
+int cpu_cluster_pm_enter(void)
+{
+	int nr_calls;
+	int ret = 0;
+
+	read_lock(&cpu_pm_notifier_lock);
+	ret = cpu_pm_notify(CPU_CLUSTER_PM_ENTER, -1, &nr_calls);
+	if (ret)
+		/*
+		 * Inform listeners (nr_calls - 1) about failure of CPU cluster
+		 * PM entry who are notified earlier to prepare for it.
+		 */
+		cpu_pm_notify(CPU_CLUSTER_PM_ENTER_FAILED, nr_calls - 1, NULL);
+	read_unlock(&cpu_pm_notifier_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cpu_cluster_pm_enter);
+
+/**
+ * cpm_cluster_pm_exit - CPU cluster low power exit notifier
+ *
+ * Notifies listeners that all cpus in a power domain are exiting form a
+ * low power state that may have caused some blocks in the same power domain
+ * to reset.
+ *
+ * Must be called after cpu_pm_exit has been called on all cpus in the power
+ * domain, and before cpu_pm_exit has been called on any cpu in the power
+ * domain. Notified drivers can include VFP co-processor, interrupt controller
+ * and it's PM extensions, local CPU timers context save/restore which
+ * shouldn't be interrupted. Hence it must be called with interrupts disabled.
+ *
+ * Return conditions are same as __raw_notifier_call_chain.
+ */
+int cpu_cluster_pm_exit(void)
+{
+	int ret;
+
+	read_lock(&cpu_pm_notifier_lock);
+	ret = cpu_pm_notify(CPU_CLUSTER_PM_EXIT, -1, NULL);
+	read_unlock(&cpu_pm_notifier_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cpu_cluster_pm_exit);
+
+#ifdef CONFIG_PM
+static int cpu_pm_suspend(void)
+{
+	int ret;
+
+	ret = cpu_pm_enter();
+	if (ret)
+		return ret;
+
+	ret = cpu_cluster_pm_enter();
+	return ret;
+}
+
+static void cpu_pm_resume(void)
+{
+	cpu_cluster_pm_exit();
+	cpu_pm_exit();
+}
+
+static struct syscore_ops cpu_pm_syscore_ops = {
+	.suspend = cpu_pm_suspend,
+	.resume = cpu_pm_resume,
+};
+
+static int cpu_pm_init(void)
+{
+	register_syscore_ops(&cpu_pm_syscore_ops);
+	return 0;
+}
+core_initcall(cpu_pm_init);
+#endif
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0f857782d06..fbe38f2e8ed 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5758,6 +5758,7 @@ struct pmu *perf_init_event(struct perf_event *event)
 	pmu = idr_find(&pmu_idr, event->attr.type);
 	rcu_read_unlock();
 	if (pmu) {
+		event->pmu = pmu;
 		ret = pmu->event_init(event);
 		if (ret)
 			pmu = ERR_PTR(ret);
@@ -5765,6 +5766,7 @@ struct pmu *perf_init_event(struct perf_event *event)
 	}
 
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		event->pmu = pmu;
 		ret = pmu->event_init(event);
 		if (!ret)
 			goto unlock;
@@ -5891,8 +5893,6 @@ done:
 		return ERR_PTR(err);
 	}
 
-	event->pmu = pmu;
-
 	if (!event->parent) {
 		if (event->attach_state & PERF_ATTACH_TASK)
 			jump_label_inc(&perf_sched_events);
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index a9205e32a05..2043c08d36c 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -885,10 +885,13 @@ static void __remove_hrtimer(struct hrtimer *timer,
 			     struct hrtimer_clock_base *base,
 			     unsigned long newstate, int reprogram)
 {
+	struct timerqueue_node *next_timer;
 	if (!(timer->state & HRTIMER_STATE_ENQUEUED))
 		goto out;
 
-	if (&timer->node == timerqueue_getnext(&base->active)) {
+	next_timer = timerqueue_getnext(&base->active);
+	timerqueue_del(&base->active, &timer->node);
+	if (&timer->node == next_timer) {
 #ifdef CONFIG_HIGH_RES_TIMERS
 		/* Reprogram the clock event device. if enabled */
 		if (reprogram && hrtimer_hres_active()) {
@@ -901,7 +904,6 @@ static void __remove_hrtimer(struct hrtimer *timer,
 		}
 #endif
 	}
-	timerqueue_del(&base->active, &timer->node);
 	if (!timerqueue_getnext(&base->active))
 		base->cpu_base->active_bases &= ~(1 << base->index);
 out:
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 9b956fa2030..d6c4adc2804 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -620,8 +620,9 @@ static irqreturn_t irq_nested_primary_handler(int irq, void *dev_id)
 
 static int irq_wait_for_interrupt(struct irqaction *action)
 {
+	set_current_state(TASK_INTERRUPTIBLE);
+
 	while (!kthread_should_stop()) {
-		set_current_state(TASK_INTERRUPTIBLE);
 
 		if (test_and_clear_bit(IRQTF_RUNTHREAD,
 				       &action->thread_flags)) {
@@ -629,7 +630,9 @@ static int irq_wait_for_interrupt(struct irqaction *action)
 			return 0;
 		}
 		schedule();
+		set_current_state(TASK_INTERRUPTIBLE);
 	}
+	__set_current_state(TASK_RUNNING);
 	return -1;
 }
 
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index f76fc00c987..15e53b1766a 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -9,6 +9,7 @@
 #include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
+#include <linux/syscore_ops.h>
 
 #include "internals.h"
 
@@ -39,25 +40,58 @@ void suspend_device_irqs(void)
 }
 EXPORT_SYMBOL_GPL(suspend_device_irqs);
 
-/**
- * resume_device_irqs - enable interrupt lines disabled by suspend_device_irqs()
- *
- * Enable all interrupt lines previously disabled by suspend_device_irqs() that
- * have the IRQS_SUSPENDED flag set.
- */
-void resume_device_irqs(void)
+static void resume_irqs(bool want_early)
 {
 	struct irq_desc *desc;
 	int irq;
 
 	for_each_irq_desc(irq, desc) {
 		unsigned long flags;
+		bool is_early = desc->action &&
+			desc->action->flags & IRQF_EARLY_RESUME;
+
+		if (is_early != want_early)
+			continue;
 
 		raw_spin_lock_irqsave(&desc->lock, flags);
 		__enable_irq(desc, irq, true);
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
 	}
 }
+
+/**
+ * irq_pm_syscore_ops - enable interrupt lines early
+ *
+ * Enable all interrupt lines with %IRQF_EARLY_RESUME set.
+ */
+static void irq_pm_syscore_resume(void)
+{
+	resume_irqs(true);
+}
+
+static struct syscore_ops irq_pm_syscore_ops = {
+	.resume		= irq_pm_syscore_resume,
+};
+
+static int __init irq_pm_init_ops(void)
+{
+	register_syscore_ops(&irq_pm_syscore_ops);
+	return 0;
+}
+
+device_initcall(irq_pm_init_ops);
+
+/**
+ * resume_device_irqs - enable interrupt lines disabled by suspend_device_irqs()
+ *
+ * Enable all non-%IRQF_EARLY_RESUME interrupt lines previously
+ * disabled by suspend_device_irqs() that have the IRQS_SUSPENDED flag
+ * set as well as those with %IRQF_FORCE_RESUME.
+ */
+void resume_device_irqs(void)
+{
+	resume_irqs(false);
+}
 EXPORT_SYMBOL_GPL(resume_device_irqs);
 
 /**
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index aa57d5da18c..dc813a948be 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -84,7 +84,9 @@ static int try_one_irq(int irq, struct irq_desc *desc, bool force)
 	 */
 	action = desc->action;
 	if (!action || !(action->flags & IRQF_SHARED) ||
-	    (action->flags & __IRQF_TIMER) || !action->next)
+	    (action->flags & __IRQF_TIMER) ||
+	    (action->handler(irq, action->dev_id) == IRQ_HANDLED) ||
+	    !action->next)
 		goto out;
 
 	/* Already running on another processor */
@@ -115,7 +117,7 @@ static int misrouted_irq(int irq)
 	struct irq_desc *desc;
 	int i, ok = 0;
 
-	if (atomic_inc_return(&irq_poll_active) == 1)
+	if (atomic_inc_return(&irq_poll_active) != 1)
 		goto out;
 
 	irq_poll_cpu = smp_processor_id();
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index a8ce45097f3..e6f1f24ad57 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -66,8 +66,9 @@ void jump_label_inc(struct jump_label_key *key)
 		return;
 
 	jump_label_lock();
-	if (atomic_add_return(1, &key->enabled) == 1)
+	if (atomic_read(&key->enabled) == 0)
 		jump_label_update(key, JUMP_LABEL_ENABLE);
+	atomic_inc(&key->enabled);
 	jump_label_unlock();
 }
 
diff --git a/kernel/kmod.c b/kernel/kmod.c
index ddc7644c130..a4bea97c75b 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -114,10 +114,12 @@ int __request_module(bool wait, const char *fmt, ...)
 	atomic_inc(&kmod_concurrent);
 	if (atomic_read(&kmod_concurrent) > max_modprobes) {
 		/* We may be blaming an innocent here, but unlikely */
-		if (kmod_loop_msg++ < 5)
+		if (kmod_loop_msg < 5) {
 			printk(KERN_ERR
 			       "request_module: runaway loop modprobe %s\n",
 			       module_name);
+			kmod_loop_msg++;
+		}
 		atomic_dec(&kmod_concurrent);
 		return -ENOMEM;
 	}
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 3744c594b19..80a85971cf6 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -235,3 +235,7 @@ config PM_GENERIC_DOMAINS
 config PM_GENERIC_DOMAINS_RUNTIME
 	def_bool y
 	depends on PM_RUNTIME && PM_GENERIC_DOMAINS
+
+config CPU_PM
+	bool
+	depends on SUSPEND || CPU_IDLE
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index b6b71ad2208..d3caa763498 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -315,7 +315,7 @@ int enter_state(suspend_state_t state)
  */
 int pm_suspend(suspend_state_t state)
 {
-	if (state > PM_SUSPEND_ON && state <= PM_SUSPEND_MAX)
+	if (state > PM_SUSPEND_ON && state < PM_SUSPEND_MAX)
 		return enter_state(state);
 	return -EINVAL;
 }
diff --git a/kernel/sched.c b/kernel/sched.c
index b50b0f0c9aa..036311afeed 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -510,7 +510,7 @@ struct rq {
 
 	unsigned long cpu_power;
 
-	unsigned char idle_at_tick;
+	unsigned char idle_balance;
 	/* For active balancing */
 	int post_schedule;
 	int active_balance;
@@ -1272,6 +1272,18 @@ void wake_up_idle_cpu(int cpu)
 		smp_send_reschedule(cpu);
 }
 
+static inline bool got_nohz_idle_kick(void)
+{
+	return idle_cpu(smp_processor_id()) && this_rq()->nohz_balance_kick;
+}
+
+#else /* CONFIG_NO_HZ */
+
+static inline bool got_nohz_idle_kick(void)
+{
+	return false;
+}
+
 #endif /* CONFIG_NO_HZ */
 
 static u64 sched_avg_period(void)
@@ -2591,7 +2603,7 @@ void scheduler_ipi(void)
 	struct rq *rq = this_rq();
 	struct task_struct *list = xchg(&rq->wake_list, NULL);
 
-	if (!list)
+	if ((!list) && !got_nohz_idle_kick())
 		return;
 
 	/*
@@ -2609,6 +2621,14 @@ void scheduler_ipi(void)
 	 */
 	irq_enter();
 	sched_ttwu_do_pending(list);
+
+	/*
+	 * Check if someone kicked us for doing the nohz idle load balance.
+	 */
+	if (unlikely(got_nohz_idle_kick() && !need_resched())) {
+		this_rq()->idle_balance = 1;
+		raise_softirq_irqoff(SCHED_SOFTIRQ);
+	}
 	irq_exit();
 }
 
@@ -4116,7 +4136,7 @@ void scheduler_tick(void)
 	perf_event_task_tick();
 
 #ifdef CONFIG_SMP
-	rq->idle_at_tick = idle_cpu(cpu);
+	rq->idle_balance = idle_cpu(cpu);
 	trigger_load_balance(rq, cpu);
 #endif
 }
@@ -8133,7 +8153,6 @@ void __init sched_init(void)
 		rq_attach_root(rq, &def_root_domain);
 #ifdef CONFIG_NO_HZ
 		rq->nohz_balance_kick = 0;
-		init_sched_softirq_csd(&per_cpu(remote_sched_softirq_cb, i));
 #endif
 #endif
 		init_rq_hrtick(rq);
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index bc8ee999381..2107c3c3049 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -91,6 +91,8 @@ unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL;
 
 static const struct sched_class fair_sched_class;
 
+static unsigned long __read_mostly max_load_balance_interval = HZ/10;
+
 /**************************************************************
  * CFS operations on generic schedulable entities:
  */
@@ -2667,6 +2669,11 @@ static void update_group_power(struct sched_domain *sd, int cpu)
 	struct sched_domain *child = sd->child;
 	struct sched_group *group, *sdg = sd->groups;
 	unsigned long power;
+	unsigned long interval;
+
+	interval = msecs_to_jiffies(sd->balance_interval);
+	interval = clamp(interval, 1UL, max_load_balance_interval);
+	sdg->sgp->next_update = jiffies + interval;
 
 	if (!child) {
 		update_cpu_power(sd, cpu);
@@ -2774,12 +2781,15 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	 * domains. In the newly idle case, we will allow all the cpu's
 	 * to do the newly idle load balance.
 	 */
-	if (idle != CPU_NEWLY_IDLE && local_group) {
-		if (balance_cpu != this_cpu) {
-			*balance = 0;
-			return;
-		}
-		update_group_power(sd, this_cpu);
+	if (local_group) {
+		if (idle != CPU_NEWLY_IDLE) {
+			if (balance_cpu != this_cpu) {
+				*balance = 0;
+				return;
+			}
+			update_group_power(sd, this_cpu);
+		} else if (time_after_eq(jiffies, group->sgp->next_update))
+			update_group_power(sd, this_cpu);
 	}
 
 	/* Adjust by relative CPU power of the group */
@@ -3612,22 +3622,6 @@ out_unlock:
 }
 
 #ifdef CONFIG_NO_HZ
-
-static DEFINE_PER_CPU(struct call_single_data, remote_sched_softirq_cb);
-
-static void trigger_sched_softirq(void *data)
-{
-	raise_softirq_irqoff(SCHED_SOFTIRQ);
-}
-
-static inline void init_sched_softirq_csd(struct call_single_data *csd)
-{
-	csd->func = trigger_sched_softirq;
-	csd->info = NULL;
-	csd->flags = 0;
-	csd->priv = 0;
-}
-
 /*
  * idle load balancing details
  * - One of the idle CPUs nominates itself as idle load_balancer, while
@@ -3793,11 +3787,16 @@ static void nohz_balancer_kick(int cpu)
 	}
 
 	if (!cpu_rq(ilb_cpu)->nohz_balance_kick) {
-		struct call_single_data *cp;
-
 		cpu_rq(ilb_cpu)->nohz_balance_kick = 1;
-		cp = &per_cpu(remote_sched_softirq_cb, cpu);
-		__smp_call_function_single(ilb_cpu, cp, 0);
+
+		smp_mb();
+		/*
+		 * Use smp_send_reschedule() instead of resched_cpu().
+		 * This way we generate a sched IPI on the target cpu which
+		 * is idle. And the softirq performing nohz idle load balance
+		 * will be run before returning from the IPI.
+		 */
+		smp_send_reschedule(ilb_cpu);
 	}
 	return;
 }
@@ -3879,8 +3878,6 @@ void select_nohz_load_balancer(int stop_tick)
 
 static DEFINE_SPINLOCK(balancing);
 
-static unsigned long __read_mostly max_load_balance_interval = HZ/10;
-
 /*
  * Scale the max load_balance interval with the number of CPUs in the system.
  * This trades load-balance latency on larger machines for less cross talk.
@@ -4030,7 +4027,7 @@ static inline int nohz_kick_needed(struct rq *rq, int cpu)
 	if (time_before(now, nohz.next_balance))
 		return 0;
 
-	if (rq->idle_at_tick)
+	if (idle_cpu(cpu))
 		return 0;
 
 	first_pick_cpu = atomic_read(&nohz.first_pick_cpu);
@@ -4066,7 +4063,7 @@ static void run_rebalance_domains(struct softirq_action *h)
 {
 	int this_cpu = smp_processor_id();
 	struct rq *this_rq = cpu_rq(this_cpu);
-	enum cpu_idle_type idle = this_rq->idle_at_tick ?
+	enum cpu_idle_type idle = this_rq->idle_balance ?
 						CPU_IDLE : CPU_NOT_IDLE;
 
 	rebalance_domains(this_cpu, idle);
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index 2e74677cb04..85f8bd92a64 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -47,7 +47,7 @@ SCHED_FEAT(CACHE_HOT_BUDDY, 1)
 /*
  * Use arch dependent cpu power functions
  */
-SCHED_FEAT(ARCH_POWER, 0)
+SCHED_FEAT(ARCH_POWER, 1)
 
 SCHED_FEAT(HRTICK, 0)
 SCHED_FEAT(DOUBLE_TICK, 0)
diff --git a/kernel/time.c b/kernel/time.c
index 8e8dc6d705c..d7760621452 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -575,7 +575,7 @@ EXPORT_SYMBOL(jiffies_to_timeval);
 /*
  * Convert jiffies/jiffies_64 to clock_t and back.
  */
-clock_t jiffies_to_clock_t(long x)
+clock_t jiffies_to_clock_t(unsigned long x)
 {
 #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0
 # if HZ < USER_HZ
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index e4c699dfa4e..13dfaaba406 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -286,6 +286,7 @@ void clockevents_exchange_device(struct clock_event_device *old,
 	 * released list and do a notify add later.
 	 */
 	if (old) {
+		old->event_handler = clockevents_handle_noop;
 		clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED);
 		list_del(&old->list);
 		list_add(&old->list, &clockevents_released);
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index e0980f0d9a0..8f77da18fef 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -494,6 +494,22 @@ void clocksource_touch_watchdog(void)
 }
 
 /**
+ * clocksource_max_adjustment- Returns max adjustment amount
+ * @cs:         Pointer to clocksource
+ *
+ */
+static u32 clocksource_max_adjustment(struct clocksource *cs)
+{
+	u64 ret;
+	/*
+	 * We won't try to correct for more then 11% adjustments (110,000 ppm),
+	 */
+	ret = (u64)cs->mult * 11;
+	do_div(ret,100);
+	return (u32)ret;
+}
+
+/**
  * clocksource_max_deferment - Returns max time the clocksource can be deferred
  * @cs:         Pointer to clocksource
  *
@@ -505,25 +521,28 @@ static u64 clocksource_max_deferment(struct clocksource *cs)
 	/*
 	 * Calculate the maximum number of cycles that we can pass to the
 	 * cyc2ns function without overflowing a 64-bit signed result. The
-	 * maximum number of cycles is equal to ULLONG_MAX/cs->mult which
-	 * is equivalent to the below.
-	 * max_cycles < (2^63)/cs->mult
-	 * max_cycles < 2^(log2((2^63)/cs->mult))
-	 * max_cycles < 2^(log2(2^63) - log2(cs->mult))
-	 * max_cycles < 2^(63 - log2(cs->mult))
-	 * max_cycles < 1 << (63 - log2(cs->mult))
+	 * maximum number of cycles is equal to ULLONG_MAX/(cs->mult+cs->maxadj)
+	 * which is equivalent to the below.
+	 * max_cycles < (2^63)/(cs->mult + cs->maxadj)
+	 * max_cycles < 2^(log2((2^63)/(cs->mult + cs->maxadj)))
+	 * max_cycles < 2^(log2(2^63) - log2(cs->mult + cs->maxadj))
+	 * max_cycles < 2^(63 - log2(cs->mult + cs->maxadj))
+	 * max_cycles < 1 << (63 - log2(cs->mult + cs->maxadj))
 	 * Please note that we add 1 to the result of the log2 to account for
 	 * any rounding errors, ensure the above inequality is satisfied and
 	 * no overflow will occur.
 	 */
-	max_cycles = 1ULL << (63 - (ilog2(cs->mult) + 1));
+	max_cycles = 1ULL << (63 - (ilog2(cs->mult + cs->maxadj) + 1));
 
 	/*
 	 * The actual maximum number of cycles we can defer the clocksource is
 	 * determined by the minimum of max_cycles and cs->mask.
+	 * Note: Here we subtract the maxadj to make sure we don't sleep for
+	 * too long if there's a large negative adjustment.
 	 */
 	max_cycles = min_t(u64, max_cycles, (u64) cs->mask);
-	max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult, cs->shift);
+	max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult - cs->maxadj,
+					cs->shift);
 
 	/*
 	 * To ensure that the clocksource does not wrap whilst we are idle,
@@ -531,7 +550,7 @@ static u64 clocksource_max_deferment(struct clocksource *cs)
 	 * note a margin of 12.5% is used because this can be computed with
 	 * a shift, versus say 10% which would require division.
 	 */
-	return max_nsecs - (max_nsecs >> 5);
+	return max_nsecs - (max_nsecs >> 3);
 }
 
 #ifndef CONFIG_ARCH_USES_GETTIMEOFFSET
@@ -642,7 +661,6 @@ static void clocksource_enqueue(struct clocksource *cs)
 void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
 {
 	u64 sec;
-
 	/*
 	 * Calc the maximum number of seconds which we can run before
 	 * wrapping around. For clocksources which have a mask > 32bit
@@ -653,7 +671,7 @@ void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
 	 * ~ 0.06ppm granularity for NTP. We apply the same 12.5%
 	 * margin as we do in clocksource_max_deferment()
 	 */
-	sec = (cs->mask - (cs->mask >> 5));
+	sec = (cs->mask - (cs->mask >> 3));
 	do_div(sec, freq);
 	do_div(sec, scale);
 	if (!sec)
@@ -663,6 +681,20 @@ void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
 
 	clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
 			       NSEC_PER_SEC / scale, sec * scale);
+
+	/*
+	 * for clocksources that have large mults, to avoid overflow.
+	 * Since mult may be adjusted by ntp, add an safety extra margin
+	 *
+	 */
+	cs->maxadj = clocksource_max_adjustment(cs);
+	while ((cs->mult + cs->maxadj < cs->mult)
+		|| (cs->mult - cs->maxadj > cs->mult)) {
+		cs->mult >>= 1;
+		cs->shift--;
+		cs->maxadj = clocksource_max_adjustment(cs);
+	}
+
 	cs->max_idle_ns = clocksource_max_deferment(cs);
 }
 EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale);
@@ -703,6 +735,12 @@ EXPORT_SYMBOL_GPL(__clocksource_register_scale);
  */
 int clocksource_register(struct clocksource *cs)
 {
+	/* calculate max adjustment for given mult/shift */
+	cs->maxadj = clocksource_max_adjustment(cs);
+	WARN_ONCE(cs->mult + cs->maxadj < cs->mult,
+		"Clocksource %s might overflow on 11%% adjustment\n",
+		cs->name);
+
 	/* calculate max idle time permitted for this clocksource */
 	cs->max_idle_ns = clocksource_max_deferment(cs);
 
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index c7218d13273..7a90d021b79 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -71,7 +71,7 @@ int tick_check_broadcast_device(struct clock_event_device *dev)
 	     (dev->features & CLOCK_EVT_FEAT_C3STOP))
 		return 0;
 
-	clockevents_exchange_device(NULL, dev);
+	clockevents_exchange_device(tick_broadcast_device.evtdev, dev);
 	tick_broadcast_device.evtdev = dev;
 	if (!cpumask_empty(tick_get_broadcast_mask()))
 		tick_broadcast_start_periodic(dev);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 2b021b0e850..6f9798bf240 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -249,6 +249,8 @@ ktime_t ktime_get(void)
 		secs = xtime.tv_sec + wall_to_monotonic.tv_sec;
 		nsecs = xtime.tv_nsec + wall_to_monotonic.tv_nsec;
 		nsecs += timekeeping_get_ns();
+		/* If arch requires, add in gettimeoffset() */
+		nsecs += arch_gettimeoffset();
 
 	} while (read_seqretry(&xtime_lock, seq));
 	/*
@@ -280,6 +282,8 @@ void ktime_get_ts(struct timespec *ts)
 		*ts = xtime;
 		tomono = wall_to_monotonic;
 		nsecs = timekeeping_get_ns();
+		/* If arch requires, add in gettimeoffset() */
+		nsecs += arch_gettimeoffset();
 
 	} while (read_seqretry(&xtime_lock, seq));
 
@@ -820,6 +824,13 @@ static void timekeeping_adjust(s64 offset)
 	} else
 		return;
 
+	WARN_ONCE(timekeeper.clock->maxadj &&
+			(timekeeper.mult + adj > timekeeper.clock->mult +
+						timekeeper.clock->maxadj),
+			"Adjusting %s more then 11%% (%ld vs %ld)\n",
+			timekeeper.clock->name, (long)timekeeper.mult + adj,
+			(long)timekeeper.clock->mult +
+				timekeeper.clock->maxadj);
 	timekeeper.mult += adj;
 	timekeeper.xtime_interval += interval;
 	timekeeper.xtime_nsec -= offset;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index c3e4575e782..48d3762b828 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -151,7 +151,6 @@ void clear_ftrace_function(void)
 	ftrace_pid_function = ftrace_stub;
 }
 
-#undef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 #ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 /*
  * For those archs that do not test ftrace_trace_stop in their
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index e7aa00caa38..3c9b9686be2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3817,8 +3817,6 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 	if (info->read < PAGE_SIZE)
 		goto read;
 
-	info->read = 0;
-
 	trace_access_lock(info->cpu);
 	ret = ring_buffer_read_page(info->tr->buffer,
 				    &info->spare,
@@ -3828,6 +3826,8 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 	if (ret < 0)
 		return 0;
 
+	info->read = 0;
+
 read:
 	size = PAGE_SIZE - info->read;
 	if (size > count)
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index b066c6dd41a..773cb84adc8 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1079,7 +1079,6 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
 	/* First see if we did not already create this dir */
 	list_for_each_entry(system, &event_subsystems, list) {
 		if (strcmp(system->name, name) == 0) {
-			__get_system(system);
 			system->nr_events++;
 			return system->entry;
 		}
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 256764ecccd..bd3c6369f80 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1766,7 +1766,7 @@ static int replace_system_preds(struct event_subsystem *system,
 		 * replace the filter for the call.
 		 */
 		filter = call->filter;
-		call->filter = filter_item->filter;
+		rcu_assign_pointer(call->filter, filter_item->filter);
 		filter_item->filter = filter;
 
 		fail = false;
@@ -1821,7 +1821,7 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
 		filter = call->filter;
 		if (!filter)
 			goto out_unlock;
-		call->filter = NULL;
+		RCU_INIT_POINTER(call->filter, NULL);
 		/* Make sure the filter is not being used */
 		synchronize_sched();
 		__free_filter(filter);
@@ -1862,7 +1862,7 @@ out:
 	 * string
 	 */
 	tmp = call->filter;
-	call->filter = filter;
+	rcu_assign_pointer(call->filter, filter);
 	if (tmp) {
 		/* Make sure the call is done with the filter */
 		synchronize_sched();
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 5fb3697bf0e..00d527c945a 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -836,11 +836,17 @@ static void __unregister_trace_probe(struct trace_probe *tp)
 }
 
 /* Unregister a trace_probe and probe_event: call with locking probe_lock */
-static void unregister_trace_probe(struct trace_probe *tp)
+static int unregister_trace_probe(struct trace_probe *tp)
 {
+	/* Enabled event can not be unregistered */
+	if (trace_probe_is_enabled(tp))
+		return -EBUSY;
+
 	__unregister_trace_probe(tp);
 	list_del(&tp->list);
 	unregister_probe_event(tp);
+
+	return 0;
 }
 
 /* Register a trace_probe and probe_event */
@@ -854,7 +860,9 @@ static int register_trace_probe(struct trace_probe *tp)
 	/* Delete old (same name) event if exist */
 	old_tp = find_trace_probe(tp->call.name, tp->call.class->system);
 	if (old_tp) {
-		unregister_trace_probe(old_tp);
+		ret = unregister_trace_probe(old_tp);
+		if (ret < 0)
+			goto end;
 		free_trace_probe(old_tp);
 	}
 
@@ -892,6 +900,7 @@ static int trace_probe_module_callback(struct notifier_block *nb,
 	mutex_lock(&probe_lock);
 	list_for_each_entry(tp, &probe_list, list) {
 		if (trace_probe_within_module(tp, mod)) {
+			/* Don't need to check busy - this should have gone. */
 			__unregister_trace_probe(tp);
 			ret = __register_trace_probe(tp);
 			if (ret)
@@ -1205,10 +1214,11 @@ static int create_trace_probe(int argc, char **argv)
 			return -ENOENT;
 		}
 		/* delete an event */
-		unregister_trace_probe(tp);
-		free_trace_probe(tp);
+		ret = unregister_trace_probe(tp);
+		if (ret == 0)
+			free_trace_probe(tp);
 		mutex_unlock(&probe_lock);
-		return 0;
+		return ret;
 	}
 
 	if (argc < 2) {
@@ -1317,18 +1327,29 @@ error:
 	return ret;
 }
 
-static void release_all_trace_probes(void)
+static int release_all_trace_probes(void)
 {
 	struct trace_probe *tp;
+	int ret = 0;
 
 	mutex_lock(&probe_lock);
+	/* Ensure no probe is in use. */
+	list_for_each_entry(tp, &probe_list, list)
+		if (trace_probe_is_enabled(tp)) {
+			ret = -EBUSY;
+			goto end;
+		}
 	/* TODO: Use batch unregistration */
 	while (!list_empty(&probe_list)) {
 		tp = list_entry(probe_list.next, struct trace_probe, list);
 		unregister_trace_probe(tp);
 		free_trace_probe(tp);
 	}
+
+end:
 	mutex_unlock(&probe_lock);
+
+	return ret;
 }
 
 /* Probes listing interfaces */
@@ -1380,9 +1401,13 @@ static const struct seq_operations probes_seq_op = {
 
 static int probes_open(struct inode *inode, struct file *file)
 {
-	if ((file->f_mode & FMODE_WRITE) &&
-	    (file->f_flags & O_TRUNC))
-		release_all_trace_probes();
+	int ret;
+
+	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
+		ret = release_all_trace_probes();
+		if (ret < 0)
+			return ret;
+	}
 
 	return seq_open(file, &probes_seq_op);
 }
@@ -2055,6 +2080,21 @@ static __init int kprobe_trace_self_tests_init(void)
 
 	ret = target(1, 2, 3, 4, 5, 6);
 
+	/* Disable trace points before removing it */
+	tp = find_trace_probe("testprobe", KPROBE_EVENT_SYSTEM);
+	if (WARN_ON_ONCE(tp == NULL)) {
+		pr_warning("error on getting test probe.\n");
+		warn++;
+	} else
+		disable_trace_probe(tp, TP_FLAG_TRACE);
+
+	tp = find_trace_probe("testprobe2", KPROBE_EVENT_SYSTEM);
+	if (WARN_ON_ONCE(tp == NULL)) {
+		pr_warning("error on getting 2nd test probe.\n");
+		warn++;
+	} else
+		disable_trace_probe(tp, TP_FLAG_TRACE);
+
 	ret = command_trace_probe("-:testprobe");
 	if (WARN_ON_ONCE(ret)) {
 		pr_warning("error on deleting a probe.\n");