Merge branch 'perf/urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

20 files changed, 337 insertions, 233 deletions

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 1ceeb049c82..9c9b7545c81 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2190,7 +2190,7 @@ int cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 	rcu_read_lock();
 	cs = task_cs(tsk);
 	if (cs)
-		cpumask_copy(&tsk->cpus_allowed, cs->cpus_allowed);
+		do_set_cpus_allowed(tsk, cs->cpus_allowed);
 	rcu_read_unlock();
 
 	/*
@@ -2217,7 +2217,7 @@ int cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 		 * Like above we can temporary set any mask and rely on
 		 * set_cpus_allowed_ptr() as synchronization point.
 		 */
-		cpumask_copy(&tsk->cpus_allowed, cpu_possible_mask);
+		do_set_cpus_allowed(tsk, cpu_possible_mask);
 		cpu = cpumask_any(cpu_active_mask);
 	}
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 8a15944bf9d..9efe7108cca 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5028,6 +5028,14 @@ static int __perf_event_overflow(struct perf_event *event, int nmi,
 	else
 		perf_event_output(event, nmi, data, regs);
 
+	if (event->fasync && event->pending_kill) {
+		if (nmi) {
+			event->pending_wakeup = 1;
+			irq_work_queue(&event->pending);
+		} else
+			perf_event_wakeup(event);
+	}
+
 	return ret;
 }
 
diff --git a/kernel/fork.c b/kernel/fork.c
index ca406d91671..0276c30401a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -484,20 +484,6 @@ static void mm_init_aio(struct mm_struct *mm)
 #endif
 }
 
-int mm_init_cpumask(struct mm_struct *mm, struct mm_struct *oldmm)
-{
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	if (!alloc_cpumask_var(&mm->cpu_vm_mask_var, GFP_KERNEL))
-		return -ENOMEM;
-
-	if (oldmm)
-		cpumask_copy(mm_cpumask(mm), mm_cpumask(oldmm));
-	else
-		memset(mm_cpumask(mm), 0, cpumask_size());
-#endif
-	return 0;
-}
-
 static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
 {
 	atomic_set(&mm->mm_users, 1);
@@ -538,17 +524,8 @@ struct mm_struct * mm_alloc(void)
 		return NULL;
 
 	memset(mm, 0, sizeof(*mm));
-	mm = mm_init(mm, current);
-	if (!mm)
-		return NULL;
-
-	if (mm_init_cpumask(mm, NULL)) {
-		mm_free_pgd(mm);
-		free_mm(mm);
-		return NULL;
-	}
-
-	return mm;
+	mm_init_cpumask(mm);
+	return mm_init(mm, current);
 }
 
 /*
@@ -559,7 +536,6 @@ struct mm_struct * mm_alloc(void)
 void __mmdrop(struct mm_struct *mm)
 {
 	BUG_ON(mm == &init_mm);
-	free_cpumask_var(mm->cpu_vm_mask_var);
 	mm_free_pgd(mm);
 	destroy_context(mm);
 	mmu_notifier_mm_destroy(mm);
@@ -753,6 +729,7 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
 		goto fail_nomem;
 
 	memcpy(mm, oldmm, sizeof(*mm));
+	mm_init_cpumask(mm);
 
 	/* Initializing for Swap token stuff */
 	mm->token_priority = 0;
@@ -765,9 +742,6 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
 	if (!mm_init(mm, tsk))
 		goto fail_nomem;
 
-	if (mm_init_cpumask(mm, oldmm))
-		goto fail_nocpumask;
-
 	if (init_new_context(tsk, mm))
 		goto fail_nocontext;
 
@@ -794,9 +768,6 @@ fail_nomem:
 	return NULL;
 
 fail_nocontext:
-	free_cpumask_var(mm->cpu_vm_mask_var);
-
-fail_nocpumask:
 	/*
 	 * If init_new_context() failed, we cannot use mmput() to free the mm
 	 * because it calls destroy_context()
@@ -1591,6 +1562,13 @@ void __init proc_caches_init(void)
 	fs_cachep = kmem_cache_create("fs_cache",
 			sizeof(struct fs_struct), 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
+	/*
+	 * FIXME! The "sizeof(struct mm_struct)" currently includes the
+	 * whole struct cpumask for the OFFSTACK case. We could change
+	 * this to *only* allocate as much of it as required by the
+	 * maximum number of CPU's we can ever have.  The cpumask_allocation
+	 * is at the end of the structure, exactly for that reason.
+	 */
 	mm_cachep = kmem_cache_create("mm_struct",
 			sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 74d1c099fbd..fa27e750dbc 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -105,9 +105,12 @@ static int __jump_label_text_reserved(struct jump_entry *iter_start,
 }
 
 static void __jump_label_update(struct jump_label_key *key,
-		struct jump_entry *entry, int enable)
+				struct jump_entry *entry,
+				struct jump_entry *stop, int enable)
 {
-	for (; entry->key == (jump_label_t)(unsigned long)key; entry++) {
+	for (; (entry < stop) &&
+	      (entry->key == (jump_label_t)(unsigned long)key);
+	      entry++) {
 		/*
 		 * entry->code set to 0 invalidates module init text sections
 		 * kernel_text_address() verifies we are not in core kernel
@@ -181,7 +184,11 @@ static void __jump_label_mod_update(struct jump_label_key *key, int enable)
 	struct jump_label_mod *mod = key->next;
 
 	while (mod) {
-		__jump_label_update(key, mod->entries, enable);
+		struct module *m = mod->mod;
+
+		__jump_label_update(key, mod->entries,
+				    m->jump_entries + m->num_jump_entries,
+				    enable);
 		mod = mod->next;
 	}
 }
@@ -245,7 +252,8 @@ static int jump_label_add_module(struct module *mod)
 		key->next = jlm;
 
 		if (jump_label_enabled(key))
-			__jump_label_update(key, iter, JUMP_LABEL_ENABLE);
+			__jump_label_update(key, iter, iter_stop,
+					    JUMP_LABEL_ENABLE);
 	}
 
 	return 0;
@@ -371,7 +379,7 @@ static void jump_label_update(struct jump_label_key *key, int enable)
 
 	/* if there are no users, entry can be NULL */
 	if (entry)
-		__jump_label_update(key, entry, enable);
+		__jump_label_update(key, entry, __stop___jump_table, enable);
 
 #ifdef CONFIG_MODULES
 	__jump_label_mod_update(key, enable);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 3b34d2732bc..4ba7cccb499 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -202,8 +202,8 @@ void kthread_bind(struct task_struct *p, unsigned int cpu)
 		return;
 	}
 
-	p->cpus_allowed = cpumask_of_cpu(cpu);
-	p->rt.nr_cpus_allowed = 1;
+	/* It's safe because the task is inactive. */
+	do_set_cpus_allowed(p, cpumask_of(cpu));
 	p->flags |= PF_THREAD_BOUND;
 }
 EXPORT_SYMBOL(kthread_bind);
diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index fd8d1e035df..6824ca7d4d0 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -54,11 +54,17 @@ enum pm_qos_type {
 	PM_QOS_MIN		/* return the smallest value */
 };
 
+/*
+ * Note: The lockless read path depends on the CPU accessing
+ * target_value atomically.  Atomic access is only guaranteed on all CPU
+ * types linux supports for 32 bit quantites
+ */
 struct pm_qos_object {
 	struct plist_head requests;
 	struct blocking_notifier_head *notifiers;
 	struct miscdevice pm_qos_power_miscdev;
 	char *name;
+	s32 target_value;	/* Do not change to 64 bit */
 	s32 default_value;
 	enum pm_qos_type type;
 };
@@ -71,7 +77,8 @@ static struct pm_qos_object cpu_dma_pm_qos = {
 	.requests = PLIST_HEAD_INIT(cpu_dma_pm_qos.requests, pm_qos_lock),
 	.notifiers = &cpu_dma_lat_notifier,
 	.name = "cpu_dma_latency",
-	.default_value = 2000 * USEC_PER_SEC,
+	.target_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
+	.default_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
 	.type = PM_QOS_MIN,
 };
 
@@ -80,7 +87,8 @@ static struct pm_qos_object network_lat_pm_qos = {
 	.requests = PLIST_HEAD_INIT(network_lat_pm_qos.requests, pm_qos_lock),
 	.notifiers = &network_lat_notifier,
 	.name = "network_latency",
-	.default_value = 2000 * USEC_PER_SEC,
+	.target_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
+	.default_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
 	.type = PM_QOS_MIN
 };
 
@@ -90,7 +98,8 @@ static struct pm_qos_object network_throughput_pm_qos = {
 	.requests = PLIST_HEAD_INIT(network_throughput_pm_qos.requests, pm_qos_lock),
 	.notifiers = &network_throughput_notifier,
 	.name = "network_throughput",
-	.default_value = 0,
+	.target_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
+	.default_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
 	.type = PM_QOS_MAX,
 };
 
@@ -136,6 +145,16 @@ static inline int pm_qos_get_value(struct pm_qos_object *o)
 	}
 }
 
+static inline s32 pm_qos_read_value(struct pm_qos_object *o)
+{
+	return o->target_value;
+}
+
+static inline void pm_qos_set_value(struct pm_qos_object *o, s32 value)
+{
+	o->target_value = value;
+}
+
 static void update_target(struct pm_qos_object *o, struct plist_node *node,
 			  int del, int value)
 {
@@ -160,6 +179,7 @@ static void update_target(struct pm_qos_object *o, struct plist_node *node,
 		plist_add(node, &o->requests);
 	}
 	curr_value = pm_qos_get_value(o);
+	pm_qos_set_value(o, curr_value);
 	spin_unlock_irqrestore(&pm_qos_lock, flags);
 
 	if (prev_value != curr_value)
@@ -194,18 +214,11 @@ static int find_pm_qos_object_by_minor(int minor)
  * pm_qos_request - returns current system wide qos expectation
  * @pm_qos_class: identification of which qos value is requested
  *
- * This function returns the current target value in an atomic manner.
+ * This function returns the current target value.
  */
 int pm_qos_request(int pm_qos_class)
 {
-	unsigned long flags;
-	int value;
-
-	spin_lock_irqsave(&pm_qos_lock, flags);
-	value = pm_qos_get_value(pm_qos_array[pm_qos_class]);
-	spin_unlock_irqrestore(&pm_qos_lock, flags);
-
-	return value;
+	return pm_qos_read_value(pm_qos_array[pm_qos_class]);
 }
 EXPORT_SYMBOL_GPL(pm_qos_request);
 
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index f07d2f03181..89419ff92e9 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -36,7 +36,7 @@
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <linux/nmi.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/completion.h>
@@ -95,7 +95,6 @@ static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);
 DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
 DEFINE_PER_CPU(int, rcu_cpu_kthread_cpu);
 DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
-static DEFINE_PER_CPU(wait_queue_head_t, rcu_cpu_wq);
 DEFINE_PER_CPU(char, rcu_cpu_has_work);
 static char rcu_kthreads_spawnable;
 
@@ -163,7 +162,7 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 #ifdef CONFIG_NO_HZ
 DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 	.dynticks_nesting = 1,
-	.dynticks = 1,
+	.dynticks = ATOMIC_INIT(1),
 };
 #endif /* #ifdef CONFIG_NO_HZ */
 
@@ -322,13 +321,25 @@ void rcu_enter_nohz(void)
 	unsigned long flags;
 	struct rcu_dynticks *rdtp;
 
-	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
 	local_irq_save(flags);
 	rdtp = &__get_cpu_var(rcu_dynticks);
-	rdtp->dynticks++;
-	rdtp->dynticks_nesting--;
-	WARN_ON_ONCE(rdtp->dynticks & 0x1);
+	if (--rdtp->dynticks_nesting) {
+		local_irq_restore(flags);
+		return;
+	}
+	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
+	smp_mb__before_atomic_inc();  /* See above. */
+	atomic_inc(&rdtp->dynticks);
+	smp_mb__after_atomic_inc();  /* Force ordering with next sojourn. */
+	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
 	local_irq_restore(flags);
+
+	/* If the interrupt queued a callback, get out of dyntick mode. */
+	if (in_irq() &&
+	    (__get_cpu_var(rcu_sched_data).nxtlist ||
+	     __get_cpu_var(rcu_bh_data).nxtlist ||
+	     rcu_preempt_needs_cpu(smp_processor_id())))
+		set_need_resched();
 }
 
 /*
@@ -344,11 +355,16 @@ void rcu_exit_nohz(void)
 
 	local_irq_save(flags);
 	rdtp = &__get_cpu_var(rcu_dynticks);
-	rdtp->dynticks++;
-	rdtp->dynticks_nesting++;
-	WARN_ON_ONCE(!(rdtp->dynticks & 0x1));
+	if (rdtp->dynticks_nesting++) {
+		local_irq_restore(flags);
+		return;
+	}
+	smp_mb__before_atomic_inc();  /* Force ordering w/previous sojourn. */
+	atomic_inc(&rdtp->dynticks);
+	/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
+	smp_mb__after_atomic_inc();  /* See above. */
+	WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
 	local_irq_restore(flags);
-	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
 }
 
 /**
@@ -362,11 +378,15 @@ void rcu_nmi_enter(void)
 {
 	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
 
-	if (rdtp->dynticks & 0x1)
+	if (rdtp->dynticks_nmi_nesting == 0 &&
+	    (atomic_read(&rdtp->dynticks) & 0x1))
 		return;
-	rdtp->dynticks_nmi++;
-	WARN_ON_ONCE(!(rdtp->dynticks_nmi & 0x1));
-	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
+	rdtp->dynticks_nmi_nesting++;
+	smp_mb__before_atomic_inc();  /* Force delay from prior write. */
+	atomic_inc(&rdtp->dynticks);
+	/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
+	smp_mb__after_atomic_inc();  /* See above. */
+	WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
 }
 
 /**
@@ -380,11 +400,14 @@ void rcu_nmi_exit(void)
 {
 	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
 
-	if (rdtp->dynticks & 0x1)
+	if (rdtp->dynticks_nmi_nesting == 0 ||
+	    --rdtp->dynticks_nmi_nesting != 0)
 		return;
-	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
-	rdtp->dynticks_nmi++;
-	WARN_ON_ONCE(rdtp->dynticks_nmi & 0x1);
+	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
+	smp_mb__before_atomic_inc();  /* See above. */
+	atomic_inc(&rdtp->dynticks);
+	smp_mb__after_atomic_inc();  /* Force delay to next write. */
+	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
 }
 
 /**
@@ -395,13 +418,7 @@ void rcu_nmi_exit(void)
  */
 void rcu_irq_enter(void)
 {
-	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
-
-	if (rdtp->dynticks_nesting++)
-		return;
-	rdtp->dynticks++;
-	WARN_ON_ONCE(!(rdtp->dynticks & 0x1));
-	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
+	rcu_exit_nohz();
 }
 
 /**
@@ -413,18 +430,7 @@ void rcu_irq_enter(void)
  */
 void rcu_irq_exit(void)
 {
-	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
-
-	if (--rdtp->dynticks_nesting)
-		return;
-	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
-	rdtp->dynticks++;
-	WARN_ON_ONCE(rdtp->dynticks & 0x1);
-
-	/* If the interrupt queued a callback, get out of dyntick mode. */
-	if (__this_cpu_read(rcu_sched_data.nxtlist) ||
-	    __this_cpu_read(rcu_bh_data.nxtlist))
-		set_need_resched();
+	rcu_enter_nohz();
 }
 
 #ifdef CONFIG_SMP
@@ -436,19 +442,8 @@ void rcu_irq_exit(void)
  */
 static int dyntick_save_progress_counter(struct rcu_data *rdp)
 {
-	int ret;
-	int snap;
-	int snap_nmi;
-
-	snap = rdp->dynticks->dynticks;
-	snap_nmi = rdp->dynticks->dynticks_nmi;
-	smp_mb();	/* Order sampling of snap with end of grace period. */
-	rdp->dynticks_snap = snap;
-	rdp->dynticks_nmi_snap = snap_nmi;
-	ret = ((snap & 0x1) == 0) && ((snap_nmi & 0x1) == 0);
-	if (ret)
-		rdp->dynticks_fqs++;
-	return ret;
+	rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks);
+	return 0;
 }
 
 /*
@@ -459,16 +454,11 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp)
  */
 static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 {
-	long curr;
-	long curr_nmi;
-	long snap;
-	long snap_nmi;
+	unsigned long curr;
+	unsigned long snap;
 
-	curr = rdp->dynticks->dynticks;
-	snap = rdp->dynticks_snap;
-	curr_nmi = rdp->dynticks->dynticks_nmi;
-	snap_nmi = rdp->dynticks_nmi_snap;
-	smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
+	curr = (unsigned long)atomic_add_return(0, &rdp->dynticks->dynticks);
+	snap = (unsigned long)rdp->dynticks_snap;
 
 	/*
 	 * If the CPU passed through or entered a dynticks idle phase with
@@ -478,8 +468,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	 * read-side critical section that started before the beginning
 	 * of the current RCU grace period.
 	 */
-	if ((curr != snap || (curr & 0x1) == 0) &&
-	    (curr_nmi != snap_nmi || (curr_nmi & 0x1) == 0)) {
+	if ((curr & 0x1) == 0 || ULONG_CMP_GE(curr, snap + 2)) {
 		rdp->dynticks_fqs++;
 		return 1;
 	}
@@ -908,6 +897,12 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
 	unsigned long gp_duration;
 
 	WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
+
+	/*
+	 * Ensure that all grace-period and pre-grace-period activity
+	 * is seen before the assignment to rsp->completed.
+	 */
+	smp_mb(); /* See above block comment. */
 	gp_duration = jiffies - rsp->gp_start;
 	if (gp_duration > rsp->gp_max)
 		rsp->gp_max = gp_duration;
@@ -1455,25 +1450,11 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
  */
 static void rcu_process_callbacks(void)
 {
-	/*
-	 * Memory references from any prior RCU read-side critical sections
-	 * executed by the interrupted code must be seen before any RCU
-	 * grace-period manipulations below.
-	 */
-	smp_mb(); /* See above block comment. */
-
 	__rcu_process_callbacks(&rcu_sched_state,
 				&__get_cpu_var(rcu_sched_data));
 	__rcu_process_callbacks(&rcu_bh_state, &__get_cpu_var(rcu_bh_data));
 	rcu_preempt_process_callbacks();
 
-	/*
-	 * Memory references from any later RCU read-side critical sections
-	 * executed by the interrupted code must be seen after any RCU
-	 * grace-period manipulations above.
-	 */
-	smp_mb(); /* See above block comment. */
-
 	/* If we are last CPU on way to dyntick-idle mode, accelerate it. */
 	rcu_needs_cpu_flush();
 }
@@ -1494,7 +1475,7 @@ static void invoke_rcu_cpu_kthread(void)
 		local_irq_restore(flags);
 		return;
 	}
-	wake_up(&__get_cpu_var(rcu_cpu_wq));
+	wake_up_process(__this_cpu_read(rcu_cpu_kthread_task));
 	local_irq_restore(flags);
 }
 
@@ -1544,13 +1525,10 @@ static void rcu_cpu_kthread_setrt(int cpu, int to_rt)
  */
 static void rcu_cpu_kthread_timer(unsigned long arg)
 {
-	unsigned long flags;
 	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, arg);
 	struct rcu_node *rnp = rdp->mynode;
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	rnp->wakemask |= rdp->grpmask;
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	atomic_or(rdp->grpmask, &rnp->wakemask);
 	invoke_rcu_node_kthread(rnp);
 }
 
@@ -1617,14 +1595,12 @@ static int rcu_cpu_kthread(void *arg)
 	unsigned long flags;
 	int spincnt = 0;
 	unsigned int *statusp = &per_cpu(rcu_cpu_kthread_status, cpu);
-	wait_queue_head_t *wqp = &per_cpu(rcu_cpu_wq, cpu);
 	char work;
 	char *workp = &per_cpu(rcu_cpu_has_work, cpu);
 
 	for (;;) {
 		*statusp = RCU_KTHREAD_WAITING;
-		wait_event_interruptible(*wqp,
-					 *workp != 0 || kthread_should_stop());
+		rcu_wait(*workp != 0 || kthread_should_stop());
 		local_bh_disable();
 		if (rcu_cpu_kthread_should_stop(cpu)) {
 			local_bh_enable();
@@ -1675,7 +1651,6 @@ static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu)
 	per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
 	WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL);
 	per_cpu(rcu_cpu_kthread_task, cpu) = t;
-	wake_up_process(t);
 	sp.sched_priority = RCU_KTHREAD_PRIO;
 	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
 	return 0;
@@ -1698,11 +1673,10 @@ static int rcu_node_kthread(void *arg)
 
 	for (;;) {
 		rnp->node_kthread_status = RCU_KTHREAD_WAITING;
-		wait_event_interruptible(rnp->node_wq, rnp->wakemask != 0);
+		rcu_wait(atomic_read(&rnp->wakemask) != 0);
 		rnp->node_kthread_status = RCU_KTHREAD_RUNNING;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
-		mask = rnp->wakemask;
-		rnp->wakemask = 0;
+		mask = atomic_xchg(&rnp->wakemask, 0);
 		rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */
 		for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) {
 			if ((mask & 0x1) == 0)
@@ -1783,13 +1757,14 @@ static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp,
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		rnp->node_kthread_task = t;
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
-		wake_up_process(t);
 		sp.sched_priority = 99;
 		sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
 	}
 	return rcu_spawn_one_boost_kthread(rsp, rnp, rnp_index);
 }
 
+static void rcu_wake_one_boost_kthread(struct rcu_node *rnp);
+
 /*
  * Spawn all kthreads -- called as soon as the scheduler is running.
  */
@@ -1797,24 +1772,31 @@ static int __init rcu_spawn_kthreads(void)
 {
 	int cpu;
 	struct rcu_node *rnp;
+	struct task_struct *t;
 
 	rcu_kthreads_spawnable = 1;
 	for_each_possible_cpu(cpu) {
-		init_waitqueue_head(&per_cpu(rcu_cpu_wq, cpu));
 		per_cpu(rcu_cpu_has_work, cpu) = 0;
-		if (cpu_online(cpu))
+		if (cpu_online(cpu)) {
 			(void)rcu_spawn_one_cpu_kthread(cpu);
+			t = per_cpu(rcu_cpu_kthread_task, cpu);
+			if (t)
+				wake_up_process(t);
+		}
 	}
 	rnp = rcu_get_root(rcu_state);
-	init_waitqueue_head(&rnp->node_wq);
-	rcu_init_boost_waitqueue(rnp);
 	(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
-	if (NUM_RCU_NODES > 1)
+	if (rnp->node_kthread_task)
+		wake_up_process(rnp->node_kthread_task);
+	if (NUM_RCU_NODES > 1) {
 		rcu_for_each_leaf_node(rcu_state, rnp) {
-			init_waitqueue_head(&rnp->node_wq);
-			rcu_init_boost_waitqueue(rnp);
 			(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
+			t = rnp->node_kthread_task;
+			if (t)
+				wake_up_process(t);
+			rcu_wake_one_boost_kthread(rnp);
 		}
+	}
 	return 0;
 }
 early_initcall(rcu_spawn_kthreads);
@@ -2218,14 +2200,14 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible)
 	raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
 }
 
-static void __cpuinit rcu_online_cpu(int cpu)
+static void __cpuinit rcu_prepare_cpu(int cpu)
 {
 	rcu_init_percpu_data(cpu, &rcu_sched_state, 0);
 	rcu_init_percpu_data(cpu, &rcu_bh_state, 0);
 	rcu_preempt_init_percpu_data(cpu);
 }
 
-static void __cpuinit rcu_online_kthreads(int cpu)
+static void __cpuinit rcu_prepare_kthreads(int cpu)
 {
 	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
 	struct rcu_node *rnp = rdp->mynode;
@@ -2239,6 +2221,31 @@ static void __cpuinit rcu_online_kthreads(int cpu)
 }
 
 /*
+ * kthread_create() creates threads in TASK_UNINTERRUPTIBLE state,
+ * but the RCU threads are woken on demand, and if demand is low this
+ * could be a while triggering the hung task watchdog.
+ *
+ * In order to avoid this, poke all tasks once the CPU is fully
+ * up and running.
+ */
+static void __cpuinit rcu_online_kthreads(int cpu)
+{
+	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
+	struct rcu_node *rnp = rdp->mynode;
+	struct task_struct *t;
+
+	t = per_cpu(rcu_cpu_kthread_task, cpu);
+	if (t)
+		wake_up_process(t);
+
+	t = rnp->node_kthread_task;
+	if (t)
+		wake_up_process(t);
+
+	rcu_wake_one_boost_kthread(rnp);
+}
+
+/*
  * Handle CPU online/offline notification events.
  */
 static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
@@ -2251,10 +2258,11 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		rcu_online_cpu(cpu);
-		rcu_online_kthreads(cpu);
+		rcu_prepare_cpu(cpu);
+		rcu_prepare_kthreads(cpu);
 		break;
 	case CPU_ONLINE:
+		rcu_online_kthreads(cpu);
 	case CPU_DOWN_FAILED:
 		rcu_node_kthread_setaffinity(rnp, -1);
 		rcu_cpu_kthread_setrt(cpu, 1);
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 257664815d5..7b9a08b4aae 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -84,11 +84,9 @@
  * Dynticks per-CPU state.
  */
 struct rcu_dynticks {
-	int dynticks_nesting;	/* Track nesting level, sort of. */
-	int dynticks;		/* Even value for dynticks-idle, else odd. */
-	int dynticks_nmi;	/* Even value for either dynticks-idle or */
-				/*  not in nmi handler, else odd.  So this */
-				/*  remains even for nmi from irq handler. */
+	int dynticks_nesting;	/* Track irq/process nesting level. */
+	int dynticks_nmi_nesting; /* Track NMI nesting level. */
+	atomic_t dynticks;	/* Even value for dynticks-idle, else odd. */
 };
 
 /* RCU's kthread states for tracing. */
@@ -121,7 +119,9 @@ struct rcu_node {
 				/*  elements that need to drain to allow the */
 				/*  current expedited grace period to */
 				/*  complete (only for TREE_PREEMPT_RCU). */
-	unsigned long wakemask; /* CPUs whose kthread needs to be awakened. */
+	atomic_t wakemask;	/* CPUs whose kthread needs to be awakened. */
+				/*  Since this has meaning only for leaf */
+				/*  rcu_node structures, 32 bits suffices. */
 	unsigned long qsmaskinit;
 				/* Per-GP initial value for qsmask & expmask. */
 	unsigned long grpmask;	/* Mask to apply to parent qsmask. */
@@ -159,9 +159,6 @@ struct rcu_node {
 	struct task_struct *boost_kthread_task;
 				/* kthread that takes care of priority */
 				/*  boosting for this rcu_node structure. */
-	wait_queue_head_t boost_wq;
-				/* Wait queue on which to park the boost */
-				/*  kthread. */
 	unsigned int boost_kthread_status;
 				/* State of boost_kthread_task for tracing. */
 	unsigned long n_tasks_boosted;
@@ -188,9 +185,6 @@ struct rcu_node {
 				/* kthread that takes care of this rcu_node */
 				/*  structure, for example, awakening the */
 				/*  per-CPU kthreads as needed. */
-	wait_queue_head_t node_wq;
-				/* Wait queue on which to park the per-node */
-				/*  kthread. */
 	unsigned int node_kthread_status;
 				/* State of node_kthread_task for tracing. */
 } ____cacheline_internodealigned_in_smp;
@@ -284,7 +278,6 @@ struct rcu_data {
 	/* 3) dynticks interface. */
 	struct rcu_dynticks *dynticks;	/* Shared per-CPU dynticks state. */
 	int dynticks_snap;		/* Per-GP tracking for dynticks. */
-	int dynticks_nmi_snap;		/* Per-GP tracking for dynticks_nmi. */
 #endif /* #ifdef CONFIG_NO_HZ */
 
 	/* 4) reasons this CPU needed to be kicked by force_quiescent_state */
@@ -337,6 +330,16 @@ struct rcu_data {
 						/*  scheduling clock irq */
 						/*  before ratting on them. */
 
+#define rcu_wait(cond)							\
+do {									\
+	for (;;) {							\
+		set_current_state(TASK_INTERRUPTIBLE);			\
+		if (cond)						\
+			break;						\
+		schedule();						\
+	}								\
+	__set_current_state(TASK_RUNNING);				\
+} while (0)
 
 /*
  * RCU global state, including node hierarchy.  This hierarchy is
@@ -446,7 +449,6 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu);
 static void rcu_preempt_send_cbs_to_online(void);
 static void __init __rcu_init_preempt(void);
 static void rcu_needs_cpu_flush(void);
-static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp);
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
 static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp,
 					  cpumask_var_t cm);
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 3f6559a5f5c..c8bff3099a8 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -1196,8 +1196,7 @@ static int rcu_boost_kthread(void *arg)
 
 	for (;;) {
 		rnp->boost_kthread_status = RCU_KTHREAD_WAITING;
-		wait_event_interruptible(rnp->boost_wq, rnp->boost_tasks ||
-							rnp->exp_tasks);
+		rcu_wait(rnp->boost_tasks || rnp->exp_tasks);
 		rnp->boost_kthread_status = RCU_KTHREAD_RUNNING;
 		more2boost = rcu_boost(rnp);
 		if (more2boost)
@@ -1275,14 +1274,6 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
 }
 
 /*
- * Initialize the RCU-boost waitqueue.
- */
-static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp)
-{
-	init_waitqueue_head(&rnp->boost_wq);
-}
-
-/*
  * Create an RCU-boost kthread for the specified node if one does not
  * already exist.  We only create this kthread for preemptible RCU.
  * Returns zero if all is well, a negated errno otherwise.
@@ -1306,12 +1297,17 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 	raw_spin_lock_irqsave(&rnp->lock, flags);
 	rnp->boost_kthread_task = t;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
-	wake_up_process(t);
 	sp.sched_priority = RCU_KTHREAD_PRIO;
 	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
 	return 0;
 }
 
+static void __cpuinit rcu_wake_one_boost_kthread(struct rcu_node *rnp)
+{
+	if (rnp->boost_kthread_task)
+		wake_up_process(rnp->boost_kthread_task);
+}
+
 #else /* #ifdef CONFIG_RCU_BOOST */
 
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
@@ -1328,10 +1324,6 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
 {
 }
 
-static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp)
-{
-}
-
 static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 						 struct rcu_node *rnp,
 						 int rnp_index)
@@ -1339,6 +1331,10 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 	return 0;
 }
 
+static void __cpuinit rcu_wake_one_boost_kthread(struct rcu_node *rnp)
+{
+}
+
 #endif /* #else #ifdef CONFIG_RCU_BOOST */
 
 #ifndef CONFIG_SMP
@@ -1520,7 +1516,6 @@ int rcu_needs_cpu(int cpu)
 {
 	int c = 0;
 	int snap;
-	int snap_nmi;
 	int thatcpu;
 
 	/* Check for being in the holdoff period. */
@@ -1531,10 +1526,10 @@ int rcu_needs_cpu(int cpu)
 	for_each_online_cpu(thatcpu) {
 		if (thatcpu == cpu)
 			continue;
-		snap = per_cpu(rcu_dynticks, thatcpu).dynticks;
-		snap_nmi = per_cpu(rcu_dynticks, thatcpu).dynticks_nmi;
+		snap = atomic_add_return(0, &per_cpu(rcu_dynticks,
+						     thatcpu).dynticks);
 		smp_mb(); /* Order sampling of snap with end of grace period. */
-		if (((snap & 0x1) != 0) || ((snap_nmi & 0x1) != 0)) {
+		if ((snap & 0x1) != 0) {
 			per_cpu(rcu_dyntick_drain, cpu) = 0;
 			per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
 			return rcu