Merge branch 'master' into for-next

Sync with Linus' tree to be able to apply pending patches that
are based on newer code already present upstream.

23 files changed, 743 insertions, 554 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 07dc154fc79..14c9b63a96c 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -560,29 +560,28 @@ void exit_files(struct task_struct *tsk)
 
 #ifdef CONFIG_MM_OWNER
 /*
- * Task p is exiting and it owned mm, lets find a new owner for it
+ * A task is exiting.   If it owned this mm, find a new owner for the mm.
  */
-static inline int
-mm_need_new_owner(struct mm_struct *mm, struct task_struct *p)
-{
-	/*
-	 * If there are other users of the mm and the owner (us) is exiting
-	 * we need to find a new owner to take on the responsibility.
-	 */
-	if (atomic_read(&mm->mm_users) <= 1)
-		return 0;
-	if (mm->owner != p)
-		return 0;
-	return 1;
-}
-
 void mm_update_next_owner(struct mm_struct *mm)
 {
 	struct task_struct *c, *g, *p = current;
 
 retry:
-	if (!mm_need_new_owner(mm, p))
+	/*
+	 * If the exiting or execing task is not the owner, it's
+	 * someone else's problem.
+	 */
+	if (mm->owner != p)
 		return;
+	/*
+	 * The current owner is exiting/execing and there are no other
+	 * candidates.  Do not leave the mm pointing to a possibly
+	 * freed task structure.
+	 */
+	if (atomic_read(&mm->mm_users) <= 1) {
+		mm->owner = NULL;
+		return;
+	}
 
 	read_lock(&tasklist_lock);
 	/*
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
index b8cadf70b1f..5bf924d80b5 100644
--- a/kernel/gcov/Kconfig
+++ b/kernel/gcov/Kconfig
@@ -2,7 +2,8 @@ menu "GCOV-based kernel profiling"
 
 config GCOV_KERNEL
 	bool "Enable gcov-based kernel profiling"
-	depends on DEBUG_FS && CONSTRUCTORS
+	depends on DEBUG_FS
+	select CONSTRUCTORS
 	default n
 	---help---
 	This option enables gcov-based code profiling (e.g. for code coverage
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index d64bafb1afd..0a7840aeb0f 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -491,6 +491,9 @@ int irq_set_irq_wake(unsigned int irq, unsigned int on)
 	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags);
 	int ret = 0;
 
+	if (!desc)
+		return -EINVAL;
+
 	/* wakeup-capable irqs can be shared between drivers that
 	 * don't need to have the same sleep mode behaviors.
 	 */
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index fa27e750dbc..a8ce45097f3 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -375,15 +375,19 @@ int jump_label_text_reserved(void *start, void *end)
 
 static void jump_label_update(struct jump_label_key *key, int enable)
 {
-	struct jump_entry *entry = key->entries;
-
-	/* if there are no users, entry can be NULL */
-	if (entry)
-		__jump_label_update(key, entry, __stop___jump_table, enable);
+	struct jump_entry *entry = key->entries, *stop = __stop___jump_table;
 
 #ifdef CONFIG_MODULES
+	struct module *mod = __module_address((jump_label_t)key);
+
 	__jump_label_mod_update(key, enable);
+
+	if (mod)
+		stop = mod->jump_entries + mod->num_jump_entries;
 #endif
+	/* if there are no users, entry can be NULL */
+	if (entry)
+		__jump_label_update(key, entry, stop, enable);
 }
 
 #endif
diff --git a/kernel/kmod.c b/kernel/kmod.c
index ad6a81c58b4..47613dfb7b2 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -156,12 +156,6 @@ static int ____call_usermodehelper(void *data)
 	 */
 	set_user_nice(current, 0);
 
-	if (sub_info->init) {
-		retval = sub_info->init(sub_info);
-		if (retval)
-			goto fail;
-	}
-
 	retval = -ENOMEM;
 	new = prepare_kernel_cred(current);
 	if (!new)
@@ -173,6 +167,14 @@ static int ____call_usermodehelper(void *data)
 					     new->cap_inheritable);
 	spin_unlock(&umh_sysctl_lock);
 
+	if (sub_info->init) {
+		retval = sub_info->init(sub_info, new);
+		if (retval) {
+			abort_creds(new);
+			goto fail;
+		}
+	}
+
 	commit_creds(new);
 
 	retval = kernel_execve(sub_info->path,
@@ -388,7 +390,7 @@ EXPORT_SYMBOL(call_usermodehelper_setup);
  * context in which call_usermodehelper_exec is called.
  */
 void call_usermodehelper_setfns(struct subprocess_info *info,
-		    int (*init)(struct subprocess_info *info),
+		    int (*init)(struct subprocess_info *info, struct cred *new),
 		    void (*cleanup)(struct subprocess_info *info),
 		    void *data)
 {
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index ace55889f70..06efa54f93d 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1211,7 +1211,11 @@ static void free_unnecessary_pages(void)
 		to_free_highmem = alloc_highmem - save;
 	} else {
 		to_free_highmem = 0;
-		to_free_normal -= save - alloc_highmem;
+		save -= alloc_highmem;
+		if (to_free_normal > save)
+			to_free_normal -= save;
+		else
+			to_free_normal = 0;
 	}
 
 	memory_bm_position_reset(&copy_bm);
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 7d02d33be69..42ddbc6f0de 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -113,8 +113,10 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 		if (error)
 			pm_notifier_call_chain(PM_POST_RESTORE);
 	}
-	if (error)
+	if (error) {
+		free_basic_memory_bitmaps();
 		atomic_inc(&snapshot_device_available);
+	}
 	data->frozen = 0;
 	data->ready = 0;
 	data->platform_support = 0;
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 89419ff92e9..7e59ffb3d0b 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -87,6 +87,8 @@ static struct rcu_state *rcu_state;
 int rcu_scheduler_active __read_mostly;
 EXPORT_SYMBOL_GPL(rcu_scheduler_active);
 
+#ifdef CONFIG_RCU_BOOST
+
 /*
  * Control variables for per-CPU and per-rcu_node kthreads.  These
  * handle all flavors of RCU.
@@ -98,8 +100,11 @@ DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
 DEFINE_PER_CPU(char, rcu_cpu_has_work);
 static char rcu_kthreads_spawnable;
 
+#endif /* #ifdef CONFIG_RCU_BOOST */
+
 static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
-static void invoke_rcu_cpu_kthread(void);
+static void invoke_rcu_core(void);
+static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
 
 #define RCU_KTHREAD_PRIO 1	/* RT priority for per-CPU kthreads. */
 
@@ -1088,14 +1093,8 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
 	int need_report = 0;
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp;
-	struct task_struct *t;
 
-	/* Stop the CPU's kthread. */
-	t = per_cpu(rcu_cpu_kthread_task, cpu);
-	if (t != NULL) {
-		per_cpu(rcu_cpu_kthread_task, cpu) = NULL;
-		kthread_stop(t);
-	}
+	rcu_stop_cpu_kthread(cpu);
 
 	/* Exclude any attempts to start a new grace period. */
 	raw_spin_lock_irqsave(&rsp->onofflock, flags);
@@ -1231,7 +1230,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 
 	/* Re-raise the RCU softirq if there are callbacks remaining. */
 	if (cpu_has_callbacks_ready_to_invoke(rdp))
-		invoke_rcu_cpu_kthread();
+		invoke_rcu_core();
 }
 
 /*
@@ -1277,7 +1276,7 @@ void rcu_check_callbacks(int cpu, int user)
 	}
 	rcu_preempt_check_callbacks(cpu);
 	if (rcu_pending(cpu))
-		invoke_rcu_cpu_kthread();
+		invoke_rcu_core();
 }
 
 #ifdef CONFIG_SMP
@@ -1442,13 +1441,14 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
 	}
 
 	/* If there are callbacks ready, invoke them. */
-	rcu_do_batch(rsp, rdp);
+	if (cpu_has_callbacks_ready_to_invoke(rdp))
+		invoke_rcu_callbacks(rsp, rdp);
 }
 
 /*
  * Do softirq processing for the current CPU.
  */
-static void rcu_process_callbacks(void)
+static void rcu_process_callbacks(struct softirq_action *unused)
 {
 	__rcu_process_callbacks(&rcu_sched_state,
 				&__get_cpu_var(rcu_sched_data));
@@ -1465,342 +1465,20 @@ static void rcu_process_callbacks(void)
  * the current CPU with interrupts disabled, the rcu_cpu_kthread_task
  * cannot disappear out from under us.
  */
-static void invoke_rcu_cpu_kthread(void)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__this_cpu_write(rcu_cpu_has_work, 1);
-	if (__this_cpu_read(rcu_cpu_kthread_task) == NULL) {
-		local_irq_restore(flags);
-		return;
-	}
-	wake_up_process(__this_cpu_read(rcu_cpu_kthread_task));
-	local_irq_restore(flags);
-}
-
-/*
- * Wake up the specified per-rcu_node-structure kthread.
- * Because the per-rcu_node kthreads are immortal, we don't need
- * to do anything to keep them alive.
- */
-static void invoke_rcu_node_kthread(struct rcu_node *rnp)
-{
-	struct task_struct *t;
-
-	t = rnp->node_kthread_task;
-	if (t != NULL)
-		wake_up_process(t);
-}
-
-/*
- * Set the specified CPU's kthread to run RT or not, as specified by
- * the to_rt argument.  The CPU-hotplug locks are held, so the task
- * is not going away.
- */
-static void rcu_cpu_kthread_setrt(int cpu, int to_rt)
-{
-	int policy;
-	struct sched_param sp;
-	struct task_struct *t;
-
-	t = per_cpu(rcu_cpu_kthread_task, cpu);
-	if (t == NULL)
-		return;
-	if (to_rt) {
-		policy = SCHED_FIFO;
-		sp.sched_priority = RCU_KTHREAD_PRIO;
-	} else {
-		policy = SCHED_NORMAL;
-		sp.sched_priority = 0;
-	}
-	sched_setscheduler_nocheck(t, policy, &sp);
-}
-
-/*
- * Timer handler to initiate the waking up of per-CPU kthreads that
- * have yielded the CPU due to excess numbers of RCU callbacks.
- * We wake up the per-rcu_node kthread, which in turn will wake up
- * the booster kthread.
- */
-static void rcu_cpu_kthread_timer(unsigned long arg)
-{
-	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, arg);
-	struct rcu_node *rnp = rdp->mynode;
-
-	atomic_or(rdp->grpmask, &rnp->wakemask);
-	invoke_rcu_node_kthread(rnp);
-}
-
-/*
- * Drop to non-real-time priority and yield, but only after posting a
- * timer that will cause us to regain our real-time priority if we
- * remain preempted.  Either way, we restore our real-time priority
- * before returning.
- */
-static void rcu_yield(void (*f)(unsigned long), unsigned long arg)
-{
-	struct sched_param sp;
-	struct timer_list yield_timer;
-
-	setup_timer_on_stack(&yield_timer, f, arg);
-	mod_timer(&yield_timer, jiffies + 2);
-	sp.sched_priority = 0;
-	sched_setscheduler_nocheck(current, SCHED_NORMAL, &sp);
-	set_user_nice(current, 19);
-	schedule();
-	sp.sched_priority = RCU_KTHREAD_PRIO;
-	sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
-	del_timer(&yield_timer);
-}
-
-/*
- * Handle cases where the rcu_cpu_kthread() ends up on the wrong CPU.
- * This can happen while the corresponding CPU is either coming online
- * or going offline.  We cannot wait until the CPU is fully online
- * before starting the kthread, because the various notifier functions
- * can wait for RCU grace periods.  So we park rcu_cpu_kthread() until
- * the corresponding CPU is online.
- *
- * Return 1 if the kthread needs to stop, 0 otherwise.
- *
- * Caller must disable bh.  This function can momentarily enable it.
- */
-static int rcu_cpu_kthread_should_stop(int cpu)
-{
-	while (cpu_is_offline(cpu) ||
-	       !cpumask_equal(&current->cpus_allowed, cpumask_of(cpu)) ||
-	       smp_processor_id() != cpu) {
-		if (kthread_should_stop())
-			return 1;
-		per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
-		per_cpu(rcu_cpu_kthread_cpu, cpu) = raw_smp_processor_id();
-		local_bh_enable();
-		schedule_timeout_uninterruptible(1);
-		if (!cpumask_equal(&current->cpus_allowed, cpumask_of(cpu)))
-			set_cpus_allowed_ptr(current, cpumask_of(cpu));
-		local_bh_disable();
-	}
-	per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
-	return 0;
-}
-
-/*
- * Per-CPU kernel thread that invokes RCU callbacks.  This replaces the
- * earlier RCU softirq.
- */
-static int rcu_cpu_kthread(void *arg)
-{
-	int cpu = (int)(long)arg;
-	unsigned long flags;
-	int spincnt = 0;
-	unsigned int *statusp = &per_cpu(rcu_cpu_kthread_status, cpu);
-	char work;
-	char *workp = &per_cpu(rcu_cpu_has_work, cpu);
-
-	for (;;) {
-		*statusp = RCU_KTHREAD_WAITING;
-		rcu_wait(*workp != 0 || kthread_should_stop());
-		local_bh_disable();
-		if (rcu_cpu_kthread_should_stop(cpu)) {
-			local_bh_enable();
-			break;
-		}
-		*statusp = RCU_KTHREAD_RUNNING;
-		per_cpu(rcu_cpu_kthread_loops, cpu)++;
-		local_irq_save(flags);
-		work = *workp;
-		*workp = 0;
-		local_irq_restore(flags);
-		if (work)
-			rcu_process_callbacks();
-		local_bh_enable();
-		if (*workp != 0)
-			spincnt++;
-		else
-			spincnt = 0;
-		if (spincnt > 10) {
-			*statusp = RCU_KTHREAD_YIELDING;
-			rcu_yield(rcu_cpu_kthread_timer, (unsigned long)cpu);
-			spincnt = 0;
-		}
-	}
-	*statusp = RCU_KTHREAD_STOPPED;
-	return 0;
-}
-
-/*
- * Spawn a per-CPU kthread, setting up affinity and priority.
- * Because the CPU hotplug lock is held, no other CPU will be attempting
- * to manipulate rcu_cpu_kthread_task.  There might be another CPU
- * attempting to access it during boot, but the locking in kthread_bind()
- * will enforce sufficient ordering.
- */
-static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu)
+static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
 {
-	struct sched_param sp;
-	struct task_struct *t;
-
-	if (!rcu_kthreads_spawnable ||
-	    per_cpu(rcu_cpu_kthread_task, cpu) != NULL)
-		return 0;
-	t = kthread_create(rcu_cpu_kthread, (void *)(long)cpu, "rcuc%d", cpu);
-	if (IS_ERR(t))
-		return PTR_ERR(t);
-	kthread_bind(t, 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;
-	sp.sched_priority = RCU_KTHREAD_PRIO;
-	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
-	return 0;
-}
-
-/*
- * Per-rcu_node kthread, which is in charge of waking up the per-CPU
- * kthreads when needed.  We ignore requests to wake up kthreads
- * for offline CPUs, which is OK because force_quiescent_state()
- * takes care of this case.
- */
-static int rcu_node_kthread(void *arg)
-{
-	int cpu;
-	unsigned long flags;
-	unsigned long mask;
-	struct rcu_node *rnp = (struct rcu_node *)arg;
-	struct sched_param sp;
-	struct task_struct *t;
-
-	for (;;) {
-		rnp->node_kthread_status = RCU_KTHREAD_WAITING;
-		rcu_wait(atomic_read(&rnp->wakemask) != 0);
-		rnp->node_kthread_status = RCU_KTHREAD_RUNNING;
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		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)
-				continue;
-			preempt_disable();
-			t = per_cpu(rcu_cpu_kthread_task, cpu);
-			if (!cpu_online(cpu) || t == NULL) {
-				preempt_enable();
-				continue;
-			}
-			per_cpu(rcu_cpu_has_work, cpu) = 1;
-			sp.sched_priority = RCU_KTHREAD_PRIO;
-			sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
-			preempt_enable();
-		}
-	}
-	/* NOTREACHED */
-	rnp->node_kthread_status = RCU_KTHREAD_STOPPED;
-	return 0;
-}
-
-/*
- * Set the per-rcu_node kthread's affinity to cover all CPUs that are
- * served by the rcu_node in question.  The CPU hotplug lock is still
- * held, so the value of rnp->qsmaskinit will be stable.
- *
- * We don't include outgoingcpu in the affinity set, use -1 if there is
- * no outgoing CPU.  If there are no CPUs left in the affinity set,
- * this function allows the kthread to execute on any CPU.
- */
-static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
-{
-	cpumask_var_t cm;
-	int cpu;
-	unsigned long mask = rnp->qsmaskinit;
-
-	if (rnp->node_kthread_task == NULL)
-		return;
-	if (!alloc_cpumask_var(&cm, GFP_KERNEL))
+	if (likely(!rsp->boost)) {
+		rcu_do_batch(rsp, rdp);
 		return;
-	cpumask_clear(cm);
-	for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1)
-		if ((mask & 0x1) && cpu != outgoingcpu)
-			cpumask_set_cpu(cpu, cm);
-	if (cpumask_weight(cm) == 0) {
-		cpumask_setall(cm);
-		for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++)
-			cpumask_clear_cpu(cpu, cm);
-		WARN_ON_ONCE(cpumask_weight(cm) == 0);
 	}
-	set_cpus_allowed_ptr(rnp->node_kthread_task, cm);
-	rcu_boost_kthread_setaffinity(rnp, cm);
-	free_cpumask_var(cm);
+	invoke_rcu_callbacks_kthread();
 }
 
-/*
- * Spawn a per-rcu_node kthread, setting priority and affinity.
- * Called during boot before online/offline can happen, or, if
- * during runtime, with the main CPU-hotplug locks held.  So only
- * one of these can be executing at a time.
- */
-static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp,
-						struct rcu_node *rnp)
+static void invoke_rcu_core(void)
 {
-	unsigned long flags;
-	int rnp_index = rnp - &rsp->node[0];
-	struct sched_param sp;
-	struct task_struct *t;
-
-	if (!rcu_kthreads_spawnable ||
-	    rnp->qsmaskinit == 0)
-		return 0;
-	if (rnp->node_kthread_task == NULL) {
-		t = kthread_create(rcu_node_kthread, (void *)rnp,
-				   "rcun%d", rnp_index);
-		if (IS_ERR(t))
-			return PTR_ERR(t);
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		rnp->node_kthread_task = t;
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
-		sp.sched_priority = 99;
-		sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
-	}
-	return rcu_spawn_one_boost_kthread(rsp, rnp, rnp_index);
+	raise_softirq(RCU_SOFTIRQ);
 }
 
-static void rcu_wake_one_boost_kthread(struct rcu_node *rnp);
-
-/*
- * Spawn all kthreads -- called as soon as the scheduler is running.
- */
-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) {
-		per_cpu(rcu_cpu_has_work, cpu) = 0;
-		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);
-	(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
-	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) {
-			(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);
-
 static void
 __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 	   struct rcu_state *rsp)
@@ -2207,44 +1885,6 @@ static void __cpuinit rcu_prepare_cpu(int cpu)
 	rcu_preempt_init_percpu_data(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;
-
-	/* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */
-	if (rcu_kthreads_spawnable) {
-		(void)rcu_spawn_one_cpu_kthread(cpu);
-		if (rnp->node_kthread_task == NULL)
-			(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
-	}
-}
-
-/*
- * 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.
  */
@@ -2262,7 +1902,6 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
 		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);
@@ -2410,6 +2049,7 @@ void __init rcu_init(void)
 	rcu_init_one(&rcu_sched_state, &rcu_sched_data);
 	rcu_init_one(&rcu_bh_state, &rcu_bh_data);
 	__rcu_init_preempt();
+	 open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 
 	/*
 	 * We don't need protection against CPU-hotplug here because
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 7b9a08b4aae..01b2ccda26f 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -369,6 +369,7 @@ struct rcu_state {
 						/*  period because */
 						/*  force_quiescent_state() */
 						/*  was running. */
+	u8	boost;				/* Subject to priority boost. */
 	unsigned long gpnum;			/* Current gp number. */
 	unsigned long completed;		/* # of last completed gp. */
 
@@ -426,6 +427,7 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
 static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,
 				      unsigned long flags);
+static void rcu_stop_cpu_kthread(int cpu);
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 static void rcu_print_detail_task_stall(struct rcu_state *rsp);
 static void rcu_print_task_stall(struct rcu_node *rnp);
@@ -450,11 +452,19 @@ 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 rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
+static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
+static void invoke_rcu_callbacks_kthread(void);
+#ifdef CONFIG_RCU_BOOST
+static void rcu_preempt_do_callbacks(void);
 static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp,
 					  cpumask_var_t cm);
-static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
 static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 						 struct rcu_node *rnp,
 						 int rnp_index);
+static void invoke_rcu_node_kthread(struct rcu_node *rnp);
+static void rcu_yield(void (*f)(unsigned long), unsigned long arg);
+#endif /* #ifdef CONFIG_RCU_BOOST */
+static void rcu_cpu_kthread_setrt(int cpu, int to_rt);
+static void __cpuinit rcu_prepare_kthreads(int cpu);
 
 #endif /* #ifndef RCU_TREE_NONCORE */
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index c8bff3099a8..14dc7dd0090 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -602,6 +602,15 @@ static void rcu_preempt_process_callbacks(void)
 				&__get_cpu_var(rcu_preempt_data));
 }
 
+#ifdef CONFIG_RCU_BOOST
+
+static void rcu_preempt_do_callbacks(void)
+{
+	rcu_do_batch(&rcu_preempt_state, &__get_cpu_var(rcu_preempt_data));
+}
+
+#endif /* #ifdef CONFIG_RCU_BOOST */
+
 /*
  * Queue a preemptible-RCU callback for invocation after a grace period.
  */
@@ -1249,6 +1258,23 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
 }
 
 /*
+ * Wake up the per-CPU kthread to invoke RCU callbacks.
+ */
+static void invoke_rcu_callbacks_kthread(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__this_cpu_write(rcu_cpu_has_work, 1);
+	if (__this_cpu_read(rcu_cpu_kthread_task) == NULL) {
+		local_irq_restore(flags);
+		return;
+	}
+	wake_up_process(__this_cpu_read(rcu_cpu_kthread_task));
+	local_irq_restore(flags);
+}
+
+/*
  * Set the affinity of the boost kthread.  The CPU-hotplug locks are
  * held, so no one should be messing with the existence of the boost
  * kthread.
@@ -1288,6 +1314,7 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 
 	if (&rcu_preempt_state != rsp)
 		return 0;
+	rsp->boost = 1;
 	if (rnp->boost_kthread_task != NULL)
 		return 0;
 	t = kthread_create(rcu_boost_kthread, (void *)rnp,
@@ -1299,13 +1326,372 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	sp.sched_priority = RCU_KTHREAD_PRIO;
 	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+	wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */
 	return 0;
 }
 
-static void __cpuinit rcu_wake_one_boost_kthread(struct rcu_node *rnp)
+#ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Stop the RCU's per-CPU kthread when its CPU goes offline,.
+ */
+static void rcu_stop_cpu_kthread(int cpu)
 {
-	if (rnp->boost_kthread_task)
-		wake_up_process(rnp->boost_kthread_task);
+	struct task_struct *t;
+
+	/* Stop the CPU's kthread. */
+	t = per_cpu(rcu_cpu_kthread_task, cpu);
+	if (t != NULL) {
+		per_cpu(rcu_cpu_kthread_task, cpu) = NULL;
+		kthread_stop(t);
+	}
+}
+
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+
+static void rcu_kthread_do_work(void)
+{
+	rcu_do_batch(&rcu_sched_state, &__get_cpu_var(rcu_sched_data));
+	rcu_do_batch(&rcu_bh_state, &__get_cpu_var(rcu_bh_data));
+	rcu_preempt_do_callbacks();
+}
+
+/*
+ * Wake up the specified per-rcu_node-structure kthread.
+ * Because the per-rcu_node kthreads are immortal, we don't need
+ * to do anything to keep them alive.
+ */
+static void invoke_rcu_node_kthread(struct rcu_node *rnp)
+{
+	struct task_struct *t;
+
+	t = rnp->node_kthread_task;
+	if (t != NULL)
+		wake_up_process(t);
+}
+
+/*
+ * Set the specified CPU's kthread to run RT or not, as specified by
+ * the to_rt argument.  The CPU-hotplug locks are held, so the task
+ * is not going away.
+ */
+static void rcu_cpu_kthread_setrt(int cpu, int to_rt)
+{
+	int policy;
+	struct sched_param sp;
+	struct task_struct *t;
+
+	t = per_cpu(rcu_cpu_kthread_task, cpu);
+	if (t == NULL)
+		return;
+	if (to_rt) {
+		policy = SCHED_FIFO;
+		sp.sched_priority = RCU_KTHREAD_PRIO;
+	} else {
+		policy = SCHED_NORMAL;
+		sp.sched_priority = 0;
+	}
+	sched_setscheduler_nocheck(t, policy, &sp);
+}
+
+/*
+ * Timer handler to initiate the waking up of per-CPU kthreads that
+ * have yielded the CPU due to excess numbers of RCU callbacks.
+ * We wake up the per-rcu_node kthread, which in turn will wake up
+ * the booster kthread.
+ */
+static void rcu_cpu_kthread_timer(unsigned long arg)
+{
+	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, arg);
+	struct rcu_node *rnp = rdp->mynode;
+
+	atomic_or(rdp->grpmask, &rnp->wakemask);
+	invoke_rcu_node_kthread(rnp);
+}
+
+/*
+ * Drop to non-real-time priority and yield, but only after posting a
+ * timer that will cause us to regain our real-time priority if we
+ * remain preempted.  Either way, we restore our real-time priority
+ * before returning.
+ */
+static void rcu_yield(void (*f)(unsigned long), unsigned long arg)
+{
+	struct sched_param sp;
+	struct timer_list yield_timer;
+
+	setup_timer_on_stack(&yield_timer, f, arg);
+	mod_timer(&yield_timer, jiffies + 2);
+	sp.sched_priority = 0;
+	sched_setscheduler_nocheck(current, SCHED_NORMAL, &sp);
+	set_user_nice(current, 19);
+	schedule();
+	sp.sched_priority = RCU_KTHREAD_PRIO;
+	sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
+	del_timer(&yield_timer);
+}
+
+/*
+ * Handle cases where the rcu_cpu_kthread() ends up on the wrong CPU.
+ * This can happen while the corresponding CPU is either coming online
+ * or going offline.  We cannot wait until the CPU is fully online
+ * before starting the kthread, because the various notifier functions
+ * can wait for RCU grace periods.  So we park rcu_cpu_kthread() until
+ * the corresponding CPU is online.
+ *
+ * Return 1 if the kthread needs to stop, 0 otherwise.
+ *
+ * Caller must disable bh.  This function can momentarily enable it.
+ */
+static int rcu_cpu_kthread_should_stop(int cpu)
+{
+	while (cpu_is_offline(cpu) ||
+	       !cpumask_equal(&current->cpus_allowed, cpumask_of(cpu)) ||
+	       smp_processor_id() != cpu) {
+		if (kthread_should_stop())
+			return 1;
+		per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
+		per_cpu(rcu_cpu_kthread_cpu, cpu) = raw_smp_processor_id();
+		local_bh_enable();
+		schedule_timeout_uninterruptible(1);
+		if (!cpumask_equal(&current->cpus_allowed, cpumask_of(cpu)))
+			set_cpus_allowed_ptr(current, cpumask_of(cpu));
+		local_bh_disable();
+	}
+	per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
+	return 0;
+}
+
+/*
+ * Per-CPU kernel thread that invokes RCU callbacks.  This replaces the
+ * earlier RCU softirq.
+ */
+static int rcu_cpu_kthread(void *arg)
+{
+	int cpu = (int)(long)arg;
+	unsigned long flags;
+	int spincnt = 0;
+	unsigned int *statusp = &per_cpu(rcu_cpu_kthread_status, cpu);
+	char work;
+	char *workp = &per_cpu(rcu_cpu_has_work, cp