Merge remote-tracking branch 'tip/smp/hotplug' into next.2012.09.25b

The conflicts between kernel/rcutree.h and kernel/rcutree_plugin.h
were due to adjacent insertions and deletions, which were resolved
by simply accepting the changes on both branches.

drivers/infiniband/hw/ehca/ehca_irq.c

@@ -42,6 +42,7 @@
  */
 
 #include <linux/slab.h>
+#include <linux/smpboot.h>
 
 #include "ehca_classes.h"
 #include "ehca_irq.h"
@@ -652,7 +653,7 @@ void ehca_tasklet_eq(unsigned long data)
 	ehca_process_eq((struct ehca_shca*)data, 1);
 }
 
-static inline int find_next_online_cpu(struct ehca_comp_pool *pool)
+static int find_next_online_cpu(struct ehca_comp_pool *pool)
 {
 	int cpu;
 	unsigned long flags;
@@ -662,17 +663,20 @@ static inline int find_next_online_cpu(struct ehca_comp_pool *pool)
 		ehca_dmp(cpu_online_mask, cpumask_size(), "");
 
 	spin_lock_irqsave(&pool->last_cpu_lock, flags);
+	do {
 		cpu = cpumask_next(pool->last_cpu, cpu_online_mask);
 		if (cpu >= nr_cpu_ids)
 			cpu = cpumask_first(cpu_online_mask);
 		pool->last_cpu = cpu;
+	} while (!per_cpu_ptr(pool->cpu_comp_tasks, cpu)->active);
 	spin_unlock_irqrestore(&pool->last_cpu_lock, flags);
 
 	return cpu;
 }
 
 static void __queue_comp_task(struct ehca_cq *__cq,
-			      struct ehca_cpu_comp_task *cct)
+			      struct ehca_cpu_comp_task *cct,
+			      struct task_struct *thread)
 {
 	unsigned long flags;
 
@@ -683,7 +687,7 @@ static void __queue_comp_task(struct ehca_cq *__cq,
 		__cq->nr_callbacks++;
 		list_add_tail(&__cq->entry, &cct->cq_list);
 		cct->cq_jobs++;
-		wake_up(&cct->wait_queue);
+		wake_up_process(thread);
 	} else
 		__cq->nr_callbacks++;
 
@@ -695,6 +699,7 @@ static void queue_comp_task(struct ehca_cq *__cq)
 {
 	int cpu_id;
 	struct ehca_cpu_comp_task *cct;
+	struct task_struct *thread;
 	int cq_jobs;
 	unsigned long flags;
 
@@ -702,7 +707,8 @@ static void queue_comp_task(struct ehca_cq *__cq)
 	BUG_ON(!cpu_online(cpu_id));
 
 	cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu_id);
-	BUG_ON(!cct);
+	thread = *per_cpu_ptr(pool->cpu_comp_threads, cpu_id);
+	BUG_ON(!cct || !thread);
 
 	spin_lock_irqsave(&cct->task_lock, flags);
 	cq_jobs = cct->cq_jobs;
@@ -710,28 +716,25 @@ static void queue_comp_task(struct ehca_cq *__cq)
 	if (cq_jobs > 0) {
 		cpu_id = find_next_online_cpu(pool);
 		cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu_id);
-		BUG_ON(!cct);
+		thread = *per_cpu_ptr(pool->cpu_comp_threads, cpu_id);
+		BUG_ON(!cct || !thread);
 	}
-
-	__queue_comp_task(__cq, cct);
+	__queue_comp_task(__cq, cct, thread);
 }
 
 static void run_comp_task(struct ehca_cpu_comp_task *cct)
 {
 	struct ehca_cq *cq;
-	unsigned long flags;
-
-	spin_lock_irqsave(&cct->task_lock, flags);
 
 	while (!list_empty(&cct->cq_list)) {
 		cq = list_entry(cct->cq_list.next, struct ehca_cq, entry);
-		spin_unlock_irqrestore(&cct->task_lock, flags);
+		spin_unlock_irq(&cct->task_lock);
 
 		comp_event_callback(cq);
 		if (atomic_dec_and_test(&cq->nr_events))
 			wake_up(&cq->wait_completion);
 
-		spin_lock_irqsave(&cct->task_lock, flags);
+		spin_lock_irq(&cct->task_lock);
 		spin_lock(&cq->task_lock);
 		cq->nr_callbacks--;
 		if (!cq->nr_callbacks) {
@@ -740,159 +743,76 @@ static void run_comp_task(struct ehca_cpu_comp_task *cct)
 		}
 		spin_unlock(&cq->task_lock);
 	}
-
-	spin_unlock_irqrestore(&cct->task_lock, flags);
 }
 
-static int comp_task(void *__cct)
+static void comp_task_park(unsigned int cpu)
 {
-	struct ehca_cpu_comp_task *cct = __cct;
-	int cql_empty;
-	DECLARE_WAITQUEUE(wait, current);
-
-	set_current_state(TASK_INTERRUPTIBLE);
-	while (!kthread_should_stop()) {
-		add_wait_queue(&cct->wait_queue, &wait);
-
-		spin_lock_irq(&cct->task_lock);
-		cql_empty = list_empty(&cct->cq_list);
-		spin_unlock_irq(&cct->task_lock);
-		if (cql_empty)
-			schedule();
-		else
-			__set_current_state(TASK_RUNNING);
-
-		remove_wait_queue(&cct->wait_queue, &wait);
+	struct ehca_cpu_comp_task *cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
+	struct ehca_cpu_comp_task *target;
+	struct task_struct *thread;
+	struct ehca_cq *cq, *tmp;
+	LIST_HEAD(list);
 
 	spin_lock_irq(&cct->task_lock);
-		cql_empty = list_empty(&cct->cq_list);
+	cct->cq_jobs = 0;
+	cct->active = 0;
+	list_splice_init(&cct->cq_list, &list);
 	spin_unlock_irq(&cct->task_lock);
-		if (!cql_empty)
-			run_comp_task(__cct);
 
-		set_current_state(TASK_INTERRUPTIBLE);
+	cpu = find_next_online_cpu(pool);
+	target = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
+	thread = *per_cpu_ptr(pool->cpu_comp_threads, cpu);
+	spin_lock_irq(&target->task_lock);
+	list_for_each_entry_safe(cq, tmp, &list, entry) {
+		list_del(&cq->entry);
+		__queue_comp_task(cq, target, thread);
 	}
-	__set_current_state(TASK_RUNNING);
-
-	return 0;
+	spin_unlock_irq(&target->task_lock);
 }
 
-static struct task_struct *create_comp_task(struct ehca_comp_pool *pool,
-					    int cpu)
+static void comp_task_stop(unsigned int cpu, bool online)
 {
-	struct ehca_cpu_comp_task *cct;
-
-	cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
-	spin_lock_init(&cct->task_lock);
-	INIT_LIST_HEAD(&cct->cq_list);
-	init_waitqueue_head(&cct->wait_queue);
-	cct->task = kthread_create_on_node(comp_task, cct, cpu_to_node(cpu),
-					   "ehca_comp/%d", cpu);
-
-	return cct->task;
-}
-
-static void destroy_comp_task(struct ehca_comp_pool *pool,
-			      int cpu)
-{
-	struct ehca_cpu_comp_task *cct;
-	struct task_struct *task;
-	unsigned long flags_cct;
-
-	cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
-
-	spin_lock_irqsave(&cct->task_lock, flags_cct);
+	struct ehca_cpu_comp_task *cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
 
-	task = cct->task;
-	cct->task = NULL;
+	spin_lock_irq(&cct->task_lock);
 	cct->cq_jobs = 0;
-
-	spin_unlock_irqrestore(&cct->task_lock, flags_cct);
-
-	if (task)
-		kthread_stop(task);
+	cct->active = 0;
+	WARN_ON(!list_empty(&cct->cq_list));
+	spin_unlock_irq(&cct->task_lock);
 }
 
-static void __cpuinit take_over_work(struct ehca_comp_pool *pool, int cpu)
+static int comp_task_should_run(unsigned int cpu)
 {
 	struct ehca_cpu_comp_task *cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
-	LIST_HEAD(list);
-	struct ehca_cq *cq;
-	unsigned long flags_cct;
-
-	spin_lock_irqsave(&cct->task_lock, flags_cct);
-
-	list_splice_init(&cct->cq_list, &list);
-
-	while (!list_empty(&list)) {
-		cq = list_entry(cct->cq_list.next, struct ehca_cq, entry);
-
-		list_del(&cq->entry);
-		__queue_comp_task(cq, this_cpu_ptr(pool->cpu_comp_tasks));
-	}
-
-	spin_unlock_irqrestore(&cct->task_lock, flags_cct);
 
+	return cct->cq_jobs;
 }
 
-static int __cpuinit comp_pool_callback(struct notifier_block *nfb,
-					unsigned long action,
-					void *hcpu)
+static void comp_task(unsigned int cpu)
 {
-	unsigned int cpu = (unsigned long)hcpu;
-	struct ehca_cpu_comp_task *cct;
+	struct ehca_cpu_comp_task *cct = this_cpu_ptr(pool->cpu_comp_tasks);
+	int cql_empty;
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		ehca_gen_dbg("CPU: %x (CPU_PREPARE)", cpu);
-		if (!create_comp_task(pool, cpu)) {
-			ehca_gen_err("Can't create comp_task for cpu: %x", cpu);
-			return notifier_from_errno(-ENOMEM);
-		}
-		break;
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-		ehca_gen_dbg("CPU: %x (CPU_CANCELED)", cpu);
-		cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
-		kthread_bind(cct->task, cpumask_any(cpu_online_mask));
-		destroy_comp_task(pool, cpu);
-		break;
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		ehca_gen_dbg("CPU: %x (CPU_ONLINE)", cpu);
-		cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
-		kthread_bind(cct->task, cpu);
-		wake_up_process(cct->task);
-		break;
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		ehca_gen_dbg("CPU: %x (CPU_DOWN_PREPARE)", cpu);
-		break;
-	case CPU_DOWN_FAILED:
-	case CPU_DOWN_FAILED_FROZEN:
-		ehca_gen_dbg("CPU: %x (CPU_DOWN_FAILED)", cpu);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		ehca_gen_dbg("CPU: %x (CPU_DEAD)", cpu);
-		destroy_comp_task(pool, cpu);
-		take_over_work(pool, cpu);
-		break;
+	spin_lock_irq(&cct->task_lock);
+	cql_empty = list_empty(&cct->cq_list);
+	if (!cql_empty) {
+		__set_current_state(TASK_RUNNING);
+		run_comp_task(cct);
 	}
-
-	return NOTIFY_OK;
+	spin_unlock_irq(&cct->task_lock);
 }
 
-static struct notifier_block comp_pool_callback_nb __cpuinitdata = {
-	.notifier_call	= comp_pool_callback,
-	.priority	= 0,
+static struct smp_hotplug_thread comp_pool_threads = {
+	.thread_should_run	= comp_task_should_run,
+	.thread_fn		= comp_task,
+	.thread_comm		= "ehca_comp/%u",
+	.cleanup		= comp_task_stop,
+	.park			= comp_task_park,
 };
 
 int ehca_create_comp_pool(void)
 {
-	int cpu;
-	struct task_struct *task;
+	int cpu, ret = -ENOMEM;
 
 	if (!ehca_scaling_code)
 		return 0;
@@ -905,38 +825,46 @@ int ehca_create_comp_pool(void)
 	pool->last_cpu = cpumask_any(cpu_online_mask);
 
 	pool->cpu_comp_tasks = alloc_percpu(struct ehca_cpu_comp_task);
-	if (pool->cpu_comp_tasks == NULL) {
-		kfree(pool);
-		return -EINVAL;
-	}
+	if (!pool->cpu_comp_tasks)
+		goto out_pool;
 
-	for_each_online_cpu(cpu) {
-		task = create_comp_task(pool, cpu);
-		if (task) {
-			kthread_bind(task, cpu);
-			wake_up_process(task);
-		}
+	pool->cpu_comp_threads = alloc_percpu(struct task_struct *);
+	if (!pool->cpu_comp_threads)
+		goto out_tasks;
+
+	for_each_present_cpu(cpu) {
+		struct ehca_cpu_comp_task *cct;
+
+		cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
+		spin_lock_init(&cct->task_lock);
+		INIT_LIST_HEAD(&cct->cq_list);
 	}
 
-	register_hotcpu_notifier(&comp_pool_callback_nb);
+	comp_pool_threads.store = pool->cpu_comp_threads;
+	ret = smpboot_register_percpu_thread(&comp_pool_threads);
+	if (ret)
+		goto out_threads;
 
-	printk(KERN_INFO "eHCA scaling code enabled\n");
+	pr_info("eHCA scaling code enabled\n");
+	return ret;
 
-	return 0;
+out_threads:
+	free_percpu(pool->cpu_comp_threads);
+out_tasks:
+	free_percpu(pool->cpu_comp_tasks);
+out_pool:
+	kfree(pool);
+	return ret;
 }
 
 void ehca_destroy_comp_pool(void)
 {
-	int i;
-
 	if (!ehca_scaling_code)
 		return;
 
-	unregister_hotcpu_notifier(&comp_pool_callback_nb);
-
-	for_each_online_cpu(i)
-		destroy_comp_task(pool, i);
+	smpboot_unregister_percpu_thread(&comp_pool_threads);
 
+	free_percpu(pool->cpu_comp_threads);
 	free_percpu(pool->cpu_comp_tasks);
 	kfree(pool);
 }

drivers/infiniband/hw/ehca/ehca_irq.h

@@ -58,15 +58,15 @@ void ehca_tasklet_eq(unsigned long data);
 void ehca_process_eq(struct ehca_shca *shca, int is_irq);
 
 struct ehca_cpu_comp_task {
-	wait_queue_head_t wait_queue;
 	struct list_head cq_list;
-	struct task_struct *task;
 	spinlock_t task_lock;
 	int cq_jobs;
+	int active;
 };
 
 struct ehca_comp_pool {
-	struct ehca_cpu_comp_task *cpu_comp_tasks;
+	struct ehca_cpu_comp_task __percpu *cpu_comp_tasks;
+	struct task_struct * __percpu *cpu_comp_threads;
 	int last_cpu;
 	spinlock_t last_cpu_lock;
 };

include/linux/kthread.h

@@ -14,6 +14,11 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
 	kthread_create_on_node(threadfn, data, -1, namefmt, ##arg)
 
 
+struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
+					  void *data,
+					  unsigned int cpu,
+					  const char *namefmt);
+
 /**
  * kthread_run - create and wake a thread.
  * @threadfn: the function to run until signal_pending(current).
@@ -34,9 +39,13 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
 
 void kthread_bind(struct task_struct *k, unsigned int cpu);
 int kthread_stop(struct task_struct *k);
-int kthread_should_stop(void);
+bool kthread_should_stop(void);
+bool kthread_should_park(void);
 bool kthread_freezable_should_stop(bool *was_frozen);
 void *kthread_data(struct task_struct *k);
+int kthread_park(struct task_struct *k);
+void kthread_unpark(struct task_struct *k);
+void kthread_parkme(void);
 
 int kthreadd(void *unused);
 extern struct task_struct *kthreadd_task;

include/linux/smpboot.h

+#ifndef _LINUX_SMPBOOT_H
+#define _LINUX_SMPBOOT_H
+
+#include <linux/types.h>
+
+struct task_struct;
+/* Cookie handed to the thread_fn*/
+struct smpboot_thread_data;
+
+/**
+ * struct smp_hotplug_thread - CPU hotplug related thread descriptor
+ * @store:		Pointer to per cpu storage for the task pointers
+ * @list:		List head for core management
+ * @thread_should_run:	Check whether the thread should run or not. Called with
+ *			preemption disabled.
+ * @thread_fn:		The associated thread function
+ * @setup:		Optional setup function, called when the thread gets
+ *			operational the first time
+ * @cleanup:		Optional cleanup function, called when the thread
+ *			should stop (module exit)
+ * @park:		Optional park function, called when the thread is
+ *			parked (cpu offline)
+ * @unpark:		Optional unpark function, called when the thread is
+ *			unparked (cpu online)
+ * @thread_comm:	The base name of the thread
+ */
+struct smp_hotplug_thread {
+	struct task_struct __percpu	**store;
+	struct list_head		list;
+	int				(*thread_should_run)(unsigned int cpu);
+	void				(*thread_fn)(unsigned int cpu);
+	void				(*setup)(unsigned int cpu);
+	void				(*cleanup)(unsigned int cpu, bool online);
+	void				(*park)(unsigned int cpu);
+	void				(*unpark)(unsigned int cpu);
+	const char			*thread_comm;
+};
+
+int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread);
+void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread);
+int smpboot_thread_schedule(void);
+
+#endif

kernel/Makefile

@@ -10,7 +10,7 @@ obj-y     = fork.o exec_domain.o panic.o printk.o \
 	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
 	    notifier.o ksysfs.o cred.o \
-	    async.o range.o groups.o lglock.o
+	    async.o range.o groups.o lglock.o smpboot.o
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace debug files and internal ftrace files
@@ -46,7 +46,6 @@ obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
 obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
 obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
 obj-$(CONFIG_SMP) += smp.o
-obj-$(CONFIG_SMP) += smpboot.o
 ifneq ($(CONFIG_SMP),y)
 obj-y += up.o
 endif

kernel/cpu.c

@@ -280,12 +280,13 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 				__func__, cpu);
 		goto out_release;
 	}
+	smpboot_park_threads(cpu);
 
 	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
 		/* CPU didn't die: tell everyone.  Can't complain. */
+		smpboot_unpark_threads(cpu);
 		cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);
-
 		goto out_release;
 	}
 	BUG_ON(cpu_online(cpu));
@@ -354,6 +355,10 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
 		goto out;
 	}
 
+	ret = smpboot_create_threads(cpu);
+	if (ret)
+		goto out;
+
 	ret = __cpu_notify(CPU_UP_PREPARE | mod, hcpu, -1, &nr_calls);
 	if (ret) {
 		nr_calls--;
@@ -368,6 +373,9 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
 		goto out_notify;
 	BUG_ON(!cpu_online(cpu));
 
+	/* Wake the per cpu threads */
+	smpboot_unpark_threads(cpu);
+
 	/* Now call notifier in preparation. */
 	cpu_notify(CPU_ONLINE | mod, hcpu);
 

kernel/kthread.c

@@ -37,11 +37,20 @@ struct kthread_create_info
 };
 
 struct kthread {
-	int should_stop;
+	unsigned long flags;
+	unsigned int cpu;
 	void *data;
+	struct completion parked;
 	struct completion exited;
 };
 
+enum KTHREAD_BITS {
+	KTHREAD_IS_PER_CPU = 0,
+	KTHREAD_SHOULD_STOP,
+	KTHREAD_SHOULD_PARK,
+	KTHREAD_IS_PARKED,
+};
+
 #define to_kthread(tsk)	\
 	container_of((tsk)->vfork_done, struct kthread, exited)
 
@@ -52,12 +61,28 @@ struct kthread {
  * and this will return true.  You should then return, and your return
  * value will be passed through to kthread_stop().
  */
-int kthread_should_stop(void)
+bool kthread_should_stop(void)
 {
-	return to_kthread(current)->should_stop;
+	return test_bit(KTHREAD_SHOULD_STOP, &to_kthread(current)->flags);
 }
 EXPORT_SYMBOL(kthread_should_stop);
 
+/**
+ * kthread_should_park - should this kthread park now?
+ *
+ * When someone calls kthread_park() on your kthread, it will be woken
+ * and this will return true.  You should then do the necessary
+ * cleanup and call kthread_parkme()
+ *
+ * Similar to kthread_should_stop(), but this keeps the thread alive
+ * and in a park position. kthread_unpark() "restarts" the thread and
+ * calls the thread function again.
+ */
+bool kthread_should_park(void)
+{
+	return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(current)->flags);
+}
+
 /**
  * kthread_freezable_should_stop - should this freezable kthread return now?
  * @was_frozen: optional out parameter, indicates whether %current was frozen
@@ -96,6 +121,24 @@ void *kthread_data(struct task_struct *task)
 	return to_kthread(task)->data;
 }
 
+static void __kthread_parkme(struct kthread *self)
+{
+	__set_current_state(TASK_INTERRUPTIBLE);
+	while (test_bit(KTHREAD_SHOULD_PARK, &self->flags)) {
+		if (!test_and_set_bit(KTHREAD_IS_PARKED, &self->flags))
+			complete(&self->parked);
+		schedule();
+		__set_current_state(TASK_INTERRUPTIBLE);
+	}
+	clear_bit(KTHREAD_IS_PARKED, &self->flags);
+	__set_current_state(TASK_RUNNING);
+}
+
+void kthread_parkme(void)
+{
+	__kthread_parkme(to_kthread(current));
+}
+
 static int kthread(void *_create)
 {
 	/* Copy data: it's on kthread's stack */
@@ -105,9 +148,10 @@ static int kthread(void *_create)
 	struct kthread self;
 	int ret;
 
-	self.should_stop = 0;
+	self.flags = 0;
 	self.data = data;
 	init_completion(&self.exited);
+	init_completion(&self.parked);
 	current->vfork_done = &self.exited;
 
 	/* OK, tell user we're spawned, wait for stop or wakeup */
@@ -117,9 +161,11 @@ static int kthread(void *_create)
 	schedule();
 
 	ret = -EINTR;
-	if (!self.should_stop)
-		ret = threadfn(data);
 
+	if (!test_bit(KTHREAD_SHOULD_STOP, &self.flags)) {
+		__kthread_parkme(&self);
+		ret = threadfn(data);
+	}
 	/* we can't just return, we must preserve "self" on stack */
 	do_exit(ret);
 }
@@ -172,8 +218,7 @@ static void create_kthread(struct kthread_create_info *create)
  * Returns a task_struct or ERR_PTR(-ENOMEM).
  */
 struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
-					   void *data,
-					   int node,
+					   void *data, int node,
 					   const char namefmt[],
 					   ...)
 {
@@ -210,6 +255,13 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
 }
 EXPORT_SYMBOL(kthread_create_on_node);
 
+static void __kthread_bind(struct task_struct *p, unsigned int cpu)
+{
+	/* It's safe because the task is inactive. */
+	do_set_cpus_allowed(p, cpumask_of(cpu));
+	p->flags |= PF_THREAD_BOUND;
+}
+
 /**
  * kthread_bind - bind a just-created kthread to a cpu.
  * @p: thread created by kthread_create().
@@ -226,13 +278,111 @@ void kthread_bind(struct task_struct *p, unsigned int cpu)
 		WARN_ON(1);
 		return;
 	}
-
-	/* It's safe because the task is inactive. */
-	do_set_cpus_allowed(p, cpumask_of(cpu));
-	p->flags |= PF_THREAD_BOUND;
+	__kthread_bind(p, cpu);
 }
 EXPORT_SYMBOL(kthread_bind);
 
+/**
+ * kthread_create_on_cpu - Create a cpu bound kthread
+ * @threadfn: the function to run until signal_pending(current).
+ * @data: data ptr for @threadfn.
+ * @cpu: The cpu on which the thread should be bound,
+ * @namefmt: printf-style name for the thread. Format is restricted
+ *	     to "name.*%u". Code fills in cpu number.
+ *
+ * Description: This helper function creates and names a kernel thread
+ * The thread will be woken and put into park mode.
+ */
+struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
+					  void *data, unsigned int cpu,
+					  const char *namefmt)
+{
+	struct task_struct *p;
+
+	p = kthread_create_on_node(threadfn, data, cpu_to_node(cpu), namefmt,
+				   cpu);
+	if (IS_ERR(p))
+		return p;
+	set_bit(KTHREAD_IS_PER_CPU, &to_kthread(p)->flags);
+	to_kthread(p)->cpu = cpu;
+	/* Park the thread to get it out of TASK_UNINTERRUPTIBLE state */
+	kthread_park(p);
+	return p;
+}
+
+static struct kthread *task_get_live_kthread(struct task_struct *k)
+{
+	struct kthread *kthread;
+
+	get_task_struct(k);
+	kthread = to_kthread(k);
+	/* It might have exited */
+	barrier();
+	if (k->vfork_done != NULL)
+		return kthread;
+	return NULL;
+}
+
+/**
+ * kthread_unpark - unpark a thread created by kthread_create().
+ * @k:		thread created by kthread_create().
+ *
+ * Sets kthread_should_park() for @k to return false, wakes it, and
+ * waits for it to return. If the thread is marked percpu then its
+ * bound to the cpu again.
+ */
+void kthread_unpark(struct task_struct *k)
+{
+	struct kthread *kthread = task_get_live_kthread(k);
+
+	if (kthread) {
+		clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+		/*
+		 * We clear the IS_PARKED bit here as we don't wait
+		 * until the task has left the park code. So if we'd
+		 * park before that happens we'd see the IS_PARKED bit
+		 * which might be about to be cleared.
+		 */
+		if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
+			if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
+				__kthread_bind(k, kthread->cpu);
+			wake_up_process(k);
+		}
+	}
+	put_task_struct(k);
+}
+
+/**
+ * kthread_park - park a thread created by kthread_create().
+ * @k: thread created by kthread_create().
+ *
+ * Sets kthread_should_park() for @k to return true, wakes it, and
+ * waits for it to return. This can also be called after kthread_create()
+ * instead of calling wake_up_process(): the thread will park without
+ * calling threadfn().
+ *
+ * Returns 0 if the thread is parked, -ENOSYS if the thread exited.
+ * If called by the kthread itself just the park bit is set.
+ */
+int kthread_park(struct task_struct *k)
+{
+	struct kthread *kthread = task_get_live_kthread(k);
+	int ret = -ENOSYS;
+
+	if (kthread) {
+		if (!test_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
+			set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+			if (k != current) {
+				wake_up_process(k);
+				wait_for_completion(&kthread->parked);
+			}
+		}
+		ret = 0;
+	}
+	put_task_struct(k);
+	return ret;
+}
+
 /**
  * kthread_stop - stop a thread created by kthread_create().
  * @k: thread created by kthread_create().
@@ -250,16 +400,13 @@ EXPORT_SYMBOL(kthread_bind);
  */
 int kthread_stop(struct task_struct *k)
 {
-	struct kthread *kthread;
+	struct kthread *kthread = task_get_live_kthread(k);
 	int ret;
 
 	trace_sched_kthread_stop(k);
-	get_task_struct(k);
-
-	kthread = to_kthread(k);
-	barrier(); /* it might have exited */
-	if (k->vfork_done != NULL) {
-		kthread->should_stop = 1;
+	if (kthread) {
+		set_bit(KTHREAD_SHOULD_STOP, &kthread->flags);
+		clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
 		wake_up_process(k);
 		wait_for_completion(&kthread->exited);
 	}

kernel/rcutree.c

@@ -134,13 +134,12 @@ static int rcu_scheduler_fully_active __read_mostly;
  */
 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);
 DEFINE_PER_CPU(char, rcu_cpu_has_work);
 
 #endif /* #ifdef CONFIG_RCU_BOOST */
 
-static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
+static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
 static void invoke_rcu_core(void);
 static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
 
@@ -1543,8 +1542,7 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
 
 	/* Adjust any no-longer-needed kthreads. */
-	rcu_stop_cpu_kthread(cpu);
-	rcu_node_kthread_setaffinity(rnp, -1);
+	rcu_boost_kthread_setaffinity(rnp, -1);
 
 	/* Remove the dead CPU from the bitmasks in the rcu_node hierarchy. */
 
@@ -2572,12 +2570,10 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
 		break;
 	case CPU_ONLINE:
 	case CPU_DOWN_FAILED:
-		rcu_node_kthread_setaffinity(rnp, -1);
-		rcu_cpu_kthread_setrt(cpu, 1);
+		rcu_boost_kthread_setaffinity(rnp, -1);
 		break;
 	case CPU_DOWN_PREPARE:
-		rcu_node_kthread_setaffinity(rnp, cpu);
-		rcu_cpu_kthread_setrt(cpu, 0);
+		rcu_boost_kthread_setaffinity(rnp, cpu);
 		break;
 	case CPU_DYING:
 	case CPU_DYING_FROZEN:

kernel/rcutree.h

@@ -196,12 +196,6 @@ struct rcu_node {
 				/* Refused to boost: not sure why, though. */
 				/*  This can happen due to race conditions. */
 #endif /* #ifdef CONFIG_RCU_BOOST */
-	struct task_struct *node_kthread_task;
-				/* kthread that takes care of this rcu_node */
-				/*  structure, for example, awakening the */
-				/*  per-CPU kthreads as needed. */
-	unsigned int node_kthread_status;
-				/* State of node_kthread_task for tracing. */
 	raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp;
 } ____cacheline_internodealigned_in_smp;
 
@@ -465,7 +459,6 @@ 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 int rcu_print_task_stall(struct rcu_node *rnp);
@@ -488,15 +481,9 @@ static void invoke_rcu_callbacks_kthread(void);
 static bool rcu_is_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 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);
+						 struct rcu_node *rnp);
 #endif /* #ifdef CONFIG_RCU_BOOST */
-static void rcu_cpu_kthread_setrt(int cpu, int to_rt);
 static void __cpuinit rcu_prepare_kthreads(int cpu);
 static void rcu_prepare_for_idle_init(int cpu);
 static void rcu_cleanup_after_idle(int cpu);

kernel/rcutree_trace.c

@@ -107,11 +107,10 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 			rdp->nxttail[RCU_WAIT_TAIL]],
 		   ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]]);
 #ifdef CONFIG_RCU_BOOST
-	seq_printf(m, " kt=%d/%c/%d ktl=%x",
+	seq_printf(m, " kt=%d/%c ktl=%x",
 		   per_cpu(rcu_cpu_has_work, rdp->cpu),
 		   convert_kthread_status(per_cpu(rcu_cpu_kthread_status,
 					  rdp->cpu)),
-		   per_cpu(rcu_cpu_kthread_cpu, rdp->cpu),
 		   per_cpu(rcu_cpu_kthread_loops, rdp->cpu) & 0xffff);
 #endif /* #ifdef CONFIG_RCU_BOOST */
 	seq_printf(m, " b=%ld", rdp->blimit);

kernel/smpboot.c

 /*
  * Common SMP CPU bringup/teardown functions
  */
+#include <linux/cpu.h>
 #include <linux/err.h>
 #include <linux/smp.h>
 #include <linux/init.h>
+#include <linux/list.h>
+#include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/export.h>
 #include <linux/percpu.h>
+#include <linux/kthread.h>
+#include <linux/smpboot.h>
 
 #include "smpboot.h"
 
+#ifdef CONFIG_SMP
+
 #ifdef CONFIG_GENERIC_SMP_IDLE_THREAD
 /*
  * For the hotplug case we keep the task structs around and reuse
@@ -65,3 +73,228 @@ void __init idle_threads_init(void)
 	}
 }
 #endif
+
+#endif /* #ifdef CONFIG_SMP */
+
+static LIST_HEAD(hotplug_threads);
+static DEFINE_MUTEX(smpboot_threads_lock);
+
+struct smpboot_thread_data {
+	unsigned int			cpu;
+	unsigned int			status;
+	struct smp_hotplug_thread	*ht;
+};
+
+enum {
+	HP_THREAD_NONE = 0,
+	HP_THREAD_ACTIVE,
+	HP_THREAD_PARKED,
+};
+
+/**
+ * smpboot_thread_fn - percpu hotplug thread loop function
+ * @data:	thread data pointer
+ *
+ * Checks for thread stop and park conditions. Calls the necessary
+ * setup, cleanup, park and unpark functions for the registered
+ * thread.
+ *
+ * Returns 1 when the thread should exit, 0 otherwise.
+ */
+static int smpboot_thread_fn(void *data)
+{
+	struct smpboot_thread_data *td = data;
+	struct smp_hotplug_thread *ht = td->ht;
+
+	while (1) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		preempt_disable();
+		if (kthread_should_stop()) {
+			set_current_state(TASK_RUNNING);
+			preempt_enable();
+			if (ht->cleanup)
+				ht->cleanup(td->cpu, cpu_online(td->cpu));
+			kfree(td);
+			return 0;
+		}
+
+		if (kthread_should_park()) {
+			__set_current_state(TASK_RUNNING);
+			preempt_enable();
+			if (ht->park && td->status == HP_THREAD_ACTIVE) {
+				BUG_ON(td->cpu != smp_processor_id());
+				ht->park(td->cpu);
+				td->status = HP_THREAD_PARKED;
+			}
+			kthread_parkme();
+			/* We might have been woken for stop */
+			continue;
+		}
+
+		BUG_ON(td->cpu != smp_processor_id());
+
+		/* Check for state change setup */
+		switch (td->status) {
+		case HP_THREAD_NONE:
+			preempt_enable();
+			if (ht->setup)
+				ht->setup(td->cpu);
+			td->status = HP_THREAD_ACTIVE;
+			preempt_disable();
+			break;
+		case HP_THREAD_PARKED:
+			preempt_enable();
+			if (ht->unpark)
+				ht->unpark(td->cpu);
+			td->status = HP_THREAD_ACTIVE;
+			preempt_disable();
+			break;
+		}
+
+		if (!ht->thread_should_run(td->cpu)) {
+			preempt_enable();
+			schedule();
+		} else {
+			set_current_state(TASK_RUNNING);
+			preempt_enable();
+			ht->thread_fn(td->cpu);
+		}
+	}
+}
+
+static int
+__smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu)
+{
+	struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
+	struct smpboot_thread_data *td;
+
+	if (tsk)
+		return 0;
+
+	td = kzalloc_node(sizeof(*td), GFP_KERNEL, cpu_to_node(cpu));
+	if (!td)
+		return -ENOMEM;
+	td->cpu = cpu;
+	td->ht = ht;
+
+	tsk = kthread_create_on_cpu(smpboot_thread_fn, td, cpu,
+				    ht->thread_comm);
+	if (IS_ERR(tsk)) {
+		kfree(td);
+		return PTR_ERR(tsk);
+	}
+
+	get_task_struct(tsk);
+	*per_cpu_ptr(ht->store, cpu) = tsk;
+	return 0;
+}
+
+int smpboot_create_threads(unsigned int cpu)
+{
+	struct smp_hotplug_thread *cur;
+	int ret = 0;
+
+	mutex_lock(&smpboot_threads_lock);
+	list_for_each_entry(cur, &hotplug_threads, list) {
+		ret = __smpboot_create_thread(cur, cpu);
+		if (ret)
+			break;
+	}
+	mutex_unlock(&smpboot_threads_lock);
+	return ret;
+}
+
+static void smpboot_unpark_thread(struct smp_hotplug_thread *ht, unsigned int cpu)
+{
+	struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
+
+	kthread_unpark(tsk);
+}
+
+void smpboot_unpark_threads(unsigned int cpu)
+{
+	struct smp_hotplug_thread *cur;
+
+	mutex_lock(&smpboot_threads_lock);
+	list_for_each_entry(cur, &hotplug_threads, list)
+		smpboot_unpark_thread(cur, cpu);
+	mutex_unlock(&smpboot_threads_lock);
+}
+
+static void smpboot_park_thread(struct smp_hotplug_thread *ht, unsigned int cpu)
+{
+	struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
+
+	if (tsk)
+		kthread_park(tsk);
+}
+
+void smpboot_park_threads(unsigned int cpu)
+{
+	struct smp_hotplug_thread *cur;
+
+	mutex_lock(&smpboot_threads_lock);
+	list_for_each_entry_reverse(cur, &hotplug_threads, list)
+		smpboot_park_thread(cur, cpu);
+	mutex_unlock(&smpboot_threads_lock);
+}
+
+static void smpboot_destroy_threads(struct smp_hotplug_thread *ht)
+{
+	unsigned int cpu;
+
+	/* We need to destroy also the parked threads of offline cpus */
+	for_each_possible_cpu(cpu) {
+		struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
+
+		if (tsk) {
+			kthread_stop(tsk);
+			put_task_struct(tsk);
+			*per_cpu_ptr(ht->store, cpu) = NULL;
+		}
+	}
+}
+
+/**
+ * smpboot_register_percpu_thread - Register a per_cpu thread related to hotplug
+ * @plug_thread:	Hotplug thread descriptor
+ *
+ * Creates and starts the threads on all online cpus.
+ */
+int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread)
+{
+	unsigned int cpu;
+	int ret = 0;
+
+	mutex_lock(&smpboot_threads_lock);
+	for_each_online_cpu(cpu) {
+		ret = __smpboot_create_thread(plug_thread, cpu);
+		if (ret) {
+			smpboot_destroy_threads(plug_thread);
+			goto out;
+		}
+		smpboot_unpark_thread(plug_thread, cpu);
+	}
+	list_add(&plug_thread->list, &hotplug_threads);
+out:
+	mutex_unlock(&smpboot_threads_lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread);
+
+/**
+ * smpboot_unregister_percpu_thread - Unregister a per_cpu thread related to hotplug
+ * @plug_thread:	Hotplug thread descriptor
+ *
+ * Stops all threads on all possible cpus.
+ */
+void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread)
+{
+	get_online_cpus();
+	mutex_lock(&smpboot_threads_lock);
+	list_del(&plug_thread->list);
+	smpboot_destroy_threads(plug_thread);
+	mutex_unlock(&smpboot_threads_lock);
+	put_online_cpus();
+}
+EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread);

kernel/smpboot.h

@@ -13,4 +13,8 @@ static inline void idle_thread_set_boot_cpu(void) { }
 static inline void idle_threads_init(void) { }
 #endif
 
+int smpboot_create_threads(unsigned int cpu);
+void smpboot_park_threads(unsigned int cpu);
+void smpboot_unpark_threads(unsigned int cpu);
+
 #endif

kernel/softirq.c

@@ -23,6 +23,7 @@
 #include <linux/rcupdate.h>
 #include <linux/ftrace.h>
 #include <linux/smp.h>
+#include <linux/smpboot.h>
 #include <linux/tick.h>
 
 #define CREATE_TRACE_POINTS
@@ -742,49 +743,22 @@ void __init softirq_init(void)
 	open_softirq(HI_SOFTIRQ, tasklet_hi_action);
 }
 
-static int run_ksoftirqd(void * __bind_cpu)
+static int ksoftirqd_should_run(unsigned int cpu)
 {
-	set_current_state(TASK_INTERRUPTIBLE);
-
-	while (!kthread_should_stop()) {
-		preempt_disable();
-		if (!local_softirq_pending()) {
-			schedule_preempt_disabled();
-		}
-
-		__set_current_state(TASK_RUNNING);
+	return local_softirq_pending();
+}
 
-		while (local_softirq_pending()) {
-			/* Preempt disable stops cpu going offline.
-			   If already offline, we'll be on wrong CPU:
-			   don't process */
-			if (cpu_is_offline((long)__bind_cpu))
-				goto wait_to_die;
+static void run_ksoftirqd(unsigned int cpu)
+{
 	local_irq_disable();
-			if (local_softirq_pending())
+	if (local_softirq_pending()) {
 		__do_softirq();
+		rcu_note_context_switch(cpu);
 		local_irq_enable();
-			sched_preempt_enable_no_resched();
 		cond_resched();
-			preempt_disable();
-			rcu_note_context_switch((long)__bind_cpu);
-		}
-		preempt_enable();
-		set_current_state(TASK_INTERRUPTIBLE);
-	}
-	__set_current_state(TASK_RUNNING);
-	return 0;
-
-wait_to_die:
-	preempt_enable();
-	/* Wait for kthread_stop */
-	set_current_state(TASK_INTERRUPTIBLE);
-	while (!kthread_should_stop()) {
-		schedule();
-		set_current_state(TASK_INTERRUPTIBLE);
+		return;
 	}
-	__set_current_state(TASK_RUNNING);
-	return 0;
+	local_irq_enable();
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -850,48 +824,12 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb,
 				  unsigned long action,
 				  void *hcpu)
 {
-	int hotcpu = (unsigned long)hcpu;
-	struct task_struct *p;
-
 	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		p = kthread_create_on_node(run_ksoftirqd,
-					   hcpu,
-					   cpu_to_node(hotcpu),
-					   "ksoftirqd/%d", hotcpu);
-		if (IS_ERR(p)) {
-			printk("ksoftirqd for %i failed\n", hotcpu);
-			return notifier_from_errno(PTR_ERR(p));
-		}
-		kthread_bind(p, hotcpu);
-  		per_cpu(ksoftirqd, hotcpu) = p;
- 		break;
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		wake_up_process(per_cpu(ksoftirqd, hotcpu));
-		break;
 #ifdef CONFIG_HOTPLUG_CPU
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-		if (!per_cpu(ksoftirqd, hotcpu))
-			break;
-		/* Unbind so it can run.  Fall thru. */
-		kthread_bind(per_cpu(ksoftirqd, hotcpu),
-			     cpumask_any(cpu_online_mask));
 	case CPU_DEAD:
-	case CPU_DEAD_FROZEN: {
-		static const struct sched_param param = {
-			.sched_priority = MAX_RT_PRIO-1
-		};
-
-		p = per_cpu(ksoftirqd, hotcpu);
-		per_cpu(ksoftirqd, hotcpu) = NULL;
-		sched_setscheduler_nocheck(p, SCHED_FIFO, &param);
-		kthread_stop(p);
-		takeover_tasklets(hotcpu);
+	case CPU_DEAD_FROZEN:
+		takeover_tasklets((unsigned long)hcpu);
 		break;
-	}
 #endif /* CONFIG_HOTPLUG_CPU */
 	}
 	return NOTIFY_OK;
@@ -901,14 +839,19 @@ static struct notifier_block __cpuinitdata cpu_nfb = {
 	.notifier_call = cpu_callback
 };
 
+static struct smp_hotplug_thread softirq_threads = {
+	.store			= &ksoftirqd,
+	.thread_should_run	= ksoftirqd_should_run,
+	.thread_fn		= run_ksoftirqd,
+	.thread_comm		= "ksoftirqd/%u",
+};
+
 static __init int spawn_ksoftirqd(void)
 {
-	void *cpu = (void *)(long)smp_processor_id();
-	int err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
-
-	BUG_ON(err != NOTIFY_OK);
-	cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
 	register_cpu_notifier(&cpu_nfb);
+
+	BUG_ON(smpboot_register_percpu_thread(&softirq_threads));
+
 	return 0;
 }
 early_initcall(spawn_ksoftirqd);

kernel/watchdog.c

@@ -22,6 +22,7 @@
 #include <linux/notifier.h>
 #include <linux/module.h>
 #include <linux/sysctl.h>
+#include <linux/smpboot.h>
 
 #include <asm/irq_regs.h>
 #include <linux/kvm_para.h>
@@ -29,16 +30,18 @@
 
 int watchdog_enabled = 1;
 int __read_mostly watchdog_thresh = 10;
+static int __read_mostly watchdog_disabled;
 
 static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
 static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog);
 static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer);
 static DEFINE_PER_CPU(bool, softlockup_touch_sync);
 static DEFINE_PER_CPU(bool, soft_watchdog_warn);
+static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
+static DEFINE_PER_CPU(unsigned long, soft_lockup_hrtimer_cnt);
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
 static DEFINE_PER_CPU(bool, hard_watchdog_warn);
 static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
-static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
 static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
 static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
 #endif
@@ -248,13 +251,15 @@ static void watchdog_overflow_callback(struct perf_event *event,
 	__this_cpu_write(hard_watchdog_warn, false);
 	return;
 }
+#endif /* CONFIG_HARDLOCKUP_DETECTOR */
+
 static void watchdog_interrupt_count(void)
 {
 	__this_cpu_inc(hrtimer_interrupts);
 }
-#else
-static inline void watchdog_interrupt_count(void) { return; }
-#endif /* CONFIG_HARDLOCKUP_DETECTOR */
+
+static int watchdog_nmi_enable(unsigned int cpu);
+static void watchdog_nmi_disable(unsigned int cpu);
 
 /* watchdog kicker functions */
 static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
@@ -327,49 +332,68 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	return HRTIMER_RESTART;
 }
 
+static void watchdog_set_prio(unsigned int policy, unsigned int prio)
+{
+	struct sched_param param = { .sched_priority = prio };
 
-/*
- * The watchdog thread - touches the timestamp.
- */
-static int watchdog(void *unused)
+	sched_setscheduler(current, policy, &param);
+}
+
+static void watchdog_enable(unsigned int cpu)
 {
-	struct sched_param param = { .sched_priority = 0 };
 	struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer);
 
-	/* initialize timestamp */
-	__touch_watchdog();
+	if (!watchdog_enabled) {
+		kthread_park(current);
+		return;
+	}
+
+	/* Enable the perf event */
+	watchdog_nmi_enable(cpu);
 
 	/* kick off the timer for the hardlockup detector */
+	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer->function = watchdog_timer_fn;
+
 	/* done here because hrtimer_start can only pin to smp_processor_id() */
 	hrtimer_start(hrtimer, ns_to_ktime(get_sample_period()),
 		      HRTIMER_MODE_REL_PINNED);
 
-	set_current_state(TASK_INTERRUPTIBLE);
-	/*
-	 * Run briefly (kicked by the hrtimer callback function) once every
-	 * get_sample_period() seconds (4 seconds by default) to reset the
-	 * softlockup timestamp. If this gets delayed for more than
-	 * 2*watchdog_thresh seconds then the debug-printout triggers in
-	 * watchdog_timer_fn().
-	 */
-	while (!kthread_should_stop()) {
+	/* initialize timestamp */
+	watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1);
 	__touch_watchdog();
-		schedule();
+}
 
-		if (kthread_should_stop())
-			break;
+static void watchdog_disable(unsigned int cpu)
+{
+	struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer);
 
-		set_current_state(TASK_INTERRUPTIBLE);
-	}
-	/*
-	 * Drop the policy/priority elevation during thread exit to avoid a
-	 * scheduling latency spike.
-	 */
-	__set_current_state(TASK_RUNNING);
-	sched_setscheduler(current, SCHED_NORMAL, &param);
-	return 0;
+	watchdog_set_prio(SCHED_NORMAL, 0);
+	hrtimer_cancel(hrtimer);
+	/* disable the perf event */
+	watchdog_nmi_disable(cpu);
 }
 
+static int watchdog_should_run(unsigned int cpu)
+{
+	return __this_cpu_read(hrtimer_interrupts) !=
+		__this_cpu_read(soft_lockup_hrtimer_cnt);
+}
+
+/*
+ * The watchdog thread function - touches the timestamp.
+ *
+ * It only runs once every get_sample_period() seconds (4 seconds by
+ * default) to reset the softlockup timestamp. If this gets delayed
+ * for more than 2*watchdog_thresh seconds then the debug-printout
+ * triggers in watchdog_timer_fn().
+ */
+static void watchdog(unsigned int cpu)
+{
+	__this_cpu_write(soft_lockup_hrtimer_cnt,
+			 __this_cpu_read(hrtimer_interrupts));
+	__touch_watchdog();
+}
 
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
 /*
@@ -379,7 +403,7 @@ static int watchdog(void *unused)
  */
 static unsigned long cpu0_err;
 
-static int watchdog_nmi_enable(int cpu)
+static int watchdog_nmi_enable(unsigned int cpu)
 {
 	struct perf_event_attr *wd_attr;
 	struct perf_event *event = per_cpu(watchdog_ev, cpu);
@@ -433,7 +457,7 @@ static int watchdog_nmi_enable(int cpu)
 	return 0;
 }
 
-static void watchdog_nmi_disable(int cpu)
+static void watchdog_nmi_disable(unsigned int cpu)
 {
 	struct perf_event *event = per_cpu(watchdog_ev, cpu);
 
@@ -447,107 +471,35 @@ static void watchdog_nmi_disable(int cpu)
 	return;
 }
 #else
-static int watchdog_nmi_enable(int cpu) { return 0; }
-static void watchdog_nmi_disable(int cpu) { return; }
+static int watchdog_nmi_enable(unsigned int cpu) { return 0; }
+static void watchdog_nmi_disable(unsigned int cpu) { return; }
 #endif /* CONFIG_HARDLOCKUP_DETECTOR */
 
 /* prepare/enable/disable routines */
-static void watchdog_prepare_cpu(int cpu)
-{
-	struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu);
-
-	WARN_ON(per_cpu(softlockup_watchdog, cpu));
-	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	hrtimer->function = watchdog_timer_fn;
-}
-
-static int watchdog_enable(int cpu)
-{
-	struct task_struct *p = per_cpu(softlockup_watchdog, cpu);
-	int err = 0;
-
-	/* enable the perf event */
-	err = watchdog_nmi_enable(cpu);
-
-	/* Regardless of err above, fall through and start softlockup */
-
-	/* create the watchdog thread */
-	if (!p) {
-		struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
-		p = kthread_create_on_node(watchdog, NULL, cpu_to_node(cpu), "watchdog/%d", cpu);
-		if (IS_ERR(p)) {
-			pr_err("softlockup watchdog for %i failed\n", cpu);
-			if (!err) {
-				/* if hardlockup hasn't already set this */
-				err = PTR_ERR(p);
-				/* and disable the perf event */
-				watchdog_nmi_disable(cpu);
-			}
-			goto out;
-		}
-		sched_setscheduler(p, SCHED_FIFO, &param);
-		kthread_bind(p, cpu);
-		per_cpu(watchdog_touch_ts, cpu) = 0;
-		per_cpu(softlockup_watchdog, cpu) = p;
-		wake_up_process(p);
-	}
-
-out:
-	return err;
-}
-
-static void watchdog_disable(int cpu)
-{
-	struct task_struct *p = per_cpu(softlockup_watchdog, cpu);
-	struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu);
-
-	/*
-	 * cancel the timer first to stop incrementing the stats
-	 * and waking up the kthread
-	 */
-	hrtimer_cancel(hrtimer);
-
-	/* disable the perf event */
-	watchdog_nmi_disable(cpu);
-
-	/* stop the watchdog thread */
-	if (p) {
-		per_cpu(softlockup_watchdog, cpu) = NULL;
-		kthread_stop(p);
-	}
-}
-
 /* sysctl functions */
 #ifdef CONFIG_SYSCTL
 static void watchdog_enable_all_cpus(void)
 {
-	int cpu;
-
-	watchdog_enabled = 0;
+	unsigned int cpu;
 
+	if (watchdog_disabled) {
+		watchdog_disabled = 0;
 		for_each_online_cpu(cpu)
-		if (!watchdog_enable(cpu))
-			/* if any cpu succeeds, watchdog is considered
-			   enabled for the system */
-			watchdog_enabled = 1;
-
-	if (!watchdog_enabled)
-		pr_err("failed to be enabled on some cpus\n");
-
+			kthread_unpark(per_cpu(softlockup_watchdog, cpu));
+	}
 }
 
 static void watchdog_disable_all_cpus(void)
 {
-	int cpu;
+	unsigned int cpu;
 
+	if (!watchdog_disabled) {
+		watchdog_disabled = 1;
 		for_each_online_cpu(cpu)
-		watchdog_disable(cpu);
-
-	/* if all watchdogs are disabled, then they are disabled for the system */
-	watchdog_enabled = 0;
+			kthread_park(per_cpu(softlockup_watchdog, cpu));
+	}
 }
 
-
 /*
  * proc handler for /proc/sys/kernel/nmi_watchdog,watchdog_thresh
  */
@@ -557,73 +509,36 @@ int proc_dowatchdog(struct ctl_table *table, int write,
 {
 	int ret;
 
+	if (watchdog_disabled < 0)
+		return -ENODEV;
+
 	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (ret || !write)
-		goto out;
+		return ret;
 
 	if (watchdog_enabled && watchdog_thresh)
 		watchdog_enable_all_cpus();
 	else
 		watchdog_disable_all_cpus();
 
-out:
 	return ret;
 }
 #endif /* CONFIG_SYSCTL */
 
-
-/*
- * Create/destroy watchdog threads as CPUs come and go:
- */
-static int __cpuinit
-cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
-{
-	int hotcpu = (unsigned long)hcpu;
-
-	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		watchdog_prepare_cpu(hotcpu);
-		break;
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		if (watchdog_enabled)
-			watchdog_enable(hotcpu);
-		break;
-#ifdef CONFIG_HOTPLUG_CPU
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-		watchdog_disable(hotcpu);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		watchdog_disable(hotcpu);
-		break;
-#endif /* CONFIG_HOTPLUG_CPU */
-	}
-
-	/*
-	 * hardlockup and softlockup are not important enough
-	 * to block cpu bring up.  Just always succeed and
-	 * rely on printk output to flag problems.
-	 */
-	return NOTIFY_OK;
-}
-
-static struct notifier_block __cpuinitdata cpu_nfb = {
-	.notifier_call = cpu_callback
+static struct smp_hotplug_thread watchdog_threads = {
+	.store			= &softlockup_watchdog,
+	.thread_should_run	= watchdog_should_run,
+	.thread_fn		= watchdog,
+	.thread_comm		= "watchdog/%u",
+	.setup			= watchdog_enable,
+	.park			= watchdog_disable,
+	.unpark			= watchdog_enable,
 };
 
 void __init lockup_detector_init(void)
 {
-	void *cpu = (void *)(long)smp_processor_id();
-	int err;
-
-	err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
-	WARN_ON(notifier_to_errno(err));
-
-	cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
-	register_cpu_notifier(&cpu_nfb);
-
-	return;
+	if (smpboot_register_percpu_thread(&watchdog_threads)) {
+		pr_err("Failed to create watchdog threads, disabled\n");
+		watchdog_disabled = -ENODEV;
+	}
 }