Merge branch 'cpu_stop' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/misc into sched/core

13 files changed, 604 insertions, 439 deletions

diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt
index 0e50bc2aa1e..5d9016795fd 100644
--- a/Documentation/RCU/torture.txt
+++ b/Documentation/RCU/torture.txt
@@ -182,16 +182,6 @@ Similarly, sched_expedited RCU provides the following:
 	sched_expedited-torture: Reader Pipe:  12660320201 95875 0 0 0 0 0 0 0 0 0
 	sched_expedited-torture: Reader Batch:  12660424885 0 0 0 0 0 0 0 0 0 0
 	sched_expedited-torture: Free-Block Circulation:  1090795 1090795 1090794 1090793 1090792 1090791 1090790 1090789 1090788 1090787 0
-	state: -1 / 0:0 3:0 4:0
-
-As before, the first four lines are similar to those for RCU.
-The last line shows the task-migration state.  The first number is
--1 if synchronize_sched_expedited() is idle, -2 if in the process of
-posting wakeups to the migration kthreads, and N when waiting on CPU N.
-Each of the colon-separated fields following the "/" is a CPU:state pair.
-Valid states are "0" for idle, "1" for waiting for quiescent state,
-"2" for passed through quiescent state, and "3" when a race with a
-CPU-hotplug event forces use of the synchronize_sched() primitive.
 
 
 USAGE
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index d906bf19c14..a2163c95eb9 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -391,7 +391,6 @@ static void __init time_init_wq(void)
 	if (time_sync_wq)
 		return;
 	time_sync_wq = create_singlethread_workqueue("timesync");
-	stop_machine_create();
 }
 
 /*
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index 2ac4440e7b0..8943b8ccee1 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -80,12 +80,6 @@ static void do_suspend(void)
 
 	shutting_down = SHUTDOWN_SUSPEND;
 
-	err = stop_machine_create();
-	if (err) {
-		printk(KERN_ERR "xen suspend: failed to setup stop_machine %d\n", err);
-		goto out;
-	}
-
 #ifdef CONFIG_PREEMPT
 	/* If the kernel is preemptible, we need to freeze all the processes
 	   to prevent them from being in the middle of a pagetable update
@@ -93,7 +87,7 @@ static void do_suspend(void)
 	err = freeze_processes();
 	if (err) {
 		printk(KERN_ERR "xen suspend: freeze failed %d\n", err);
-		goto out_destroy_sm;
+		goto out;
 	}
 #endif
 
@@ -136,12 +130,8 @@ out_resume:
 out_thaw:
 #ifdef CONFIG_PREEMPT
 	thaw_processes();
-
-out_destroy_sm:
-#endif
-	stop_machine_destroy();
-
 out:
+#endif
 	shutting_down = SHUTDOWN_INVALID;
 }
 #endif	/* CONFIG_PM_SLEEP */
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index a5195875480..0006b2df00e 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -60,8 +60,6 @@ static inline long rcu_batches_completed_bh(void)
 	return 0;
 }
 
-extern int rcu_expedited_torture_stats(char *page);
-
 static inline void rcu_force_quiescent_state(void)
 {
 }
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 42cc3a04779..24e467e526b 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -35,7 +35,6 @@ struct notifier_block;
 extern void rcu_sched_qs(int cpu);
 extern void rcu_bh_qs(int cpu);
 extern int rcu_needs_cpu(int cpu);
-extern int rcu_expedited_torture_stats(char *page);
 
 #ifdef CONFIG_TREE_PREEMPT_RCU
 
diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index baba3a23a81..6b524a0d02e 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -1,13 +1,101 @@
 #ifndef _LINUX_STOP_MACHINE
 #define _LINUX_STOP_MACHINE
-/* "Bogolock": stop the entire machine, disable interrupts.  This is a
-   very heavy lock, which is equivalent to grabbing every spinlock
-   (and more).  So the "read" side to such a lock is anything which
-   disables preeempt. */
+
 #include <linux/cpu.h>
 #include <linux/cpumask.h>
+#include <linux/list.h>
 #include <asm/system.h>
 
+/*
+ * stop_cpu[s]() is simplistic per-cpu maximum priority cpu
+ * monopolization mechanism.  The caller can specify a non-sleeping
+ * function to be executed on a single or multiple cpus preempting all
+ * other processes and monopolizing those cpus until it finishes.
+ *
+ * Resources for this mechanism are preallocated when a cpu is brought
+ * up and requests are guaranteed to be served as long as the target
+ * cpus are online.
+ */
+typedef int (*cpu_stop_fn_t)(void *arg);
+
+#ifdef CONFIG_SMP
+
+struct cpu_stop_work {
+	struct list_head	list;		/* cpu_stopper->works */
+	cpu_stop_fn_t		fn;
+	void			*arg;
+	struct cpu_stop_done	*done;
+};
+
+int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg);
+void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
+			 struct cpu_stop_work *work_buf);
+int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg);
+int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg);
+
+#else	/* CONFIG_SMP */
+
+#include <linux/workqueue.h>
+
+struct cpu_stop_work {
+	struct work_struct	work;
+	cpu_stop_fn_t		fn;
+	void			*arg;
+};
+
+static inline int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
+{
+	int ret = -ENOENT;
+	preempt_disable();
+	if (cpu == smp_processor_id())
+		ret = fn(arg);
+	preempt_enable();
+	return ret;
+}
+
+static void stop_one_cpu_nowait_workfn(struct work_struct *work)
+{
+	struct cpu_stop_work *stwork =
+		container_of(work, struct cpu_stop_work, work);
+	preempt_disable();
+	stwork->fn(stwork->arg);
+	preempt_enable();
+}
+
+static inline void stop_one_cpu_nowait(unsigned int cpu,
+				       cpu_stop_fn_t fn, void *arg,
+				       struct cpu_stop_work *work_buf)
+{
+	if (cpu == smp_processor_id()) {
+		INIT_WORK(&work_buf->work, stop_one_cpu_nowait_workfn);
+		work_buf->fn = fn;
+		work_buf->arg = arg;
+		schedule_work(&work_buf->work);
+	}
+}
+
+static inline int stop_cpus(const struct cpumask *cpumask,
+			    cpu_stop_fn_t fn, void *arg)
+{
+	if (cpumask_test_cpu(raw_smp_processor_id(), cpumask))
+		return stop_one_cpu(raw_smp_processor_id(), fn, arg);
+	return -ENOENT;
+}
+
+static inline int try_stop_cpus(const struct cpumask *cpumask,
+				cpu_stop_fn_t fn, void *arg)
+{
+	return stop_cpus(cpumask, fn, arg);
+}
+
+#endif	/* CONFIG_SMP */
+
+/*
+ * stop_machine "Bogolock": stop the entire machine, disable
+ * interrupts.  This is a very heavy lock, which is equivalent to
+ * grabbing every spinlock (and more).  So the "read" side to such a
+ * lock is anything which disables preeempt.
+ */
 #if defined(CONFIG_STOP_MACHINE) && defined(CONFIG_SMP)
 
 /**
@@ -36,24 +124,7 @@ int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus);
  */
 int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus);
 
-/**
- * stop_machine_create: create all stop_machine threads
- *
- * Description: This causes all stop_machine threads to be created before
- * stop_machine actually gets called. This can be used by subsystems that
- * need a non failing stop_machine infrastructure.
- */
-int stop_machine_create(void);
-
-/**
- * stop_machine_destroy: destroy all stop_machine threads
- *
- * Description: This causes all stop_machine threads which were created with
- * stop_machine_create to be destroyed again.
- */
-void stop_machine_destroy(void);
-
-#else
+#else	 /* CONFIG_STOP_MACHINE && CONFIG_SMP */
 
 static inline int stop_machine(int (*fn)(void *), void *data,
 			       const struct cpumask *cpus)
@@ -65,8 +136,5 @@ static inline int stop_machine(int (*fn)(void *), void *data,
 	return ret;
 }
 
-static inline int stop_machine_create(void) { return 0; }
-static inline void stop_machine_destroy(void) { }
-
-#endif /* CONFIG_SMP */
-#endif /* _LINUX_STOP_MACHINE */
+#endif	/* CONFIG_STOP_MACHINE && CONFIG_SMP */
+#endif	/* _LINUX_STOP_MACHINE */
diff --git a/kernel/Makefile b/kernel/Makefile
index a987aa1676b..149e18ef1ab 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -68,7 +68,7 @@ obj-$(CONFIG_USER_NS) += user_namespace.o
 obj-$(CONFIG_PID_NS) += pid_namespace.o
 obj-$(CONFIG_IKCONFIG) += configs.o
 obj-$(CONFIG_RESOURCE_COUNTERS) += res_counter.o
-obj-$(CONFIG_STOP_MACHINE) += stop_machine.o
+obj-$(CONFIG_SMP) += stop_machine.o
 obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o
 obj-$(CONFIG_AUDIT) += audit.o auditfilter.o audit_watch.o
 obj-$(CONFIG_AUDITSYSCALL) += auditsc.o
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 914aedcde84..54577757477 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -266,9 +266,6 @@ int __ref cpu_down(unsigned int cpu)
 {
 	int err;
 
-	err = stop_machine_create();
-	if (err)
-		return err;
 	cpu_maps_update_begin();
 
 	if (cpu_hotplug_disabled) {
@@ -280,7 +277,6 @@ int __ref cpu_down(unsigned int cpu)
 
 out:
 	cpu_maps_update_done();
-	stop_machine_destroy();
 	return err;
 }
 EXPORT_SYMBOL(cpu_down);
@@ -361,9 +357,6 @@ int disable_nonboot_cpus(void)
 {
 	int cpu, first_cpu, error;
 
-	error = stop_machine_create();
-	if (error)
-		return error;
 	cpu_maps_update_begin();
 	first_cpu = cpumask_first(cpu_online_mask);
 	/*
@@ -394,7 +387,6 @@ int disable_nonboot_cpus(void)
 		printk(KERN_ERR "Non-boot CPUs are not disabled\n");
 	}
 	cpu_maps_update_done();
-	stop_machine_destroy();
 	return error;
 }
 
diff --git a/kernel/module.c b/kernel/module.c
index 1016b75b026..0838246d8c9 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -723,16 +723,8 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 		return -EFAULT;
 	name[MODULE_NAME_LEN-1] = '\0';
 
-	/* Create stop_machine threads since free_module relies on
-	 * a non-failing stop_machine call. */
-	ret = stop_machine_create();
-	if (ret)
-		return ret;
-
-	if (mutex_lock_interruptible(&module_mutex) != 0) {
-		ret = -EINTR;
-		goto out_stop;
-	}
+	if (mutex_lock_interruptible(&module_mutex) != 0)
+		return -EINTR;
 
 	mod = find_module(name);
 	if (!mod) {
@@ -792,8 +784,6 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 
  out:
 	mutex_unlock(&module_mutex);
-out_stop:
-	stop_machine_destroy();
 	return ret;
 }
 
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 58df55bf83e..2b676f3a0f2 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -669,7 +669,7 @@ static struct rcu_torture_ops sched_expedited_ops = {
 	.sync		= synchronize_sched_expedited,
 	.cb_barrier	= NULL,
 	.fqs		= rcu_sched_force_quiescent_state,
-	.stats		= rcu_expedited_torture_stats,
+	.stats		= NULL,
 	.irq_capable	= 1,
 	.name		= "sched_expedited"
 };
diff --git a/kernel/sched.c b/kernel/sched.c
index 11ac0eb0bce..39aa9c7e22c 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -55,9 +55,9 @@
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
 #include <linux/percpu.h>
-#include <linux/kthread.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/stop_machine.h>
 #include <linux/sysctl.h>
 #include <linux/syscalls.h>
 #include <linux/times.h>
@@ -539,15 +539,13 @@ struct rq {
 	int post_schedule;
 	int active_balance;
 	int push_cpu;
+	struct cpu_stop_work active_balance_work;
 	/* cpu of this runqueue: */
 	int cpu;
 	int online;
 
 	unsigned long avg_load_per_task;
 
-	struct task_struct *migration_thread;
-	struct list_head migration_queue;
-
 	u64 rt_avg;
 	u64 age_stamp;
 	u64 idle_stamp;
@@ -2037,21 +2035,18 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	__set_task_cpu(p, new_cpu);
 }
 
-struct migration_req {
-	struct list_head list;
-
+struct migration_arg {
 	struct task_struct *task;
 	int dest_cpu;
-
-	struct completion done;
 };
 
+static int migration_cpu_stop(void *data);
+
 /*
  * The task's runqueue lock must be held.
  * Returns true if you have to wait for migration thread.
  */
-static int
-migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
+static bool migrate_task(struct task_struct *p, int dest_cpu)
 {
 	struct rq *rq = task_rq(p);
 
@@ -2059,15 +2054,7 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
 	 * If the task is not on a runqueue (and not running), then
 	 * the next wake-up will properly place the task.
 	 */
-	if (!p->se.on_rq && !task_running(rq, p))
-		return 0;
-
-	init_completion(&req->done);
-	req->task = p;
-	req->dest_cpu = dest_cpu;
-	list_add(&req->list, &rq->migration_queue);
-
-	return 1;
+	return p->se.on_rq || task_running(rq, p);
 }
 
 /*
@@ -3110,7 +3097,6 @@ static void update_cpu_load(struct rq *this_rq)
 void sched_exec(void)
 {
 	struct task_struct *p = current;
-	struct migration_req req;
 	unsigned long flags;
 	struct rq *rq;
 	int dest_cpu;
@@ -3124,17 +3110,11 @@ void sched_exec(void)
 	 * select_task_rq() can race against ->cpus_allowed
 	 */
 	if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) &&
-	    likely(cpu_active(dest_cpu)) &&
-	    migrate_task(p, dest_cpu, &req)) {
-		/* Need to wait for migration thread (might exit: take ref). */
-		struct task_struct *mt = rq->migration_thread;
+	    likely(cpu_active(dest_cpu)) && migrate_task(p, dest_cpu)) {
+		struct migration_arg arg = { p, dest_cpu };
 
-		get_task_struct(mt);
 		task_rq_unlock(rq, &flags);
-		wake_up_process(mt);
-		put_task_struct(mt);
-		wait_for_completion(&req.done);
-
+		stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
 		return;
 	}
 unlock:
@@ -5290,17 +5270,15 @@ static inline void sched_init_granularity(void)
 /*
  * This is how migration works:
  *
- * 1) we queue a struct migration_req structure in the source CPU's
- *    runqueue and wake up that CPU's migration thread.
- * 2) we down() the locked semaphore => thread blocks.
- * 3) migration thread wakes up (implicitly it forces the migrated
- *    thread off the CPU)
- * 4) it gets the migration request and checks whether the migrated
- *    task is still in the wrong runqueue.
- * 5) if it's in the wrong runqueue then the migration thread removes
+ * 1) we invoke migration_cpu_stop() on the target CPU using
+ *    stop_one_cpu().
+ * 2) stopper starts to run (implicitly forcing the migrated thread
+ *    off the CPU)
+ * 3) it checks whether the migrated task is still in the wrong runqueue.
+ * 4) if it's in the wrong runqueue then the migration thread removes
  *    it and puts it into the right queue.
- * 6) migration thread up()s the semaphore.
- * 7) we wake up and the migration is done.
+ * 5) stopper completes and stop_one_cpu() returns and the migration
+ *    is done.
  */
 
 /*
@@ -5314,9 +5292,9 @@ static inline void sched_init_granularity(void)
  */
 int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 {
-	struct migration_req req;
 	unsigned long flags;
 	struct rq *rq;
+	unsigned int dest_cpu;
 	int ret = 0;
 
 	/*
@@ -5354,15 +5332,12 @@ again:
 	if (cpumask_test_cpu(task_cpu(p), new_mask))
 		goto out;
 
-	if (migrate_task(p, cpumask_any_and(cpu_active_mask, new_mask), &req)) {
+	dest_cpu = cpumask_any_and(cpu_active_mask, new_mask);
+	if (migrate_task(p, dest_cpu)) {
+		struct migration_arg arg = { p, dest_cpu };
 		/* Need help from migration thread: drop lock and wait. */
-		struct task_struct *mt = rq->migration_thread;
-
-		get_task_struct(mt);
 		task_rq_unlock(rq, &flags);
-		wake_up_process(mt);
-		put_task_struct(mt);
-		wait_for_completion(&req.done);
+		stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
 		tlb_migrate_finish(p->mm);
 		return 0;
 	}
@@ -5420,70 +5395,22 @@ fail:
 	return ret;
 }
 
-#define RCU_MIGRATION_IDLE	0
-#define RCU_MIGRATION_NEED_QS	1
-#define RCU_MIGRATION_GOT_QS	2
-#define RCU_MIGRATION_MUST_SYNC	3
-
 /*
- * migration_thread - this is a highprio system thread that performs
- * thread migration by bumping thread off CPU then 'pushing' onto
- * another runqueue.
+ * migration_cpu_stop - this will be executed by a highprio stopper thread
+ * and performs thread migration by bumping thread off CPU then
+ * 'pushing' onto another runqueue.
  */
-static int migration_thread(void *data)
+static int migration_cpu_stop(void *data)
 {
-	int badcpu;
-	int cpu = (long)data;
-	struct rq *rq;
-
-	rq = cpu_rq(cpu);
-	BUG_ON(rq->migration_thread != current);
-
-	set_current_state(TASK_INTERRUPTIBLE);
-	while (!kthread_should_stop()) {
-		struct migration_req *req;
-		struct list_head *head;
-
-		raw_spin_lock_irq(&rq->lock);
-
-		if (cpu_is_offline(cpu)) {
-			raw_spin_unlock_irq(&rq->lock);
-			break;
-		}
-
-		if (rq->active_balance) {
-			active_load_balance(rq, cpu);
-			rq->active_balance = 0;
-		}
-
-		head = &rq->migration_queue;
-
-		if (list_empty(head)) {
-			raw_spin_unlock_irq(&rq->lock);
-			schedule();
-			set_current_state(TASK_INTERRUPTIBLE);
-			continue;
-		}
-		req = list_entry(head->next, struct migration_req, list);
-		list_del_init(head->next);
-
-		if (req->task != NULL) {
-			raw_spin_unlock(&rq->lock);
-			__migrate_task(req->task, cpu, req->dest_cpu);
-		} else if (likely(cpu == (badcpu = smp_processor_id()))) {
-			req->dest_cpu = RCU_MIGRATION_GOT_QS;
-			raw_spin_unlock(&rq->lock);
-		} else {
-			req->dest_cpu = RCU_MIGRATION_MUST_SYNC;
-			raw_spin_unlock(&rq->lock);
-			WARN_ONCE(1, "migration_thread() on CPU %d, expected %d\n", badcpu, cpu);
-		}
-		local_irq_enable();
-
-		complete(&req->done);
-	}
-	__set_current_state(TASK_RUNNING);
+	struct migration_arg *arg = data;
 
+	/*
+	 * The original target cpu might have gone down and we might
+	 * be on another cpu but it doesn't matter.
+	 */
+	local_irq_disable();
+	__migrate_task(arg->task, raw_smp_processor_id(), arg->dest_cpu);
+	local_irq_enable();
 	return 0;
 }
 
@@ -5850,35 +5777,20 @@ static void set_rq_offline(struct rq *rq)
 static int __cpuinit
 migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
-	struct task_struct *p;
 	int cpu = (long)hcpu;
 	unsigned long flags;
-	struct rq *rq;
+	struct rq *rq = cpu_rq(cpu);
 
 	switch (action) {
 
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		p = kthread_create(migration_thread, hcpu, "migration/%d", cpu);
-		if (IS_ERR(p))
-			return NOTIFY_BAD;
-		kthread_bind(p, cpu);
-		/* Must be high prio: stop_machine expects to yield to it. */
-		rq = task_rq_lock(p, &flags);
-		__setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
-		task_rq_unlock(rq, &flags);
-		get_task_struct(p);
-		cpu_rq(cpu)->migration_thread = p;
 		rq->calc_load_update = calc_load_update;
 		break;
 
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
-		/* Strictly unnecessary, as first user will wake it. */
-		wake_up_process(cpu_rq(cpu)->migration_thread);
-
 		/* Update our root-domain */
-		rq = cpu_rq(cpu);
 		raw_spin_lock_irqsave(&rq->lock, flags);
 		if (rq->rd) {
 			BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
@@ -5889,25 +5801,9 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		break;
 
 #ifdef CONFIG_HOTPLUG_CPU
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-		if (!cpu_rq(cpu)->migration_thread)
-			break;
-		/* Unbind it from offline cpu so it can run. Fall thru. */
-		kthread_bind(cpu_rq(cpu)->migration_thread,
-			     cpumask_any(cpu_online_mask));
-		kthread_stop(cpu_rq(cpu)->migration_thread);
-		put_task_struct(cpu_rq(cpu)->migration_thread);
-		cpu_rq(cpu)->migration_thread = NULL;
-		break;
-
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 		migrate_live_tasks(cpu);
-		rq = cpu_rq(cpu);
-		kthread_stop(rq->migration_thread);
-		put_task_struct(rq->migration_thread);
-		rq->migration_thread = NULL;
 		/* Idle task back to normal (off runqueue, low prio) */
 		raw_spin_lock_irq(&rq->lock);
 		deactivate_task(rq, rq->idle, 0);
@@ -5918,29 +5814,11 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		migrate_nr_uninterruptible(rq);
 		BUG_ON(rq->nr_running != 0);
 		calc_global_load_remove(rq);
-		/*
-		 * No need to migrate the tasks: it was best-effort if
-		 * they didn't take sched_hotcpu_mutex. Just wake up
-		 * the requestors.
-		 */
-		raw_spin_lock_irq(&rq->lock);
-		while (!list_empty(&rq->migration_queue)) {
-			struct migration_req *req;
-
-			req = list_entry(rq->migration_queue.next,
-					 struct migration_req, list);
-			list_del_init(&req->list);
-			raw_spin_unlock_irq(&rq->lock);
-			complete(&req->done);
-			raw_spin_lock_irq(&rq->lock);
-		}
-		raw_spin_unlock_irq(&rq->lock);
 		break;
 
 	case CPU_DYING:
 	case CPU_DYING_FROZEN:
 		/* Update our root-domain */
-		rq = cpu_rq(cpu);
 		raw_spin_lock_irqsave(&rq->lock, flags);
 		if (rq->rd) {
 			BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
@@ -7757,10 +7635,8 @@ void __init sched_init(void)
 		rq->push_cpu = 0;
 		rq->cpu = i;
 		rq->online = 0;
-		rq->migration_thread = NULL;
 		rq->idle_stamp = 0;
 		rq->avg_idle = 2*sysctl_sched_migration_cost;
-		INIT_LIST_HEAD(&rq->migration_queue);
 		rq_attach_root(rq, &def_root_domain);
 #endif
 		init_rq_hrtick(rq);
@@ -9054,43 +8930,32 @@ struct cgroup_subsys cpuacct_subsys = {
 
 #ifndef CONFIG_SMP
 
-int rcu_expedited_torture_stats(char *page)
-{
-	return 0;
-}
-EXPORT_SYMBOL_GPL(rcu_expedited_torture_stats);
-
 void synchronize_sched_expedited(void)
 {
+	barrier();
 }
 EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
 
 #else /* #ifndef CONFIG_SMP */
 
-static DEFINE_PER_CPU(struct migration_req, rcu_migration_req);
-static DEFINE_MUTEX(rcu_sched_expedited_mutex);
-
-#define RCU_EXPEDITED_STATE_POST -2
-#define RCU_EXPEDITED_STATE_IDLE -1
-
-static int rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE;
+static atomic_t synchronize_sched_expedited_count = ATOMIC_INIT(0);
 
-int rcu_expedited_torture_stats(char *page)
+static int synchronize_sched_expedited_cpu_stop(void *data)
 {
-	int cnt = 0;
-	int cpu;
-
-	cnt += sprintf(&page[cnt], "state: %d /", rcu_expedited_state);
-	for_each_online_cpu(cpu) {
-		 cnt += sprintf(&page[cnt], " %d:%d",
-				cpu, per_cpu(rcu_migration_req, cpu).dest_cpu);
-	}
-	cnt += sprintf(&page[cnt], "\n");
-	return cnt;
+	/*
+	 * There must be a full memory barrier on each affected CPU
+	 * between the time that try_stop_cpus() is called and the
+	 * time that it returns.
+	 *
+	 * In the current initial implementation of cpu_stop, the
+	 * above condition is already met when the control reaches
+	 * this point and the following smp_mb() is not strictly
+	 * necessary.  Do smp_mb() anyway for documentation and
+	 * robustness against future implementation changes.
+	 */
+	smp_mb(); /* See above comment block. */
+	return 0;
 }
-EXPORT_SYMBOL_GPL(rcu_expedited_torture_stats);
-
-static long synchronize_sched_expedited_count;
 
 /*
  * Wait for an rcu-sched grace period to elapse, but use "big hammer"
@@ -9104,18 +8969,14 @@ static long synchronize_sched_expedited_count;
  */
 void synchronize_sched_expedited(void)
 {
-	int cpu;
-	unsigned long flags;
-	bool need_full_sync = 0;
-	struct rq *rq;
-	struct migration_req *req;
-	long snap;
-	int trycount = 0;
+	int snap, trycount = 0;
 
 	smp_mb();  /* ensure prior mod happens before capturing snap. */
-	snap = ACCESS_ONCE(synchronize_sched_expedited_count) + 1;
+	snap = atomic_read(&synchronize_sched_expedited_count) + 1;
 	get_online_cpus();
-	while (!mutex_trylock(&rcu_sched_expedited_mutex)) {
+	while (try_stop_cpus(cpu_online_mask,
+			     synchronize_sched_expedited_cpu_stop,
+			     NULL) == -EAGAIN) {
 		put_online_cpus();
 		if (trycount++ < 10)
 			udelay(trycount * num_online_cpus());
@@ -9123,41 +8984,15 @@ void synchronize_sched_expedited(void)
 			synchronize_sched();
 			return;
 		}
-		if (ACCESS_ONCE(synchronize_sched_expedited_count) - snap > 0) {
+		if (atomic_read(&synchronize_sched_expedited_count) - snap > 0) {
 			smp_mb(); /* ensure test happens before caller kfree */
 			return;
 		}
 		get_online_cpus();
 	}
-	rcu_expedited_state = RCU_EXPEDITED_STATE_POST;
-	for_each_online_cpu(cpu) {
-		rq = cpu_rq(cpu);
-		req = &per_cpu(rcu_migration_req, cpu);
-		init_completion(&req->done);
-		req->task = NULL;
-		req->dest_cpu = RCU_MIGRATION_NEED_QS;
-		raw_spin_lock_irqsave(&rq->lock, flags);
-		list_add(&req->list, &rq->migration_queue);
-		raw_spin_unlock_irqrestore(&rq->lock, flags);
-		wake_up_process(rq->migration_thread);
-	}
-	for_each_online_cpu(cpu) {
-		rcu_expedited_state = cpu;
-		req = &per_cpu(rcu_migration_req, cpu);
-		rq = cpu_rq(cpu);
-		wait_for_completion(&req->done);
-		raw_spin_lock_irqsave(&rq->lock, flags);
-		if (unlikely(req->dest_cpu == RCU_MIGRATION_MUST_SYNC))
-			need_full_sync = 1;
-		req->dest_cpu = RCU_MIGRATION_IDLE;
-		raw_spin_unlock_irqrestore(&rq->lock, flags);
-	}
-	rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE;
-	synchronize_sched_expedited_count++;
-	mutex_unlock(&rcu_sched_expedited_mutex);
+	atomic_inc(&synchronize_sched_expedited_count);
+	smp_mb__after_atomic_inc(); /* ensure post-GP actions seen after GP. */
 	put_online_cpus();
-	if (need_full_sync)
-		synchronize_sched();
 }
 EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
 
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index cbd8b8a296d..217e4a9393e 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -2798,6 +2798,8 @@ static int need_active_balance(struct sched_domain *sd, int sd_idle, int idle)
 	return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2);
 }
 
+static int active_load_balance_cpu_stop(void *data);
+
 /*
  * Check this_cpu to ensure it is balanced within domain. Attempt to move
  * tasks if there is an imbalance.
@@ -2887,8 +2889,9 @@ redo:
 		if (need_active_balance(sd, sd_idle, idle)) {
 			raw_spin_lock_irqsave(&busiest->lock, flags);
 
-			/* don't kick the migration_thread, if the curr
-			 * task on busiest cpu can't be moved to this_cpu
+			/* don't kick the active_load_balance_cpu_stop,
+			 * if the curr task on busiest cpu can't be
+			 * moved to this_cpu
 			 */
 			if (!cpumask_test_cpu(this_cpu,
 					      &busiest->curr->cpus_allowed)) {
@@ -2898,14 +2901,22 @@ redo:
 				goto out_one_pinned;
 			}
 
+			/*
+			 * ->active_balance synchronizes accesses to
+			 * ->active_balance_work.  Once set, it's cleared
+			 * only after active load balance is finished.
+			 */
 			if (!busiest->active_balance) {
 				busiest->active_balance = 1;
 				busiest->push_cpu = this_cpu;
 				active_balance = 1;
 			}
 			raw_spin_unlock_irqrestore(&busiest->lock, flags);
+
 			if (active_balance)
-				wake_up_process(busiest->migration_thread);
+				stop_one_cpu_nowait(cpu_of(busiest),
+					active_load_balance_cpu_stop, busiest,
+					&busiest->active_balance_work);
 
 			/*
 			 * We've kicked active balancing, reset the failure
@@ -3012,24 +3023,29 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 }
 
 /*
- * active_load_balance is run by migration threads. It pushes running tasks
- * off the busiest CPU onto idle CPUs. It requires at least 1 task to be
- * running on each physical CPU where possible, and avoids physical /
- * logical imbalances.
- *
- * Called with busiest_rq locked.
+ * active_load_balance_cpu_stop is run by cpu stopper. It pushes
+ * running tasks off the busiest CPU onto idle CPUs. It requires at
+ * least 1 task to be running on each physical CPU where possible, and
+ * avoids physical / logical imbalances.
  */
-static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
+static int active_load_balance_cpu_stop(void *data)
 {
+	struct rq *busiest_rq = data;
+	int busiest_cpu = cpu_of(busiest_rq);
 	int target_cpu = busiest_rq->push_cpu;
+	struct rq *target_rq = cpu_rq(target_cpu);
 	struct sched_domain *sd;
-	struct rq *target_rq;
+
+	raw_spin_lock_irq(&busiest_rq->lock);
+
+	/* make sure the requested cpu hasn't gone down in the meantime */
+	if (unlikely(busiest_cpu != smp_processor_id() ||
+		     !busiest_rq->active_balance))
+		goto out_unlock;
 
 	/* Is there any task to move? */
 	if (busiest_rq->nr_running <= 1)
-		return;
-
-	target_rq = cpu_rq(target_cpu);
+		goto out_unlock;
 
 	/*
 	 * This condition is "impossible", if it occurs
@@ -3058,6 +3074,10 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
 			schedstat_inc(sd, alb_failed);
 	}
 	double_unlock_balance(busiest_rq, target_rq);
+out_unlock:
+	busiest_rq->active_balance = 0;
+	raw_spin_unlock_irq(&busiest_rq->lock);
+	return 0;
 }
 
 #ifdef CONFIG_NO_HZ
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 9bb9fb1bd79..ef51d1fcf5e 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -1,17 +1,381 @@
-/* Copyright 2008, 2005 Rusty Russell rusty@rustcorp.com.au IBM Corporation.
- * GPL v2 and any later version.
+/*
+ * kernel/stop_machine.c
+ *
+ * Copyright (C) 2008, 2005	IBM Corporation.
+ * Copyright (C) 2008, 2005	Rusty Russell rusty@rustcorp.com.au
+ * Copyright (C) 2010		SUSE Linux Products GmbH
+ * Copyright (C) 2010		Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2 and any later version.
  */
+#include <linux/completion.h>
 #include <linux/cpu.h>
-#include <linux/err.h>
+#include <linux/init.h>
 #include <linux/kthread.h>
 #include <linux/module.h>
+#include <linux/percpu.h>
 #include <linux/sched.h>
 #include <linux/stop_machine.h>
-#include <linux/syscalls.h>
 #include <linux/interrupt.h>
+#include <linux/kallsyms.h>
 
 #include <asm/atomic.h>
-#include <asm/uaccess.h>
+
+/*
+ * Structure to determine completion condition and record errors.  May
+ * be shared by works on different cpus.
+ */
+struct cpu_stop_done {
+	atomic_t		nr_todo;	/* nr left to execute */
+	bool			executed;	/* actually executed? */
+	int			ret;		/* collected return value */
+	struct completion	completion;	/* fired if nr_todo reaches 0 */
+};
+
+/* the actual stopper, one per every possible cpu, enabled on online cpus */
+struct cpu_stopper {
+	spinlock_t		lock;
+	struct list_head	works;		/* list of pending works */
+	struct task_struct	*thread;	/* stopper thread */
+	bool			enabled;	/* is this stopper enabled? */
+};
+
+static DEFINE_PER_CPU(struct cpu_stopper, cpu_stopper);
+
+static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo)
+{
+	memset(done, 0, sizeof(*done));
+	atomic_set(&done->nr_todo, nr_todo);
+	init_completion(&done->completion);
+}
+
+/* signal completion unless @done is NULL */
+static void cpu_stop_signal_done(struct cpu_stop