1 files changed, 586 insertions, 151 deletions

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 9124669f458..a343bde710b 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -10,16 +10,44 @@
 #include <linux/sched.h>
 #include <linux/unistd.h>
 #include <linux/cpu.h>
-#include <linux/module.h>
+#include <linux/oom.h>
+#include <linux/rcupdate.h>
+#include <linux/export.h>
+#include <linux/bug.h>
 #include <linux/kthread.h>
 #include <linux/stop_machine.h>
 #include <linux/mutex.h>
+#include <linux/gfp.h>
+#include <linux/suspend.h>
+#include <linux/lockdep.h>
+#include <trace/events/power.h>
 
-/* This protects CPUs going up and down... */
+#include "smpboot.h"
+
+#ifdef CONFIG_SMP
+/* Serializes the updates to cpu_online_mask, cpu_present_mask */
 static DEFINE_MUTEX(cpu_add_remove_lock);
-static DEFINE_MUTEX(cpu_bitmask_lock);
 
-static __cpuinitdata RAW_NOTIFIER_HEAD(cpu_chain);
+/*
+ * The following two APIs (cpu_maps_update_begin/done) must be used when
+ * attempting to serialize the updates to cpu_online_mask & cpu_present_mask.
+ * The APIs cpu_notifier_register_begin/done() must be used to protect CPU
+ * hotplug callback (un)registration performed using __register_cpu_notifier()
+ * or __unregister_cpu_notifier().
+ */
+void cpu_maps_update_begin(void)
+{
+	mutex_lock(&cpu_add_remove_lock);
+}
+EXPORT_SYMBOL(cpu_notifier_register_begin);
+
+void cpu_maps_update_done(void)
+{
+	mutex_unlock(&cpu_add_remove_lock);
+}
+EXPORT_SYMBOL(cpu_notifier_register_done);
+
+static RAW_NOTIFIER_HEAD(cpu_chain);
 
 /* If set, cpu_up and cpu_down will return -EBUSY and do nothing.
  * Should always be manipulated under cpu_add_remove_lock
@@ -28,84 +56,250 @@ static int cpu_hotplug_disabled;
 
 #ifdef CONFIG_HOTPLUG_CPU
 
-/* Crappy recursive lock-takers in cpufreq! Complain loudly about idiots */
-static struct task_struct *recursive;
-static int recursive_depth;
+static struct {
+	struct task_struct *active_writer;
+	struct mutex lock; /* Synchronizes accesses to refcount, */
+	/*
+	 * Also blocks the new readers during
+	 * an ongoing cpu hotplug operation.
+	 */
+	int refcount;
 
-void lock_cpu_hotplug(void)
-{
-	struct task_struct *tsk = current;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map dep_map;
+#endif
+} cpu_hotplug = {
+	.active_writer = NULL,
+	.lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),
+	.refcount = 0,
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	.dep_map = {.name = "cpu_hotplug.lock" },
+#endif
+};
 
-	if (tsk == recursive) {
-		static int warnings = 10;
-		if (warnings) {
-			printk(KERN_ERR "Lukewarm IQ detected in hotplug locking\n");
-			WARN_ON(1);
-			warnings--;
-		}
-		recursive_depth++;
+/* Lockdep annotations for get/put_online_cpus() and cpu_hotplug_begin/end() */
+#define cpuhp_lock_acquire_read() lock_map_acquire_read(&cpu_hotplug.dep_map)
+#define cpuhp_lock_acquire()      lock_map_acquire(&cpu_hotplug.dep_map)
+#define cpuhp_lock_release()      lock_map_release(&cpu_hotplug.dep_map)
+
+void get_online_cpus(void)
+{
+	might_sleep();
+	if (cpu_hotplug.active_writer == current)
 		return;
-	}
-	mutex_lock(&cpu_bitmask_lock);
-	recursive = tsk;
+	cpuhp_lock_acquire_read();
+	mutex_lock(&cpu_hotplug.lock);
+	cpu_hotplug.refcount++;
+	mutex_unlock(&cpu_hotplug.lock);
+
 }
-EXPORT_SYMBOL_GPL(lock_cpu_hotplug);
+EXPORT_SYMBOL_GPL(get_online_cpus);
 
-void unlock_cpu_hotplug(void)
+void put_online_cpus(void)
 {
-	WARN_ON(recursive != current);
-	if (recursive_depth) {
-		recursive_depth--;
+	if (cpu_hotplug.active_writer == current)
 		return;
+	mutex_lock(&cpu_hotplug.lock);
+
+	if (WARN_ON(!cpu_hotplug.refcount))
+		cpu_hotplug.refcount++; /* try to fix things up */
+
+	if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer))
+		wake_up_process(cpu_hotplug.active_writer);
+	mutex_unlock(&cpu_hotplug.lock);
+	cpuhp_lock_release();
+
+}
+EXPORT_SYMBOL_GPL(put_online_cpus);
+
+/*
+ * This ensures that the hotplug operation can begin only when the
+ * refcount goes to zero.
+ *
+ * Note that during a cpu-hotplug operation, the new readers, if any,
+ * will be blocked by the cpu_hotplug.lock
+ *
+ * Since cpu_hotplug_begin() is always called after invoking
+ * cpu_maps_update_begin(), we can be sure that only one writer is active.
+ *
+ * Note that theoretically, there is a possibility of a livelock:
+ * - Refcount goes to zero, last reader wakes up the sleeping
+ *   writer.
+ * - Last reader unlocks the cpu_hotplug.lock.
+ * - A new reader arrives at this moment, bumps up the refcount.
+ * - The writer acquires the cpu_hotplug.lock finds the refcount
+ *   non zero and goes to sleep again.
+ *
+ * However, this is very difficult to achieve in practice since
+ * get_online_cpus() not an api which is called all that often.
+ *
+ */
+void cpu_hotplug_begin(void)
+{
+	cpu_hotplug.active_writer = current;
+
+	cpuhp_lock_acquire();
+	for (;;) {
+		mutex_lock(&cpu_hotplug.lock);
+		if (likely(!cpu_hotplug.refcount))
+			break;
+		__set_current_state(TASK_UNINTERRUPTIBLE);
+		mutex_unlock(&cpu_hotplug.lock);
+		schedule();
 	}
-	recursive = NULL;
-	mutex_unlock(&cpu_bitmask_lock);
 }
-EXPORT_SYMBOL_GPL(unlock_cpu_hotplug);
+
+void cpu_hotplug_done(void)
+{
+	cpu_hotplug.active_writer = NULL;
+	mutex_unlock(&cpu_hotplug.lock);
+	cpuhp_lock_release();
+}
+
+/*
+ * Wait for currently running CPU hotplug operations to complete (if any) and
+ * disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects
+ * the 'cpu_hotplug_disabled' flag. The same lock is also acquired by the
+ * hotplug path before performing hotplug operations. So acquiring that lock
+ * guarantees mutual exclusion from any currently running hotplug operations.
+ */
+void cpu_hotplug_disable(void)
+{
+	cpu_maps_update_begin();
+	cpu_hotplug_disabled = 1;
+	cpu_maps_update_done();
+}
+
+void cpu_hotplug_enable(void)
+{
+	cpu_maps_update_begin();
+	cpu_hotplug_disabled = 0;
+	cpu_maps_update_done();
+}
 
 #endif	/* CONFIG_HOTPLUG_CPU */
 
 /* Need to know about CPUs going up/down? */
-int __cpuinit register_cpu_notifier(struct notifier_block *nb)
+int __ref register_cpu_notifier(struct notifier_block *nb)
 {
 	int ret;
-	mutex_lock(&cpu_add_remove_lock);
+	cpu_maps_update_begin();
 	ret = raw_notifier_chain_register(&cpu_chain, nb);
-	mutex_unlock(&cpu_add_remove_lock);
+	cpu_maps_update_done();
 	return ret;
 }
 
+int __ref __register_cpu_notifier(struct notifier_block *nb)
+{
+	return raw_notifier_chain_register(&cpu_chain, nb);
+}
+
+static int __cpu_notify(unsigned long val, void *v, int nr_to_call,
+			int *nr_calls)
+{
+	int ret;
+
+	ret = __raw_notifier_call_chain(&cpu_chain, val, v, nr_to_call,
+					nr_calls);
+
+	return notifier_to_errno(ret);
+}
+
+static int cpu_notify(unsigned long val, void *v)
+{
+	return __cpu_notify(val, v, -1, NULL);
+}
+
 #ifdef CONFIG_HOTPLUG_CPU
 
+static void cpu_notify_nofail(unsigned long val, void *v)
+{
+	BUG_ON(cpu_notify(val, v));
+}
 EXPORT_SYMBOL(register_cpu_notifier);
+EXPORT_SYMBOL(__register_cpu_notifier);
 
-void unregister_cpu_notifier(struct notifier_block *nb)
+void __ref unregister_cpu_notifier(struct notifier_block *nb)
 {
-	mutex_lock(&cpu_add_remove_lock);
+	cpu_maps_update_begin();
 	raw_notifier_chain_unregister(&cpu_chain, nb);
-	mutex_unlock(&cpu_add_remove_lock);
+	cpu_maps_update_done();
 }
 EXPORT_SYMBOL(unregister_cpu_notifier);
 
+void __ref __unregister_cpu_notifier(struct notifier_block *nb)
+{
+	raw_notifier_chain_unregister(&cpu_chain, nb);
+}
+EXPORT_SYMBOL(__unregister_cpu_notifier);
+
+/**
+ * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
+ * @cpu: a CPU id
+ *
+ * This function walks all processes, finds a valid mm struct for each one and
+ * then clears a corresponding bit in mm's cpumask.  While this all sounds
+ * trivial, there are various non-obvious corner cases, which this function
+ * tries to solve in a safe manner.
+ *
+ * Also note that the function uses a somewhat relaxed locking scheme, so it may
+ * be called only for an already offlined CPU.
+ */
+void clear_tasks_mm_cpumask(int cpu)
+{
+	struct task_struct *p;
+
+	/*
+	 * This function is called after the cpu is taken down and marked
+	 * offline, so its not like new tasks will ever get this cpu set in
+	 * their mm mask. -- Peter Zijlstra
+	 * Thus, we may use rcu_read_lock() here, instead of grabbing
+	 * full-fledged tasklist_lock.
+	 */
+	WARN_ON(cpu_online(cpu));
+	rcu_read_lock();
+	for_each_process(p) {
+		struct task_struct *t;
+
+		/*
+		 * Main thread might exit, but other threads may still have
+		 * a valid mm. Find one.
+		 */
+		t = find_lock_task_mm(p);
+		if (!t)
+			continue;
+		cpumask_clear_cpu(cpu, mm_cpumask(t->mm));
+		task_unlock(t);
+	}
+	rcu_read_unlock();
+}
+
 static inline void check_for_tasks(int cpu)
 {
 	struct task_struct *p;
+	cputime_t utime, stime;
 
 	write_lock_irq(&tasklist_lock);
 	for_each_process(p) {
-		if (task_cpu(p) == cpu &&
-		    (!cputime_eq(p->utime, cputime_zero) ||
-		     !cputime_eq(p->stime, cputime_zero)))
-			printk(KERN_WARNING "Task %s (pid = %d) is on cpu %d\
-				(state = %ld, flags = %lx) \n",
-				 p->comm, p->pid, cpu, p->state, p->flags);
+		task_cputime(p, &utime, &stime);
+		if (task_cpu(p) == cpu && p->state == TASK_RUNNING &&
+		    (utime || stime))
+			pr_warn("Task %s (pid = %d) is on cpu %d (state = %ld, flags = %x)\n",
+				p->comm, task_pid_nr(p), cpu,
+				p->state, p->flags);
 	}
 	write_unlock_irq(&tasklist_lock);
 }
 
+struct take_cpu_down_param {
+	unsigned long mod;
+	void *hcpu;
+};
+
 /* Take this CPU down. */
-static int take_cpu_down(void *unused)
+static int __ref take_cpu_down(void *_param)
 {
+	struct take_cpu_down_param *param = _param;
 	int err;
 
 	/* Ensure this CPU doesn't handle any more interrupts. */
@@ -113,18 +307,22 @@ static int take_cpu_down(void *unused)
 	if (err < 0)
 		return err;
 
-	/* Force idle task to run as soon as we yield: it should
-	   immediately notice cpu is offline and die quickly. */
-	sched_idle_next();
+	cpu_notify(CPU_DYING | param->mod, param->hcpu);
+	/* Park the stopper thread */
+	kthread_park(current);
 	return 0;
 }
 
 /* Requires cpu_add_remove_lock to be held */
-static int _cpu_down(unsigned int cpu)
+static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 {
-	int err;
-	struct task_struct *p;
-	cpumask_t old_allowed, tmp;
+	int err, nr_calls = 0;
+	void *hcpu = (void *)(long)cpu;
+	unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
+	struct take_cpu_down_param tcd_param = {
+		.mod = mod,
+		.hcpu = hcpu,
+	};
 
 	if (num_online_cpus() == 1)
 		return -EBUSY;
@@ -132,194 +330,431 @@ static int _cpu_down(unsigned int cpu)
 	if (!cpu_online(cpu))
 		return -EINVAL;
 
-	err = raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE,
-						(void *)(long)cpu);
-	if (err == NOTIFY_BAD) {
-		printk("%s: attempt to take down CPU %u failed\n",
-				__FUNCTION__, cpu);
-		return -EINVAL;
+	cpu_hotplug_begin();
+
+	err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls);
+	if (err) {
+		nr_calls--;
+		__cpu_notify(CPU_DOWN_FAILED | mod, hcpu, nr_calls, NULL);
+		pr_warn("%s: attempt to take down CPU %u failed\n",
+			__func__, cpu);
+		goto out_release;
 	}
 
-	/* Ensure that we are not runnable on dying cpu */
-	old_allowed = current->cpus_allowed;
-	tmp = CPU_MASK_ALL;
-	cpu_clear(cpu, tmp);
-	set_cpus_allowed(current, tmp);
+	/*
+	 * By now we've cleared cpu_active_mask, wait for all preempt-disabled
+	 * and RCU users of this state to go away such that all new such users
+	 * will observe it.
+	 *
+	 * For CONFIG_PREEMPT we have preemptible RCU and its sync_rcu() might
+	 * not imply sync_sched(), so explicitly call both.
+	 *
+	 * Do sync before park smpboot threads to take care the rcu boost case.
+	 */
+#ifdef CONFIG_PREEMPT
+	synchronize_sched();
+#endif
+	synchronize_rcu();
 
-	mutex_lock(&cpu_bitmask_lock);
-	p = __stop_machine_run(take_cpu_down, NULL, cpu);
-	mutex_unlock(&cpu_bitmask_lock);
+	smpboot_park_threads(cpu);
 
-	if (IS_ERR(p) || cpu_online(cpu)) {
-		/* CPU didn't die: tell everyone.  Can't complain. */
-		if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED,
-				(void *)(long)cpu) == NOTIFY_BAD)
-			BUG();
+	/*
+	 * So now all preempt/rcu users must observe !cpu_active().
+	 */
 
-		if (IS_ERR(p)) {
-			err = PTR_ERR(p);
-			goto out_allowed;
-		}
-		goto out_thread;
+	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;
 	}
-
-	/* Wait for it to sleep (leaving idle task). */
+	BUG_ON(cpu_online(cpu));
+
+	/*
+	 * The migration_call() CPU_DYING callback will have removed all
+	 * runnable tasks from the cpu, there's only the idle task left now
+	 * that the migration thread is done doing the stop_machine thing.
+	 *
+	 * Wait for the stop thread to go away.
+	 */
 	while (!idle_cpu(cpu))
-		yield();
+		cpu_relax();
 
 	/* This actually kills the CPU. */
 	__cpu_die(cpu);
 
-	/* Move it here so it can run. */
-	kthread_bind(p, get_cpu());
-	put_cpu();
-
 	/* CPU is completely dead: tell everyone.  Too late to complain. */
-	if (raw_notifier_call_chain(&cpu_chain, CPU_DEAD,
-			(void *)(long)cpu) == NOTIFY_BAD)
-		BUG();
+	cpu_notify_nofail(CPU_DEAD | mod, hcpu);
 
 	check_for_tasks(cpu);
 
-out_thread:
-	err = kthread_stop(p);
-out_allowed:
-	set_cpus_allowed(current, old_allowed);
+out_release:
+	cpu_hotplug_done();
+	if (!err)
+		cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu);
 	return err;
 }
 
-int cpu_down(unsigned int cpu)
+int __ref cpu_down(unsigned int cpu)
 {
-	int err = 0;
+	int err;
 
-	mutex_lock(&cpu_add_remove_lock);
-	if (cpu_hotplug_disabled)
+	cpu_maps_update_begin();
+
+	if (cpu_hotplug_disabled) {
 		err = -EBUSY;
-	else
-		err = _cpu_down(cpu);
+		goto out;
+	}
 
-	mutex_unlock(&cpu_add_remove_lock);
+	err = _cpu_down(cpu, 0);
+
+out:
+	cpu_maps_update_done();
 	return err;
 }
+EXPORT_SYMBOL(cpu_down);
 #endif /*CONFIG_HOTPLUG_CPU*/
 
 /* Requires cpu_add_remove_lock to be held */
-static int __devinit _cpu_up(unsigned int cpu)
+static int _cpu_up(unsigned int cpu, int tasks_frozen)
 {
-	int ret;
+	int ret, nr_calls = 0;
 	void *hcpu = (void *)(long)cpu;
+	unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
+	struct task_struct *idle;
 
-	if (cpu_online(cpu) || !cpu_present(cpu))
-		return -EINVAL;
+	cpu_hotplug_begin();
 
-	ret = raw_notifier_call_chain(&cpu_chain, CPU_UP_PREPARE, hcpu);
-	if (ret == NOTIFY_BAD) {
-		printk("%s: attempt to bring up CPU %u failed\n",
-				__FUNCTION__, cpu);
+	if (cpu_online(cpu) || !cpu_present(cpu)) {
 		ret = -EINVAL;
+		goto out;
+	}
+
+	idle = idle_thread_get(cpu);
+	if (IS_ERR(idle)) {
+		ret = PTR_ERR(idle);
+		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--;
+		pr_warn("%s: attempt to bring up CPU %u failed\n",
+			__func__, cpu);
 		goto out_notify;
 	}
 
 	/* Arch-specific enabling code. */
-	mutex_lock(&cpu_bitmask_lock);
-	ret = __cpu_up(cpu);
-	mutex_unlock(&cpu_bitmask_lock);
+	ret = __cpu_up(cpu, idle);
 	if (ret != 0)
 		goto out_notify;
 	BUG_ON(!cpu_online(cpu));
 
+	/* Wake the per cpu threads */
+	smpboot_unpark_threads(cpu);
+
 	/* Now call notifier in preparation. */
-	raw_notifier_call_chain(&cpu_chain, CPU_ONLINE, hcpu);
+	cpu_notify(CPU_ONLINE | mod, hcpu);
 
 out_notify:
 	if (ret != 0)
-		raw_notifier_call_chain(&cpu_chain,
-				CPU_UP_CANCELED, hcpu);
+		__cpu_notify(CPU_UP_CANCELED | mod, hcpu, nr_calls, NULL);
+out:
+	cpu_hotplug_done();
 
 	return ret;
 }
 
-int __devinit cpu_up(unsigned int cpu)
+int cpu_up(unsigned int cpu)
 {
 	int err = 0;
 
-	mutex_lock(&cpu_add_remove_lock);
-	if (cpu_hotplug_disabled)
+	if (!cpu_possible(cpu)) {
+		pr_err("can't online cpu %d because it is not configured as may-hotadd at boot time\n",
+		       cpu);
+#if defined(CONFIG_IA64)
+		pr_err("please check additional_cpus= boot parameter\n");
+#endif
+		return -EINVAL;
+	}
+
+	err = try_online_node(cpu_to_node(cpu));
+	if (err)
+		return err;
+
+	cpu_maps_update_begin();
+
+	if (cpu_hotplug_disabled) {
 		err = -EBUSY;
-	else
-		err = _cpu_up(cpu);
+		goto out;
+	}
 
-	mutex_unlock(&cpu_add_remove_lock);
+	err = _cpu_up(cpu, 0);
+
+out:
+	cpu_maps_update_done();
 	return err;
 }
+EXPORT_SYMBOL_GPL(cpu_up);
 
-#ifdef CONFIG_SUSPEND_SMP
-static cpumask_t frozen_cpus;
+#ifdef CONFIG_PM_SLEEP_SMP
+static cpumask_var_t frozen_cpus;
 
 int disable_nonboot_cpus(void)
 {
-	int cpu, first_cpu, error;
+	int cpu, first_cpu, error = 0;
 
-	mutex_lock(&cpu_add_remove_lock);
-	first_cpu = first_cpu(cpu_present_map);
-	if (!cpu_online(first_cpu)) {
-		error = _cpu_up(first_cpu);
-		if (error) {
-			printk(KERN_ERR "Could not bring CPU%d up.\n",
-				first_cpu);
-			goto out;
-		}
-	}
-
-	/* We take down all of the non-boot CPUs in one shot to avoid races
+	cpu_maps_update_begin();
+	first_cpu = cpumask_first(cpu_online_mask);
+	/*
+	 * We take down all of the non-boot CPUs in one shot to avoid races
 	 * with the userspace trying to use the CPU hotplug at the same time
 	 */
-	cpus_clear(frozen_cpus);
-	printk("Disabling non-boot CPUs ...\n");
+	cpumask_clear(frozen_cpus);
+
+	pr_info("Disabling non-boot CPUs ...\n");
 	for_each_online_cpu(cpu) {
 		if (cpu == first_cpu)
 			continue;
-		error = _cpu_down(cpu);
-		if (!error) {
-			cpu_set(cpu, frozen_cpus);
-			printk("CPU%d is down\n", cpu);
-		} else {
-			printk(KERN_ERR "Error taking CPU%d down: %d\n",
-				cpu, error);
+		trace_suspend_resume(TPS("CPU_OFF"), cpu, true);
+		error = _cpu_down(cpu, 1);
+		trace_suspend_resume(TPS("CPU_OFF"), cpu, false);
+		if (!error)
+			cpumask_set_cpu(cpu, frozen_cpus);
+		else {
+			pr_err("Error taking CPU%d down: %d\n", cpu, error);
 			break;
 		}
 	}
+
 	if (!error) {
 		BUG_ON(num_online_cpus() > 1);
 		/* Make sure the CPUs won't be enabled by someone else */
 		cpu_hotplug_disabled = 1;
 	} else {
-		printk(KERN_ERR "Non-boot CPUs are not disabled");
+		pr_err("Non-boot CPUs are not disabled\n");
 	}
-out:
-	mutex_unlock(&cpu_add_remove_lock);
+	cpu_maps_update_done();
 	return error;
 }
 
-void enable_nonboot_cpus(void)
+void __weak arch_enable_nonboot_cpus_begin(void)
+{
+}
+
+void __weak arch_enable_nonboot_cpus_end(void)
+{
+}
+
+void __ref enable_nonboot_cpus(void)
 {
 	int cpu, error;
 
 	/* Allow everyone to use the CPU hotplug again */
-	mutex_lock(&cpu_add_remove_lock);
+	cpu_maps_update_begin();
 	cpu_hotplug_disabled = 0;
-	mutex_unlock(&cpu_add_remove_lock);
+	if (cpumask_empty(frozen_cpus))
+		goto out;
+
+	pr_info("Enabling non-boot CPUs ...\n");
+
+	arch_enable_nonboot_cpus_begin();
 
-	printk("Enabling non-boot CPUs ...\n");
-	for_each_cpu_mask(cpu, frozen_cpus) {
-		error = cpu_up(cpu);
+	for_each_cpu(cpu, frozen_cpus) {
+		trace_suspend_resume(TPS("CPU_ON"), cpu, true);
+		error = _cpu_up(cpu, 1);
+		trace_suspend_resume(TPS("CPU_ON"), cpu, false);
 		if (!error) {
-			printk("CPU%d is up\n", cpu);
+			pr_info("CPU%d is up\n", cpu);
 			continue;
 		}
-		printk(KERN_WARNING "Error taking CPU%d up: %d\n",
-			cpu, error);
+		pr_warn("Error taking CPU%d up: %d\n", cpu, error);
+	}
+
+	arch_enable_nonboot_cpus_end();
+
+	cpumask_clear(frozen_cpus);
+out:
+	cpu_maps_update_done();
+}
+
+static int __init alloc_frozen_cpus(void)
+{
+	if (!alloc_cpumask_var(&frozen_cpus, GFP_KERNEL|__GFP_ZERO))
+		return -ENOMEM;
+	return 0;
+}
+core_initcall(alloc_frozen_cpus);
+
+/*
+ * When callbacks for CPU hotplug notifications are being executed, we must
+ * ensure that the state of the system with respect to the tasks being frozen
+ * or not, as reported by the notification, remains unchanged *throughout the
+ * duration* of the execution of the callbacks.
+ * Hence we need to prevent the freezer from racing with regular CPU hotplug.
+ *
+ * This synchronization is implemented by mutually excluding regular CPU
+ * hotplug and Suspend/Hibernate call paths by hooking onto the Suspend/
+ * Hibernate notifications.
+ */
+static int
+cpu_hotplug_pm_callback(struct notifier_block *nb,
+			unsigned long action, void *ptr)
+{
+	switch (action) {
+
+	case PM_SUSPEND_PREPARE:
+	case PM_HIBERNATION_PREPARE:
+		cpu_hotplug_disable();
+		break;
+
+	case PM_POST_SUSPEND:
+	case PM_POST_HIBERNATION:
+		cpu_hotplug_enable();
+		break;
+
+	default:
+		return NOTIFY_DONE;
 	}
-	cpus_clear(frozen_cpus);
+
+	return NOTIFY_OK;
 }
+
+
+static int __init cpu_hotplug_pm_sync_init(void)
+{
+	/*
+	 * cpu_hotplug_pm_callback has higher priority than x86
+	 * bsp_pm_callback which depends on cpu_hotplug_pm_callback
+	 * to disable cpu hotplug to avoid cpu hotplug race.
+	 */
+	pm_notifier(cpu_hotplug_pm_callback, 0);
+	return 0;
+}
+core_initcall(cpu_hotplug_pm_sync_init);
+
+#endif /* CONFIG_PM_SLEEP_SMP */
+
+/**
+ * notify_cpu_starting(cpu) - call the CPU_STARTING notifiers
+ * @cpu: cpu that just started
+ *
+ * This function calls the cpu_chain notifiers with CPU_STARTING.
+ * It must be called by the arch code on the new cpu, before the new cpu
+ * enables interrupts and before the "boot" cpu returns from __cpu_up().
+ */
+void notify_cpu_starting(unsigned int cpu)
+{
+	unsigned long val = CPU_STARTING;
+
+#ifdef CONFIG_PM_SLEEP_SMP
+	if (frozen_cpus != NULL && cpumask_test_cpu(cpu, frozen_cpus))
+		val = CPU_STARTING_FROZEN;
+#endif /* CONFIG_PM_SLEEP_SMP */
+	cpu_notify(val, (void *)(long)cpu);
+}
+
+#endif /* CONFIG_SMP */
+
+/*
+ * cpu_bit_bitmap[] is a special, "compressed" data structure that
+ * represents all NR_CPUS bits binary values of 1<<nr.
+ *
+ * It is used by cpumask_of() to get a constant address to a CPU
+ * mask value that has a single bit set only.
+ */
+
+/* cpu_bit_bitmap[0] is empty - so we can back into it */
+#define MASK_DECLARE_1(x)	[x+1][0] = (1UL << (x))
+#define MASK_DECLARE_2(x)	MASK_DECLARE_1(x), MASK_DECLARE_1(x+1)
+#define MASK_DECLARE_4(x)	MASK_DECLARE_2(x), MASK_DECLARE_2(x+2)
+#define MASK_DECLARE_8(x)	MASK_DECLARE_4(x), MASK_DECLARE_4(x+4)
+
+const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = {
+
+	MASK_DECLARE_8(0),	MASK_DECLARE_8(8),
+	MASK_DECLARE_8(16),	MASK_DECLARE_8(24),
+#if BITS_PER_LONG > 32
+	MASK_DECLARE_8(32),	MASK_DECLARE_8(40),
+	MASK_DECLARE_8(48),	MASK_DECLARE_8(56),
 #endif
+};
+EXPORT_SYMBOL_GPL(cpu_bit_bitmap);
+
+const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL;
+EXPORT_SYMBOL(cpu_all_bits);
+
+#ifdef CONFIG_INIT_ALL_POSSIBLE
+static DECLARE_BITMAP(cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly
+	= CPU_BITS_ALL;
+#else
+static DECLARE_BITMAP(cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly;
+#endif
+const struct cpumask *const cpu_possible_mask = to_cpumask(cpu_possible_bits);
+EXPORT_SYMBOL(cpu_possible_mask);
+
+static DECLARE_BITMAP(cpu_online_bits, CONFIG_NR_CPUS) __read_mostly;
+const struct cpumask *const cpu_online_mask = to_cpumask(cpu_online_bits);
+EXPORT_SYMBOL(cpu_online_mask);
+
+static DECLARE_BITMAP(cpu_present_bits, CONFIG_NR_CPUS) __read_mostly;
+const struct cpumask *const cpu_present_mask = to_cpumask(cpu_present_bits);
+EXPORT_SYMBOL(cpu_present_mask);
+
+static DECLARE_BITMAP(cpu_active_bits, CONFIG_NR_CPUS) __read_mostly;
+const struct cpumask *const cpu_active_mask = to_cpumask(cpu_active_bits);
+EXPORT_SYMBOL(cpu_active_mask);
+
+void set_cpu_possible(unsigned int cpu, bool possible)
+{
+	if (possible)
+		cpumask_set_cpu(cpu, to_cpumask(cpu_possible_bits));
+	else
+		cpumask_clear_cpu(cpu, to_cpumask(cpu_possible_bits));
+}
+
+void set_cpu_present(unsigned int cpu, bool present)
+{
+	if (present)
+		cpumask_set_cpu(cpu, to_cpumask(cpu_present_bits));
+	else
+		cpumask_clear_cpu(cpu, to_cpumask(cpu_present_bits));
+}
+
+void set_cpu_online(unsigned int cpu, bool online)
+{
+	if (online) {
+		cpumask_set_cpu(cpu, to_cpumask(cpu_online_bits));
+		cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits));
+	} else {
+		cpumask_clear_cpu(cpu, to_cpumask(cpu_online_bits));
+	}
+}
+
+void set_cpu_active(unsigned int cpu, bool active)
+{
+	if (active)
+		cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits));
+	else
+		cpumask_clear_cpu(cpu, to_cpumask(cpu_active_bits));
+}
+
+void init_cpu_present(const struct cpumask *src)
+{
+	cpumask_copy(to_cpumask(cpu_present_bits), src);
+}
+
+void init_cpu_possible(const struct cpumask *src)
+{
+	cpumask_copy(to_cpumask(cpu_possible_bits), src);
+}
+
+void init_cpu_online(const struct cpumask *src)
+{
+	cpumask_copy(to_cpumask(cpu_online_bits), src);
+}