cpu/hotplug: Add sysfs state interface

[linux-2.6-block.git] / kernel / cpu.c

/* CPU control.
 * (C) 2001, 2002, 2003, 2004 Rusty Russell
 *
 * This code is licenced under the GPL.
 */
#include <linux/proc_fs.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/notifier.h>
#include <linux/sched.h>
#include <linux/unistd.h>
#include <linux/cpu.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 <linux/tick.h>
#include <linux/irq.h>

#include <trace/events/power.h>
#define CREATE_TRACE_POINTS
#include <trace/events/cpuhp.h>

#include "smpboot.h"

/**
 * cpuhp_cpu_state - Per cpu hotplug state storage
 * @state:	The current cpu state
 * @target:	The target state
 */
struct cpuhp_cpu_state {
	enum cpuhp_state	state;
	enum cpuhp_state	target;
};

static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state);

/**
 * cpuhp_step - Hotplug state machine step
 * @name:	Name of the step
 * @startup:	Startup function of the step
 * @teardown:	Teardown function of the step
 * @skip_onerr:	Do not invoke the functions on error rollback
 *		Will go away once the notifiers	are gone
 */
struct cpuhp_step {
	const char	*name;
	int		(*startup)(unsigned int cpu);
	int		(*teardown)(unsigned int cpu);
	bool		skip_onerr;
};

static DEFINE_MUTEX(cpuhp_state_mutex);
static struct cpuhp_step cpuhp_bp_states[];
static struct cpuhp_step cpuhp_ap_states[];

/**
 * cpuhp_invoke_callback _ Invoke the callbacks for a given state
 * @cpu:	The cpu for which the callback should be invoked
 * @step:	The step in the state machine
 * @cb:		The callback function to invoke
 *
 * Called from cpu hotplug and from the state register machinery
 */
static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state step,
				 int (*cb)(unsigned int))
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
	int ret = 0;

	if (cb) {
		trace_cpuhp_enter(cpu, st->target, step, cb);
		ret = cb(cpu);
		trace_cpuhp_exit(cpu, st->state, step, ret);
	}
	return ret;
}

#ifdef CONFIG_SMP
/* Serializes the updates to cpu_online_mask, cpu_present_mask */
static DEFINE_MUTEX(cpu_add_remove_lock);
bool cpuhp_tasks_frozen;
EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen);

/*
 * 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
 */
static int cpu_hotplug_disabled;

#ifdef CONFIG_HOTPLUG_CPU

static struct {
	struct task_struct *active_writer;
	/* wait queue to wake up the active_writer */
	wait_queue_head_t wq;
	/* verifies that no writer will get active while readers are active */
	struct mutex lock;
	/*
	 * Also blocks the new readers during
	 * an ongoing cpu hotplug operation.
	 */
	atomic_t refcount;

#ifdef CONFIG_DEBUG_LOCK_ALLOC
	struct lockdep_map dep_map;
#endif
} cpu_hotplug = {
	.active_writer = NULL,
	.wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq),
	.lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),
#ifdef CONFIG_DEBUG_LOCK_ALLOC
	.dep_map = {.name = "cpu_hotplug.lock" },
#endif
};

/* 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_tryread() \
				  lock_map_acquire_tryread(&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;
	cpuhp_lock_acquire_read();
	mutex_lock(&cpu_hotplug.lock);
	atomic_inc(&cpu_hotplug.refcount);
	mutex_unlock(&cpu_hotplug.lock);
}
EXPORT_SYMBOL_GPL(get_online_cpus);

void put_online_cpus(void)
{
	int refcount;

	if (cpu_hotplug.active_writer == current)
		return;

	refcount = atomic_dec_return(&cpu_hotplug.refcount);
	if (WARN_ON(refcount < 0)) /* try to fix things up */
		atomic_inc(&cpu_hotplug.refcount);

	if (refcount <= 0 && waitqueue_active(&cpu_hotplug.wq))
		wake_up(&cpu_hotplug.wq);

	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)
{
	DEFINE_WAIT(wait);

	cpu_hotplug.active_writer = current;
	cpuhp_lock_acquire();

	for (;;) {
		mutex_lock(&cpu_hotplug.lock);
		prepare_to_wait(&cpu_hotplug.wq, &wait, TASK_UNINTERRUPTIBLE);
		if (likely(!atomic_read(&cpu_hotplug.refcount)))
				break;
		mutex_unlock(&cpu_hotplug.lock);
		schedule();
	}
	finish_wait(&cpu_hotplug.wq, &wait);
}

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++;
	cpu_maps_update_done();
}
EXPORT_SYMBOL_GPL(cpu_hotplug_disable);

void cpu_hotplug_enable(void)
{
	cpu_maps_update_begin();
	WARN_ON(--cpu_hotplug_disabled < 0);
	cpu_maps_update_done();
}
EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
#endif	/* CONFIG_HOTPLUG_CPU */

/* Need to know about CPUs going up/down? */
int register_cpu_notifier(struct notifier_block *nb)
{
	int ret;
	cpu_maps_update_begin();
	ret = raw_notifier_chain_register(&cpu_chain, nb);
	cpu_maps_update_done();
	return ret;
}

int __register_cpu_notifier(struct notifier_block *nb)
{
	return raw_notifier_chain_register(&cpu_chain, nb);
}

static int __cpu_notify(unsigned long val, unsigned int cpu, int nr_to_call,
			int *nr_calls)
{
	unsigned long mod = cpuhp_tasks_frozen ? CPU_TASKS_FROZEN : 0;
	void *hcpu = (void *)(long)cpu;

	int ret;

	ret = __raw_notifier_call_chain(&cpu_chain, val | mod, hcpu, nr_to_call,
					nr_calls);

	return notifier_to_errno(ret);
}

static int cpu_notify(unsigned long val, unsigned int cpu)
{
	return __cpu_notify(val, cpu, -1, NULL);
}

/* Notifier wrappers for transitioning to state machine */
static int notify_prepare(unsigned int cpu)
{
	int nr_calls = 0;
	int ret;

	ret = __cpu_notify(CPU_UP_PREPARE, cpu, -1, &nr_calls);
	if (ret) {
		nr_calls--;
		printk(KERN_WARNING "%s: attempt to bring up CPU %u failed\n",
				__func__, cpu);
		__cpu_notify(CPU_UP_CANCELED, cpu, nr_calls, NULL);
	}
	return ret;
}

static int notify_online(unsigned int cpu)
{
	cpu_notify(CPU_ONLINE, cpu);
	return 0;
}

static int notify_starting(unsigned int cpu)
{
	cpu_notify(CPU_STARTING, cpu);
	return 0;
}

static int bringup_cpu(unsigned int cpu)
{
	struct task_struct *idle = idle_thread_get(cpu);
	int ret;

	/* Arch-specific enabling code. */
	ret = __cpu_up(cpu, idle);
	if (ret) {
		cpu_notify(CPU_UP_CANCELED, cpu);
		return ret;
	}
	BUG_ON(!cpu_online(cpu));
	return 0;
}

#ifdef CONFIG_HOTPLUG_CPU
EXPORT_SYMBOL(register_cpu_notifier);
EXPORT_SYMBOL(__register_cpu_notifier);

void unregister_cpu_notifier(struct notifier_block *nb)
{
	cpu_maps_update_begin();
	raw_notifier_chain_unregister(&cpu_chain, nb);
	cpu_maps_update_done();
}
EXPORT_SYMBOL(unregister_cpu_notifier);

void __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 dead_cpu)
{
	struct task_struct *g, *p;

	read_lock(&tasklist_lock);
	for_each_process_thread(g, p) {
		if (!p->on_rq)
			continue;
		/*
		 * We do the check with unlocked task_rq(p)->lock.
		 * Order the reading to do not warn about a task,
		 * which was running on this cpu in the past, and
		 * it's just been woken on another cpu.
		 */
		rmb();
		if (task_cpu(p) != dead_cpu)
			continue;

		pr_warn("Task %s (pid=%d) is on cpu %d (state=%ld, flags=%x)\n",
			p->comm, task_pid_nr(p), dead_cpu, p->state, p->flags);
	}
	read_unlock(&tasklist_lock);
}

static void cpu_notify_nofail(unsigned long val, unsigned int cpu)
{
	BUG_ON(cpu_notify(val, cpu));
}

static int notify_down_prepare(unsigned int cpu)
{
	int err, nr_calls = 0;

	err = __cpu_notify(CPU_DOWN_PREPARE, cpu, -1, &nr_calls);
	if (err) {
		nr_calls--;
		__cpu_notify(CPU_DOWN_FAILED, cpu, nr_calls, NULL);
		pr_warn("%s: attempt to take down CPU %u failed\n",
				__func__, cpu);
	}
	return err;
}

static int notify_dying(unsigned int cpu)
{
	cpu_notify(CPU_DYING, cpu);
	return 0;
}

/* Take this CPU down. */
static int take_cpu_down(void *_param)
{
	struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
	enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE);
	int err, cpu = smp_processor_id();

	/* Ensure this CPU doesn't handle any more interrupts. */
	err = __cpu_disable();
	if (err < 0)
		return err;

	/* Invoke the former CPU_DYING callbacks */
	for (; st->state > target; st->state--) {
		struct cpuhp_step *step = cpuhp_ap_states + st->state;

		cpuhp_invoke_callback(cpu, st->state, step->teardown);
	}
	/* Give up timekeeping duties */
	tick_handover_do_timer();
	/* Park the stopper thread */
	stop_machine_park(cpu);
	return 0;
}

static int takedown_cpu(unsigned int cpu)
{
	int err;

	/*
	 * 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 wait for both.
	 *
	 * Do sync before park smpboot threads to take care the rcu boost case.
	 */
	if (IS_ENABLED(CONFIG_PREEMPT))
		synchronize_rcu_mult(call_rcu, call_rcu_sched);
	else
		synchronize_rcu();

	smpboot_park_threads(cpu);

	/*
	 * Prevent irq alloc/free while the dying cpu reorganizes the
	 * interrupt affinities.
	 */
	irq_lock_sparse();

	/*
	 * So now all preempt/rcu users must observe !cpu_active().
	 */
	err = stop_machine(take_cpu_down, NULL, cpumask_of(cpu));
	if (err) {
		/* CPU didn't die: tell everyone.  Can't complain. */
		cpu_notify_nofail(CPU_DOWN_FAILED, cpu);
		irq_unlock_sparse();
		return err;
	}
	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 (!per_cpu(cpu_dead_idle, cpu))
		cpu_relax();
	smp_mb(); /* Read from cpu_dead_idle before __cpu_die(). */
	per_cpu(cpu_dead_idle, cpu) = false;

	/* Interrupts are moved away from the dying cpu, reenable alloc/free */
	irq_unlock_sparse();

	hotplug_cpu__broadcast_tick_pull(cpu);
	/* This actually kills the CPU. */
	__cpu_die(cpu);

	tick_cleanup_dead_cpu(cpu);
	return 0;
}

static int notify_dead(unsigned int cpu)
{
	cpu_notify_nofail(CPU_DEAD, cpu);
	check_for_tasks(cpu);
	return 0;
}

#else
#define notify_down_prepare	NULL
#define takedown_cpu		NULL
#define notify_dead		NULL
#define notify_dying		NULL
#endif

#ifdef CONFIG_HOTPLUG_CPU
static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st)
{
	for (st->state++; st->state < st->target; st->state++) {
		struct cpuhp_step *step = cpuhp_bp_states + st->state;

		if (!step->skip_onerr)
			cpuhp_invoke_callback(cpu, st->state, step->startup);
	}
}

/* Requires cpu_add_remove_lock to be held */
static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
			   enum cpuhp_state target)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
	int prev_state, ret = 0;
	bool hasdied = false;

	if (num_online_cpus() == 1)
		return -EBUSY;

	if (!cpu_online(cpu))
		return -EINVAL;

	cpu_hotplug_begin();

	cpuhp_tasks_frozen = tasks_frozen;

	prev_state = st->state;
	st->target = target;
	for (; st->state > st->target; st->state--) {
		struct cpuhp_step *step = cpuhp_bp_states + st->state;

		ret = cpuhp_invoke_callback(cpu, st->state, step->teardown);
		if (ret) {
			st->target = prev_state;
			undo_cpu_down(cpu, st);
			break;
		}
	}
	hasdied = prev_state != st->state && st->state == CPUHP_OFFLINE;

	cpu_hotplug_done();
	/* This post dead nonsense must die */
	if (!ret && hasdied)
		cpu_notify_nofail(CPU_POST_DEAD, cpu);
	return ret;
}

static int do_cpu_down(unsigned int cpu, enum cpuhp_state target)
{
	int err;

	cpu_maps_update_begin();

	if (cpu_hotplug_disabled) {
		err = -EBUSY;
		goto out;
	}

	err = _cpu_down(cpu, 0, target);

out:
	cpu_maps_update_done();
	return err;
}
int cpu_down(unsigned int cpu)
{
	return do_cpu_down(cpu, CPUHP_OFFLINE);
}
EXPORT_SYMBOL(cpu_down);
#endif /*CONFIG_HOTPLUG_CPU*/

/*
 * Unpark per-CPU smpboot kthreads at CPU-online time.
 */
static int smpboot_thread_call(struct notifier_block *nfb,
			       unsigned long action, void *hcpu)
{
	int cpu = (long)hcpu;

	switch (action & ~CPU_TASKS_FROZEN) {

	case CPU_DOWN_FAILED:
	case CPU_ONLINE:
		smpboot_unpark_threads(cpu);
		break;

	default:
		break;
	}

	return NOTIFY_OK;
}

static struct notifier_block smpboot_thread_notifier = {
	.notifier_call = smpboot_thread_call,
	.priority = CPU_PRI_SMPBOOT,
};

void smpboot_thread_init(void)
{
	register_cpu_notifier(&smpboot_thread_notifier);
}

/**
 * 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)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
	enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE);

	while (st->state < target) {
		struct cpuhp_step *step;

		st->state++;
		step = cpuhp_ap_states + st->state;
		cpuhp_invoke_callback(cpu, st->state, step->startup);
	}
}

static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st)
{
	for (st->state--; st->state > st->target; st->state--) {
		struct cpuhp_step *step = cpuhp_bp_states + st->state;

		if (!step->skip_onerr)
			cpuhp_invoke_callback(cpu, st->state, step->teardown);
	}
}

/* Requires cpu_add_remove_lock to be held */
static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
	struct task_struct *idle;
	int prev_state, ret = 0;

	cpu_hotplug_begin();

	if (cpu_online(cpu) || !cpu_present(cpu)) {
		ret = -EINVAL;
		goto out;
	}

	/* Let it fail before we try to bring the cpu up */
	idle = idle_thread_get(cpu);
	if (IS_ERR(idle)) {
		ret = PTR_ERR(idle);
		goto out;
	}

	cpuhp_tasks_frozen = tasks_frozen;

	prev_state = st->state;
	st->target = target;
	while (st->state < st->target) {
		struct cpuhp_step *step;

		st->state++;
		step = cpuhp_bp_states + st->state;
		ret = cpuhp_invoke_callback(cpu, st->state, step->startup);
		if (ret) {
			st->target = prev_state;
			undo_cpu_up(cpu, st);
			break;
		}
	}
out:
	cpu_hotplug_done();
	return ret;
}

static int do_cpu_up(unsigned int cpu, enum cpuhp_state target)
{
	int err = 0;

	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;
		goto out;
	}

	err = _cpu_up(cpu, 0, target);
out:
	cpu_maps_update_done();
	return err;
}

int cpu_up(unsigned int cpu)
{
	return do_cpu_up(cpu, CPUHP_ONLINE);
}
EXPORT_SYMBOL_GPL(cpu_up);

#ifdef CONFIG_PM_SLEEP_SMP
static cpumask_var_t frozen_cpus;

int disable_nonboot_cpus(void)
{
	int cpu, first_cpu, error = 0;

	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
	 */
	cpumask_clear(frozen_cpus);

	pr_info("Disabling non-boot CPUs ...\n");
	for_each_online_cpu(cpu) {
		if (cpu == first_cpu)
			continue;
		trace_suspend_resume(TPS("CPU_OFF"), cpu, true);
		error = _cpu_down(cpu, 1, CPUHP_OFFLINE);
		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);
	else
		pr_err("Non-boot CPUs are not disabled\n");

	/*
	 * Make sure the CPUs won't be enabled by someone else. We need to do
	 * this even in case of failure as all disable_nonboot_cpus() users are
	 * supposed to do enable_nonboot_cpus() on the failure path.
	 */
	cpu_hotplug_disabled++;

	cpu_maps_update_done();
	return error;
}

void __weak arch_enable_nonboot_cpus_begin(void)
{
}

void __weak arch_enable_nonboot_cpus_end(void)
{
}

void enable_nonboot_cpus(void)
{
	int cpu, error;

	/* Allow everyone to use the CPU hotplug again */
	cpu_maps_update_begin();
	WARN_ON(--cpu_hotplug_disabled < 0);
	if (cpumask_empty(frozen_cpus))
		goto out;

	pr_info("Enabling non-boot CPUs ...\n");

	arch_enable_nonboot_cpus_begin();

	for_each_cpu(cpu, frozen_cpus) {
		trace_suspend_resume(TPS("CPU_ON"), cpu, true);
		error = _cpu_up(cpu, 1, CPUHP_ONLINE);
		trace_suspend_resume(TPS("CPU_ON"), cpu, false);
		if (!error) {
			pr_info("CPU%d is up\n", cpu);
			continue;
		}
		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;
	}

	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 */

#endif /* CONFIG_SMP */

/* Boot processor state steps */
static struct cpuhp_step cpuhp_bp_states[] = {
	[CPUHP_OFFLINE] = {
		.name			= "offline",
		.startup		= NULL,
		.teardown		= NULL,
	},
#ifdef CONFIG_SMP
	[CPUHP_CREATE_THREADS]= {
		.name			= "threads:create",
		.startup		= smpboot_create_threads,
		.teardown		= NULL,
	},
	[CPUHP_NOTIFY_PREPARE] = {
		.name			= "notify:prepare",
		.startup		= notify_prepare,
		.teardown		= notify_dead,
		.skip_onerr		= true,
	},
	[CPUHP_BRINGUP_CPU] = {
		.name			= "cpu:bringup",
		.startup		= bringup_cpu,
		.teardown		= NULL,
	},
	[CPUHP_TEARDOWN_CPU] = {
		.name			= "cpu:teardown",
		.startup		= NULL,
		.teardown		= takedown_cpu,
	},
	[CPUHP_NOTIFY_ONLINE] = {
		.name			= "notify:online",
		.startup		= notify_online,
		.teardown		= notify_down_prepare,
	},
#endif
	[CPUHP_ONLINE] = {
		.name			= "online",
		.startup		= NULL,
		.teardown		= NULL,
	},
};

/* Application processor state steps */
static struct cpuhp_step cpuhp_ap_states[] = {
#ifdef CONFIG_SMP
	[CPUHP_AP_NOTIFY_STARTING] = {
		.name			= "notify:starting",
		.startup		= notify_starting,
		.teardown		= notify_dying,
		.skip_onerr		= true,
	},
#endif
	[CPUHP_ONLINE] = {
		.name			= "online",
		.startup		= NULL,
		.teardown		= NULL,
	},
};

static bool cpuhp_is_ap_state(enum cpuhp_state state)
{
	return (state > CPUHP_AP_OFFLINE && state < CPUHP_AP_ONLINE);
}

static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state)
{
	struct cpuhp_step *sp;

	sp = cpuhp_is_ap_state(state) ? cpuhp_ap_states : cpuhp_bp_states;
	return sp + state;
}

#if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU)
static ssize_t show_cpuhp_state(struct device *dev,
				struct device_attribute *attr, char *buf)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);

	return sprintf(buf, "%d\n", st->state);
}
static DEVICE_ATTR(state, 0444, show_cpuhp_state, NULL);

static ssize_t show_cpuhp_target(struct device *dev,
				 struct device_attribute *attr, char *buf)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);

	return sprintf(buf, "%d\n", st->target);
}
static DEVICE_ATTR(target, 0444, show_cpuhp_target, NULL);

static struct attribute *cpuhp_cpu_attrs[] = {
	&dev_attr_state.attr,
	&dev_attr_target.attr,
	NULL
};

static struct attribute_group cpuhp_cpu_attr_group = {
	.attrs = cpuhp_cpu_attrs,
	.name = "hotplug",
	NULL
};

static ssize_t show_cpuhp_states(struct device *dev,
				 struct device_attribute *attr, char *buf)
{
	ssize_t cur, res = 0;
	int i;

	mutex_lock(&cpuhp_state_mutex);
	for (i = 0; i <= CPUHP_ONLINE; i++) {
		struct cpuhp_step *sp = cpuhp_get_step(i);

		if (sp->name) {
			cur = sprintf(buf, "%3d: %s\n", i, sp->name);
			buf += cur;
			res += cur;
		}
	}
	mutex_unlock(&cpuhp_state_mutex);
	return res;
}
static DEVICE_ATTR(states, 0444, show_cpuhp_states, NULL);

static struct attribute *cpuhp_cpu_root_attrs[] = {
	&dev_attr_states.attr,
	NULL
};

static struct attribute_group cpuhp_cpu_root_attr_group = {
	.attrs = cpuhp_cpu_root_attrs,
	.name = "hotplug",
	NULL
};

static int __init cpuhp_sysfs_init(void)
{
	int cpu, ret;

	ret = sysfs_create_group(&cpu_subsys.dev_root->kobj,
				 &cpuhp_cpu_root_attr_group);
	if (ret)
		return ret;

	for_each_possible_cpu(cpu) {
		struct device *dev = get_cpu_device(cpu);

		if (!dev)
			continue;
		ret = sysfs_create_group(&dev->kobj, &cpuhp_cpu_attr_group);
		if (ret)
			return ret;
	}
	return 0;
}
device_initcall(cpuhp_sysfs_init);
#endif

/*
 * 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
struct cpumask __cpu_possible_mask __read_mostly
	= {CPU_BITS_ALL};
#else
struct cpumask __cpu_possible_mask __read_mostly;
#endif
EXPORT_SYMBOL(__cpu_possible_mask);

struct cpumask __cpu_online_mask __read_mostly;
EXPORT_SYMBOL(__cpu_online_mask);

struct cpumask __cpu_present_mask __read_mostly;
EXPORT_SYMBOL(__cpu_present_mask);

struct cpumask __cpu_active_mask __read_mostly;
EXPORT_SYMBOL(__cpu_active_mask);

void init_cpu_present(const struct cpumask *src)
{
	cpumask_copy(&__cpu_present_mask, src);
}

void init_cpu_possible(const struct cpumask *src)
{
	cpumask_copy(&__cpu_possible_mask, src);
}

void init_cpu_online(const struct cpumask *src)
{
	cpumask_copy(&__cpu_online_mask, src);
}

/*
 * Activate the first processor.
 */
void __init boot_cpu_init(void)
{
	int cpu = smp_processor_id();

	/* Mark the boot cpu "present", "online" etc for SMP and UP case */
	set_cpu_online(cpu, true);
	set_cpu_active(cpu, true);
	set_cpu_present(cpu, true);
	set_cpu_possible(cpu, true);
}

/*
 * Must be called _AFTER_ setting up the per_cpu areas
 */
void __init boot_cpu_state_init(void)
{
	per_cpu_ptr(&cpuhp_state, smp_processor_id())->state = CPUHP_ONLINE;
}