616 lines · 16.3 KB · C
RawDownload
/* * 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/init.h>#include <linux/kthread.h>#include <linux/export.h>#include <linux/percpu.h>#include <linux/sched.h>#include <linux/stop_machine.h>#include <linux/interrupt.h>#include <linux/kallsyms.h>#include <linux/smpboot.h>#include <linux/atomic.h>#include <linux/lglock.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;	bool			enabled;	/* is this stopper enabled? */	struct list_head	works;		/* list of pending works */}; static DEFINE_PER_CPU(struct cpu_stopper, cpu_stopper);static DEFINE_PER_CPU(struct task_struct *, cpu_stopper_task);static bool stop_machine_initialized = false; /* * Avoids a race between stop_two_cpus and global stop_cpus, where * the stoppers could get queued up in reverse order, leading to * system deadlock. Using an lglock means stop_two_cpus remains * relatively cheap. */DEFINE_STATIC_LGLOCK(stop_cpus_lock); 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_done *done, bool executed){	if (done) {		if (executed)			done->executed = true;		if (atomic_dec_and_test(&done->nr_todo))			complete(&done->completion);	}} /* queue @work to @stopper.  if offline, @work is completed immediately */static void cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work){	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);	struct task_struct *p = per_cpu(cpu_stopper_task, cpu); 	unsigned long flags; 	spin_lock_irqsave(&stopper->lock, flags); 	if (stopper->enabled) {		list_add_tail(&work->list, &stopper->works);		wake_up_process(p);	} else		cpu_stop_signal_done(work->done, false); 	spin_unlock_irqrestore(&stopper->lock, flags);} /** * stop_one_cpu - stop a cpu * @cpu: cpu to stop * @fn: function to execute * @arg: argument to @fn * * Execute @fn(@arg) on @cpu.  @fn is run in a process context with * the highest priority preempting any task on the cpu and * monopolizing it.  This function returns after the execution is * complete. * * This function doesn't guarantee @cpu stays online till @fn * completes.  If @cpu goes down in the middle, execution may happen * partially or fully on different cpus.  @fn should either be ready * for that or the caller should ensure that @cpu stays online until * this function completes. * * CONTEXT: * Might sleep. * * RETURNS: * -ENOENT if @fn(@arg) was not executed because @cpu was offline; * otherwise, the return value of @fn. */int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg){	struct cpu_stop_done done;	struct cpu_stop_work work = { .fn = fn, .arg = arg, .done = &done }; 	cpu_stop_init_done(&done, 1);	cpu_stop_queue_work(cpu, &work);	wait_for_completion(&done.completion);	return done.executed ? done.ret : -ENOENT;} /* This controls the threads on each CPU. */enum multi_stop_state {	/* Dummy starting state for thread. */	MULTI_STOP_NONE,	/* Awaiting everyone to be scheduled. */	MULTI_STOP_PREPARE,	/* Disable interrupts. */	MULTI_STOP_DISABLE_IRQ,	/* Run the function */	MULTI_STOP_RUN,	/* Exit */	MULTI_STOP_EXIT,}; struct multi_stop_data {	int			(*fn)(void *);	void			*data;	/* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */	unsigned int		num_threads;	const struct cpumask	*active_cpus; 	enum multi_stop_state	state;	atomic_t		thread_ack;}; static void set_state(struct multi_stop_data *msdata,		      enum multi_stop_state newstate){	/* Reset ack counter. */	atomic_set(&msdata->thread_ack, msdata->num_threads);	smp_wmb();	msdata->state = newstate;} /* Last one to ack a state moves to the next state. */static void ack_state(struct multi_stop_data *msdata){	if (atomic_dec_and_test(&msdata->thread_ack))		set_state(msdata, msdata->state + 1);} /* This is the cpu_stop function which stops the CPU. */static int multi_cpu_stop(void *data){	struct multi_stop_data *msdata = data;	enum multi_stop_state curstate = MULTI_STOP_NONE;	int cpu = smp_processor_id(), err = 0;	unsigned long flags;	bool is_active; 	/*	 * When called from stop_machine_from_inactive_cpu(), irq might	 * already be disabled.  Save the state and restore it on exit.	 */	local_save_flags(flags); 	if (!msdata->active_cpus)		is_active = cpu == cpumask_first(cpu_online_mask);	else		is_active = cpumask_test_cpu(cpu, msdata->active_cpus); 	/* Simple state machine */	do {		/* Chill out and ensure we re-read multi_stop_state. */		cpu_relax();		if (msdata->state != curstate) {			curstate = msdata->state;			switch (curstate) {			case MULTI_STOP_DISABLE_IRQ:				local_irq_disable();				hard_irq_disable();				break;			case MULTI_STOP_RUN:				if (is_active)					err = msdata->fn(msdata->data);				break;			default:				break;			}			ack_state(msdata);		}	} while (curstate != MULTI_STOP_EXIT); 	local_irq_restore(flags);	return err;} /** * stop_two_cpus - stops two cpus * @cpu1: the cpu to stop * @cpu2: the other cpu to stop * @fn: function to execute * @arg: argument to @fn * * Stops both the current and specified CPU and runs @fn on one of them. * * returns when both are completed. */int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *arg){	struct cpu_stop_done done;	struct cpu_stop_work work1, work2;	struct multi_stop_data msdata; 	preempt_disable();	msdata = (struct multi_stop_data){		.fn = fn,		.data = arg,		.num_threads = 2,		.active_cpus = cpumask_of(cpu1),	}; 	work1 = work2 = (struct cpu_stop_work){		.fn = multi_cpu_stop,		.arg = &msdata,		.done = &done	}; 	cpu_stop_init_done(&done, 2);	set_state(&msdata, MULTI_STOP_PREPARE); 	/*	 * If we observe both CPUs active we know _cpu_down() cannot yet have	 * queued its stop_machine works and therefore ours will get executed	 * first. Or its not either one of our CPUs that's getting unplugged,	 * in which case we don't care.	 *	 * This relies on the stopper workqueues to be FIFO.	 */	if (!cpu_active(cpu1) || !cpu_active(cpu2)) {		preempt_enable();		return -ENOENT;	} 	lg_double_lock(&stop_cpus_lock, cpu1, cpu2);	cpu_stop_queue_work(cpu1, &work1);	cpu_stop_queue_work(cpu2, &work2);	lg_double_unlock(&stop_cpus_lock, cpu1, cpu2); 	preempt_enable(); 	wait_for_completion(&done.completion); 	return done.executed ? done.ret : -ENOENT;} /** * stop_one_cpu_nowait - stop a cpu but don't wait for completion * @cpu: cpu to stop * @fn: function to execute * @arg: argument to @fn * @work_buf: pointer to cpu_stop_work structure * * Similar to stop_one_cpu() but doesn't wait for completion.  The * caller is responsible for ensuring @work_buf is currently unused * and will remain untouched until stopper starts executing @fn. * * CONTEXT: * Don't care. */void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,			struct cpu_stop_work *work_buf){	*work_buf = (struct cpu_stop_work){ .fn = fn, .arg = arg, };	cpu_stop_queue_work(cpu, work_buf);} /* static data for stop_cpus */static DEFINE_MUTEX(stop_cpus_mutex);static DEFINE_PER_CPU(struct cpu_stop_work, stop_cpus_work); static void queue_stop_cpus_work(const struct cpumask *cpumask,				 cpu_stop_fn_t fn, void *arg,				 struct cpu_stop_done *done){	struct cpu_stop_work *work;	unsigned int cpu; 	/* initialize works and done */	for_each_cpu(cpu, cpumask) {		work = &per_cpu(stop_cpus_work, cpu);		work->fn = fn;		work->arg = arg;		work->done = done;	} 	/*	 * Disable preemption while queueing to avoid getting	 * preempted by a stopper which might wait for other stoppers	 * to enter @fn which can lead to deadlock.	 */	lg_global_lock(&stop_cpus_lock);	for_each_cpu(cpu, cpumask)		cpu_stop_queue_work(cpu, &per_cpu(stop_cpus_work, cpu));	lg_global_unlock(&stop_cpus_lock);} static int __stop_cpus(const struct cpumask *cpumask,		       cpu_stop_fn_t fn, void *arg){	struct cpu_stop_done done; 	cpu_stop_init_done(&done, cpumask_weight(cpumask));	queue_stop_cpus_work(cpumask, fn, arg, &done);	wait_for_completion(&done.completion);	return done.executed ? done.ret : -ENOENT;} /** * stop_cpus - stop multiple cpus * @cpumask: cpus to stop * @fn: function to execute * @arg: argument to @fn * * Execute @fn(@arg) on online cpus in @cpumask.  On each target cpu, * @fn is run in a process context with the highest priority * preempting any task on the cpu and monopolizing it.  This function * returns after all executions are complete. * * This function doesn't guarantee the cpus in @cpumask stay online * till @fn completes.  If some cpus go down in the middle, execution * on the cpu may happen partially or fully on different cpus.  @fn * should either be ready for that or the caller should ensure that * the cpus stay online until this function completes. * * All stop_cpus() calls are serialized making it safe for @fn to wait * for all cpus to start executing it. * * CONTEXT: * Might sleep. * * RETURNS: * -ENOENT if @fn(@arg) was not executed at all because all cpus in * @cpumask were offline; otherwise, 0 if all executions of @fn * returned 0, any non zero return value if any returned non zero. */int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg){	int ret; 	/* static works are used, process one request at a time */	mutex_lock(&stop_cpus_mutex);	ret = __stop_cpus(cpumask, fn, arg);	mutex_unlock(&stop_cpus_mutex);	return ret;} /** * try_stop_cpus - try to stop multiple cpus * @cpumask: cpus to stop * @fn: function to execute * @arg: argument to @fn * * Identical to stop_cpus() except that it fails with -EAGAIN if * someone else is already using the facility. * * CONTEXT: * Might sleep. * * RETURNS: * -EAGAIN if someone else is already stopping cpus, -ENOENT if * @fn(@arg) was not executed at all because all cpus in @cpumask were * offline; otherwise, 0 if all executions of @fn returned 0, any non * zero return value if any returned non zero. */int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg){	int ret; 	/* static works are used, process one request at a time */	if (!mutex_trylock(&stop_cpus_mutex))		return -EAGAIN;	ret = __stop_cpus(cpumask, fn, arg);	mutex_unlock(&stop_cpus_mutex);	return ret;} static int cpu_stop_should_run(unsigned int cpu){	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);	unsigned long flags;	int run; 	spin_lock_irqsave(&stopper->lock, flags);	run = !list_empty(&stopper->works);	spin_unlock_irqrestore(&stopper->lock, flags);	return run;} static void cpu_stopper_thread(unsigned int cpu){	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);	struct cpu_stop_work *work;	int ret; repeat:	work = NULL;	spin_lock_irq(&stopper->lock);	if (!list_empty(&stopper->works)) {		work = list_first_entry(&stopper->works,					struct cpu_stop_work, list);		list_del_init(&work->list);	}	spin_unlock_irq(&stopper->lock); 	if (work) {		cpu_stop_fn_t fn = work->fn;		void *arg = work->arg;		struct cpu_stop_done *done = work->done;		char ksym_buf[KSYM_NAME_LEN] __maybe_unused; 		/* cpu stop callbacks are not allowed to sleep */		preempt_disable(); 		ret = fn(arg);		if (ret)			done->ret = ret; 		/* restore preemption and check it's still balanced */		preempt_enable();		WARN_ONCE(preempt_count(),			  "cpu_stop: %s(%p) leaked preempt count\n",			  kallsyms_lookup((unsigned long)fn, NULL, NULL, NULL,					  ksym_buf), arg); 		cpu_stop_signal_done(done, true);		goto repeat;	}} extern void sched_set_stop_task(int cpu, struct task_struct *stop); static void cpu_stop_create(unsigned int cpu){	sched_set_stop_task(cpu, per_cpu(cpu_stopper_task, cpu));} static void cpu_stop_park(unsigned int cpu){	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);	struct cpu_stop_work *work;	unsigned long flags; 	/* drain remaining works */	spin_lock_irqsave(&stopper->lock, flags);	list_for_each_entry(work, &stopper->works, list)		cpu_stop_signal_done(work->done, false);	stopper->enabled = false;	spin_unlock_irqrestore(&stopper->lock, flags);} static void cpu_stop_unpark(unsigned int cpu){	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); 	spin_lock_irq(&stopper->lock);	stopper->enabled = true;	spin_unlock_irq(&stopper->lock);} static struct smp_hotplug_thread cpu_stop_threads = {	.store			= &cpu_stopper_task,	.thread_should_run	= cpu_stop_should_run,	.thread_fn		= cpu_stopper_thread,	.thread_comm		= "migration/%u",	.create			= cpu_stop_create,	.setup			= cpu_stop_unpark,	.park			= cpu_stop_park,	.pre_unpark		= cpu_stop_unpark,	.selfparking		= true,}; static int __init cpu_stop_init(void){

Lines 1–500 of 616.