686 lines · 17.8 KB · C
RawDownload
// SPDX-License-Identifier: GPL-2.0-or-later/* * 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> */#include <linux/compiler.h>#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/nmi.h>#include <linux/sched/wake_q.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 */	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 {	struct task_struct	*thread; 	raw_spinlock_t		lock;	bool			enabled;	/* is this stopper enabled? */	struct list_head	works;		/* list of pending works */ 	struct cpu_stop_work	stop_work;	/* for stop_cpus */	unsigned long		caller;	cpu_stop_fn_t		fn;}; static DEFINE_PER_CPU(struct cpu_stopper, cpu_stopper);static bool stop_machine_initialized = false; void print_stop_info(const char *log_lvl, struct task_struct *task){	/*	 * If @task is a stopper task, it cannot migrate and task_cpu() is	 * stable.	 */	struct cpu_stopper *stopper = per_cpu_ptr(&cpu_stopper, task_cpu(task)); 	if (task != stopper->thread)		return; 	printk("%sStopper: %pS <- %pS\n", log_lvl, stopper->fn, (void *)stopper->caller);} /* static data for stop_cpus */static DEFINE_MUTEX(stop_cpus_mutex);static bool stop_cpus_in_progress; 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){	if (atomic_dec_and_test(&done->nr_todo))		complete(&done->completion);} static void __cpu_stop_queue_work(struct cpu_stopper *stopper,					struct cpu_stop_work *work,					struct wake_q_head *wakeq){	list_add_tail(&work->list, &stopper->works);	wake_q_add(wakeq, stopper->thread);} /* queue @work to @stopper.  if offline, @work is completed immediately */static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work){	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);	DEFINE_WAKE_Q(wakeq);	unsigned long flags;	bool enabled; 	preempt_disable();	raw_spin_lock_irqsave(&stopper->lock, flags);	enabled = stopper->enabled;	if (enabled)		__cpu_stop_queue_work(stopper, work, &wakeq);	else if (work->done)		cpu_stop_signal_done(work->done);	raw_spin_unlock_irqrestore(&stopper->lock, flags); 	wake_up_q(&wakeq);	preempt_enable(); 	return enabled;} /** * 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, .caller = _RET_IP_ }; 	cpu_stop_init_done(&done, 1);	if (!cpu_stop_queue_work(cpu, &work))		return -ENOENT;	/*	 * In case @cpu == smp_proccessor_id() we can avoid a sleep+wakeup	 * cycle by doing a preemption:	 */	cond_resched();	wait_for_completion(&done.completion);	return done.ret;} /* 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 {	cpu_stop_fn_t		fn;	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();	WRITE_ONCE(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);} notrace void __weak stop_machine_yield(const struct cpumask *cpumask){	cpu_relax();} /* 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 newstate, curstate = MULTI_STOP_NONE;	int cpu = smp_processor_id(), err = 0;	const struct cpumask *cpumask;	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) {		cpumask = cpu_online_mask;		is_active = cpu == cpumask_first(cpumask);	} else {		cpumask = msdata->active_cpus;		is_active = cpumask_test_cpu(cpu, cpumask);	} 	/* Simple state machine */	do {		/* Chill out and ensure we re-read multi_stop_state. */		stop_machine_yield(cpumask);		newstate = READ_ONCE(msdata->state);		if (newstate != curstate) {			curstate = newstate;			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);		} else if (curstate > MULTI_STOP_PREPARE) {			/*			 * At this stage all other CPUs we depend on must spin			 * in the same loop. Any reason for hard-lockup should			 * be detected and reported on their side.			 */			touch_nmi_watchdog();		}		rcu_momentary_dyntick_idle();	} while (curstate != MULTI_STOP_EXIT); 	local_irq_restore(flags);	return err;} static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,				    int cpu2, struct cpu_stop_work *work2){	struct cpu_stopper *stopper1 = per_cpu_ptr(&cpu_stopper, cpu1);	struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2);	DEFINE_WAKE_Q(wakeq);	int err; retry:	/*	 * The waking up of stopper threads has to happen in the same	 * scheduling context as the queueing.  Otherwise, there is a	 * possibility of one of the above stoppers being woken up by another	 * CPU, and preempting us. This will cause us to not wake up the other	 * stopper forever.	 */	preempt_disable();	raw_spin_lock_irq(&stopper1->lock);	raw_spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING); 	if (!stopper1->enabled || !stopper2->enabled) {		err = -ENOENT;		goto unlock;	} 	/*	 * Ensure that if we race with __stop_cpus() the stoppers won't get	 * queued up in reverse order leading to system deadlock.	 *	 * We can't miss stop_cpus_in_progress if queue_stop_cpus_work() has	 * queued a work on cpu1 but not on cpu2, we hold both locks.	 *	 * It can be falsely true but it is safe to spin until it is cleared,	 * queue_stop_cpus_work() does everything under preempt_disable().	 */	if (unlikely(stop_cpus_in_progress)) {		err = -EDEADLK;		goto unlock;	} 	err = 0;	__cpu_stop_queue_work(stopper1, work1, &wakeq);	__cpu_stop_queue_work(stopper2, work2, &wakeq); unlock:	raw_spin_unlock(&stopper2->lock);	raw_spin_unlock_irq(&stopper1->lock); 	if (unlikely(err == -EDEADLK)) {		preempt_enable(); 		while (stop_cpus_in_progress)			cpu_relax(); 		goto retry;	} 	wake_up_q(&wakeq);	preempt_enable(); 	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; 	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,		.caller = _RET_IP_,	}; 	cpu_stop_init_done(&done, 2);	set_state(&msdata, MULTI_STOP_PREPARE); 	if (cpu1 > cpu2)		swap(cpu1, cpu2);	if (cpu_stop_queue_two_works(cpu1, &work1, cpu2, &work2))		return -ENOENT; 	wait_for_completion(&done.completion);	return done.ret;} /** * 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. * * RETURNS: * true if cpu_stop_work was queued successfully and @fn will be called, * false otherwise. */bool 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, .caller = _RET_IP_, };	return cpu_stop_queue_work(cpu, work_buf);} static bool 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;	bool queued = false; 	/*	 * 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.	 */	preempt_disable();	stop_cpus_in_progress = true;	barrier();	for_each_cpu(cpu, cpumask) {		work = &per_cpu(cpu_stopper.stop_work, cpu);		work->fn = fn;		work->arg = arg;		work->done = done;		if (cpu_stop_queue_work(cpu, work))			queued = true;	}	barrier();	stop_cpus_in_progress = false;	preempt_enable(); 	return queued;} 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));	if (!queue_stop_cpus_work(cpumask, fn, arg, &done))		return -ENOENT;	wait_for_completion(&done.completion);	return done.ret;} /** * 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. */static 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;} static int cpu_stop_should_run(unsigned int cpu){	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);	unsigned long flags;	int run; 	raw_spin_lock_irqsave(&stopper->lock, flags);	run = !list_empty(&stopper->works);	raw_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; repeat:	work = NULL;	raw_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);	}	raw_spin_unlock_irq(&stopper->lock); 	if (work) {

Lines 1–500 of 686.