825 lines · 20.0 KB · C
RawDownload
/* 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 <trace/events/power.h> #include "smpboot.h" #ifdef CONFIG_SMP/* Serializes the updates to cpu_online_mask, cpu_present_mask */static DEFINE_MUTEX(cpu_add_remove_lock); /* * 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); bool try_get_online_cpus(void){	if (cpu_hotplug.active_writer == current)		return true;	if (!mutex_trylock(&cpu_hotplug.lock))		return false;	cpuhp_lock_acquire_tryread();	atomic_inc(&cpu_hotplug.refcount);	mutex_unlock(&cpu_hotplug.lock);	return true;}EXPORT_SYMBOL_GPL(try_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 = 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 __ref 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 __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 __ref 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 __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 dead_cpu){	struct task_struct *g, *p; 	read_lock_irq(&tasklist_lock);	do_each_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);	} while_each_thread(g, p);	read_unlock_irq(&tasklist_lock);} struct take_cpu_down_param {	unsigned long mod;	void *hcpu;}; /* Take this CPU down. */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. */	err = __cpu_disable();	if (err < 0)		return err; 	cpu_notify(CPU_DYING | param->mod, param->hcpu);	/* Give up timekeeping duties */	tick_handover_do_timer();	/* Park the stopper thread */	kthread_park(current);	return 0;} /* Requires cpu_add_remove_lock to be held */static int __ref _cpu_down(unsigned int cpu, int tasks_frozen){	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; 	if (!cpu_online(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;	} 	/*	 * 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(); 	smpboot_park_threads(cpu); 	/*	 * So now all preempt/rcu users must observe !cpu_active().	 */ 	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;	}	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; 	hotplug_cpu__broadcast_tick_pull(cpu);	/* This actually kills the CPU. */	__cpu_die(cpu); 	/* CPU is completely dead: tell everyone.  Too late to complain. */	tick_cleanup_dead_cpu(cpu);	cpu_notify_nofail(CPU_DEAD | mod, hcpu); 	check_for_tasks(cpu); out_release:	cpu_hotplug_done();	if (!err)		cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu);	return err;} int __ref cpu_down(unsigned int cpu){	int err; 	cpu_maps_update_begin(); 	if (cpu_hotplug_disabled) {		err = -EBUSY;		goto out;	} 	err = _cpu_down(cpu, 0); out:	cpu_maps_update_done();	return err;}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_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 __cpuinit smpboot_thread_init(void){	register_cpu_notifier(&smpboot_thread_notifier);} /* Requires cpu_add_remove_lock to be held */static int _cpu_up(unsigned int cpu, int tasks_frozen){	int ret, nr_calls = 0;	void *hcpu = (void *)(long)cpu;	unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;	struct task_struct *idle; 	cpu_hotplug_begin(); 	if (cpu_online(cpu) || !cpu_present(cpu)) {		ret = -EINVAL;		goto out;	}

Lines 1–500 of 825.