728 lines · 17.1 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 "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 API's must be used when attempting * to serialize the updates to cpu_online_mask, cpu_present_mask. */void cpu_maps_update_begin(void){	mutex_lock(&cpu_add_remove_lock);} void cpu_maps_update_done(void){	mutex_unlock(&cpu_add_remove_lock);} 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;	struct mutex lock; /* Synchronizes accesses to refcount, */	/*	 * Also blocks the new readers during	 * an ongoing cpu hotplug operation.	 */	int refcount;} cpu_hotplug = {	.active_writer = NULL,	.lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),	.refcount = 0,}; void get_online_cpus(void){	might_sleep();	if (cpu_hotplug.active_writer == current)		return;	mutex_lock(&cpu_hotplug.lock);	cpu_hotplug.refcount++;	mutex_unlock(&cpu_hotplug.lock); }EXPORT_SYMBOL_GPL(get_online_cpus); void put_online_cpus(void){	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); }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. * */static void cpu_hotplug_begin(void){	cpu_hotplug.active_writer = current; 	for (;;) {		mutex_lock(&cpu_hotplug.lock);		if (likely(!cpu_hotplug.refcount))			break;		__set_current_state(TASK_UNINTERRUPTIBLE);		mutex_unlock(&cpu_hotplug.lock);		schedule();	}} static void cpu_hotplug_done(void){	cpu_hotplug.active_writer = NULL;	mutex_unlock(&cpu_hotplug.lock);} /* * 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();} #else /* #if CONFIG_HOTPLUG_CPU */static void cpu_hotplug_begin(void) {}static void cpu_hotplug_done(void) {}#endif	/* #else #if 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;} 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); 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); /** * 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) {		task_cputime(p, &utime, &stime);		if (task_cpu(p) == cpu && p->state == TASK_RUNNING &&		    (utime || stime))			printk(KERN_WARNING "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 __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);	/* 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);		printk("%s: attempt to take down CPU %u failed\n",				__func__, cpu);		goto out_release;	}	smpboot_park_threads(cpu); 	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 (!idle_cpu(cpu))		cpu_relax(); 	/* This actually kills the CPU. */	__cpu_die(cpu); 	/* CPU is completely dead: tell everyone.  Too late to complain. */	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*/ /* Requires cpu_add_remove_lock to be held */static int __cpuinit _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;	} 	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--;		printk(KERN_WARNING "%s: attempt to bring up CPU %u failed\n",				__func__, cpu);		goto out_notify;	} 	/* Arch-specific enabling code. */	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. */	cpu_notify(CPU_ONLINE | mod, hcpu); out_notify:	if (ret != 0)		__cpu_notify(CPU_UP_CANCELED | mod, hcpu, nr_calls, NULL);out:	cpu_hotplug_done(); 	return ret;} int __cpuinit cpu_up(unsigned int cpu){	int err = 0; #ifdef	CONFIG_MEMORY_HOTPLUG	int nid;	pg_data_t	*pgdat;#endif 	if (!cpu_possible(cpu)) {		printk(KERN_ERR "can't online cpu %d because it is not "			"configured as may-hotadd at boot time\n", cpu);#if defined(CONFIG_IA64)		printk(KERN_ERR "please check additional_cpus= boot "				"parameter\n");#endif		return -EINVAL;	} #ifdef	CONFIG_MEMORY_HOTPLUG	nid = cpu_to_node(cpu);	if (!node_online(nid)) {		err = mem_online_node(nid);		if (err)			return err;	} 	pgdat = NODE_DATA(nid);	if (!pgdat) {		printk(KERN_ERR			"Can't online cpu %d due to NULL pgdat\n", cpu);		return -ENOMEM;	} 	if (pgdat->node_zonelists->_zonerefs->zone == NULL) {		mutex_lock(&zonelists_mutex);		build_all_zonelists(NULL, NULL);		mutex_unlock(&zonelists_mutex);	}#endif 	cpu_maps_update_begin(); 	if (cpu_hotplug_disabled) {		err = -EBUSY;		goto out;	} 	err = _cpu_up(cpu, 0); out:	cpu_maps_update_done();	return err;}EXPORT_SYMBOL_GPL(cpu_up); #ifdef CONFIG_PM_SLEEP_SMPstatic 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); 	printk("Disabling non-boot CPUs ...\n");	for_each_online_cpu(cpu) {		if (cpu == first_cpu)			continue;		error = _cpu_down(cpu, 1);		if (!error)			cpumask_set_cpu(cpu, frozen_cpus);		else {

Lines 1–500 of 728.