summaryrefslogtreecommitdiff
path: root/kernel/cpu.c
blob: 38033db8d8ec3d8f23af3973560dc995782efbda (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
/* 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/module.h>
#include <linux/kthread.h>
#include <linux/stop_machine.h>
#include <linux/mutex.h>

/* This protects CPUs going up and down... */
static DEFINE_MUTEX(cpu_add_remove_lock);
static DEFINE_MUTEX(cpu_bitmask_lock);

static __cpuinitdata 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

/* Crappy recursive lock-takers in cpufreq! Complain loudly about idiots */
static struct task_struct *recursive;
static int recursive_depth;

void lock_cpu_hotplug(void)
{
	struct task_struct *tsk = current;

	if (tsk == recursive) {
		static int warnings = 10;
		if (warnings) {
			printk(KERN_ERR "Lukewarm IQ detected in hotplug locking\n");
			WARN_ON(1);
			warnings--;
		}
		recursive_depth++;
		return;
	}
	mutex_lock(&cpu_bitmask_lock);
	recursive = tsk;
}
EXPORT_SYMBOL_GPL(lock_cpu_hotplug);

void unlock_cpu_hotplug(void)
{
	WARN_ON(recursive != current);
	if (recursive_depth) {
		recursive_depth--;
		return;
	}
	recursive = NULL;
	mutex_unlock(&cpu_bitmask_lock);
}
EXPORT_SYMBOL_GPL(unlock_cpu_hotplug);

#endif	/* CONFIG_HOTPLUG_CPU */

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

#ifdef CONFIG_HOTPLUG_CPU

EXPORT_SYMBOL(register_cpu_notifier);

void unregister_cpu_notifier(struct notifier_block *nb)
{
	mutex_lock(&cpu_add_remove_lock);
	raw_notifier_chain_unregister(&cpu_chain, nb);
	mutex_unlock(&cpu_add_remove_lock);
}
EXPORT_SYMBOL(unregister_cpu_notifier);

static inline void check_for_tasks(int cpu)
{
	struct task_struct *p;

	write_lock_irq(&tasklist_lock);
	for_each_process(p) {
		if (task_cpu(p) == cpu &&
		    (!cputime_eq(p->utime, cputime_zero) ||
		     !cputime_eq(p->stime, cputime_zero)))
			printk(KERN_WARNING "Task %s (pid = %d) is on cpu %d\
				(state = %ld, flags = %x) \n",
				 p->comm, p->pid, 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 take_cpu_down(void *_param)
{
	struct take_cpu_down_param *param = _param;
	int err;

	raw_notifier_call_chain(&cpu_chain, CPU_DYING | param->mod,
				param->hcpu);
	/* Ensure this CPU doesn't handle any more interrupts. */
	err = __cpu_disable();
	if (err < 0)
		return err;

	/* Force idle task to run as soon as we yield: it should
	   immediately notice cpu is offline and die quickly. */
	sched_idle_next();
	return 0;
}

/* Requires cpu_add_remove_lock to be held */
static int _cpu_down(unsigned int cpu, int tasks_frozen)
{
	int err, nr_calls = 0;
	struct task_struct *p;
	cpumask_t old_allowed, tmp;
	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;

	raw_notifier_call_chain(&cpu_chain, CPU_LOCK_ACQUIRE, hcpu);
	err = __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE | mod,
					hcpu, -1, &nr_calls);
	if (err == NOTIFY_BAD) {
		__raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
					  hcpu, nr_calls, NULL);
		printk("%s: attempt to take down CPU %u failed\n",
				__FUNCTION__, cpu);
		err = -EINVAL;
		goto out_release;
	}

	/* Ensure that we are not runnable on dying cpu */
	old_allowed = current->cpus_allowed;
	tmp = CPU_MASK_ALL;
	cpu_clear(cpu, tmp);
	set_cpus_allowed(current, tmp);

	mutex_lock(&cpu_bitmask_lock);
	p = __stop_machine_run(take_cpu_down, &tcd_param, cpu);
	mutex_unlock(&cpu_bitmask_lock);

	if (IS_ERR(p) || cpu_online(cpu)) {
		/* CPU didn't die: tell everyone.  Can't complain. */
		if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
					    hcpu) == NOTIFY_BAD)
			BUG();

		if (IS_ERR(p)) {
			err = PTR_ERR(p);
			goto out_allowed;
		}
		goto out_thread;
	}

	/* Wait for it to sleep (leaving idle task). */
	while (!idle_cpu(cpu))
		yield();

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

	/* CPU is completely dead: tell everyone.  Too late to complain. */
	if (raw_notifier_call_chain(&cpu_chain, CPU_DEAD | mod,
				    hcpu) == NOTIFY_BAD)
		BUG();

	check_for_tasks(cpu);

out_thread:
	err = kthread_stop(p);
out_allowed:
	set_cpus_allowed(current, old_allowed);
out_release:
	raw_notifier_call_chain(&cpu_chain, CPU_LOCK_RELEASE, hcpu);
	return err;
}

int cpu_down(unsigned int cpu)
{
	int err = 0;

	mutex_lock(&cpu_add_remove_lock);
	if (cpu_hotplug_disabled)
		err = -EBUSY;
	else
		err = _cpu_down(cpu, 0);

	mutex_unlock(&cpu_add_remove_lock);
	return err;
}
#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;

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

	raw_notifier_call_chain(&cpu_chain, CPU_LOCK_ACQUIRE, hcpu);
	ret = __raw_notifier_call_chain(&cpu_chain, CPU_UP_PREPARE | mod, hcpu,
							-1, &nr_calls);
	if (ret == NOTIFY_BAD) {
		printk("%s: attempt to bring up CPU %u failed\n",
				__FUNCTION__, cpu);
		ret = -EINVAL;
		goto out_notify;
	}

	/* Arch-specific enabling code. */
	mutex_lock(&cpu_bitmask_lock);
	ret = __cpu_up(cpu);
	mutex_unlock(&cpu_bitmask_lock);
	if (ret != 0)
		goto out_notify;
	BUG_ON(!cpu_online(cpu));

	/* Now call notifier in preparation. */
	raw_notifier_call_chain(&cpu_chain, CPU_ONLINE | mod, hcpu);

out_notify:
	if (ret != 0)
		__raw_notifier_call_chain(&cpu_chain,
				CPU_UP_CANCELED | mod, hcpu, nr_calls, NULL);
	raw_notifier_call_chain(&cpu_chain, CPU_LOCK_RELEASE, hcpu);

	return ret;
}

int __cpuinit cpu_up(unsigned int cpu)
{
	int err = 0;

	mutex_lock(&cpu_add_remove_lock);
	if (cpu_hotplug_disabled)
		err = -EBUSY;
	else
		err = _cpu_up(cpu, 0);

	mutex_unlock(&cpu_add_remove_lock);
	return err;
}

#ifdef CONFIG_PM_SLEEP_SMP
static cpumask_t frozen_cpus;

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

	mutex_lock(&cpu_add_remove_lock);
	first_cpu = first_cpu(cpu_online_map);
	/* 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
	 */
	cpus_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) {
			cpu_set(cpu, frozen_cpus);
			printk("CPU%d is down\n", cpu);
		} else {
			printk(KERN_ERR "Error taking CPU%d down: %d\n",
				cpu, error);
			break;
		}
	}
	if (!error) {
		BUG_ON(num_online_cpus() > 1);
		/* Make sure the CPUs won't be enabled by someone else */
		cpu_hotplug_disabled = 1;
	} else {
		printk(KERN_ERR "Non-boot CPUs are not disabled\n");
	}
	mutex_unlock(&cpu_add_remove_lock);
	return error;
}

void enable_nonboot_cpus(void)
{
	int cpu, error;

	/* Allow everyone to use the CPU hotplug again */
	mutex_lock(&cpu_add_remove_lock);
	cpu_hotplug_disabled = 0;
	if (cpus_empty(frozen_cpus))
		goto out;

	printk("Enabling non-boot CPUs ...\n");
	for_each_cpu_mask(cpu, frozen_cpus) {
		error = _cpu_up(cpu, 1);
		if (!error) {
			printk("CPU%d is up\n", cpu);
			continue;
		}
		printk(KERN_WARNING "Error taking CPU%d up: %d\n", cpu, error);
	}
	cpus_clear(frozen_cpus);
out:
	mutex_unlock(&cpu_add_remove_lock);
}
#endif /* CONFIG_PM_SLEEP_SMP */