cpu.c 39.0 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12
/* 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>
13 14
#include <linux/oom.h>
#include <linux/rcupdate.h>
15
#include <linux/export.h>
16
#include <linux/bug.h>
L
Linus Torvalds 已提交
17 18
#include <linux/kthread.h>
#include <linux/stop_machine.h>
19
#include <linux/mutex.h>
20
#include <linux/gfp.h>
21
#include <linux/suspend.h>
22
#include <linux/lockdep.h>
23
#include <linux/tick.h>
24
#include <linux/irq.h>
25
#include <linux/smpboot.h>
26

27
#include <trace/events/power.h>
28 29
#define CREATE_TRACE_POINTS
#include <trace/events/cpuhp.h>
L
Linus Torvalds 已提交
30

31 32
#include "smpboot.h"

33 34 35 36
/**
 * cpuhp_cpu_state - Per cpu hotplug state storage
 * @state:	The current cpu state
 * @target:	The target state
37 38 39 40 41 42
 * @thread:	Pointer to the hotplug thread
 * @should_run:	Thread should execute
 * @cb_stat:	The state for a single callback (install/uninstall)
 * @cb:		Single callback function (install/uninstall)
 * @result:	Result of the operation
 * @done:	Signal completion to the issuer of the task
43 44 45 46
 */
struct cpuhp_cpu_state {
	enum cpuhp_state	state;
	enum cpuhp_state	target;
47 48 49 50 51 52 53 54
#ifdef CONFIG_SMP
	struct task_struct	*thread;
	bool			should_run;
	enum cpuhp_state	cb_state;
	int			(*cb)(unsigned int cpu);
	int			result;
	struct completion	done;
#endif
55 56 57 58 59 60 61 62 63 64 65
};

static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state);

/**
 * cpuhp_step - Hotplug state machine step
 * @name:	Name of the step
 * @startup:	Startup function of the step
 * @teardown:	Teardown function of the step
 * @skip_onerr:	Do not invoke the functions on error rollback
 *		Will go away once the notifiers	are gone
66
 * @cant_stop:	Bringup/teardown can't be stopped at this step
67 68 69 70 71 72
 */
struct cpuhp_step {
	const char	*name;
	int		(*startup)(unsigned int cpu);
	int		(*teardown)(unsigned int cpu);
	bool		skip_onerr;
73
	bool		cant_stop;
74 75
};

76
static DEFINE_MUTEX(cpuhp_state_mutex);
77
static struct cpuhp_step cpuhp_bp_states[];
78
static struct cpuhp_step cpuhp_ap_states[];
79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101

/**
 * cpuhp_invoke_callback _ Invoke the callbacks for a given state
 * @cpu:	The cpu for which the callback should be invoked
 * @step:	The step in the state machine
 * @cb:		The callback function to invoke
 *
 * Called from cpu hotplug and from the state register machinery
 */
static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state step,
				 int (*cb)(unsigned int))
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
	int ret = 0;

	if (cb) {
		trace_cpuhp_enter(cpu, st->target, step, cb);
		ret = cb(cpu);
		trace_cpuhp_exit(cpu, st->state, step, ret);
	}
	return ret;
}

102
#ifdef CONFIG_SMP
103
/* Serializes the updates to cpu_online_mask, cpu_present_mask */
104
static DEFINE_MUTEX(cpu_add_remove_lock);
105 106
bool cpuhp_tasks_frozen;
EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen);
L
Linus Torvalds 已提交
107

108
/*
109 110 111 112 113
 * 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().
114 115 116 117 118
 */
void cpu_maps_update_begin(void)
{
	mutex_lock(&cpu_add_remove_lock);
}
119
EXPORT_SYMBOL(cpu_notifier_register_begin);
120 121 122 123 124

void cpu_maps_update_done(void)
{
	mutex_unlock(&cpu_add_remove_lock);
}
125
EXPORT_SYMBOL(cpu_notifier_register_done);
126

127
static RAW_NOTIFIER_HEAD(cpu_chain);
L
Linus Torvalds 已提交
128

129 130 131 132 133
/* 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;

134 135
#ifdef CONFIG_HOTPLUG_CPU

136 137
static struct {
	struct task_struct *active_writer;
138 139 140 141
	/* 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;
142 143 144 145
	/*
	 * Also blocks the new readers during
	 * an ongoing cpu hotplug operation.
	 */
146
	atomic_t refcount;
147 148 149 150

#ifdef CONFIG_DEBUG_LOCK_ALLOC
	struct lockdep_map dep_map;
#endif
151 152
} cpu_hotplug = {
	.active_writer = NULL,
153
	.wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq),
154
	.lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),
155 156 157
#ifdef CONFIG_DEBUG_LOCK_ALLOC
	.dep_map = {.name = "cpu_hotplug.lock" },
#endif
158
};
159

160 161
/* 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)
162 163
#define cpuhp_lock_acquire_tryread() \
				  lock_map_acquire_tryread(&cpu_hotplug.dep_map)
164 165 166
#define cpuhp_lock_acquire()      lock_map_acquire(&cpu_hotplug.dep_map)
#define cpuhp_lock_release()      lock_map_release(&cpu_hotplug.dep_map)

167

168
void get_online_cpus(void)
169
{
170 171
	might_sleep();
	if (cpu_hotplug.active_writer == current)
172
		return;
173
	cpuhp_lock_acquire_read();
174
	mutex_lock(&cpu_hotplug.lock);
175
	atomic_inc(&cpu_hotplug.refcount);
176
	mutex_unlock(&cpu_hotplug.lock);
177
}
178
EXPORT_SYMBOL_GPL(get_online_cpus);
179

180
void put_online_cpus(void)
181
{
182 183
	int refcount;

184
	if (cpu_hotplug.active_writer == current)
185
		return;
186

187 188 189 190 191 192
	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);
193

194
	cpuhp_lock_release();
195

196
}
197
EXPORT_SYMBOL_GPL(put_online_cpus);
198

199 200 201 202 203 204 205
/*
 * 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
 *
206 207
 * Since cpu_hotplug_begin() is always called after invoking
 * cpu_maps_update_begin(), we can be sure that only one writer is active.
208 209 210 211 212 213 214 215 216 217
 *
 * 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
218
 * get_online_cpus() not an api which is called all that often.
219 220
 *
 */
221
void cpu_hotplug_begin(void)
222
{
223
	DEFINE_WAIT(wait);
224

225
	cpu_hotplug.active_writer = current;
226
	cpuhp_lock_acquire();
227

228 229
	for (;;) {
		mutex_lock(&cpu_hotplug.lock);
230 231 232
		prepare_to_wait(&cpu_hotplug.wq, &wait, TASK_UNINTERRUPTIBLE);
		if (likely(!atomic_read(&cpu_hotplug.refcount)))
				break;
233 234 235
		mutex_unlock(&cpu_hotplug.lock);
		schedule();
	}
236
	finish_wait(&cpu_hotplug.wq, &wait);
237 238
}

239
void cpu_hotplug_done(void)
240 241 242
{
	cpu_hotplug.active_writer = NULL;
	mutex_unlock(&cpu_hotplug.lock);
243
	cpuhp_lock_release();
244
}
245

246 247 248 249 250 251 252 253 254 255
/*
 * 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();
256
	cpu_hotplug_disabled++;
257 258
	cpu_maps_update_done();
}
259
EXPORT_SYMBOL_GPL(cpu_hotplug_disable);
260 261 262 263

void cpu_hotplug_enable(void)
{
	cpu_maps_update_begin();
264
	WARN_ON(--cpu_hotplug_disabled < 0);
265 266
	cpu_maps_update_done();
}
267
EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
268
#endif	/* CONFIG_HOTPLUG_CPU */
269

L
Linus Torvalds 已提交
270
/* Need to know about CPUs going up/down? */
271
int register_cpu_notifier(struct notifier_block *nb)
L
Linus Torvalds 已提交
272
{
273
	int ret;
274
	cpu_maps_update_begin();
275
	ret = raw_notifier_chain_register(&cpu_chain, nb);
276
	cpu_maps_update_done();
277
	return ret;
L
Linus Torvalds 已提交
278
}
279

280
int __register_cpu_notifier(struct notifier_block *nb)
281 282 283 284
{
	return raw_notifier_chain_register(&cpu_chain, nb);
}

285
static int __cpu_notify(unsigned long val, unsigned int cpu, int nr_to_call,
286 287
			int *nr_calls)
{
288 289 290
	unsigned long mod = cpuhp_tasks_frozen ? CPU_TASKS_FROZEN : 0;
	void *hcpu = (void *)(long)cpu;

291 292
	int ret;

293
	ret = __raw_notifier_call_chain(&cpu_chain, val | mod, hcpu, nr_to_call,
294
					nr_calls);
295 296

	return notifier_to_errno(ret);
297 298
}

299
static int cpu_notify(unsigned long val, unsigned int cpu)
300
{
301
	return __cpu_notify(val, cpu, -1, NULL);
302 303
}

304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325
/* Notifier wrappers for transitioning to state machine */
static int notify_prepare(unsigned int cpu)
{
	int nr_calls = 0;
	int ret;

	ret = __cpu_notify(CPU_UP_PREPARE, cpu, -1, &nr_calls);
	if (ret) {
		nr_calls--;
		printk(KERN_WARNING "%s: attempt to bring up CPU %u failed\n",
				__func__, cpu);
		__cpu_notify(CPU_UP_CANCELED, cpu, nr_calls, NULL);
	}
	return ret;
}

static int notify_online(unsigned int cpu)
{
	cpu_notify(CPU_ONLINE, cpu);
	return 0;
}

326 327 328 329 330 331
static int notify_starting(unsigned int cpu)
{
	cpu_notify(CPU_STARTING, cpu);
	return 0;
}

332 333 334 335 336 337 338 339 340 341 342 343 344 345 346
static int bringup_cpu(unsigned int cpu)
{
	struct task_struct *idle = idle_thread_get(cpu);
	int ret;

	/* Arch-specific enabling code. */
	ret = __cpu_up(cpu, idle);
	if (ret) {
		cpu_notify(CPU_UP_CANCELED, cpu);
		return ret;
	}
	BUG_ON(!cpu_online(cpu));
	return 0;
}

347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411
/*
 * Hotplug state machine related functions
 */
static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st,
			  struct cpuhp_step *steps)
{
	for (st->state++; st->state < st->target; st->state++) {
		struct cpuhp_step *step = steps + st->state;

		if (!step->skip_onerr)
			cpuhp_invoke_callback(cpu, st->state, step->startup);
	}
}

static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
				struct cpuhp_step *steps, enum cpuhp_state target)
{
	enum cpuhp_state prev_state = st->state;
	int ret = 0;

	for (; st->state > target; st->state--) {
		struct cpuhp_step *step = steps + st->state;

		ret = cpuhp_invoke_callback(cpu, st->state, step->teardown);
		if (ret) {
			st->target = prev_state;
			undo_cpu_down(cpu, st, steps);
			break;
		}
	}
	return ret;
}

static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st,
			struct cpuhp_step *steps)
{
	for (st->state--; st->state > st->target; st->state--) {
		struct cpuhp_step *step = steps + st->state;

		if (!step->skip_onerr)
			cpuhp_invoke_callback(cpu, st->state, step->teardown);
	}
}

static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
			      struct cpuhp_step *steps, enum cpuhp_state target)
{
	enum cpuhp_state prev_state = st->state;
	int ret = 0;

	while (st->state < target) {
		struct cpuhp_step *step;

		st->state++;
		step = steps + st->state;
		ret = cpuhp_invoke_callback(cpu, st->state, step->startup);
		if (ret) {
			st->target = prev_state;
			undo_cpu_up(cpu, st, steps);
			break;
		}
	}
	return ret;
}

412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431
/*
 * The cpu hotplug threads manage the bringup and teardown of the cpus
 */
static void cpuhp_create(unsigned int cpu)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);

	init_completion(&st->done);
}

static int cpuhp_should_run(unsigned int cpu)
{
	struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);

	return st->should_run;
}

/* Execute the teardown callbacks. Used to be CPU_DOWN_PREPARE */
static int cpuhp_ap_offline(unsigned int cpu, struct cpuhp_cpu_state *st)
{
432
	enum cpuhp_state target = max((int)st->target, CPUHP_TEARDOWN_CPU);
433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471

	return cpuhp_down_callbacks(cpu, st, cpuhp_ap_states, target);
}

/* Execute the online startup callbacks. Used to be CPU_ONLINE */
static int cpuhp_ap_online(unsigned int cpu, struct cpuhp_cpu_state *st)
{
	return cpuhp_up_callbacks(cpu, st, cpuhp_ap_states, st->target);
}

/*
 * Execute teardown/startup callbacks on the plugged cpu. Also used to invoke
 * callbacks when a state gets [un]installed at runtime.
 */
static void cpuhp_thread_fun(unsigned int cpu)
{
	struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
	int ret = 0;

	/*
	 * Paired with the mb() in cpuhp_kick_ap_work and
	 * cpuhp_invoke_ap_callback, so the work set is consistent visible.
	 */
	smp_mb();
	if (!st->should_run)
		return;

	st->should_run = false;

	/* Single callback invocation for [un]install ? */
	if (st->cb) {
		if (st->cb_state < CPUHP_AP_ONLINE) {
			local_irq_disable();
			ret = cpuhp_invoke_callback(cpu, st->cb_state, st->cb);
			local_irq_enable();
		} else {
			ret = cpuhp_invoke_callback(cpu, st->cb_state, st->cb);
		}
	} else {
472 473 474
		/* Cannot happen .... */
		BUG_ON(st->state < CPUHP_KICK_AP_THREAD);

475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507
		/* Regular hotplug work */
		if (st->state < st->target)
			ret = cpuhp_ap_online(cpu, st);
		else if (st->state > st->target)
			ret = cpuhp_ap_offline(cpu, st);
	}
	st->result = ret;
	complete(&st->done);
}

/* Invoke a single callback on a remote cpu */
static int cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state,
				    int (*cb)(unsigned int))
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);

	if (!cpu_online(cpu))
		return 0;

	st->cb_state = state;
	st->cb = cb;
	/*
	 * Make sure the above stores are visible before should_run becomes
	 * true. Paired with the mb() above in cpuhp_thread_fun()
	 */
	smp_mb();
	st->should_run = true;
	wake_up_process(st->thread);
	wait_for_completion(&st->done);
	return st->result;
}

/* Regular hotplug invocation of the AP hotplug thread */
508
static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st)
509 510 511 512 513 514 515 516 517 518
{
	st->result = 0;
	st->cb = NULL;
	/*
	 * Make sure the above stores are visible before should_run becomes
	 * true. Paired with the mb() above in cpuhp_thread_fun()
	 */
	smp_mb();
	st->should_run = true;
	wake_up_process(st->thread);
519 520 521 522 523 524 525 526 527
}

static int cpuhp_kick_ap_work(unsigned int cpu)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
	enum cpuhp_state state = st->state;

	trace_cpuhp_enter(cpu, st->target, state, cpuhp_kick_ap_work);
	__cpuhp_kick_ap_work(st);
528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547
	wait_for_completion(&st->done);
	trace_cpuhp_exit(cpu, st->state, state, st->result);
	return st->result;
}

static struct smp_hotplug_thread cpuhp_threads = {
	.store			= &cpuhp_state.thread,
	.create			= &cpuhp_create,
	.thread_should_run	= cpuhp_should_run,
	.thread_fn		= cpuhp_thread_fun,
	.thread_comm		= "cpuhp/%u",
	.selfparking		= true,
};

void __init cpuhp_threads_init(void)
{
	BUG_ON(smpboot_register_percpu_thread(&cpuhp_threads));
	kthread_unpark(this_cpu_read(cpuhp_state.thread));
}

548
#ifdef CONFIG_HOTPLUG_CPU
L
Linus Torvalds 已提交
549
EXPORT_SYMBOL(register_cpu_notifier);
550
EXPORT_SYMBOL(__register_cpu_notifier);
551
void unregister_cpu_notifier(struct notifier_block *nb)
L
Linus Torvalds 已提交
552
{
553
	cpu_maps_update_begin();
554
	raw_notifier_chain_unregister(&cpu_chain, nb);
555
	cpu_maps_update_done();
L
Linus Torvalds 已提交
556 557 558
}
EXPORT_SYMBOL(unregister_cpu_notifier);

559
void __unregister_cpu_notifier(struct notifier_block *nb)
560 561 562 563 564
{
	raw_notifier_chain_unregister(&cpu_chain, nb);
}
EXPORT_SYMBOL(__unregister_cpu_notifier);

565 566 567 568 569 570 571 572 573 574 575 576
/**
 * 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.
 */
577 578 579 580 581 582 583 584 585 586 587
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.
	 */
588
	WARN_ON(cpu_online(cpu));
589 590 591 592
	rcu_read_lock();
	for_each_process(p) {
		struct task_struct *t;

593 594 595 596
		/*
		 * Main thread might exit, but other threads may still have
		 * a valid mm. Find one.
		 */
597 598 599 600 601 602 603 604 605
		t = find_lock_task_mm(p);
		if (!t)
			continue;
		cpumask_clear_cpu(cpu, mm_cpumask(t->mm));
		task_unlock(t);
	}
	rcu_read_unlock();
}

K
Kirill Tkhai 已提交
606
static inline void check_for_tasks(int dead_cpu)
L
Linus Torvalds 已提交
607
{
K
Kirill Tkhai 已提交
608
	struct task_struct *g, *p;
L
Linus Torvalds 已提交
609

610 611
	read_lock(&tasklist_lock);
	for_each_process_thread(g, p) {
K
Kirill Tkhai 已提交
612 613 614 615 616 617 618 619 620 621 622 623 624 625
		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);
626 627
	}
	read_unlock(&tasklist_lock);
L
Linus Torvalds 已提交
628 629
}

630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648
static void cpu_notify_nofail(unsigned long val, unsigned int cpu)
{
	BUG_ON(cpu_notify(val, cpu));
}

static int notify_down_prepare(unsigned int cpu)
{
	int err, nr_calls = 0;

	err = __cpu_notify(CPU_DOWN_PREPARE, cpu, -1, &nr_calls);
	if (err) {
		nr_calls--;
		__cpu_notify(CPU_DOWN_FAILED, cpu, nr_calls, NULL);
		pr_warn("%s: attempt to take down CPU %u failed\n",
				__func__, cpu);
	}
	return err;
}

649 650 651 652 653 654
static int notify_dying(unsigned int cpu)
{
	cpu_notify(CPU_DYING, cpu);
	return 0;
}

L
Linus Torvalds 已提交
655
/* Take this CPU down. */
656
static int take_cpu_down(void *_param)
L
Linus Torvalds 已提交
657
{
658 659
	struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
	enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE);
660
	int err, cpu = smp_processor_id();
L
Linus Torvalds 已提交
661 662 663 664

	/* Ensure this CPU doesn't handle any more interrupts. */
	err = __cpu_disable();
	if (err < 0)
Z
Zwane Mwaikambo 已提交
665
		return err;
L
Linus Torvalds 已提交
666

667 668 669 670 671 672
	/* Invoke the former CPU_DYING callbacks */
	for (; st->state > target; st->state--) {
		struct cpuhp_step *step = cpuhp_ap_states + st->state;

		cpuhp_invoke_callback(cpu, st->state, step->teardown);
	}
673 674
	/* Give up timekeeping duties */
	tick_handover_do_timer();
675
	/* Park the stopper thread */
676
	stop_machine_park(cpu);
Z
Zwane Mwaikambo 已提交
677
	return 0;
L
Linus Torvalds 已提交
678 679
}

680
static int takedown_cpu(unsigned int cpu)
L
Linus Torvalds 已提交
681
{
682
	int err;
L
Linus Torvalds 已提交
683

684 685 686 687 688 689
	/*
	 * 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
690
	 * not imply sync_sched(), so wait for both.
691 692
	 *
	 * Do sync before park smpboot threads to take care the rcu boost case.
693
	 */
694 695 696 697
	if (IS_ENABLED(CONFIG_PREEMPT))
		synchronize_rcu_mult(call_rcu, call_rcu_sched);
	else
		synchronize_rcu();
698

699 700 701
	/* Park the hotplug thread */
	kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread);

702
	/*
703 704
	 * Prevent irq alloc/free while the dying cpu reorganizes the
	 * interrupt affinities.
705
	 */
706
	irq_lock_sparse();
707

708 709 710
	/*
	 * So now all preempt/rcu users must observe !cpu_active().
	 */
711
	err = stop_machine(take_cpu_down, NULL, cpumask_of(cpu));
712
	if (err) {
L
Linus Torvalds 已提交
713
		/* CPU didn't die: tell everyone.  Can't complain. */
714
		cpu_notify_nofail(CPU_DOWN_FAILED, cpu);
715
		irq_unlock_sparse();
716
		return err;
717
	}
718
	BUG_ON(cpu_online(cpu));
L
Linus Torvalds 已提交
719

720 721 722 723
	/*
	 * 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.
P
Peter Zijlstra 已提交
724 725
	 *
	 * Wait for the stop thread to go away.
726
	 */
727
	while (!per_cpu(cpu_dead_idle, cpu))
P
Peter Zijlstra 已提交
728
		cpu_relax();
729 730
	smp_mb(); /* Read from cpu_dead_idle before __cpu_die(). */
	per_cpu(cpu_dead_idle, cpu) = false;
L
Linus Torvalds 已提交
731

732 733 734
	/* Interrupts are moved away from the dying cpu, reenable alloc/free */
	irq_unlock_sparse();

735
	hotplug_cpu__broadcast_tick_pull(cpu);
L
Linus Torvalds 已提交
736 737 738
	/* This actually kills the CPU. */
	__cpu_die(cpu);

739
	tick_cleanup_dead_cpu(cpu);
740 741
	return 0;
}
L
Linus Torvalds 已提交
742

743 744 745
static int notify_dead(unsigned int cpu)
{
	cpu_notify_nofail(CPU_DEAD, cpu);
L
Linus Torvalds 已提交
746
	check_for_tasks(cpu);
747 748 749
	return 0;
}

750 751 752 753
#else
#define notify_down_prepare	NULL
#define takedown_cpu		NULL
#define notify_dead		NULL
754
#define notify_dying		NULL
755 756 757 758
#endif

#ifdef CONFIG_HOTPLUG_CPU

759
/* Requires cpu_add_remove_lock to be held */
760 761
static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
			   enum cpuhp_state target)
762
{
763 764 765
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
	int prev_state, ret = 0;
	bool hasdied = false;
766 767 768 769

	if (num_online_cpus() == 1)
		return -EBUSY;

770
	if (!cpu_present(cpu))
771 772 773 774 775 776
		return -EINVAL;

	cpu_hotplug_begin();

	cpuhp_tasks_frozen = tasks_frozen;

777
	prev_state = st->state;
778
	st->target = target;
779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802
	/*
	 * If the current CPU state is in the range of the AP hotplug thread,
	 * then we need to kick the thread.
	 */
	if (st->state >= CPUHP_KICK_AP_THREAD) {
		ret = cpuhp_kick_ap_work(cpu);
		/*
		 * The AP side has done the error rollback already. Just
		 * return the error code..
		 */
		if (ret)
			goto out;

		/*
		 * We might have stopped still in the range of the AP hotplug
		 * thread. Nothing to do anymore.
		 */
		if (st->state >= CPUHP_KICK_AP_THREAD)
			goto out;
	}
	/*
	 * The AP brought itself down below CPUHP_KICK_AP_THREAD. So we need
	 * to do the further cleanups.
	 */
803
	ret = cpuhp_down_callbacks(cpu, st, cpuhp_bp_states, target);
804

805
	hasdied = prev_state != st->state && st->state == CPUHP_OFFLINE;
806
out:
807
	cpu_hotplug_done();
808 809
	/* This post dead nonsense must die */
	if (!ret && hasdied)
810
		cpu_notify_nofail(CPU_POST_DEAD, cpu);
811
	return ret;
812 813
}

814
static int do_cpu_down(unsigned int cpu, enum cpuhp_state target)
815
{
816
	int err;
817

818
	cpu_maps_update_begin();
819 820

	if (cpu_hotplug_disabled) {
821
		err = -EBUSY;
822 823 824
		goto out;
	}

825
	err = _cpu_down(cpu, 0, target);
826

827
out:
828
	cpu_maps_update_done();
L
Linus Torvalds 已提交
829 830
	return err;
}
831 832 833 834
int cpu_down(unsigned int cpu)
{
	return do_cpu_down(cpu, CPUHP_OFFLINE);
}
835
EXPORT_SYMBOL(cpu_down);
L
Linus Torvalds 已提交
836 837
#endif /*CONFIG_HOTPLUG_CPU*/

838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859
/**
 * notify_cpu_starting(cpu) - call the CPU_STARTING notifiers
 * @cpu: cpu that just started
 *
 * This function calls the cpu_chain notifiers with CPU_STARTING.
 * It must be called by the arch code on the new cpu, before the new cpu
 * enables interrupts and before the "boot" cpu returns from __cpu_up().
 */
void notify_cpu_starting(unsigned int cpu)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
	enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE);

	while (st->state < target) {
		struct cpuhp_step *step;

		st->state++;
		step = cpuhp_ap_states + st->state;
		cpuhp_invoke_callback(cpu, st->state, step->startup);
	}
}

860 861 862 863 864 865
/*
 * Called from the idle task. We need to set active here, so we can kick off
 * the stopper thread.
 */
static int cpuhp_set_cpu_active(unsigned int cpu)
{
866 867
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);

868 869
	/* The cpu is marked online, set it active now */
	set_cpu_active(cpu, true);
870
	/* Unpark the stopper thread and the hotplug thread */
871
	stop_machine_unpark(cpu);
872
	kthread_unpark(st->thread);
873 874 875
	return 0;
}

876
/* Requires cpu_add_remove_lock to be held */
877
static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target)
L
Linus Torvalds 已提交
878
{
879
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
880
	struct task_struct *idle;
881
	int ret = 0;
L
Linus Torvalds 已提交
882

883
	cpu_hotplug_begin();
884

885
	if (!cpu_present(cpu)) {
886 887 888 889
		ret = -EINVAL;
		goto out;
	}

890 891 892 893 894
	/*
	 * The caller of do_cpu_up might have raced with another
	 * caller. Ignore it for now.
	 */
	if (st->state >= target)
895
		goto out;
896 897 898 899 900 901 902 903

	if (st->state == CPUHP_OFFLINE) {
		/* Let it fail before we try to bring the cpu up */
		idle = idle_thread_get(cpu);
		if (IS_ERR(idle)) {
			ret = PTR_ERR(idle);
			goto out;
		}
904
	}
905

906 907
	cpuhp_tasks_frozen = tasks_frozen;

908
	st->target = target;
909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928
	/*
	 * If the current CPU state is in the range of the AP hotplug thread,
	 * then we need to kick the thread once more.
	 */
	if (st->state >= CPUHP_KICK_AP_THREAD) {
		ret = cpuhp_kick_ap_work(cpu);
		/*
		 * The AP side has done the error rollback already. Just
		 * return the error code..
		 */
		if (ret)
			goto out;
	}

	/*
	 * Try to reach the target state. We max out on the BP at
	 * CPUHP_KICK_AP_THREAD. After that the AP hotplug thread is
	 * responsible for bringing it up to the target state.
	 */
	target = min((int)target, CPUHP_KICK_AP_THREAD);
929
	ret = cpuhp_up_callbacks(cpu, st, cpuhp_bp_states, target);
930
out:
931
	cpu_hotplug_done();
932 933 934
	return ret;
}

935
static int do_cpu_up(unsigned int cpu, enum cpuhp_state target)
936 937
{
	int err = 0;
938

R
Rusty Russell 已提交
939
	if (!cpu_possible(cpu)) {
940 941
		pr_err("can't online cpu %d because it is not configured as may-hotadd at boot time\n",
		       cpu);
942
#if defined(CONFIG_IA64)
943
		pr_err("please check additional_cpus= boot parameter\n");
944 945 946
#endif
		return -EINVAL;
	}
947

948 949 950
	err = try_online_node(cpu_to_node(cpu));
	if (err)
		return err;
951

952
	cpu_maps_update_begin();
953 954

	if (cpu_hotplug_disabled) {
955
		err = -EBUSY;
956 957 958
		goto out;
	}

959
	err = _cpu_up(cpu, 0, target);
960
out:
961
	cpu_maps_update_done();
962 963
	return err;
}
964 965 966 967 968

int cpu_up(unsigned int cpu)
{
	return do_cpu_up(cpu, CPUHP_ONLINE);
}
P
Paul E. McKenney 已提交
969
EXPORT_SYMBOL_GPL(cpu_up);
970

971
#ifdef CONFIG_PM_SLEEP_SMP
R
Rusty Russell 已提交
972
static cpumask_var_t frozen_cpus;
973 974 975

int disable_nonboot_cpus(void)
{
976
	int cpu, first_cpu, error = 0;
977

978
	cpu_maps_update_begin();
R
Rusty Russell 已提交
979
	first_cpu = cpumask_first(cpu_online_mask);
980 981
	/*
	 * We take down all of the non-boot CPUs in one shot to avoid races
982 983
	 * with the userspace trying to use the CPU hotplug at the same time
	 */
R
Rusty Russell 已提交
984
	cpumask_clear(frozen_cpus);
985

986
	pr_info("Disabling non-boot CPUs ...\n");
987 988 989
	for_each_online_cpu(cpu) {
		if (cpu == first_cpu)
			continue;
990
		trace_suspend_resume(TPS("CPU_OFF"), cpu, true);
991
		error = _cpu_down(cpu, 1, CPUHP_OFFLINE);
992
		trace_suspend_resume(TPS("CPU_OFF"), cpu, false);
993
		if (!error)
R
Rusty Russell 已提交
994
			cpumask_set_cpu(cpu, frozen_cpus);
995
		else {
996
			pr_err("Error taking CPU%d down: %d\n", cpu, error);
997 998 999
			break;
		}
	}
1000

1001
	if (!error)
1002
		BUG_ON(num_online_cpus() > 1);
1003
	else
1004
		pr_err("Non-boot CPUs are not disabled\n");
1005 1006 1007 1008 1009 1010 1011 1012

	/*
	 * Make sure the CPUs won't be enabled by someone else. We need to do
	 * this even in case of failure as all disable_nonboot_cpus() users are
	 * supposed to do enable_nonboot_cpus() on the failure path.
	 */
	cpu_hotplug_disabled++;

1013
	cpu_maps_update_done();
1014 1015 1016
	return error;
}

1017 1018 1019 1020 1021 1022 1023 1024
void __weak arch_enable_nonboot_cpus_begin(void)
{
}

void __weak arch_enable_nonboot_cpus_end(void)
{
}

1025
void enable_nonboot_cpus(void)
1026 1027 1028 1029
{
	int cpu, error;

	/* Allow everyone to use the CPU hotplug again */
1030
	cpu_maps_update_begin();
1031
	WARN_ON(--cpu_hotplug_disabled < 0);
R
Rusty Russell 已提交
1032
	if (cpumask_empty(frozen_cpus))
1033
		goto out;
1034

1035
	pr_info("Enabling non-boot CPUs ...\n");
1036 1037 1038

	arch_enable_nonboot_cpus_begin();

R
Rusty Russell 已提交
1039
	for_each_cpu(cpu, frozen_cpus) {
1040
		trace_suspend_resume(TPS("CPU_ON"), cpu, true);
1041
		error = _cpu_up(cpu, 1, CPUHP_ONLINE);
1042
		trace_suspend_resume(TPS("CPU_ON"), cpu, false);
1043
		if (!error) {
1044
			pr_info("CPU%d is up\n", cpu);
1045 1046
			continue;
		}
1047
		pr_warn("Error taking CPU%d up: %d\n", cpu, error);
1048
	}
1049 1050 1051

	arch_enable_nonboot_cpus_end();

R
Rusty Russell 已提交
1052
	cpumask_clear(frozen_cpus);
1053
out:
1054
	cpu_maps_update_done();
L
Linus Torvalds 已提交
1055
}
R
Rusty Russell 已提交
1056

1057
static int __init alloc_frozen_cpus(void)
R
Rusty Russell 已提交
1058 1059 1060 1061 1062 1063
{
	if (!alloc_cpumask_var(&frozen_cpus, GFP_KERNEL|__GFP_ZERO))
		return -ENOMEM;
	return 0;
}
core_initcall(alloc_frozen_cpus);
1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083

/*
 * When callbacks for CPU hotplug notifications are being executed, we must
 * ensure that the state of the system with respect to the tasks being frozen
 * or not, as reported by the notification, remains unchanged *throughout the
 * duration* of the execution of the callbacks.
 * Hence we need to prevent the freezer from racing with regular CPU hotplug.
 *
 * This synchronization is implemented by mutually excluding regular CPU
 * hotplug and Suspend/Hibernate call paths by hooking onto the Suspend/
 * Hibernate notifications.
 */
static int
cpu_hotplug_pm_callback(struct notifier_block *nb,
			unsigned long action, void *ptr)
{
	switch (action) {

	case PM_SUSPEND_PREPARE:
	case PM_HIBERNATION_PREPARE:
1084
		cpu_hotplug_disable();
1085 1086 1087 1088
		break;

	case PM_POST_SUSPEND:
	case PM_POST_HIBERNATION:
1089
		cpu_hotplug_enable();
1090 1091 1092 1093 1094 1095 1096 1097 1098 1099
		break;

	default:
		return NOTIFY_DONE;
	}

	return NOTIFY_OK;
}


1100
static int __init cpu_hotplug_pm_sync_init(void)
1101
{
1102 1103 1104 1105 1106
	/*
	 * cpu_hotplug_pm_callback has higher priority than x86
	 * bsp_pm_callback which depends on cpu_hotplug_pm_callback
	 * to disable cpu hotplug to avoid cpu hotplug race.
	 */
1107 1108 1109 1110 1111
	pm_notifier(cpu_hotplug_pm_callback, 0);
	return 0;
}
core_initcall(cpu_hotplug_pm_sync_init);

1112
#endif /* CONFIG_PM_SLEEP_SMP */
1113 1114

#endif /* CONFIG_SMP */
1115

1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127
/* Boot processor state steps */
static struct cpuhp_step cpuhp_bp_states[] = {
	[CPUHP_OFFLINE] = {
		.name			= "offline",
		.startup		= NULL,
		.teardown		= NULL,
	},
#ifdef CONFIG_SMP
	[CPUHP_CREATE_THREADS]= {
		.name			= "threads:create",
		.startup		= smpboot_create_threads,
		.teardown		= NULL,
1128
		.cant_stop		= true,
1129 1130 1131 1132 1133 1134
	},
	[CPUHP_NOTIFY_PREPARE] = {
		.name			= "notify:prepare",
		.startup		= notify_prepare,
		.teardown		= notify_dead,
		.skip_onerr		= true,
1135
		.cant_stop		= true,
1136 1137 1138 1139
	},
	[CPUHP_BRINGUP_CPU] = {
		.name			= "cpu:bringup",
		.startup		= bringup_cpu,
1140
		.teardown		= NULL,
1141
		.cant_stop		= true,
1142 1143 1144 1145
	},
	[CPUHP_TEARDOWN_CPU] = {
		.name			= "cpu:teardown",
		.startup		= NULL,
1146
		.teardown		= takedown_cpu,
1147
		.cant_stop		= true,
1148
	},
1149 1150 1151 1152 1153
	[CPUHP_CPU_SET_ACTIVE] = {
		.name			= "cpu:active",
		.startup		= cpuhp_set_cpu_active,
		.teardown		= NULL,
	},
1154 1155 1156 1157
	[CPUHP_KICK_AP_THREAD] = {
		.name			= "cpuhp:kickthread",
		.startup		= cpuhp_kick_ap_work,
		.teardown		= cpuhp_kick_ap_work,
1158 1159
	},
#endif
1160
	[CPUHP_BP_ONLINE] = {
1161 1162 1163 1164 1165 1166
		.name			= "online",
		.startup		= NULL,
		.teardown		= NULL,
	},
};

1167 1168 1169 1170 1171 1172 1173 1174
/* Application processor state steps */
static struct cpuhp_step cpuhp_ap_states[] = {
#ifdef CONFIG_SMP
	[CPUHP_AP_NOTIFY_STARTING] = {
		.name			= "notify:starting",
		.startup		= notify_starting,
		.teardown		= notify_dying,
		.skip_onerr		= true,
1175
		.cant_stop		= true,
1176
	},
1177 1178 1179 1180 1181 1182 1183 1184 1185 1186
	[CPUHP_AP_SMPBOOT_THREADS] = {
		.name			= "smpboot:threads",
		.startup		= smpboot_unpark_threads,
		.teardown		= smpboot_park_threads,
	},
	[CPUHP_AP_NOTIFY_ONLINE] = {
		.name			= "notify:online",
		.startup		= notify_online,
		.teardown		= notify_down_prepare,
	},
1187 1188 1189 1190 1191 1192 1193 1194
#endif
	[CPUHP_ONLINE] = {
		.name			= "online",
		.startup		= NULL,
		.teardown		= NULL,
	},
};

1195 1196 1197 1198 1199 1200 1201 1202
/* Sanity check for callbacks */
static int cpuhp_cb_check(enum cpuhp_state state)
{
	if (state <= CPUHP_OFFLINE || state >= CPUHP_ONLINE)
		return -EINVAL;
	return 0;
}

1203 1204
static bool cpuhp_is_ap_state(enum cpuhp_state state)
{
1205 1206 1207
	if (state >= CPUHP_AP_OFFLINE && state <= CPUHP_AP_ONLINE)
		return true;
	return state > CPUHP_BP_ONLINE;
1208 1209 1210 1211 1212 1213 1214 1215 1216 1217
}

static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state)
{
	struct cpuhp_step *sp;

	sp = cpuhp_is_ap_state(state) ? cpuhp_ap_states : cpuhp_bp_states;
	return sp + state;
}

1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253
static void cpuhp_store_callbacks(enum cpuhp_state state,
				  const char *name,
				  int (*startup)(unsigned int cpu),
				  int (*teardown)(unsigned int cpu))
{
	/* (Un)Install the callbacks for further cpu hotplug operations */
	struct cpuhp_step *sp;

	mutex_lock(&cpuhp_state_mutex);
	sp = cpuhp_get_step(state);
	sp->startup = startup;
	sp->teardown = teardown;
	sp->name = name;
	mutex_unlock(&cpuhp_state_mutex);
}

static void *cpuhp_get_teardown_cb(enum cpuhp_state state)
{
	return cpuhp_get_step(state)->teardown;
}

/*
 * Call the startup/teardown function for a step either on the AP or
 * on the current CPU.
 */
static int cpuhp_issue_call(int cpu, enum cpuhp_state state,
			    int (*cb)(unsigned int), bool bringup)
{
	int ret;

	if (!cb)
		return 0;
	/*
	 * The non AP bound callbacks can fail on bringup. On teardown
	 * e.g. module removal we crash for now.
	 */
1254 1255 1256 1257 1258 1259 1260 1261
#ifdef CONFIG_SMP
	if (cpuhp_is_ap_state(state))
		ret = cpuhp_invoke_ap_callback(cpu, state, cb);
	else
		ret = cpuhp_invoke_callback(cpu, state, cb);
#else
	ret = cpuhp_invoke_callback(cpu, state, cb);
#endif
1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302
	BUG_ON(ret && !bringup);
	return ret;
}

/*
 * Called from __cpuhp_setup_state on a recoverable failure.
 *
 * Note: The teardown callbacks for rollback are not allowed to fail!
 */
static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state,
				   int (*teardown)(unsigned int cpu))
{
	int cpu;

	if (!teardown)
		return;

	/* Roll back the already executed steps on the other cpus */
	for_each_present_cpu(cpu) {
		struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
		int cpustate = st->state;

		if (cpu >= failedcpu)
			break;

		/* Did we invoke the startup call on that cpu ? */
		if (cpustate >= state)
			cpuhp_issue_call(cpu, state, teardown, false);
	}
}

/*
 * Returns a free for dynamic slot assignment of the Online state. The states
 * are protected by the cpuhp_slot_states mutex and an empty slot is identified
 * by having no name assigned.
 */
static int cpuhp_reserve_state(enum cpuhp_state state)
{
	enum cpuhp_state i;

	mutex_lock(&cpuhp_state_mutex);
1303 1304
	for (i = CPUHP_AP_ONLINE_DYN; i <= CPUHP_AP_ONLINE_DYN_END; i++) {
		if (cpuhp_ap_states[i].name)
1305 1306
			continue;

1307
		cpuhp_ap_states[i].name = "Reserved";
1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339
		mutex_unlock(&cpuhp_state_mutex);
		return i;
	}
	mutex_unlock(&cpuhp_state_mutex);
	WARN(1, "No more dynamic states available for CPU hotplug\n");
	return -ENOSPC;
}

/**
 * __cpuhp_setup_state - Setup the callbacks for an hotplug machine state
 * @state:	The state to setup
 * @invoke:	If true, the startup function is invoked for cpus where
 *		cpu state >= @state
 * @startup:	startup callback function
 * @teardown:	teardown callback function
 *
 * Returns 0 if successful, otherwise a proper error code
 */
int __cpuhp_setup_state(enum cpuhp_state state,
			const char *name, bool invoke,
			int (*startup)(unsigned int cpu),
			int (*teardown)(unsigned int cpu))
{
	int cpu, ret = 0;
	int dyn_state = 0;

	if (cpuhp_cb_check(state) || !name)
		return -EINVAL;

	get_online_cpus();

	/* currently assignments for the ONLINE state are possible */
1340
	if (state == CPUHP_AP_ONLINE_DYN) {
1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417
		dyn_state = 1;
		ret = cpuhp_reserve_state(state);
		if (ret < 0)
			goto out;
		state = ret;
	}

	cpuhp_store_callbacks(state, name, startup, teardown);

	if (!invoke || !startup)
		goto out;

	/*
	 * Try to call the startup callback for each present cpu
	 * depending on the hotplug state of the cpu.
	 */
	for_each_present_cpu(cpu) {
		struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
		int cpustate = st->state;

		if (cpustate < state)
			continue;

		ret = cpuhp_issue_call(cpu, state, startup, true);
		if (ret) {
			cpuhp_rollback_install(cpu, state, teardown);
			cpuhp_store_callbacks(state, NULL, NULL, NULL);
			goto out;
		}
	}
out:
	put_online_cpus();
	if (!ret && dyn_state)
		return state;
	return ret;
}
EXPORT_SYMBOL(__cpuhp_setup_state);

/**
 * __cpuhp_remove_state - Remove the callbacks for an hotplug machine state
 * @state:	The state to remove
 * @invoke:	If true, the teardown function is invoked for cpus where
 *		cpu state >= @state
 *
 * The teardown callback is currently not allowed to fail. Think
 * about module removal!
 */
void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
{
	int (*teardown)(unsigned int cpu) = cpuhp_get_teardown_cb(state);
	int cpu;

	BUG_ON(cpuhp_cb_check(state));

	get_online_cpus();

	if (!invoke || !teardown)
		goto remove;

	/*
	 * Call the teardown callback for each present cpu depending
	 * on the hotplug state of the cpu. This function is not
	 * allowed to fail currently!
	 */
	for_each_present_cpu(cpu) {
		struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
		int cpustate = st->state;

		if (cpustate >= state)
			cpuhp_issue_call(cpu, state, teardown, false);
	}
remove:
	cpuhp_store_callbacks(state, NULL, NULL, NULL);
	put_online_cpus();
}
EXPORT_SYMBOL(__cpuhp_remove_state);

1418 1419 1420 1421 1422 1423 1424 1425 1426 1427
#if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU)
static ssize_t show_cpuhp_state(struct device *dev,
				struct device_attribute *attr, char *buf)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);

	return sprintf(buf, "%d\n", st->state);
}
static DEVICE_ATTR(state, 0444, show_cpuhp_state, NULL);

1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467
static ssize_t write_cpuhp_target(struct device *dev,
				  struct device_attribute *attr,
				  const char *buf, size_t count)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
	struct cpuhp_step *sp;
	int target, ret;

	ret = kstrtoint(buf, 10, &target);
	if (ret)
		return ret;

#ifdef CONFIG_CPU_HOTPLUG_STATE_CONTROL
	if (target < CPUHP_OFFLINE || target > CPUHP_ONLINE)
		return -EINVAL;
#else
	if (target != CPUHP_OFFLINE && target != CPUHP_ONLINE)
		return -EINVAL;
#endif

	ret = lock_device_hotplug_sysfs();
	if (ret)
		return ret;

	mutex_lock(&cpuhp_state_mutex);
	sp = cpuhp_get_step(target);
	ret = !sp->name || sp->cant_stop ? -EINVAL : 0;
	mutex_unlock(&cpuhp_state_mutex);
	if (ret)
		return ret;

	if (st->state < target)
		ret = do_cpu_up(dev->id, target);
	else
		ret = do_cpu_down(dev->id, target);

	unlock_device_hotplug();
	return ret ? ret : count;
}

1468 1469 1470 1471 1472 1473 1474
static ssize_t show_cpuhp_target(struct device *dev,
				 struct device_attribute *attr, char *buf)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);

	return sprintf(buf, "%d\n", st->target);
}
1475
static DEVICE_ATTR(target, 0644, show_cpuhp_target, write_cpuhp_target);
1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495

static struct attribute *cpuhp_cpu_attrs[] = {
	&dev_attr_state.attr,
	&dev_attr_target.attr,
	NULL
};

static struct attribute_group cpuhp_cpu_attr_group = {
	.attrs = cpuhp_cpu_attrs,
	.name = "hotplug",
	NULL
};

static ssize_t show_cpuhp_states(struct device *dev,
				 struct device_attribute *attr, char *buf)
{
	ssize_t cur, res = 0;
	int i;

	mutex_lock(&cpuhp_state_mutex);
1496
	for (i = CPUHP_OFFLINE; i <= CPUHP_ONLINE; i++) {
1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543
		struct cpuhp_step *sp = cpuhp_get_step(i);

		if (sp->name) {
			cur = sprintf(buf, "%3d: %s\n", i, sp->name);
			buf += cur;
			res += cur;
		}
	}
	mutex_unlock(&cpuhp_state_mutex);
	return res;
}
static DEVICE_ATTR(states, 0444, show_cpuhp_states, NULL);

static struct attribute *cpuhp_cpu_root_attrs[] = {
	&dev_attr_states.attr,
	NULL
};

static struct attribute_group cpuhp_cpu_root_attr_group = {
	.attrs = cpuhp_cpu_root_attrs,
	.name = "hotplug",
	NULL
};

static int __init cpuhp_sysfs_init(void)
{
	int cpu, ret;

	ret = sysfs_create_group(&cpu_subsys.dev_root->kobj,
				 &cpuhp_cpu_root_attr_group);
	if (ret)
		return ret;

	for_each_possible_cpu(cpu) {
		struct device *dev = get_cpu_device(cpu);

		if (!dev)
			continue;
		ret = sysfs_create_group(&dev->kobj, &cpuhp_cpu_attr_group);
		if (ret)
			return ret;
	}
	return 0;
}
device_initcall(cpuhp_sysfs_init);
#endif

1544 1545 1546 1547
/*
 * cpu_bit_bitmap[] is a special, "compressed" data structure that
 * represents all NR_CPUS bits binary values of 1<<nr.
 *
R
Rusty Russell 已提交
1548
 * It is used by cpumask_of() to get a constant address to a CPU
1549 1550
 * mask value that has a single bit set only.
 */
1551

1552
/* cpu_bit_bitmap[0] is empty - so we can back into it */
1553
#define MASK_DECLARE_1(x)	[x+1][0] = (1UL << (x))
1554 1555 1556
#define MASK_DECLARE_2(x)	MASK_DECLARE_1(x), MASK_DECLARE_1(x+1)
#define MASK_DECLARE_4(x)	MASK_DECLARE_2(x), MASK_DECLARE_2(x+2)
#define MASK_DECLARE_8(x)	MASK_DECLARE_4(x), MASK_DECLARE_4(x+4)
1557

1558 1559 1560 1561 1562 1563 1564
const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = {

	MASK_DECLARE_8(0),	MASK_DECLARE_8(8),
	MASK_DECLARE_8(16),	MASK_DECLARE_8(24),
#if BITS_PER_LONG > 32
	MASK_DECLARE_8(32),	MASK_DECLARE_8(40),
	MASK_DECLARE_8(48),	MASK_DECLARE_8(56),
1565 1566
#endif
};
1567
EXPORT_SYMBOL_GPL(cpu_bit_bitmap);
1568 1569 1570

const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL;
EXPORT_SYMBOL(cpu_all_bits);
1571 1572

#ifdef CONFIG_INIT_ALL_POSSIBLE
1573
struct cpumask __cpu_possible_mask __read_mostly
1574
	= {CPU_BITS_ALL};
1575
#else
1576
struct cpumask __cpu_possible_mask __read_mostly;
1577
#endif
1578
EXPORT_SYMBOL(__cpu_possible_mask);
1579

1580 1581
struct cpumask __cpu_online_mask __read_mostly;
EXPORT_SYMBOL(__cpu_online_mask);
1582

1583 1584
struct cpumask __cpu_present_mask __read_mostly;
EXPORT_SYMBOL(__cpu_present_mask);
1585

1586 1587
struct cpumask __cpu_active_mask __read_mostly;
EXPORT_SYMBOL(__cpu_active_mask);
1588 1589 1590

void init_cpu_present(const struct cpumask *src)
{
1591
	cpumask_copy(&__cpu_present_mask, src);
1592 1593 1594 1595
}

void init_cpu_possible(const struct cpumask *src)
{
1596
	cpumask_copy(&__cpu_possible_mask, src);
1597 1598 1599 1600
}

void init_cpu_online(const struct cpumask *src)
{
1601
	cpumask_copy(&__cpu_online_mask, src);
1602
}
1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624

/*
 * Activate the first processor.
 */
void __init boot_cpu_init(void)
{
	int cpu = smp_processor_id();

	/* Mark the boot cpu "present", "online" etc for SMP and UP case */
	set_cpu_online(cpu, true);
	set_cpu_active(cpu, true);
	set_cpu_present(cpu, true);
	set_cpu_possible(cpu, true);
}

/*
 * Must be called _AFTER_ setting up the per_cpu areas
 */
void __init boot_cpu_state_init(void)
{
	per_cpu_ptr(&cpuhp_state, smp_processor_id())->state = CPUHP_ONLINE;
}