wait.h 34.9 KB
Newer Older
L
Linus Torvalds 已提交
1 2
#ifndef _LINUX_WAIT_H
#define _LINUX_WAIT_H
3 4 5
/*
 * Linux wait queue related types and methods
 */
L
Linus Torvalds 已提交
6 7 8 9
#include <linux/list.h>
#include <linux/stddef.h>
#include <linux/spinlock.h>
#include <asm/current.h>
10
#include <uapi/linux/wait.h>
L
Linus Torvalds 已提交
11 12

typedef struct __wait_queue wait_queue_t;
P
Peter Zijlstra 已提交
13 14
typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int flags, void *key);
int default_wake_function(wait_queue_t *wait, unsigned mode, int flags, void *key);
L
Linus Torvalds 已提交
15 16

struct __wait_queue {
17
	unsigned int		flags;
L
Linus Torvalds 已提交
18
#define WQ_FLAG_EXCLUSIVE	0x01
19 20 21
	void			*private;
	wait_queue_func_t	func;
	struct list_head	task_list;
L
Linus Torvalds 已提交
22 23 24
};

struct wait_bit_key {
25 26 27
	void			*flags;
	int			bit_nr;
#define WAIT_ATOMIC_T_BIT_NR	-1
28
	unsigned long		private;
L
Linus Torvalds 已提交
29 30 31
};

struct wait_bit_queue {
32 33
	struct wait_bit_key	key;
	wait_queue_t		wait;
L
Linus Torvalds 已提交
34 35 36
};

struct __wait_queue_head {
37 38
	spinlock_t		lock;
	struct list_head	task_list;
L
Linus Torvalds 已提交
39 40 41
};
typedef struct __wait_queue_head wait_queue_head_t;

42
struct task_struct;
L
Linus Torvalds 已提交
43 44 45 46 47 48

/*
 * Macros for declaration and initialisaton of the datatypes
 */

#define __WAITQUEUE_INITIALIZER(name, tsk) {				\
49
	.private	= tsk,						\
L
Linus Torvalds 已提交
50 51 52 53 54 55 56
	.func		= default_wake_function,			\
	.task_list	= { NULL, NULL } }

#define DECLARE_WAITQUEUE(name, tsk)					\
	wait_queue_t name = __WAITQUEUE_INITIALIZER(name, tsk)

#define __WAIT_QUEUE_HEAD_INITIALIZER(name) {				\
57
	.lock		= __SPIN_LOCK_UNLOCKED(name.lock),		\
L
Linus Torvalds 已提交
58 59 60 61 62 63 64 65
	.task_list	= { &(name).task_list, &(name).task_list } }

#define DECLARE_WAIT_QUEUE_HEAD(name) \
	wait_queue_head_t name = __WAIT_QUEUE_HEAD_INITIALIZER(name)

#define __WAIT_BIT_KEY_INITIALIZER(word, bit)				\
	{ .flags = word, .bit_nr = bit, }

66 67 68
#define __WAIT_ATOMIC_T_KEY_INITIALIZER(p)				\
	{ .flags = p, .bit_nr = WAIT_ATOMIC_T_BIT_NR, }

69
extern void __init_waitqueue_head(wait_queue_head_t *q, const char *name, struct lock_class_key *);
70 71 72 73 74

#define init_waitqueue_head(q)				\
	do {						\
		static struct lock_class_key __key;	\
							\
75
		__init_waitqueue_head((q), #q, &__key);	\
76
	} while (0)
L
Linus Torvalds 已提交
77

78 79 80 81 82 83 84 85 86
#ifdef CONFIG_LOCKDEP
# define __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) \
	({ init_waitqueue_head(&name); name; })
# define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) \
	wait_queue_head_t name = __WAIT_QUEUE_HEAD_INIT_ONSTACK(name)
#else
# define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) DECLARE_WAIT_QUEUE_HEAD(name)
#endif

L
Linus Torvalds 已提交
87 88
static inline void init_waitqueue_entry(wait_queue_t *q, struct task_struct *p)
{
89 90 91
	q->flags	= 0;
	q->private	= p;
	q->func		= default_wake_function;
L
Linus Torvalds 已提交
92 93
}

94 95
static inline void
init_waitqueue_func_entry(wait_queue_t *q, wait_queue_func_t func)
L
Linus Torvalds 已提交
96
{
97 98 99
	q->flags	= 0;
	q->private	= NULL;
	q->func		= func;
L
Linus Torvalds 已提交
100 101 102 103 104 105 106
}

static inline int waitqueue_active(wait_queue_head_t *q)
{
	return !list_empty(&q->task_list);
}

107 108 109
extern void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait);
extern void add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait);
extern void remove_wait_queue(wait_queue_head_t *q, wait_queue_t *wait);
L
Linus Torvalds 已提交
110 111 112 113 114 115 116 117 118

static inline void __add_wait_queue(wait_queue_head_t *head, wait_queue_t *new)
{
	list_add(&new->task_list, &head->task_list);
}

/*
 * Used for wake-one threads:
 */
119 120
static inline void
__add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait)
C
Changli Gao 已提交
121 122 123 124 125
{
	wait->flags |= WQ_FLAG_EXCLUSIVE;
	__add_wait_queue(q, wait);
}

L
Linus Torvalds 已提交
126
static inline void __add_wait_queue_tail(wait_queue_head_t *head,
C
Changli Gao 已提交
127
					 wait_queue_t *new)
L
Linus Torvalds 已提交
128 129 130 131
{
	list_add_tail(&new->task_list, &head->task_list);
}

132 133
static inline void
__add_wait_queue_tail_exclusive(wait_queue_head_t *q, wait_queue_t *wait)
C
Changli Gao 已提交
134 135 136 137 138
{
	wait->flags |= WQ_FLAG_EXCLUSIVE;
	__add_wait_queue_tail(q, wait);
}

139 140
static inline void
__remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old)
L
Linus Torvalds 已提交
141 142 143 144
{
	list_del(&old->task_list);
}

145
typedef int wait_bit_action_f(struct wait_bit_key *);
146
void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
147
void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
148
void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
149
void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr);
150
void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr);
151
void __wake_up_bit(wait_queue_head_t *, void *, int);
152 153
int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_action_f *, unsigned);
int __wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_action_f *, unsigned);
154
void wake_up_bit(void *, int);
155
void wake_up_atomic_t(atomic_t *);
156 157
int out_of_line_wait_on_bit(void *, int, wait_bit_action_f *, unsigned);
int out_of_line_wait_on_bit_lock(void *, int, wait_bit_action_f *, unsigned);
158
int out_of_line_wait_on_atomic_t(atomic_t *, int (*)(atomic_t *), unsigned);
159
wait_queue_head_t *bit_waitqueue(void *, int);
L
Linus Torvalds 已提交
160

M
Matthew Wilcox 已提交
161 162 163
#define wake_up(x)			__wake_up(x, TASK_NORMAL, 1, NULL)
#define wake_up_nr(x, nr)		__wake_up(x, TASK_NORMAL, nr, NULL)
#define wake_up_all(x)			__wake_up(x, TASK_NORMAL, 0, NULL)
164 165
#define wake_up_locked(x)		__wake_up_locked((x), TASK_NORMAL, 1)
#define wake_up_all_locked(x)		__wake_up_locked((x), TASK_NORMAL, 0)
M
Matthew Wilcox 已提交
166

L
Linus Torvalds 已提交
167 168 169
#define wake_up_interruptible(x)	__wake_up(x, TASK_INTERRUPTIBLE, 1, NULL)
#define wake_up_interruptible_nr(x, nr)	__wake_up(x, TASK_INTERRUPTIBLE, nr, NULL)
#define wake_up_interruptible_all(x)	__wake_up(x, TASK_INTERRUPTIBLE, 0, NULL)
M
Matthew Wilcox 已提交
170
#define wake_up_interruptible_sync(x)	__wake_up_sync((x), TASK_INTERRUPTIBLE, 1)
L
Linus Torvalds 已提交
171

P
Peter Zijlstra 已提交
172
/*
173
 * Wakeup macros to be used to report events to the targets.
P
Peter Zijlstra 已提交
174
 */
175
#define wake_up_poll(x, m)						\
176
	__wake_up(x, TASK_NORMAL, 1, (void *) (m))
177
#define wake_up_locked_poll(x, m)					\
178
	__wake_up_locked_key((x), TASK_NORMAL, (void *) (m))
179
#define wake_up_interruptible_poll(x, m)				\
180 181 182
	__wake_up(x, TASK_INTERRUPTIBLE, 1, (void *) (m))
#define wake_up_interruptible_sync_poll(x, m)				\
	__wake_up_sync_key((x), TASK_INTERRUPTIBLE, 1, (void *) (m))
P
Peter Zijlstra 已提交
183

184
#define ___wait_cond_timeout(condition)					\
P
Peter Zijlstra 已提交
185
({									\
186 187 188 189
	bool __cond = (condition);					\
	if (__cond && !__ret)						\
		__ret = 1;						\
	__cond || !__ret;						\
P
Peter Zijlstra 已提交
190 191
})

192 193 194
#define ___wait_is_interruptible(state)					\
	(!__builtin_constant_p(state) ||				\
		state == TASK_INTERRUPTIBLE || state == TASK_KILLABLE)	\
195

196 197 198 199 200 201 202 203 204 205 206 207
/*
 * The below macro ___wait_event() has an explicit shadow of the __ret
 * variable when used from the wait_event_*() macros.
 *
 * This is so that both can use the ___wait_cond_timeout() construct
 * to wrap the condition.
 *
 * The type inconsistency of the wait_event_*() __ret variable is also
 * on purpose; we use long where we can return timeout values and int
 * otherwise.
 */

208
#define ___wait_event(wq, condition, state, exclusive, ret, cmd)	\
209
({									\
210
	__label__ __out;						\
211
	wait_queue_t __wait;						\
212
	long __ret = ret;	/* explicit shadow */			\
213
									\
214 215 216 217 218 219
	INIT_LIST_HEAD(&__wait.task_list);				\
	if (exclusive)							\
		__wait.flags = WQ_FLAG_EXCLUSIVE;			\
	else								\
		__wait.flags = 0;					\
									\
220
	for (;;) {							\
221
		long __int = prepare_to_wait_event(&wq, &__wait, state);\
222 223 224 225
									\
		if (condition)						\
			break;						\
									\
226 227
		if (___wait_is_interruptible(state) && __int) {		\
			__ret = __int;					\
228
			if (exclusive) {				\
229 230
				abort_exclusive_wait(&wq, &__wait,	\
						     state, NULL);	\
231 232 233 234 235 236 237 238
				goto __out;				\
			}						\
			break;						\
		}							\
									\
		cmd;							\
	}								\
	finish_wait(&wq, &__wait);					\
239 240
__out:	__ret;								\
})
241

242
#define __wait_event(wq, condition)					\
243 244
	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
			    schedule())
L
Linus Torvalds 已提交
245 246 247 248 249 250 251 252 253 254 255 256 257

/**
 * wait_event - sleep until a condition gets true
 * @wq: the waitqueue to wait on
 * @condition: a C expression for the event to wait for
 *
 * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
 * @condition evaluates to true. The @condition is checked each time
 * the waitqueue @wq is woken up.
 *
 * wake_up() has to be called after changing any variable that could
 * change the result of the wait condition.
 */
258
#define wait_event(wq, condition)					\
L
Linus Torvalds 已提交
259
do {									\
260
	if (condition)							\
L
Linus Torvalds 已提交
261 262 263 264
		break;							\
	__wait_event(wq, condition);					\
} while (0)

265 266 267 268
#define __wait_event_timeout(wq, condition, timeout)			\
	___wait_event(wq, ___wait_cond_timeout(condition),		\
		      TASK_UNINTERRUPTIBLE, 0, timeout,			\
		      __ret = schedule_timeout(__ret))
L
Linus Torvalds 已提交
269 270 271 272 273 274 275 276 277 278 279 280 281 282

/**
 * wait_event_timeout - sleep until a condition gets true or a timeout elapses
 * @wq: the waitqueue to wait on
 * @condition: a C expression for the event to wait for
 * @timeout: timeout, in jiffies
 *
 * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
 * @condition evaluates to true. The @condition is checked each time
 * the waitqueue @wq is woken up.
 *
 * wake_up() has to be called after changing any variable that could
 * change the result of the wait condition.
 *
283 284 285
 * The function returns 0 if the @timeout elapsed, or the remaining
 * jiffies (at least 1) if the @condition evaluated to %true before
 * the @timeout elapsed.
L
Linus Torvalds 已提交
286 287 288 289
 */
#define wait_event_timeout(wq, condition, timeout)			\
({									\
	long __ret = timeout;						\
290
	if (!___wait_cond_timeout(condition))				\
291
		__ret = __wait_event_timeout(wq, condition, timeout);	\
L
Linus Torvalds 已提交
292 293 294
	__ret;								\
})

S
Shaohua Li 已提交
295 296 297 298 299 300 301 302
#define __wait_event_cmd(wq, condition, cmd1, cmd2)			\
	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
			    cmd1; schedule(); cmd2)

/**
 * wait_event_cmd - sleep until a condition gets true
 * @wq: the waitqueue to wait on
 * @condition: a C expression for the event to wait for
303 304
 * @cmd1: the command will be executed before sleep
 * @cmd2: the command will be executed after sleep
S
Shaohua Li 已提交
305 306 307 308 309 310 311 312 313 314 315 316 317 318 319
 *
 * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
 * @condition evaluates to true. The @condition is checked each time
 * the waitqueue @wq is woken up.
 *
 * wake_up() has to be called after changing any variable that could
 * change the result of the wait condition.
 */
#define wait_event_cmd(wq, condition, cmd1, cmd2)			\
do {									\
	if (condition)							\
		break;							\
	__wait_event_cmd(wq, condition, cmd1, cmd2);			\
} while (0)

320 321
#define __wait_event_interruptible(wq, condition)			\
	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0,		\
322
		      schedule())
L
Linus Torvalds 已提交
323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342

/**
 * wait_event_interruptible - sleep until a condition gets true
 * @wq: the waitqueue to wait on
 * @condition: a C expression for the event to wait for
 *
 * The process is put to sleep (TASK_INTERRUPTIBLE) until the
 * @condition evaluates to true or a signal is received.
 * The @condition is checked each time the waitqueue @wq is woken up.
 *
 * wake_up() has to be called after changing any variable that could
 * change the result of the wait condition.
 *
 * The function will return -ERESTARTSYS if it was interrupted by a
 * signal and 0 if @condition evaluated to true.
 */
#define wait_event_interruptible(wq, condition)				\
({									\
	int __ret = 0;							\
	if (!(condition))						\
343
		__ret = __wait_event_interruptible(wq, condition);	\
L
Linus Torvalds 已提交
344 345 346
	__ret;								\
})

347 348 349 350
#define __wait_event_interruptible_timeout(wq, condition, timeout)	\
	___wait_event(wq, ___wait_cond_timeout(condition),		\
		      TASK_INTERRUPTIBLE, 0, timeout,			\
		      __ret = schedule_timeout(__ret))
L
Linus Torvalds 已提交
351 352 353 354 355 356 357 358 359 360 361 362 363 364

/**
 * wait_event_interruptible_timeout - sleep until a condition gets true or a timeout elapses
 * @wq: the waitqueue to wait on
 * @condition: a C expression for the event to wait for
 * @timeout: timeout, in jiffies
 *
 * The process is put to sleep (TASK_INTERRUPTIBLE) until the
 * @condition evaluates to true or a signal is received.
 * The @condition is checked each time the waitqueue @wq is woken up.
 *
 * wake_up() has to be called after changing any variable that could
 * change the result of the wait condition.
 *
365 366 367 368
 * Returns:
 * 0 if the @timeout elapsed, -%ERESTARTSYS if it was interrupted by
 * a signal, or the remaining jiffies (at least 1) if the @condition
 * evaluated to %true before the @timeout elapsed.
L
Linus Torvalds 已提交
369 370 371 372
 */
#define wait_event_interruptible_timeout(wq, condition, timeout)	\
({									\
	long __ret = timeout;						\
373
	if (!___wait_cond_timeout(condition))				\
374
		__ret = __wait_event_interruptible_timeout(wq,		\
375
						condition, timeout);	\
L
Linus Torvalds 已提交
376 377 378
	__ret;								\
})

379 380 381 382 383 384 385 386 387 388 389 390 391
#define __wait_event_hrtimeout(wq, condition, timeout, state)		\
({									\
	int __ret = 0;							\
	struct hrtimer_sleeper __t;					\
									\
	hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC,		\
			      HRTIMER_MODE_REL);			\
	hrtimer_init_sleeper(&__t, current);				\
	if ((timeout).tv64 != KTIME_MAX)				\
		hrtimer_start_range_ns(&__t.timer, timeout,		\
				       current->timer_slack_ns,		\
				       HRTIMER_MODE_REL);		\
									\
392
	__ret = ___wait_event(wq, condition, state, 0, 0,		\
393 394 395 396
		if (!__t.task) {					\
			__ret = -ETIME;					\
			break;						\
		}							\
397
		schedule());						\
398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453
									\
	hrtimer_cancel(&__t.timer);					\
	destroy_hrtimer_on_stack(&__t.timer);				\
	__ret;								\
})

/**
 * wait_event_hrtimeout - sleep until a condition gets true or a timeout elapses
 * @wq: the waitqueue to wait on
 * @condition: a C expression for the event to wait for
 * @timeout: timeout, as a ktime_t
 *
 * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
 * @condition evaluates to true or a signal is received.
 * The @condition is checked each time the waitqueue @wq is woken up.
 *
 * wake_up() has to be called after changing any variable that could
 * change the result of the wait condition.
 *
 * The function returns 0 if @condition became true, or -ETIME if the timeout
 * elapsed.
 */
#define wait_event_hrtimeout(wq, condition, timeout)			\
({									\
	int __ret = 0;							\
	if (!(condition))						\
		__ret = __wait_event_hrtimeout(wq, condition, timeout,	\
					       TASK_UNINTERRUPTIBLE);	\
	__ret;								\
})

/**
 * wait_event_interruptible_hrtimeout - sleep until a condition gets true or a timeout elapses
 * @wq: the waitqueue to wait on
 * @condition: a C expression for the event to wait for
 * @timeout: timeout, as a ktime_t
 *
 * The process is put to sleep (TASK_INTERRUPTIBLE) until the
 * @condition evaluates to true or a signal is received.
 * The @condition is checked each time the waitqueue @wq is woken up.
 *
 * wake_up() has to be called after changing any variable that could
 * change the result of the wait condition.
 *
 * The function returns 0 if @condition became true, -ERESTARTSYS if it was
 * interrupted by a signal, or -ETIME if the timeout elapsed.
 */
#define wait_event_interruptible_hrtimeout(wq, condition, timeout)	\
({									\
	long __ret = 0;							\
	if (!(condition))						\
		__ret = __wait_event_hrtimeout(wq, condition, timeout,	\
					       TASK_INTERRUPTIBLE);	\
	__ret;								\
})

454 455
#define __wait_event_interruptible_exclusive(wq, condition)		\
	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0,		\
456
		      schedule())
L
Linus Torvalds 已提交
457 458 459 460 461

#define wait_event_interruptible_exclusive(wq, condition)		\
({									\
	int __ret = 0;							\
	if (!(condition))						\
462
		__ret = __wait_event_interruptible_exclusive(wq, condition);\
L
Linus Torvalds 已提交
463 464 465
	__ret;								\
})

466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613

#define __wait_event_interruptible_locked(wq, condition, exclusive, irq) \
({									\
	int __ret = 0;							\
	DEFINE_WAIT(__wait);						\
	if (exclusive)							\
		__wait.flags |= WQ_FLAG_EXCLUSIVE;			\
	do {								\
		if (likely(list_empty(&__wait.task_list)))		\
			__add_wait_queue_tail(&(wq), &__wait);		\
		set_current_state(TASK_INTERRUPTIBLE);			\
		if (signal_pending(current)) {				\
			__ret = -ERESTARTSYS;				\
			break;						\
		}							\
		if (irq)						\
			spin_unlock_irq(&(wq).lock);			\
		else							\
			spin_unlock(&(wq).lock);			\
		schedule();						\
		if (irq)						\
			spin_lock_irq(&(wq).lock);			\
		else							\
			spin_lock(&(wq).lock);				\
	} while (!(condition));						\
	__remove_wait_queue(&(wq), &__wait);				\
	__set_current_state(TASK_RUNNING);				\
	__ret;								\
})


/**
 * wait_event_interruptible_locked - sleep until a condition gets true
 * @wq: the waitqueue to wait on
 * @condition: a C expression for the event to wait for
 *
 * The process is put to sleep (TASK_INTERRUPTIBLE) until the
 * @condition evaluates to true or a signal is received.
 * The @condition is checked each time the waitqueue @wq is woken up.
 *
 * It must be called with wq.lock being held.  This spinlock is
 * unlocked while sleeping but @condition testing is done while lock
 * is held and when this macro exits the lock is held.
 *
 * The lock is locked/unlocked using spin_lock()/spin_unlock()
 * functions which must match the way they are locked/unlocked outside
 * of this macro.
 *
 * wake_up_locked() has to be called after changing any variable that could
 * change the result of the wait condition.
 *
 * The function will return -ERESTARTSYS if it was interrupted by a
 * signal and 0 if @condition evaluated to true.
 */
#define wait_event_interruptible_locked(wq, condition)			\
	((condition)							\
	 ? 0 : __wait_event_interruptible_locked(wq, condition, 0, 0))

/**
 * wait_event_interruptible_locked_irq - sleep until a condition gets true
 * @wq: the waitqueue to wait on
 * @condition: a C expression for the event to wait for
 *
 * The process is put to sleep (TASK_INTERRUPTIBLE) until the
 * @condition evaluates to true or a signal is received.
 * The @condition is checked each time the waitqueue @wq is woken up.
 *
 * It must be called with wq.lock being held.  This spinlock is
 * unlocked while sleeping but @condition testing is done while lock
 * is held and when this macro exits the lock is held.
 *
 * The lock is locked/unlocked using spin_lock_irq()/spin_unlock_irq()
 * functions which must match the way they are locked/unlocked outside
 * of this macro.
 *
 * wake_up_locked() has to be called after changing any variable that could
 * change the result of the wait condition.
 *
 * The function will return -ERESTARTSYS if it was interrupted by a
 * signal and 0 if @condition evaluated to true.
 */
#define wait_event_interruptible_locked_irq(wq, condition)		\
	((condition)							\
	 ? 0 : __wait_event_interruptible_locked(wq, condition, 0, 1))

/**
 * wait_event_interruptible_exclusive_locked - sleep exclusively until a condition gets true
 * @wq: the waitqueue to wait on
 * @condition: a C expression for the event to wait for
 *
 * The process is put to sleep (TASK_INTERRUPTIBLE) until the
 * @condition evaluates to true or a signal is received.
 * The @condition is checked each time the waitqueue @wq is woken up.
 *
 * It must be called with wq.lock being held.  This spinlock is
 * unlocked while sleeping but @condition testing is done while lock
 * is held and when this macro exits the lock is held.
 *
 * The lock is locked/unlocked using spin_lock()/spin_unlock()
 * functions which must match the way they are locked/unlocked outside
 * of this macro.
 *
 * The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag
 * set thus when other process waits process on the list if this
 * process is awaken further processes are not considered.
 *
 * wake_up_locked() has to be called after changing any variable that could
 * change the result of the wait condition.
 *
 * The function will return -ERESTARTSYS if it was interrupted by a
 * signal and 0 if @condition evaluated to true.
 */
#define wait_event_interruptible_exclusive_locked(wq, condition)	\
	((condition)							\
	 ? 0 : __wait_event_interruptible_locked(wq, condition, 1, 0))

/**
 * wait_event_interruptible_exclusive_locked_irq - sleep until a condition gets true
 * @wq: the waitqueue to wait on
 * @condition: a C expression for the event to wait for
 *
 * The process is put to sleep (TASK_INTERRUPTIBLE) until the
 * @condition evaluates to true or a signal is received.
 * The @condition is checked each time the waitqueue @wq is woken up.
 *
 * It must be called with wq.lock being held.  This spinlock is
 * unlocked while sleeping but @condition testing is done while lock
 * is held and when this macro exits the lock is held.
 *
 * The lock is locked/unlocked using spin_lock_irq()/spin_unlock_irq()
 * functions which must match the way they are locked/unlocked outside
 * of this macro.
 *
 * The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag
 * set thus when other process waits process on the list if this
 * process is awaken further processes are not considered.
 *
 * wake_up_locked() has to be called after changing any variable that could
 * change the result of the wait condition.
 *
 * The function will return -ERESTARTSYS if it was interrupted by a
 * signal and 0 if @condition evaluated to true.
 */
#define wait_event_interruptible_exclusive_locked_irq(wq, condition)	\
	((condition)							\
	 ? 0 : __wait_event_interruptible_locked(wq, condition, 1, 1))


614 615
#define __wait_event_killable(wq, condition)				\
	___wait_event(wq, condition, TASK_KILLABLE, 0, 0, schedule())
M
Matthew Wilcox 已提交
616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635

/**
 * wait_event_killable - sleep until a condition gets true
 * @wq: the waitqueue to wait on
 * @condition: a C expression for the event to wait for
 *
 * The process is put to sleep (TASK_KILLABLE) until the
 * @condition evaluates to true or a signal is received.
 * The @condition is checked each time the waitqueue @wq is woken up.
 *
 * wake_up() has to be called after changing any variable that could
 * change the result of the wait condition.
 *
 * The function will return -ERESTARTSYS if it was interrupted by a
 * signal and 0 if @condition evaluated to true.
 */
#define wait_event_killable(wq, condition)				\
({									\
	int __ret = 0;							\
	if (!(condition))						\
636
		__ret = __wait_event_killable(wq, condition);		\
M
Matthew Wilcox 已提交
637 638 639
	__ret;								\
})

640 641

#define __wait_event_lock_irq(wq, condition, lock, cmd)			\
642 643 644 645 646
	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
			    spin_unlock_irq(&lock);			\
			    cmd;					\
			    schedule();					\
			    spin_lock_irq(&lock))
647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705

/**
 * wait_event_lock_irq_cmd - sleep until a condition gets true. The
 *			     condition is checked under the lock. This
 *			     is expected to be called with the lock
 *			     taken.
 * @wq: the waitqueue to wait on
 * @condition: a C expression for the event to wait for
 * @lock: a locked spinlock_t, which will be released before cmd
 *	  and schedule() and reacquired afterwards.
 * @cmd: a command which is invoked outside the critical section before
 *	 sleep
 *
 * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
 * @condition evaluates to true. The @condition is checked each time
 * the waitqueue @wq is woken up.
 *
 * wake_up() has to be called after changing any variable that could
 * change the result of the wait condition.
 *
 * This is supposed to be called while holding the lock. The lock is
 * dropped before invoking the cmd and going to sleep and is reacquired
 * afterwards.
 */
#define wait_event_lock_irq_cmd(wq, condition, lock, cmd)		\
do {									\
	if (condition)							\
		break;							\
	__wait_event_lock_irq(wq, condition, lock, cmd);		\
} while (0)

/**
 * wait_event_lock_irq - sleep until a condition gets true. The
 *			 condition is checked under the lock. This
 *			 is expected to be called with the lock
 *			 taken.
 * @wq: the waitqueue to wait on
 * @condition: a C expression for the event to wait for
 * @lock: a locked spinlock_t, which will be released before schedule()
 *	  and reacquired afterwards.
 *
 * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
 * @condition evaluates to true. The @condition is checked each time
 * the waitqueue @wq is woken up.
 *
 * wake_up() has to be called after changing any variable that could
 * change the result of the wait condition.
 *
 * This is supposed to be called while holding the lock. The lock is
 * dropped before going to sleep and is reacquired afterwards.
 */
#define wait_event_lock_irq(wq, condition, lock)			\
do {									\
	if (condition)							\
		break;							\
	__wait_event_lock_irq(wq, condition, lock, );			\
} while (0)


706
#define __wait_event_interruptible_lock_irq(wq, condition, lock, cmd)	\
707
	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0,		\
708 709 710
		      spin_unlock_irq(&lock);				\
		      cmd;						\
		      schedule();					\
711
		      spin_lock_irq(&lock))
712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741

/**
 * wait_event_interruptible_lock_irq_cmd - sleep until a condition gets true.
 *		The condition is checked under the lock. This is expected to
 *		be called with the lock taken.
 * @wq: the waitqueue to wait on
 * @condition: a C expression for the event to wait for
 * @lock: a locked spinlock_t, which will be released before cmd and
 *	  schedule() and reacquired afterwards.
 * @cmd: a command which is invoked outside the critical section before
 *	 sleep
 *
 * The process is put to sleep (TASK_INTERRUPTIBLE) until the
 * @condition evaluates to true or a signal is received. The @condition is
 * checked each time the waitqueue @wq is woken up.
 *
 * wake_up() has to be called after changing any variable that could
 * change the result of the wait condition.
 *
 * This is supposed to be called while holding the lock. The lock is
 * dropped before invoking the cmd and going to sleep and is reacquired
 * afterwards.
 *
 * The macro will return -ERESTARTSYS if it was interrupted by a signal
 * and 0 if @condition evaluated to true.
 */
#define wait_event_interruptible_lock_irq_cmd(wq, condition, lock, cmd)	\
({									\
	int __ret = 0;							\
	if (!(condition))						\
742
		__ret = __wait_event_interruptible_lock_irq(wq,		\
743
						condition, lock, cmd);	\
744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772
	__ret;								\
})

/**
 * wait_event_interruptible_lock_irq - sleep until a condition gets true.
 *		The condition is checked under the lock. This is expected
 *		to be called with the lock taken.
 * @wq: the waitqueue to wait on
 * @condition: a C expression for the event to wait for
 * @lock: a locked spinlock_t, which will be released before schedule()
 *	  and reacquired afterwards.
 *
 * The process is put to sleep (TASK_INTERRUPTIBLE) until the
 * @condition evaluates to true or signal is received. The @condition is
 * checked each time the waitqueue @wq is woken up.
 *
 * wake_up() has to be called after changing any variable that could
 * change the result of the wait condition.
 *
 * This is supposed to be called while holding the lock. The lock is
 * dropped before going to sleep and is reacquired afterwards.
 *
 * The macro will return -ERESTARTSYS if it was interrupted by a signal
 * and 0 if @condition evaluated to true.
 */
#define wait_event_interruptible_lock_irq(wq, condition, lock)		\
({									\
	int __ret = 0;							\
	if (!(condition))						\
773
		__ret = __wait_event_interruptible_lock_irq(wq,		\
T
Thierry Reding 已提交
774
						condition, lock,);	\
775 776 777
	__ret;								\
})

778 779
#define __wait_event_interruptible_lock_irq_timeout(wq, condition,	\
						    lock, timeout)	\
780
	___wait_event(wq, ___wait_cond_timeout(condition),		\
781
		      TASK_INTERRUPTIBLE, 0, timeout,			\
782 783
		      spin_unlock_irq(&lock);				\
		      __ret = schedule_timeout(__ret);			\
784
		      spin_lock_irq(&lock));
785 786

/**
787 788 789
 * wait_event_interruptible_lock_irq_timeout - sleep until a condition gets
 *		true or a timeout elapses. The condition is checked under
 *		the lock. This is expected to be called with the lock taken.
790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812
 * @wq: the waitqueue to wait on
 * @condition: a C expression for the event to wait for
 * @lock: a locked spinlock_t, which will be released before schedule()
 *	  and reacquired afterwards.
 * @timeout: timeout, in jiffies
 *
 * The process is put to sleep (TASK_INTERRUPTIBLE) until the
 * @condition evaluates to true or signal is received. The @condition is
 * checked each time the waitqueue @wq is woken up.
 *
 * wake_up() has to be called after changing any variable that could
 * change the result of the wait condition.
 *
 * This is supposed to be called while holding the lock. The lock is
 * dropped before going to sleep and is reacquired afterwards.
 *
 * The function returns 0 if the @timeout elapsed, -ERESTARTSYS if it
 * was interrupted by a signal, and the remaining jiffies otherwise
 * if the condition evaluated to true before the timeout elapsed.
 */
#define wait_event_interruptible_lock_irq_timeout(wq, condition, lock,	\
						  timeout)		\
({									\
813
	long __ret = timeout;						\
814
	if (!___wait_cond_timeout(condition))				\
815 816
		__ret = __wait_event_interruptible_lock_irq_timeout(	\
					wq, condition, lock, timeout);	\
817 818 819
	__ret;								\
})

L
Linus Torvalds 已提交
820 821 822
/*
 * Waitqueues which are removed from the waitqueue_head at wakeup time
 */
823 824
void prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state);
void prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state);
825
long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state);
826
void finish_wait(wait_queue_head_t *q, wait_queue_t *wait);
827
void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait, unsigned int mode, void *key);
L
Linus Torvalds 已提交
828 829 830
int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);

831
#define DEFINE_WAIT_FUNC(name, function)				\
L
Linus Torvalds 已提交
832
	wait_queue_t name = {						\
833
		.private	= current,				\
834
		.func		= function,				\
835
		.task_list	= LIST_HEAD_INIT((name).task_list),	\
L
Linus Torvalds 已提交
836 837
	}

838 839
#define DEFINE_WAIT(name) DEFINE_WAIT_FUNC(name, autoremove_wake_function)

L
Linus Torvalds 已提交
840 841 842 843
#define DEFINE_WAIT_BIT(name, word, bit)				\
	struct wait_bit_queue name = {					\
		.key = __WAIT_BIT_KEY_INITIALIZER(word, bit),		\
		.wait	= {						\
844
			.private	= current,			\
L
Linus Torvalds 已提交
845 846 847 848 849 850 851 852
			.func		= wake_bit_function,		\
			.task_list	=				\
				LIST_HEAD_INIT((name).wait.task_list),	\
		},							\
	}

#define init_wait(wait)							\
	do {								\
853
		(wait)->private = current;				\
L
Linus Torvalds 已提交
854 855
		(wait)->func = autoremove_wake_function;		\
		INIT_LIST_HEAD(&(wait)->task_list);			\
856
		(wait)->flags = 0;					\
L
Linus Torvalds 已提交
857 858
	} while (0)

859

860 861
extern int bit_wait(struct wait_bit_key *);
extern int bit_wait_io(struct wait_bit_key *);
862

L
Linus Torvalds 已提交
863 864 865 866 867 868 869 870 871 872 873 874
/**
 * wait_on_bit - wait for a bit to be cleared
 * @word: the word being waited on, a kernel virtual address
 * @bit: the bit of the word being waited on
 * @mode: the task state to sleep in
 *
 * There is a standard hashed waitqueue table for generic use. This
 * is the part of the hashtable's accessor API that waits on a bit.
 * For instance, if one were to have waiters on a bitflag, one would
 * call wait_on_bit() in threads waiting for the bit to clear.
 * One uses wait_on_bit() where one is waiting for the bit to clear,
 * but has no intention of setting it.
875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927
 * Returned value will be zero if the bit was cleared, or non-zero
 * if the process received a signal and the mode permitted wakeup
 * on that signal.
 */
static inline int
wait_on_bit(void *word, int bit, unsigned mode)
{
	if (!test_bit(bit, word))
		return 0;
	return out_of_line_wait_on_bit(word, bit,
				       bit_wait,
				       mode);
}

/**
 * wait_on_bit_io - wait for a bit to be cleared
 * @word: the word being waited on, a kernel virtual address
 * @bit: the bit of the word being waited on
 * @mode: the task state to sleep in
 *
 * Use the standard hashed waitqueue table to wait for a bit
 * to be cleared.  This is similar to wait_on_bit(), but calls
 * io_schedule() instead of schedule() for the actual waiting.
 *
 * Returned value will be zero if the bit was cleared, or non-zero
 * if the process received a signal and the mode permitted wakeup
 * on that signal.
 */
static inline int
wait_on_bit_io(void *word, int bit, unsigned mode)
{
	if (!test_bit(bit, word))
		return 0;
	return out_of_line_wait_on_bit(word, bit,
				       bit_wait_io,
				       mode);
}

/**
 * wait_on_bit_action - wait for a bit to be cleared
 * @word: the word being waited on, a kernel virtual address
 * @bit: the bit of the word being waited on
 * @action: the function used to sleep, which may take special actions
 * @mode: the task state to sleep in
 *
 * Use the standard hashed waitqueue table to wait for a bit
 * to be cleared, and allow the waiting action to be specified.
 * This is like wait_on_bit() but allows fine control of how the waiting
 * is done.
 *
 * Returned value will be zero if the bit was cleared, or non-zero
 * if the process received a signal and the mode permitted wakeup
 * on that signal.
L
Linus Torvalds 已提交
928
 */
929
static inline int
930
wait_on_bit_action(void *word, int bit, wait_bit_action_f *action, unsigned mode)
L
Linus Torvalds 已提交
931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950
{
	if (!test_bit(bit, word))
		return 0;
	return out_of_line_wait_on_bit(word, bit, action, mode);
}

/**
 * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it
 * @word: the word being waited on, a kernel virtual address
 * @bit: the bit of the word being waited on
 * @mode: the task state to sleep in
 *
 * There is a standard hashed waitqueue table for generic use. This
 * is the part of the hashtable's accessor API that waits on a bit
 * when one intends to set it, for instance, trying to lock bitflags.
 * For instance, if one were to have waiters trying to set bitflag
 * and waiting for it to clear before setting it, one would call
 * wait_on_bit() in threads waiting to be able to set the bit.
 * One uses wait_on_bit_lock() where one is waiting for the bit to
 * clear with the intention of setting it, and when done, clearing it.
951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002
 *
 * Returns zero if the bit was (eventually) found to be clear and was
 * set.  Returns non-zero if a signal was delivered to the process and
 * the @mode allows that signal to wake the process.
 */
static inline int
wait_on_bit_lock(void *word, int bit, unsigned mode)
{
	if (!test_and_set_bit(bit, word))
		return 0;
	return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode);
}

/**
 * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it
 * @word: the word being waited on, a kernel virtual address
 * @bit: the bit of the word being waited on
 * @mode: the task state to sleep in
 *
 * Use the standard hashed waitqueue table to wait for a bit
 * to be cleared and then to atomically set it.  This is similar
 * to wait_on_bit(), but calls io_schedule() instead of schedule()
 * for the actual waiting.
 *
 * Returns zero if the bit was (eventually) found to be clear and was
 * set.  Returns non-zero if a signal was delivered to the process and
 * the @mode allows that signal to wake the process.
 */
static inline int
wait_on_bit_lock_io(void *word, int bit, unsigned mode)
{
	if (!test_and_set_bit(bit, word))
		return 0;
	return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode);
}

/**
 * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it
 * @word: the word being waited on, a kernel virtual address
 * @bit: the bit of the word being waited on
 * @action: the function used to sleep, which may take special actions
 * @mode: the task state to sleep in
 *
 * Use the standard hashed waitqueue table to wait for a bit
 * to be cleared and then to set it, and allow the waiting action
 * to be specified.
 * This is like wait_on_bit() but allows fine control of how the waiting
 * is done.
 *
 * Returns zero if the bit was (eventually) found to be clear and was
 * set.  Returns non-zero if a signal was delivered to the process and
 * the @mode allows that signal to wake the process.
L
Linus Torvalds 已提交
1003
 */
1004
static inline int
1005
wait_on_bit_lock_action(void *word, int bit, wait_bit_action_f *action, unsigned mode)
L
Linus Torvalds 已提交
1006 1007 1008 1009 1010
{
	if (!test_and_set_bit(bit, word))
		return 0;
	return out_of_line_wait_on_bit_lock(word, bit, action, mode);
}
1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028

/**
 * wait_on_atomic_t - Wait for an atomic_t to become 0
 * @val: The atomic value being waited on, a kernel virtual address
 * @action: the function used to sleep, which may take special actions
 * @mode: the task state to sleep in
 *
 * Wait for an atomic_t to become 0.  We abuse the bit-wait waitqueue table for
 * the purpose of getting a waitqueue, but we set the key to a bit number
 * outside of the target 'word'.
 */
static inline
int wait_on_atomic_t(atomic_t *val, int (*action)(atomic_t *), unsigned mode)
{
	if (atomic_read(val) == 0)
		return 0;
	return out_of_line_wait_on_atomic_t(val, action, mode);
}
1029 1030

#endif /* _LINUX_WAIT_H */