kernel-ark/include/linux/wait.h
Peter Zijlstra 0ccf831cbe lockdep: annotate epoll
On Sat, 2008-01-05 at 13:35 -0800, Davide Libenzi wrote:

> I remember I talked with Arjan about this time ago. Basically, since 1)
> you can drop an epoll fd inside another epoll fd 2) callback-based wakeups
> are used, you can see a wake_up() from inside another wake_up(), but they
> will never refer to the same lock instance.
> Think about:
>
> 	dfd = socket(...);
> 	efd1 = epoll_create();
> 	efd2 = epoll_create();
> 	epoll_ctl(efd1, EPOLL_CTL_ADD, dfd, ...);
> 	epoll_ctl(efd2, EPOLL_CTL_ADD, efd1, ...);
>
> When a packet arrives to the device underneath "dfd", the net code will
> issue a wake_up() on its poll wake list. Epoll (efd1) has installed a
> callback wakeup entry on that queue, and the wake_up() performed by the
> "dfd" net code will end up in ep_poll_callback(). At this point epoll
> (efd1) notices that it may have some event ready, so it needs to wake up
> the waiters on its poll wait list (efd2). So it calls ep_poll_safewake()
> that ends up in another wake_up(), after having checked about the
> recursion constraints. That are, no more than EP_MAX_POLLWAKE_NESTS, to
> avoid stack blasting. Never hit the same queue, to avoid loops like:
>
> 	epoll_ctl(efd2, EPOLL_CTL_ADD, efd1, ...);
> 	epoll_ctl(efd3, EPOLL_CTL_ADD, efd2, ...);
> 	epoll_ctl(efd4, EPOLL_CTL_ADD, efd3, ...);
> 	epoll_ctl(efd1, EPOLL_CTL_ADD, efd4, ...);
>
> The code "if (tncur->wq == wq || ..." prevents re-entering the same
> queue/lock.

Since the epoll code is very careful to not nest same instance locks
allow the recursion.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: Stefan Richter <stefanr@s5r6.in-berlin.de>
Acked-by: Davide Libenzi <davidel@xmailserver.org>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 09:44:07 -08:00

522 lines
16 KiB
C

#ifndef _LINUX_WAIT_H
#define _LINUX_WAIT_H
#define WNOHANG 0x00000001
#define WUNTRACED 0x00000002
#define WSTOPPED WUNTRACED
#define WEXITED 0x00000004
#define WCONTINUED 0x00000008
#define WNOWAIT 0x01000000 /* Don't reap, just poll status. */
#define __WNOTHREAD 0x20000000 /* Don't wait on children of other threads in this group */
#define __WALL 0x40000000 /* Wait on all children, regardless of type */
#define __WCLONE 0x80000000 /* Wait only on non-SIGCHLD children */
/* First argument to waitid: */
#define P_ALL 0
#define P_PID 1
#define P_PGID 2
#ifdef __KERNEL__
#include <linux/list.h>
#include <linux/stddef.h>
#include <linux/spinlock.h>
#include <asm/system.h>
#include <asm/current.h>
typedef struct __wait_queue wait_queue_t;
typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int sync, void *key);
int default_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
struct __wait_queue {
unsigned int flags;
#define WQ_FLAG_EXCLUSIVE 0x01
void *private;
wait_queue_func_t func;
struct list_head task_list;
};
struct wait_bit_key {
void *flags;
int bit_nr;
};
struct wait_bit_queue {
struct wait_bit_key key;
wait_queue_t wait;
};
struct __wait_queue_head {
spinlock_t lock;
struct list_head task_list;
};
typedef struct __wait_queue_head wait_queue_head_t;
struct task_struct;
/*
* Macros for declaration and initialisaton of the datatypes
*/
#define __WAITQUEUE_INITIALIZER(name, tsk) { \
.private = tsk, \
.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) { \
.lock = __SPIN_LOCK_UNLOCKED(name.lock), \
.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, }
extern void init_waitqueue_head(wait_queue_head_t *q);
#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
static inline void init_waitqueue_entry(wait_queue_t *q, struct task_struct *p)
{
q->flags = 0;
q->private = p;
q->func = default_wake_function;
}
static inline void init_waitqueue_func_entry(wait_queue_t *q,
wait_queue_func_t func)
{
q->flags = 0;
q->private = NULL;
q->func = func;
}
static inline int waitqueue_active(wait_queue_head_t *q)
{
return !list_empty(&q->task_list);
}
/*
* Used to distinguish between sync and async io wait context:
* sync i/o typically specifies a NULL wait queue entry or a wait
* queue entry bound to a task (current task) to wake up.
* aio specifies a wait queue entry with an async notification
* callback routine, not associated with any task.
*/
#define is_sync_wait(wait) (!(wait) || ((wait)->private))
extern void FASTCALL(add_wait_queue(wait_queue_head_t *q, wait_queue_t * wait));
extern void FASTCALL(add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t * wait));
extern void FASTCALL(remove_wait_queue(wait_queue_head_t *q, wait_queue_t * wait));
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:
*/
static inline void __add_wait_queue_tail(wait_queue_head_t *head,
wait_queue_t *new)
{
list_add_tail(&new->task_list, &head->task_list);
}
static inline void __remove_wait_queue(wait_queue_head_t *head,
wait_queue_t *old)
{
list_del(&old->task_list);
}
void FASTCALL(__wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key));
extern void FASTCALL(__wake_up_locked(wait_queue_head_t *q, unsigned int mode));
extern void FASTCALL(__wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr));
void FASTCALL(__wake_up_bit(wait_queue_head_t *, void *, int));
int FASTCALL(__wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned));
int FASTCALL(__wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned));
void FASTCALL(wake_up_bit(void *, int));
int FASTCALL(out_of_line_wait_on_bit(void *, int, int (*)(void *), unsigned));
int FASTCALL(out_of_line_wait_on_bit_lock(void *, int, int (*)(void *), unsigned));
wait_queue_head_t *FASTCALL(bit_waitqueue(void *, int));
#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)
#define wake_up_locked(x) __wake_up_locked((x), TASK_NORMAL)
#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)
#define wake_up_interruptible_sync(x) __wake_up_sync((x), TASK_INTERRUPTIBLE, 1)
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/*
* macro to avoid include hell
*/
#define wake_up_nested(x, s) \
do { \
unsigned long flags; \
\
spin_lock_irqsave_nested(&(x)->lock, flags, (s)); \
wake_up_locked(x); \
spin_unlock_irqrestore(&(x)->lock, flags); \
} while (0)
#else
#define wake_up_nested(x, s) wake_up(x)
#endif
#define __wait_event(wq, condition) \
do { \
DEFINE_WAIT(__wait); \
\
for (;;) { \
prepare_to_wait(&wq, &__wait, TASK_UNINTERRUPTIBLE); \
if (condition) \
break; \
schedule(); \
} \
finish_wait(&wq, &__wait); \
} while (0)
/**
* 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.
*/
#define wait_event(wq, condition) \
do { \
if (condition) \
break; \
__wait_event(wq, condition); \
} while (0)
#define __wait_event_timeout(wq, condition, ret) \
do { \
DEFINE_WAIT(__wait); \
\
for (;;) { \
prepare_to_wait(&wq, &__wait, TASK_UNINTERRUPTIBLE); \
if (condition) \
break; \
ret = schedule_timeout(ret); \
if (!ret) \
break; \
} \
finish_wait(&wq, &__wait); \
} while (0)
/**
* 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.
*
* The function returns 0 if the @timeout elapsed, and the remaining
* jiffies if the condition evaluated to true before the timeout elapsed.
*/
#define wait_event_timeout(wq, condition, timeout) \
({ \
long __ret = timeout; \
if (!(condition)) \
__wait_event_timeout(wq, condition, __ret); \
__ret; \
})
#define __wait_event_interruptible(wq, condition, ret) \
do { \
DEFINE_WAIT(__wait); \
\
for (;;) { \
prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE); \
if (condition) \
break; \
if (!signal_pending(current)) { \
schedule(); \
continue; \
} \
ret = -ERESTARTSYS; \
break; \
} \
finish_wait(&wq, &__wait); \
} while (0)
/**
* 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)) \
__wait_event_interruptible(wq, condition, __ret); \
__ret; \
})
#define __wait_event_interruptible_timeout(wq, condition, ret) \
do { \
DEFINE_WAIT(__wait); \
\
for (;;) { \
prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE); \
if (condition) \
break; \
if (!signal_pending(current)) { \
ret = schedule_timeout(ret); \
if (!ret) \
break; \
continue; \
} \
ret = -ERESTARTSYS; \
break; \
} \
finish_wait(&wq, &__wait); \
} while (0)
/**
* 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.
*
* 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_timeout(wq, condition, timeout) \
({ \
long __ret = timeout; \
if (!(condition)) \
__wait_event_interruptible_timeout(wq, condition, __ret); \
__ret; \
})
#define __wait_event_interruptible_exclusive(wq, condition, ret) \
do { \
DEFINE_WAIT(__wait); \
\
for (;;) { \
prepare_to_wait_exclusive(&wq, &__wait, \
TASK_INTERRUPTIBLE); \
if (condition) \
break; \
if (!signal_pending(current)) { \
schedule(); \
continue; \
} \
ret = -ERESTARTSYS; \
break; \
} \
finish_wait(&wq, &__wait); \
} while (0)
#define wait_event_interruptible_exclusive(wq, condition) \
({ \
int __ret = 0; \
if (!(condition)) \
__wait_event_interruptible_exclusive(wq, condition, __ret);\
__ret; \
})
#define __wait_event_killable(wq, condition, ret) \
do { \
DEFINE_WAIT(__wait); \
\
for (;;) { \
prepare_to_wait(&wq, &__wait, TASK_KILLABLE); \
if (condition) \
break; \
if (!fatal_signal_pending(current)) { \
schedule(); \
continue; \
} \
ret = -ERESTARTSYS; \
break; \
} \
finish_wait(&wq, &__wait); \
} while (0)
/**
* 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)) \
__wait_event_killable(wq, condition, __ret); \
__ret; \
})
/*
* Must be called with the spinlock in the wait_queue_head_t held.
*/
static inline void add_wait_queue_exclusive_locked(wait_queue_head_t *q,
wait_queue_t * wait)
{
wait->flags |= WQ_FLAG_EXCLUSIVE;
__add_wait_queue_tail(q, wait);
}
/*
* Must be called with the spinlock in the wait_queue_head_t held.
*/
static inline void remove_wait_queue_locked(wait_queue_head_t *q,
wait_queue_t * wait)
{
__remove_wait_queue(q, wait);
}
/*
* These are the old interfaces to sleep waiting for an event.
* They are racy. DO NOT use them, use the wait_event* interfaces above.
* We plan to remove these interfaces.
*/
extern void sleep_on(wait_queue_head_t *q);
extern long sleep_on_timeout(wait_queue_head_t *q,
signed long timeout);
extern void interruptible_sleep_on(wait_queue_head_t *q);
extern long interruptible_sleep_on_timeout(wait_queue_head_t *q,
signed long timeout);
/*
* Waitqueues which are removed from the waitqueue_head at wakeup time
*/
void FASTCALL(prepare_to_wait(wait_queue_head_t *q,
wait_queue_t *wait, int state));
void FASTCALL(prepare_to_wait_exclusive(wait_queue_head_t *q,
wait_queue_t *wait, int state));
void FASTCALL(finish_wait(wait_queue_head_t *q, wait_queue_t *wait));
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);
#define DEFINE_WAIT(name) \
wait_queue_t name = { \
.private = current, \
.func = autoremove_wake_function, \
.task_list = LIST_HEAD_INIT((name).task_list), \
}
#define DEFINE_WAIT_BIT(name, word, bit) \
struct wait_bit_queue name = { \
.key = __WAIT_BIT_KEY_INITIALIZER(word, bit), \
.wait = { \
.private = current, \
.func = wake_bit_function, \
.task_list = \
LIST_HEAD_INIT((name).wait.task_list), \
}, \
}
#define init_wait(wait) \
do { \
(wait)->private = current; \
(wait)->func = autoremove_wake_function; \
INIT_LIST_HEAD(&(wait)->task_list); \
} while (0)
/**
* 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
* @action: the function used to sleep, which may take special actions
* @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.
*/
static inline int wait_on_bit(void *word, int bit,
int (*action)(void *), unsigned mode)
{
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
* @action: the function used to sleep, which may take special actions
* @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.
*/
static inline int wait_on_bit_lock(void *word, int bit,
int (*action)(void *), unsigned mode)
{
if (!test_and_set_bit(bit, word))
return 0;
return out_of_line_wait_on_bit_lock(word, bit, action, mode);
}
#endif /* __KERNEL__ */
#endif