linux_dsm_epyc7002/include/linux/wait.h

651 lines
21 KiB
C
Raw Normal View History

#ifndef _LINUX_WAIT_H
#define _LINUX_WAIT_H
#include <linux/list.h>
#include <linux/stddef.h>
#include <linux/spinlock.h>
#include <asm/current.h>
#include <uapi/linux/wait.h>
typedef struct __wait_queue wait_queue_t;
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);
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, const char *name, struct lock_class_key *);
#define init_waitqueue_head(q) \
do { \
static struct lock_class_key __key; \
\
__init_waitqueue_head((q), #q, &__key); \
} while (0)
#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);
}
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);
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_exclusive(wait_queue_head_t *q,
wait_queue_t *wait)
{
wait->flags |= WQ_FLAG_EXCLUSIVE;
__add_wait_queue(q, wait);
}
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 __add_wait_queue_tail_exclusive(wait_queue_head_t *q,
wait_queue_t *wait)
{
wait->flags |= WQ_FLAG_EXCLUSIVE;
__add_wait_queue_tail(q, wait);
}
static inline void __remove_wait_queue(wait_queue_head_t *head,
wait_queue_t *old)
{
list_del(&old->task_list);
}
void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
epoll keyed wakeups: add __wake_up_locked_key() and __wake_up_sync_key() This patchset introduces wakeup hints for some of the most popular (from epoll POV) devices, so that epoll code can avoid spurious wakeups on its waiters. The problem with epoll is that the callback-based wakeups do not, ATM, carry any information about the events the wakeup is related to. So the only choice epoll has (not being able to call f_op->poll() from inside the callback), is to add the file* to a ready-list and resolve the real events later on, at epoll_wait() (or its own f_op->poll()) time. This can cause spurious wakeups, since the wake_up() itself might be for an event the caller is not interested into. The rate of these spurious wakeup can be pretty high in case of many network sockets being monitored. By allowing devices to report the events the wakeups refer to (at least the two major classes - POLLIN/POLLOUT), we are able to spare useless wakeups by proper handling inside the epoll's poll callback. Epoll will have in any case to call f_op->poll() on the file* later on, since the change to be done in order to have the full event set sent via wakeup, is too invasive for the way our f_op->poll() system works (the full event set is calculated inside the poll function - there are too many of them to even start thinking the change - also poll/select would need change too). Epoll is changed in a way that both devices which send event hints, and the ones that don't, are correctly handled. The former will gain some efficiency though. As a general rule for devices, would be to add an event mask by using key-aware wakeup macros, when making up poll wait queues. I tested it (together with the epoll's poll fix patch Andrew has in -mm) and wakeups for the supported devices are correctly filtered. Test program available here: http://www.xmailserver.org/epoll_test.c This patch: Nothing revolutionary here. Just using the available "key" that our wakeup core already support. The __wake_up_locked_key() was no brainer, since both __wake_up_locked() and __wake_up_locked_key() are thin wrappers around __wake_up_common(). The __wake_up_sync() function had a body, so the choice was between borrowing the body for __wake_up_sync_key() and calling it from __wake_up_sync(), or make an inline and calling it from both. I chose the former since in most archs it all resolves to "mov $0, REG; jmp ADDR". Signed-off-by: Davide Libenzi <davidel@xmailserver.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Ingo Molnar <mingo@elte.hu> Cc: David Miller <davem@davemloft.net> Cc: William Lee Irwin III <wli@movementarian.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-01 05:24:20 +07:00
void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr,
void *key);
void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr);
epoll keyed wakeups: add __wake_up_locked_key() and __wake_up_sync_key() This patchset introduces wakeup hints for some of the most popular (from epoll POV) devices, so that epoll code can avoid spurious wakeups on its waiters. The problem with epoll is that the callback-based wakeups do not, ATM, carry any information about the events the wakeup is related to. So the only choice epoll has (not being able to call f_op->poll() from inside the callback), is to add the file* to a ready-list and resolve the real events later on, at epoll_wait() (or its own f_op->poll()) time. This can cause spurious wakeups, since the wake_up() itself might be for an event the caller is not interested into. The rate of these spurious wakeup can be pretty high in case of many network sockets being monitored. By allowing devices to report the events the wakeups refer to (at least the two major classes - POLLIN/POLLOUT), we are able to spare useless wakeups by proper handling inside the epoll's poll callback. Epoll will have in any case to call f_op->poll() on the file* later on, since the change to be done in order to have the full event set sent via wakeup, is too invasive for the way our f_op->poll() system works (the full event set is calculated inside the poll function - there are too many of them to even start thinking the change - also poll/select would need change too). Epoll is changed in a way that both devices which send event hints, and the ones that don't, are correctly handled. The former will gain some efficiency though. As a general rule for devices, would be to add an event mask by using key-aware wakeup macros, when making up poll wait queues. I tested it (together with the epoll's poll fix patch Andrew has in -mm) and wakeups for the supported devices are correctly filtered. Test program available here: http://www.xmailserver.org/epoll_test.c This patch: Nothing revolutionary here. Just using the available "key" that our wakeup core already support. The __wake_up_locked_key() was no brainer, since both __wake_up_locked() and __wake_up_locked_key() are thin wrappers around __wake_up_common(). The __wake_up_sync() function had a body, so the choice was between borrowing the body for __wake_up_sync_key() and calling it from __wake_up_sync(), or make an inline and calling it from both. I chose the former since in most archs it all resolves to "mov $0, REG; jmp ADDR". Signed-off-by: Davide Libenzi <davidel@xmailserver.org> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Ingo Molnar <mingo@elte.hu> Cc: David Miller <davem@davemloft.net> Cc: William Lee Irwin III <wli@movementarian.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-01 05:24:20 +07:00
void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr);
void __wake_up_bit(wait_queue_head_t *, void *, int);
int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned);
int __wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned);
void wake_up_bit(void *, int);
int out_of_line_wait_on_bit(void *, int, int (*)(void *), unsigned);
int out_of_line_wait_on_bit_lock(void *, int, int (*)(void *), unsigned);
wait_queue_head_t *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, 1)
#define wake_up_all_locked(x) __wake_up_locked((x), TASK_NORMAL, 0)
#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)
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 13:27:20 +07:00
/*
* Wakeup macros to be used to report events to the targets.
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 13:27:20 +07:00
*/
#define wake_up_poll(x, m) \
__wake_up(x, TASK_NORMAL, 1, (void *) (m))
#define wake_up_locked_poll(x, m) \
__wake_up_locked_key((x), TASK_NORMAL, (void *) (m))
#define wake_up_interruptible_poll(x, m) \
__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))
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 13:27:20 +07:00
#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); \
wait: prevent exclusive waiter starvation With exclusive waiters, every process woken up through the wait queue must ensure that the next waiter down the line is woken when it has finished. Interruptible waiters don't do that when aborting due to a signal. And if an aborting waiter is concurrently woken up through the waitqueue, noone will ever wake up the next waiter. This has been observed with __wait_on_bit_lock() used by lock_page_killable(): the first contender on the queue was aborting when the actual lock holder woke it up concurrently. The aborted contender didn't acquire the lock and therefor never did an unlock followed by waking up the next waiter. Add abort_exclusive_wait() which removes the process' wait descriptor from the waitqueue, iff still queued, or wakes up the next waiter otherwise. It does so under the waitqueue lock. Racing with a wake up means the aborting process is either already woken (removed from the queue) and will wake up the next waiter, or it will remove itself from the queue and the concurrent wake up will apply to the next waiter after it. Use abort_exclusive_wait() in __wait_event_interruptible_exclusive() and __wait_on_bit_lock() when they were interrupted by other means than a wake up through the queue. [akpm@linux-foundation.org: coding-style fixes] Reported-by: Chris Mason <chris.mason@oracle.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Mentored-by: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Chuck Lever <cel@citi.umich.edu> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Ingo Molnar <mingo@elte.hu> Cc: <stable@kernel.org> ["after some testing"] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-05 06:12:14 +07:00
if (condition) { \
finish_wait(&wq, &__wait); \
break; \
wait: prevent exclusive waiter starvation With exclusive waiters, every process woken up through the wait queue must ensure that the next waiter down the line is woken when it has finished. Interruptible waiters don't do that when aborting due to a signal. And if an aborting waiter is concurrently woken up through the waitqueue, noone will ever wake up the next waiter. This has been observed with __wait_on_bit_lock() used by lock_page_killable(): the first contender on the queue was aborting when the actual lock holder woke it up concurrently. The aborted contender didn't acquire the lock and therefor never did an unlock followed by waking up the next waiter. Add abort_exclusive_wait() which removes the process' wait descriptor from the waitqueue, iff still queued, or wakes up the next waiter otherwise. It does so under the waitqueue lock. Racing with a wake up means the aborting process is either already woken (removed from the queue) and will wake up the next waiter, or it will remove itself from the queue and the concurrent wake up will apply to the next waiter after it. Use abort_exclusive_wait() in __wait_event_interruptible_exclusive() and __wait_on_bit_lock() when they were interrupted by other means than a wake up through the queue. [akpm@linux-foundation.org: coding-style fixes] Reported-by: Chris Mason <chris.mason@oracle.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Mentored-by: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Chuck Lever <cel@citi.umich.edu> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Ingo Molnar <mingo@elte.hu> Cc: <stable@kernel.org> ["after some testing"] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-05 06:12:14 +07:00
} \
if (!signal_pending(current)) { \
schedule(); \
continue; \
} \
ret = -ERESTARTSYS; \
wait: prevent exclusive waiter starvation With exclusive waiters, every process woken up through the wait queue must ensure that the next waiter down the line is woken when it has finished. Interruptible waiters don't do that when aborting due to a signal. And if an aborting waiter is concurrently woken up through the waitqueue, noone will ever wake up the next waiter. This has been observed with __wait_on_bit_lock() used by lock_page_killable(): the first contender on the queue was aborting when the actual lock holder woke it up concurrently. The aborted contender didn't acquire the lock and therefor never did an unlock followed by waking up the next waiter. Add abort_exclusive_wait() which removes the process' wait descriptor from the waitqueue, iff still queued, or wakes up the next waiter otherwise. It does so under the waitqueue lock. Racing with a wake up means the aborting process is either already woken (removed from the queue) and will wake up the next waiter, or it will remove itself from the queue and the concurrent wake up will apply to the next waiter after it. Use abort_exclusive_wait() in __wait_event_interruptible_exclusive() and __wait_on_bit_lock() when they were interrupted by other means than a wake up through the queue. [akpm@linux-foundation.org: coding-style fixes] Reported-by: Chris Mason <chris.mason@oracle.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Mentored-by: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Chuck Lever <cel@citi.umich.edu> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Ingo Molnar <mingo@elte.hu> Cc: <stable@kernel.org> ["after some testing"] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-05 06:12:14 +07:00
abort_exclusive_wait(&wq, &__wait, \
TASK_INTERRUPTIBLE, NULL); \
break; \
} \
} while (0)
#define wait_event_interruptible_exclusive(wq, condition) \
({ \
int __ret = 0; \
if (!(condition)) \
__wait_event_interruptible_exclusive(wq, condition, __ret);\
__ret; \
})
wait_event_interruptible_locked() interface New wait_event_interruptible{,_exclusive}_locked{,_irq} macros added. They work just like versions without _locked* suffix but require the wait queue's lock to be held. Also __wake_up_locked() is now exported as to pair it with the above macros. The use case of this new facility is when one uses wait queue's lock to protect a data structure. This may be advantageous if the structure needs to be protected by a spinlock anyway. In particular, with additional spinlock the following code has to be used to wait for a condition: spin_lock(&data.lock); ... for (ret = 0; !ret && !(condition); ) { spin_unlock(&data.lock); ret = wait_event_interruptible(data.wqh, (condition)); spin_lock(&data.lock); } ... spin_unlock(&data.lock); This looks bizarre plus wait_event_interruptible() locks the wait queue's lock anyway so there is a unlock+lock sequence where it could be avoided. To avoid those problems and benefit from wait queue's lock, a code similar to the following should be used: /* Waiting */ spin_lock(&data.wqh.lock); ... ret = wait_event_interruptible_locked(data.wqh, (condition)); ... spin_unlock(&data.wqh.lock); /* Waiting exclusively */ spin_lock(&data.whq.lock); ... ret = wait_event_interruptible_exclusive_locked(data.whq, (condition)); ... spin_unlock(&data.whq.lock); /* Waking up */ spin_lock(&data.wqh.lock); ... wake_up_locked(&data.wqh); ... spin_unlock(&data.wqh.lock); When spin_lock_irq() is used matching versions of macros need to be used (*_locked_irq()). Signed-off-by: Michal Nazarewicz <m.nazarewicz@samsung.com> Cc: Kyungmin Park <kyungmin.park@samsung.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Takashi Iwai <tiwai@suse.de> Cc: David Howells <dhowells@redhat.com> Cc: Andreas Herrmann <andreas.herrmann3@amd.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Mike Galbraith <efault@gmx.de> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-05-05 17:53:11 +07:00
#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))
#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; \
})
/*
* 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 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);
void finish_wait(wait_queue_head_t *q, wait_queue_t *wait);
wait: prevent exclusive waiter starvation With exclusive waiters, every process woken up through the wait queue must ensure that the next waiter down the line is woken when it has finished. Interruptible waiters don't do that when aborting due to a signal. And if an aborting waiter is concurrently woken up through the waitqueue, noone will ever wake up the next waiter. This has been observed with __wait_on_bit_lock() used by lock_page_killable(): the first contender on the queue was aborting when the actual lock holder woke it up concurrently. The aborted contender didn't acquire the lock and therefor never did an unlock followed by waking up the next waiter. Add abort_exclusive_wait() which removes the process' wait descriptor from the waitqueue, iff still queued, or wakes up the next waiter otherwise. It does so under the waitqueue lock. Racing with a wake up means the aborting process is either already woken (removed from the queue) and will wake up the next waiter, or it will remove itself from the queue and the concurrent wake up will apply to the next waiter after it. Use abort_exclusive_wait() in __wait_event_interruptible_exclusive() and __wait_on_bit_lock() when they were interrupted by other means than a wake up through the queue. [akpm@linux-foundation.org: coding-style fixes] Reported-by: Chris Mason <chris.mason@oracle.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Mentored-by: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Chuck Lever <cel@citi.umich.edu> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Ingo Molnar <mingo@elte.hu> Cc: <stable@kernel.org> ["after some testing"] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-05 06:12:14 +07:00
void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
unsigned int mode, void *key);
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);
net: Avoid extra wakeups of threads blocked in wait_for_packet() In 2.6.25 we added UDP mem accounting. This unfortunatly added a penalty when a frame is transmitted, since we have at TX completion time to call sock_wfree() to perform necessary memory accounting. This calls sock_def_write_space() and utimately scheduler if any thread is waiting on the socket. Thread(s) waiting for an incoming frame was scheduled, then had to sleep again as event was meaningless. (All threads waiting on a socket are using same sk_sleep anchor) This adds lot of extra wakeups and increases latencies, as noted by Christoph Lameter, and slows down softirq handler. Reference : http://marc.info/?l=linux-netdev&m=124060437012283&w=2 Fortunatly, Davide Libenzi recently added concept of keyed wakeups into kernel, and particularly for sockets (see commit 37e5540b3c9d838eb20f2ca8ea2eb8072271e403 epoll keyed wakeups: make sockets use keyed wakeups) Davide goal was to optimize epoll, but this new wakeup infrastructure can help non epoll users as well, if they care to setup an appropriate handler. This patch introduces new DEFINE_WAIT_FUNC() helper and uses it in wait_for_packet(), so that only relevant event can wakeup a thread blocked in this function. Trace of function calls from bnx2 TX completion bnx2_poll_work() is : __kfree_skb() skb_release_head_state() sock_wfree() sock_def_write_space() __wake_up_sync_key() __wake_up_common() receiver_wake_function() : Stops here since thread is waiting for an INPUT Reported-by: Christoph Lameter <cl@linux.com> Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-04-28 16:24:21 +07:00
#define DEFINE_WAIT_FUNC(name, function) \
wait_queue_t name = { \
.private = current, \
net: Avoid extra wakeups of threads blocked in wait_for_packet() In 2.6.25 we added UDP mem accounting. This unfortunatly added a penalty when a frame is transmitted, since we have at TX completion time to call sock_wfree() to perform necessary memory accounting. This calls sock_def_write_space() and utimately scheduler if any thread is waiting on the socket. Thread(s) waiting for an incoming frame was scheduled, then had to sleep again as event was meaningless. (All threads waiting on a socket are using same sk_sleep anchor) This adds lot of extra wakeups and increases latencies, as noted by Christoph Lameter, and slows down softirq handler. Reference : http://marc.info/?l=linux-netdev&m=124060437012283&w=2 Fortunatly, Davide Libenzi recently added concept of keyed wakeups into kernel, and particularly for sockets (see commit 37e5540b3c9d838eb20f2ca8ea2eb8072271e403 epoll keyed wakeups: make sockets use keyed wakeups) Davide goal was to optimize epoll, but this new wakeup infrastructure can help non epoll users as well, if they care to setup an appropriate handler. This patch introduces new DEFINE_WAIT_FUNC() helper and uses it in wait_for_packet(), so that only relevant event can wakeup a thread blocked in this function. Trace of function calls from bnx2 TX completion bnx2_poll_work() is : __kfree_skb() skb_release_head_state() sock_wfree() sock_def_write_space() __wake_up_sync_key() __wake_up_common() receiver_wake_function() : Stops here since thread is waiting for an INPUT Reported-by: Christoph Lameter <cl@linux.com> Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-04-28 16:24:21 +07:00
.func = function, \
.task_list = LIST_HEAD_INIT((name).task_list), \
}
net: Avoid extra wakeups of threads blocked in wait_for_packet() In 2.6.25 we added UDP mem accounting. This unfortunatly added a penalty when a frame is transmitted, since we have at TX completion time to call sock_wfree() to perform necessary memory accounting. This calls sock_def_write_space() and utimately scheduler if any thread is waiting on the socket. Thread(s) waiting for an incoming frame was scheduled, then had to sleep again as event was meaningless. (All threads waiting on a socket are using same sk_sleep anchor) This adds lot of extra wakeups and increases latencies, as noted by Christoph Lameter, and slows down softirq handler. Reference : http://marc.info/?l=linux-netdev&m=124060437012283&w=2 Fortunatly, Davide Libenzi recently added concept of keyed wakeups into kernel, and particularly for sockets (see commit 37e5540b3c9d838eb20f2ca8ea2eb8072271e403 epoll keyed wakeups: make sockets use keyed wakeups) Davide goal was to optimize epoll, but this new wakeup infrastructure can help non epoll users as well, if they care to setup an appropriate handler. This patch introduces new DEFINE_WAIT_FUNC() helper and uses it in wait_for_packet(), so that only relevant event can wakeup a thread blocked in this function. Trace of function calls from bnx2 TX completion bnx2_poll_work() is : __kfree_skb() skb_release_head_state() sock_wfree() sock_def_write_space() __wake_up_sync_key() __wake_up_common() receiver_wake_function() : Stops here since thread is waiting for an INPUT Reported-by: Christoph Lameter <cl@linux.com> Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-04-28 16:24:21 +07:00
#define DEFINE_WAIT(name) DEFINE_WAIT_FUNC(name, autoremove_wake_function)
#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); \
(wait)->flags = 0; \
} 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