1
linux/kernel/semaphore.c
Linus Torvalds 00b41ec261 Revert "semaphore: fix"
This reverts commit bf726eab37, as it has
been reported to cause a regression with processes stuck in __down(),
apparently because some missing wakeup.

Quoth Sven Wegener:
 "I'm currently investigating a regression that has showed up with my
  last git pull yesterday.  Bisecting the commits showed bf726e
  "semaphore: fix" to be the culprit, reverting it fixed the issue.

  Symptoms: During heavy filesystem usage (e.g.  a kernel compile) I get
  several compiler processes in uninterruptible sleep, blocking all i/o
  on the filesystem.  System is an Intel Core 2 Quad running a 64bit
  kernel and userspace.  Filesystem is xfs on top of lvm.  See below for
  the output of sysrq-w."

See

	http://lkml.org/lkml/2008/5/10/45

for full report.

In the meantime, we can just fix the BKL performance regression by
reverting back to the good old BKL spinlock implementation instead,
since any sleeping lock will generally perform badly, especially if it
tries to be fair.

Reported-by: Sven Wegener <sven.wegener@stealer.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-05-10 20:43:22 -07:00

265 lines
7.2 KiB
C

/*
* Copyright (c) 2008 Intel Corporation
* Author: Matthew Wilcox <willy@linux.intel.com>
*
* Distributed under the terms of the GNU GPL, version 2
*
* This file implements counting semaphores.
* A counting semaphore may be acquired 'n' times before sleeping.
* See mutex.c for single-acquisition sleeping locks which enforce
* rules which allow code to be debugged more easily.
*/
/*
* Some notes on the implementation:
*
* The spinlock controls access to the other members of the semaphore.
* down_trylock() and up() can be called from interrupt context, so we
* have to disable interrupts when taking the lock. It turns out various
* parts of the kernel expect to be able to use down() on a semaphore in
* interrupt context when they know it will succeed, so we have to use
* irqsave variants for down(), down_interruptible() and down_killable()
* too.
*
* The ->count variable represents how many more tasks can acquire this
* semaphore. If it's zero, there may be tasks waiting on the wait_list.
*/
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/semaphore.h>
#include <linux/spinlock.h>
static noinline void __down(struct semaphore *sem);
static noinline int __down_interruptible(struct semaphore *sem);
static noinline int __down_killable(struct semaphore *sem);
static noinline int __down_timeout(struct semaphore *sem, long jiffies);
static noinline void __up(struct semaphore *sem);
/**
* down - acquire the semaphore
* @sem: the semaphore to be acquired
*
* Acquires the semaphore. If no more tasks are allowed to acquire the
* semaphore, calling this function will put the task to sleep until the
* semaphore is released.
*
* Use of this function is deprecated, please use down_interruptible() or
* down_killable() instead.
*/
void down(struct semaphore *sem)
{
unsigned long flags;
spin_lock_irqsave(&sem->lock, flags);
if (likely(sem->count > 0))
sem->count--;
else
__down(sem);
spin_unlock_irqrestore(&sem->lock, flags);
}
EXPORT_SYMBOL(down);
/**
* down_interruptible - acquire the semaphore unless interrupted
* @sem: the semaphore to be acquired
*
* Attempts to acquire the semaphore. If no more tasks are allowed to
* acquire the semaphore, calling this function will put the task to sleep.
* If the sleep is interrupted by a signal, this function will return -EINTR.
* If the semaphore is successfully acquired, this function returns 0.
*/
int down_interruptible(struct semaphore *sem)
{
unsigned long flags;
int result = 0;
spin_lock_irqsave(&sem->lock, flags);
if (likely(sem->count > 0))
sem->count--;
else
result = __down_interruptible(sem);
spin_unlock_irqrestore(&sem->lock, flags);
return result;
}
EXPORT_SYMBOL(down_interruptible);
/**
* down_killable - acquire the semaphore unless killed
* @sem: the semaphore to be acquired
*
* Attempts to acquire the semaphore. If no more tasks are allowed to
* acquire the semaphore, calling this function will put the task to sleep.
* If the sleep is interrupted by a fatal signal, this function will return
* -EINTR. If the semaphore is successfully acquired, this function returns
* 0.
*/
int down_killable(struct semaphore *sem)
{
unsigned long flags;
int result = 0;
spin_lock_irqsave(&sem->lock, flags);
if (likely(sem->count > 0))
sem->count--;
else
result = __down_killable(sem);
spin_unlock_irqrestore(&sem->lock, flags);
return result;
}
EXPORT_SYMBOL(down_killable);
/**
* down_trylock - try to acquire the semaphore, without waiting
* @sem: the semaphore to be acquired
*
* Try to acquire the semaphore atomically. Returns 0 if the mutex has
* been acquired successfully or 1 if it it cannot be acquired.
*
* NOTE: This return value is inverted from both spin_trylock and
* mutex_trylock! Be careful about this when converting code.
*
* Unlike mutex_trylock, this function can be used from interrupt context,
* and the semaphore can be released by any task or interrupt.
*/
int down_trylock(struct semaphore *sem)
{
unsigned long flags;
int count;
spin_lock_irqsave(&sem->lock, flags);
count = sem->count - 1;
if (likely(count >= 0))
sem->count = count;
spin_unlock_irqrestore(&sem->lock, flags);
return (count < 0);
}
EXPORT_SYMBOL(down_trylock);
/**
* down_timeout - acquire the semaphore within a specified time
* @sem: the semaphore to be acquired
* @jiffies: how long to wait before failing
*
* Attempts to acquire the semaphore. If no more tasks are allowed to
* acquire the semaphore, calling this function will put the task to sleep.
* If the semaphore is not released within the specified number of jiffies,
* this function returns -ETIME. It returns 0 if the semaphore was acquired.
*/
int down_timeout(struct semaphore *sem, long jiffies)
{
unsigned long flags;
int result = 0;
spin_lock_irqsave(&sem->lock, flags);
if (likely(sem->count > 0))
sem->count--;
else
result = __down_timeout(sem, jiffies);
spin_unlock_irqrestore(&sem->lock, flags);
return result;
}
EXPORT_SYMBOL(down_timeout);
/**
* up - release the semaphore
* @sem: the semaphore to release
*
* Release the semaphore. Unlike mutexes, up() may be called from any
* context and even by tasks which have never called down().
*/
void up(struct semaphore *sem)
{
unsigned long flags;
spin_lock_irqsave(&sem->lock, flags);
if (likely(list_empty(&sem->wait_list)))
sem->count++;
else
__up(sem);
spin_unlock_irqrestore(&sem->lock, flags);
}
EXPORT_SYMBOL(up);
/* Functions for the contended case */
struct semaphore_waiter {
struct list_head list;
struct task_struct *task;
int up;
};
/*
* Because this function is inlined, the 'state' parameter will be
* constant, and thus optimised away by the compiler. Likewise the
* 'timeout' parameter for the cases without timeouts.
*/
static inline int __sched __down_common(struct semaphore *sem, long state,
long timeout)
{
struct task_struct *task = current;
struct semaphore_waiter waiter;
list_add_tail(&waiter.list, &sem->wait_list);
waiter.task = task;
waiter.up = 0;
for (;;) {
if (state == TASK_INTERRUPTIBLE && signal_pending(task))
goto interrupted;
if (state == TASK_KILLABLE && fatal_signal_pending(task))
goto interrupted;
if (timeout <= 0)
goto timed_out;
__set_task_state(task, state);
spin_unlock_irq(&sem->lock);
timeout = schedule_timeout(timeout);
spin_lock_irq(&sem->lock);
if (waiter.up)
return 0;
}
timed_out:
list_del(&waiter.list);
return -ETIME;
interrupted:
list_del(&waiter.list);
return -EINTR;
}
static noinline void __sched __down(struct semaphore *sem)
{
__down_common(sem, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
}
static noinline int __sched __down_interruptible(struct semaphore *sem)
{
return __down_common(sem, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
}
static noinline int __sched __down_killable(struct semaphore *sem)
{
return __down_common(sem, TASK_KILLABLE, MAX_SCHEDULE_TIMEOUT);
}
static noinline int __sched __down_timeout(struct semaphore *sem, long jiffies)
{
return __down_common(sem, TASK_UNINTERRUPTIBLE, jiffies);
}
static noinline void __sched __up(struct semaphore *sem)
{
struct semaphore_waiter *waiter = list_first_entry(&sem->wait_list,
struct semaphore_waiter, list);
list_del(&waiter->list);
waiter->up = 1;
wake_up_process(waiter->task);
}