linux/kernel/locking/semaphore.c
Davidlohr Bueso 642fa448ae sched/core: Remove set_task_state()
This is a nasty interface and setting the state of a foreign task must
not be done. As of the following commit:

  be628be095 ("bcache: Make gc wakeup sane, remove set_task_state()")

... everyone in the kernel calls set_task_state() with current, allowing
the helper to be removed.

However, as the comment indicates, it is still around for those archs
where computing current is more expensive than using a pointer, at least
in theory. An important arch that is affected is arm64, however this has
been addressed now [1] and performance is up to par making no difference
with either calls.

Of all the callers, if any, it's the locking bits that would care most
about this -- ie: we end up passing a tsk pointer to a lot of the lock
slowpath, and setting ->state on that. The following numbers are based
on two tests: a custom ad-hoc microbenchmark that just measures
latencies (for ~65 million calls) between get_task_state() vs
get_current_state().

Secondly for a higher overview, an unlink microbenchmark was used,
which pounds on a single file with open, close,unlink combos with
increasing thread counts (up to 4x ncpus). While the workload is quite
unrealistic, it does contend a lot on the inode mutex or now rwsem.

[1] https://lkml.kernel.org/r/1483468021-8237-1-git-send-email-mark.rutland@arm.com

== 1. x86-64 ==

Avg runtime set_task_state():    601 msecs
Avg runtime set_current_state(): 552 msecs

                                            vanilla                 dirty
Hmean    unlink1-processes-2      36089.26 (  0.00%)    38977.33 (  8.00%)
Hmean    unlink1-processes-5      28555.01 (  0.00%)    29832.55 (  4.28%)
Hmean    unlink1-processes-8      37323.75 (  0.00%)    44974.57 ( 20.50%)
Hmean    unlink1-processes-12     43571.88 (  0.00%)    44283.01 (  1.63%)
Hmean    unlink1-processes-21     34431.52 (  0.00%)    38284.45 ( 11.19%)
Hmean    unlink1-processes-30     34813.26 (  0.00%)    37975.17 (  9.08%)
Hmean    unlink1-processes-48     37048.90 (  0.00%)    39862.78 (  7.59%)
Hmean    unlink1-processes-79     35630.01 (  0.00%)    36855.30 (  3.44%)
Hmean    unlink1-processes-110    36115.85 (  0.00%)    39843.91 ( 10.32%)
Hmean    unlink1-processes-141    32546.96 (  0.00%)    35418.52 (  8.82%)
Hmean    unlink1-processes-172    34674.79 (  0.00%)    36899.21 (  6.42%)
Hmean    unlink1-processes-203    37303.11 (  0.00%)    36393.04 ( -2.44%)
Hmean    unlink1-processes-224    35712.13 (  0.00%)    36685.96 (  2.73%)

== 2. ppc64le ==

Avg runtime set_task_state():  938 msecs
Avg runtime set_current_state: 940 msecs

                                            vanilla                 dirty
Hmean    unlink1-processes-2      19269.19 (  0.00%)    30704.50 ( 59.35%)
Hmean    unlink1-processes-5      20106.15 (  0.00%)    21804.15 (  8.45%)
Hmean    unlink1-processes-8      17496.97 (  0.00%)    17243.28 ( -1.45%)
Hmean    unlink1-processes-12     14224.15 (  0.00%)    17240.21 ( 21.20%)
Hmean    unlink1-processes-21     14155.66 (  0.00%)    15681.23 ( 10.78%)
Hmean    unlink1-processes-30     14450.70 (  0.00%)    15995.83 ( 10.69%)
Hmean    unlink1-processes-48     16945.57 (  0.00%)    16370.42 ( -3.39%)
Hmean    unlink1-processes-79     15788.39 (  0.00%)    14639.27 ( -7.28%)
Hmean    unlink1-processes-110    14268.48 (  0.00%)    14377.40 (  0.76%)
Hmean    unlink1-processes-141    14023.65 (  0.00%)    16271.69 ( 16.03%)
Hmean    unlink1-processes-172    13417.62 (  0.00%)    16067.55 ( 19.75%)
Hmean    unlink1-processes-203    15293.08 (  0.00%)    15440.40 (  0.96%)
Hmean    unlink1-processes-234    13719.32 (  0.00%)    16190.74 ( 18.01%)
Hmean    unlink1-processes-265    16400.97 (  0.00%)    16115.22 ( -1.74%)
Hmean    unlink1-processes-296    14388.60 (  0.00%)    16216.13 ( 12.70%)
Hmean    unlink1-processes-320    15771.85 (  0.00%)    15905.96 (  0.85%)

x86-64 (known to be fast for get_current()/this_cpu_read_stable() caching)
and ppc64 (with paca) show similar improvements in the unlink microbenches.
The small delta for ppc64 (2ms), does not represent the gains on the unlink
runs. In the case of x86, there was a decent amount of variation in the
latency runs, but always within a 20 to 50ms increase), ppc was more constant.

Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: dave@stgolabs.net
Cc: mark.rutland@arm.com
Link: http://lkml.kernel.org/r/1483479794-14013-5-git-send-email-dave@stgolabs.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-01-14 11:14:16 +01:00

263 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/export.h>
#include <linux/sched.h>
#include <linux/semaphore.h>
#include <linux/spinlock.h>
#include <linux/ftrace.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 timeout);
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;
raw_spin_lock_irqsave(&sem->lock, flags);
if (likely(sem->count > 0))
sem->count--;
else
__down(sem);
raw_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;
raw_spin_lock_irqsave(&sem->lock, flags);
if (likely(sem->count > 0))
sem->count--;
else
result = __down_interruptible(sem);
raw_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;
raw_spin_lock_irqsave(&sem->lock, flags);
if (likely(sem->count > 0))
sem->count--;
else
result = __down_killable(sem);
raw_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 semaphore 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;
raw_spin_lock_irqsave(&sem->lock, flags);
count = sem->count - 1;
if (likely(count >= 0))
sem->count = count;
raw_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
* @timeout: 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 timeout)
{
unsigned long flags;
int result = 0;
raw_spin_lock_irqsave(&sem->lock, flags);
if (likely(sem->count > 0))
sem->count--;
else
result = __down_timeout(sem, timeout);
raw_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;
raw_spin_lock_irqsave(&sem->lock, flags);
if (likely(list_empty(&sem->wait_list)))
sem->count++;
else
__up(sem);
raw_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;
bool 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 semaphore_waiter waiter;
list_add_tail(&waiter.list, &sem->wait_list);
waiter.task = current;
waiter.up = false;
for (;;) {
if (signal_pending_state(state, current))
goto interrupted;
if (unlikely(timeout <= 0))
goto timed_out;
__set_current_state(state);
raw_spin_unlock_irq(&sem->lock);
timeout = schedule_timeout(timeout);
raw_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 timeout)
{
return __down_common(sem, TASK_UNINTERRUPTIBLE, timeout);
}
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 = true;
wake_up_process(waiter->task);
}