kernel_optimize_test/kernel/locking/qrwlock.c
Waiman Long 405963b6a5 locking/qrwlock: Don't contend with readers when setting _QW_WAITING
The current cmpxchg() loop in setting the _QW_WAITING flag for writers
in queue_write_lock_slowpath() will contend with incoming readers
causing possibly extra cmpxchg() operations that are wasteful. This
patch changes the code to do a byte cmpxchg() to eliminate contention
with new readers.

A multithreaded microbenchmark running 5M read_lock/write_lock loop
on a 8-socket 80-core Westmere-EX machine running 4.0 based kernel
with the qspinlock patch have the following execution times (in ms)
with and without the patch:

With R:W ratio = 5:1

	Threads	   w/o patch	with patch	% change
	-------	   ---------	----------	--------
	   2	     990	    895		  -9.6%
	   3	    2136	   1912		 -10.5%
	   4	    3166	   2830		 -10.6%
	   5	    3953	   3629		  -8.2%
	   6	    4628	   4405		  -4.8%
	   7	    5344	   5197		  -2.8%
	   8	    6065	   6004		  -1.0%
	   9	    6826	   6811		  -0.2%
	  10	    7599	   7599		   0.0%
	  15	    9757	   9766		  +0.1%
	  20	   13767	  13817		  +0.4%

With small number of contending threads, this patch can improve
locking performance by up to 10%. With more contending threads,
however, the gain diminishes.

Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Douglas Hatch <doug.hatch@hp.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hp.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1433863153-30722-3-git-send-email-Waiman.Long@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-06-19 09:45:38 +02:00

153 lines
4.0 KiB
C

/*
* Queued read/write locks
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* (C) Copyright 2013-2014 Hewlett-Packard Development Company, L.P.
*
* Authors: Waiman Long <waiman.long@hp.com>
*/
#include <linux/smp.h>
#include <linux/bug.h>
#include <linux/cpumask.h>
#include <linux/percpu.h>
#include <linux/hardirq.h>
#include <asm/qrwlock.h>
/*
* This internal data structure is used for optimizing access to some of
* the subfields within the atomic_t cnts.
*/
struct __qrwlock {
union {
atomic_t cnts;
struct {
#ifdef __LITTLE_ENDIAN
u8 wmode; /* Writer mode */
u8 rcnts[3]; /* Reader counts */
#else
u8 rcnts[3]; /* Reader counts */
u8 wmode; /* Writer mode */
#endif
};
};
arch_spinlock_t lock;
};
/**
* rspin_until_writer_unlock - inc reader count & spin until writer is gone
* @lock : Pointer to queue rwlock structure
* @writer: Current queue rwlock writer status byte
*
* In interrupt context or at the head of the queue, the reader will just
* increment the reader count & wait until the writer releases the lock.
*/
static __always_inline void
rspin_until_writer_unlock(struct qrwlock *lock, u32 cnts)
{
while ((cnts & _QW_WMASK) == _QW_LOCKED) {
cpu_relax_lowlatency();
cnts = smp_load_acquire((u32 *)&lock->cnts);
}
}
/**
* queue_read_lock_slowpath - acquire read lock of a queue rwlock
* @lock: Pointer to queue rwlock structure
*/
void queue_read_lock_slowpath(struct qrwlock *lock)
{
u32 cnts;
/*
* Readers come here when they cannot get the lock without waiting
*/
if (unlikely(in_interrupt())) {
/*
* Readers in interrupt context will spin until the lock is
* available without waiting in the queue.
*/
cnts = smp_load_acquire((u32 *)&lock->cnts);
rspin_until_writer_unlock(lock, cnts);
return;
}
atomic_sub(_QR_BIAS, &lock->cnts);
/*
* Put the reader into the wait queue
*/
arch_spin_lock(&lock->lock);
/*
* At the head of the wait queue now, wait until the writer state
* goes to 0 and then try to increment the reader count and get
* the lock. It is possible that an incoming writer may steal the
* lock in the interim, so it is necessary to check the writer byte
* to make sure that the write lock isn't taken.
*/
while (atomic_read(&lock->cnts) & _QW_WMASK)
cpu_relax_lowlatency();
cnts = atomic_add_return(_QR_BIAS, &lock->cnts) - _QR_BIAS;
rspin_until_writer_unlock(lock, cnts);
/*
* Signal the next one in queue to become queue head
*/
arch_spin_unlock(&lock->lock);
}
EXPORT_SYMBOL(queue_read_lock_slowpath);
/**
* queue_write_lock_slowpath - acquire write lock of a queue rwlock
* @lock : Pointer to queue rwlock structure
*/
void queue_write_lock_slowpath(struct qrwlock *lock)
{
u32 cnts;
/* Put the writer into the wait queue */
arch_spin_lock(&lock->lock);
/* Try to acquire the lock directly if no reader is present */
if (!atomic_read(&lock->cnts) &&
(atomic_cmpxchg(&lock->cnts, 0, _QW_LOCKED) == 0))
goto unlock;
/*
* Set the waiting flag to notify readers that a writer is pending,
* or wait for a previous writer to go away.
*/
for (;;) {
struct __qrwlock *l = (struct __qrwlock *)lock;
if (!READ_ONCE(l->wmode) &&
(cmpxchg(&l->wmode, 0, _QW_WAITING) == 0))
break;
cpu_relax_lowlatency();
}
/* When no more readers, set the locked flag */
for (;;) {
cnts = atomic_read(&lock->cnts);
if ((cnts == _QW_WAITING) &&
(atomic_cmpxchg(&lock->cnts, _QW_WAITING,
_QW_LOCKED) == _QW_WAITING))
break;
cpu_relax_lowlatency();
}
unlock:
arch_spin_unlock(&lock->lock);
}
EXPORT_SYMBOL(queue_write_lock_slowpath);