diff options
author | Waiman Long <Waiman.Long@hp.com> | 2014-02-03 16:18:49 +0400 |
---|---|---|
committer | Ingo Molnar <mingo@kernel.org> | 2014-06-06 09:58:28 +0400 |
commit | 70af2f8a4f48d6cebdf92d533d3aef37853ce6de (patch) | |
tree | 2a8d7b54053ef9fc7d45794ab28addbd00870819 /include/asm-generic/qrwlock.h | |
parent | 9161f5409798d52aa8598ff12575fde2327bed84 (diff) | |
download | linux-70af2f8a4f48d6cebdf92d533d3aef37853ce6de.tar.xz |
locking/rwlocks: Introduce 'qrwlocks' - fair, queued rwlocks
This rwlock uses the arch_spin_lock_t as a waitqueue, and assuming the
arch_spin_lock_t is a fair lock (ticket,mcs etc..) the resulting
rwlock is a fair lock.
It fits in the same 8 bytes as the regular rwlock_t by folding the
reader and writer count into a single integer, using the remaining 4
bytes for the arch_spinlock_t.
Architectures that can single-copy adress bytes can optimize
queue_write_unlock() with a 0 write to the LSB (the write count).
Performance as measured by Davidlohr Bueso (rwlock_t -> qrwlock_t):
+--------------+-------------+---------------+
| Workload | #users | delta |
+--------------+-------------+---------------+
| alltests | > 1400 | -4.83% |
| custom | 0-100,> 100 | +1.43%,-1.57% |
| high_systime | > 1000 | -2.61 |
| shared | all | +0.32 |
+--------------+-------------+---------------+
http://www.stgolabs.net/qrwlock-stuff/aim7-results-vs-rwsem_optsin/
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
[peterz: near complete rewrite]
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: "Paul E.McKenney" <paulmck@linux.vnet.ibm.com>
Cc: linux-arch@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Link: http://lkml.kernel.org/n/tip-gac1nnl3wvs2ij87zv2xkdzq@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'include/asm-generic/qrwlock.h')
-rw-r--r-- | include/asm-generic/qrwlock.h | 166 |
1 files changed, 166 insertions, 0 deletions
diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h new file mode 100644 index 000000000000..6383d54bf983 --- /dev/null +++ b/include/asm-generic/qrwlock.h @@ -0,0 +1,166 @@ +/* + * Queue read/write lock + * + * 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> + */ +#ifndef __ASM_GENERIC_QRWLOCK_H +#define __ASM_GENERIC_QRWLOCK_H + +#include <linux/atomic.h> +#include <asm/barrier.h> +#include <asm/processor.h> + +#include <asm-generic/qrwlock_types.h> + +/* + * Writer states & reader shift and bias + */ +#define _QW_WAITING 1 /* A writer is waiting */ +#define _QW_LOCKED 0xff /* A writer holds the lock */ +#define _QW_WMASK 0xff /* Writer mask */ +#define _QR_SHIFT 8 /* Reader count shift */ +#define _QR_BIAS (1U << _QR_SHIFT) + +/* + * External function declarations + */ +extern void queue_read_lock_slowpath(struct qrwlock *lock); +extern void queue_write_lock_slowpath(struct qrwlock *lock); + +/** + * queue_read_can_lock- would read_trylock() succeed? + * @lock: Pointer to queue rwlock structure + */ +static inline int queue_read_can_lock(struct qrwlock *lock) +{ + return !(atomic_read(&lock->cnts) & _QW_WMASK); +} + +/** + * queue_write_can_lock- would write_trylock() succeed? + * @lock: Pointer to queue rwlock structure + */ +static inline int queue_write_can_lock(struct qrwlock *lock) +{ + return !atomic_read(&lock->cnts); +} + +/** + * queue_read_trylock - try to acquire read lock of a queue rwlock + * @lock : Pointer to queue rwlock structure + * Return: 1 if lock acquired, 0 if failed + */ +static inline int queue_read_trylock(struct qrwlock *lock) +{ + u32 cnts; + + cnts = atomic_read(&lock->cnts); + if (likely(!(cnts & _QW_WMASK))) { + cnts = (u32)atomic_add_return(_QR_BIAS, &lock->cnts); + if (likely(!(cnts & _QW_WMASK))) + return 1; + atomic_sub(_QR_BIAS, &lock->cnts); + } + return 0; +} + +/** + * queue_write_trylock - try to acquire write lock of a queue rwlock + * @lock : Pointer to queue rwlock structure + * Return: 1 if lock acquired, 0 if failed + */ +static inline int queue_write_trylock(struct qrwlock *lock) +{ + u32 cnts; + + cnts = atomic_read(&lock->cnts); + if (unlikely(cnts)) + return 0; + + return likely(atomic_cmpxchg(&lock->cnts, + cnts, cnts | _QW_LOCKED) == cnts); +} +/** + * queue_read_lock - acquire read lock of a queue rwlock + * @lock: Pointer to queue rwlock structure + */ +static inline void queue_read_lock(struct qrwlock *lock) +{ + u32 cnts; + + cnts = atomic_add_return(_QR_BIAS, &lock->cnts); + if (likely(!(cnts & _QW_WMASK))) + return; + + /* The slowpath will decrement the reader count, if necessary. */ + queue_read_lock_slowpath(lock); +} + +/** + * queue_write_lock - acquire write lock of a queue rwlock + * @lock : Pointer to queue rwlock structure + */ +static inline void queue_write_lock(struct qrwlock *lock) +{ + /* Optimize for the unfair lock case where the fair flag is 0. */ + if (atomic_cmpxchg(&lock->cnts, 0, _QW_LOCKED) == 0) + return; + + queue_write_lock_slowpath(lock); +} + +/** + * queue_read_unlock - release read lock of a queue rwlock + * @lock : Pointer to queue rwlock structure + */ +static inline void queue_read_unlock(struct qrwlock *lock) +{ + /* + * Atomically decrement the reader count + */ + smp_mb__before_atomic(); + atomic_sub(_QR_BIAS, &lock->cnts); +} + +#ifndef queue_write_unlock +/** + * queue_write_unlock - release write lock of a queue rwlock + * @lock : Pointer to queue rwlock structure + */ +static inline void queue_write_unlock(struct qrwlock *lock) +{ + /* + * If the writer field is atomic, it can be cleared directly. + * Otherwise, an atomic subtraction will be used to clear it. + */ + smp_mb__before_atomic(); + atomic_sub(_QW_LOCKED, &lock->cnts); +} +#endif + +/* + * Remapping rwlock architecture specific functions to the corresponding + * queue rwlock functions. + */ +#define arch_read_can_lock(l) queue_read_can_lock(l) +#define arch_write_can_lock(l) queue_write_can_lock(l) +#define arch_read_lock(l) queue_read_lock(l) +#define arch_write_lock(l) queue_write_lock(l) +#define arch_read_trylock(l) queue_read_trylock(l) +#define arch_write_trylock(l) queue_write_trylock(l) +#define arch_read_unlock(l) queue_read_unlock(l) +#define arch_write_unlock(l) queue_write_unlock(l) + +#endif /* __ASM_GENERIC_QRWLOCK_H */ |