* [PATCH 1/2] x86: optimize a bit __raw_read_trylock
@ 2009-01-25 20:50 Frederic Weisbecker
2009-01-26 13:07 ` Ingo Molnar
0 siblings, 1 reply; 2+ messages in thread
From: Frederic Weisbecker @ 2009-01-25 20:50 UTC (permalink / raw)
To: Ingo Molnar; +Cc: linux-kernel, Frederic Weisbecker
The current version of __raw_read_trylock starts with decrementing the lock
and read its new value as a separate operation after that.
That makes 3 dereferences (read, write (after sub), read) whereas
a single atomic_dec_return does only two pointers dereferences (read, write).
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
---
arch/x86/include/asm/spinlock.h | 3 +--
1 files changed, 1 insertions(+), 2 deletions(-)
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 2bd6b11..139b424 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -267,8 +267,7 @@ static inline int __raw_read_trylock(raw_rwlock_t *lock)
{
atomic_t *count = (atomic_t *)lock;
- atomic_dec(count);
- if (atomic_read(count) >= 0)
+ if (atomic_dec_return(count) >= 0)
return 1;
atomic_inc(count);
return 0;
--
1.6.1
^ permalink raw reply related [flat|nested] 2+ messages in thread
* Re: [PATCH 1/2] x86: optimize a bit __raw_read_trylock
2009-01-25 20:50 [PATCH 1/2] x86: optimize a bit __raw_read_trylock Frederic Weisbecker
@ 2009-01-26 13:07 ` Ingo Molnar
0 siblings, 0 replies; 2+ messages in thread
From: Ingo Molnar @ 2009-01-26 13:07 UTC (permalink / raw)
To: Frederic Weisbecker, H. Peter Anvin, Thomas Gleixner; +Cc: linux-kernel
* Frederic Weisbecker <fweisbec@gmail.com> wrote:
> The current version of __raw_read_trylock starts with decrementing the lock
> and read its new value as a separate operation after that.
>
> That makes 3 dereferences (read, write (after sub), read) whereas
> a single atomic_dec_return does only two pointers dereferences (read, write).
>
> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
> ---
> arch/x86/include/asm/spinlock.h | 3 +--
> 1 files changed, 1 insertions(+), 2 deletions(-)
>
> diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
> index 2bd6b11..139b424 100644
> --- a/arch/x86/include/asm/spinlock.h
> +++ b/arch/x86/include/asm/spinlock.h
> @@ -267,8 +267,7 @@ static inline int __raw_read_trylock(raw_rwlock_t *lock)
> {
> atomic_t *count = (atomic_t *)lock;
>
> - atomic_dec(count);
> - if (atomic_read(count) >= 0)
> + if (atomic_dec_return(count) >= 0)
> return 1;
> atomic_inc(count);
> return 0;
nice one ... applied it to tip/x86/asm, thanks Frederic!
Ingo
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2009-01-26 13:07 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2009-01-25 20:50 [PATCH 1/2] x86: optimize a bit __raw_read_trylock Frederic Weisbecker
2009-01-26 13:07 ` Ingo Molnar
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox