2012-05-30 07:51:43

by Yong Zhang

Subject: [RFC PATCH] ARM: cmpxchg: define __HAVE_ARCH_CMPXCHG for armv6 and later

From: Yong Zhang <[email protected]>

Both pi_stress and sigwaittest in rt-test show performance gain with
__HAVE_ARCH_CMPXCHG. Testing result on coretile_express_a9x4:

pi_stress -p 99 --duration=300 (on linux-3.4-rc5; bigger is better)
vanilla: Total inversion performed: 5493381
patched: Total inversion performed: 5621746

sigwaittest -p 99 -l 100000 (on linux-3.4-rc5-rt6; less is better)
3.4-rc5-rt6: Min 24, Cur 27, Avg 30, Max 98
patched: Min 19, Cur 21, Avg 23, Max 96

Signed-off-by: Yong Zhang <[email protected]>
Cc: Russell King <[email protected]>
Cc: Nicolas Pitre <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: Catalin Marinas <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
---
arch/arm/include/asm/cmpxchg.h | 2 ++
1 files changed, 2 insertions(+), 0 deletions(-)

diff --git a/arch/arm/include/asm/cmpxchg.h b/arch/arm/include/asm/cmpxchg.h
index 7eb18c1..a91b44e 100644
--- a/arch/arm/include/asm/cmpxchg.h
+++ b/arch/arm/include/asm/cmpxchg.h
@@ -127,6 +127,8 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size

#else /* min ARCH >= ARMv6 */

+#define __HAVE_ARCH_CMPXCHG 1
+
extern void __bad_cmpxchg(volatile void *ptr, int size);

/*
--
1.7.5.4

2012-05-31 01:25:09

by Will Deacon

Subject: Re: [RFC PATCH] ARM: cmpxchg: define __HAVE_ARCH_CMPXCHG for armv6 and later

Hello,

On Wed, May 30, 2012 at 08:51:26AM +0100, Yong Zhang wrote:
> diff --git a/arch/arm/include/asm/cmpxchg.h b/arch/arm/include/asm/cmpxchg.h
> index 7eb18c1..a91b44e 100644
> --- a/arch/arm/include/asm/cmpxchg.h
> +++ b/arch/arm/include/asm/cmpxchg.h
> @@ -127,6 +127,8 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
>
> #else /* min ARCH >= ARMv6 */
>
> +#define __HAVE_ARCH_CMPXCHG 1
> +
> extern void __bad_cmpxchg(volatile void *ptr, int size);

As long as this only requires 4-byte cmpxchg support then I think this is
fine. It looks like that's currently the case, so:

Acked-by: Will Deacon <[email protected]>

Will

2012-05-31 12:50:30

by Yong Zhang

Subject: Re: [RFC PATCH] ARM: cmpxchg: define __HAVE_ARCH_CMPXCHG for armv6 and later

On Thu, May 31, 2012 at 02:24:50AM +0100, Will Deacon wrote:
> Hello,
>
> On Wed, May 30, 2012 at 08:51:26AM +0100, Yong Zhang wrote:
> > diff --git a/arch/arm/include/asm/cmpxchg.h b/arch/arm/include/asm/cmpxchg.h
> > index 7eb18c1..a91b44e 100644
> > --- a/arch/arm/include/asm/cmpxchg.h
> > +++ b/arch/arm/include/asm/cmpxchg.h
> > @@ -127,6 +127,8 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
> >
> > #else /* min ARCH >= ARMv6 */
> >
> > +#define __HAVE_ARCH_CMPXCHG 1
> > +
> > extern void __bad_cmpxchg(volatile void *ptr, int size);
>
> As long as this only requires 4-byte cmpxchg support then I think this is
> fine. It looks like that's currently the case, so:

Yes and thanks for review.

Yong

>
> Acked-by: Will Deacon <[email protected]>
>
> Will