Jan Kiszka wrote:
> According to Linux and the Intel spec, this prefix is not needed.
>
Obviously, it's not, since the whole purpose of xchg() is to guarantee bus
locking for memory operands anyway. Please merge.
> ---
> include/asm-x86/atomic_32.h |2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> Index: b/include/asm-x86/atomic_32.h
> ===
> --- a/include/asm-x86/atomic_32.h
> +++ b/include/asm-x86/atomic_32.h
> @@ -64,7 +64,7 @@ struct __xeno_xchg_dummy { unsigned long
> static inline unsigned long xnarch_atomic_xchg (volatile void *ptr,
> unsigned long x)
> {
> - __asm__ __volatile__(LOCK_PREFIX "xchgl %0,%1"
> + __asm__ __volatile__("xchgl %0,%1"
>:"=r" (x)
>:"m" (*__xeno_xg(ptr)), "0" (x)
>:"memory");
>
>
>
>
>
> ___
> Xenomai-core mailing list
> Xenomai-core@gna.org
> https://mail.gna.org/listinfo/xenomai-core
--
Philippe.
___
Xenomai-core mailing list
Xenomai-core@gna.org
https://mail.gna.org/listinfo/xenomai-core