Re: [RFC][PATCH 05/12] arch: Introduce arch_{,try_}_cmpxchg128{,_local}()

[Boqun Feng]

On Mon, Dec 19, 2022 at 04:35:30PM +0100, Peter Zijlstra wrote:
> For all architectures that currently support cmpxchg_double()
> implement the cmpxchg128() family of functions that is basically the
> same but with a saner interface.
> 
> Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
> ---
>  arch/arm64/include/asm/atomic_ll_sc.h |   38 +++++++++++++++++++++++
>  arch/arm64/include/asm/atomic_lse.h   |   33 +++++++++++++++++++-
>  arch/arm64/include/asm/cmpxchg.h      |   26 ++++++++++++++++
>  arch/s390/include/asm/cmpxchg.h       |   33 ++++++++++++++++++++
>  arch/x86/include/asm/cmpxchg_32.h     |    3 +
>  arch/x86/include/asm/cmpxchg_64.h     |   55 +++++++++++++++++++++++++++++++++-
>  6 files changed, 185 insertions(+), 3 deletions(-)
> 
> --- a/arch/arm64/include/asm/atomic_ll_sc.h
> +++ b/arch/arm64/include/asm/atomic_ll_sc.h
> @@ -326,6 +326,44 @@ __CMPXCHG_DBL(   ,        ,  ,         )
>  __CMPXCHG_DBL(_mb, dmb ish, l, "memory")
>  
>  #undef __CMPXCHG_DBL
> +
> +union __u128_halves {
> +	u128 full;
> +	struct {
> +		u64 low, high;
> +	};
> +};
> +
> +#define __CMPXCHG128(name, mb, rel, cl)					\
> +static __always_inline u128						\
> +__ll_sc__cmpxchg128##name(volatile u128 *ptr, u128 old, u128 new)	\
> +{									\
> +	union __u128_halves r, o = { .full = (old) },			\
> +			       n = { .full = (new) };			\
> +									\
> +	asm volatile("// __cmpxchg128" #name "\n"			\
> +	"	prfm	pstl1strm, %2\n"				\
> +	"1:	ldxp	%0, %1, %2\n"					\
> +	"	eor	%3, %0, %3\n"					\
> +	"	eor	%4, %1, %4\n"					\
> +	"	orr	%3, %4, %3\n"					\
> +	"	cbnz	%3, 2f\n"					\
> +	"	st" #rel "xp	%w3, %5, %6, %2\n"			\
> +	"	cbnz	%w3, 1b\n"					\
> +	"	" #mb "\n"						\
> +	"2:"								\
> +	: "=&r" (r.low), "=&r" (r.high), "+Q" (*(unsigned long *)ptr)	\

I wonder whether we should use "(*(u128 *)ptr)" instead of "(*(unsigned
long *) ptr)"? Because compilers may think only 64bit value pointed by
"ptr" gets modified, and they are allowed to do "useful" optimization.

Same for lse and s390.

Regards,
Boqun

> +	: "r" (o.low), "r" (o.high), "r" (n.low), "r" (n.high)		\
> +	: cl);								\
> +									\
> +	return r.full;							\
> +}
> +
> +__CMPXCHG128(   ,        ,  ,         )
> +__CMPXCHG128(_mb, dmb ish, l, "memory")
> +
> +#undef __CMPXCHG128
> +
>  #undef K
>  
>  #endif	/* __ASM_ATOMIC_LL_SC_H */