[PATCH] arm64: remove HAVE_CMPXCHG_LOCAL

[Will Deacon]

On Sun, Feb 15, 2026 at 11:39:44AM +0800, Jisheng Zhang wrote:
> It turns out the generic disable/enable irq this_cpu_cmpxchg
> implementation is faster than LL/SC or lse implementation. Remove
> HAVE_CMPXCHG_LOCAL for better performance on arm64.
> 
> Tested on Quad 1.9GHZ CA55 platform:
> average mod_node_page_state() cost decreases from 167ns to 103ns
> the spawn (30 duration) benchmark in unixbench is improved
> from 147494 lps to 150561 lps, improved by 2.1%
> 
> Tested on Quad 2.1GHZ CA73 platform:
> average mod_node_page_state() cost decreases from 113ns to 85ns
> the spawn (30 duration) benchmark in unixbench is improved
> from 209844 lps to 212581 lps, improved by 1.3%
> 
> Signed-off-by: Jisheng Zhang <jszhang at kernel.org>
> ---
>  arch/arm64/Kconfig              |  1 -
>  arch/arm64/include/asm/percpu.h | 24 ------------------------
>  2 files changed, 25 deletions(-)

That is _entirely_ dependent on the system, so this isn't the right
approach. I also don't think it's something we particularly want to
micro-optimise to accomodate systems that suck at atomics.

Will

> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> index 38dba5f7e4d2..5e7e2e65d5a5 100644
> --- a/arch/arm64/Kconfig
> +++ b/arch/arm64/Kconfig
> @@ -205,7 +205,6 @@ config ARM64
>  	select HAVE_EBPF_JIT
>  	select HAVE_C_RECORDMCOUNT
>  	select HAVE_CMPXCHG_DOUBLE
> -	select HAVE_CMPXCHG_LOCAL
>  	select HAVE_CONTEXT_TRACKING_USER
>  	select HAVE_DEBUG_KMEMLEAK
>  	select HAVE_DMA_CONTIGUOUS
> diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
> index b57b2bb00967..70ffe566cb4b 100644
> --- a/arch/arm64/include/asm/percpu.h
> +++ b/arch/arm64/include/asm/percpu.h
> @@ -232,30 +232,6 @@ PERCPU_RET_OP(add, add, ldadd)
>  #define this_cpu_xchg_8(pcp, val)	\
>  	_pcp_protect_return(xchg_relaxed, pcp, val)
>  
> -#define this_cpu_cmpxchg_1(pcp, o, n)	\
> -	_pcp_protect_return(cmpxchg_relaxed, pcp, o, n)
> -#define this_cpu_cmpxchg_2(pcp, o, n)	\
> -	_pcp_protect_return(cmpxchg_relaxed, pcp, o, n)
> -#define this_cpu_cmpxchg_4(pcp, o, n)	\
> -	_pcp_protect_return(cmpxchg_relaxed, pcp, o, n)
> -#define this_cpu_cmpxchg_8(pcp, o, n)	\
> -	_pcp_protect_return(cmpxchg_relaxed, pcp, o, n)
> -
> -#define this_cpu_cmpxchg64(pcp, o, n)	this_cpu_cmpxchg_8(pcp, o, n)
> -
> -#define this_cpu_cmpxchg128(pcp, o, n)					\
> -({									\
> -	typedef typeof(pcp) pcp_op_T__;					\
> -	u128 old__, new__, ret__;					\
> -	pcp_op_T__ *ptr__;						\
> -	old__ = o;							\
> -	new__ = n;							\
> -	preempt_disable_notrace();					\
> -	ptr__ = raw_cpu_ptr(&(pcp));					\
> -	ret__ = cmpxchg128_local((void *)ptr__, old__, new__);		\
> -	preempt_enable_notrace();					\
> -	ret__;								\
> -})
>  
>  #ifdef __KVM_NVHE_HYPERVISOR__
>  extern unsigned long __hyp_per_cpu_offset(unsigned int cpu);
> -- 
> 2.51.0
>