[PATCH cmpxchg 2/3] ARC: Emulate one-byte cmpxchg

[Vineet Gupta]

Hi Paul,

On 8/5/24 12:21, Paul E. McKenney wrote:
> Use the new cmpxchg_emu_u8() to emulate one-byte cmpxchg() on arc.
>
> [ paulmck: Drop two-byte support per Arnd Bergmann feedback. ]
> [ paulmck: Apply feedback from Naresh Kamboju. ]
> [ paulmck: Apply kernel test robot feedback. ]
>
> Signed-off-by: Paul E. McKenney <paulmck at kernel.org>
> Cc: Vineet Gupta <vgupta at kernel.org>
> Cc: Andi Shyti <andi.shyti at linux.intel.com>
> Cc: Andrzej Hajda <andrzej.hajda at intel.com>
> Cc: Arnd Bergmann <arnd at arndb.de>
> Cc: Palmer Dabbelt <palmer at rivosinc.com>
> Cc: <linux-snps-arc at lists.infradead.org>
> ---
>  arch/arc/Kconfig               |  1 +
>  arch/arc/include/asm/cmpxchg.h | 33 ++++++++++++++++++++++++---------
>  2 files changed, 25 insertions(+), 9 deletions(-)
>
> diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
> index fd0b0a0d4686a..163608fd49d18 100644
> --- a/arch/arc/Kconfig
> +++ b/arch/arc/Kconfig
> @@ -13,6 +13,7 @@ config ARC
>  	select ARCH_HAS_SETUP_DMA_OPS
>  	select ARCH_HAS_SYNC_DMA_FOR_CPU
>  	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
> +	select ARCH_NEED_CMPXCHG_1_EMU
>  	select ARCH_SUPPORTS_ATOMIC_RMW if ARC_HAS_LLSC
>  	select ARCH_32BIT_OFF_T
>  	select BUILDTIME_TABLE_SORT
> diff --git a/arch/arc/include/asm/cmpxchg.h b/arch/arc/include/asm/cmpxchg.h
> index e138fde067dea..2102ce076f28b 100644
> --- a/arch/arc/include/asm/cmpxchg.h
> +++ b/arch/arc/include/asm/cmpxchg.h
> @@ -8,6 +8,7 @@
>  
>  #include <linux/build_bug.h>
>  #include <linux/types.h>
> +#include <linux/cmpxchg-emu.h>
>  
>  #include <asm/barrier.h>
>  #include <asm/smp.h>
> @@ -46,6 +47,9 @@
>  	__typeof__(*(ptr)) _prev_;					\
>  									\
>  	switch(sizeof((_p_))) {						\
> +	case 1:								\
> +		_prev_ = (__typeof__(*(ptr)))cmpxchg_emu_u8((volatile u8 *)_p_, (uintptr_t)_o_, (uintptr_t)_n_);	\
> +		break;							\
>  	case 4:								\
>  		_prev_ = __cmpxchg(_p_, _o_, _n_);			\
>  		break;							\
> @@ -65,16 +69,27 @@
>  	__typeof__(*(ptr)) _prev_;					\
>  	unsigned long __flags;						\
>  									\
> -	BUILD_BUG_ON(sizeof(_p_) != 4);					\

Is this alone not sufficient: i.e. for !LLSC let the atomic op happen
under a spin-lock for non 4 byte quantities as well.

> +	switch(sizeof((_p_))) {						\
> +	case 1:								\
> +		__flags = cmpxchg_emu_u8((volatile u8 *)_p_, (uintptr_t)_o_, (uintptr_t)_n_);	\
> +		_prev_ = (__typeof__(*(ptr)))__flags;			\
> +		break;							\
> +		break;							\

FWIW, the 2nd break seems extraneous.

> +	case 4:								\
> +		/*							\
> +		 * spin lock/unlock provide the needed smp_mb()		\
> +		 * before/after						\
> +		 */							\
> +		atomic_ops_lock(__flags);				\
> +		_prev_ = *_p_;						\
> +		if (_prev_ == _o_)					\
> +			*_p_ = _n_;					\
> +		atomic_ops_unlock(__flags);				\
> +		break;							\
> +	default:							\
> +		BUILD_BUG();						\
> +	}								\
>  									\
> -	/*								\
> -	 * spin lock/unlock provide the needed smp_mb() before/after	\
> -	 */								\
> -	atomic_ops_lock(__flags);					\
> -	_prev_ = *_p_;							\
> -	if (_prev_ == _o_)						\
> -		*_p_ = _n_;						\
> -	atomic_ops_unlock(__flags);					\
>  	_prev_;								\
>  })

-Vineet