Re: [PATCH 2/2] bitops: rotate: Add riscv implementation using Zbb extension

[Yury Norov <yury.norov@gmail.com>]

On Fri, Jun 20, 2025 at 07:16:10PM +0800, cp0613@linux.alibaba.com wrote:
> From: Chen Pei <cp0613@linux.alibaba.com>
> 
> The RISC-V Zbb extension[1] defines bitwise rotation instructions,
> which can be used to implement rotate related functions.
> 
> [1] https://github.com/riscv/riscv-bitmanip/
> 
> Signed-off-by: Chen Pei <cp0613@linux.alibaba.com>
> ---
>  arch/riscv/include/asm/bitops.h | 172 ++++++++++++++++++++++++++++++++
>  1 file changed, 172 insertions(+)
> 
> diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
> index d59310f74c2b..be247ef9e686 100644
> --- a/arch/riscv/include/asm/bitops.h
> +++ b/arch/riscv/include/asm/bitops.h
> @@ -20,17 +20,20 @@
>  #include <asm-generic/bitops/__fls.h>
>  #include <asm-generic/bitops/ffs.h>
>  #include <asm-generic/bitops/fls.h>
> +#include <asm-generic/bitops/rotate.h>
>  
>  #else
>  #define __HAVE_ARCH___FFS
>  #define __HAVE_ARCH___FLS
>  #define __HAVE_ARCH_FFS
>  #define __HAVE_ARCH_FLS
> +#define __HAVE_ARCH_ROTATE
>  
>  #include <asm-generic/bitops/__ffs.h>
>  #include <asm-generic/bitops/__fls.h>
>  #include <asm-generic/bitops/ffs.h>
>  #include <asm-generic/bitops/fls.h>
> +#include <asm-generic/bitops/rotate.h>
>  
>  #include <asm/alternative-macros.h>
>  #include <asm/hwcap.h>
> @@ -175,6 +178,175 @@ static __always_inline int variable_fls(unsigned int x)
>  	 variable_fls(x_);					\
>  })

...

> +static inline u8 variable_ror8(u8 word, unsigned int shift)
> +{
> +	u32 word32 = ((u32)word << 24) | ((u32)word << 16) | ((u32)word << 8) | word;

Can you add a comment about what is happening here? Are you sure it's
optimized out in case of the 'legacy' alternative?

> +
> +	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
> +				      RISCV_ISA_EXT_ZBB, 1)
> +			  : : : : legacy);
> +
> +	asm volatile(
> +		".option push\n"
> +		".option arch,+zbb\n"
> +		"rorw %0, %1, %2\n"
> +		".option pop\n"
> +		: "=r" (word32) : "r" (word32), "r" (shift) :);
> +
> +	return (u8)word32;
> +
> +legacy:
> +	return generic_ror8(word, shift);
> +}
> +
> +#define rol64(word, shift) variable_rol64(word, shift)
> +#define ror64(word, shift) variable_ror64(word, shift)
> +#define rol32(word, shift) variable_rol32(word, shift)
> +#define ror32(word, shift) variable_ror32(word, shift)
> +#define rol16(word, shift) variable_rol16(word, shift)
> +#define ror16(word, shift) variable_ror16(word, shift)
> +#define rol8(word, shift)  variable_rol8(word, shift)
> +#define ror8(word, shift)  variable_ror8(word, shift)

Here you wire ror/rol() to the variable_ror/rol() unconditionally, and
that breaks compile-time rotation if the parameter is known at compile
time.

I believe, generic implementation will allow compiler to handle this
case better. Can you do a similar thing to what fls() does in the same
file?

Thanks,
Yury

> +
>  #endif /* !(defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB)) || defined(NO_ALTERNATIVE) */
>  
>  #include <asm-generic/bitops/ffz.h>
> -- 
> 2.49.0