Re: [PATCH 3/3] raid6: simplify CPU feature checks

[David Laight]

On Sun, 25 Oct 2026 12:12:07 -0700
Eric Biggers <ebiggers@xxxxxxxxxx> wrote:

> Remove unnecessary checks for features that are prerequisites for other
> features, such as AVX which is a prerequisite for AVX2.
> 
> (Note: in most cases arch/x86/kernel/cpu/cpuid-deps.c warns about
> missing prerequisites rather than enforcing them.  This is intentional,
> and it does not mean the prerequisites should be checked elsewhere.)
> 
> Then, move the raid6_recov_algo_add() lines into the appropriate places
> just above so that the same CPU features aren't checked multiple times.
> 
> Signed-off-by: Eric Biggers <ebiggers@xxxxxxxxxx>
> ---
>  lib/raid/raid6/x86/pq_arch.h | 51 ++++++++----------------------------
>  1 file changed, 11 insertions(+), 40 deletions(-)
> 
> diff --git a/lib/raid/raid6/x86/pq_arch.h b/lib/raid/raid6/x86/pq_arch.h
> index 4a863b253b909..418e4d4a2930f 100644
> --- a/lib/raid/raid6/x86/pq_arch.h
> +++ b/lib/raid/raid6/x86/pq_arch.h
> @@ -16,63 +16,34 @@ extern const struct raid6_recov_calls raid6_recov_ssse3;
>  extern const struct raid6_recov_calls raid6_recov_avx2;
>  extern const struct raid6_recov_calls raid6_recov_avx512;
>  
> ...
>  static __always_inline void __init arch_raid6_init(void)
>  {
> -	if (raid6_has_avx2()) {
> +	if (boot_cpu_has(X86_FEATURE_AVX2)) {
>  		raid6_algo_add(&raid6_avx2x1);
>  		raid6_algo_add(&raid6_avx2x2);
>  		if (IS_ENABLED(CONFIG_X86_64))
>  			raid6_algo_add(&raid6_avx2x4);
> -		if (raid6_has_avx512()) {
> +		if (boot_cpu_has(X86_FEATURE_AVX512BW) &&
> +		    boot_cpu_has(X86_FEATURE_AVX512VL) &&
> +		    boot_cpu_has(X86_FEATURE_AVX512DQ)) {
>  			raid6_algo_add(&raid6_avx512x1);
>  			raid6_algo_add(&raid6_avx512x2);
>  			if (IS_ENABLED(CONFIG_X86_64))
>  				raid6_algo_add(&raid6_avx512x4);
> +			raid6_recov_algo_add(&raid6_recov_avx512);
> +		} else {
> +			raid6_recov_algo_add(&raid6_recov_avx2);

Is that right (you haven't changed it)?
You get both the avx2 and axv512 normal algorithms, but only one
of the recov ones.

I presume these are added in addition to the generic C code and
some startup test decides which is fastest and so used?

David


>  		}
> -	} else if (IS_ENABLED(CONFIG_X86_64) || raid6_has_sse2()) {
> +	} else if (IS_ENABLED(CONFIG_X86_64) ||
> +		   boot_cpu_has(X86_FEATURE_XMM2)) {
>  		/* x86_64 can assume SSE2 as baseline */
>  		raid6_algo_add(&raid6_sse2x1);
>  		raid6_algo_add(&raid6_sse2x2);
>  		if (IS_ENABLED(CONFIG_X86_64))
>  			raid6_algo_add(&raid6_sse2x4);
> +		if (boot_cpu_has(X86_FEATURE_SSSE3))
> +			raid6_recov_algo_add(&raid6_recov_ssse3);
>  	} else {
>  		raid6_algo_add_default();
>  	}
> -
> -	if (raid6_has_avx512())
> -		raid6_recov_algo_add(&raid6_recov_avx512);
> -	else if (raid6_has_avx2())
> -		raid6_recov_algo_add(&raid6_recov_avx2);
> -	else if (raid6_has_ssse3())
> -		raid6_recov_algo_add(&raid6_recov_ssse3);
>  }