Re: [PATCH v3] selftests/resctrl: Fix non-contiguous CBM for AMD

[Ilpo Järvinen]

On Tue, 11 Jun 2024, Babu Moger wrote:

> The non-contiguous CBM test fails on AMD with:
> Starting L3_NONCONT_CAT test ...
> Mounting resctrl to "/sys/fs/resctrl"
> CPUID output doesn't match 'sparse_masks' file content!
> not ok 5 L3_NONCONT_CAT: test
> 
> AMD always supports non-contiguous CBM but does not report it via CPUID.
> 
> Fix the non-contiguous CBM test to use CPUID to discover non-contiguous
> CBM support only on Intel.
> 
> Fixes: ae638551ab64 ("selftests/resctrl: Add non-contiguous CBMs CAT test")
> Signed-off-by: Babu Moger <babu.moger@xxxxxxx>
> Reviewed-by: Reinette Chatre <reinette.chatre@xxxxxxxxx>

Thanks.

Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@xxxxxxxxxxxxxxx>

-- 
 i.

> ---
> v3: Reworked changelong.
> 
> v2: Moved the non-contiguous CBM verification to a new function
>     arch_supports_noncont_cat.
> 
> v1: This was part of the series
>     https://lore.kernel.org/lkml/cover.1708637563.git.babu.moger@xxxxxxx/
>     Sending this as a separate fix per review comments.
> ---
>  tools/testing/selftests/resctrl/cat_test.c | 32 +++++++++++++++-------
>  1 file changed, 22 insertions(+), 10 deletions(-)
> 
> diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
> index d4dffc934bc3..742782438ca3 100644
> --- a/tools/testing/selftests/resctrl/cat_test.c
> +++ b/tools/testing/selftests/resctrl/cat_test.c
> @@ -288,11 +288,30 @@ static int cat_run_test(const struct resctrl_test *test, const struct user_param
>  	return ret;
>  }
>  
> +static bool arch_supports_noncont_cat(const struct resctrl_test *test)
> +{
> +	unsigned int eax, ebx, ecx, edx;
> +
> +	/* AMD always supports non-contiguous CBM. */
> +	if (get_vendor() == ARCH_AMD)
> +		return true;
> +
> +	/* Intel support for non-contiguous CBM needs to be discovered. */
> +	if (!strcmp(test->resource, "L3"))
> +		__cpuid_count(0x10, 1, eax, ebx, ecx, edx);
> +	else if (!strcmp(test->resource, "L2"))
> +		__cpuid_count(0x10, 2, eax, ebx, ecx, edx);
> +	else
> +		return false;
> +
> +	return ((ecx >> 3) & 1);
> +}
> +
>  static int noncont_cat_run_test(const struct resctrl_test *test,
>  				const struct user_params *uparams)
>  {
>  	unsigned long full_cache_mask, cont_mask, noncont_mask;
> -	unsigned int eax, ebx, ecx, edx, sparse_masks;
> +	unsigned int sparse_masks;
>  	int bit_center, ret;
>  	char schemata[64];
>  
> @@ -301,15 +320,8 @@ static int noncont_cat_run_test(const struct resctrl_test *test,
>  	if (ret)
>  		return ret;
>  
> -	if (!strcmp(test->resource, "L3"))
> -		__cpuid_count(0x10, 1, eax, ebx, ecx, edx);
> -	else if (!strcmp(test->resource, "L2"))
> -		__cpuid_count(0x10, 2, eax, ebx, ecx, edx);
> -	else
> -		return -EINVAL;
> -
> -	if (sparse_masks != ((ecx >> 3) & 1)) {
> -		ksft_print_msg("CPUID output doesn't match 'sparse_masks' file content!\n");
> +	if (arch_supports_noncont_cat(test) != sparse_masks) {
> +		ksft_print_msg("Hardware and kernel differ on non-contiguous CBM support!\n");
>  		return 1;
>  	}
>  
>