Re: [PATCH v5 2/2] perf pmu intel: Adjust cpumaks for sub-NUMA clusters on Emeraldrapids

[Namhyung Kim <namhyung@kernel.org>]

On Tue, Apr 07, 2026 at 01:38:43PM -0700, Chun-Tse Shao wrote:
> Similar to GNR [1], Emeraldrapids supports sub-NUMA clusters as well.
> Adjust cpumasks as the logic for GNR in [1].
> 
> Tested on Emeraldrapids with SNC2 enabled:
>   $ perf stat --per-node -e 'UNC_CHA_CLOCKTICKS,UNC_M_CLOCKTICKS' -a -- sleep 1
> 
>    Performance counter stats for 'system wide':
> 
>   N0       30        72125876670      UNC_CHA_CLOCKTICKS
>   N0        4         8815163648      UNC_M_CLOCKTICKS
>   N1       30        72124958844      UNC_CHA_CLOCKTICKS
>   N1        4         8815014974      UNC_M_CLOCKTICKS
>   N2       30        72121049022      UNC_CHA_CLOCKTICKS
>   N2        4         8814592626      UNC_M_CLOCKTICKS
>   N3       30        72117133854      UNC_CHA_CLOCKTICKS
>   N3        4         8814012840      UNC_M_CLOCKTICKS
> 
>          1.001574118 seconds time elapsed
> 
> [1] lore.kernel.org/20250515181417.491401-1-irogers@google.com
> 
> Reviewed-by: Zide Chen <zide.chen@intel.com>
> Reviewed-by: Ian Rogers <irogers@google.com>
> Signed-off-by: Chun-Tse Shao <ctshao@google.com>
> ---
>  tools/perf/arch/x86/util/pmu.c | 56 +++++++++++++++++++++++-----------
>  1 file changed, 38 insertions(+), 18 deletions(-)
> 
> diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c
> index 938be36ec0f7..3743f5145505 100644
> --- a/tools/perf/arch/x86/util/pmu.c
> +++ b/tools/perf/arch/x86/util/pmu.c
> @@ -30,8 +30,9 @@ static bool x86__is_snc_supported(void)
>  
>  	if (!checked_if_snc_supported) {
>  
> -		/* Graniterapids supports SNC configuration. */
> +		/* Emeraldrapids Graniterapids support SNC configuration. */
>  		static const char *const supported_cpuids[] = {
> +			"GenuineIntel-6-CF", /* Emeraldrapids */
>  			"GenuineIntel-6-A[DE]", /* Graniterapids */

It'd be great if we can share these string literals..


>  		};
>  		char *cpuid = get_cpuid_str((struct perf_cpu){0});
> @@ -141,23 +142,42 @@ static int uncore_imc_snc(struct perf_pmu *pmu)
>  	// Compute the IMC SNC using lookup tables.
>  	unsigned int imc_num;
>  	int snc_nodes = snc_nodes_per_l3_cache();
> -	const u8 snc2_map[] = {1, 1, 0, 0};
> -	const u8 snc3_map[] = {1, 1, 0, 0, 2, 2};
> -	const u8 *snc_map;
> -	size_t snc_map_len;
> -
> -	switch (snc_nodes) {
> -	case 2:
> -		snc_map = snc2_map;
> -		snc_map_len = ARRAY_SIZE(snc2_map);
> -		break;
> -	case 3:
> -		snc_map = snc3_map;
> -		snc_map_len = ARRAY_SIZE(snc3_map);
> -		break;
> -	default:
> -		/* Error or no lookup support for SNC with >3 nodes. */
> -		return 0;
> +	char *cpuid;
> +	static const u8 emr_snc2_map[] = { 0, 0, 1, 1 };
> +	static const u8 gnr_snc2_map[] = { 1, 1, 0, 0 };
> +	static const u8 snc3_map[] = { 1, 1, 0, 0, 2, 2 };
> +	static const u8 *snc_map;
> +	static size_t snc_map_len;
> +
> +	/* snc_map is not inited yet. We only look up once to avoid expensive operations. */
> +	if (!snc_map) {
> +		switch (snc_nodes) {
> +		case 2:
> +			cpuid = get_cpuid_str((struct perf_cpu){ 0 });
> +			if (cpuid) {
> +				if (strcmp_cpuid_str("GenuineIntel-6-CF", cpuid) == 0) {
> +					snc_map = emr_snc2_map;
> +					snc_map_len = ARRAY_SIZE(emr_snc2_map);
> +				} else if (strcmp_cpuid_str("GenuineIntel-6-A[DE]", cpuid) == 0) {
> +					snc_map = gnr_snc2_map;
> +					snc_map_len = ARRAY_SIZE(gnr_snc2_map);

... in here as well.

Thanks,
Namhyung


> +				}
> +				free(cpuid);
> +			}
> +			break;
> +		case 3:
> +			snc_map = snc3_map;
> +			snc_map_len = ARRAY_SIZE(snc3_map);
> +			break;
> +		default:
> +			/* Error or no lookup support for SNC with >3 nodes. */
> +			return 0;
> +		}
> +
> +		if (!snc_map) {
> +			pr_warning("Unexpected: can not find snc map config");
> +			return 0;
> +		}
>  	}
>  
>  	/* Compute SNC for PMU. */
> -- 
> 2.53.0.1213.gd9a14994de-goog
>