Re: [PATCH V3 0/5] perf core PMU support for Sapphire Rapids (Kernel)

["Liang, Kan" <kan.liang@linux.intel.com>]

On 2/1/2021 9:30 AM, Peter Zijlstra wrote:
> 
> I made the below changes, does that work?

Yes, it works well.

Thanks,
Kan

> 
> ---
> 
> --- a/arch/x86/events/intel/core.c
> +++ b/arch/x86/events/intel/core.c
> @@ -3627,6 +3627,15 @@ static int core_pmu_hw_config(struct per
>   	return intel_pmu_bts_config(event);
>   }
>   
> +#define INTEL_TD_METRIC_AVAILABLE_MAX	(INTEL_TD_METRIC_RETIRING + \
> +					 ((x86_pmu.num_topdown_events - 1) << 8))
> +
> +static bool is_available_metric_event(struct perf_event *event)
> +{
> +	return is_metric_event(event) &&
> +		event->attr.config <= INTEL_TD_METRIC_AVAILABLE_MAX;
> +}
> +
>   static inline bool is_mem_loads_event(struct perf_event *event)
>   {
>   	return (event->attr.config & INTEL_ARCH_EVENT_MASK) == X86_CONFIG(.event=0xcd, .umask=0x01);
> @@ -3711,7 +3720,7 @@ static int intel_pmu_hw_config(struct pe
>   		if (event->attr.config & X86_ALL_EVENT_FLAGS)
>   			return -EINVAL;
>   
> -		if (is_metric_event(event)) {
> +		if (is_available_metric_event(event)) {
>   			struct perf_event *leader = event->group_leader;
>   
>   			/* The metric events don't support sampling. */
> --- a/arch/x86/events/perf_event.h
> +++ b/arch/x86/events/perf_event.h
> @@ -87,7 +87,14 @@ static inline bool is_topdown_count(stru
>   	return event->hw.flags & PERF_X86_EVENT_TOPDOWN;
>   }
>   
> -static inline bool is_metric_event(struct perf_event *event);
> +static inline bool is_metric_event(struct perf_event *event)
> +{
> +	u64 config = event->attr.config;
> +
> +	return ((config & ARCH_PERFMON_EVENTSEL_EVENT) == 0) &&
> +		((config & INTEL_ARCH_EVENT_MASK) >= INTEL_TD_METRIC_RETIRING)  &&
> +		((config & INTEL_ARCH_EVENT_MASK) <= INTEL_TD_METRIC_MAX);
> +}
>   
>   static inline bool is_slots_event(struct perf_event *event)
>   {
> @@ -901,18 +908,6 @@ static struct perf_pmu_events_ht_attr ev
>   struct pmu *x86_get_pmu(void);
>   extern struct x86_pmu x86_pmu __read_mostly;
>   
> -#define INTEL_TD_METRIC_AVAILABLE_MAX	(INTEL_TD_METRIC_RETIRING + \
> -					 ((x86_pmu.num_topdown_events - 1) << 8))
> -
> -static inline bool is_metric_event(struct perf_event *event)
> -{
> -	u64 config = event->attr.config;
> -
> -	return ((config & ARCH_PERFMON_EVENTSEL_EVENT) == 0) &&
> -		((config & INTEL_ARCH_EVENT_MASK) >= INTEL_TD_METRIC_RETIRING)  &&
> -		((config & INTEL_ARCH_EVENT_MASK) <= INTEL_TD_METRIC_AVAILABLE_MAX);
> -}
> -
>   static __always_inline struct x86_perf_task_context_opt *task_context_opt(void *ctx)
>   {
>   	if (static_cpu_has(X86_FEATURE_ARCH_LBR))
> --- a/arch/x86/include/asm/perf_event.h
> +++ b/arch/x86/include/asm/perf_event.h
> @@ -284,10 +284,12 @@ struct x86_pmu_capability {
>   #define INTEL_TD_METRIC_BAD_SPEC		0x8100	/* Bad speculation metric */
>   #define INTEL_TD_METRIC_FE_BOUND		0x8200	/* FE bound metric */
>   #define INTEL_TD_METRIC_BE_BOUND		0x8300	/* BE bound metric */
> -#define INTEL_TD_METRIC_HEAVY_OPS		0x8400	/* Heavy Operations metric */
> -#define INTEL_TD_METRIC_BR_MISPREDICT		0x8500	/* Branch Mispredict metric */
> -#define INTEL_TD_METRIC_FETCH_LAT		0x8600	/* Fetch Latency metric */
> -#define INTEL_TD_METRIC_MEM_BOUND		0x8700	/* Memory bound metric */
> +/* Level 2 metrics */
> +#define INTEL_TD_METRIC_HEAVY_OPS		0x8400  /* Heavy Operations metric */
> +#define INTEL_TD_METRIC_BR_MISPREDICT		0x8500  /* Branch Mispredict metric */
> +#define INTEL_TD_METRIC_FETCH_LAT		0x8600  /* Fetch Latency metric */
> +#define INTEL_TD_METRIC_MEM_BOUND		0x8700  /* Memory bound metric */
> +
>   #define INTEL_TD_METRIC_MAX			INTEL_TD_METRIC_MEM_BOUND
>   #define INTEL_TD_METRIC_NUM			8
>   
> --- a/include/uapi/linux/perf_event.h
> +++ b/include/uapi/linux/perf_event.h
> @@ -908,7 +908,6 @@ enum perf_event_type {
>   	 *			u32	var1_dw;
>   	 *		} && PERF_SAMPLE_WEIGHT_STRUCT
>   	 *	#endif
> -	 *
>   	 *	 }
>   	 *	}
>   	 *	{ u64			data_src; } && PERF_SAMPLE_DATA_SRC
> @@ -1276,29 +1275,23 @@ struct perf_branch_entry {
>   		reserved:40;
>   };
>   
> -#if defined(__LITTLE_ENDIAN_BITFIELD)
>   union perf_sample_weight {
>   	__u64		full;
> +#if defined(__LITTLE_ENDIAN_BITFIELD)
>   	struct {
>   		__u32	var1_dw;
>   		__u16	var2_w;
>   		__u16	var3_w;
>   	};
> -};
> -
>   #elif defined(__BIG_ENDIAN_BITFIELD)
> -
> -union perf_sample_weight {
> -	__u64		full;
>   	struct {
>   		__u16	var3_w;
>   		__u16	var2_w;
>   		__u32	var1_dw;
>   	};
> -};
> -
>   #else
>   #error "Unknown endianness"
>   #endif
> +};
>   
>   #endif /* _UAPI_LINUX_PERF_EVENT_H */
>