[PATCH] perf: arm_pmuv3: Use BR_RETIRED for HW branch event if enabled

[Anshuman Khandual]

On 9/6/24 02:17, Ilkka Koskinen wrote:
> The PMU driver attempts to use PC_WRITE_RETIRED for the HW branch event,
> if enabled. However, PC_WRITE_RETIRED counts only taken branches,
> whereas BR_RETIRED counts also non-taken ones.
> 
> Furthermore, perf uses HW branch event to calculate branch misses ratio,
> implying BR_RETIRED is the correct event to count.
But is the event BR_RETIRED always guaranteed to be available. Should not
armpmu->pmceid_bitmap be checked first ?

> 
> Signed-off-by: Ilkka Koskinen <ilkka at os.amperecomputing.com>
> ---
>  drivers/perf/arm_pmuv3.c | 27 ++++-----------------------
>  1 file changed, 4 insertions(+), 23 deletions(-)
> 
> diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
> index d246840797b6..a8ed08df1411 100644
> --- a/drivers/perf/arm_pmuv3.c
> +++ b/drivers/perf/arm_pmuv3.c
> @@ -46,6 +46,7 @@ static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = {
>  	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV8_PMUV3_PERFCTR_INST_RETIRED,
>  	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV8_PMUV3_PERFCTR_L1D_CACHE,
>  	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL,
> +	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV8_PMUV3_PERFCTR_BR_RETIRED,
>  	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
>  	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV8_PMUV3_PERFCTR_BUS_CYCLES,
>  	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= ARMV8_PMUV3_PERFCTR_STALL_FRONTEND,
> @@ -1083,28 +1084,6 @@ static void armv8pmu_reset(void *info)
>  	armv8pmu_pmcr_write(pmcr);
>  }
>  
> -static int __armv8_pmuv3_map_event_id(struct arm_pmu *armpmu,
> -				      struct perf_event *event)
> -{
> -	if (event->attr.type == PERF_TYPE_HARDWARE &&
> -	    event->attr.config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) {
> -
> -		if (test_bit(ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED,
> -			     armpmu->pmceid_bitmap))
> -			return ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED;
> -
> -		if (test_bit(ARMV8_PMUV3_PERFCTR_BR_RETIRED,
> -			     armpmu->pmceid_bitmap))
> -			return ARMV8_PMUV3_PERFCTR_BR_RETIRED;

If BR_RETIRED event is absent on the platform, PC_WRITE_RETIRED still remains
a good alternative to fallback on. Hence wondering if the above order could
just be changed to use BR_RETIRED first when available.

> -
> -		return HW_OP_UNSUPPORTED;
> -	}
> -
> -	return armpmu_map_event(event, &armv8_pmuv3_perf_map,
> -				&armv8_pmuv3_perf_cache_map,
> -				ARMV8_PMU_EVTYPE_EVENT);
> -}
> -
>  static int __armv8_pmuv3_map_event(struct perf_event *event,
>  				   const unsigned (*extra_event_map)
>  						  [PERF_COUNT_HW_MAX],
> @@ -1116,7 +1095,9 @@ static int __armv8_pmuv3_map_event(struct perf_event *event,
>  	int hw_event_id;
>  	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
>  
> -	hw_event_id = __armv8_pmuv3_map_event_id(armpmu, event);
> +	hw_event_id = armpmu_map_event(event, &armv8_pmuv3_perf_map,
> +				       &armv8_pmuv3_perf_cache_map,
> +				       ARMV8_PMU_EVTYPE_EVENT);
>  
>  	/*
>  	 * CHAIN events only work when paired with an adjacent counter, and it