Re: [PATCH v3] perf/arm: adjust hwevents mappings on boot

[Peter Newman]

On Tue, Aug 16, 2022 at 4:18 PM Mark Rutland <mark.rutland@xxxxxxx> wrote:
> On big.LITTLE systems this is array is shared by multiple PMUs, so this cannot
> be altered based on a single PMU.
>
> Rather than applying a fixup, could we special-case this at mapping time?
>
> Does the following work for you?
>
> Thanks
> Mark.
>
> ---->8----
> From 6cf78ec72194296e8d0c87572b81f2b02a097918 Mon Sep 17 00:00:00 2001
> From: Mark Rutland <mark.rutland@xxxxxxx>
> Date: Tue, 16 Aug 2022 15:16:23 +0100
> Subject: [PATCH] arm64: pmuv3: dynamically map
>  PERF_COUNT_HW_BRANCH_INSTRUCTIONS
>
> Signed-off-by: Mark Rutland <mark.rutland@xxxxxxx>


Reviewed-by: Peter Newman <peternewman@xxxxxxxxxx>
Tested-by: Peter Newman <peternewman@xxxxxxxxxx>


> ---
>  arch/arm64/kernel/perf_event.c | 27 +++++++++++++++++++++++----
>  1 file changed, 23 insertions(+), 4 deletions(-)
>
> diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
> index cb69ff1e61380..0435adee5cab8 100644
> --- a/arch/arm64/kernel/perf_event.c
> +++ b/arch/arm64/kernel/perf_event.c
> @@ -45,7 +45,6 @@ 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_PC_WRITE_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,
> @@ -1050,6 +1049,28 @@ 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;
> +
> +               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],
> @@ -1061,9 +1082,7 @@ 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 = armpmu_map_event(event, &armv8_pmuv3_perf_map,
> -                                      &armv8_pmuv3_perf_cache_map,
> -                                      ARMV8_PMU_EVTYPE_EVENT);
> +       hw_event_id = __armv8_pmuv3_map_event_id(armpmu, event);
>
>         if (armv8pmu_event_is_64bit(event))
>                 event->hw.flags |= ARMPMU_EVT_64BIT;
> --
> 2.30.2
>

Hi Mark,

I can confirm that your patch fixes the issue we saw.

Thank you for coming back with this quickly, it looks like a better
solution to me.

Which branch were you going to apply it to?

Thanks!
-Peter