Re: [PATCH RESEND] perf/marvell_cn10k: Add MPAM support for TAD PMU

From: Will Deacon
Date: Fri Jun 24 2022 - 08:17:11 EST


On Sat, May 28, 2022 at 12:26:47AM +0530, Tanmay Jagdale wrote:
> The TAD PMU supports following counters that can be filtered by MPAM
> partition id.
> - (0x1a) tad_alloc_dtg : Allocations to DTG.
> - (0x1b) tad_alloc_ltg : Allocations to LTG.
> - (0x1c) tad_alloc_any : Total allocations to DTG/LTG.
> - (0x1d) tad_hit_dtg : DTG hits.
> - (0x1e) tad_hit_ltg : LTG hits.
> - (0x1f) tad_hit_any : Hit in LTG/DTG.
> - (0x20) tad_tag_rd : Total tag reads.
>
> Add a new 'partid' attribute of 16-bits to get the partition id
> passed from perf tool. This value would be stored in config1 field
> of perf_event_attr structure.
>
> Example:
> perf stat -e tad/tad_alloc_any,partid=0x12/ <program>
>
> - Drop read of TAD_PRF since we don't have to preserve any
> bit fields and always write an updated value.
> - Update register offsets of TAD_PRF and TAD_PFC.

It would be great if you could document some of this under
Documentation/admin-guide/perf like many of the other PMU drivers have
done.

> Signed-off-by: Tanmay Jagdale <tanmay@xxxxxxxxxxx>
> ---
> drivers/perf/marvell_cn10k_tad_pmu.c | 23 ++++++++++++++++++-----
> 1 file changed, 18 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/perf/marvell_cn10k_tad_pmu.c b/drivers/perf/marvell_cn10k_tad_pmu.c
> index 282d3a071a67..f552e6bffcac 100644
> --- a/drivers/perf/marvell_cn10k_tad_pmu.c
> +++ b/drivers/perf/marvell_cn10k_tad_pmu.c
> @@ -18,10 +18,12 @@
> #include <linux/perf_event.h>
> #include <linux/platform_device.h>
>
> -#define TAD_PFC_OFFSET 0x0
> +#define TAD_PFC_OFFSET 0x800
> #define TAD_PFC(counter) (TAD_PFC_OFFSET | (counter << 3))
> -#define TAD_PRF_OFFSET 0x100
> +#define TAD_PRF_OFFSET 0x900
> #define TAD_PRF(counter) (TAD_PRF_OFFSET | (counter << 3))
> +#define TAD_PRF_MATCH_PARTID (1 << 8)
> +#define TAD_PRF_PARTID_NS (1 << 10)
> #define TAD_PRF_CNTSEL_MASK 0xFF
> #define TAD_MAX_COUNTERS 8
>
> @@ -86,23 +88,32 @@ static void tad_pmu_event_counter_start(struct perf_event *event, int flags)
> struct hw_perf_event *hwc = &event->hw;
> u32 event_idx = event->attr.config;
> u32 counter_idx = hwc->idx;
> + u32 partid_filter = 0;
> u64 reg_val;
> + u32 partid;
> int i;
>
> hwc->state = 0;
>
> + /* Extract the partid (if any) passed by user */
> + partid = event->attr.config1 & 0x3f;

[...]

> PMU_FORMAT_ATTR(event, "config:0-7");
> +PMU_FORMAT_ATTR(partid, "config1:0-15");

This doesn't seem to match the mask used above?

Will