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

[Tanmay Jagdale]

Hi Rob,


> > The TAD PMU supports following counters that can be filtered by MPAM
> > partition id.
> 
> How are you setting the PARTID? There's no support yet in the kernel to
> set it.
We have ported MPAM support from James Morse private tree to test this.

> 
> >     - (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>
> 
> How would userspace get the 0x12 value?
It's up to the user to create partition id and use the same id here.
For testing, I had used the MPAM resctrl infrastructure to create
and get partition ID.

> 
> >
> > - 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.
> >
> > Signed-off-by: Tanmay Jagdale <tanmay at marvell.com>
> > ---
> >  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
> 
> Does this h/w block follow the MPAM specification or just uses PARTID in
> its own way?
No, these counters are not as per the MPAM monitoring specification and we
use them in our own way.

Thanks,
Tanmay
> 
> Rob