linux-perf-users.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Rob Herring <robh@kernel.org>
To: James Clark <james.clark@arm.com>
Cc: "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	linux-arm-kernel <linux-arm-kernel@lists.infradead.org>,
	linux-perf-users <linux-perf-users@vger.kernel.org>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Ingo Molnar <mingo@redhat.com>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Mark Rutland <mark.rutland@arm.com>,
	Will Deacon <will@kernel.org>, Jiri Olsa <jolsa@kernel.org>,
	Namhyung Kim <namhyung@kernel.org>,
	Arnaldo Carvalho de Melo <acme@kernel.org>
Subject: Re: [PATCH RFC v1 3/3] perf: arm_spe: Add support for SPEv1.2 inverted event filtering
Date: Tue, 6 Sep 2022 08:48:33 -0500	[thread overview]
Message-ID: <CAL_Jsq+BCrBe-qPaHA7LuhqSCO1PZo2uRHjC-CT_xgyVX4868w@mail.gmail.com> (raw)
In-Reply-To: <b357cc19-8b3f-ef97-efb1-8e7a8f5b2b8b@arm.com>

On Mon, Sep 5, 2022 at 9:55 AM James Clark <james.clark@arm.com> wrote:
>
>
>
> On 25/08/2022 19:08, Rob Herring wrote:
> > Arm SPEv1.2 (Arm v8.7/v9.2) adds a new feature called Inverted Event
> > Filter which excludes samples matching the event filter. The feature
> > mirrors the existing event filter in PMSEVFR_EL1 adding a new register,
> > PMSNEVFR_EL1, which has the same event bit assignments.
> >
> > Signed-off-by: Rob Herring <robh@kernel.org>
> >
> > diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
> > index 57904c11aece..9744da888818 100644
> > --- a/arch/arm64/include/asm/sysreg.h
> > +++ b/arch/arm64/include/asm/sysreg.h
> > @@ -258,6 +258,7 @@
> >  #define SYS_PMSIDR_EL1_ARCHINST_SHIFT        3
> >  #define SYS_PMSIDR_EL1_LDS_SHIFT     4
> >  #define SYS_PMSIDR_EL1_ERND_SHIFT    5
> > +#define SYS_PMSIDR_EL1_FNE_SHIFT     6
> >  #define SYS_PMSIDR_EL1_INTERVAL_SHIFT        8
> >  #define SYS_PMSIDR_EL1_INTERVAL_MASK 0xfUL
> >  #define SYS_PMSIDR_EL1_MAXSIZE_SHIFT 12
> > @@ -302,6 +303,7 @@
> >  #define SYS_PMSFCR_EL1_FE_SHIFT              0
> >  #define SYS_PMSFCR_EL1_FT_SHIFT              1
> >  #define SYS_PMSFCR_EL1_FL_SHIFT              2
> > +#define SYS_PMSFCR_EL1_FNE_SHIFT     3
> >  #define SYS_PMSFCR_EL1_B_SHIFT               16
> >  #define SYS_PMSFCR_EL1_LD_SHIFT              17
> >  #define SYS_PMSFCR_EL1_ST_SHIFT              18
> > diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
> > index a75b03b5c8f9..724409a88423 100644
> > --- a/drivers/perf/arm_spe_pmu.c
> > +++ b/drivers/perf/arm_spe_pmu.c
> > @@ -82,6 +82,7 @@ struct arm_spe_pmu {
> >  #define SPE_PMU_FEAT_ARCH_INST                       (1UL << 3)
> >  #define SPE_PMU_FEAT_LDS                     (1UL << 4)
> >  #define SPE_PMU_FEAT_ERND                    (1UL << 5)
> > +#define SPE_PMU_FEAT_INV_FILT_EVT            (1UL << 6)
> >  #define SPE_PMU_FEAT_DEV_PROBED                      (1UL << 63)
> >       u64                                     features;
> >
> > @@ -199,6 +200,10 @@ static const struct attribute_group arm_spe_pmu_cap_group = {
> >  #define ATTR_CFG_FLD_min_latency_LO          0
> >  #define ATTR_CFG_FLD_min_latency_HI          11
> >
> > +#define ATTR_CFG_FLD_inv_event_filter_CFG    config3 /* PMSNEVFR_EL1 */
> > +#define ATTR_CFG_FLD_inv_event_filter_LO     0
> > +#define ATTR_CFG_FLD_inv_event_filter_HI     63
> > +
> >  /* Why does everything I do descend into this? */
> >  #define __GEN_PMU_FORMAT_ATTR(cfg, lo, hi)                           \
> >       (lo) == (hi) ? #cfg ":" #lo "\n" : #cfg ":" #lo "-" #hi
> > @@ -229,6 +234,7 @@ GEN_PMU_FORMAT_ATTR(branch_filter);
> >  GEN_PMU_FORMAT_ATTR(load_filter);
> >  GEN_PMU_FORMAT_ATTR(store_filter);
> >  GEN_PMU_FORMAT_ATTR(event_filter);
> > +GEN_PMU_FORMAT_ATTR(inv_event_filter);
> >  GEN_PMU_FORMAT_ATTR(min_latency);
> >
> >  static struct attribute *arm_spe_pmu_formats_attr[] = {
> > @@ -240,12 +246,27 @@ static struct attribute *arm_spe_pmu_formats_attr[] = {
> >       &format_attr_load_filter.attr,
> >       &format_attr_store_filter.attr,
> >       &format_attr_event_filter.attr,
> > +     &format_attr_inv_event_filter.attr,
> >       &format_attr_min_latency.attr,
> >       NULL,
> >  };
> >
> > +static umode_t arm_spe_pmu_format_attr_is_visible(struct kobject *kobj,
> > +                                               struct attribute *attr,
> > +                                               int unused)
> > +     {
> > +     struct device *dev = kobj_to_dev(kobj);
> > +     struct arm_spe_pmu *spe_pmu = dev_get_drvdata(dev);
> > +
> > +     if (attr == &format_attr_inv_event_filter.attr && !(spe_pmu->features & SPE_PMU_FEAT_INV_FILT_EVT))
> > +             return 0;
> > +
> > +     return attr->mode;
> > +}
> > +
> >  static const struct attribute_group arm_spe_pmu_format_group = {
> >       .name   = "format",
> > +     .is_visible = arm_spe_pmu_format_attr_is_visible,
> >       .attrs  = arm_spe_pmu_formats_attr,
> >  };
> >
> > @@ -341,6 +362,9 @@ static u64 arm_spe_event_to_pmsfcr(struct perf_event *event)
> >       if (ATTR_CFG_GET_FLD(attr, event_filter))
> >               reg |= BIT(SYS_PMSFCR_EL1_FE_SHIFT);
> >
> > +     if (ATTR_CFG_GET_FLD(attr, inv_event_filter))
> > +             reg |= BIT(SYS_PMSFCR_EL1_FNE_SHIFT);
> > +
> >       if (ATTR_CFG_GET_FLD(attr, min_latency))
> >               reg |= BIT(SYS_PMSFCR_EL1_FL_SHIFT);
> >
> > @@ -353,6 +377,12 @@ static u64 arm_spe_event_to_pmsevfr(struct perf_event *event)
> >       return ATTR_CFG_GET_FLD(attr, event_filter);
> >  }
> >
> > +static u64 arm_spe_event_to_pmsnevfr(struct perf_event *event)
> > +{
> > +     struct perf_event_attr *attr = &event->attr;
> > +     return ATTR_CFG_GET_FLD(attr, inv_event_filter);
> > +}
> > +
> >  static u64 arm_spe_event_to_pmslatfr(struct perf_event *event)
> >  {
> >       struct perf_event_attr *attr = &event->attr;
> > @@ -703,6 +733,9 @@ static int arm_spe_pmu_event_init(struct perf_event *event)
> >       if (arm_spe_event_to_pmsevfr(event) & arm_spe_pmsevfr_res0(spe_pmu->pmsver))
> >               return -EOPNOTSUPP;
> >
> > +     if (arm_spe_event_to_pmsnevfr(event) & arm_spe_pmsevfr_res0(spe_pmu->pmsver))
> > +             return -EOPNOTSUPP;
> > +
> >       if (attr->exclude_idle)
> >               return -EOPNOTSUPP;
> >
> > @@ -721,6 +754,10 @@ static int arm_spe_pmu_event_init(struct perf_event *event)
> >           !(spe_pmu->features & SPE_PMU_FEAT_FILT_EVT))
> >               return -EOPNOTSUPP;
> >
> > +     if ((reg & BIT(SYS_PMSFCR_EL1_FNE_SHIFT)) &&
> > +         !(spe_pmu->features & SPE_PMU_FEAT_INV_FILT_EVT))
> > +             return -EOPNOTSUPP;
> > +
> >       if ((reg & BIT(SYS_PMSFCR_EL1_FT_SHIFT)) &&
> >           !(spe_pmu->features & SPE_PMU_FEAT_FILT_TYP))
> >               return -EOPNOTSUPP;
> > @@ -757,6 +794,9 @@ static void arm_spe_pmu_start(struct perf_event *event, int flags)
> >       reg = arm_spe_event_to_pmsevfr(event);
> >       write_sysreg_s(reg, SYS_PMSEVFR_EL1);
> >
> > +     reg = arm_spe_event_to_pmsnevfr(event);
> > +     write_sysreg_s(reg, SYS_PMSNEVFR_EL1);
> > +
>
> I think this needs to check if the feature is present before writing
> otherwise you get a crash, pasted below. Otherwise it looks ok to me.

Yes, that's the 1 fix I've needed in my testing.

Rob

  reply	other threads:[~2022-09-06 14:14 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-08-25 18:07 [PATCH RFC v1 0/3] perf: Arm SPEv1.2 support Rob Herring
2022-08-25 18:08 ` [PATCH RFC v1 1/3] perf: arm_spe: Support new SPEv1.2/v8.7 'not taken' event Rob Herring
2022-08-25 18:08 ` [PATCH RFC v1 2/3] perf: Add perf_event_attr::config3 Rob Herring
2022-08-25 19:31   ` Arnaldo Carvalho de Melo
2022-08-25 19:43     ` Rob Herring
2022-08-25 19:53       ` Arnaldo Carvalho de Melo
2022-08-31 19:06   ` Rob Herring
2022-08-31 20:07     ` Arnaldo Carvalho de Melo
2022-08-25 18:08 ` [PATCH RFC v1 3/3] perf: arm_spe: Add support for SPEv1.2 inverted event filtering Rob Herring
2022-09-05 14:55   ` James Clark
2022-09-06 13:48     ` Rob Herring [this message]
2022-09-12  8:53   ` Leo Yan

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=CAL_Jsq+BCrBe-qPaHA7LuhqSCO1PZo2uRHjC-CT_xgyVX4868w@mail.gmail.com \
    --to=robh@kernel.org \
    --cc=acme@kernel.org \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=catalin.marinas@arm.com \
    --cc=james.clark@arm.com \
    --cc=jolsa@kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=will@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).