Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
MIME-Version: 1.0
References: <20230620091603.269-1-ravi.bangoria@amd.com> <CAP-5=fXS726wY1taYEYXDz3YZ4ZwxcL+nhh_yNM7rwamMd8mWg@mail.gmail.com>
 <3b0abd4a-6450-c282-65ff-ec0c7df67b03@amd.com>
In-Reply-To: <3b0abd4a-6450-c282-65ff-ec0c7df67b03@amd.com>
From:   Ian Rogers <irogers@google.com>
Date:   Wed, 21 Jun 2023 22:09:18 -0700
Message-ID: <CAP-5=fXfTDY9-uDq2BR2QmTP=-1=4RKRK=dvKmz5CF+oXgz+Eg@mail.gmail.com>
Subject: Re: [PATCH] perf/amd: Prevent grouping of IBS events
To:     Ravi Bangoria <ravi.bangoria@amd.com>
Cc:     peterz@infradead.org, acme@kernel.org, jolsa@kernel.org,
        namhyung@kernel.org, bp@alien8.de, x86@kernel.org,
        linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org,
        sandipan.das@amd.com, ananth.narayan@amd.com,
        santosh.shukla@amd.com
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

On Tue, Jun 20, 2023 at 8:27=E2=80=AFPM Ravi Bangoria <ravi.bangoria@amd.co=
m> wrote:
>
> Hi Ian,
>
> On 20-Jun-23 10:14 PM, Ian Rogers wrote:
> > On Tue, Jun 20, 2023 at 2:16=E2=80=AFAM Ravi Bangoria <ravi.bangoria@am=
d.com> wrote:
> >>
> >> IBS PMUs can have only one event active at any point in time. Restrict
> >> grouping of multiple IBS events.
> >
> > Thanks Ravi,
> >
> > can you provide an example/test for this? Should this be a weak group i=
ssue?
>
> Before:
>   $ sudo ./perf record -e "{ibs_op//,ibs_op//}" -C 0
>   ^C[ perf record: Woken up 1 times to write data ]
>   [ perf record: Captured and wrote 0.540 MB perf.data (531 samples) ]
>
> After:
>   $ sudo ./perf record -e "{ibs_op//,ibs_op//}" -C 0
>   Error:
>   AMD IBS may only be available in system-wide/per-cpu mode.
>   Try using -a, or -C and workload affinity
>
> The error message is stale and misleading. I have a patch to fix it.
> I'll post it separately.

Thanks Ravi, so this is a workaround for a PMU driver bug where the
perf_event_open should have failed for the sibling event?

The behavior is somewhat reminiscent of arch_evsel__must_be_in_group:
https://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git/tree/tools/p=
erf/arch/x86/util/evsel.c?h=3Dperf-tools-next#n41

Normally software events would be valid in the group, should the code
ignore these?

Thanks,
Ian

> Thanks,
> Ravi