Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Content-Type: text/plain;
        charset=utf-8
Mime-Version: 1.0 (Mac OS X Mail 14.0 \(3654.120.0.1.13\))
Subject: Re: Using perf_event_open() to sample multiple events of a process
From:   Nadav Amit <nadav.amit@gmail.com>
In-Reply-To: <YYXQRYbRO193U4re@hirez.programming.kicks-ass.net>
Date:   Fri, 5 Nov 2021 17:59:26 -0700
Cc:     kan.liang@linux.intel.com, LKML <linux-kernel@vger.kernel.org>,
        linux-perf-users@vger.kernel.org
Content-Transfer-Encoding: quoted-printable
Message-Id: <DB6138F5-29A4-40AE-8307-6C3ED07A0649@gmail.com>
References: <92645262-D319-4068-9C44-2409EF44888E@gmail.com>
 <YYXQRYbRO193U4re@hirez.programming.kicks-ass.net>
To:     Peter Zijlstra <peterz@infradead.org>
Precedence: bulk


> On Nov 5, 2021, at 5:45 PM, Peter Zijlstra <peterz@infradead.org> =
wrote:
>=20
> On Thu, Nov 04, 2021 at 10:57:50PM -0700, Nadav Amit wrote:
>> Hello Ken, Peter,
>>=20
>> I would appreciate some help regarding the use of perf_event_open()
>> to have multiple samples getting into the same mmap=E2=80=99d memory =
when they
>> are both attached to the same process.
>>=20
>> I am doing so (using both PERF_FLAG_FD_NO_GROUP and =
PERF_FLAG_FD_OUTPUT),
>> but it results in -EINVAL. Debugging the code shows that
>> perf_event_set_output() fails due to the following check:
>>=20
>>        /*
>>         * If its not a per-cpu rb, it must be the same task.
>>         */
>>        if (output_event->cpu =3D=3D -1 && output_event->ctx !=3D =
event->ctx)
>>                goto out;
>>=20
>> However, it appears that at this point, event->ctx is not initialized
>> (it is null) so the test fails and the whole perf_event_open() =
syscall
>> fails.
>>=20
>> Am I missing something? If not, I am unsure, unfortunately, what the
>> proper way to fix it is=E2=80=A6
>>=20
>> I include a small test that fails on my system. The second
>> perf_event_open fails due to the check in perf_event_set_output():
>>=20
>=20
> Works when you use the SET_OUTPUT ioctl()...
>=20
> I think something went sideways in the syscall path and things went =
out
> of order :/ I'll try and have a look.

Highly appreciated.

While at it, I would note that there is a mistake in Intel SDM =
31.4.2.27,
Table 31-47 =E2=80=9CBlock Item Packet Definition=E2=80=9D. The ID[5:0] =
takes 6 bits,
when in fact I presume it is only 5 bits (according to the table).

Perhaps you can forward it to the relevant people.

Thanks again,
Nadav=