Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Song Liu <songliubraving@fb.com>
To:     Arnaldo Carvalho de Melo <acme@kernel.org>,
        David Ahern <dsahern@gmail.com>
CC:     lkml <linux-kernel@vger.kernel.org>,
        "netdev@vger.kernel.org" <netdev@vger.kernel.org>,
        "peterz@infradead.org" <peterz@infradead.org>,
        "ast@kernel.org" <ast@kernel.org>,
        "daniel@iogearbox.net" <daniel@iogearbox.net>,
        Kernel Team <Kernel-team@fb.com>
Subject: Re: [PATCH v6 perf, bpf-next 1/7] perf, bpf: Introduce
 PERF_RECORD_KSYMBOL
Thread-Topic: [PATCH v6 perf, bpf-next 1/7] perf, bpf: Introduce
 PERF_RECORD_KSYMBOL
Thread-Index: AQHUqFCaPbT+UGXQnkaaX1wm9KrpVKWo0rKAgAAEoACAAAQiAIAACcSAgAAEI4A=
Date:   Thu, 10 Jan 2019 19:45:09 +0000
Message-ID: <E220DFC6-A2E2-4B3A-B52B-3B194315D2A0@fb.com>
References: <20190109192111.130995-1-songliubraving@fb.com>
 <20190109192111.130995-2-songliubraving@fb.com>
 <20190110182403.GN22483@kernel.org>
 <064FBBA4-A0D0-4335-BCE7-902724CE2988@fb.com>
 <20190110185524.GO22483@kernel.org>
 <CCB26BF8-9FF5-4BBF-84BE-878CF0D3882A@fb.com>
In-Reply-To: <CCB26BF8-9FF5-4BBF-84BE-878CF0D3882A@fb.com>
Accept-Language: en-US
Content-Language: en-US
received-spf: None (protection.outlook.com: fb.com does not designate
 permitted sender hosts)
spamdiagnosticoutput: 1:99
spamdiagnosticmetadata: NSPM
Content-Type: text/plain; charset="us-ascii"
Content-ID: <947F72252E066746917AA9BFCD4B5F6E@namprd15.prod.outlook.com>
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
X-MS-Exchange-CrossTenant-Network-Message-Id: 5adb4b4a-31bd-4431-19ac-08d677342117
X-MS-Exchange-CrossTenant-originalarrivaltime: 10 Jan 2019 19:45:09.5420
 (UTC)
X-MS-Exchange-CrossTenant-fromentityheader: Hosted
X-MS-Exchange-CrossTenant-id: 8ae927fe-1255-47a7-a2af-5f3a069daaa2
X-MS-Exchange-Transport-CrossTenantHeadersStamped: DM5PR15MB1484
X-OriginatorOrg: fb.com
X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:,, definitions=2019-01-10_07:,,
 signatures=0
X-Proofpoint-Spam-Reason: safe
X-FB-Internal: Safe
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org


> On Jan 10, 2019, at 11:30 AM, Song Liu <songliubraving@fb.com> wrote:
>=20
>=20
>=20
>> On Jan 10, 2019, at 10:55 AM, Arnaldo Carvalho de Melo <acme@kernel.org>=
 wrote:
>>=20
>> Em Thu, Jan 10, 2019 at 06:40:37PM +0000, Song Liu escreveu:
>>>=20
>>>=20
>>>> On Jan 10, 2019, at 10:24 AM, Arnaldo Carvalho de Melo <acme@kernel.or=
g> wrote:
>>>>=20
>>>> Em Wed, Jan 09, 2019 at 11:21:05AM -0800, Song Liu escreveu:
>>>>> For better performance analysis of dynamically JITed and loaded kerne=
l
>>>>> functions, such as BPF programs, this patch introduces
>>>>> PERF_RECORD_KSYMBOL, a new perf_event_type that exposes kernel symbol
>>>>> register/unregister information to user space.
>>>>>=20
>>>>> The following data structure is used for PERF_RECORD_KSYMBOL.
>>>>>=20
>>>>>  /*
>>>>>   * struct {
>>>>>   *      struct perf_event_header        header;
>>>>>   *      u64                             addr;
>>>>>   *      u32                             len;
>>>>>   *      u16                             ksym_type;
>>>>>   *      u16                             flags;
>>>>>   *      char                            name[];
>>>>>   *      struct sample_id                sample_id;
>>>>>   * };
>>>>>   */
>>>>=20
>>>> So, I couldn't find where this gets used, the intention here is just t=
o
>>>> add the interfaces and afterwards is that you will wire this up? I wou=
ld
>>>> like to test the whole shebang to see it working.
>>>=20
>>> I guess you meant PERF_RECORD_BPF_EVENT not being used?=20
>>>=20
>>> PERF_RECORD_KSYMBOL is used by BPF in 3/7 and 5/7. I tested=20
>>=20
>> Oops, I didn't look at 3/7, just read its cset summary line and as it
>> says:
>>=20
>> Subject: [PATCH v6 perf, bpf-next 3/7] perf, bpf: introduce PERF_RECORD_=
BPF_EVENT
>>=20
>> I didn't thought it was related, perhaps break it down into one that
>> states that it is wiring up PERF_RECORD_KSYMBOL, and at that point we
>> could just test it, getting the notifications for new kallsyms related
>> to BPF?
>=20
> Good idea! I will split it into two patches as:
>=20
> [3/8] perf, bpf: generate PERF_RECORD_KSYMBOL for BPF program=20
> [4/8] perf, bpf: introduce PERF_RECORD_BPF_EVENT
>=20
>>=20
>>> PERF_RECORD_BPF_EVENT with dump_trace. As we separate RECORD_KSYMBOL fr=
om
>>> RECORD_BPF_EVENT, user space won't use BPF_EVENT until annotation suppo=
rt. =20
>>=20
>> Right, so why not just introduce PERF_RECORD_KSYMBOL, make it be used by
>> tooling, etc, then move on to PERF_RECORD_BPF_EVENT?
>=20
> I'd like to make sure we all agree on the new ABI for RECORD_KSYMBOL and=
=20
> RECORD_BPF_EVENT. Multiple user space tools dependent on RECORD_BPF_EVENT=
,
> for example, bcc and auditing. Finalizing RECORD_BPF_EVENT will unblock t=
he=20
> development of these tools. On perf side, it will take us quite some time=
=20
> to finish annotation. Ideally, I don't want to block the development of=20
> other tools for so long.=20
>=20
> Thanks,
> Song

+ DavidA

Hi David,=20

Could you please share your feedback on PERF_RECORD_BPF_EVENT for auditing
use cases?

Thanks,
Song