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: <20221101052340.1210239-1-namhyung@kernel.org> <20221101052340.1210239-3-namhyung@kernel.org>
 <Y2DuzmnUm6NIh25a@krava> <CAADnVQJ6+N6vQ=ZUgUjoB_M2RoTGGPXpLwz81mNDmLWrGYKetw@mail.gmail.com>
 <CAPhsuW6iuEZCCYJk-cra8DkEWNtdin8GyJDZ6Y8zd4ecfd1gQA@mail.gmail.com>
 <CAADnVQ+SYv5O+UxnGaBAvxptopWyANdbQRg=e2GXiRBPyJMGgA@mail.gmail.com>
 <CAPhsuW55zAYCipf1P4dM8Cu9QFewnyZE+SOquKhSbdqUWG_EKg@mail.gmail.com> <CAM9d7chKunyZX=-9gANZ2BKZTzQXuWYCgPQU46jCHkqsjsoGUg@mail.gmail.com>
In-Reply-To: <CAM9d7chKunyZX=-9gANZ2BKZTzQXuWYCgPQU46jCHkqsjsoGUg@mail.gmail.com>
From:   Song Liu <song@kernel.org>
Date:   Tue, 1 Nov 2022 17:13:29 -0700
Message-ID: <CAPhsuW70GMFfzvgp__GOhebPu9bXnG7PzEby6xEExFgg+JmeTQ@mail.gmail.com>
Subject: Re: [PATCH bpf-next 2/3] bpf: Add bpf_perf_event_read_sample() helper
To:     Namhyung Kim <namhyung@kernel.org>
Cc:     Alexei Starovoitov <alexei.starovoitov@gmail.com>,
        Jiri Olsa <olsajiri@gmail.com>,
        Alexei Starovoitov <ast@kernel.org>,
        Daniel Borkmann <daniel@iogearbox.net>,
        Andrii Nakryiko <andrii@kernel.org>,
        Song Liu <songliubraving@fb.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Martin KaFai Lau <kafai@fb.com>, Yonghong Song <yhs@fb.com>,
        John Fastabend <john.fastabend@gmail.com>,
        KP Singh <kpsingh@kernel.org>, Hao Luo <haoluo@google.com>,
        Stanislav Fomichev <sdf@google.com>,
        LKML <linux-kernel@vger.kernel.org>, bpf <bpf@vger.kernel.org>,
        Steven Rostedt <rostedt@goodmis.org>,
        Ingo Molnar <mingo@kernel.org>,
        Arnaldo Carvalho de Melo <acme@kernel.org>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Tue, Nov 1, 2022 at 3:17 PM Namhyung Kim <namhyung@kernel.org> wrote:
> > > > >
> > > > > +1
> > > > > Let's avoid new stable helpers for this.
> > > > > Pls use CORE and read perf_sample_data directly.
> > > >
> > > > We have legacy ways to access sample_period and addr with
> > > > struct bpf_perf_event_data and struct bpf_perf_event_data_kern. I
> > > > think mixing that
> > > > with CORE makes it confusing for the user. And a helper or a kfunc would make it
> > > > easier to follow. perf_btf might also be a good approach for this.
> > >
> > > imo that's a counter argument to non-CORE style.
> > > struct bpf_perf_event_data has sample_period and addr,
> > > and as soon as we pushed the boundaries it turned out it's not enough.
> > > Now we're proposing to extend uapi a bit with sample_ip.
> > > That will repeat the same mistake.
> > > Just use CORE and read everything that is there today
> > > and will be there in the future.
> >
> > Another work of this effort is that we need the perf_event to prepare
> > required fields before calling the BPF program. I think we will need
> > some logic in addition to CORE to get that right. How about we add
> > perf_btf where the perf_event prepare all fields before calling the
> > BPF program? perf_btf + CORE will be able to read all fields in the
> > sample.
>
> IIUC we want something like below to access sample data directly,
> right?
>
>   BPF_CORE_READ(ctx, data, ip);
>

I haven't tried this, but I guess we may need something like

data = ctx->data;
BPF_CORE_READ(data, ip);

> Some fields like raw and callchains will have variable length data
> so it'd be hard to check the boundary at load time.

I think we are fine as long as we can check boundaries at run time.

> Also it's possible
> that some fields are not set (according to sample type), and it'd be
> the user's (or programmer's) responsibility to check if the data is
> valid.  If these are not the concerns, I think I'm good.

So we still need 1/3 of the set to make sure the data is valid?

Thanks,
Song