netdev - Re: [PATCH] bpf: validate bpf_func when BPF

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <87sgp1ssfk.fsf@toke.dk>
Date:   Thu, 12 Sep 2019 11:46:39 +0100
From:   Toke Høiland-Jørgensen <toke@...hat.com>
To:     Sami Tolvanen <samitolvanen@...gle.com>
Cc:     Björn Töpel <bjorn.topel@...el.com>,
        Yonghong Song <yhs@...com>,
        Alexei Starovoitov <ast@...nel.org>,
        Daniel Borkmann <daniel@...earbox.net>,
        Kees Cook <keescook@...omium.org>, Martin Lau <kafai@...com>,
        Song Liu <songliubraving@...com>,
        "netdev\@vger.kernel.org" <netdev@...r.kernel.org>,
        "bpf\@vger.kernel.org" <bpf@...r.kernel.org>,
        "linux-kernel\@vger.kernel.org" <linux-kernel@...r.kernel.org>,
        Jesper Dangaard Brouer <brouer@...hat.com>
Subject: Re: [PATCH] bpf: validate bpf_func when BPF_JIT is enabled

Sami Tolvanen <samitolvanen@...gle.com> writes:

> On Wed, Sep 11, 2019 at 5:09 AM Toke Høiland-Jørgensen <toke@...hat.com> wrote:
>>
>> Björn Töpel <bjorn.topel@...el.com> writes:
>> > I ran the "xdp_rxq_info" sample with and without Sami's patch:
>>
>> Thanks for doing this!
>
> Yes, thanks for testing this Björn!
>
>> Or (1/22998700 - 1/23923874) * 10**9 == 1.7 nanoseconds of overhead.
>>
>> I guess that is not *too* bad; but it's still chipping away at
>> performance; anything we could do to lower the overhead?
>
> The check is already rather minimal, but I could move this to a static
> inline function to help ensure the compiler doesn't generate an
> additional function call for this. I'm also fine with gating this
> behind a separate config option, but I'm not sure if that's worth it.
> Any thoughts?

I think it would be good if you do both. I'm a bit worried that XDP
performance will end up in a "death by a thousand paper cuts" situation,
so I'd rather push back on even relatively small overheads like this; so
being able to turn it off in the config would be good.

Can you share more details about what the "future CFI checking" is
likely to look like?

-Toke