netdev - Re: [Patch bpf-next v3 4/5] skmsg: use skb ext instead of TCP_SKB

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] [day] [month] [year] [list]

Date:   Wed, 17 Feb 2021 11:19:16 -0800
From:   John Fastabend <john.fastabend@...il.com>
To:     Lorenz Bauer <lmb@...udflare.com>,
        John Fastabend <john.fastabend@...il.com>
Cc:     Cong Wang <xiyou.wangcong@...il.com>,
        Networking <netdev@...r.kernel.org>, bpf <bpf@...r.kernel.org>,
        duanxiongchun@...edance.com, wangdongdong.6@...edance.com,
        jiang.wang@...edance.com, Cong Wang <cong.wang@...edance.com>,
        Daniel Borkmann <daniel@...earbox.net>,
        Jakub Sitnicki <jakub@...udflare.com>
Subject: Re: [Patch bpf-next v3 4/5] skmsg: use skb ext instead of TCP_SKB_CB

Lorenz Bauer wrote:
> On Mon, 15 Feb 2021 at 19:20, John Fastabend <john.fastabend@...il.com> wrote:
> >
> > Cong Wang wrote:
> > > From: Cong Wang <cong.wang@...edance.com>
> > >
> > > Currently TCP_SKB_CB() is hard-coded in skmsg code, it certainly
> > > does not work for any other non-TCP protocols. We can move them to
> > > skb ext instead of playing with skb cb, which is harder to make
> > > correct.
> > >
> > > Cc: John Fastabend <john.fastabend@...il.com>
> > > Cc: Daniel Borkmann <daniel@...earbox.net>
> > > Cc: Jakub Sitnicki <jakub@...udflare.com>
> > > Reviewed-by: Lorenz Bauer <lmb@...udflare.com>
> > > Signed-off-by: Cong Wang <cong.wang@...edance.com>
> > > ---
> >
> > I'm not seeing the advantage of doing this at the moment. We can
> > continue to use cb[] here, which is simpler IMO and use the ext
> > if needed for the other use cases. This is adding a per packet
> > alloc cost that we don't have at the moment as I understand it.
> 
> John, do you have a benchmark we can look at? Right now we're arguing
> in the abstract.

Sure, but looks like Cong found some spare fields in sk_buff so
that looks much nicer.

I'll mess aound a bit with our benchmarks and see where we can
publish them. It would be good to have some repeatable tests
here folks can use.

Thanks,
John