netdev - Re: [PATCH net-next 2/4] mlx4: xdp: Allow raising MTU up to one page minus eth and vlan hdrs

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: <20161203034232.GA70461@kafai-mba.local>
Date:   Fri, 2 Dec 2016 19:42:32 -0800
From:   Martin KaFai Lau <kafai@...com>
To:     Eric Dumazet <eric.dumazet@...il.com>
CC:     Alexei Starovoitov <ast@...com>, <netdev@...r.kernel.org>,
        Brenden Blanco <bblanco@...mgrid.com>,
        Daniel Borkmann <daniel@...earbox.net>,
        David Miller <davem@...emloft.net>,
        Saeed Mahameed <saeedm@...lanox.com>,
        Tariq Toukan <tariqt@...lanox.com>,
        Kernel Team <kernel-team@...com>
Subject: Re: [PATCH net-next 2/4] mlx4: xdp: Allow raising MTU up to one page
 minus eth and vlan hdrs

On Fri, Dec 02, 2016 at 06:15:26PM -0800, Eric Dumazet wrote:
> On Fri, 2016-12-02 at 16:53 -0800, Alexei Starovoitov wrote:
> > On 12/2/16 4:38 PM, Eric Dumazet wrote:
> > > On Fri, 2016-12-02 at 15:23 -0800, Martin KaFai Lau wrote:
> > >> When XDP prog is attached, it is currently limiting
> > >> MTU to be FRAG_SZ0 - ETH_HLEN - (2 * VLAN_HLEN) which is 1514
> > >> in x86.
> > >>
> > >> AFAICT, since mlx4 is doing one page per packet for XDP,
> > >> we can at least raise the MTU limitation up to
> > >> PAGE_SIZE - ETH_HLEN - (2 * VLAN_HLEN) which this patch is
> > >> doing.  It will be useful in the next patch which allows
> > >> XDP program to extend the packet by adding new header(s).
> > >>
> > >> Signed-off-by: Martin KaFai Lau <kafai@...com>
> > >> ---
> > >
> > > Have you tested your patch on a host with PAGE_SIZE = 64 KB ?
> > >
> > > Looks XDP really kills arches with bigger pages :(
> >
> > I'm afraid xdp mlx[45] support was not tested on arches
> > with 64k pages at all. Not just this patch.
> > I think people who care about such archs should test?
> > Note page per packet is not a hard requirement for all drivers
> > and all archs. For mlx[45] it was the easiest and the most
> > convenient way to achieve desired performance.
> > If there are ways to do the same performance differently,
> > I'm all ears :)
> >
>
> My question was more like :
>
> Can we double check all these patches wont break mlx4 driver (non XDP
> path) on arches with PAGE_SIZE=64KB.
The page/pkt requirement is not added by this patch.  The earlier
XDP patch series has already ensured this page/pkt requirement
is effective only when XDP prog is attached.

In the earlier XDP patches, MTU is limited to 1514 when
XDP is ative.   This patch is to allow fully use of the
page for a packet (and also only matter when XDP is active).