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: <58421775.6090905@fb.com>
Date:   Fri, 2 Dec 2016 16:53:09 -0800
From:   Alexei Starovoitov <ast@...com>
To:     Eric Dumazet <eric.dumazet@...il.com>,
        Martin KaFai Lau <kafai@...com>
CC:     <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 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 :)