Message-ID: <CAOJe8K0fBBi-M+Tdv2kC+ZaNvjx92tzYaU1QX2zr8QOBRLwu3g@mail.gmail.com>
Date:   Mon, 23 Mar 2020 13:15:40 +0300
From:   Denis Kirjanov <kda@...ux-powerpc.org>
To:     Jürgen Groß <jgross@...e.com>
Cc:     netdev@...r.kernel.org, ilias.apalodimas@...aro.org,
        wei.liu@...nel.org, paul@....org
Subject: Re: [PATCH net-next v4] xen networking: add basic XDP support for xen-netfront

On 3/18/20, Jürgen Groß <jgross@...e.com> wrote:
> On 18.03.20 13:50, Denis Kirjanov wrote:
>> On 3/18/20, Jürgen Groß <jgross@...e.com> wrote:
>>> On 16.03.20 14:09, Denis Kirjanov wrote:
>>>> The patch adds a basic XDP processing to xen-netfront driver.
>>>>
>>>> We ran an XDP program for an RX response received from netback
>>>> driver. Also we request xen-netback to adjust data offset for
>>>> bpf_xdp_adjust_head() header space for custom headers.
>>>
>>> This is in no way a "verbose patch descriprion".
>>>
>>> I'm missing:
>>>
>>> - Why are you doing this. "Add XDP support" is not enough, for such
>>>     a change I'd like to see some performance numbers to get an idea
>>>     of the improvement to expect, or which additional functionality
>>>     for the user is available.
>> Ok, I'll try to measure  some numbers.
>>
>>>
>>> - A short description for me as a Xen maintainer with only basic
>>>     networking know-how, what XDP programs are about (a link to some
>>>     more detailed doc is enough, of course) and how the interface
>>>     is working (especially for switching between XDP mode and normal
>>>     SKB processing).
>>
>> You can search for the "A practical introduction to XDP" tutorial.
>> Actually there is a lot of information available regarding XDP, you
>> can easily find it.
>>
>>>
>>> - A proper description of the netfront/netback communication when
>>>     enabling or disabling XDP mode (who is doing what, is silencing
>>>     of the virtual adapter required, ...).
>> Currently we need only a header offset from netback driver so that we can
>> put
>> custom encapsulation header if required and that's done using xen bus
>> state switching,
>> so that:
>> - netback tells that it can adjust the header offset
>> - netfront part reads it
>
> Yes, but how is this synchronized with currently running network load?
> Assume you are starting without XDP being active and then you are
> activating it. How is the synchronization done from which request on
> the XDP headroom is available?

Hi Jurgen,

basically XDP is activated when you've assigned an xdp program to the
networking device.
Assigning an xdp program means that we have to adjust a pointer which
is RCU protected.

>
>>>
>>> - Reasoning why the suggested changes of frontend and backend state
>>>     are no problem for special cases like hot-remove of an interface or
>>>     live migration or suspend of the guest.
>>
>> I've put the code to talk_to_netback which is called "when first
>> setting up, and when resuming"
>> If you see a problem with that please share.
>
> What happens if a migration is just starting when netfront has switched
> its state to "Reconfigured"? Will the new device activation at the
> target host work as desired? In which state will XDP be on the frontend
> after that (i.e. is a direct state transition on the frontend from
> "Reconfigured" to "Initializing" fine)? It should be spelled out in the
> commit message that this scenario has been thought of and that it will
> work.
Well, that definitely means that I have to play with that scenario.

Moreover, I've found a problem with memory consumption while testing a
pktgen load with
xen-netfront.

Thank!
>
>>
>>>
>>> Finally I'd like to ask you to split up the patch into a netfront and
>>> a netback one.
>>
>> Ok, will do.
>
> Thanks.
>
>
> Juergen
>

Powered by blists - more mailing lists