[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <fc739287-62d1-e90c-c935-685b8db7970f@gmail.com>
Date: Mon, 23 Dec 2019 20:06:53 +0900
From: Prashant Bhole <prashantbhole.linux@...il.com>
To: Jason Wang <jasowang@...hat.com>, David Ahern <dsahern@...il.com>,
Toke Høiland-Jørgensen <toke@...hat.com>,
Alexei Starovoitov <alexei.starovoitov@...il.com>,
Jesper Dangaard Brouer <jbrouer@...hat.com>
Cc: "David S . Miller" <davem@...emloft.net>,
"Michael S . Tsirkin" <mst@...hat.com>,
Alexei Starovoitov <ast@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>,
Jesper Dangaard Brouer <hawk@...nel.org>,
Jakub Kicinski <jakub.kicinski@...ronome.com>,
John Fastabend <john.fastabend@...il.com>,
Toshiaki Makita <toshiaki.makita1@...il.com>,
Martin KaFai Lau <kafai@...com>,
Song Liu <songliubraving@...com>, Yonghong Song <yhs@...com>,
Andrii Nakryiko <andriin@...com>, netdev@...r.kernel.org,
Ilias Apalodimas <ilias.apalodimas@...aro.org>
Subject: Re: [RFC net-next 11/14] tun: run XDP program in tx path
On 12/23/2019 5:34 PM, Jason Wang wrote:
>
> On 2019/12/23 下午4:09, Prashant Bhole wrote:
>>
>>
>> On 12/23/19 3:05 PM, Jason Wang wrote:
>>>
>>> On 2019/12/21 上午6:17, Prashant Bhole wrote:
>>>>
>>>>
>>>> On 12/21/2019 1:11 AM, David Ahern wrote:
>>>>> On 12/19/19 9:46 PM, Prashant Bhole wrote:
>>>>>>
>>>>>> "It can improve container networking where veth pair links the
>>>>>> host and
>>>>>> the container. Host can set ACL by setting tx path XDP to the veth
>>>>>> iface."
>>>>>
>>>>> Just to be clear, this is the use case of interest to me, not the
>>>>> offloading. I want programs managed by and viewable by the host OS and
>>>>> not necessarily viewable by the guest OS or container programs.
>>>>>
>>>>
>>>> Yes the plan is to implement this while having a provision to implement
>>>> offload feature on top of it.
>>>
>>>
>>> I wonder maybe it's easier to focus on the TX path first then
>>> consider building offloading support on top.
>> Currently working on TX path. I will try make sure that we will be able
>> to implement offloading on top of it later.
>>
>> Thanks.
>
>
> Right, then I think it's better to drop patch 13 and bring it back in
> the offloading series.
>
Yes that patch actually makes sense in offloading series.
Powered by blists - more mailing lists