Netdev Archive on lore.kernel.org
 help / color / Atom feed
From: "Toke Høiland-Jørgensen" <toke@redhat.com>
To: Eelco Chaudron <echaudro@redhat.com>,
	Jesper Dangaard Brouer <brouer@redhat.com>
Cc: "Machulsky\, Zorik" <zorik@amazon.com>, "Jubran\,
	Samih" <sameehj@amazon.com>,
	davem@davemloft.net, netdev@vger.kernel.org, "Woodhouse\,
	David" <dwmw@amazon.co.uk>, "Matushevsky\,
	Alexander" <matua@amazon.com>, "Bshara\,
	Saeed" <saeedb@amazon.com>, "Wilson\, Matt" <msw@amazon.com>,
	"Liguori\, Anthony" <aliguori@amazon.com>, "Bshara\,
	Nafea" <nafea@amazon.com>, "Tzalik\, Guy" <gtzalik@amazon.com>,
	"Belgazal\, Netanel" <netanel@amazon.com>, "Saidi\,
	Ali" <alisaidi@amazon.com>, "Herrenschmidt\,
	Benjamin" <benh@amazon.com>, "Kiyanovski\,
	Arthur" <akiyano@amazon.com>,
	Daniel Borkmann <borkmann@iogearbox.net>,
	Ilias Apalodimas <ilias.apalodimas@linaro.org>,
	Alexei Starovoitov <alexei.starovoitov@gmail.com>,
	Jakub Kicinski <jakub.kicinski@netronome.com>,
	xdp-newbies@vger.kernel.org
Subject: Re: XDP multi-buffer incl. jumbo-frames (Was: [RFC V1 net-next 1/1] net: ena: implement XDP drop support)
Date: Fri, 28 Jun 2019 09:46:45 +0200
Message-ID: <87y31m884a.fsf@toke.dk> (raw)
In-Reply-To: <CC99D6DE-5B6B-42F3-8D68-7F9AFF1712FF@redhat.com>

"Eelco Chaudron" <echaudro@redhat.com> writes:

> On 26 Jun 2019, at 10:38, Jesper Dangaard Brouer wrote:
>
>> On Tue, 25 Jun 2019 03:19:22 +0000
>> "Machulsky, Zorik" <zorik@amazon.com> wrote:
>>
>>> On 6/23/19, 7:21 AM, "Jesper Dangaard Brouer" <brouer@redhat.com> 
>>> wrote:
>>>
>>>     On Sun, 23 Jun 2019 10:06:49 +0300 <sameehj@amazon.com> wrote:
>>>
>>>     > This commit implements the basic functionality of drop/pass 
>>> logic in the
>>>     > ena driver.
>>>
>>>     Usually we require a driver to implement all the XDP return 
>>> codes,
>>>     before we accept it.  But as Daniel and I discussed with Zorik 
>>> during
>>>     NetConf[1], we are going to make an exception and accept the 
>>> driver
>>>     if you also implement XDP_TX.
>>>
>>>     As we trust that Zorik/Amazon will follow and implement 
>>> XDP_REDIRECT
>>>     later, given he/you wants AF_XDP support which requires 
>>> XDP_REDIRECT.
>>>
>>> Jesper, thanks for your comments and very helpful discussion during
>>> NetConf! That's the plan, as we agreed. From our side I would like to
>>> reiterate again the importance of multi-buffer support by xdp frame.
>>> We would really prefer not to see our MTU shrinking because of xdp
>>> support.
>>
>> Okay we really need to make a serious attempt to find a way to support
>> multi-buffer packets with XDP. With the important criteria of not
>> hurting performance of the single-buffer per packet design.
>>
>> I've created a design document[2], that I will update based on our
>> discussions: [2] 
>> https://github.com/xdp-project/xdp-project/blob/master/areas/core/xdp-multi-buffer01-design.org
>>
>> The use-case that really convinced me was Eric's packet header-split.
>>
>>
>> Lets refresh: Why XDP don't have multi-buffer support:
>>
>> XDP is designed for maximum performance, which is why certain 
>> driver-level
>> use-cases were not supported, like multi-buffer packets (like 
>> jumbo-frames).
>> As it e.g. complicated the driver RX-loop and memory model handling.
>>
>> The single buffer per packet design, is also tied into eBPF 
>> Direct-Access
>> (DA) to packet data, which can only be allowed if the packet memory is 
>> in
>> contiguous memory.  This DA feature is essential for XDP performance.
>>
>>
>> One way forward is to define that XDP only get access to the first
>> packet buffer, and it cannot see subsequent buffers.  For XDP_TX and
>> XDP_REDIRECT to work then XDP still need to carry pointers (plus
>> len+offset) to the other buffers, which is 16 bytes per extra buffer.
>
>
> I’ve seen various network processor HW designs, and they normally get 
> the first x bytes (128 - 512) which they can manipulate 
> (append/prepend/insert/modify/delete).
>
> There are designs where they can “page in” the additional fragments 
> but it’s expensive as it requires additional memory transfers. But the 
> majority do not care (cannot change) the remaining fragments. Can also 
> not think of a reason why you might want to remove something at the end 
> of the frame (thinking about routing/forwarding needs here).
>
> If we do want XDP to access other fragments we could do this through a 
> helper which swaps the packet context?

Yeah, I was also going to suggest a helper for that. It doesn't
necessarily need to swap the packet context, it could just return a new
pointer?

-Toke

  reply index

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-23  7:06 [RFC V1 net-next 0/1] Introduce xdp to ena sameehj
2019-06-23  7:06 ` [RFC V1 net-next 1/1] net: ena: implement XDP drop support sameehj
2019-06-23 14:09   ` Jesper Dangaard Brouer
2019-06-23 14:21   ` Jesper Dangaard Brouer
2019-06-25  3:19     ` Machulsky, Zorik
2019-06-26  8:38       ` XDP multi-buffer incl. jumbo-frames (Was: [RFC V1 net-next 1/1] net: ena: implement XDP drop support) Jesper Dangaard Brouer
2019-06-26 11:52         ` Toke Høiland-Jørgensen
2019-06-26 14:40           ` Jesper Dangaard Brouer
2019-06-26 15:01             ` Toke Høiland-Jørgensen
2019-06-26 15:20               ` Willem de Bruijn
2019-06-26 16:42                 ` Jonathan Lemon
2019-06-26 20:00                   ` Jesper Dangaard Brouer
2019-06-27 22:07                     ` Jonathan Lemon
2019-06-28  8:46                 ` Jesper Dangaard Brouer
2019-06-26 15:14             ` Toke Høiland-Jørgensen
2019-06-26 16:36               ` Jesper Dangaard Brouer
2019-06-28  7:14         ` Eelco Chaudron
2019-06-28  7:46           ` Toke Høiland-Jørgensen [this message]
2019-06-28 11:49             ` Eelco Chaudron
2019-06-28  8:22           ` Jesper Dangaard Brouer
2019-06-23 14:28   ` [RFC V1 net-next 1/1] net: ena: implement XDP drop support David Ahern
2019-06-23 14:51   ` Maciej Fijalkowski

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=87y31m884a.fsf@toke.dk \
    --to=toke@redhat.com \
    --cc=akiyano@amazon.com \
    --cc=alexei.starovoitov@gmail.com \
    --cc=aliguori@amazon.com \
    --cc=alisaidi@amazon.com \
    --cc=benh@amazon.com \
    --cc=borkmann@iogearbox.net \
    --cc=brouer@redhat.com \
    --cc=davem@davemloft.net \
    --cc=dwmw@amazon.co.uk \
    --cc=echaudro@redhat.com \
    --cc=gtzalik@amazon.com \
    --cc=ilias.apalodimas@linaro.org \
    --cc=jakub.kicinski@netronome.com \
    --cc=matua@amazon.com \
    --cc=msw@amazon.com \
    --cc=nafea@amazon.com \
    --cc=netanel@amazon.com \
    --cc=netdev@vger.kernel.org \
    --cc=saeedb@amazon.com \
    --cc=sameehj@amazon.com \
    --cc=xdp-newbies@vger.kernel.org \
    --cc=zorik@amazon.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Netdev Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/netdev/0 netdev/git/0.git
	git clone --mirror https://lore.kernel.org/netdev/1 netdev/git/1.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 netdev netdev/ https://lore.kernel.org/netdev \
		netdev@vger.kernel.org netdev@archiver.kernel.org
	public-inbox-index netdev


Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.netdev


AGPL code for this site: git clone https://public-inbox.org/ public-inbox