RE: [PATCH v6 bpf-next 0/8] mvneta: introduce XDP multi-buffer support

["Jubran, Samih" <sameehj@amazon.com>]

> -----Original Message-----
> From: Lorenzo Bianconi <lorenzo@kernel.org>
> Sent: Sunday, January 31, 2021 7:24 PM
> To: Daniel Borkmann <daniel@iogearbox.net>
> Cc: bpf@vger.kernel.org; netdev@vger.kernel.org;
> lorenzo.bianconi@redhat.com; davem@davemloft.net; kuba@kernel.org;
> ast@kernel.org; Agroskin, Shay <shayagr@amazon.com>;
> john.fastabend@gmail.com; dsahern@kernel.org; brouer@redhat.com;
> echaudro@redhat.com; jasowang@redhat.com;
> alexander.duyck@gmail.com; saeed@kernel.org;
> maciej.fijalkowski@intel.com; Jubran, Samih <sameehj@amazon.com>
> Subject: RE: [EXTERNAL] [PATCH v6 bpf-next 0/8] mvneta: introduce XDP
> multi-buffer support
> 
> > Hi Lorenzo,
> 
> Hi Daniel,
> 
> sorry for the delay.
> 
> >
> > On 1/19/21 9:20 PM, Lorenzo Bianconi wrote:
> > > This series introduce XDP multi-buffer support. The mvneta driver is
> > > the first to support these new "non-linear" xdp_{buff,frame}.
> > > Reviewers please focus on how these new types of xdp_{buff,frame}
> > > packets traverse the different layers and the layout design. It is
> > > on purpose that BPF-helpers are kept simple, as we don't want to
> > > expose the internal layout to allow later changes.
> > >
> > > For now, to keep the design simple and to maintain performance, the
> > > XDP BPF-prog (still) only have access to the first-buffer. It is
> > > left for later (another patchset) to add payload access across multiple
> buffers.
> >
> > I think xmas break has mostly wiped my memory from 2020 ;) so it would
> > be good to describe the sketched out design for how this will look
> > like inside the cover letter in terms of planned uapi exposure.
> > (Additionally discussing api design proposal could also be sth for BPF
> > office hour to move things quicker + posting a summary to the list for
> > transparency of course .. just a thought.)
> 
> I guess the main goal of this series is to add the multi-buffer support to the
> xdp core (e.g. in xdp_frame/xdp_buff or in xdp_return_{buff/frame}) and to
> provide the first driver with xdp mult-ibuff support. We tried to make the
> changes independent from eBPF helpers since we do not have defined use
> cases for them yet and we don't want to expose the internal layout to allow
> later changes.
> One possible example is bpf_xdp_adjust_mb_header() helper we sent in v2
> patch 6/9 [0] to try to address use-case explained by Eric @ NetDev 0x14 [1].
> Anyway I agree there are some missing bits we need to address (e.g. what is
> the behaviour when we redirect a mb xdp_frame to a driver not supporting
> it?)
> 
> Ack, I agree we can discuss about mb eBPF helper APIs in BPF office hour mtg
> in order to speed-up the process.
> 
> >
> > Glancing over the series, while you've addressed the
> > bpf_xdp_adjust_tail() helper API, this series will be breaking one
> > assumption of programs at least for the mvneta driver from one kernel
> > to another if you then use the multi buff mode, and that is basically
> > bpf_xdp_event_output() API: the assumption is that you can do full
> > packet capture by passing in the xdp buff len that is data_end - data
> > ptr. We use it this way for sampling & others might as well (e.g.
> > xdpcap). But bpf_xdp_copy() would only copy the first buffer today
> > which would break the full pkt visibility assumption. Just walking the
> > frags if
> > xdp->mb bit is set would still need some sort of struct xdp_md
> > xdp->exposure so
> > the prog can figure out the actual full size..
> 
> ack, thx for pointing this out, I will take a look to it.
> Eelco added xdp_len to xdp_md in the previous series (he is still working on
> it). Another possible approach would be defining a helper, what do you
> think?
> 
> >
> > > This patchset should still allow for these future extensions. The
> > > goal is to lift the XDP MTU restriction that comes with XDP, but
> > > maintain same performance as before.
> > >
> > > The main idea for the new multi-buffer layout is to reuse the same
> > > layout used for non-linear SKB. We introduced a "xdp_shared_info"
> > > data structure at the end of the first buffer to link together subsequent
> buffers.
> > > xdp_shared_info will alias skb_shared_info allowing to keep most of
> > > the frags in the same cache-line (while with skb_shared_info only
> > > the first fragment will be placed in the first "shared_info"
> > > cache-line). Moreover we introduced some xdp_shared_info helpers
> aligned to skb_frag* ones.
> > > Converting xdp_frame to SKB and deliver it to the network stack is
> > > shown in cpumap code (patch 7/8). Building the SKB, the
> > > xdp_shared_info structure will be converted in a skb_shared_info one.
> > >
> > > A multi-buffer bit (mb) has been introduced in xdp_{buff,frame}
> > > structure to notify the bpf/network layer if this is a xdp
> > > multi-buffer frame (mb = 1) or not (mb = 0).
> > > The mb bit will be set by a xdp multi-buffer capable driver only for
> > > non-linear frames maintaining the capability to receive linear
> > > frames without any extra cost since the xdp_shared_info structure at
> > > the end of the first buffer will be initialized only if mb is set.
> > >
> > > Typical use cases for this series are:
> > > - Jumbo-frames
> > > - Packet header split (please see Google’s use-case @ NetDevConf
> > > 0x14, [0])
> > > - TSO
> > >
> > > bpf_xdp_adjust_tail helper has been modified to take info account
> > > xdp multi-buff frames.
> >
> > Also in terms of logistics (I think mentioned earlier already), for
> > the series to be merged - as with other networking features spanning
> > core + driver (example
> > af_xdp) - we also need a second driver (ideally mlx5, i40e or ice)
> > implementing this and ideally be submitted together in the same series
> > for review. For that it probably also makes sense to more cleanly
> > split out the core pieces from the driver ones. Either way, how is progress
> on that side coming along?
> 
> I do not have any updated news about it so far, but afaik amazon folks were
> working on adding mb support to ena driver, while intel was planning to add
> it to af_xdp.
Hi all,

The ENA XDP MB implementation is currently being rebased on top of this
series. We are in final stages of polishing and testing the code and
looking forward to send it for review, hopefully till the end of March.

> Moreover Jason was looking to add it to virtio-net.
> 
> >
> > Thanks,
> > Daniel
> 
> Regards,
> Lorenzo
>
Best regards,
Sameeh
 
> [0]
> https://patchwork.ozlabs.org/project/netdev/patch/b7475687bb09aac6ec05
> 1596a8ccbb311a54cb8a.1599165031.git.lorenzo@kernel.org/
> [1] https://netdevconf.info/0x14/session.html?talk-the-path-to-tcp-4k-mtu-
> and-rx-zerocopy