Re: [virtio-dev] Re: [PATCH] virtio_net: support split header

[Heng Qi <hengqi@linux.alibaba.com>]

å 2022/8/4 äå9:50, Cornelia Huck åé:

> On Thu, Aug 04 2022, Heng Qi <hengqi@linux.alibaba.com> wrote:
>
> > å 2022/8/4 äå2:27, Jason Wang åé:
> > > On Mon, Aug 1, 2022 at 2:59 PM Heng Qi<hengqi@linux.alibaba.com>  wrote:
> > > > @@ -3820,9 +3826,13 @@ \subsubsection{Processing of Incoming Packets}\label{sec:Device Types / Network
> > > >   driver MUST NOT use the \field{csum_start} and \field{csum_offset}.
> > > >
> > > >   If one of the VIRTIO_NET_F_GUEST_TSO4, TSO6, UFO, USO4 or USO6 options have
> > > > -been negotiated, the driver MAY use \field{hdr_len} only as a hint about the
> > > > +been negotiated and the VIRTIO_NET_HDR_F_SPLIT_HEADER bit in \field{flags}
> > > > +is not set, the driver MAY use \field{hdr_len} only as a hint about the
> > > >   transport header size.
> > > > -The driver MUST NOT rely on \field{hdr_len} to be correct.
> > > > +
> > > > +If the VIRTIO_NET_HDR_F_SPLIT_HEADER bit in \field{flags} is not set, the driver
> > > > +MUST NOT rely on \field{hdr_len} to be correct.
> > > >           
> > > I think we should keep the above description as-is. For whatever case,
> > > the driver must not trust the metadata set by the device and must
> > > perform necessary sanity tests on them.
> > >         
> >
> > My idea is to keep the current description as it is,
> > but to emphasize in the next version:
> > "If the VIRTIO_NET_HDR_F_SPLIT_HEADER bit in \field{flags} is set,
> > the driver MAY treat the \field{hdr_len} as the length of the
> > protocol header inside the first descriptor."
> >       
>
> Just to be clear, you suggest using
>
> "If one of the VIRTIO_NET_F_GUEST_TSO4, TSO6, UFO, USO4 or USO6 options have
> been negotiated, the driver MAY use \field{hdr_len} only as a hint about the
> transport header size.
>
> The driver MUST NOT rely on \field{hdr_len} to be correct.
>
> If the VIRTIO_NET_HDR_F_SPLIT_HEADER bit in \field{flags} is set,
> the driver MAY treat the \field{hdr_len} as the length of the
> protocol header inside the first descriptor."
>     
Yes. I will use the above description to make it clearer in the next version.


> (Maybe "...the driver MAY use \field{hdr_len} as a hint about the length
> of the protocol header..."? It's still not reliable, right?)
>
>     
\field{hdr_len} is unreliable when VIRTIO_NET_F_SPLIT_HEADER is not negotiated.


If VIRTIO_NET_F_SPLIT_HEADER is negotiated, "split header" MAY perform the split
from the IP layer, so the protocol header and the transport header are different.

so I think the "...the driver MAY use \field{hdr_len} only as a hint about the
transport header size..." paragraph can be left as-is.