Re: [PATCH bpf-next] net: veth: account total xdp_frame len running ndo_xdp_xmit

[Lorenzo Bianconi <lorenzo@kernel.org>]

[-- Attachment #1: Type: text/plain, Size: 1753 bytes --]

> On Tue, Feb 1, 2022 at 2:46 AM Lorenzo Bianconi <lorenzo@kernel.org> wrote:
> >
> > Introduce xdp_get_frame_len utility routine to get the xdp_frame full
> > length and account total frame size running XDP_REDIRECT of a
> > non-linear xdp frame into a veth device.
> >
> > Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
> > ---
> >  drivers/net/veth.c |  4 ++--
> >  include/net/xdp.h  | 14 ++++++++++++++
> >  2 files changed, 16 insertions(+), 2 deletions(-)
> >
> > diff --git a/drivers/net/veth.c b/drivers/net/veth.c
> > index 354a963075c5..22ecaf8b8f98 100644
> > --- a/drivers/net/veth.c
> > +++ b/drivers/net/veth.c
> > @@ -493,7 +493,7 @@ static int veth_xdp_xmit(struct net_device *dev, int n,
> >                 struct xdp_frame *frame = frames[i];
> >                 void *ptr = veth_xdp_to_ptr(frame);
> >
> > -               if (unlikely(frame->len > max_len ||
> > +               if (unlikely(xdp_get_frame_len(frame) > max_len ||
> >                              __ptr_ring_produce(&rq->xdp_ring, ptr)))
> >                         break;
> 
> Looks correct, but could you explain what happens without this fix?

I guess this is just a theoretical issue, since at the moment we can't perform
a XDP_REDIRECT with a non-linear xdp buffer, but without this patch we will fail
to account peer max packet size since we take care of just the linear part of
the xdp_buff.
I am working on adding xdp multi-buff support to veth driver so I will repost this
patch into the series.

> 
> Any other drivers might have the same issue?

I do not think so since other drivers are not able to map multi-frags yet (veth
already support it since we run __xdp_build_skb_from_frame()).

Regards,
Lorenzo

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]