Re: [PATCH net-next 0/2] virtio-net: re enable XDP_REDIRECT for mergeable buffer

[Jason Wang <jasowang@redhat.com>]

On 2018年03月01日 18:35, Jesper Dangaard Brouer wrote:
> On Thu, 1 Mar 2018 17:23:37 +0800
> Jason Wang <jasowang@redhat.com> wrote:
>
>> On 2018年03月01日 17:10, Jesper Dangaard Brouer wrote:
>>> On Thu,  1 Mar 2018 11:19:03 +0800
>>> Jason Wang <jasowang@redhat.com> wrote:
>>>   
>>>> This series tries to re-enable XDP_REDIRECT for mergeable buffer which
>>>> was removed since commit 7324f5399b06 ("virtio_net: disable
>>>> XDP_REDIRECT in receive_mergeable() case"). Main concerns are:
>>>>
>>>> - not enough tailroom was reserved which breaks cpumap
>>> To address this at a more fundamental level, I would suggest that we/you
>>> instead extend XDP to know it's buffers "frame" size/end.  (The
>>> assumption use to be, xdp_buff->data_hard_start + PAGE_SIZE, but
>>> ixgbe+virtio_net broke that assumption).
>>>
>>> It should actually be fairly easy to implement:
>>>    * Simply extend xdp_buff with a "data_hard_end" pointer.
>> Right, and then cpumap can warn and drop packets with insufficient
>> tailroom.
>>
>> But it should be a patch on top of this I think.
> Hmmm, not really.  If we/you instead fix the issue of XDP doesn't know
> the end/size of the frame, then we don't need this mixed XDP
> generic/native code path mixing.

I know this but I'm still a little bit confused. According to the commit 
log of 7324f5399b06 ("virtio_net: disable XDP_REDIRECT in 
receive_mergeable() case"), you said:

"""
     The longer explaination is that receive_mergeable() tries to
     work-around and satisfy these XDP requiresments e.g. by having a
     function xdp_linearize_page() that allocates and memcpy RX buffers
     around (in case packet is scattered across multiple rx buffers).  This
     does currently satisfy XDP_PASS, XDP_DROP and XDP_TX (but only because
     we have not implemented bpf_xdp_adjust_tail yet).
"""

So I consider the tailroom is a must for the (future) tail adjustment.

>
> You could re-enable native redirect, and push the responsibility to
> cpumap for detecting this too-small frame "missing tailroom" (and avoid
> crashing...). (If we really want to support this, cpumap could fallback
> to dev_alloc_skb, and handle it gracefully).
>

Right but it will be slower than build_skb().

Thanks