Re: [PATCH] net-xdp: netdev attribute to control xdpgeneric skb linearization

Luigi Rizzo [off-list ref] writes:

On Fri, Jan 24, 2020 at 1:28 PM Toke Høiland-Jørgensen [off-list ref]
wrote:

quoted

Luigi Rizzo [off-list ref] writes:

quoted

On Fri, Jan 24, 2020 at 7:31 AM Toke Høiland-Jørgensen [off-list ref]

wrote:

quoted

quoted

Luigi Rizzo [off-list ref] writes:

...

quoted

quoted

My motivation for this change is that enforcing those guarantees has
significant cost (even for native xdp in the cases I mentioned - mtu >
1 page, hw LRO, header split), and this is an interim solution to make
generic skb usable without too much penalty.

Sure, that part I understand; I just don't like that this "interim"
solution makes generic and native XDP diverge further in their
semantics...

As a matter of fact I think it would make full sense to use the same

approach

quoted

to control whether native xdp should pay the price converting to linear

buffers

quoted

when the hw cannot guarantee that.

To me this seems to be a case of "perfect is enemy of good":..

Hmm, I can kinda see your point (now that I've actually grok'ed how the
length works with skbs and generic XDP :)). I would still worry that
only having the header there would lead some XDP programs to just
silently fail. But on the other hand, this is opt-in... so IDK - maybe
this is fine to merge as-is, and leave improvements for later?

Sorry I let this slip, any consensus on this patch?

Dunno if there's a consensus, but I certainly ran out of objections ;)

-Toke