Re: [net-next V4 PATCH 2/5] bpf: XDP_REDIRECT enable use of cpumap

[Jesper Dangaard Brouer <brouer@redhat.com>]

On Fri, 6 Oct 2017 13:17:48 +0200
Jesper Dangaard Brouer <brouer@redhat.com> wrote:

> > > +static void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index)
> > > +{
> > > +	switch (map->map_type) {
> > > +	case BPF_MAP_TYPE_DEVMAP:
> > > +		return __dev_map_lookup_elem(map, index);
> > > +	case BPF_MAP_TYPE_CPUMAP:
> > > +		return __cpu_map_lookup_elem(map, index);
> > > +	default:
> > > +		return NULL;
> > > +	}    
> > 
> > Should we just have a callback and instead of the above use
> > map->ptr_lookup_elem() (or however we name it) ... lot of it
> > is pretty much the same logic as with devmap.  
> 
> We could extend struct bpf_map *map with such a callback, I was just
> afraid that this would be too invasive.
> 
> Performance wise, I don't thinks will hurt too much.
> http://www.cipht.net/2017/10/03/are-jump-tables-always-fastest.html

Looking at the code, I would like to postpone this callback work until
after this patchset is merged.  As this work will also touch devmap +
sockmap.

-- 
Best regards,
  Jesper Dangaard Brouer
  MSc.CS, Principal Kernel Engineer at Red Hat
  LinkedIn: http://www.linkedin.com/in/brouer