Re: [RFC Patch net-next] net_sched: introduce eBPF based Qdisc

[Alexei Starovoitov <alexei.starovoitov@gmail.com>]

On Wed, Sep 1, 2021 at 10:46 AM Martin KaFai Lau <kafai@fb.com> wrote:
> > > Another idea. Rather than work with qdisc objects which creates all
> > > these issues with how to work with existing interfaces, filters, etc.
> > > Why not create an sk_buff map? Then this can be used from the existing
> > > egress/ingress hooks independent of the actual qdisc being used.
> >
> > I agree. In fact, I'm working on doing just this for XDP, and I see no
> > reason why the map type couldn't be reused for skbs as well. Doing it
> > this way has a couple of benefits:
> >
> > - It leaves more flexibility to BPF: want a simple FIFO queue? just
> >   implement that with a single queue map. Or do you want to build a full
> >   hierarchical queueing structure? Just instantiate as many queue maps
> >   as you need to achieve this. Etc.
> Agree.  Regardless how the interface may look like,
> I even think being able to queue/dequeue an skb into different bpf maps
> should be the first thing to do here.  Looking forward to your patches.
>
> >
> > - The behaviour is defined entirely by BPF program behaviour, and does
> >   not require setting up a qdisc hierarchy in addition to writing BPF
> >   code.
> Interesting idea.  If it does not need to use the qdisc object/interface
> and be able to do the qdisc hierarchy setup in a programmable way, it may
> be nice.  It will be useful for the future patches to come with some
> bpf prog examples to do that.

Wow. When core developers think along the same lines and
build/refine the idea together it's simply awesome.