Re: [PATCH rcu/dev 3/3] net: Use call_rcu_flush() for dst_destroy_rcu

[Eric Dumazet]

On Thu, Nov 17, 2022 at 10:18 AM Joel Fernandes <joel@xxxxxxxxxxxxxxxxx> wrote:
>
> On Thu, Nov 17, 2022 at 5:49 PM Eric Dumazet <edumazet@xxxxxxxxxx> wrote:
> >
> > On Thu, Nov 17, 2022 at 9:42 AM Joel Fernandes <joel@xxxxxxxxxxxxxxxxx> wrote:
> > >
> >
> > >
> > > Yes, I agree. Your comments here have not been useful (or respectful)
> > > so I am Ok with that.
> > >
> > >  - Joel
> >
> > Well, I have discovered that some changes went in networking tree
> > without network maintainers being involved nor CCed.
> >
> > What can I say ?
> >
> > It seems I have no say, right ?
>
> Sorry, I take responsibility for that. FWIW, the rxrpc change is not
> yet in Linus's tree.
>
> Also FWIW, the rxrpc case came up because we detected that it does a
> scheduler wakeup from the callback. We did both static and dynamic
> testing to identify callbacks that do wakeups throughout the kernel
> (kernel patch available on request), as the pattern observed is things
> doing wakeups typically are for use cases that are not freeing memory
> but something blocking, similar to synchronize_rcu(). So it was a
> "trivial/obvious" change to make for rxrpc which I might have assumed
> did not need much supervision because it just reverts that API to the
> old behavior -- still probably no excuse.
>
> Again, we can talk this out no problem. But I would strongly recommend
> not calling it "crazy thing", as we did all due diligence for almost a
> year (talking about it at LPC, working through various code paths and
> bugs, 4 different patch redesigns on the idea (including the opt-in
> that you are bringing up), including a late night debugging session to
> figure this out etc).

Apologies.

For me "crazy" does not have the same meaning, apparently.

I will try to use more neutral words in the future.

>
> Just to clarify, I know you review/maintain a lot of the networking
> code and I really appreciate that (not praising just for the sake).
> And I care about the kernel too, just like you.

I had no doubts about that, really.