Re: Improving use of rt_refcnt

[Ryota Ozaki <ozaki-r%netbsd.org@localhost>]

On Sun, Jul 5, 2015 at 6:50 PM, Joerg Sonnenberger
<joerg%britannica.bec.de@localhost> wrote:
> On Sun, Jul 05, 2015 at 02:12:18PM +0900, Ryota Ozaki wrote:
>> On Sun, Jul 5, 2015 at 2:35 AM, David Young <dyoung%pobox.com@localhost> wrote:
>> > On Sat, Jul 04, 2015 at 09:52:56PM +0900, Ryota Ozaki wrote:
>> >> I'm trying to improve use of rt_refcnt: reducing
>> >> abuse of it, e.g., rt_refcnt++/rt_refcnt-- outside
>> >> route.c and extending it to treat referencing
>> >> during packet processing (IOW, references from
>> >> local variables) -- currently it handles only
>> >> references between routes. The latter is needed for
>> >> MP-safe networking.
>> >
>> > Do you propose to increase/decrease rt_refcnt in the packet processing
>> > path, using atomic instructions?
>>
>> Atomic instructions aren't used yet, i.e., softnet_lock is still needed.
>> I will introduce them later. (Using refcount(9) by riastradh would be
>> good once it is committed.)
>
> I think the main point that David wanted to raise is that the normal
> path for packets should *not* do any ref count changes at all.

Why? rtentry can be freed during the normal path in MP-safe world.
Do you suggest using pserialize instead?

  ozaki-r

>
> Joerg