[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <3aa17b8d72f8d4605d1cccb7692cc152b77d7f87.camel@redhat.com>
Date: Tue, 05 Mar 2024 11:36:39 +0100
From: Paolo Abeni <pabeni@...hat.com>
To: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
Cc: netdev@...r.kernel.org, "David S. Miller" <davem@...emloft.net>, Eric
Dumazet <edumazet@...gle.com>, Jakub Kicinski <kuba@...nel.org>, Jesper
Dangaard Brouer <hawk@...nel.org>, Thomas Gleixner <tglx@...utronix.de>,
Wander Lairson Costa <wander@...hat.com>, Yan Zhai <yan@...udflare.com>
Subject: Re: [PATCH v3 net-next 3/4] net: Use backlog-NAPI to clean up the
defer_list.
On Tue, 2024-03-05 at 11:25 +0100, Sebastian Andrzej Siewior wrote:
> On 2024-03-05 10:55:45 [+0100], Paolo Abeni wrote:
> > On Wed, 2024-02-28 at 13:05 +0100, Sebastian Andrzej Siewior wrote:
> > > @@ -4736,6 +4736,26 @@ static void napi_schedule_rps(struct softnet_data *sd)
> > > __napi_schedule_irqoff(&mysd->backlog);
> > > }
> > >
> > > +void kick_defer_list_purge(unsigned int cpu)
> > > +{
> >
> > Minor nit: I guess passing directly 'sd' as an argument here would be
> > better, but that could be a follow-up.
>
> I need the CPU number in the "non-backlog threaded" case for
> smp_call_function_single_async(cpu, ). sd->cpu has the CPU stored but
> only in the CONFIG_RPS case. In the theoretical case +SMP -SYSFS we
> wouldn't have RPS but would need this CPU member.
To clarify: I'm suggesting passing both arguments.
Cheers,
Paolo
Powered by blists - more mailing lists