[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <Zr3XA-VIE_pAu_k0@LQ3V64L9R2>
Date: Thu, 15 Aug 2024 11:22:59 +0100
From: Joe Damato <jdamato@...tly.com>
To: Jakub Kicinski <kuba@...nel.org>
Cc: Shay Drori <shayd@...dia.com>, netdev@...r.kernel.org,
Daniel Borkmann <daniel@...earbox.net>,
"David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>,
Harshitha Ramamurthy <hramamurthy@...gle.com>,
"moderated list:INTEL ETHERNET DRIVERS" <intel-wired-lan@...ts.osuosl.org>,
Jeroen de Borst <jeroendb@...gle.com>,
Jiri Pirko <jiri@...nulli.us>, Leon Romanovsky <leon@...nel.org>,
open list <linux-kernel@...r.kernel.org>,
"open list:MELLANOX MLX4 core VPI driver" <linux-rdma@...r.kernel.org>,
Lorenzo Bianconi <lorenzo@...nel.org>,
Paolo Abeni <pabeni@...hat.com>,
Praveen Kaligineedi <pkaligineedi@...gle.com>,
Przemek Kitszel <przemyslaw.kitszel@...el.com>,
Saeed Mahameed <saeedm@...dia.com>,
Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
Shailend Chand <shailend@...gle.com>,
Tariq Toukan <tariqt@...dia.com>,
Tony Nguyen <anthony.l.nguyen@...el.com>,
Willem de Bruijn <willemb@...gle.com>,
Yishai Hadas <yishaih@...dia.com>,
Ziwei Xiao <ziweixiao@...gle.com>
Subject: Re: [RFC net-next 0/6] Cleanup IRQ affinity checks in several drivers
On Wed, Aug 14, 2024 at 05:20:46PM -0700, Jakub Kicinski wrote:
> On Wed, 14 Aug 2024 19:01:40 +0100 Joe Damato wrote:
> > If it is, then the only option is to have the drivers pass in their
> > IRQ affinity masks, as Stanislav suggested, to avoid adding that
> > call to the hot path.
> >
> > If not, then the IRQ from napi_struct can be used and the affinity
> > mask can be generated on every napi poll. i40e/gve/iavf would need
> > calls to netif_napi_set_irq to set the IRQ mapping, which seems to
> > be straightforward.
>
> It's a bit sad to have the generic solution blocked.
> cpu_rmap_update() is exported. Maybe we can call it from our notifier?
> rmap lives in struct net_device
I agree on the sadness. I will take a look today.
I guess if we were being really ambitious, we'd try to move ARFS
stuff into the core (as RSS was moved into the core).
Powered by blists - more mailing lists