netdev - Re: [RFC net-next 0/6] Cleanup IRQ affinity checks in several drivers

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20240814172046.7753a62c@kernel.org>
Date: Wed, 14 Aug 2024 17:20:46 -0700
From: Jakub Kicinski <kuba@...nel.org>
To: Joe Damato <jdamato@...tly.com>
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, 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