[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ZwOESgIy481G/3zn@gauss3.secunet.de>
Date: Mon, 7 Oct 2024 08:48:42 +0200
From: Steffen Klassert <steffen.klassert@...unet.com>
To: Tobias Brunner <tobias@...ongswan.org>, Antony Antony
<antony.antony@...unet.com>, Daniel Xu <dxu@...uu.xyz>, Paul Wouters
<paul@...ats.ca>, Simon Horman <horms@...nel.org>, Sabrina Dubroca
<sd@...asysnail.net>, <netdev@...r.kernel.org>
CC: <devel@...ux-ipsec.org>
Subject: Re: [PATCH 0/4] xfrm: Add support for RFC 9611 per cpu xfrm states
I forgot to mention that this is the v2 patchset and based on
the ipsec-next tree...
On Mon, Oct 07, 2024 at 08:44:49AM +0200, Steffen Klassert wrote:
> This patchset implements the xfrm part of per cpu SAs as specified in
> RFC 9611.
>
> Patch 1 adds the cpu as a lookup key and config option to to generate
> acquire messages for each cpu.
>
> Patch 2 caches outbound states at the policy.
>
> Patch 3 caches inbound states on a new percpu state cache.
>
> Patch 4 restricts percpu SA attributes to specific netlink message types.
>
> Please review and test.
>
> ---
>
> Changes from v1:
>
> - Add compat layer attributes
>
> - Fix a 'use always slowpath' condition
>
> - Document get_cpu() usage
>
> - Fix forgotten update of xfrm_expire_msgsize()
Powered by blists - more mailing lists