[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250328043941.085de23b@kernel.org>
Date: Fri, 28 Mar 2025 04:39:41 -0700
From: Jakub Kicinski <kuba@...nel.org>
To: "Jiayuan Chen" <jiayuan.chen@...ux.dev>
Cc: "Willem de Bruijn" <willemdebruijn.kernel@...il.com>,
netdev@...r.kernel.org, jasowang@...hat.com, andrew+netdev@...n.ch,
davem@...emloft.net, edumazet@...gle.com, pabeni@...hat.com,
ast@...nel.org, daniel@...earbox.net, hawk@...nel.org,
john.fastabend@...il.com, linux-kernel@...r.kernel.org,
syzbot+0e6ddb1ef80986bdfe64@...kaller.appspotmail.com, bpf@...r.kernel.org,
martin.lau@...ux.dev, eddyz87@...il.com, song@...nel.org,
kpsingh@...nel.org, jolsa@...nel.org
Subject: Re: [PATCH net v1] net: Fix tuntap uninitialized value
On Fri, 28 Mar 2025 09:15:53 +0000 Jiayuan Chen wrote:
> I'm wondering if we can directly perform a memset in bpf_xdp_adjust_head
> when users execute an expand header (offset < 0).
Same situation happens in bpf_xdp_adjust_meta(), but I'm pretty
sure this was discussed and considered too high cost for XDP.
Could you find the old discussions and double check the arguments
made back then? Opinions may have changed but let's make sure we're
not missing anything. And performance numbers would be good to have
since the main reason this isn't done today was perf.
Powered by blists - more mailing lists