[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20250829170929.28cfac72@kernel.org>
Date: Fri, 29 Aug 2025 17:09:29 -0700
From: Jakub Kicinski <kuba@...nel.org>
To: Amery Hung <ameryhung@...il.com>
Cc: Nimrod Oren <noren@...dia.com>, bpf@...r.kernel.org,
netdev@...r.kernel.org, alexei.starovoitov@...il.com, andrii@...nel.org,
daniel@...earbox.net, martin.lau@...nel.org, mohsin.bashr@...il.com,
saeedm@...dia.com, tariqt@...dia.com, mbloch@...dia.com,
maciej.fijalkowski@...el.com, kernel-team@...a.com, Dragos Tatulea
<dtatulea@...dia.com>
Subject: Re: [RFC bpf-next v1 0/7] Add kfunc bpf_xdp_pull_data
On Fri, 29 Aug 2025 00:26:29 -0700 Amery Hung wrote:
> > I'm currently working on a series that converts the xdp_native program
> > to use dynptr for accessing header data. If accepted, it should provide
> > better performance, since dynptr can access without copying the data.
>
> I feel that bpf_xdp_pull_data() is a more generic approach, but yeah
> dynptr may yield better performance. Looking forward to seeing the
> numbers.
To be 100% clear, being able to push and pull custom UDP encap headers
(that the NIC may not even be able to parse) is one of the main use
cases for XDP, for L3 load balances. dynptr may be slower or faster
for reading and writing to the packet, but it can't push or pull.
So this is a bit of a side conversation. Sorry if I'm stating the
obvious.
Powered by blists - more mailing lists