[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <af0ce325-15ea-e3fd-9c20-fd4296266e63@redhat.com>
Date: Mon, 2 Dec 2019 10:45:39 +0800
From: Jason Wang <jasowang@...hat.com>
To: David Ahern <dsahern@...il.com>,
Prashant Bhole <prashantbhole.linux@...il.com>,
"David S . Miller" <davem@...emloft.net>,
"Michael S . Tsirkin" <mst@...hat.com>
Cc: Alexei Starovoitov <ast@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>,
Jakub Kicinski <jakub.kicinski@...ronome.com>,
Jesper Dangaard Brouer <hawk@...nel.org>,
John Fastabend <john.fastabend@...il.com>,
Martin KaFai Lau <kafai@...com>,
Song Liu <songliubraving@...com>, Yonghong Song <yhs@...com>,
Andrii Nakryiko <andriin@...com>, netdev@...r.kernel.org,
qemu-devel@...gnu.org, kvm@...r.kernel.org
Subject: Re: [RFC net-next 08/18] tun: run offloaded XDP program in Tx path
On 2019/12/2 上午12:39, David Ahern wrote:
> On 11/26/19 4:07 AM, Prashant Bhole wrote:
>> run offloaded XDP program as soon as packet is removed from the ptr
>> ring. Since this is XDP in Tx path, the traditional handling of
>> XDP actions XDP_TX/REDIRECT isn't valid. For this reason we call
>> do_xdp_generic_core instead of do_xdp_generic. do_xdp_generic_core
>> just runs the program and leaves the action handling to us.
> What happens if an offloaded program returns XDP_REDIRECT?
>
> Below you just drop the packet which is going to be a bad user
> experience. A better user experience is to detect XDP return codes a
> program uses, catch those that are not supported for this use case and
> fail the install of the program.
Yes, this could be done in the guest.
Thanks
Powered by blists - more mailing lists