netdev - Re: [ovs-dev] [PATCH 1/2] Add GSO UDP Offloading feature to OVS Internal Port

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] [day] [month] [year] [list]

Message-ID: <82757f26-350a-4b5f-8751-f33d0668632a@ovn.org>
Date: Tue, 25 Jun 2024 15:55:56 +0200
From: Ilya Maximets <i.maximets@....org>
To: Mike Pattrick <mkp@...hat.com>, echken <chengcheng.luo@...rtx.com>
Cc: dev@...nvswitch.org, netdev@...r.kernel.org,
 linux-kernel@...r.kernel.org, edumazet@...gle.com, kuba@...nel.org,
 pabeni@...hat.com, davem@...emloft.net, i.maximets@....org
Subject: Re: [ovs-dev] [PATCH 1/2] Add GSO UDP Offloading feature to OVS
 Internal Port

On 6/25/24 15:27, Mike Pattrick wrote:
> On Tue, Jun 25, 2024 at 4:30 AM echken <chengcheng.luo@...rtx.com> wrote:
>>
>> The OVS internal port does not support UDP fragmentation offloading,
>> resulting in large packets sent through the OVS internal port to OVS
>> being prematurely fragmented. This increases the total number of packets
>> processed in the path from the vport to the OVS bridge output port,
>> affecting transmission efficiency.
>>
>> Signed-off-by: echken <chengcheng.luo@...rtx.com>
>> ---
>>  net/openvswitch/vport-internal_dev.c | 3 ++-
>>  1 file changed, 2 insertions(+), 1 deletion(-)
>>
>> diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
>> index 74c88a6baa43..c5a72c4dc6fd 100644
>> --- a/net/openvswitch/vport-internal_dev.c
>> +++ b/net/openvswitch/vport-internal_dev.c
>> @@ -110,7 +110,8 @@ static void do_setup(struct net_device *netdev)
>>
>>         netdev->features = NETIF_F_LLTX | NETIF_F_SG | NETIF_F_FRAGLIST |
>>                            NETIF_F_HIGHDMA | NETIF_F_HW_CSUM |
>> -                          NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL;
>> +                          NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL |
>> +                          NETIF_F_GSO_UDP | NETIF_F_GSO_UDP_L4;
> 
> I'll try testing this out, but preliminarily, NETIF_F_GSO_SOFTWARE
> already contains NETIF_F_GSO_UDP_L4.

And as far as my understanding goes, NETIF_F_GSO_UDP is
deprecated for all use, except for tuntap.  So, we probably
shouldn't add it.  UFO generally creates more issues than
it solves.

Best regards, Ilya Maximets.