[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <b37b38df-cbb8-ca86-d460-9d3ec7acc2c6@linux.vnet.ibm.com>
Date: Thu, 12 Oct 2017 12:48:04 +0200
From: Ursula Braun <ubraun@...ux.vnet.ibm.com>
To: David Miller <davem@...emloft.net>
Cc: netdev@...r.kernel.org, linux-s390@...r.kernel.org,
jwi@...ux.vnet.ibm.com, schwidefsky@...ibm.com,
heiko.carstens@...ibm.com, raspl@...ux.vnet.ibm.com,
hwippel@...ux.vnet.ibm.com
Subject: Re: [PATCH net-next 1/1] net/smc: add SMC rendezvous protocol
On 10/11/2017 11:06 PM, David Miller wrote:
> From: Ursula Braun <ubraun@...ux.vnet.ibm.com>
> Date: Tue, 10 Oct 2017 16:14:19 +0200
>
>> The goal of this patch is to leave common TCP code unmodified. Thus,
>> it uses netfilter hooks to intercept TCP SYN and SYN/ACK
>> packets. For outgoing packets originating from SMC sockets, the
>> experimental option is added. For inbound packets destined for SMC
>> sockets, the experimental option is checked.
>
> I think this really isn't going to pass.
>
> It's a user experience nightmare when the kernel inserts and
> deletes filtering rules outside of what the user configures
> on their system.
>
> This approach was also considerd for ipv6 ILA, and the same
> pushback was given.
>
> Why not add support for these new options as a normal TCP
> socket option based feature? Then normal userspace as well
> as the SMC stack can make use of it.
>
Do you mean a solution like
https://www.mail-archive.com/netdev@vger.kernel.org/msg71321.html
https://www.mail-archive.com/netdev@vger.kernel.org/msg71324.html
with a new smc_rendezvous TCP socket option as trigger?
Powered by blists - more mailing lists