[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20200223193710.596fb5d9ebb23959a3fee187@linux-foundation.org>
Date: Sun, 23 Feb 2020 19:37:10 -0800
From: Andrew Morton <akpm@...ux-foundation.org>
To: Arjun Roy <arjunroy@...gle.com>
Cc: Arjun Roy <arjunroy.kdev@...il.com>,
David Miller <davem@...emloft.net>, netdev@...r.kernel.org,
linux-mm@...ck.org, Eric Dumazet <edumazet@...gle.com>,
Soheil Hassas Yeganeh <soheil@...gle.com>
Subject: Re: [PATCH resend mm,net-next 3/3] net-zerocopy: Use
vm_insert_pages() for tcp rcv zerocopy.
On Fri, 21 Feb 2020 13:21:41 -0800 Arjun Roy <arjunroy@...gle.com> wrote:
> I remain a bit concerned regarding the merge process for this specific
> patch (0003, the net/ipv4/tcp.c change) since I have other in-flight
> changes for TCP receive zerocopy that I'd like to upstream for
> net-next - and would like to avoid weird merge issues.
>
> So perhaps the following could work:
>
> 1. Andrew, perhaps we could remove this particular patch (0003, the
> net/ipv4/tcp.c change) from mm-next; that way we merge
> vm_insert_pages() but not the call-site within TCP, for now.
> 2. net-next will eventually pick vm_insert_pages() up.
> 3. I can modify the zerocopy code to use it at that point?
>
> Else I'm concerned a complicated merge situation may result.
>
> What do you all think?
We could do that.
For now, I'll stage the entire patch series after linux-next and shall
wait and see whether things which appear in linux-next cause serious
merge issues to occur. Sound OK?
Powered by blists - more mailing lists