netdev - Re: [PATCH 2/2 net-next] tcp: sk_add_backlog() is too agressive for TCP

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] [thread-next>] [day] [month] [year] [list]

Date:	Tue, 24 Apr 2012 13:32:34 +0300 (EEST)
From:	"Ilpo Järvinen" <ilpo.jarvinen@...sinki.fi>
To:	David Miller <davem@...emloft.net>
cc:	Eric Dumazet <eric.dumazet@...il.com>, rick.jones2@...com,
	Netdev <netdev@...r.kernel.org>, therbert@...gle.com,
	ncardwell@...gle.com, maze@...gle.com,
	Yuchung Cheng <ycheng@...gle.com>
Subject: Re: [PATCH 2/2 net-next] tcp: sk_add_backlog() is too agressive for
 TCP

On Tue, 24 Apr 2012, David Miller wrote:

> From: "Ilpo Järvinen" <ilpo.jarvinen@...sinki.fi>
> Date: Tue, 24 Apr 2012 11:40:27 +0300 (EEST)
> 
> > And the problem I mentioned in the previous mail (in the terms of this 
> > code fragment) is that ackdiff is no longer MSS or 2*MSS because of GRO 
> > for the opposite direction doesn't trigger all those ACKs a non-GRO 
> > receiver would.
> 
> And in any event, you cannot depend upon the ACK boundaries in any way
> shape or form, 2 * MSS is just one valid mode of ACK'ing.
> 
> Whether we get a GRO stretch ACK or a normal 2 * MSS one, it has to
> work properly either way.

I don't see how any of this is that much different from the data side. x 
bytes, x bytes, x bytes, ... (typically x=MSS) is just one valid mode of 
data sending, and yet the GRO is currently based on this one mode only. 
...It of course works properly also when that is not true but won't work 
as efficiently as when the size remains the same.


-- 
 i.