[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <alpine.DEB.2.20.1612141520350.24815@east.gentwo.org>
Date: Wed, 14 Dec 2016 15:22:30 -0600 (CST)
From: Christoph Lameter <cl@...ux.com>
To: Hannes Frederic Sowa <hannes@...essinduktion.org>
cc: David Laight <David.Laight@...LAB.COM>,
Jesper Dangaard Brouer <brouer@...hat.com>,
John Fastabend <john.fastabend@...il.com>,
Mike Rapoport <rppt@...ux.vnet.ibm.com>,
"netdev@...r.kernel.org" <netdev@...r.kernel.org>,
linux-mm <linux-mm@...ck.org>,
Willem de Bruijn <willemdebruijn.kernel@...il.com>,
Björn Töpel <bjorn.topel@...el.com>,
"Karlsson, Magnus" <magnus.karlsson@...el.com>,
Alexander Duyck <alexander.duyck@...il.com>,
Mel Gorman <mgorman@...hsingularity.net>,
Tom Herbert <tom@...bertland.com>,
Brenden Blanco <bblanco@...mgrid.com>,
Tariq Toukan <tariqt@...lanox.com>,
Saeed Mahameed <saeedm@...lanox.com>,
Jesse Brandeburg <jesse.brandeburg@...el.com>,
Kalman Meth <METH@...ibm.com>,
Vladislav Yasevich <vyasevich@...il.com>
Subject: Re: Designing a safe RX-zero-copy Memory Model for Networking
On Wed, 14 Dec 2016, Hannes Frederic Sowa wrote:
> Wouldn't changing of the pages cause expensive TLB flushes?
Yes so you would only want that feature if its realized at the page
table level for debugging issues.
Once you have memory registered with the hardware device then also the
device could itself could perform snooping to realize that data was
changed and thus abort the operation.
Powered by blists - more mailing lists