Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 12 Jan 2018 11:51:36 -0700
From:      Brett Glass <brett@lariat.org>
To:        Mike Tancsa <mike@sentex.net>, Brett Glass <brett@lariat.org>, Oliver Pinter <oliver.pinter@hardenedbsd.org>, "Zahrir, Abderrahmane" <Abderrahmane.Zahrir@ca.com>
Cc:        "freebsd-security@freebsd.org" <freebsd-security@freebsd.org>
Subject:   Re: Response to Meltdown and Spectre
Message-ID:  <201801121851.LAA17145@mail.lariat.net>
In-Reply-To: <b878f894-b005-f93b-c515-6fed466b760a@sentex.net>
References:  <CY1PR01MB124768D9AE4AB4D9CDAB565B8F170@CY1PR01MB1247.prod.exchangelabs.com> <CAPQ4ffsL40LsNM1deHLeSQtwAcjszqJC%2BLSd5KiSvncrPiU6jQ@mail.gmail.com> <201801121807.LAA16736@mail.lariat.net> <b878f894-b005-f93b-c515-6fed466b760a@sentex.net>

next in thread | previous in thread | raw e-mail | index | archive | help
At 11:26 AM 1/12/2018, Mike Tancsa wrote:

>"The code will be selectable via a tunable which ..." Perhaps wait for
>the final product.
>
>         ---Mike

Yes, I will be eagerly awaiting the final patch! In the meantime, I 
have located some architectural information about the latest Intel 
Atoms which indicates that they are not vulnerable even without the 
patch. As the article at

https://www.anandtech.com/show/6936/intels-silvermont-architecture-revealed-getting-serious-about-mobile/2

from AnandTech (among other sources) explains, even the Atoms that 
do OOE only do it on wholly register-based operations. This means 
that operations which are accelerated and then conditionally 
committed later cannot affect the cache. So, no processor from the 
Atom family should be susceptible to Meltdown or Spectre, and the 
extra security measures can safely be turned off automatically on 
all of them. This would be a big help to those of us who would 
otherwise have to recompile the kernel and/or set a special tunable.

--Brett Glass 




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?201801121851.LAA17145>