From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jeremy Fitzhardinge Subject: Re: RE: AMD Phenom II 940: Upgrade to 2.6.32.12 fixes it and upgrades CPU from 3.1Ghz to 1.2Thz! Date: Mon, 10 May 2010 10:56:20 -0700 Message-ID: <4BE848C4.1090005@goop.org> References: <482967.72793.qm@web56107.mail.re3.yahoo.com> <4BE44375.1030300@verizon.net> <4BE48BE4.8000607@verizon.net> <20100510141038.GA29517@phenom.dumpdata.com> <4BE82E3D.5090405@verizon.net 20100510161703.GA30879@phenom.dumpdata.com> <81240ce8-4265-431e-b5e6-71c5340e2af3@default> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <81240ce8-4265-431e-b5e6-71c5340e2af3@default> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com To: Dan Magenheimer Cc: Gerry Reno , xen-devel@lists.xensource.com, konrad.wilk@oracle.com List-Id: xen-devel@lists.xenproject.org On 05/10/2010 09:40 AM, Dan Magenheimer wrote: >>>>> enlighten.c, 'd0 domain attempted wrmsr', 'Detected 1226681.732 MHz >>>>> processor.'(a 1.2 TeraHz processor??? - the processor is actually a >>>>> >> 3.1 >> >>> I'm wondering if this bothers delay loop timings, etc. ??? >>> >> Dan, thoughts? >> > This info is obtained from Xen via the shared_info struct, so > I'd bet the shared_info struct is getting trashed. > > Or, for awhile, Jeremy had some code that made it possible > for pvclock to use multiple shared_info structs to detect > TSC skew. I had a patch for multiple pvclock structures so that they could be exported to userspace, but I screwed up the Xen side so that it was trashing memory on context switch. But the use of pvclock in usermode is fairly iffy anyway, since there are concerns about how to attain the monotonicity guarantees required by clock_gettime, etc. So at the moment, neither Xen nor the .32+ kernels have support for that. J