From: Borislav Petkov Subject: Re: [Xen-devel] [PATCH] x86/amd: fix crash as Xen Dom0 on AMD Trinity systems Date: Thu, 31 May 2012 18:55:23 +0200 Message-ID: <20120531165522.GA3834@x1.osrc.amd.com> References: <20120530144851.GA12184@jshin-Toonie> <20120530145005.GI3207@phenom.dumpdata.com> <20120530150334.GA13349@jshin-Toonie> <20120530171754.GA5115@phenom.dumpdata.com> <20120530173247.GC15635@x1.osrc.amd.com> <4FC65D34.1060803@zytor.com> <20120530175150.GE15438@x1.osrc.amd.com> <4FC66037.6020506@zytor.com> <20120530181722.GF15438@x1.osrc.amd.com> <4FC73C430200007800087137@nat28.tlf.novell.com> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8 Return-path: Content-Disposition: inline In-Reply-To: <4FC73C430200007800087137@nat28.tlf.novell.com> Sender: linux-kernel-owner@vger.kernel.org To: Jan Beulich Cc: Andre Przywara , Jacob Shin , mingo@elte.hu, jeremy@goop.org, tglx@linutronix.de, xen-devel@lists.xensource.com, Konrad Rzeszutek Wilk , linux-kernel@vger.kernel.org, "H. Peter Anvin" , Yinghai Lu List-Id: xen-devel@lists.xenproject.org On Thu, May 31, 2012 at 08:39:15AM +0100, Jan Beulich wrote: > >>> On 30.05.12 at 20:17, Borislav Petkov wrote: > > On Wed, May 30, 2012 at 11:00:23AM -0700, H. Peter Anvin wrote: > > The other place where we use the amd_safe variants is an obscure K8, > > revC and earlier fix for _some_ BIOSen and this hasn't bitten us yet > > so I'm assuming people haven't run xen on such boxes yet. Does it need > > fixing? Probably, if we really really have to. > > This again is something that shouldn't even be attempted under > Xen. The hypervisor, unless really old, does this (and wouldn't > allow the write by any domain - privileged or not - anyway). > > There's one more user though - the code triggered by the > "show_msr=" command line option. This one indeed requires > rdmsr_safe_regs to be functional (albeit under Xen, once > again, this won't work currently anyway for those MRS on > old CPUs where the special key in %edi is required, which the > emulation code in Xen doesn't support). This doesn't look right. Yinghai, why does generic x86 code use rdmsrl_amd_safe - it should simply use rdmsrl_safe. -- Regards/Gruss, Boris.