From mboxrd@z Thu Jan 1 00:00:00 1970 From: Toshi Kani Subject: Re: Fwd: [PATCH] x86: Use larger chunks in mtrr_cleanup Date: Fri, 04 Sep 2015 08:56:21 -0600 Message-ID: <1441378581.21638.9.camel@hpe.com> References: <20150903184029.GV8051@wotan.suse.de> <1441308162.3277.20.camel@hpe.com> <20150903195134.GW8051@wotan.suse.de> <1441315902.3277.39.camel@hpe.com> <20150903220711.GX8051@wotan.suse.de> <1441319131.3277.54.camel@hpe.com> <20150903224556.GY8051@wotan.suse.de> <1441322474.3277.78.camel@hpe.com> <20150903235429.GZ8051@wotan.suse.de> <1441327726.3277.109.camel@hpe.com> <20150904014040.GA8051@wotan.suse.de> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: In-Reply-To: <20150904014040.GA8051@wotan.suse.de> Sender: linux-kernel-owner@vger.kernel.org To: "Luis R. Rodriguez" Cc: Prarit Bhargava , Stuart Hayes , tglx@linutronix.de, mingo@redhat.com, "H. Peter Anvin" , linux-kernel@vger.kernel.org, x86@kernel.org, mcgrof@do-not-panic.com, Toshi Kani , Jan Beulich , Juergen Gross , Roger Pau =?ISO-8859-1?Q?Monn=E9?= , xen-devel@lists.xensource.com List-Id: xen-devel@lists.xenproject.org On Fri, 2015-09-04 at 03:40 +0200, Luis R. Rodriguez wrote: > On Thu, Sep 03, 2015 at 06:48:46PM -0600, Toshi Kani wrote: > > On Fri, 2015-09-04 at 01:54 +0200, Luis R. Rodriguez wrote: > > > On Thu, Sep 03, 2015 at 05:21:14PM -0600, Toshi Kani wrote: > > > > On Fri, 2015-09-04 at 00:45 +0200, Luis R. Rodriguez wrote: > > > > > On Thu, Sep 03, 2015 at 04:25:31PM -0600, Toshi Kani wrote: > > : > > > > > > On Xen, > > > > >=20 > > > > > When Xen is used a platform firmware may still set up MTRR, e= ven if=20 > > > > > the hypervisor doesn't set up MTRR right ? So same issue and=20 > > > > > question here. > > > >=20 > > > > Right, I meant to say Xen guests. > > >=20 > > > Ah but its import complicated than that. > > >=20 > > > > In case of the Xen hypervisor, > > > > mtrr_type_lookup() returns a valid type as it runs on a platfor= m. > > >=20 > > > I am not sure if this happens today, I know MTRR is simply disabl= ed by > > > the Xen Hypervisor on the CPU explicitly, it disable it so guests= =20 > > > reading the MTRR capabilities sees it as disabled when queried. > >=20 > > Oh, I would not let the hypervisor to disable MTRRs... >=20 > Commit 586ab6a055376ec3f3e1e8 ("x86/pvh: disable MTRR feature on cpui= d for=20 > Dom0") by Roger Pau Monn=C3=A9 disables MTRR for PVH dom0, so that cp= uid returns=20 > that MTRR is disabled to guests.=20 Oh, I see. It just clears the capability bit so that the kernel thinks= MTRRs are disabled. That makes sense. > Then later on Linux as of commit 47591df50512 ("xen: Support Xen pv-d= omains > using PAT") added by Juergen as of v3.19 Linux guests can end up boot= ing > without MTRR but with PAT now enabled. Nice! > > > Then since the Xen Linux guests cannot speak MTRR through the hyp= ervisor > > > (for instance Xen guests cannot ask Xen hypervisor to mtrr_type_l= ookup()=20 > > > for it) if PCI passthrough is used it could mean a guest might se= t up /=20 > > > use incorrect info as well. > > >=20 > > > If I undestand this correctly then I think we're in a pickle with= Xen=20 > > > unless we add hypervisor support and hypercall support for > > > mtrr_type_lookup(). > >=20 > > I was under assumption that MTRRs are emulated and disabled on gues= ts. >=20 > Some "special" flavor Linux guests (with non-upstream code) have gues= t > MTRR hypercall support, for vanilla Xen and Linux they just never get= MTRR > support. After Juergen's Linux changes though Xen guests can now get > shiny PAT support. Since MTRR hypercall support is not upstream and M= TRR is > ancient I decided instead of adding MTRR hypercall support upstream t= o go=20 > with converting all drivers to PAT interfaces, with the assumption th= ere=20 > would be no issues. >=20 > > Isn't guest physical address virtualized? >=20 > It is, there is a xen iotlb and stuff but that should ensure dom0 get= s > to get proper access to devices, and if you use PCI passthrough you w= ant > the best experience as well. >=20 > > I know other proprietary VMMs on IA64, but know nothing about Xen..= =2E So,=20 > > please disregard my comments to Xen. :-) >=20 > No worries, no one knows all the answers, we work together to remove > cob webs off of these odd corners no one cares about :) Thanks for all the info! That helps. -Toshi