Fwd: Re: [Xen-devel] [PATCH/RFC] Fix xsave bug on older Xen hypervisors

Stefan Bader stefan.bader at canonical.com
Thu Sep 13 08:33:43 UTC 2012

I will not get to this is week. But this basically means that we can drop any
xen work-around patches (even the ones I currently submitted for SRU) for
kernels after 2.6.38 (which was the time Xen kernel code changed in a way that
it would not test XSAVE capabilities by flipping the bit on in CR4 but looked at
the CPU feature bits and apparently this will work better).

The work-around is not harmful, so it will be ok to leave things in for this
stable cycle and then proceed in the next one. If there is a re-build required
for any other reason then the new work-around might be dropped, too (keeping the
revert of the old one). But I probably would not rush a re-build just for that.


-------- Original Message --------
Subject: Re: [Xen-devel] [PATCH/RFC] Fix xsave bug on older Xen hypervisors
Date: Mon, 10 Sep 2012 19:40:47 -0700
From: Matt Wilson <msw at amazon.com>
To: Justin M. Forbes <jmforbes at linuxtx.org>
CC: Linux Kernel Mailing List <linux-kernel at vger.kernel.org>,        Konrad
Rzeszutek Wilk <konrad.wilk at oracle.com>,        Stefan Bader
<stefan.bader at canonical.com>,        Jan Beulich <JBeulich at suse.com>,
xen-devel at lists.xen.org

On Fri, Sep 07, 2012 at 11:00:22AM -0500, Justin M. Forbes wrote:
> On Fri, 2012-09-07 at 16:44 +0100, Jan Beulich wrote:
> > 
> > All of this still doesn't provide evidence that a plain upstream
> > kernel is actually having any problems in the first place. Further,
> > if you say EC2 has a crippled hypervisor patch - is that patch
> > available for looking at somewhere?
> Yes, I can verify that a plain upstream kernel has problems in the first
> place, which is why we are carrying a patch to simply disable xsave all
> together in the pv guest.
> EC2 is not carrying a patch to cripple the hypervisor, there was an old
> xen bug that makes all this fail.  The correct fix for that bug is to
> patch the hypervisor, but they have not done so. Upstream xen has had
> the fix for quite some time, but that doesn't change the fact that a lot
> of xen guest usage these days is on EC2.  This is no different than
> putting in a quirk to work around a firmware bug in common use.

I've done some testing and have results that indicate otherwise. The
out-of-tree xen_write_cr4() patch is not needed as of 2.6.39. I tested
3.2.21 on a machine that has XSAVE capabilities:

[ec2-user at ip-10-160-18-80 ~]$ cpuid -1 -i | grep -i xsave/xstor
      XSAVE/XSTOR states                      = true
      OS-enabled XSAVE/XSTOR                  = false

on an older hypervisor build:

[ec2-user at ip-10-160-18-80 ~]$ cat /sys/hypervisor/version/major
[ec2-user at ip-10-160-18-80 ~]$ cat /sys/hypervisor/version/minor

and it boots without a problem. This patch correctly detects that the
hypervisor supports XSAVE by testing for OSXSAVE:

commit 947ccf9c3c30307b774af3666ee74fcd9f47f646
Author:     Shan Haitao <haitao.shan at intel.com>
AuthorDate: Tue Nov 9 11:43:36 2010 -0800
Commit:     Konrad Rzeszutek Wilk <konrad.wilk at oracle.com>
CommitDate: Wed Apr 6 08:31:13 2011 -0400

    xen: Allow PV-OPS kernel to detect whether XSAVE is supported

    Xen fails to mask XSAVE from the cpuid feature, despite not historically
    supporting guest use of XSAVE.  However, now that XSAVE support has been
    added to Xen, we need to reliably detect its presence.

    The most reliable way to do this is to look at the OSXSAVE feature in
    cpuid which is set iff the OS (Xen, in this case), has set


Xen-devel mailing list
Xen-devel at lists.xen.org

More information about the kernel-team mailing list