From mboxrd@z Thu Jan  1 00:00:00 1970
From: Peter Zijlstra <peterz@infradead.org>
Subject: Re: [PATCH 08/13] xen/pvticketlock: disable interrupts
 while blocking
Date: Sat, 03 Sep 2011 00:37:07 +0200
Message-ID: <1315003027.10110.2.camel@twins>
References: <cover.1314922370.git.jeremy.fitzhardinge@citrix.com>
	<38bb37e15f6e5056d5238adac945bc1837a996ec.1314922370.git.jeremy.fitzhardinge@citrix.com>
	<1314974826.1861.1.camel@twins> <4E612EA1.20007@goop.org>
	<1314996468.8255.0.camel@twins> <4E614FBD.2030509@goop.org>
Mime-Version: 1.0
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Return-path: <xen-devel-bounces@lists.xensource.com>
In-Reply-To: <4E614FBD.2030509@goop.org>
List-Unsubscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>,
	<mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe>
List-Post: <mailto:xen-devel@lists.xensource.com>
List-Help: <mailto:xen-devel-request@lists.xensource.com?subject=help>
List-Subscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>,
	<mailto:xen-devel-request@lists.xensource.com?subject=subscribe>
Sender: xen-devel-bounces@lists.xensource.com
Errors-To: xen-devel-bounces@lists.xensource.com
To: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Xen Devel <xen-devel@lists.xensource.com>, Marcelo Tosatti <mtosatti@redhat.com>, Nick Piggin <npiggin@kernel.dk>, KVM <kvm@vger.kernel.org>, Stefano Stabellini <stefano.stabellini@eu.citrix.com>, maintainers <x86@kernel.org>, Linux Kernel Mailing List <linux-kernel@vger.kernel.org>, Andi Kleen <andi@firstfloor.org>, Avi Kivity <avi@redhat.com>, Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>, "H. Peter Anvin" <hpa@zytor.com>, Ingo Molnar <mingo@elte.hu>, Linus Torvalds <torvalds@linux-foundation.org>, the
List-Id: xen-devel@lists.xenproject.org

On Fri, 2011-09-02 at 14:50 -0700, Jeremy Fitzhardinge wrote:
> On 09/02/2011 01:47 PM, Peter Zijlstra wrote:
> > On Fri, 2011-09-02 at 12:29 -0700, Jeremy Fitzhardinge wrote:
> >>> I know that its generally considered bad form, but there's at least o=
ne
> >>> spinlock that's only taken from NMI context and thus hasn't got any
> >>> deadlock potential.
> >> Which one?=20
> > arch/x86/kernel/traps.c:nmi_reason_lock
> >
> > It serializes NMI access to the NMI reason port across CPUs.
>=20
> Ah, OK.  Well, that will never happen in a PV Xen guest.  But PV
> ticketlocks are equally applicable to an HVM Xen domain (and KVM guest),
> so I guess there's at least some chance there could be a virtual
> emulated NMI.  Maybe?  Does qemu do that kind of thing?

Afaik qemu/kvm can do the whole NMI thing, yes.

> But, erm, does that even make sense?  I'm assuming the NMI reason port
> tells the CPU why it got an NMI.  If multiple CPUs can get NMIs and
> there's only a single reason port, then doesn't that mean that either 1)
> they all got the NMI for the same reason, or 2) having a single port is
> inherently racy?  How does the locking actually work there?

I really wouldn't know, the whole NMI thing is a bit of a trainwreck
architecturally. Maybe the x86 maintainers or Linus knows more on this
aspect of it.