From mboxrd@z Thu Jan 1 00:00:00 1970 From: Keir Fraser Subject: Re: use tasklet to handle init/sipi? Date: Thu, 28 Mar 2013 20:02:29 +0000 Message-ID: References: <51546FFF02000078000C95C2@nat28.tlf.novell.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <51546FFF02000078000C95C2@nat28.tlf.novell.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Jan Beulich Cc: Yang Z Zhang , Shuang Qiu , SongtaoX Liu , Xiantao Zhang , "xen-devel@lists.xen.org" List-Id: xen-devel@lists.xenproject.org On 28/03/2013 15:29, "Jan Beulich" wrote: >>>> On 28.03.13 at 12:48, Keir Fraser wrote: >> On 28/03/2013 06:39, "Qiu, Shuang" wrote: >>> We've patched the enclosed file on xen-unstable and tested on qemu.git and >>> qemu-upstream-unstable.git as backends. >>> In both cases, your patch works. >> >> Thanks for the testing! I have now committed my patch. > > Question now is - do we want this on the stable trees (once it > passed the push gate of course), despite APIC virtualization > (which triggered this) isn't in anything pre-4.3? There are possibly other ways in which an INIT or SIPI could be broadcast/multicast and not be properly handled -- hvm_x2apic_msr_write()? vlapic_ipi() via the Viridian MSRs? I think it's fairly theoretical risk though! Overall I would be inclined not to backport. -- Keir > Jan >