From mboxrd@z Thu Jan 1 00:00:00 1970 From: Weidong Han Subject: Re: Xen 4.0.0-rc7 problem/hang with vt-d DMAR parsing Date: Wed, 24 Mar 2010 08:40:16 +0800 Message-ID: <4BA95F70.8080904@intel.com> References: <20100323193748.GW1878@reaktio.net> <20100323200515.GZ1878@reaktio.net> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: quoted-printable Return-path: In-Reply-To: <20100323200515.GZ1878@reaktio.net> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com To: =?ISO-8859-1?Q?Pasi_K=E4rkk=E4inen?= Cc: "xen-devel@lists.xensource.com" , Keir Fraser List-Id: xen-devel@lists.xenproject.org Pasi K=E4rkk=E4inen wrote: > On Tue, Mar 23, 2010 at 07:54:33PM +0000, Keir Fraser wrote: > =20 >> On 23/03/2010 19:37, "Pasi K=E4rkk=E4inen" wrote: >> >> =20 >>>> It's not impossible that the BIOS VT-d support is just broken (I ass= ume >>>> you've never tested VT-d on this particular type of system before). >>>> =20 >>> Yeah, I've never used VT-d on this system earlier, so it could just b= e broken >>> BIOS. >>> I guess Xen still shouldn't hang on it? >>> =20 >> We'd prefer to gracefully disable VT-d. >> >> =20 > > 4.0.0-rc7 (without any extra cmdline options) does disable vt-d and boo= t ok,=20 > after 'hanging' for 30 seconds while parsing the DMAR tables. > > If I add "iommu=3Dverbose" option for Xen, then it'll print huge amount= of stuff=20 > like I pasted earlier.. and it takes forever to print all that. > =20 The BIOS is likely broken. Could you dump the ACPI tables? Then we can=20 confirm if it's BIOS issue. Maybe we can cook a patch to detect this=20 issue (dmaru->address =3D=3D 0), and handle it more gracefully. I will ha= ve=20 a look at it. Regards, Weidong. > Hmm.. wondering if the patch Jan just sent will help with that.=20 > Sounds like it might help :) > > -- Pasi > > =20