From mboxrd@z Thu Jan 1 00:00:00 1970 From: Konrad Rzeszutek Wilk Subject: Re: Regression with Xen 4.4 when booting with AMD IOMMU on TA890FXE BIOSTAR Date: Thu, 19 Dec 2013 21:43:12 -0500 Message-ID: <20131220024312.GI25322@phenom.dumpdata.com> References: <20131219182519.GA6479@pegasus.dumpdata.com> <52B33D32.1080101@citrix.com> <20131219185211.GA8224@andromeda.dapyr.net> <52B3626B.7050607@oracle.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Received: from mail6.bemta3.messagelabs.com ([195.245.230.39]) by lists.xen.org with esmtp (Exim 4.72) (envelope-from ) id 1Vtq3n-0006C9-CW for xen-devel@lists.xenproject.org; Fri, 20 Dec 2013 02:43:31 +0000 Content-Disposition: inline In-Reply-To: <52B3626B.7050607@oracle.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: Boris Ostrovsky Cc: Konrad Rzeszutek Wilk , xen-devel@lists.xenproject.org, jbeulich@suse.com, suravee.suthikulpanit@amd.com, Andrew Cooper List-Id: xen-devel@lists.xenproject.org > >(XEN) AMD-Vi: per-device vector map logic is broken. Using per-device-global maps instead until a fix is found. > > Looks like IOAPIC definition is missing from IVRS. The one that's > listed (0000:00:00.1 variety 0x1 handle 0x6) is usually unused IIRC. > I'd expect an entry for the second one (that lives on the > southbridge), such as > AMD-Vi: IVHD Special: 0000:00:14.0 variety 0x1 handle 0 > > And page faults that you are seeing may also be related to this > since 0xa0 is 00:14.0. > > BIOS update might help with this problem (looks like Biostar has a > newer BIOS for this board) but I think this should be fixed so maybe > you want to keep this BIOS until a fix is developed. OK. > > You could try booting with iommu=no-intremap to work around this in > the meantime. That did make it boot. Thanks!