From mboxrd@z Thu Jan 1 00:00:00 1970 From: Joerg Roedel Subject: Re: BUG: unable to handle kernel paging request with v4.3-rc4 Date: Fri, 9 Oct 2015 17:34:40 +0200 Message-ID: <20151009153440.GE27420@8bytes.org> References: <20151009145827.GB27420@8bytes.org> <1444404640.4059.219.camel@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Cc: iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org, linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, kvm-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: Alex Williamson Return-path: Content-Disposition: inline In-Reply-To: <1444404640.4059.219.camel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: iommu-bounces-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org Errors-To: iommu-bounces-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org List-Id: kvm.vger.kernel.org On Fri, Oct 09, 2015 at 09:30:40AM -0600, Alex Williamson wrote: > I have not seen this one yet. There literally have been no changes for > vfio in 4.3, so if this is new, it may be collateral from changes > elsewhere. 32bit devices really shouldn't make any difference to vfio, > I'll see if I can reproduce it myself though. Thanks, Great, thanks. It looks like some sort of memory corruption to me. What I did was trying to assign the 32bit dev together with its PCI bridge. Probing the bridge in VFIO fails due to the first check in the probe function and then I get the oops. I also tried assigning other bridges, or only the bridge to the 32bit bus, but this did not trigger the oops (but fails too, as it should). I'll also try to debug this more. Joerg