From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:36476) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1bLGSB-0001D0-Ko for qemu-devel@nongnu.org; Thu, 07 Jul 2016 17:03:24 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1bLGS6-0008Oe-LO for qemu-devel@nongnu.org; Thu, 07 Jul 2016 17:03:22 -0400 Received: from mx1.redhat.com ([209.132.183.28]:49620) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1bLGS6-0008OA-Ew for qemu-devel@nongnu.org; Thu, 07 Jul 2016 17:03:18 -0400 Date: Thu, 7 Jul 2016 15:03:16 -0600 From: Alex Williamson Message-ID: <20160707150316.0a715b82@t450s.home> In-Reply-To: <20160707203415.17948.81896.malone@wampee.canonical.com> References: <20160511061916.21125.98809.malonedeb@wampee.canonical.com> <20160707203415.17948.81896.malone@wampee.canonical.com> MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [Bug 1580459] Re: Windows (10?) guest freezes entire host on shutdown if using PCI passthrough List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org, me@clifhouck.com Cc: Bug 1580459 <1580459@bugs.launchpad.net> On Thu, 07 Jul 2016 20:34:15 -0000 Clif Houck wrote: > I was also experiencing the host hard locking when shutting down a > Windows 10 guest with a Nvidia GPU passed-through, but the issue appears > to be completely solved after switching the card to MSI mode in the > Windows guest. > > However, I would be interested in understanding *why* using the card in > line-interrupt mode in the guest causes the host to lockup when the > guest relinquishes control of the device. Is it a bug in qemu or vfio, > or even the Linux kernel? > > I don't know if its relevant, but I've noticed when the card is not > being used by the guest it is listed as MSI: Enable- by lspci, > suggesting that vfio is keeping the card in line-interrupt mode when not > in use. > Interrupts are disabled when the card is not in use. Can you test whether the following commit fixes the problem: http://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=956b56a984ddf10aa69b25318dc04430101beed6 This was added in v4.7-rc2, so it will also be included in anything newer. Thanks, Alex