Return-Path: Received: from mail.linutronix.de (146.0.238.70:993) by crypto-ml.lab.linutronix.de with IMAP4-SSL for ; 10 Jan 2019 16:05:07 -0000 Received: from mga06.intel.com ([134.134.136.31]) by Galois.linutronix.de with esmtps (TLS1.2:DHE_RSA_AES_256_CBC_SHA256:256) (Exim 4.80) (envelope-from ) id 1ghcpN-0007zI-Bp for speck@linutronix.de; Thu, 10 Jan 2019 17:05:06 +0100 Date: Thu, 10 Jan 2019 08:05:01 -0800 From: Andi Kleen Subject: [MODERATED] Re: [PATCH v3 00/32] MDSv3 12 Message-ID: <20190110160501.GY6118@tassilo.jf.intel.com> References: <20190109181455.GU6118@tassilo.jf.intel.com> MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit To: speck@linutronix.de List-ID: On Thu, Jan 10, 2019 at 07:01:21AM +0100, speck for Jiri Kosina wrote: > On Wed, 9 Jan 2019, speck for Andi Kleen wrote: > > > The case that worried me is that with this we would end up with some > > systems which are actually protected, but report vulnerable. > > > > So you could not simply say > > > > "If the sysfs file says you're vulnerable you're vulnerable" > > > > but would need > > > > "If the sysfs file says you're vulnerable, you're vulnerable except > > > vmware and other hyper visor versions>" > > > > Doesn't seem like a clear message for me. > > Please see what I did for Meltdown and XenPV in commit 6cb2b08ff92. I > believe something similar could be easily used there. This is different because it doesn't require para virtualization. For paravirtualization we are guaranteed that Linux knows all cases and can enumerate them, and yes with that it's possible to add ifs for the specific cases. But VERW is not paravirtualized. But for a non PV hypervisor there is no guarantee Linux even knows about all the HyperVisors in existence (undoubtedly there are many about which Linux has no clue of) I don't think this is a scalable solution. -Andi