From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail.linutronix.de (146.0.238.70:993) by crypto-ml.lab.linutronix.de with IMAP4-SSL for ; 14 Jan 2019 19:31:35 -0000 Received: from mga04.intel.com ([192.55.52.120]) by Galois.linutronix.de with esmtps (TLS1.2:DHE_RSA_AES_256_CBC_SHA256:256) (Exim 4.80) (envelope-from ) id 1gj7xN-000417-Qw for speck@linutronix.de; Mon, 14 Jan 2019 20:31:34 +0100 Date: Mon, 14 Jan 2019 11:31:31 -0800 From: Andi Kleen Subject: [MODERATED] Re: [PATCH v4 05/28] MDSv4 10 Message-ID: <20190114193131.GG6118@tassilo.jf.intel.com> References: <021c5ba2a9fdae326058dd16785b30c31546cd0f.1547256470.git.ak@linux.intel.com> <1ce79648-6263-d726-bb69-da54131535a2@intel.com> MIME-Version: 1.0 In-Reply-To: <1ce79648-6263-d726-bb69-da54131535a2@intel.com> Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit To: speck@linutronix.de List-ID: > > + clear_cpu_idle(); > > + > > mwait_idle_with_hints(eax, ecx); > > And my like bikeshed: It seems like this would be a much smaller patch, > and be less likely to have future code add vulnerabilities if we just > patched mwait_idle_with_hints(). I had this originally, but it caused some issues. For me it seems also unclean to pollute a low level "maps to an instruction" inline with such functionality. -Andi