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 04:38:17 -0000 Received: from mga07.intel.com ([134.134.136.100]) by Galois.linutronix.de with esmtps (TLS1.2:DHE_RSA_AES_256_CBC_SHA256:256) (Exim 4.80) (envelope-from ) id 1giu0s-00031v-N6 for speck@linutronix.de; Mon, 14 Jan 2019 05:38:16 +0100 Date: Sun, 13 Jan 2019 20:38:08 -0800 From: Andi Kleen Subject: [MODERATED] Re: [PATCH v4 07/28] MDSv4 0 Message-ID: <20190114043808.GC6118@tassilo.jf.intel.com> References: <12f1a5725f437f45abfe455cd344e1c037a7de2c.1547256470.git.ak@linux.intel.com> <20190114040302.vv5oywwdpm3mwq5p@treble> MIME-Version: 1.0 In-Reply-To: <20190114040302.vv5oywwdpm3mwq5p@treble> Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit To: speck@linutronix.de List-ID: On Sun, Jan 13, 2019 at 10:03:02PM -0600, speck for Josh Poimboeuf wrote: > On Fri, Jan 11, 2019 at 05:29:20PM -0800, speck for Andi Kleen wrote: > > From: Andi Kleen > > Subject: x86/speculation/mds: Support mds=full for NMIs > > > > NMIs don't go through C code when exiting to user space > > What about do_nmi()? NMIs = any NMI like exception, like machine check. Yes they could be all handled in C, but it seems simpler to just do it once in assembler. -Andi