Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751854AbeADAbS (ORCPT + 1 other); Wed, 3 Jan 2018 19:31:18 -0500 Received: from lang.hm ([66.167.227.134]:33013 "EHLO bifrost.lang.hm" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751615AbeADAbR (ORCPT ); Wed, 3 Jan 2018 19:31:17 -0500 X-Greylist: delayed 714 seconds by postgrey-1.27 at vger.kernel.org; Wed, 03 Jan 2018 19:31:17 EST Date: Wed, 3 Jan 2018 16:18:39 -0800 (PST) From: David Lang X-X-Sender: dlang@asgard.lang.hm To: Andi Kleen cc: Linus Torvalds , tglx@linutronix.de, Greg Kroah-Hartman , dwmw@amazon.co.uk, Tim Chen , Linux Kernel Mailing List , Dave Hansen Subject: Re: Avoid speculative indirect calls in kernel In-Reply-To: <20180104000927.co5umvfzfwliqvqt@two.firstfloor.org> Message-ID: References: <20180103230934.15788-1-andi@firstfloor.org> <20180104000927.co5umvfzfwliqvqt@two.firstfloor.org> User-Agent: Alpine 2.02 (DEB 1266 2009-07-14) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Return-Path: On Wed, 3 Jan 2018, Andi Kleen wrote: >> >> Why is this all done without any configuration options? > > I was thinking of a config option, but I was struggling with a name. > > CONFIG_INSECURE_KERNEL, CONFIG_LEAK_MEMORY? CONFIG_BUGGY_INTEL_CACHE (or similar) something that indicates that this is to support the Intel CPUs that have this bug in them. We've had such CPU specific support options in the past. Some people will need the speed more than the protection, some people will be running on CPUs that don't need this. Why is this needed? because of an Intel bug, so name it accordingly. David Lang