From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756247Ab3JGRYN (ORCPT ); Mon, 7 Oct 2013 13:24:13 -0400 Received: from terminus.zytor.com ([198.137.202.10]:57871 "EHLO mail.zytor.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751851Ab3JGRYL (ORCPT ); Mon, 7 Oct 2013 13:24:11 -0400 Message-ID: <5252EDBE.7030805@zytor.com> Date: Mon, 07 Oct 2013 10:22:06 -0700 From: "H. Peter Anvin" User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:17.0) Gecko/20130923 Thunderbird/17.0.9 MIME-Version: 1.0 To: Ingo Molnar CC: Peter Zijlstra , Adrian Hunter , linux-kernel@vger.kernel.org, tglx@linutronix.de, linux-tip-commits@vger.kernel.org Subject: Re: [tip:perf/core] perf/x86: Clean up cap_user_time* setting References: <524F097A.9010506@intel.com> <20131004185539.GT15690@laptop.programming.kicks-ass.net> <20131006091054.GA4342@gmail.com> In-Reply-To: <20131006091054.GA4342@gmail.com> X-Enigmail-Version: 1.5.2 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 10/06/2013 02:10 AM, Ingo Molnar wrote: >> >> I'm wanting to hear from the x86 people on why we have this absurd knob >> to begin with; but I'm tempted to simply disable all of perf if you >> touch it. > > I'm fully with you, please zap the 'notsc' boot option - it's an ancient > relic, if any box is still broken with the TSC on we want to hear about it > and fix it! > Perhaps better would be to make the notsc option do what other feature removal options do and just remove the CPU feature flag. Early on we had a bunch of ad hoc behaviors for feature disabling. They are harmful and just wrong... "not present" and "disabled" should be the same thing in 99% of all cases (in the case of the TSC one may wish to set the CR4 bit which disables the TSC from userspace, but I don't think "notsc" ever did that.) However: pr_warn("Kernel compiled with CONFIG_X86_TSC, cannot disable TSC completely\n"); That is a total "say what"? At one point it even said: printk(KERN_WARNING "notsc: Kernel compiled with CONFIG_X86_TSC, " "cannot disable TSC.\n"); CONFIG_X86_TSC is a baseline control option; we shouldn't key functionality off of it. It's fine to say notsc -> no tracing, but making it a compile-time key makes me a bit uphappy. We cut off 386, but cutting of 486 at this point makes me nervous. -hpa