Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752228AbdLFMv2 (ORCPT ); Wed, 6 Dec 2017 07:51:28 -0500 Received: from bombadil.infradead.org ([65.50.211.133]:46389 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751546AbdLFMv0 (ORCPT ); Wed, 6 Dec 2017 07:51:26 -0500 Date: Wed, 6 Dec 2017 13:51:14 +0100 From: Peter Zijlstra To: Jan Dakinevich Cc: linux-kernel@vger.kernel.org, "Denis V . Lunev" , Roman Kagan , Ingo Molnar , Arnaldo Carvalho de Melo , Alexander Shishkin , Jiri Olsa , Namhyung Kim , Thomas Gleixner , "H. Peter Anvin" , x86@kernel.org, Paolo Bonzini , Radim =?utf-8?B?S3LEjW3DocWZ?= , Andi Kleen , Kan Liang , Stephane Eranian , Zhou Chengming , Sebastian Andrzej Siewior , Colin King , Greg Kroah-Hartman , Jin Yao , kvm@vger.kernel.org Subject: Re: [PATCH RFC 1/2] perf/x86/intel: make reusable LBR initialization code Message-ID: <20171206125114.jfp56mhmvbugqpan@hirez.programming.kicks-ass.net> References: <1512560585-27263-1-git-send-email-jan.dakinevich@virtuozzo.com> <1512560585-27263-2-git-send-email-jan.dakinevich@virtuozzo.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1512560585-27263-2-git-send-email-jan.dakinevich@virtuozzo.com> User-Agent: NeoMutt/20170609 (1.8.3) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 763 Lines: 16 On Wed, Dec 06, 2017 at 02:43:02PM +0300, Jan Dakinevich wrote: > This patch introduces globally visible intel_pmu_lbr_fill() routine, > which gathers information which LBR MSRs are support for specific CPU > family/model. > > It is supposed that the routine would be used in KVM code, using guest > CPU information as an input. By this reason, it should not have any side > effect which could affect host system. > > * LBR information moved to separate structure `struct x86_pmu_lbr'; > * All family-specific tweaks on gathered information are applied only > for global x86_pmu.lbr to keep current perf initialization behavior. > > Signed-off-by: Jan Dakinevich Hurch, that's a lot of churn. Nothing bad stood out though.