From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752415AbaHTQDl (ORCPT ); Wed, 20 Aug 2014 12:03:41 -0400 Received: from mx1.redhat.com ([209.132.183.28]:41251 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751438AbaHTQDj (ORCPT ); Wed, 20 Aug 2014 12:03:39 -0400 Message-ID: <53F4C6D2.9050209@redhat.com> Date: Wed, 20 Aug 2014 18:03:30 +0200 From: Paolo Bonzini User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:24.0) Gecko/20100101 Thunderbird/24.7.0 MIME-Version: 1.0 To: =?UTF-8?B?UmFkaW0gS3LEjW3DocWZ?= CC: kvm@vger.kernel.org, linux-kernel@vger.kernel.org, Gleb Natapov , Raghavendra KT , Vinod Chegu , Hui-Zhi Subject: Re: [PATCH 9/9] KVM: VMX: automatic PLE window maximum References: <1408480536-8240-1-git-send-email-rkrcmar@redhat.com> <1408480536-8240-10-git-send-email-rkrcmar@redhat.com> <53F44B40.6060806@redhat.com> <20140820124112.GC28873@potion.brq.redhat.com> <53F49F80.1090408@redhat.com> <20140820153115.GA20453@potion.brq.redhat.com> <53F4BFF3.3060606@redhat.com> <20140820160137.GB20453@potion.brq.redhat.com> In-Reply-To: <20140820160137.GB20453@potion.brq.redhat.com> Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Il 20/08/2014 18:01, Radim Krčmář ha scritto: > 2014-08-20 17:34+0200, Paolo Bonzini: >> Il 20/08/2014 17:31, Radim Krčmář ha scritto: >>> Btw. without extra code, we are still going to overflow on races when >>> changing PW_grow, should they be covered as well? >> >> You mean because there is no spinlock or similar protecting the changes? >> I guess you could use a seqlock. > > Yes, for example between a modification of ple_window > new = min(old, PW_actual_max) * PW_grow > which gets compiled into something like this: > 1) tmp = min(old, PW_actual_max) > 2) new = tmp * PW_grow > and a write to increase PW_grow > 3) PW_actual_max = min(PW_max / new_PW_grow, PW_actual_max) > 4) PW_grow = new_PW_grow > 5) PW_actual_max = PW_max / new_PW_grow > > 3 and 4 can exectute between 1 and 2, which could overflow. > > I don't think they are important enough to warrant a significant > performance hit of locking. A seqlock just costs two memory accesses to the same (shared) cache line as the PW data, and a non-taken branch. I don't like code that is unsafe by design... Paolo > Or even more checks that would prevent it in a lockless way. > > (I'd just see that the result is set to something legal and also drop > line 3, because it does not help things that much.) >