From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752788AbdHGJhd (ORCPT ); Mon, 7 Aug 2017 05:37:33 -0400 Received: from mx1.redhat.com ([209.132.183.28]:37414 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752367AbdHGJhc (ORCPT ); Mon, 7 Aug 2017 05:37:32 -0400 DMARC-Filter: OpenDMARC Filter v1.3.2 mx1.redhat.com 772C4C047B6B Authentication-Results: ext-mx07.extmail.prod.ext.phx2.redhat.com; dmarc=none (p=none dis=none) header.from=redhat.com Authentication-Results: ext-mx07.extmail.prod.ext.phx2.redhat.com; spf=fail smtp.mailfrom=david@redhat.com Subject: Re: [PATCH RESEND] mm: don't zero ballooned pages To: Michal Hocko Cc: Wei Wang , linux-kernel@vger.kernel.org, linux-mm@kvack.org, virtualization@lists.linux-foundation.org, mst@redhat.com, zhenwei.pi@youruncloud.com, dave.hansen@intel.com, akpm@linux-foundation.org, mawilcox@microsoft.com, Andrea Arcangeli References: <1501761557-9758-1-git-send-email-wei.w.wang@intel.com> <9ac31505-0996-2822-752e-8ec055373aa0@redhat.com> <20170807092525.GE32434@dhcp22.suse.cz> From: David Hildenbrand Organization: Red Hat GmbH Message-ID: <8b862c93-1a9f-9247-8401-5092cc35a857@redhat.com> Date: Mon, 7 Aug 2017 11:37:26 +0200 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101 Thunderbird/52.2.1 MIME-Version: 1.0 In-Reply-To: <20170807092525.GE32434@dhcp22.suse.cz> Content-Type: text/plain; charset=utf-8 Content-Language: en-US Content-Transfer-Encoding: 7bit X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.31]); Mon, 07 Aug 2017 09:37:32 +0000 (UTC) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org > Maybe it is my absolute lack of familiarity with what the host actually > does with balloon pages but I fail to see why the above matters at all. > ksm will not try to merge sub page units (4k for hugetlb or a large base > page). And if you need to hide the guest contents then the host can > clear the respective subpage just fine. So could you be more explicit > why MADV_DONTNEED matters at all? Also does any host actually share sub > pages between different guests? This sounds like a bad idea to me in > general. > Okay, I think I got the issue wrong. I thought that the original patch tried to also fix a corner case where the guest would assume that it would get supplied zero pages afterwards. Please ignore the noise. :) -- Thanks, David