From mboxrd@z Thu Jan 1 00:00:00 1970 From: Julien Grall Subject: Re: [PATCH] xen/arm: Scrub heap pages during boot Date: Fri, 10 Jan 2014 13:48:12 +0000 Message-ID: <52CFFA1C.7000500@linaro.org> References: <1389324476-9158-1-git-send-email-julien.grall@linaro.org> <1389347521.19142.9.camel@kazak.uk.xensource.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; Format="flowed" Content-Transfer-Encoding: 7bit Return-path: Received: from mail6.bemta4.messagelabs.com ([85.158.143.247]) by lists.xen.org with esmtp (Exim 4.72) (envelope-from ) id 1W1cRc-0004u1-HB for xen-devel@lists.xenproject.org; Fri, 10 Jan 2014 13:48:16 +0000 Received: by mail-wi0-f179.google.com with SMTP id z2so4843702wiv.12 for ; Fri, 10 Jan 2014 05:48:14 -0800 (PST) In-Reply-To: <1389347521.19142.9.camel@kazak.uk.xensource.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Ian Campbell Cc: xen-devel@lists.xenproject.org, tim@xen.org, stefano.stabellini@citrix.com, patches@linaro.org List-Id: xen-devel@lists.xenproject.org On 01/10/2014 09:52 AM, Ian Campbell wrote: > On Fri, 2014-01-10 at 03:27 +0000, Julien Grall wrote: >> Scrub heap pages was disabled because it was slow on the models. Now that Xen >> supports real hardware, it's possible to enable by default scrubbing. >> >> Signed-off-by: Julien Grall > > Acked-by: Ian Campbell Thanks. >> --- >> This patch should go to Xen 4.4. It avoid to give non-cleared page to >> a domain. >> >> The downside is it's now slow on models. > > There is a no-bootscrub command-line option which can be used in that > case. Could you update the relevant model wiki pages to mention it > please? I have updated the wiki page. > >> The current implementation of scrub_heap_pages loop on every page in the >> frametable. On ARM, there is only which can contains MMIO. We are safe >> because when frametable is initialized, page are marked inuse. So the >> function won't clear theses pages. > > I don't think this behaviour is specific to ARM, x86 has MMIO regions > mixed in with RAM as well. I was not sure, so I prefered to explain why it's ok. -- Julien Grall