From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751919AbbJLKck (ORCPT ); Mon, 12 Oct 2015 06:32:40 -0400 Received: from mail-wi0-f178.google.com ([209.85.212.178]:35259 "EHLO mail-wi0-f178.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751415AbbJLKci (ORCPT ); Mon, 12 Oct 2015 06:32:38 -0400 Date: Mon, 12 Oct 2015 11:32:35 +0100 From: Matt Fleming To: "Luck, Tony" Cc: "Hansen, Dave" , Xishi Qiu , Kamezawa Hiroyuki , Taku Izumi , "linux-kernel@vger.kernel.org" , "linux-mm@kvack.org" , "mel@csn.ul.ie" , "akpm@linux-foundation.org" , Mel Gorman , Ingo Molnar , "zhongjiang@huawei.com" Subject: Re: [PATCH][RFC] mm: Introduce kernelcore=reliable option Message-ID: <20151012103235.GB2579@codeblueprint.co.uk> References: <1444402599-15274-1-git-send-email-izumi.taku@jp.fujitsu.com> <561762DC.3080608@huawei.com> <561787DA.4040809@jp.fujitsu.com> <5617989E.9070700@huawei.com> <5617D878.5060903@intel.com> <3908561D78D1C84285E8C5FCA982C28F32B523DB@ORSMSX114.amr.corp.intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <3908561D78D1C84285E8C5FCA982C28F32B523DB@ORSMSX114.amr.corp.intel.com> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, 09 Oct, at 06:51:34PM, Luck, Tony wrote: > > Current hardware can map one mirrored region from each memory controller. > We have two memory controllers per socket. So on a 4-socket machine we will > usually have 8 separate mirrored ranges. Two per NUMA node (assuming > cluster on die is not enabled). > > Practically I think it is safe to assume that any sane configuration will always > choose to mirror the <4GB range: > > 1) It's a trivial percentage of total memory on a system that supports mirror > (2GB[1] out of my, essentially minimal, 512GB[2] machine). So 0.4% ... why would > you not mirror it? > 2) It contains a bunch of things that you are likely to want mirrored. Currently > our boot loaders put the kernel there (don't they??). All sorts of BIOS space that > might be accessed at any time by SMI is there. Yeah, the bootloader and kernel image will most likely be in < 4GB region. That's not a hard requirement, and there's certainly support for loading things at higher addresses, but this low region is currently still preferred (see CONFIG_PHYSICAL_START). -- Matt Fleming, Intel Open Source Technology Center