From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755169Ab3LUPfl (ORCPT ); Sat, 21 Dec 2013 10:35:41 -0500 Received: from smtp.nue.novell.com ([195.135.221.5]:33902 "EHLO smtp.nue.novell.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753143Ab3LUPfj (ORCPT ); Sat, 21 Dec 2013 10:35:39 -0500 Subject: Re: [RFC PATCH 06/14] rtc-efi: register rtc-efi device when EFI enabled From: joeyli To: "H. Peter Anvin" Cc: Matthew Garrett , "bp@alien8.de" , "samer.el-haj-mahmoud@hp.com" , "linux-kernel@vger.kernel.org" , "tglx@linutronix.de" , "a.zummo@towertech.it" , "Elliott@hp.com" , "werner@suse.com" , "rtc-linux@googlegroups.com" , "x86@kernel.org" , "rjw@rjwysocki.net" , "mingo@redhat.com" , "oneukum@suse.de" , "linux-efi@vger.kernel.org" , "trenn@suse.de" , "matt.fleming@intel.com" , "JBeulich@suse.com" , "linux-acpi@vger.kernel.org" , "matt@console-pimps.org" In-Reply-To: <52B4F421.2000403@zytor.com> References: <1387439515-8926-1-git-send-email-jlee@suse.com> <1387439515-8926-7-git-send-email-jlee@suse.com> <20131219140918.GF3145@console-pimps.org> <1387513491.3539.4345.camel@linux-s257.site> <52B3C7F8.3040901@zytor.com> <20131220103755.GA14784@pd.tnic> <1387552463.17961.2.camel@x230> <52B4B0ED.7030600@zytor.com> <1387589042.3539.4901.camel@linux-s257.site> <52B4F421.2000403@zytor.com> Content-Type: text/plain; charset="UTF-8" Date: Sat, 21 Dec 2013 23:34:08 +0800 Message-ID: <1387640048.3539.5760.camel@linux-s257.site> Mime-Version: 1.0 X-Mailer: Evolution 2.28.2 Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 於 五，2013-12-20 於 17:51 -0800，H. Peter Anvin 提到： > On 12/20/2013 05:24 PM, joeyli wrote: > > 於 五，2013-12-20 於 13:04 -0800，H. Peter Anvin 提到： > >> > >> Actually, it doesn't have to reprogram the clock ... it just needs to > >> know if another OS has already done so. All Linux needs to do is to be > >> able to derive UTC from whatever the RTC is set to and to be able to > >> keep it consistent. > >> > > > > It's dependent on a right boot initial priority of distribution. > > -ENOPARSE > > > Here have a discussion of adjusting system clock by TZ (from ACPI or > > UEFI): > > Discussion on BIOS/CMOS/UEFI clock in local time > > http://www.spinics.net/lists/util-linux-ng/msg07639.html > > > > and, > > from Ted Ts'o in the mail thread > > https://lkml.org/lkml/2008/1/8/195 > > > > If kernel use the TZ field from ACPI TAD or EFI to adjust system > > clock when booting, then it can avoid buggy distributions adjust > > system clock AFTER e2fsck is run. > > > > Using ACPI TAD should after DSDT parsing in subsystem initial stage, > > so I choice EFI time services before we can move DSDT parser to > > start_kernel(). > > > > Yes, of course. That is irrelevant to needing to reprogram the clock, > though. > > My argument is very simple: if we have to rely on EFI, we can get the > offset in the boot stub before ExitBootServices(), and then simply never > change it. That way we still pick up if another operating system has > changed it, and it will still reflect the proper UTC time. > > -hpa > OK, I will add this part to next version for the UEFI system doesn't have ACPI TAD. Thanks for your suggestion! Joey Lee