Re: [RFC PATCH 06/14] rtc-efi: register rtc-efi device when EFIenabled

[joeyli]

æ äï2013-12-20 æ 17:51 -0800ïH. Peter Anvin æåï
> On 12/20/2013 05:24 PM, joeyli wrote:
> > æ äï2013-12-20 æ 13:04 -0800ïH. Peter Anvin æåï
> >>
> >> 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

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/