[PATCH 2/3] RTC: omap-rtc: enable pm_runtime

[Hiremath, Vaibhav]

On Mon, Oct 22, 2012 at 01:21:37, Daniel Mack wrote:
> On 19.10.2012 12:58, Mohammed, Afzal wrote:
> > Hi Daniel,
> > 
> > On Thu, Oct 18, 2012 at 22:03:13, Hiremath, Vaibhav wrote:
> >> On Thu, Oct 18, 2012 at 21:49:44, Daniel Mack wrote:
> >>> On 18.10.2012 18:12, Vaibhav Hiremath wrote:
> > 
> >>>> It would be really helpful if you could test these patches and ack them.
> > 
> >>> Ok, will do tomorrow. What's missing there is support for writing to the
> >>> OMAP_RTC_OSC_REG (path 3/3 in my series). Would like me to rebase the
> >>> functionality? I need thatkind of setup for my board ...
> > 
> >> This is bit tricky and required more discussion before merging it, 
> >> let me reopen the old discussion which I had started some time back -
> >>
> >>
> >> RTC OSC clock is required to configure clocksource systemtimer for the 
> >> kernel, and it is important when you get into PM related features.
> >>
> >> Please refer the below commit for more reference,
> >>
> >> http://marc.info/?l=u-boot&m=135057734713796&w=2
> > 
> > Newer version (v4) of omap rtc patches for am335x has been
> > posted, "rtc: omap dt support (for am33xx)".
> > In case you can test, please do it over the new series.
> > 
> > You would need also need DT patch that adds DT node to
> > test (it has been separated from the series as it is
> > felt that it should not be part of same series),
> > "arm/dts: am33xx rtc node"
> 
> Agreed. I tested your patches and they do basically the same thing than
> mine. You can take my
> 
>   Tested-by: Daniel Mack <zonque at gmail.com>
> 

Thanks Daniel for testing these patches.

> on all patches in this series except for 2/5 which I didn't test as I
> don't have any Davinci platform.
> 
> > If you are using mainline uboot, you would need the fix as
> > mentioned by Vaibhav H (as in the link he provided above),
> > expecting it to reach uboot mainline soon.
> > 
> > If the above is being attempted to achieve in Kernel it
> > would cause 2-3 seconds delay in boot time (else it had
> > to be made a module), please refer link provided by
> > Vaibhav H for more details.
> > 
> > else you can do in current mainline uboot,
> > 
> > mw.l 0x44e3e06c 0x83e70b13
> > mw.l 0x44e3e070 0x95a4f1e0
> > mw.b 0x44e3e054 0x48
> >
> > and then boot kernel.
> 
> I'm surprised that survives the kernel boot, but I'll give it a try. In
> case you want to add that logic to the kernel as well, please copy me in
> the discussion :)
> 
> 

Certainly...

Some background information for your reference,
We had some discussion in the past on this, and we decided to make this as a 
fallback mechanism considering following scenarios - 

 - System built with 32k crystal OSC, connected to RTC module

 - System without 32k crystal OSC, as RTC is not used.

 - Boot-Loader dependency for RTC clock enable (required for system-timer)

So the fallback mechanism would be something similar -

http://arago-project.org/git/projects/?p=linux-am33x.git;a=commit;h=58abec6ac010f4f8818caa4a52d16c4802e14acc


Thanks,
Vaibhav

> Thanks,
> Daniel
> 
>