Quoting Kukjin Kim (2013-08-17 03:30:11)

Tomasz Figa wrote:

[...]

quoted

quoted

quoted

quoted

quoted

Basically, this series looks good to me, but I'm not sure how this
should be handled because of dependency with PWM cleanup and clk
stuff
in clk tree now...

Patches 1-3 can go into the clk tree. 4-6 should go through their
respective trees.

It looks like version 2 of patch 2/8 has been applied by mistake,
breaking compilation (and operation) of the clock driver added in
patch 3/8.

Ugh. My mistake.

Happens. Thanks for fast response.

Sorry for late ;-)

quoted

quoted

quoted

Could you please fix this up? Thanks in advance.

This is a little tricky since I published the clk-next-s3c64xx branch as
a stable branch for Samsung which I think has been merged to the
Samsung tree already.

Right, this somewhat limits our options. Although I'm not really sure
whether Kukjin already has pushed it to his public tree.

Yeah, I already did sort out in my local but not public tree because of some
problem.

quoted

quoted

So what are the options?

One option is to create a fixup patch that just manages the delta
between V2 and V3. I can then add this to the top of clk-next-s3c64xx
and re-merge it into clk-next. Then the Samsung tree will need to
re-merge that dependency branch.

Well, I can make a "convert PLL65xx to new registration method" patch,
that would be basically the delta. If this could be merged before patch
7/8, no regression would be introduced.

quoted

Do you have a better idea?

Not really. Maybe let's ask Kukjin whether he has already merged it to his
tree. Kukjin, have you?

OK, if new branch is ready, I will replace with that or if re-merge is
required, I will. Either way, I'm fine and can handle. Mike, let me know
your choice :-)

Since I have already published it let's just go with the delta patch.  I
can create another stable branch named clk-next-s3c64xx-delta that just
has this patch on top of clk-next-s3c64xx OR I can apply it on top of
the existing clk-next-s3c64xx and re-merge it.

I'm trying to think on whether there are any weird git corner cases with
re-merging clk-next-s3c64xx. Let me know if re-merging is somehow unsafe
(makes history weird, or whatever).

Let me know what option is better for you. I'll publish as soon as I get
the delta patch. Apologies again for creating some extra work!

Thanks,
Mike

Thanks,
Kukjin