[PATCH v2] clk: sunxi: fix sun6i PLL1 .recalc_rate() result

[Mike Turquette]

Quoting Chen-Yu Tsai (2015-01-27 22:19:22)
> On Wed, Jan 28, 2015 at 2:41 AM, Mike Turquette <mturquette at linaro.org> wrote:
> > Quoting Maxime Ripard (2015-01-24 07:29:44)
> >> Hi Mike,
> >>
> >> On Sat, Jan 24, 2015 at 04:42:39PM +0800, Chen-Yu Tsai wrote:
> >> > PLL1 on sun6i has its N factor start from 1 (N = register value + 1).
> >> > Make the factors clk driver aware of this so clk_factors_recalc_rate()
> >> > gives the correct result.
> >> >
> >> > Cc: <stable at vger.kernel.org> # 3.12 9a5e6c7eb5cc clk: sunxi: Support factor
> >> > Cc: <stable at vger.kernel.org> # 3.12
> >> > Signed-off-by: Chen-Yu Tsai <wens at csie.org>
> >>
> >> Could you queue this for 3.19?
> >
> > This is fixed in 76820fc in clk-next, destined for 3.20.
> >
> > Also I'm confused by the stable tags above. Looks like 9a5e6c7eb5cc was
> > merged for 3.16, not 3.12.
> 
> I think so. I wasn't quite sure what the version number was
> supposed to be, the first version it is applicable? or the
> first version the specific patch was merged.

Chen-Yu,

I think that struct clk_factors_config did not have the n_start member
before 9a5e6c7eb5cc, so this patch could not apply without 9a5e6c7eb5cc.
That's from memory though, and I might be mis-remembering.

The fix is not for a new regression, thus it is going into 3.20 and I am
remiss to rebase my tree to add a stable tag. Can you submit this to
stable yourself after 3.20-rc1? I think the proper thing to do is to
reference this patch and the commitlog to show that it was fixed
upstream.

Regards,
Mike

> 
> ChenYu
> 
> >>
> >> Thanks,
> >> Maxime
> >>
> >> --
> >> Maxime Ripard, Free Electrons
> >> Embedded Linux, Kernel and Android engineering
> >> http://free-electrons.com