Re: [PATCH 3/4] sh: remove superhyway bus support

Hi Arnd!

On Thu, 2023-08-03 at 11:19 +0200, Arnd Bergmann wrote:
> Applying this first should definitely help with the DT conversion,
> especially not having to create a bus specific binding for superhyway
> would help, as converting that to DT would be a complete rewrite
> but also be untestable without drivers attaching to the bus.

OK, we'll discuss this on the #linux-sh IRC channel and if no one objects,
I'm going to apply the series.

> I would also recommend trying to eliminate most of the SoC
> support for chips that only support a reference board but no
> products or known user of the reference board itself. While
> a lot of the conversion could be done fairly mechanical, at
> least the clk driver for each chip is a huge effort.

It depends on what Yoshinori plans for the device tree conversion. The
latest version of his series was posted here [1]. But he promised to
send a rebased and updated version soon.

> I looked at the clk conversion in the past, as this is not just
> needed for the DT work, but also to remove CONFIG_HAVE_LEGACY_CLK.
> The patch series I did a while ago renames the sh clk interfaces
> to no longer conflict with COMMON_CLK, which should allow it
> to coexist with a DT-enabled platform in the same kernel build.
> Let me know if you'd like me to dig out and rebase that series,
> it probably still applies and may help you here.

Yes, that would be greatly appreciated. Please go ahead.

FWIW, I am currently on vacation until August 15th, so I might be a bit
slow with open source stuff. I am using the free time to get things done
on my TODO list.

Adrian

> [1] https://lore.kernel.org/all/[email protected]/t/

-- 
 .''`.  John Paul Adrian Glaubitz
: :' :  Debian Developer
`. `'   Physicist
  `-    GPG: 62FF 8A75 84E0 2956 9546  0006 7426 3B37 F5B5 F913