[PATCH v1] Revert "ARM: dts: imx7: Fix NAND controller size-cells"

[Marek Vasut]

On 12/8/22 14:49, Francesco Dolcini wrote:
> Il 8 dicembre 2022 14:21:31 CET, Marek Vasut <marex at denx.de> ha scritto:
>> On 12/8/22 11:51, Miquel Raynal wrote:
>>> Hi Shawn,
>>
>> Hi,
>>
>>> + Thorsten
>>>
>>> marex at denx.de wrote on Mon, 5 Dec 2022 17:26:53 +0100:
>>>
>>>> On 12/5/22 16:23, Francesco Dolcini wrote:
>>>>> From: Francesco Dolcini <francesco.dolcini at toradex.com>
>>>>>
>>>>> This reverts commit 753395ea1e45c724150070b5785900b6a44bd5fb.
>>>>>
>>>>> It introduced a boot regression on colibri-imx7, and potentially any
>>>>> other i.MX7 boards with MTD partition list generated into the fdt by
>>>>> U-Boot.
>>>>>
>>>>> While the commit we are reverting here is not obviously wrong, it fixes
>>>>> only a dt binding checker warning that is non-functional, while it
>>>>> introduces a boot regression and there is no obvious fix ready.
>>>>>
>>>>> Cc: stable at vger.kernel.org
>>>>> Fixes: 753395ea1e45 ("ARM: dts: imx7: Fix NAND controller size-cells")
>>>>> Link: https://lore.kernel.org/all/Y4dgBTGNWpM6SQXI@francesco-nb.int.toradex.com/
>>>>> Link: https://lore.kernel.org/all/20221205144917.6514168a@xps-13/
>>>>> Signed-off-by: Francesco Dolcini <francesco.dolcini at toradex.com>
>>> [...]
>>>> Reviewed-by: Miquel Raynal <miquel.raynal at bootlin.com>
>>> [...]
>>>> Acked-by: Marek Vasut <marex at denx.de>
>>> [...]
>>>
>>> As discussed in the above links, boot is broken on imx7 Colibri boards,
>>> this revert was the most quick and straightforward fix we agreed upon
>>> with the hope (~ duty?) it would make it in v6.1. Any chance you could
>>> pick this up rapidly and forward it to Linus? Or should we involve
>>> him directly (Thorsten?).
>>
>> It seems neither Francesco nor me agree that this is the right approach and rather the fix should be the two-liner change to the OF partition parser, so maybe this should not be picked ?
> 
> I think that the 2 lines change might not be good enough to properly handle the U-Boot generated OF partitions in the general case, even if it fixes my specific issue.
> 
> Given that I would do the revert as an immediate first step.

Then that's fine, let's do it.

Will you also follow up on the parser fix please ?