Re: [PATCH v6 4/4] net: phy: realtek: Add LED configuration support for RTL8211E

From: Florian Fainelli
Date: Fri Aug 16 2019 - 18:12:54 EST

On 8/16/19 2:27 PM, Matthias Kaehlcke wrote:
> On Fri, Aug 16, 2019 at 10:13:42PM +0200, Pavel Machek wrote:
>> On Tue 2019-08-13 12:11:47, Matthias Kaehlcke wrote:
>>> Add a .config_led hook which is called by the PHY core when
>>> configuration data for a PHY LED is available. Each LED can be
>>> configured to be solid 'off, solid 'on' for certain (or all)
>>> link speeds or to blink on RX/TX activity.
>>> Signed-off-by: Matthias Kaehlcke <mka@xxxxxxxxxxxx>
>> THis really needs to go through the LED subsystem,
> Sorry, I used what threw at me, I should have
> manually cc-ed the LED list.
>> and use the same userland interfaces as the rest of the system.
> With the PHY maintainers we discussed to define a binding that is
> compatible with that of the LED one, to have the option to integrate
> it with the LED subsystem later. The integration itself is beyond the
> scope of this patchset.
> The PHY LED configuration is a low priority for the project I'm
> working on. I wanted to make an attempt to upstream it and spent
> already significantly more time on it than planned, if integration
> with the LED framework now is a requirement please consider this
> series abandonded.

While I have an appreciation for how hard it can be to work in a
corporate environment while doing upstream first and working with
virtually unbounded goals (in time or scope) due to maintainers and
reviewers, that kind of statement can hinder your ability to establish
trust with peers in the community as it can be read as take it or leave it.

The LED subsystem integration can definitively come in later from my 2
cents perspective and this patch series as it stands is valuable and
avoids inventing new bindings.