Re: [PATCH v6 3/3] hwmon: (max6639) Change from pdata to dt configuration

[Rob Herring]

On Sun, Nov 20, 2022 at 07:19:46AM -0800, Guenter Roeck wrote:
> On Thu, Nov 17, 2022 at 10:13:24AM +0100, Uwe Kleine-König wrote:
> > On Thu, Nov 17, 2022 at 02:10:45PM +0530, Naresh Solanki wrote:
> > > 
> > > 
> > > On 17-11-2022 01:15 pm, Uwe Kleine-König wrote:
> > > > Hello,
> > > > 
> > > > On Wed, Nov 16, 2022 at 10:36:15PM +0100, Naresh Solanki wrote:
> > > > > max6639_platform_data is not used by any in-kernel driver and does not
> > > > > address the MAX6639 fans separately.
> > > > > Move to device tree configuration with explicit properties to configure
> > > > > each fan.
> > > > > 
> > > > > Non-DT platform can still use this module with its default
> > > > > configuration.
> > > > > 
> > > > > Signed-off-by: Marcello Sylvester Bauer <sylv@xxxxxxx>
> > > > > Signed-off-by: Naresh Solanki <Naresh.Solanki@xxxxxxxxxxxxx>
> > > > 
> > > > What changed here since v5? Please either add a changelog below the
> > > > tripple-dash for a new revision, or make sure that all relevant people
> > > > get the cover letter.
> > > > 
> > > > It seems you didn't address my comments for v5 :-\
> > > Not sure what I missed but did following changes:
> > > Removed unused header max6639.h
> > > Used dev_err_probe instead,
> > > Removed of_pwm_n_cells,
> > > if condition for freq_table
> > > removed pwm_get_state & instead use pwm->state
> > > division/multiplication optimizations,
> > > indentation of freq_table,
> > 
> > In the cover letter you just wrote:
> > 
> > | Changes in V6:
> > | - Remove unused header file
> > | - minor cleanup
> > 
> > which is too short in my eyes. If you wrote instead:
> > 
> > 	Address review feedback by Uwe Kleine-König in patch #3, patches #1 and
> > 	#2 unchanged.
> > 
> > This would be much more helpful as people that were already happy with
> > v5 wouldn't need to look at the first two patches and I would know that
> > you addressed my feedback and would have looked in more detail.
> > 
> > What I miss is the most critical part of my feedback, i.e.:
> > | My overall impression is that this patch mixes too much things. IMHO it
> > | should be split in (at least)
> > | 
> > |  - Add dt support
> > |  - Drop platform support
> > |  - Add PWM provider support
> > |  - Make use of the PWM API
> > |
> > | maybe also add the 2nd PWM in a separate step.
> 
> Those will definitely need to be separate patches. I am far from convinced
> that all fan controllers in the hwmon subsystem should implement pwm
> providers just to match devicetree requirements. That adds zero value in
> 99% of all use cases. Actually, I don't know of any use cases where it
> would add value or even make sense.

There's no requirement that using a binding means using corresponding 
Linux subsystem. Convenient usually, but not required.

Rob