On Fri, Jan 22, 2021 at 2:03 AM Hans de Goede hdegoede@redhat.com wrote:
On 1/18/21 1:02 PM, Andy Shevchenko wrote:
On Sun, Jan 17, 2021 at 6:06 PM Hans de Goede hdegoede@redhat.com wrote:
...
Can you elaborate switchings from get() to get_sync() in few places
Sorry, those 2 changes really should have been in a separate commit. I've put the 2 get -> get_sync() changed in their own commit now with the following commit-msg:
""" extcon: arizona: Always use pm_runtime_get_sync() when we need the device to be awake
Before this commit the extcon-arizona code was mixing pm_runtime_get() and pm_runtime_get_sync() in different places. In all cases where either function is called we make use of the device immediately
called and we
afterwards. This means that we should always use pm_runtime_get_sync(). """
along with moving disable()?
The enable / disable calls are not moved, they are removed.
Here is a new commit msg which hopefully explains this better which I plan to use for v3:
""" Drivers for MFD child-devices such as the arizona codec drivers and the arizona-extcon driver can choose to either make runtime_pm_get/_put calls on their own child-device, which will then be propagated to their parent; or they can make them directly on their MFD parent-device.
The arizona-extcon code was using runtime_pm_get/_put calls on its own child-device where as the codec drivers are using runtime_pm_get/_put calls on their parent.
The arizona-extcon MFD cell/child-device has been removed and this commit is part of refactoring the arizona-extcon code into a library to be used directly from the codec drivers.
Specifically this commit moves the code over to make runtime_pm_get/_put calls on the parent device (on arizona->dev) bringing the code inline with how the codec drivers do this.
Note this also removes the pm_runtime_enable/_disable calls as pm_runtime support has already been enabled on the parent-device by the arizona MFD driver. """
Makes sense to me, thanks!