Re: [alsa-devel] [RFC PATCH 2/7] soundwire: add Slave sysfs support

From: Pierre-Louis Bossart
Date: Wed May 08 2019 - 12:52:31 EST

Vinod, the question was not for dp0 and dpN, it's fine to have
subdirectories there, but rather why we need separate devices for the master
and slave properties.

Slave does not have a separate device. IIRC the properties for Slave are
in /sys/bus/soundwire/device/<slave>/...

I am not sure this is correct

ACPI defines the slaves devices under
/sys/bus/acpi/PRP0001, e.g.

Yes the bus will create 'soundwire slave' device type (In acpi case
created from ACPI walk) and we do link the ACPI as the firmware node.
This is 'not' created for properties but for soundwire representation of
slave devices. This is the one code driver attaches to.
/sys/bus/acpi/devices/PRP00001:00/device:17# ls

Yes this would the companion ACPI device

I see, I must admit I missed this part.

I guess it's not technically broken but was is really necessary though to use this notion of companion ACPI device? For the controller it makes sense, that's how to match ACPI and PCI, but since Soundwire slaves are not fully enumerable, precisely why we need all these _DSD properties, couldn't we just use ACPI devices directly?