On 5/27/20 2:34 PM, Arnd Bergmann wrote:
With SND_SOC_AMD_RV_RT5682_MACH using the i2c version of the driver, we can easily get a build failure when I2C is built-in but soundwire is not: WARNING: unmet direct dependencies detected for SND_SOC_RT5682 Depends on [m]: SOUND [=y] && !UML && SND [=y] && SND_SOC [=y] && (I2C [=y] || SOUNDWIRE [=m]) && (SOUNDWIRE [=m] || !SOUNDWIRE [=m]) && (I2C [=y] || !I2C [=y]) Selected by [y]: - SND_SOC_AMD_RV_RT5682_MACH [=y] && SOUND [=y] && !UML && SND [=y] && SND_SOC [=y] && SND_SOC_AMD_ACP3x [=y] && I2C [=y] && CROS_EC [=y] Selected by [m]: - SND_SOC_RT5682_SDW [=m] && SOUND [=y] && !UML && SND [=y] && SND_SOC [=y] && SOUNDWIRE [=m] && (I2C [=y] || !I2C [=y]) Rework the driver to have three separate modules, with the main driver just dealing with the common bits and the actual initialization as part of i2c and sdw specific modules. The conversion is fairly mechanical to keep it easy to review, i.e. it moves code around with the minimal required renaming and changes. Fixes: 6b8e4e7db3cd ("ASoC: amd: Add machine driver for Raven based platform") Fixes: fd443a20c2f0 ("ASoC: rt5682: fix I2C/Soundwire dependencies") Signed-off-by: Arnd Bergmann <arnd@xxxxxxxx>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@xxxxxxxxxxxxxxx> Thanks for this cleanup.