Since all regmap CODECs should be (and are) using the more advance regmap
cache infrastructure remove the code which supports that and just proxy
I/O straight through to regmap.
Signed-off-by: Mark Brown <broonie@linaro.org>

Since the CODEC driver could specify its own I/O(read and write)
while registering the CODEC for some reason, maybe the MFDs is
used, etc.

So just do check it, if they are not specified by CODEC driver
then try to set up the default regmap I/O if regmap is used.
Signed-off-by: Xiubo Li <Li.Xiubo@freescale.com>
Signed-off-by: Mark Brown <broonie@linaro.org>

Now that all users have been converted to regmap and the config.reg_bits
and config.val_bits can be setted by each user through regmap core API.
So these two params are redundant here.

Since the only control type that left is SND_SOC_REGMAP, so remove it. Drop
the control params and add struct regmap *regmap to simplify the code.
Signed-off-by: Xiubo Li <Li.Xiubo@freescale.com>
Signed-off-by: Mark Brown <broonie@linaro.org>

For some CODEC drivers like who act as the MFDs children are ignored
by this patch.
Signed-off-by: Xiubo Li <Li.Xiubo@freescale.com>
Signed-off-by: Mark Brown <broonie@linaro.org>

Merge branches 'topic/ad193x', 'topic/tlv320aic23', 'topic/tlv320aic32x4', 'topic/wm8991', 'fix/si476x' and 'fix/88pm860' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound into asoc-io

The 88pm860 is a MFD device and the CODEC driver is using the regmap struct of
the parent device, hence automatic IO setup will not work and we need to
manually call snd_soc_codec_set_cache_io(). The issue was introduced in commit
f9ded3b2 ("ASoC: 88pm860x: Use regmap for I/O").

Fixes: f9ded3b2 ("ASoC: 88pm860x: Use regmap for I/O").
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@linaro.org>
Cc: stable@vger.kernel.org

The si476x is a MFD device and the CODEC driver is using the regmap struct of
the parent device, hence automatic IO setup will not work and we need to
manually call snd_soc_codec_set_cache_io(). The issue was introduced commit
d6173df3 ("ASoC: si476x: Remove custom register I/O implementation")

Fixes: d6173df3 ("ASoC: si476x: Remove custom register I/O implementation")
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@linaro.org>
Cc: stable@vger.kernel.org

The tlv320aic32x4 related lines were wrongly placed after tlv320aic3x lines.
Signed-off-by: Jyri Sarha <jsarha@ti.com>
Signed-off-by: Mark Brown <broonie@linaro.org>

This fixes the following build errors when aic23 is configured as
module:

>> ERROR: "tlv320aic23_probe"
>> [sound/soc/codecs/snd-soc-tlv320aic23-i2c.ko] undefined!
>> ERROR: "tlv320aic23_regmap"
>> [sound/soc/codecs/snd-soc-tlv320aic23-i2c.ko] undefined!
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Signed-off-by: Mark Brown <broonie@linaro.org>

Now that AIC23 supports two control interfaces all existing I2C users
should select I2C variant.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Signed-off-by: Mark Brown <broonie@linaro.org>

tlv320aic23 chip control interface may work in either I2C or SPI mode
depending on the MODE pin state. Functionality and register layout are
independent of the control mode.

Implement bus-specific parts as separate modules.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Signed-off-by: Mark Brown <broonie@linaro.org>

We now no longer have any users of hw_read() in the kernel so remove the
code in order to prevent any new users being added. Users should be using
regmap.
Signed-off-by: Mark Brown <broonie@linaro.org>

Pre-merge code was using direct hw_read() calls as an out of framework
way of doing volatile register I/O when not using regmap. This has never
functioned correctly in mainline due to the regmap conversion, the
hw_read() implementation still does caching. In order to facilitate
removal of the subsystem level I/O code convert to use snd_soc_read(),
there should be no functional impact.
Signed-off-by: Mark Brown <broonie@linaro.org>
Acked-by: Adam Thomson <Adam.Thomson.Opensource@diasemi.com>

Signed-off-by: Xiubo Li <Li.Xiubo@freescale.com>
Signed-off-by: Mark Brown <broonie@linaro.org>

For most CODEC drivers which the REGMAP is used, the soc_probe_codec()
will do the stuff work of snd_soc_codec_set_cache_io(), which the CODEC
drivers' ASoC probe will do too, and almost at the same time.

This patch set the default I/O up try regmap, and then the CODEC drivers'
stuff work of snd_soc_codec_set_cache_io() will be redundant, while if one
CODEC driver needed to set it's own I/O, then it can rewrite the default ones.
Then could we just discard the snd_soc_codec_set_cache_io() from the CODEC
drivers' ASoC probe to simplify the code.
Signed-off-by: Xiubo Li <Li.Xiubo@freescale.com>
Signed-off-by: Mark Brown <broonie@linaro.org>

Now that all users have been converted to regmap and the config.reg_bits
and config.val_bits can be setted by each user through regmap core API.
So these two params are redundant here.
Signed-off-by: Xiubo Li <Li.Xiubo@freescale.com>
Signed-off-by: Mark Brown <broonie@linaro.org>

Now that all users have been converted to regmap we can eliminate the ASoC
level wrapper for I2C I/O reducing the amount of duplicated functionality.
Signed-off-by: Mark Brown <broonie@linaro.org>

Merge remote-tracking branches 'asoc/topic/ak4671', 'asoc/topic/cs42l51' and 'asoc/topic/alc5623' into asoc-io

Rearrange clock tree shutdown to disable them in the reversed order of
startup. First disable all dividers, then PLL followed by master clock.
Signed-off-by: Markus Pargmann <mpa@pengutronix.de>
Signed-off-by: Mark Brown <broonie@linaro.org>

Support regulators to power up the codec. This patch also enables the
AVDD LDO if no AV regulator was found.
Signed-off-by: Markus Pargmann <mpa@pengutronix.de>
Signed-off-by: Mark Brown <broonie@linaro.org>

Add support for a master clock passed through DT. The master clock of
the codec is only active when the codec is in use.
Signed-off-by: Markus Pargmann <mpa@pengutronix.de>
Signed-off-by: Mark Brown <broonie@linaro.org>

Just replace with the helper macro.  No functional change at all.
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Acked-by: Liam Girdwood <liam.r.girdwood@linux.intel.com>
Acked-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@linaro.org>

Convert to directly use the regmap API, allowing us to eliminate the last
user of the ASoC level I/O implementations (there are still open coded
I/O implementations in drivers), avoiding duplicating code in regmap.

We no longer cache the entire CODEC register map on probe since the more
advanced cache infrastructure in regmap is able to fill the cache on
demand.
Signed-off-by: Mark Brown <broonie@linaro.org>

Just replace with the helper macro.  No functional change at all.
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Acked-by: Liam Girdwood <liam.r.girdwood@linux.intel.com>
Acked-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@linaro.org>

Just replace with the helper macro.  No functional change at all.
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Acked-by: Liam Girdwood <liam.r.girdwood@linux.intel.com>
Acked-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@linaro.org>

Just replace with the helper macro.  No functional change at all.
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Acked-by: Liam Girdwood <liam.r.girdwood@linux.intel.com>
Acked-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@linaro.org>

Just replace with the helper macro.  No functional change at all.
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Acked-by: Liam Girdwood <liam.r.girdwood@linux.intel.com>
Acked-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@linaro.org>

wm8991 codec driver has a few places wrongly defining the number of
enum items.

Use SOC_ENUM_SINGLE_DECL() macro and they are automatically fixed.
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Acked-by: Liam Girdwood <liam.r.girdwood@linux.intel.com>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Acked-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@linaro.org>

‘cs42l51’ is not used. Remove it.
Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Acked-by: Brian Austin <brian.austin@cirrus.com>
Signed-off-by: Mark Brown <broonie@linaro.org>

There are a few known (minor) problems with having the support code for both I2C
and SPI in the same module:
    * We need to be extra careful to make sure to not build the driver into the
      kernel if one of the subsystems is build as a module (Currently only I2C
      can be build as a module).
    * The module init path error handling is rather ugly. E.g. what should be
      done if either the SPI or the I2C driver fails to register? Most drivers
      that implement SPI and I2C in the same module currently fallback to
      undefined behavior in that case. Splitting the the driver into two
      modules, one for each bus, allows the registration of the other bus driver
      to continue without problems if one of them fails.

This patch splits the AD193X driver into 3 modules. One core module that
implements the device logic, but is independent of the bus method used. And one
module for SPI and I2C each that registers the drivers and sets up the regmap
struct for the bus.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@linaro.org>

All ASoC CODEC drivers that use SPI have now been converted to use regmap
so we can delete SND_SOC_SPI, preventing any new users being added.
Signed-off-by: Mark Brown <broonie@linaro.org>

This helps us remove the ASoC level I/O functionality which is now just
a thin wrapper around regmap.
Signed-off-by: Mark Brown <broonie@linaro.org>

Saves code and adds error handling.
Signed-off-by: Mark Brown <broonie@linaro.org>

As part of phasing out the ASoC level register I/O code (which is now just
a thin wrapper around regmap anyway) convert the cs42l51 driver to use the
regmap API directly.

We now no longer initialise the cache from hardware at startup, the regmap
caches are smart enough to understand which registers are actually cached
and read on demand. This should have no visible effect on the system.
Signed-off-by: Mark Brown <broonie@linaro.org>
Acked-by: Brian Austin <brian.austin@cirrus.com>

The VM subsystem already logs quite loudly if we run out of memory so
don't bother here.
Signed-off-by: Mark Brown <broonie@linaro.org>
Acked-by: Brian Austin <brian.austin@cirrus.com>

This commit adds a trivial Device Tree binding to the I2C-based
cs42l51 sound codec, so that it can be used from Device Tree based
platforms.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Signed-off-by: Mark Brown <broonie@linaro.org>

Remove unused pointer 'wm8991' in function wm8991_probe(). The last user
vanished with a86652e5 (ASoC: wm8991: Convert to direct regmap API usage)

Detected by Coverity: CID 1162831
Signed-off-by: Christian Engelmayer <cengelma@gmx.at>
Signed-off-by: Mark Brown <broonie@linaro.org>

Add DT support for this codec. The bindings differ a bit from the aic3x
codec bindings, so I created a new binding documentation.
Signed-off-by: Markus Pargmann <mpa@pengutronix.de>
Signed-off-by: Mark Brown <broonie@linaro.org>

There are a number of mixer controls that support negative values. They
use signed values for this with different number of bits for the values.
Currently they only support the positive range.

This patch replaces the unsigned mixers with signed mixers to support
the full range.
Signed-off-by: Markus Pargmann <mpa@pengutronix.de>
Signed-off-by: Mark Brown <broonie@linaro.org>

Merge branch 'topic/sign' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound into asoc-tlv320aic32x4