01 Oct, 2010
2 commits
-
Add the widget for MICBIAS power control and allow configuration of the
microphone bias setup via the platform data for the WM8962. When
microphone status signals are brought out to GPIO this should be
sufficient to enable microphone detection.Signed-off-by: Mark Brown
Acked-by: Liam Girdwood -
There are some status bits for microphone detection in here.
Signed-off-by: Mark Brown
Acked-by: Liam Girdwood
29 Sep, 2010
4 commits
-
Provide an initial hookup for interrupts on the WM8962. Currently we simply
report error status via log messages if an IRQ is provided for the device.Signed-off-by: Mark Brown
Acked-by: Liam Girdwood -
For consistency.
Signed-off-by: Mark Brown
Acked-by: Liam Girdwood -
When configuring the FLL we preserve the FLL enable configuration in order
to allow us to reenable the FLL after configuration but we do not clear
the other bits in the register, causing old configuration to be preserved.Signed-off-by: Mark Brown
Acked-by: Liam Girdwood -
Since we are using custom get/put handlers
use SOC_ENUM_SINGLE_EXT_DECL instead of the original SOC_ENUM_SINGLE_DECL
macro.Signed-off-by: Dimitris Papastamos
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown
27 Sep, 2010
1 commit
-
sound/soc/codecs/wm8985.c: In function 'wm8985_hw_params':
sound/soc/codecs/wm8985.c:731:2: warning: format '%d' expects type 'int', but argument 4 has type 'size_t'Actually the variable is fine as int.
Signed-off-by: Takashi Iwai
25 Sep, 2010
3 commits
-
Since Jassi is doing so much good work and can offer such good review
for the Samsung CPU support add an entry for the Samsung ASoC drivers
to MAINTAINERS listing him.Signed-off-by: Mark Brown
Acked-by: Jassi Brar
Acked-by: Liam Girdwood -
We are not using the private data in this function, so get rid of it.
Signed-off-by: Dimitris Papastamos
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown
24 Sep, 2010
8 commits
-
Remove version number and clean up some indentation.
Signed-off-by: Mark Brown
Acked-by: Liam Girdwood -
Helps tracing errors further up the stack.
Signed-off-by: Mark Brown
Acked-by: Jassi Brar
Acked-by: Liam Girdwood -
Could use dev_() but we'd have to remember the struct device somewhere
and it wouldn't make the logging clearer.Signed-off-by: Mark Brown
Acked-by: Jassi Brar
Acked-by: Liam Girdwood -
Otherwise we try to re-register the CODEC device if the module is reloaded
and sysfs becomes miserable.Signed-off-by: Mark Brown
Acked-by: Jassi Brar
Acked-by: Liam Girdwood -
At least some of the systems using this device have multiple audio
subsystems so provide some guidance to userspace about which one this
is.Signed-off-by: Mark Brown
Acked-by: Jassi Brar
Acked-by: Liam Girdwood -
Signed-off-by: Mark Brown
Acked-by: Jassi Brar
Acked-by: Liam Girdwood -
We need to pass the register index and not the register value.
This patch depends on my previous patch "ASoC: Delegate to hw
specific read for volatile registers".Signed-off-by: Dimitris Papastamos
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown -
Ensure that reads on volatile registers will correctly delegate
to the bus specific read function.Signed-off-by: Dimitris Papastamos
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown
23 Sep, 2010
3 commits
-
Go back to the new world order.
(Also fixed indentation.)
Signed-off-by: Takashi Iwai
-
…ie/sound-2.6 into topic/asoc
-
Spot the build testing.
Signed-off-by: Mark Brown
22 Sep, 2010
7 commits
-
The code can't really cope with I/O errors, so it would be better
to be consistent throughout all cache functions and return -1 instead
of -EINVAL.The return value of snd_soc_read(...) is mostly checked in the probe
function and nowhere else.Signed-off-by: Dimitris Papastamos
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown -
Also clean up the error print a bit.
Signed-off-by: Mark Brown
Acked-by: Liam Girdwood -
…soc-2.6 into for-2.6.37
-
Make sure we stay within the cache boundaries when updating the
register cache.Signed-off-by: Dimitris Papastamos
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown -
Make sure we stay within the cache boundaries when updating the
register cache.Signed-off-by: Dimitris Papastamos
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown -
rtd->dev.init_name is set twice in soc_probe_dai_link. I removed the first
assignement from dai_link->stream_name since then there won't be sysfs name
changes and usually dai_link->name seems to fit anyway better for a sysfs
directory name.Signed-off-by: Jarkko Nikula
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown
21 Sep, 2010
10 commits
-
Let's not add the core controls twice.
Signed-off-by: Mark Brown
Acked-by: Liam Girdwood -
Helps with diagnostics.
Signed-off-by: Mark Brown
Acked-by: Liam Girdwood -
So machine drivers can see the declaration.
Signed-off-by: Mark Brown
Acked-by: Jassi Brar
Acked-by: Liam Girdwood -
Current FSI driver had data push/pop functions.
But the main operation of these 2 were very similar.
This mean it is possible to merge these to 1 function.Signed-off-by: Kuninori Morimoto
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown -
Current FSI driver is using
data-length / width / number / offset for variables.
But it was a very confusing name.This patch rename them to easy to understand,
and add new functions for it.Signed-off-by: Kuninori Morimoto
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown -
Standardise on 'wm8978' as the name for the CODEC.
Reported-by: Guennadi Liakhovetski
Signed-off-by: Mark Brown
Acked-by: Liam Girdwood -
Now codec hits the SND_SOC_BIAS_OFF also when it is idle. This is also
the default state after probing and codec is left unconfigured and
unpowered by default. Initialization will happen when the bias state changes
and aic3x_set_power does power-up and cache sync.Signed-off-by: Jarkko Nikula
Acked-by: Mark Brown
Signed-off-by: Liam Girdwood -
There is no need to reset the codec and perform cache sync if none of the
supply regulators were not disabled. Patch registers a notifier callback for
each supply and callback then sets a flag to indicate when cache sync is
required.HW writes are also needless when codec bias is off so cache_only flag is set
independently of actual supply regulators state.Signed-off-by: Jarkko Nikula
Acked-by: Mark Brown
Signed-off-by: Liam Girdwood -
Now all the regulators are disabled when entering into SND_SOC_BIAS_OFF
and enabled when coming back to SND_SOC_BIAS_STANDBY state. Currently this
runtime control happens only with suspend/resume as this patch does not
change the default idle behavior.This patch manages all the regulators and reset since it seems that register
sync is needed even if only analog supplies AVDD and DRVDD are disabled.
This was noted when the system was running with idle behavior changed and
IOVDD and DVDD were on.It is not known are all the registers needed to sync or only some subset of
them. Therefore patch plays safe and does always full shutdown/power-up.Signed-off-by: Jarkko Nikula
Acked-by: Mark Brown
Signed-off-by: Liam Girdwood -
It will be easier to keep regulator enable/disable calls in sync when dynamic
regulator management is added if regulator management is moved from
aic3x_i2c_probe/_remove to aic3x_probe/_remove.Signed-off-by: Jarkko Nikula
Acked-by: Mark Brown
Signed-off-by: Liam Girdwood
20 Sep, 2010
2 commits
-
Purpose of this virtual Detection pin is to keep codec bias on whenever the
GPIO or jack detection features are needed.Jack detection needs a mic bias so machine drivers can construct a following
route for instance for keeping the path and codec bias on:"Input Jack" -> "Mic Bias xV" -> "Detection" -> detection block inside codec.
For the GPIO the machine driver can force the pin on with
snd_soc_dapm_force_enable_pin.Signed-off-by: Jarkko Nikula
Acked-by: Mark Brown
Signed-off-by: Liam Girdwood