02 Dec, 2010
1 commit
-
The use of DAPM widgets, and extra routing can cause ordering
problems in the system.
Machine drivers should use the exported direct interface with
SND_SOC_DAPM_HP's event callback to manage the state of the
amplifier.Signed-off-by: Peter Ujfalusi
Acked-by: Mark Brown
Signed-off-by: Liam Girdwood
30 Nov, 2010
13 commits
-
New DAPM widgets, and paths to enable both channels at the
same time (for stereo output).
With this path the switch time difference can be avoided
between left and right channels.
The original DAPM paths can be still used, if only one of
TPA's output has been connected to a speaker, but for most of
the cases, switching to the stereo path is better.Signed-off-by: Peter Ujfalusi
Acked-by: Mark Brown
Signed-off-by: Liam Girdwood -
Reduce the amount of duplicated code by using single
event handler for PGA_E to enable the needed channel.
Use the w->shift to pass the channel information to
the handler function.Signed-off-by: Peter Ujfalusi
Acked-by: Mark Brown
Signed-off-by: Liam Girdwood -
Do not enable the amplifier right after the power has been
restored to the amplifier.
The DAPM_SUPPLY widget turns on the amp early in the DAPM
power walk, and the unmuting of channel happens quite late.
Keeping the amp in SW reset state ensures better muting.
In this way the pop noise coming from other components (codec)
can be filtered out.Signed-off-by: Peter Ujfalusi
Acked-by: Mark Brown
Signed-off-by: Liam Girdwood -
Use simpler way to avoid setting the same power state
for the amplifier.
Simplifies the check introduced by patch:
ASoC: tpa6130a2: Fix unbalanced regulator disablesSigned-off-by: Peter Ujfalusi
Cc: Jarkko Nikula
Signed-off-by: Liam Girdwood -
During playback start the codec has been already powered at
BIAS_ON event time, so there's no need to enable the codec again.Signed-off-by: Peter Ujfalusi
Acked-by: Mark Brown
Signed-off-by: Liam Girdwood -
No need to enable the codec at this time.
The codec will be enabled later by other eventsSigned-off-by: Peter Ujfalusi
Acked-by: Mark Brown
Signed-off-by: Liam Girdwood -
Otherwise, calling dev_get_drvdata in p1022_ds_remove returns NULL.
Signed-off-by: Axel Lin
Acked-by: Timur Tabi
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown -
Otherwise, calling dev_get_drvdata in mpc8610_hpcd_remove returns NULL.
Signed-off-by: Axel Lin
Acked-by: Timur Tabi
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown -
I think this unneededd !! operations just reduce the readability.
Signed-off-by: Axel Lin
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown -
This patch fixes below error:
CC sound/soc/nuc900/nuc900-pcm.o
sound/soc/nuc900/nuc900-pcm.c: In function 'nuc900_dma_open':
sound/soc/nuc900/nuc900-pcm.c:267: error: 'nuc900_ac97_data' undeclared (first use in this function)
sound/soc/nuc900/nuc900-pcm.c:267: error: (Each undeclared identifier is reported only once
sound/soc/nuc900/nuc900-pcm.c:267: error: for each function it appears in.)
sound/soc/nuc900/nuc900-pcm.c: At top level:
sound/soc/nuc900/nuc900-pcm.c:337: error: expected ',' or ';' before 'static'
sound/soc/nuc900/nuc900-pcm.c:354: error: 'nuc900_soc_platform_probe' undeclared here (not in a function)
make[3]: *** [sound/soc/nuc900/nuc900-pcm.o] Error 1
make[2]: *** [sound/soc/nuc900] Error 2
make[1]: *** [sound/soc] Error 2
make: *** [sound] Error 2Signed-off-by: Axel Lin
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown -
This patch fixes below compile warning:
CC sound/soc/nuc900/nuc900-ac97.o
sound/soc/nuc900/nuc900-ac97.c:300: warning: initialization from incompatible pointer type
sound/soc/nuc900/nuc900-ac97.c:301: warning: initialization from incompatible pointer typeSigned-off-by: Axel Lin
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown -
Fix below compile error by add a missing ';'.
CC sound/soc/nuc900/nuc900-ac97.o
sound/soc/nuc900/nuc900-ac97.c:300: warning: initialization from incompatible pointer type
sound/soc/nuc900/nuc900-ac97.c:301: warning: initialization from incompatible pointer type
sound/soc/nuc900/nuc900-ac97.c:318: error: expected ',' or ';' before 'static'
sound/soc/nuc900/nuc900-ac97.c:405: error: 'nuc900_ac97_drvprobe' undeclared here (not in a function)
make[3]: *** [sound/soc/nuc900/nuc900-ac97.o] Error 1
make[2]: *** [sound/soc/nuc900] Error 2
make[1]: *** [sound/soc] Error 2
make: *** [sound] Error 2Signed-off-by: Axel Lin
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown
29 Nov, 2010
6 commits
-
Signed-off-by: Dimitris Papastamos
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown -
Ensure that we report any errors encountered during reads/writes
in the cache syncing functions.Remove redundant newline in the source code.
Signed-off-by: Dimitris Papastamos
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown -
Properly free allocated resources in smdk_init() error path.
Add missing platform_device_unregister() in smdk_exit().Signed-off-by: Axel Lin
Acked-by: Jassi Brar
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown -
Signed-off-by: Axel Lin
Acked-by: Jassi Brar
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown -
Properly free allocated resources in neo1973_gta02_init() error path.
Signed-off-by: Axel Lin
Acked-by: Jassi Brar
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown -
Properly free allocated resources in goni_init() error path.
Add missing snd_soc_unregister_dai() in goni_exit().Signed-off-by: Axel Lin
Acked-by: Jassi Brar
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown
27 Nov, 2010
8 commits
-
This allows us to communicate our power management state back to the
parent device, allowing it to do a full power down when the device is
idle.Signed-off-by: Mark Brown
Acked-by: Liam Girdwood -
The WM8994 and WM8958 register map is relatively sparse so benefits
from compression. The rbtree compression gives better results than
LZO for both memory and CPU consumption on a map as sparse as this.Signed-off-by: Mark Brown
Acked-by: Liam Girdwood -
In the process we convert the driver to read registers one at a time
when initialising the cache. This has the effect of working around
limitations in the sizes of I2C transactions which can be done by some
CPUs. Due to the sparseness of the register map the overhead from this
should be minimual unless I2C transactions are very expensive to start.Signed-off-by: Mark Brown
Acked-by: Liam Girdwood -
The WM8958 contains an advanced accessory detection feature which allows
detection of up to seven different impedence levels on the microphone
bias output, including detection of video outputs. Since some of the
more involved accessory interfaces may involve noticable interactions
with external components a simple detection scheme is provided by
default with the option to provide custom handling of accessory detect.Signed-off-by: Mark Brown
Acked-by: Liam Girdwood -
The WM8958 features a multi-band compressor which can be enabled on
any of the AIF inputs. The MBC allows different gains to be applied to
differnt audio bands, providing an improvement in perceived loudness
of the signal by avoiding overdriving the output transducers. This
patch enables support for the MBC.Signed-off-by: Mark Brown
Acked-by: Liam Girdwood -
Additional audio routing options are available on the WM8958 audio
interface 3. Add support for these.Signed-off-by: Mark Brown
Acked-by: Liam Girdwood -
The WM8958 is a WM8994 derivative. This patch merely ensures that some
revision specific configuration for WM8994 is not enabled on WM8994,
additional patches will add support for the new features introduced on
the WM8958.Signed-off-by: Mark Brown
Acked-by: Liam Girdwood -
Devices which do not have a DCS correction applied can use the explicit
DC servo startup mode for optimal startup performance. This most
immediately affects the WM8958.Signed-off-by: Mark Brown
Acked-by: Liam Girdwood
26 Nov, 2010
6 commits
-
Several of the GPIOs on the WM8994 are fixed function on the WM8958 so
error out if the user tries to request them with gpiolib.Signed-off-by: Mark Brown
Acked-by: Liam Girdwood -
The WM8958 is a derivative of the WM8994 which is register compatible
with the addition of some extra features, mostly in the CODEC side.
The major change visible at the MFD level is that rather than a single
DBVDD supply we now have three separate DBVDDs so we must request and
enable a different set of supplies.Signed-off-by: Mark Brown
Acked-by: Samuel Ortiz
Acked-by: Liam Girdwood -
Signed-off-by: Mark Brown
Acked-by: Liam Girdwood -
In current implementation, there are resources leak in the error path.
This patch properly reclaims the allocated resources in the error path.Also adds a missing clk_put in osk_soc_exit.
Signed-off-by: Axel Lin
Acked-by: Jarkko Nikula
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown -
If aic3x_read failed , val is used uninitialized.
Fix it by initializing val to 0.This patch fixes below compile warning:
sound/soc/codecs/tlv320aic3x.c: In function 'aic3x_get_gpio':
sound/soc/codecs/tlv320aic3x.c:1183: warning: 'val' may be used uninitialized in this function
sound/soc/codecs/tlv320aic3x.c: In function 'aic3x_headset_detected':
sound/soc/codecs/tlv320aic3x.c:1211: warning: 'val' may be used uninitialized in this function
sound/soc/codecs/tlv320aic3x.c: In function 'aic3x_button_pressed':
sound/soc/codecs/tlv320aic3x.c:1219: warning: 'val' may be used uninitialized in this functionSigned-off-by: Axel Lin
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown
25 Nov, 2010
6 commits
-
Ensure that the prototype agrees with the definition and stop sparse
complaining when building the file.Signed-off-by: Mark Brown
Acked-by: Kukjin Kim
Acked-by: Jassi Brar
Acked-by: Liam Girdwood -
Signed-off-by: Mark Brown
Acked-by: Liam Girdwood -
Signed-off-by: Mark Brown
Acked-by: Jassi Brar
Acked-by: Liam Girdwood -
Supply a module exit function so that the driver can be unloaded.
Signed-off-by: Mark Brown
Acked-by: Jassi Brar
Acked-by: Liam Girdwood -
Fix the error path to properly free allocated resources.
Signed-off-by: Axel Lin
Acked-by: Jassi Brar
Acked-by: Liam Girdwood
Signed-off-by: Mark Brown