The commit e41975ed (ASoC: core: Fix the DAI name getting) added a break
within the "if (id < 0 || id >= pos->num_dai)" while the original design
of the search didn't break the loop if that condition contented but only
mark the ret error and let it go on to search the next component.

In a case like dmaengine which's not a dai but as a component sharing an
identical name with a dai, both the id and pos->num_dai here could be 0.
If we break the search, we may never find the dai we want as it might be
placed behind its dmaengine in the component list.

So this patch fixes the issue above by following the original design to
let the search carry on.
Signed-off-by: NNicolin Chen <Guangyu.Chen@freescale.com>
Signed-off-by: NMark Brown <broonie@linaro.org>

PTR_RET is deprecated. PTR_ERR_OR_ZERO should be used instead. However,
we already know that IS_ERR is true, and thus PTR_ERR_OR_ZERO would
never yield zero, so we can use PTR_ERR here.
Signed-off-by: NChristoph Jaeger <christophjaeger@linux.com>
Signed-off-by: NMark Brown <broonie@linaro.org>

Change reg's type from unsigned short to unsigned int. So that we can use
32 bits reg value in snd_soc_update_bits.
Signed-off-by: NBard Liao <bardliao@realtek.com>
Signed-off-by: NMark Brown <broonie@linaro.org>

Signed-off-by: NNariman Poushin <nariman@opensource.wolfsonmicro.com>
Signed-off-by: NMark Brown <broonie@linaro.org>

Signed-off-by: NNariman Poushin <nariman@opensource.wolfsonmicro.com>
Signed-off-by: NMark Brown <broonie@linaro.org>

There is an increasing amount of code that is very similar between platforms,
CODECS and other components. Making platforms a component will allow us to
share this code. For now the patch just adds component and component_driver
fields to the platform and platform_driver structs and registers the platform as
a component. Followup patches will be used to consolidate code between the
different types of components.
Signed-off-by: NLars-Peter Clausen <lars@metafoo.de>
Signed-off-by: NMark Brown <broonie@linaro.org>

snd_soc_unregister_component() takes the parent device of the component as a
parameter and then looks up the component based on this. This is a problem if
multiple components are registered for the same parent device. Currently drivers
do not do this, but some drivers register a CPU DAI component and a platform for
the same parent device. This will become a problem once platforms are also made
components. To make sure that snd_soc_unregister_component() will not
accidentally unregister the platform in such a case only consider components
that were registered with snd_soc_register_component(). This is only meant as
short term stopgap solution to be able to continue componentisation. Long term
we'll need something different.
Signed-off-by: NLars-Peter Clausen <lars@metafoo.de>
Signed-off-by: NMark Brown <broonie@linaro.org>

There are no ASoC drivers left that use them and new drivers are supposed to use
regmap for this.
Signed-off-by: NLars-Peter Clausen <lars@metafoo.de>
Signed-off-by: NMark Brown <broonie@linaro.org>

soc-core.c is getting quite crowded. Move all IO related functions that are
still in soc-core.c to soc-io.c
Signed-off-by: NLars-Peter Clausen <lars@metafoo.de>
Signed-off-by: NMark Brown <broonie@linaro.org>

SOC_SINGLE_XR_SX controls currently only work with CODECs that set the
'reg_word_size' field in their snd_soc_codec_driver struct. Going forward
support for ASoC level IO will eventually be removed and all drivers will be
converted to regmap. Preparing for the transition this patch adds support for
CODECs using regmap for IO to the SOC_SINGLE_XR_SX control. We already have the
val_bytes field in the CODEC struct which holds the number of bytes per word,
but it is only initialized when regmap is used. Also initialize it for drivers
still using legacy IO and update the SOC_SINGLE_XR_SX handlers to use it.
Signed-off-by: NLars-Peter Clausen <lars@metafoo.de>
Signed-off-by: NMark Brown <broonie@linaro.org>

The 'of_' is not appropriate here for there hasn't any DT parsing.
Signed-off-by: NXiubo Li <Li.Xiubo@freescale.com>
Signed-off-by: NMark Brown <broonie@linaro.org>

Before we had card level support for DAPM and controls machine drivers would
register their controls and DAPM elements with the CODEC. This required us to
temporarily unset the name_prefix of a CODEC during the rtd init callback to
avoid the machine level controls getting the CODEC's prefix. Now that all
machine drivers properly register their machine level controls and DAPM elements
with the card rather than with the CODEC we can drop the hack that sets the
CODEC's name_prefix to NULL while calling the DAI link or AUX dev init callback.
Signed-off-by: NLars-Peter Clausen <lars@metafoo.de>
Signed-off-by: NMark Brown <broonie@linaro.org>

Freeing the current list element while iterating over the list will cause a use
after free since the iterator function will still use the current element to
look up the next. Use list_for_each_safe() and remove the element from the list
before freeing it to avoid this.

Fixes: 1438c2f6 ("ASoC: Add a per component dai list")
Reported-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NLars-Peter Clausen <lars@metafoo.de>
Signed-off-by: NMark 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: NXiubo Li <Li.Xiubo@freescale.com>
Signed-off-by: NMark 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: NXiubo Li <Li.Xiubo@freescale.com>
Signed-off-by: NMark Brown <broonie@linaro.org>

Now that every DAI has a component we can track the DAIs on a per component
basis. This simplifies the DAI lookup when we are only interested in DAIs of a
specific component and also makes it possible to have multiple components with
the same parent device and also register DAIs.
Signed-off-by: NLars-Peter Clausen <lars@metafoo.de>
Signed-off-by: NMark Brown <broonie@linaro.org>

snd_soc_register_dais() looks up the CODEC that is registering the DAIs by
looping over all registered CODECs. This patch updates the code to
simply pass the CODEC that registers the DAIs to snd_soc_register_dais() thus
avoiding the lookup.
Signed-off-by: NLars-Peter Clausen <lars@metafoo.de>
Signed-off-by: NMark Brown <broonie@linaro.org>

snd_soc_register_dais() has basically the same code as snd_soc_register_dai(),
but running in a loop. The only difference is that snd_soc_register_dai() calls
fmt_single_name() to generate the DAIs name and snd_soc_register_dais() calls
fmt_multiple_name(). This patch pushes the check in __snd_soc_register_component()
which decides whether to call snd_soc_register_dai() or snd_soc_register_dais()
to snd_soc_register_dais() to decide which naming scheme to use. This allows us
to remove snd_soc_register_dai().

The patch also updates snd_soc_register_dais() to unregister every DAI it finds
for the component rather than trying to unregister one DAI for each DAI that was
registered. Both have the same result since there won't be more DAIs than what
have been registered, but the former is easier to implement.
Signed-off-by: NLars-Peter Clausen <lars@metafoo.de>
Signed-off-by: NMark Brown <broonie@linaro.org>

    In snd_soc_bytes_put function, it forces cpu to do cpu_to_be translation,
but for mmio bus which uses REGMAP_ENDIAN_NATIVE, it doesn't need to do
endian translation. So it is better to use regmap's api which can decide
if this translation is needed according to bus configuration.
Signed-off-by: NNenghua Cao <nhcao@marvell.com>
Signed-off-by: NMark Brown <broonie@linaro.org>

In preparation for componentization move the ignore_pmdown_time field from the
snd_soc_codec struct to the snd_soc_component struct. Set it to true for non
CODEC components for now.
Signed-off-by: NLars-Peter Clausen <lars@metafoo.de>
Signed-off-by: NMark Brown <broonie@linaro.org>

Keep track of which component registered a DAI. We'll need this as
componentization progresses.
Signed-off-by: NLars-Peter Clausen <lars@metafoo.de>
Signed-off-by: NMark Brown <broonie@linaro.org>

sound/soc/soc-core.c:2708:6-13: WARNING: Assignment of
bool to 0/1
sound/soc/soc-core.c:2726:3-10: WARNING: Assignment of
bool to 0/1

    More information about semantic patching is available at
http://coccinelle.lip6.fr/Signed-off-by: NNenghua Cao <nhcao@marvell.com>
Signed-off-by: NMark Brown <broonie@linaro.org>

sound/soc/soc-core.c:2708:6-13: WARNING: Assignment of
bool to 0/1
sound/soc/soc-core.c:2726:3-10: WARNING: Assignment of
bool to 0/1

    More information about semantic patching is available at
http://coccinelle.lip6.fr/Signed-off-by: NNenghua Cao <nhcao@marvell.com>
Signed-off-by: NMark Brown <broonie@linaro.org>

The implementations for enum and value enum controls are almost identical. The
only difference is that the value enum uses an additional look-up table to map
the control value to the register value, while the enum control uses a direct
mapping. Enums and value enums can easily be distinguished at runtime, for value
enums the values field of the snd_soc_enum struct contains the look-up table,
while for enums it is NULL. This patch adds two new small helper functions
called snd_soc_enum_item_to_val() and snd_soc_enum_val_to_item() which map
between register value and control item. If the items field of the snd_soc_enum
struct is NULL the function will do a direct mapping otherwise they'll use the
look-up table to do the mapping. Using these small helper functions it is
possible to use the same kcontrol handlers for both enums and value enums. The
functions are added a inline functions in soc.h so they can also be used by the
DAPM code to accomplish similar consolidation.
Signed-off-by: NLars-Peter Clausen <lars@metafoo.de>
Signed-off-by: NMark 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: NXiubo Li <Li.Xiubo@freescale.com>
Signed-off-by: NMark Brown <broonie@linaro.org>

For some CPU/CODEC DAI devices the TDM slot infomation maybe needed. This
patch adds the slot parsing from DT supports.

TDM slot properties:
    dai-tdm-slot-num : Number of slots in use.
    dai-tdm-slot-width :  Width in bits for each slot.

For instance:
    dai-tdm-slot-num = <2>;
    dai-tdm-slot-width = <8>;

And for each spcified driver, there could be one .of_xlate_tdm_slot_mask()
to specify a explicit mapping of the channels and the slots. If it's absent
the default snd_soc_of_xlate_tdm_slot_mask() will be used to generating the
tx and rx masks.

For snd_soc_of_xlate_tdm_slot_mask(), the tx and rx masks will use a 1 bit
for an active slot as default, and the default active bits are at the LSB of
the masks.
Signed-off-by: NXiubo Li <Li.Xiubo@freescale.com>
Signed-off-by: NMark Brown <broonie@linaro.org>

The name "max" in struct soc_enum is rather confusing since it
actually takes the number of items.  With "max", one might try to
assign (nitems - 1) value.

Rename the field to a more appropriate one, "items", which is also
used in struct snd_ctl_elem_info, too.

This patch also rewrites some code like "if (x > e->nitems - 1)" with
"if (x >= e->nitems)".  Not only the latter improves the readability,
it also fixes a potential bug when e->items is zero.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>
Acked-by: NLiam Girdwood <liam.r.girdwood@linux.intel.com>
Acked-by: NLars-Peter Clausen <lars@metafoo.de>
Signed-off-by: NMark Brown <broonie@linaro.org>

Also remove superfluous card->dev assignment.
Reviewed-by: NMark Brown <broonie@linaro.org>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This patch adds snd_soc_of_parse_audio_simple_widgets() and supports
below style of widgets name on DT:

	"template-wname", "user supplied wname"

For instance:
	simple-audio-widgets =
		"Microphone", "Microphone Jack",
		"Line", "Line In Jack",
		"Line", "Line Out Jack",
		"Headphone", "Headphone Jack",
		"Speaker", "Speaker External";

The "template-wname" currently includes: "Microphone", "Line", "Headphone"
and "Speaker".
Signed-off-by: NXiubo Li <Li.Xiubo@freescale.com>
Signed-off-by: NMark Brown <broonie@linaro.org>

Some codecs use signed volume control representation with non standard
register sizes, e.g. 6 or 7 bit signed integers.

This patch adds generic signed register volume control logic to
soc-core. Instead of a fixed width signed register control, this
implementation uses a 'min' value and the signed bit location to translate
it to an absolute volume. Using the 'sign_bit' we can calculate a
correct mask for the register values and translate it back into signed
integers of standard size.
Signed-off-by: NMarkus Pargmann <mpa@pengutronix.de>
Signed-off-by: NMark Brown <broonie@linaro.org>

Make it easier for generic code to work with set_tdm_slot() by distinguishing
between the operation not being supported and an error as is done.
Signed-off-by: NXiubo Li <Li.Xiubo@freescale.com>
Signed-off-by: NMark Brown <broonie@linaro.org>

Make it easier for generic code to work with set_sysclk() by distinguishing
between the operation not being supported and an error as is done for
other operations like set_dai_fmt()
Signed-off-by: NMark Brown <broonie@linaro.org>

Connect the DAPM graph through each BE DAI link to the componnent(s) on the
other side of the BE DAI link. This allows the graph to be walked on
both sides of the link when graph changes are made.
Signed-off-by: NLiam Girdwood <liam.r.girdwood@linux.intel.com>
Signed-off-by: NMark Brown <broonie@linaro.org>

From "ASoC: make snd_soc_dai_link more symmetrical", can we see that
the name of CPU DAI maybe omitted. If the DAI name is omitted, try to
use the component name instead.
Signed-off-by: NXiubo Li <Li.Xiubo@freescale.com>
Signed-off-by: NMark Brown <broonie@linaro.org>

snd_soc_bytes_put treats the data in the binary control as big endian
words, however snd_soc_bytes_get uses the endian of the host machine.
This causes the two functions to be inconsistant with how the mask is
applied on little endian machines.

This patch applies the big_endian format used in snd_soc_bytes_put to
snd_soc_bytes_get.
Signed-off-by: NCharles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: NMark Brown <broonie@linaro.org>

It's quite popular that more drivers are using pinctrl PM, for example:
(Documentation/devicetree/bindings/arm/primecell.txt). Just like what
runtime PM does, it would deactivate and activate pin group depending
on whether it's being used or not.

And this pinctrl PM might be also beneficial to cpu dai drivers because
they might have actual pinctrl so as to sleep their pins and wake them
up as needed.

To achieve this goal, this patch sets pins to the default state during
resume or startup; While during suspend and shutdown, it would set pins
to the sleep state.

As pinctrl PM would return zero if there is no such pinctrl sleep state
settings, this patch would not break current ASoC subsystem directly.

[ However, there is still an exception that the patch can not handle,
that is, when cpu dai driver does not have pinctrl property but another
device has it. (The AUDMUX <-> SSI on Freescale i.MX6 series for example.
SSI as a cpu dai doesn't contain pinctrl property while AUDMUX, an Audio
Multiplexer, has it). In this case, this kind of cpu dai driver needs to
find a way to obtain the pinctrl property as its own, by moving property
from AUDMUX to SSI, or creating a pins link/dependency between these two
devices, or using a more decent way after we figure it out. ]
Signed-off-by: NNicolin Chen <b42378@freescale.com>
Signed-off-by: NMark Brown <broonie@linaro.org>

The provided texts aren't guaranteed to be in the fixed size.
Spotted by coverity CID 139318.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>
Signed-off-by: NMark Brown <broonie@linaro.org>

Current snd_soc_of_get_dai_name() needs .of_xlate_dai_name()
callback on each component drivers.
But required behavior on almost all these drivers is
just returns its indexed driver's name.

This patch adds this feature as default behavior.
.of_xlate_dai_name() can overwrite it.
Signed-off-by: NKuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: NMark Brown <broonie@linaro.org>

ASoC sound driver requires CPU/CODEC drivers for probing,
and each CPU/CODEC has some DAI on it.
Then, "dai name matching" have been used to identify
CPU-CODEC DAI pair on ASoC.

But, the "dai port number matching" is now required from DeviceTree.
The solution of this issue is to replace
the dai port number into dai name.
Now, CPU/CODEC are based on struct snd_soc_component,
and it can care above as common issue.

This patch adds .of_xlate_dai_name callback interface
on struct snd_soc_component_driver,
and snd_soc_of_get_dai_name() which is using .of_xlate_dai_name.

Then, #sound-dai-cells which enables DAI specifier is required
on CPU/CODEC device tree properties.
Signed-off-by: NKuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: NMark Brown <broonie@linaro.org>

Codec includes component by this patch,
and component moved to upside of codec
to avoid extra declaration.
Codec dai will be registered via component
by this patch.

Current component register function
is used for cpu, and it is using
dai/dais functions properly to keep
existing cpu dai name.

And now, it will be used from codec also.
But codec driver had been used dais function only
even though it was single dai.
This patch adds new flag which can selects
dai/dais function on component register
function to keep existing codec dai name.
Signed-off-by: NKuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: NMark Brown <broonie@linaro.org>