Since both snd_hda_codec_flush_amp_cache() and
snd_hda_codec_flush_cmd_cache() are called usually at the same time,
we can simply combine them to a single function,
snd_hda_codec_flush_cache().
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The capture volume put callback may call the node selection change,
and its actual call won't be triggered unless flushed.  In general,
we always need to call both snd_hda_codec_flush_amp_cache() and
snd_hda_codec_flush_cmd_cache() at the same place...
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The stuff that was dropped while transition to the generic parser is
now recovered.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Both the HP auto-mute and the independent HP mode conflict with each
other.  Make HP auto-mute disabled (only for the affected HP jack)
during the driver is in HP independent mode.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

It'd be better to give another name to the secondary (alt) analog PCM
stream, which is dedicated for the independent HP out and extra
inputs.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The aamix NIDs are also missing for AD codecs.  All AD codecs seem to
have a (more or less) working aamix widget.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

IDT codecs have analog-loopback mixer widgets, but we haven't cared
about it, so far.  Let's set them.  This will avoid also possible
wrong routes for the input paths.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The original VIA codec parser enabled it as default, so let's keep the
behavior as it was.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This patch eventually fixes two issues:
- Handle the case where the primary output is a headphone and can have
  independent HP mode;
  so far we checked only the case where the headphone is the secondary
  output.

- Fix the conflict of HP independent mode and aamix mode;
  when switched to aamix mode, the DAC might be also switched to
  another widget shared with other outputs.  Then even if we disable
  the DAC for the original output, it doesn't change -- because the
  active route is from another (shared) DAC to HP pin through aamix.
  So, in such a case, we have to prohibit the switch to aamix for HP
  routes.

This fixes issues appearing on VT codecs.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Many codecs provide routes to multiple output pins through an aamix
widget, but most of them do it only from a single DAC.  However, the
current generic parser checks only the aamix paths from the original
(directly bound) DACs through aamix NID, and miss the path:
  primary DAC -> aamix -> target out pin

This patch adds a more check for the routes like the above.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

When a patch couldn't be resolved in try_assign_dacs() although the
target DAC is expected, we forgot to add a proper badness value but
continued.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Since fill_and_eval_dacs() may be called repeatedly with different
configurations, setting pinctls at each time there isn't optimal.
We can set it better only once after deciding the output configuration
in parse_output_paths().
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Print the information of outputs in a bit more details and concisely
in a single place instead of printing the path at each time when
detected.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Conexant CX20551 codec has a mixer in NID 0x19 and a few outputs have
to take the input through this widget.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Looking through the whole definitions, some fields have inappropriate
array sizes, especially about the capture.  The array assigned to each
input (pin) should have HDA_MAX_NUM_INPUTS entries while the array
assigned to each ADC should have AUTO_CFG_MAX_INS entries.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The patch "ALSA: hda - fix wrong adc_idx in generic parser" fixed the
adc_idx for the capture volume and capture switch controls.  But also
modified the adc_idx retrieval for the capture source controls
wrongly.  As multiple capture source controls are created in a single
shot with counts > 1, the id.index doesn't contain the real value.
The real index has to be taken via snd_ctl_get_ioffidx() as in the
original code.

This patch reverts the fixes partially to recover from the
regression.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

If there's one each of HDMI and SPDIF, we should not add an index
on the one that comes second.

[slight code refactoring by tiwai]
Signed-off-by: NDavid Henningsson <david.henningsson@canonical.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Just stumbled over this one while reading the code.
Signed-off-by: NDavid Henningsson <david.henningsson@canonical.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

I found a codec configuration which had six inputs, so the max of
five was not appropriate.
Signed-off-by: NDavid Henningsson <david.henningsson@canonical.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Some BIOS version of FSC Lifebook S7110 laptop seems to give a wrong
default pin config for NID 0x15, which confuses the parser.  Give a
fixup to correct the value.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Although I commented that boost volumes would be added only for
line-in and mic pins in the source code, the actual code excludes but
for mic-in.  Fix it to accept the line-ins, too.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The pin configuration for the bass speaker needs to be corrected in a
fixup.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Two hooks in hda_gen_spec, cap_sync_hook and capture_switch_hook, play
very similar roles.  The only differences are that the former is
called more often (e.g. at init or switching capsrc) while the latter
can take an on/off argument.

As a more generic implementation, consolidate these two hooks, and
pass snd_ctl_elem_value pointer as the second argument.  If the
secondary argument is non-NULL, it can take the on/off value, so the
caller handles it like the former capture_switch_hook.  If it's NULL,
it's called in the init or capsrc switch case.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

When a standard capture switch without multiple binding is used, the
call for capture_switch_hook isn't called properly.  Replace the put
ops to add the hook call in that case.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

In the current generic parser code, we look for the (mic) boost
controls only on input pins.  But many codecs assign the boost volume
to a widget connected to each input pin instead of the input amp of
the pin itself.

In this patch, the parser tries to look through more widgets connected
to the pin and find a boost amp.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

When an amp in the activation path is associated with mixer controls,
activate_amp() tries to skip the initialization.  It's good, but only
if the mixer really initializes both mute and volume.  Otherwise,
either the mute of the volume is left uninitialized.

This patch adds this missing check and properly initialize the
partially controlled amps in an activation path.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

There are a few places creating the labels and indices of kctls for
each input pin in the current generic parser code.  This is redundant
and makes harder to maintain.  Let's create the labels and indices at
once and keep them in hda_gen_spec.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Since the imux table entries can be a subset of autocfg.input table,
the indices of these aren't always same.  For passing the proper index
value of autocfg.input at creating input ctl labels (via
snd_hda_autocfg_input_label()), keep the corresponding autocfg.input
idx value in the index field of each imux item, which isn't used in
the generic driver.

Also, this makes easier to check the invalid imux pin for stereo mix.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This resulted in non-working auto-mute behavior, of course...
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Finally we reached here.  All codecs driver (except for CA0132, which
has really device-specific requirements) have been converted to use
the generic parser.

This patch appears bigger than others since it also involves with the
code shuffling, but mostly the cut-off of parser codes and adapt to
the generic parser flags.  Most of fixup codecs haven't been changed
but just removed a few unnecessary codes.

The only missing stuff is the SPDIF mux control.  It'll be added again
later.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

* test/hda-gen-parser:
  ALSA: hda - Improve naming rule for primary output
  ALSA: hda - Add PCM capture hook to hda_gen_spec
  ALSA: hda - Record all detected ADCs in hda_gen_spec
  ALSA: hda - Move vmaster TLV parsing to snd_hda_gen_parse_auto_config()
  ALSA: hda - Add input jack mode enum controls to generic parser
  ALSA: hda - Give more comments to hda_gen_spec flags
  ALSA: hda - Add suppress_auto_mute flag to hda_gen_spec
  ALSA: hda - Record the current speaker / LO mute status in hda_gen_spec
  ALSA: hda - Properly call automute/switch hooks at init

When the volume or mute control of the primary output is shared with
other (headphone or speaker) outputs, we shouldn't name it as a
specific output type but rather name it with the channel name or a
generic name like "PCM".

Also, this check should be performed individually for the volume and
the mute controls because some codecs may have shared volumes but
separate mute controls.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Not only PCM playback, a hook for PCM capture would be required for
power controls in codec drivers.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Since the generic parser reduces the ADC list, copy the list of the
all detected ADCs and keep it.

This list can be later referred by the codec driver for finer power
controls.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Add vmaster_tlv[] to hda_gen_spec and store the suggested TLV data
in snd_hda_gen_parse_auto_config().  This allows the codec driver to
correct the TLV data (e.g. mute capability) before actually creating
vmaster instance.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Just like the jack mode enum ctls for output jacks, add the support
for similar enum ctls for input pins to control the bias Vref.
The new controls will be added when spec->add_in_jack_modes is set
either by the codec driver or by a hint string.

Note that ground and 100% vrefs are excluded from the list for
simplicity, currently.  We may add a new flag to allow them, too.
But I guess it's easier to put a value override in the pinfix in such
a case.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

- spec->hp_detect has to be overridden in HDA_FIXUP_ACT_PARSE, not in
  PRE_PARSE.
- Remove err == 0 check but return directly -EINVAL from
  stac92xx_parse_auto_config()
- Set spec->default_polarity for 92HD71bxx
- Some code shuffles
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Since we have many bit flags in hda_gen_spec, rearrange in sections
and give more comments there.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>