This is a merge of really big changes: the generic parser is heavily
enhanced for handling all cases, based on the former Realtek codec
driver code.  And all codec drivers except for a few ones (CA0132,
HDMI and modem) have been converted to use the new generic driver.

Conflicts:
	sound/pci/hda/patch_realtek.c

This is a preliminary merge before the upcoming merge of generic parser
branch.

Now all AD codecs have the proper BIOS auto-parser, and we can make
it for default, finally.  (AD1988 already did it because it had the
auto-parser.)
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Other remaining quirks are mostly resolvable via pincfg fixes, even if
it matters.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

As done for patch_conexant.c, put ifdef ENABLE_AD_STATIC_QUIRKS for
preparing t odrop the static quirk codes in patch_analog.c.

The whole static quirk code can be omitted by commenting out
ENABLE_AD_STATIC_QUIRKS define now.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

AD codecs have strange implementations for choosing the SPDIF-output
mux source: the digital audio out widget may take the sources from
multiple connections, where 0x01 indicates it's a PCM while others
point ADCs.  It's obviously invalid in the HD-audio spec POV, but it's
somehow convincing, too.  And, to make things more complex, AD1988A
and AD1882 have deeper connection routes that aren't expressed
correctly.

In this patch, the SPDIF mux control is implemented in two ways:
- For easier one like AD1981, AD1983, AD1884 and AD1984, where the
  SPDIF audio out widget takes just two or three sources, we can
  simply implement via the normal input_mux and connection verb
  calls.

- For the complex routes like AD1988A (but not AD1988B) or AD1882, we
  prepare "faked" paths represented statically, and switch the paths
  using these static ones, instead of parsing the routes from the
  widget tree.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

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: Takashi 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: Takashi Iwai <tiwai@suse.de>

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

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

These are just compatible with other CX2075x codecs.

Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi 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: Takashi Iwai <tiwai@suse.de>

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

Acer AO725 needs the same fixup as AO756.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=52181Signed-off-by: Takashi 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: Takashi 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: Takashi 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: Takashi 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: David Henningsson <david.henningsson@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

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

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

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

This machine also has the "HP_Mute_LED_0_A" string in DMI information.

Cc: <stable@vger.kernel.org>
BugLink: https://bugs.launchpad.net/bugs/1096789Tested-by: Tammy Yang <tammy.yang@canonical.com>
Signed-off-by: David Henningsson <david.henningsson@canonical.com>
Signed-off-by: Takashi 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: Takashi 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: Takashi 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: Takashi 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: Takashi Iwai <tiwai@suse.de>

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