Merge the 3.8 devel branch for correcting the newly added PB desktop
fixup with the automute support.

A Packard-Bell desktop machine gives no proper pin configuration from
BIOS.  It's almost equivalent with the 6stack+fp standard config, just
take the existing fixup.

Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=901846

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

Sometimes we want to call a fixup after applying other existing
fixups, but currently the fixup chain mechanism allows only the call
the others after the target fixup.  This patch adds a new flag,
chained_before, to struct hda_fixup, for allowing the chained call
before the current execution.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Introduce a helper function to do the same thing.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

AD1988 family and AD1882 codecs have another mixer widget (0x21)
between the analog-loopback mixer widget (0x20) and the actual
outputs.  Due to this hole, the analog-loopbacks aren't sent properly
to the output pins.

As a band-aid fix, introduce another fields holding the aamix merge
path, and activate it.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The commit [26a6cb6c: ALSA: hda - Implement a poll loop for jacks as a
module parameter] introduced the polling jack detection code, but it
also moved the call of snd_hda_jack_set_dirty_all() in the resume path
after resume/init ops call.  This caused a regression when the jack
state has been changed during power-down (e.g. in the power save
mode).  Since the driver doesn't probe the new jack state but keeps
using the cached value due to no dirty flag, the pin state remains
also as if the jack is still plugged.

The fix is simply moving snd_hda_jack_set_dirty_all() to the original
position.
Reported-by: NManolo Díaz <diaz.manolo@gmail.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The fixup function is called multiple times before parsing the pins,
so snd_BUG_ON() hits when loaded.  Move it to the proper place in the
if block.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

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: NTakashi Iwai <tiwai@suse.de>

Other remaining quirks are mostly resolvable via pincfg fixes, even if
it matters.
Signed-off-by: NTakashi 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: NTakashi 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: NTakashi 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: 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>

These are just compatible with other CX2075x codecs.

Cc: <stable@vger.kernel.org>
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>

Acer AO725 needs the same fixup as AO756.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=52181Signed-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>