This patch adds a better power filter hook for powering down unused
widgets in the generic parser.

The feature is enabled by setting hda_gen_spec.power_down_unused
flag.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

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

Put the power state synchronization at the end of the parsing of
codec.  This is necessary when the power filter is changed during the
codec probe.  Since the first power-up sequence is performed without
the special filter, all widgets are supposed to be ON at this point.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Add a hook to struct hda_codec for filtering the target power state of
each widget when powering up/down.  The current hackish EAPD check is
implemented as the default hook pointer, too.

This allows codec drivers to implement own power filter.  In the
upcoming changes, the generic parser will have the better power filter
based on the active paths.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

AC_VERB_GET_POWER_STATE returns the combined bits of the actual state
and the target state.  Thus, comparing the obtained value directly
with the target value can't work.  The value has to be shifted and
masked properly.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

The arguments to call is_active_nid() in activate_amp() were swapped,
and this resulted in the muted amp on some SPDIF output pins.

Also, the index to be passed to is_active_nid() must be idx_to_check.
Otherwise it checks the wrong connection in the case of implicit aamix
connection paths.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Using the new chained_before flag, we can correct the headphone jack
detection capability easily over the existing ALC880 6stack model
(which disables the jack detection intentionally for compatibility
reason).

Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=901846Signed-off-by: Takashi Iwai <tiwai@suse.de>

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

Introduce a helper function to do the same thing.
Signed-off-by: Takashi 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: Takashi 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: Manolo Díaz <diaz.manolo@gmail.com>
Signed-off-by: Takashi 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: Takashi 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: 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>