add_control_with_pfx() in hda_generic.c assumes a shorter name string
for the control element, and this resulted in the truncation of the
long but valid string like "Headphone Surround Switch" in the middle.

This patch aligns the max size to the actual limit of snd_ctl_elem_id,
44.

Cc: <stable@vger.kernel.org> [v3.9+]
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Add a new flag, auto_mute_via_amp, to determine the behavior of the
headphone / line-out auto-mute.  When this flag is set, the generic
driver mutes the speaker and line outputs via the amp mute of each
pin, instead of changing the pin control values.

This is introduced for devices that don't work expectedly with the pin
control values; for example, some devices are known to keep enabling
the speaker outputs no matter which pin control values are set on the
speaker pins.

The driver doesn't check actually whether the pins have the output amp
caps, but assumes that the proper mixer (mute) controls are created on
all these pins.  If not the case, you can't use this flag for your
device.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The previous commit was written in the way to make the backport to
3.9.y easier, and left the duplicated open codes intentionally.
Now let's clean up the duplicated codes.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

VT1802 codec seems to reset EAPD of other pins in the hardware level,
and this was another reason of the silent headphone output on some
machines.  As a workaround, introduce a new flag indicating to keep
the EPAD on to the generic parser, and set it in patch_via.c.
Reported-by: NAlex Riesen <raa.lkml@gmail.com>
Cc: <stable@vger.kernel.org> [v3.9]
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Some codec drivers (VIA codecs and some Realtek fixups) set the
automute and automic hooks after calling
snd_hda_gen_parse_auto_config().  In the current code, the hook
pointers are referred only in snd_hda_gen_parse_auto_config() and
passed to snd_hda_jack_detect_enable_callback(), thus changing the
hook values won't change the actually called callbacks properly.

This patch fixes this bug by setting the static functions as the
primary callback functions for the jack detection, and let them
calling the appropriate hooks dynamically.

Cc: <stable@vger.kernel.org> [v3.9]
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

When an inactive path is powered down with spec->power_down_unused
flag, we should check the activity of each widget in the path whether
it's still referred from any active path.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

When setting up the aamix output paths, use the primary DAC instead of
the individual DAC for each output as default.  Otherwise multiple
DACs will be turned on for a single aamix widget, which results in
doubly or more volumes, because the duplicated signals will be sent
through all these DACs for a single stream.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

When we have a loopback mixer control, this should manage the state
whether the output paths include the aamix or not.  But the current
code blindly initializes the output paths with aamix = true, thus the
aamix is enabled unless the loopback mixer control is changed.

Also, update_aamix_paths() called by the loopback mixer control put
callback invokes snd_hda_activate_path() with aamix = true even for
disabling the mixing.  This leaves the aamix path even though the
loopback control is turned off.

This patch fixes these issues:
- Introduced aamix_default() helper to indicate whether with_aamix is
  true or false as default
- Fix the argument in update_aamix_paths() for disabling loopback
Reported-by: NLydia Wang <LydiaWang@viatech.com.cn>
Cc: <stable@vger.kernel.org> [v3.9+]
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Now that we have a flag for headphone mics, we can use that flag
in the jack creation instead of creating the jack manually.
Signed-off-by: NDavid Henningsson <david.henningsson@canonical.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This allows a specific mic to get the "Headphone Mic" name, in addition
to the existing "Headset Mic" name.

Also, it allows for a special mark: if the sequence number is set
to 0xc, that's an indication to prefer it for headset mic, and if it's
set to 0xd, that's an indication to prefer it for headphone mic.
Signed-off-by: NDavid Henningsson <david.henningsson@canonical.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

changed is not initialized in path_power_down_sync, but it is expected
to be false in case no change happened in the loop. So set it to
false.
Signed-off-by: NJiri Slaby <jslaby@suse.cz>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The lack of independent HP mode shouldn't be too bad, but currently
its badness is set a bit too high.  Let's lower it.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The standard badness values don't seem to fit to all preferences.
Some configuration prefer the side output over the headphone, some
want the speaker over the surround, etc.

This patch moves the badness table pointers into hda_gen_spec, so that
the codec driver can override them.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The generic parser should evaluate the availability of the independent
HP when specified.  Otherwise a DAC without the direct connection to
the corresponding pin may be assigned for the HP, but the driver
doesn't check it at all.  The problem was actually seen on some
machines with VT1708s or equivalent codec, where DAC0 is assigned to
HP although it can be connected only via aamix.

This patch adds the badness evaluation for the independent HP to make
it working properly.
Reported-by: NLydia Wang <LydiaWang@viatech.com.cn>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Instead of calling snd_hda_attach_beep_device() and
snd_hda_detach_beep_device() in each codec driver, move them to the
generic parser.  The codec driver just needs to set spec->beep_nid for
activating the digital beep.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

When a headphone pin is set up as a shared hp/mic pin, we rather want
to keep it as a headphone primarily as default, but the driver
overrides it always as a mic pin, just because the input controls are
created after outputs.  Add a check of pin NID and skip the
re-initialization of pinctl for such a shared hp/mic pin.
Reported-by: NJonathan Woithe <jwoithe@just42.net>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

When the headphone mic jack enum control is created (via explicitly
specification by user), it doesn't make much sense to change the I/O
direction dynamically per capture source change, since the I/O
direction is rather controlled over the enum ctl.

This also reduces the implicit dependency between the capture source
and the hp mic jack enum ctls, which might confuse a program accessing
the whole control elements at once like alsactl.

In addition, this patch introduces update_hp_automute_hook() function
to call the proper hook function.  It's just to remove the open codes
in multiple places in hda_generic.c.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

There is no big merit to distinguish these two hints.  Instead, just
have a single flag, add_jack_modes, for creating the jack mode enum
ctls for both I/O directions.

The hint string parser code is left and translated as add_jack_modes
just for keeping compatibility.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The previous commits added the capability to change the pin control of
hp/mic shared jack, but it actually didn't work as expected when the
value is changed from the output to the input, since I forgot to reset
the pin I/O bit in that case.  This patch fixes the problem.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

When a headphone jack is configured as a shared hp/mic jack, the jack
mode enum needs to handle both input and output directions.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This patch improves the generic parser code to allow to set up the
headphone jack as a mic input.  User can enable this feature by giving
hp_mic hint string.

The former shared hp/mic feature for the single built-in mic is still
retained.  This detection can be disabled now via hp_mic_detect hint
string, too.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The current badness value used for the missing multi-io seems too
weak, and the multi-io tends to be skipped for desktop configurations
when no enough DACs are available.  It's because the total badness of
the multi-io becomes often larger than the badness with assigning an
individual DAC to a headphone jack.  This is good for one side, but it
seems that the surround outputs are more demanded by that.

This patch increases the badness value for the missing multi-io
slightly so that the multi-io would be preferred than the individual
headphone DAC if they conflict.  Through the tests with hda-emu,
mostly only desktop configurations with ALC662/663 and CMI codecs are
affected by this change, and all look reasonable.
Reported-by: NRaymond Yau <superquad.vortex2@gmail.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

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

The loopback list is referred by the VIA codec driver no matter
whether CONFIG_PM is set or not, thus we need to enable it always.
Otherwise it gets compile errors.
Reported-by: NRandy Dunlap <rdunlap@infradead.org>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Because currently snd_printd() and snd_printdd() macros are expanded
to empty when CONFIG_SND_DEBUG=n, a compile warning like below
appears sometimes, and we had to covert it by ugly ifdefs:
  sound/pci/hda/patch_sigmatel.c: In function ‘stac92hd71bxx_fixup_hp’:
  sound/pci/hda/patch_sigmatel.c:2434:24: warning: unused variable ‘spec’ [-Wunused-variable]

For "fixing" these issues better, this patch replaces snd_printd() and
snd_printdd() definitions with empty inline functions instead of
macros.  This should have the same effect but shut up warnings like
above.

But since we had already put ifdefs, changing to inline functions
would trigger compile errors.  So, such ifdefs is removed in this
patch.

In addition, snd_pci_quirk name field is defined only when
CONFIG_SND_DEBUG_VERBOSE is set, and the reference to it in
snd_printdd() argument triggers the build errors, too.  For avoiding
these errors, introduce a new macro snd_pci_quirk_name() that is
defined no matter how the debug option is set.
Reported-by: NStratos Karafotis <stratosk@semaphore.gr>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

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: NTakashi 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: 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>

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>

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>

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>

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>