Takashi Iwai [Fri, 18 Jan 2013 15:38:08 +0000 (16:38 +0100)]
ALSA: hda - Correct more array rooms in hda_gen_spec
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.
Takashi Iwai [Fri, 18 Jan 2013 15:23:25 +0000 (16:23 +0100)]
ALSA: hda - Fix the wrong adc_idx for capture source
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.
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.
Takashi Iwai [Fri, 18 Jan 2013 13:37:16 +0000 (14:37 +0100)]
ALSA: hda - Add boost to line inputs, too
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.
Takashi Iwai [Fri, 18 Jan 2013 13:10:00 +0000 (14:10 +0100)]
ALSA: hda - Consolidate cap_sync_hook and capture_switch_hook
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.
Takashi Iwai [Fri, 18 Jan 2013 13:01:14 +0000 (14:01 +0100)]
ALSA: hda - Fix missing call of capture_switch_hook
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.
Takashi Iwai [Fri, 18 Jan 2013 10:07:15 +0000 (11:07 +0100)]
ALSA: hda - Look for boost controls more deeply
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.
Takashi Iwai [Fri, 18 Jan 2013 10:01:33 +0000 (11:01 +0100)]
ALSA: hda - Fix invalid mute in path activation
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.
Takashi Iwai [Fri, 18 Jan 2013 09:17:30 +0000 (10:17 +0100)]
ALSA: hda - Unify input label creations in generic parser
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.
Takashi Iwai [Fri, 18 Jan 2013 09:01:15 +0000 (10:01 +0100)]
ALSA: hda - Keep autocfg.input idx value in imux table
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.
Takashi Iwai [Thu, 17 Jan 2013 16:07:59 +0000 (17:07 +0100)]
ALSA: hda - Use generic parser for STAC/IDT codec driver
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.
Takashi Iwai [Thu, 17 Jan 2013 15:20:14 +0000 (16:20 +0100)]
Merge branch 'test/hda-gen-parser' into test/hda-migrate
* 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
Takashi Iwai [Thu, 17 Jan 2013 15:18:11 +0000 (16:18 +0100)]
ALSA: hda - Improve naming rule for primary output
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.
Takashi Iwai [Thu, 17 Jan 2013 09:25:15 +0000 (10:25 +0100)]
ALSA: hda - Move vmaster TLV parsing to snd_hda_gen_parse_auto_config()
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.
Takashi Iwai [Thu, 17 Jan 2013 08:52:11 +0000 (09:52 +0100)]
ALSA: hda - Add input jack mode enum controls to generic parser
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.
Takashi Iwai [Thu, 17 Jan 2013 07:49:01 +0000 (08:49 +0100)]
ALSA: hda - Minor cleanup/fixes for patch_sigmatel.c fixup transition
- 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
Takashi Iwai [Wed, 16 Jan 2013 17:20:07 +0000 (18:20 +0100)]
ALSA: hda - Add suppress_auto_mute flag to hda_gen_spec
A new flag to skip the auto-mute handling in the generic parser, just
like suppress_auto_mic flag. It has to be set before calling
snd_hda_gen_parse_auto_config().
Takashi Iwai [Wed, 16 Jan 2013 15:25:24 +0000 (16:25 +0100)]
Merge branch 'test/hda-gen-parser' into test/hda-migrate
* test/hda-gen-parser:
ALSA: hda - Make sure fill_all_dac_nids is called for digital only codecs
ALSA: hda - force different capture controls if amp caps differ
ALSA: hda - do not add non-existing Mic boost controls
ALSA: hda - initialize channel counts correctly
ALSA: hda - fix wrong adc_idx in generic parser
ALSA: hda - Check array bounds in get_input_path
ALSA: hda - Add prefer_hp_amp flag to hda_gen_spec
ALSA: hda - fix OOPS in hda_mark_cmd_cache_dirty
ALSA: hda - Check pincap while parsing the configuration
ALSA: hda - force different capture controls if amp caps differ
Otherwise setting the capture volume for amps will be weird and
inconsistent (it will try to set values outside the range of the
second amp based on capabilities of the first amp).
Signed-off-by: David Henningsson <david.henningsson@canonical.com> Signed-off-by: Takashi Iwai <tiwai@suse.de>
Takashi Iwai [Tue, 15 Jan 2013 17:45:53 +0000 (18:45 +0100)]
ALSA: hda - Add prefer_hp_amp flag to hda_gen_spec
Add a new flag to indicate whether HP amp is turned on as default for
speaker or line-outs, and enable this for ALC260 codec, as many
machines with this codec require the HP amp even for speakers.
Takashi Iwai [Mon, 14 Jan 2013 17:06:34 +0000 (18:06 +0100)]
ALSA: hda - Use standard fixup table for IDT92HD83xxx
Finally all codecs in patch_sigmatel.c have been converted to use the
standard fixup helpers. This change also includes trivial cleanups
like the call of common setup for GPIO LED or the removal of unused
function.
Takashi Iwai [Mon, 14 Jan 2013 16:05:25 +0000 (17:05 +0100)]
ALSA: hda - Use standard fixup table for IDT92HD71Bxx
This time, the only intrusive changes are for HP machines.
As the mute LED fixup and the bass speaker switch are required only
for HP machines, we can move these checks into the fixup entries; the
former is applied generically to all HP machines while the latter for
only certain models.
Takashi Iwai [Tue, 15 Jan 2013 07:45:33 +0000 (08:45 +0100)]
ALSA: hda - Check pincap while parsing the configuration
Sometimes (or rather often) BIOS sets the pin default configurations
obviously wrongly. Looking through these failures, one common pattern
is to enable some dead pins that are usually marked as speaker pins.
In such a case, we can skip them if the pins don't have the output
capability.
In this patch, add a check for the valid pin cap bit for each parsed
pin, and filter out when it's invalid.
Takashi Iwai [Mon, 14 Jan 2013 15:03:38 +0000 (16:03 +0100)]
ALSA: hda - Use standard fixup table for STAC927x
This conversion is a bit tricky. Since STAC927x may take two
different volume-knob initialization values depending on the model, a
new flag, spec->volknob_init, is introduced to indicate whether it's
the standard volume-knob initialization or not.
Also, Dell BIOS model is now directly mapped onto the fixup table
instead of parsing in the function. This resulted in a new model ref,
STAC_927X_DELL_BIOS_SPDIF, which is a chained entry.
Also, for reducing the fixups, virtual entries like
STAC_927X_DELL_DMIC and STAC_D965_VERBS are introduced.
Takashi Iwai [Mon, 14 Jan 2013 14:20:13 +0000 (15:20 +0100)]
ALSA: hda - Use standard fixup table for STAC922x
Rather straightforward conversion, except for ones for Intel Mac.
As Intel Mac have only unique codec SSIDs, we need to remap the fixup
again for the codec SSID and call the new fixup there.
Also, we can reduce model enums like STAC_MACMINI, which are model
aliases for backward compatibility, since they can be pointed directly
via hda_model_fixup table.
Takashi Iwai [Mon, 7 Jan 2013 11:27:36 +0000 (12:27 +0100)]
ALSA: hda - Use generic parser for VIA codec driver
Yet another step forward. As all features for VIA codecs have been
implemented in the generic driver, we can move on to migrate the VIA
codec parser, too.
Takashi Iwai [Fri, 21 Dec 2012 14:17:06 +0000 (15:17 +0100)]
ALSA: hda - Add generic parser support to Analog Device codec driver
This patch adds the support for the generic auto-parser to AD codec
driver. For AD1988, the old code is replaced simply with the new
generic parser. For other codecs, new model "auto" is added and
directed to use the generic parser.
No fixup codes have been implemented yet as of now. Eventually we'd
replace each static quirk with the generic parser + fixup.
Takashi Iwai [Wed, 19 Dec 2012 15:39:18 +0000 (16:39 +0100)]
ALSA: hda - Use generic parser for Cirrus codec driver
This time, the target is Cirrus codec. Its parser is a subset of
generic parser, so we can migrate fully with it now.
The only tricky part is the handling of SPDIF automute.
Cirrus driver sets the SPDIF out plug over the headphone. As a
workaround, set spec->gen.master_mute for toggling the headphone (and
other) mute.
Takashi Iwai [Wed, 19 Dec 2012 17:04:37 +0000 (18:04 +0100)]
ALSA: hda - Use generic parser for CA0110 codec
CA0110 codec is a fairly straightforward hardware implementation,
and we can use the generic parser almost as is.
Just set spec->multi_cap_vol flag to follow the current behavior.
Takashi Iwai [Wed, 19 Dec 2012 16:35:47 +0000 (17:35 +0100)]
ALSA: hda - Use generic codec parser for C-Media codecs
Replace the old parser code for C-Media auto-parser with the latest
generic parser. For compatibility reason, the static bindings are
still left, but they could be cleaned up in future.
Takashi Iwai [Thu, 10 Jan 2013 17:21:56 +0000 (18:21 +0100)]
ALSA: hda - Protect user-defined arrays via mutex
The pincfgs, init_verbs and hints set by sysfs or patch might be
changed dynamically on the fly, thus we need to protect it.
Add a simple protection via a mutex.
Takashi Iwai [Thu, 10 Jan 2013 16:33:58 +0000 (17:33 +0100)]
ALSA: hda/realtek - Generic mute LED implementation for HP laptops
As David Henningsson recently suggested, some HP laptops use an unused
mic pin for controlling a mute LED, and this information is provided
via DMI string "HP_Mute_LED_X_Y" string. This patch adds the generic
support for such cases, as we've already done in patch_sigmatel.c.
This is applied generically to all devices with ID 0x103c.
But as we don't know whether the device 103c:1586 really contains
HP_Mute_LED_X_Y DMI string, still keep the static setup for this
device using the mic2 pin 0x19.
Takashi Iwai [Thu, 10 Jan 2013 15:57:58 +0000 (16:57 +0100)]
ALSA: hda - Add output jack mode enum controls
Add the enum controls for changing the headphone amp bits of output
jacks, such as "Headphone Jack Mode". This feature isn't enabled as
default, so far, unless spec->add_out_jack_modes flag is set.
Takashi Iwai [Thu, 10 Jan 2013 15:10:06 +0000 (16:10 +0100)]
ALSA: hda - Update automute / automic upon jack retasking
When a multi-io jack is switched to another direction, call the
automute and autoswitch update functions, as this jack won't be used
as the headphone or the mic jack that may turn off others.
Takashi Iwai [Thu, 10 Jan 2013 09:18:14 +0000 (10:18 +0100)]
ALSA: hda - Add a new fixup type to override pinctl values
Add a new fixup type, HDA_FIXUP_PINCTLS, for overriding the pinctl
values of the given pins. It takes the same array of struct pintbl
like HDA_FIXUP_PINS, but each entry contains the pinctl value instead
of the pin default config value.
This patch also replaces the corresponding codes in patch_realtek.c.
Without this change, the direct call of verbs may be overridden again
by the later call of pinctl restoration by the driver.
Takashi Iwai [Thu, 10 Jan 2013 08:45:13 +0000 (09:45 +0100)]
ALSA: hda - Avoid auto-mute or auto-mic of retasked jacks
When a jack is retasked as a different direction (e.g. a mic jack is
used as a CLFE output), such a jack shouldn't be counted as the target
for the automatic jack switching. Skip the automute or the autoswitch
when the current pinctl direction is different from what we suppose.
Takashi Iwai [Thu, 10 Jan 2013 08:33:29 +0000 (09:33 +0100)]
ALSA: hda - Manage current pinctl values in generic parser
Use the new pin target accessors for managing the current pinctl
values in the generic parser. The pinctl values of all active pins
are once determined at the initialization phase, and stored via
snd_hda_codec_set_pin_target(). This will be referred again in the
codec init or resume phase to set the actual pinctl.
This value is kept while the auto-mute. When a line-out or a speaker
pin is muted by auto-mute, the driver simply disables the pin, but it
doesn't touch the cached pinctl target value. Upon unmute, this value
is used to restore the original pinctl in return.
Takashi Iwai [Thu, 10 Jan 2013 07:56:46 +0000 (08:56 +0100)]
ALSA: hda - More strict correction of invalid pinctl bits
Check more strictly about the validity of pinctl values in
snd_hda_set_pin_ctl() and correct the wrong bits automatically.
Also provide the helper function to correct pinctl bits to codec
drivers.
This automatically fixes the invalid pinctl writes that are found in
a few Realtek fixups for NID 0x0f amp like ASUS A6Rp.
Takashi Iwai [Wed, 9 Jan 2013 08:28:20 +0000 (09:28 +0100)]
ALSA: hda - Clear the dropped paths properly
When a DAC is reassigned from surrounds to front or ADCs are reduced
due to incomplete imux, we clear the path indices but the path
instances remain as is. Since the paths might be still referred
through the whole path list parsing (e.g. is_active_nid()), we should
clear these path instances as well.
Takashi Iwai [Wed, 9 Jan 2013 08:14:23 +0000 (09:14 +0100)]
ALSA: hda - Allow aamix as a capture source
Since some codecs can choose the aamix as a capture source, we should
support it as well. When spec->add_stereo_mix_input flag is set, the
parser checks the availability of aamix as the input source, and adds
the paths automatically when possible.
Takashi Iwai [Wed, 9 Jan 2013 08:06:18 +0000 (09:06 +0100)]
ALSA: hda - Fix inconsistent input_paths after ADC reduction
In the current parser code, the input_paths[] may become inconsistent
when some of detected ADCs are dropped due to incomplete inputs, since
the driver rearranges only adc_nids[] but doesn't touch input_paths[].
This patch fixes the issue, and also it optimizes the reachability
checks by simply referring to the parsed input_paths[] instead of
calling is_reachable() again for each connection.
Takashi Iwai [Wed, 9 Jan 2013 07:46:34 +0000 (08:46 +0100)]
ALSA: hda - Return "Headphone Mic" from hda_get_autocfg_input_label()
Instead of handling special cases in the caller side, give a proper
name string "Headphone Mic" from hda_get_autocfg_input_label() when
the headhpone jack pin is specified as an input.
Takashi Iwai [Mon, 7 Jan 2013 17:21:47 +0000 (18:21 +0100)]
ALSA: hda - Handle BOTH jack port as a fixed output
When the default config value shows the connection AC_JACK_PORT_BOTH,
it's better to handle it as a speaker pin. This makes the behavior
consistent in snd_hda_get_pin_label() and snd_hda_parse_pin_defcfg().
There are only few old machines showing this attribute, and all of
them are actually fixed speaker pins, as far as I know.
Takashi Iwai [Mon, 7 Jan 2013 16:25:08 +0000 (17:25 +0100)]
ALSA: hda - Re-define snd_hda_parse_nid_path()
This commit modifies the definition of snd_hda_parse_nid_path()
slightly, now with_aa_mix argument is changed to anchor_nid, so that
it can handle any NID generically as an anchor point to include or
exclude.
The with_aa_mix field in struct nid_path is removed again by this
change.
Takashi Iwai [Mon, 7 Jan 2013 15:44:06 +0000 (16:44 +0100)]
ALSA: hda - Fix multi-io channel mode management
The multi-io channels can vary not only from 1 to 6 but also may vary
from 6 to 8 or such. At the same time, there are more speaker pins
available than the primary output pins. So, we need three variables
to check: the minimum channel counts for primary outputs, the current
channel counts for primary outputs, and the minimum channel counts for
all outputs.
Takashi Iwai [Mon, 7 Jan 2013 14:11:44 +0000 (15:11 +0100)]
ALSA: hda - Use direct path reference in assign_out_path_ctls()
Instead of looking through paths with the dac -> pin connection at
each time, just pass the already parsed path index to
assign_out_path_ctls(). This simplifies the code a bit.
Takashi Iwai [Mon, 7 Jan 2013 14:07:00 +0000 (15:07 +0100)]
ALSA: hda - Clear path indices properly at each re-evaluation
The path indices must be reset at each evaluation of DAC assignment.
Otherwise the badness value will be wrongly calculated and mixers may
be inconsistently assigned.
Takashi Iwai [Mon, 7 Jan 2013 09:33:57 +0000 (10:33 +0100)]
ALSA: hda - Drop bind-volume workaround
The bind-volume workaround was introduced for simplifying the mixer
abstraction in the case where one or more pins of multiple outputs
lack of individual volume controls. This was essentially the case
like Acer Aspire 5935, which has 5.1 speakers and 5.1 (multi-io)
jacks although there are 5 DACs, so some of them must share a DAC.
However, the recent code rewrite changed the DAC assignment policy to
share with the same channel instead of binding to the front, thus
binding the volumes for all channels makes little sense now, rather
it's confusing. So in this patch, the ugly workaround is finally
dropped and simply create the volume control corresponding to the
parsed path position.
For dual headphones or 2.1 speakers with a shared volume control, it's
anyway bound to the same DAC if needed, so this change shouldn't bring
any practical difference.
And, as a good bonus, we can cut off the whole code handling the bind
volume elements.
Takashi Iwai [Mon, 7 Jan 2013 08:50:52 +0000 (09:50 +0100)]
ALSA: hda - Prefer binding the primary CLFE output
When 5.1 or more multiple speakers with found but not enough DACs are
available, it's better to bind such pins to the DACs of the primary
outputs with the same channels rather than binding to the first DAC
(i.e. the front channel). For the cases with two speaker pins, it's
rather regarded as front + bass combination, thus it's more practical
to still bind to the front, though.
Takashi Iwai [Mon, 7 Jan 2013 08:43:18 +0000 (09:43 +0100)]
ALSA: hda - Fix truncated control names
... like "Speaker Surround Playback Switch".
This fix had been already applied to patch_conexant.c but was
forgotten in other places, then migrated to hda_generic.c.
Takashi Iwai [Fri, 4 Jan 2013 15:42:48 +0000 (16:42 +0100)]
ALSA: hda - Add Loopback Mixing control
For codecs that have individual routes going through a loopback mixer
(like VIA codecs), we need to provide an explicit switch to choose
whether the output goes through mixer or directly from DAC.
This patch adds the check for such paths and creates "Loopback Mixing"
enum control when available.
It won't influence on codecs like Realtek or others where the loopback
mixer is connected independently from the primary output routes.
Takashi Iwai [Fri, 4 Jan 2013 14:41:41 +0000 (15:41 +0100)]
ALSA: hda - Correct aamix output paths
The output paths including aamix should be parsed only for the first
output. The surround paths including aamix must be wrong, since it
would mix all streams, i.e. all channels would be mixed into a single
and multiplexed again.