- 22 Jan, 2013 11 commits
-
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
Other remaining quirks are mostly resolvable via pincfg fixes, even if it matters. Signed-off-by: Takashi Iwai <tiwai@suse.de>
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
Signed-off-by: Takashi Iwai <tiwai@suse.de>
-
Takashi Iwai authored
The stuff that was dropped while transition to the generic parser is now recovered. Signed-off-by: Takashi Iwai <tiwai@suse.de>
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
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>
-
- 21 Jan, 2013 8 commits
-
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
Signed-off-by: Takashi Iwai <tiwai@suse.de>
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
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>
-
- 18 Jan, 2013 16 commits
-
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
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>
-
David Henningsson authored
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>
-
David Henningsson authored
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>
-
David Henningsson authored
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>
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
The pin configuration for the bass speaker needs to be corrected in a fixup. Signed-off-by: Takashi Iwai <tiwai@suse.de>
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
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>
-
Takashi Iwai authored
This resulted in non-working auto-mute behavior, of course... Signed-off-by: Takashi Iwai <tiwai@suse.de>
-
- 17 Jan, 2013 5 commits
-
-
Takashi Iwai authored
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. Signed-off-by: Takashi Iwai <tiwai@suse.de>
-
Takashi Iwai authored
* 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 authored
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. Signed-off-by: Takashi Iwai <tiwai@suse.de>
-
Takashi Iwai authored
Not only PCM playback, a hook for PCM capture would be required for power controls in codec drivers. Signed-off-by: Takashi Iwai <tiwai@suse.de>
-
Takashi Iwai authored
Since the generic parser reduces the ADC list, copy the list of the all detected ADCs and keep it. This list can be later referred by the codec driver for finer power controls. Signed-off-by: Takashi Iwai <tiwai@suse.de>
-