- 24 1月, 2013 1 次提交
-
-
由 Takashi Iwai 提交于
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>
-
- 23 1月, 2013 6 次提交
-
-
由 Takashi Iwai 提交于
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>
-
由 Takashi Iwai 提交于
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
-
由 Takashi Iwai 提交于
This is a preliminary merge before the upcoming merge of generic parser branch.
-
由 Takashi Iwai 提交于
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>
-
由 Takashi Iwai 提交于
Other remaining quirks are mostly resolvable via pincfg fixes, even if it matters. Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
由 Takashi Iwai 提交于
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>
-
- 22 1月, 2013 8 次提交
-
-
由 Takashi Iwai 提交于
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>
-
由 Takashi Iwai 提交于
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>
-
由 Takashi Iwai 提交于
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>
-
由 Takashi Iwai 提交于
Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
由 Takashi Iwai 提交于
The stuff that was dropped while transition to the generic parser is now recovered. Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
由 Takashi Iwai 提交于
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>
-
由 Takashi Iwai 提交于
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>
-
由 Takashi Iwai 提交于
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>
-
- 21 1月, 2013 9 次提交
-
-
由 Takashi Iwai 提交于
These are just compatible with other CX2075x codecs. Cc: <stable@vger.kernel.org> Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
由 Takashi Iwai 提交于
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>
-
由 Takashi Iwai 提交于
Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
由 Takashi Iwai 提交于
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>
-
由 Takashi Iwai 提交于
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>
-
由 Takashi Iwai 提交于
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>
-
由 Takashi Iwai 提交于
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>
-
由 Takashi Iwai 提交于
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>
-
由 Takashi Iwai 提交于
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>
-
- 19 1月, 2013 2 次提交
-
-
由 Takashi Iwai 提交于
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>
-
由 Takashi Iwai 提交于
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>
-
- 18 1月, 2013 14 次提交
-
-
由 Takashi Iwai 提交于
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>
-
由 Takashi Iwai 提交于
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>
-
由 David Henningsson 提交于
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>
-
由 David Henningsson 提交于
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>
-
由 David Henningsson 提交于
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>
-
由 Takashi Iwai 提交于
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>
-
由 Takashi Iwai 提交于
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>
-
由 Takashi Iwai 提交于
The pin configuration for the bass speaker needs to be corrected in a fixup. Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
由 Takashi Iwai 提交于
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>
-
由 Takashi Iwai 提交于
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: NTakashi Iwai <tiwai@suse.de>
-
由 David Henningsson 提交于
This machine also has the "HP_Mute_LED_0_A" string in DMI information. Cc: <stable@vger.kernel.org> BugLink: https://bugs.launchpad.net/bugs/1096789Tested-by: NTammy Yang <tammy.yang@canonical.com> Signed-off-by: NDavid Henningsson <david.henningsson@canonical.com> Signed-off-by: NTakashi Iwai <tiwai@suse.de>
-
由 Takashi Iwai 提交于
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: NTakashi Iwai <tiwai@suse.de>
-
由 Takashi Iwai 提交于
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: NTakashi Iwai <tiwai@suse.de>
-
由 Takashi Iwai 提交于
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: NTakashi Iwai <tiwai@suse.de>
-