ALSA: hda/realtek: add more delay time before determine_headset_type

We found a recording issue on the headset-mic recently, sometimes
users plug a headset and select headset-mic from UI, but can't record
any sound from headset-mic. The root cause is the
determine_headset_type() returns a wrong type, e.g. users plug a ctia
type headset, but that function returns omtp type.

In the past, determine_headset_type() worked well because the internal
mic is connected to the codec, so the "Input Source" or
"Capture Source" is internal mic by default when users plug a headset,
the determine_headset_type() will not be called unless users select
headset-mic from UI, when users select headset-mic, the plugging
action already finished and the headset is completely plugged into the
jack, so determine_headset_type() could return a correct type.

But more and more machines connect the internal mic to the PCH now,
and the "Input Source" is headset mic by default, when users plug a
headset, the determine_headset_type() will be called immediately, if
the headset is not completely plugged in, it will return a wrong type.

Here add 2s delay before calling determine_headset_type(), and since
there is a pop-up dialogue when users do plugging action, to avoid
freezing the UI, use the deleyed_work to call that function.

Signed-off-by: Hui Wang <hui.wang@canonical.com>
---
 sound/pci/hda/patch_realtek.c | 31 ++++++++++++++++++++++++-------
 1 file changed, 24 insertions(+), 7 deletions(-)

On 3/16/21 10:17 PM, Takashi Iwai wrote:
> On Tue, 16 Mar 2021 12:55:49 +0100,
> Hui Wang wrote:
>> We found a recording issue on the headset-mic recently, sometimes
>> users plug a headset and select headset-mic from UI, but can't record
>> any sound from headset-mic. The root cause is the
>> determine_headset_type() returns a wrong type, e.g. users plug a ctia
>> type headset, but that function returns omtp type.
>>
>> In the past, determine_headset_type() worked well because the internal
>> mic is connected to the codec, so the "Input Source" or
>> "Capture Source" is internal mic by default when users plug a headset,
>> the determine_headset_type() will not be called unless users select
>> headset-mic from UI, when users select headset-mic, the plugging
>> action already finished and the headset is completely plugged into the
>> jack, so determine_headset_type() could return a correct type.
>>
>> But more and more machines connect the internal mic to the PCH now,
>> and the "Input Source" is headset mic by default, when users plug a
>> headset, the determine_headset_type() will be called immediately, if
>> the headset is not completely plugged in, it will return a wrong type.
>>
>> Here add 2s delay before calling determine_headset_type(), and since
>> there is a pop-up dialogue when users do plugging action, to avoid
>> freezing the UI, use the deleyed_work to call that function.
> Hm, two seconds are quite long, IMHO.  How is this delay determined?
>
>
> Takashi

Two seconds delay is for a latest Dell AIO machine, and this issue is 
exposed on that machine. The audio jack is designed to the left side of 
that AIO machine, users need to use left hand to plug a headset, and 
since it is an AIO, it is similar to plug sth to the left side on a 
monitor, users usually don't use the great force to plug otherwise they 
could introduce the movement of monitor; sometimes they use left hand to 
plug a headset, the headset is not 100% plugged in, meanwhile they need 
to put the right hand to the right side of the monitor to fix the 
monitor. All these actions make the plugging not finished as fast as on 
laptops or normal desktops. Our QA tested different delays, it has a 
pretty good chance to return the correct type after adding two seconds 
delay on that AIO machine. And I guess all Dell AIO machines will face 
the same issue since they all have multi-function audio jack.


And I did a test on some Dell laptops, on which the internal mic 
connects to the PCH, if I plug the headset a bit slower than normal 
speed on purpose, the determine_headset_type() has some chance to return 
the wrong type and make the headset-mic can't record sound. Adding two 
seconds delay could make them work more stable.


Thanks,

Hui.