[alsa-devel] why error return in sound/soc/codecs/pcm3168a.c::pcm3168a_set_dai_fmt ?
Alexandre Belloni
alexandre.belloni at bootlin.com
Mon Jul 1 15:06:09 CEST 2019
Hello,
On 04/06/2019 06:37:48+0000, Jurgen Lambrecht wrote:
> Hi,
>
> When following
> https://bootlin.com/blog/eight-channels-audio-on-i-mx7-with-pcm3168/ I
> get this error (from soc_core.c):
>
> ... kernel: [ 3.059634][ T15] pcm3168a 3-0039: ASoC: Failed to set
> DAI format: -22
>
> I could propose this patch (I get that printf when applying the patch)
> (all other errors in that file have a printf):
>
> diff --git a/sound/soc/codecs/pcm3168a.c b/sound/soc/codecs/pcm3168a.c
> index 08d3fe192e65..75ccbb919902 100644
> --- a/sound/soc/codecs/pcm3168a.c
> +++ b/sound/soc/codecs/pcm3168a.c
> @@ -353,6 +353,7 @@ static int pcm3168a_set_dai_fmt(struct snd_soc_dai *dai,
> case SND_SOC_DAIFMT_NB_NF:
> break;
> default:
> + dev_err(component->dev, "wrong INV_MASK\n");
> return -EINVAL;
> }
>
> But why does this code returns an error for code that has no effect?
> OK, it could be because SND_SOC_DAIFMT_INV_MASK must be
> SND_SOC_DAIFMT_NB_NF. But then Alexandre's blog contains an error,
> because the dac TDM sets frame-inversion in its dts (and it should not).
>
While I'm pretty sure what is in the blog is working (it is deployed in
production), I remember there was something fishy with frame-inversion.
I unfortunately don't remember the specifics.
Honestly, I would think you can remove frame-inversion safely as the
codec is only supposed to support NB_NF.
--
Alexandre Belloni, Bootlin
Embedded Linux and Kernel engineering
https://bootlin.com
More information about the Alsa-devel
mailing list