On 12/06/2020 11.59, Peter Ujfalusi wrote:
> The audio support on the board is using pcm3168a codec connected to McASP10
> serializers in parallel setup.
> The pcm3168a SCKI clock is coming via the j721e AUDIO_REFCLK2 pin.
> In order to support 48KHz and 44.1KHz family of sampling rates the parent
> clock
> for AUDIO_REFCLK2 needs to be changed between PLL4 (for 48KHz) and PLL15 (for
> 44.1KHz). The same PLLs are used for McASP10's AUXCLK clock via different
> HSDIVIDER.
>
> Generic card can not be used for the board as we need to switch between
> clock paths for different sampling rate families and also need to change
> the slot_width between 16 and 24 bit audio.
>
> The audio support on the Infotainment Expansion Board consists of McASP0
> connected to two pcm3168a codecs with dedicated set of serializers to each.
> The SCKI for pcm3168a is sourced from j721e AUDIO_REFCLK0 pin.
> It is extending the audio support on the CPB.
>
> Due to the fact that the same PLL4/15 is used by both domains (CPB/IVI)
> there are cross restriction on sampling rates.
>
> The IVI side is represented as multicodec setup.
>
> PCMs available on a plain CPB (no IVI addon):
> hw:0,0 - cpb playback (8 channels)
> hw:0,1 - cpb capture (6 channels)
>
> When the IVI addon is present, additional two PCMs will be present:
> hw:0,2 - ivi multicodec playback (16 channels)
> hw:0,3 - ivi multicodec capture (12 channels)
>
> Signed-off-by: Peter Ujfalusi <[email protected]>
> ---
> sound/soc/ti/Kconfig | 8 +
> sound/soc/ti/Makefile | 2 +
> sound/soc/ti/j721e-evm.c | 887 +++++++++++++++++++++++++++++++++++++++
> 3 files changed, 897 insertions(+)
> create mode 100644 sound/soc/ti/j721e-evm.c
> diff --git a/sound/soc/ti/j721e-evm.c b/sound/soc/ti/j721e-evm.c
> new file mode 100644
> index 000000000000..096f045a1120
> --- /dev/null
> +++ b/sound/soc/ti/j721e-evm.c
...
> +static int j721e_get_clocks(struct device *dev,
> + struct j721e_audio_clocks *clocks, char *prefix)
> +{
> + struct clk *parent;
> + char *clk_name;
> + int ret;
> +
> + clocks->target = devm_clk_get(dev, prefix);
> + if (IS_ERR(clocks->target)) {
> + ret = PTR_ERR(clocks->target);
> + if (ret != -EPROBE_DEFER)
> + dev_err(dev, "failed to acquire %s': %d\n",
Looks like I have extra "'" in the prints...
> + prefix, ret);
> + return ret;
> + }
> +
> + clk_name = kasprintf(GFP_KERNEL, "%s-48000", prefix);
> + if (clk_name) {
> + parent = devm_clk_get(dev, clk_name);
> + kfree(clk_name);
> + if (IS_ERR(parent)) {
> + ret = PTR_ERR(parent);
> + if (ret != -EPROBE_DEFER)
> + dev_err(dev, "failed to acquire %s': %d\n",
> + prefix, ret);
> + return ret;
It should be like this to really not fail with single PLL (from DT), but
it is not documented and supported officially.
if (ret == -EPROBE_DEFER)
return ret;
dev_dbg(dev, "no 48KHz parent for %s: %d\n", prefix, ret);
parent = NULL;
> + }
> + clocks->parent[J721E_CLK_PARENT_48000] = parent;
> + } else {
> + return -ENOMEM;
> + }
> +
> + clk_name = kasprintf(GFP_KERNEL, "%s-44100", prefix);
> + if (clk_name) {
> + parent = devm_clk_get(dev, clk_name);
> + kfree(clk_name);
> + if (IS_ERR(parent)) {
> + ret = PTR_ERR(parent);
> + if (ret != -EPROBE_DEFER)
> + dev_err(dev, "failed to acquire %s': %d\n",
> + prefix, ret);
> + return ret;
and here
> + }
> + clocks->parent[J721E_CLK_PARENT_44100] = parent;
> + } else {
> + return -ENOMEM;
> + }
then:
if (!clocks->parent[J721E_CLK_PARENT_44100] &&
!clocks->parent[J721E_CLK_PARENT_48000]) {
dev_err(dev, "At least on parent clock is needed for %s\n",
prefix);
return -EINVAL;
}
> +
> + return 0;
> +}
- Péter
Texas Instruments Finland Oy, Porkkalankatu 22, 00180 Helsinki.
Y-tunnus/Business ID: 0615521-4. Kotipaikka/Domicile: Helsinki
