lkml.org 
[lkml]   [2022]   [Jun]   [17]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
SubjectRe: [PATCH v3 1/3] ASoC: rockchip: i2s: switch BCLK to GPIO
Hi,

On Fri, Jun 17, 2022 at 04:42:49AM +0000, Judy Hsiao wrote:
> We discovered that the state of BCLK on, LRCLK off and SD_MODE on
> may cause the speaker melting issue. Removing LRCLK while BCLK
> is present can cause unexpected output behavior including a large
> DC output voltage as described in the Max98357a datasheet.
>
> In order to:
> 1. prevent BCLK from turning on by other component.
> 2. keep BCLK and LRCLK being present at the same time
>
> This patch switches BCLK to GPIO func before LRCLK output, and
> configures BCLK func back during LRCLK is output.
>
> Without this fix, BCLK is turned on 11 ms earlier than LRCK by the
> da7219.
> With this fix, BCLK is turned on only 0.4 ms earlier than LRCK by
> the rockchip codec.
>
> Signed-off-by: Judy Hsiao <judyhsiao@chromium.org>
> ---
> sound/soc/rockchip/rockchip_i2s.c | 167 ++++++++++++++++++++++--------
> 1 file changed, 121 insertions(+), 46 deletions(-)
>
> diff --git a/sound/soc/rockchip/rockchip_i2s.c b/sound/soc/rockchip/rockchip_i2s.c
> index 47a3971a9ce1..5e3cb06377a1 100644
> --- a/sound/soc/rockchip/rockchip_i2s.c
> +++ b/sound/soc/rockchip/rockchip_i2s.c

> @@ -92,39 +122,46 @@ static inline struct rk_i2s_dev *to_info(struct snd_soc_dai *dai)
> return snd_soc_dai_get_drvdata(dai);
> }
>
> -static void rockchip_snd_txctrl(struct rk_i2s_dev *i2s, int on)
> +static int rockchip_snd_txctrl(struct rk_i2s_dev *i2s, int on)
> {
> unsigned int val = 0;
> int retry = 10;
> -
> + int ret = 0;
> +
> spin_lock(&i2s->lock);
> if (on) {
> - regmap_update_bits(i2s->regmap, I2S_DMACR,
> - I2S_DMACR_TDE_ENABLE, I2S_DMACR_TDE_ENABLE);
> -
> - regmap_update_bits(i2s->regmap, I2S_XFER,
> - I2S_XFER_TXS_START | I2S_XFER_RXS_START,
> - I2S_XFER_TXS_START | I2S_XFER_RXS_START);
> -
> + ret = regmap_update_bits(i2s->regmap, I2S_DMACR,
> + I2S_DMACR_TDE_ENABLE, I2S_DMACR_TDE_ENABLE);
> + if (ret < 0)
> + goto end;
> + ret = regmap_update_bits(i2s->regmap, I2S_XFER,
> + I2S_XFER_TXS_START | I2S_XFER_RXS_START,
> + I2S_XFER_TXS_START | I2S_XFER_RXS_START);

This still isn't how I'd expect the indentation to look, but I think I
will stop complaining about whitespace. Maybe you can either use
'clang-format' (sparingly), or else see what Mark thinks.

> + if (ret < 0)
> + goto end;
> i2s->tx_start = true;
> } else {
> i2s->tx_start = false;
>
...

> static void rockchip_snd_rxctrl(struct rk_i2s_dev *i2s, int on)

I didn't think I needed to call this out, because you already got build
bots complaining about this, but...
...did you even compile-test this? You should be making this function
return 'int', not 'void', because you're adding return values below.

> {
> unsigned int val = 0;
> int retry = 10;
> + int ret = 0;
>
...
> +end:
> spin_unlock(&i2s->lock);
> + if (ret < 0)
> + dev_err(i2s->dev, "lrclk update failed\n");
> +
> + return ret;

^^ here.

> }
>
> static int rockchip_i2s_set_fmt(struct snd_soc_dai *cpu_dai,

Aside from those, I think this looks OK to the best of my
(not-very-familiar with sounds/soc/) ability:

Reviewed-by: Brian Norris <briannorris@chromium.org>

\
 
 \ /
  Last update: 2022-06-17 22:50    [W:0.375 / U:0.204 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site