[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <YqzoNqd3Mpv3r2tS@google.com>
Date: Fri, 17 Jun 2022 13:46:46 -0700
From: Brian Norris <briannorris@...omium.org>
To: Judy Hsiao <judyhsiao@...omium.org>
Cc: Heiko Stuebner <heiko@...ech.de>,
Liam Girdwood <lgirdwood@...il.com>,
Rob Herring <robh+dt@...nel.org>,
Mark Brown <broonie@...nel.org>,
Jaroslav Kysela <perex@...ex.cz>,
Chen-Yu Tsai <wenst@...omium.org>, alsa-devel@...a-project.org,
linux-arm-kernel@...ts.infradead.org,
linux-rockchip@...ts.infradead.org, linux-kernel@...r.kernel.org
Subject: Re: [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@...omium.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@...omium.org>
Powered by blists - more mailing lists