lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<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

Powered by Openwall GNU/*/Linux Powered by OpenVZ