[PATCH] drm/mediatek: fix race condition for HDMI jack status reporting

[CK Hu]

Hi, Tzung-Bi:

On Thu, 2020-02-13 at 15:59 +0800, Tzung-Bi Shih wrote:
> hdmi_conn_detect and mtk_hdmi_audio_hook_plugged_cb would be called
> by different threads.
> 
> Imaging the following calling sequence:
>            Thread A                            Thread B
> --------------------------------------------------------------------
> mtk_hdmi_audio_hook_plugged_cb()
> mtk_cec_hpd_high() -> disconnected
>                                      hdmi_conn_detect()
>                                      mtk_cec_hpd_high() -> connected
>                                      plugged_cb(connected)
> plugged_cb(disconnected)
> 
> The latest disconnected is false reported.  Makes mtk_cec_hpd_high
> and plugged_cb atomic to fix.
> 
> plugged_cb and codec_dev are also in danger of race condition.  Instead
> of using mutex to protect them:
> - Checks NULLs first.
> - Uses WRITE_ONCE() to prevent store tearing (i.e. write to plugged_cb
>   after codec_dev).
> - Uses codec_dev as a signal to report HDMI jack status.
> 
> Fixes: 5d3c64477392 ("drm/mediatek: support HDMI jack status reporting")
> 
> Signed-off-by: Tzung-Bi Shih <tzungbi at google.com>
> ---
> Previous discussion: https://patchwork.kernel.org/patch/11367625/
> Previous attempt: https://patchwork.kernel.org/patch/11378413/
> 
>  drivers/gpu/drm/mediatek/mtk_hdmi.c | 18 ++++++++++++++----
>  1 file changed, 14 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c
> index 03aeb73005ef..b1e5d0c538fa 100644
> --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c
> +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c
> @@ -12,6 +12,7 @@
>  #include <linux/io.h>
>  #include <linux/kernel.h>
>  #include <linux/mfd/syscon.h>
> +#include <linux/mutex.h>
>  #include <linux/of_platform.h>
>  #include <linux/of.h>
>  #include <linux/of_gpio.h>
> @@ -171,6 +172,7 @@ struct mtk_hdmi {
>  	bool enabled;
>  	hdmi_codec_plugged_cb plugged_cb;
>  	struct device *codec_dev;
> +	struct mutex update_plugged_status_lock;
>  };
>  
>  static inline struct mtk_hdmi *hdmi_ctx_from_bridge(struct drm_bridge *b)
> @@ -1199,10 +1201,13 @@ static void mtk_hdmi_clk_disable_audio(struct mtk_hdmi *hdmi)
>  static enum drm_connector_status
>  mtk_hdmi_update_plugged_status(struct mtk_hdmi *hdmi)
>  {
> -	bool connected = mtk_cec_hpd_high(hdmi->cec_dev);
> +	bool connected;
>  
> -	if (hdmi->plugged_cb && hdmi->codec_dev)
> +	mutex_lock(&hdmi->update_plugged_status_lock);
> +	connected = mtk_cec_hpd_high(hdmi->cec_dev);
> +	if (hdmi->codec_dev)
>  		hdmi->plugged_cb(hdmi->codec_dev, connected);
> +	mutex_unlock(&hdmi->update_plugged_status_lock);
>  
>  	return connected ?
>  	       connector_status_connected : connector_status_disconnected;
> @@ -1669,8 +1674,12 @@ static int mtk_hdmi_audio_hook_plugged_cb(struct device *dev, void *data,
>  {
>  	struct mtk_hdmi *hdmi = data;
>  
> -	hdmi->plugged_cb = fn;
> -	hdmi->codec_dev = codec_dev;
> +	if (!fn || !codec_dev)

I think sound driver could be removed for some reason, and fn should be
set to NULL before sound driver removed. In this case, codec_dev != NULL
and fn == NULL.

Regards,
CK

> +		return -EINVAL;
> +
> +	/* Use WRITE_ONCE() to prevent store tearing. */
> +	WRITE_ONCE(hdmi->plugged_cb, fn);
> +	WRITE_ONCE(hdmi->codec_dev, codec_dev);
>  	mtk_hdmi_update_plugged_status(hdmi);
>  
>  	return 0;
> @@ -1729,6 +1738,7 @@ static int mtk_drm_hdmi_probe(struct platform_device *pdev)
>  		return ret;
>  	}
>  
> +	mutex_init(&hdmi->update_plugged_status_lock);
>  	platform_set_drvdata(pdev, hdmi);
>  
>  	ret = mtk_hdmi_output_init(hdmi);