[PATCH] ASoC: wm8962: Do not access WM8962_GPIO_BASE
Charles Keepax
ckeepax at opensource.cirrus.com
Thu Jul 23 11:11:18 CEST 2020
On Fri, Jul 17, 2020 at 10:59:59AM -0300, Fabio Estevam wrote:
> According to the WM8962 datasheet, there is no register at address 0x200.
>
> WM8962_GPIO_BASE is just a base address for the GPIO registers and not a
> real register, so remove it from wm8962_readable_register().
>
> Also, Register 515 (WM8962_GPIO_BASE + 3) does not exist, so skip
> its access.
>
> This fixes the following errors:
>
> wm8962 0-001a: ASoC: error at soc_component_read_no_lock on wm8962.0-001a: -16
> wm8962 0-001a: ASoC: error at soc_component_read_no_lock on wm8962.0-001a: -16
>
> Signed-off-by: Fabio Estevam <festevam at gmail.com>
> ---
This doesn't quite smell right admittedly I am not 100% sure for this
chip but usually the Wolfson chips just return zero when you read a
non-existant register rather than NACKing the transaction. But even
if the chip was NACKing the transaction I would probably expect an
EIO rather than EBUSY error.
Are we sure we understand the error we are addressing here?
Thanks,
Charles
> Hi,
>
> There is still one more soc_component_read_no_lock error left on register 48.
>
> I can get rid of it with the below change:
>
> --- a/sound/soc/codecs/wm8962.c
> +++ b/sound/soc/codecs/wm8962.c
> @@ -151,6 +151,7 @@ static const struct reg_default wm8962_reg[] = {
> { 40, 0x0000 }, /* R40 - SPKOUTL volume */
> { 41, 0x0000 }, /* R41 - SPKOUTR volume */
>
> + { 48, 0x0000 }, /* R48 - Additional control(4) */
> { 49, 0x0010 }, /* R49 - Class D Control 1 */
> { 51, 0x0003 }, /* R51 - Class D Control 2 */
>
> @@ -841,7 +842,6 @@ static bool wm8962_readable_register(struct device *dev, unsigned int reg)
> case WM8962_SPKOUTL_VOLUME:
> case WM8962_SPKOUTR_VOLUME:
> case WM8962_THERMAL_SHUTDOWN_STATUS:
> - case WM8962_ADDITIONAL_CONTROL_4:
> case WM8962_CLASS_D_CONTROL_1:
> case WM8962_CLASS_D_CONTROL_2:
> case WM8962_CLOCKING_4:
>
> I haven't submitted it yet because I don't know if this is the correct
> approach.
>
> Please advise.
>
> Thanks
>
> sound/soc/codecs/wm8962.c | 9 +++++++--
> 1 file changed, 7 insertions(+), 2 deletions(-)
>
> diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c
> index df8cdc71357d..8159a3866cde 100644
> --- a/sound/soc/codecs/wm8962.c
> +++ b/sound/soc/codecs/wm8962.c
> @@ -956,7 +956,6 @@ static bool wm8962_readable_register(struct device *dev, unsigned int reg)
> case WM8962_EQ39:
> case WM8962_EQ40:
> case WM8962_EQ41:
> - case WM8962_GPIO_BASE:
> case WM8962_GPIO_2:
> case WM8962_GPIO_3:
> case WM8962_GPIO_5:
> @@ -3437,7 +3436,13 @@ static int wm8962_probe(struct snd_soc_component *component)
> /* Save boards having to disable DMIC when not in use */
> dmicclk = false;
> dmicdat = false;
> - for (i = 0; i < WM8962_MAX_GPIO; i++) {
> + for (i = 1; i < WM8962_MAX_GPIO; i++) {
> + /*
> + * Register 515 (WM8962_GPIO_BASE + 3) does not exist,
> + * so skip its access
> + */
> + if (i == 3)
> + continue;
> switch (snd_soc_component_read(component, WM8962_GPIO_BASE + i)
> & WM8962_GP2_FN_MASK) {
> case WM8962_GPIO_FN_DMICCLK:
> --
> 2.17.1
>
More information about the Alsa-devel
mailing list