| Message ID | 1311158730-12412-1-git-send-email-sudhakar.raj@ti.com (mailing list archive) |
|---|---|
| State | Awaiting Upstream |
| Headers | show |
Hi Sudhakar, On Wed, Jul 20, 2011 at 16:15:30, Rajashekhara, Sudhakar wrote: > This patch fixes the following bugs found in DaVinci voice codec driver. > > a. According to DM365 voice codec data sheet at [1], before starting > recording or playback, ADC/DAC modules should follow a reset and > enable cycle. Writing a 1 to the ADC/DAC bit in the register resets > the module and clearing the bit to 0 will enable the module. But the > driver seems to be doing the reverse of it. > > b. In davinci_vcif_trigger() function, a break() statement was missing > causing the davinci_vcif_stop() function to be called as a fallback > after calling davinci_vcif_start(). These should be two different patches. Also, please CC the ALSA maintainers. Thanks, Sekhar
Hi Sekhar, On Wed, Jul 20, 2011 at 17:04:55, Nori, Sekhar wrote: > Hi Sudhakar, > > On Wed, Jul 20, 2011 at 16:15:30, Rajashekhara, Sudhakar wrote: > > This patch fixes the following bugs found in DaVinci voice codec driver. > > > > a. According to DM365 voice codec data sheet at [1], before starting > > recording or playback, ADC/DAC modules should follow a reset and > > enable cycle. Writing a 1 to the ADC/DAC bit in the register resets > > the module and clearing the bit to 0 will enable the module. But the > > driver seems to be doing the reverse of it. > > > > b. In davinci_vcif_trigger() function, a break() statement was missing > > causing the davinci_vcif_stop() function to be called as a fallback > > after calling davinci_vcif_start(). > > These should be two different patches. Also, please CC the ALSA maintainers. > I'll split the patches and resend them. Regards, Sudhakar
diff --git a/sound/soc/davinci/davinci-vcif.c b/sound/soc/davinci/davinci-vcif.c index 9259f1f..1f11525 100644 --- a/sound/soc/davinci/davinci-vcif.c +++ b/sound/soc/davinci/davinci-vcif.c @@ -62,9 +62,9 @@ static void davinci_vcif_start(struct snd_pcm_substream *substream) w = readl(davinci_vc->base + DAVINCI_VC_CTRL); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - MOD_REG_BIT(w, DAVINCI_VC_CTRL_RSTDAC, 1); + MOD_REG_BIT(w, DAVINCI_VC_CTRL_RSTDAC, 0); else - MOD_REG_BIT(w, DAVINCI_VC_CTRL_RSTADC, 1); + MOD_REG_BIT(w, DAVINCI_VC_CTRL_RSTADC, 0); writel(w, davinci_vc->base + DAVINCI_VC_CTRL); } @@ -80,9 +80,9 @@ static void davinci_vcif_stop(struct snd_pcm_substream *substream) /* Reset transmitter/receiver and sample rate/frame sync generators */ w = readl(davinci_vc->base + DAVINCI_VC_CTRL); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - MOD_REG_BIT(w, DAVINCI_VC_CTRL_RSTDAC, 0); + MOD_REG_BIT(w, DAVINCI_VC_CTRL_RSTDAC, 1); else - MOD_REG_BIT(w, DAVINCI_VC_CTRL_RSTADC, 0); + MOD_REG_BIT(w, DAVINCI_VC_CTRL_RSTADC, 1); writel(w, davinci_vc->base + DAVINCI_VC_CTRL); } @@ -159,6 +159,7 @@ static int davinci_vcif_trigger(struct snd_pcm_substream *substream, int cmd, case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: davinci_vcif_start(substream); + break; case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
This patch fixes the following bugs found in DaVinci voice codec driver. a. According to DM365 voice codec data sheet at [1], before starting recording or playback, ADC/DAC modules should follow a reset and enable cycle. Writing a 1 to the ADC/DAC bit in the register resets the module and clearing the bit to 0 will enable the module. But the driver seems to be doing the reverse of it. b. In davinci_vcif_trigger() function, a break() statement was missing causing the davinci_vcif_stop() function to be called as a fallback after calling davinci_vcif_start(). [1] http://focus.ti.com/lit/ug/sprufi9b/sprufi9b.pdf Signed-off-by: Rajashekhara, Sudhakar <sudhakar.raj@ti.com> --- sound/soc/davinci/davinci-vcif.c | 9 +++++---- 1 files changed, 5 insertions(+), 4 deletions(-)