diff mbox

overrun occuring in arecord for 2.6.30

Message ID 4A48E54C.9070209@gmail.com (mailing list archive)
State Not Applicable
Headers show

Commit Message

Yusuf Caglar AKYUZ June 29, 2009, 4:01 p.m. UTC
Mani, Arun wrote:
> Hi All,
> Anyone tried arecord in 2.6.30. I am constantly getting a overrun error which is blocking the capture.
> 
> Thanks,
> Arun
> 

I tried it, and it is not working for me. I see constant overruns as well. This 
code was working quite well on 2.6.28, I have no idea what happened since then.

Anyway patches posted by Troy Kisky at [1] seems to fix overrun issues. This 
version of patch does not apply to 2.6.30, you can find the attached patched I 
modified for applying to 2.6.30. Arago tree has further modifications, if you 
want I can send this patch against arago tree.

Regards,
Caglar

[1] http://www.mail-archive.com/davinci-linux-open-source@linux.davincidsp.com/msg12568.html
diff mbox

Patch

diff --git a/sound/soc/davinci/davinci-i2s.c b/sound/soc/davinci/davinci-i2s.c
index b1ea52f..70e8706 100644
--- a/sound/soc/davinci/davinci-i2s.c
+++ b/sound/soc/davinci/davinci-i2s.c
@@ -63,6 +63,7 @@ 
 #define DAVINCI_MCBSP_RCR_RWDLEN1(v)	((v) << 5)
 #define DAVINCI_MCBSP_RCR_RFRLEN1(v)	((v) << 8)
 #define DAVINCI_MCBSP_RCR_RDATDLY(v)	((v) << 16)
+#define DAVINCI_MCBSP_RCR_RFIG		(1 << 18)
 #define DAVINCI_MCBSP_RCR_RWDLEN2(v)	((v) << 21)
 
 #define DAVINCI_MCBSP_XCR_XWDLEN1(v)	((v) << 5)
@@ -85,14 +86,6 @@ 
 #define DAVINCI_MCBSP_PCR_FSRM		(1 << 10)
 #define DAVINCI_MCBSP_PCR_FSXM		(1 << 11)
 
-#define MOD_REG_BIT(val, mask, set) do { \
-	if (set) { \
-		val |= mask; \
-	} else { \
-		val &= ~mask; \
-	} \
-} while (0)
-
 enum {
 	DAVINCI_MCBSP_WORD_8 = 0,
 	DAVINCI_MCBSP_WORD_12,
@@ -112,8 +105,13 @@  static struct davinci_pcm_dma_params davinci_i2s_pcm_in = {
 
 struct davinci_mcbsp_dev {
 	void __iomem			*base;
+#define MOD_DSP_A	0
+#define MOD_DSP_B	1
+	int				mode;
+	u32				pcr;
 	struct clk			*clk;
 	struct davinci_pcm_dma_params	*dma_params[2];
+	struct snd_soc_dai *codec_dai;
 };
 
 static inline void davinci_mcbsp_write_reg(struct davinci_mcbsp_dev *dev,
@@ -127,96 +125,100 @@  static inline u32 davinci_mcbsp_read_reg(struct davinci_mcbsp_dev *dev, int reg)
 	return __raw_readl(dev->base + reg);
 }
 
-static void davinci_mcbsp_start(struct snd_pcm_substream *substream)
+static void toggle_clock(struct davinci_mcbsp_dev *dev, int playback)
+{
+	u32 m = playback ? DAVINCI_MCBSP_PCR_CLKXP : DAVINCI_MCBSP_PCR_CLKRP;
+	/* The clock needs to toggle to complete reset.
+	 * So, fake it by toggling the clk polarity.
+	 */
+	davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_PCR_REG, dev->pcr ^ m);
+	davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_PCR_REG, dev->pcr);
+}
+
+static void davinci_mcbsp_start(struct davinci_mcbsp_dev *dev,
+		struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct davinci_mcbsp_dev *dev = rtd->dai->cpu_dai->private_data;
 	struct snd_soc_device *socdev = rtd->socdev;
 	struct snd_soc_platform *platform = socdev->card->platform;
-	u32 w;
-	int ret;
-
-	/* Start the sample generator and enable transmitter/receiver */
-	w = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
-	MOD_REG_BIT(w, DAVINCI_MCBSP_SPCR_GRST, 1);
-	davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, w);
+	int playback = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK);
+	u32 spcr;
+	u32 mask = playback ? DAVINCI_MCBSP_SPCR_XRST : DAVINCI_MCBSP_SPCR_RRST;
+	spcr = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
+	if (spcr & mask) {
+		/* start off disabled */
+		davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG,
+				spcr & ~mask);
+		toggle_clock(dev, playback);
+	}
+	if (dev->pcr & (DAVINCI_MCBSP_PCR_FSXM | DAVINCI_MCBSP_PCR_FSRM |
+			DAVINCI_MCBSP_PCR_CLKXM | DAVINCI_MCBSP_PCR_CLKRM)) {
+		/* Start the sample generator */
+		spcr |= DAVINCI_MCBSP_SPCR_GRST;
+		davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, spcr);
+	}
 
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+	if (playback) {
 		/* Stop the DMA to avoid data loss */
 		/* while the transmitter is out of reset to handle XSYNCERR */
 		if (platform->pcm_ops->trigger) {
-			ret = platform->pcm_ops->trigger(substream,
+			int ret = platform->pcm_ops->trigger(substream,
 				SNDRV_PCM_TRIGGER_STOP);
 			if (ret < 0)
 				printk(KERN_DEBUG "Playback DMA stop failed\n");
 		}
 
 		/* Enable the transmitter */
-		w = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
-		MOD_REG_BIT(w, DAVINCI_MCBSP_SPCR_XRST, 1);
-		davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, w);
+		spcr = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
+		spcr |= DAVINCI_MCBSP_SPCR_XRST;
+		davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, spcr);
 
 		/* wait for any unexpected frame sync error to occur */
 		udelay(100);
 
 		/* Disable the transmitter to clear any outstanding XSYNCERR */
-		w = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
-		MOD_REG_BIT(w, DAVINCI_MCBSP_SPCR_XRST, 0);
-		davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, w);
+		spcr = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
+		spcr &= ~DAVINCI_MCBSP_SPCR_XRST;
+		davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, spcr);
+		toggle_clock(dev, playback);
 
 		/* Restart the DMA */
 		if (platform->pcm_ops->trigger) {
-			ret = platform->pcm_ops->trigger(substream,
+			int ret = platform->pcm_ops->trigger(substream,
 				SNDRV_PCM_TRIGGER_START);
 			if (ret < 0)
 				printk(KERN_DEBUG "Playback DMA start failed\n");
 		}
-		/* Enable the transmitter */
-		w = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
-		MOD_REG_BIT(w, DAVINCI_MCBSP_SPCR_XRST, 1);
-		davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, w);
-
-	} else {
-
-		/* Enable the reciever */
-		w = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
-		MOD_REG_BIT(w, DAVINCI_MCBSP_SPCR_RRST, 1);
-		davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, w);
 	}
 
+	/* Enable transmitter or receiver */
+	spcr = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
+	spcr |= mask;
 
-	/* Start frame sync */
-	w = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
-	MOD_REG_BIT(w, DAVINCI_MCBSP_SPCR_FRST, 1);
-	davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, w);
+	if (dev->pcr & (DAVINCI_MCBSP_PCR_FSXM | DAVINCI_MCBSP_PCR_FSRM)) {
+		/* Start frame sync */
+		spcr |= DAVINCI_MCBSP_SPCR_FRST;
+	}
+	davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, spcr);
 }
 
-static void davinci_mcbsp_stop(struct snd_pcm_substream *substream)
+static void davinci_mcbsp_stop(struct davinci_mcbsp_dev *dev, int playback)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct davinci_mcbsp_dev *dev = rtd->dai->cpu_dai->private_data;
-	u32 w;
+	u32 spcr;
 
 	/* Reset transmitter/receiver and sample rate/frame sync generators */
-	w = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
-	MOD_REG_BIT(w, DAVINCI_MCBSP_SPCR_GRST |
-		       DAVINCI_MCBSP_SPCR_FRST, 0);
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
-		MOD_REG_BIT(w, DAVINCI_MCBSP_SPCR_XRST, 0);
-	else
-		MOD_REG_BIT(w, DAVINCI_MCBSP_SPCR_RRST, 0);
-	davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, w);
+	spcr = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
+	spcr &= ~(DAVINCI_MCBSP_SPCR_GRST | DAVINCI_MCBSP_SPCR_FRST);
+	spcr &= playback ? ~DAVINCI_MCBSP_SPCR_XRST : ~DAVINCI_MCBSP_SPCR_RRST;
+	davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, spcr);
+	toggle_clock(dev, playback);
 }
 
 static int davinci_i2s_startup(struct snd_pcm_substream *substream,
-			       struct snd_soc_dai *dai)
+			       struct snd_soc_dai *cpu_dai)
 {
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_dai *cpu_dai = rtd->dai->cpu_dai;
-	struct davinci_mcbsp_dev *dev = rtd->dai->cpu_dai->private_data;
-
+	struct davinci_mcbsp_dev *dev = cpu_dai->private_data;
 	cpu_dai->dma_data = dev->dma_params[substream->stream];
-
 	return 0;
 }
 
@@ -228,12 +230,11 @@  static int davinci_i2s_set_dai_fmt(struct snd_soc_dai *cpu_dai,
 	struct davinci_mcbsp_dev *dev = cpu_dai->private_data;
 	unsigned int pcr;
 	unsigned int srgr;
-	unsigned int rcr;
-	unsigned int xcr;
 	srgr = DAVINCI_MCBSP_SRGR_FSGM |
 		DAVINCI_MCBSP_SRGR_FPER(DEFAULT_BITPERSAMPLE * 2 - 1) |
 		DAVINCI_MCBSP_SRGR_FWID(DEFAULT_BITPERSAMPLE - 1);
 
+	/* set master/slave audio interface */
 	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
 	case SND_SOC_DAIFMT_CBS_CFS:
 		/* cpu is master */
@@ -258,11 +259,8 @@  static int davinci_i2s_set_dai_fmt(struct snd_soc_dai *cpu_dai,
 		return -EINVAL;
 	}
 
-	rcr = DAVINCI_MCBSP_RCR_RFRLEN1(1);
-	xcr = DAVINCI_MCBSP_XCR_XFIG | DAVINCI_MCBSP_XCR_XFRLEN1(1);
+	/* interface format */
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
-	case SND_SOC_DAIFMT_DSP_B:
-		break;
 	case SND_SOC_DAIFMT_I2S:
 		/* Davinci doesn't support TRUE I2S, but some codecs will have
 		 * the left and right channels contiguous. This allows
@@ -282,8 +280,10 @@  static int davinci_i2s_set_dai_fmt(struct snd_soc_dai *cpu_dai,
 		 */
 		fmt ^= SND_SOC_DAIFMT_NB_IF;
 	case SND_SOC_DAIFMT_DSP_A:
-		rcr |= DAVINCI_MCBSP_RCR_RDATDLY(1);
-		xcr |= DAVINCI_MCBSP_XCR_XDATDLY(1);
+		dev->mode = MOD_DSP_A;
+		break;
+	case SND_SOC_DAIFMT_DSP_B:
+		dev->mode = MOD_DSP_B;
 		break;
 	default:
 		printk(KERN_ERR "%s:bad format\n", __func__);
@@ -343,9 +343,8 @@  static int davinci_i2s_set_dai_fmt(struct snd_soc_dai *cpu_dai,
 		return -EINVAL;
 	}
 	davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SRGR_REG, srgr);
+	dev->pcr = pcr;
 	davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_PCR_REG, pcr);
-	davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_RCR_REG, rcr);
-	davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_XCR_REG, xcr);
 	return 0;
 }
 
@@ -356,92 +355,184 @@  static int davinci_i2s_hw_params(struct snd_pcm_substream *substream,
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct davinci_pcm_dma_params *dma_params = rtd->dai->cpu_dai->dma_data;
 	struct davinci_mcbsp_dev *dev = rtd->dai->cpu_dai->private_data;
+	struct snd_soc_dai *codec_dai = dev->codec_dai;
 	struct snd_interval *i = NULL;
 	int mcbsp_word_length;
-	u32 w;
+	int bits_per_sample;
+	int bits_per_frame;
+	unsigned int rcr, xcr, srgr;
+	int channels;
+	int format;
+	int element_cnt = 1;
+	u32 spcr;
+	int right_first = 0;
+
+	i = hw_param_interval(params, SNDRV_PCM_HW_PARAM_SAMPLE_BITS);
+	bits_per_sample = snd_interval_value(i);
+	/* always 2 samples/frame, mono will convert to stereo */
+	bits_per_frame = bits_per_sample << 1;
+	srgr = DAVINCI_MCBSP_SRGR_FSGM |
+		DAVINCI_MCBSP_SRGR_FPER(bits_per_frame - 1) |
+		DAVINCI_MCBSP_SRGR_FWID(bits_per_sample - 1);
 
 	/* general line settings */
-	w = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
-	if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) {
-		w |= DAVINCI_MCBSP_SPCR_RINTM(3) | DAVINCI_MCBSP_SPCR_FREE;
-		davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, w);
+	spcr = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
+	spcr |= DAVINCI_MCBSP_SPCR_FREE;
+	spcr |= (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) ?
+			DAVINCI_MCBSP_SPCR_XINTM(3) :
+			DAVINCI_MCBSP_SPCR_RINTM(3);
+	davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, spcr);
+
+	rcr = DAVINCI_MCBSP_RCR_RFIG;
+	xcr = DAVINCI_MCBSP_XCR_XFIG;
+	if (dev->mode == MOD_DSP_B) {
+		rcr |= DAVINCI_MCBSP_RCR_RDATDLY(0);
+		xcr |= DAVINCI_MCBSP_XCR_XDATDLY(0);
 	} else {
-		w |= DAVINCI_MCBSP_SPCR_XINTM(3) | DAVINCI_MCBSP_SPCR_FREE;
-		davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, w);
+		rcr |= DAVINCI_MCBSP_RCR_RDATDLY(1);
+		xcr |= DAVINCI_MCBSP_XCR_XDATDLY(1);
 	}
-
-	i = hw_param_interval(params, SNDRV_PCM_HW_PARAM_SAMPLE_BITS);
-	w = DAVINCI_MCBSP_SRGR_FSGM;
-	MOD_REG_BIT(w, DAVINCI_MCBSP_SRGR_FWID(snd_interval_value(i) - 1), 1);
-
-	i = hw_param_interval(params, SNDRV_PCM_HW_PARAM_FRAME_BITS);
-	MOD_REG_BIT(w, DAVINCI_MCBSP_SRGR_FPER(snd_interval_value(i) - 1), 1);
-	davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SRGR_REG, w);
-
+	channels = params_channels(params);
+	format = params_format(params);
 	/* Determine xfer data type */
-	switch (params_format(params)) {
-	case SNDRV_PCM_FORMAT_S8:
-		dma_params->data_type = 1;
-		mcbsp_word_length = DAVINCI_MCBSP_WORD_8;
-		break;
-	case SNDRV_PCM_FORMAT_S16_LE:
-		dma_params->data_type = 2;
-		mcbsp_word_length = DAVINCI_MCBSP_WORD_16;
-		break;
-	case SNDRV_PCM_FORMAT_S32_LE:
-		dma_params->data_type = 4;
-		mcbsp_word_length = DAVINCI_MCBSP_WORD_32;
-		break;
-	default:
-		printk(KERN_WARNING "davinci-i2s: unsupported PCM format\n");
-		return -EINVAL;
-	}
-
-	if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) {
-		w = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_RCR_REG);
-		MOD_REG_BIT(w, DAVINCI_MCBSP_RCR_RWDLEN1(mcbsp_word_length) |
-			       DAVINCI_MCBSP_RCR_RWDLEN2(mcbsp_word_length), 1);
-		davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_RCR_REG, w);
-
+	if (channels == 2) {
+		/* Combining both channels into 1 element will x10 the
+		 * amount of time between servicing the dma channel, increase
+		 * effiency, and reduce the chance of overrun/underrun. But,
+		 * it will result in the left & right channels being swapped.
+		 * So, let the codec know to swap them back.
+		 *
+		 * It is x10 instead of x2 because the clock from the codec
+		 * runs at mclk speed, independent of the sample rate.
+		 * So, having an entire frame at once means it has to be
+		 * serviced at the sample rate instead of the mclk speed.
+		 *
+		 * In the now very unlikely case that an underrun still
+		 * occurs, both the left and right samples will be repeated
+		 * so that no pops are heard, and the left and right channels
+		 * won't end up being swapped because of the underrun.
+		 */
+		right_first = 1;
+		dma_params->convert_mono_stereo = 0;
+		switch (format) {
+		case SNDRV_PCM_FORMAT_S8:
+			dma_params->data_type = 2;	/* 2 byte frame */
+			mcbsp_word_length = DAVINCI_MCBSP_WORD_16;
+			break;
+		case SNDRV_PCM_FORMAT_S16_LE:
+			dma_params->data_type = 4;	/* 4 byte frame */
+			mcbsp_word_length = DAVINCI_MCBSP_WORD_32;
+			break;
+		case SNDRV_PCM_FORMAT_S32_LE:
+			right_first = 0;
+			element_cnt = 2;
+			dma_params->data_type = 4;	/* 4 byte element */
+			mcbsp_word_length = DAVINCI_MCBSP_WORD_32;
+			break;
+		default:
+			printk(KERN_WARNING
+					"davinci-i2s: unsupported PCM format");
+			return -EINVAL;
+		}
 	} else {
-		w = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_XCR_REG);
-		MOD_REG_BIT(w, DAVINCI_MCBSP_XCR_XWDLEN1(mcbsp_word_length) |
-			       DAVINCI_MCBSP_XCR_XWDLEN2(mcbsp_word_length), 1);
-		davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_XCR_REG, w);
-
+		dma_params->convert_mono_stereo = 1;
+		/* 1 element in ram becomes 2 for stereo */
+		element_cnt = 2;
+		switch (format) {
+		case SNDRV_PCM_FORMAT_S8:
+			/* 1 byte frame in ram */
+			dma_params->data_type = 1;
+			mcbsp_word_length = DAVINCI_MCBSP_WORD_8;
+			break;
+		case SNDRV_PCM_FORMAT_S16_LE:
+			/* 2 byte frame in ram */
+			dma_params->data_type = 2;
+			mcbsp_word_length = DAVINCI_MCBSP_WORD_16;
+			break;
+		case SNDRV_PCM_FORMAT_S32_LE:
+			/* 4 byte element */
+			dma_params->data_type = 4;
+			mcbsp_word_length = DAVINCI_MCBSP_WORD_32;
+			break;
+		default:
+			printk(KERN_WARNING
+					"davinci-i2s: unsupported PCM format");
+			return -EINVAL;
+		}
 	}
+	if (codec_dai->ops->inform_channel_order)
+		codec_dai->ops->inform_channel_order(codec_dai, right_first);
+	rcr |=	DAVINCI_MCBSP_RCR_RFRLEN1(element_cnt - 1);
+	xcr |=  DAVINCI_MCBSP_XCR_XFRLEN1(element_cnt - 1);
+
+	rcr |=  DAVINCI_MCBSP_RCR_RWDLEN1(mcbsp_word_length) |
+		DAVINCI_MCBSP_RCR_RWDLEN2(mcbsp_word_length);
+	xcr |=  DAVINCI_MCBSP_XCR_XWDLEN1(mcbsp_word_length) |
+		DAVINCI_MCBSP_XCR_XWDLEN2(mcbsp_word_length);
+	davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SRGR_REG, srgr);
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_XCR_REG, xcr);
+	else
+		davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_RCR_REG, rcr);
 	return 0;
 }
 
+static int davinci_i2s_prepare(struct snd_pcm_substream *substream,
+		struct snd_soc_dai *dai)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct davinci_mcbsp_dev *dev = rtd->dai->cpu_dai->private_data;
+	int playback = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK);
+	davinci_mcbsp_stop(dev, playback);
+	if ((dev->pcr & DAVINCI_MCBSP_PCR_FSXM) == 0) {
+		/* codec is master */
+		davinci_mcbsp_start(dev, substream);
+	}
+	return 0;
+}
 static int davinci_i2s_trigger(struct snd_pcm_substream *substream, int cmd,
 			       struct snd_soc_dai *dai)
 {
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct davinci_mcbsp_dev *dev = rtd->dai->cpu_dai->private_data;
 	int ret = 0;
+	int playback = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK);
+	if ((dev->pcr & DAVINCI_MCBSP_PCR_FSXM) == 0)
+		return 0;	/* return if codec is master */
 
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_START:
 	case SNDRV_PCM_TRIGGER_RESUME:
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
-		davinci_mcbsp_start(substream);
+		davinci_mcbsp_start(dev, substream);
 		break;
 	case SNDRV_PCM_TRIGGER_STOP:
 	case SNDRV_PCM_TRIGGER_SUSPEND:
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
-		davinci_mcbsp_stop(substream);
+		davinci_mcbsp_stop(dev, playback);
 		break;
 	default:
 		ret = -EINVAL;
 	}
-
 	return ret;
 }
 
+static void davinci_i2s_shutdown(struct snd_pcm_substream *substream,
+		struct snd_soc_dai *dai)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct davinci_mcbsp_dev *dev = rtd->dai->cpu_dai->private_data;
+	int playback = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK);
+	davinci_mcbsp_stop(dev, playback);
+}
+
 static int davinci_i2s_probe(struct platform_device *pdev,
 			     struct snd_soc_dai *dai)
 {
 	struct snd_soc_device *socdev = platform_get_drvdata(pdev);
 	struct snd_soc_card *card = socdev->card;
 	struct snd_soc_dai *cpu_dai = card->dai_link->cpu_dai;
+	struct snd_soc_dai *codec_dai = card->dai_link->codec_dai;
 	struct davinci_mcbsp_dev *dev;
 	struct resource *mem, *ioarea;
 	struct evm_snd_platform_data *pdata;
@@ -465,6 +556,7 @@  static int davinci_i2s_probe(struct platform_device *pdev,
 		ret = -ENOMEM;
 		goto err_release_region;
 	}
+	dev->codec_dai = codec_dai;
 
 	cpu_dai->private_data = dev;
 
@@ -517,10 +609,13 @@  static void davinci_i2s_remove(struct platform_device *pdev,
 	release_mem_region(mem->start, (mem->end - mem->start) + 1);
 }
 
-#define DAVINCI_I2S_RATES	SNDRV_PCM_RATE_8000_96000
+#define DAVINCI_I2S_RATES	(SNDRV_PCM_RATE_8000_96000 |\
+	SNDRV_PCM_RATE_5512 | SNDRV_PCM_RATE_KNOT | SNDRV_PCM_RATE_CONTINUOUS)
 
 static struct snd_soc_dai_ops davinci_i2s_dai_ops = {
 	.startup	= davinci_i2s_startup,
+	.shutdown	= davinci_i2s_shutdown,
+	.prepare	= davinci_i2s_prepare,
 	.trigger	= davinci_i2s_trigger,
 	.hw_params	= davinci_i2s_hw_params,
 	.set_fmt	= davinci_i2s_set_dai_fmt,
@@ -532,12 +627,14 @@  struct snd_soc_dai davinci_i2s_dai = {
 	.probe = davinci_i2s_probe,
 	.remove = davinci_i2s_remove,
 	.playback = {
-		.channels_min = 2,
+		/* fixme, codecs shouldn't need to lie */
+		.channels_min = 1, /* lie, I2S dma will convert to stereo*/
 		.channels_max = 2,
 		.rates = DAVINCI_I2S_RATES,
 		.formats = SNDRV_PCM_FMTBIT_S16_LE,},
 	.capture = {
-		.channels_min = 2,
+		/* fixme, codecs shouldn't need to lie */
+		.channels_min = 1, /* lie, I2S dma will convert from stereo */
 		.channels_max = 2,
 		.rates = DAVINCI_I2S_RATES,
 		.formats = SNDRV_PCM_FMTBIT_S16_LE,},
diff --git a/sound/soc/davinci/davinci-pcm.c b/sound/soc/davinci/davinci-pcm.c
index 3ee38b6..b48d559 100644
--- a/sound/soc/davinci/davinci-pcm.c
+++ b/sound/soc/davinci/davinci-pcm.c
@@ -23,6 +23,7 @@ 
 
 #include <asm/dma.h>
 #include <mach/edma.h>
+#include <mach/sram.h>
 
 #include "davinci-pcm.h"
 
@@ -42,70 +43,62 @@  static struct snd_pcm_hardware davinci_pcm_hardware = {
 	.channels_max = 2,
 	.buffer_bytes_max = 128 * 1024,
 	.period_bytes_min = 32,
-	.period_bytes_max = 8 * 1024,
+	.period_bytes_max = 7 * 512,
 	.periods_min = 16,
 	.periods_max = 255,
 	.fifo_size = 0,
 };
 
+/*
+ * How it works....
+ *
+ * Playback:
+ * ram_params - copys 2*ping_size from start of SDRAM to iram,
+ * 	links to ram_link_lch2
+ * ram_link_lch2 - copys rest of SDRAM to iram in ping_size units,
+ * 	links to ram_link_lch
+ * ram_link_lch - copys entire SDRAM to iram in ping_size uints,
+ * 	links to self
+ *
+ * asp_params - same as asp_link_lch[0]
+ * asp_link_lch[0] - copys from lower half of iram to asp port
+ * 	links to asp_link_lch[1], triggers iram copy event on completion
+ * asp_link_lch[1] - copys from upper half of iram to asp port
+ * 	links to asp_link_lch[0], triggers iram copy event on completion
+ * 	triggers interrupt only needed to let upper SOC levels update position
+ * 	in stream on completion
+ *
+ * When playback is started:
+ * 	ram_params started
+ * 	asp_params started
+ *
+ * Capture:
+ * ram_params - same as ram_link_lch,
+ * 	links to ram_link_lch
+ * ram_link_lch - same as playback
+ * 	links to self
+ *
+ * asp_params - same as playback
+ * asp_link_lch[0] - same as playback
+ * asp_link_lch[1] - same as playback
+ *
+ * When capture is started:
+ * 	asp_params started
+ */
 struct davinci_runtime_data {
 	spinlock_t lock;
-	int period;		/* current DMA period */
-	int master_lch;		/* Master DMA channel */
-	int slave_lch;		/* linked parameter RAM reload slot */
-	struct davinci_pcm_dma_params *params;	/* DMA params */
+	int asp_master_lch;		/* Master DMA channel */
+	int asp_link_lch[2];	/* asp parameter link channel */
+	int ram_master_lch;
+	int ram_link_lch;
+	int ram_link_lch2;
+	struct edmacc_param asp_params;
+	struct edmacc_param ram_params;
 };
 
-static void davinci_pcm_enqueue_dma(struct snd_pcm_substream *substream)
-{
-	struct davinci_runtime_data *prtd = substream->runtime->private_data;
-	struct snd_pcm_runtime *runtime = substream->runtime;
-	int lch = prtd->slave_lch;
-	unsigned int period_size;
-	unsigned int dma_offset;
-	dma_addr_t dma_pos;
-	dma_addr_t src, dst;
-	unsigned short src_bidx, dst_bidx;
-	unsigned int data_type;
-	unsigned int count;
-
-	period_size = snd_pcm_lib_period_bytes(substream);
-	dma_offset = prtd->period * period_size;
-	dma_pos = runtime->dma_addr + dma_offset;
-
-	pr_debug("davinci_pcm: audio_set_dma_params_play channel = %d "
-		"dma_ptr = %x period_size=%x\n", lch, dma_pos, period_size);
-
-	data_type = prtd->params->data_type;
-	count = period_size / data_type;
-
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-		src = dma_pos;
-		dst = prtd->params->dma_addr;
-		src_bidx = data_type;
-		dst_bidx = 0;
-	} else {
-		src = prtd->params->dma_addr;
-		dst = dma_pos;
-		src_bidx = 0;
-		dst_bidx = data_type;
-	}
-
-	edma_set_src(lch, src, INCR, W8BIT);
-	edma_set_dest(lch, dst, INCR, W8BIT);
-	edma_set_src_index(lch, src_bidx, 0);
-	edma_set_dest_index(lch, dst_bidx, 0);
-	edma_set_transfer_params(lch, data_type, count, 1, 0, ASYNC);
-
-	prtd->period++;
-	if (unlikely(prtd->period >= runtime->periods))
-		prtd->period = 0;
-}
-
 static void davinci_pcm_dma_irq(unsigned lch, u16 ch_status, void *data)
 {
 	struct snd_pcm_substream *substream = data;
-	struct davinci_runtime_data *prtd = substream->runtime->private_data;
 
 	pr_debug("davinci_pcm: lch=%d, status=0x%x\n", lch, ch_status);
 
@@ -114,59 +107,260 @@  static void davinci_pcm_dma_irq(unsigned lch, u16 ch_status, void *data)
 
 	if (snd_pcm_running(substream)) {
 		snd_pcm_period_elapsed(substream);
-
-		spin_lock(&prtd->lock);
-		davinci_pcm_enqueue_dma(substream);
-		spin_unlock(&prtd->lock);
 	}
 }
 
+/*
+ * This is called after runtime->dma_addr, period_bytes and data_type are valid
+ */
+static int davinci_pcm_dma_setup(struct snd_pcm_substream *substream)
+{
+	unsigned short ram_src_cidx, ram_dst_cidx;
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct davinci_runtime_data *prtd = runtime->private_data;
+	struct snd_dma_buffer *iram_dma =
+		(struct snd_dma_buffer *)substream->dma_buffer.private_data;
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct davinci_pcm_dma_params *dma_data = rtd->dai->cpu_dai->dma_data;
+	unsigned int data_type = dma_data->data_type;
+	unsigned int convert_mono_stereo = dma_data->convert_mono_stereo;
+	/* divide by 2 for ping/pong */
+	unsigned int ping_size = snd_pcm_lib_period_bytes(substream) >> 1;
+	int lch = prtd->asp_link_lch[1];
+	if ((data_type == 0) || (data_type > 4)) {
+		printk(KERN_ERR "%s: data_type=%i\n", __func__, data_type);
+		return -EINVAL;
+	}
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		dma_addr_t asp_src_pong = iram_dma->addr + ping_size;
+		ram_src_cidx = ping_size;
+		ram_dst_cidx = -ping_size;
+		edma_set_src(lch, asp_src_pong, INCR, W8BIT);
+
+		lch = prtd->asp_link_lch[0];
+		if (convert_mono_stereo) {
+			edma_set_src_index(lch, 0, data_type);
+			lch = prtd->asp_link_lch[1];
+			edma_set_src_index(lch, 0, data_type);
+		} else {
+			edma_set_src_index(lch, data_type, 0);
+			lch = prtd->asp_link_lch[1];
+			edma_set_src_index(lch, data_type, 0);
+		}
+
+		lch = prtd->ram_link_lch;
+		edma_set_src(lch, runtime->dma_addr, INCR, W32BIT);
+	} else {
+		dma_addr_t asp_dst_pong = iram_dma->addr + ping_size;
+		ram_src_cidx = -ping_size;
+		ram_dst_cidx = ping_size;
+		edma_set_dest(lch, asp_dst_pong, INCR, W8BIT);
+
+		lch = prtd->asp_link_lch[0];
+		if (convert_mono_stereo) {
+			edma_set_dest_index(lch, 0, data_type);
+			lch = prtd->asp_link_lch[1];
+			edma_set_dest_index(lch, 0, data_type);
+		} else {
+			edma_set_dest_index(lch, data_type, 0);
+			lch = prtd->asp_link_lch[1];
+			edma_set_dest_index(lch, data_type, 0);
+		}
+		lch = prtd->ram_link_lch;
+		edma_set_dest(lch, runtime->dma_addr, INCR, W32BIT);
+	}
+
+	lch = prtd->asp_link_lch[0];
+	if (convert_mono_stereo) {
+		/*
+		 * Each byte is sent twice, so
+		 * A_CNT * B_CNT * C_CNT = 2 * ping_size
+		 */
+		edma_set_transfer_params(lch, data_type,
+				2, ping_size/data_type, 2, ASYNC);
+		lch = prtd->asp_link_lch[1];
+		edma_set_transfer_params(lch, data_type,
+				2, ping_size/data_type, 2, ASYNC);
+	} else {
+		edma_set_transfer_params(lch, data_type,
+				ping_size/data_type, 1, 0, ASYNC);
+		lch = prtd->asp_link_lch[1];
+		edma_set_transfer_params(lch, data_type,
+				ping_size/data_type, 1, 0, ASYNC);
+	}
+
+
+	lch = prtd->ram_link_lch;
+	edma_set_src_index(lch, ping_size, ram_src_cidx);
+	edma_set_dest_index(lch, ping_size, ram_dst_cidx);
+	edma_set_transfer_params(lch, ping_size, 2,
+			runtime->periods, 2, ASYNC);
+
+	/* init master params */
+	edma_read_slot(prtd->asp_link_lch[0], &prtd->asp_params);
+	edma_read_slot(prtd->ram_link_lch, &prtd->ram_params);
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		struct edmacc_param p_ram;
+		/* Copy entire iram buffer before playback started */
+		prtd->ram_params.a_b_cnt = (1 << 16) | (ping_size << 1);
+		/* 0 dst_bidx */
+		prtd->ram_params.src_dst_bidx = (ping_size << 1);
+		/* 0 dst_cidx */
+		prtd->ram_params.src_dst_cidx = (ping_size << 1);
+		prtd->ram_params.ccnt = 1;
+
+		/* Skip 1st period */
+		edma_read_slot(prtd->ram_link_lch, &p_ram);
+		p_ram.src += (ping_size << 1);
+		p_ram.ccnt -= 1;
+		edma_write_slot(prtd->ram_link_lch2, &p_ram);
+/*
+ * when 1st started, ram -> iram dma channel will fill the entire iram
+ * Then, whenever a ping/pong asp buffer finishes, 1/2 iram will be filled
+ */
+		prtd->ram_params.link_bcntrld = prtd->ram_link_lch2 << 5;
+ 	}
+	return 0;
+ }
+ 
+/* 1 asp tx or rx channel using 2 parameter channels
+ * 1 ram to/from iram channel using 1 parameter channel
+ *
+ * Playback
+ * ram copy channel kicks off first,
+ * 1st ram copy of entire iram buffer completion kicks off asp channel
+ * asp tcc always kicks off ram copy of 1/2 iram buffer
+ *
+ * Record
+ * asp channel starts, tcc kicks off ram copy
+ */
+
 static int davinci_pcm_dma_request(struct snd_pcm_substream *substream)
 {
-	struct davinci_runtime_data *prtd = substream->runtime->private_data;
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct snd_dma_buffer *iram_dma =
+		(struct snd_dma_buffer *)substream->dma_buffer.private_data;
+	struct davinci_runtime_data *prtd = runtime->private_data;
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct davinci_pcm_dma_params *dma_data = rtd->dai->cpu_dai->dma_data;
 	struct edmacc_param p_ram;
+
+	dma_addr_t asp_src_ping;
+	dma_addr_t asp_dst_ping;
+
 	int ret;
+	int lch;
 
-	if (!dma_data)
+	if ((!dma_data) || (!iram_dma))
 		return -ENODEV;
 
-	prtd->params = dma_data;
-
-	/* Request master DMA channel */
-	ret = edma_alloc_channel(prtd->params->channel,
+	/* Request ram master channel */
+	ret = prtd->ram_master_lch = edma_alloc_channel(EDMA_CHANNEL_ANY,
 				  davinci_pcm_dma_irq, substream,
-				  EVENTQ_0);
+				  EVENTQ_1);
 	if (ret < 0)
-		return ret;
-	prtd->master_lch = ret;
+		goto exit1;
 
-	/* Request parameter RAM reload slot */
-	ret = edma_alloc_slot(EDMA_CTLR(prtd->master_lch), EDMA_SLOT_ANY);
-	if (ret < 0) {
-		edma_free_channel(prtd->master_lch);
-		return ret;
+	/* Request ram link channel */
+	ret = prtd->ram_link_lch 
+		= edma_alloc_slot(EDMA_CTLR(prtd->ram_master_lch), EDMA_SLOT_ANY);
+	if (ret < 0)
+		goto exit2;
+
+	/* Request asp master DMA channel */
+	ret = prtd->asp_master_lch = edma_alloc_channel(dma_data->channel,
+			  davinci_pcm_dma_irq, substream,
+			  EVENTQ_0);
+	if (ret < 0)
+		goto exit3;
+
+	/* Request asp link channels */
+	ret = prtd->asp_link_lch[0] 
+		= edma_alloc_slot(EDMA_CTLR(prtd->asp_master_lch), EDMA_SLOT_ANY);
+	if (ret < 0)
+		goto exit4;
+	ret = prtd->asp_link_lch[1] 
+		= edma_alloc_slot(EDMA_CTLR(prtd->asp_master_lch), EDMA_SLOT_ANY);
+	if (ret < 0)
+		goto exit5;
+
+	prtd->ram_link_lch2 = -1;
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		ret = prtd->ram_link_lch2 
+			= edma_alloc_slot(EDMA_CTLR(prtd->ram_master_lch), EDMA_SLOT_ANY);
+		if (ret < 0)
+			goto exit6;
+	}
+
+	/* circle ping-pong buffers */
+	edma_link(prtd->asp_link_lch[0], prtd->asp_link_lch[1]);
+	edma_link(prtd->asp_link_lch[1], prtd->asp_link_lch[0]);
+	/* circle ram buffers */
+	edma_link(prtd->ram_link_lch, prtd->ram_link_lch);
+ 
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		asp_src_ping = iram_dma->addr;
+		asp_dst_ping = dma_data->dma_addr;	/* fifo */
+	} else {
+		asp_src_ping = dma_data->dma_addr;	/* fifo */
+		asp_dst_ping = iram_dma->addr;
 	}
-	prtd->slave_lch = ret;
-
-	/* Issue transfer completion IRQ when the channel completes a
-	 * transfer, then always reload from the same slot (by a kind
-	 * of loopback link).  The completion IRQ handler will update
-	 * the reload slot with a new buffer.
-	 *
-	 * REVISIT save p_ram here after setting up everything except
-	 * the buffer and its length (ccnt) ... use it as a template
-	 * so davinci_pcm_enqueue_dma() takes less time in IRQ.
-	 */
-	edma_read_slot(prtd->slave_lch, &p_ram);
-	p_ram.opt |= TCINTEN | EDMA_TCC(EDMA_CHAN_SLOT(prtd->master_lch));
-	p_ram.link_bcntrld = EDMA_CHAN_SLOT(prtd->slave_lch) << 5;
-	edma_write_slot(prtd->slave_lch, &p_ram);
+	/* ping */
+	lch = prtd->asp_link_lch[0];
+	edma_set_src(lch, asp_src_ping, INCR, W16BIT);
+	edma_set_dest(lch, asp_dst_ping, INCR, W16BIT);
+	edma_set_src_index(lch, 0, 0);
+	edma_set_dest_index(lch, 0, 0);
+
+	edma_read_slot(lch, &p_ram);
+	p_ram.opt &= ~(TCCMODE | EDMA_TCC(0x3f) | TCINTEN);
+	p_ram.opt |= TCCHEN | EDMA_TCC(prtd->ram_master_lch & 0x3f);
+	edma_write_slot(lch, &p_ram);
+
+	/* pong */
+	lch = prtd->asp_link_lch[1];
+	edma_set_src(lch, asp_src_ping, INCR, W16BIT);
+	edma_set_dest(lch, asp_dst_ping, INCR, W16BIT);
+	edma_set_src_index(lch, 0, 0);
+	edma_set_dest_index(lch, 0, 0);
+
+	edma_read_slot(lch, &p_ram);
+	p_ram.opt &= ~(TCCMODE | EDMA_TCC(0x3f));
+	/* interrupt after every pong completion */
+	p_ram.opt |= TCINTEN | TCCHEN | ((prtd->ram_master_lch & 0x3f)<<12);
+	edma_write_slot(lch, &p_ram);
+
+	/* ram */
+	lch = prtd->ram_link_lch;
+	edma_set_src(lch, iram_dma->addr, INCR, W32BIT);
+	edma_set_dest(lch, iram_dma->addr, INCR, W32BIT);
+	pr_debug("%s: audio dma channels/slots in use for ram:%u %u %u,"
+		"for asp:%u %u %u\n", __func__,
+		prtd->ram_master_lch, prtd->ram_link_lch, prtd->ram_link_lch2,
+		prtd->asp_master_lch, prtd->asp_link_lch[0],
+		prtd->asp_link_lch[1]);
 
 	return 0;
+exit6:
+	edma_free_channel(prtd->ram_link_lch2);
+exit5:
+	edma_free_channel(prtd->asp_link_lch[0]);
+exit4:
+	edma_free_channel(prtd->asp_master_lch);
+exit3:
+	edma_free_channel(prtd->ram_link_lch);
+exit2:
+	edma_free_channel(prtd->ram_master_lch);
+exit1:
+	return ret;
 }
 
+/* I2S master (codec/cpudai) should start/stop dma request,
+ *  we shouldn't ignore them
+ *  codec AIC33 needs fixed
+ */
+#define BROKEN_MASTER 1
+#ifdef BROKEN_MASTER
 static int davinci_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 {
 	struct davinci_runtime_data *prtd = substream->runtime->private_data;
@@ -178,12 +372,12 @@  static int davinci_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 	case SNDRV_PCM_TRIGGER_START:
 	case SNDRV_PCM_TRIGGER_RESUME:
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
-		edma_start(prtd->master_lch);
+		edma_resume(prtd->asp_master_lch);
 		break;
 	case SNDRV_PCM_TRIGGER_STOP:
 	case SNDRV_PCM_TRIGGER_SUSPEND:
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
-		edma_stop(prtd->master_lch);
+		edma_pause(prtd->asp_master_lch);
 		break;
 	default:
 		ret = -EINVAL;
@@ -194,18 +388,25 @@  static int davinci_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 
 	return ret;
 }
+#endif
 
 static int davinci_pcm_prepare(struct snd_pcm_substream *substream)
 {
+	int ret;
 	struct davinci_runtime_data *prtd = substream->runtime->private_data;
-	struct edmacc_param temp;
 
-	prtd->period = 0;
-	davinci_pcm_enqueue_dma(substream);
+	ret = davinci_pcm_dma_setup(substream);
+	if (ret < 0)
+		return ret;
 
-	/* Copy self-linked parameter RAM entry into master channel */
-	edma_read_slot(prtd->slave_lch, &temp);
-	edma_write_slot(prtd->master_lch, &temp);
+	edma_write_slot(prtd->ram_master_lch, &prtd->ram_params);
+	edma_write_slot(prtd->asp_master_lch, &prtd->asp_params);
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		/* copy 1st iram buffer */
+		edma_start(prtd->ram_master_lch);
+	}
+	edma_start(prtd->asp_master_lch);
 
 	return 0;
 }
@@ -216,20 +417,43 @@  davinci_pcm_pointer(struct snd_pcm_substream *substream)
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct davinci_runtime_data *prtd = runtime->private_data;
 	unsigned int offset;
-	dma_addr_t count;
-	dma_addr_t src, dst;
+	int count_asp, count_ram;
+	int mod_ram;
+	dma_addr_t ram_src, ram_dst;
+	dma_addr_t asp_src, asp_dst;
+	unsigned int period_size = snd_pcm_lib_period_bytes(substream);
 
 	spin_lock(&prtd->lock);
-
-	edma_get_position(prtd->master_lch, &src, &dst);
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
-		count = src - runtime->dma_addr;
-	else
-		count = dst - runtime->dma_addr;
-
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		/* reading ram before asp should be safe
+		 * as long as the asp transfers less than a ping size
+		 * of bytes between the 2 reads
+		 */
+		edma_get_position(prtd->ram_master_lch,
+				&ram_src, &ram_dst);
+		edma_get_position(prtd->asp_master_lch,
+				&asp_src, &asp_dst);
+		count_asp = asp_src - prtd->asp_params.src;
+		count_ram = ram_src - prtd->ram_params.src;
+		mod_ram = count_ram % period_size;
+		mod_ram -= count_asp;
+		if (mod_ram < 0)
+			mod_ram += period_size;
+		else if (mod_ram == 0) {
+			if (snd_pcm_running(substream))
+				mod_ram += period_size;
+		}
+		count_ram -= mod_ram;
+		if (count_ram < 0)
+			count_ram += period_size * runtime->periods;
+	} else {
+		edma_get_position(prtd->ram_master_lch,
+				&ram_src, &ram_dst);
+		count_ram = ram_dst - prtd->ram_params.dst;
+	}
 	spin_unlock(&prtd->lock);
 
-	offset = bytes_to_frames(runtime, count);
+	offset = bytes_to_frames(runtime, count_ram);
 	if (offset >= runtime->buffer_size)
 		offset = 0;
 
@@ -243,6 +467,11 @@  static int davinci_pcm_open(struct snd_pcm_substream *substream)
 	int ret = 0;
 
 	snd_soc_set_runtime_hwparams(substream, &davinci_pcm_hardware);
+	/* ensure that buffer size is a multiple of period size */
+	ret = snd_pcm_hw_constraint_integer(runtime,
+						SNDRV_PCM_HW_PARAM_PERIODS);
+	if (ret < 0)
+		return ret;
 
 	prtd = kzalloc(sizeof(struct davinci_runtime_data), GFP_KERNEL);
 	if (prtd == NULL)
@@ -266,11 +495,21 @@  static int davinci_pcm_close(struct snd_pcm_substream *substream)
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct davinci_runtime_data *prtd = runtime->private_data;
 
-	edma_unlink(prtd->slave_lch);
-
-	edma_free_slot(prtd->slave_lch);
-	edma_free_channel(prtd->master_lch);
-
+	edma_stop(prtd->ram_master_lch);
+	edma_stop(prtd->asp_master_lch);
+	edma_unlink(prtd->asp_link_lch[0]);
+	edma_unlink(prtd->asp_link_lch[1]);
+	edma_unlink(prtd->ram_link_lch);
+
+	edma_free_slot(prtd->asp_link_lch[0]);
+	edma_free_slot(prtd->asp_link_lch[1]);
+	edma_free_channel(prtd->asp_master_lch);
+	edma_free_slot(prtd->ram_link_lch);
+	if (prtd->ram_link_lch2 != -1) {
+		edma_free_slot(prtd->ram_link_lch2);
+		prtd->ram_link_lch2 = -1;
+	}
+	edma_free_channel(prtd->ram_master_lch);
 	kfree(prtd);
 
 	return 0;
@@ -306,7 +545,9 @@  static struct snd_pcm_ops davinci_pcm_ops = {
 	.hw_params = 	davinci_pcm_hw_params,
 	.hw_free = 	davinci_pcm_hw_free,
 	.prepare = 	davinci_pcm_prepare,
-	.trigger = 	davinci_pcm_trigger,
+#ifdef BROKEN_MASTER
+	.trigger =	davinci_pcm_trigger,
+#endif
 	.pointer = 	davinci_pcm_pointer,
 	.mmap = 	davinci_pcm_mmap,
 };
@@ -316,10 +557,15 @@  static int davinci_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream)
 	struct snd_pcm_substream *substream = pcm->streams[stream].substream;
 	struct snd_dma_buffer *buf = &substream->dma_buffer;
 	size_t size = davinci_pcm_hardware.buffer_bytes_max;
+	struct snd_dma_buffer *iram_dma = NULL;
+	dma_addr_t iram_phys = 0;
+	void *iram_virt = NULL;
+	unsigned int iram_size = davinci_pcm_hardware.period_bytes_max;
 
 	buf->dev.type = SNDRV_DMA_TYPE_DEV;
 	buf->dev.dev = pcm->card->dev;
 	buf->private_data = NULL;
+	buf->bytes = size;
 	buf->area = dma_alloc_writecombine(pcm->card->dev, size,
 					   &buf->addr, GFP_KERNEL);
 
@@ -327,10 +573,27 @@  static int davinci_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream)
 		"size=%d\n", (void *) buf->area, (void *) buf->addr, size);
 
 	if (!buf->area)
-		return -ENOMEM;
-
-	buf->bytes = size;
+		goto exit1;
+	iram_virt = sram_alloc(iram_size, &iram_phys);
+	if (!iram_virt)
+		goto exit2;
+	iram_dma = kzalloc(sizeof(*iram_dma), GFP_KERNEL);
+	if (!iram_dma)
+		goto exit3;
+	iram_dma->area = iram_virt;
+	iram_dma->addr = iram_phys;
+	memset(iram_dma->area, 0, iram_size);
+	buf->private_data = iram_dma ;
 	return 0;
+	kfree(iram_dma);
+exit3:
+	if (iram_virt)
+		sram_free(iram_virt, iram_size);
+exit2:
+	dma_free_writecombine(pcm->card->dev, size, buf->area, buf->addr);
+	buf->area = NULL;
+exit1:
+	return -ENOMEM;
 }
 
 static void davinci_pcm_free(struct snd_pcm *pcm)
@@ -340,6 +603,8 @@  static void davinci_pcm_free(struct snd_pcm *pcm)
 	int stream;
 
 	for (stream = 0; stream < 2; stream++) {
+		unsigned int iram_size = davinci_pcm_hardware.period_bytes_max;
+		struct snd_dma_buffer *iram_dma;
 		substream = pcm->streams[stream].substream;
 		if (!substream)
 			continue;
@@ -351,6 +616,11 @@  static void davinci_pcm_free(struct snd_pcm *pcm)
 		dma_free_writecombine(pcm->card->dev, buf->bytes,
 				      buf->area, buf->addr);
 		buf->area = NULL;
+		iram_dma = (struct snd_dma_buffer *)buf->private_data;
+		if (iram_dma) {
+			sram_free(iram_dma->area, iram_size);
+			kfree(iram_dma);
+		}
 	}
 }
 
@@ -368,14 +638,14 @@  static int davinci_pcm_new(struct snd_card *card,
 
 	if (dai->playback.channels_min) {
 		ret = davinci_pcm_preallocate_dma_buffer(pcm,
-			SNDRV_PCM_STREAM_PLAYBACK);
+				SNDRV_PCM_STREAM_PLAYBACK);
 		if (ret)
 			return ret;
 	}
 
 	if (dai->capture.channels_min) {
 		ret = davinci_pcm_preallocate_dma_buffer(pcm,
-			SNDRV_PCM_STREAM_CAPTURE);
+				SNDRV_PCM_STREAM_CAPTURE);
 		if (ret)
 			return ret;
 	}
diff --git a/sound/soc/davinci/davinci-pcm.h b/sound/soc/davinci/davinci-pcm.h
index 62cb4eb..fc70161 100644
--- a/sound/soc/davinci/davinci-pcm.h
+++ b/sound/soc/davinci/davinci-pcm.h
@@ -16,7 +16,8 @@  struct davinci_pcm_dma_params {
 	char *name;		/* stream identifier */
 	int channel;		/* sync dma channel ID */
 	dma_addr_t dma_addr;	/* device physical address for DMA */
-	unsigned int data_type;	/* xfer data type */
+	unsigned char data_type;	/* xfer data type */
+	unsigned char convert_mono_stereo;
 };
 
 struct evm_snd_platform_data {
diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h
index 1367647..fe9bfa3 100644
--- a/include/sound/soc-dai.h
+++ b/include/sound/soc-dai.h
@@ -137,6 +137,7 @@  int snd_soc_dai_digital_mute(struct snd_soc_dai *dai, int mute);
  * This structure covers the clocking, formating and ALSA operations for each
  * interface a
  */
+/* ASoC DAI ops */
 struct snd_soc_dai_ops {
 	/*
 	 * DAI clocking configuration, all optional.
@@ -162,6 +163,7 @@  struct snd_soc_dai_ops {
 	 * Called by soc-core to minimise any pops.
 	 */
 	int (*digital_mute)(struct snd_soc_dai *dai, int mute);
+	int (*inform_channel_order)(struct snd_soc_dai *dai, int right_first);
 
 	/*
 	 * ALSA PCM audio operations - all optional.