ASoC: fsl: add memory to memory function for ASRC

Merge series from Shengjiu Wang <shengjiu.wang@nxp.com>:

This function is base on the accelerator implementation
for compress API:
0417715 ("ALSA: compress_offload: introduce accel operation mode")

Audio signal processing also has the requirement for memory to
memory similar as Video.

This asrc memory to memory (memory ->asrc->memory) case is a non
real time use case.

User fills the input buffer to the asrc module, after conversion, then asrc
sends back the output buffer to user. So it is not a traditional ALSA playback
and capture case.

Because we had implemented the "memory -> asrc ->i2s device-> codec"
use case in ALSA.  Now the "memory->asrc->memory" needs
to reuse the code in asrc driver, so the patch 1 and patch 2 is for refining
the code to make it can be shared by the "memory->asrc->memory"
driver.

Other change is to add memory to memory support for two kinds of i.MX ASRC
modules.

Author: broonie

include/uapi/sound/compress_params.h

@@ -334,6 +334,14 @@ union snd_codec_options {
 	struct snd_dec_wma wma_d;
 	struct snd_dec_alac alac_d;
 	struct snd_dec_ape ape_d;
+	struct {
+		__u32 out_sample_rate;
+	} src_d;
+} __attribute__((packed, aligned(4)));
+
+struct snd_codec_desc_src {
+	__u32 out_sample_rate_min;
+	__u32 out_sample_rate_max;
 } __attribute__((packed, aligned(4)));
 
 /** struct snd_codec_desc - description of codec capabilities
@@ -347,6 +355,9 @@ union snd_codec_options {
  * @modes: Supported modes. See SND_AUDIOMODE defines
  * @formats: Supported formats. See SND_AUDIOSTREAMFORMAT defines
  * @min_buffer: Minimum buffer size handled by codec implementation
+ * @pcm_formats: Output (for decoders) or input (for encoders)
+ *               PCM formats (required to accel mode, 0 for other modes)
+ * @u_space: union space (for codec dependent data)
  * @reserved: reserved for future use
  *
  * This structure provides a scalar value for profiles, modes and stream
@@ -370,7 +381,12 @@ struct snd_codec_desc {
 	__u32 modes;
 	__u32 formats;
 	__u32 min_buffer;
-	__u32 reserved[15];
+	__u32 pcm_formats;
+	union {
+		__u32 u_space[6];
+		struct snd_codec_desc_src src;
+	} __attribute__((packed, aligned(4)));
+	__u32 reserved[8];
 } __attribute__((packed, aligned(4)));
 
 /** struct snd_codec
@@ -395,6 +411,8 @@ struct snd_codec_desc {
  * @align: Block alignment in bytes of an audio sample.
  *		Only required for PCM or IEC formats.
  * @options: encoder-specific settings
+ * @pcm_format: Output (for decoders) or input (for encoders)
+ *               PCM formats (required to accel mode, 0 for other modes)
  * @reserved: reserved for future use
  */
 
@@ -411,7 +429,8 @@ struct snd_codec {
 	__u32 format;
 	__u32 align;
 	union snd_codec_options options;
-	__u32 reserved[3];
+	__u32 pcm_format;
+	__u32 reserved[2];
 } __attribute__((packed, aligned(4)));
 
 #endif

sound/soc/fsl/Kconfig

@@ -8,6 +8,8 @@ config SND_SOC_FSL_ASRC
 	depends on HAS_DMA
 	select REGMAP_MMIO
 	select SND_SOC_GENERIC_DMAENGINE_PCM
+	select SND_COMPRESS_ACCEL
+	select SND_COMPRESS_OFFLOAD
 	help
 	  Say Y if you want to add Asynchronous Sample Rate Converter (ASRC)
 	  support for the Freescale CPUs.

sound/soc/fsl/Makefile

@@ -10,7 +10,7 @@ obj-$(CONFIG_SND_SOC_P1022_RDK) += snd-soc-p1022-rdk.o
 # Freescale SSI/DMA/SAI/SPDIF Support
 snd-soc-fsl-audmix-y := fsl_audmix.o
 snd-soc-fsl-asoc-card-y := fsl-asoc-card.o
-snd-soc-fsl-asrc-y := fsl_asrc.o fsl_asrc_dma.o
+snd-soc-fsl-asrc-y := fsl_asrc.o fsl_asrc_dma.o fsl_asrc_m2m.o
 snd-soc-fsl-lpc3xxx-y := lpc3xxx-pcm.o lpc3xxx-i2s.o
 snd-soc-fsl-sai-y := fsl_sai.o
 snd-soc-fsl-ssi-y := fsl_ssi.o

sound/soc/fsl/fsl_asrc.c

@@ -1063,6 +1063,139 @@ static int fsl_asrc_get_fifo_addr(u8 dir, enum asrc_pair_index index)
 	return REG_ASRDx(dir, index);
 }
 
+/* Get sample numbers in FIFO */
+static unsigned int fsl_asrc_get_output_fifo_size(struct fsl_asrc_pair *pair)
+{
+	struct fsl_asrc *asrc = pair->asrc;
+	enum asrc_pair_index index = pair->index;
+	u32 val;
+
+	regmap_read(asrc->regmap, REG_ASRFST(index), &val);
+
+	val &= ASRFSTi_OUTPUT_FIFO_MASK;
+
+	return val >> ASRFSTi_OUTPUT_FIFO_SHIFT;
+}
+
+static int fsl_asrc_m2m_prepare(struct fsl_asrc_pair *pair)
+{
+	struct fsl_asrc_pair_priv *pair_priv = pair->private;
+	struct fsl_asrc *asrc = pair->asrc;
+	struct device *dev = &asrc->pdev->dev;
+	struct asrc_config config;
+	int ret;
+
+	/* fill config */
+	config.pair = pair->index;
+	config.channel_num = pair->channels;
+	config.input_sample_rate = pair->rate[IN];
+	config.output_sample_rate = pair->rate[OUT];
+	config.input_format = pair->sample_format[IN];
+	config.output_format = pair->sample_format[OUT];
+	config.inclk = INCLK_NONE;
+	config.outclk = OUTCLK_ASRCK1_CLK;
+
+	pair_priv->config = &config;
+	ret = fsl_asrc_config_pair(pair, true);
+	if (ret) {
+		dev_err(dev, "failed to config pair: %d\n", ret);
+		return ret;
+	}
+
+	pair->first_convert = 1;
+
+	return 0;
+}
+
+static int fsl_asrc_m2m_start(struct fsl_asrc_pair *pair)
+{
+	if (pair->first_convert) {
+		fsl_asrc_start_pair(pair);
+		pair->first_convert = 0;
+	}
+	/*
+	 * Clear DMA request during the stall state of ASRC:
+	 * During STALL state, the remaining in input fifo would never be
+	 * smaller than the input threshold while the output fifo would not
+	 * be bigger than output one. Thus the DMA request would be cleared.
+	 */
+	fsl_asrc_set_watermarks(pair, ASRC_FIFO_THRESHOLD_MIN,
+				ASRC_FIFO_THRESHOLD_MAX);
+
+	/* Update the real input threshold to raise DMA request */
+	fsl_asrc_set_watermarks(pair, ASRC_M2M_INPUTFIFO_WML,
+				ASRC_M2M_OUTPUTFIFO_WML);
+
+	return 0;
+}
+
+static int fsl_asrc_m2m_stop(struct fsl_asrc_pair *pair)
+{
+	if (!pair->first_convert) {
+		fsl_asrc_stop_pair(pair);
+		pair->first_convert = 1;
+	}
+
+	return 0;
+}
+
+/* calculate capture data length according to output data length and sample rate */
+static int fsl_asrc_m2m_calc_out_len(struct fsl_asrc_pair *pair, int input_buffer_length)
+{
+	unsigned int in_width, out_width;
+	unsigned int channels = pair->channels;
+	unsigned int in_samples, out_samples;
+	unsigned int out_length;
+
+	in_width = snd_pcm_format_physical_width(pair->sample_format[IN]) / 8;
+	out_width = snd_pcm_format_physical_width(pair->sample_format[OUT]) / 8;
+
+	in_samples = input_buffer_length / in_width / channels;
+	out_samples = pair->rate[OUT] * in_samples / pair->rate[IN];
+	out_length = (out_samples - ASRC_OUTPUT_LAST_SAMPLE) * out_width * channels;
+
+	return out_length;
+}
+
+static int fsl_asrc_m2m_get_maxburst(u8 dir, struct fsl_asrc_pair *pair)
+{
+	struct fsl_asrc *asrc = pair->asrc;
+	struct fsl_asrc_priv *asrc_priv = asrc->private;
+	int wml = (dir == IN) ? ASRC_M2M_INPUTFIFO_WML : ASRC_M2M_OUTPUTFIFO_WML;
+
+	if (!asrc_priv->soc->use_edma)
+		return wml * pair->channels;
+	else
+		return 1;
+}
+
+static int fsl_asrc_m2m_get_cap(struct fsl_asrc_m2m_cap *cap)
+{
+	cap->fmt_in = FSL_ASRC_FORMATS;
+	cap->fmt_out = FSL_ASRC_FORMATS | SNDRV_PCM_FMTBIT_S8;
+
+	cap->rate_in = supported_asrc_rate;
+	cap->rate_in_count = ARRAY_SIZE(supported_asrc_rate);
+	cap->rate_out = supported_asrc_rate;
+	cap->rate_out_count = ARRAY_SIZE(supported_asrc_rate);
+	cap->chan_min = 1;
+	cap->chan_max = 10;
+
+	return 0;
+}
+
+static int fsl_asrc_m2m_pair_resume(struct fsl_asrc_pair *pair)
+{
+	struct fsl_asrc *asrc = pair->asrc;
+	int i;
+
+	for (i = 0; i < pair->channels * 4; i++)
+		regmap_write(asrc->regmap, REG_ASRDI(pair->index), 0);
+
+	pair->first_convert = 1;
+	return 0;
+}
+
 static int fsl_asrc_runtime_resume(struct device *dev);
 static int fsl_asrc_runtime_suspend(struct device *dev);
 
@@ -1147,6 +1280,15 @@ static int fsl_asrc_probe(struct platform_device *pdev)
 	asrc->get_fifo_addr = fsl_asrc_get_fifo_addr;
 	asrc->pair_priv_size = sizeof(struct fsl_asrc_pair_priv);
 
+	asrc->m2m_prepare = fsl_asrc_m2m_prepare;
+	asrc->m2m_start = fsl_asrc_m2m_start;
+	asrc->m2m_stop = fsl_asrc_m2m_stop;
+	asrc->get_output_fifo_size = fsl_asrc_get_output_fifo_size;
+	asrc->m2m_calc_out_len = fsl_asrc_m2m_calc_out_len;
+	asrc->m2m_get_maxburst = fsl_asrc_m2m_get_maxburst;
+	asrc->m2m_pair_resume = fsl_asrc_m2m_pair_resume;
+	asrc->m2m_get_cap = fsl_asrc_m2m_get_cap;
+
 	if (of_device_is_compatible(np, "fsl,imx35-asrc")) {
 		asrc_priv->clk_map[IN] = input_clk_map_imx35;
 		asrc_priv->clk_map[OUT] = output_clk_map_imx35;
@@ -1242,6 +1384,12 @@ static int fsl_asrc_probe(struct platform_device *pdev)
 		goto err_pm_get_sync;
 	}
 
+	ret = fsl_asrc_m2m_init(asrc);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to init m2m device %d\n", ret);
+		return ret;
+	}
+
 	return 0;
 
 err_pm_get_sync:
@@ -1254,6 +1402,10 @@ static int fsl_asrc_probe(struct platform_device *pdev)
 
 static void fsl_asrc_remove(struct platform_device *pdev)
 {
+	struct fsl_asrc *asrc = dev_get_drvdata(&pdev->dev);
+
+	fsl_asrc_m2m_exit(asrc);
+
 	pm_runtime_disable(&pdev->dev);
 	if (!pm_runtime_status_suspended(&pdev->dev))
 		fsl_asrc_runtime_suspend(&pdev->dev);
@@ -1355,10 +1507,29 @@ static int fsl_asrc_runtime_suspend(struct device *dev)
 	return 0;
 }
 
+static int fsl_asrc_suspend(struct device *dev)
+{
+	struct fsl_asrc *asrc = dev_get_drvdata(dev);
+	int ret;
+
+	fsl_asrc_m2m_suspend(asrc);
+	ret = pm_runtime_force_suspend(dev);
+	return ret;
+}
+
+static int fsl_asrc_resume(struct device *dev)
+{
+	struct fsl_asrc *asrc = dev_get_drvdata(dev);
+	int ret;
+
+	ret = pm_runtime_force_resume(dev);
+	fsl_asrc_m2m_resume(asrc);
+	return ret;
+}
+
 static const struct dev_pm_ops fsl_asrc_pm = {
-	SET_RUNTIME_PM_OPS(fsl_asrc_runtime_suspend, fsl_asrc_runtime_resume, NULL)
-	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
-				pm_runtime_force_resume)
+	RUNTIME_PM_OPS(fsl_asrc_runtime_suspend, fsl_asrc_runtime_resume, NULL)
+	SYSTEM_SLEEP_PM_OPS(fsl_asrc_suspend, fsl_asrc_resume)
 };
 
 static const struct fsl_asrc_soc_data fsl_asrc_imx35_data = {
@@ -1396,7 +1567,7 @@ static struct platform_driver fsl_asrc_driver = {
 	.driver = {
 		.name = "fsl-asrc",
 		.of_match_table = fsl_asrc_ids,
-		.pm = &fsl_asrc_pm,
+		.pm = pm_ptr(&fsl_asrc_pm),
 	},
 };
 module_platform_driver(fsl_asrc_driver);

sound/soc/fsl/fsl_asrc.h

@@ -12,6 +12,8 @@
 
 #include  "fsl_asrc_common.h"
 
+#define ASRC_M2M_INPUTFIFO_WML		0x4
+#define ASRC_M2M_OUTPUTFIFO_WML		0x2
 #define ASRC_DMA_BUFFER_NUM		2
 #define ASRC_INPUTFIFO_THRESHOLD	32
 #define ASRC_OUTPUTFIFO_THRESHOLD	32