ASoC: qcom: q6apm: Add support for early buffer mapping on DSP

Buffers are allocated on pcm_new and mapped in the dsp on every
prepare call, which is inefficient and unnecessary.

Add new functions q6apm_[un]map_memory_fixed_region to map it on
to dsp only once after allocation.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@oss.qualcomm.com>
Link: https://patch.msgid.link/20260402081118.348071-14-srinivas.kandagatla@oss.qualcomm.com
Signed-off-by: Mark Brown <broonie@kernel.org>

sound/soc/qcom/qdsp6/audioreach.c

@@ -1396,66 +1396,6 @@ void audioreach_graph_free_buf(struct q6apm_graph *graph)
 }
 EXPORT_SYMBOL_GPL(audioreach_graph_free_buf);
 
-int audioreach_map_memory_regions(struct q6apm_graph *graph, unsigned int dir, size_t period_sz,
-				  unsigned int periods, bool is_contiguous)
-{
-	struct apm_shared_map_region_payload *mregions;
-	struct apm_cmd_shared_mem_map_regions *cmd;
-	uint32_t num_regions, buf_sz, payload_size;
-	struct audioreach_graph_data *data;
-	struct gpr_pkt *pkt __free(kfree) = NULL;
-	void *p;
-	int i;
-
-	if (dir == SNDRV_PCM_STREAM_PLAYBACK)
-		data = &graph->rx_data;
-	else
-		data = &graph->tx_data;
-
-	if (is_contiguous) {
-		num_regions = 1;
-		buf_sz = period_sz * periods;
-	} else {
-		buf_sz = period_sz;
-		num_regions = periods;
-	}
-
-	/* DSP expects size should be aligned to 4K */
-	buf_sz = ALIGN(buf_sz, 4096);
-
-	payload_size = sizeof(*cmd) + (sizeof(*mregions) * num_regions);
-
-	pkt = audioreach_alloc_apm_pkt(payload_size, APM_CMD_SHARED_MEM_MAP_REGIONS, dir,
-				     graph->port->id);
-	if (IS_ERR(pkt))
-		return PTR_ERR(pkt);
-
-	p = (void *)pkt + GPR_HDR_SIZE;
-	cmd = p;
-	cmd->mem_pool_id = APM_MEMORY_MAP_SHMEM8_4K_POOL;
-	cmd->num_regions = num_regions;
-
-	cmd->property_flag = 0x0;
-
-	mregions = p + sizeof(*cmd);
-
-	mutex_lock(&graph->lock);
-
-	for (i = 0; i < num_regions; i++) {
-		struct audio_buffer *ab;
-
-		ab = &data->buf[i];
-		mregions->shm_addr_lsw = lower_32_bits(ab->phys);
-		mregions->shm_addr_msw = upper_32_bits(ab->phys);
-		mregions->mem_size_bytes = buf_sz;
-		++mregions;
-	}
-	mutex_unlock(&graph->lock);
-
-	return audioreach_graph_send_cmd_sync(graph, pkt, APM_CMD_RSP_SHARED_MEM_MAP_REGIONS);
-}
-EXPORT_SYMBOL_GPL(audioreach_map_memory_regions);
-
 int audioreach_shared_memory_send_eos(struct q6apm_graph *graph)
 {
 	struct data_cmd_wr_sh_mem_ep_eos *eos;

sound/soc/qcom/qdsp6/audioreach.h

@@ -722,6 +722,7 @@ struct audioreach_connection {
 
 struct audioreach_graph_info {
 	int id;
+	uint32_t mem_map_handle;
 	uint32_t num_sub_graphs;
 	struct list_head sg_list;
 	/* DPCM connection from FE Graph to BE graph */
@@ -838,10 +839,6 @@ int audioreach_tplg_init(struct snd_soc_component *component);
 
 /* Module specific */
 void audioreach_graph_free_buf(struct q6apm_graph *graph);
-int audioreach_map_memory_regions(struct q6apm_graph *graph,
-				  unsigned int dir, size_t period_sz,
-				  unsigned int periods,
-				  bool is_contiguous);
 int audioreach_send_cmd_sync(struct device *dev, gpr_device_t *gdev, struct gpr_ibasic_rsp_result_t *result,
 			     struct mutex *cmd_lock, gpr_port_t *port, wait_queue_head_t *cmd_wait,
 			     struct gpr_pkt *pkt, uint32_t rsp_opcode);

sound/soc/qcom/qdsp6/q6apm-dai.c

@@ -228,11 +228,10 @@ static int q6apm_dai_prepare(struct snd_soc_component *component,
 	cfg.bit_width = prtd->bits_per_sample;
 	cfg.fmt = SND_AUDIOCODEC_PCM;
 	audioreach_set_default_channel_mapping(cfg.channel_map, runtime->channels);
-
 	if (prtd->state) {
 		/* clear the previous setup if any  */
 		q6apm_graph_stop(prtd->graph);
-		q6apm_unmap_memory_regions(prtd->graph, substream->stream);
+		q6apm_free_fragments(prtd->graph, substream->stream);
 	}
 
 	prtd->pcm_count = snd_pcm_lib_period_bytes(substream);
@@ -247,8 +246,8 @@ static int q6apm_dai_prepare(struct snd_soc_component *component,
 	if (ret < 0)
 		dev_err(dev, "%s: CMD Format block failed\n", __func__);
 
-	ret = q6apm_map_memory_regions(prtd->graph, substream->stream, prtd->phys,
+	ret = q6apm_alloc_fragments(prtd->graph, substream->stream, prtd->phys,
-				       (prtd->pcm_size / prtd->periods), prtd->periods);
+				(prtd->pcm_size / prtd->periods), prtd->periods);
 
 	if (ret < 0) {
 		dev_err(dev, "Audio Start: Buffer Allocation failed rc = %d\n",	ret);
@@ -416,9 +415,10 @@ static int q6apm_dai_close(struct snd_soc_component *component,
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct q6apm_dai_rtd *prtd = runtime->private_data;
 
-	if (prtd->state) { /* only stop graph that is started */
+	if (prtd->state) {
+		/* only stop graph that is started */
 		q6apm_graph_stop(prtd->graph);
-		q6apm_unmap_memory_regions(prtd->graph, substream->stream);
+		q6apm_free_fragments(prtd->graph, substream->stream);
 	}
 
 	q6apm_graph_close(prtd->graph);
@@ -467,11 +467,94 @@ static int q6apm_dai_hw_params(struct snd_soc_component *component,
 	return 0;
 }
 
+static int q6apm_dai_memory_map(struct snd_soc_component *component,
+				struct snd_pcm_substream *substream, int graph_id)
+{
+	struct q6apm_dai_data *pdata;
+	struct device *dev = component->dev;
+	phys_addr_t phys;
+	int ret;
+
+	pdata = snd_soc_component_get_drvdata(component);
+	if (!pdata) {
+		dev_err(component->dev, "Drv data not found ..\n");
+		return -EINVAL;
+	}
+
+	if (pdata->sid < 0)
+		phys = substream->dma_buffer.addr;
+	else
+		phys = substream->dma_buffer.addr | (pdata->sid << 32);
+
+	ret = q6apm_map_memory_fixed_region(dev, graph_id, phys, BUFFER_BYTES_MAX);
+	if (ret < 0)
+		dev_err(dev, "Audio Start: Buffer Allocation failed rc = %d\n",	ret);
+
+	return ret;
+}
+
 static int q6apm_dai_pcm_new(struct snd_soc_component *component, struct snd_soc_pcm_runtime *rtd)
 {
+	struct snd_soc_dai *cpu_dai = snd_soc_rtd_to_cpu(rtd, 0);
+	struct snd_pcm *pcm = rtd->pcm;
 	int size = BUFFER_BYTES_MAX;
+	int graph_id, ret;
+	struct snd_pcm_substream *substream;
 
-	return snd_pcm_set_fixed_buffer_all(rtd->pcm, SNDRV_DMA_TYPE_DEV, component->dev, size);
+	graph_id = cpu_dai->driver->id;
+
+	ret = snd_pcm_set_fixed_buffer_all(pcm, SNDRV_DMA_TYPE_DEV, component->dev, size);
+	if (ret)
+		return ret;
+
+	/* Note: DSP backend dais are uni-directional ONLY(either playback or capture) */
+	if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) {
+		substream = pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream;
+		ret = q6apm_dai_memory_map(component, substream, graph_id);
+		if (ret)
+			return ret;
+	}
+
+	if (pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream) {
+		substream = pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream;
+		ret = q6apm_dai_memory_map(component, substream, graph_id);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void q6apm_dai_memory_unmap(struct snd_soc_component *component,
+				   struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *soc_prtd;
+	struct snd_soc_dai *cpu_dai;
+	int graph_id;
+
+	soc_prtd = snd_soc_substream_to_rtd(substream);
+	if (!soc_prtd)
+		return;
+
+	cpu_dai = snd_soc_rtd_to_cpu(soc_prtd, 0);
+	if (!cpu_dai)
+		return;
+
+	graph_id = cpu_dai->driver->id;
+	q6apm_unmap_memory_fixed_region(component->dev, graph_id);
+}
+
+static void q6apm_dai_pcm_free(struct snd_soc_component *component, struct snd_pcm *pcm)
+{
+	struct snd_pcm_substream *substream;
+
+	substream = pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream;
+	if (substream)
+		q6apm_dai_memory_unmap(component, substream);
+
+	substream = pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream;
+	if (substream)
+		q6apm_dai_memory_unmap(component, substream);
 }
 
 static int q6apm_dai_compr_open(struct snd_soc_component *component,
@@ -530,7 +613,8 @@ static int q6apm_dai_compr_free(struct snd_soc_component *component,
 	struct q6apm_dai_rtd *prtd = runtime->private_data;
 
 	q6apm_graph_stop(prtd->graph);
-	q6apm_unmap_memory_regions(prtd->graph, SNDRV_PCM_STREAM_PLAYBACK);
+	q6apm_free_fragments(prtd->graph, SNDRV_PCM_STREAM_PLAYBACK);
+	q6apm_unmap_memory_fixed_region(component->dev, prtd->graph->id);
 	q6apm_graph_close(prtd->graph);
 	snd_dma_free_pages(&prtd->dma_buffer);
 	prtd->graph = NULL;
@@ -679,9 +763,9 @@ static int q6apm_dai_compr_set_params(struct snd_soc_component *component,
 		if (ret)
 			return ret;
 
-		ret = q6apm_map_memory_regions(prtd->graph, SNDRV_PCM_STREAM_PLAYBACK,
+		ret = q6apm_alloc_fragments(prtd->graph, SNDRV_PCM_STREAM_PLAYBACK,
-					       prtd->phys, (prtd->pcm_size / prtd->periods),
+					prtd->phys, (prtd->pcm_size / prtd->periods),
-					       prtd->periods);
+					prtd->periods);
 		if (ret < 0)
 			return -ENOMEM;
 
@@ -834,6 +918,7 @@ static const struct snd_soc_component_driver q6apm_fe_dai_component = {
 	.close		= q6apm_dai_close,
 	.prepare	= q6apm_dai_prepare,
 	.pcm_new	= q6apm_dai_pcm_new,
+	.pcm_free	= q6apm_dai_pcm_free,
 	.hw_params	= q6apm_dai_hw_params,
 	.pointer	= q6apm_dai_pointer,
 	.trigger	= q6apm_dai_trigger,

sound/soc/qcom/qdsp6/q6apm.c

@@ -200,13 +200,53 @@ int q6apm_graph_media_format_shmem(struct q6apm_graph *graph,
 }
 EXPORT_SYMBOL_GPL(q6apm_graph_media_format_shmem);
 
-int q6apm_map_memory_regions(struct q6apm_graph *graph, unsigned int dir, phys_addr_t phys,
+int q6apm_map_memory_fixed_region(struct device *dev, unsigned int graph_id, phys_addr_t phys,
-			     size_t period_sz, unsigned int periods)
+				  size_t sz)
+{
+	struct audioreach_graph_info *info;
+	struct q6apm *apm = dev_get_drvdata(dev->parent);
+	struct apm_shared_map_region_payload *mregions;
+	struct apm_cmd_shared_mem_map_regions *cmd;
+	int payload_size = sizeof(*cmd) + (sizeof(*mregions));
+	uint32_t buf_sz;
+	void *p;
+	struct gpr_pkt *pkt __free(kfree) = audioreach_alloc_apm_cmd_pkt(payload_size,
+						APM_CMD_SHARED_MEM_MAP_REGIONS, graph_id);
+	if (IS_ERR(pkt))
+		return PTR_ERR(pkt);
+
+	info = idr_find(&apm->graph_info_idr, graph_id);
+	if (!info)
+		return -ENODEV;
+
+	if (info->mem_map_handle)
+		return 0;
+
+	/* DSP expects size should be aligned to 4K */
+	buf_sz = ALIGN(sz, 4096);
+
+	p = (void *)pkt + GPR_HDR_SIZE;
+	cmd = p;
+	cmd->mem_pool_id = APM_MEMORY_MAP_SHMEM8_4K_POOL;
+	cmd->num_regions = 1;
+	cmd->property_flag = 0x0;
+
+	mregions = p + sizeof(*cmd);
+
+	mregions->shm_addr_lsw = lower_32_bits(phys);
+	mregions->shm_addr_msw = upper_32_bits(phys);
+	mregions->mem_size_bytes = buf_sz;
+
+	return q6apm_send_cmd_sync(apm, pkt, APM_CMD_RSP_SHARED_MEM_MAP_REGIONS);
+}
+EXPORT_SYMBOL_GPL(q6apm_map_memory_fixed_region);
+
+int q6apm_alloc_fragments(struct q6apm_graph *graph, unsigned int dir, phys_addr_t phys,
+				size_t period_sz, unsigned int periods)
 {
 	struct audioreach_graph_data *data;
 	struct audio_buffer *buf;
 	int cnt;
-	int rc;
 
 	if (dir == SNDRV_PCM_STREAM_PLAYBACK)
 		data = &graph->rx_data;
@@ -248,46 +288,41 @@ int q6apm_map_memory_regions(struct q6apm_graph *graph, unsigned int dir, phys_a
 
 	mutex_unlock(&graph->lock);
 
-	rc = audioreach_map_memory_regions(graph, dir, period_sz, periods, 1);
+	return 0;
-	if (rc < 0) {
-		dev_err(graph->dev, "Memory_map_regions failed\n");
-		audioreach_graph_free_buf(graph);
-	}
-
-	return rc;
 }
-EXPORT_SYMBOL_GPL(q6apm_map_memory_regions);
+EXPORT_SYMBOL_GPL(q6apm_alloc_fragments);
 
-int q6apm_unmap_memory_regions(struct q6apm_graph *graph, unsigned int dir)
+int q6apm_unmap_memory_fixed_region(struct device *dev, unsigned int graph_id)
 {
 	struct apm_cmd_shared_mem_unmap_regions *cmd;
-	struct audioreach_graph_data *data;
+	struct q6apm *apm = dev_get_drvdata(dev->parent);
-	int rc;
+	struct audioreach_graph_info *info;
-
+	struct gpr_pkt *pkt __free(kfree) = audioreach_alloc_apm_cmd_pkt(sizeof(*cmd),
-	if (dir == SNDRV_PCM_STREAM_PLAYBACK)
+						APM_CMD_SHARED_MEM_UNMAP_REGIONS, graph_id);
-		data = &graph->rx_data;
-	else
-		data = &graph->tx_data;
-
-	if (!data->mem_map_handle)
-		return 0;
-
-	struct gpr_pkt *pkt __free(kfree) =
-		audioreach_alloc_apm_pkt(sizeof(*cmd), APM_CMD_SHARED_MEM_UNMAP_REGIONS,
-					 dir, graph->port->id);
 	if (IS_ERR(pkt))
 		return PTR_ERR(pkt);
 
+	info = idr_find(&apm->graph_info_idr, graph_id);
+	if (!info)
+		return -ENODEV;
+
+	if (!info->mem_map_handle)
+		return 0;
+
 	cmd = (void *)pkt + GPR_HDR_SIZE;
-	cmd->mem_map_handle = data->mem_map_handle;
+	cmd->mem_map_handle = info->mem_map_handle;
 
-	rc = audioreach_graph_send_cmd_sync(graph, pkt, APM_CMD_SHARED_MEM_UNMAP_REGIONS);
+	return q6apm_send_cmd_sync(apm, pkt, APM_CMD_SHARED_MEM_UNMAP_REGIONS);
+}
+EXPORT_SYMBOL_GPL(q6apm_unmap_memory_fixed_region);
 
+int q6apm_free_fragments(struct q6apm_graph *graph, unsigned int dir)
+{
 	audioreach_graph_free_buf(graph);
 
-	return rc;
+	return 0;
 }
-EXPORT_SYMBOL_GPL(q6apm_unmap_memory_regions);
+EXPORT_SYMBOL_GPL(q6apm_free_fragments);
 
 int q6apm_remove_initial_silence(struct device *dev, struct q6apm_graph *graph, uint32_t samples)
 {
@@ -429,7 +464,7 @@ int q6apm_write_async(struct q6apm_graph *graph, uint32_t len, uint32_t msw_ts,
 	write_buffer->buf_size = len;
 	write_buffer->timestamp_lsw = lsw_ts;
 	write_buffer->timestamp_msw = msw_ts;
-	write_buffer->mem_map_handle = graph->rx_data.mem_map_handle;
+	write_buffer->mem_map_handle = graph->info->mem_map_handle;
 	write_buffer->flags = wflags;
 
 	graph->rx_data.dsp_buf++;
@@ -463,7 +498,7 @@ int q6apm_read(struct q6apm_graph *graph)
 
 	read_buffer->buf_addr_lsw = lower_32_bits(ab->phys);
 	read_buffer->buf_addr_msw = upper_32_bits(ab->phys);
-	read_buffer->mem_map_handle = port->mem_map_handle;
+	read_buffer->mem_map_handle = graph->info->mem_map_handle;
 	read_buffer->buf_size = ab->size;
 
 	port->dsp_buf++;
@@ -494,7 +529,6 @@ static int graph_callback(const struct gpr_resp_pkt *data, void *priv, int op)
 {
 	struct data_cmd_rsp_rd_sh_mem_ep_data_buffer_done_v2 *rd_done;
 	struct data_cmd_rsp_wr_sh_mem_ep_data_buffer_done_v2 *done;
-	struct apm_cmd_rsp_shared_mem_map_regions *rsp;
 	const struct gpr_ibasic_rsp_result_t *result;
 	struct q6apm_graph *graph = priv;
 	const struct gpr_hdr *hdr = &data->hdr;
@@ -529,18 +563,6 @@ static int graph_callback(const struct gpr_resp_pkt *data, void *priv, int op)
 				done->buf_addr_msw);
 		}
 
-		break;
-	case APM_CMD_RSP_SHARED_MEM_MAP_REGIONS:
-		graph->result.opcode = hdr->opcode;
-		graph->result.status = 0;
-		rsp = data->payload;
-
-		if (hdr->token == SNDRV_PCM_STREAM_PLAYBACK)
-			graph->rx_data.mem_map_handle = rsp->mem_map_handle;
-		else
-			graph->tx_data.mem_map_handle = rsp->mem_map_handle;
-
-		wake_up(&graph->cmd_wait);
 		break;
 	case DATA_CMD_RSP_RD_SH_MEM_EP_DATA_BUFFER_V2:
 		if (!graph->ar_graph)
@@ -571,16 +593,6 @@ static int graph_callback(const struct gpr_resp_pkt *data, void *priv, int op)
 		break;
 	case GPR_BASIC_RSP_RESULT:
 		switch (result->opcode) {
-		case APM_CMD_SHARED_MEM_UNMAP_REGIONS:
-			graph->result.opcode = result->opcode;
-			graph->result.status = 0;
-			if (hdr->token == SNDRV_PCM_STREAM_PLAYBACK)
-				graph->rx_data.mem_map_handle = 0;
-			else
-				graph->tx_data.mem_map_handle = 0;
-
-			wake_up(&graph->cmd_wait);
-			break;
 		case APM_CMD_SHARED_MEM_MAP_REGIONS:
 		case DATA_CMD_WR_SH_MEM_EP_MEDIA_FORMAT:
 		case APM_CMD_SET_CFG:
@@ -784,7 +796,9 @@ struct audioreach_module *q6apm_find_module_by_mid(struct q6apm_graph *graph, ui
 static int apm_callback(const struct gpr_resp_pkt *data, void *priv, int op)
 {
 	gpr_device_t *gdev = priv;
+	struct audioreach_graph_info *info;
 	struct q6apm *apm = dev_get_drvdata(&gdev->dev);
+	struct apm_cmd_rsp_shared_mem_map_regions *rsp;
 	struct device *dev = &gdev->dev;
 	struct gpr_ibasic_rsp_result_t *result;
 	const struct gpr_hdr *hdr = &data->hdr;
@@ -801,6 +815,7 @@ static int apm_callback(const struct gpr_resp_pkt *data, void *priv, int op)
 		break;
 	case GPR_BASIC_RSP_RESULT:
 		switch (result->opcode) {
+		case APM_CMD_SHARED_MEM_MAP_REGIONS:
 		case APM_CMD_GRAPH_START:
 		case APM_CMD_GRAPH_OPEN:
 		case APM_CMD_GRAPH_PREPARE:
@@ -815,10 +830,38 @@ static int apm_callback(const struct gpr_resp_pkt *data, void *priv, int op)
 					result->opcode);
 			wake_up(&apm->wait);
 			break;
+		case APM_CMD_SHARED_MEM_UNMAP_REGIONS:
+			apm->result.opcode = hdr->opcode;
+			apm->result.status = 0;
+			rsp = data->payload;
+
+			info = idr_find(&apm->graph_info_idr, hdr->token);
+			if (info)
+				info->mem_map_handle = 0;
+			else
+				dev_err(dev, "Error (%d) Processing 0x%08x cmd\n", result->status,
+					result->opcode);
+
+			wake_up(&apm->wait);
+			break;
 		default:
 			break;
 		}
 		break;
+	case APM_CMD_RSP_SHARED_MEM_MAP_REGIONS:
+		apm->result.opcode = hdr->opcode;
+		apm->result.status = 0;
+		rsp = data->payload;
+
+		info = idr_find(&apm->graph_info_idr, hdr->token);
+		if (info)
+			info->mem_map_handle = rsp->mem_map_handle;
+		else
+			dev_err(dev, "Error (%d) Processing 0x%08x cmd\n", result->status,
+				result->opcode);
+
+		wake_up(&apm->wait);
+		break;
 	default:
 		break;
 	}

sound/soc/qcom/qdsp6/q6apm.h

@@ -78,7 +78,6 @@ struct audioreach_graph_data {
 	struct audio_buffer *buf;
 	uint32_t num_periods;
 	uint32_t dsp_buf;
-	uint32_t mem_map_handle;
 	atomic_t hw_ptr;
 };
 
@@ -134,11 +133,14 @@ int q6apm_write_async(struct q6apm_graph *graph, uint32_t len, uint32_t msw_ts,
 		      uint32_t lsw_ts, uint32_t wflags);
 
 /* Memory Map related */
-int q6apm_map_memory_regions(struct q6apm_graph *graph,
+int q6apm_map_memory_fixed_region(struct device *dev,
-			     unsigned int dir, phys_addr_t phys,
+			     unsigned int graph_id, phys_addr_t phys,
-			     size_t period_sz, unsigned int periods);
+			     size_t sz);
-int q6apm_unmap_memory_regions(struct q6apm_graph *graph,
+int q6apm_alloc_fragments(struct q6apm_graph *graph,
-			       unsigned int dir);
+			unsigned int dir, phys_addr_t phys,
+			size_t period_sz, unsigned int periods);
+int q6apm_free_fragments(struct q6apm_graph *graph, unsigned int dir);
+int q6apm_unmap_memory_fixed_region(struct device *dev, unsigned int graph_id);
 /* Helpers */
 int q6apm_send_cmd_sync(struct q6apm *apm, struct gpr_pkt *pkt,
 			uint32_t rsp_opcode);