spi: spi-fsl-dspi: Use non-coherent memory for DMA

Using coherent memory here isn't functionally necessary, we're only
either sending data to the device or reading from it. This means
explicit synchronizations are only required around those points and the
change is fairly trivial.

This gives us around a 10% increase in throughput for large DMA
transfers and no loss for small transfers.

Suggested-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: James Clark <james.clark@linaro.org>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Message-ID: <20250902-james-nxp-spi-dma-v6-4-f7aa2c5e56e2@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>

Author: james-c-linaro

drivers/spi/spi-fsl-dspi.c

@@ -493,21 +493,33 @@ static u32 dspi_pop_tx_pushr(struct fsl_dspi *dspi)
 	return cmd << 16 | data;
 }
 
+static size_t dspi_dma_transfer_size(struct fsl_dspi *dspi)
+{
+	return dspi->words_in_flight * DMA_SLAVE_BUSWIDTH_4_BYTES;
+}
+
 static void dspi_tx_dma_callback(void *arg)
 {
 	struct fsl_dspi *dspi = arg;
 	struct fsl_dspi_dma *dma = dspi->dma;
+	struct device *dev = &dspi->pdev->dev;
 
+	dma_sync_single_for_cpu(dev, dma->tx_dma_phys,
+				dspi_dma_transfer_size(dspi), DMA_TO_DEVICE);
 	complete(&dma->cmd_tx_complete);
 }
 
 static void dspi_rx_dma_callback(void *arg)
 {
 	struct fsl_dspi *dspi = arg;
 	struct fsl_dspi_dma *dma = dspi->dma;
+	struct device *dev = &dspi->pdev->dev;
 	int i;
 
 	if (dspi->rx) {
+		dma_sync_single_for_cpu(dev, dma->rx_dma_phys,
+					dspi_dma_transfer_size(dspi),
+					DMA_FROM_DEVICE);
 		for (i = 0; i < dspi->words_in_flight; i++)
 			dspi_push_rx(dspi, dspi->dma->rx_dma_buf[i]);
 	}
@@ -517,6 +529,7 @@ static void dspi_rx_dma_callback(void *arg)
 
 static int dspi_next_xfer_dma_submit(struct fsl_dspi *dspi)
 {
+	size_t size = dspi_dma_transfer_size(dspi);
 	struct device *dev = &dspi->pdev->dev;
 	struct fsl_dspi_dma *dma = dspi->dma;
 	int time_left;
@@ -525,12 +538,12 @@ static int dspi_next_xfer_dma_submit(struct fsl_dspi *dspi)
 	for (i = 0; i < dspi->words_in_flight; i++)
 		dspi->dma->tx_dma_buf[i] = dspi_pop_tx_pushr(dspi);
 
+	dma_sync_single_for_device(dev, dma->tx_dma_phys, size, DMA_TO_DEVICE);
 	dma->tx_desc = dmaengine_prep_slave_single(dma->chan_tx,
-					dma->tx_dma_phys,
-					dspi->words_in_flight *
-					DMA_SLAVE_BUSWIDTH_4_BYTES,
-					DMA_MEM_TO_DEV,
-					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+						   dma->tx_dma_phys, size,
+						   DMA_MEM_TO_DEV,
+						   DMA_PREP_INTERRUPT |
+						   DMA_CTRL_ACK);
 	if (!dma->tx_desc) {
 		dev_err(dev, "Not able to get desc for DMA xfer\n");
 		return -EIO;
@@ -543,12 +556,13 @@ static int dspi_next_xfer_dma_submit(struct fsl_dspi *dspi)
 		return -EINVAL;
 	}
 
+	dma_sync_single_for_device(dev, dma->rx_dma_phys, size,
+				   DMA_FROM_DEVICE);
 	dma->rx_desc = dmaengine_prep_slave_single(dma->chan_rx,
-					dma->rx_dma_phys,
-					dspi->words_in_flight *
-					DMA_SLAVE_BUSWIDTH_4_BYTES,
-					DMA_DEV_TO_MEM,
-					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+						   dma->rx_dma_phys, size,
+						   DMA_DEV_TO_MEM,
+						   DMA_PREP_INTERRUPT |
+						   DMA_CTRL_ACK);
 	if (!dma->rx_desc) {
 		dev_err(dev, "Not able to get desc for DMA xfer\n");
 		return -EIO;
@@ -643,17 +657,17 @@ static int dspi_request_dma(struct fsl_dspi *dspi, phys_addr_t phy_addr)
 		goto err_tx_channel;
 	}
 
-	dma->tx_dma_buf = dma_alloc_coherent(dma->chan_tx->device->dev,
-					     dma_bufsize, &dma->tx_dma_phys,
-					     GFP_KERNEL);
+	dma->tx_dma_buf = dma_alloc_noncoherent(dma->chan_tx->device->dev,
+						dma_bufsize, &dma->tx_dma_phys,
+						DMA_TO_DEVICE, GFP_KERNEL);
 	if (!dma->tx_dma_buf) {
 		ret = -ENOMEM;
 		goto err_tx_dma_buf;
 	}
 
-	dma->rx_dma_buf = dma_alloc_coherent(dma->chan_rx->device->dev,
-					     dma_bufsize, &dma->rx_dma_phys,
-					     GFP_KERNEL);
+	dma->rx_dma_buf = dma_alloc_noncoherent(dma->chan_rx->device->dev,
+						dma_bufsize, &dma->rx_dma_phys,
+						DMA_FROM_DEVICE, GFP_KERNEL);
 	if (!dma->rx_dma_buf) {
 		ret = -ENOMEM;
 		goto err_rx_dma_buf;
@@ -688,11 +702,12 @@ static int dspi_request_dma(struct fsl_dspi *dspi, phys_addr_t phy_addr)
 	return 0;
 
 err_slave_config:
-	dma_free_coherent(dma->chan_rx->device->dev,
-			  dma_bufsize, dma->rx_dma_buf, dma->rx_dma_phys);
+	dma_free_noncoherent(dma->chan_rx->device->dev, dma_bufsize,
+			     dma->rx_dma_buf, dma->rx_dma_phys,
+			     DMA_FROM_DEVICE);
 err_rx_dma_buf:
-	dma_free_coherent(dma->chan_tx->device->dev,
-			  dma_bufsize, dma->tx_dma_buf, dma->tx_dma_phys);
+	dma_free_noncoherent(dma->chan_tx->device->dev, dma_bufsize,
+			     dma->tx_dma_buf, dma->tx_dma_phys, DMA_TO_DEVICE);
 err_tx_dma_buf:
 	dma_release_channel(dma->chan_tx);
 err_tx_channel:
@@ -713,14 +728,16 @@ static void dspi_release_dma(struct fsl_dspi *dspi)
 		return;
 
 	if (dma->chan_tx) {
-		dma_free_coherent(dma->chan_tx->device->dev, dma_bufsize,
-				  dma->tx_dma_buf, dma->tx_dma_phys);
+		dma_free_noncoherent(dma->chan_tx->device->dev, dma_bufsize,
+				     dma->tx_dma_buf, dma->tx_dma_phys,
+				     DMA_TO_DEVICE);
 		dma_release_channel(dma->chan_tx);
 	}
 
 	if (dma->chan_rx) {
-		dma_free_coherent(dma->chan_rx->device->dev, dma_bufsize,
-				  dma->rx_dma_buf, dma->rx_dma_phys);
+		dma_free_noncoherent(dma->chan_rx->device->dev, dma_bufsize,
+				     dma->rx_dma_buf, dma->rx_dma_phys,
+				     DMA_FROM_DEVICE);
 		dma_release_channel(dma->chan_rx);
 	}
 }