Message-ID: <20250103060407.1064107-7-va@nvidia.com>
Date: Fri, 3 Jan 2025 06:04:07 +0000
From: Vishwaroop A <va@...dia.com>
To: <thierry.reding@...il.com>, <jonathanh@...dia.com>,
	<skomatineni@...dia.com>, <ldewangan@...dia.com>, <broonie@...nel.org>,
	<linux-spi@...r.kernel.org>, <linux-tegra@...r.kernel.org>,
	<linux-kernel@...r.kernel.org>, <kyarlagadda@...dia.com>,
	<smangipudi@...dia.com>
CC: <va@...dia.com>
Subject: [PATCH V1 6/6] spi: tegra210-quad: Introduce native DMA support

Previous generations of Tegra supported DMA operations by an external
DMA controller, but the QSPI on Tegra234 devices now have an internal
DMA controller.

Internal DMA: Uses the QSPI controller's built-in DMA engine, which is
limited in capabilities and tied directly to the QSPI module.

External DMA: Utilizes a separate, GPCDMA DMA controller that can
transfer data between QSPI and any memory location.

Native DMA Initialization: Introduce routines to initialize and
configure native DMA channels for both transmit and receive paths.
Set up DMA mapping functions to manage buffer addresses effectively.

Enhance Transfer Logic: Implement logic to choose between CPU-based
and DMA-based transfers based on data size.

Change-Id: Icf3ef4767947cef67821c092ecd9ea6bccb2a4e4
Signed-off-by: Vishwaroop A <va@...dia.com>
---
 drivers/spi/spi-tegra210-quad.c | 218 ++++++++++++++++++--------------
 1 file changed, 126 insertions(+), 92 deletions(-)

diff --git a/drivers/spi/spi-tegra210-quad.c b/drivers/spi/spi-tegra210-quad.c
index 04f41e92c1e2..066caee85c52 100644
--- a/drivers/spi/spi-tegra210-quad.c
+++ b/drivers/spi/spi-tegra210-quad.c
@@ -111,6 +111,9 @@
 #define QSPI_DMA_BLK				0x024
 #define QSPI_DMA_BLK_SET(x)			(((x) & 0xffff) << 0)
 
+#define QSPI_DMA_MEM_ADDRESS_REG		0x028
+#define QSPI_DMA_HI_ADDRESS_REG			0x02c
+
 #define QSPI_TX_FIFO				0x108
 #define QSPI_RX_FIFO				0x188
 
@@ -167,9 +170,9 @@ enum tegra_qspi_transfer_type {
 };
 
 struct tegra_qspi_soc_data {
-	bool has_dma;
 	bool cmb_xfer_capable;
 	bool supports_tpm;
+	bool has_ext_dma;
 	unsigned int cs_count;
 };
 
@@ -605,17 +608,21 @@ static void tegra_qspi_dma_unmap_xfer(struct tegra_qspi *tqspi, struct spi_trans
 
 	len = DIV_ROUND_UP(tqspi->curr_dma_words * tqspi->bytes_per_word, 4) * 4;
 
-	dma_unmap_single(tqspi->dev, t->tx_dma, len, DMA_TO_DEVICE);
-	dma_unmap_single(tqspi->dev, t->rx_dma, len, DMA_FROM_DEVICE);
+	if (t->tx_buf)
+		dma_unmap_single(tqspi->dev, t->tx_dma, len, DMA_TO_DEVICE);
+	if (t->rx_buf)
+		dma_unmap_single(tqspi->dev, t->rx_dma, len, DMA_FROM_DEVICE);
 }
 
 static int tegra_qspi_start_dma_based_transfer(struct tegra_qspi *tqspi, struct spi_transfer *t)
 {
 	struct dma_slave_config dma_sconfig = { 0 };
+	dma_addr_t rx_dma_phys, tx_dma_phys;
 	unsigned int len;
 	u8 dma_burst;
 	int ret = 0;
 	u32 val;
+	bool has_ext_dma = tqspi->soc_data->has_ext_dma;
 
 	if (tqspi->is_packed) {
 		ret = tegra_qspi_dma_map_xfer(tqspi, t);
@@ -634,60 +641,85 @@ static int tegra_qspi_start_dma_based_transfer(struct tegra_qspi *tqspi, struct
 		len = tqspi->curr_dma_words * 4;
 
 	/* set attention level based on length of transfer */
-	val = 0;
-	if (len & 0xf) {
-		val |= QSPI_TX_TRIG_1 | QSPI_RX_TRIG_1;
-		dma_burst = 1;
-	} else if (((len) >> 4) & 0x1) {
-		val |= QSPI_TX_TRIG_4 | QSPI_RX_TRIG_4;
-		dma_burst = 4;
-	} else {
-		val |= QSPI_TX_TRIG_8 | QSPI_RX_TRIG_8;
-		dma_burst = 8;
+	if (has_ext_dma) {
+		val = 0;
+		if (len & 0xf) {
+			val |= QSPI_TX_TRIG_1 | QSPI_RX_TRIG_1;
+			dma_burst = 1;
+		} else if (((len) >> 4) & 0x1) {
+			val |= QSPI_TX_TRIG_4 | QSPI_RX_TRIG_4;
+			dma_burst = 4;
+		} else {
+			val |= QSPI_TX_TRIG_8 | QSPI_RX_TRIG_8;
+			dma_burst = 8;
+		}
+
+		tegra_qspi_writel(tqspi, val, QSPI_DMA_CTL);
 	}
 
-	tegra_qspi_writel(tqspi, val, QSPI_DMA_CTL);
 	tqspi->dma_control_reg = val;
 
 	dma_sconfig.device_fc = true;
-	if (tqspi->cur_direction & DATA_DIR_TX) {
-		dma_sconfig.dst_addr = tqspi->phys + QSPI_TX_FIFO;
-		dma_sconfig.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
-		dma_sconfig.dst_maxburst = dma_burst;
-		ret = dmaengine_slave_config(tqspi->tx_dma_chan, &dma_sconfig);
-		if (ret < 0) {
-			dev_err(tqspi->dev, "failed DMA slave config: %d\n", ret);
-			return ret;
-		}
 
-		tegra_qspi_copy_client_txbuf_to_qspi_txbuf(tqspi, t);
-		ret = tegra_qspi_start_tx_dma(tqspi, t, len);
-		if (ret < 0) {
-			dev_err(tqspi->dev, "failed to starting TX DMA: %d\n", ret);
-			return ret;
+	if ((tqspi->cur_direction & DATA_DIR_TX)) {
+		if (has_ext_dma) {
+			dma_sconfig.dst_addr = tqspi->phys + QSPI_TX_FIFO;
+			dma_sconfig.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+			dma_sconfig.dst_maxburst = dma_burst;
+			ret = dmaengine_slave_config(tqspi->tx_dma_chan, &dma_sconfig);
+			if (ret < 0) {
+				dev_err(tqspi->dev, "failed DMA slave config: %d\n", ret);
+				return ret;
+			}
+
+			tegra_qspi_copy_client_txbuf_to_qspi_txbuf(tqspi, t);
+			ret = tegra_qspi_start_tx_dma(tqspi, t, len);
+			if (ret < 0) {
+				dev_err(tqspi->dev, "failed to starting TX DMA: %d\n", ret);
+				return ret;
+			}
+		} else {
+			if (tqspi->is_packed)
+				tx_dma_phys = t->tx_dma;
+			else
+				tx_dma_phys = tqspi->tx_dma_phys;
+			tegra_qspi_copy_client_txbuf_to_qspi_txbuf(tqspi, t);
+			tegra_qspi_writel(tqspi, lower_32_bits(tx_dma_phys),
+					  QSPI_DMA_MEM_ADDRESS_REG);
+			tegra_qspi_writel(tqspi, (upper_32_bits(tx_dma_phys) & 0xff),
+					  QSPI_DMA_HI_ADDRESS_REG);
 		}
 	}
 
 	if (tqspi->cur_direction & DATA_DIR_RX) {
-		dma_sconfig.src_addr = tqspi->phys + QSPI_RX_FIFO;
-		dma_sconfig.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
-		dma_sconfig.src_maxburst = dma_burst;
-		ret = dmaengine_slave_config(tqspi->rx_dma_chan, &dma_sconfig);
-		if (ret < 0) {
-			dev_err(tqspi->dev, "failed DMA slave config: %d\n", ret);
-			return ret;
-		}
-
-		dma_sync_single_for_device(tqspi->dev, tqspi->rx_dma_phys,
-					   tqspi->dma_buf_size,
-					   DMA_FROM_DEVICE);
-
-		ret = tegra_qspi_start_rx_dma(tqspi, t, len);
-		if (ret < 0) {
-			dev_err(tqspi->dev, "failed to start RX DMA: %d\n", ret);
-			if (tqspi->cur_direction & DATA_DIR_TX)
-				dmaengine_terminate_all(tqspi->tx_dma_chan);
-			return ret;
+		if (has_ext_dma) {
+			dma_sconfig.src_addr = tqspi->phys + QSPI_RX_FIFO;
+			dma_sconfig.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+			dma_sconfig.src_maxburst = dma_burst;
+			ret = dmaengine_slave_config(tqspi->rx_dma_chan, &dma_sconfig);
+			if (ret < 0) {
+				dev_err(tqspi->dev, "failed DMA slave config: %d\n", ret);
+				return ret;
+			}
+			dma_sync_single_for_device(tqspi->dev, tqspi->rx_dma_phys,
+						   tqspi->dma_buf_size, DMA_FROM_DEVICE);
+			ret = tegra_qspi_start_rx_dma(tqspi, t, len);
+			if (ret < 0) {
+				dev_err(tqspi->dev, "failed to start RX DMA: %d\n", ret);
+				if (tqspi->cur_direction & DATA_DIR_TX)
+					dmaengine_terminate_all(tqspi->tx_dma_chan);
+				return ret;
+			}
+		} else {
+			if (tqspi->is_packed)
+				rx_dma_phys = t->rx_dma;
+			else
+				rx_dma_phys = tqspi->rx_dma_phys;
+
+			tegra_qspi_writel(tqspi, (rx_dma_phys & 0xffffffff),
+					  QSPI_DMA_MEM_ADDRESS_REG);
+			tegra_qspi_writel(tqspi, ((rx_dma_phys >> 32) & 0xff),
+					  QSPI_DMA_HI_ADDRESS_REG);
 		}
 	}
 
@@ -726,9 +758,6 @@ static int tegra_qspi_start_cpu_based_transfer(struct tegra_qspi *qspi, struct s
 
 static void tegra_qspi_deinit_dma(struct tegra_qspi *tqspi)
 {
-	if (!tqspi->soc_data->has_dma)
-		return;
-
 	if (tqspi->tx_dma_buf) {
 		dma_free_coherent(tqspi->dev, tqspi->dma_buf_size,
 				  tqspi->tx_dma_buf, tqspi->tx_dma_phys);
@@ -759,16 +788,26 @@ static int tegra_qspi_init_dma(struct tegra_qspi *tqspi)
 	u32 *dma_buf;
 	int err;
 
-	if (!tqspi->soc_data->has_dma)
-		return 0;
+	if (tqspi->soc_data->has_ext_dma) {
+		dma_chan = dma_request_chan(tqspi->dev, "rx");
+		if (IS_ERR(dma_chan)) {
+			err = PTR_ERR(dma_chan);
+			goto err_out;
+		}
 
-	dma_chan = dma_request_chan(tqspi->dev, "rx");
-	if (IS_ERR(dma_chan)) {
-		err = PTR_ERR(dma_chan);
-		goto err_out;
-	}
+		tqspi->rx_dma_chan = dma_chan;
 
-	tqspi->rx_dma_chan = dma_chan;
+		dma_chan = dma_request_chan(tqspi->dev, "tx");
+		if (IS_ERR(dma_chan)) {
+			err = PTR_ERR(dma_chan);
+			goto err_out;
+		}
+
+		tqspi->tx_dma_chan = dma_chan;
+	} else {
+		tqspi->rx_dma_chan = NULL;
+		tqspi->tx_dma_chan = NULL;
+	}
 
 	dma_buf = dma_alloc_coherent(tqspi->dev, tqspi->dma_buf_size, &dma_phys, GFP_KERNEL);
 	if (!dma_buf) {
@@ -779,14 +818,6 @@ static int tegra_qspi_init_dma(struct tegra_qspi *tqspi)
 	tqspi->rx_dma_buf = dma_buf;
 	tqspi->rx_dma_phys = dma_phys;
 
-	dma_chan = dma_request_chan(tqspi->dev, "tx");
-	if (IS_ERR(dma_chan)) {
-		err = PTR_ERR(dma_chan);
-		goto err_out;
-	}
-
-	tqspi->tx_dma_chan = dma_chan;
-
 	dma_buf = dma_alloc_coherent(tqspi->dev, tqspi->dma_buf_size, &dma_phys, GFP_KERNEL);
 	if (!dma_buf) {
 		err = -ENOMEM;
@@ -1056,6 +1087,7 @@ static int tegra_qspi_combined_seq_xfer(struct tegra_qspi *tqspi,
 					struct spi_message *msg)
 {
 	bool is_first_msg = true;
+	bool has_ext_dma = tqspi->soc_data->has_ext_dma;
 	struct spi_transfer *xfer;
 	struct spi_device *spi = msg->spi;
 	u8 transfer_phase = 0;
@@ -1128,15 +1160,12 @@ static int tegra_qspi_combined_seq_xfer(struct tegra_qspi *tqspi,
 			if (WARN_ON(ret == 0)) {
 				dev_err(tqspi->dev, "QSPI Transfer failed with timeout: %d\n",
 					ret);
-				if (tqspi->is_curr_dma_xfer &&
-				    (tqspi->cur_direction & DATA_DIR_TX))
-					dmaengine_terminate_all
-						(tqspi->tx_dma_chan);
-
-				if (tqspi->is_curr_dma_xfer &&
-				    (tqspi->cur_direction & DATA_DIR_RX))
-					dmaengine_terminate_all
-						(tqspi->rx_dma_chan);
+				if (tqspi->is_curr_dma_xfer && has_ext_dma) {
+					if (tqspi->cur_direction & DATA_DIR_TX)
+						dmaengine_terminate_all(tqspi->tx_dma_chan);
+					if (tqspi->cur_direction & DATA_DIR_RX)
+						dmaengine_terminate_all(tqspi->rx_dma_chan);
+				}
 
 				/* Abort transfer by resetting pio/dma bit */
 				if (!tqspi->is_curr_dma_xfer) {
@@ -1197,6 +1226,7 @@ static int tegra_qspi_non_combined_seq_xfer(struct tegra_qspi *tqspi,
 	struct spi_device *spi = msg->spi;
 	struct spi_transfer *transfer;
 	bool is_first_msg = true;
+	bool has_ext_dma = tqspi->soc_data->has_ext_dma;
 	int ret = 0, val = 0;
 
 	msg->status = 0;
@@ -1251,10 +1281,12 @@ static int tegra_qspi_non_combined_seq_xfer(struct tegra_qspi *tqspi,
 						  QSPI_DMA_TIMEOUT);
 		if (WARN_ON(ret == 0)) {
 			dev_err(tqspi->dev, "transfer timeout\n");
-			if (tqspi->is_curr_dma_xfer && (tqspi->cur_direction & DATA_DIR_TX))
-				dmaengine_terminate_all(tqspi->tx_dma_chan);
-			if (tqspi->is_curr_dma_xfer && (tqspi->cur_direction & DATA_DIR_RX))
-				dmaengine_terminate_all(tqspi->rx_dma_chan);
+			if (tqspi->is_curr_dma_xfer && has_ext_dma) {
+				if (tqspi->cur_direction & DATA_DIR_TX)
+					dmaengine_terminate_all(tqspi->tx_dma_chan);
+				if (tqspi->cur_direction & DATA_DIR_RX)
+					dmaengine_terminate_all(tqspi->rx_dma_chan);
+			}
 			tegra_qspi_handle_error(tqspi);
 			ret = -EIO;
 			goto complete_xfer;
@@ -1323,7 +1355,7 @@ static bool tegra_qspi_validate_cmb_seq(struct tegra_qspi *tqspi,
 			return false;
 		xfer = list_next_entry(xfer, transfer_list);
 	}
-	if (!tqspi->soc_data->has_dma && xfer->len > (QSPI_FIFO_DEPTH << 2))
+	if (!tqspi->soc_data->has_ext_dma && xfer->len > (QSPI_FIFO_DEPTH << 2))
 		return false;
 
 	return true;
@@ -1388,30 +1420,32 @@ static irqreturn_t handle_dma_based_xfer(struct tegra_qspi *tqspi)
 
 	if (tqspi->cur_direction & DATA_DIR_TX) {
 		if (tqspi->tx_status) {
-			dmaengine_terminate_all(tqspi->tx_dma_chan);
-			err += 1;
-		} else {
+			if (tqspi->tx_dma_chan)
+				dmaengine_terminate_all(tqspi->tx_dma_chan);
+			err++;
+		} else if (tqspi->tx_dma_chan) {
 			wait_status = wait_for_completion_interruptible_timeout(
 				&tqspi->tx_dma_complete, QSPI_DMA_TIMEOUT);
 			if (wait_status <= 0) {
 				dmaengine_terminate_all(tqspi->tx_dma_chan);
 				dev_err(tqspi->dev, "failed TX DMA transfer\n");
-				err += 1;
+				err++;
 			}
 		}
 	}
 
 	if (tqspi->cur_direction & DATA_DIR_RX) {
 		if (tqspi->rx_status) {
-			dmaengine_terminate_all(tqspi->rx_dma_chan);
-			err += 2;
-		} else {
+			if (tqspi->rx_dma_chan)
+				dmaengine_terminate_all(tqspi->rx_dma_chan);
+			err++;
+		} else if (tqspi->rx_dma_chan) {
 			wait_status = wait_for_completion_interruptible_timeout(
 				&tqspi->rx_dma_complete, QSPI_DMA_TIMEOUT);
 			if (wait_status <= 0) {
 				dmaengine_terminate_all(tqspi->rx_dma_chan);
 				dev_err(tqspi->dev, "failed RX DMA transfer\n");
-				err += 2;
+				err++;
 			}
 		}
 	}
@@ -1474,28 +1508,28 @@ static irqreturn_t tegra_qspi_isr_thread(int irq, void *context_data)
 }
 
 static struct tegra_qspi_soc_data tegra210_qspi_soc_data = {
-	.has_dma = true,
+	.has_ext_dma = true,
 	.cmb_xfer_capable = false,
 	.supports_tpm = false,
 	.cs_count = 1,
 };
 
 static struct tegra_qspi_soc_data tegra186_qspi_soc_data = {
-	.has_dma = true,
+	.has_ext_dma = true,
 	.cmb_xfer_capable = true,
 	.supports_tpm = false,
 	.cs_count = 1,
 };
 
 static struct tegra_qspi_soc_data tegra234_qspi_soc_data = {
-	.has_dma = false,
+	.has_ext_dma = false,
 	.cmb_xfer_capable = true,
 	.supports_tpm = true,
 	.cs_count = 1,
 };
 
 static struct tegra_qspi_soc_data tegra241_qspi_soc_data = {
-	.has_dma = false,
+	.has_ext_dma = true,
 	.cmb_xfer_capable = true,
 	.supports_tpm = true,
 	.cs_count = 4,
-- 
2.17.1

Powered by blists - more mailing lists