[PATCH v1 1/1] spi: spi-geni-qcom: Add immediate DMA support

[Jyothi Kumar Seerapu <quic_jseerapu@xxxxxxxxxxx>]

The DMA TRE(Transfer ring element) buffer contains the DMA
buffer address. Accessing data from this address can cause
significant delays in SPI transfers, which can be mitigated to
some extent by utilizing immediate DMA support.

QCOM GPI DMA hardware supports an immediate DMA feature for data
up to 8 bytes, storing the data directly in the DMA TRE buffer
instead of the DMA buffer address. This enhancement enables faster
SPI data transfers.

This optimization reduces the average transfer time from 25 us to
16 us for a single SPI transfer of 8 bytes length, with a clock
frequency of 50 MHz.

Signed-off-by: Jyothi Kumar Seerapu <quic_jseerapu@xxxxxxxxxxx>
---
 drivers/dma/qcom/gpi.c           | 32 +++++++++++++++++++++++++++-----
 drivers/spi/spi-geni-qcom.c      |  7 +++++++
 include/linux/dma/qcom-gpi-dma.h |  7 +++++++
 3 files changed, 41 insertions(+), 5 deletions(-)

diff --git a/drivers/dma/qcom/gpi.c b/drivers/dma/qcom/gpi.c
index 52a7c8f2498f..a8df1e835e27 100644
--- a/drivers/dma/qcom/gpi.c
+++ b/drivers/dma/qcom/gpi.c
@@ -27,6 +27,7 @@
 #define TRE_FLAGS_IEOT		BIT(9)
 #define TRE_FLAGS_BEI		BIT(10)
 #define TRE_FLAGS_LINK		BIT(11)
+#define TRE_FLAGS_IMMEDIATE_DMA	BIT(16)
 #define TRE_FLAGS_TYPE		GENMASK(23, 16)
 
 /* SPI CONFIG0 WD0 */
@@ -64,6 +65,7 @@
 
 /* DMA TRE */
 #define TRE_DMA_LEN		GENMASK(23, 0)
+#define TRE_DMA_IMMEDIATE_LEN	GENMASK(3, 0)
 
 /* Register offsets from gpi-top */
 #define GPII_n_CH_k_CNTXT_0_OFFS(n, k)	(0x20000 + (0x4000 * (n)) + (0x80 * (k)))
@@ -1711,6 +1713,8 @@ static int gpi_create_spi_tre(struct gchan *chan, struct gpi_desc *desc,
 	dma_addr_t address;
 	struct gpi_tre *tre;
 	unsigned int i;
+	u8 *buf;
+	int len = 0;
 
 	/* first create config tre if applicable */
 	if (direction == DMA_MEM_TO_DEV && spi->set_config) {
@@ -1763,14 +1767,32 @@ static int gpi_create_spi_tre(struct gchan *chan, struct gpi_desc *desc,
 	tre_idx++;
 
 	address = sg_dma_address(sgl);
-	tre->dword[0] = lower_32_bits(address);
-	tre->dword[1] = upper_32_bits(address);
+	len = sg_dma_len(sgl);
 
-	tre->dword[2] = u32_encode_bits(sg_dma_len(sgl), TRE_DMA_LEN);
+	/* Support Immediate dma for write transfers for data length up to 8 bytes */
+	if ((spi->flags & QCOM_GPI_IMMEDIATE_DMA) && direction == DMA_MEM_TO_DEV) {
+		buf = (u8 *)sg_virt(sgl);
 
-	tre->dword[3] = u32_encode_bits(TRE_TYPE_DMA, TRE_FLAGS_TYPE);
-	if (direction == DMA_MEM_TO_DEV)
+		/* memcpy may not always be length of 8, hence pre-fill both dword's with 0 */
+		tre->dword[0] = 0;
+		tre->dword[1] = 0;
+		memcpy((u8 *)&tre->dword[0], buf, len);
+
+		tre->dword[2] = u32_encode_bits(len, TRE_DMA_IMMEDIATE_LEN);
+
+		tre->dword[3] = u32_encode_bits(TRE_TYPE_DMA, TRE_FLAGS_TYPE);
 		tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_IEOT);
+		tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_IMMEDIATE_DMA);
+	} else {
+		tre->dword[0] = lower_32_bits(address);
+		tre->dword[1] = upper_32_bits(address);
+
+		tre->dword[2] = u32_encode_bits(len, TRE_DMA_LEN);
+
+		tre->dword[3] = u32_encode_bits(TRE_TYPE_DMA, TRE_FLAGS_TYPE);
+		if (direction == DMA_MEM_TO_DEV)
+			tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_IEOT);
+	}
 
 	for (i = 0; i < tre_idx; i++)
 		dev_dbg(dev, "TRE:%d %x:%x:%x:%x\n", i, desc->tre[i].dword[0],
diff --git a/drivers/spi/spi-geni-qcom.c b/drivers/spi/spi-geni-qcom.c
index 768d7482102a..53c8f6b7f3c5 100644
--- a/drivers/spi/spi-geni-qcom.c
+++ b/drivers/spi/spi-geni-qcom.c
@@ -472,11 +472,18 @@ static int setup_gsi_xfer(struct spi_transfer *xfer, struct spi_geni_master *mas
 		mas->cur_speed_hz = xfer->speed_hz;
 	}
 
+	/*
+	 * Set QCOM_GPI_IMMEDIATE_DMA flag if transfer length up to 8 bytes.
+	 */
 	if (xfer->tx_buf && xfer->rx_buf) {
 		peripheral.cmd = SPI_DUPLEX;
+		if (xfer->len <= QCOM_GPI_IMMEDIATE_DMA_LEN)
+			peripheral.flags |= QCOM_GPI_IMMEDIATE_DMA;
 	} else if (xfer->tx_buf) {
 		peripheral.cmd = SPI_TX;
 		peripheral.rx_len = 0;
+		if (xfer->len <= QCOM_GPI_IMMEDIATE_DMA_LEN)
+			peripheral.flags |= QCOM_GPI_IMMEDIATE_DMA;
 	} else if (xfer->rx_buf) {
 		peripheral.cmd = SPI_RX;
 		if (!(mas->cur_bits_per_word % MIN_WORD_LEN)) {
diff --git a/include/linux/dma/qcom-gpi-dma.h b/include/linux/dma/qcom-gpi-dma.h
index 6680dd1a43c6..0eb96e62a1f1 100644
--- a/include/linux/dma/qcom-gpi-dma.h
+++ b/include/linux/dma/qcom-gpi-dma.h
@@ -15,6 +15,11 @@ enum spi_transfer_cmd {
 	SPI_DUPLEX,
 };
 
+#define QCOM_GPI_BLOCK_EVENT_IRQ	BIT(0)
+#define QCOM_GPI_IMMEDIATE_DMA		BIT(1)
+
+#define QCOM_GPI_IMMEDIATE_DMA_LEN	8
+
 /**
  * struct gpi_spi_config - spi config for peripheral
  *
@@ -30,6 +35,7 @@ enum spi_transfer_cmd {
  * @cs: chip select toggle
  * @set_config: set peripheral config
  * @rx_len: receive length for buffer
+ * @flags: flags for immediate dma and block event interrupt support
  */
 struct gpi_spi_config {
 	u8 set_config;
@@ -44,6 +50,7 @@ struct gpi_spi_config {
 	u32 clk_src;
 	enum spi_transfer_cmd cmd;
 	u32 rx_len;
+	u8 flags;
 };
 
 enum i2c_op {
-- 
2.17.1