spi: ti-qspi: use 128 bit transfer mode where possible

TI QSPI has four 32 bit data regsiters which can be used to transfer 16
bytes of data at once. The register group QSPI_SPI_DATA_REG_3,
QSPI_SPI_DATA_REG_2, QSPI_SPI_DATA_REG_1 and QSPI_SPI_DATA_REG is
treated as a single 128-bit word for shifting data in and out. The bit
at QSPI_SPI_DATA_REG_3[31] position is the first bit to be shifted out
in case of 128 bit transfer mode. Therefore the first byte to be written
to flash should be at QSPI_SPI_DATA_REG_3[31-25] position.
Instead of writing 1 byte at a time when interacting with spi-nor flash,
make use of all the four registers so that 16 bytes can be transferred
in one go. This reduces number of register writes and Word Complete
interrupts for a given transfer message size, thereby increasing the
write performance.

Without this patch the raw flash write speed is ~100KB/s, with this
patch the write speed increases to ~400 kB/s on DRA74 EVM.

Signed-off-by: Vignesh R <vigneshr@ti.com>
Signed-off-by: Mark Brown <broonie@kernel.org>

1 files changed, 30 insertions, 4 deletions

diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c
index 5c0616870358..aa6d284131e0 100644
--- a/drivers/spi/spi-ti-qspi.c
+++ b/drivers/spi/spi-ti-qspi.c
@@ -99,6 +99,8 @@ struct ti_qspi {
 #define QSPI_INVAL			(4 << 16)
 #define QSPI_WC_CMD_INT_EN			(1 << 14)
 #define QSPI_FLEN(n)			((n - 1) << 0)
+#define QSPI_WLEN_MAX_BITS		128
+#define QSPI_WLEN_MAX_BYTES		16
 
 /* STATUS REGISTER */
 #define BUSY				0x01
@@ -217,14 +219,16 @@ static inline u32 qspi_is_busy(struct ti_qspi *qspi)
 
 static int qspi_write_msg(struct ti_qspi *qspi, struct spi_transfer *t)
 {
-	int wlen, count;
+	int wlen, count, xfer_len;
 	unsigned int cmd;
 	const u8 *txbuf;
+	u32 data;
 
 	txbuf = t->tx_buf;
 	cmd = qspi->cmd | QSPI_WR_SNGL;
 	count = t->len;
 	wlen = t->bits_per_word >> 3;	/* in bytes */
+	xfer_len = wlen;
 
 	while (count) {
 		if (qspi_is_busy(qspi))
@@ -234,7 +238,29 @@ static int qspi_write_msg(struct ti_qspi *qspi, struct spi_transfer *t)
 		case 1:
 			dev_dbg(qspi->dev, "tx cmd %08x dc %08x data %02x\n",
 					cmd, qspi->dc, *txbuf);
-			writeb(*txbuf, qspi->base + QSPI_SPI_DATA_REG);
+			if (count >= QSPI_WLEN_MAX_BYTES) {
+				u32 *txp = (u32 *)txbuf;
+
+				data = cpu_to_be32(*txp++);
+				writel(data, qspi->base +
+				       QSPI_SPI_DATA_REG_3);
+				data = cpu_to_be32(*txp++);
+				writel(data, qspi->base +
+				       QSPI_SPI_DATA_REG_2);
+				data = cpu_to_be32(*txp++);
+				writel(data, qspi->base +
+				       QSPI_SPI_DATA_REG_1);
+				data = cpu_to_be32(*txp++);
+				writel(data, qspi->base +
+				       QSPI_SPI_DATA_REG);
+				xfer_len = QSPI_WLEN_MAX_BYTES;
+				cmd |= QSPI_WLEN(QSPI_WLEN_MAX_BITS);
+			} else {
+				writeb(*txbuf, qspi->base + QSPI_SPI_DATA_REG);
+				cmd = qspi->cmd | QSPI_WR_SNGL;
+				xfer_len = wlen;
+				cmd |= QSPI_WLEN(wlen);
+			}
 			break;
 		case 2:
 			dev_dbg(qspi->dev, "tx cmd %08x dc %08x data %04x\n",
@@ -254,8 +280,8 @@ static int qspi_write_msg(struct ti_qspi *qspi, struct spi_transfer *t)
 			dev_err(qspi->dev, "write timed out\n");
 			return -ETIMEDOUT;
 		}
-		txbuf += wlen;
-		count -= wlen;
+		txbuf += xfer_len;
+		count -= xfer_len;
 	}
 
 	return 0;