spi: spi-fsl-dspi: Optimize dspi_setup_accel for lowest interrupt count

Currently, a SPI transfer that is not multiple of the highest supported
word width (e.g. 4 bytes) will be transmitted as follows (assume a
30-byte buffer transmitted through a 32-bit wide FIFO that is 32 bytes
deep):

 - First 28 bytes are sent as 7 words of 32 bits each
 - Last 2 bytes are sent as 1 word of 16 bits size

But if the dspi_setup_accel function had decided to use a lower
oper_bits_per_word value (16 instead of 32), there would have been
enough space in the TX FIFO to fit the entire buffer in one go (15 words
of 16 bits each).

What we're actually trying to avoid is mixing word sizes within the same
run with the TX FIFO, since there is an erratum surrounding this, and
invalid data might get transmitted.

So this patch adds special cases for when the remaining length of the
buffer can be sent in one go as 8-bit or 16-bit words, otherwise it
falls back to the standard logic of sending as many bytes as possible at
the highest oper_bits_per_word value possible.

The benefit is that there will be one less CMDFQ/EOQ interrupt to
service when the entire buffer is transmitted during a single go, and
that will improve the overall latency of the transfer.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20200304220044.11193-11-olteanv@gmail.comSigned-off-by: Mark Brown <broonie@kernel.org>

drivers/spi/spi-fsl-dspi.c

@@ -775,20 +775,34 @@ static void dspi_fifo_read(struct fsl_dspi *dspi)
 static void dspi_setup_accel(struct fsl_dspi *dspi)
 {
 	struct spi_transfer *xfer = dspi->cur_transfer;
+	bool odd = !!(dspi->len & 1);
 
-	/* Start off with maximum supported by hardware */
-	if (dspi->devtype_data->trans_mode == DSPI_XSPI_MODE)
-		dspi->oper_bits_per_word = 32;
-	else
+	/* No accel for frames not multiple of 8 bits at the moment */
+	if (xfer->bits_per_word % 8)
+		goto no_accel;
+
+	if (!odd && dspi->len <= dspi->devtype_data->fifo_size * 2) {
 		dspi->oper_bits_per_word = 16;
+	} else if (odd && dspi->len <= dspi->devtype_data->fifo_size) {
+		dspi->oper_bits_per_word = 8;
+	} else {
+		/* Start off with maximum supported by hardware */
+		if (dspi->devtype_data->trans_mode == DSPI_XSPI_MODE)
+			dspi->oper_bits_per_word = 32;
+		else
+			dspi->oper_bits_per_word = 16;
 
-	/* And go down only if the buffer can't be sent with words this big */
-	do {
-		if (dspi->len >= DIV_ROUND_UP(dspi->oper_bits_per_word, 8))
-			break;
+		/*
+		 * And go down only if the buffer can't be sent with
+		 * words this big
+		 */
+		do {
+			if (dspi->len >= DIV_ROUND_UP(dspi->oper_bits_per_word, 8))
+				break;
 
-		dspi->oper_bits_per_word /= 2;
-	} while (dspi->oper_bits_per_word > 8);
+			dspi->oper_bits_per_word /= 2;
+		} while (dspi->oper_bits_per_word > 8);
+	}
 
 	if (xfer->bits_per_word == 8 && dspi->oper_bits_per_word == 32) {
 		dspi->dev_to_host = dspi_8on32_dev_to_host;
@@ -800,7 +814,7 @@ static void dspi_setup_accel(struct fsl_dspi *dspi)
 		dspi->dev_to_host = dspi_16on32_dev_to_host;
 		dspi->host_to_dev = dspi_16on32_host_to_dev;
 	} else {
-		/* No acceleration needed (8<N<=16 on 16, 16<N<=32 on 32) */
+no_accel:
 		dspi->dev_to_host = dspi_native_dev_to_host;
 		dspi->host_to_dev = dspi_native_host_to_dev;
 		dspi->oper_bits_per_word = xfer->bits_per_word;