spi: spi-fsl-dspi: Use EOQ for last word in buffer even for XSPI mode

The EOQ mode has a hardware limitation in that it stops the transmission
(including the deassertion of the chip select signal) once the host CPU
requests end-of-queue for a particular word in the TX FIFO.

And XSPI mode has a limitation in that we need a separate CMD FIFO entry
for the last byte in the buffer, where the chip select signal needs to
be deasserted. It's not a functional limitation, but it's rather clunky
and the fact that we need to halt the pipeline and write a single entry
to the TX FIFO whenever a buffer ends brings the throughput down when
transmitting small buffers.

So the idea here is to use EOQ's limitation in our favor when using XSPI
mode. Stop special-casing that final word in the buffer, and just kill
the chip select signal by issuing an EOQ for that last word. Now it can
be mixed in with all the other words in the current TX FIFO train.

A small trick here is that we still keep using the XSPI-specific
signaling via the CMDTCFQ interrupt in RSER, and not enabling the EOQ
interrupt, in order to avoid hardware weirdness (potential races with
separate interrupts being raised for CMDTCFQ and EOQ for what is in fact
the end of the same transmission). That is just theoretical, but it's
good to be cautious, and the EOQ interrupt isn't needed.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20200304220044.11193-12-olteanv@gmail.comSigned-off-by: Mark Brown <broonie@kernel.org>

drivers/spi/spi-fsl-dspi.c

@@ -656,10 +656,8 @@ static void dspi_pushr_write(struct fsl_dspi *dspi)
 	regmap_write(dspi->regmap, SPI_PUSHR, dspi_pop_tx_pushr(dspi));
 }
 
-static void dspi_pushr_cmd_write(struct fsl_dspi *dspi)
+static void dspi_pushr_cmd_write(struct fsl_dspi *dspi, u16 cmd)
 {
-	u16 cmd = dspi->tx_cmd;
-
 	/*
 	 * The only time when the PCS doesn't need continuation after this word
 	 * is when it's last. We need to look ahead, because we actually call
@@ -680,8 +678,13 @@ static void dspi_pushr_txdata_write(struct fsl_dspi *dspi, u16 txdata)
 	regmap_write(dspi->regmap_pushr, PUSHR_TX, txdata);
 }
 
-static void dspi_xspi_write(struct fsl_dspi *dspi, int cnt)
+static void dspi_xspi_write(struct fsl_dspi *dspi, int cnt, bool eoq)
 {
+	u16 tx_cmd = dspi->tx_cmd;
+
+	if (eoq)
+		tx_cmd |= SPI_PUSHR_CMD_EOQ;
+
 	/* Update CTARE */
 	regmap_write(dspi->regmap, SPI_CTARE(0),
 		     SPI_FRAME_EBITS(dspi->oper_bits_per_word) |
@@ -691,7 +694,7 @@ static void dspi_xspi_write(struct fsl_dspi *dspi, int cnt)
 	 * Write the CMD FIFO entry first, and then the two
 	 * corresponding TX FIFO entries (or one...).
 	 */
-	dspi_pushr_cmd_write(dspi);
+	dspi_pushr_cmd_write(dspi, tx_cmd);
 
 	/* Fill TX FIFO with as many transfers as possible */
 	while (cnt--) {
@@ -707,6 +710,7 @@ static void dspi_xspi_fifo_write(struct fsl_dspi *dspi)
 {
 	int num_fifo_entries = dspi->devtype_data->fifo_size;
 	int bytes_in_flight;
+	bool eoq = false;
 
 	/* In XSPI mode each 32-bit word occupies 2 TX FIFO entries */
 	if (dspi->oper_word_size == 4)
@@ -732,11 +736,11 @@ static void dspi_xspi_fifo_write(struct fsl_dspi *dspi)
 	 * So send one word less during this go, to force a split and a command
 	 * with a single word next time, when CONT will be unset.
 	 */
-	if (bytes_in_flight == dspi->len && dspi->words_in_flight > 1 &&
-	    !(dspi->tx_cmd & SPI_PUSHR_CMD_CONT))
-		dspi->words_in_flight--;
+	if (!(dspi->tx_cmd & SPI_PUSHR_CMD_CONT) &&
+	    bytes_in_flight == dspi->len)
+		eoq = true;
 
-	dspi_xspi_write(dspi, dspi->words_in_flight);
+	dspi_xspi_write(dspi, dspi->words_in_flight, eoq);
 }
 
 static void dspi_eoq_fifo_write(struct fsl_dspi *dspi)