spi: spi-fsl-spi: automatically adapt bits-per-word in cpu mode

Taking one interrupt for every byte is rather slow. Since the
controller is perfectly capable of transmitting 32 bits at a time,
change t->bits_per-word to 32 when the length is divisible by 4 and
large enough that the reduced number of interrupts easily compensates
for the one or two extra fsl_spi_setup_transfer() calls this causes.
Signed-off-by: Rasmus Villemoes <rasmus.villemoes@prevas.dk>
Signed-off-by: Mark Brown <broonie@kernel.org>

drivers/spi/spi-fsl-spi.c

@@ -363,12 +363,28 @@ static int fsl_spi_bufs(struct spi_device *spi, struct spi_transfer *t,
 static int fsl_spi_do_one_msg(struct spi_master *master,
 			      struct spi_message *m)
 {
+	struct mpc8xxx_spi *mpc8xxx_spi = spi_master_get_devdata(master);
 	struct spi_device *spi = m->spi;
 	struct spi_transfer *t, *first;
 	unsigned int cs_change;
 	const int nsecs = 50;
 	int status, last_bpw;
 
+	/*
+	 * In CPU mode, optimize large byte transfers to use larger
+	 * bits_per_word values to reduce number of interrupts taken.
+	 */
+	if (!(mpc8xxx_spi->flags & SPI_CPM_MODE)) {
+		list_for_each_entry(t, &m->transfers, transfer_list) {
+			if (t->len < 256 || t->bits_per_word != 8)
+				continue;
+			if ((t->len & 3) == 0)
+				t->bits_per_word = 32;
+			else if ((t->len & 1) == 0)
+				t->bits_per_word = 16;
+		}
+	}
+
 	/* Don't allow changes if CS is active */
 	cs_change = 1;
 	list_for_each_entry(t, &m->transfers, transfer_list) {