spi: bcm2835: Cache CS register value for ->prepare_message()

The BCM2835 SPI driver needs to set up the clock polarity in its
->prepare_message() hook before spi_transfer_one_message() asserts chip
select to avoid a gratuitous clock signal edge (cf. commit acace73
("spi: bcm2835: set up spi-mode before asserting cs-gpio")).

Precalculate the CS register value (which selects the clock polarity)
once in ->setup() and use that cached value in ->prepare_message() and
->transfer_one().  This avoids one MMIO read per message and one per
transfer, yielding a small latency improvement.  Additionally, a
forthcoming commit will use the precalculated value to derive the
register value for clearing the RX FIFO, which will eliminate the need
for an RX dummy buffer when performing TX-only DMA transfers.

Signed-off-by: Lukas Wunner <[email protected]>
Cc: Martin Sperl <[email protected]>
Cc: Noralf Trønnes <[email protected]>

drivers/spi/spi-bcm2835.c

@@ -75,6 +75,7 @@
 #define BCM2835_SPI_FIFO_SIZE		64
 #define BCM2835_SPI_FIFO_SIZE_3_4	48
 #define BCM2835_SPI_DMA_MIN_LENGTH	96
+#define BCM2835_SPI_NUM_CS		3   /* raise as necessary */
 #define BCM2835_SPI_MODE_BITS	(SPI_CPOL | SPI_CPHA | SPI_CS_HIGH \
 				| SPI_NO_CS | SPI_3WIRE)
 
@@ -101,6 +102,8 @@ MODULE_PARM_DESC(polling_limit_us,
  * @rx_prologue: bytes received without DMA if first RX sglist entry's
  *	length is not a multiple of 4 (to overcome hardware limitation)
  * @tx_spillover: whether @tx_prologue spills over to second TX sglist entry
+ * @prepare_cs: precalculated CS register value for ->prepare_message()
+ *	(uses slave-specific clock polarity and phase settings)
  * @debugfs_dir: the debugfs directory - neede to remove debugfs when
  *      unloading the module
  * @count_transfer_polling: count of how often polling mode is used
@@ -123,6 +126,7 @@ struct bcm2835_spi {
 	int tx_prologue;
 	int rx_prologue;
 	unsigned int tx_spillover;
+	u32 prepare_cs[BCM2835_SPI_NUM_CS];
 
 	struct dentry *debugfs_dir;
 	u64 count_transfer_polling;
@@ -825,7 +829,7 @@ static int bcm2835_spi_transfer_one(struct spi_controller *ctlr,
 	struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
 	unsigned long spi_hz, clk_hz, cdiv, spi_used_hz;
 	unsigned long hz_per_byte, byte_limit;
-	u32 cs = bcm2835_rd(bs, BCM2835_SPI_CS);
+	u32 cs = bs->prepare_cs[spi->chip_select];
 
 	/* set clock */
 	spi_hz = tfr->speed_hz;
@@ -849,15 +853,6 @@ static int bcm2835_spi_transfer_one(struct spi_controller *ctlr,
 	/* handle all the 3-wire mode */
 	if ((spi->mode & SPI_3WIRE) && (tfr->rx_buf))
 		cs |= BCM2835_SPI_CS_REN;
-	else
-		cs &= ~BCM2835_SPI_CS_REN;
-
-	/*
-	 * The driver always uses software-controlled GPIO Chip Select.
-	 * Set the hardware-controlled native Chip Select to an invalid
-	 * value to prevent it from interfering.
-	 */
-	cs |= BCM2835_SPI_CS_CS_10 | BCM2835_SPI_CS_CS_01;
 
 	/* set transmit buffers and length */
 	bs->tx_buf = tfr->tx_buf;
@@ -894,7 +889,6 @@ static int bcm2835_spi_prepare_message(struct spi_controller *ctlr,
 {
 	struct spi_device *spi = msg->spi;
 	struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
-	u32 cs = bcm2835_rd(bs, BCM2835_SPI_CS);
 	int ret;
 
 	if (ctlr->can_dma) {
@@ -909,14 +903,11 @@ static int bcm2835_spi_prepare_message(struct spi_controller *ctlr,
 			return ret;
 	}
 
-	cs &= ~(BCM2835_SPI_CS_CPOL | BCM2835_SPI_CS_CPHA);
-
-	if (spi->mode & SPI_CPOL)
-		cs |= BCM2835_SPI_CS_CPOL;
-	if (spi->mode & SPI_CPHA)
-		cs |= BCM2835_SPI_CS_CPHA;
-
-	bcm2835_wr(bs, BCM2835_SPI_CS, cs);
+	/*
+	 * Set up clock polarity before spi_transfer_one_message() asserts
+	 * chip select to avoid a gratuitous clock signal edge.
+	 */
+	bcm2835_wr(bs, BCM2835_SPI_CS, bs->prepare_cs[spi->chip_select]);
 
 	return 0;
 }
@@ -942,8 +933,24 @@ static int chip_match_name(struct gpio_chip *chip, void *data)
 
 static int bcm2835_spi_setup(struct spi_device *spi)
 {
+	struct bcm2835_spi *bs = spi_controller_get_devdata(spi->controller);
 	int err;
 	struct gpio_chip *chip;
+	u32 cs;
+
+	/*
+	 * Precalculate SPI slave's CS register value for ->prepare_message():
+	 * The driver always uses software-controlled GPIO chip select, hence
+	 * set the hardware-controlled native chip select to an invalid value
+	 * to prevent it from interfering.
+	 */
+	cs = BCM2835_SPI_CS_CS_10 | BCM2835_SPI_CS_CS_01;
+	if (spi->mode & SPI_CPOL)
+		cs |= BCM2835_SPI_CS_CPOL;
+	if (spi->mode & SPI_CPHA)
+		cs |= BCM2835_SPI_CS_CPHA;
+	bs->prepare_cs[spi->chip_select] = cs;
+
 	/*
 	 * sanity checking the native-chipselects
 	 */
@@ -1002,7 +1009,7 @@ static int bcm2835_spi_probe(struct platform_device *pdev)
 
 	ctlr->mode_bits = BCM2835_SPI_MODE_BITS;
 	ctlr->bits_per_word_mask = SPI_BPW_MASK(8);
-	ctlr->num_chipselect = 3;
+	ctlr->num_chipselect = BCM2835_SPI_NUM_CS;
 	ctlr->setup = bcm2835_spi_setup;
 	ctlr->transfer_one = bcm2835_spi_transfer_one;
 	ctlr->handle_err = bcm2835_spi_handle_err;