can: m_can: Batch FIFO reads during CAN receive

On peripherals communicating over a relatively slow SPI line
(e.g. tcan4x5x), individual transfers have high fixed costs.
This causes the driver to spend most of its time waiting between
transfers and severely limits throughput.

Reduce these overheads by reading more than one word at a time.
Writing could get a similar treatment in follow-on commits.

Link: https://lore.kernel.org/r/20210817050853.14875-3-matt@bitbashing.ioSigned-off-by: Matt Kline <matt@bitbashing.io>
[mkl: remove __packed from struct id_and_dlc]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>

drivers/net/can/m_can/m_can.c

@@ -309,6 +309,15 @@ enum m_can_reg {
 #define TX_EVENT_MM_MASK	GENMASK(31, 24)
 #define TX_EVENT_TXTS_MASK	GENMASK(15, 0)
 
+/* The ID and DLC registers are adjacent in M_CAN FIFO memory,
+ * and we can save a (potentially slow) bus round trip by combining
+ * reads and writes to them.
+ */
+struct id_and_dlc {
+	u32 id;
+	u32 dlc;
+};
+
 static inline u32 m_can_read(struct m_can_classdev *cdev, enum m_can_reg reg)
 {
 	return cdev->ops->read_reg(cdev, reg);
@@ -464,17 +473,18 @@ static int m_can_read_fifo(struct net_device *dev, u32 rxfs)
 	struct m_can_classdev *cdev = netdev_priv(dev);
 	struct canfd_frame *cf;
 	struct sk_buff *skb;
-	u32 id, fgi, dlc;
+	struct id_and_dlc fifo_header;
+	u32 fgi;
 	u32 timestamp = 0;
-	int i, err;
+	int err;
 
 	/* calculate the fifo get index for where to read data */
 	fgi = FIELD_GET(RXFS_FGI_MASK, rxfs);
-	err = m_can_fifo_read(cdev, fgi, M_CAN_FIFO_DLC, &dlc, 1);
+	err = m_can_fifo_read(cdev, fgi, M_CAN_FIFO_ID, &fifo_header, 2);
 	if (err)
 		goto out_fail;
 
-	if (dlc & RX_BUF_FDF)
+	if (fifo_header.dlc & RX_BUF_FDF)
 		skb = alloc_canfd_skb(dev, &cf);
 	else
 		skb = alloc_can_skb(dev, (struct can_frame **)&cf);
@@ -483,37 +493,32 @@ static int m_can_read_fifo(struct net_device *dev, u32 rxfs)
 		return 0;
 	}
 
-	if (dlc & RX_BUF_FDF)
-		cf->len = can_fd_dlc2len((dlc >> 16) & 0x0F);
+	if (fifo_header.dlc & RX_BUF_FDF)
+		cf->len = can_fd_dlc2len((fifo_header.dlc >> 16) & 0x0F);
 	else
-		cf->len = can_cc_dlc2len((dlc >> 16) & 0x0F);
+		cf->len = can_cc_dlc2len((fifo_header.dlc >> 16) & 0x0F);
 
-	err = m_can_fifo_read(cdev, fgi, M_CAN_FIFO_ID, &id, 1);
-	if (err)
-		goto out_fail;
-
-	if (id & RX_BUF_XTD)
-		cf->can_id = (id & CAN_EFF_MASK) | CAN_EFF_FLAG;
+	if (fifo_header.id & RX_BUF_XTD)
+		cf->can_id = (fifo_header.id & CAN_EFF_MASK) | CAN_EFF_FLAG;
 	else
-		cf->can_id = (id >> 18) & CAN_SFF_MASK;
+		cf->can_id = (fifo_header.id >> 18) & CAN_SFF_MASK;
 
-	if (id & RX_BUF_ESI) {
+	if (fifo_header.id & RX_BUF_ESI) {
 		cf->flags |= CANFD_ESI;
 		netdev_dbg(dev, "ESI Error\n");
 	}
 
-	if (!(dlc & RX_BUF_FDF) && (id & RX_BUF_RTR)) {
+	if (!(fifo_header.dlc & RX_BUF_FDF) && (fifo_header.id & RX_BUF_RTR)) {
 		cf->can_id |= CAN_RTR_FLAG;
 	} else {
-		if (dlc & RX_BUF_BRS)
+		if (fifo_header.dlc & RX_BUF_BRS)
 			cf->flags |= CANFD_BRS;
 
-		for (i = 0; i < cf->len; i += 4) {
-			err = m_can_fifo_read(cdev, fgi, M_CAN_FIFO_DATA(i / 4), cf->data + i, 1);
+		err = m_can_fifo_read(cdev, fgi, M_CAN_FIFO_DATA(0),
+				      cf->data, DIV_ROUND_UP(cf->len, 4));
 		if (err)
 			goto out_fail;
 	}
-	}
 
 	/* acknowledge rx fifo 0 */
 	m_can_write(cdev, M_CAN_RXF0A, fgi);
@@ -521,7 +526,7 @@ static int m_can_read_fifo(struct net_device *dev, u32 rxfs)
 	stats->rx_packets++;
 	stats->rx_bytes += cf->len;
 
-	timestamp = FIELD_GET(RX_BUF_RXTS_MASK, dlc);
+	timestamp = FIELD_GET(RX_BUF_RXTS_MASK, fifo_header.dlc);
 
 	m_can_receive_skb(cdev, skb, timestamp);