can: m_can: Implement transmit submission coalescing

m_can supports submitting multiple transmits with one register write.
This is an interesting option to reduce the number of SPI transfers for
peripheral chips.

The m_can_tx_op is extended with a bool that signals if it is the last
transmission and the submit should be executed immediately.

The worker then writes the skb to the FIFO and submits it only if the
submit bool is set. If it isn't set, the worker will write the next skb
which is waiting in the workqueue to the FIFO, etc.
Signed-off-by: Markus Schneider-Pargmann <msp@baylibre.com>
Link: https://lore.kernel.org/all/20240207093220.2681425-15-msp@baylibre.comSigned-off-by: Marc Kleine-Budde <mkl@pengutronix.de>

drivers/net/can/m_can/m_can.c

@@ -1539,6 +1539,9 @@ static int m_can_start(struct net_device *dev)
 	if (ret)
 		return ret;
 
+	netdev_queue_set_dql_min_limit(netdev_get_tx_queue(cdev->net, 0),
+				       cdev->tx_max_coalesced_frames);
+
 	cdev->can.state = CAN_STATE_ERROR_ACTIVE;
 
 	m_can_enable_all_interrupts(cdev);
@@ -1835,8 +1838,13 @@ static netdev_tx_t m_can_tx_handler(struct m_can_classdev *cdev,
 		 */
 		can_put_echo_skb(skb, dev, putidx, frame_len);
 
-		/* Enable TX FIFO element to start transfer  */
-		m_can_write(cdev, M_CAN_TXBAR, (1 << putidx));
+		if (cdev->is_peripheral) {
+			/* Delay enabling TX FIFO element */
+			cdev->tx_peripheral_submit |= BIT(putidx);
+		} else {
+			/* Enable TX FIFO element to start transfer  */
+			m_can_write(cdev, M_CAN_TXBAR, BIT(putidx));
+		}
 		cdev->tx_fifo_putidx = (++cdev->tx_fifo_putidx >= cdev->can.echo_skb_max ?
 					0 : cdev->tx_fifo_putidx);
 	}
@@ -1849,6 +1857,17 @@ static netdev_tx_t m_can_tx_handler(struct m_can_classdev *cdev,
 	return NETDEV_TX_BUSY;
 }
 
+static void m_can_tx_submit(struct m_can_classdev *cdev)
+{
+	if (cdev->version == 30)
+		return;
+	if (!cdev->is_peripheral)
+		return;
+
+	m_can_write(cdev, M_CAN_TXBAR, cdev->tx_peripheral_submit);
+	cdev->tx_peripheral_submit = 0;
+}
+
 static void m_can_tx_work_queue(struct work_struct *ws)
 {
 	struct m_can_tx_op *op = container_of(ws, struct m_can_tx_op, work);
@@ -1857,11 +1876,15 @@ static void m_can_tx_work_queue(struct work_struct *ws)
 
 	op->skb = NULL;
 	m_can_tx_handler(cdev, skb);
+	if (op->submit)
+		m_can_tx_submit(cdev);
 }
 
-static void m_can_tx_queue_skb(struct m_can_classdev *cdev, struct sk_buff *skb)
+static void m_can_tx_queue_skb(struct m_can_classdev *cdev, struct sk_buff *skb,
+			       bool submit)
 {
 	cdev->tx_ops[cdev->next_tx_op].skb = skb;
+	cdev->tx_ops[cdev->next_tx_op].submit = submit;
 	queue_work(cdev->tx_wq, &cdev->tx_ops[cdev->next_tx_op].work);
 
 	++cdev->next_tx_op;
@@ -1872,7 +1895,17 @@ static void m_can_tx_queue_skb(struct m_can_classdev *cdev, struct sk_buff *skb)
 static netdev_tx_t m_can_start_peripheral_xmit(struct m_can_classdev *cdev,
 					       struct sk_buff *skb)
 {
-	m_can_tx_queue_skb(cdev, skb);
+	bool submit;
+
+	++cdev->nr_txs_without_submit;
+	if (cdev->nr_txs_without_submit >= cdev->tx_max_coalesced_frames ||
+	    !netdev_xmit_more()) {
+		cdev->nr_txs_without_submit = 0;
+		submit = true;
+	} else {
+		submit = false;
+	}
+	m_can_tx_queue_skb(cdev, skb, submit);
 
 	return NETDEV_TX_OK;
 }
@@ -2015,6 +2048,7 @@ static int m_can_get_coalesce(struct net_device *dev,
 
 	ec->rx_max_coalesced_frames_irq = cdev->rx_max_coalesced_frames_irq;
 	ec->rx_coalesce_usecs_irq = cdev->rx_coalesce_usecs_irq;
+	ec->tx_max_coalesced_frames = cdev->tx_max_coalesced_frames;
 	ec->tx_max_coalesced_frames_irq = cdev->tx_max_coalesced_frames_irq;
 	ec->tx_coalesce_usecs_irq = cdev->tx_coalesce_usecs_irq;
 
@@ -2059,6 +2093,18 @@ static int m_can_set_coalesce(struct net_device *dev,
 		netdev_err(dev, "tx-frames-irq and tx-usecs-irq can only be set together\n");
 		return -EINVAL;
 	}
+	if (ec->tx_max_coalesced_frames > cdev->mcfg[MRAM_TXE].num) {
+		netdev_err(dev, "tx-frames %u greater than the TX event FIFO %u\n",
+			   ec->tx_max_coalesced_frames,
+			   cdev->mcfg[MRAM_TXE].num);
+		return -EINVAL;
+	}
+	if (ec->tx_max_coalesced_frames > cdev->mcfg[MRAM_TXB].num) {
+		netdev_err(dev, "tx-frames %u greater than the TX FIFO %u\n",
+			   ec->tx_max_coalesced_frames,
+			   cdev->mcfg[MRAM_TXB].num);
+		return -EINVAL;
+	}
 	if (ec->rx_coalesce_usecs_irq != 0 && ec->tx_coalesce_usecs_irq != 0 &&
 	    ec->rx_coalesce_usecs_irq != ec->tx_coalesce_usecs_irq) {
 		netdev_err(dev, "rx-usecs-irq %u needs to be equal to tx-usecs-irq %u if both are enabled\n",
@@ -2069,6 +2115,7 @@ static int m_can_set_coalesce(struct net_device *dev,
 
 	cdev->rx_max_coalesced_frames_irq = ec->rx_max_coalesced_frames_irq;
 	cdev->rx_coalesce_usecs_irq = ec->rx_coalesce_usecs_irq;
+	cdev->tx_max_coalesced_frames = ec->tx_max_coalesced_frames;
 	cdev->tx_max_coalesced_frames_irq = ec->tx_max_coalesced_frames_irq;
 	cdev->tx_coalesce_usecs_irq = ec->tx_coalesce_usecs_irq;
 
@@ -2086,6 +2133,7 @@ static const struct ethtool_ops m_can_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_RX_USECS_IRQ |
 		ETHTOOL_COALESCE_RX_MAX_FRAMES_IRQ |
 		ETHTOOL_COALESCE_TX_USECS_IRQ |
+		ETHTOOL_COALESCE_TX_MAX_FRAMES |
 		ETHTOOL_COALESCE_TX_MAX_FRAMES_IRQ,
 	.get_ts_info = ethtool_op_get_ts_info,
 	.get_coalesce = m_can_get_coalesce,

drivers/net/can/m_can/m_can.h

@@ -74,6 +74,7 @@ struct m_can_tx_op {
 	struct m_can_classdev *cdev;
 	struct work_struct work;
 	struct sk_buff *skb;
+	bool submit;
 };
 
 struct m_can_classdev {
@@ -102,6 +103,7 @@ struct m_can_classdev {
 	u32 active_interrupts;
 	u32 rx_max_coalesced_frames_irq;
 	u32 rx_coalesce_usecs_irq;
+	u32 tx_max_coalesced_frames;
 	u32 tx_max_coalesced_frames_irq;
 	u32 tx_coalesce_usecs_irq;
 
@@ -116,6 +118,10 @@ struct m_can_classdev {
 	int tx_fifo_size;
 	int next_tx_op;
 
+	int nr_txs_without_submit;
+	/* bitfield of fifo elements that will be submitted together */
+	u32 tx_peripheral_submit;
+
 	struct mram_cfg mcfg[MRAM_CFG_NUM];
 
 	struct hrtimer hrtimer;