can: c_can: cache frames to operate as a true FIFO

As reported by a comment in the c_can_start_xmit() this was not a FIFO.
C/D_CAN controller sends out the buffers prioritized so that the lowest
buffer number wins.

What did c_can_start_xmit() do if head was less tail in the tx ring ? It
waited until all the frames queued in the FIFO was actually transmitted
by the controller before accepting a new CAN frame to transmit, even if
the FIFO was not full, to ensure that the messages were transmitted in
the order in which they were loaded.

By storing the frames in the FIFO without requiring its transmission, we
will be able to use the full size of the FIFO even in cases such as the
one described above. The transmission interrupt will trigger their
transmission only when all the messages previously loaded but stored in
less priority positions of the buffers have been transmitted.

Link: https://lore.kernel.org/r/20210807130800.5246-5-dariobin@libero.itSuggested-by: Gianluca Falavigna <gianluca.falavigna@inwind.it>
Signed-off-by: Dario Binacchi <dariobin@libero.it>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>

drivers/net/can/c_can/c_can.h

@@ -238,16 +238,7 @@ static inline u8 c_can_get_tx_tail(const struct c_can_tx_ring *ring)
 
 static inline u8 c_can_get_tx_free(const struct c_can_tx_ring *ring)
 {
-	u8 head = c_can_get_tx_head(ring);
-	u8 tail = c_can_get_tx_tail(ring);
-
-	/* This is not a FIFO. C/D_CAN sends out the buffers
-	 * prioritized. The lowest buffer number wins.
-	 */
-	if (head < tail)
-		return 0;
-
-	return ring->obj_num - head;
+	return ring->obj_num - (ring->head - ring->tail);
 }
 
 #endif /* C_CAN_H */

drivers/net/can/c_can/c_can_main.c

@@ -456,7 +456,7 @@ static netdev_tx_t c_can_start_xmit(struct sk_buff *skb,
 	struct can_frame *frame = (struct can_frame *)skb->data;
 	struct c_can_priv *priv = netdev_priv(dev);
 	struct c_can_tx_ring *tx_ring = &priv->tx;
-	u32 idx, obj;
+	u32 idx, obj, cmd = IF_COMM_TX;
 
 	if (can_dropped_invalid_skb(dev, skb))
 		return NETDEV_TX_OK;
@@ -469,7 +469,8 @@ static netdev_tx_t c_can_start_xmit(struct sk_buff *skb,
 	if (c_can_get_tx_free(tx_ring) == 0)
 		netif_stop_queue(dev);
 
-	obj = idx + priv->msg_obj_tx_first;
+	if (idx < c_can_get_tx_tail(tx_ring))
+		cmd &= ~IF_COMM_TXRQST; /* Cache the message */
 
 	/* Store the message in the interface so we can call
 	 * can_put_echo_skb(). We must do this before we enable
@@ -478,9 +479,8 @@ static netdev_tx_t c_can_start_xmit(struct sk_buff *skb,
 	c_can_setup_tx_object(dev, IF_TX, frame, idx);
 	priv->dlc[idx] = frame->len;
 	can_put_echo_skb(skb, dev, idx, 0);
-
-	/* Start transmission */
-	c_can_object_put(dev, IF_TX, obj, IF_COMM_TX);
+	obj = idx + priv->msg_obj_tx_first;
+	c_can_object_put(dev, IF_TX, obj, cmd);
 
 	return NETDEV_TX_OK;
 }
@@ -725,6 +725,7 @@ static void c_can_do_tx(struct net_device *dev)
 	struct c_can_tx_ring *tx_ring = &priv->tx;
 	struct net_device_stats *stats = &dev->stats;
 	u32 idx, obj, pkts = 0, bytes = 0, pend;
+	u8 tail;
 
 	if (priv->msg_obj_tx_last > 32)
 		pend = priv->read_reg32(priv, C_CAN_INTPND3_REG);
@@ -761,6 +762,18 @@ static void c_can_do_tx(struct net_device *dev)
 	stats->tx_bytes += bytes;
 	stats->tx_packets += pkts;
 	can_led_event(dev, CAN_LED_EVENT_TX);
+
+	tail = c_can_get_tx_tail(tx_ring);
+
+	if (tail == 0) {
+		u8 head = c_can_get_tx_head(tx_ring);
+
+		/* Start transmission for all cached messages */
+		for (idx = tail; idx < head; idx++) {
+			obj = idx + priv->msg_obj_tx_first;
+			c_can_object_put(dev, IF_NAPI, obj, IF_COMM_TXRQST);
+		}
+	}
 }
 
 /* If we have a gap in the pending bits, that means we either