macb_tx_complete() processing loop assumes a packet is composed of
multiple frames and composes around this idea. However, this is only
true in the SKB case ie `tx_buff->type == MACB_TYPE_SKB`.

Rework macb_tx_complete() to bring the tx_buff->type switch statement
outside and the frame iteration loop now lives only inside the SKB
case.

Fix Tx XDP stats that were not accounted for, in the XDP_TX|NDO cases.
Only increment statistics once per macb_tx_complete() call rather than
once per frame.

The `bytes` and `packets` stack variables now gets incremented for
completed XDP XMIT/TX packets. This implies the DQL subsystem through
netdev_tx_completed_queue() now gets notified of those packets
completing. We must therefore also report those bytes as sent, using
netdev_tx_sent_queue(), in macb_xdp_submit_frame() called by:
 - Rx XDP programs returning action XDP_TX and,
 - the .ndo_xdp_xmit() callback.

Incrementing `packets` also implies XDP packets are accounted for in our
NAPI budget calculation.

Signed-off-by: Théo Lebrun <theo.lebrun@bootlin.com>
---
 drivers/net/ethernet/cadence/macb_main.c | 71 +++++++++++++++-----------------
 1 file changed, 33 insertions(+), 38 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 1aa90499343a..c1677f1d8f23 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1212,7 +1212,7 @@ static int macb_tx_complete(struct macb_queue *queue, int budget)
 {
 	struct macb *bp = queue->bp;
 	unsigned long flags;
-	int skb_packets = 0;
+	int xsk_frames = 0;
 	unsigned int tail;
 	unsigned int head;
 	u16 queue_index;
@@ -1227,7 +1227,6 @@ static int macb_tx_complete(struct macb_queue *queue, int budget)
 		struct macb_tx_buff *tx_buff;
 		struct macb_dma_desc *desc;
 		struct sk_buff *skb;
-		void *data = NULL;
 		u32 ctrl;
 
 		desc = macb_tx_desc(queue, tail);
@@ -1243,52 +1242,46 @@ static int macb_tx_complete(struct macb_queue *queue, int budget)
 		if (!(ctrl & MACB_BIT(TX_USED)))
 			break;
 
-		/* Process all buffers of the current transmitted frame */
-		for (;; tail++) {
-			tx_buff = macb_tx_buff(queue, tail);
+		tx_buff = macb_tx_buff(queue, tail);
 
-			if (tx_buff->type != MACB_TYPE_SKB) {
-				data = tx_buff->ptr;
-				packets++;
-				goto unmap;
+		switch (tx_buff->type) {
+		case MACB_TYPE_SKB:
+			/* Process all buffers of the current transmitted frame */
+			while (!tx_buff->ptr) {
+				macb_tx_unmap(bp, tx_buff, budget);
+				tail++;
+				tx_buff = macb_tx_buff(queue, tail);
 			}
 
-			/* First, update TX stats if needed */
-			if (tx_buff->ptr) {
-				data = tx_buff->ptr;
-				skb = tx_buff->ptr;
+			skb = tx_buff->ptr;
 
-				if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
-				    !ptp_one_step_sync(skb))
-					gem_ptp_do_txstamp(bp, skb, desc);
+			if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+			    !ptp_one_step_sync(skb))
+				gem_ptp_do_txstamp(bp, skb, desc);
 
-				netdev_vdbg(bp->dev, "skb %u (data %p) TX complete\n",
-					    macb_tx_ring_wrap(bp, tail),
-					    skb->data);
-				bp->dev->stats.tx_packets++;
-				queue->stats.tx_packets++;
-				bp->dev->stats.tx_bytes += skb->len;
-				queue->stats.tx_bytes += skb->len;
-				skb_packets++;
-				packets++;
-				bytes += skb->len;
-			}
+			netdev_vdbg(bp->dev, "skb %u (data %p) TX complete\n",
+				    macb_tx_ring_wrap(bp, tail),
+				    skb->data);
+			bytes += skb->len;
+			break;
 
-unmap:
-			/* Now we can safely release resources */
-			macb_tx_unmap(bp, tx_buff, budget);
-
-			/* data is set only for the last buffer of the frame.
-			 * WARNING: at this point the buffer has been freed by
-			 * macb_tx_unmap().
-			 */
-			if (data)
-				break;
+		case MACB_TYPE_XDP_TX:
+		case MACB_TYPE_XDP_NDO:
+			bytes += tx_buff->size;
+			break;
 		}
+
+		packets++;
+		macb_tx_unmap(bp, tx_buff, budget);
 	}
 
+	bp->dev->stats.tx_packets += packets;
+	queue->stats.tx_packets += packets;
+	bp->dev->stats.tx_bytes += bytes;
+	queue->stats.tx_bytes += bytes;
+
 	netdev_tx_completed_queue(netdev_get_tx_queue(bp->dev, queue_index),
-				  skb_packets, bytes);
+				  packets, bytes);
 
 	queue->tx_tail = tail;
 	if (__netif_subqueue_stopped(bp->dev, queue_index) &&
@@ -1529,6 +1522,8 @@ static int macb_xdp_submit_frame(struct macb *bp, struct xdp_frame *xdpf,
 	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART));
 	spin_unlock(&bp->lock);
 
+	netdev_tx_sent_queue(netdev_get_tx_queue(bp->dev, queue_index), xdpf->len);
+
 	if (CIRC_SPACE(queue->tx_head, queue->tx_tail, bp->tx_ring_size) < 1)
 		netif_stop_subqueue(dev, queue_index);
 

-- 
2.53.0