Part of macb_xdp_submit_frame() is specific to the handling of an XDP
buffer (pick a queue for emission, DMA map or sync, report emitted
bytes), part is chitchat with hardware to update DMA descriptor and
start transmit.

Move the hardware specific code out of macb_xdp_submit_frame() into a
macb_xdp_submit_buff() helper function. The goal is to make code
reusable to support XSK buffers.

The macb_xdp_submit_frame() body is modified slightly: we bring the
dma_map_single() call outside of the queue->tx_ptr_lock critical
section, to minimise its span.

Signed-off-by: Théo Lebrun <theo.lebrun@bootlin.com>
---
 drivers/net/ethernet/cadence/macb_main.c | 143 +++++++++++++++++--------------
 1 file changed, 78 insertions(+), 65 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index ed94f9f0894b..65c2ec2a843c 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1208,6 +1208,52 @@ static bool ptp_one_step_sync(struct sk_buff *skb)
 	return false;
 }
 
+static void macb_xdp_submit_buff(struct macb *bp, unsigned int queue_index,
+				 struct macb_tx_buff buff)
+{
+	struct macb_queue *queue = &bp->queues[queue_index];
+	struct net_device *netdev = bp->dev;
+	struct macb_tx_buff *tx_buff;
+	struct macb_dma_desc *desc;
+	unsigned int next_head;
+	u32 ctrl;
+
+	next_head = queue->tx_head + 1;
+
+	ctrl = MACB_BIT(TX_USED);
+	desc = macb_tx_desc(queue, next_head);
+	desc->ctrl = ctrl;
+
+	desc = macb_tx_desc(queue, queue->tx_head);
+	tx_buff = macb_tx_buff(queue, queue->tx_head);
+	*tx_buff = buff;
+
+	ctrl = (u32)buff.size;
+	ctrl |= MACB_BIT(TX_LAST);
+
+	if (unlikely(macb_tx_ring_wrap(bp, queue->tx_head) == (bp->tx_ring_size - 1)))
+		ctrl |= MACB_BIT(TX_WRAP);
+
+	/* Set TX buffer descriptor */
+	macb_set_addr(bp, desc, buff.mapping);
+	/* desc->addr must be visible to hardware before clearing
+	 * 'TX_USED' bit in desc->ctrl.
+	 */
+	wmb();
+	desc->ctrl = ctrl;
+	queue->tx_head = next_head;
+
+	/* Make newly initialized descriptor visible to hardware */
+	wmb();
+
+	spin_lock(&bp->lock);
+	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART));
+	spin_unlock(&bp->lock);
+
+	if (CIRC_SPACE(queue->tx_head, queue->tx_tail, bp->tx_ring_size) < 1)
+		netif_stop_subqueue(netdev, queue_index);
+}
+
 static int macb_tx_complete(struct macb_queue *queue, int budget)
 {
 	struct macb *bp = queue->bp;
@@ -1430,44 +1476,25 @@ static void discard_partial_frame(struct macb_queue *queue, unsigned int begin,
 }
 
 static int macb_xdp_submit_frame(struct macb *bp, struct xdp_frame *xdpf,
-				 struct net_device *dev, bool dma_map,
+				 struct net_device *netdev, bool dma_map,
 				 dma_addr_t addr)
 {
+	struct device *dev = &bp->pdev->dev;
 	enum macb_tx_buff_type buff_type;
-	struct macb_tx_buff *tx_buff;
 	int cpu = smp_processor_id();
-	struct macb_dma_desc *desc;
 	struct macb_queue *queue;
-	unsigned int next_head;
 	unsigned long flags;
 	dma_addr_t mapping;
 	u16 queue_index;
 	int err = 0;
-	u32 ctrl;
-
-	queue_index = cpu % bp->num_queues;
-	queue = &bp->queues[queue_index];
-	buff_type = dma_map ? MACB_TYPE_XDP_NDO : MACB_TYPE_XDP_TX;
-
-	spin_lock_irqsave(&queue->tx_ptr_lock, flags);
-
-	/* This is a hard error, log it. */
-	if (CIRC_SPACE(queue->tx_head, queue->tx_tail, bp->tx_ring_size) < 1) {
-		netif_stop_subqueue(dev, queue_index);
-		netdev_dbg(bp->dev, "tx_head = %u, tx_tail = %u\n",
-			   queue->tx_head, queue->tx_tail);
-		err = -ENOMEM;
-		goto unlock;
-	}
 
 	if (dma_map) {
-		mapping = dma_map_single(&bp->pdev->dev,
-					 xdpf->data,
-					 xdpf->len, DMA_TO_DEVICE);
-		if (unlikely(dma_mapping_error(&bp->pdev->dev, mapping))) {
-			err = -ENOMEM;
-			goto unlock;
-		}
+		mapping = dma_map_single(dev, xdpf->data, xdpf->len, DMA_TO_DEVICE);
+		err = dma_mapping_error(&bp->pdev->dev, mapping);
+		if (unlikely(err))
+			return err;
+
+		buff_type = MACB_TYPE_XDP_NDO;
 	} else {
 		/* progs can adjust the head. Sync and set the adjusted one.
 		 * This also implicitly takes into account ip alignment,
@@ -1476,52 +1503,38 @@ static int macb_xdp_submit_frame(struct macb *bp, struct xdp_frame *xdpf,
 		mapping = addr + xdpf->headroom + sizeof(*xdpf);
 		dma_sync_single_for_device(&bp->pdev->dev, mapping,
 					   xdpf->len, DMA_BIDIRECTIONAL);
+
+		buff_type = MACB_TYPE_XDP_TX;
 	}
 
-	next_head = queue->tx_head + 1;
+	queue_index = cpu % bp->num_queues;
+	queue = &bp->queues[queue_index];
 
-	ctrl = MACB_BIT(TX_USED);
-	desc = macb_tx_desc(queue, next_head);
-	desc->ctrl = ctrl;
+	spin_lock_irqsave(&queue->tx_ptr_lock, flags);
 
-	desc = macb_tx_desc(queue, queue->tx_head);
-	tx_buff = macb_tx_buff(queue, queue->tx_head);
-	tx_buff->ptr = xdpf;
-	tx_buff->type = buff_type;
-	tx_buff->mapping = dma_map ? mapping : 0;
-	tx_buff->size = xdpf->len;
-	tx_buff->mapped_as_page = false;
+	if (CIRC_SPACE(queue->tx_head, queue->tx_tail, bp->tx_ring_size) < 1) {
+		/* This is a hard error, log it. */
+		netif_stop_subqueue(netdev, queue_index);
+		netdev_dbg(netdev, "tx_head = %u, tx_tail = %u\n",
+			   queue->tx_head, queue->tx_tail);
+		err = -ENOMEM;
+	} else {
+		macb_xdp_submit_buff(bp, queue_index, (struct macb_tx_buff){
+			.ptr = xdpf,
+			.mapping = dma_map ? mapping : 0,
+			.size = xdpf->len,
+			.mapped_as_page = false,
+			.type = buff_type,
+		});
 
-	ctrl = (u32)tx_buff->size;
-	ctrl |= MACB_BIT(TX_LAST);
+		netdev_tx_sent_queue(netdev_get_tx_queue(bp->dev, queue_index), xdpf->len);
+	}
 
-	if (unlikely(macb_tx_ring_wrap(bp, queue->tx_head) == (bp->tx_ring_size - 1)))
-		ctrl |= MACB_BIT(TX_WRAP);
-
-	/* Set TX buffer descriptor */
-	macb_set_addr(bp, desc, mapping);
-	/* desc->addr must be visible to hardware before clearing
-	 * 'TX_USED' bit in desc->ctrl.
-	 */
-	wmb();
-	desc->ctrl = ctrl;
-	queue->tx_head = next_head;
-
-	/* Make newly initialized descriptor visible to hardware */
-	wmb();
-
-	spin_lock(&bp->lock);
-	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);
-
-unlock:
 	spin_unlock_irqrestore(&queue->tx_ptr_lock, flags);
 
+	if (err && dma_map)
+		dma_unmap_single(dev, mapping, xdpf->len, DMA_TO_DEVICE);
+
 	return err;
 }
 

-- 
2.53.0