net: lan966x: Add support for XDP_TX

Extend lan966x XDP support with the action XDP_TX. In this case when the
received buffer needs to execute XDP_TX, the buffer will be moved to the
TX buffers. So a new RX buffer will be allocated.
When the TX finish with the frame, it would give back the buffer to the
page pool.

Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 72 insertions, 7 deletions

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
index bc30c31c4360..cd622310385b 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
@@ -410,12 +410,17 @@ static void lan966x_fdma_tx_clear_buf(struct lan966x *lan966x, int weight)
 		dcb_buf->dev->stats.tx_bytes += dcb_buf->len;
 
 		dcb_buf->used = false;
-		dma_unmap_single(lan966x->dev,
-				 dcb_buf->dma_addr,
-				 dcb_buf->len,
-				 DMA_TO_DEVICE);
-		if (!dcb_buf->ptp)
-			dev_kfree_skb_any(dcb_buf->skb);
+		if (dcb_buf->use_skb) {
+			dma_unmap_single(lan966x->dev,
+					 dcb_buf->dma_addr,
+					 dcb_buf->len,
+					 DMA_TO_DEVICE);
+
+			if (!dcb_buf->ptp)
+				napi_consume_skb(dcb_buf->data.skb, weight);
+		} else {
+			xdp_return_frame_rx_napi(dcb_buf->data.xdpf);
+		}
 
 		clear = true;
 	}
@@ -548,6 +553,9 @@ static int lan966x_fdma_napi_poll(struct napi_struct *napi, int weight)
 			lan966x_fdma_rx_free_page(rx);
 			lan966x_fdma_rx_advance_dcb(rx);
 			goto allocate_new;
+		case FDMA_TX:
+			lan966x_fdma_rx_advance_dcb(rx);
+			continue;
 		case FDMA_DROP:
 			lan966x_fdma_rx_free_page(rx);
 			lan966x_fdma_rx_advance_dcb(rx);
@@ -669,6 +677,62 @@ static void lan966x_fdma_tx_start(struct lan966x_tx *tx, int next_to_use)
 	tx->last_in_use = next_to_use;
 }
 
+int lan966x_fdma_xmit_xdpf(struct lan966x_port *port,
+			   struct xdp_frame *xdpf,
+			   struct page *page)
+{
+	struct lan966x *lan966x = port->lan966x;
+	struct lan966x_tx_dcb_buf *next_dcb_buf;
+	struct lan966x_tx *tx = &lan966x->tx;
+	dma_addr_t dma_addr;
+	int next_to_use;
+	__be32 *ifh;
+	int ret = 0;
+
+	spin_lock(&lan966x->tx_lock);
+
+	/* Get next index */
+	next_to_use = lan966x_fdma_get_next_dcb(tx);
+	if (next_to_use < 0) {
+		netif_stop_queue(port->dev);
+		ret = NETDEV_TX_BUSY;
+		goto out;
+	}
+
+	/* Generate new IFH */
+	ifh = page_address(page) + XDP_PACKET_HEADROOM;
+	memset(ifh, 0x0, sizeof(__be32) * IFH_LEN);
+	lan966x_ifh_set_bypass(ifh, 1);
+	lan966x_ifh_set_port(ifh, BIT_ULL(port->chip_port));
+
+	dma_addr = page_pool_get_dma_addr(page);
+	dma_sync_single_for_device(lan966x->dev, dma_addr + XDP_PACKET_HEADROOM,
+				   xdpf->len + IFH_LEN_BYTES,
+				   DMA_TO_DEVICE);
+
+	/* Setup next dcb */
+	lan966x_fdma_tx_setup_dcb(tx, next_to_use, xdpf->len + IFH_LEN_BYTES,
+				  dma_addr + XDP_PACKET_HEADROOM);
+
+	/* Fill up the buffer */
+	next_dcb_buf = &tx->dcbs_buf[next_to_use];
+	next_dcb_buf->use_skb = false;
+	next_dcb_buf->data.xdpf = xdpf;
+	next_dcb_buf->len = xdpf->len + IFH_LEN_BYTES;
+	next_dcb_buf->dma_addr = dma_addr;
+	next_dcb_buf->used = true;
+	next_dcb_buf->ptp = false;
+	next_dcb_buf->dev = port->dev;
+
+	/* Start the transmission */
+	lan966x_fdma_tx_start(tx, next_to_use);
+
+out:
+	spin_unlock(&lan966x->tx_lock);
+
+	return ret;
+}
+
 int lan966x_fdma_xmit(struct sk_buff *skb, __be32 *ifh, struct net_device *dev)
 {
 	struct lan966x_port *port = netdev_priv(dev);
@@ -724,7 +788,8 @@ int lan966x_fdma_xmit(struct sk_buff *skb, __be32 *ifh, struct net_device *dev)
 
 	/* Fill up the buffer */
 	next_dcb_buf = &tx->dcbs_buf[next_to_use];
-	next_dcb_buf->skb = skb;
+	next_dcb_buf->use_skb = true;
+	next_dcb_buf->data.skb = skb;
 	next_dcb_buf->len = skb->len;
 	next_dcb_buf->dma_addr = dma_addr;
 	next_dcb_buf->used = true;