Add XDP_REDIRECT support and implement ndo_xdp_xmit for receiving
redirected frames from other devices.

XDP_REDIRECT calls xdp_do_redirect() in the RX path with
xdp_do_flush() once per NAPI poll cycle. ndo_xdp_xmit batches frames
into ring 16 under a single spinlock acquisition.

Advertise NETDEV_XDP_ACT_REDIRECT and NETDEV_XDP_ACT_NDO_XMIT in
xdp_features.

Signed-off-by: Nicolai Buchwitz <nb@tipi-net.de>
---
 .../net/ethernet/broadcom/genet/bcmgenet.c    | 96 +++++++++++++++----
 1 file changed, 78 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 922895bc7461..5dfe6b764930 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2320,23 +2320,23 @@ static struct sk_buff *bcmgenet_xdp_build_skb(struct bcmgenet_rx_ring *ring,
 	return skb;
 }
 
+/* Submit a single XDP frame to the TX ring. Caller must hold ring->lock.
+ * Returns true on success. Does not ring the doorbell - caller must
+ * write TDMA_PROD_INDEX after batching.
+ */
 static bool bcmgenet_xdp_xmit_frame(struct bcmgenet_priv *priv,
+				     struct bcmgenet_tx_ring *ring,
 				     struct xdp_frame *xdpf,
 				     bool dma_map)
 {
-	struct bcmgenet_tx_ring *ring = &priv->tx_rings[DESC_INDEX];
 	struct device *kdev = &priv->pdev->dev;
 	struct enet_cb *tx_cb_ptr;
 	dma_addr_t mapping;
 	unsigned int dma_len;
 	u32 len_stat;
 
-	spin_lock(&ring->lock);
-
-	if (ring->free_bds < 1) {
-		spin_unlock(&ring->lock);
+	if (ring->free_bds < 1)
 		return false;
-	}
 
 	tx_cb_ptr = bcmgenet_get_txcb(priv, ring);
 
@@ -2350,7 +2350,6 @@ static bool bcmgenet_xdp_xmit_frame(struct bcmgenet_priv *priv,
 		 */
 		if (unlikely(xdpf->headroom < sizeof(struct status_64))) {
 			bcmgenet_put_txcb(priv, ring);
-			spin_unlock(&ring->lock);
 			return false;
 		}
 
@@ -2364,7 +2363,6 @@ static bool bcmgenet_xdp_xmit_frame(struct bcmgenet_priv *priv,
 			tx_cb_ptr->skb = NULL;
 			tx_cb_ptr->xdpf = NULL;
 			bcmgenet_put_txcb(priv, ring);
-			spin_unlock(&ring->lock);
 			return false;
 		}
 	} else {
@@ -2396,12 +2394,14 @@ static bool bcmgenet_xdp_xmit_frame(struct bcmgenet_priv *priv,
 	ring->prod_index++;
 	ring->prod_index &= DMA_P_INDEX_MASK;
 
+	return true;
+}
+
+static void bcmgenet_xdp_ring_doorbell(struct bcmgenet_priv *priv,
+					struct bcmgenet_tx_ring *ring)
+{
 	bcmgenet_tdma_ring_writel(priv, ring->index, ring->prod_index,
 				  TDMA_PROD_INDEX);
-
-	spin_unlock(&ring->lock);
-
-	return true;
 }
 
 static unsigned int
@@ -2417,7 +2417,11 @@ bcmgenet_run_xdp(struct bcmgenet_rx_ring *ring, struct bpf_prog *prog,
 	switch (act) {
 	case XDP_PASS:
 		return XDP_PASS;
-	case XDP_TX:
+	case XDP_TX: {
+		struct bcmgenet_tx_ring *tx_ring;
+
+		tx_ring = &priv->tx_rings[DESC_INDEX];
+
 		/* Prepend a zeroed TSB (Transmit Status Block).  The GENET
 		 * MAC has TBUF_64B_EN set globally, so hardware expects every
 		 * TX buffer to begin with a 64-byte struct status_64.  Back
@@ -2429,14 +2433,26 @@ bcmgenet_run_xdp(struct bcmgenet_rx_ring *ring, struct bpf_prog *prog,
 		memset(xdp->data, 0, sizeof(struct status_64));
 
 		xdpf = xdp_convert_buff_to_frame(xdp);
-		if (unlikely(!xdpf) ||
-		    unlikely(!bcmgenet_xdp_xmit_frame(priv, xdpf, false))) {
-			page_pool_put_full_page(ring->page_pool, rx_page,
-						true);
+		if (unlikely(!xdpf))
+			goto drop_page;
+
+		spin_lock(&tx_ring->lock);
+		if (unlikely(!bcmgenet_xdp_xmit_frame(priv, tx_ring, xdpf,
+						       false))) {
+			spin_unlock(&tx_ring->lock);
+			xdp_return_frame_rx_napi(xdpf);
 			return XDP_DROP;
 		}
+		bcmgenet_xdp_ring_doorbell(priv, tx_ring);
+		spin_unlock(&tx_ring->lock);
 		return XDP_TX;
+	}
+	case XDP_REDIRECT:
+		if (unlikely(xdp_do_redirect(priv->dev, xdp, prog)))
+			goto drop_page;
+		return XDP_REDIRECT;
 	case XDP_DROP:
+drop_page:
 		page_pool_put_full_page(ring->page_pool, rx_page, true);
 		return XDP_DROP;
 	default:
@@ -2459,6 +2475,7 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 	struct bcmgenet_priv *priv = ring->priv;
 	struct net_device *dev = priv->dev;
 	struct bpf_prog *xdp_prog;
+	bool xdp_flush = false;
 	struct enet_cb *cb;
 	struct sk_buff *skb;
 	u32 dma_length_status;
@@ -2597,6 +2614,8 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 
 			xdp_act = bcmgenet_run_xdp(ring, xdp_prog, &xdp,
 						   rx_page);
+			if (xdp_act == XDP_REDIRECT)
+				xdp_flush = true;
 			if (xdp_act != XDP_PASS)
 				goto next;
 
@@ -2670,6 +2689,9 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 		bcmgenet_rdma_ring_writel(priv, ring->index, ring->c_index, RDMA_CONS_INDEX);
 	}
 
+	if (xdp_flush)
+		xdp_do_flush();
+
 	ring->dim.bytes = bytes_processed;
 	ring->dim.packets = rxpktprocessed;
 
@@ -3996,10 +4018,16 @@ static int bcmgenet_xdp_setup(struct net_device *dev,
 		return -EOPNOTSUPP;
 	}
 
+	if (!prog)
+		xdp_features_clear_redirect_target(dev);
+
 	old_prog = xchg(&priv->xdp_prog, prog);
 	if (old_prog)
 		bpf_prog_put(old_prog);
 
+	if (prog)
+		xdp_features_set_redirect_target(dev, false);
+
 	return 0;
 }
 
@@ -4013,6 +4041,36 @@ static int bcmgenet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	}
 }
 
+static int bcmgenet_xdp_xmit(struct net_device *dev, int num_frames,
+			      struct xdp_frame **frames, u32 flags)
+{
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct bcmgenet_tx_ring *ring = &priv->tx_rings[DESC_INDEX];
+	int sent = 0;
+	int i;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	if (unlikely(!netif_running(dev)))
+		return -ENETDOWN;
+
+	spin_lock(&ring->lock);
+
+	for (i = 0; i < num_frames; i++) {
+		if (!bcmgenet_xdp_xmit_frame(priv, ring, frames[i], true))
+			break;
+		sent++;
+	}
+
+	if (sent)
+		bcmgenet_xdp_ring_doorbell(priv, ring);
+
+	spin_unlock(&ring->lock);
+
+	return sent;
+}
+
 static const struct net_device_ops bcmgenet_netdev_ops = {
 	.ndo_open		= bcmgenet_open,
 	.ndo_stop		= bcmgenet_close,
@@ -4025,6 +4083,7 @@ static const struct net_device_ops bcmgenet_netdev_ops = {
 	.ndo_get_stats64	= bcmgenet_get_stats64,
 	.ndo_change_carrier	= bcmgenet_change_carrier,
 	.ndo_bpf		= bcmgenet_xdp,
+	.ndo_xdp_xmit		= bcmgenet_xdp_xmit,
 };
 
 /* GENET hardware parameters/characteristics */
@@ -4327,7 +4386,8 @@ static int bcmgenet_probe(struct platform_device *pdev)
 			 NETIF_F_RXCSUM;
 	dev->hw_features |= dev->features;
 	dev->vlan_features |= dev->features;
-	dev->xdp_features = NETDEV_XDP_ACT_BASIC;
+	dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			    NETDEV_XDP_ACT_NDO_XMIT;
 
 	netdev_sw_irq_coalesce_default_on(dev);
 
-- 
2.51.0