[PATCH net-next 8/8] cadence: macb: introduce xmit support

[Paolo Valerio <pvalerio@redhat.com>]

Add XDP_TX verdict support, also introduce ndo_xdp_xmit function for
redirection, and update macb_tx_unmap() to handle both skbs and xdp
frames advertising NETDEV_XDP_ACT_NDO_XMIT capability and the ability
to process XDP_TX verdicts.

Signed-off-by: Paolo Valerio <pvalerio@redhat.com>
---
 drivers/net/ethernet/cadence/macb_main.c | 165 +++++++++++++++++++++--
 1 file changed, 157 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index afd8c0f2d895..32f8629bcb25 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -969,6 +969,17 @@ static int macb_halt_tx(struct macb *bp)
 					bp, TSR);
 }
 
+static void release_buff(void *buff, enum macb_tx_buff_type type, int budget)
+{
+	if (type == MACB_TYPE_SKB) {
+		napi_consume_skb(buff, budget);
+	} else if (type == MACB_TYPE_XDP_TX) {
+		xdp_return_frame_rx_napi(buff);
+	} else {
+		xdp_return_frame(buff);
+	}
+}
+
 static void macb_tx_unmap(struct macb *bp, struct macb_tx_buff *tx_buff,
 			  int budget)
 {
@@ -983,7 +994,7 @@ static void macb_tx_unmap(struct macb *bp, struct macb_tx_buff *tx_buff,
 	}
 
 	if (tx_buff->ptr) {
-		napi_consume_skb(tx_buff->ptr, budget);
+		release_buff(tx_buff->ptr, tx_buff->type, budget);
 		tx_buff->ptr = NULL;
 	}
 }
@@ -1071,6 +1082,10 @@ static void macb_tx_error_task(struct work_struct *work)
 		desc = macb_tx_desc(queue, tail);
 		ctrl = desc->ctrl;
 		tx_buff = macb_tx_buff(queue, tail);
+
+		if (tx_buff->type != MACB_TYPE_SKB)
+			goto unmap;
+
 		skb = tx_buff->ptr;
 
 		if (ctrl & MACB_BIT(TX_USED)) {
@@ -1108,6 +1123,7 @@ static void macb_tx_error_task(struct work_struct *work)
 			desc->ctrl = ctrl | MACB_BIT(TX_USED);
 		}
 
+unmap:
 		macb_tx_unmap(bp, tx_buff, 0);
 	}
 
@@ -1186,6 +1202,7 @@ static int macb_tx_complete(struct macb_queue *queue, int budget)
 	spin_lock_irqsave(&queue->tx_ptr_lock, flags);
 	head = queue->tx_head;
 	for (tail = queue->tx_tail; tail != head && packets < budget; tail++) {
+		void			*data = NULL;
 		struct macb_tx_buff	*tx_buff;
 		struct sk_buff		*skb;
 		struct macb_dma_desc	*desc;
@@ -1208,11 +1225,16 @@ static int macb_tx_complete(struct macb_queue *queue, int budget)
 		for (;; tail++) {
 			tx_buff = macb_tx_buff(queue, tail);
 
-			if (tx_buff->type == MACB_TYPE_SKB)
-				skb = tx_buff->ptr;
+			if (tx_buff->type != MACB_TYPE_SKB) {
+				data = tx_buff->ptr;
+				goto unmap;
+			}
 
 			/* First, update TX stats if needed */
-			if (skb) {
+			if (tx_buff->type == MACB_TYPE_SKB && tx_buff->ptr) {
+				data = 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);
@@ -1228,6 +1250,7 @@ static int macb_tx_complete(struct macb_queue *queue, int budget)
 				bytes += skb->len;
 			}
 
+unmap:
 			/* Now we can safely release resources */
 			macb_tx_unmap(bp, tx_buff, budget);
 
@@ -1235,7 +1258,7 @@ static int macb_tx_complete(struct macb_queue *queue, int budget)
 			 * WARNING: at this point skb has been freed by
 			 * macb_tx_unmap().
 			 */
-			if (skb)
+			if (data)
 				break;
 		}
 	}
@@ -1350,10 +1373,127 @@ 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,
+				 dma_addr_t addr)
+{
+	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;
+		}
+	} else {
+		mapping = addr;
+		dma_sync_single_for_device(&bp->pdev->dev, mapping,
+					   xdpf->len, DMA_BIDIRECTIONAL);
+	}
+
+	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->ptr = xdpf;
+	tx_buff->type = buff_type;
+	tx_buff->mapping = mapping;
+	tx_buff->size = xdpf->len;
+	tx_buff->mapped_as_page = false;
+
+	ctrl = (u32)tx_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, tx_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(dev, queue_index);
+
+unlock:
+	spin_unlock_irqrestore(&queue->tx_ptr_lock, flags);
+
+	if (err)
+		release_buff(xdpf, buff_type, 0);
+
+	return err;
+}
+
+static int gem_xdp_xmit(struct net_device *dev, int num_frame,
+			struct xdp_frame **frames, u32 flags)
+{
+	struct macb *bp = netdev_priv(dev);
+	u32 xmitted = 0;
+	int i;
+
+	if (!macb_is_gem(bp))
+		return -EOPNOTSUPP;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	for (i = 0; i < num_frame; i++) {
+		if (macb_xdp_submit_frame(bp, frames[i], dev, true, 0))
+			break;
+
+		xmitted++;
+	}
+
+	return xmitted;
+}
+
 static u32 gem_xdp_run(struct macb_queue *queue, void *buff_head,
-		       unsigned int len)
+		       unsigned int len, dma_addr_t addr)
 {
 	struct net_device *dev;
+	struct xdp_frame *xdpf;
 	struct bpf_prog *prog;
 	struct xdp_buff xdp;
 
@@ -1380,6 +1520,13 @@ static u32 gem_xdp_run(struct macb_queue *queue, void *buff_head,
 			break;
 		}
 		goto out;
+	case XDP_TX:
+		xdpf = xdp_convert_buff_to_frame(&xdp);
+
+		if (!xdpf || macb_xdp_submit_frame(queue->bp, xdpf, dev, false,
+						   addr))
+			act = XDP_DROP;
+		goto out;
 	default:
 		bpf_warn_invalid_xdp_action(dev, prog, act);
 		fallthrough;
@@ -1467,7 +1614,7 @@ static int gem_rx(struct macb_queue *queue, struct napi_struct *napi,
 		if (!(first_frame && last_frame))
 			goto skip_xdp;
 
-		ret = gem_xdp_run(queue, buff_head, data_len);
+		ret = gem_xdp_run(queue, buff_head, data_len, addr);
 		if (ret == XDP_REDIRECT)
 			xdp_flush = true;
 
@@ -4580,6 +4727,7 @@ static const struct net_device_ops macb_netdev_ops = {
 	.ndo_hwtstamp_get	= macb_hwtstamp_get,
 	.ndo_setup_tc		= macb_setup_tc,
 	.ndo_bpf		= gem_xdp,
+	.ndo_xdp_xmit		= gem_xdp_xmit,
 };
 
 /* Configure peripheral capabilities according to device tree
@@ -5888,7 +6036,8 @@ static int macb_probe(struct platform_device *pdev)
 			bp->rx_headroom += NET_IP_ALIGN;
 
 		dev->xdp_features = NETDEV_XDP_ACT_BASIC |
-				    NETDEV_XDP_ACT_REDIRECT;
+				    NETDEV_XDP_ACT_REDIRECT |
+				    NETDEV_XDP_ACT_NDO_XMIT;
 	}
 
 	netif_carrier_off(dev);
-- 
2.52.0