xdp: transition into using xdp_frame for ndo_xdp_xmit

Changing API ndo_xdp_xmit to take a struct xdp_frame instead of struct
xdp_buff.  This brings xdp_return_frame and ndp_xdp_xmit in sync.

This builds towards changing the API further to become a bulk API,
because xdp_buff is not a queue-able object while xdp_frame is.

V4: Adjust for commit 59655a5b6c83 ("tuntap: XDP_TX can use native XDP")
V7: Adjust for commit d9314c474d4f ("i40e: add support for XDP_REDIRECT")

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/intel/i40e/i40e_txrx.c

@@ -2203,9 +2203,20 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring,
 #define I40E_XDP_CONSUMED 1
 #define I40E_XDP_TX 2
 
-static int i40e_xmit_xdp_ring(struct xdp_buff *xdp,
+static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf,
 			      struct i40e_ring *xdp_ring);
 
+static int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp,
+				 struct i40e_ring *xdp_ring)
+{
+	struct xdp_frame *xdpf = convert_to_xdp_frame(xdp);
+
+	if (unlikely(!xdpf))
+		return I40E_XDP_CONSUMED;
+
+	return i40e_xmit_xdp_ring(xdpf, xdp_ring);
+}
+
 /**
  * i40e_run_xdp - run an XDP program
  * @rx_ring: Rx ring being processed
@@ -2233,7 +2244,7 @@ static struct sk_buff *i40e_run_xdp(struct i40e_ring *rx_ring,
 		break;
 	case XDP_TX:
 		xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index];
-		result = i40e_xmit_xdp_ring(xdp, xdp_ring);
+		result = i40e_xmit_xdp_tx_ring(xdp, xdp_ring);
 		break;
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
@@ -3480,21 +3491,14 @@ dma_error:
  * @xdp: data to transmit
  * @xdp_ring: XDP Tx ring
  **/
-static int i40e_xmit_xdp_ring(struct xdp_buff *xdp,
+static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf,
 			      struct i40e_ring *xdp_ring)
 {
 	u16 i = xdp_ring->next_to_use;
 	struct i40e_tx_buffer *tx_bi;
 	struct i40e_tx_desc *tx_desc;
-	struct xdp_frame *xdpf;
+	u32 size = xdpf->len;
 	dma_addr_t dma;
-	u32 size;
-
-	xdpf = convert_to_xdp_frame(xdp);
-	if (unlikely(!xdpf))
-		return I40E_XDP_CONSUMED;
-
-	size = xdpf->len;
 
 	if (!unlikely(I40E_DESC_UNUSED(xdp_ring))) {
 		xdp_ring->tx_stats.tx_busy++;
@@ -3684,7 +3688,7 @@ netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
  *
  * Returns Zero if sent, else an error code
  **/
-int i40e_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
+int i40e_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf)
 {
 	struct i40e_netdev_priv *np = netdev_priv(dev);
 	unsigned int queue_index = smp_processor_id();
@@ -3697,7 +3701,7 @@ int i40e_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
 	if (!i40e_enabled_xdp_vsi(vsi) || queue_index >= vsi->num_queue_pairs)
 		return -ENXIO;
 
-	err = i40e_xmit_xdp_ring(xdp, vsi->xdp_rings[queue_index]);
+	err = i40e_xmit_xdp_ring(xdpf, vsi->xdp_rings[queue_index]);
 	if (err != I40E_XDP_TX)
 		return -ENOSPC;
 

drivers/net/ethernet/intel/i40e/i40e_txrx.h

@@ -511,7 +511,7 @@ u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw);
 void i40e_detect_recover_hung(struct i40e_vsi *vsi);
 int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size);
 bool __i40e_chk_linearize(struct sk_buff *skb);
-int i40e_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp);
+int i40e_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf);
 void i40e_xdp_flush(struct net_device *dev);
 
 /**

drivers/net/ethernet/intel/ixgbe/ixgbe_main.c

@@ -2262,7 +2262,7 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
 #define IXGBE_XDP_TX 2
 
 static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
-			       struct xdp_buff *xdp);
+			       struct xdp_frame *xdpf);
 
 static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
 				     struct ixgbe_ring *rx_ring,
@@ -2270,6 +2270,7 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
 {
 	int err, result = IXGBE_XDP_PASS;
 	struct bpf_prog *xdp_prog;
+	struct xdp_frame *xdpf;
 	u32 act;
 
 	rcu_read_lock();
@@ -2278,12 +2279,19 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
 	if (!xdp_prog)
 		goto xdp_out;
 
+	prefetchw(xdp->data_hard_start); /* xdp_frame write */
+
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
 	switch (act) {
 	case XDP_PASS:
 		break;
 	case XDP_TX:
-		result = ixgbe_xmit_xdp_ring(adapter, xdp);
+		xdpf = convert_to_xdp_frame(xdp);
+		if (unlikely(!xdpf)) {
+			result = IXGBE_XDP_CONSUMED;
+			break;
+		}
+		result = ixgbe_xmit_xdp_ring(adapter, xdpf);
 		break;
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog);
@@ -2386,7 +2394,6 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 			xdp.data_hard_start = xdp.data -
 					      ixgbe_rx_offset(rx_ring);
 			xdp.data_end = xdp.data + size;
-			prefetchw(xdp.data_hard_start); /* xdp_frame write */
 
 			skb = ixgbe_run_xdp(adapter, rx_ring, &xdp);
 		}
@@ -8344,20 +8351,15 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 }
 
 static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
-			       struct xdp_buff *xdp)
+			       struct xdp_frame *xdpf)
 {
 	struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()];
 	struct ixgbe_tx_buffer *tx_buffer;
 	union ixgbe_adv_tx_desc *tx_desc;
-	struct xdp_frame *xdpf;
 	u32 len, cmd_type;
 	dma_addr_t dma;
 	u16 i;
 
-	xdpf = convert_to_xdp_frame(xdp);
-	if (unlikely(!xdpf))
-		return -EOVERFLOW;
-
 	len = xdpf->len;
 
 	if (unlikely(!ixgbe_desc_unused(ring)))
@@ -10010,7 +10012,7 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	}
 }
 
-static int ixgbe_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
+static int ixgbe_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 	struct ixgbe_ring *ring;
@@ -10026,7 +10028,7 @@ static int ixgbe_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
 	if (unlikely(!ring))
 		return -ENXIO;
 
-	err = ixgbe_xmit_xdp_ring(adapter, xdp);
+	err = ixgbe_xmit_xdp_ring(adapter, xdpf);
 	if (err != IXGBE_XDP_TX)
 		return -ENOSPC;
 

drivers/net/tun.c

@@ -1301,18 +1301,13 @@ static const struct net_device_ops tun_netdev_ops = {
 	.ndo_get_stats64	= tun_net_get_stats64,
 };
 
-static int tun_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
+static int tun_xdp_xmit(struct net_device *dev, struct xdp_frame *frame)
 {
 	struct tun_struct *tun = netdev_priv(dev);
-	struct xdp_frame *frame;
 	struct tun_file *tfile;
 	u32 numqueues;
 	int ret = 0;
 
-	frame = convert_to_xdp_frame(xdp);
-	if (unlikely(!frame))
-		return -EOVERFLOW;
-
 	rcu_read_lock();
 
 	numqueues = READ_ONCE(tun->numqueues);
@@ -1336,6 +1331,16 @@ out:
 	return ret;
 }
 
+static int tun_xdp_tx(struct net_device *dev, struct xdp_buff *xdp)
+{
+	struct xdp_frame *frame = convert_to_xdp_frame(xdp);
+
+	if (unlikely(!frame))
+		return -EOVERFLOW;
+
+	return tun_xdp_xmit(dev, frame);
+}
+
 static void tun_xdp_flush(struct net_device *dev)
 {
 	struct tun_struct *tun = netdev_priv(dev);
@@ -1683,7 +1688,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 		case XDP_TX:
 			get_page(alloc_frag->page);
 			alloc_frag->offset += buflen;
-			if (tun_xdp_xmit(tun->dev, &xdp))
+			if (tun_xdp_tx(tun->dev, &xdp))
 				goto err_redirect;
 			tun_xdp_flush(tun->dev);
 			rcu_read_unlock();

drivers/net/virtio_net.c

@@ -416,10 +416,10 @@ static void virtnet_xdp_flush(struct net_device *dev)
 }
 
 static int __virtnet_xdp_xmit(struct virtnet_info *vi,
-			      struct xdp_buff *xdp)
+			       struct xdp_frame *xdpf)
 {
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
-	struct xdp_frame *xdpf, *xdpf_sent;
+	struct xdp_frame *xdpf_sent;
 	struct send_queue *sq;
 	unsigned int len;
 	unsigned int qp;
@@ -432,10 +432,6 @@ static int __virtnet_xdp_xmit(struct virtnet_info *vi,
 	while ((xdpf_sent = virtqueue_get_buf(sq->vq, &len)) != NULL)
 		xdp_return_frame(xdpf_sent);
 
-	xdpf = convert_to_xdp_frame(xdp);
-	if (unlikely(!xdpf))
-		return -EOVERFLOW;
-
 	/* virtqueue want to use data area in-front of packet */
 	if (unlikely(xdpf->metasize > 0))
 		return -EOPNOTSUPP;
@@ -459,7 +455,7 @@ static int __virtnet_xdp_xmit(struct virtnet_info *vi,
 	return 0;
 }
 
-static int virtnet_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
+static int virtnet_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
 	struct receive_queue *rq = vi->rq;
@@ -472,7 +468,7 @@ static int virtnet_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
 	if (!xdp_prog)
 		return -ENXIO;
 
-	return __virtnet_xdp_xmit(vi, xdp);
+	return __virtnet_xdp_xmit(vi, xdpf);
 }
 
 static unsigned int virtnet_get_headroom(struct virtnet_info *vi)
@@ -569,6 +565,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 	xdp_prog = rcu_dereference(rq->xdp_prog);
 	if (xdp_prog) {
 		struct virtio_net_hdr_mrg_rxbuf *hdr = buf + header_offset;
+		struct xdp_frame *xdpf;
 		struct xdp_buff xdp;
 		void *orig_data;
 		u32 act;
@@ -611,7 +608,10 @@ static struct sk_buff *receive_small(struct net_device *dev,
 			delta = orig_data - xdp.data;
 			break;
 		case XDP_TX:
-			err = __virtnet_xdp_xmit(vi, &xdp);
+			xdpf = convert_to_xdp_frame(&xdp);
+			if (unlikely(!xdpf))
+				goto err_xdp;
+			err = __virtnet_xdp_xmit(vi, xdpf);
 			if (unlikely(err)) {
 				trace_xdp_exception(vi->dev, xdp_prog, act);
 				goto err_xdp;
@@ -702,6 +702,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
 	if (xdp_prog) {
+		struct xdp_frame *xdpf;
 		struct page *xdp_page;
 		struct xdp_buff xdp;
 		void *data;
@@ -766,7 +767,10 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			}
 			break;
 		case XDP_TX:
-			err = __virtnet_xdp_xmit(vi, &xdp);
+			xdpf = convert_to_xdp_frame(&xdp);
+			if (unlikely(!xdpf))
+				goto err_xdp;
+			err = __virtnet_xdp_xmit(vi, xdpf);
 			if (unlikely(err)) {
 				trace_xdp_exception(vi->dev, xdp_prog, act);
 				if (unlikely(xdp_page != page))

include/linux/netdevice.h

@@ -1165,7 +1165,7 @@ struct dev_ifalias {
  *	This function is used to set or query state related to XDP on the
  *	netdevice and manage BPF offload. See definition of
  *	enum bpf_netdev_command for details.
- * int (*ndo_xdp_xmit)(struct net_device *dev, struct xdp_buff *xdp);
+ * int (*ndo_xdp_xmit)(struct net_device *dev, struct xdp_frame *xdp);
  *	This function is used to submit a XDP packet for transmit on a
  *	netdevice.
  * void (*ndo_xdp_flush)(struct net_device *dev);
@@ -1356,7 +1356,7 @@ struct net_device_ops {
 	int			(*ndo_bpf)(struct net_device *dev,
 					   struct netdev_bpf *bpf);
 	int			(*ndo_xdp_xmit)(struct net_device *dev,
-						struct xdp_buff *xdp);
+						struct xdp_frame *xdp);
 	void			(*ndo_xdp_flush)(struct net_device *dev);
 };
 

net/core/filter.c

@@ -2749,13 +2749,18 @@ static int __bpf_tx_xdp(struct net_device *dev,
 			struct xdp_buff *xdp,
 			u32 index)
 {
+	struct xdp_frame *xdpf;
 	int err;
 
 	if (!dev->netdev_ops->ndo_xdp_xmit) {
 		return -EOPNOTSUPP;
 	}
 
-	err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp);
+	xdpf = convert_to_xdp_frame(xdp);
+	if (unlikely(!xdpf))
+		return -EOVERFLOW;
+
+	err = dev->netdev_ops->ndo_xdp_xmit(dev, xdpf);
 	if (err)
 		return err;
 	dev->netdev_ops->ndo_xdp_flush(dev);
@@ -2771,11 +2776,19 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
 
 	if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
 		struct net_device *dev = fwd;
+		struct xdp_frame *xdpf;
 
 		if (!dev->netdev_ops->ndo_xdp_xmit)
 			return -EOPNOTSUPP;
 
-		err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp);
+		xdpf = convert_to_xdp_frame(xdp);
+		if (unlikely(!xdpf))
+			return -EOVERFLOW;
+
+		/* TODO: move to inside map code instead, for bulk support
+		 * err = dev_map_enqueue(dev, xdp);
+		 */
+		err = dev->netdev_ops->ndo_xdp_xmit(dev, xdpf);
 		if (err)
 			return err;
 		__dev_map_insert_ctx(map, index);