diff mbox series

[v8,bpf-next,06/10] veth: Add ndo_xdp_xmit

Message ID 1533283098-2397-7-git-send-email-makita.toshiaki@lab.ntt.co.jp
State Accepted, archived
Delegated to: BPF Maintainers
Headers show
Series veth: Driver XDP | expand

Commit Message

Toshiaki Makita Aug. 3, 2018, 7:58 a.m. UTC 
This allows NIC's XDP to redirect packets to veth. The destination veth
device enqueues redirected packets to the napi ring of its peer, then
they are processed by XDP on its peer veth device.
This can be thought as calling another XDP program by XDP program using
REDIRECT, when the peer enables driver XDP.

Note that when the peer veth device does not set driver xdp, redirected
packets will be dropped because the peer is not ready for NAPI.

v4:
- Don't use xdp_ok_fwd_dev() because checking IFF_UP is not necessary.
  Add comments about it and check only MTU.

v2:
- Drop the part converting xdp_frame into skb when XDP is not enabled.
- Implement bulk interface of ndo_xdp_xmit.
- Implement XDP_XMIT_FLUSH bit and drop ndo_xdp_flush.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: John Fastabend <john.fastabend@gmail.com>
---
 drivers/net/veth.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)
diff mbox series

Patch

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 89f3059..dbb693a 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -17,6 +17,7 @@ 
 #include <net/rtnetlink.h>
 #include <net/dst.h>
 #include <net/xfrm.h>
+#include <net/xdp.h>
 #include <linux/veth.h>
 #include <linux/module.h>
 #include <linux/bpf.h>
@@ -125,6 +126,11 @@  static void *veth_ptr_to_xdp(void *ptr)
 	return (void *)((unsigned long)ptr & ~VETH_XDP_FLAG);
 }
 
+static void *veth_xdp_to_ptr(void *ptr)
+{
+	return (void *)((unsigned long)ptr | VETH_XDP_FLAG);
+}
+
 static void veth_ptr_free(void *ptr)
 {
 	if (veth_is_xdp_frame(ptr))
@@ -267,6 +273,50 @@  static struct sk_buff *veth_build_skb(void *head, int headroom, int len,
 	return skb;
 }
 
+static int veth_xdp_xmit(struct net_device *dev, int n,
+			 struct xdp_frame **frames, u32 flags)
+{
+	struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
+	struct net_device *rcv;
+	unsigned int max_len;
+	int i, drops = 0;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	rcv = rcu_dereference(priv->peer);
+	if (unlikely(!rcv))
+		return -ENXIO;
+
+	rcv_priv = netdev_priv(rcv);
+	/* Non-NULL xdp_prog ensures that xdp_ring is initialized on receive
+	 * side. This means an XDP program is loaded on the peer and the peer
+	 * device is up.
+	 */
+	if (!rcu_access_pointer(rcv_priv->xdp_prog))
+		return -ENXIO;
+
+	max_len = rcv->mtu + rcv->hard_header_len + VLAN_HLEN;
+
+	spin_lock(&rcv_priv->xdp_ring.producer_lock);
+	for (i = 0; i < n; i++) {
+		struct xdp_frame *frame = frames[i];
+		void *ptr = veth_xdp_to_ptr(frame);
+
+		if (unlikely(frame->len > max_len ||
+			     __ptr_ring_produce(&rcv_priv->xdp_ring, ptr))) {
+			xdp_return_frame_rx_napi(frame);
+			drops++;
+		}
+	}
+	spin_unlock(&rcv_priv->xdp_ring.producer_lock);
+
+	if (flags & XDP_XMIT_FLUSH)
+		__veth_xdp_flush(rcv_priv);
+
+	return n - drops;
+}
+
 static struct sk_buff *veth_xdp_rcv_one(struct veth_priv *priv,
 					struct xdp_frame *frame)
 {
@@ -769,6 +819,7 @@  static int veth_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	.ndo_features_check	= passthru_features_check,
 	.ndo_set_rx_headroom	= veth_set_rx_headroom,
 	.ndo_bpf		= veth_xdp,
+	.ndo_xdp_xmit		= veth_xdp_xmit,
 };
 
 #define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | \