tap: accept an array of XDP buffs through sendmsg()

This patch implement TUN_MSG_PTR msg_control type. This type allows
the caller to pass an array of XDP buffs to tuntap through ptr field
of the tun_msg_control. Tap will build skb through those XDP buffers.

This will avoid lots of indirect calls thus improves the icache
utilization and allows to do XDP batched flushing when doing XDP
redirection.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 72 insertions, 2 deletions

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 7996ed7cbf18..a4ab4a791fe7 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -1146,14 +1146,84 @@ static const struct file_operations tap_fops = {
 #endif
 };
 
+static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp)
+{
+	struct tun_xdp_hdr *hdr = xdp->data_hard_start;
+	struct virtio_net_hdr *gso = &hdr->gso;
+	int buflen = hdr->buflen;
+	int vnet_hdr_len = 0;
+	struct tap_dev *tap;
+	struct sk_buff *skb;
+	int err, depth;
+
+	if (q->flags & IFF_VNET_HDR)
+		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
+
+	skb = build_skb(xdp->data_hard_start, buflen);
+	if (!skb) {
+		err = -ENOMEM;
+		goto err;
+	}
+
+	skb_reserve(skb, xdp->data - xdp->data_hard_start);
+	skb_put(skb, xdp->data_end - xdp->data);
+
+	skb_set_network_header(skb, ETH_HLEN);
+	skb_reset_mac_header(skb);
+	skb->protocol = eth_hdr(skb)->h_proto;
+
+	if (vnet_hdr_len) {
+		err = virtio_net_hdr_to_skb(skb, gso, tap_is_little_endian(q));
+		if (err)
+			goto err_kfree;
+	}
+
+	skb_probe_transport_header(skb, ETH_HLEN);
+
+	/* Move network header to the right position for VLAN tagged packets */
+	if ((skb->protocol == htons(ETH_P_8021Q) ||
+	     skb->protocol == htons(ETH_P_8021AD)) &&
+	    __vlan_get_protocol(skb, skb->protocol, &depth) != 0)
+		skb_set_network_header(skb, depth);
+
+	rcu_read_lock();
+	tap = rcu_dereference(q->tap);
+	if (tap) {
+		skb->dev = tap->dev;
+		dev_queue_xmit(skb);
+	} else {
+		kfree_skb(skb);
+	}
+	rcu_read_unlock();
+
+	return 0;
+
+err_kfree:
+	kfree_skb(skb);
+err:
+	rcu_read_lock();
+		tap = rcu_dereference(q->tap);
+	if (tap && tap->count_tx_dropped)
+		tap->count_tx_dropped(tap);
+	rcu_read_unlock();
+	return err;
+}
+
 static int tap_sendmsg(struct socket *sock, struct msghdr *m,
 		       size_t total_len)
 {
 	struct tap_queue *q = container_of(sock, struct tap_queue, sock);
 	struct tun_msg_ctl *ctl = m->msg_control;
+	struct xdp_buff *xdp;
+	int i;
 
-	if (ctl && ctl->type != TUN_MSG_UBUF)
-		return -EINVAL;
+	if (ctl && (ctl->type == TUN_MSG_PTR)) {
+		for (i = 0; i < ctl->num; i++) {
+			xdp = &((struct xdp_buff *)ctl->ptr)[i];
+			tap_get_user_xdp(q, xdp);
+		}
+		return 0;
+	}
 
 	return tap_get_user(q, ctl ? ctl->ptr : NULL, &m->msg_iter,
 			    m->msg_flags & MSG_DONTWAIT);