tuntap: 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. If an XDP program is attached, tuntap can run
XDP program directly. If not, tuntap will build skb and do a fast
receiving since part of the work has been done by vhost_net.

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>

drivers/net/tun.c

@@ -2426,22 +2426,133 @@ static void tun_sock_write_space(struct sock *sk)
 	kill_fasync(&tfile->fasync, SIGIO, POLL_OUT);
 }
 
+static int tun_xdp_one(struct tun_struct *tun,
+		       struct tun_file *tfile,
+		       struct xdp_buff *xdp, int *flush)
+{
+	struct tun_xdp_hdr *hdr = xdp->data_hard_start;
+	struct virtio_net_hdr *gso = &hdr->gso;
+	struct tun_pcpu_stats *stats;
+	struct bpf_prog *xdp_prog;
+	struct sk_buff *skb = NULL;
+	u32 rxhash = 0, act;
+	int buflen = hdr->buflen;
+	int err = 0;
+	bool skb_xdp = false;
+
+	xdp_prog = rcu_dereference(tun->xdp_prog);
+	if (xdp_prog) {
+		if (gso->gso_type) {
+			skb_xdp = true;
+			goto build;
+		}
+		xdp_set_data_meta_invalid(xdp);
+		xdp->rxq = &tfile->xdp_rxq;
+
+		act = bpf_prog_run_xdp(xdp_prog, xdp);
+		err = tun_xdp_act(tun, xdp_prog, xdp, act);
+		if (err < 0) {
+			put_page(virt_to_head_page(xdp->data));
+			return err;
+		}
+
+		switch (err) {
+		case XDP_REDIRECT:
+			*flush = true;
+			/* fall through */
+		case XDP_TX:
+			return 0;
+		case XDP_PASS:
+			break;
+		default:
+			put_page(virt_to_head_page(xdp->data));
+			return 0;
+		}
+	}
+
+build:
+	skb = build_skb(xdp->data_hard_start, buflen);
+	if (!skb) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	skb_reserve(skb, xdp->data - xdp->data_hard_start);
+	skb_put(skb, xdp->data_end - xdp->data);
+
+	if (virtio_net_hdr_to_skb(skb, gso, tun_is_little_endian(tun))) {
+		this_cpu_inc(tun->pcpu_stats->rx_frame_errors);
+		kfree_skb(skb);
+		err = -EINVAL;
+		goto out;
+	}
+
+	skb->protocol = eth_type_trans(skb, tun->dev);
+	skb_reset_network_header(skb);
+	skb_probe_transport_header(skb, 0);
+
+	if (skb_xdp) {
+		err = do_xdp_generic(xdp_prog, skb);
+		if (err != XDP_PASS)
+			goto out;
+	}
+
+	if (!rcu_dereference(tun->steering_prog))
+		rxhash = __skb_get_hash_symmetric(skb);
+
+	netif_receive_skb(skb);
+
+	stats = get_cpu_ptr(tun->pcpu_stats);
+	u64_stats_update_begin(&stats->syncp);
+	stats->rx_packets++;
+	stats->rx_bytes += skb->len;
+	u64_stats_update_end(&stats->syncp);
+	put_cpu_ptr(stats);
+
+	if (rxhash)
+		tun_flow_update(tun, rxhash, tfile);
+
+out:
+	return err;
+}
+
 static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 {
-	int ret;
+	int ret, i;
 	struct tun_file *tfile = container_of(sock, struct tun_file, socket);
 	struct tun_struct *tun = tun_get(tfile);
 	struct tun_msg_ctl *ctl = m->msg_control;
+	struct xdp_buff *xdp;
 
 	if (!tun)
 		return -EBADFD;
 
-	if (ctl && ctl->type != TUN_MSG_UBUF)
-		return -EINVAL;
+	if (ctl && (ctl->type == TUN_MSG_PTR)) {
+		int n = ctl->num;
+		int flush = 0;
+
+		local_bh_disable();
+		rcu_read_lock();
+
+		for (i = 0; i < n; i++) {
+			xdp = &((struct xdp_buff *)ctl->ptr)[i];
+			tun_xdp_one(tun, tfile, xdp, &flush);
+		}
+
+		if (flush)
+			xdp_do_flush_map();
+
+		rcu_read_unlock();
+		local_bh_enable();
+
+		ret = total_len;
+		goto out;
+	}
 
 	ret = tun_get_user(tun, tfile, ctl ? ctl->ptr : NULL, &m->msg_iter,
 			   m->msg_flags & MSG_DONTWAIT,
 			   m->msg_flags & MSG_MORE);
+out:
 	tun_put(tun);
 	return ret;
 }