veth: Add XDP TX and REDIRECT

This allows further redirection of xdp_frames like

 NIC   -> veth--veth -> veth--veth
 (XDP)          (XDP)         (XDP)

The intermediate XDP, redirecting packets from NIC to the other veth,
reuses xdp_mem_info from NIC so that page recycling of the NIC works on
the destination veth's XDP.
In this way return_frame is not fully guarded by NAPI, since another
NAPI handler on another cpu may use the same xdp_mem_info concurrently.
Thus disable napi_direct by xdp_set_return_frame_no_direct() during the
NAPI context.

v8:
- Don't use xdp_frame pointer address for data_hard_start of xdp_buff.

v4:
- Use xdp_[set|clear]_return_frame_no_direct() instead of a flag in
  xdp_mem_info.

v3:
- Fix double free when veth_xdp_tx() returns a positive value.
- Convert xdp_xmit and xdp_redir variables into flags.
Signed-off-by: NToshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>

drivers/net/veth.c

@@ -32,6 +32,10 @@
 #define VETH_RING_SIZE		256
 #define VETH_XDP_HEADROOM	(XDP_PACKET_HEADROOM + NET_IP_ALIGN)
 
+/* Separating two types of XDP xmit */
+#define VETH_XDP_TX		BIT(0)
+#define VETH_XDP_REDIR		BIT(1)
+
 struct pcpu_vstats {
 	u64			packets;
 	u64			bytes;
@@ -45,6 +49,7 @@ struct veth_priv {
 	struct bpf_prog		*_xdp_prog;
 	struct net_device __rcu	*peer;
 	atomic64_t		dropped;
+	struct xdp_mem_info	xdp_mem;
 	unsigned		requested_headroom;
 	bool			rx_notify_masked;
 	struct ptr_ring		xdp_ring;
@@ -317,12 +322,44 @@ static int veth_xdp_xmit(struct net_device *dev, int n,
 	return n - drops;
 }
 
+static void veth_xdp_flush(struct net_device *dev)
+{
+	struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
+	struct net_device *rcv;
+
+	rcu_read_lock();
+	rcv = rcu_dereference(priv->peer);
+	if (unlikely(!rcv))
+		goto out;
+
+	rcv_priv = netdev_priv(rcv);
+	/* xdp_ring is initialized on receive side? */
+	if (unlikely(!rcu_access_pointer(rcv_priv->xdp_prog)))
+		goto out;
+
+	__veth_xdp_flush(rcv_priv);
+out:
+	rcu_read_unlock();
+}
+
+static int veth_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 veth_xdp_xmit(dev, 1, &frame, 0);
+}
+
 static struct sk_buff *veth_xdp_rcv_one(struct veth_priv *priv,
-					struct xdp_frame *frame)
+					struct xdp_frame *frame,
+					unsigned int *xdp_xmit)
 {
 	void *hard_start = frame->data - frame->headroom;
 	void *head = hard_start - sizeof(struct xdp_frame);
 	int len = frame->len, delta = 0;
+	struct xdp_frame orig_frame;
 	struct bpf_prog *xdp_prog;
 	unsigned int headroom;
 	struct sk_buff *skb;
@@ -346,6 +383,29 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_priv *priv,
 			delta = frame->data - xdp.data;
 			len = xdp.data_end - xdp.data;
 			break;
+		case XDP_TX:
+			orig_frame = *frame;
+			xdp.data_hard_start = head;
+			xdp.rxq->mem = frame->mem;
+			if (unlikely(veth_xdp_tx(priv->dev, &xdp) < 0)) {
+				trace_xdp_exception(priv->dev, xdp_prog, act);
+				frame = &orig_frame;
+				goto err_xdp;
+			}
+			*xdp_xmit |= VETH_XDP_TX;
+			rcu_read_unlock();
+			goto xdp_xmit;
+		case XDP_REDIRECT:
+			orig_frame = *frame;
+			xdp.data_hard_start = head;
+			xdp.rxq->mem = frame->mem;
+			if (xdp_do_redirect(priv->dev, &xdp, xdp_prog)) {
+				frame = &orig_frame;
+				goto err_xdp;
+			}
+			*xdp_xmit |= VETH_XDP_REDIR;
+			rcu_read_unlock();
+			goto xdp_xmit;
 		default:
 			bpf_warn_invalid_xdp_action(act);
 		case XDP_ABORTED:
@@ -370,12 +430,13 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_priv *priv,
 err_xdp:
 	rcu_read_unlock();
 	xdp_return_frame(frame);
-
+xdp_xmit:
 	return NULL;
 }
 
 static struct sk_buff *veth_xdp_rcv_skb(struct veth_priv *priv,
-					struct sk_buff *skb)
+					struct sk_buff *skb,
+					unsigned int *xdp_xmit)
 {
 	u32 pktlen, headroom, act, metalen;
 	void *orig_data, *orig_data_end;
@@ -447,6 +508,26 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_priv *priv,
 	switch (act) {
 	case XDP_PASS:
 		break;
+	case XDP_TX:
+		get_page(virt_to_page(xdp.data));
+		consume_skb(skb);
+		xdp.rxq->mem = priv->xdp_mem;
+		if (unlikely(veth_xdp_tx(priv->dev, &xdp) < 0)) {
+			trace_xdp_exception(priv->dev, xdp_prog, act);
+			goto err_xdp;
+		}
+		*xdp_xmit |= VETH_XDP_TX;
+		rcu_read_unlock();
+		goto xdp_xmit;
+	case XDP_REDIRECT:
+		get_page(virt_to_page(xdp.data));
+		consume_skb(skb);
+		xdp.rxq->mem = priv->xdp_mem;
+		if (xdp_do_redirect(priv->dev, &xdp, xdp_prog))
+			goto err_xdp;
+		*xdp_xmit |= VETH_XDP_REDIR;
+		rcu_read_unlock();
+		goto xdp_xmit;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 	case XDP_ABORTED:
@@ -477,9 +558,15 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_priv *priv,
 	rcu_read_unlock();
 	kfree_skb(skb);
 	return NULL;
+err_xdp:
+	rcu_read_unlock();
+	page_frag_free(xdp.data);
+xdp_xmit:
+	return NULL;
 }
 
-static int veth_xdp_rcv(struct veth_priv *priv, int budget)
+static int veth_xdp_rcv(struct veth_priv *priv, int budget,
+			unsigned int *xdp_xmit)
 {
 	int i, done = 0;
 
@@ -490,10 +577,12 @@ static int veth_xdp_rcv(struct veth_priv *priv, int budget)
 		if (!ptr)
 			break;
 
-		if (veth_is_xdp_frame(ptr))
-			skb = veth_xdp_rcv_one(priv, veth_ptr_to_xdp(ptr));
-		else
-			skb = veth_xdp_rcv_skb(priv, ptr);
+		if (veth_is_xdp_frame(ptr)) {
+			skb = veth_xdp_rcv_one(priv, veth_ptr_to_xdp(ptr),
+					       xdp_xmit);
+		} else {
+			skb = veth_xdp_rcv_skb(priv, ptr, xdp_xmit);
+		}
 
 		if (skb)
 			napi_gro_receive(&priv->xdp_napi, skb);
@@ -508,9 +597,11 @@ static int veth_poll(struct napi_struct *napi, int budget)
 {
 	struct veth_priv *priv =
 		container_of(napi, struct veth_priv, xdp_napi);
+	unsigned int xdp_xmit = 0;
 	int done;
 
-	done = veth_xdp_rcv(priv, budget);
+	xdp_set_return_frame_no_direct();
+	done = veth_xdp_rcv(priv, budget, &xdp_xmit);
 
 	if (done < budget && napi_complete_done(napi, done)) {
 		/* Write rx_notify_masked before reading ptr_ring */
@@ -521,6 +612,12 @@ static int veth_poll(struct napi_struct *napi, int budget)
 		}
 	}
 
+	if (xdp_xmit & VETH_XDP_TX)
+		veth_xdp_flush(priv->dev);
+	if (xdp_xmit & VETH_XDP_REDIR)
+		xdp_do_flush_map();
+	xdp_clear_return_frame_no_direct();
+
 	return done;
 }
 
@@ -567,6 +664,9 @@ static int veth_enable_xdp(struct net_device *dev)
 		err = veth_napi_add(dev);
 		if (err)
 			goto err;
+
+		/* Save original mem info as it can be overwritten */
+		priv->xdp_mem = priv->xdp_rxq.mem;
 	}
 
 	rcu_assign_pointer(priv->xdp_prog, priv->_xdp_prog);
@@ -584,6 +684,7 @@ static void veth_disable_xdp(struct net_device *dev)
 
 	rcu_assign_pointer(priv->xdp_prog, NULL);
 	veth_napi_del(dev);
+	priv->xdp_rxq.mem = priv->xdp_mem;
 	xdp_rxq_info_unreg(&priv->xdp_rxq);
 }