1 files changed, 54 insertions, 14 deletions

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 01251868a9c2..e58a0f1b5c5b 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/netdev_lock.h>
 #include <net/xfrm.h>
 #include <net/xdp.h>
 #include <linux/veth.h>
@@ -306,12 +307,10 @@ static void __veth_xdp_flush(struct veth_rq *rq)
 
 static int veth_xdp_rx(struct veth_rq *rq, struct sk_buff *skb)
 {
-	if (unlikely(ptr_ring_produce(&rq->xdp_ring, skb))) {
-		dev_kfree_skb_any(skb);
-		return NET_RX_DROP;
-	}
+	if (unlikely(ptr_ring_produce(&rq->xdp_ring, skb)))
+		return NETDEV_TX_BUSY; /* signal qdisc layer */
 
-	return NET_RX_SUCCESS;
+	return NET_RX_SUCCESS; /* same as NETDEV_TX_OK */
 }
 
 static int veth_forward_skb(struct net_device *dev, struct sk_buff *skb,
@@ -345,11 +344,11 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
 	struct veth_rq *rq = NULL;
-	int ret = NETDEV_TX_OK;
+	struct netdev_queue *txq;
 	struct net_device *rcv;
 	int length = skb->len;
 	bool use_napi = false;
-	int rxq;
+	int ret, rxq;
 
 	rcu_read_lock();
 	rcv = rcu_dereference(priv->peer);
@@ -372,17 +371,45 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	skb_tx_timestamp(skb);
-	if (likely(veth_forward_skb(rcv, skb, rq, use_napi) == NET_RX_SUCCESS)) {
+
+	ret = veth_forward_skb(rcv, skb, rq, use_napi);
+	switch (ret) {
+	case NET_RX_SUCCESS: /* same as NETDEV_TX_OK */
 		if (!use_napi)
 			dev_sw_netstats_tx_add(dev, 1, length);
 		else
 			__veth_xdp_flush(rq);
-	} else {
+		break;
+	case NETDEV_TX_BUSY:
+		/* If a qdisc is attached to our virtual device, returning
+		 * NETDEV_TX_BUSY is allowed.
+		 */
+		txq = netdev_get_tx_queue(dev, rxq);
+
+		if (qdisc_txq_has_no_queue(txq)) {
+			dev_kfree_skb_any(skb);
+			goto drop;
+		}
+		/* Restore Eth hdr pulled by dev_forward_skb/eth_type_trans */
+		__skb_push(skb, ETH_HLEN);
+		/* Depend on prior success packets started NAPI consumer via
+		 * __veth_xdp_flush(). Cancel TXQ stop if consumer stopped,
+		 * paired with empty check in veth_poll().
+		 */
+		netif_tx_stop_queue(txq);
+		smp_mb__after_atomic();
+		if (unlikely(__ptr_ring_empty(&rq->xdp_ring)))
+			netif_tx_wake_queue(txq);
+		break;
+	case NET_RX_DROP: /* same as NET_XMIT_DROP */
 drop:
 		atomic64_inc(&priv->dropped);
 		ret = NET_XMIT_DROP;
+		break;
+	default:
+		net_crit_ratelimited("%s(%s): Invalid return code(%d)",
+				     __func__, dev->name, ret);
 	}
-
 	rcu_read_unlock();
 
 	return ret;
@@ -684,8 +711,7 @@ static void veth_xdp_rcv_bulk_skb(struct veth_rq *rq, void **frames,
 	void *skbs[VETH_XDP_BATCH];
 	int i;
 
-	if (xdp_alloc_skb_bulk(skbs, n_xdpf,
-			       GFP_ATOMIC | __GFP_ZERO) < 0) {
+	if (unlikely(!napi_skb_cache_get_bulk(skbs, n_xdpf))) {
 		for (i = 0; i < n_xdpf; i++)
 			xdp_return_frame(frames[i]);
 		stats->rx_drops += n_xdpf;
@@ -874,9 +900,17 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget,
 			struct veth_xdp_tx_bq *bq,
 			struct veth_stats *stats)
 {
+	struct veth_priv *priv = netdev_priv(rq->dev);
+	int queue_idx = rq->xdp_rxq.queue_index;
+	struct netdev_queue *peer_txq;
+	struct net_device *peer_dev;
 	int i, done = 0, n_xdpf = 0;
 	void *xdpf[VETH_XDP_BATCH];
 
+	/* NAPI functions as RCU section */
+	peer_dev = rcu_dereference_check(priv->peer, rcu_read_lock_bh_held());
+	peer_txq = netdev_get_tx_queue(peer_dev, queue_idx);
+
 	for (i = 0; i < budget; i++) {
 		void *ptr = __ptr_ring_consume(&rq->xdp_ring);
 
@@ -925,6 +959,9 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget,
 	rq->stats.vs.xdp_packets += done;
 	u64_stats_update_end(&rq->stats.syncp);
 
+	if (unlikely(netif_tx_queue_stopped(peer_txq)))
+		netif_tx_wake_queue(peer_txq);
+
 	return done;
 }
 
@@ -1765,10 +1802,13 @@ static int veth_init_queues(struct net_device *dev, struct nlattr *tb[])
 	return 0;
 }
 
-static int veth_newlink(struct net *peer_net, struct net_device *dev,
-			struct nlattr *tb[], struct nlattr *data[],
+static int veth_newlink(struct net_device *dev,
+			struct rtnl_newlink_params *params,
 			struct netlink_ext_ack *extack)
 {
+	struct net *peer_net = rtnl_newlink_peer_net(params);
+	struct nlattr **data = params->data;
+	struct nlattr **tb = params->tb;
 	int err;
 	struct net_device *peer;
 	struct veth_priv *priv;