2 files changed, 68 insertions, 21 deletions

diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 16d5f353163a..3049af269fbf 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -27,6 +27,9 @@ void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
 {
 	unsigned long flags;
 
+	if (!xs->tx)
+		return;
+
 	spin_lock_irqsave(&umem->xsk_list_lock, flags);
 	list_add_rcu(&xs->list, &umem->xsk_list);
 	spin_unlock_irqrestore(&umem->xsk_list_lock, flags);
@@ -36,6 +39,9 @@ void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
 {
 	unsigned long flags;
 
+	if (!xs->tx)
+		return;
+
 	spin_lock_irqsave(&umem->xsk_list_lock, flags);
 	list_del_rcu(&xs->list);
 	spin_unlock_irqrestore(&umem->xsk_list_lock, flags);
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index fa8fbb8fa3c8..956793893c9d 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -196,7 +196,7 @@ static bool xsk_is_bound(struct xdp_sock *xs)
 	return false;
 }
 
-int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
+static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 {
 	u32 len;
 
@@ -212,7 +212,7 @@ int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 		__xsk_rcv_zc(xs, xdp, len) : __xsk_rcv(xs, xdp, len);
 }
 
-void xsk_flush(struct xdp_sock *xs)
+static void xsk_flush(struct xdp_sock *xs)
 {
 	xskq_produce_flush_desc(xs->rx);
 	xs->sk.sk_data_ready(&xs->sk);
@@ -264,6 +264,35 @@ out_unlock:
 	return err;
 }
 
+int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
+		       struct xdp_sock *xs)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	struct list_head *flush_list = this_cpu_ptr(m->flush_list);
+	int err;
+
+	err = xsk_rcv(xs, xdp);
+	if (err)
+		return err;
+
+	if (!xs->flush_node.prev)
+		list_add(&xs->flush_node, flush_list);
+
+	return 0;
+}
+
+void __xsk_map_flush(struct bpf_map *map)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	struct list_head *flush_list = this_cpu_ptr(m->flush_list);
+	struct xdp_sock *xs, *tmp;
+
+	list_for_each_entry_safe(xs, tmp, flush_list, flush_node) {
+		xsk_flush(xs);
+		__list_del_clearprev(&xs->flush_node);
+	}
+}
+
 void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries)
 {
 	xskq_produce_flush_addr_n(umem->cq, nb_entries);
@@ -305,9 +334,8 @@ out:
 }
 EXPORT_SYMBOL(xsk_umem_consume_tx);
 
-static int xsk_zc_xmit(struct sock *sk)
+static int xsk_zc_xmit(struct xdp_sock *xs)
 {
-	struct xdp_sock *xs = xdp_sk(sk);
 	struct net_device *dev = xs->dev;
 
 	return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id,
@@ -327,11 +355,10 @@ static void xsk_destruct_skb(struct sk_buff *skb)
 	sock_wfree(skb);
 }
 
-static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
-			    size_t total_len)
+static int xsk_generic_xmit(struct sock *sk)
 {
-	u32 max_batch = TX_BATCH_SIZE;
 	struct xdp_sock *xs = xdp_sk(sk);
+	u32 max_batch = TX_BATCH_SIZE;
 	bool sent_frame = false;
 	struct xdp_desc desc;
 	struct sk_buff *skb;
@@ -394,6 +421,18 @@ out:
 	return err;
 }
 
+static int __xsk_sendmsg(struct sock *sk)
+{
+	struct xdp_sock *xs = xdp_sk(sk);
+
+	if (unlikely(!(xs->dev->flags & IFF_UP)))
+		return -ENETDOWN;
+	if (unlikely(!xs->tx))
+		return -ENOBUFS;
+
+	return xs->zc ? xsk_zc_xmit(xs) : xsk_generic_xmit(sk);
+}
+
 static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 {
 	bool need_wait = !(m->msg_flags & MSG_DONTWAIT);
@@ -402,21 +441,18 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 
 	if (unlikely(!xsk_is_bound(xs)))
 		return -ENXIO;
-	if (unlikely(!(xs->dev->flags & IFF_UP)))
-		return -ENETDOWN;
-	if (unlikely(!xs->tx))
-		return -ENOBUFS;
-	if (need_wait)
+	if (unlikely(need_wait))
 		return -EOPNOTSUPP;
 
-	return (xs->zc) ? xsk_zc_xmit(sk) : xsk_generic_xmit(sk, m, total_len);
+	return __xsk_sendmsg(sk);
 }
 
-static unsigned int xsk_poll(struct file *file, struct socket *sock,
+static __poll_t xsk_poll(struct file *file, struct socket *sock,
 			     struct poll_table_struct *wait)
 {
-	unsigned int mask = datagram_poll(file, sock, wait);
-	struct xdp_sock *xs = xdp_sk(sock->sk);
+	__poll_t mask = datagram_poll(file, sock, wait);
+	struct sock *sk = sock->sk;
+	struct xdp_sock *xs = xdp_sk(sk);
 	struct net_device *dev;
 	struct xdp_umem *umem;
 
@@ -426,14 +462,19 @@ static unsigned int xsk_poll(struct file *file, struct socket *sock,
 	dev = xs->dev;
 	umem = xs->umem;
 
-	if (umem->need_wakeup)
-		dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id,
-						umem->need_wakeup);
+	if (umem->need_wakeup) {
+		if (dev->netdev_ops->ndo_xsk_wakeup)
+			dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id,
+							umem->need_wakeup);
+		else
+			/* Poll needs to drive Tx also in copy mode */
+			__xsk_sendmsg(sk);
+	}
 
 	if (xs->rx && !xskq_empty_desc(xs->rx))
-		mask |= POLLIN | POLLRDNORM;
+		mask |= EPOLLIN | EPOLLRDNORM;
 	if (xs->tx && !xskq_full_desc(xs->tx))
-		mask |= POLLOUT | POLLWRNORM;
+		mask |= EPOLLOUT | EPOLLWRNORM;
 
 	return mask;
 }