1 files changed, 139 insertions, 11 deletions

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index b7b039bd9d03..8037b04a9edd 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -23,6 +23,7 @@
 #include <linux/netdevice.h>
 #include <linux/rculist.h>
 #include <net/xdp_sock_drv.h>
+#include <net/busy_poll.h>
 #include <net/xdp.h>
 
 #include "xsk_queue.h"
@@ -211,6 +212,14 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len,
 	return 0;
 }
 
+static bool xsk_tx_writeable(struct xdp_sock *xs)
+{
+	if (xskq_cons_present_entries(xs->tx) > xs->tx->nentries / 2)
+		return false;
+
+	return true;
+}
+
 static bool xsk_is_bound(struct xdp_sock *xs)
 {
 	if (READ_ONCE(xs->state) == XSK_BOUND) {
@@ -232,6 +241,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp,
 	if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
 		return -EINVAL;
 
+	sk_mark_napi_id_once_xdp(&xs->sk, xdp);
 	len = xdp->data_end - xdp->data;
 
 	return xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL ?
@@ -296,7 +306,8 @@ void xsk_tx_release(struct xsk_buff_pool *pool)
 	rcu_read_lock();
 	list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) {
 		__xskq_cons_release(xs->tx);
-		xs->sk.sk_write_space(&xs->sk);
+		if (xsk_tx_writeable(xs))
+			xs->sk.sk_write_space(&xs->sk);
 	}
 	rcu_read_unlock();
 }
@@ -332,6 +343,63 @@ out:
 }
 EXPORT_SYMBOL(xsk_tx_peek_desc);
 
+static u32 xsk_tx_peek_release_fallback(struct xsk_buff_pool *pool, struct xdp_desc *descs,
+					u32 max_entries)
+{
+	u32 nb_pkts = 0;
+
+	while (nb_pkts < max_entries && xsk_tx_peek_desc(pool, &descs[nb_pkts]))
+		nb_pkts++;
+
+	xsk_tx_release(pool);
+	return nb_pkts;
+}
+
+u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, struct xdp_desc *descs,
+				   u32 max_entries)
+{
+	struct xdp_sock *xs;
+	u32 nb_pkts;
+
+	rcu_read_lock();
+	if (!list_is_singular(&pool->xsk_tx_list)) {
+		/* Fallback to the non-batched version */
+		rcu_read_unlock();
+		return xsk_tx_peek_release_fallback(pool, descs, max_entries);
+	}
+
+	xs = list_first_or_null_rcu(&pool->xsk_tx_list, struct xdp_sock, tx_list);
+	if (!xs) {
+		nb_pkts = 0;
+		goto out;
+	}
+
+	nb_pkts = xskq_cons_peek_desc_batch(xs->tx, descs, pool, max_entries);
+	if (!nb_pkts) {
+		xs->tx->queue_empty_descs++;
+		goto out;
+	}
+
+	/* This is the backpressure mechanism for the Tx path. Try to
+	 * reserve space in the completion queue for all packets, but
+	 * if there are fewer slots available, just process that many
+	 * packets. This avoids having to implement any buffering in
+	 * the Tx path.
+	 */
+	nb_pkts = xskq_prod_reserve_addr_batch(pool->cq, descs, nb_pkts);
+	if (!nb_pkts)
+		goto out;
+
+	xskq_cons_release_n(xs->tx, nb_pkts);
+	__xskq_cons_release(xs->tx);
+	xs->sk.sk_write_space(&xs->sk);
+
+out:
+	rcu_read_unlock();
+	return nb_pkts;
+}
+EXPORT_SYMBOL(xsk_tx_peek_release_desc_batch);
+
 static int xsk_wakeup(struct xdp_sock *xs, u8 flags)
 {
 	struct net_device *dev = xs->dev;
@@ -355,9 +423,9 @@ static void xsk_destruct_skb(struct sk_buff *skb)
 	struct xdp_sock *xs = xdp_sk(skb->sk);
 	unsigned long flags;
 
-	spin_lock_irqsave(&xs->tx_completion_lock, flags);
+	spin_lock_irqsave(&xs->pool->cq_lock, flags);
 	xskq_prod_submit_addr(xs->pool->cq, addr);
-	spin_unlock_irqrestore(&xs->tx_completion_lock, flags);
+	spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
 
 	sock_wfree(skb);
 }
@@ -369,6 +437,7 @@ static int xsk_generic_xmit(struct sock *sk)
 	bool sent_frame = false;
 	struct xdp_desc desc;
 	struct sk_buff *skb;
+	unsigned long flags;
 	int err = 0;
 
 	mutex_lock(&xs->mutex);
@@ -400,10 +469,13 @@ static int xsk_generic_xmit(struct sock *sk)
 		 * if there is space in it. This avoids having to implement
 		 * any buffering in the Tx path.
 		 */
+		spin_lock_irqsave(&xs->pool->cq_lock, flags);
 		if (unlikely(err) || xskq_prod_reserve(xs->pool->cq)) {
+			spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
 			kfree_skb(skb);
 			goto out;
 		}
+		spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
 
 		skb->dev = xs->dev;
 		skb->priority = sk->sk_priority;
@@ -415,6 +487,9 @@ static int xsk_generic_xmit(struct sock *sk)
 		if  (err == NETDEV_TX_BUSY) {
 			/* Tell user-space to retry the send */
 			skb->destructor = sock_wfree;
+			spin_lock_irqsave(&xs->pool->cq_lock, flags);
+			xskq_prod_cancel(xs->pool->cq);
+			spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
 			/* Free skb without triggering the perf drop trace */
 			consume_skb(skb);
 			err = -EAGAIN;
@@ -436,7 +511,8 @@ static int xsk_generic_xmit(struct sock *sk)
 
 out:
 	if (sent_frame)
-		sk->sk_write_space(sk);
+		if (xsk_tx_writeable(xs))
+			sk->sk_write_space(sk);
 
 	mutex_unlock(&xs->mutex);
 	return err;
@@ -454,28 +530,77 @@ static int __xsk_sendmsg(struct sock *sk)
 	return xs->zc ? xsk_zc_xmit(xs) : xsk_generic_xmit(sk);
 }
 
+static bool xsk_no_wakeup(struct sock *sk)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	/* Prefer busy-polling, skip the wakeup. */
+	return READ_ONCE(sk->sk_prefer_busy_poll) && READ_ONCE(sk->sk_ll_usec) &&
+		READ_ONCE(sk->sk_napi_id) >= MIN_NAPI_ID;
+#else
+	return false;
+#endif
+}
+
 static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 {
 	bool need_wait = !(m->msg_flags & MSG_DONTWAIT);
 	struct sock *sk = sock->sk;
 	struct xdp_sock *xs = xdp_sk(sk);
+	struct xsk_buff_pool *pool;
 
 	if (unlikely(!xsk_is_bound(xs)))
 		return -ENXIO;
 	if (unlikely(need_wait))
 		return -EOPNOTSUPP;
 
-	return __xsk_sendmsg(sk);
+	if (sk_can_busy_loop(sk))
+		sk_busy_loop(sk, 1); /* only support non-blocking sockets */
+
+	if (xsk_no_wakeup(sk))
+		return 0;
+
+	pool = xs->pool;
+	if (pool->cached_need_wakeup & XDP_WAKEUP_TX)
+		return __xsk_sendmsg(sk);
+	return 0;
+}
+
+static int xsk_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int flags)
+{
+	bool need_wait = !(flags & MSG_DONTWAIT);
+	struct sock *sk = sock->sk;
+	struct xdp_sock *xs = xdp_sk(sk);
+
+	if (unlikely(!xsk_is_bound(xs)))
+		return -ENXIO;
+	if (unlikely(!(xs->dev->flags & IFF_UP)))
+		return -ENETDOWN;
+	if (unlikely(!xs->rx))
+		return -ENOBUFS;
+	if (unlikely(need_wait))
+		return -EOPNOTSUPP;
+
+	if (sk_can_busy_loop(sk))
+		sk_busy_loop(sk, 1); /* only support non-blocking sockets */
+
+	if (xsk_no_wakeup(sk))
+		return 0;
+
+	if (xs->pool->cached_need_wakeup & XDP_WAKEUP_RX && xs->zc)
+		return xsk_wakeup(xs, XDP_WAKEUP_RX);
+	return 0;
 }
 
 static __poll_t xsk_poll(struct file *file, struct socket *sock,
 			     struct poll_table_struct *wait)
 {
-	__poll_t mask = datagram_poll(file, sock, wait);
+	__poll_t mask = 0;
 	struct sock *sk = sock->sk;
 	struct xdp_sock *xs = xdp_sk(sk);
 	struct xsk_buff_pool *pool;
 
+	sock_poll_wait(file, sock, wait);
+
 	if (unlikely(!xsk_is_bound(xs)))
 		return mask;
 
@@ -491,7 +616,7 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock,
 
 	if (xs->rx && !xskq_prod_is_empty(xs->rx))
 		mask |= EPOLLIN | EPOLLRDNORM;
-	if (xs->tx && !xskq_cons_is_full(xs->tx))
+	if (xs->tx && xsk_tx_writeable(xs))
 		mask |= EPOLLOUT | EPOLLWRNORM;
 
 	return mask;
@@ -542,7 +667,7 @@ static struct xsk_map *xsk_get_map_list_entry(struct xdp_sock *xs,
 	node = list_first_entry_or_null(&xs->map_list, struct xsk_map_node,
 					node);
 	if (node) {
-		WARN_ON(xsk_map_inc(node->map));
+		bpf_map_inc(&node->map->map);
 		map = node->map;
 		*map_entry = node->map_entry;
 	}
@@ -572,7 +697,7 @@ static void xsk_delete_from_maps(struct xdp_sock *xs)
 
 	while ((map = xsk_get_map_list_entry(xs, &map_entry))) {
 		xsk_map_try_sock_delete(map, xs, map_entry);
-		xsk_map_put(map);
+		bpf_map_put(&map->map);
 	}
 }
 
@@ -760,6 +885,10 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 		}
 	}
 
+	/* FQ and CQ are now owned by the buffer pool and cleaned up with it. */
+	xs->fq_tmp = NULL;
+	xs->cq_tmp = NULL;
+
 	xs->dev = dev;
 	xs->zc = xs->umem->zc;
 	xs->queue_id = qid;
@@ -1128,7 +1257,7 @@ static const struct proto_ops xsk_proto_ops = {
 	.setsockopt	= xsk_setsockopt,
 	.getsockopt	= xsk_getsockopt,
 	.sendmsg	= xsk_sendmsg,
-	.recvmsg	= sock_no_recvmsg,
+	.recvmsg	= xsk_recvmsg,
 	.mmap		= xsk_mmap,
 	.sendpage	= sock_no_sendpage,
 };
@@ -1181,7 +1310,6 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol,
 	xs->state = XSK_READY;
 	mutex_init(&xs->mutex);
 	spin_lock_init(&xs->rx_lock);
-	spin_lock_init(&xs->tx_completion_lock);
 
 	INIT_LIST_HEAD(&xs->map_list);
 	spin_lock_init(&xs->map_list_lock);