1 files changed, 53 insertions, 19 deletions

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 3fa70286c846..9c3acecc14b1 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -25,6 +25,7 @@
 #include <linux/vmalloc.h>
 #include <net/xdp_sock_drv.h>
 #include <net/busy_poll.h>
+#include <net/netdev_lock.h>
 #include <net/netdev_rx_queue.h>
 #include <net/xdp.h>
 
@@ -33,7 +34,7 @@
 #include "xsk.h"
 
 #define TX_BATCH_SIZE 32
-#define MAX_PER_SOCKET_BUDGET (TX_BATCH_SIZE)
+#define MAX_PER_SOCKET_BUDGET 32
 
 void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool)
 {
@@ -299,6 +300,13 @@ static bool xsk_tx_writeable(struct xdp_sock *xs)
 	return true;
 }
 
+static void __xsk_tx_release(struct xdp_sock *xs)
+{
+	__xskq_cons_release(xs->tx);
+	if (xsk_tx_writeable(xs))
+		xs->sk.sk_write_space(&xs->sk);
+}
+
 static bool xsk_is_bound(struct xdp_sock *xs)
 {
 	if (READ_ONCE(xs->state) == XSK_BOUND) {
@@ -322,7 +330,6 @@ static int xsk_rcv_check(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 		return -ENOSPC;
 	}
 
-	sk_mark_napi_id_once_xdp(&xs->sk, xdp);
 	return 0;
 }
 
@@ -338,13 +345,14 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 	u32 len = xdp_get_buff_len(xdp);
 	int err;
 
-	spin_lock_bh(&xs->rx_lock);
 	err = xsk_rcv_check(xs, xdp, len);
 	if (!err) {
+		spin_lock_bh(&xs->pool->rx_lock);
 		err = __xsk_rcv(xs, xdp, len);
 		xsk_flush(xs);
+		spin_unlock_bh(&xs->pool->rx_lock);
 	}
-	spin_unlock_bh(&xs->rx_lock);
+
 	return err;
 }
 
@@ -406,11 +414,8 @@ void xsk_tx_release(struct xsk_buff_pool *pool)
 	struct xdp_sock *xs;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) {
-		__xskq_cons_release(xs->tx);
-		if (xsk_tx_writeable(xs))
-			xs->sk.sk_write_space(&xs->sk);
-	}
+	list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list)
+		__xsk_tx_release(xs);
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL(xsk_tx_release);
@@ -743,6 +748,9 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 						goto free_err;
 				}
 			}
+
+			if (meta->flags & XDP_TXMD_FLAGS_LAUNCH_TIME)
+				skb->skb_mstamp_ns = meta->request.launch_time;
 		}
 	}
 
@@ -775,10 +783,10 @@ free_err:
 static int __xsk_generic_xmit(struct sock *sk)
 {
 	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;
+	u32 max_batch;
 	int err = 0;
 
 	mutex_lock(&xs->mutex);
@@ -792,6 +800,7 @@ static int __xsk_generic_xmit(struct sock *sk)
 	if (xs->queue_id >= xs->dev->real_num_tx_queues)
 		goto out;
 
+	max_batch = READ_ONCE(xs->max_tx_budget);
 	while (xskq_cons_peek_desc(xs->tx, &desc, xs->pool)) {
 		if (max_batch-- == 0) {
 			err = -EAGAIN;
@@ -803,8 +812,11 @@ 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.
 		 */
-		if (xsk_cq_reserve_addr_locked(xs->pool, desc.addr))
+		err = xsk_cq_reserve_addr_locked(xs->pool, desc.addr);
+		if (err) {
+			err = -EAGAIN;
 			goto out;
+		}
 
 		skb = xsk_build_skb(xs, &desc);
 		if (IS_ERR(skb)) {
@@ -851,8 +863,7 @@ static int __xsk_generic_xmit(struct sock *sk)
 
 out:
 	if (sent_frame)
-		if (xsk_tx_writeable(xs))
-			sk->sk_write_space(sk);
+		__xsk_tx_release(xs);
 
 	mutex_unlock(&xs->mutex);
 	return err;
@@ -876,7 +887,7 @@ 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;
+		napi_id_valid(READ_ONCE(sk->sk_napi_id));
 #else
 	return false;
 #endif
@@ -908,11 +919,8 @@ static int __xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len
 	if (unlikely(!xs->tx))
 		return -ENOBUFS;
 
-	if (sk_can_busy_loop(sk)) {
-		if (xs->zc)
-			__sk_mark_napi_id_once(sk, xsk_pool_get_napi_id(xs->pool));
+	if (sk_can_busy_loop(sk))
 		sk_busy_loop(sk, 1); /* only support non-blocking sockets */
-	}
 
 	if (xs->zc && xsk_no_wakeup(sk))
 		return 0;
@@ -1182,6 +1190,8 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 		goto out_release;
 	}
 
+	netdev_lock_ops(dev);
+
 	if (!xs->rx && !xs->tx) {
 		err = -EINVAL;
 		goto out_unlock;
@@ -1298,6 +1308,14 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 	xs->queue_id = qid;
 	xp_add_xsk(xs->pool, xs);
 
+	if (qid < dev->real_num_rx_queues) {
+		struct netdev_rx_queue *rxq;
+
+		rxq = __netif_get_rx_queue(dev, qid);
+		if (rxq->napi)
+			__sk_mark_napi_id_once(sk, rxq->napi->napi_id);
+	}
+
 out_unlock:
 	if (err) {
 		dev_put(dev);
@@ -1308,6 +1326,7 @@ out_unlock:
 		smp_wmb();
 		WRITE_ONCE(xs->state, XSK_BOUND);
 	}
+	netdev_unlock_ops(dev);
 out_release:
 	mutex_unlock(&xs->mutex);
 	rtnl_unlock();
@@ -1422,6 +1441,21 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
 		mutex_unlock(&xs->mutex);
 		return err;
 	}
+	case XDP_MAX_TX_SKB_BUDGET:
+	{
+		unsigned int budget;
+
+		if (optlen != sizeof(budget))
+			return -EINVAL;
+		if (copy_from_sockptr(&budget, optval, sizeof(budget)))
+			return -EFAULT;
+		if (!xs->tx ||
+		    budget < TX_BATCH_SIZE || budget > xs->tx->nentries)
+			return -EACCES;
+
+		WRITE_ONCE(xs->max_tx_budget, budget);
+		return 0;
+	}
 	default:
 		break;
 	}
@@ -1719,8 +1753,8 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol,
 
 	xs = xdp_sk(sk);
 	xs->state = XSK_READY;
+	xs->max_tx_budget = TX_BATCH_SIZE;
 	mutex_init(&xs->mutex);
-	spin_lock_init(&xs->rx_lock);
 
 	INIT_LIST_HEAD(&xs->map_list);
 	spin_lock_init(&xs->map_list_lock);