xsk: change the tx writeable condition

Modify the tx writeable condition from the queue is not full to the
number of remaining tx queues is less than the half of the total number
of queues. Because the tx queue not full is a very short time, this will
cause a large number of EPOLLOUT events, and cause a large number of
process wake up.

Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>

Author: fengidri

net/xdp/xsk.c

@@ -211,6 +211,17 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len,
 	return 0;
 }
 
+static bool xsk_writeable(struct xdp_sock *xs)
+{
+	if (!xs->tx)
+		return false;
+
+	if (xskq_cons_left(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) {
@@ -296,7 +307,8 @@ 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_writeable(xs))
+			xs->sk.sk_write_space(&xs->sk);
 	}
 	rcu_read_unlock();
 }
@@ -442,7 +454,8 @@ static int xsk_generic_xmit(struct sock *sk)
 
 out:
 	if (sent_frame)
-		sk->sk_write_space(sk);
+		if (xsk_writeable(xs))
+			sk->sk_write_space(sk);
 
 	mutex_unlock(&xs->mutex);
 	return err;
@@ -499,7 +512,8 @@ 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 (xsk_writeable(xs))
 		mask |= EPOLLOUT | EPOLLWRNORM;
 
 	return mask;

net/xdp/xsk_queue.h

@@ -264,6 +264,12 @@ static inline bool xskq_cons_is_full(struct xsk_queue *q)
 		q->nentries;
 }
 
+static inline __u64 xskq_cons_left(struct xsk_queue *q)
+{
+	/* No barriers needed since data is not accessed */
+	return READ_ONCE(q->ring->producer) - READ_ONCE(q->ring->consumer);
+}
+
 /* Functions for producers */
 
 static inline bool xskq_prod_is_full(struct xsk_queue *q)