tun: switch to use skb array for tx

We used to queue tx packets in sk_receive_queue, this is less
efficient since it requires spinlocks to synchronize between producer
and consumer.

This patch tries to address this by:

- switch from sk_receive_queue to a skb_array, and resize it when
  tx_queue_len was changed.
- introduce a new proto_ops peek_len which was used for peeking the
  skb length.
- implement a tun version of peek_len for vhost_net to use and convert
  vhost_net to use peek_len if possible.

Pktgen test shows about 15.3% improvement on guest receiving pps for small
buffers:

Before: ~1300000pps
After : ~1500000pps

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/tun.c

@@ -71,6 +71,7 @@
 #include <net/sock.h>
 #include <linux/seq_file.h>
 #include <linux/uio.h>
+#include <linux/skb_array.h>
 
 #include <asm/uaccess.h>
 
@@ -167,6 +168,7 @@ struct tun_file {
 	};
 	struct list_head next;
 	struct tun_struct *detached;
+	struct skb_array tx_array;
 };
 
 struct tun_flow_entry {
@@ -515,7 +517,11 @@ static struct tun_struct *tun_enable_queue(struct tun_file *tfile)
 
 static void tun_queue_purge(struct tun_file *tfile)
 {
-	skb_queue_purge(&tfile->sk.sk_receive_queue);
+	struct sk_buff *skb;
+
+	while ((skb = skb_array_consume(&tfile->tx_array)) != NULL)
+		kfree_skb(skb);
+
 	skb_queue_purge(&tfile->sk.sk_error_queue);
 }
 
@@ -560,6 +566,8 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 			    tun->dev->reg_state == NETREG_REGISTERED)
 				unregister_netdevice(tun->dev);
 		}
+		if (tun)
+			skb_array_cleanup(&tfile->tx_array);
 		sock_put(&tfile->sk);
 	}
 }
@@ -613,6 +621,7 @@ static void tun_detach_all(struct net_device *dev)
 static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filter)
 {
 	struct tun_file *tfile = file->private_data;
+	struct net_device *dev = tun->dev;
 	int err;
 
 	err = security_tun_dev_attach(tfile->socket.sk, tun->security);
@@ -642,6 +651,13 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte
 		if (!err)
 			goto out;
 	}
+
+	if (!tfile->detached &&
+	    skb_array_init(&tfile->tx_array, dev->tx_queue_len, GFP_KERNEL)) {
+		err = -ENOMEM;
+		goto out;
+	}
+
 	tfile->queue_index = tun->numqueues;
 	tfile->socket.sk->sk_shutdown &= ~RCV_SHUTDOWN;
 	rcu_assign_pointer(tfile->tun, tun);
@@ -891,8 +907,8 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	nf_reset(skb);
 
-	/* Enqueue packet */
+	if (skb_array_produce(&tfile->tx_array, skb))
-	skb_queue_tail(&tfile->socket.sk->sk_receive_queue, skb);
+		goto drop;
 
 	/* Notify and wake up reader process */
 	if (tfile->flags & TUN_FASYNC)
@@ -1107,7 +1123,7 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait)
 
 	poll_wait(file, sk_sleep(sk), wait);
 
-	if (!skb_queue_empty(&sk->sk_receive_queue))
+	if (!skb_array_empty(&tfile->tx_array))
 		mask |= POLLIN | POLLRDNORM;
 
 	if (sock_writeable(sk) ||
@@ -1426,22 +1442,61 @@ done:
 	return total;
 }
 
+static struct sk_buff *tun_ring_recv(struct tun_file *tfile, int noblock,
+				     int *err)
+{
+	DECLARE_WAITQUEUE(wait, current);
+	struct sk_buff *skb = NULL;
+
+	skb = skb_array_consume(&tfile->tx_array);
+	if (skb)
+		goto out;
+	if (noblock) {
+		*err = -EAGAIN;
+		goto out;
+	}
+
+	add_wait_queue(&tfile->wq.wait, &wait);
+	current->state = TASK_INTERRUPTIBLE;
+
+	while (1) {
+		skb = skb_array_consume(&tfile->tx_array);
+		if (skb)
+			break;
+		if (signal_pending(current)) {
+			*err = -ERESTARTSYS;
+			break;
+		}
+		if (tfile->socket.sk->sk_shutdown & RCV_SHUTDOWN) {
+			*err = -EFAULT;
+			break;
+		}
+
+		schedule();
+	}
+
+	current->state = TASK_RUNNING;
+	remove_wait_queue(&tfile->wq.wait, &wait);
+
+out:
+	return skb;
+}
+
 static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile,
 			   struct iov_iter *to,
 			   int noblock)
 {
 	struct sk_buff *skb;
 	ssize_t ret;
-	int peeked, err, off = 0;
+	int err;
 
 	tun_debug(KERN_INFO, tun, "tun_do_read\n");
 
 	if (!iov_iter_count(to))
 		return 0;
 
-	/* Read frames from queue */
+	/* Read frames from ring */
-	skb = __skb_recv_datagram(tfile->socket.sk, noblock ? MSG_DONTWAIT : 0,
+	skb = tun_ring_recv(tfile, noblock, &err);
-				  &peeked, &off, &err);
 	if (!skb)
 		return err;
 
@@ -1574,8 +1629,25 @@ out:
 	return ret;
 }
 
+static int tun_peek_len(struct socket *sock)
+{
+	struct tun_file *tfile = container_of(sock, struct tun_file, socket);
+	struct tun_struct *tun;
+	int ret = 0;
+
+	tun = __tun_get(tfile);
+	if (!tun)
+		return 0;
+
+	ret = skb_array_peek_len(&tfile->tx_array);
+	tun_put(tun);
+
+	return ret;
+}
+
 /* Ops structure to mimic raw sockets with tun */
 static const struct proto_ops tun_socket_ops = {
+	.peek_len = tun_peek_len,
 	.sendmsg = tun_sendmsg,
 	.recvmsg = tun_recvmsg,
 };
@@ -2397,6 +2469,53 @@ static const struct ethtool_ops tun_ethtool_ops = {
 	.get_ts_info	= ethtool_op_get_ts_info,
 };
 
+static int tun_queue_resize(struct tun_struct *tun)
+{
+	struct net_device *dev = tun->dev;
+	struct tun_file *tfile;
+	struct skb_array **arrays;
+	int n = tun->numqueues + tun->numdisabled;
+	int ret, i;
+
+	arrays = kmalloc(sizeof *arrays * n, GFP_KERNEL);
+	if (!arrays)
+		return -ENOMEM;
+
+	for (i = 0; i < tun->numqueues; i++) {
+		tfile = rtnl_dereference(tun->tfiles[i]);
+		arrays[i] = &tfile->tx_array;
+	}
+	list_for_each_entry(tfile, &tun->disabled, next)
+		arrays[i++] = &tfile->tx_array;
+
+	ret = skb_array_resize_multiple(arrays, n,
+					dev->tx_queue_len, GFP_KERNEL);
+
+	kfree(arrays);
+	return ret;
+}
+
+static int tun_device_event(struct notifier_block *unused,
+			    unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct tun_struct *tun = netdev_priv(dev);
+
+	switch (event) {
+	case NETDEV_CHANGE_TX_QUEUE_LEN:
+		if (tun_queue_resize(tun))
+			return NOTIFY_BAD;
+		break;
+	default:
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block tun_notifier_block __read_mostly = {
+	.notifier_call	= tun_device_event,
+};
 
 static int __init tun_init(void)
 {
@@ -2416,6 +2535,8 @@ static int __init tun_init(void)
 		pr_err("Can't register misc device %d\n", TUN_MINOR);
 		goto err_misc;
 	}
+
+	register_netdevice_notifier(&tun_notifier_block);
 	return  0;
 err_misc:
 	rtnl_link_unregister(&tun_link_ops);
@@ -2427,6 +2548,7 @@ static void tun_cleanup(void)
 {
 	misc_deregister(&tun_miscdev);
 	rtnl_link_unregister(&tun_link_ops);
+	unregister_netdevice_notifier(&tun_notifier_block);
 }
 
 /* Get an underlying socket object from tun file.  Returns error unless file is

drivers/vhost/net.c

@@ -481,10 +481,14 @@ out:
 
 static int peek_head_len(struct sock *sk)
 {
+	struct socket *sock = sk->sk_socket;
 	struct sk_buff *head;
 	int len = 0;
 	unsigned long flags;
 
+	if (sock->ops->peek_len)
+		return sock->ops->peek_len(sock);
+
 	spin_lock_irqsave(&sk->sk_receive_queue.lock, flags);
 	head = skb_peek(&sk->sk_receive_queue);
 	if (likely(head)) {
@@ -497,6 +501,16 @@ static int peek_head_len(struct sock *sk)
 	return len;
 }
 
+static int sk_has_rx_data(struct sock *sk)
+{
+	struct socket *sock = sk->sk_socket;
+
+	if (sock->ops->peek_len)
+		return sock->ops->peek_len(sock);
+
+	return skb_queue_empty(&sk->sk_receive_queue);
+}
+
 static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
 {
 	struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
@@ -513,7 +527,7 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
 		endtime = busy_clock() + vq->busyloop_timeout;
 
 		while (vhost_can_busy_poll(&net->dev, endtime) &&
-		       skb_queue_empty(&sk->sk_receive_queue) &&
+		       !sk_has_rx_data(sk) &&
 		       vhost_vq_avail_empty(&net->dev, vq))
 			cpu_relax_lowlatency();
 

include/linux/net.h

@@ -185,6 +185,7 @@ struct proto_ops {
 	ssize_t 	(*splice_read)(struct socket *sock,  loff_t *ppos,
 				       struct pipe_inode_info *pipe, size_t len, unsigned int flags);
 	int		(*set_peek_off)(struct sock *sk, int val);
+	int		(*peek_len)(struct socket *sock);
 };
 
 #define DECLARE_SOCKADDR(type, dst, src)	\