Merge branch 'vhost_net-batching'

Jason Wang says:

====================
vhost_net tx batching

This series tries to implement tx batching support for vhost. This was
done by using MSG_MORE as a hint for under layer socket. The backend
(e.g tap) can then batch the packets temporarily in a list and
submit it all once the number of bacthed exceeds a limitation.

Tests shows obvious improvement on guest pktgen over over
mlx4(noqueue) on host:

                                     Mpps  -+%
        rx-frames = 0                0.91  +0%
        rx-frames = 4                1.00  +9.8%
        rx-frames = 8                1.00  +9.8%
        rx-frames = 16               1.01  +10.9%
        rx-frames = 32               1.07  +17.5%
        rx-frames = 48               1.07  +17.5%
        rx-frames = 64               1.08  +18.6%
        rx-frames = 64 (no MSG_MORE) 0.91  +0%

Changes from V4:
- stick to NAPI_POLL_WEIGHT for rx-frames is user specify a value
  greater than it.
Changes from V3:
- use ethtool instead of module parameter to control the maximum
  number of batched packets
- avoid overhead when MSG_MORE were not set and no packet queued
Changes from V2:
- remove uselss queue limitation check (and we don't drop any packet now)
Changes from V1:
- drop NAPI handler since we don't use NAPI now
- fix the issues that may exceeds max pending of zerocopy
- more improvement on available buffer detection
- move the limitation of batched pacekts from vhost to tuntap
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/tun.c

@@ -218,6 +218,7 @@ struct tun_struct {
 	struct list_head disabled;
 	void *security;
 	u32 flow_count;
+	u32 rx_batched;
 	struct tun_pcpu_stats __percpu *pcpu_stats;
 };
 
@@ -522,6 +523,7 @@ static void tun_queue_purge(struct tun_file *tfile)
 	while ((skb = skb_array_consume(&tfile->tx_array)) != NULL)
 		kfree_skb(skb);
 
+	skb_queue_purge(&tfile->sk.sk_write_queue);
 	skb_queue_purge(&tfile->sk.sk_error_queue);
 }
 
@@ -1139,10 +1141,46 @@ static struct sk_buff *tun_alloc_skb(struct tun_file *tfile,
 	return skb;
 }
 
+static void tun_rx_batched(struct tun_struct *tun, struct tun_file *tfile,
+			   struct sk_buff *skb, int more)
+{
+	struct sk_buff_head *queue = &tfile->sk.sk_write_queue;
+	struct sk_buff_head process_queue;
+	u32 rx_batched = tun->rx_batched;
+	bool rcv = false;
+
+	if (!rx_batched || (!more && skb_queue_empty(queue))) {
+		local_bh_disable();
+		netif_receive_skb(skb);
+		local_bh_enable();
+		return;
+	}
+
+	spin_lock(&queue->lock);
+	if (!more || skb_queue_len(queue) == rx_batched) {
+		__skb_queue_head_init(&process_queue);
+		skb_queue_splice_tail_init(queue, &process_queue);
+		rcv = true;
+	} else {
+		__skb_queue_tail(queue, skb);
+	}
+	spin_unlock(&queue->lock);
+
+	if (rcv) {
+		struct sk_buff *nskb;
+
+		local_bh_disable();
+		while ((nskb = __skb_dequeue(&process_queue)))
+			netif_receive_skb(nskb);
+		netif_receive_skb(skb);
+		local_bh_enable();
+	}
+}
+
 /* Get packet from user space buffer */
 static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 			    void *msg_control, struct iov_iter *from,
-			    int noblock)
+			    int noblock, bool more)
 {
 	struct tun_pi pi = { 0, cpu_to_be16(ETH_P_IP) };
 	struct sk_buff *skb;
@@ -1283,9 +1321,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 
 	rxhash = skb_get_hash(skb);
 #ifndef CONFIG_4KSTACKS
-	local_bh_disable();
-	netif_receive_skb(skb);
-	local_bh_enable();
+	tun_rx_batched(tun, tfile, skb, more);
 #else
 	netif_rx_ni(skb);
 #endif
@@ -1311,7 +1347,8 @@ static ssize_t tun_chr_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (!tun)
 		return -EBADFD;
 
-	result = tun_get_user(tun, tfile, NULL, from, file->f_flags & O_NONBLOCK);
+	result = tun_get_user(tun, tfile, NULL, from,
+			      file->f_flags & O_NONBLOCK, false);
 
 	tun_put(tun);
 	return result;
@@ -1569,7 +1606,8 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 		return -EBADFD;
 
 	ret = tun_get_user(tun, tfile, m->msg_control, &m->msg_iter,
-			   m->msg_flags & MSG_DONTWAIT);
+			   m->msg_flags & MSG_DONTWAIT,
+			   m->msg_flags & MSG_MORE);
 	tun_put(tun);
 	return ret;
 }
@@ -1770,6 +1808,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 		tun->align = NET_SKB_PAD;
 		tun->filter_attached = false;
 		tun->sndbuf = tfile->socket.sk->sk_sndbuf;
+		tun->rx_batched = 0;
 
 		tun->pcpu_stats = netdev_alloc_pcpu_stats(struct tun_pcpu_stats);
 		if (!tun->pcpu_stats) {
@@ -2438,6 +2477,29 @@ static void tun_set_msglevel(struct net_device *dev, u32 value)
 #endif
 }
 
+static int tun_get_coalesce(struct net_device *dev,
+			    struct ethtool_coalesce *ec)
+{
+	struct tun_struct *tun = netdev_priv(dev);
+
+	ec->rx_max_coalesced_frames = tun->rx_batched;
+
+	return 0;
+}
+
+static int tun_set_coalesce(struct net_device *dev,
+			    struct ethtool_coalesce *ec)
+{
+	struct tun_struct *tun = netdev_priv(dev);
+
+	if (ec->rx_max_coalesced_frames > NAPI_POLL_WEIGHT)
+		tun->rx_batched = NAPI_POLL_WEIGHT;
+	else
+		tun->rx_batched = ec->rx_max_coalesced_frames;
+
+	return 0;
+}
+
 static const struct ethtool_ops tun_ethtool_ops = {
 	.get_settings	= tun_get_settings,
 	.get_drvinfo	= tun_get_drvinfo,
@@ -2445,6 +2507,8 @@ static const struct ethtool_ops tun_ethtool_ops = {
 	.set_msglevel	= tun_set_msglevel,
 	.get_link	= ethtool_op_get_link,
 	.get_ts_info	= ethtool_op_get_ts_info,
+	.get_coalesce   = tun_get_coalesce,
+	.set_coalesce   = tun_set_coalesce,
 };
 
 static int tun_queue_resize(struct tun_struct *tun)

drivers/vhost/net.c

@@ -351,6 +351,15 @@ static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
 	return r;
 }
 
+static bool vhost_exceeds_maxpend(struct vhost_net *net)
+{
+	struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
+	struct vhost_virtqueue *vq = &nvq->vq;
+
+	return (nvq->upend_idx + vq->num - VHOST_MAX_PEND) % UIO_MAXIOV
+		== nvq->done_idx;
+}
+
 /* Expects to be always run from workqueue - which acts as
  * read-size critical section for our kind of RCU. */
 static void handle_tx(struct vhost_net *net)
@@ -394,8 +403,7 @@ static void handle_tx(struct vhost_net *net)
 		/* If more outstanding DMAs, queue the work.
 		 * Handle upend_idx wrap around
 		 */
-		if (unlikely((nvq->upend_idx + vq->num - VHOST_MAX_PEND)
-			      % UIO_MAXIOV == nvq->done_idx))
+		if (unlikely(vhost_exceeds_maxpend(net)))
 			break;
 
 		head = vhost_net_tx_get_vq_desc(net, vq, vq->iov,
@@ -454,6 +462,16 @@ static void handle_tx(struct vhost_net *net)
 			msg.msg_control = NULL;
 			ubufs = NULL;
 		}
+
+		total_len += len;
+		if (total_len < VHOST_NET_WEIGHT &&
+		    !vhost_vq_avail_empty(&net->dev, vq) &&
+		    likely(!vhost_exceeds_maxpend(net))) {
+			msg.msg_flags |= MSG_MORE;
+		} else {
+			msg.msg_flags &= ~MSG_MORE;
+		}
+
 		/* TODO: Check specific error and bomb out unless ENOBUFS? */
 		err = sock->ops->sendmsg(sock, &msg, len);
 		if (unlikely(err < 0)) {
@@ -472,7 +490,6 @@ static void handle_tx(struct vhost_net *net)
 			vhost_add_used_and_signal(&net->dev, vq, head, 0);
 		else
 			vhost_zerocopy_signal_used(net, vq);
-		total_len += len;
 		vhost_net_tx_packet(net);
 		if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
 			vhost_poll_queue(&vq->poll);

drivers/vhost/vhost.c

@@ -2241,11 +2241,15 @@ bool vhost_vq_avail_empty(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 	__virtio16 avail_idx;
 	int r;
 
+	if (vq->avail_idx != vq->last_avail_idx)
+		return false;
+
 	r = vhost_get_user(vq, avail_idx, &vq->avail->idx);
-	if (r)
+	if (unlikely(r))
 		return false;
+	vq->avail_idx = vhost16_to_cpu(vq, avail_idx);
 
-	return vhost16_to_cpu(vq, avail_idx) == vq->avail_idx;
+	return vq->avail_idx == vq->last_avail_idx;
 }
 EXPORT_SYMBOL_GPL(vhost_vq_avail_empty);