net: Remove ndo_xmit_flush netdev operation, use signalling instead.

As reported by Jesper Dangaard Brouer, for high packet rates the
overhead of having another indirect call in the TX path is
non-trivial.

There is the indirect call itself, and then there is all of the
reloading of the state to refetch the tail pointer value and
then write the device register.

Move to a more passive scheme, which requires very light modifications
to the device drivers.

The signal is a new skb->xmit_more value, if it is non-zero it means
that more SKBs are pending to be transmitted on the same queue as the
current SKB.  And therefore, the driver may elide the tail pointer
update.

Right now skb->xmit_more is always zero.

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 15 insertions, 33 deletions

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index b9c020a05fb8..89c29b40d61c 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -136,7 +136,6 @@ static void igb_update_phy_info(unsigned long);
 static void igb_watchdog(unsigned long);
 static void igb_watchdog_task(struct work_struct *);
 static netdev_tx_t igb_xmit_frame(struct sk_buff *skb, struct net_device *);
-static void igb_xmit_flush(struct net_device *netdev, u16 queue);
 static struct rtnl_link_stats64 *igb_get_stats64(struct net_device *dev,
 					  struct rtnl_link_stats64 *stats);
 static int igb_change_mtu(struct net_device *, int);
@@ -2076,7 +2075,6 @@ static const struct net_device_ops igb_netdev_ops = {
 	.ndo_open		= igb_open,
 	.ndo_stop		= igb_close,
 	.ndo_start_xmit		= igb_xmit_frame,
-	.ndo_xmit_flush		= igb_xmit_flush,
 	.ndo_get_stats64	= igb_get_stats64,
 	.ndo_set_rx_mode	= igb_set_rx_mode,
 	.ndo_set_mac_address	= igb_set_mac,
@@ -4917,6 +4915,14 @@ static void igb_tx_map(struct igb_ring *tx_ring,
 
 	tx_ring->next_to_use = i;
 
+	if (!skb->xmit_more) {
+		writel(i, tx_ring->tail);
+
+		/* we need this if more than one processor can write to our tail
+		 * at a time, it synchronizes IO on IA64/Altix systems
+		 */
+		mmiowb();
+	}
 	return;
 
 dma_error:
@@ -5052,20 +5058,17 @@ out_drop:
 	return NETDEV_TX_OK;
 }
 
-static struct igb_ring *__igb_tx_queue_mapping(struct igb_adapter *adapter, unsigned int r_idx)
+static inline struct igb_ring *igb_tx_queue_mapping(struct igb_adapter *adapter,
+						    struct sk_buff *skb)
 {
+	unsigned int r_idx = skb->queue_mapping;
+
 	if (r_idx >= adapter->num_tx_queues)
 		r_idx = r_idx % adapter->num_tx_queues;
 
 	return adapter->tx_ring[r_idx];
 }
 
-static inline struct igb_ring *igb_tx_queue_mapping(struct igb_adapter *adapter,
-						    struct sk_buff *skb)
-{
-	return __igb_tx_queue_mapping(adapter, skb->queue_mapping);
-}
-
 static netdev_tx_t igb_xmit_frame(struct sk_buff *skb,
 				  struct net_device *netdev)
 {
@@ -5094,21 +5097,6 @@ static netdev_tx_t igb_xmit_frame(struct sk_buff *skb,
 	return igb_xmit_frame_ring(skb, igb_tx_queue_mapping(adapter, skb));
 }
 
-static void igb_xmit_flush(struct net_device *netdev, u16 queue)
-{
-	struct igb_adapter *adapter = netdev_priv(netdev);
-	struct igb_ring *tx_ring;
-
-	tx_ring = __igb_tx_queue_mapping(adapter, queue);
-
-	writel(tx_ring->next_to_use, tx_ring->tail);
-
-	/* we need this if more than one processor can write to our tail
-	 * at a time, it synchronizes IO on IA64/Altix systems
-	 */
-	mmiowb();
-}
-
 /**
  *  igb_tx_timeout - Respond to a Tx Hang
  *  @netdev: network interface device structure
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 62421086d3e6..f0c2824f5e0f 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -953,15 +953,10 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 	}
 
-	return NETDEV_TX_OK;
-}
+	if (!skb->xmit_more)
+		virtqueue_kick(sq->vq);
 
-static void xmit_flush(struct net_device *dev, u16 qnum)
-{
-	struct virtnet_info *vi = netdev_priv(dev);
-	struct send_queue *sq = &vi->sq[qnum];
-
-	virtqueue_kick(sq->vq);
+	return NETDEV_TX_OK;
 }
 
 /*
@@ -1393,7 +1388,6 @@ static const struct net_device_ops virtnet_netdev = {
 	.ndo_open            = virtnet_open,
 	.ndo_stop   	     = virtnet_close,
 	.ndo_start_xmit      = start_xmit,
-	.ndo_xmit_flush      = xmit_flush,
 	.ndo_validate_addr   = eth_validate_addr,
 	.ndo_set_mac_address = virtnet_set_mac_address,
 	.ndo_set_rx_mode     = virtnet_set_rx_mode,