Merge branch 'ndo_xmit_flush'

Basic deferred TX queue flushing infrastructure.

Over time, and specifically and more recently at the Networking
Workshop during Kernel SUmmit in Chicago, we have discussed the idea
of having some way to optimize transmits of multiple TX packets at
a time.

There are several areas of overhead that could be amortized with such
schemes.  One has to do with locking and transactional overhead, the
other has to do with device specific costs.

This patch set here is more aimed at device specific costs.

Typically a device queues up a packet in the TX queue and then has to
do something to have the device start processing that new entry.
Sometimes this is composed of doing an MMIO write to a "tail"
register, and in other cases it can involve something as expensive as
a hypervisor call.

The basic setup defined here is that when the driver supports deferred
TX queue flushing, ndo_start_xmit should no longer perform that
operation.  Instead a new operation, ndo_xmit_flush, should do it.

I have converted IGB and virtio_net as example initial users.  The IGB
conversion is tested, virtio_net is not but it does compile :-)

All ndo_start_xmit call sites have been abstracted behind a new helper
called netdev_start_xmit().

This just adds the infrastructure, it does not actually add any
instances of actually doing multiple ndo_start_xmit calls per
ndo_xmit_flush invocation.

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

6 files changed, 7 insertions, 13 deletions

diff --git a/net/atm/mpc.c b/net/atm/mpc.c
index e8e0e7a8a23d..d662da161e5a 100644
--- a/net/atm/mpc.c
+++ b/net/atm/mpc.c
@@ -599,7 +599,7 @@ static netdev_tx_t mpc_send_packet(struct sk_buff *skb,
 	}
 
 non_ip:
-	return mpc->old_ops->ndo_start_xmit(skb, dev);
+	return __netdev_start_xmit(mpc->old_ops, skb, dev);
 }
 
 static int atm_mpoa_vcc_attach(struct atm_vcc *vcc, void __user *arg)
diff --git a/net/core/dev.c b/net/core/dev.c
index b6a718ec11c1..26d296c2447c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2602,7 +2602,6 @@ EXPORT_SYMBOL(netif_skb_features);
 int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 			struct netdev_queue *txq)
 {
-	const struct net_device_ops *ops = dev->netdev_ops;
 	int rc = NETDEV_TX_OK;
 	unsigned int skb_len;
 
@@ -2667,7 +2666,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 
 		skb_len = skb->len;
 		trace_net_dev_start_xmit(skb, dev);
-		rc = ops->ndo_start_xmit(skb, dev);
+		rc = netdev_start_xmit(skb, dev);
 		trace_net_dev_xmit(skb, rc, dev, skb_len);
 		if (rc == NETDEV_TX_OK)
 			txq_trans_update(txq);
@@ -2686,7 +2685,7 @@ gso:
 
 		skb_len = nskb->len;
 		trace_net_dev_start_xmit(nskb, dev);
-		rc = ops->ndo_start_xmit(nskb, dev);
+		rc = netdev_start_xmit(nskb, dev);
 		trace_net_dev_xmit(nskb, rc, dev, skb_len);
 		if (unlikely(rc != NETDEV_TX_OK)) {
 			if (rc & ~NETDEV_TX_MASK)
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 907fb5e36c02..a5ad06828d67 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -72,7 +72,6 @@ module_param(carrier_timeout, uint, 0644);
 static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
 			      struct netdev_queue *txq)
 {
-	const struct net_device_ops *ops = dev->netdev_ops;
 	int status = NETDEV_TX_OK;
 	netdev_features_t features;
 
@@ -92,7 +91,7 @@ static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
 		skb->vlan_tci = 0;
 	}
 
-	status = ops->ndo_start_xmit(skb, dev);
+	status = netdev_start_xmit(skb, dev);
 	if (status == NETDEV_TX_OK)
 		txq_trans_update(txq);
 
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 8b849ddfef2e..83e2b4b19eb7 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3285,8 +3285,6 @@ static void pktgen_wait_for_skb(struct pktgen_dev *pkt_dev)
 static void pktgen_xmit(struct pktgen_dev *pkt_dev)
 {
 	struct net_device *odev = pkt_dev->odev;
-	netdev_tx_t (*xmit)(struct sk_buff *, struct net_device *)
-		= odev->netdev_ops->ndo_start_xmit;
 	struct netdev_queue *txq;
 	u16 queue_map;
 	int ret;
@@ -3339,7 +3337,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev)
 		goto unlock;
 	}
 	atomic_inc(&(pkt_dev->skb->users));
-	ret = (*xmit)(pkt_dev->skb, odev);
+	ret = netdev_start_xmit(pkt_dev->skb, odev);
 
 	switch (ret) {
 	case NETDEV_TX_OK:
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 93896d2092f6..0dfa990d4eaa 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -240,7 +240,6 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po);
 static int packet_direct_xmit(struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
-	const struct net_device_ops *ops = dev->netdev_ops;
 	netdev_features_t features;
 	struct netdev_queue *txq;
 	int ret = NETDEV_TX_BUSY;
@@ -262,7 +261,7 @@ static int packet_direct_xmit(struct sk_buff *skb)
 
 	HARD_TX_LOCK(dev, txq, smp_processor_id());
 	if (!netif_xmit_frozen_or_drv_stopped(txq)) {
-		ret = ops->ndo_start_xmit(skb, dev);
+		ret = netdev_start_xmit(skb, dev);
 		if (ret == NETDEV_TX_OK)
 			txq_trans_update(txq);
 	}
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index bd33793b527e..64cd93ca8104 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -301,7 +301,6 @@ restart:
 	do {
 		struct net_device *slave = qdisc_dev(q);
 		struct netdev_queue *slave_txq = netdev_get_tx_queue(slave, 0);
-		const struct net_device_ops *slave_ops = slave->netdev_ops;
 
 		if (slave_txq->qdisc_sleeping != q)
 			continue;
@@ -317,7 +316,7 @@ restart:
 				unsigned int length = qdisc_pkt_len(skb);
 
 				if (!netif_xmit_frozen_or_stopped(slave_txq) &&
-				    slave_ops->ndo_start_xmit(skb, slave) == NETDEV_TX_OK) {
+				    netdev_start_xmit(skb, slave) == NETDEV_TX_OK) {
 					txq_trans_update(slave_txq);
 					__netif_tx_unlock(slave_txq);
 					master->slaves = NEXT_SLAVE(q);