Merge branch 'net-bql-better-deal-with-GSO'

Eric Dumazet says:

====================
net: bql: better deal with GSO

While BQL bulk dequeue works well for TSO packets, it is
not very efficient as soon as GSO is involved.

On a GSO only workload (UDP or TCP), this patch series
can save about 8 % of cpu cycles on a 40Gbit mlx4 NIC,
by keeping optimal batching, and avoiding expensive
doorbells, qdisc requeues and reschedules.

This patch series :

- Add __netdev_tx_sent_queue() so that drivers
  can implement efficient BQL and xmit_more support.

- Implement a work around in dev_hard_start_xmit()
  for drivers not using __netdev_tx_sent_queue()

- changes mlx4 to use __netdev_tx_sent_queue()

v2: Tariq and Willem feedback addressed.
    added __netdev_tx_sent_queue() (Willem suggestion)
====================

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

3 files changed, 25 insertions, 3 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 1857ee0f0871..6f5153afcab4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -1006,7 +1006,6 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		ring->packets++;
 	}
 	ring->bytes += tx_info->nr_bytes;
-	netdev_tx_sent_queue(ring->tx_queue, tx_info->nr_bytes);
 	AVG_PERF_COUNTER(priv->pstats.tx_pktsz_avg, skb->len);
 
 	if (tx_info->inl)
@@ -1044,7 +1043,10 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		netif_tx_stop_queue(ring->tx_queue);
 		ring->queue_stopped++;
 	}
-	send_doorbell = !skb->xmit_more || netif_xmit_stopped(ring->tx_queue);
+
+	send_doorbell = __netdev_tx_sent_queue(ring->tx_queue,
+					       tx_info->nr_bytes,
+					       skb->xmit_more);
 
 	real_size = (real_size / 16) & 0x3f;
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index dc1d9ed33b31..857f8abf7b91 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3190,6 +3190,26 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue,
 #endif
 }
 
+/* Variant of netdev_tx_sent_queue() for drivers that are aware
+ * that they should not test BQL status themselves.
+ * We do want to change __QUEUE_STATE_STACK_XOFF only for the last
+ * skb of a batch.
+ * Returns true if the doorbell must be used to kick the NIC.
+ */
+static inline bool __netdev_tx_sent_queue(struct netdev_queue *dev_queue,
+					  unsigned int bytes,
+					  bool xmit_more)
+{
+	if (xmit_more) {
+#ifdef CONFIG_BQL
+		dql_queued(&dev_queue->dql, bytes);
+#endif
+		return netif_tx_queue_stopped(dev_queue);
+	}
+	netdev_tx_sent_queue(dev_queue, bytes);
+	return true;
+}
+
 /**
  * 	netdev_sent_queue - report the number of bytes queued to hardware
  * 	@dev: network device
diff --git a/net/core/dev.c b/net/core/dev.c
index 77d43ae2a7bb..0ffcbdd55fa9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3272,7 +3272,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *de
 		}
 
 		skb = next;
-		if (netif_xmit_stopped(txq) && skb) {
+		if (netif_tx_queue_stopped(txq) && skb) {
 			rc = NETDEV_TX_BUSY;
 			break;
 		}