am335x: cpsw: optimize cpsw_send to increase network performance

Before submitting packets to cpdma, phy status is updated on every packet
which leads to delay in packet send intern reduces the Ethernet performance.
Checking mdio status for each packet will reduce timetaken to send a packet
and there by increasing the Ethernet performance. With this the performance
is increased from 208KiB/s to 375KiB/s on EVMsk

Signed-off-by: Mugunthan V N <mugunthanvnm@ti.com>
diff --git a/drivers/net/cpsw.c b/drivers/net/cpsw.c
index db04795..93f8417 100644
--- a/drivers/net/cpsw.c
+++ b/drivers/net/cpsw.c
@@ -227,6 +227,9 @@
 	struct cpsw_slave		*slaves;
 	struct phy_device		*phydev;
 	struct mii_dev			*bus;
+
+	u32				mdio_link;
+	u32				phy_mask;
 };
 
 static inline int cpsw_ale_get_field(u32 *ale_entry, u32 start, u32 bits)
@@ -598,10 +601,21 @@
 
 	for_each_slave(slave, priv)
 		cpsw_slave_update_link(slave, priv, &link);
-
+	priv->mdio_link = readl(&mdio_regs->link);
 	return link;
 }
 
+static int cpsw_check_link(struct cpsw_priv *priv)
+{
+	u32 link = 0;
+
+	link = __raw_readl(&mdio_regs->link) & priv->phy_mask;
+	if ((link) && (link == priv->mdio_link))
+		return 1;
+
+	return cpsw_update_link(priv);
+}
+
 static inline u32  cpsw_get_slave_port(struct cpsw_priv *priv, u32 slave_num)
 {
 	if (priv->host_port == 0)
@@ -631,6 +645,8 @@
 	cpsw_ale_port_state(priv, slave_port, ALE_PORT_STATE_FORWARD);
 
 	cpsw_ale_add_mcast(priv, NetBcastAddr, 1 << slave_port);
+
+	priv->phy_mask |= 1 << slave->data->phy_id;
 }
 
 static struct cpdma_desc *cpdma_desc_alloc(struct cpsw_priv *priv)
@@ -862,7 +878,7 @@
 	int len;
 	int timeout = CPDMA_TIMEOUT;
 
-	if (!cpsw_update_link(priv))
+	if (!cpsw_check_link(priv))
 		return -EIO;
 
 	flush_dcache_range((unsigned long)packet,