[LEDE-DEV] [PATCH] ag71xx: Add some unlikely calls + rearange some stuff in hard_start_xmit.

[Rosen Penev]

Based on Qualcomm driver. Improves iperf3 throughput by ~20mbps on transmit on Archer C7v4.

Signed-off-by: Rosen Penev <rosenp at gmail.com>
---
 .../drivers/net/ethernet/atheros/ag71xx/ag71xx_main.c      | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/target/linux/ar71xx/files/drivers/net/ethernet/atheros/ag71xx/ag71xx_main.c b/target/linux/ar71xx/files/drivers/net/ethernet/atheros/ag71xx/ag71xx_main.c
index 95682b7641..d32f220178 100644
--- a/target/linux/ar71xx/files/drivers/net/ethernet/atheros/ag71xx/ag71xx_main.c
+++ b/target/linux/ar71xx/files/drivers/net/ethernet/atheros/ag71xx/ag71xx_main.c
@@ -797,11 +797,14 @@ static netdev_tx_t ag71xx_hard_start_xmit(struct sk_buff *skb,
 	if (ag71xx_has_ar8216(ag))
 		ag71xx_add_ar8216_header(ag, skb);
 
-	if (skb->len <= 4) {
+	dma_cache_sync (NULL, skb->data, skb->len, DMA_TO_DEVICE);
+
+	if (unlikely(skb->len <= 4)) {
 		DBG("%s: packet len is too small\n", ag->dev->name);
 		goto err_drop;
 	}
 
+	netdev_sent_queue(dev, skb->len);
 	dma_addr = dma_map_single(&dev->dev, skb->data, skb->len,
 				  DMA_TO_DEVICE);
 
@@ -817,27 +820,24 @@ static netdev_tx_t ag71xx_hard_start_xmit(struct sk_buff *skb,
 	ring->buf[i].len = skb->len;
 	ring->buf[i].skb = skb;
 
-	netdev_sent_queue(dev, skb->len);
-
 	skb_tx_timestamp(skb);
 
 	desc->ctrl &= ~DESC_EMPTY;
 	ring->curr += n;
 
-	/* flush descriptor */
-	wmb();
-
 	ring_min = 2;
 	if (ring->desc_split)
 	    ring_min *= AG71XX_TX_RING_DS_PER_PKT;
 
-	if (ring->curr - ring->dirty >= ring_size - ring_min) {
+	if (unlikely(ring->curr - ring->dirty >= ring_size - ring_min)) {
 		DBG("%s: tx queue full\n", dev->name);
 		netif_stop_queue(dev);
 	}
 
 	DBG("%s: packet injected into TX queue\n", ag->dev->name);
 
+	/* flush descriptor */
+	wmb();
 	/* enable TX engine */
 	ag71xx_wr(ag, AG71XX_REG_TX_CTRL, TX_CTRL_TXE);
 
-- 
2.14.3