Setting the FOR_EMAC flag should be the last step of modifying the buffer
descriptor, or possible racing will occur.

The loop counter i in tx_clean() is not needed, and we need to make sure
it does not clear the finished txbds.

Signed-off-by: Shuyu Wei <sy.w@outlook.com>
---
Changes in v2:
- Remove loop counter in tx_clean and check for unfinished txbds (Ueimor)
- Use dma_wmb() to sync writes (Ueimor)

diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index a3a9392..df3dfef 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -153,9 +153,8 @@ static void arc_emac_tx_clean(struct net_device *ndev)
 {
 	struct arc_emac_priv *priv = netdev_priv(ndev);
 	struct net_device_stats *stats = &ndev->stats;
-	unsigned int i;
 
-	for (i = 0; i < TX_BD_NUM; i++) {
+	while (priv->txbd_dirty != priv->txbd_curr) {
 		unsigned int *txbd_dirty = &priv->txbd_dirty;
 		struct arc_emac_bd *txbd = &priv->txbd[*txbd_dirty];
 		struct buffer_state *tx_buff = &priv->tx_buff[*txbd_dirty];
@@ -685,13 +684,15 @@ static int arc_emac_tx(struct sk_buff *skb, struct net_device *ndev)
 	wmb();
 
 	skb_tx_timestamp(skb);
+	priv->tx_buff[*txbd_curr].skb = skb;
+
+	dma_wmb();
 
 	*info = cpu_to_le32(FOR_EMAC | FIRST_OR_LAST_MASK | len);
 
 	/* Make sure info word is set */
 	wmb();
 
-	priv->tx_buff[*txbd_curr].skb = skb;
 
 	/* Increment index to point to the next BD */
 	*txbd_curr = (*txbd_curr + 1) % TX_BD_NUM;