diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c
index b0cb29d4cc01e735b7855e99f7e3a7c81650d3db..c37acc1d10acccb1ecebfafca0c9af7d07e2c37f 100644
--- a/drivers/net/bnx2.c
+++ b/drivers/net/bnx2.c
@@ -2630,14 +2630,15 @@ bnx2_tx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget)
 		tx_buf = &txr->tx_buf_ring[sw_ring_cons];
 		skb = tx_buf->skb;
 
+		/* prefetch skb_end_pointer() to speedup skb_shinfo(skb) */
+		prefetch(&skb->end);
+
 		/* partial BD completions possible with TSO packets */
-		if (skb_is_gso(skb)) {
+		if (tx_buf->is_gso) {
 			u16 last_idx, last_ring_idx;
 
-			last_idx = sw_cons +
-				skb_shinfo(skb)->nr_frags + 1;
-			last_ring_idx = sw_ring_cons +
-				skb_shinfo(skb)->nr_frags + 1;
+			last_idx = sw_cons + tx_buf->nr_frags + 1;
+			last_ring_idx = sw_ring_cons + tx_buf->nr_frags + 1;
 			if (unlikely(last_ring_idx >= MAX_TX_DESC_CNT)) {
 				last_idx++;
 			}
@@ -2649,7 +2650,7 @@ bnx2_tx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget)
 		skb_dma_unmap(&bp->pdev->dev, skb, DMA_TO_DEVICE);
 
 		tx_buf->skb = NULL;
-		last = skb_shinfo(skb)->nr_frags;
+		last = tx_buf->nr_frags;
 
 		for (i = 0; i < last; i++) {
 			sw_cons = NEXT_TX_BD(sw_cons);
@@ -2662,7 +2663,8 @@ bnx2_tx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget)
 		if (tx_pkt == budget)
 			break;
 
-		hw_cons = bnx2_get_hw_tx_cons(bnapi);
+		if (hw_cons == sw_cons)
+			hw_cons = bnx2_get_hw_tx_cons(bnapi);
 	}
 
 	txr->hw_tx_cons = hw_cons;
@@ -6179,6 +6181,8 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	txbd->tx_bd_vlan_tag_flags = vlan_tag_flags | TX_BD_FLAGS_START;
 
 	last_frag = skb_shinfo(skb)->nr_frags;
+	tx_buf->nr_frags = last_frag;
+	tx_buf->is_gso = skb_is_gso(skb);
 
 	for (i = 0; i < last_frag; i++) {
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
diff --git a/drivers/net/bnx2.h b/drivers/net/bnx2.h
index 5b570e17c839a2d35db6fba9f27da71a1efaf41e..026ed1c846983179c9831bda7afe542ad52b8865 100644
--- a/drivers/net/bnx2.h
+++ b/drivers/net/bnx2.h
@@ -6552,6 +6552,8 @@ struct sw_pg {
 
 struct sw_tx_bd {
 	struct sk_buff		*skb;
+	unsigned short		is_gso;
+	unsigned short		nr_frags;
 };
 
 #define SW_RXBD_RING_SIZE (sizeof(struct sw_bd) * RX_DESC_CNT)