e1000e: save skb counts in TX to avoid cache misses

In e1000_tx_map, precompute number of segements and bytecounts which
are derived from fields in skb; these are stored in buffer_info.  When
cleaning tx in e1000_clean_tx_irq use the values in the associated
buffer_info for statistics counting, this eliminates cache misses
on skb fields.

Signed-off-by: Tom Herbert <therbert@google.com>
Acked-by: Bruce Allan <bruce.w.allan@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/drivers/net/e1000e/e1000.h b/drivers/net/e1000e/e1000.h
index 906c4da..c0b3db4 100644
--- a/drivers/net/e1000e/e1000.h
+++ b/drivers/net/e1000e/e1000.h
@@ -189,6 +189,8 @@
 			unsigned long time_stamp;
 			u16 length;
 			u16 next_to_watch;
+			unsigned int segs;
+			unsigned int bytecount;
 			u16 mapped_as_page;
 		};
 		/* Rx */
diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c
index d13760d..8de64ed 100644
--- a/drivers/net/e1000e/netdev.c
+++ b/drivers/net/e1000e/netdev.c
@@ -1001,14 +1001,8 @@
 			cleaned = (i == eop);
 
 			if (cleaned) {
-				struct sk_buff *skb = buffer_info->skb;
-				unsigned int segs, bytecount;
-				segs = skb_shinfo(skb)->gso_segs ?: 1;
-				/* multiply data chunks by size of headers */
-				bytecount = ((segs - 1) * skb_headlen(skb)) +
-					    skb->len;
-				total_tx_packets += segs;
-				total_tx_bytes += bytecount;
+				total_tx_packets += buffer_info->segs;
+				total_tx_bytes += buffer_info->bytecount;
 			}
 
 			e1000_put_txbuf(adapter, buffer_info);
@@ -4261,7 +4255,7 @@
 	struct e1000_buffer *buffer_info;
 	unsigned int len = skb_headlen(skb);
 	unsigned int offset = 0, size, count = 0, i;
-	unsigned int f;
+	unsigned int f, bytecount, segs;
 
 	i = tx_ring->next_to_use;
 
@@ -4321,7 +4315,13 @@
 		}
 	}
 
+	segs = skb_shinfo(skb)->gso_segs ?: 1;
+	/* multiply data chunks by size of headers */
+	bytecount = ((segs - 1) * skb_headlen(skb)) + skb->len;
+
 	tx_ring->buffer_info[i].skb = skb;
+	tx_ring->buffer_info[i].segs = segs;
+	tx_ring->buffer_info[i].bytecount = bytecount;
 	tx_ring->buffer_info[first].next_to_watch = i;
 
 	return count;