bridge: per-cpu packet statistics (v3)

The shared packet statistics are a potential source of slow down
on bridged traffic. Convert to per-cpu array, but only keep those
statistics which change per-packet.

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 846d7d1..791d4ab 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -135,6 +135,14 @@
 	spinlock_t			lock;
 	struct list_head		port_list;
 	struct net_device		*dev;
+
+	struct br_cpu_netstats __percpu {
+		unsigned long	rx_packets;
+		unsigned long	rx_bytes;
+		unsigned long	tx_packets;
+		unsigned long	tx_bytes;
+	} *stats;
+
 	spinlock_t			hash_lock;
 	struct hlist_head		hash[BR_HASH_SIZE];
 	unsigned long			feature_mask;