ipvlan: Defer multicast / broadcast processing to a work-queue

Processing multicast / broadcast in fast path is performance draining
and having more links means more cloning and bringing performance
down further.

Broadcast; in particular, need to be given to all the virtual links.
Earlier tricks of enabling broadcast bit for IPv4 only interfaces are not
really working since it fails autoconf. Which means enabling broadcast
for all the links if protocol specific hacks do not have to be added into
the driver.

This patch defers all (incoming as well as outgoing) multicast traffic to
a work-queue leaving only the unicast traffic in the fast-path. Now if we
need to apply any additional tricks to further reduce the impact of this
(multicast / broadcast) type of traffic, it can be implemented while
processing this work without affecting the fast-path.

Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h
index 54549a6..953a974 100644
--- a/drivers/net/ipvlan/ipvlan.h
+++ b/drivers/net/ipvlan/ipvlan.h
@@ -39,6 +39,8 @@
 #define IPVLAN_MAC_FILTER_SIZE	(1 << IPVLAN_MAC_FILTER_BITS)
 #define IPVLAN_MAC_FILTER_MASK	(IPVLAN_MAC_FILTER_SIZE - 1)
 
+#define IPVLAN_QBACKLOG_LIMIT	1000
+
 typedef enum {
 	IPVL_IPV6 = 0,
 	IPVL_ICMPV6,
@@ -93,6 +95,8 @@
 	struct hlist_head	hlhead[IPVLAN_HASH_SIZE];
 	struct list_head	ipvlans;
 	struct rcu_head		rcu;
+	struct work_struct	wq;
+	struct sk_buff_head	backlog;
 	int			count;
 	u16			mode;
 };
@@ -112,6 +116,7 @@
 void ipvlan_init_secret(void);
 unsigned int ipvlan_mac_hash(const unsigned char *addr);
 rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb);
+void ipvlan_process_multicast(struct work_struct *work);
 int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev);
 void ipvlan_ht_addr_add(struct ipvl_dev *ipvlan, struct ipvl_addr *addr);
 struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan,