vlan/8021q: avoid retpoline overhead on GRO

The two most popular headers going after VLAN are IPv4 and IPv6.
Retpoline overhead for them is addressed only in dev_gro_receive(),
when they lie right after the outermost Ethernet header.
Use the indirect call wrappers in VLAN GRO receive code to reduce
the penalty on receiving tagged frames (when hardware stripping is
off or not available).

Signed-off-by: Alexander Lobakin <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

net/8021q/vlan_core.c

@@ -4,6 +4,7 @@
 #include <linux/if_vlan.h>
 #include <linux/netpoll.h>
 #include <linux/export.h>
+#include <net/gro.h>
 #include "vlan.h"
 
 bool vlan_do_receive(struct sk_buff **skbp)
@@ -495,7 +496,10 @@ static struct sk_buff *vlan_gro_receive(struct list_head *head,
 
 	skb_gro_pull(skb, sizeof(*vhdr));
 	skb_gro_postpull_rcsum(skb, vhdr, sizeof(*vhdr));
-	pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
+
+	pp = indirect_call_gro_receive_inet(ptype->callbacks.gro_receive,
+					    ipv6_gro_receive, inet_gro_receive,
+					    head, skb);
 
 out_unlock:
 	rcu_read_unlock();
@@ -515,7 +519,9 @@ static int vlan_gro_complete(struct sk_buff *skb, int nhoff)
 	rcu_read_lock();
 	ptype = gro_find_complete_by_type(type);
 	if (ptype)
-		err = ptype->callbacks.gro_complete(skb, nhoff + sizeof(*vhdr));
+		err = INDIRECT_CALL_INET(ptype->callbacks.gro_complete,
+					 ipv6_gro_complete, inet_gro_complete,
+					 skb, nhoff + sizeof(*vhdr));
 
 	rcu_read_unlock();
 	return err;