tcp: remove indirect calls for icsk->icsk_af_ops->queue_xmit

Mitigate RETPOLINE costs in __tcp_transmit_skb()
by using INDIRECT_CALL_INET() wrapper.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/include/net/ip.h b/include/net/ip.h
index 04ebe7b..862c954 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -231,11 +231,7 @@ struct sk_buff *ip_make_skb(struct sock *sk, struct flowi4 *fl4,
 			    struct ipcm_cookie *ipc, struct rtable **rtp,
 			    struct inet_cork *cork, unsigned int flags);
 
-static inline int ip_queue_xmit(struct sock *sk, struct sk_buff *skb,
-				struct flowi *fl)
-{
-	return __ip_queue_xmit(sk, skb, fl, inet_sk(sk)->tos);
-}
+int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl);
 
 static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4)
 {
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 4de9485..e5d7e0b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -25,6 +25,7 @@
 #include <linux/skbuff.h>
 #include <linux/kref.h>
 #include <linux/ktime.h>
+#include <linux/indirect_call_wrapper.h>
 
 #include <net/inet_connection_sock.h>
 #include <net/inet_timewait_sock.h>
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 090d309..d946356 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -539,6 +539,12 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 }
 EXPORT_SYMBOL(__ip_queue_xmit);
 
+int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)
+{
+	return __ip_queue_xmit(sk, skb, fl, inet_sk(sk)->tos);
+}
+EXPORT_SYMBOL(ip_queue_xmit);
+
 static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 {
 	to->pkt_type = from->pkt_type;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a50e199..be1bd37 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1064,6 +1064,9 @@ static void tcp_update_skb_after_send(struct sock *sk, struct sk_buff *skb,
 	list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue);
 }
 
+INDIRECT_CALLABLE_DECLARE(int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl));
+INDIRECT_CALLABLE_DECLARE(int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl));
+
 /* This routine actually transmits TCP packets queued in by
  * tcp_do_sendmsg().  This is used by both the initial
  * transmission and possible later retransmissions.
@@ -1235,7 +1238,9 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 
 	tcp_add_tx_delay(skb, tp);
 
-	err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl);
+	err = INDIRECT_CALL_INET(icsk->icsk_af_ops->queue_xmit,
+				 inet6_csk_xmit, ip_queue_xmit,
+				 sk, skb, &inet->cork.fl);
 
 	if (unlikely(err > 0)) {
 		tcp_enter_cwr(sk);