[TCP]: Fix send-side cpu utiliziation regression.

Only put user data purely to pages when doing TSO.

The extra page allocations cause two problems:

1) Add the overhead of the page allocations themselves.
2) Make us do small user copies when we get to the end
   of the TCP socket cache page.

It is still beneficial to purely use pages for TSO,
so we will do it for that case.
Signed-off-by: David S. Miller <davem@davemloft.net>

net/ipv4/tcp.c

@@ -756,8 +756,17 @@ static inline int select_size(struct sock *sk, struct tcp_sock *tp)
 {
 	int tmp = tp->mss_cache_std;
 
-	if (sk->sk_route_caps & NETIF_F_SG)
-		tmp = 0;
+	if (sk->sk_route_caps & NETIF_F_SG) {
+		if (sk->sk_route_caps & NETIF_F_TSO)
+			tmp = 0;
+		else {
+			int pgbreak = SKB_MAX_HEAD(MAX_TCP_HEADER);
+
+			if (tmp >= pgbreak &&
+			    tmp <= pgbreak + (MAX_SKB_FRAGS - 1) * PAGE_SIZE)
+				tmp = pgbreak;
+		}
+	}
 
 	return tmp;
 }