net: introduce __skb_header_release()

While profiling TCP stack, I noticed one useless atomic operation
in tcp_sendmsg(), caused by skb_header_release().

It turns out all current skb_header_release() users have a fresh skb,
that no other user can see, so we can avoid one atomic operation.

Introduce __skb_header_release() to clearly document this.

This gave me a 1.5 % improvement on TCP_RR workload.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 2 insertions, 2 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 070aeff1b131..553b01f52f71 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -609,7 +609,7 @@ static inline bool forced_push(const struct tcp_sock *tp)
         return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1));
 }
 
-static inline void skb_entail(struct sock *sk, struct sk_buff *skb)
+static void skb_entail(struct sock *sk, struct sk_buff *skb)
 {
         struct tcp_sock *tp = tcp_sk(sk);
         struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
@@ -618,7 +618,7 @@ static inline void skb_entail(struct sock *sk, struct sk_buff *skb)
         tcb->seq     = tcb->end_seq = tp->write_seq;
         tcb->tcp_flags = TCPHDR_ACK;
         tcb->sacked  = 0;
-        skb_header_release(skb);
+        __skb_header_release(skb);
         tcp_add_write_queue_tail(sk, skb);
         sk->sk_wmem_queued += skb->truesize;
         sk_mem_charge(sk, skb->truesize);