[PATCH net-next] tcp: use __skb_push() in __tcp_transmit_skb()

[PATCH net-next] tcp: use __skb_push() in __tcp_transmit_skb()

[Eric Dumazet]

We trust MAX_TCP_HEADER to be large enough.

Using the inlined version of skb_push() trades 8 bytes
of text for better performance of TCP TX fast path.

$ scripts/bloat-o-meter -t vmlinux.old vmlinux.new
add/remove: 0/0 grow/shrink: 1/0 up/down: 8/0 (8)
Function                                     old     new   delta
__tcp_transmit_skb                          3181    3189      +8
Total: Before=24896035, After=24896043, chg +0.00%

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 net/ipv4/tcp_output.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 597e888af36d..f907f24f74f7 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1565,7 +1565,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 	 */
 	skb->pfmemalloc = 0;
 
-	skb_push(skb, tcp_header_size);
+	__skb_push(skb, tcp_header_size);
 	skb_reset_transport_header(skb);
 
 	skb_orphan(skb);
-- 
2.53.0.rc1.225.gd81095ad13-goog

Re: [PATCH net-next] tcp: use __skb_push() in __tcp_transmit_skb()

[Kuniyuki Iwashima]

On Mon, Feb 2, 2026 at 8:42 PM Eric Dumazet <edumazet@google.com> wrote:
>
> We trust MAX_TCP_HEADER to be large enough.
>
> Using the inlined version of skb_push() trades 8 bytes
> of text for better performance of TCP TX fast path.
>
> $ scripts/bloat-o-meter -t vmlinux.old vmlinux.new
> add/remove: 0/0 grow/shrink: 1/0 up/down: 8/0 (8)
> Function                                     old     new   delta
> __tcp_transmit_skb                          3181    3189      +8
> Total: Before=24896035, After=24896043, chg +0.00%
>
> Signed-off-by: Eric Dumazet <edumazet@google.com>

Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>

Re: [PATCH net-next] tcp: use __skb_push() in __tcp_transmit_skb()

[patchwork-bot+netdevbpf]

Hello:

This patch was applied to netdev/net-next.git (main)
by Jakub Kicinski <kuba@kernel.org>:

On Tue,  3 Feb 2026 04:42:26 +0000 you wrote:
> We trust MAX_TCP_HEADER to be large enough.
> 
> Using the inlined version of skb_push() trades 8 bytes
> of text for better performance of TCP TX fast path.
> 
> $ scripts/bloat-o-meter -t vmlinux.old vmlinux.new
> add/remove: 0/0 grow/shrink: 1/0 up/down: 8/0 (8)
> Function                                     old     new   delta
> __tcp_transmit_skb                          3181    3189      +8
> Total: Before=24896035, After=24896043, chg +0.00%
> 
> [...]

Here is the summary with links:
  - [net-next] tcp: use __skb_push() in __tcp_transmit_skb()
    https://git.kernel.org/netdev/net-next/c/59b5e7f47c7c

You are awesome, thank you!
-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html