[PATCH net-next] tcp: move tcp_rbtree_insert() to tcp_output.c

[PATCH net-next] tcp: move tcp_rbtree_insert() to tcp_output.c

[Eric Dumazet]

tcp_rbtree_insert() is primarily used from tcp_output.c
In tcp_input.c, only (slow path) tcp_collapse() uses it.

Move it to tcp_output.c to allow its (auto)inlining to improve
TCP tx fast path.

$ scripts/bloat-o-meter -t vmlinux.old vmlinux.new
add/remove: 0/0 grow/shrink: 4/1 up/down: 445/-115 (330)
Function                                     old     new   delta
tcp_connect                                 4277    4478    +201
tcp_event_new_data_sent                      162     248     +86
tcp_send_synack                              780     862     +82
tcp_fragment                                1185    1261     +76
tcp_collapse                                1524    1409    -115
Total: Before=24896043, After=24896373, chg +0.00%

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 net/ipv4/tcp_input.c  | 19 -------------------
 net/ipv4/tcp_output.c | 19 +++++++++++++++++++
 2 files changed, 19 insertions(+), 19 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a2a872382fc0..10f864179982 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5756,25 +5756,6 @@ static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb,
 	return next;
 }
 
-/* Insert skb into rb tree, ordered by TCP_SKB_CB(skb)->seq */
-void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb)
-{
-	struct rb_node **p = &root->rb_node;
-	struct rb_node *parent = NULL;
-	struct sk_buff *skb1;
-
-	while (*p) {
-		parent = *p;
-		skb1 = rb_to_skb(parent);
-		if (before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb1)->seq))
-			p = &parent->rb_left;
-		else
-			p = &parent->rb_right;
-	}
-	rb_link_node(&skb->rbnode, parent, p);
-	rb_insert_color(&skb->rbnode, root);
-}
-
 /* Collapse contiguous sequence of skbs head..tail with
  * sequence numbers start..end.
  *
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f907f24f74f7..b09f2bcfc237 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -66,6 +66,25 @@ void tcp_mstamp_refresh(struct tcp_sock *tp)
 static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 			   int push_one, gfp_t gfp);
 
+/* Insert skb into rb tree, ordered by TCP_SKB_CB(skb)->seq */
+void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct sk_buff *skb1;
+
+	while (*p) {
+		parent = *p;
+		skb1 = rb_to_skb(parent);
+		if (before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb1)->seq))
+			p = &parent->rb_left;
+		else
+			p = &parent->rb_right;
+	}
+	rb_link_node(&skb->rbnode, parent, p);
+	rb_insert_color(&skb->rbnode, root);
+}
+
 /* Account for new data that has been sent to the network. */
 static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb)
 {
-- 
2.53.0.rc1.225.gd81095ad13-goog

Re: [PATCH net-next] tcp: move tcp_rbtree_insert() to tcp_output.c

[Kuniyuki Iwashima]

On Mon, Feb 2, 2026 at 8:51 PM Eric Dumazet <edumazet@google.com> wrote:
>
> tcp_rbtree_insert() is primarily used from tcp_output.c
> In tcp_input.c, only (slow path) tcp_collapse() uses it.
>
> Move it to tcp_output.c to allow its (auto)inlining to improve
> TCP tx fast path.
>
> $ scripts/bloat-o-meter -t vmlinux.old vmlinux.new
> add/remove: 0/0 grow/shrink: 4/1 up/down: 445/-115 (330)
> Function                                     old     new   delta
> tcp_connect                                 4277    4478    +201
> tcp_event_new_data_sent                      162     248     +86
> tcp_send_synack                              780     862     +82
> tcp_fragment                                1185    1261     +76
> tcp_collapse                                1524    1409    -115
> Total: Before=24896043, After=24896373, chg +0.00%
>
> Signed-off-by: Eric Dumazet <edumazet@google.com>

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

Re: [PATCH net-next] tcp: move tcp_rbtree_insert() to tcp_output.c

[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 04:51:10 +0000 you wrote:
> tcp_rbtree_insert() is primarily used from tcp_output.c
> In tcp_input.c, only (slow path) tcp_collapse() uses it.
> 
> Move it to tcp_output.c to allow its (auto)inlining to improve
> TCP tx fast path.
> 
> $ scripts/bloat-o-meter -t vmlinux.old vmlinux.new
> add/remove: 0/0 grow/shrink: 4/1 up/down: 445/-115 (330)
> Function                                     old     new   delta
> tcp_connect                                 4277    4478    +201
> tcp_event_new_data_sent                      162     248     +86
> tcp_send_synack                              780     862     +82
> tcp_fragment                                1185    1261     +76
> tcp_collapse                                1524    1409    -115
> Total: Before=24896043, After=24896373, chg +0.00%
> 
> [...]

Here is the summary with links:
  - [net-next] tcp: move tcp_rbtree_insert() to tcp_output.c
    https://git.kernel.org/netdev/net-next/c/7c1db78ff75f

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