From: Eric Dumazet <edumazet@google.com>
Date: Tue, 10 Mar 2026 12:44:51 +0000 (+0000)
Subject: tcp: add tcp_release_cb_cond() helper
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=6f459eda8b60382efa0da2ca025c26a2018adc87;p=thirdparty%2Flinux.git

tcp: add tcp_release_cb_cond() helper

Majority of tcp_release_cb() calls do nothing at all.

Provide tcp_release_cb_cond() helper so that release_sock()
can avoid these calls.

Also hint the compiler that __release_sock() and wake_up()
are rarely called.

$ scripts/bloat-o-meter -t vmlinux.old vmlinux.new
add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-77 (-77)
Function                                     old     new   delta
release_sock                                 258     181     -77
Total: Before=25235790, After=25235713, chg -0.00%

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260310124451.2280968-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index c44cf9ae8d16f..bcebc4f07532f 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -548,6 +548,13 @@ enum tsq_flags {
 	TCPF_ACK_DEFERRED		= BIT(TCP_ACK_DEFERRED),
 };
 
+/* Flags of interest for tcp_release_cb() */
+#define TCP_DEFERRED_ALL (TCPF_TSQ_DEFERRED |		\
+			  TCPF_WRITE_TIMER_DEFERRED |	\
+			  TCPF_DELACK_TIMER_DEFERRED |	\
+			  TCPF_MTU_REDUCED_DEFERRED |	\
+			  TCPF_ACK_DEFERRED)
+
 #define tcp_sk(ptr) container_of_const(ptr, struct tcp_sock, inet_conn.icsk_inet.sk)
 
 /* Variant of tcp_sk() upgrading a const sock to a read/write tcp socket.
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 9f0aee9e5d76d..48dffcca0a71b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -375,7 +375,21 @@ int tcp_send_mss(struct sock *sk, int *size_goal, int flags);
 int tcp_wmem_schedule(struct sock *sk, int copy);
 void tcp_push(struct sock *sk, int flags, int mss_now, int nonagle,
 	      int size_goal);
+
 void tcp_release_cb(struct sock *sk);
+
+static inline bool tcp_release_cb_cond(struct sock *sk)
+{
+#ifdef CONFIG_INET
+	if (likely(sk->sk_prot->release_cb == tcp_release_cb)) {
+		if (unlikely(smp_load_acquire(&sk->sk_tsq_flags) & TCP_DEFERRED_ALL))
+			tcp_release_cb(sk);
+		return true;
+	}
+#endif
+	return false;
+}
+
 void tcp_wfree(struct sk_buff *skb);
 void tcp_write_timer_handler(struct sock *sk);
 void tcp_delack_timer_handler(struct sock *sk);
diff --git a/net/core/sock.c b/net/core/sock.c
index f4e2ff23d60eb..fdaf66e6dc18c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3807,16 +3807,18 @@ EXPORT_SYMBOL(lock_sock_nested);
 void release_sock(struct sock *sk)
 {
 	spin_lock_bh(&sk->sk_lock.slock);
-	if (sk->sk_backlog.tail)
-		__release_sock(sk);
 
-	if (sk->sk_prot->release_cb)
-		INDIRECT_CALL_INET_1(sk->sk_prot->release_cb,
-				     tcp_release_cb, sk);
+	if (unlikely(sk->sk_backlog.tail))
+		__release_sock(sk);
 
+	if (sk->sk_prot->release_cb) {
+		if (!tcp_release_cb_cond(sk))
+			sk->sk_prot->release_cb(sk);
+	}
 	sock_release_ownership(sk);
-	if (waitqueue_active(&sk->sk_lock.wq))
+	if (unlikely(waitqueue_active(&sk->sk_lock.wq)))
 		wake_up(&sk->sk_lock.wq);
+
 	spin_unlock_bh(&sk->sk_lock.slock);
 }
 EXPORT_SYMBOL(release_sock);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a53802f28dd17..34a25ef610060 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1320,11 +1320,6 @@ static void tcp_tsq_workfn(struct work_struct *work)
 	}
 }
 
-#define TCP_DEFERRED_ALL (TCPF_TSQ_DEFERRED |		\
-			  TCPF_WRITE_TIMER_DEFERRED |	\
-			  TCPF_DELACK_TIMER_DEFERRED |	\
-			  TCPF_MTU_REDUCED_DEFERRED |	\
-			  TCPF_ACK_DEFERRED)
 /**
  * tcp_release_cb - tcp release_sock() callback
  * @sk: socket