diff mbox series

[net-next,1/2] vsock: Linger on unsent data

Message ID 20250407-vsock-linger-v1-1-1458038e3492@rbox.co (mailing list archive)
State New
Headers show
Series vsock: SOCK_LINGER rework | expand

Commit Message

Michal Luczaj April 7, 2025, 6:41 p.m. UTC
Change the behaviour of a lingering close(): instead of waiting for all
data to be consumed, block until data is considered sent, i.e. until worker
picks the packets and decrements virtio_vsock_sock::bytes_unsent down to 0.

Do linger on shutdown() just as well.

Signed-off-by: Michal Luczaj <mhal@rbox.co>
---
 include/net/af_vsock.h                  |  1 +
 net/vmw_vsock/af_vsock.c                | 25 +++++++++++++++++++++++++
 net/vmw_vsock/virtio_transport_common.c | 25 +++----------------------
 3 files changed, 29 insertions(+), 22 deletions(-)
diff mbox series

Patch

diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index 9e85424c834353d016a527070dd62e15ff3bfce1..bd8b88d70423051dd05fc445fe37971af631ba03 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -221,6 +221,7 @@  void vsock_for_each_connected_socket(struct vsock_transport *transport,
 				     void (*fn)(struct sock *sk));
 int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk);
 bool vsock_find_cid(unsigned int cid);
+void vsock_linger(struct sock *sk, long timeout);
 
 /**** TAP ****/
 
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index fc6afbc8d6806a4d98c66abc3af4bd139c583b08..383c6644d047589035c0439c47d1440273e67ea9 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1013,6 +1013,29 @@  static int vsock_getname(struct socket *sock,
 	return err;
 }
 
+void vsock_linger(struct sock *sk, long timeout)
+{
+	if (timeout) {
+		DEFINE_WAIT_FUNC(wait, woken_wake_function);
+		ssize_t (*unsent)(struct vsock_sock *vsk);
+		struct vsock_sock *vsk = vsock_sk(sk);
+
+		unsent = vsk->transport->unsent_bytes;
+		if (!unsent)
+			return;
+
+		add_wait_queue(sk_sleep(sk), &wait);
+
+		do {
+			if (sk_wait_event(sk, &timeout, unsent(vsk) == 0, &wait))
+				break;
+		} while (!signal_pending(current) && timeout);
+
+		remove_wait_queue(sk_sleep(sk), &wait);
+	}
+}
+EXPORT_SYMBOL_GPL(vsock_linger);
+
 static int vsock_shutdown(struct socket *sock, int mode)
 {
 	int err;
@@ -1056,6 +1079,8 @@  static int vsock_shutdown(struct socket *sock, int mode)
 		if (sock_type_connectible(sk->sk_type)) {
 			sock_reset_flag(sk, SOCK_DONE);
 			vsock_send_shutdown(sk, mode);
+			if (sock_flag(sk, SOCK_LINGER))
+				vsock_linger(sk, sk->sk_lingertime);
 		}
 	}
 
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 7f7de6d8809655fe522749fbbc9025df71f071bd..66ff2e694e474ad16f70248cc1dc235f4e1ebaa1 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -1192,23 +1192,6 @@  static void virtio_transport_remove_sock(struct vsock_sock *vsk)
 	vsock_remove_sock(vsk);
 }
 
-static void virtio_transport_wait_close(struct sock *sk, long timeout)
-{
-	if (timeout) {
-		DEFINE_WAIT_FUNC(wait, woken_wake_function);
-
-		add_wait_queue(sk_sleep(sk), &wait);
-
-		do {
-			if (sk_wait_event(sk, &timeout,
-					  sock_flag(sk, SOCK_DONE), &wait))
-				break;
-		} while (!signal_pending(current) && timeout);
-
-		remove_wait_queue(sk_sleep(sk), &wait);
-	}
-}
-
 static void virtio_transport_cancel_close_work(struct vsock_sock *vsk,
 					       bool cancel_timeout)
 {
@@ -1279,15 +1262,13 @@  static bool virtio_transport_close(struct vsock_sock *vsk)
 		(void)virtio_transport_shutdown(vsk, SHUTDOWN_MASK);
 
 	if (sock_flag(sk, SOCK_LINGER) && !(current->flags & PF_EXITING))
-		virtio_transport_wait_close(sk, sk->sk_lingertime);
+		vsock_linger(sk, sk->sk_lingertime);
 
-	if (sock_flag(sk, SOCK_DONE)) {
+	if (sock_flag(sk, SOCK_DONE))
 		return true;
-	}
 
 	sock_hold(sk);
-	INIT_DELAYED_WORK(&vsk->close_work,
-			  virtio_transport_close_timeout);
+	INIT_DELAYED_WORK(&vsk->close_work, virtio_transport_close_timeout);
 	vsk->close_work_scheduled = true;
 	schedule_delayed_work(&vsk->close_work, VSOCK_CLOSE_TIMEOUT);
 	return false;