On Sun, Sep 20, 2026 at 08:47:09PM +0100, David Carlier wrote:
AF_VSOCK stream receives never fill msghdr.msg_inq, so io_uring cannot set
IORING_CQE_F_SOCK_NONEMPTY and retries a multishot receive even after the
queue has been drained.
Fill the hint at the common receive exit using the transport callback that
SIOCINQ already uses, and report 1 once the connection is finished so the
caller performs the receive which observes EOF, as TCP does after a FIN.
A vsock loopback ping-pong with io_uring multishot receive drops entries
into __vsock_connectible_recvmsg from 1.97 to 1.00 per delivered message,
and receiver CPU time by about 3% (25 runs of 50000 messages, p=0.006).
Signed-off-by: David Carlier <[email protected]>
---
net/vmw_vsock/af_vsock.c | 39 +++++++++++++++++++++++++++++++++++++++
1 file changed, 39 insertions(+)
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index f840498b58af..63309708c916 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -2543,6 +2543,38 @@ static int __vsock_seqpacket_recvmsg(struct sock *sk,
struct msghdr *msg,
return err;
}
+/* Bytes a following receive can consume, 1 if it would only see EOF, or a
+ * negative value to leave the caller's hint alone.
+ *
+ * Called under the socket lock after a nonnegative stream receive, so a NULL
+ * transport implies SOCK_DONE.
+ */
+static int vsock_inq_hint(struct sock *sk)
can we add "stream" in the name so it's clear that is stream only?
(e.g. vsock_stream_inq_hint)
+{
+ struct vsock_sock *vsk = vsock_sk(sk);
+ s64 data;
+
+ if ((sk->sk_shutdown & RCV_SHUTDOWN) ||
+ (sock_flag(sk, SOCK_DONE) && sk->sk_state != TCP_ESTABLISHED))
+ return 1;
+
+ if (!vsk->transport)
+ return 1;
Can we squash this in the previous block?
+
+ data = vsock_stream_has_data(vsk);
+ if (data < 0)
+ return -1;
+ if (data > 0)
+ return (int)min_t(s64, data, INT_MAX);
nit: IMO we can remove the int cast.
+
+ /* Empty but finished: keep the caller reading so it sees EOF. */
+ if (sock_flag(sk, SOCK_DONE) ||
+ (READ_ONCE(vsk->peer_shutdown) & SEND_SHUTDOWN))
+ return 1;
+
+ return 0;
+}
+
int
__vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
int flags)
@@ -2606,6 +2638,13 @@ __vsock_connectible_recvmsg(struct socket *sock, struct
msghdr *msg, size_t len,
err = __vsock_seqpacket_recvmsg(sk, msg, len, flags);
out:
+ if (msg->msg_get_inq && err >= 0 && sk->sk_type == SOCK_STREAM) {
Why only STREAM?
A comment here and in the commit would be nice.
+ int inq = vsock_inq_hint(sk);
+
+ if (inq >= 0)
Why assigning only >= 0 values?
Thanks,
Stefano
+ msg->msg_inq = inq;
+ }
+
release_sock(sk);
return err;
}
--
2.55.0
