Linux Virtualization - May 2021 - [RFC PATCH v9 04/19] af_vsock: implement SEQPACKET receive loop

On Sat, May 08, 2021 at 07:33:14PM +0300, Arseny Krasnov
wrote:
>This adds receive loop for SEQPACKET. It looks like receive loop for
>STREAM, but there is a little bit difference:
>1) It doesn't call notify callbacks.
>2) It doesn't care about 'SO_SNDLOWAT' and 'SO_RCVLOWAT'
values, because
>   there is no sense for these values in SEQPACKET case.
>3) It waits until whole record is received or error is found during
>   receiving.
>4) It processes and sets 'MSG_TRUNC' flag.
>
>So to avoid extra conditions for two types of socket inside one loop, two
>independent functions were created.
>
>Signed-off-by: Arseny Krasnov <arseny.krasnov at kaspersky.com>
>---
> v8 -> v9:
> 1) 'tmp_record_len' renamed to 'fragment_len'.
> 2) MSG_TRUNC handled in af_vsock.c instead of transport.
> 3) 'flags' still passed to transport for MSG_PEEK support.
Ah, right I see, sorry for the wrong suggestion to remove it.
>
> include/net/af_vsock.h   |  4 +++
> net/vmw_vsock/af_vsock.c | 72 +++++++++++++++++++++++++++++++++++++++-
> 2 files changed, 75 insertions(+), 1 deletion(-)
>
>diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
>index b1c717286993..5175f5a52ce1 100644
>--- a/include/net/af_vsock.h
>+++ b/include/net/af_vsock.h
>@@ -135,6 +135,10 @@ struct vsock_transport {
> 	bool (*stream_is_active)(struct vsock_sock *);
> 	bool (*stream_allow)(u32 cid, u32 port);
>
>+	/* SEQ_PACKET. */
>+	ssize_t (*seqpacket_dequeue)(struct vsock_sock *vsk, struct msghdr *msg,
>+				     int flags, bool *msg_ready);
>+
> 	/* Notification. */
> 	int (*notify_poll_in)(struct vsock_sock *, size_t, bool *);
> 	int (*notify_poll_out)(struct vsock_sock *, size_t, bool *);
>diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
>index c4f6bfa1e381..78b9af545ca8 100644
>--- a/net/vmw_vsock/af_vsock.c
>+++ b/net/vmw_vsock/af_vsock.c
>@@ -1974,6 +1974,73 @@ static int __vsock_stream_recvmsg(struct sock *sk,
struct msghdr *msg,
> 	return err;
> }
>
>+static int __vsock_seqpacket_recvmsg(struct sock *sk, struct msghdr *msg,
>+				     size_t len, int flags)
>+{
>+	const struct vsock_transport *transport;
>+	bool msg_ready;
>+	struct vsock_sock *vsk;
>+	ssize_t record_len;
>+	long timeout;
>+	int err = 0;
>+	DEFINE_WAIT(wait);
>+
>+	vsk = vsock_sk(sk);
>+	transport = vsk->transport;
>+
>+	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
>+	msg_ready = false;
>+	record_len = 0;
>+
>+	while (1) {
>+		ssize_t fragment_len;
>+
>+		if (vsock_wait_data(sk, &wait, timeout, NULL, 0) <= 0) {
>+			/* In case of any loop break(timeout, signal
>+			 * interrupt or shutdown), we report user that
>+			 * nothing was copied.
>+			 */
>+			err = 0;
>+			break;
>+		}
>+
>+		fragment_len = transport->seqpacket_dequeue(vsk, msg, flags,
&msg_ready);
>+
So, IIUC, seqpacket_dequeue() must return the real length,
and not the bytes copied, right?

I'm not sure virtio_transport_seqpacket_do_dequeue() is doing that.
I'll post a comment on that patch.
>+		if (fragment_len < 0) {
>+			err = -ENOMEM;
>+			break;
>+		}
>+
>+		record_len += fragment_len;
>+
>+		if (msg_ready)
>+			break;
>+	}
>+
>+	if (sk->sk_err)
>+		err = -sk->sk_err;
>+	else if (sk->sk_shutdown & RCV_SHUTDOWN)
>+		err = 0;
>+
>+	if (msg_ready && err == 0) {
>+		/* User sets MSG_TRUNC, so return real length of
>+		 * packet.
>+		 */
>+		if (flags & MSG_TRUNC)
>+			err = record_len;
>+		else
>+			err = len - msg->msg_iter.count;
I think is better to use msg_data_left(msg) instead of accessing fields.
>+
>+		/* Always set MSG_TRUNC if real length of packet is
>+		 * bigger than user's buffer.
>+		 */
>+		if (record_len > len)
>+			msg->msg_flags |= MSG_TRUNC;
>+	}
>+
>+	return err;
>+}
>+
> static int
> vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t
len,
> 			  int flags)
>@@ -2029,7 +2096,10 @@ vsock_connectible_recvmsg(struct socket *sock, struct
msghdr *msg, size_t len,
> 		goto out;
> 	}
>
>-	err = __vsock_stream_recvmsg(sk, msg, len, flags);
>+	if (sk->sk_type == SOCK_STREAM)
>+		err = __vsock_stream_recvmsg(sk, msg, len, flags);
>+	else
>+		err = __vsock_seqpacket_recvmsg(sk, msg, len, flags);
>
> out:
> 	release_sock(sk);
>-- 
>2.25.1
>