Virtualization - Jun 2021 - [PATCH v10 11/18] virtio/vsock: dequeue callback for SOCK_SEQPACKET

On Thu, May 20, 2021 at 10:17:58PM +0300, Arseny Krasnov
wrote:
>Callback fetches RW packets from rx queue of socket until whole record
>is copied(if user's buffer is full, user is not woken up). This is done
>to not stall sender, because if we wake up user and it leaves syscall,
>nobody will send credit update for rest of record, and sender will wait
>for next enter of read syscall at receiver's side. So if user buffer is
>full, we just send credit update and drop data.
>
>Signed-off-by: Arseny Krasnov <arseny.krasnov at kaspersky.com>
>---
> v9 -> v10:
> 1) Number of dequeued bytes incremented even in case when
>    user's buffer is full.
> 2) Use 'msg_data_left()' instead of direct access to
'msg_hdr'.
> 3) Rename variable 'err' to 'dequeued_len', in case of
error
>    it has negative value.
>
> include/linux/virtio_vsock.h            |  5 ++
> net/vmw_vsock/virtio_transport_common.c | 65 +++++++++++++++++++++++++
> 2 files changed, 70 insertions(+)
>
>diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
>index dc636b727179..02acf6e9ae04 100644
>--- a/include/linux/virtio_vsock.h
>+++ b/include/linux/virtio_vsock.h
>@@ -80,6 +80,11 @@ virtio_transport_dgram_dequeue(struct vsock_sock *vsk,
> 			       struct msghdr *msg,
> 			       size_t len, int flags);
>
>+ssize_t
>+virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk,
>+				   struct msghdr *msg,
>+				   int flags,
>+				   bool *msg_ready);
> s64 virtio_transport_stream_has_data(struct vsock_sock *vsk);
> s64 virtio_transport_stream_has_space(struct vsock_sock *vsk);
>
>diff --git a/net/vmw_vsock/virtio_transport_common.c
b/net/vmw_vsock/virtio_transport_common.c
>index ad0d34d41444..61349b2ea7fe 100644
>--- a/net/vmw_vsock/virtio_transport_common.c
>+++ b/net/vmw_vsock/virtio_transport_common.c
>@@ -393,6 +393,59 @@ virtio_transport_stream_do_dequeue(struct vsock_sock
*vsk,
> 	return err;
> }
>
>+static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk,
>+						 struct msghdr *msg,
>+						 int flags,
>+						 bool *msg_ready)
>+{
>+	struct virtio_vsock_sock *vvs = vsk->trans;
>+	struct virtio_vsock_pkt *pkt;
>+	int dequeued_len = 0;
>+	size_t user_buf_len = msg_data_left(msg);
>+
>+	*msg_ready = false;
>+	spin_lock_bh(&vvs->rx_lock);
>+
>+	while (!*msg_ready && !list_empty(&vvs->rx_queue)
&& dequeued_len >= 0) {
I'
>+		size_t bytes_to_copy;
>+		size_t pkt_len;
>+
>+		pkt = list_first_entry(&vvs->rx_queue, struct virtio_vsock_pkt,
list);
>+		pkt_len = (size_t)le32_to_cpu(pkt->hdr.len);
>+		bytes_to_copy = min(user_buf_len, pkt_len);
>+
>+		if (bytes_to_copy) {
>+			/* sk_lock is held by caller so no one else can dequeue.
>+			 * Unlock rx_lock since memcpy_to_msg() may sleep.
>+			 */
>+			spin_unlock_bh(&vvs->rx_lock);
>+
>+			if (memcpy_to_msg(msg, pkt->buf, bytes_to_copy))
>+				dequeued_len = -EINVAL;
I think here is better to return the error returned by memcpy_to_msg(), 
as we do in the other place where we use memcpy_to_msg().

I mean something like this:
			err = memcpy_to_msgmsg, pkt->buf, bytes_to_copy);
			if (err)
				dequeued_len = err;
>+			else
>+				user_buf_len -= bytes_to_copy;
>+
>+			spin_lock_bh(&vvs->rx_lock);
>+		}
>+
Maybe here we can simply break the cycle if we have an error:
		if (dequeued_len < 0)
			break;

Or we can refactor a bit, simplifying the while() condition and also the 
code in this way (not tested):

	while (!*msg_ready && !list_empty(&vvs->rx_queue)) {
		...

		if (bytes_to_copy) {
			int err;

			/* ...
			*/
			spin_unlock_bh(&vvs->rx_lock);
			err = memcpy_to_msgmsg, pkt->buf, bytes_to_copy);
			if (err) {
				dequeued_len = err;
				goto out;
			}
			spin_lock_bh(&vvs->rx_lock);

			user_buf_len -= bytes_to_copy;
		}

		dequeued_len += pkt_len;

		if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR)
			*msg_ready = true;

		virtio_transport_dec_rx_pkt(vvs, pkt);
		list_del(&pkt->list);
		virtio_transport_free_pkt(pkt);
	}

out:
	spin_unlock_bh(&vvs->rx_lock);

	virtio_transport_send_credit_update(vsk);

	return dequeued_len;
}