Re: [RFC PATCH v6 14/22] virtio/vsock: rest of SOCK_SEQPACKET support

[Stefano Garzarella <sgarzare@redhat.com>]

On Sun, Mar 07, 2021 at 09:03:09PM +0300, Arseny Krasnov wrote:
>This adds rest of logic for SEQPACKET:
>1) SEQPACKET specific functions which send SEQ_BEGIN/SEQ_END.
>   Note that both functions may sleep to wait enough space for
>   SEQPACKET header.
>2) SEQ_BEGIN/SEQ_END in TAP packet capture.
>3) Send SHUTDOWN on socket close for SEQPACKET type.
>4) Set SEQPACKET packet type during send.
>5) Set MSG_EOR in flags for SEQPACKET during send.
>6) 'seqpacket_allow' flag to virtio transport.
>
>Signed-off-by: Arseny Krasnov <arseny.krasnov@kaspersky.com>
>---
> include/linux/virtio_vsock.h            |  8 +++
> net/vmw_vsock/virtio_transport_common.c | 87 ++++++++++++++++++++++++-
> 2 files changed, 93 insertions(+), 2 deletions(-)
>
>diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
>index d7edcfeb4cd2..6b45a8b98226 100644
>--- a/include/linux/virtio_vsock.h
>+++ b/include/linux/virtio_vsock.h
>@@ -22,6 +22,7 @@ struct virtio_vsock_seqpack_state {
> 	u32 user_read_seq_len;
> 	u32 user_read_copied;
> 	u32 curr_rx_msg_id;
>+	u32 next_tx_msg_id;
> };
>
> /* Per-socket state (accessed via vsk->trans) */
>@@ -76,6 +77,8 @@ struct virtio_transport {
>
> 	/* Takes ownership of the packet */
> 	int (*send_pkt)(struct virtio_vsock_pkt *pkt);
>+
>+	bool seqpacket_allow;
> };
>
> ssize_t
>@@ -90,6 +93,11 @@ virtio_transport_dgram_dequeue(struct vsock_sock *vsk,
>
> size_t virtio_transport_seqpacket_seq_get_len(struct vsock_sock *vsk);
> int
>+virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk,
>+				   struct msghdr *msg,
>+				   int flags,
>+				   size_t len);
>+int
> virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk,
> 				   struct msghdr *msg,
> 				   int flags,
>diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
>index 9d86375935ce..8e9fdd8aba5d 100644
>--- a/net/vmw_vsock/virtio_transport_common.c
>+++ b/net/vmw_vsock/virtio_transport_common.c
>@@ -139,6 +139,8 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque)
> 		break;
> 	case VIRTIO_VSOCK_OP_CREDIT_UPDATE:
> 	case VIRTIO_VSOCK_OP_CREDIT_REQUEST:
>+	case VIRTIO_VSOCK_OP_SEQ_BEGIN:
>+	case VIRTIO_VSOCK_OP_SEQ_END:
> 		hdr->op = cpu_to_le16(AF_VSOCK_OP_CONTROL);
> 		break;
> 	default:
>@@ -187,7 +189,12 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
> 	struct virtio_vsock_pkt *pkt;
> 	u32 pkt_len = info->pkt_len;
>
>-	info->type = VIRTIO_VSOCK_TYPE_STREAM;
>+	info->type = virtio_transport_get_type(sk_vsock(vsk));
>+
>+	if (info->type == VIRTIO_VSOCK_TYPE_SEQPACKET &&
>+	    info->msg &&
>+	    info->msg->msg_flags & MSG_EOR)
>+		info->flags |= VIRTIO_VSOCK_RW_EOR;
>
> 	t_ops = virtio_transport_get_ops(vsk);
> 	if (unlikely(!t_ops))
>@@ -401,6 +408,43 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk,
> 	return err;
> }
>
>+static int virtio_transport_seqpacket_send_ctrl(struct vsock_sock *vsk,
>+						int type,
>+						size_t len,
>+						int flags)
>+{
>+	struct virtio_vsock_sock *vvs = vsk->trans;
>+	struct virtio_vsock_pkt_info info = {
>+		.op = type,
>+		.vsk = vsk,
>+		.pkt_len = sizeof(struct virtio_vsock_seq_hdr)
>+	};
>+
>+	struct virtio_vsock_seq_hdr seq_hdr = {
>+		.msg_id = cpu_to_le32(vvs->seqpacket_state.next_tx_msg_id),
>+		.msg_len = cpu_to_le32(len)
>+	};
>+
>+	struct kvec seq_hdr_kiov = {
>+		.iov_base = (void *)&seq_hdr,
>+		.iov_len = sizeof(struct virtio_vsock_seq_hdr)
>+	};
>+
>+	struct msghdr msg = {0};
>+
>+	//XXX: do we need 'vsock_transport_send_notify_data' pointer?
>+	if (vsock_wait_space(sk_vsock(vsk),
>+			     sizeof(struct virtio_vsock_seq_hdr),
>+			     flags, NULL))
>+		return -1;
>+
>+	iov_iter_kvec(&msg.msg_iter, WRITE, &seq_hdr_kiov, 1, sizeof(seq_hdr));
>+
>+	info.msg = &msg;
>+
>+	return virtio_transport_send_pkt_info(vsk, &info);
>+}
>+
> static inline void virtio_transport_remove_pkt(struct virtio_vsock_pkt *pkt)
> {
> 	list_del(&pkt->list);
>@@ -582,6 +626,45 @@ virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk,
> }
> EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_dequeue);
>
>+int
>+virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk,
>+				   struct msghdr *msg,
>+				   int flags,
>+				   size_t len)
>+{
>+	int written;
>+
>+	if (msg->msg_iter.iov_offset == 0) {
>+		/* Send SEQBEGIN. */
>+		if (virtio_transport_seqpacket_send_ctrl(vsk,
>+							 VIRTIO_VSOCK_OP_SEQ_BEGIN,
>+							 len,
>+							 flags) < 0)
>+			return -1;
>+	}
>+
>+	written = virtio_transport_stream_enqueue(vsk, msg, len);
>+
>+	if (written < 0)
>+		return -1;
>+
>+	if (msg->msg_iter.count == 0) {
>+		struct virtio_vsock_sock *vvs = vsk->trans;
>+
>+		/* Send SEQEND. */
>+		if (virtio_transport_seqpacket_send_ctrl(vsk,
>+							 VIRTIO_VSOCK_OP_SEQ_END,
>+							 0,
>+							 flags) < 0)
>+			return -1;
>+
>+		vvs->seqpacket_state.next_tx_msg_id++;
>+	}

I suspect we should increment next_tx_msg_id even in case of an error to 
avoid issues with packets with same IDs, so in case of error I would do:

	if (/* error */) {
		written = -1;
		goto out;
	}

Then we can add the 'out' label and the id increment:

out:
	vvs->seqpacket_state.next_tx_msg_id++;
>+
>+	return written;
>+}
>+EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_enqueue);
>+
> int
> virtio_transport_dgram_dequeue(struct vsock_sock *vsk,
> 			       struct msghdr *msg,
>@@ -1001,7 +1084,7 @@ void virtio_transport_release(struct vsock_sock *vsk)
> 	struct sock *sk = &vsk->sk;
> 	bool remove_sock = true;
>
>-	if (sk->sk_type == SOCK_STREAM)
>+	if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)
> 		remove_sock = virtio_transport_close(vsk);
>
> 	list_for_each_entry_safe(pkt, tmp, &vvs->rx_queue, list) {
>-- 
>2.25.1
>