virtio/vsock: dequeue callback for SOCK_SEQPACKET

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@kaspersky.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/virtio_vsock.h

@@ -36,6 +36,7 @@ struct virtio_vsock_sock {
 	u32 rx_bytes;
 	u32 buf_alloc;
 	struct list_head rx_queue;
+	u32 msg_count;
 };
 
 struct virtio_vsock_pkt {
@@ -80,6 +81,10 @@ 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);
 s64 virtio_transport_stream_has_data(struct vsock_sock *vsk);
 s64 virtio_transport_stream_has_space(struct vsock_sock *vsk);
 

net/vmw_vsock/virtio_transport_common.c

@@ -393,6 +393,78 @@ out:
 	return err;
 }
 
+static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk,
+						 struct msghdr *msg,
+						 int flags)
+{
+	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);
+	bool copy_failed = false;
+	bool msg_ready = false;
+
+	spin_lock_bh(&vvs->rx_lock);
+
+	if (vvs->msg_count == 0) {
+		spin_unlock_bh(&vvs->rx_lock);
+		return 0;
+	}
+
+	while (!msg_ready) {
+		pkt = list_first_entry(&vvs->rx_queue, struct virtio_vsock_pkt, list);
+
+		if (!copy_failed) {
+			size_t pkt_len;
+			size_t bytes_to_copy;
+
+			pkt_len = (size_t)le32_to_cpu(pkt->hdr.len);
+			bytes_to_copy = min(user_buf_len, pkt_len);
+
+			if (bytes_to_copy) {
+				int err;
+
+				/* 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);
+
+				err = memcpy_to_msg(msg, pkt->buf, bytes_to_copy);
+				if (err) {
+					/* Copy of message failed, set flag to skip
+					 * copy path for rest of fragments. Rest of
+					 * fragments will be freed without copy.
+					 */
+					copy_failed = true;
+					dequeued_len = err;
+				} else {
+					user_buf_len -= bytes_to_copy;
+				}
+
+				spin_lock_bh(&vvs->rx_lock);
+			}
+
+			if (dequeued_len >= 0)
+				dequeued_len += pkt_len;
+		}
+
+		if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR) {
+			msg_ready = true;
+			vvs->msg_count--;
+		}
+
+		virtio_transport_dec_rx_pkt(vvs, pkt);
+		list_del(&pkt->list);
+		virtio_transport_free_pkt(pkt);
+	}
+
+	spin_unlock_bh(&vvs->rx_lock);
+
+	virtio_transport_send_credit_update(vsk);
+
+	return dequeued_len;
+}
+
 ssize_t
 virtio_transport_stream_dequeue(struct vsock_sock *vsk,
 				struct msghdr *msg,
@@ -405,6 +477,18 @@ virtio_transport_stream_dequeue(struct vsock_sock *vsk,
 }
 EXPORT_SYMBOL_GPL(virtio_transport_stream_dequeue);
 
+ssize_t
+virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk,
+				   struct msghdr *msg,
+				   int flags)
+{
+	if (flags & MSG_PEEK)
+		return -EOPNOTSUPP;
+
+	return virtio_transport_seqpacket_do_dequeue(vsk, msg, flags);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_dequeue);
+
 int
 virtio_transport_dgram_dequeue(struct vsock_sock *vsk,
 			       struct msghdr *msg,