1 files changed, 57 insertions, 20 deletions

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 6a50e1d0529c..c9bb2bd2d494 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -102,7 +102,7 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 		struct iov_iter iov_iter;
 		unsigned out, in;
 		size_t nbytes;
-		size_t len;
+		size_t iov_len, payload_len;
 		int head;
 
 		spin_lock_bh(&vsock->send_pkt_list_lock);
@@ -147,8 +147,24 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 			break;
 		}
 
-		len = iov_length(&vq->iov[out], in);
-		iov_iter_init(&iov_iter, READ, &vq->iov[out], in, len);
+		iov_len = iov_length(&vq->iov[out], in);
+		if (iov_len < sizeof(pkt->hdr)) {
+			virtio_transport_free_pkt(pkt);
+			vq_err(vq, "Buffer len [%zu] too small\n", iov_len);
+			break;
+		}
+
+		iov_iter_init(&iov_iter, READ, &vq->iov[out], in, iov_len);
+		payload_len = pkt->len - pkt->off;
+
+		/* If the packet is greater than the space available in the
+		 * buffer, we split it using multiple buffers.
+		 */
+		if (payload_len > iov_len - sizeof(pkt->hdr))
+			payload_len = iov_len - sizeof(pkt->hdr);
+
+		/* Set the correct length in the header */
+		pkt->hdr.len = cpu_to_le32(payload_len);
 
 		nbytes = copy_to_iter(&pkt->hdr, sizeof(pkt->hdr), &iov_iter);
 		if (nbytes != sizeof(pkt->hdr)) {
@@ -157,33 +173,47 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 			break;
 		}
 
-		nbytes = copy_to_iter(pkt->buf, pkt->len, &iov_iter);
-		if (nbytes != pkt->len) {
+		nbytes = copy_to_iter(pkt->buf + pkt->off, payload_len,
+				      &iov_iter);
+		if (nbytes != payload_len) {
 			virtio_transport_free_pkt(pkt);
 			vq_err(vq, "Faulted on copying pkt buf\n");
 			break;
 		}
 
-		vhost_add_used(vq, head, sizeof(pkt->hdr) + pkt->len);
+		/* Deliver to monitoring devices all packets that we
+		 * will transmit.
+		 */
+		virtio_transport_deliver_tap_pkt(pkt);
+
+		vhost_add_used(vq, head, sizeof(pkt->hdr) + payload_len);
 		added = true;
 
-		if (pkt->reply) {
-			int val;
+		pkt->off += payload_len;
+		total_len += payload_len;
 
-			val = atomic_dec_return(&vsock->queued_replies);
+		/* If we didn't send all the payload we can requeue the packet
+		 * to send it with the next available buffer.
+		 */
+		if (pkt->off < pkt->len) {
+			spin_lock_bh(&vsock->send_pkt_list_lock);
+			list_add(&pkt->list, &vsock->send_pkt_list);
+			spin_unlock_bh(&vsock->send_pkt_list_lock);
+		} else {
+			if (pkt->reply) {
+				int val;
 
-			/* Do we have resources to resume tx processing? */
-			if (val + 1 == tx_vq->num)
-				restart_tx = true;
-		}
+				val = atomic_dec_return(&vsock->queued_replies);
 
-		/* Deliver to monitoring devices all correctly transmitted
-		 * packets.
-		 */
-		virtio_transport_deliver_tap_pkt(pkt);
+				/* Do we have resources to resume tx
+				 * processing?
+				 */
+				if (val + 1 == tx_vq->num)
+					restart_tx = true;
+			}
 
-		total_len += pkt->len;
-		virtio_transport_free_pkt(pkt);
+			virtio_transport_free_pkt(pkt);
+		}
 	} while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len)));
 	if (added)
 		vhost_signal(&vsock->dev, vq);
@@ -405,7 +435,9 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 		virtio_transport_deliver_tap_pkt(pkt);
 
 		/* Only accept correctly addressed packets */
-		if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid)
+		if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid &&
+		    le64_to_cpu(pkt->hdr.dst_cid) ==
+		    vhost_transport_get_local_cid())
 			virtio_transport_recv_pkt(pkt);
 		else
 			virtio_transport_free_pkt(pkt);
@@ -466,6 +498,11 @@ static int vhost_vsock_start(struct vhost_vsock *vsock)
 		mutex_unlock(&vq->mutex);
 	}
 
+	/* Some packets may have been queued before the device was started,
+	 * let's kick the send worker to send them.
+	 */
+	vhost_work_queue(&vsock->dev, &vsock->send_pkt_work);
+
 	mutex_unlock(&vsock->dev.mutex);
 	return 0;