vsock: add multi-transports support

This patch adds the support of multiple transports in the
VSOCK core.

With the multi-transports support, we can use vsock with nested VMs
(using also different hypervisors) loading both guest->host and
host->guest transports at the same time.

Major changes:
- vsock core module can be loaded regardless of the transports
- vsock_core_init() and vsock_core_exit() are renamed to
  vsock_core_register() and vsock_core_unregister()
- vsock_core_register() has a feature parameter (H2G, G2H, DGRAM)
  to identify which directions the transport can handle and if it's
  support DGRAM (only vmci)
- each stream socket is assigned to a transport when the remote CID
  is set (during the connect() or when we receive a connection request
  on a listener socket).
  The remote CID is used to decide which transport to use:
  - remote CID <= VMADDR_CID_HOST will use guest->host transport;
  - remote CID == local_cid (guest->host transport) will use guest->host
    transport for loopback (host->guest transports don't support loopback);
  - remote CID > VMADDR_CID_HOST will use host->guest transport;
- listener sockets are not bound to any transports since no transport
  operations are done on it. In this way we can create a listener
  socket, also if the transports are not loaded or with VMADDR_CID_ANY
  to listen on all transports.
- DGRAM sockets are handled as before, since only the vmci_transport
  provides this feature.
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/vhost/vsock.c

@@ -831,7 +831,8 @@ static int __init vhost_vsock_init(void)
 {
 	int ret;
 
-	ret = vsock_core_init(&vhost_transport.transport);
+	ret = vsock_core_register(&vhost_transport.transport,
+				  VSOCK_TRANSPORT_F_H2G);
 	if (ret < 0)
 		return ret;
 	return misc_register(&vhost_vsock_misc);
@@ -840,7 +841,7 @@ static int __init vhost_vsock_init(void)
 static void __exit vhost_vsock_exit(void)
 {
 	misc_deregister(&vhost_vsock_misc);
-	vsock_core_exit();
+	vsock_core_unregister(&vhost_transport.transport);
 };
 
 module_init(vhost_vsock_init);

include/net/af_vsock.h

@@ -91,6 +91,14 @@ struct vsock_transport_send_notify_data {
 	u64 data2; /* Transport-defined. */
 };
 
+/* Transport features flags */
+/* Transport provides host->guest communication */
+#define VSOCK_TRANSPORT_F_H2G		0x00000001
+/* Transport provides guest->host communication */
+#define VSOCK_TRANSPORT_F_G2H		0x00000002
+/* Transport provides DGRAM communication */
+#define VSOCK_TRANSPORT_F_DGRAM		0x00000004
+
 struct vsock_transport {
 	/* Initialize/tear-down socket. */
 	int (*init)(struct vsock_sock *, struct vsock_sock *);
@@ -154,12 +162,8 @@ struct vsock_transport {
 
 /**** CORE ****/
 
-int __vsock_core_init(const struct vsock_transport *t, struct module *owner);
-static inline int vsock_core_init(const struct vsock_transport *t)
-{
-	return __vsock_core_init(t, THIS_MODULE);
-}
-void vsock_core_exit(void);
+int vsock_core_register(const struct vsock_transport *t, int features);
+void vsock_core_unregister(const struct vsock_transport *t);
 
 /* The transport may downcast this to access transport-specific functions */
 const struct vsock_transport *vsock_core_get_transport(struct vsock_sock *vsk);
@@ -190,6 +194,8 @@ struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
 					 struct sockaddr_vm *dst);
 void vsock_remove_sock(struct vsock_sock *vsk);
 void vsock_for_each_connected_socket(void (*fn)(struct sock *sk));
+int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk);
+bool vsock_find_cid(unsigned int cid);
 
 /**** TAP ****/
 

net/vmw_vsock/hyperv_transport.c

@@ -165,6 +165,8 @@ static const guid_t srv_id_template =
 	GUID_INIT(0x00000000, 0xfacb, 0x11e6, 0xbd, 0x58,
 		  0x64, 0x00, 0x6a, 0x79, 0x86, 0xd3);
 
+static bool hvs_check_transport(struct vsock_sock *vsk);
+
 static bool is_valid_srv_id(const guid_t *id)
 {
 	return !memcmp(&id->b[4], &srv_id_template.b[4], sizeof(guid_t) - 4);
@@ -367,6 +369,18 @@ static void hvs_open_connection(struct vmbus_channel *chan)
 
 		new->sk_state = TCP_SYN_SENT;
 		vnew = vsock_sk(new);
+
+		hvs_addr_init(&vnew->local_addr, if_type);
+		hvs_remote_addr_init(&vnew->remote_addr, &vnew->local_addr);
+
+		ret = vsock_assign_transport(vnew, vsock_sk(sk));
+		/* Transport assigned (looking at remote_addr) must be the
+		 * same where we received the request.
+		 */
+		if (ret || !hvs_check_transport(vnew)) {
+			sock_put(new);
+			goto out;
+		}
 		hvs_new = vnew->trans;
 		hvs_new->chan = chan;
 	} else {
@@ -430,9 +444,6 @@ static void hvs_open_connection(struct vmbus_channel *chan)
 		new->sk_state = TCP_ESTABLISHED;
 		sk_acceptq_added(sk);
 
-		hvs_addr_init(&vnew->local_addr, if_type);
-		hvs_remote_addr_init(&vnew->remote_addr, &vnew->local_addr);
-
 		hvs_new->vm_srv_id = *if_type;
 		hvs_new->host_srv_id = *if_instance;
 
@@ -880,6 +891,11 @@ static struct vsock_transport hvs_transport = {
 
 };
 
+static bool hvs_check_transport(struct vsock_sock *vsk)
+{
+	return vsk->transport == &hvs_transport;
+}
+
 static int hvs_probe(struct hv_device *hdev,
 		     const struct hv_vmbus_device_id *dev_id)
 {
@@ -928,7 +944,7 @@ static int __init hvs_init(void)
 	if (ret != 0)
 		return ret;
 
-	ret = vsock_core_init(&hvs_transport);
+	ret = vsock_core_register(&hvs_transport, VSOCK_TRANSPORT_F_G2H);
 	if (ret) {
 		vmbus_driver_unregister(&hvs_drv);
 		return ret;
@@ -939,7 +955,7 @@ static int __init hvs_init(void)
 
 static void __exit hvs_exit(void)
 {
-	vsock_core_exit();
+	vsock_core_unregister(&hvs_transport);
 	vmbus_driver_unregister(&hvs_drv);
 }
 

net/vmw_vsock/virtio_transport.c

@@ -770,7 +770,8 @@ static int __init virtio_vsock_init(void)
 	if (!virtio_vsock_workqueue)
 		return -ENOMEM;
 
-	ret = vsock_core_init(&virtio_transport.transport);
+	ret = vsock_core_register(&virtio_transport.transport,
+				  VSOCK_TRANSPORT_F_G2H);
 	if (ret)
 		goto out_wq;
 
@@ -781,7 +782,7 @@ static int __init virtio_vsock_init(void)
 	return 0;
 
 out_vci:
-	vsock_core_exit();
+	vsock_core_unregister(&virtio_transport.transport);
 out_wq:
 	destroy_workqueue(virtio_vsock_workqueue);
 	return ret;
@@ -790,7 +791,7 @@ static int __init virtio_vsock_init(void)
 static void __exit virtio_vsock_exit(void)
 {
 	unregister_virtio_driver(&virtio_vsock_driver);
-	vsock_core_exit();
+	vsock_core_unregister(&virtio_transport.transport);
 	destroy_workqueue(virtio_vsock_workqueue);
 }
 

net/vmw_vsock/virtio_transport_common.c

@@ -453,7 +453,7 @@ int virtio_transport_do_socket_init(struct vsock_sock *vsk,
 
 	vsk->trans = vvs;
 	vvs->vsk = vsk;
-	if (psk) {
+	if (psk && psk->trans) {
 		struct virtio_vsock_sock *ptrans = psk->trans;
 
 		vvs->peer_buf_alloc = ptrans->peer_buf_alloc;
@@ -986,13 +986,39 @@ virtio_transport_send_response(struct vsock_sock *vsk,
 	return virtio_transport_send_pkt_info(vsk, &info);
 }
 
+static bool virtio_transport_space_update(struct sock *sk,
+					  struct virtio_vsock_pkt *pkt)
+{
+	struct vsock_sock *vsk = vsock_sk(sk);
+	struct virtio_vsock_sock *vvs = vsk->trans;
+	bool space_available;
+
+	/* Listener sockets are not associated with any transport, so we are
+	 * not able to take the state to see if there is space available in the
+	 * remote peer, but since they are only used to receive requests, we
+	 * can assume that there is always space available in the other peer.
+	 */
+	if (!vvs)
+		return true;
+
+	/* buf_alloc and fwd_cnt is always included in the hdr */
+	spin_lock_bh(&vvs->tx_lock);
+	vvs->peer_buf_alloc = le32_to_cpu(pkt->hdr.buf_alloc);
+	vvs->peer_fwd_cnt = le32_to_cpu(pkt->hdr.fwd_cnt);
+	space_available = virtio_transport_has_space(vsk);
+	spin_unlock_bh(&vvs->tx_lock);
+	return space_available;
+}
+
 /* Handle server socket */
 static int
-virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt)
+virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt,
+			     struct virtio_transport *t)
 {
 	struct vsock_sock *vsk = vsock_sk(sk);
 	struct vsock_sock *vchild;
 	struct sock *child;
+	int ret;
 
 	if (le16_to_cpu(pkt->hdr.op) != VIRTIO_VSOCK_OP_REQUEST) {
 		virtio_transport_reset(vsk, pkt);
@@ -1022,6 +1048,20 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt)
 	vsock_addr_init(&vchild->remote_addr, le64_to_cpu(pkt->hdr.src_cid),
 			le32_to_cpu(pkt->hdr.src_port));
 
+	ret = vsock_assign_transport(vchild, vsk);
+	/* Transport assigned (looking at remote_addr) must be the same
+	 * where we received the request.
+	 */
+	if (ret || vchild->transport != &t->transport) {
+		release_sock(child);
+		virtio_transport_reset(vsk, pkt);
+		sock_put(child);
+		return ret;
+	}
+
+	if (virtio_transport_space_update(child, pkt))
+		child->sk_write_space(child);
+
 	vsock_insert_connected(vchild);
 	vsock_enqueue_accept(sk, child);
 	virtio_transport_send_response(vchild, pkt);
@@ -1032,22 +1072,6 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt)
 	return 0;
 }
 
-static bool virtio_transport_space_update(struct sock *sk,
-					  struct virtio_vsock_pkt *pkt)
-{
-	struct vsock_sock *vsk = vsock_sk(sk);
-	struct virtio_vsock_sock *vvs = vsk->trans;
-	bool space_available;
-
-	/* buf_alloc and fwd_cnt is always included in the hdr */
-	spin_lock_bh(&vvs->tx_lock);
-	vvs->peer_buf_alloc = le32_to_cpu(pkt->hdr.buf_alloc);
-	vvs->peer_fwd_cnt = le32_to_cpu(pkt->hdr.fwd_cnt);
-	space_available = virtio_transport_has_space(vsk);
-	spin_unlock_bh(&vvs->tx_lock);
-	return space_available;
-}
-
 /* We are under the virtio-vsock's vsock->rx_lock or vhost-vsock's vq->mutex
  * lock.
  */
@@ -1104,7 +1128,7 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
 
 	switch (sk->sk_state) {
 	case TCP_LISTEN:
-		virtio_transport_recv_listen(sk, pkt);
+		virtio_transport_recv_listen(sk, pkt, t);
 		virtio_transport_free_pkt(pkt);
 		break;
 	case TCP_SYN_SENT:
@@ -1122,6 +1146,7 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
 		virtio_transport_free_pkt(pkt);
 		break;
 	}
+
 	release_sock(sk);
 
 	/* Release refcnt obtained when we fetched this socket out of the

net/vmw_vsock/vmci_transport.c

@@ -57,6 +57,7 @@ static bool vmci_transport_old_proto_override(bool *old_pkt_proto);
 static u16 vmci_transport_new_proto_supported_versions(void);
 static bool vmci_transport_proto_to_notify_struct(struct sock *sk, u16 *proto,
 						  bool old_pkt_proto);
+static bool vmci_check_transport(struct vsock_sock *vsk);
 
 struct vmci_transport_recv_pkt_info {
 	struct work_struct work;
@@ -1017,6 +1018,16 @@ static int vmci_transport_recv_listen(struct sock *sk,
 	vsock_addr_init(&vpending->remote_addr, pkt->dg.src.context,
 			pkt->src_port);
 
+	err = vsock_assign_transport(vpending, vsock_sk(sk));
+	/* Transport assigned (looking at remote_addr) must be the same
+	 * where we received the request.
+	 */
+	if (err || !vmci_check_transport(vpending)) {
+		vmci_transport_send_reset(sk, pkt);
+		sock_put(pending);
+		return err;
+	}
+
 	/* If the proposed size fits within our min/max, accept it. Otherwise
 	 * propose our own size.
 	 */
@@ -2008,7 +2019,7 @@ static u32 vmci_transport_get_local_cid(void)
 	return vmci_get_context_id();
 }
 
-static const struct vsock_transport vmci_transport = {
+static struct vsock_transport vmci_transport = {
 	.init = vmci_transport_socket_init,
 	.destruct = vmci_transport_destruct,
 	.release = vmci_transport_release,
@@ -2038,10 +2049,25 @@ static const struct vsock_transport vmci_transport = {
 	.get_local_cid = vmci_transport_get_local_cid,
 };
 
+static bool vmci_check_transport(struct vsock_sock *vsk)
+{
+	return vsk->transport == &vmci_transport;
+}
+
 static int __init vmci_transport_init(void)
 {
+	int features = VSOCK_TRANSPORT_F_DGRAM | VSOCK_TRANSPORT_F_H2G;
+	int cid;
 	int err;
 
+	cid = vmci_get_context_id();
+
+	if (cid == VMCI_INVALID_ID)
+		return -EINVAL;
+
+	if (cid != VMCI_HOST_CONTEXT_ID)
+		features |= VSOCK_TRANSPORT_F_G2H;
+
 	/* Create the datagram handle that we will use to send and receive all
 	 * VSocket control messages for this context.
 	 */
@@ -2065,7 +2091,7 @@ static int __init vmci_transport_init(void)
 		goto err_destroy_stream_handle;
 	}
 
-	err = vsock_core_init(&vmci_transport);
+	err = vsock_core_register(&vmci_transport, features);
 	if (err < 0)
 		goto err_unsubscribe;
 
@@ -2096,7 +2122,7 @@ static void __exit vmci_transport_exit(void)
 		vmci_transport_qp_resumed_sub_id = VMCI_INVALID_ID;
 	}
 
-	vsock_core_exit();
+	vsock_core_unregister(&vmci_transport);
 }
 module_exit(vmci_transport_exit);