1 files changed, 68 insertions, 16 deletions

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 2e7a3034e965..ead6a3c14b87 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -407,6 +407,8 @@ EXPORT_SYMBOL_GPL(vsock_enqueue_accept);
 
 static bool vsock_use_local_transport(unsigned int remote_cid)
 {
+	lockdep_assert_held(&vsock_register_mutex);
+
 	if (!transport_local)
 		return false;
 
@@ -464,6 +466,8 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 
 	remote_flags = vsk->remote_addr.svm_flags;
 
+	mutex_lock(&vsock_register_mutex);
+
 	switch (sk->sk_type) {
 	case SOCK_DGRAM:
 		new_transport = transport_dgram;
@@ -479,12 +483,15 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 			new_transport = transport_h2g;
 		break;
 	default:
-		return -ESOCKTNOSUPPORT;
+		ret = -ESOCKTNOSUPPORT;
+		goto err;
 	}
 
 	if (vsk->transport) {
-		if (vsk->transport == new_transport)
-			return 0;
+		if (vsk->transport == new_transport) {
+			ret = 0;
+			goto err;
+		}
 
 		/* transport->release() must be called with sock lock acquired.
 		 * This path can only be taken during vsock_connect(), where we
@@ -508,8 +515,16 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 	/* We increase the module refcnt to prevent the transport unloading
 	 * while there are open sockets assigned to it.
 	 */
-	if (!new_transport || !try_module_get(new_transport->module))
-		return -ENODEV;
+	if (!new_transport || !try_module_get(new_transport->module)) {
+		ret = -ENODEV;
+		goto err;
+	}
+
+	/* It's safe to release the mutex after a successful try_module_get().
+	 * Whichever transport `new_transport` points at, it won't go away until
+	 * the last module_put() below or in vsock_deassign_transport().
+	 */
+	mutex_unlock(&vsock_register_mutex);
 
 	if (sk->sk_type == SOCK_SEQPACKET) {
 		if (!new_transport->seqpacket_allow ||
@@ -528,12 +543,31 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 	vsk->transport = new_transport;
 
 	return 0;
+err:
+	mutex_unlock(&vsock_register_mutex);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(vsock_assign_transport);
 
+/*
+ * Provide safe access to static transport_{h2g,g2h,dgram,local} callbacks.
+ * Otherwise we may race with module removal. Do not use on `vsk->transport`.
+ */
+static u32 vsock_registered_transport_cid(const struct vsock_transport **transport)
+{
+	u32 cid = VMADDR_CID_ANY;
+
+	mutex_lock(&vsock_register_mutex);
+	if (*transport)
+		cid = (*transport)->get_local_cid();
+	mutex_unlock(&vsock_register_mutex);
+
+	return cid;
+}
+
 bool vsock_find_cid(unsigned int cid)
 {
-	if (transport_g2h && cid == transport_g2h->get_local_cid())
+	if (cid == vsock_registered_transport_cid(&transport_g2h))
 		return true;
 
 	if (transport_h2g && cid == VMADDR_CID_HOST)
@@ -994,11 +1028,6 @@ static int vsock_getname(struct socket *sock,
 		vm_addr = &vsk->local_addr;
 	}
 
-	if (!vm_addr) {
-		err = -EINVAL;
-		goto out;
-	}
-
 	/* sys_getsockname() and sys_getpeername() pass us a
 	 * MAX_SOCK_ADDR-sized buffer and don't set addr_len.  Unfortunately
 	 * that macro is defined in socket.c instead of .h, so we hardcode its
@@ -1389,6 +1418,28 @@ static int vsock_do_ioctl(struct socket *sock, unsigned int cmd,
 	vsk = vsock_sk(sk);
 
 	switch (cmd) {
+	case SIOCINQ: {
+		ssize_t n_bytes;
+
+		if (!vsk->transport) {
+			ret = -EOPNOTSUPP;
+			break;
+		}
+
+		if (sock_type_connectible(sk->sk_type) &&
+		    sk->sk_state == TCP_LISTEN) {
+			ret = -EINVAL;
+			break;
+		}
+
+		n_bytes = vsock_stream_has_data(vsk);
+		if (n_bytes < 0) {
+			ret = n_bytes;
+			break;
+		}
+		ret = put_user(n_bytes, arg);
+		break;
+	}
 	case SIOCOUTQ: {
 		ssize_t n_bytes;
 
@@ -2536,18 +2587,19 @@ static long vsock_dev_do_ioctl(struct file *filp,
 			       unsigned int cmd, void __user *ptr)
 {
 	u32 __user *p = ptr;
-	u32 cid = VMADDR_CID_ANY;
 	int retval = 0;
+	u32 cid;
 
 	switch (cmd) {
 	case IOCTL_VM_SOCKETS_GET_LOCAL_CID:
 		/* To be compatible with the VMCI behavior, we prioritize the
 		 * guest CID instead of well-know host CID (VMADDR_CID_HOST).
 		 */
-		if (transport_g2h)
-			cid = transport_g2h->get_local_cid();
-		else if (transport_h2g)
-			cid = transport_h2g->get_local_cid();
+		cid = vsock_registered_transport_cid(&transport_g2h);
+		if (cid == VMADDR_CID_ANY)
+			cid = vsock_registered_transport_cid(&transport_h2g);
+		if (cid == VMADDR_CID_ANY)
+			cid = vsock_registered_transport_cid(&transport_local);
 
 		if (put_user(cid, p) != 0)
 			retval = -EFAULT;