[PATCH net-next 2/6] vsock: add IOCTL_VM_SOCKETS_ASSIGN_G2H_NETNS

[Bobby Eshleman <bobbyeshleman@gmail.com>]

From: Bobby Eshleman <bobbyeshleman@meta.com>

Namespaces let a host isolate a VM's vsock traffic to a specific
namespace, but in a guest vsock traffic cannot be isolated to a
namespace. The vsock device is hardcoded to global mode and can't be
moved into a local-mode namespace.

Introduce ioctl IOCTL_VM_SOCKETS_ASSIGN_G2H_NETNS on /dev/vsock that
gives userspace a way to move the device to the calling pid's namespace.
The call requires CAP_NET_ADMIN in the root user namespace. A privileged
user wishing to "unassign" the device can move it to the init_netns,
which is hardcoded to global mode (so no unassign call is necessary).

A getter to read the current assignment back was considered, returning
either the namespace's net_cookie or its nsfs inode number, but neither
seemed useful enough to bake into the uAPI now. It can be added later if
a user turns up that needs it.

Add a transport hook to indicate support for guest namespacing, so that
transports may opt in/out. A transport that opts out keeps the
reachability rules it had before this ioctl existed.

Sockets are reset when the underlying device moves to a different
namespace, so as to prevent reachability from the previous and now
disallowed namespace.

Following the approach of netdevs, the device returns to init_net when
its namespace is removed. Care is taken to not break flows when the
device is inside a global namespace that is being torn down and alive
sockets are in a different global namespace. In this scenario, the
device's netns getter pre-emptively falls back to the init_net (always
global) so that these flows are not disrupted. If init_netns ever
supports local-mode in the future, this logic will have to be changed.

Suggested-by: Stefano Garzarella <sgarzare@redhat.com>
Link: https://lore.kernel.org/all/20200427142518.uwssa6dtasrp3bfc@steredhat/
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
 Documentation/admin-guide/sysctl/net.rst |  18 +++
 include/net/af_vsock.h                   |   7 ++
 include/uapi/linux/vm_sockets.h          |   6 +
 net/vmw_vsock/af_vsock.c                 | 198 ++++++++++++++++++++++++++++++-
 4 files changed, 228 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst
index e586e17fc7a5..1e9c0d2be7b8 100644
--- a/Documentation/admin-guide/sysctl/net.rst
+++ b/Documentation/admin-guide/sysctl/net.rst
@@ -515,6 +515,24 @@ their hosts. The behavior of VSOCK sockets in a network namespace is determined
 by the namespace's mode (``global`` or ``local``), which controls how CIDs
 (Context IDs) are allocated and how sockets interact across namespaces.
 
+In a guest, the vsock device owned by the guest-to-host (G2H) transport belongs
+to one network namespace at a time. The ``IOCTL_VM_SOCKETS_ASSIGN_G2H_NETNS``
+ioctl on ``/dev/vsock`` moves it to the namespace of the calling process, which
+requires ``CAP_NET_ADMIN`` in the initial user namespace. The namespace's mode
+decides who may then use the device:
+
+- ``global`` - every ``global`` mode namespace may use it.
+- ``local`` - only that namespace may use it, which reserves the connection to
+  the host for it alone.
+
+The device starts out in the initial namespace, so until the ioctl is issued
+nothing has moved and no mode has changed.
+
+Connections made before the move, from a namespace that can no longer reach the
+device, are reset. The device returns to the initial namespace when the
+namespace it was moved to is deleted, so assigning it to the initial namespace
+is how an assignment is undone.
+
 ns_mode
 -------
 
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index 87fdec60ba45..64c4b205a11b 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -190,6 +190,9 @@ struct vsock_transport {
 
 	/* Zero-copy. */
 	bool (*msgzerocopy_allow)(void);
+
+	/* True if the transport honours IOCTL_VM_SOCKETS_ASSIGN_G2H_NETNS. */
+	bool (*netns_assign_allow)(void);
 };
 
 /**** CORE ****/
@@ -235,6 +238,10 @@ void vsock_for_each_connected_socket(const struct vsock_transport *transport,
 int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk);
 bool vsock_find_cid(unsigned int cid);
 void vsock_linger(struct sock *sk);
+struct net *vsock_g2h_net_get(void);
+bool vsock_g2h_net_reachable(struct net *net);
+bool vsock_g2h_reachable_sk(struct vsock_sock *vsk);
+bool vsock_maybe_set_connected(struct vsock_sock *vsk);
 
 /**** TAP ****/
 
diff --git a/include/uapi/linux/vm_sockets.h b/include/uapi/linux/vm_sockets.h
index e05280e41522..894b0d65b458 100644
--- a/include/uapi/linux/vm_sockets.h
+++ b/include/uapi/linux/vm_sockets.h
@@ -195,6 +195,12 @@ struct sockaddr_vm {
 
 #define IOCTL_VM_SOCKETS_GET_LOCAL_CID		_IO(7, 0xb9)
 
+/* Assign the guest's vsock device to the network namespace of the calling
+ * process. Requires CAP_NET_ADMIN in the initial user namespace. To undo an
+ * assignment, assign the device to the initial network namespace.
+ */
+#define IOCTL_VM_SOCKETS_ASSIGN_G2H_NETNS	_IO(7, 0xba)
+
 /* MSG_ZEROCOPY notifications are encoded in the standard error format,
  * sock_extended_err. See Documentation/networking/msg_zerocopy.rst in
  * kernel source tree for more details.
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 29cde17e08f3..ad11f0f56eb8 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -130,6 +130,24 @@
  *       a different transport that *does* support local mode. For
  *       example, virtio-vsock may not support local mode, but the socket
  *       may still accept a connection from vhost-vsock which does.
+ *
+ * - A guest has a single vsock device, owned by the guest->host transport.
+ *   IOCTL_VM_SOCKETS_ASSIGN_G2H_NETNS on /dev/vsock assigns it to the
+ *   namespace of the caller. It starts out in init_net. The mode rules then
+ *   decide who may use it, and which namespace packets from the host are
+ *   delivered to:
+ *
+ *   - assigned to a global mode namespace - every global mode namespace may
+ *     use it. Until the ioctl is issued nothing has moved and no mode has
+ *     changed, so the default is the behaviour that predates it.
+ *   - assigned to a local mode namespace - only that namespace may use it.
+ *     This is how a nested VM is isolated from the rest of the guest.
+ *
+ *   Connections made before an assignment, from a namespace that can no
+ *   longer reach the device, are reset.
+ *
+ *   No reference is taken on the assigned namespace. As is done for netdevs,
+ *   the device is moved back to init_net when that namespace is destroyed.
  */
 
 #include <linux/compat.h>
@@ -208,6 +226,11 @@ static const struct vsock_transport *transport_dgram;
 static const struct vsock_transport *transport_local;
 static DEFINE_MUTEX(vsock_register_mutex);
 
+/* Network namespace of the g2h device. Protected by
+ * vsock_register_mutex/RCU.
+ */
+static struct net __rcu *vsock_g2h_net = RCU_INITIALIZER(&init_net);
+
 /**** UTILS ****/
 
 /* Each bound VSocket is stored in the bind hash table and each connected
@@ -548,6 +571,17 @@ static void vsock_deassign_transport(struct vsock_sock *vsk)
 	vsk->transport = NULL;
 }
 
+/* Return true if the loaded g2h transport honours namespace assignment. One
+ * that does not keeps the reachability rules it had before the ioctl existed.
+ *
+ * Must be called with vsock_register_mutex held.
+ */
+static bool vsock_g2h_netns_assignable(void)
+{
+	return transport_g2h && transport_g2h->netns_assign_allow &&
+	       transport_g2h->netns_assign_allow();
+}
+
 /* Assign a transport to a socket and call the .init transport callback.
  *
  * Note: for connection oriented socket this must be called when vsk->remote_addr
@@ -622,6 +656,13 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 		goto err;
 	}
 
+	if (new_transport && new_transport == transport_g2h &&
+	    vsock_g2h_netns_assignable() &&
+	    !vsock_g2h_net_reachable(sock_net(sk))) {
+		ret = -ENETUNREACH;
+		goto err;
+	}
+
 	/* We increase the module refcnt to prevent the transport unloading
 	 * while there are open sockets assigned to it.
 	 */
@@ -710,6 +751,140 @@ bool vsock_find_cid(unsigned int cid)
 }
 EXPORT_SYMBOL_GPL(vsock_find_cid);
 
+/* Return the g2h devices' namespace with a reference held, or NULL if that
+ * namespace is being destroyed.
+ */
+struct net *vsock_g2h_net_get(void)
+{
+	struct net *assigned;
+	struct net *net;
+
+	rcu_read_lock();
+	assigned = rcu_dereference(vsock_g2h_net);
+	net = maybe_get_net(assigned);
+
+	/* !net means the net is about to be destroyed, at which point the g2h
+	 * device will move to the init_net.  If the init_net and the dying net
+	 * are both global mode, we use the init_net as a fallback to avoid
+	 * disrupting global-mode flows. The per-net destructor hook will
+	 * eventually move the g2h device to the init_net anyway.
+	 */
+	if (!net && vsock_net_check_mode(&init_net, assigned))
+		net = get_net(&init_net);
+	rcu_read_unlock();
+
+	return net;
+}
+EXPORT_SYMBOL_GPL(vsock_g2h_net_get);
+
+bool vsock_g2h_net_reachable(struct net *net)
+{
+	bool reachable;
+
+	rcu_read_lock();
+	reachable = vsock_net_check_mode(net, rcu_dereference(vsock_g2h_net));
+	rcu_read_unlock();
+
+	return reachable;
+}
+EXPORT_SYMBOL_GPL(vsock_g2h_net_reachable);
+
+bool vsock_g2h_reachable_sk(struct vsock_sock *vsk)
+{
+	const struct vsock_transport *t = vsk->transport;
+
+	if (!t || !t->netns_assign_allow || !t->netns_assign_allow())
+		return true;
+
+	return vsock_g2h_net_reachable(sock_net(sk_vsock(vsk)));
+}
+EXPORT_SYMBOL_GPL(vsock_g2h_reachable_sk);
+
+/* Move @vsk to TCP_ESTABLISHED and into the connected table, unless the device
+ * has moved to a namespace @vsk cannot reach. Returns false without doing
+ * either in that case.
+ *
+ * vsock_g2h_net_assign() resets the sockets it finds in the same table under
+ * the same lock. Either vsock_g2h_net_assign() sees the vsk in the table and
+ * resets it, or it does not see the @vsk in the table and this function
+ * refuses to add it. This avoids netns assignment racing with outstanding
+ * connection responses and incoming connection requests.
+ */
+bool vsock_maybe_set_connected(struct vsock_sock *vsk)
+{
+	struct list_head *list = vsock_connected_sockets(&vsk->remote_addr,
+							 &vsk->local_addr);
+	bool reachable;
+
+	spin_lock_bh(&vsock_table_lock);
+	reachable = vsock_g2h_reachable_sk(vsk);
+	if (reachable) {
+		sk_vsock(vsk)->sk_state = TCP_ESTABLISHED;
+		__vsock_insert_connected(list, vsk);
+	}
+	spin_unlock_bh(&vsock_table_lock);
+
+	return reachable;
+}
+EXPORT_SYMBOL_GPL(vsock_maybe_set_connected);
+
+static void vsock_reset_unreachable_sock(struct sock *sk)
+{
+	if (vsock_g2h_net_reachable(sock_net(sk)))
+		return;
+
+	sk->sk_state = TCP_CLOSE;
+	sk->sk_err = ECONNRESET;
+	sk_error_report(sk);
+}
+
+/* Move the g2h device to @net. Returns -ENODEV if no g2h transport is loaded
+ * and -EOPNOTSUPP if the loaded one cannot be moved.
+ */
+static int vsock_g2h_net_assign(struct net *net)
+{
+	int ret = 0;
+
+	mutex_lock(&vsock_register_mutex);
+	if (!transport_g2h) {
+		ret = -ENODEV;
+	} else if (!vsock_g2h_netns_assignable()) {
+		ret = -EOPNOTSUPP;
+	} else {
+		/* See vsock_maybe_set_connected() comment about synchronizing
+		 * with connecting sockets.
+		 */
+		rcu_assign_pointer(vsock_g2h_net, net);
+		vsock_for_each_connected_socket(transport_g2h,
+						vsock_reset_unreachable_sock);
+	}
+	mutex_unlock(&vsock_register_mutex);
+
+	return ret;
+}
+
+/* Move the g2h device back to init_net if it lives in @net, which is about to
+ * be destroyed.
+ */
+static void vsock_g2h_net_reset(struct net *net)
+{
+	bool reset = false;
+
+	/* Avoid taking the mutex if the namespaces don't match. */
+	if (likely(rcu_access_pointer(vsock_g2h_net) != net))
+		return;
+
+	mutex_lock(&vsock_register_mutex);
+	if (rcu_access_pointer(vsock_g2h_net) == net) {
+		rcu_assign_pointer(vsock_g2h_net, &init_net);
+		reset = true;
+	}
+	mutex_unlock(&vsock_register_mutex);
+
+	if (reset)
+		synchronize_rcu();
+}
+
 static struct sock *vsock_dequeue_accept(struct sock *listener)
 {
 	struct vsock_sock *vlistener;
@@ -2745,6 +2920,15 @@ static long vsock_dev_do_ioctl(struct file *filp,
 			retval = -EFAULT;
 		break;
 
+	case IOCTL_VM_SOCKETS_ASSIGN_G2H_NETNS:
+		if (!capable(CAP_NET_ADMIN)) {
+			retval = -EPERM;
+			break;
+		}
+
+		retval = vsock_g2h_net_assign(current->nsproxy->net_ns);
+		break;
+
 	default:
 		retval = -ENOIOCTLCMD;
 	}
@@ -2978,6 +3162,7 @@ static __net_init int vsock_sysctl_init_net(struct net *net)
 
 static __net_exit void vsock_sysctl_exit_net(struct net *net)
 {
+	vsock_g2h_net_reset(net);
 	vsock_sysctl_unregister(net);
 }
 
@@ -3104,13 +3289,21 @@ EXPORT_SYMBOL_GPL(vsock_core_register);
 
 void vsock_core_unregister(const struct vsock_transport *t)
 {
+	bool g2h_net_reset = false;
+
 	mutex_lock(&vsock_register_mutex);
 
 	if (transport_h2g == t)
 		transport_h2g = NULL;
 
-	if (transport_g2h == t)
+	if (transport_g2h == t) {
 		transport_g2h = NULL;
+		/* The device is gone, so is its namespace assignment. */
+		if (rcu_access_pointer(vsock_g2h_net) != &init_net) {
+			rcu_assign_pointer(vsock_g2h_net, &init_net);
+			g2h_net_reset = true;
+		}
+	}
 
 	if (transport_dgram == t)
 		transport_dgram = NULL;
@@ -3119,6 +3312,9 @@ void vsock_core_unregister(const struct vsock_transport *t)
 		transport_local = NULL;
 
 	mutex_unlock(&vsock_register_mutex);
+
+	if (g2h_net_reset)
+		synchronize_rcu();
 }
 EXPORT_SYMBOL_GPL(vsock_core_unregister);
 

-- 
2.53.0-Meta