net/9p: add vsock transport

Add vsock as a transport option for 9P client connections. This
allows mounting 9P filesystems over VM sockets without requiring TCP/IP
networking or additional userspace tools, which can be useful with
hypervisors other than Qemu/KVM, for example Hyper-V/WSL which is used
by podman machine on Windows[1][2].

The implementation extends trans_fd.c with vsock support, reusing the
existing socket infrastructure. A new p9_fd_create_vsock() function
handles vsock connection setup by parsing the CID from the mount source,
creating an AF_VSOCK socket, and connecting to the specified endpoint.
All other transport operations (close, request, cancel) use the shared
fd transport implementation.

The privport mount option is not currently implemented for vsock and
returns -EOPNOTSUPP if specified.

Add CONFIG_NET_9P_VSOCK option that conditionally compiles vsock support
into 9pnet_fd.ko. This follows the pattern where socket-based transports
(TCP, Unix, vsock) share trans_fd.c, while specialized hardware transports
(virtio, xen, rdma) have dedicated files.

Usage:
  mount -t 9p -o trans=vsock[,port=<port>] <CID> /mnt/point

Link: https://github.com/podman-container-tools/podman/blob/main/cmd/podman/machine/server9p.go [1]
Link: https://github.com/podman-container-tools/podman/blob/main/cmd/podman/machine/client9p.go [2]
Signed-off-by: Matus Skvarla <skvarlamatus@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Acked-by: Stefano Garzarella <sgarzare@redhat.com>
Message-ID: <20260709161741.15138-1-skvarlamatus@gmail.com>
Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>

Documentation/filesystems/9p.rst

@@ -50,6 +50,14 @@ mount points. Each 9P export is seen by the client as a virtio device with an
 associated "mount_tag" property. Available mount tags can be
 seen by reading /sys/bus/virtio/drivers/9pnet_virtio/virtio<n>/mount_tag files.
 
+For server accessible over vsock (VM sockets)::
+
+	mount -t 9p -o trans=vsock[,port=<port>] <CID> /mnt/9
+
+where CID is the vsock Context ID of the remote endpoint (2 for host from
+a guest VM, 3+ for guest VMs from the host). The port to connect to can be
+specified with the port option (default: 564).
+
 USBG Usage
 ==========
 
@@ -117,6 +125,8 @@ Options
 			tcp	  specifying a normal TCP/IP connection
 			fd   	  used passed file descriptors for connection
                                   (see rfdno and wfdno)
+			vsock	  connect over VM sockets (vsock) using
+				  CID as the mount source
 			virtio	  connect to the next virtio channel available
 				  (from QEMU with trans_virtio module)
 			rdma	  connect to a specified RDMA channel

include/net/9p/client.h

@@ -122,8 +122,12 @@ struct p9_client {
 		struct {
 			u16 port;
 			bool privport;
-
 		} tcp;
+#if IS_ENABLED(CONFIG_NET_9P_VSOCK)
+		struct {
+			u32 port;
+		} vsock;
+#endif
 	} trans_opts;
 
 	struct idr fids;
@@ -151,13 +155,13 @@ struct p9_client_opts {
  * struct p9_fd_opts - per-transport options for fd transport
  * @rfd: file descriptor for reading (trans=fd)
  * @wfd: file descriptor for writing (trans=fd)
- * @port: port to connect to (trans=tcp)
+ * @port: port to connect to (trans=tcp, trans=vsock)
  * @privport: port is privileged
  */
 struct p9_fd_opts {
 	int rfd;
 	int wfd;
-	u16 port;
+	u32 port;
 	bool privport;
 };
 

net/9p/Kconfig

@@ -32,6 +32,16 @@ config NET_9P_VIRTIO
 	  This builds support for a transports between
 	  guest partitions and a host partition.
 
+config NET_9P_VSOCK
+	depends on NET_9P_FD
+	depends on VSOCKETS
+	bool "9P VSOCK Transport"
+	help
+	  This builds support for a transport for 9pfs over
+	  virtual sockets (vsock). This is useful for communication
+	  between virtual machines and their host without requiring
+	  TCP/IP networking configuration or additional userspace software.
+
 config NET_9P_XEN
 	depends on XEN
 	select XEN_XENBUS_FRONTEND

net/9p/trans_fd.c

@@ -28,6 +28,9 @@
 #include <net/9p/9p.h>
 #include <net/9p/client.h>
 #include <net/9p/transport.h>
+#if IS_ENABLED(CONFIG_NET_9P_VSOCK)
+#include <uapi/linux/vm_sockets.h>
+#endif
 
 #include <linux/syscalls.h> /* killme */
 
@@ -36,6 +39,9 @@
 
 static struct p9_trans_module p9_tcp_trans;
 static struct p9_trans_module p9_fd_trans;
+#if IS_ENABLED(CONFIG_NET_9P_VSOCK)
+static struct p9_trans_module p9_vsock_trans;
+#endif
 
 enum {
 	Rworksched = 1,		/* read work scheduled or running */
@@ -714,6 +720,12 @@ static int p9_fd_show_options(struct seq_file *m, struct p9_client *clnt)
 		if (clnt->trans_opts.fd.wfd != ~0)
 			seq_printf(m, ",wfd=%u", clnt->trans_opts.fd.wfd);
 	}
+#if IS_ENABLED(CONFIG_NET_9P_VSOCK)
+	else if (clnt->trans_mod == &p9_vsock_trans) {
+		if (clnt->trans_opts.vsock.port != P9_FD_PORT)
+			seq_printf(m, ",port=%u", clnt->trans_opts.vsock.port);
+	}
+#endif
 	return 0;
 }
 
@@ -875,7 +887,7 @@ p9_fd_create_tcp(struct p9_client *client, struct fs_context *fc)
 	const char *addr = fc->source;
 	struct v9fs_context *ctx = fc->fs_private;
 	int err;
-	char port_str[6];
+	char port_str[11];
 	struct socket *csocket;
 	struct sockaddr_storage stor = { 0 };
 	struct p9_fd_opts opts;
@@ -965,6 +977,67 @@ p9_fd_create_unix(struct p9_client *client, struct fs_context *fc)
 	return p9_socket_open(client, csocket);
 }
 
+#if IS_ENABLED(CONFIG_NET_9P_VSOCK)
+static int
+p9_fd_create_vsock(struct p9_client *client, struct fs_context *fc)
+{
+	const char *addr = fc->source;
+	struct v9fs_context *ctx = fc->fs_private;
+	int err;
+	struct socket *csocket;
+	struct sockaddr_vm addr_vm = { 0 };
+	struct p9_fd_opts opts;
+	unsigned int cid;
+
+	/* opts are already parsed in context */
+	opts = ctx->fd_opts;
+
+	if (opts.privport) {
+		// TODO: implement vsock privileged port binding
+		pr_err("%s (%d): privport currently not implemented for vsock\n",
+		       __func__, task_pid_nr(current));
+		return -EOPNOTSUPP;
+	}
+
+	if (!addr)
+		return -EINVAL;
+
+	err = kstrtouint(addr, 10, &cid);
+	if (err < 0) {
+		pr_err("%s (%d): invalid CID: %s\n",
+		       __func__, task_pid_nr(current), addr);
+		return err;
+	}
+
+	csocket = NULL;
+
+	client->trans_opts.vsock.port = opts.port;
+	err = __sock_create(fc->net_ns, AF_VSOCK,
+			    SOCK_STREAM, 0, &csocket, 1);
+	if (err) {
+		pr_err("%s (%d): problem creating socket\n",
+		       __func__, task_pid_nr(current));
+		return err;
+	}
+
+	addr_vm.svm_family = AF_VSOCK;
+	addr_vm.svm_port = opts.port;
+	addr_vm.svm_cid = cid;
+
+	err = READ_ONCE(csocket->ops)->connect(csocket,
+					       (struct sockaddr_unsized *)&addr_vm,
+					       sizeof(addr_vm), 0);
+	if (err < 0) {
+		pr_err("%s (%d): problem connecting socket to %s:%u\n",
+		       __func__, task_pid_nr(current), addr, opts.port);
+		sock_release(csocket);
+		return err;
+	}
+
+	return p9_socket_open(client, csocket);
+}
+#endif /* CONFIG_NET_9P_VSOCK */
+
 static int
 p9_fd_create(struct p9_client *client, struct fs_context *fc)
 {
@@ -1035,6 +1108,23 @@ static struct p9_trans_module p9_fd_trans = {
 };
 MODULE_ALIAS_9P("fd");
 
+#if IS_ENABLED(CONFIG_NET_9P_VSOCK)
+static struct p9_trans_module p9_vsock_trans = {
+	.name = "vsock",
+	.maxsize = MAX_SOCK_BUF,
+	.def = false,
+	.supports_vmalloc = true,
+	.create = p9_fd_create_vsock,
+	.close = p9_fd_close,
+	.request = p9_fd_request,
+	.cancel = p9_fd_cancel,
+	.cancelled = p9_fd_cancelled,
+	.show_options = p9_fd_show_options,
+	.owner = THIS_MODULE,
+};
+MODULE_ALIAS_9P("vsock");
+#endif
+
 /**
  * p9_poll_workfn - poll worker thread
  * @work: work queue
@@ -1072,6 +1162,9 @@ static int __init p9_trans_fd_init(void)
 	v9fs_register_trans(&p9_tcp_trans);
 	v9fs_register_trans(&p9_unix_trans);
 	v9fs_register_trans(&p9_fd_trans);
+#if IS_ENABLED(CONFIG_NET_9P_VSOCK)
+	v9fs_register_trans(&p9_vsock_trans);
+#endif
 
 	return 0;
 }
@@ -1082,6 +1175,9 @@ static void __exit p9_trans_fd_exit(void)
 	v9fs_unregister_trans(&p9_tcp_trans);
 	v9fs_unregister_trans(&p9_unix_trans);
 	v9fs_unregister_trans(&p9_fd_trans);
+#if IS_ENABLED(CONFIG_NET_9P_VSOCK)
+	v9fs_unregister_trans(&p9_vsock_trans);
+#endif
 }
 
 module_init(p9_trans_fd_init);