VSOCK: Introduce VM Sockets

VM Sockets allows communication between virtual machines and the hypervisor.
User level applications both in a virtual machine and on the host can use the
VM Sockets API, which facilitates fast and efficient communication between
guest virtual machines and their host.  A socket address family, designed to be
compatible with UDP and TCP at the interface level, is provided.

Today, VM Sockets is used by various VMware Tools components inside the guest
for zero-config, network-less access to VMware host services.  In addition to
this, VMware's users are using VM Sockets for various applications, where
network access of the virtual machine is restricted or non-existent.  Examples
of this are VMs communicating with device proxies for proprietary hardware
running as host applications and automated testing of applications running
within virtual machines.

The VMware VM Sockets are similar to other socket types, like Berkeley UNIX
socket interface.  The VM Sockets module supports both connection-oriented
stream sockets like TCP, and connectionless datagram sockets like UDP. The VM
Sockets protocol family is defined as "AF_VSOCK" and the socket operations
split for SOCK_DGRAM and SOCK_STREAM.

For additional information about the use of VM Sockets, please refer to the
VM Sockets Programming Guide available at:

https://www.vmware.com/support/developer/vmci-sdk/

Signed-off-by: George Zhang <georgezhang@vmware.com>
Signed-off-by: Dmitry Torokhov <dtor@vmware.com>
Signed-off-by: Andy king <acking@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 175 insertions, 0 deletions

diff --git a/net/vmw_vsock/af_vsock.h b/net/vmw_vsock/af_vsock.h
new file mode 100644
index 000000000000..7d64d3609ec9
--- /dev/null
+++ b/net/vmw_vsock/af_vsock.h
@@ -0,0 +1,175 @@
+/*
+ * VMware vSockets Driver
+ *
+ * Copyright (C) 2007-2013 VMware, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation version 2 and no later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef __AF_VSOCK_H__
+#define __AF_VSOCK_H__
+
+#include <linux/kernel.h>
+#include <linux/workqueue.h>
+#include <linux/vm_sockets.h>
+
+#include "vsock_addr.h"
+
+#define LAST_RESERVED_PORT 1023
+
+#define vsock_sk(__sk)    ((struct vsock_sock *)__sk)
+#define sk_vsock(__vsk)   (&(__vsk)->sk)
+
+struct vsock_sock {
+	/* sk must be the first member. */
+	struct sock sk;
+	struct sockaddr_vm local_addr;
+	struct sockaddr_vm remote_addr;
+	/* Links for the global tables of bound and connected sockets. */
+	struct list_head bound_table;
+	struct list_head connected_table;
+	/* Accessed without the socket lock held. This means it can never be
+	 * modified outsided of socket create or destruct.
+	 */
+	bool trusted;
+	bool cached_peer_allow_dgram;	/* Dgram communication allowed to
+					 * cached peer?
+					 */
+	u32 cached_peer;  /* Context ID of last dgram destination check. */
+	const struct cred *owner;
+	/* Rest are SOCK_STREAM only. */
+	long connect_timeout;
+	/* Listening socket that this came from. */
+	struct sock *listener;
+	/* Used for pending list and accept queue during connection handshake.
+	 * The listening socket is the head for both lists.  Sockets created
+	 * for connection requests are placed in the pending list until they
+	 * are connected, at which point they are put in the accept queue list
+	 * so they can be accepted in accept().  If accept() cannot accept the
+	 * connection, it is marked as rejected so the cleanup function knows
+	 * to clean up the socket.
+	 */
+	struct list_head pending_links;
+	struct list_head accept_queue;
+	bool rejected;
+	struct delayed_work dwork;
+	u32 peer_shutdown;
+	bool sent_request;
+	bool ignore_connecting_rst;
+
+	/* Private to transport. */
+	void *trans;
+};
+
+s64 vsock_stream_has_data(struct vsock_sock *vsk);
+s64 vsock_stream_has_space(struct vsock_sock *vsk);
+void vsock_pending_work(struct work_struct *work);
+struct sock *__vsock_create(struct net *net,
+			    struct socket *sock,
+			    struct sock *parent,
+			    gfp_t priority, unsigned short type);
+
+/**** TRANSPORT ****/
+
+struct vsock_transport_recv_notify_data {
+	u64 data1; /* Transport-defined. */
+	u64 data2; /* Transport-defined. */
+	bool notify_on_block;
+};
+
+struct vsock_transport_send_notify_data {
+	u64 data1; /* Transport-defined. */
+	u64 data2; /* Transport-defined. */
+};
+
+struct vsock_transport {
+	/* Initialize/tear-down socket. */
+	int (*init)(struct vsock_sock *, struct vsock_sock *);
+	void (*destruct)(struct vsock_sock *);
+	void (*release)(struct vsock_sock *);
+
+	/* Connections. */
+	int (*connect)(struct vsock_sock *);
+
+	/* DGRAM. */
+	int (*dgram_bind)(struct vsock_sock *, struct sockaddr_vm *);
+	int (*dgram_dequeue)(struct kiocb *kiocb, struct vsock_sock *vsk,
+			     struct msghdr *msg, size_t len, int flags);
+	int (*dgram_enqueue)(struct vsock_sock *, struct sockaddr_vm *,
+			     struct iovec *, size_t len);
+	bool (*dgram_allow)(u32 cid, u32 port);
+
+	/* STREAM. */
+	/* TODO: stream_bind() */
+	ssize_t (*stream_dequeue)(struct vsock_sock *, struct iovec *,
+				  size_t len, int flags);
+	ssize_t (*stream_enqueue)(struct vsock_sock *, struct iovec *,
+				  size_t len);
+	s64 (*stream_has_data)(struct vsock_sock *);
+	s64 (*stream_has_space)(struct vsock_sock *);
+	u64 (*stream_rcvhiwat)(struct vsock_sock *);
+	bool (*stream_is_active)(struct vsock_sock *);
+	bool (*stream_allow)(u32 cid, u32 port);
+
+	/* Notification. */
+	int (*notify_poll_in)(struct vsock_sock *, size_t, bool *);
+	int (*notify_poll_out)(struct vsock_sock *, size_t, bool *);
+	int (*notify_recv_init)(struct vsock_sock *, size_t,
+		struct vsock_transport_recv_notify_data *);
+	int (*notify_recv_pre_block)(struct vsock_sock *, size_t,
+		struct vsock_transport_recv_notify_data *);
+	int (*notify_recv_pre_dequeue)(struct vsock_sock *, size_t,
+		struct vsock_transport_recv_notify_data *);
+	int (*notify_recv_post_dequeue)(struct vsock_sock *, size_t,
+		ssize_t, bool, struct vsock_transport_recv_notify_data *);
+	int (*notify_send_init)(struct vsock_sock *,
+		struct vsock_transport_send_notify_data *);
+	int (*notify_send_pre_block)(struct vsock_sock *,
+		struct vsock_transport_send_notify_data *);
+	int (*notify_send_pre_enqueue)(struct vsock_sock *,
+		struct vsock_transport_send_notify_data *);
+	int (*notify_send_post_enqueue)(struct vsock_sock *, ssize_t,
+		struct vsock_transport_send_notify_data *);
+
+	/* Shutdown. */
+	int (*shutdown)(struct vsock_sock *, int);
+
+	/* Buffer sizes. */
+	void (*set_buffer_size)(struct vsock_sock *, u64);
+	void (*set_min_buffer_size)(struct vsock_sock *, u64);
+	void (*set_max_buffer_size)(struct vsock_sock *, u64);
+	u64 (*get_buffer_size)(struct vsock_sock *);
+	u64 (*get_min_buffer_size)(struct vsock_sock *);
+	u64 (*get_max_buffer_size)(struct vsock_sock *);
+
+	/* Addressing. */
+	u32 (*get_local_cid)(void);
+};
+
+/**** CORE ****/
+
+int vsock_core_init(const struct vsock_transport *t);
+void vsock_core_exit(void);
+
+/**** UTILS ****/
+
+void vsock_release_pending(struct sock *pending);
+void vsock_add_pending(struct sock *listener, struct sock *pending);
+void vsock_remove_pending(struct sock *listener, struct sock *pending);
+void vsock_enqueue_accept(struct sock *listener, struct sock *connected);
+void vsock_insert_connected(struct vsock_sock *vsk);
+void vsock_remove_bound(struct vsock_sock *vsk);
+void vsock_remove_connected(struct vsock_sock *vsk);
+struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr);
+struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
+					 struct sockaddr_vm *dst);
+void vsock_for_each_connected_socket(void (*fn)(struct sock *sk));
+
+#endif /* __AF_VSOCK_H__ */