af_vsock.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * VMware vSockets Driver
 *
 * Copyright (C) 2007-2013 VMware, Inc. All rights reserved.
 */

/* Implementation notes:
 *
 * - There are two kinds of sockets: those created by user action (such as
 * calling socket(2)) and those created by incoming connection request packets.
 *
 * - There are two "global" tables, one for bound sockets (sockets that have
 * specified an address that they are responsible for) and one for connected
 * sockets (sockets that have established a connection with another socket).
 * These tables are "global" in that all sockets on the system are placed
 * within them. - Note, though, that the bound table contains an extra entry
 * for a list of unbound sockets and SOCK_DGRAM sockets will always remain in
 * that list. The bound table is used solely for lookup of sockets when packets
 * are received and that's not necessary for SOCK_DGRAM sockets since we create
 * a datagram handle for each and need not perform a lookup.  Keeping SOCK_DGRAM
 * sockets out of the bound hash buckets will reduce the chance of collisions
 * when looking for SOCK_STREAM sockets and prevents us from having to check the
 * socket type in the hash table lookups.
 *
 * - Sockets created by user action will either be "client" sockets that
 * initiate a connection or "server" sockets that listen for connections; we do
 * not support simultaneous connects (two "client" sockets connecting).
 *
 * - "Server" sockets are referred to as listener sockets throughout this
 * implementation because they are in the TCP_LISTEN state.  When a
 * connection request is received (the second kind of socket mentioned above),
 * we create a new socket and refer to it as a pending socket.  These pending
 * sockets are placed on the pending connection list of the listener socket.
 * When future packets are received for the address the listener socket is
 * bound to, we check if the source of the packet is from one that has an
 * existing pending connection.  If it does, we process the packet for the
 * pending socket.  When that socket reaches the connected state, it is removed
 * from the listener socket's pending list and enqueued in the listener
 * socket's accept queue.  Callers of accept(2) will accept connected sockets
 * from the listener socket's accept queue.  If the socket cannot be accepted
 * for some reason then it is marked rejected.  Once the connection is
 * accepted, it is owned by the user process and the responsibility for cleanup
 * falls with that user process.
 *
 * - It is possible that these pending sockets will never reach the connected
 * state; in fact, we may never receive another packet after the connection
 * request.  Because of this, we must schedule a cleanup function to run in the
 * future, after some amount of time passes where a connection should have been
 * established.  This function ensures that the socket is off all lists so it
 * cannot be retrieved, then drops all references to the socket so it is cleaned
 * up (sock_put() -> sk_free() -> our sk_destruct implementation).  Note this
 * function will also cleanup rejected sockets, those that reach the connected
 * state but leave it before they have been accepted.
 *
 * - Lock ordering for pending or accept queue sockets is:
 *
 *     lock_sock(listener);
 *     lock_sock_nested(pending, SINGLE_DEPTH_NESTING);
 *
 * Using explicit nested locking keeps lockdep happy since normally only one
 * lock of a given class may be taken at a time.
 *
 * - Sockets created by user action will be cleaned up when the user process
 * calls close(2), causing our release implementation to be called. Our release
 * implementation will perform some cleanup then drop the last reference so our
 * sk_destruct implementation is invoked.  Our sk_destruct implementation will
 * perform additional cleanup that's common for both types of sockets.
 *
 * - A socket's reference count is what ensures that the structure won't be
 * freed.  Each entry in a list (such as the "global" bound and connected tables
 * and the listener socket's pending list and connected queue) ensures a
 * reference.  When we defer work until process context and pass a socket as our
 * argument, we must ensure the reference count is increased to ensure the
 * socket isn't freed before the function is run; the deferred function will
 * then drop the reference.
 *
 * - sk->sk_state uses the TCP state constants because they are widely used by
 * other address families and exposed to userspace tools like ss(8):
 *
 *   TCP_CLOSE - unconnected
 *   TCP_SYN_SENT - connecting
 *   TCP_ESTABLISHED - connected
 *   TCP_CLOSING - disconnecting
 *   TCP_LISTEN - listening
 */

#include <linux/types.h>
#include <linux/bitops.h>
#include <linux/cred.h>
#include <linux/init.h>
#include <linux/io.h>
#include <linux/kernel.h>
#include <linux/sched/signal.h>
#include <linux/kmod.h>
#include <linux/list.h>
#include <linux/miscdevice.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/net.h>
#include <linux/poll.h>
#include <linux/random.h>
#include <linux/skbuff.h>
#include <linux/smp.h>
#include <linux/socket.h>
#include <linux/stddef.h>
#include <linux/unistd.h>
#include <linux/wait.h>
#include <linux/workqueue.h>
#include <net/sock.h>
#include <net/af_vsock.h>

static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr);
static void vsock_sk_destruct(struct sock *sk);
static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);

/* Protocol family. */
static struct proto vsock_proto = {
	.name = "AF_VSOCK",
	.owner = THIS_MODULE,
	.obj_size = sizeof(struct vsock_sock),
};

/* The default peer timeout indicates how long we will wait for a peer response
 * to a control message.
 */
#define VSOCK_DEFAULT_CONNECT_TIMEOUT (2 * HZ)

#define VSOCK_DEFAULT_BUFFER_SIZE     (1024 * 256)
#define VSOCK_DEFAULT_BUFFER_MAX_SIZE (1024 * 256)
#define VSOCK_DEFAULT_BUFFER_MIN_SIZE 128

/* Transport used for host->guest communication */
static const struct vsock_transport *transport_h2g;
/* Transport used for guest->host communication */
static const struct vsock_transport *transport_g2h;
/* Transport used for DGRAM communication */
static const struct vsock_transport *transport_dgram;
/* Transport used for local communication */
static const struct vsock_transport *transport_local;
static DEFINE_MUTEX(vsock_register_mutex);

/**** UTILS ****/

/* Each bound VSocket is stored in the bind hash table and each connected
 * VSocket is stored in the connected hash table.
 *
 * Unbound sockets are all put on the same list attached to the end of the hash
 * table (vsock_unbound_sockets).  Bound sockets are added to the hash table in
 * the bucket that their local address hashes to (vsock_bound_sockets(addr)
 * represents the list that addr hashes to).
 *
 * Specifically, we initialize the vsock_bind_table array to a size of
 * VSOCK_HASH_SIZE + 1 so that vsock_bind_table[0] through
 * vsock_bind_table[VSOCK_HASH_SIZE - 1] are for bound sockets and
 * vsock_bind_table[VSOCK_HASH_SIZE] is for unbound sockets.  The hash function
 * mods with VSOCK_HASH_SIZE to ensure this.
 */
#define MAX_PORT_RETRIES        24

#define VSOCK_HASH(addr)        ((addr)->svm_port % VSOCK_HASH_SIZE)
#define vsock_bound_sockets(addr) (&vsock_bind_table[VSOCK_HASH(addr)])
#define vsock_unbound_sockets     (&vsock_bind_table[VSOCK_HASH_SIZE])

/* XXX This can probably be implemented in a better way. */
#define VSOCK_CONN_HASH(src, dst)				\
	(((src)->svm_cid ^ (dst)->svm_port) % VSOCK_HASH_SIZE)
#define vsock_connected_sockets(src, dst)		\
	(&vsock_connected_table[VSOCK_CONN_HASH(src, dst)])
#define vsock_connected_sockets_vsk(vsk)				\
	vsock_connected_sockets(&(vsk)->remote_addr, &(vsk)->local_addr)

struct list_head vsock_bind_table[VSOCK_HASH_SIZE + 1];
EXPORT_SYMBOL_GPL(vsock_bind_table);
struct list_head vsock_connected_table[VSOCK_HASH_SIZE];
EXPORT_SYMBOL_GPL(vsock_connected_table);
DEFINE_SPINLOCK(vsock_table_lock);
EXPORT_SYMBOL_GPL(vsock_table_lock);

/* Autobind this socket to the local address if necessary. */
static int vsock_auto_bind(struct vsock_sock *vsk)
{
	struct sock *sk = sk_vsock(vsk);
	struct sockaddr_vm local_addr;

	if (vsock_addr_bound(&vsk->local_addr))
		return 0;
	vsock_addr_init(&local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY);
	return __vsock_bind(sk, &local_addr);
}

static void vsock_init_tables(void)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(vsock_bind_table); i++)
		INIT_LIST_HEAD(&vsock_bind_table[i]);

	for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++)
		INIT_LIST_HEAD(&vsock_connected_table[i]);
}

static void __vsock_insert_bound(struct list_head *list,
				 struct vsock_sock *vsk)
{
	sock_hold(&vsk->sk);
	list_add(&vsk->bound_table, list);
}

static void __vsock_insert_connected(struct list_head *list,
				     struct vsock_sock *vsk)
{
	sock_hold(&vsk->sk);
	list_add(&vsk->connected_table, list);
}

static void __vsock_remove_bound(struct vsock_sock *vsk)
{
	list_del_init(&vsk->bound_table);
	sock_put(&vsk->sk);
}

static void __vsock_remove_connected(struct vsock_sock *vsk)
{
	list_del_init(&vsk->connected_table);
	sock_put(&vsk->sk);
}

static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr)
{
	struct vsock_sock *vsk;

	list_for_each_entry(vsk, vsock_bound_sockets(addr), bound_table) {
		if (vsock_addr_equals_addr(addr, &vsk->local_addr))
			return sk_vsock(vsk);

		if (addr->svm_port == vsk->local_addr.svm_port &&
		    (vsk->local_addr.svm_cid == VMADDR_CID_ANY ||
		     addr->svm_cid == VMADDR_CID_ANY))
			return sk_vsock(vsk);
	}

	return NULL;
}

static struct sock *__vsock_find_connected_socket(struct sockaddr_vm *src,
						  struct sockaddr_vm *dst)
{
	struct vsock_sock *vsk;

	list_for_each_entry(vsk, vsock_connected_sockets(src, dst),
			    connected_table) {
		if (vsock_addr_equals_addr(src, &vsk->remote_addr) &&
		    dst->svm_port == vsk->local_addr.svm_port) {
			return sk_vsock(vsk);
		}
	}

	return NULL;
}

static void vsock_insert_unbound(struct vsock_sock *vsk)
{
	spin_lock_bh(&vsock_table_lock);
	__vsock_insert_bound(vsock_unbound_sockets, vsk);
	spin_unlock_bh(&vsock_table_lock);
}

void vsock_insert_connected(struct vsock_sock *vsk)
{
	struct list_head *list = vsock_connected_sockets(
		&vsk->remote_addr, &vsk->local_addr);

	spin_lock_bh(&vsock_table_lock);
	__vsock_insert_connected(list, vsk);
	spin_unlock_bh(&vsock_table_lock);
}
EXPORT_SYMBOL_GPL(vsock_insert_connected);

void vsock_remove_bound(struct vsock_sock *vsk)
{
	spin_lock_bh(&vsock_table_lock);
	if (__vsock_in_bound_table(vsk))
		__vsock_remove_bound(vsk);
	spin_unlock_bh(&vsock_table_lock);
}
EXPORT_SYMBOL_GPL(vsock_remove_bound);

void vsock_remove_connected(struct vsock_sock *vsk)
{
	spin_lock_bh(&vsock_table_lock);
	if (__vsock_in_connected_table(vsk))
		__vsock_remove_connected(vsk);
	spin_unlock_bh(&vsock_table_lock);
}
EXPORT_SYMBOL_GPL(vsock_remove_connected);

struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr)
{
	struct sock *sk;

	spin_lock_bh(&vsock_table_lock);
	sk = __vsock_find_bound_socket(addr);
	if (sk)
		sock_hold(sk);

	spin_unlock_bh(&vsock_table_lock);

	return sk;
}
EXPORT_SYMBOL_GPL(vsock_find_bound_socket);

struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
					 struct sockaddr_vm *dst)
{
	struct sock *sk;

	spin_lock_bh(&vsock_table_lock);
	sk = __vsock_find_connected_socket(src, dst);
	if (sk)
		sock_hold(sk);

	spin_unlock_bh(&vsock_table_lock);

	return sk;
}
EXPORT_SYMBOL_GPL(vsock_find_connected_socket);

void vsock_remove_sock(struct vsock_sock *vsk)
{
	vsock_remove_bound(vsk);
	vsock_remove_connected(vsk);
}
EXPORT_SYMBOL_GPL(vsock_remove_sock);

void vsock_for_each_connected_socket(void (*fn)(struct sock *sk))
{
	int i;

	spin_lock_bh(&vsock_table_lock);

	for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++) {
		struct vsock_sock *vsk;
		list_for_each_entry(vsk, &vsock_connected_table[i],
				    connected_table)
			fn(sk_vsock(vsk));
	}

	spin_unlock_bh(&vsock_table_lock);
}
EXPORT_SYMBOL_GPL(vsock_for_each_connected_socket);

void vsock_add_pending(struct sock *listener, struct sock *pending)
{
	struct vsock_sock *vlistener;
	struct vsock_sock *vpending;

	vlistener = vsock_sk(listener);
	vpending = vsock_sk(pending);

	sock_hold(pending);
	sock_hold(listener);
	list_add_tail(&vpending->pending_links, &vlistener->pending_links);
}
EXPORT_SYMBOL_GPL(vsock_add_pending);

void vsock_remove_pending(struct sock *listener, struct sock *pending)
{
	struct vsock_sock *vpending = vsock_sk(pending);

	list_del_init(&vpending->pending_links);
	sock_put(listener);
	sock_put(pending);
}
EXPORT_SYMBOL_GPL(vsock_remove_pending);

void vsock_enqueue_accept(struct sock *listener, struct sock *connected)
{
	struct vsock_sock *vlistener;
	struct vsock_sock *vconnected;

	vlistener = vsock_sk(listener);
	vconnected = vsock_sk(connected);

	sock_hold(connected);
	sock_hold(listener);
	list_add_tail(&vconnected->accept_queue, &vlistener->accept_queue);
}
EXPORT_SYMBOL_GPL(vsock_enqueue_accept);

static bool vsock_use_local_transport(unsigned int remote_cid)
{
	if (!transport_local)
		return false;

	if (remote_cid == VMADDR_CID_LOCAL)
		return true;

	if (transport_g2h) {
		return remote_cid == transport_g2h->get_local_cid();
	} else {
		return remote_cid == VMADDR_CID_HOST;
	}
}

static void vsock_deassign_transport(struct vsock_sock *vsk)
{
	if (!vsk->transport)
		return;

	vsk->transport->destruct(vsk);
	module_put(vsk->transport->module);
	vsk->transport = NULL;
}

/* Assign a transport to a socket and call the .init transport callback.
 *
 * Note: for stream socket this must be called when vsk->remote_addr is set
 * (e.g. during the connect() or when a connection request on a listener
 * socket is received).
 * The vsk->remote_addr is used to decide which transport to use:
 *  - remote CID == VMADDR_CID_LOCAL or g2h->local_cid or VMADDR_CID_HOST if
 *    g2h is not loaded, will use local transport;
 *  - remote CID <= VMADDR_CID_HOST or h2g is not loaded or remote flags field
 *    includes VMADDR_FLAG_TO_HOST flag value, will use guest->host transport;
 *  - remote CID > VMADDR_CID_HOST will use host->guest transport;
 */
int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
{
	const struct vsock_transport *new_transport;
	struct sock *sk = sk_vsock(vsk);
	unsigned int remote_cid = vsk->remote_addr.svm_cid;
	__u8 remote_flags;
	int ret;

	/* If the packet is coming with the source and destination CIDs higher
	 * than VMADDR_CID_HOST, then a vsock channel where all the packets are
	 * forwarded to the host should be established. Then the host will
	 * need to forward the packets to the guest.
	 *
	 * The flag is set on the (listen) receive path (psk is not NULL). On
	 * the connect path the flag can be set by the user space application.
	 */
	if (psk && vsk->local_addr.svm_cid > VMADDR_CID_HOST &&
	    vsk->remote_addr.svm_cid > VMADDR_CID_HOST)
		vsk->remote_addr.svm_flags |= VMADDR_FLAG_TO_HOST;

	remote_flags = vsk->remote_addr.svm_flags;

	switch (sk->sk_type) {
	case SOCK_DGRAM:
		new_transport = transport_dgram;
		break;
	case SOCK_STREAM:
		if (vsock_use_local_transport(remote_cid))
			new_transport = transport_local;
		else if (remote_cid <= VMADDR_CID_HOST || !transport_h2g ||
			 (remote_flags & VMADDR_FLAG_TO_HOST))
			new_transport = transport_g2h;
		else
			new_transport = transport_h2g;
		break;
	default:
		return -ESOCKTNOSUPPORT;
	}

	if (vsk->transport) {
		if (vsk->transport == new_transport)
			return 0;

		/* transport->release() must be called with sock lock acquired.
		 * This path can only be taken during vsock_stream_connect(),
		 * where we have already held the sock lock.
		 * In the other cases, this function is called on a new socket
		 * which is not assigned to any transport.
		 */
		vsk->transport->release(vsk);
		vsock_deassign_transport(vsk);
	}

	/* 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;

	ret = new_transport->init(vsk, psk);
	if (ret) {
		module_put(new_transport->module);
		return ret;
	}

	vsk->transport = new_transport;

	return 0;
}
EXPORT_SYMBOL_GPL(vsock_assign_transport);

bool vsock_find_cid(unsigned int cid)
{
	if (transport_g2h && cid == transport_g2h->get_local_cid())
		return true;

	if (transport_h2g && cid == VMADDR_CID_HOST)
		return true;

	if (transport_local && cid == VMADDR_CID_LOCAL)
		return true;

	return false;
}
EXPORT_SYMBOL_GPL(vsock_find_cid);

static struct sock *vsock_dequeue_accept(struct sock *listener)
{
	struct vsock_sock *vlistener;
	struct vsock_sock *vconnected;

	vlistener = vsock_sk(listener);

	if (list_empty(&vlistener->accept_queue))
		return NULL;

	vconnected = list_entry(vlistener->accept_queue.next,
				struct vsock_sock, accept_queue);

	list_del_init(&vconnected->accept_queue);
	sock_put(listener);
	/* The caller will need a reference on the connected socket so we let
	 * it call sock_put().
	 */

	return sk_vsock(vconnected);
}

static bool vsock_is_accept_queue_empty(struct sock *sk)
{
	struct vsock_sock *vsk = vsock_sk(sk);
	return list_empty(&vsk->accept_queue);
}

static bool vsock_is_pending(struct sock *sk)
{
	struct vsock_sock *vsk = vsock_sk(sk);
	return !list_empty(&vsk->pending_links);
}

static int vsock_send_shutdown(struct sock *sk, int mode)
{
	struct vsock_sock *vsk = vsock_sk(sk);

	if (!vsk->transport)
		return -ENODEV;

	return vsk->transport->shutdown(vsk, mode);
}

static void vsock_pending_work(struct work_struct *work)
{
	struct sock *sk;
	struct sock *listener;
	struct vsock_sock *vsk;
	bool cleanup;

	vsk = container_of(work, struct vsock_sock, pending_work.work);
	sk = sk_vsock(vsk);
	listener = vsk->listener;
	cleanup = true;

	lock_sock(listener);
	lock_sock_nested(sk, SINGLE_DEPTH_NESTING);

	if (vsock_is_pending(sk)) {
		vsock_remove_pending(listener, sk);

		sk_acceptq_removed(listener);
	} else if (!vsk->rejected) {
		/* We are not on the pending list and accept() did not reject
		 * us, so we must have been accepted by our user process.  We
		 * just need to drop our references to the sockets and be on
		 * our way.
		 */
		cleanup = false;
		goto out;
	}

	/* We need to remove ourself from the global connected sockets list so
	 * incoming packets can't find this socket, and to reduce the reference
	 * count.
	 */
	vsock_remove_connected(vsk);

	sk->sk_state = TCP_CLOSE;

out:
	release_sock(sk);
	release_sock(listener);
	if (cleanup)
		sock_put(sk);

	sock_put(sk);
	sock_put(listener);
}

/**** SOCKET OPERATIONS ****/

static int __vsock_bind_stream(struct vsock_sock *vsk,
			       struct sockaddr_vm *addr)
{
	static u32 port;
	struct sockaddr_vm new_addr;

	if (!port)
		port = LAST_RESERVED_PORT + 1 +
			prandom_u32_max(U32_MAX - LAST_RESERVED_PORT);

	vsock_addr_init(&new_addr, addr->svm_cid, addr->svm_port);

	if (addr->svm_port == VMADDR_PORT_ANY) {
		bool found = false;
		unsigned int i;

		for (i = 0; i < MAX_PORT_RETRIES; i++) {
			if (port <= LAST_RESERVED_PORT)
				port = LAST_RESERVED_PORT + 1;

			new_addr.svm_port = port++;

			if (!__vsock_find_bound_socket(&new_addr)) {
				found = true;
				break;
			}
		}

		if (!found)
			return -EADDRNOTAVAIL;
	} else {
		/* If port is in reserved range, ensure caller
		 * has necessary privileges.
		 */
		if (addr->svm_port <= LAST_RESERVED_PORT &&
		    !capable(CAP_NET_BIND_SERVICE)) {
			return -EACCES;
		}

		if (__vsock_find_bound_socket(&new_addr))
			return -EADDRINUSE;
	}

	vsock_addr_init(&vsk->local_addr, new_addr.svm_cid, new_addr.svm_port);

	/* Remove stream sockets from the unbound list and add them to the hash
	 * table for easy lookup by its address.  The unbound list is simply an
	 * extra entry at the end of the hash table, a trick used by AF_UNIX.
	 */
	__vsock_remove_bound(vsk);
	__vsock_insert_bound(vsock_bound_sockets(&vsk->local_addr), vsk);

	return 0;
}

static int __vsock_bind_dgram(struct vsock_sock *vsk,
			      struct sockaddr_vm *addr)
{
	return vsk->transport->dgram_bind(vsk, addr);
}

static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr)
{
	struct vsock_sock *vsk = vsock_sk(sk);
	int retval;

	/* First ensure this socket isn't already bound. */
	if (vsock_addr_bound(&vsk->local_addr))
		return -EINVAL;

	/* Now bind to the provided address or select appropriate values if
	 * none are provided (VMADDR_CID_ANY and VMADDR_PORT_ANY).  Note that
	 * like AF_INET prevents binding to a non-local IP address (in most
	 * cases), we only allow binding to a local CID.
	 */
	if (addr->svm_cid != VMADDR_CID_ANY && !vsock_find_cid(addr->svm_cid))
		return -EADDRNOTAVAIL;

	switch (sk->sk_socket->type) {
	case SOCK_STREAM:
		spin_lock_bh(&vsock_table_lock);
		retval = __vsock_bind_stream(vsk, addr);
		spin_unlock_bh(&vsock_table_lock);
		break;

	case SOCK_DGRAM:
		retval = __vsock_bind_dgram(vsk, addr);
		break;

	default:
		retval = -EINVAL;
		break;
	}

	return retval;
}

static void vsock_connect_timeout(struct work_struct *work);

static struct sock *__vsock_create(struct net *net,
				   struct socket *sock,
				   struct sock *parent,
				   gfp_t priority,
				   unsigned short type,
				   int kern)
{
	struct sock *sk;
	struct vsock_sock *psk;
	struct vsock_sock *vsk;

	sk = sk_alloc(net, AF_VSOCK, priority, &vsock_proto, kern);
	if (!sk)
		return NULL;

	sock_init_data(sock, sk);

	/* sk->sk_type is normally set in sock_init_data, but only if sock is
	 * non-NULL. We make sure that our sockets always have a type by
	 * setting it here if needed.
	 */
	if (!sock)
		sk->sk_type = type;

	vsk = vsock_sk(sk);
	vsock_addr_init(&vsk->local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY);
	vsock_addr_init(&vsk->remote_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY);

	sk->sk_destruct = vsock_sk_destruct;
	sk->sk_backlog_rcv = vsock_queue_rcv_skb;
	sock_reset_flag(sk, SOCK_DONE);

	INIT_LIST_HEAD(&vsk->bound_table);
	INIT_LIST_HEAD(&vsk->connected_table);
	vsk->listener = NULL;
	INIT_LIST_HEAD(&vsk->pending_links);
	INIT_LIST_HEAD(&vsk->accept_queue);
	vsk->rejected = false;
	vsk->sent_request = false;
	vsk->ignore_connecting_rst = false;
	vsk->peer_shutdown = 0;
	INIT_DELAYED_WORK(&vsk->connect_work, vsock_connect_timeout);
	INIT_DELAYED_WORK(&vsk->pending_work, vsock_pending_work);

	psk = parent ? vsock_sk(parent) : NULL;
	if (parent) {
		vsk->trusted = psk->trusted;
		vsk->owner = get_cred(psk->owner);
		vsk->connect_timeout = psk->connect_timeout;
		vsk->buffer_size = psk->buffer_size;
		vsk->buffer_min_size = psk->buffer_min_size;
		vsk->buffer_max_size = psk->buffer_max_size;
		security_sk_clone(parent, sk);
	} else {
		vsk->trusted = ns_capable_noaudit(&init_user_ns, CAP_NET_ADMIN);
		vsk->owner = get_current_cred();
		vsk->connect_timeout = VSOCK_DEFAULT_CONNECT_TIMEOUT;
		vsk->buffer_size = VSOCK_DEFAULT_BUFFER_SIZE;
		vsk->buffer_min_size = VSOCK_DEFAULT_BUFFER_MIN_SIZE;
		vsk->buffer_max_size = VSOCK_DEFAULT_BUFFER_MAX_SIZE;
	}

	return sk;
}

static void __vsock_release(struct sock *sk, int level)
{
	if (sk) {
		struct sock *pending;
		struct vsock_sock *vsk;

		vsk = vsock_sk(sk);
		pending = NULL;	/* Compiler warning. */

		/* When "level" is SINGLE_DEPTH_NESTING, use the nested
		 * version to avoid the warning "possible recursive locking
		 * detected". When "level" is 0, lock_sock_nested(sk, level)
		 * is the same as lock_sock(sk).
		 */
		lock_sock_nested(sk, level);

		if (vsk->transport)
			vsk->transport->release(vsk);
		else if (sk->sk_type == SOCK_STREAM)
			vsock_remove_sock(vsk);

		sock_orphan(sk);
		sk->sk_shutdown = SHUTDOWN_MASK;

		skb_queue_purge(&sk->sk_receive_queue);

		/* Clean up any sockets that never were accepted. */
		while ((pending = vsock_dequeue_accept(sk)) != NULL) {
			__vsock_release(pending, SINGLE_DEPTH_NESTING);
			sock_put(pending);
		}

		release_sock(sk);
		sock_put(sk);
	}
}

static void vsock_sk_destruct(struct sock *sk)
{
	struct vsock_sock *vsk = vsock_sk(sk);

	vsock_deassign_transport(vsk);

	/* When clearing these addresses, there's no need to set the family and
	 * possibly register the address family with the kernel.
	 */
	vsock_addr_init(&vsk->local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY);
	vsock_addr_init(&vsk->remote_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY);

	put_cred(vsk->owner);
}

static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
	int err;

	err = sock_queue_rcv_skb(sk, skb);
	if (err)
		kfree_skb(skb);

	return err;
}

struct sock *vsock_create_connected(struct sock *parent)
{
	return __vsock_create(sock_net(parent), NULL, parent, GFP_KERNEL,
			      parent->sk_type, 0);
}
EXPORT_SYMBOL_GPL(vsock_create_connected);

s64 vsock_stream_has_data(struct vsock_sock *vsk)
{
	return vsk->transport->stream_has_data(vsk);
}
EXPORT_SYMBOL_GPL(vsock_stream_has_data);

s64 vsock_stream_has_space(struct vsock_sock *vsk)
{
	return vsk->transport->stream_has_space(vsk);
}
EXPORT_SYMBOL_GPL(vsock_stream_has_space);

static int vsock_release(struct socket *sock)
{
	__vsock_release(sock->sk, 0);
	sock->sk = NULL;
	sock->state = SS_FREE;

	return 0;
}

static int
vsock_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
{
	int err;
	struct sock *sk;
	struct sockaddr_vm *vm_addr;

	sk = sock->sk;

	if (vsock_addr_cast(addr, addr_len, &vm_addr) != 0)
		return -EINVAL;

	lock_sock(sk);
	err = __vsock_bind(sk, vm_addr);
	release_sock(sk);

	return err;
}

static int vsock_getname(struct socket *sock,
			 struct sockaddr *addr, int peer)
{
	int err;
	struct sock *sk;
	struct vsock_sock *vsk;
	struct sockaddr_vm *vm_addr;

	sk = sock->sk;
	vsk = vsock_sk(sk);
	err = 0;

	lock_sock(sk);

	if (peer) {
		if (sock->state != SS_CONNECTED) {
			err = -ENOTCONN;
			goto out;
		}
		vm_addr = &vsk->remote_addr;
	} else {
		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
	 * value here.
	 */
	BUILD_BUG_ON(sizeof(*vm_addr) > 128);
	memcpy(addr, vm_addr, sizeof(*vm_addr));
	err = sizeof(*vm_addr);

out:
	release_sock(sk);
	return err;
}

static int vsock_shutdown(struct socket *sock, int mode)
{
	int err;
	struct sock *sk;

	/* User level uses SHUT_RD (0) and SHUT_WR (1), but the kernel uses
	 * RCV_SHUTDOWN (1) and SEND_SHUTDOWN (2), so we must increment mode
	 * here like the other address families do.  Note also that the
	 * increment makes SHUT_RDWR (2) into RCV_SHUTDOWN | SEND_SHUTDOWN (3),
	 * which is what we want.
	 */
	mode++;

	if ((mode & ~SHUTDOWN_MASK) || !mode)
		return -EINVAL;

	/* If this is a STREAM socket and it is not connected then bail out
	 * immediately.  If it is a DGRAM socket then we must first kick the
	 * socket so that it wakes up from any sleeping calls, for example
	 * recv(), and then afterwards return the error.
	 */

	sk = sock->sk;

	lock_sock(sk);
	if (sock->state == SS_UNCONNECTED) {
		err = -ENOTCONN;
		if (sk->sk_type == SOCK_STREAM)
			goto out;
	} else {
		sock->state = SS_DISCONNECTING;
		err = 0;
	}

	/* Receive and send shutdowns are treated alike. */
	mode = mode & (RCV_SHUTDOWN | SEND_SHUTDOWN);
	if (mode) {
		sk->sk_shutdown |= mode;
		sk->sk_state_change(sk);

		if (sk->sk_type == SOCK_STREAM) {
			sock_reset_flag(sk, SOCK_DONE);
			vsock_send_shutdown(sk, mode);
		}
	}

out:
	release_sock(sk);
	return err;
}

static __poll_t vsock_poll(struct file *file, struct socket *sock,
			       poll_table *wait)
{
	struct sock *sk;
	__poll_t mask;
	struct vsock_sock *vsk;

	sk = sock->sk;
	vsk = vsock_sk(sk);

	poll_wait(file, sk_sleep(sk), wait);
	mask = 0;

	if (sk->sk_err)
		/* Signify that there has been an error on this socket. */
		mask |= EPOLLERR;

	/* INET sockets treat local write shutdown and peer write shutdown as a
	 * case of EPOLLHUP set.
	 */
	if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
	    ((sk->sk_shutdown & SEND_SHUTDOWN) &&
	     (vsk->peer_shutdown & SEND_SHUTDOWN))) {
		mask |= EPOLLHUP;
	}