/* 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 int vsock_dgram_connect(struct socket *sock,
struct sockaddr *addr, int addr_len, int flags)
{
int err;
struct sock *sk;
struct vsock_sock *vsk;
struct sockaddr_vm *remote_addr;
sk = sock->sk;
vsk = vsock_sk(sk);
err = vsock_addr_cast(addr, addr_len, &remote_addr);
if (err == -EAFNOSUPPORT && remote_addr->svm_family == AF_UNSPEC) {
lock_sock(sk);
vsock_addr_init(&vsk->remote_addr, VMADDR_CID_ANY,
VMADDR_PORT_ANY);
sock->state = SS_UNCONNECTED;
release_sock(sk);
return 0;
} else if (err != 0)
return -EINVAL;
lock_sock(sk);
if (!vsock_addr_bound(&vsk->local_addr)) {
struct sockaddr_vm local_addr;
vsock_addr_init(&local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY);
err = __vsock_bind(sk, &local_addr);
if (err != 0)
goto out;
}
if (!transport->dgram_allow(remote_addr->svm_cid,
remote_addr->svm_port)) {
err = -EINVAL;
goto out;
}
memcpy(&vsk->remote_addr, remote_addr, sizeof(vsk->remote_addr));
sock->state = SS_CONNECTED;
out:
release_sock(sk);
return err;
}
static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr)
{
struct vsock_sock *vsk = vsock_sk(sk);
u32 cid;
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 the local CID.
*/
cid = transport->get_local_cid();
if (addr->svm_cid != cid && addr->svm_cid != VMADDR_CID_ANY)
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 int vsock_listen(struct socket *sock, int backlog)
{
int err;
struct sock *sk;
struct vsock_sock *vsk;
sk = sock->sk;
lock_sock(sk);
if (sock->type != SOCK_STREAM) {
err = -EOPNOTSUPP;
goto out;
}
if (sock->state != SS_UNCONNECTED) {
err = -EINVAL;
goto out;
}
vsk = vsock_sk(sk);
if (!vsock_addr_bound(&vsk->local_addr)) {
err = -EINVAL;
goto out;
}
sk->sk_max_ack_backlog = backlog;
sk->sk_state = TCP_LISTEN;
err = 0;
out:
release_sock(sk);
return err;
}
static int vsock_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
size_t len)
{
int err;
struct sock *sk;
struct vsock_sock *vsk;
struct sockaddr_vm *remote_addr;
if (msg->msg_flags & MSG_OOB)
return -EOPNOTSUPP;
/* For now, MSG_DONTWAIT is always assumed... */
err = 0;
sk = sock->sk;
vsk = vsock_sk(sk);
lock_sock(sk);
err = vsock_auto_bind(vsk);
if (err)
goto out;
/* If the provided message contains an address, use that. Otherwise
* fall back on the socket's remote handle (if it has been connected).
*/
if (msg->msg_name &&
vsock_addr_cast(msg->msg_name, msg->msg_namelen,
&remote_addr) == 0) {
/* Ensure this address is of the right type and is a valid
* destination.
*/
if (remote_addr->svm_cid == VMADDR_CID_ANY)
remote_addr->svm_cid = transport->get_local_cid();
if (!vsock_addr_bound(remote_addr)) {
err = -EINVAL;
goto out;
}
} else if (sock->state == SS_CONNECTED) {
remote_addr = &vsk->remote_addr;
if (remote_addr->svm_cid == VMADDR_CID_ANY)
remote_addr->svm_cid = transport->get_local_cid();
/* XXX Should connect() or this function ensure remote_addr is
* bound?
*/
if (!vsock_addr_bound(&vsk->remote_addr)) {
err = -EINVAL;
goto out;
}
} else {
err = -EINVAL;
goto out;
}
if (!transport->dgram_allow(remote_addr->svm_cid,
remote_addr->svm_port)) {
err = -EINVAL;
goto out;
}
err = transport->dgram_enqueue(vsk, remote_addr, msg, len);
out:
release_sock(sk);
return err;
}
static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
size_t len)
{
struct sock *sk;
struct vsock_sock *vsk;
ssize_t total_written;
long timeout;
int err;
struct vsock_transport_send_notify_data send_data;
DEFINE_WAIT_FUNC(wait, woken_wake_function);
sk = sock->sk;
vsk = vsock_sk(sk);
total_written = 0;
err = 0;
if (msg->msg_flags & MSG_OOB)
return -EOPNOTSUPP;
lock_sock(sk);
/* Callers should not provide a destination with stream sockets. */
if (msg->msg_namelen) {
err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP;
goto out;
}
/* Send data only if both sides are not shutdown in the direction. */
if (sk->sk_shutdown & SEND_SHUTDOWN ||
vsk->peer_shutdown & RCV_SHUTDOWN) {
err = -EPIPE;
goto out;
}
if (sk->sk_state != TCP_ESTABLISHED ||
!vsock_addr_bound(&vsk->local_addr)) {
err = -ENOTCONN;
goto out;
}
if (!vsock_addr_bound(&vsk->remote_addr)) {
err = -EDESTADDRREQ;
goto out;
}
/* Wait for room in the produce queue to enqueue our user's data. */
timeout = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
err = transport->notify_send_init(vsk, &send_data);
if (err < 0)
goto out;
while (total_written < len) {
ssize_t written;
add_wait_queue(sk_sleep(sk), &wait);
while (vsock_stream_has_space(vsk) == 0 &&
sk->sk_err == 0 &&
!(sk->sk_shutdown & SEND_SHUTDOWN) &&
!(vsk->peer_shutdown & RCV_SHUTDOWN)) {
/* Don't wait for non-blocking sockets. */
if (timeout == 0) {
err = -EAGAIN;
remove_wait_queue(sk_sleep(sk), &wait);
goto out_err;
}
err = transport->notify_send_pre_block(vsk, &send_data);
if (err < 0) {
remove_wait_queue(sk_sleep(sk), &wait);
goto out_err;
}
release_sock(sk);
timeout = wait_woken(&wait, TASK_INTERRUPTIBLE, timeout);
lock_sock(sk);
if (signal_pending(current)) {
err = sock_intr_errno(timeout);
remove_wait_queue(sk_sleep(sk), &wait);
goto out_err;
} else if (timeout == 0) {
err = -EAGAIN;
remove_wait_queue(sk_sleep(sk), &wait);
goto out_err;
}
}
remove_wait_queue(sk_sleep(sk), &wait);
/* These checks occur both as part of and after the loop
* conditional since we need to check before and after
* sleeping.
*/
if (sk->sk_err) {
err = -sk->sk_err;
goto out_err;
} else if ((sk->sk_shutdown & SEND_SHUTDOWN) ||
(vsk->peer_shutdown & RCV_SHUTDOWN)) {
err = -EPIPE;
goto out_err;
}
err = transport->notify_send_pre_enqueue(vsk, &send_data);
if (err < 0)
goto out_err;
/* Note that enqueue will only write as many bytes as are free
* in the produce queue, so we don't need to ensure len is
* smaller than the queue size. It is the caller's
* responsibility to check how many bytes we were able to send.
*/
written = transport->stream_enqueue(
vsk, msg,
len - total_written);
if (written < 0) {
err = -ENOMEM;
goto out_err;
}
total_written += written;
err = transport->notify_send_post_enqueue(
vsk, written, &send_data);
if (err < 0)
goto out_err;
}
out_err:
if (total_written > 0)
err = total_written;
out:
release_sock(sk);
return err;
}
static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
int addr_len, int flags)
{
int err;
struct sock *sk;
struct vsock_sock *vsk;
struct sockaddr_vm *remote_addr;
long timeout;
DEFINE_WAIT(wait);
err = 0;
sk = sock->sk;
vsk = vsock_sk(sk);
lock_sock(sk);
/* XXX AF_UNSPEC should make us disconnect like AF_INET. */
switch (sock->state) {
case SS_CONNECTED:
err = -EISCONN;
goto out;
case SS_DISCONNECTING:
err = -EINVAL;
goto out;
case SS_CONNECTING:
/* This continues on so we can move sock into the SS_CONNECTED
* state once the connection has completed (at which point err
* will be set to zero also). Otherwise, we will either wait
* for the connection or return -EALREADY should this be a
* non-blocking call.
*/
err = -EALREADY;
break;
default:
if ((sk->sk_state == SS_LISTEN) ||
vsock_addr_cast(addr, addr_len, &remote_addr) != 0) {
err = -EINVAL;
goto out;
}
/* The hypervisor and well-known contexts do not have socket
* endpoints.
*/
if (!transport->stream_allow(remote_addr->svm_cid,
remote_addr->svm_port)) {
err = -ENETUNREACH;
goto out;
}
/* Set the remote address that we are connecting to. */
memcpy(&vsk->remote_addr, remote_addr,
sizeof(vsk->remote_addr));
/* Autobind this socket to the local address if necessary. */
if (!vsock_addr_bound(&vsk->local_addr)) {
struct sockaddr_vm local_addr;
vsock_addr_init(&local_addr, VMADDR_CID_ANY,
VMADDR_PORT_ANY);
err = __vsock_bind(sk, &local_addr);
if (err != 0)
goto out;
}
sk->sk_state = SS_CONNECTING;
err = transport->connect(vsk);
if (err < 0)
goto out;
/* Mark sock as connecting and set the error code to in
* progress in case this is a non-blocking connect.
*/
sock->state = SS_CONNECTING;
err = -EINPROGRESS;
}
/* The receive path will handle all communication until we are able to
* enter the connected state. Here we wait for the connection to be
* completed or a notification of an error.
*/
timeout = vsk->connect_timeout;
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
while (sk->sk_state != SS_CONNECTED && sk->sk_err == 0) {
if (flags & O_NONBLOCK) {
/* If we're not going to block, we schedule a timeout
* function to generate a timeout on the connection
* attempt, in case the peer doesn't respond in a
* timely manner. We hold on to the socket until the
* timeout fires.
*/
sock_hold(sk);
INIT_DELAYED_WORK(&vsk->dwork,
vsock_connect_timeout);
schedule_delayed_work(&vsk->dwork, timeout);
/* Skip ahead to preserve error code set above. */
goto out_wait;
}
release_sock(sk);
timeout = schedule_timeout(timeout);
lock_sock(sk);
if (signal_pending(current)) {
err = sock_intr_errno(timeout);
goto out_wait_error;
} else if (timeout == 0) {
err = -ETIMEDOUT;
goto out_wait_error;
}
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
if (sk->sk_err) {
err = -sk->sk_err;
goto out_wait_error;
} else
err = 0;
out_wait:
finish_wait(sk_sleep(sk), &wait);
out:
release_sock(sk);
return err;
out_wait_error:
sk->sk_state = SS_UNCONNECTED;
sock->state = SS_UNCONNECTED;
goto out_wait;
}