/**
* sk_stream_wait_connect - Wait for a socket to get into the connected state
* @sk: sock to wait on
* @timeo_p: for how long to wait
*
* Must be called with the socket locked.
*/
int sk_stream_wait_connect(struct sock *sk, long *timeo_p)
{
struct task_struct *tsk = current;
DEFINE_WAIT(wait);
int done;
do {
int err = sock_error(sk);
if (err)
return err;
if ((1 << sk->sk_state) & ~(TCPF_SYN_SENT | TCPF_SYN_RECV))
return -EPIPE;
if (!*timeo_p)
return -EAGAIN;
if (signal_pending(tsk))
return sock_intr_errno(*timeo_p);
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
sk->sk_write_pending++;
done = sk_wait_event(sk, timeo_p,
!sk->sk_err &&
!((1 << sk->sk_state) &
~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)));
finish_wait(sk_sleep(sk), &wait);
sk->sk_write_pending--;
} while (!done);
return 0;
}
/* wait for sndbuf data being transmitted */
static void smc_close_stream_wait(struct smc_sock *smc, long timeout)
{
DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct sock *sk = &smc->sk;
if (!timeout)
return;
if (!smc_tx_prepared_sends(&smc->conn))
return;
smc->wait_close_tx_prepared = 1;
add_wait_queue(sk_sleep(sk), &wait);
while (!signal_pending(current) && timeout) {
int rc;
rc = sk_wait_event(sk, &timeout,
!smc_tx_prepared_sends(&smc->conn) ||
(sk->sk_err == ECONNABORTED) ||
(sk->sk_err == ECONNRESET),
&wait);
if (rc)
break;
}
remove_wait_queue(sk_sleep(sk), &wait);
smc->wait_close_tx_prepared = 0;
}
int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
{
int err = 0;
long vm_wait = 0;
long current_timeo = *timeo_p;
DEFINE_WAIT(wait);
if (sk_stream_memory_free(sk))
current_timeo = vm_wait = (net_random() % (HZ / 5)) + 2;
while (1) {
set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
goto do_error;
if (!*timeo_p)
goto do_nonblock;
if (signal_pending(current))
goto do_interrupted;
clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
if (sk_stream_memory_free(sk) && !vm_wait)
break;
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
sk->sk_write_pending++;
sk_wait_event(sk, ¤t_timeo, sk->sk_err ||
(sk->sk_shutdown & SEND_SHUTDOWN) ||
(sk_stream_memory_free(sk) &&
!vm_wait));
sk->sk_write_pending--;
if (vm_wait) {
vm_wait -= current_timeo;
current_timeo = *timeo_p;
if (current_timeo != MAX_SCHEDULE_TIMEOUT &&
(current_timeo -= vm_wait) < 0)
current_timeo = 0;
vm_wait = 0;
}
*timeo_p = current_timeo;
}
out:
finish_wait(sk_sleep(sk), &wait);
return err;
do_error:
err = -EPIPE;
goto out;
do_nonblock:
err = -EAGAIN;
goto out;
do_interrupted:
err = sock_intr_errno(*timeo_p);
goto out;
}
/* blocks sndbuf producer until at least one byte of free space available */
static int smc_tx_wait_memory(struct smc_sock *smc, int flags)
{
DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct smc_connection *conn = &smc->conn;
struct sock *sk = &smc->sk;
bool noblock;
long timeo;
int rc = 0;
/* similar to sk_stream_wait_memory */
timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
noblock = timeo ? false : true;
add_wait_queue(sk_sleep(sk), &wait);
while (1) {
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
if (sk->sk_err ||
(sk->sk_shutdown & SEND_SHUTDOWN) ||
conn->local_tx_ctrl.conn_state_flags.peer_done_writing) {
rc = -EPIPE;
break;
}
if (smc_cdc_rxed_any_close(conn)) {
rc = -ECONNRESET;
break;
}
if (!timeo) {
if (noblock)
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
rc = -EAGAIN;
break;
}
if (signal_pending(current)) {
rc = sock_intr_errno(timeo);
break;
}
sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
if (atomic_read(&conn->sndbuf_space))
break; /* at least 1 byte of free space available */
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
sk_wait_event(sk, &timeo,
sk->sk_err ||
(sk->sk_shutdown & SEND_SHUTDOWN) ||
smc_cdc_rxed_any_close(conn) ||
atomic_read(&conn->sndbuf_space),
&wait);
}
remove_wait_queue(sk_sleep(sk), &wait);
return rc;
}
void sk_stream_wait_close(struct sock *sk, long timeout)
{
if (timeout) {
DEFINE_WAIT(wait);
do {
prepare_to_wait(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
if (sk_wait_event(sk, &timeout, !sk_stream_closing(sk)))
break;
} while (!signal_pending(current) && timeout);
finish_wait(sk_sleep(sk), &wait);
}
}
static int pep_sendmsg(struct kiocb *iocb, struct sock *sk,
struct msghdr *msg, size_t len)
{
struct pep_sock *pn = pep_sk(sk);
struct sk_buff *skb;
long timeo;
int flags = msg->msg_flags;
int err, done;
if ((msg->msg_flags & ~(MSG_DONTWAIT|MSG_EOR|MSG_NOSIGNAL|
MSG_CMSG_COMPAT)) ||
!(msg->msg_flags & MSG_EOR))
return -EOPNOTSUPP;
skb = sock_alloc_send_skb(sk, MAX_PNPIPE_HEADER + len,
flags & MSG_DONTWAIT, &err);
if (!skb)
return -ENOBUFS;
skb_reserve(skb, MAX_PHONET_HEADER + 3);
err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
if (err < 0)
goto outfree;
lock_sock(sk);
timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
if ((1 << sk->sk_state) & (TCPF_LISTEN|TCPF_CLOSE)) {
err = -ENOTCONN;
goto out;
}
if (sk->sk_state != TCP_ESTABLISHED) {
/* Wait until the pipe gets to enabled state */
disabled:
err = sk_stream_wait_connect(sk, &timeo);
if (err)
goto out;
if (sk->sk_state == TCP_CLOSE_WAIT) {
err = -ECONNRESET;
goto out;
}
}
BUG_ON(sk->sk_state != TCP_ESTABLISHED);
/* Wait until flow control allows TX */
done = atomic_read(&pn->tx_credits);
while (!done) {
DEFINE_WAIT(wait);
if (!timeo) {
err = -EAGAIN;
goto out;
}
if (signal_pending(current)) {
err = sock_intr_errno(timeo);
goto out;
}
prepare_to_wait(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
done = sk_wait_event(sk, &timeo, atomic_read(&pn->tx_credits));
finish_wait(sk_sleep(sk), &wait);
if (sk->sk_state != TCP_ESTABLISHED)
goto disabled;
}
err = pipe_skb_send(sk, skb);
if (err >= 0)
err = len; /* success! */
skb = NULL;
out:
release_sock(sk);
outfree:
kfree_skb(skb);
return err;
}
int virtio_transport_shutdown(struct vsock_sock *vsk, int mode)
{
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_SHUTDOWN,
.type = VIRTIO_VSOCK_TYPE_STREAM,
.flags = (mode & RCV_SHUTDOWN ?
VIRTIO_VSOCK_SHUTDOWN_RCV : 0) |
(mode & SEND_SHUTDOWN ?
VIRTIO_VSOCK_SHUTDOWN_SEND : 0),
.vsk = vsk,
};
return virtio_transport_send_pkt_info(vsk, &info);
}
EXPORT_SYMBOL_GPL(virtio_transport_shutdown);
int
virtio_transport_dgram_enqueue(struct vsock_sock *vsk,
struct sockaddr_vm *remote_addr,
struct msghdr *msg,
size_t dgram_len)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL_GPL(virtio_transport_dgram_enqueue);
ssize_t
virtio_transport_stream_enqueue(struct vsock_sock *vsk,
struct msghdr *msg,
size_t len)
{
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_RW,
.type = VIRTIO_VSOCK_TYPE_STREAM,
.msg = msg,
.pkt_len = len,
.vsk = vsk,
};
return virtio_transport_send_pkt_info(vsk, &info);
}
EXPORT_SYMBOL_GPL(virtio_transport_stream_enqueue);
void virtio_transport_destruct(struct vsock_sock *vsk)
{
struct virtio_vsock_sock *vvs = vsk->trans;
kfree(vvs);
}
EXPORT_SYMBOL_GPL(virtio_transport_destruct);
static int virtio_transport_reset(struct vsock_sock *vsk,
struct virtio_vsock_pkt *pkt)
{
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_RST,
.type = VIRTIO_VSOCK_TYPE_STREAM,
.reply = !!pkt,
.vsk = vsk,
};
/* Send RST only if the original pkt is not a RST pkt */
if (pkt && le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST)
return 0;
return virtio_transport_send_pkt_info(vsk, &info);
}
/* Normally packets are associated with a socket. There may be no socket if an
* attempt was made to connect to a socket that does not exist.
*/
static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt)
{
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_RST,
.type = le16_to_cpu(pkt->hdr.type),
.reply = true,
};
/* Send RST only if the original pkt is not a RST pkt */
if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST)
return 0;
pkt = virtio_transport_alloc_pkt(&info, 0,
le64_to_cpu(pkt->hdr.dst_cid),
le32_to_cpu(pkt->hdr.dst_port),
le64_to_cpu(pkt->hdr.src_cid),
le32_to_cpu(pkt->hdr.src_port));
if (!pkt)
return -ENOMEM;
return virtio_transport_get_ops()->send_pkt(pkt);
}
static void virtio_transport_wait_close(struct sock *sk, long timeout)
{
if (timeout) {
DEFINE_WAIT_FUNC(wait, woken_wake_function);
add_wait_queue(sk_sleep(sk), &wait);
do {
if (sk_wait_event(sk, &timeout,
sock_flag(sk, SOCK_DONE), &wait))
break;
} while (!signal_pending(current) && timeout);
remove_wait_queue(sk_sleep(sk), &wait);
}
}
static void virtio_transport_do_close(struct vsock_sock *vsk,
bool cancel_timeout)
{
struct sock *sk = sk_vsock(vsk);
sock_set_flag(sk, SOCK_DONE);
vsk->peer_shutdown = SHUTDOWN_MASK;
if (vsock_stream_has_data(vsk) <= 0)
sk->sk_state = SS_DISCONNECTING;
sk->sk_state_change(sk);
if (vsk->close_work_scheduled &&
(!cancel_timeout || cancel_delayed_work(&vsk->close_work))) {
vsk->close_work_scheduled = false;
vsock_remove_sock(vsk);
/* Release refcnt obtained when we scheduled the timeout */
sock_put(sk);
}
}
static void virtio_transport_close_timeout(struct work_struct *work)
{
struct vsock_sock *vsk =
container_of(work, struct vsock_sock, close_work.work);
struct sock *sk = sk_vsock(vsk);
sock_hold(sk);
lock_sock(sk);
if (!sock_flag(sk, SOCK_DONE)) {
(void)virtio_transport_reset(vsk, NULL);
virtio_transport_do_close(vsk, false);
}
vsk->close_work_scheduled = false;
release_sock(sk);
sock_put(sk);
}
/* User context, vsk->sk is locked */
static bool virtio_transport_close(struct vsock_sock *vsk)
{
struct sock *sk = &vsk->sk;
if (!(sk->sk_state == SS_CONNECTED ||
sk->sk_state == SS_DISCONNECTING))
return true;
/* Already received SHUTDOWN from peer, reply with RST */
if ((vsk->peer_shutdown & SHUTDOWN_MASK) == SHUTDOWN_MASK) {
(void)virtio_transport_reset(vsk, NULL);
return true;
}
if ((sk->sk_shutdown & SHUTDOWN_MASK) != SHUTDOWN_MASK)
(void)virtio_transport_shutdown(vsk, SHUTDOWN_MASK);
if (sock_flag(sk, SOCK_LINGER) && !(current->flags & PF_EXITING))
virtio_transport_wait_close(sk, sk->sk_lingertime);
if (sock_flag(sk, SOCK_DONE)) {
return true;
}
sock_hold(sk);
INIT_DELAYED_WORK(&vsk->close_work,
virtio_transport_close_timeout);
vsk->close_work_scheduled = true;
schedule_delayed_work(&vsk->close_work, VSOCK_CLOSE_TIMEOUT);
return false;
}
void virtio_transport_release(struct vsock_sock *vsk)
{
struct sock *sk = &vsk->sk;
bool remove_sock = true;
lock_sock(sk);
if (sk->sk_type == SOCK_STREAM)
remove_sock = virtio_transport_close(vsk);
release_sock(sk);
if (remove_sock)
vsock_remove_sock(vsk);
}
EXPORT_SYMBOL_GPL(virtio_transport_release);
static int
virtio_transport_recv_connecting(struct sock *sk,
struct virtio_vsock_pkt *pkt)
{
struct vsock_sock *vsk = vsock_sk(sk);
int err;
int skerr;
switch (le16_to_cpu(pkt->hdr.op)) {
case VIRTIO_VSOCK_OP_RESPONSE:
sk->sk_state = SS_CONNECTED;
sk->sk_socket->state = SS_CONNECTED;
vsock_insert_connected(vsk);
sk->sk_state_change(sk);
break;
case VIRTIO_VSOCK_OP_INVALID:
break;
case VIRTIO_VSOCK_OP_RST:
skerr = ECONNRESET;
err = 0;
goto destroy;
default:
skerr = EPROTO;
err = -EINVAL;
goto destroy;
}
return 0;
destroy:
virtio_transport_reset(vsk, pkt);
sk->sk_state = SS_UNCONNECTED;
sk->sk_err = skerr;
sk->sk_error_report(sk);
return err;
}
static int
virtio_transport_recv_connected(struct sock *sk,
struct virtio_vsock_pkt *pkt)
{
struct vsock_sock *vsk = vsock_sk(sk);
struct virtio_vsock_sock *vvs = vsk->trans;
int err = 0;
switch (le16_to_cpu(pkt->hdr.op)) {
case VIRTIO_VSOCK_OP_RW:
pkt->len = le32_to_cpu(pkt->hdr.len);
pkt->off = 0;
spin_lock_bh(&vvs->rx_lock);
virtio_transport_inc_rx_pkt(vvs, pkt);
list_add_tail(&pkt->list, &vvs->rx_queue);
spin_unlock_bh(&vvs->rx_lock);
sk->sk_data_ready(sk);
return err;
case VIRTIO_VSOCK_OP_CREDIT_UPDATE:
sk->sk_write_space(sk);
break;
case VIRTIO_VSOCK_OP_SHUTDOWN:
if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_RCV)
vsk->peer_shutdown |= RCV_SHUTDOWN;
if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_SEND)
vsk->peer_shutdown |= SEND_SHUTDOWN;
if (vsk->peer_shutdown == SHUTDOWN_MASK &&
vsock_stream_has_data(vsk) <= 0)
sk->sk_state = SS_DISCONNECTING;
if (le32_to_cpu(pkt->hdr.flags))
sk->sk_state_change(sk);
break;
case VIRTIO_VSOCK_OP_RST:
virtio_transport_do_close(vsk, true);
break;
default:
err = -EINVAL;
break;
}
virtio_transport_free_pkt(pkt);
return err;
}
static void
virtio_transport_recv_disconnecting(struct sock *sk,
struct virtio_vsock_pkt *pkt)
{
struct vsock_sock *vsk = vsock_sk(sk);
if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST)
virtio_transport_do_close(vsk, true);
}
static int
virtio_transport_send_response(struct vsock_sock *vsk,
struct virtio_vsock_pkt *pkt)
{
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_RESPONSE,
.type = VIRTIO_VSOCK_TYPE_STREAM,
.remote_cid = le64_to_cpu(pkt->hdr.src_cid),
.remote_port = le32_to_cpu(pkt->hdr.src_port),
.reply = true,
.vsk = vsk,
};
return virtio_transport_send_pkt_info(vsk, &info);
}
/* Handle server socket */
static int
virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt)
{
struct vsock_sock *vsk = vsock_sk(sk);
struct vsock_sock *vchild;
struct sock *child;
if (le16_to_cpu(pkt->hdr.op) != VIRTIO_VSOCK_OP_REQUEST) {
virtio_transport_reset(vsk, pkt);
return -EINVAL;
}
if (sk_acceptq_is_full(sk)) {
virtio_transport_reset(vsk, pkt);
return -ENOMEM;
}
child = __vsock_create(sock_net(sk), NULL, sk, GFP_KERNEL,
sk->sk_type, 0);
if (!child) {
virtio_transport_reset(vsk, pkt);
return -ENOMEM;
}
sk->sk_ack_backlog++;
lock_sock_nested(child, SINGLE_DEPTH_NESTING);
child->sk_state = SS_CONNECTED;
vchild = vsock_sk(child);
vsock_addr_init(&vchild->local_addr, le64_to_cpu(pkt->hdr.dst_cid),
le32_to_cpu(pkt->hdr.dst_port));
vsock_addr_init(&vchild->remote_addr, le64_to_cpu(pkt->hdr.src_cid),
le32_to_cpu(pkt->hdr.src_port));
vsock_insert_connected(vchild);
vsock_enqueue_accept(sk, child);
virtio_transport_send_response(vchild, pkt);
release_sock(child);
sk->sk_data_ready(sk);
return 0;
}
static bool virtio_transport_space_update(struct sock *sk,
struct virtio_vsock_pkt *pkt)
{
struct vsock_sock *vsk = vsock_sk(sk);
struct virtio_vsock_sock *vvs = vsk->trans;
bool space_available;
/* buf_alloc and fwd_cnt is always included in the hdr */
spin_lock_bh(&vvs->tx_lock);
vvs->peer_buf_alloc = le32_to_cpu(pkt->hdr.buf_alloc);
vvs->peer_fwd_cnt = le32_to_cpu(pkt->hdr.fwd_cnt);
space_available = virtio_transport_has_space(vsk);
spin_unlock_bh(&vvs->tx_lock);
return space_available;
}
/* We are under the virtio-vsock's vsock->rx_lock or vhost-vsock's vq->mutex
* lock.
*/
void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt)
{
struct sockaddr_vm src, dst;
struct vsock_sock *vsk;
struct sock *sk;
bool space_available;
vsock_addr_init(&src, le64_to_cpu(pkt->hdr.src_cid),
le32_to_cpu(pkt->hdr.src_port));
vsock_addr_init(&dst, le64_to_cpu(pkt->hdr.dst_cid),
le32_to_cpu(pkt->hdr.dst_port));
trace_virtio_transport_recv_pkt(src.svm_cid, src.svm_port,
dst.svm_cid, dst.svm_port,
le32_to_cpu(pkt->hdr.len),
le16_to_cpu(pkt->hdr.type),
le16_to_cpu(pkt->hdr.op),
le32_to_cpu(pkt->hdr.flags),
le32_to_cpu(pkt->hdr.buf_alloc),
le32_to_cpu(pkt->hdr.fwd_cnt));
if (le16_to_cpu(pkt->hdr.type) != VIRTIO_VSOCK_TYPE_STREAM) {
(void)virtio_transport_reset_no_sock(pkt);
goto free_pkt;
}
/* The socket must be in connected or bound table
* otherwise send reset back
*/
sk = vsock_find_connected_socket(&src, &dst);
if (!sk) {
sk = vsock_find_bound_socket(&dst);
if (!sk) {
(void)virtio_transport_reset_no_sock(pkt);
goto free_pkt;
}
}
vsk = vsock_sk(sk);
space_available = virtio_transport_space_update(sk, pkt);
lock_sock(sk);
/* Update CID in case it has changed after a transport reset event */
vsk->local_addr.svm_cid = dst.svm_cid;
if (space_available)
sk->sk_write_space(sk);
switch (sk->sk_state) {
case VSOCK_SS_LISTEN:
virtio_transport_recv_listen(sk, pkt);
virtio_transport_free_pkt(pkt);
break;
case SS_CONNECTING:
virtio_transport_recv_connecting(sk, pkt);
virtio_transport_free_pkt(pkt);
break;
case SS_CONNECTED:
virtio_transport_recv_connected(sk, pkt);
break;
case SS_DISCONNECTING:
virtio_transport_recv_disconnecting(sk, pkt);
virtio_transport_free_pkt(pkt);
break;
default:
virtio_transport_free_pkt(pkt);
break;
}
release_sock(sk);
/* Release refcnt obtained when we fetched this socket out of the
* bound or connected list.
*/
sock_put(sk);
return;
free_pkt:
virtio_transport_free_pkt(pkt);
}
EXPORT_SYMBOL_GPL(virtio_transport_recv_pkt);
void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt)
{
kfree(pkt->buf);
kfree(pkt);
}
EXPORT_SYMBOL_GPL(virtio_transport_free_pkt);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Asias He");
MODULE_DESCRIPTION("common code for virtio vsock");