static unsigned int
kni_sock_poll(struct file *file, struct socket *sock, poll_table * wait)
{
struct kni_vhost_queue *q =
container_of(sock->sk, struct kni_vhost_queue, sk);
struct kni_dev *kni;
unsigned int mask = 0;
if (unlikely(q == NULL || q->kni == NULL))
return POLLERR;
kni = q->kni;
KNI_DBG("start kni_poll on group %d, wq 0x%16llx\n",
kni->group_id, (uint64_t)sock->wq);
poll_wait(file, &sock->wq->wait, wait);
if (kni_fifo_count(kni->rx_q) > 0)
mask |= POLLIN | POLLRDNORM;
if (sock_writeable(&q->sk) ||
(!test_and_set_bit(SOCK_ASYNC_NOSPACE, &q->sock->flags) &&
sock_writeable(&q->sk)))
mask |= POLLOUT | POLLWRNORM;
return mask;
}
unsigned int datagram_poll(struct file * file, struct socket *sock, poll_table *wait)
{
struct sock *sk = sock->sk;
unsigned int mask;
poll_wait(file, sk->sleep, wait);
mask = 0;
/* exceptional events? */
if (sk->err || !skb_queue_empty(&sk->error_queue))
mask |= POLLERR;
if (sk->shutdown == SHUTDOWN_MASK)
mask |= POLLHUP;
/* readable? */
if (!skb_queue_empty(&sk->receive_queue) || (sk->shutdown&RCV_SHUTDOWN))
mask |= POLLIN | POLLRDNORM;
/* Connection-based need to check for termination and startup */
if (connection_based(sk)) {
if (sk->state==TCP_CLOSE)
mask |= POLLHUP;
/* connection hasn't started yet? */
if (sk->state == TCP_SYN_SENT)
return mask;
}
/* writable? */
if (sock_writeable(sk))
mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
else
set_bit(SOCK_ASYNC_NOSPACE, &sk->socket->flags);
return mask;
}
void dccp_write_space(struct sock *sk)
{
read_lock(&sk->sk_callback_lock);
if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
wake_up_interruptible(sk->sk_sleep);
/* Should agree with poll, otherwise some programs break */
if (sock_writeable(sk))
sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
read_unlock(&sk->sk_callback_lock);
}
void dccp_write_space(struct sock *sk)
{
read_lock(&sk->sk_callback_lock);
if (sk_has_sleeper(sk))
wake_up_interruptible(sk->sk_sleep);
if (sock_writeable(sk))
sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
read_unlock(&sk->sk_callback_lock);
}
void dccp_write_space(struct sock *sk)
{
struct socket_wq *wq;
rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
if (wq_has_sleeper(wq))
wake_up_interruptible(&wq->wait);
/* Should agree with poll, otherwise some programs break */
if (sock_writeable(sk))
sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
rcu_read_unlock();
}
static void
kni_sk_write_space(struct sock *sk)
{
wait_queue_head_t *wqueue;
if (!sock_writeable(sk) ||
!test_and_clear_bit(SOCK_ASYNC_NOSPACE,
&sk->sk_socket->flags))
return;
wqueue = sk_sleep(sk);
if (wqueue && waitqueue_active(wqueue))
wake_up_interruptible_poll(
wqueue, POLLOUT | POLLWRNORM | POLLWRBAND);
}
static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, unsigned int offset, size_t len)
{
struct rpc_xprt *xprt = rd_desc->arg.data;
skb_reader_t desc = {
.skb = skb,
.offset = offset,
.count = len,
.csum = 0
};
dprintk("RPC: xs_tcp_data_recv started\n");
do {
/* Read in a new fragment marker if necessary */
/* Can we ever really expect to get completely empty fragments? */
if (xprt->tcp_flags & XPRT_COPY_RECM) {
xs_tcp_read_fraghdr(xprt, &desc);
continue;
}
/* Read in the xid if necessary */
if (xprt->tcp_flags & XPRT_COPY_XID) {
xs_tcp_read_xid(xprt, &desc);
continue;
}
/* Read in the request data */
if (xprt->tcp_flags & XPRT_COPY_DATA) {
xs_tcp_read_request(xprt, &desc);
continue;
}
/* Skip over any trailing bytes on short reads */
xs_tcp_read_discard(xprt, &desc);
} while (desc.count);
dprintk("RPC: xs_tcp_data_recv done\n");
return len - desc.count;
}
/**
* xs_tcp_data_ready - "data ready" callback for TCP sockets
* @sk: socket with data to read
* @bytes: how much data to read
*
*/
static void xs_tcp_data_ready(struct sock *sk, int bytes)
{
struct rpc_xprt *xprt;
read_descriptor_t rd_desc;
read_lock(&sk->sk_callback_lock);
dprintk("RPC: xs_tcp_data_ready...\n");
if (!(xprt = xprt_from_sock(sk)))
goto out;
if (xprt->shutdown)
goto out;
/* We use rd_desc to pass struct xprt to xs_tcp_data_recv */
rd_desc.arg.data = xprt;
rd_desc.count = 65536;
tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv);
out:
read_unlock(&sk->sk_callback_lock);
}
/**
* xs_tcp_state_change - callback to handle TCP socket state changes
* @sk: socket whose state has changed
*
*/
static void xs_tcp_state_change(struct sock *sk)
{
struct rpc_xprt *xprt;
read_lock(&sk->sk_callback_lock);
if (!(xprt = xprt_from_sock(sk)))
goto out;
dprintk("RPC: xs_tcp_state_change client %p...\n", xprt);
dprintk("RPC: state %x conn %d dead %d zapped %d\n",
sk->sk_state, xprt_connected(xprt),
sock_flag(sk, SOCK_DEAD),
sock_flag(sk, SOCK_ZAPPED));
switch (sk->sk_state) {
case TCP_ESTABLISHED:
spin_lock_bh(&xprt->transport_lock);
if (!xprt_test_and_set_connected(xprt)) {
/* Reset TCP record info */
xprt->tcp_offset = 0;
xprt->tcp_reclen = 0;
xprt->tcp_copied = 0;
if (xprt->tcp_flags & XPRT_SRCADDR_PRESENT)
xprt->tcp_flags = XPRT_SRCADDR_PRESENT |
XPRT_COPY_RECM |
XPRT_COPY_XID;
else
xprt->tcp_flags = XPRT_COPY_RECM |
XPRT_COPY_XID;
xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
xprt_wake_pending_tasks(xprt, 0);
}
spin_unlock_bh(&xprt->transport_lock);
break;
case TCP_SYN_SENT:
case TCP_SYN_RECV:
break;
case TCP_CLOSE_WAIT:
/* Try to schedule an autoclose RPC calls */
set_bit(XPRT_CLOSE_WAIT, &xprt->state);
if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0)
queue_work(rpciod_workqueue, &xprt->task_cleanup);
default:
xprt_disconnect(xprt);
}
out:
read_unlock(&sk->sk_callback_lock);
}
/**
* xs_udp_write_space - callback invoked when socket buffer space
* becomes available
* @sk: socket whose state has changed
*
* Called when more output buffer space is available for this socket.
* We try not to wake our writers until they can make "significant"
* progress, otherwise we'll waste resources thrashing kernel_sendmsg
* with a bunch of small requests.
*/
static void xs_udp_write_space(struct sock *sk)
{
read_lock(&sk->sk_callback_lock);
/* from net/core/sock.c:sock_def_write_space */
if (sock_writeable(sk)) {
struct socket *sock;
struct rpc_xprt *xprt;
if (unlikely(!(sock = sk->sk_socket)))
goto out;
if (unlikely(!(xprt = xprt_from_sock(sk))))
goto out;
if (unlikely(!test_and_clear_bit(SOCK_NOSPACE, &sock->flags)))
goto out;
xprt_write_space(xprt);
}
out:
read_unlock(&sk->sk_callback_lock);
}