/**
* xs_udp_connect_worker - set up a UDP socket
* @args: RPC transport to connect
*
* Invoked by a work queue tasklet.
*/
static void xs_udp_connect_worker(void *args)
{
struct rpc_xprt *xprt = (struct rpc_xprt *) args;
struct socket *sock = xprt->sock;
int err, status = -EIO;
if (xprt->shutdown || xprt->addr.sin_port == 0)
goto out;
dprintk("RPC: xs_udp_connect_worker for xprt %p\n", xprt);
/* Start by resetting any existing state */
xs_close(xprt);
if ((err = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock)) < 0) {
dprintk("RPC: can't create UDP transport socket (%d).\n", -err);
goto out;
}
xs_reclassify_socket(sock);
if (xs_bind(xprt, sock)) {
sock_release(sock);
goto out;
}
if (!xprt->inet) {
struct sock *sk = sock->sk;
write_lock_bh(&sk->sk_callback_lock);
sk->sk_user_data = xprt;
xprt->old_data_ready = sk->sk_data_ready;
xprt->old_state_change = sk->sk_state_change;
xprt->old_write_space = sk->sk_write_space;
sk->sk_data_ready = xs_udp_data_ready;
sk->sk_write_space = xs_udp_write_space;
sk->sk_no_check = UDP_CSUM_NORCV;
sk->sk_allocation = GFP_ATOMIC;
xprt_set_connected(xprt);
/* Reset to new socket */
xprt->sock = sock;
xprt->inet = sk;
write_unlock_bh(&sk->sk_callback_lock);
}
xs_udp_do_set_buffer_size(xprt);
status = 0;
out:
xprt_wake_pending_tasks(xprt, status);
xprt_clear_connecting(xprt);
}
/**
* xprt_rdma_connect_worker - establish connection in the background
* @work: worker thread context
*
* Requester holds the xprt's send lock to prevent activity on this
* transport while a fresh connection is being established. RPC tasks
* sleep on the xprt's pending queue waiting for connect to complete.
*/
static void
xprt_rdma_connect_worker(struct work_struct *work)
{
struct rpcrdma_xprt *r_xprt = container_of(work, struct rpcrdma_xprt,
rx_connect_worker.work);
struct rpc_xprt *xprt = &r_xprt->rx_xprt;
int rc;
rc = rpcrdma_ep_connect(&r_xprt->rx_ep, &r_xprt->rx_ia);
xprt_clear_connecting(xprt);
if (r_xprt->rx_ep.rep_connected > 0) {
if (!xprt_test_and_set_connected(xprt)) {
xprt->stat.connect_count++;
xprt->stat.connect_time += (long)jiffies -
xprt->stat.connect_start;
xprt_wake_pending_tasks(xprt, -EAGAIN);
}
} else {
if (xprt_test_and_clear_connected(xprt))
xprt_wake_pending_tasks(xprt, rc);
}
}
static void
xprt_rdma_connect_worker(struct work_struct *work)
{
struct rpcrdma_xprt *r_xprt = container_of(work, struct rpcrdma_xprt,
rx_connect_worker.work);
struct rpc_xprt *xprt = &r_xprt->rx_xprt;
int rc = 0;
xprt_clear_connected(xprt);
dprintk("RPC: %s: %sconnect\n", __func__,
r_xprt->rx_ep.rep_connected != 0 ? "re" : "");
rc = rpcrdma_ep_connect(&r_xprt->rx_ep, &r_xprt->rx_ia);
if (rc)
xprt_wake_pending_tasks(xprt, rc);
dprintk("RPC: %s: exit\n", __func__);
xprt_clear_connecting(xprt);
}
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);
}
/**
* xs_tcp_connect_worker - connect a TCP socket to a remote endpoint
* @args: RPC transport to connect
*
* Invoked by a work queue tasklet.
*/
static void xs_tcp_connect_worker(void *args)
{
struct rpc_xprt *xprt = (struct rpc_xprt *)args;
struct socket *sock = xprt->sock;
int err, status = -EIO;
if (xprt->shutdown || xprt->addr.sin_port == 0)
goto out;
dprintk("RPC: xs_tcp_connect_worker for xprt %p\n", xprt);
if (!xprt->sock) {
/* start from scratch */
if ((err = sock_create_kern(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock)) < 0) {
dprintk("RPC: can't create TCP transport socket (%d).\n", -err);
goto out;
}
xs_reclassify_socket(sock);
if (xs_bind(xprt, sock)) {
sock_release(sock);
goto out;
}
} else
/* "close" the socket, preserving the local port */
xs_tcp_reuse_connection(xprt);
if (!xprt->inet) {
struct sock *sk = sock->sk;
write_lock_bh(&sk->sk_callback_lock);
sk->sk_user_data = xprt;
xprt->old_data_ready = sk->sk_data_ready;
xprt->old_state_change = sk->sk_state_change;
xprt->old_write_space = sk->sk_write_space;
sk->sk_data_ready = xs_tcp_data_ready;
sk->sk_state_change = xs_tcp_state_change;
sk->sk_write_space = xs_tcp_write_space;
sk->sk_allocation = GFP_ATOMIC;
/* socket options */
sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
sock_reset_flag(sk, SOCK_LINGER);
tcp_sk(sk)->linger2 = 0;
tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF;
xprt_clear_connected(xprt);
/* Reset to new socket */
xprt->sock = sock;
xprt->inet = sk;
write_unlock_bh(&sk->sk_callback_lock);
}
/* Tell the socket layer to start connecting... */
xprt->stat.connect_count++;
xprt->stat.connect_start = jiffies;
status = kernel_connect(sock, (struct sockaddr *) &xprt->addr,
sizeof(xprt->addr), O_NONBLOCK);
dprintk("RPC: %p connect status %d connected %d sock state %d\n",
xprt, -status, xprt_connected(xprt), sock->sk->sk_state);
if (status < 0) {
switch (status) {
case -EINPROGRESS:
case -EALREADY:
goto out_clear;
case -ECONNREFUSED:
case -ECONNRESET:
/* retry with existing socket, after a delay */
break;
case -ENETUNREACH:
status = -ENOTCONN;
break;
default:
/* get rid of existing socket, and retry */
xs_close(xprt);
break;
}
}
out:
xprt_wake_pending_tasks(xprt, status);
out_clear:
xprt_clear_connecting(xprt);
}