/**
* 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;
}
static int pep_wait_connreq(struct sock *sk, int noblock)
{
struct task_struct *tsk = current;
struct pep_sock *pn = pep_sk(sk);
long timeo = sock_rcvtimeo(sk, noblock);
for (;;) {
DEFINE_WAIT(wait);
if (sk->sk_state != TCP_LISTEN)
return -EINVAL;
if (!hlist_empty(&pn->ackq))
break;
if (!timeo)
return -EWOULDBLOCK;
if (signal_pending(tsk))
return sock_intr_errno(timeo);
prepare_to_wait_exclusive(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
release_sock(sk);
timeo = schedule_timeout(timeo);
lock_sock(sk);
finish_wait(sk_sleep(sk), &wait);
}
return 0;
}
/*
* wait for space to appear in the transmit/ACK window
* - caller holds the socket locked
*/
static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx,
struct rxrpc_call *call,
long *timeo)
{
DECLARE_WAITQUEUE(myself, current);
int ret;
_enter(",{%d},%ld",
CIRC_SPACE(call->acks_head, call->acks_tail, call->acks_winsz),
*timeo);
add_wait_queue(&call->tx_waitq, &myself);
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
ret = 0;
if (CIRC_SPACE(call->acks_head, call->acks_tail,
call->acks_winsz) > 0)
break;
if (signal_pending(current)) {
ret = sock_intr_errno(*timeo);
break;
}
release_sock(&rx->sk);
*timeo = schedule_timeout(*timeo);
lock_sock(&rx->sk);
}
remove_wait_queue(&call->tx_waitq, &myself);
set_current_state(TASK_RUNNING);
_leave(" = %d", ret);
return ret;
}
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;
}
static int l2cap_sock_accept(struct socket *sock, struct socket *newsock,
int flags)
{
DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct sock *sk = sock->sk, *nsk;
long timeo;
int err = 0;
lock_sock_nested(sk, L2CAP_NESTING_PARENT);
timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);
BT_DBG("sk %p timeo %ld", sk, timeo);
/* Wait for an incoming connection. (wake-one). */
add_wait_queue_exclusive(sk_sleep(sk), &wait);
while (1) {
if (sk->sk_state != BT_LISTEN) {
err = -EBADFD;
break;
}
nsk = bt_accept_dequeue(sk, newsock);
if (nsk)
break;
if (!timeo) {
err = -EAGAIN;
break;
}
if (signal_pending(current)) {
err = sock_intr_errno(timeo);
break;
}
release_sock(sk);
timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
lock_sock_nested(sk, L2CAP_NESTING_PARENT);
}
remove_wait_queue(sk_sleep(sk), &wait);
if (err)
goto done;
newsock->state = SS_CONNECTED;
BT_DBG("new socket %p", nsk);
done:
release_sock(sk);
return err;
}
static int l2cap_sock_accept(struct socket *sock, struct socket *newsock, int flags)
{
DECLARE_WAITQUEUE(wait, current);
struct sock *sk = sock->sk, *nsk;
long timeo;
int err = 0;
lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
if (sk->sk_state != BT_LISTEN) {
err = -EBADFD;
goto done;
}
timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);
BT_DBG("sk %p timeo %ld", sk, timeo);
/* Wait for an incoming connection. (wake-one). */
add_wait_queue_exclusive(sk_sleep(sk), &wait);
while (!(nsk = bt_accept_dequeue(sk, newsock))) {
set_current_state(TASK_INTERRUPTIBLE);
if (!timeo) {
err = -EAGAIN;
break;
}
release_sock(sk);
timeo = schedule_timeout(timeo);
lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
if (sk->sk_state != BT_LISTEN) {
err = -EBADFD;
break;
}
if (signal_pending(current)) {
err = sock_intr_errno(timeo);
break;
}
}
set_current_state(TASK_RUNNING);
remove_wait_queue(sk_sleep(sk), &wait);
if (err)
goto done;
newsock->state = SS_CONNECTED;
BT_DBG("new socket %p", nsk);
done:
release_sock(sk);
return err;
}
/*
* Wrapper for the above, for allocs of data skbs. We try and get the
* whole size thats been asked for (plus 11 bytes of header). If this
* fails, then we try for any size over 16 bytes for SOCK_STREAMS.
*/
struct sk_buff *dn_alloc_send_skb(struct sock *sk, size_t *size, int noblock, long timeo, int *err)
{
int space;
int len;
struct sk_buff *skb = NULL;
*err = 0;
while(skb == NULL) {
if (signal_pending(current)) {
*err = sock_intr_errno(timeo);
break;
}
if (sk->sk_shutdown & SEND_SHUTDOWN) {
*err = EINVAL;
break;
}
if (sk->sk_err)
break;
len = *size + 11;
space = sk->sk_sndbuf - atomic_read(&sk->sk_wmem_alloc);
if (space < len) {
if ((sk->sk_socket->type == SOCK_STREAM) &&
(space >= (16 + 11)))
len = space;
}
if (space < len) {
set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
if (noblock) {
*err = EWOULDBLOCK;
break;
}
clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
SOCK_SLEEP_PRE(sk)
if ((sk->sk_sndbuf - atomic_read(&sk->sk_wmem_alloc)) <
len)
schedule();
SOCK_SLEEP_POST(sk)
continue;
}
if ((skb = dn_alloc_skb(sk, len, sk->sk_allocation)) == NULL)
continue;
*size = len - 11;
}
static int wait_for_packet(struct sock * sk, int *err, long *timeo_p)
{
int error;
DECLARE_WAITQUEUE(wait, current);
__set_current_state(TASK_INTERRUPTIBLE);
add_wait_queue_exclusive(sk->sleep, &wait);
/* Socket errors? */
error = sock_error(sk);
if (error)
goto out_err;
if (!skb_queue_empty(&sk->receive_queue))
goto ready;
/* Socket shut down? */
if (sk->shutdown & RCV_SHUTDOWN)
goto out_noerr;
/* Sequenced packets can come disconnected. If so we report the problem */
error = -ENOTCONN;
if(connection_based(sk) && !(sk->state==TCP_ESTABLISHED || sk->state==TCP_LISTEN))
goto out_err;
/* handle signals */
if (signal_pending(current))
goto interrupted;
*timeo_p = schedule_timeout(*timeo_p);
ready:
current->state = TASK_RUNNING;
remove_wait_queue(sk->sleep, &wait);
return 0;
interrupted:
error = sock_intr_errno(*timeo_p);
out_err:
*err = error;
out:
current->state = TASK_RUNNING;
remove_wait_queue(sk->sleep, &wait);
return error;
out_noerr:
*err = 0;
error = 1;
goto out;
}
/*
* Wait for a packet..
*/
static int wait_for_packet(struct sock *sk, int *err, long *timeo_p)
{
int error;
DEFINE_WAIT_FUNC(wait, receiver_wake_function);
/*
前面的操作都是初始化wait，为将socket加入wait队列作准备，这部分代码牵涉到进程调度。关于进程调度，我 只是知道一些皮毛，留在以后学习。这里只需要将其看作是一些加入wait队列的准备工作即可，并不影响理解代码 。
*/
prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
/* Socket errors? */
error = sock_error(sk);
if (error)
goto out_err;
/* 一个完备检测。在决定wait和调用wait之间，有数据包到了，那么就不需要wait，所以这里再次检查socket 的队列是否为空 */
if (!skb_queue_empty(&sk->sk_receive_queue))
goto out;
/* Socket shut down? */
/* 完备检测。也许socket无数据包读取，因为socket已经被另外的线程关闭了。这样可以保证关闭socket的时 候，不会导致其他的socket的读写操作被阻塞。*/
if (sk->sk_shutdown & RCV_SHUTDOWN)
goto out_noerr;
/* Sequenced packets can come disconnected.
* If so we report the problem
*//* 对于面向连接的socket进行检查。如果是面向连接的socket，如果不是已经建立连接或者正在监听状态的so cket是不可能有数据包的。不然即出错*/
error = -ENOTCONN;
if (connection_based(sk) &&
!(sk->sk_state == TCP_ESTABLISHED || sk->sk_state == TCP_LISTEN))
goto out_err;
/* handle signals */
if (signal_pending(current))/* 检查是否有pending的signal，保证阻塞时，进程可以被signal唤醒 */
goto interrupted;
error = 0;
*timeo_p = schedule_timeout(*timeo_p); /* sleep本进程，直至满足唤醒条件或者被信号唤醒——因为前面设置了TASK_INTERRUPTIBLE*/
out:
finish_wait(sk_sleep(sk), &wait); /* wait队列的清理工作 */
return error;
interrupted:
error = sock_intr_errno(*timeo_p);
out_err:
*err = error;
goto out;
out_noerr:
*err = 0;
error = 1;
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;
}
static void skb_async_read_worker(void *_data)
{
struct skb_async_info *info = _data;
int error;
/* Socket errors? */
error = sock_error(sk);
if (error)
goto out_err;
if (!skb_queue_empty(&sk->receive_queue))
goto ready;
/* Socket shut down? */
if (sk->shutdown & RCV_SHUTDOWN)
goto out_noerr;
/* Sequenced packets can come disconnected. If so we report the problem */
error = -ENOTCONN;
if(connection_based(sk) && !(sk->state==TCP_ESTABLISHED || sk->state==TCP_LISTEN))
goto out_err;
/* handle signals */
if (signal_pending(current))
goto interrupted;
/* here: queue sleep */
*timeo_p = schedule_timeout(*timeo_p);
return;
ready:
current->state = TASK_RUNNING;
remove_wait_queue(sk->sleep, &wait);
return 0;
interrupted:
error = sock_intr_errno(*timeo_p);
out_err:
*err = error;
out:
current->state = TASK_RUNNING;
remove_wait_queue(sk->sleep, &wait);
return error;
out_noerr:
*err = 0;
error = 1;
goto out;
}
/*
* Wait for the last received packet to be different from skb
*/
static int wait_for_more_packets(struct sock *sk, int *err, long *timeo_p,
const struct sk_buff *skb)
{
int error;
DEFINE_WAIT_FUNC(wait, receiver_wake_function);
prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
/* Socket errors? */
error = sock_error(sk);
if (error)
goto out_err;
if (sk->sk_receive_queue.prev != skb)
goto out;
/* Socket shut down? */
if (sk->sk_shutdown & RCV_SHUTDOWN)
goto out_noerr;
/* Sequenced packets can come disconnected.
* If so we report the problem
*/
error = -ENOTCONN;
if (connection_based(sk) &&
!(sk->sk_state == TCP_ESTABLISHED || sk->sk_state == TCP_LISTEN))
goto out_err;
/* handle signals */
if (signal_pending(current))
goto interrupted;
error = 0;
*timeo_p = schedule_timeout(*timeo_p);
out:
finish_wait(sk_sleep(sk), &wait);
return error;
interrupted:
error = sock_intr_errno(*timeo_p);
out_err:
*err = error;
goto out;
out_noerr:
*err = 0;
error = 1;
goto out;
}
/**
* dccp_wait_for_ccid - Wait for ccid to tell us we can send a packet
* @sk: socket to wait for
* @timeo: for how long
*/
static int dccp_wait_for_ccid(struct sock *sk, struct sk_buff *skb,
long *timeo)
{
struct dccp_sock *dp = dccp_sk(sk);
DEFINE_WAIT(wait);
long delay;
int rc;
while (1) {
prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
goto do_error;
if (!*timeo)
goto do_nonblock;
if (signal_pending(current))
goto do_interrupted;
rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb,
skb->len);
if (rc <= 0)
break;
delay = msecs_to_jiffies(rc);
if (delay > *timeo || delay < 0)
goto do_nonblock;
sk->sk_write_pending++;
release_sock(sk);
*timeo -= schedule_timeout(delay);
lock_sock(sk);
sk->sk_write_pending--;
}
out:
finish_wait(sk->sk_sleep, &wait);
return rc;
do_error:
rc = -EPIPE;
goto out;
do_nonblock:
rc = -EAGAIN;
goto out;
do_interrupted:
rc = sock_intr_errno(*timeo);
goto out;
}
/*
* Attach a skb to a netlink socket.
* The caller must hold a reference to the destination socket. On error, the
* reference is dropped. The skb is not send to the destination, just all
* all error checks are performed and memory in the queue is reserved.
* Return values:
* < 0: error. skb freed, reference to sock dropped.
* 0: continue
* 1: repeat lookup - reference dropped while waiting for socket memory.
*/
int netlink_attachskb(struct sock *sk, struct sk_buff *skb, int nonblock,
long timeo, struct sock *ssk)
{
struct netlink_opt *nlk;
nlk = nlk_sk(sk);
#ifdef NL_EMULATE_DEV
if (nlk->handler)
return 0;
#endif
if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
test_bit(0, &nlk->state)) {
DECLARE_WAITQUEUE(wait, current);
if (!timeo) {
if (!ssk || nlk_sk(ssk)->pid == 0)
netlink_overrun(sk);
sock_put(sk);
kfree_skb(skb);
return -EAGAIN;
}
__set_current_state(TASK_INTERRUPTIBLE);
add_wait_queue(&nlk->wait, &wait);
if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
test_bit(0, &nlk->state)) &&
!sock_flag(sk, SOCK_DEAD))
timeo = schedule_timeout(timeo);
__set_current_state(TASK_RUNNING);
remove_wait_queue(&nlk->wait, &wait);
sock_put(sk);
if (signal_pending(current)) {
kfree_skb(skb);
return sock_intr_errno(timeo);
}
return 1;
}
skb_orphan(skb);
skb_set_owner_r(skb, sk);
return 0;
}
static int wait_for_packet(struct sock *sk, int *err, long *timeo_p)
{
int error;
DEFINE_WAIT_FUNC(wait, receiver_wake_function);
prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
error = sock_error(sk);
if (error)
goto out_err;
if (!skb_queue_empty(&sk->sk_receive_queue))
goto out;
if (sk->sk_shutdown & RCV_SHUTDOWN)
goto out_noerr;
error = -ENOTCONN;
if (connection_based(sk) &&
!(sk->sk_state == TCP_ESTABLISHED || sk->sk_state == TCP_LISTEN))
goto out_err;
if (signal_pending(current))
goto interrupted;
error = 0;
*timeo_p = schedule_timeout(*timeo_p);
out:
finish_wait(sk_sleep(sk), &wait);
return error;
interrupted:
error = sock_intr_errno(*timeo_p);
out_err:
*err = error;
goto out;
out_noerr:
*err = 0;
error = 1;
goto out;
}
static int pn_socket_connect(struct socket *sock, struct sockaddr *addr,
int len, int flags)
{
struct sock *sk = sock->sk;
struct pn_sock *pn = pn_sk(sk);
struct sockaddr_pn *spn = (struct sockaddr_pn *)addr;
struct task_struct *tsk = current;
long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);
int err;
if (pn_socket_autobind(sock))
return -ENOBUFS;
if (len < sizeof(struct sockaddr_pn))
return -EINVAL;
if (spn->spn_family != AF_PHONET)
return -EAFNOSUPPORT;
lock_sock(sk);
switch (sock->state) {
case SS_UNCONNECTED:
if (sk->sk_state != TCP_CLOSE) {
err = -EISCONN;
goto out;
}
break;
case SS_CONNECTING:
err = -EALREADY;
goto out;
default:
err = -EISCONN;
goto out;
}
pn->dobject = pn_sockaddr_get_object(spn);
pn->resource = pn_sockaddr_get_resource(spn);
sock->state = SS_CONNECTING;
err = sk->sk_prot->connect(sk, addr, len);
if (err) {
sock->state = SS_UNCONNECTED;
pn->dobject = 0;
goto out;
}
while (sk->sk_state == TCP_SYN_SENT) {
DEFINE_WAIT(wait);
if (!timeo) {
err = -EINPROGRESS;
goto out;
}
if (signal_pending(tsk)) {
err = sock_intr_errno(timeo);
goto out;
}
prepare_to_wait_exclusive(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
release_sock(sk);
timeo = schedule_timeout(timeo);
lock_sock(sk);
finish_wait(sk_sleep(sk), &wait);
}
if ((1 << sk->sk_state) & (TCPF_SYN_RECV|TCPF_ESTABLISHED))
err = 0;
else if (sk->sk_state == TCP_CLOSE_WAIT)
err = -ECONNRESET;
else
err = -ECONNREFUSED;
sock->state = err ? SS_UNCONNECTED : SS_CONNECTED;
out:
release_sock(sk);
return err;
}
/*
* Receive a message from an RxRPC socket
* - we need to be careful about two or more threads calling recvmsg
* simultaneously
*/
int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
int flags)
{
struct rxrpc_call *call;
struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
struct list_head *l;
size_t copied = 0;
long timeo;
int ret;
DEFINE_WAIT(wait);
trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_enter, 0, 0, 0, 0);
if (flags & (MSG_OOB | MSG_TRUNC))
return -EOPNOTSUPP;
timeo = sock_rcvtimeo(&rx->sk, flags & MSG_DONTWAIT);
try_again:
lock_sock(&rx->sk);
/* Return immediately if a client socket has no outstanding calls */
if (RB_EMPTY_ROOT(&rx->calls) &&
list_empty(&rx->recvmsg_q) &&
rx->sk.sk_state != RXRPC_SERVER_LISTENING) {
release_sock(&rx->sk);
return -ENODATA;
}
if (list_empty(&rx->recvmsg_q)) {
ret = -EWOULDBLOCK;
if (timeo == 0) {
call = NULL;
goto error_no_call;
}
release_sock(&rx->sk);
/* Wait for something to happen */
prepare_to_wait_exclusive(sk_sleep(&rx->sk), &wait,
TASK_INTERRUPTIBLE);
ret = sock_error(&rx->sk);
if (ret)
goto wait_error;
if (list_empty(&rx->recvmsg_q)) {
if (signal_pending(current))
goto wait_interrupted;
trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_wait,
0, 0, 0, 0);
timeo = schedule_timeout(timeo);
}
finish_wait(sk_sleep(&rx->sk), &wait);
goto try_again;
}
/* Find the next call and dequeue it if we're not just peeking. If we
* do dequeue it, that comes with a ref that we will need to release.
*/
write_lock_bh(&rx->recvmsg_lock);
l = rx->recvmsg_q.next;
call = list_entry(l, struct rxrpc_call, recvmsg_link);
if (!(flags & MSG_PEEK))
list_del_init(&call->recvmsg_link);
else
rxrpc_get_call(call, rxrpc_call_got);
write_unlock_bh(&rx->recvmsg_lock);
trace_rxrpc_recvmsg(call, rxrpc_recvmsg_dequeue, 0, 0, 0, 0);
if (test_bit(RXRPC_CALL_RELEASED, &call->flags))
BUG();
if (test_bit(RXRPC_CALL_HAS_USERID, &call->flags)) {
if (flags & MSG_CMSG_COMPAT) {
unsigned int id32 = call->user_call_ID;
ret = put_cmsg(msg, SOL_RXRPC, RXRPC_USER_CALL_ID,
sizeof(unsigned int), &id32);
} else {
ret = put_cmsg(msg, SOL_RXRPC, RXRPC_USER_CALL_ID,
sizeof(unsigned long),
&call->user_call_ID);
}
if (ret < 0)
goto error;
}
if (msg->msg_name) {
size_t len = sizeof(call->conn->params.peer->srx);
memcpy(msg->msg_name, &call->conn->params.peer->srx, len);
msg->msg_namelen = len;
}
switch (call->state) {
case RXRPC_CALL_SERVER_ACCEPTING:
ret = rxrpc_recvmsg_new_call(rx, call, msg, flags);
break;
case RXRPC_CALL_CLIENT_RECV_REPLY:
case RXRPC_CALL_SERVER_RECV_REQUEST:
case RXRPC_CALL_SERVER_ACK_REQUEST:
ret = rxrpc_recvmsg_data(sock, call, msg, &msg->msg_iter, len,
flags, &copied);
if (ret == -EAGAIN)
ret = 0;
if (after(call->rx_top, call->rx_hard_ack) &&
call->rxtx_buffer[(call->rx_hard_ack + 1) & RXRPC_RXTX_BUFF_MASK])
rxrpc_notify_socket(call);
break;
default:
ret = 0;
break;
}
if (ret < 0)
goto error;
if (call->state == RXRPC_CALL_COMPLETE) {
ret = rxrpc_recvmsg_term(call, msg);
if (ret < 0)
goto error;
if (!(flags & MSG_PEEK))
rxrpc_release_call(rx, call);
msg->msg_flags |= MSG_EOR;
ret = 1;
}
if (ret == 0)
msg->msg_flags |= MSG_MORE;
else
msg->msg_flags &= ~MSG_MORE;
ret = copied;
error:
rxrpc_put_call(call, rxrpc_call_put);
error_no_call:
release_sock(&rx->sk);
trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret);
return ret;
wait_interrupted:
ret = sock_intr_errno(timeo);
wait_error:
finish_wait(sk_sleep(&rx->sk), &wait);
call = NULL;
goto error_no_call;
}
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;
}
static int
vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
int flags)
{
struct sock *sk;
struct vsock_sock *vsk;
int err;
size_t target;
ssize_t copied;
long timeout;
struct vsock_transport_recv_notify_data recv_data;
DEFINE_WAIT(wait);
sk = sock->sk;
vsk = vsock_sk(sk);
err = 0;
lock_sock(sk);
if (sk->sk_state != TCP_ESTABLISHED) {
/* Recvmsg is supposed to return 0 if a peer performs an
* orderly shutdown. Differentiate between that case and when a
* peer has not connected or a local shutdown occured with the
* SOCK_DONE flag.
*/
if (sock_flag(sk, SOCK_DONE))
err = 0;
else
err = -ENOTCONN;
goto out;
}
if (flags & MSG_OOB) {
err = -EOPNOTSUPP;
goto out;
}
/* We don't check peer_shutdown flag here since peer may actually shut
* down, but there can be data in the queue that a local socket can
* receive.
*/
if (sk->sk_shutdown & RCV_SHUTDOWN) {
err = 0;
goto out;
}
/* It is valid on Linux to pass in a zero-length receive buffer. This
* is not an error. We may as well bail out now.
*/
if (!len) {
err = 0;
goto out;
}
/* We must not copy less than target bytes into the user's buffer
* before returning successfully, so we wait for the consume queue to
* have that much data to consume before dequeueing. Note that this
* makes it impossible to handle cases where target is greater than the
* queue size.
*/
target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
if (target >= transport->stream_rcvhiwat(vsk)) {
err = -ENOMEM;
goto out;
}
timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
copied = 0;
err = transport->notify_recv_init(vsk, target, &recv_data);
if (err < 0)
goto out;
while (1) {
s64 ready;
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
ready = vsock_stream_has_data(vsk);
if (ready == 0) {
if (sk->sk_err != 0 ||
(sk->sk_shutdown & RCV_SHUTDOWN) ||
(vsk->peer_shutdown & SEND_SHUTDOWN)) {
finish_wait(sk_sleep(sk), &wait);
break;
}
/* Don't wait for non-blocking sockets. */
if (timeout == 0) {
err = -EAGAIN;
finish_wait(sk_sleep(sk), &wait);
break;
}
err = transport->notify_recv_pre_block(
vsk, target, &recv_data);
if (err < 0) {
finish_wait(sk_sleep(sk), &wait);
break;
}
release_sock(sk);
timeout = schedule_timeout(timeout);
lock_sock(sk);
if (signal_pending(current)) {
err = sock_intr_errno(timeout);
finish_wait(sk_sleep(sk), &wait);
break;
} else if (timeout == 0) {
err = -EAGAIN;
finish_wait(sk_sleep(sk), &wait);
break;
}
} else {
ssize_t read;
finish_wait(sk_sleep(sk), &wait);
if (ready < 0) {
/* Invalid queue pair content. XXX This should
* be changed to a connection reset in a later
* change.
*/
err = -ENOMEM;
goto out;
}
err = transport->notify_recv_pre_dequeue(
vsk, target, &recv_data);
if (err < 0)
break;
read = transport->stream_dequeue(
vsk, msg,
len - copied, flags);
if (read < 0) {
err = -ENOMEM;
break;
}
copied += read;
err = transport->notify_recv_post_dequeue(
vsk, target, read,
!(flags & MSG_PEEK), &recv_data);
if (err < 0)
goto out;
if (read >= target || flags & MSG_PEEK)
break;
target -= read;
}
}
if (sk->sk_err)
err = -sk->sk_err;
else if (sk->sk_shutdown & RCV_SHUTDOWN)
err = 0;
if (copied > 0)
err = copied;
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_accept(struct socket *sock, struct socket *newsock, int flags,
bool kern)
{
struct sock *listener;
int err;
struct sock *connected;
struct vsock_sock *vconnected;
long timeout;
DEFINE_WAIT(wait);
err = 0;
listener = sock->sk;
lock_sock(listener);
if (sock->type != SOCK_STREAM) {
err = -EOPNOTSUPP;
goto out;
}
if (listener->sk_state != TCP_LISTEN) {
err = -EINVAL;
goto out;
}
/* Wait for children sockets to appear; these are the new sockets
* created upon connection establishment.
*/
timeout = sock_sndtimeo(listener, flags & O_NONBLOCK);
prepare_to_wait(sk_sleep(listener), &wait, TASK_INTERRUPTIBLE);
while ((connected = vsock_dequeue_accept(listener)) == NULL &&
listener->sk_err == 0) {
release_sock(listener);
timeout = schedule_timeout(timeout);
finish_wait(sk_sleep(listener), &wait);
lock_sock(listener);
if (signal_pending(current)) {
err = sock_intr_errno(timeout);
goto out;
} else if (timeout == 0) {
err = -EAGAIN;
goto out;
}
prepare_to_wait(sk_sleep(listener), &wait, TASK_INTERRUPTIBLE);
}
finish_wait(sk_sleep(listener), &wait);
if (listener->sk_err)
err = -listener->sk_err;
if (connected) {
listener->sk_ack_backlog--;
lock_sock_nested(connected, SINGLE_DEPTH_NESTING);
vconnected = vsock_sk(connected);
/* If the listener socket has received an error, then we should
* reject this socket and return. Note that we simply mark the
* socket rejected, drop our reference, and let the cleanup
* function handle the cleanup; the fact that we found it in
* the listener's accept queue guarantees that the cleanup
* function hasn't run yet.
*/
if (err) {
vconnected->rejected = true;
} else {
newsock->state = SS_CONNECTED;
sock_graft(connected, newsock);
}
release_sock(connected);
sock_put(connected);
}
out:
release_sock(listener);
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 == TCP_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));
err = vsock_auto_bind(vsk);
if (err)
goto out;
sk->sk_state = TCP_SYN_SENT;
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 != TCP_ESTABLISHED && 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);
sk->sk_state = TCP_CLOSE;
sock->state = SS_UNCONNECTED;
vsock_transport_cancel_pkt(vsk);
goto out_wait;
} else if (timeout == 0) {
err = -ETIMEDOUT;
sk->sk_state = TCP_CLOSE;
sock->state = SS_UNCONNECTED;
vsock_transport_cancel_pkt(vsk);
goto out_wait;
}
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
if (sk->sk_err) {
err = -sk->sk_err;
sk->sk_state = TCP_CLOSE;
sock->state = SS_UNCONNECTED;
} else {
err = 0;
}
out_wait:
finish_wait(sk_sleep(sk), &wait);
out:
release_sock(sk);
return err;
}
int netlink_unicast(struct sock *ssk, struct sk_buff *skb, u32 pid, int nonblock)
{
struct sock *sk;
int len = skb->len;
int protocol = ssk->protocol;
long timeo;
DECLARE_WAITQUEUE(wait, current);
timeo = sock_sndtimeo(ssk, nonblock);
retry:
sk = netlink_lookup(protocol, pid);
if (sk == NULL)
goto no_dst;
#ifdef NL_EMULATE_DEV
if (sk->protinfo.af_netlink->handler) {
skb_orphan(skb);
len = sk->protinfo.af_netlink->handler(protocol, skb);
sock_put(sk);
return len;
}
#endif
if (atomic_read(&sk->rmem_alloc) > sk->rcvbuf ||
test_bit(0, &sk->protinfo.af_netlink->state)) {
if (!timeo) {
if (ssk->protinfo.af_netlink->pid == 0)
netlink_overrun(sk);
sock_put(sk);
kfree_skb(skb);
return -EAGAIN;
}
__set_current_state(TASK_INTERRUPTIBLE);
add_wait_queue(&sk->protinfo.af_netlink->wait, &wait);
if ((atomic_read(&sk->rmem_alloc) > sk->rcvbuf ||
test_bit(0, &sk->protinfo.af_netlink->state)) &&
!sk->dead)
timeo = schedule_timeout(timeo);
__set_current_state(TASK_RUNNING);
remove_wait_queue(&sk->protinfo.af_netlink->wait, &wait);
sock_put(sk);
if (signal_pending(current)) {
kfree_skb(skb);
return sock_intr_errno(timeo);
}
goto retry;
}
skb_orphan(skb);
skb_set_owner_r(skb, sk);
skb_queue_tail(&sk->receive_queue, skb);
sk->data_ready(sk, len);
sock_put(sk);
return len;
no_dst:
kfree_skb(skb);
return -ECONNREFUSED;
}
int dccp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t len, int nonblock, int flags, int *addr_len)
{
const struct dccp_hdr *dh;
long timeo;
lock_sock(sk);
if (sk->sk_state == DCCP_LISTEN) {
len = -ENOTCONN;
goto out;
}
timeo = sock_rcvtimeo(sk, nonblock);
do {
struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
if (skb == NULL)
goto verify_sock_status;
dh = dccp_hdr(skb);
switch (dh->dccph_type) {
case DCCP_PKT_DATA:
case DCCP_PKT_DATAACK:
goto found_ok_skb;
case DCCP_PKT_CLOSE:
case DCCP_PKT_CLOSEREQ:
if (!(flags & MSG_PEEK))
dccp_finish_passive_close(sk);
/* fall through */
case DCCP_PKT_RESET:
dccp_pr_debug("found fin (%s) ok!\n",
dccp_packet_name(dh->dccph_type));
len = 0;
goto found_fin_ok;
default:
dccp_pr_debug("packet_type=%s\n",
dccp_packet_name(dh->dccph_type));
sk_eat_skb(sk, skb, false);
}
verify_sock_status:
if (sock_flag(sk, SOCK_DONE)) {
len = 0;
break;
}
if (sk->sk_err) {
len = sock_error(sk);
break;
}
if (sk->sk_shutdown & RCV_SHUTDOWN) {
len = 0;
break;
}
if (sk->sk_state == DCCP_CLOSED) {
if (!sock_flag(sk, SOCK_DONE)) {
/* This occurs when user tries to read
* from never connected socket.
*/
len = -ENOTCONN;
break;
}
len = 0;
break;
}
if (!timeo) {
len = -EAGAIN;
break;
}
if (signal_pending(current)) {
len = sock_intr_errno(timeo);
break;
}
sk_wait_data(sk, &timeo);
continue;
found_ok_skb:
if (len > skb->len)
len = skb->len;
else if (len < skb->len)
msg->msg_flags |= MSG_TRUNC;
if (skb_copy_datagram_iovec(skb, 0, msg->msg_iov, len)) {
/* Exception. Bailout! */
len = -EFAULT;
break;
}
if (flags & MSG_TRUNC)
len = skb->len;
found_fin_ok:
if (!(flags & MSG_PEEK))
sk_eat_skb(sk, skb, false);
break;
} while (1);
out:
release_sock(sk);
return len;
}
