#include "ccid.h"
#include "dccp.h"
-DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics);
+DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics) __read_mostly;
atomic_t dccp_orphan_count = ATOMIC_INIT(0);
return err;
}
+/*
+ * Wait for a DCCP event.
+ *
+ * Note that we don't need to lock the socket, as the upper poll layers
+ * take care of normal races (between the test and the event) and we don't
+ * go look at any of the socket buffers directly.
+ */
+static unsigned int dccp_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
+{
+ unsigned int mask;
+ struct sock *sk = sock->sk;
+
+ poll_wait(file, sk->sk_sleep, wait);
+ if (sk->sk_state == DCCP_LISTEN)
+ return inet_csk_listen_poll(sk);
+
+ /* Socket is not locked. We are protected from async events
+ by poll logic and correct handling of state changes
+ made by another threads is impossible in any case.
+ */
+
+ mask = 0;
+ if (sk->sk_err)
+ mask = POLLERR;
+
+ if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == DCCP_CLOSED)
+ mask |= POLLHUP;
+ if (sk->sk_shutdown & RCV_SHUTDOWN)
+ mask |= POLLIN | POLLRDNORM;
+
+ /* Connected? */
+ if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) {
+ if (atomic_read(&sk->sk_rmem_alloc) > 0)
+ mask |= POLLIN | POLLRDNORM;
+
+ if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
+ if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) {
+ mask |= POLLOUT | POLLWRNORM;
+ } else { /* send SIGIO later */
+ set_bit(SOCK_ASYNC_NOSPACE,
+ &sk->sk_socket->flags);
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+
+ /* Race breaker. If space is freed after
+ * wspace test but before the flags are set,
+ * IO signal will be lost.
+ */
+ if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk))
+ mask |= POLLOUT | POLLWRNORM;
+ }
+ }
+ }
+ return mask;
+}
+
int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
dccp_pr_debug("entry\n");
int dccp_setsockopt(struct sock *sk, int level, int optname,
char __user *optval, int optlen)
{
- dccp_pr_debug("entry\n");
+ struct dccp_sock *dp;
+ int err;
+ int val;
if (level != SOL_DCCP)
return ip_setsockopt(sk, level, optname, optval, optlen);
- return -EOPNOTSUPP;
+ if (optlen < sizeof(int))
+ return -EINVAL;
+
+ if (get_user(val, (int __user *)optval))
+ return -EFAULT;
+
+ lock_sock(sk);
+
+ dp = dccp_sk(sk);
+ err = 0;
+
+ switch (optname) {
+ case DCCP_SOCKOPT_PACKET_SIZE:
+ dp->dccps_packet_size = val;
+ break;
+ default:
+ err = -ENOPROTOOPT;
+ break;
+ }
+
+ release_sock(sk);
+ return err;
}
int dccp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
- dccp_pr_debug("entry\n");
+ struct dccp_sock *dp;
+ int val, len;
if (level != SOL_DCCP)
return ip_getsockopt(sk, level, optname, optval, optlen);
- return -EOPNOTSUPP;
+ if (get_user(len, optlen))
+ return -EFAULT;
+
+ len = min_t(unsigned int, len, sizeof(int));
+ if (len < 0)
+ return -EINVAL;
+
+ dp = dccp_sk(sk);
+
+ switch (optname) {
+ case DCCP_SOCKOPT_PACKET_SIZE:
+ val = dp->dccps_packet_size;
+ break;
+ default:
+ return -ENOPROTOOPT;
+ }
+
+ if (put_user(len, optlen) || copy_to_user(optval, &val, len))
+ return -EFAULT;
+
+ return 0;
}
int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
if (rc != 0)
goto out_discard;
- rc = dccp_write_xmit(sk, skb, len);
+ rc = dccp_write_xmit(sk, skb, &timeo);
+ /*
+ * XXX we don't use sk_write_queue, so just discard the packet.
+ * Current plan however is to _use_ sk_write_queue with
+ * an algorith similar to tcp_sendmsg, where the main difference
+ * is that in DCCP we have to respect packet boundaries, so
+ * no coalescing of skbs.
+ *
+ * This bug was _quickly_ found & fixed by just looking at an OSTRA
+ * generated callgraph 8) -acme
+ */
+ if (rc != 0)
+ goto out_discard;
out_release:
release_sock(sk);
return rc ? : len;
/* Check zero linger _after_ checking for unread data. */
sk->sk_prot->disconnect(sk, 0);
} else if (dccp_close_state(sk)) {
- dccp_send_close(sk);
+ dccp_send_close(sk, 1);
}
sk_stream_wait_close(sk, timeout);
adjudge_to_death:
+ /*
+ * It is the last release_sock in its life. It will remove backlog.
+ */
release_sock(sk);
/*
* Now socket is owned by kernel and we acquire BH lock
sock_hold(sk);
sock_orphan(sk);
-
- if (sk->sk_state != DCCP_CLOSED)
+
+ /*
+ * The last release_sock may have processed the CLOSE or RESET
+ * packet moving sock to CLOSED state, if not we have to fire
+ * the CLOSE/CLOSEREQ retransmission timer, see "8.3. Termination"
+ * in draft-ietf-dccp-spec-11. -acme
+ */
+ if (sk->sk_state == DCCP_CLOSING) {
+ /* FIXME: should start at 2 * RTT */
+ /* Timer for repeating the CLOSE/CLOSEREQ until an answer. */
+ inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+ inet_csk(sk)->icsk_rto,
+ DCCP_RTO_MAX);
+#if 0
+ /* Yeah, we should use sk->sk_prot->orphan_count, etc */
dccp_set_state(sk, DCCP_CLOSED);
+#endif
+ }
- atomic_inc(&dccp_orphan_count);
+ atomic_inc(sk->sk_prot->orphan_count);
if (sk->sk_state == DCCP_CLOSED)
inet_csk_destroy_sock(sk);
.socketpair = sock_no_socketpair,
.accept = inet_accept,
.getname = inet_getname,
- .poll = sock_no_poll,
+ /* FIXME: work on tcp_poll to rename it to inet_csk_poll */
+ .poll = dccp_poll,
.ioctl = inet_ioctl,
/* FIXME: work on inet_listen to rename it to sock_common_listen */
.listen = inet_dccp_listen,