/*
* Before killing the tcp socket this needs to serialize with callbacks. The
* caller has already grabbed the sending sem so we're serialized with other
* senders.
*
* TCP calls the callbacks with the sock lock so we hold it while we reset the
* callbacks to those set by TCP. Our callbacks won't execute again once we
* hold the sock lock.
*/
void rds_tcp_conn_path_shutdown(struct rds_conn_path *cp)
{
struct rds_tcp_connection *tc = cp->cp_transport_data;
struct socket *sock = tc->t_sock;
rdsdebug("shutting down conn %p tc %p sock %p\n",
cp->cp_conn, tc, sock);
if (sock) {
if (rds_destroy_pending(cp->cp_conn))
rds_tcp_set_linger(sock);
sock->ops->shutdown(sock, RCV_SHUTDOWN | SEND_SHUTDOWN);
lock_sock(sock->sk);
rds_tcp_restore_callbacks(sock, tc); /* tc->tc_sock = NULL */
release_sock(sock->sk);
sock_release(sock);
}
if (tc->t_tinc) {
rds_inc_put(&tc->t_tinc->ti_inc);
tc->t_tinc = NULL;
}
tc->t_tinc_hdr_rem = sizeof(struct rds_header);
tc->t_tinc_data_rem = 0;
}
int rds_tcp_conn_connect(struct rds_connection *conn)
{
struct socket *sock = NULL;
struct sockaddr_in src, dest;
int ret;
struct rds_tcp_connection *tc = conn->c_transport_data;
mutex_lock(&tc->t_conn_lock);
if (rds_conn_up(conn)) {
mutex_unlock(&tc->t_conn_lock);
return 0;
}
ret = sock_create_kern(rds_conn_net(conn), PF_INET,
SOCK_STREAM, IPPROTO_TCP, &sock);
if (ret < 0)
goto out;
rds_tcp_tune(sock);
src.sin_family = AF_INET;
src.sin_addr.s_addr = (__force u32)conn->c_laddr;
src.sin_port = (__force u16)htons(0);
ret = sock->ops->bind(sock, (struct sockaddr *)&src, sizeof(src));
if (ret) {
rdsdebug("bind failed with %d at address %pI4\n",
ret, &conn->c_laddr);
goto out;
}
dest.sin_family = AF_INET;
dest.sin_addr.s_addr = (__force u32)conn->c_faddr;
dest.sin_port = (__force u16)htons(RDS_TCP_PORT);
/*
* once we call connect() we can start getting callbacks and they
* own the socket
*/
rds_tcp_set_callbacks(sock, conn);
ret = sock->ops->connect(sock, (struct sockaddr *)&dest, sizeof(dest),
O_NONBLOCK);
rdsdebug("connect to address %pI4 returned %d\n", &conn->c_faddr, ret);
if (ret == -EINPROGRESS)
ret = 0;
if (ret == 0) {
rds_tcp_keepalive(sock);
sock = NULL;
} else {
rds_tcp_restore_callbacks(sock, conn->c_transport_data);
}
out:
mutex_unlock(&tc->t_conn_lock);
if (sock)
sock_release(sock);
return ret;
}
int rds_tcp_accept_one(struct socket *sock)
{
struct socket *new_sock = NULL;
struct rds_connection *conn;
int ret;
struct inet_sock *inet;
struct rds_tcp_connection *rs_tcp;
ret = sock_create_kern(sock_net(sock->sk), sock->sk->sk_family,
sock->sk->sk_type, sock->sk->sk_protocol,
&new_sock);
if (ret)
goto out;
new_sock->type = sock->type;
new_sock->ops = sock->ops;
ret = sock->ops->accept(sock, new_sock, O_NONBLOCK);
if (ret < 0)
goto out;
ret = rds_tcp_keepalive(new_sock);
if (ret < 0)
goto out;
rds_tcp_tune(new_sock);
inet = inet_sk(new_sock->sk);
rdsdebug("accepted tcp %pI4:%u -> %pI4:%u\n",
&inet->inet_saddr, ntohs(inet->inet_sport),
&inet->inet_daddr, ntohs(inet->inet_dport));
conn = rds_conn_create(sock_net(sock->sk),
inet->inet_saddr, inet->inet_daddr,
&rds_tcp_transport, GFP_KERNEL);
if (IS_ERR(conn)) {
ret = PTR_ERR(conn);
goto out;
}
/* An incoming SYN request came in, and TCP just accepted it.
*
* If the client reboots, this conn will need to be cleaned up.
* rds_tcp_state_change() will do that cleanup
*/
rs_tcp = (struct rds_tcp_connection *)conn->c_transport_data;
if (rs_tcp->t_sock &&
ntohl(inet->inet_saddr) < ntohl(inet->inet_daddr)) {
struct sock *nsk = new_sock->sk;
nsk->sk_user_data = NULL;
nsk->sk_prot->disconnect(nsk, 0);
tcp_done(nsk);
new_sock = NULL;
ret = 0;
goto out;
} else if (rs_tcp->t_sock) {
rds_tcp_restore_callbacks(rs_tcp->t_sock, rs_tcp);
conn->c_outgoing = 0;
}
rds_conn_transition(conn, RDS_CONN_DOWN, RDS_CONN_CONNECTING);
rds_tcp_set_callbacks(new_sock, conn);
rds_connect_complete(conn);
new_sock = NULL;
ret = 0;
out:
if (new_sock)
sock_release(new_sock);
return ret;
}
