void rds_tcp_state_change(struct sock *sk)
{
void (*state_change)(struct sock *sk);
struct rds_connection *conn;
struct rds_tcp_connection *tc;
read_lock_bh(&sk->sk_callback_lock);
conn = sk->sk_user_data;
if (conn == NULL) {
state_change = sk->sk_state_change;
goto out;
}
tc = conn->c_transport_data;
state_change = tc->t_orig_state_change;
rdsdebug("sock %p state_change to %d\n", tc->t_sock, sk->sk_state);
switch(sk->sk_state) {
/* ignore connecting sockets as they make progress */
case TCP_SYN_SENT:
case TCP_SYN_RECV:
break;
case TCP_ESTABLISHED:
rds_connect_complete(conn);
break;
case TCP_CLOSE:
rds_conn_drop(conn);
default:
break;
}
out:
read_unlock_bh(&sk->sk_callback_lock);
state_change(sk);
}
/*
* Connection established.
* We get here for both outgoing and incoming connection.
*/
void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_event *event)
{
const struct rds_ib_connect_private *dp = NULL;
struct rds_ib_connection *ic = conn->c_transport_data;
struct rds_ib_device *rds_ibdev;
struct ib_qp_attr qp_attr;
int err;
if (event->param.conn.private_data_len >= sizeof(*dp)) {
dp = event->param.conn.private_data;
/* make sure it isn't empty data */
if (dp->dp_protocol_major) {
rds_ib_set_protocol(conn,
RDS_PROTOCOL(dp->dp_protocol_major,
dp->dp_protocol_minor));
rds_ib_set_flow_control(conn, be32_to_cpu(dp->dp_credit));
}
}
printk(KERN_NOTICE "RDS/IB: connected to %pI4 version %u.%u%s\n",
&conn->c_faddr,
RDS_PROTOCOL_MAJOR(conn->c_version),
RDS_PROTOCOL_MINOR(conn->c_version),
ic->i_flowctl ? ", flow control" : "");
/*
* Init rings and fill recv. this needs to wait until protocol negotiation
* is complete, since ring layout is different from 3.0 to 3.1.
*/
rds_ib_send_init_ring(ic);
rds_ib_recv_init_ring(ic);
/* Post receive buffers - as a side effect, this will update
* the posted credit count. */
rds_ib_recv_refill(conn, GFP_KERNEL, GFP_HIGHUSER, 1);
/* Tune RNR behavior */
rds_ib_tune_rnr(ic, &qp_attr);
qp_attr.qp_state = IB_QPS_RTS;
err = ib_modify_qp(ic->i_cm_id->qp, &qp_attr, IB_QP_STATE);
if (err)
printk(KERN_NOTICE "ib_modify_qp(IB_QP_STATE, RTS): err=%d\n", err);
/* update ib_device with this local ipaddr & conn */
rds_ibdev = ib_get_client_data(ic->i_cm_id->device, &rds_ib_client);
err = rds_ib_update_ipaddr(rds_ibdev, conn->c_laddr);
if (err)
printk(KERN_ERR "rds_ib_update_ipaddr failed (%d)\n", err);
rds_ib_add_conn(rds_ibdev, conn);
/* If the peer gave us the last packet it saw, process this as if
* we had received a regular ACK. */
if (dp && dp->dp_ack_seq)
rds_send_drop_acked(conn, be64_to_cpu(dp->dp_ack_seq), NULL);
rds_connect_complete(conn);
}
void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_event *event)
{
const struct rds_ib_connect_private *dp = NULL;
struct rds_ib_connection *ic = conn->c_transport_data;
struct ib_qp_attr qp_attr;
int err;
if (event->param.conn.private_data_len >= sizeof(*dp)) {
dp = event->param.conn.private_data;
if (dp->dp_protocol_major) {
rds_ib_set_protocol(conn,
RDS_PROTOCOL(dp->dp_protocol_major,
dp->dp_protocol_minor));
rds_ib_set_flow_control(conn, be32_to_cpu(dp->dp_credit));
}
}
if (conn->c_version < RDS_PROTOCOL(3,1)) {
printk(KERN_NOTICE "RDS/IB: Connection to %pI4 version %u.%u failed,"
" no longer supported\n",
&conn->c_faddr,
RDS_PROTOCOL_MAJOR(conn->c_version),
RDS_PROTOCOL_MINOR(conn->c_version));
rds_conn_destroy(conn);
return;
} else {
printk(KERN_NOTICE "RDS/IB: connected to %pI4 version %u.%u%s\n",
&conn->c_faddr,
RDS_PROTOCOL_MAJOR(conn->c_version),
RDS_PROTOCOL_MINOR(conn->c_version),
ic->i_flowctl ? ", flow control" : "");
}
rds_ib_send_init_ring(ic);
rds_ib_recv_init_ring(ic);
rds_ib_recv_refill(conn, 1);
rds_ib_tune_rnr(ic, &qp_attr);
qp_attr.qp_state = IB_QPS_RTS;
err = ib_modify_qp(ic->i_cm_id->qp, &qp_attr, IB_QP_STATE);
if (err)
printk(KERN_NOTICE "ib_modify_qp(IB_QP_STATE, RTS): err=%d\n", err);
err = rds_ib_update_ipaddr(ic->rds_ibdev, conn->c_laddr);
if (err)
printk(KERN_ERR "rds_ib_update_ipaddr failed (%d)\n",
err);
if (dp && dp->dp_ack_seq)
rds_send_drop_acked(conn, be64_to_cpu(dp->dp_ack_seq), NULL);
rds_connect_complete(conn);
}
static int rds_tcp_accept_one(struct socket *sock)
{
struct socket *new_sock = NULL;
struct rds_connection *conn;
int ret;
struct inet_sock *inet;
ret = sock_create_lite(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;
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(inet->inet_saddr, inet->inet_daddr,
&rds_tcp_transport, GFP_KERNEL);
if (IS_ERR(conn)) {
ret = PTR_ERR(conn);
goto out;
}
/*
* see the comment above rds_queue_delayed_reconnect()
*/
if (!rds_conn_transition(conn, RDS_CONN_DOWN, RDS_CONN_CONNECTING)) {
if (rds_conn_state(conn) == RDS_CONN_UP)
rds_tcp_stats_inc(s_tcp_listen_closed_stale);
else
rds_tcp_stats_inc(s_tcp_connect_raced);
rds_conn_drop(conn);
ret = 0;
goto out;
}
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;
}
/*
* Connection established.
* We get here for both outgoing and incoming connection.
*/
void rds_iw_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_event *event)
{
const struct rds_iw_connect_private *dp = NULL;
struct rds_iw_connection *ic = conn->c_transport_data;
struct rds_iw_device *rds_iwdev;
int err;
if (event->param.conn.private_data_len) {
dp = event->param.conn.private_data;
rds_iw_set_protocol(conn,
RDS_PROTOCOL(dp->dp_protocol_major,
dp->dp_protocol_minor));
rds_iw_set_flow_control(conn, be32_to_cpu(dp->dp_credit));
}
/* update ib_device with this local ipaddr & conn */
rds_iwdev = ib_get_client_data(ic->i_cm_id->device, &rds_iw_client);
err = rds_iw_update_cm_id(rds_iwdev, ic->i_cm_id);
if (err)
printk(KERN_ERR "rds_iw_update_ipaddr failed (%d)\n", err);
rds_iw_add_conn(rds_iwdev, conn);
/* If the peer gave us the last packet it saw, process this as if
* we had received a regular ACK. */
if (dp && dp->dp_ack_seq)
rds_send_drop_acked(conn, be64_to_cpu(dp->dp_ack_seq), NULL);
printk(KERN_NOTICE "RDS/IW: connected to %pI4<->%pI4 version %u.%u%s\n",
&conn->c_laddr, &conn->c_faddr,
RDS_PROTOCOL_MAJOR(conn->c_version),
RDS_PROTOCOL_MINOR(conn->c_version),
ic->i_flowctl ? ", flow control" : "");
rds_connect_complete(conn);
}
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;
}
/*
* Connection established.
* We get here for both outgoing and incoming connection.
*/
void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_event *event)
{
const struct rds_ib_connect_private *dp = NULL;
struct rds_ib_connection *ic = conn->c_transport_data;
struct ib_qp_attr qp_attr;
int err;
if (event->param.conn.private_data_len >= sizeof(*dp)) {
dp = event->param.conn.private_data;
/* make sure it isn't empty data */
if (dp->dp_protocol_major) {
rds_ib_set_protocol(conn,
RDS_PROTOCOL(dp->dp_protocol_major,
dp->dp_protocol_minor));
rds_ib_set_flow_control(conn, be32_to_cpu(dp->dp_credit));
}
}
if (conn->c_version < RDS_PROTOCOL(3, 1)) {
printk(KERN_NOTICE "RDS/IB: Connection to %pI4 version %u.%u failed,"
" no longer supported\n",
&conn->c_faddr,
RDS_PROTOCOL_MAJOR(conn->c_version),
RDS_PROTOCOL_MINOR(conn->c_version));
rds_conn_destroy(conn);
return;
} else {
printk(KERN_NOTICE "RDS/IB: connected to %pI4 version %u.%u%s\n",
&conn->c_faddr,
RDS_PROTOCOL_MAJOR(conn->c_version),
RDS_PROTOCOL_MINOR(conn->c_version),
ic->i_flowctl ? ", flow control" : "");
}
/*
* Init rings and fill recv. this needs to wait until protocol negotiation
* is complete, since ring layout is different from 3.0 to 3.1.
*/
rds_ib_send_init_ring(ic);
rds_ib_recv_init_ring(ic);
/* Post receive buffers - as a side effect, this will update
* the posted credit count. */
rds_ib_recv_refill(conn, 1, GFP_KERNEL);
/* Tune RNR behavior */
rds_ib_tune_rnr(ic, &qp_attr);
qp_attr.qp_state = IB_QPS_RTS;
err = ib_modify_qp(ic->i_cm_id->qp, &qp_attr, IB_QP_STATE);
if (err)
printk(KERN_NOTICE "ib_modify_qp(IB_QP_STATE, RTS): err=%d\n", err);
/* update ib_device with this local ipaddr */
err = rds_ib_update_ipaddr(ic->rds_ibdev, conn->c_laddr);
if (err)
printk(KERN_ERR "rds_ib_update_ipaddr failed (%d)\n",
err);
/* If the peer gave us the last packet it saw, process this as if
* we had received a regular ACK. */
if (dp) {
/* dp structure start is not guaranteed to be 8 bytes aligned.
* Since dp_ack_seq is 64-bit extended load operations can be
* used so go through get_unaligned to avoid unaligned errors.
*/
__be64 dp_ack_seq = get_unaligned(&dp->dp_ack_seq);
if (dp_ack_seq)
rds_send_drop_acked(conn, be64_to_cpu(dp_ack_seq),
NULL);
}
rds_connect_complete(conn);
}