summaryrefslogtreecommitdiff
path: root/net/rds/tcp_listen.c
diff options
context:
space:
mode:
authorSowmini Varadhan <sowmini.varadhan@oracle.com>2016-11-16 13:29:50 -0800
committerDavid S. Miller <davem@davemloft.net>2016-11-17 13:35:18 -0500
commit1a0e100fb2c9667cea2a7d755faaa83569942f05 (patch)
tree234b4827c3c99e6d911bd4b7ea787a1185e695df /net/rds/tcp_listen.c
parent905dd4184e0732de41d6ee3c7b06e0cfdd9f0aad (diff)
RDS: TCP: Force every connection to be initiated by numerically smaller IP address
When 2 RDS peers initiate an RDS-TCP connection simultaneously, there is a potential for "duelling syns" on either/both sides. See commit 241b271952eb ("RDS-TCP: Reset tcp callbacks if re-using an outgoing socket in rds_tcp_accept_one()") for a description of this condition, and the arbitration logic which ensures that the numerically large IP address in the TCP connection is bound to the RDS_TCP_PORT ("canonical ordering"). The rds_connection should not be marked as RDS_CONN_UP until the arbitration logic has converged for the following reason. The sender may start transmitting RDS datagrams as soon as RDS_CONN_UP is set, and since the sender removes all datagrams from the rds_connection's cp_retrans queue based on TCP acks. If the TCP ack was sent from a tcp socket that got reset as part of duel aribitration (but before data was delivered to the receivers RDS socket layer), the sender may end up prematurely freeing the datagram, and the datagram is no longer reliably deliverable. This patch remedies that condition by making sure that, upon receipt of 3WH completion state change notification of TCP_ESTABLISHED in rds_tcp_state_change, we mark the rds_connection as RDS_CONN_UP if, and only if, the IP addresses and ports for the connection are canonically ordered. In all other cases, rds_tcp_state_change will force an rds_conn_path_drop(), and rds_queue_reconnect() on both peers will restart the connection to ensure canonical ordering. A side-effect of enforcing this condition in rds_tcp_state_change() is that rds_tcp_accept_one_path() can now be refactored for simplicity. It is also no longer possible to encounter an RDS_CONN_UP connection in the arbitration logic in rds_tcp_accept_one(). Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com> Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/rds/tcp_listen.c')
-rw-r--r--net/rds/tcp_listen.c29
1 files changed, 12 insertions, 17 deletions
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index c9c496844cd7..f74bab3ecdca 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -83,25 +83,20 @@ struct rds_tcp_connection *rds_tcp_accept_one_path(struct rds_connection *conn)
{
int i;
bool peer_is_smaller = (conn->c_faddr < conn->c_laddr);
- int npaths = conn->c_npaths;
-
- if (npaths <= 1) {
- struct rds_conn_path *cp = &conn->c_path[0];
- int ret;
-
- ret = rds_conn_path_transition(cp, RDS_CONN_DOWN,
- RDS_CONN_CONNECTING);
- if (!ret)
- rds_conn_path_transition(cp, RDS_CONN_ERROR,
- RDS_CONN_CONNECTING);
- return cp->cp_transport_data;
- }
+ int npaths = max_t(int, 1, conn->c_npaths);
- /* for mprds, paths with cp_index > 0 MUST be initiated by the peer
+ /* for mprds, all paths MUST be initiated by the peer
* with the smaller address.
*/
- if (!peer_is_smaller)
+ if (!peer_is_smaller) {
+ /* Make sure we initiate at least one path if this
+ * has not already been done; rds_start_mprds() will
+ * take care of additional paths, if necessary.
+ */
+ if (npaths == 1)
+ rds_conn_path_connect_if_down(&conn->c_path[0]);
return NULL;
+ }
for (i = 0; i < npaths; i++) {
struct rds_conn_path *cp = &conn->c_path[i];
@@ -171,8 +166,8 @@ int rds_tcp_accept_one(struct socket *sock)
mutex_lock(&rs_tcp->t_conn_path_lock);
cp = rs_tcp->t_cpath;
conn_state = rds_conn_path_state(cp);
- if (conn_state != RDS_CONN_CONNECTING && conn_state != RDS_CONN_UP &&
- conn_state != RDS_CONN_ERROR)
+ WARN_ON(conn_state == RDS_CONN_UP);
+ if (conn_state != RDS_CONN_CONNECTING && conn_state != RDS_CONN_ERROR)
goto rst_nsk;
if (rs_tcp->t_sock) {
/* Need to resolve a duelling SYN between peers.