tipc: use pseudo message to wake up sockets after link congestion

The current link implementation keeps a linked list of blocked ports/
sockets that is populated when there is link congestion. The purpose
of this is to let the link know which users to wake up when the
congestion abates.

This adds unnecessary complexity to the data structure and the code,
since it forces us to involve the link each time we want to delete
a socket. It also forces us to grab the spinlock port_lock within
the scope of node_lock. We want to get rid of this direct dependence,
as well as the deadlock hazard resulting from the usage of port_lock.

In this commit, we instead let the link keep list of a "wakeup" pseudo
messages for use in such situations. Those messages are sent to the
pending sockets via the ordinary message reception path, and wake up
the socket's owner when they are received.

This enables us to get rid of the 'waiting_ports' linked lists in struct
tipc_port that manifest this direct reference. As a consequence, we can
eliminate another BH entry into the socket, and hence the need to grab
port_lock. This is a further step in our effort to remove port_lock
altogether.

Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 12 insertions, 3 deletions

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index ff8c8118d56e..a8be4d2001f7 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -579,6 +579,7 @@ new_mtu:
                         goto new_mtu;
                 if (rc != -ELINKCONG)
                         break;
+                tipc_sk(sk)->link_cong = 1;
                 rc = tipc_wait_for_sndmsg(sock, &timeo);
                 if (rc)
                         kfree_skb_list(buf);
@@ -651,7 +652,7 @@ static int tipc_sk_proto_rcv(struct tipc_sock *tsk, u32 *dnode,
                 conn_cong = tipc_sk_conn_cong(tsk);
                 tsk->sent_unacked -= msg_msgcnt(msg);
                 if (conn_cong)
-                        tipc_sock_wakeup(tsk);
+                        tsk->sk.sk_write_space(&tsk->sk);
         } else if (msg_type(msg) == CONN_PROBE) {
                 if (!tipc_msg_reverse(buf, dnode, TIPC_OK))
                         return TIPC_OK;
@@ -826,6 +827,7 @@ new_mtu:
                 goto exit;
 
         do {
+                TIPC_SKB_CB(buf)->wakeup_pending = tsk->link_cong;
                 rc = tipc_link_xmit(buf, dnode, tsk->port.ref);
                 if (likely(rc >= 0)) {
                         if (sock->state != SS_READY)
@@ -835,10 +837,9 @@ new_mtu:
                 }
                 if (rc == -EMSGSIZE)
                         goto new_mtu;
-
                 if (rc != -ELINKCONG)
                         break;
-
+                tsk->link_cong = 1;
                 rc = tipc_wait_for_sndmsg(sock, &timeo);
                 if (rc)
                         kfree_skb_list(buf);
@@ -953,6 +954,7 @@ next:
                         }
                         if (rc != -ELINKCONG)
                                 break;
+                        tsk->link_cong = 1;
                 }
                 rc = tipc_wait_for_sndpkt(sock, &timeo);
                 if (rc)
@@ -1518,6 +1520,13 @@ static int filter_rcv(struct sock *sk, struct sk_buff *buf)
         if (unlikely(msg_user(msg) == CONN_MANAGER))
                 return tipc_sk_proto_rcv(tsk, &onode, buf);
 
+        if (unlikely(msg_user(msg) == SOCK_WAKEUP)) {
+                kfree_skb(buf);
+                tsk->link_cong = 0;
+                sk->sk_write_space(sk);
+                return TIPC_OK;
+        }
+
         /* Reject message if it is wrong sort of message for socket */
         if (msg_type(msg) > TIPC_DIRECT_MSG)
                 return -TIPC_ERR_NO_PORT;