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, 3 insertions, 4 deletions

diff --git a/net/tipc/link.h b/net/tipc/link.h
index 782983ccd323..b567a3427fda 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -1,7 +1,7 @@
 /*
  * net/tipc/link.h: Include file for TIPC link code
  *
- * Copyright (c) 1995-2006, 2013, Ericsson AB
+ * Copyright (c) 1995-2006, 2013-2014, Ericsson AB
  * Copyright (c) 2004-2005, 2010-2011, Wind River Systems
  * All rights reserved.
  *
@@ -133,7 +133,7 @@ struct tipc_stats {
  * @retransm_queue_size: number of messages to retransmit
  * @retransm_queue_head: sequence number of first message to retransmit
  * @next_out: ptr to first unsent outbound message in queue
- * @waiting_ports: linked list of ports waiting for link congestion to abate
+ * @waiting_sks: linked list of sockets waiting for link congestion to abate
  * @long_msg_seq_no: next identifier to use for outbound fragmented messages
  * @reasm_buf: head of partially reassembled inbound message fragments
  * @stats: collects statistics regarding link activity
@@ -194,7 +194,7 @@ struct tipc_link {
         u32 retransm_queue_size;
         u32 retransm_queue_head;
         struct sk_buff *next_out;
-        struct list_head waiting_ports;
+        struct sk_buff_head waiting_sks;
 
         /* Fragmentation/reassembly */
         u32 long_msg_seq_no;
@@ -235,7 +235,6 @@ void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int prob,
 void tipc_link_push_queue(struct tipc_link *l_ptr);
 u32 tipc_link_defer_pkt(struct sk_buff **head, struct sk_buff **tail,
                         struct sk_buff *buf);
-void tipc_link_wakeup_ports(struct tipc_link *l_ptr, int all);
 void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window);
 void tipc_link_retransmit(struct tipc_link *l_ptr,
                           struct sk_buff *start, u32 retransmits);