tipc: fix bug in multicast congestion handling

Jon Maloy · davem330 · commit 908344cdda80 · 2014-10-07T14:50:15.000-04:00
One aim of commit 50100a5 ("tipc: use pseudo message to wake up sockets after link congestion") was to handle link congestion abatement in a uniform way for both unicast and multicast transmit. However, the latter doesn't work correctly, and has been broken since the referenced commit was applied. If a user now sends a burst of multicast messages that is big enough to cause broadcast link congestion, it will be put to sleep, and not be waked up when the congestion abates as it should be. This has two reasons. First, the flag that is used, TIPC_WAKEUP_USERS, is set correctly, but in the wrong field. Instead of setting it in the 'action_flags' field of the arrival node struct, it is by mistake set in the dummy node struct that is owned by the broadcast link, where it will never tested for. Second, we cannot use the same flag for waking up unicast and multicast users, since the function tipc_node_unlock() needs to pick the wakeup pseudo messages to deliver from different queues. It must hence be able to distinguish between the two cases. This commit solves this problem by adding a new flag TIPC_WAKEUP_BCAST_USERS, and a new function tipc_bclink_wakeup_user(). The latter is to be called by tipc_node_unlock() when the named flag, now set in the correct field, is encountered. v2: using explicit 'unsigned int' declaration instead of 'uint', as per comment from David Miller. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
@@ -225,6 +225,17 @@ static void bclink_retransmit_pkt(u32 after, u32 to)
 	tipc_link_retransmit(bcl, buf, mod(to - after));
 }
 
+/**
+ * tipc_bclink_wakeup_users - wake up pending users
+ *
+ * Called with no locks taken
+ */
+void tipc_bclink_wakeup_users(void)
+{
+	while (skb_queue_len(&bclink->link.waiting_sks))
+		tipc_sk_rcv(skb_dequeue(&bclink->link.waiting_sks));
+}
+
 /**
  * tipc_bclink_acknowledge - handle acknowledgement of broadcast packets
  * @n_ptr: node that sent acknowledgement info
@@ -300,7 +311,8 @@ void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked)
 		bclink_set_last_sent();
 	}
 	if (unlikely(released && !skb_queue_empty(&bcl->waiting_sks)))
-		bclink->node.action_flags |= TIPC_WAKEUP_USERS;
+		n_ptr->action_flags |= TIPC_WAKEUP_BCAST_USERS;
+
 exit:
 	tipc_bclink_unlock();
 }
diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h
@@ -99,5 +99,5 @@ int  tipc_bclink_set_queue_limits(u32 limit);
 void tipc_bcbearer_sort(struct tipc_node_map *nm_ptr, u32 node, bool action);
 uint  tipc_bclink_get_mtu(void);
 int tipc_bclink_xmit(struct sk_buff *buf);
-
+void tipc_bclink_wakeup_users(void);
 #endif
diff --git a/net/tipc/node.c b/net/tipc/node.c
@@ -552,6 +552,7 @@ void tipc_node_unlock(struct tipc_node *node)
 	LIST_HEAD(conn_sks);
 	struct sk_buff_head waiting_sks;
 	u32 addr = 0;
+	unsigned int flags = node->action_flags;
 
 	if (likely(!node->action_flags)) {
 		spin_unlock_bh(&node->lock);
@@ -572,6 +573,7 @@ void tipc_node_unlock(struct tipc_node *node)
 		node->action_flags &= ~TIPC_NOTIFY_NODE_UP;
 		addr = node->addr;
 	}
+	node->action_flags &= ~TIPC_WAKEUP_BCAST_USERS;
 	spin_unlock_bh(&node->lock);
 
 	while (!skb_queue_empty(&waiting_sks))
@@ -583,6 +585,9 @@ void tipc_node_unlock(struct tipc_node *node)
 	if (!list_empty(&nsub_list))
 		tipc_nodesub_notify(&nsub_list);
 
+	if (flags & TIPC_WAKEUP_BCAST_USERS)
+		tipc_bclink_wakeup_users();
+
 	if (addr)
 		tipc_named_node_up(addr);
 }
diff --git a/net/tipc/node.h b/net/tipc/node.h
@@ -59,7 +59,8 @@ enum {
 	TIPC_WAIT_OWN_LINKS_DOWN	= (1 << 2),
 	TIPC_NOTIFY_NODE_DOWN		= (1 << 3),
 	TIPC_NOTIFY_NODE_UP		= (1 << 4),
-	TIPC_WAKEUP_USERS		= (1 << 5)
+	TIPC_WAKEUP_USERS		= (1 << 5),
+	TIPC_WAKEUP_BCAST_USERS		= (1 << 6)
 };
 
 /**
