tipc: introduce node contact FSM

The logics for determining when a node is permitted to establish
and maintain contact with its peer node becomes non-trivial in the
presence of multiple parallel links that may come and go independently.

A known failure scenario is that one endpoint registers both its links
to the peer lost, cleans up it binding table, and prepares for a table
update once contact is re-establihed, while the other endpoint may
see its links reset and re-established one by one, hence seeing
no need to re-synchronize the binding table. To avoid this, a node
must not allow re-establishing contact until it has confirmation that
even the peer has lost both links.

Currently, the mechanism for handling this consists of setting and
resetting two state flags from different locations in the code. This
solution is hard to understand and maintain. A closer analysis even
reveals that it is not completely safe.

In this commit we do instead introduce an FSM that keeps track of
the conditions for when the node can establish and maintain links.
It has six states and four events, and is strictly based on explicit
knowledge about the own node's and the peer node's contact states.
Only events leading to state change are shown as edges in the figure
below.

                             +--------------+
                             | SELF_UP/     |
           +---------------->| PEER_COMING  |-----------------+
    SELF_  |                 +--------------+                 |PEER_
    ESTBL_ |                        |                         |ESTBL_
    CONTACT|      SELF_LOST_CONTACT |                         |CONTACT
           |                        v                         |
           |                 +--------------+                 |
           |      PEER_      | SELF_DOWN/   |     SELF_       |
           |      LOST_   +--| PEER_LEAVING |<--+ LOST_       v
+-------------+   CONTACT |  +--------------+   | CONTACT  +-----------+
| SELF_DOWN/  |<----------+                     +----------| SELF_UP/  |
| PEER_DOWN   |<----------+                     +----------| PEER_UP   |
+-------------+   SELF_   |  +--------------+   | PEER_    +-----------+
           |      LOST_   +--| SELF_LEAVING/|<--+ LOST_       A
           |      CONTACT    | PEER_DOWN    |     CONTACT     |
           |                 +--------------+                 |
           |                         A                        |
    PEER_  |       PEER_LOST_CONTACT |                        |SELF_
    ESTBL_ |                         |                        |ESTBL_
    CONTACT|                 +--------------+                 |CONTACT
           +---------------->| PEER_UP/     |-----------------+
                             | SELF_COMING  |
                             +--------------+

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

1 files changed, 21 insertions, 7 deletions

diff --git a/net/tipc/node.h b/net/tipc/node.h
index 2d56344..270256e 100644
--- a/net/tipc/node.h
+++ b/net/tipc/node.h
@@ -47,6 +47,24 @@
 
 #define INVALID_BEARER_ID -1
 
+/* Node FSM states and events:
+ */
+enum {
+	SELF_DOWN_PEER_DOWN    = 0xdd,
+	SELF_UP_PEER_UP        = 0xaa,
+	SELF_DOWN_PEER_LEAVING = 0xd1,
+	SELF_UP_PEER_COMING    = 0xac,
+	SELF_COMING_PEER_UP    = 0xca,
+	SELF_LEAVING_PEER_DOWN = 0x1d,
+};
+
+enum {
+	SELF_ESTABL_CONTACT_EVT = 0xec,
+	SELF_LOST_CONTACT_EVT   = 0x1c,
+	PEER_ESTABL_CONTACT_EVT = 0xfec,
+	PEER_LOST_CONTACT_EVT   = 0xf1c
+};
+
 /* Flags used to take different actions according to flag type
  * TIPC_WAIT_PEER_LINKS_DOWN: wait to see that peer's links are down
  * TIPC_WAIT_OWN_LINKS_DOWN: wait until peer node is declared down
@@ -56,8 +74,6 @@
  */
 enum {
 	TIPC_MSG_EVT                    = 1,
-	TIPC_WAIT_PEER_LINKS_DOWN	= (1 << 1),
-	TIPC_WAIT_OWN_LINKS_DOWN	= (1 << 2),
 	TIPC_NOTIFY_NODE_DOWN		= (1 << 3),
 	TIPC_NOTIFY_NODE_UP		= (1 << 4),
 	TIPC_WAKEUP_BCAST_USERS		= (1 << 5),
@@ -133,6 +149,7 @@ struct tipc_node {
 	int action_flags;
 	struct tipc_node_bclink bclink;
 	struct list_head list;
+	int state;
 	int link_cnt;
 	u16 working_links;
 	u16 capabilities;
@@ -176,11 +193,8 @@ static inline void tipc_node_lock(struct tipc_node *node)
 	spin_lock_bh(&node->lock);
 }
 
-static inline bool tipc_node_blocked(struct tipc_node *node)
-{
-	return (node->action_flags & (TIPC_WAIT_PEER_LINKS_DOWN |
-		TIPC_NOTIFY_NODE_DOWN | TIPC_WAIT_OWN_LINKS_DOWN));
-}
+void tipc_node_fsm_evt(struct tipc_node *n, int evt);
+bool tipc_node_filter_skb(struct tipc_node *n, struct tipc_msg *hdr);
 
 static inline struct tipc_link *node_active_link(struct tipc_node *n, int sel)
 {