tipc: delay ESTABLISH state event when link is established

Link establishing, just like link teardown, is a non-atomic action, in
the sense that discovering that conditions are right to establish a link,
and the actual adding of the link to one of the node's send slots is done
in two different lock contexts. The link FSM is designed to help bridging
the gap between the two contexts in a safe manner.

We have now discovered a weakness in the implementaton of this FSM.
Because we directly let the link go from state LINK_ESTABLISHING to
state LINK_ESTABLISHED already in the first lock context, we are unable
to distinguish between a fully established link, i.e., a link that has
been added to its slot, and a link that has not yet reached the second
lock context. It may hence happen that a manual intervention, e.g., when
disabling an interface, causes the function tipc_node_link_down() to try
removing the link from the node slots, decrementing its active link
counter etc, although the link was never added there in the first place.

We solve this by delaying the actual state change until we reach the
second lock context, inside the function tipc_node_link_up(). This
makes it possible for potentail callers of __tipc_node_link_down() to
know if they should proceed or not, and the problem is solved.

Unforunately, the situation described above also has a second problem.
Since there by necessity is a tipc_node_link_up() call pending once
the node lock has been released, we must defuse that call by setting
the link back from LINK_ESTABLISHING to LINK_RESET state. This forces
us to make a slight modification to the link FSM, which will now look
as follows.

 +------------------------------------+
 |RESET_EVT                           |
 |                                    |
 |                             +--------------+
 |           +-----------------|   SYNCHING   |-----------------+
 |           |FAILURE_EVT      +--------------+   PEER_RESET_EVT|
 |           |                  A            |                  |
 |           |                  |            |                  |
 |           |                  |            |                  |
 |           |                  |SYNCH_      |SYNCH_            |
 |           |                  |BEGIN_EVT   |END_EVT           |
 |           |                  |            |                  |
 |           V                  |            V                  V
 |    +-------------+          +--------------+          +------------+
 |    |  RESETTING  |<---------|  ESTABLISHED |--------->| PEER_RESET |
 |    +-------------+ FAILURE_ +--------------+ PEER_    +------------+
 |           |        EVT        |    A         RESET_EVT       |
 |           |                   |    |                         |
 |           |  +----------------+    |                         |
 |  RESET_EVT|  |RESET_EVT            |                         |
 |           |  |                     |                         |
 |           |  |                     |ESTABLISH_EVT            |
 |           |  |  +-------------+    |                         |
 |           |  |  | RESET_EVT   |    |                         |
 |           |  |  |             |    |                         |
 |           V  V  V             |    |                         |
 |    +-------------+          +--------------+        RESET_EVT|
 +--->|    RESET    |--------->| ESTABLISHING |<----------------+
      +-------------+ PEER_    +--------------+
       |           A  RESET_EVT       |
       |           |                  |
       |           |                  |
       |FAILOVER_  |FAILOVER_         |FAILOVER_
       |BEGIN_EVT  |END_EVT           |BEGIN_EVT
       |           |                  |
       V           |                  |
      +-------------+                 |
      | FAILINGOVER |<----------------+
      +-------------+

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

1 files changed, 26 insertions, 14 deletions

diff --git a/net/tipc/link.c b/net/tipc/link.c
index e7c608631276..8c794c1dd531 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -125,6 +125,11 @@ bool tipc_link_is_reset(struct tipc_link *l)
 	return l->state & (LINK_RESET | LINK_FAILINGOVER | LINK_ESTABLISHING);
 }
 
+bool tipc_link_is_establishing(struct tipc_link *l)
+{
+	return l->state == LINK_ESTABLISHING;
+}
+
 bool tipc_link_is_synching(struct tipc_link *l)
 {
 	return l->state == LINK_SYNCHING;
@@ -321,14 +326,15 @@ int tipc_link_fsm_evt(struct tipc_link *l, int evt)
 		switch (evt) {
 		case LINK_ESTABLISH_EVT:
 			l->state = LINK_ESTABLISHED;
-			rc |= TIPC_LINK_UP_EVT;
 			break;
 		case LINK_FAILOVER_BEGIN_EVT:
 			l->state = LINK_FAILINGOVER;
 			break;
-		case LINK_PEER_RESET_EVT:
 		case LINK_RESET_EVT:
+			l->state = LINK_RESET;
+			break;
 		case LINK_FAILURE_EVT:
+		case LINK_PEER_RESET_EVT:
 		case LINK_SYNCH_BEGIN_EVT:
 		case LINK_FAILOVER_END_EVT:
 			break;
@@ -1091,9 +1097,9 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb,
 			return tipc_link_proto_rcv(l, skb, xmitq);
 
 		if (unlikely(!link_is_up(l))) {
-			rc = tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT);
-			if (!link_is_up(l))
-				goto drop;
+			if (l->state == LINK_ESTABLISHING)
+				rc = TIPC_LINK_UP_EVT;
+			goto drop;
 		}
 
 		/* Don't send probe at next timeout expiration */
@@ -1338,6 +1344,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 	u16 peers_tol = msg_link_tolerance(hdr);
 	u16 peers_prio = msg_linkprio(hdr);
 	u16 rcv_nxt = l->rcv_nxt;
+	int mtyp = msg_type(hdr);
 	char *if_name;
 	int rc = 0;
 
@@ -1347,7 +1354,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 	if (link_own_addr(l) > msg_prevnode(hdr))
 		l->net_plane = msg_net_plane(hdr);
 
-	switch (msg_type(hdr)) {
+	switch (mtyp) {
 	case RESET_MSG:
 
 		/* Ignore duplicate RESET with old session number */
@@ -1374,12 +1381,14 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 		if (in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI))
 			l->priority = peers_prio;
 
-		if (msg_type(hdr) == RESET_MSG) {
-			rc |= tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT);
-		} else if (!link_is_up(l)) {
-			tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT);
-			rc |= tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT);
-		}
+		/* ACTIVATE_MSG serves as PEER_RESET if link is already down */
+		if ((mtyp == RESET_MSG) || !link_is_up(l))
+			rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT);
+
+		/* ACTIVATE_MSG takes up link if it was already locally reset */
+		if ((mtyp == ACTIVATE_MSG) && (l->state == LINK_ESTABLISHING))
+			rc = TIPC_LINK_UP_EVT;
+
 		l->peer_session = msg_session(hdr);
 		l->peer_bearer_id = msg_bearer_id(hdr);
 		if (l->mtu > msg_max_pkt(hdr))
@@ -1396,9 +1405,12 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 		l->stats.recv_states++;
 		if (msg_probe(hdr))
 			l->stats.recv_probes++;
-		rc = tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT);
-		if (!link_is_up(l))
+
+		if (!link_is_up(l)) {
+			if (l->state == LINK_ESTABLISHING)
+				rc = TIPC_LINK_UP_EVT;
 			break;
+		}
 
 		/* Send NACK if peer has sent pkts we haven't received yet */
 		if (more(peers_snd_nxt, rcv_nxt) && !tipc_link_is_synching(l))