summaryrefslogtreecommitdiff
path: root/net/tipc/discover.c
diff options
context:
space:
mode:
authorJon Maloy <jon.maloy@ericsson.com>2018-03-22 22:42:47 +0300
committerDavid S. Miller <davem@davemloft.net>2018-03-23 20:12:18 +0300
commit2026364149db36c6a2c0c8cae8362fe9a7f954dd (patch)
tree267dc296fc385f53a8bd9537c9ac8193ea4b5663 /net/tipc/discover.c
parentb39e465e56ec38ca64b4c0affeb6411eb0ed7267 (diff)
downloadlinux-2026364149db36c6a2c0c8cae8362fe9a7f954dd.tar.xz
tipc: remove restrictions on node address values
Nominally, TIPC organizes network nodes into a three-level network hierarchy consisting of the levels 'zone', 'cluster' and 'node'. This hierarchy is reflected in the node address format, - it is sub-divided into an 8-bit zone id, and 12 bit cluster id, and a 12-bit node id. However, the 'zone' and 'cluster' levels have in reality never been fully implemented,and never will be. The result of this has been that the first 20 bits the node identity structure have been wasted, and the usable node identity range within a cluster has been limited to 12 bits. This is starting to become a problem. In the following commits, we will need to be able to connect between nodes which are using the whole 32-bit value space of the node address. We therefore remove the restrictions on which values can be assigned to node identity, -it is from now on only a 32-bit integer with no assumed internal structure. Isolation between clusters is now achieved only by setting different values for the 'network id' field used during neighbor discovery, in practice leading to the latter becoming the new cluster identity. The rules for accepting discovery requests/responses from neighboring nodes now become: - If the user is using legacy address format on both peers, reception of discovery messages is subject to the legacy lookup domain check in addition to the cluster id check. - Otherwise, the discovery request/response is always accepted, provided both peers have the same network id. This secures backwards compatibility for users who have been using zone or cluster identities as cluster separators, instead of the intended 'network id'. Acked-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>
Diffstat (limited to 'net/tipc/discover.c')
-rw-r--r--net/tipc/discover.c15
1 files changed, 7 insertions, 8 deletions
diff --git a/net/tipc/discover.c b/net/tipc/discover.c
index 09f75558d353..669af125b3de 100644
--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -161,18 +161,17 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb,
return;
if (net_id != tn->net_id)
return;
- if (!tipc_addr_domain_valid(dst))
- return;
- if (!tipc_addr_node_valid(src))
- return;
if (in_own_node(net, src)) {
disc_dupl_alert(b, self, &maddr);
return;
}
- if (!tipc_in_scope(dst, self))
- return;
- if (!tipc_in_scope(b->domain, src))
- return;
+ /* Domain filter only works if both peers use legacy address format */
+ if (b->domain) {
+ if (!tipc_in_scope(dst, self))
+ return;
+ if (!tipc_in_scope(b->domain, src))
+ return;
+ }
tipc_node_check_dest(net, src, b, caps, signature,
&maddr, &respond, &dupl_addr);
if (dupl_addr)