2006-01-03 02:04:38 +08:00
|
|
|
/*
|
|
|
|
|
* net/tipc/name_table.h: Include file for TIPC name table code
|
2007-02-09 22:25:21 +08:00
|
|
|
*
|
2018-03-15 23:48:54 +08:00
|
|
|
* Copyright (c) 2000-2006, 2014-2018, Ericsson AB
|
2011-05-30 22:48:48 +08:00
|
|
|
* Copyright (c) 2004-2005, 2010-2011, Wind River Systems
|
2006-01-03 02:04:38 +08:00
|
|
|
* All rights reserved.
|
|
|
|
|
*
|
2006-01-11 20:30:43 +08:00
|
|
|
* Redistribution and use in source and binary forms, with or without
|
2006-01-03 02:04:38 +08:00
|
|
|
* modification, are permitted provided that the following conditions are met:
|
|
|
|
|
*
|
2006-01-11 20:30:43 +08:00
|
|
|
* 1. Redistributions of source code must retain the above copyright
|
|
|
|
|
* notice, this list of conditions and the following disclaimer.
|
|
|
|
|
* 2. Redistributions in binary form must reproduce the above copyright
|
|
|
|
|
* notice, this list of conditions and the following disclaimer in the
|
|
|
|
|
* documentation and/or other materials provided with the distribution.
|
|
|
|
|
* 3. Neither the names of the copyright holders nor the names of its
|
|
|
|
|
* contributors may be used to endorse or promote products derived from
|
|
|
|
|
* this software without specific prior written permission.
|
2006-01-03 02:04:38 +08:00
|
|
|
*
|
2006-01-11 20:30:43 +08:00
|
|
|
* Alternatively, this software may be distributed under the terms of the
|
|
|
|
|
* GNU General Public License ("GPL") version 2 as published by the Free
|
|
|
|
|
* Software Foundation.
|
|
|
|
|
*
|
|
|
|
|
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
|
|
|
|
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
|
|
|
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
|
|
|
|
* ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
|
|
|
|
|
* LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
|
|
|
|
|
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
|
|
|
|
|
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
|
|
|
|
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
|
|
|
|
|
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
|
|
|
|
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
|
2006-01-03 02:04:38 +08:00
|
|
|
* POSSIBILITY OF SUCH DAMAGE.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#ifndef _TIPC_NAME_TABLE_H
|
|
|
|
|
#define _TIPC_NAME_TABLE_H
|
|
|
|
|
|
2011-12-30 09:43:44 +08:00
|
|
|
struct tipc_subscription;
|
2015-02-05 21:36:43 +08:00
|
|
|
struct tipc_plist;
|
2017-01-19 02:50:51 +08:00
|
|
|
struct tipc_nlist;
|
tipc: introduce communication groups
As a preparation for introducing flow control for multicast and datagram
messaging we need a more strictly defined framework than we have now. A
socket must be able keep track of exactly how many and which other
sockets it is allowed to communicate with at any moment, and keep the
necessary state for those.
We therefore introduce a new concept we have named Communication Group.
Sockets can join a group via a new setsockopt() call TIPC_GROUP_JOIN.
The call takes four parameters: 'type' serves as group identifier,
'instance' serves as an logical member identifier, and 'scope' indicates
the visibility of the group (node/cluster/zone). Finally, 'flags' makes
it possible to set certain properties for the member. For now, there is
only one flag, indicating if the creator of the socket wants to receive
a copy of broadcast or multicast messages it is sending via the socket,
and if wants to be eligible as destination for its own anycasts.
A group is closed, i.e., sockets which have not joined a group will
not be able to send messages to or receive messages from members of
the group, and vice versa.
Any member of a group can send multicast ('group broadcast') messages
to all group members, optionally including itself, using the primitive
send(). The messages are received via the recvmsg() primitive. A socket
can only be member of one group at a time.
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>
2017-10-13 17:04:23 +08:00
|
|
|
struct tipc_group;
|
2006-01-03 02:04:38 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* TIPC name types reserved for internal TIPC use (both current and planned)
|
|
|
|
|
*/
|
2014-12-02 15:00:24 +08:00
|
|
|
#define TIPC_ZM_SRV 3 /* zone master service name type */
|
|
|
|
|
#define TIPC_PUBL_SCOPE_NUM (TIPC_NODE_SCOPE + 1)
|
|
|
|
|
#define TIPC_NAMETBL_SIZE 1024 /* must be a power of 2 */
|
2006-01-03 02:04:38 +08:00
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* struct publication - info about a published (name or) name sequence
|
|
|
|
|
* @type: name sequence type
|
|
|
|
|
* @lower: name sequence lower bound
|
|
|
|
|
* @upper: name sequence upper bound
|
2018-03-15 23:48:55 +08:00
|
|
|
* @scope: scope of publication, TIPC_NODE_SCOPE or TIPC_CLUSTER_SCOPE
|
|
|
|
|
* @node: network address of publishing socket's node
|
|
|
|
|
* @port: publishing port
|
|
|
|
|
* @key: publication key, unique across the cluster
|
tipc: support in-order name publication events
It is observed that TIPC service binding order will not be kept in the
publication event report to user if the service is subscribed after the
bindings.
For example, services are bound by application in the following order:
Server: bound port A to {18888,66,66} scope 2
Server: bound port A to {18888,33,33} scope 2
Now, if a client subscribes to the service range (e.g. {18888, 0-100}),
it will get the 'TIPC_PUBLISHED' events in that binding order only when
the subscription is started before the bindings.
Otherwise, if started after the bindings, the events will arrive in the
opposite order:
Client: received event for published {18888,33,33}
Client: received event for published {18888,66,66}
For the latter case, it is clear that the bindings have existed in the
name table already, so when reported, the events' order will follow the
order of the rbtree binding nodes (- a node with lesser 'lower'/'upper'
range value will be first).
This is correct as we provide the tracking on a specific service status
(available or not), not the relationship between multiple services.
However, some users expect to see the same order of arriving events
irrespective of when the subscription is issued. This turns out to be
easy to fix. We now add functionality to ensure that publication events
always are issued in the same temporal order as the corresponding
bindings were performed.
v2: replace the unnecessary macro - 'publication_after()' with inline
function.
v3: reuse 'time_after32()' instead of reinventing the same exact code.
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-21 16:34:58 +08:00
|
|
|
* @id: publication id
|
2018-03-15 23:48:55 +08:00
|
|
|
* @binding_node: all publications from the same node which bound this one
|
|
|
|
|
* - Remote publications: in node->publ_list
|
|
|
|
|
* Used by node/name distr to withdraw publications when node is lost
|
|
|
|
|
* - Local/node scope publications: in name_table->node_scope list
|
|
|
|
|
* - Local/cluster scope publications: in name_table->cluster_scope list
|
|
|
|
|
* @binding_sock: all publications from the same socket which bound this one
|
|
|
|
|
* Used by socket to withdraw publications when socket is unbound/released
|
|
|
|
|
* @local_publ: list of identical publications made from this node
|
|
|
|
|
* Used by closest_first and multicast receive lookup algorithms
|
|
|
|
|
* @all_publ: all publications identical to this one, whatever node and scope
|
|
|
|
|
* Used by round-robin lookup algorithm
|
tipc: support in-order name publication events
It is observed that TIPC service binding order will not be kept in the
publication event report to user if the service is subscribed after the
bindings.
For example, services are bound by application in the following order:
Server: bound port A to {18888,66,66} scope 2
Server: bound port A to {18888,33,33} scope 2
Now, if a client subscribes to the service range (e.g. {18888, 0-100}),
it will get the 'TIPC_PUBLISHED' events in that binding order only when
the subscription is started before the bindings.
Otherwise, if started after the bindings, the events will arrive in the
opposite order:
Client: received event for published {18888,33,33}
Client: received event for published {18888,66,66}
For the latter case, it is clear that the bindings have existed in the
name table already, so when reported, the events' order will follow the
order of the rbtree binding nodes (- a node with lesser 'lower'/'upper'
range value will be first).
This is correct as we provide the tracking on a specific service status
(available or not), not the relationship between multiple services.
However, some users expect to see the same order of arriving events
irrespective of when the subscription is issued. This turns out to be
easy to fix. We now add functionality to ensure that publication events
always are issued in the same temporal order as the corresponding
bindings were performed.
v2: replace the unnecessary macro - 'publication_after()' with inline
function.
v3: reuse 'time_after32()' instead of reinventing the same exact code.
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-21 16:34:58 +08:00
|
|
|
* @list: to form a list of publications in temporal order
|
2014-12-02 15:00:30 +08:00
|
|
|
* @rcu: RCU callback head used for deferred freeing
|
2006-01-03 02:04:38 +08:00
|
|
|
*/
|
|
|
|
|
struct publication {
|
|
|
|
|
u32 type;
|
|
|
|
|
u32 lower;
|
|
|
|
|
u32 upper;
|
|
|
|
|
u32 scope;
|
|
|
|
|
u32 node;
|
2018-03-15 23:48:55 +08:00
|
|
|
u32 port;
|
2006-01-03 02:04:38 +08:00
|
|
|
u32 key;
|
tipc: support in-order name publication events
It is observed that TIPC service binding order will not be kept in the
publication event report to user if the service is subscribed after the
bindings.
For example, services are bound by application in the following order:
Server: bound port A to {18888,66,66} scope 2
Server: bound port A to {18888,33,33} scope 2
Now, if a client subscribes to the service range (e.g. {18888, 0-100}),
it will get the 'TIPC_PUBLISHED' events in that binding order only when
the subscription is started before the bindings.
Otherwise, if started after the bindings, the events will arrive in the
opposite order:
Client: received event for published {18888,33,33}
Client: received event for published {18888,66,66}
For the latter case, it is clear that the bindings have existed in the
name table already, so when reported, the events' order will follow the
order of the rbtree binding nodes (- a node with lesser 'lower'/'upper'
range value will be first).
This is correct as we provide the tracking on a specific service status
(available or not), not the relationship between multiple services.
However, some users expect to see the same order of arriving events
irrespective of when the subscription is issued. This turns out to be
easy to fix. We now add functionality to ensure that publication events
always are issued in the same temporal order as the corresponding
bindings were performed.
v2: replace the unnecessary macro - 'publication_after()' with inline
function.
v3: reuse 'time_after32()' instead of reinventing the same exact code.
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-21 16:34:58 +08:00
|
|
|
u32 id;
|
2018-03-15 23:48:54 +08:00
|
|
|
struct list_head binding_node;
|
2018-03-15 23:48:55 +08:00
|
|
|
struct list_head binding_sock;
|
|
|
|
|
struct list_head local_publ;
|
|
|
|
|
struct list_head all_publ;
|
tipc: support in-order name publication events
It is observed that TIPC service binding order will not be kept in the
publication event report to user if the service is subscribed after the
bindings.
For example, services are bound by application in the following order:
Server: bound port A to {18888,66,66} scope 2
Server: bound port A to {18888,33,33} scope 2
Now, if a client subscribes to the service range (e.g. {18888, 0-100}),
it will get the 'TIPC_PUBLISHED' events in that binding order only when
the subscription is started before the bindings.
Otherwise, if started after the bindings, the events will arrive in the
opposite order:
Client: received event for published {18888,33,33}
Client: received event for published {18888,66,66}
For the latter case, it is clear that the bindings have existed in the
name table already, so when reported, the events' order will follow the
order of the rbtree binding nodes (- a node with lesser 'lower'/'upper'
range value will be first).
This is correct as we provide the tracking on a specific service status
(available or not), not the relationship between multiple services.
However, some users expect to see the same order of arriving events
irrespective of when the subscription is issued. This turns out to be
easy to fix. We now add functionality to ensure that publication events
always are issued in the same temporal order as the corresponding
bindings were performed.
v2: replace the unnecessary macro - 'publication_after()' with inline
function.
v3: reuse 'time_after32()' instead of reinventing the same exact code.
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-21 16:34:58 +08:00
|
|
|
struct list_head list;
|
2014-12-02 15:00:30 +08:00
|
|
|
struct rcu_head rcu;
|
2006-01-03 02:04:38 +08:00
|
|
|
};
|
|
|
|
|
|
2014-12-02 15:00:24 +08:00
|
|
|
/**
|
|
|
|
|
* struct name_table - table containing all existing port name publications
|
|
|
|
|
* @seq_hlist: name sequence hash lists
|
2018-03-15 23:48:52 +08:00
|
|
|
* @node_scope: all local publications with node scope
|
2018-03-15 23:48:55 +08:00
|
|
|
* - used by name_distr during re-init of name table
|
2018-03-15 23:48:52 +08:00
|
|
|
* @cluster_scope: all local publications with cluster scope
|
2018-03-15 23:48:55 +08:00
|
|
|
* - used by name_distr to send bulk updates to new nodes
|
|
|
|
|
* - used by name_distr during re-init of name table
|
2014-12-02 15:00:24 +08:00
|
|
|
* @local_publ_count: number of publications issued by this node
|
|
|
|
|
*/
|
|
|
|
|
struct name_table {
|
2018-03-30 05:20:41 +08:00
|
|
|
struct hlist_head services[TIPC_NAMETBL_SIZE];
|
2018-03-15 23:48:52 +08:00
|
|
|
struct list_head node_scope;
|
|
|
|
|
struct list_head cluster_scope;
|
tipc: eliminate message disordering during binding table update
We have seen the following race scenario:
1) named_distribute() builds a "bulk" message, containing a PUBLISH
item for a certain publication. This is based on the contents of
the binding tables's 'cluster_scope' list.
2) tipc_named_withdraw() removes the same publication from the list,
bulds a WITHDRAW message and distributes it to all cluster nodes.
3) tipc_named_node_up(), which was calling named_distribute(), sends
out the bulk message built under 1)
4) The WITHDRAW message arrives at the just detected node, finds
no corresponding publication, and is dropped.
5) The PUBLISH item arrives at the same node, is added to its binding
table, and remains there forever.
This arrival disordering was earlier taken care of by the backlog queue,
originally added for a different purpose, which was removed in the
commit referred to below, but we now need a different solution.
In this commit, we replace the rcu lock protecting the 'cluster_scope'
list with a regular RW lock which comprises even the sending of the
bulk message. This both guarantees both the list integrity and the
message sending order. We will later add a commit which cleans up
this code further.
Note that this commit needs recently added commit d3092b2efca1 ("tipc:
fix unsafe rcu locking when accessing publication list") to apply
cleanly.
Fixes: 37922ea4a310 ("tipc: permit overlapping service ranges in name table")
Reported-by: Tuong Lien Tong <tuong.t.lien@dektech.com.au>
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>
2018-10-20 01:55:40 +08:00
|
|
|
rwlock_t cluster_scope_lock;
|
2014-12-02 15:00:24 +08:00
|
|
|
u32 local_publ_count;
|
|
|
|
|
};
|
2006-01-03 02:04:38 +08:00
|
|
|
|
2014-11-20 17:29:20 +08:00
|
|
|
int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb);
|
|
|
|
|
|
2015-01-09 15:27:09 +08:00
|
|
|
u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, u32 *node);
|
2018-03-15 23:48:53 +08:00
|
|
|
void tipc_nametbl_mc_lookup(struct net *net, u32 type, u32 lower, u32 upper,
|
|
|
|
|
u32 scope, bool exact, struct list_head *dports);
|
tipc: introduce communication groups
As a preparation for introducing flow control for multicast and datagram
messaging we need a more strictly defined framework than we have now. A
socket must be able keep track of exactly how many and which other
sockets it is allowed to communicate with at any moment, and keep the
necessary state for those.
We therefore introduce a new concept we have named Communication Group.
Sockets can join a group via a new setsockopt() call TIPC_GROUP_JOIN.
The call takes four parameters: 'type' serves as group identifier,
'instance' serves as an logical member identifier, and 'scope' indicates
the visibility of the group (node/cluster/zone). Finally, 'flags' makes
it possible to set certain properties for the member. For now, there is
only one flag, indicating if the creator of the socket wants to receive
a copy of broadcast or multicast messages it is sending via the socket,
and if wants to be eligible as destination for its own anycasts.
A group is closed, i.e., sockets which have not joined a group will
not be able to send messages to or receive messages from members of
the group, and vice versa.
Any member of a group can send multicast ('group broadcast') messages
to all group members, optionally including itself, using the primitive
send(). The messages are received via the recvmsg() primitive. A socket
can only be member of one group at a time.
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>
2017-10-13 17:04:23 +08:00
|
|
|
void tipc_nametbl_build_group(struct net *net, struct tipc_group *grp,
|
|
|
|
|
u32 type, u32 domain);
|
2017-01-19 02:50:51 +08:00
|
|
|
void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower,
|
2018-01-13 03:56:50 +08:00
|
|
|
u32 upper, struct tipc_nlist *nodes);
|
2017-10-13 17:04:28 +08:00
|
|
|
bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 domain,
|
|
|
|
|
struct list_head *dsts, int *dstcnt, u32 exclude,
|
|
|
|
|
bool all);
|
2015-01-09 15:27:05 +08:00
|
|
|
struct publication *tipc_nametbl_publish(struct net *net, u32 type, u32 lower,
|
2018-03-30 05:20:43 +08:00
|
|
|
u32 upper, u32 scope, u32 port,
|
2015-01-09 15:27:05 +08:00
|
|
|
u32 key);
|
2018-03-30 05:20:43 +08:00
|
|
|
int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower, u32 upper,
|
2015-01-09 15:27:05 +08:00
|
|
|
u32 key);
|
2015-01-09 15:27:09 +08:00
|
|
|
struct publication *tipc_nametbl_insert_publ(struct net *net, u32 type,
|
|
|
|
|
u32 lower, u32 upper, u32 scope,
|
|
|
|
|
u32 node, u32 ref, u32 key);
|
|
|
|
|
struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type,
|
2018-03-30 05:20:43 +08:00
|
|
|
u32 lower, u32 upper,
|
|
|
|
|
u32 node, u32 key);
|
2018-04-12 04:52:09 +08:00
|
|
|
bool tipc_nametbl_subscribe(struct tipc_subscription *s);
|
2011-12-30 09:43:44 +08:00
|
|
|
void tipc_nametbl_unsubscribe(struct tipc_subscription *s);
|
2015-01-09 15:27:09 +08:00
|
|
|
int tipc_nametbl_init(struct net *net);
|
|
|
|
|
void tipc_nametbl_stop(struct net *net);
|
2006-01-03 02:04:38 +08:00
|
|
|
|
2017-10-13 17:04:22 +08:00
|
|
|
struct tipc_dest {
|
2017-01-19 02:50:51 +08:00
|
|
|
struct list_head list;
|
2018-08-27 09:32:26 +08:00
|
|
|
u32 port;
|
|
|
|
|
u32 node;
|
2017-01-19 02:50:51 +08:00
|
|
|
};
|
|
|
|
|
|
2017-10-13 17:04:22 +08:00
|
|
|
struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port);
|
|
|
|
|
bool tipc_dest_push(struct list_head *l, u32 node, u32 port);
|
|
|
|
|
bool tipc_dest_pop(struct list_head *l, u32 *node, u32 *port);
|
|
|
|
|
bool tipc_dest_del(struct list_head *l, u32 node, u32 port);
|
|
|
|
|
void tipc_dest_list_purge(struct list_head *l);
|
|
|
|
|
int tipc_dest_list_len(struct list_head *l);
|
2015-02-05 21:36:43 +08:00
|
|
|
|
2006-01-03 02:04:38 +08:00
|
|
|
#endif
|