2006-01-03 01:04:38 +07:00
|
|
|
/*
|
|
|
|
* net/tipc/node.h: Include file for TIPC node management routines
|
2007-02-09 21:25:21 +07:00
|
|
|
*
|
2006-01-12 01:14:19 +07:00
|
|
|
* Copyright (c) 2000-2006, Ericsson AB
|
2011-02-26 06:42:52 +07:00
|
|
|
* Copyright (c) 2005, 2010-2011, Wind River Systems
|
2006-01-03 01:04:38 +07:00
|
|
|
* All rights reserved.
|
|
|
|
*
|
2006-01-11 19:30:43 +07:00
|
|
|
* Redistribution and use in source and binary forms, with or without
|
2006-01-03 01:04:38 +07:00
|
|
|
* modification, are permitted provided that the following conditions are met:
|
|
|
|
*
|
2006-01-11 19:30:43 +07:00
|
|
|
* 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 01:04:38 +07:00
|
|
|
*
|
2006-01-11 19:30:43 +07:00
|
|
|
* 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 01:04:38 +07:00
|
|
|
* POSSIBILITY OF SUCH DAMAGE.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef _TIPC_NODE_H
|
|
|
|
#define _TIPC_NODE_H
|
|
|
|
|
|
|
|
#include "node_subscr.h"
|
2011-01-01 01:59:19 +07:00
|
|
|
#include "addr.h"
|
|
|
|
#include "net.h"
|
2006-01-03 01:04:38 +07:00
|
|
|
#include "bearer.h"
|
|
|
|
|
2011-10-29 03:26:41 +07:00
|
|
|
/*
|
|
|
|
* Out-of-range value for node signature
|
|
|
|
*/
|
|
|
|
#define INVALID_NODE_SIG 0x10000
|
|
|
|
|
tipc: Ensure both nodes recognize loss of contact between them
Enhances TIPC to ensure that a node that loses contact with a
neighboring node does not allow contact to be re-established until
it sees that its peer has also recognized the loss of contact.
Previously, nodes that were connected by two or more links could
encounter a situation in which node A would lose contact with node B
on all of its links, purge its name table of names published by B,
and then fail to repopulate those names once contact with B was restored.
This would happen because B was able to re-establish one or more links
so quickly that it never reached a point where it had no links to A --
meaning that B never saw a loss of contact with A, and consequently
didn't re-publish its names to A.
This problem is now prevented by enhancing the cleanup done by TIPC
following a loss of contact with a neighboring node to ensure that
node A ignores all messages sent by B until it receives a LINK_PROTOCOL
message that indicates B has lost contact with A, thereby preventing
the (re)establishment of links between the nodes. The loss of contact
is recognized when a RESET or ACTIVATE message is received that has
a "redundant link exists" field of 0, indicating that B's sending link
endpoint is in a reset state and that B has no other working links.
Additionally, TIPC now suppresses the sending of (most) link protocol
messages to a neighboring node while it is cleaning up after an earlier
loss of contact with that node. This stops the peer node from prematurely
activating its link endpoint, which would prevent TIPC from later
activating its own end. TIPC still allows outgoing RESET messages to
occur during cleanup, to avoid problems if its own node recognizes
the loss of contact first and tries to notify the peer of the situation.
Finally, TIPC now recognizes an impending loss of contact with a peer node
as soon as it receives a RESET message on a working link that is the
peer's only link to the node, and ensures that the link protocol
suppression mentioned above goes into effect right away -- that is,
even before its own link endpoints have failed. This is necessary to
ensure correct operation when there are redundant links between the nodes,
since otherwise TIPC would send an ACTIVATE message upon receiving a RESET
on its first link and only begin suppressing when a RESET on its second
link was received, instead of initiating suppression with the first RESET
message as it needs to.
Note: The reworked cleanup code also eliminates a check that prevented
a link endpoint's discovery object from responding to incoming messages
while stale name table entries are being purged. This check is now
unnecessary and would have slowed down re-establishment of communication
between the nodes in some situations.
Signed-off-by: Allan Stephens <allan.stephens@windriver.com>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2011-05-27 22:00:51 +07:00
|
|
|
/* Flags used to block (re)establishment of contact with a neighboring node */
|
|
|
|
#define WAIT_PEER_DOWN 0x0001 /* wait to see that peer's links are down */
|
|
|
|
#define WAIT_NAMES_GONE 0x0002 /* wait for peer's publications to be purged */
|
|
|
|
#define WAIT_NODE_DOWN 0x0004 /* wait until peer node is declared down */
|
|
|
|
|
2006-01-03 01:04:38 +07:00
|
|
|
/**
|
2008-09-03 13:38:32 +07:00
|
|
|
* struct tipc_node - TIPC node structure
|
2006-01-03 01:04:38 +07:00
|
|
|
* @addr: network address of node
|
|
|
|
* @lock: spinlock governing access to structure
|
2011-02-26 06:42:52 +07:00
|
|
|
* @hash: links to adjacent nodes in unsorted hash chain
|
|
|
|
* @list: links to adjacent nodes in sorted list of cluster's nodes
|
2006-01-03 01:04:38 +07:00
|
|
|
* @nsub: list of "node down" subscriptions monitoring node
|
|
|
|
* @active_links: pointers to active links to node
|
|
|
|
* @links: pointers to all links to node
|
2006-06-26 13:52:50 +07:00
|
|
|
* @working_links: number of working links to node (both active and standby)
|
tipc: Ensure both nodes recognize loss of contact between them
Enhances TIPC to ensure that a node that loses contact with a
neighboring node does not allow contact to be re-established until
it sees that its peer has also recognized the loss of contact.
Previously, nodes that were connected by two or more links could
encounter a situation in which node A would lose contact with node B
on all of its links, purge its name table of names published by B,
and then fail to repopulate those names once contact with B was restored.
This would happen because B was able to re-establish one or more links
so quickly that it never reached a point where it had no links to A --
meaning that B never saw a loss of contact with A, and consequently
didn't re-publish its names to A.
This problem is now prevented by enhancing the cleanup done by TIPC
following a loss of contact with a neighboring node to ensure that
node A ignores all messages sent by B until it receives a LINK_PROTOCOL
message that indicates B has lost contact with A, thereby preventing
the (re)establishment of links between the nodes. The loss of contact
is recognized when a RESET or ACTIVATE message is received that has
a "redundant link exists" field of 0, indicating that B's sending link
endpoint is in a reset state and that B has no other working links.
Additionally, TIPC now suppresses the sending of (most) link protocol
messages to a neighboring node while it is cleaning up after an earlier
loss of contact with that node. This stops the peer node from prematurely
activating its link endpoint, which would prevent TIPC from later
activating its own end. TIPC still allows outgoing RESET messages to
occur during cleanup, to avoid problems if its own node recognizes
the loss of contact first and tries to notify the peer of the situation.
Finally, TIPC now recognizes an impending loss of contact with a peer node
as soon as it receives a RESET message on a working link that is the
peer's only link to the node, and ensures that the link protocol
suppression mentioned above goes into effect right away -- that is,
even before its own link endpoints have failed. This is necessary to
ensure correct operation when there are redundant links between the nodes,
since otherwise TIPC would send an ACTIVATE message upon receiving a RESET
on its first link and only begin suppressing when a RESET on its second
link was received, instead of initiating suppression with the first RESET
message as it needs to.
Note: The reworked cleanup code also eliminates a check that prevented
a link endpoint's discovery object from responding to incoming messages
while stale name table entries are being purged. This check is now
unnecessary and would have slowed down re-establishment of communication
between the nodes in some situations.
Signed-off-by: Allan Stephens <allan.stephens@windriver.com>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2011-05-27 22:00:51 +07:00
|
|
|
* @block_setup: bit mask of conditions preventing link establishment to node
|
2006-01-03 01:04:38 +07:00
|
|
|
* @link_cnt: number of links to node
|
2011-10-29 03:26:41 +07:00
|
|
|
* @signature: node instance identifier
|
2006-01-03 01:04:38 +07:00
|
|
|
* @bclink: broadcast-related info
|
|
|
|
* @acked: sequence # of last outbound b'cast message acknowledged by node
|
|
|
|
* @last_in: sequence # of last in-sequence b'cast message received from node
|
tipc: Major redesign of broadcast link ACK/NACK algorithms
Completely redesigns broadcast link ACK and NACK mechanisms to prevent
spurious retransmit requests in dual LAN networks, and to prevent the
broadcast link from stalling due to the failure of a receiving node to
acknowledge receiving a broadcast message or request its retransmission.
Note: These changes only impact the timing of when ACK and NACK messages
are sent, and not the basic broadcast link protocol itself, so inter-
operability with nodes using the "classic" algorithms is maintained.
The revised algorithms are as follows:
1) An explicit ACK message is still sent after receiving 16 in-sequence
messages, and implicit ACK information continues to be carried in other
unicast link message headers (including link state messages). However,
the timing of explicit ACKs is now based on the receiving node's absolute
network address rather than its relative network address to ensure that
the failure of another node does not delay the ACK beyond its 16 message
target.
2) A NACK message is now typically sent only when a message gap persists
for two consecutive incoming link state messages; this ensures that a
suspected gap is not confirmed until both LANs in a dual LAN network have
had an opportunity to deliver the message, thereby preventing spurious NACKs.
A NACK message can also be generated by the arrival of a single link state
message, if the deferred queue is so big that the current message gap
cannot be the result of "normal" mis-ordering due to the use of dual LANs
(or one LAN using a bonded interface). Since link state messages typically
arrive at different nodes at different times the problem of multiple nodes
issuing identical NACKs simultaneously is inherently avoided.
3) Nodes continue to "peek" at NACK messages sent by other nodes. If
another node requests retransmission of a message gap suspected (but not
yet confirmed) by the peeking node, the peeking node forgets about the
gap and does not generate a duplicate retransmit request. (If the peeking
node subsequently fails to receive the lost message, later link state
messages will cause it to rediscover and confirm the gap and send another
NACK.)
4) Message gap "equality" is now determined by the start of the gap only.
This is sufficient to deal with the most common cases of message loss,
and eliminates the need for complex end of gap computations.
5) A peeking node no longer tries to determine whether it should send a
complementary NACK, since the most common cases of message loss don't
require it to be sent. Consequently, the node no longer examines the
"broadcast tag" field of a NACK message when peeking.
Signed-off-by: Allan Stephens <allan.stephens@windriver.com>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2011-10-28 01:17:53 +07:00
|
|
|
* @last_sent: sequence # of last b'cast message sent by node
|
|
|
|
* @oos_state: state tracker for handling OOS b'cast messages
|
|
|
|
* @deferred_size: number of OOS b'cast messages in deferred queue
|
2006-01-03 01:04:38 +07:00
|
|
|
* @deferred_head: oldest OOS b'cast message received from node
|
|
|
|
* @deferred_tail: newest OOS b'cast message received from node
|
tipc: message reassembly using fragment chain
When the first fragment of a long data data message is received on a link, a
reassembly buffer large enough to hold the data from this and all subsequent
fragments of the message is allocated. The payload of each new fragment is
copied into this buffer upon arrival. When the last fragment is received, the
reassembled message is delivered upwards to the port/socket layer.
Not only is this an inefficient approach, but it may also cause bursts of
reassembly failures in low memory situations. since we may fail to allocate
the necessary large buffer in the first place. Furthermore, after 100 subsequent
such failures the link will be reset, something that in reality aggravates the
situation.
To remedy this problem, this patch introduces a different approach. Instead of
allocating a big reassembly buffer, we now append the arriving fragments
to a reassembly chain on the link, and deliver the whole chain up to the
socket layer once the last fragment has been received. This is safe because
the retransmission layer of a TIPC link always delivers packets in strict
uninterrupted order, to the reassembly layer as to all other upper layers.
Hence there can never be more than one fragment chain pending reassembly at
any given time in a link, and we can trust (but still verify) that the
fragments will be chained up in the correct order.
Signed-off-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-11-06 15:28:06 +07:00
|
|
|
* @reasm_head: broadcast reassembly queue head from node
|
|
|
|
* @reasm_tail: last broadcast fragment received from node
|
2012-11-16 12:51:30 +07:00
|
|
|
* @recv_permitted: true if node is allowed to receive b'cast messages
|
2006-01-03 01:04:38 +07:00
|
|
|
*/
|
2008-09-03 13:38:32 +07:00
|
|
|
struct tipc_node {
|
2006-01-03 01:04:38 +07:00
|
|
|
u32 addr;
|
|
|
|
spinlock_t lock;
|
2011-02-26 06:42:52 +07:00
|
|
|
struct hlist_node hash;
|
|
|
|
struct list_head list;
|
2006-01-03 01:04:38 +07:00
|
|
|
struct list_head nsub;
|
2011-12-30 08:58:42 +07:00
|
|
|
struct tipc_link *active_links[2];
|
|
|
|
struct tipc_link *links[MAX_BEARERS];
|
2006-01-03 01:04:38 +07:00
|
|
|
int link_cnt;
|
2006-06-26 13:52:50 +07:00
|
|
|
int working_links;
|
tipc: Ensure both nodes recognize loss of contact between them
Enhances TIPC to ensure that a node that loses contact with a
neighboring node does not allow contact to be re-established until
it sees that its peer has also recognized the loss of contact.
Previously, nodes that were connected by two or more links could
encounter a situation in which node A would lose contact with node B
on all of its links, purge its name table of names published by B,
and then fail to repopulate those names once contact with B was restored.
This would happen because B was able to re-establish one or more links
so quickly that it never reached a point where it had no links to A --
meaning that B never saw a loss of contact with A, and consequently
didn't re-publish its names to A.
This problem is now prevented by enhancing the cleanup done by TIPC
following a loss of contact with a neighboring node to ensure that
node A ignores all messages sent by B until it receives a LINK_PROTOCOL
message that indicates B has lost contact with A, thereby preventing
the (re)establishment of links between the nodes. The loss of contact
is recognized when a RESET or ACTIVATE message is received that has
a "redundant link exists" field of 0, indicating that B's sending link
endpoint is in a reset state and that B has no other working links.
Additionally, TIPC now suppresses the sending of (most) link protocol
messages to a neighboring node while it is cleaning up after an earlier
loss of contact with that node. This stops the peer node from prematurely
activating its link endpoint, which would prevent TIPC from later
activating its own end. TIPC still allows outgoing RESET messages to
occur during cleanup, to avoid problems if its own node recognizes
the loss of contact first and tries to notify the peer of the situation.
Finally, TIPC now recognizes an impending loss of contact with a peer node
as soon as it receives a RESET message on a working link that is the
peer's only link to the node, and ensures that the link protocol
suppression mentioned above goes into effect right away -- that is,
even before its own link endpoints have failed. This is necessary to
ensure correct operation when there are redundant links between the nodes,
since otherwise TIPC would send an ACTIVATE message upon receiving a RESET
on its first link and only begin suppressing when a RESET on its second
link was received, instead of initiating suppression with the first RESET
message as it needs to.
Note: The reworked cleanup code also eliminates a check that prevented
a link endpoint's discovery object from responding to incoming messages
while stale name table entries are being purged. This check is now
unnecessary and would have slowed down re-establishment of communication
between the nodes in some situations.
Signed-off-by: Allan Stephens <allan.stephens@windriver.com>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2011-05-27 22:00:51 +07:00
|
|
|
int block_setup;
|
2011-10-29 03:26:41 +07:00
|
|
|
u32 signature;
|
2006-01-03 01:04:38 +07:00
|
|
|
struct {
|
|
|
|
u32 acked;
|
|
|
|
u32 last_in;
|
tipc: Major redesign of broadcast link ACK/NACK algorithms
Completely redesigns broadcast link ACK and NACK mechanisms to prevent
spurious retransmit requests in dual LAN networks, and to prevent the
broadcast link from stalling due to the failure of a receiving node to
acknowledge receiving a broadcast message or request its retransmission.
Note: These changes only impact the timing of when ACK and NACK messages
are sent, and not the basic broadcast link protocol itself, so inter-
operability with nodes using the "classic" algorithms is maintained.
The revised algorithms are as follows:
1) An explicit ACK message is still sent after receiving 16 in-sequence
messages, and implicit ACK information continues to be carried in other
unicast link message headers (including link state messages). However,
the timing of explicit ACKs is now based on the receiving node's absolute
network address rather than its relative network address to ensure that
the failure of another node does not delay the ACK beyond its 16 message
target.
2) A NACK message is now typically sent only when a message gap persists
for two consecutive incoming link state messages; this ensures that a
suspected gap is not confirmed until both LANs in a dual LAN network have
had an opportunity to deliver the message, thereby preventing spurious NACKs.
A NACK message can also be generated by the arrival of a single link state
message, if the deferred queue is so big that the current message gap
cannot be the result of "normal" mis-ordering due to the use of dual LANs
(or one LAN using a bonded interface). Since link state messages typically
arrive at different nodes at different times the problem of multiple nodes
issuing identical NACKs simultaneously is inherently avoided.
3) Nodes continue to "peek" at NACK messages sent by other nodes. If
another node requests retransmission of a message gap suspected (but not
yet confirmed) by the peeking node, the peeking node forgets about the
gap and does not generate a duplicate retransmit request. (If the peeking
node subsequently fails to receive the lost message, later link state
messages will cause it to rediscover and confirm the gap and send another
NACK.)
4) Message gap "equality" is now determined by the start of the gap only.
This is sufficient to deal with the most common cases of message loss,
and eliminates the need for complex end of gap computations.
5) A peeking node no longer tries to determine whether it should send a
complementary NACK, since the most common cases of message loss don't
require it to be sent. Consequently, the node no longer examines the
"broadcast tag" field of a NACK message when peeking.
Signed-off-by: Allan Stephens <allan.stephens@windriver.com>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2011-10-28 01:17:53 +07:00
|
|
|
u32 last_sent;
|
|
|
|
u32 oos_state;
|
|
|
|
u32 deferred_size;
|
2006-01-03 01:04:38 +07:00
|
|
|
struct sk_buff *deferred_head;
|
|
|
|
struct sk_buff *deferred_tail;
|
tipc: message reassembly using fragment chain
When the first fragment of a long data data message is received on a link, a
reassembly buffer large enough to hold the data from this and all subsequent
fragments of the message is allocated. The payload of each new fragment is
copied into this buffer upon arrival. When the last fragment is received, the
reassembled message is delivered upwards to the port/socket layer.
Not only is this an inefficient approach, but it may also cause bursts of
reassembly failures in low memory situations. since we may fail to allocate
the necessary large buffer in the first place. Furthermore, after 100 subsequent
such failures the link will be reset, something that in reality aggravates the
situation.
To remedy this problem, this patch introduces a different approach. Instead of
allocating a big reassembly buffer, we now append the arriving fragments
to a reassembly chain on the link, and deliver the whole chain up to the
socket layer once the last fragment has been received. This is safe because
the retransmission layer of a TIPC link always delivers packets in strict
uninterrupted order, to the reassembly layer as to all other upper layers.
Hence there can never be more than one fragment chain pending reassembly at
any given time in a link, and we can trust (but still verify) that the
fragments will be chained up in the correct order.
Signed-off-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-11-06 15:28:06 +07:00
|
|
|
struct sk_buff *reasm_head;
|
|
|
|
struct sk_buff *reasm_tail;
|
2012-11-16 12:51:30 +07:00
|
|
|
bool recv_permitted;
|
2006-01-03 01:04:38 +07:00
|
|
|
} bclink;
|
|
|
|
};
|
|
|
|
|
2011-02-26 06:42:52 +07:00
|
|
|
extern struct list_head tipc_node_list;
|
|
|
|
|
|
|
|
struct tipc_node *tipc_node_find(u32 addr);
|
2008-09-03 13:38:32 +07:00
|
|
|
struct tipc_node *tipc_node_create(u32 addr);
|
|
|
|
void tipc_node_delete(struct tipc_node *n_ptr);
|
2011-12-30 08:58:42 +07:00
|
|
|
void tipc_node_attach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr);
|
|
|
|
void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr);
|
|
|
|
void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr);
|
|
|
|
void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr);
|
2011-02-28 22:36:21 +07:00
|
|
|
int tipc_node_active_links(struct tipc_node *n_ptr);
|
2008-09-03 13:38:32 +07:00
|
|
|
int tipc_node_is_up(struct tipc_node *n_ptr);
|
2006-01-18 06:38:21 +07:00
|
|
|
struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space);
|
|
|
|
struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space);
|
2006-01-03 01:04:38 +07:00
|
|
|
|
2008-09-03 13:38:32 +07:00
|
|
|
static inline void tipc_node_lock(struct tipc_node *n_ptr)
|
2006-01-03 01:04:38 +07:00
|
|
|
{
|
|
|
|
spin_lock_bh(&n_ptr->lock);
|
|
|
|
}
|
|
|
|
|
2008-09-03 13:38:32 +07:00
|
|
|
static inline void tipc_node_unlock(struct tipc_node *n_ptr)
|
2006-01-03 01:04:38 +07:00
|
|
|
{
|
|
|
|
spin_unlock_bh(&n_ptr->lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
#endif
|