linux/net/tipc/node.h

177 lines
6.2 KiB
C
Raw Normal View History

/*
* net/tipc/node.h: Include file for TIPC node management routines
*
* Copyright (c) 2000-2006, 2014, Ericsson AB
* Copyright (c) 2005, 2010-2014, Wind River Systems
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* 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.
*
* 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
* POSSIBILITY OF SUCH DAMAGE.
*/
#ifndef _TIPC_NODE_H
#define _TIPC_NODE_H
#include "node_subscr.h"
#include "addr.h"
#include "net.h"
#include "bearer.h"
#include "msg.h"
/*
* Out-of-range value for node signature
*/
#define INVALID_NODE_SIG 0x10000
/* 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
* TIPC_NOTIFY_NODE_DOWN: notify node is down
* TIPC_NOTIFY_NODE_UP: notify node is up
* TIPC_DISTRIBUTE_NAME: publish or withdraw link state name type
*/
enum {
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: fix bug in multicast congestion handling One aim of commit 50100a5e39461b2a61d6040e73c384766c29975d ("tipc: use pseudo message to wake up sockets after link congestion") was to handle link congestion abatement in a uniform way for both unicast and multicast transmit. However, the latter doesn't work correctly, and has been broken since the referenced commit was applied. If a user now sends a burst of multicast messages that is big enough to cause broadcast link congestion, it will be put to sleep, and not be waked up when the congestion abates as it should be. This has two reasons. First, the flag that is used, TIPC_WAKEUP_USERS, is set correctly, but in the wrong field. Instead of setting it in the 'action_flags' field of the arrival node struct, it is by mistake set in the dummy node struct that is owned by the broadcast link, where it will never tested for. Second, we cannot use the same flag for waking up unicast and multicast users, since the function tipc_node_unlock() needs to pick the wakeup pseudo messages to deliver from different queues. It must hence be able to distinguish between the two cases. This commit solves this problem by adding a new flag TIPC_WAKEUP_BCAST_USERS, and a new function tipc_bclink_wakeup_user(). The latter is to be called by tipc_node_unlock() when the named flag, now set in the correct field, is encountered. v2: using explicit 'unsigned int' declaration instead of 'uint', as per comment from David Miller. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-07 18:12:34 +00:00
TIPC_WAKEUP_USERS = (1 << 5),
TIPC_WAKEUP_BCAST_USERS = (1 << 6),
TIPC_NOTIFY_LINK_UP = (1 << 7),
TIPC_NOTIFY_LINK_DOWN = (1 << 8)
};
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 15:00:51 +00:00
/**
* struct tipc_node_bclink - TIPC node bclink structure
* @acked: sequence # of last outbound b'cast message acknowledged by node
* @last_in: sequence # of last in-sequence b'cast message received from node
* @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
* @deferred_head: oldest OOS b'cast message received from node
* @deferred_tail: newest OOS b'cast message received from node
* @reasm_buf: broadcast reassembly queue head from node
* @recv_permitted: true if node is allowed to receive b'cast messages
*/
struct tipc_node_bclink {
u32 acked;
u32 last_in;
u32 last_sent;
u32 oos_state;
u32 deferred_size;
struct sk_buff *deferred_head;
struct sk_buff *deferred_tail;
struct sk_buff *reasm_buf;
bool recv_permitted;
};
/**
* struct tipc_node - TIPC node structure
* @addr: network address of node
* @lock: spinlock governing access to structure
* @hash: links to adjacent nodes in unsorted hash chain
* @active_links: pointers to active links to node
* @links: pointers to all links to node
* @action_flags: bit mask of different types of node actions
* @bclink: broadcast-related info
* @list: links to adjacent nodes in sorted list of cluster's nodes
* @working_links: number of working links to node (both active and standby)
* @link_cnt: number of links to node
* @signature: node instance identifier
* @link_id: local and remote bearer ids of changing link, if any
* @nsub: list of "node down" subscriptions monitoring node
* @rcu: rcu struct for tipc_node
*/
struct tipc_node {
u32 addr;
spinlock_t lock;
struct hlist_node hash;
struct tipc_link *active_links[2];
u32 act_mtus[2];
struct tipc_link *links[MAX_BEARERS];
unsigned int action_flags;
struct tipc_node_bclink bclink;
struct list_head list;
int link_cnt;
int working_links;
u32 signature;
u32 link_id;
struct list_head nsub;
struct sk_buff_head waiting_sks;
tipc: use message to abort connections when losing contact to node In the current implementation, each 'struct tipc_node' instance keeps a linked list of those ports/sockets that are connected to the node represented by that struct. The purpose of this is to let the node object know which sockets to alert when it loses contact with its peer node, i.e., which sockets need to have their connections aborted. This entails an unwanted direct reference from the node structure back to the port/socket structure, and a need to grab port_lock when we have to make an upcall to the port. We want to get rid of this unecessary BH entry point into the socket, and also eliminate its use of port_lock. In this commit, we instead let the node struct keep list of "connected socket" structs, which each represents a connected socket, but is allocated independently by the node at the moment of connection. If the node loses contact with its peer node, the list is traversed, and a "connection abort" message is created for each entry in the list. The message is sent to it respective connected socket using the ordinary data path, and the receiving socket aborts its connections upon reception of the message. This enables us to get rid of the direct reference from 'struct node' to ´struct port', and another unwanted BH access point to the latter. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Reviewed-by: Erik Hugne <erik.hugne@ericsson.com> Reviewed-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-08-22 22:09:08 +00:00
struct list_head conn_sks;
struct rcu_head rcu;
};
extern struct list_head tipc_node_list;
struct tipc_node *tipc_node_find(u32 addr);
struct tipc_node *tipc_node_create(u32 addr);
void tipc_node_stop(void);
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);
int tipc_node_active_links(struct tipc_node *n_ptr);
int tipc_node_is_up(struct tipc_node *n_ptr);
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);
int tipc_node_get_linkname(u32 bearer_id, u32 node, char *linkname, size_t len);
void tipc_node_unlock(struct tipc_node *node);
tipc: use message to abort connections when losing contact to node In the current implementation, each 'struct tipc_node' instance keeps a linked list of those ports/sockets that are connected to the node represented by that struct. The purpose of this is to let the node object know which sockets to alert when it loses contact with its peer node, i.e., which sockets need to have their connections aborted. This entails an unwanted direct reference from the node structure back to the port/socket structure, and a need to grab port_lock when we have to make an upcall to the port. We want to get rid of this unecessary BH entry point into the socket, and also eliminate its use of port_lock. In this commit, we instead let the node struct keep list of "connected socket" structs, which each represents a connected socket, but is allocated independently by the node at the moment of connection. If the node loses contact with its peer node, the list is traversed, and a "connection abort" message is created for each entry in the list. The message is sent to it respective connected socket using the ordinary data path, and the receiving socket aborts its connections upon reception of the message. This enables us to get rid of the direct reference from 'struct node' to ´struct port', and another unwanted BH access point to the latter. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Reviewed-by: Erik Hugne <erik.hugne@ericsson.com> Reviewed-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-08-22 22:09:08 +00:00
int tipc_node_add_conn(u32 dnode, u32 port, u32 peer_port);
void tipc_node_remove_conn(u32 dnode, u32 port);
int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb);
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));
}
static inline uint tipc_node_get_mtu(u32 addr, u32 selector)
{
struct tipc_node *node;
u32 mtu;
node = tipc_node_find(addr);
if (likely(node))
mtu = node->act_mtus[selector & 1];
else
mtu = MAX_MSG_SIZE;
return mtu;
}
#endif