alistair23-linux/net/tipc/core.c

192 lines
5 KiB
C
Raw Normal View History

/*
* net/tipc/core.c: TIPC module code
*
* Copyright (c) 2003-2006, Ericsson AB
tipc: convert topology server to use new server facility As the new TIPC server infrastructure has been introduced, we can now convert the TIPC topology server to it. We get two benefits from doing this: 1) It simplifies the topology server locking policy. In the original locking policy, we placed one spin lock pointer in the tipc_subscriber structure to reuse the lock of the subscriber's server port, controlling access to members of tipc_subscriber instance. That is, we only used one lock to ensure both tipc_port and tipc_subscriber members were safely accessed. Now we introduce another spin lock for tipc_subscriber structure only protecting themselves, to get a finer granularity locking policy. Moreover, the change will allow us to make the topology server code more readable and maintainable. 2) It fixes a bug where sent subscription events may be lost when the topology port is congested. Using the new service, the topology server now queues sent events into an outgoing buffer, and then wakes up a sender process which has been blocked in workqueue context. The process will keep picking events from the buffer and send them to their respective subscribers, using the kernel socket interface, until the buffer is empty. Even if the socket is congested during transmission there is no risk that events may be dropped, since the sender process may block when needed. Some minor reordering of initialization is done, since we now have a scenario where the topology server must be started after socket initialization has taken place, as the former depends on the latter. And overall, we see a simplification of the TIPC subscriber code in making this changeover. Signed-off-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-17 08:54:40 -06:00
* Copyright (c) 2005-2006, 2010-2013, 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.
*/
#include "core.h"
#include "ref.h"
#include "name_table.h"
#include "subscr.h"
#include "config.h"
#include "port.h"
#include <linux/module.h>
/* global variables used by multiple sub-systems within TIPC */
int tipc_random __read_mostly;
/* configurable TIPC parameters */
u32 tipc_own_addr __read_mostly;
int tipc_max_ports __read_mostly;
int tipc_net_id __read_mostly;
int tipc_remote_management __read_mostly;
int sysctl_tipc_rmem[3] __read_mostly; /* min/default/max */
/**
* tipc_buf_acquire - creates a TIPC message buffer
* @size: message size (including TIPC header)
*
* Returns a new buffer with data pointers set to the specified size.
*
* NOTE: Headroom is reserved to allow prepending of a data link header.
* There may also be unrequested tailroom present at the buffer's end.
*/
struct sk_buff *tipc_buf_acquire(u32 size)
{
struct sk_buff *skb;
unsigned int buf_size = (BUF_HEADROOM + size + 3) & ~3u;
skb = alloc_skb_fclone(buf_size, GFP_ATOMIC);
if (skb) {
skb_reserve(skb, BUF_HEADROOM);
skb_put(skb, size);
skb->next = NULL;
}
return skb;
}
/**
* tipc_core_stop_net - shut down TIPC networking sub-systems
*/
static void tipc_core_stop_net(void)
{
tipc_net_stop();
tipc_eth_media_stop();
tipc: add InfiniBand media type Add InfiniBand media type based on the ethernet media type. The only real difference is that in case of InfiniBand, we need the entire 20 bytes of space reserved for media addresses, so the TIPC media type ID is not explicitly stored in the packet payload. Sample output of tipc-config: # tipc-config -v -addr -netid -nt=all -p -m -b -n -ls node address: <10.1.4> current network id: 4711 Type Lower Upper Port Identity Publication Scope 0 167776257 167776257 <10.1.1:1855512577> 1855512578 cluster 167776260 167776260 <10.1.4:1216454657> 1216454658 zone 1 1 1 <10.1.4:1216479235> 1216479236 node Ports: 1216479235: bound to {1,1} 1216454657: bound to {0,167776260} Media: eth ib Bearers: ib:ib0 Nodes known: <10.1.1>: up Link <broadcast-link> Window:20 packets RX packets:0 fragments:0/0 bundles:0/0 TX packets:0 fragments:0/0 bundles:0/0 RX naks:0 defs:0 dups:0 TX naks:0 acks:0 dups:0 Congestion bearer:0 link:0 Send queue max:0 avg:0 Link <10.1.4:ib0-10.1.1:ib0> ACTIVE MTU:2044 Priority:10 Tolerance:1500 ms Window:50 packets RX packets:80 fragments:0/0 bundles:0/0 TX packets:40 fragments:0/0 bundles:0/0 TX profile sample:22 packets average:54 octets 0-64:100% -256:0% -1024:0% -4096:0% -16384:0% -32768:0% -66000:0% RX states:410 probes:213 naks:0 defs:0 dups:0 TX states:410 probes:197 naks:0 acks:0 dups:0 Congestion bearer:0 link:0 Send queue max:1 avg:0 Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-04-17 00:18:28 -06:00
tipc_ib_media_stop();
}
/**
* start_net - start TIPC networking sub-systems
*/
int tipc_core_start_net(unsigned long addr)
{
int res;
tipc_net_start(addr);
res = tipc_eth_media_start();
tipc: add InfiniBand media type Add InfiniBand media type based on the ethernet media type. The only real difference is that in case of InfiniBand, we need the entire 20 bytes of space reserved for media addresses, so the TIPC media type ID is not explicitly stored in the packet payload. Sample output of tipc-config: # tipc-config -v -addr -netid -nt=all -p -m -b -n -ls node address: <10.1.4> current network id: 4711 Type Lower Upper Port Identity Publication Scope 0 167776257 167776257 <10.1.1:1855512577> 1855512578 cluster 167776260 167776260 <10.1.4:1216454657> 1216454658 zone 1 1 1 <10.1.4:1216479235> 1216479236 node Ports: 1216479235: bound to {1,1} 1216454657: bound to {0,167776260} Media: eth ib Bearers: ib:ib0 Nodes known: <10.1.1>: up Link <broadcast-link> Window:20 packets RX packets:0 fragments:0/0 bundles:0/0 TX packets:0 fragments:0/0 bundles:0/0 RX naks:0 defs:0 dups:0 TX naks:0 acks:0 dups:0 Congestion bearer:0 link:0 Send queue max:0 avg:0 Link <10.1.4:ib0-10.1.1:ib0> ACTIVE MTU:2044 Priority:10 Tolerance:1500 ms Window:50 packets RX packets:80 fragments:0/0 bundles:0/0 TX packets:40 fragments:0/0 bundles:0/0 TX profile sample:22 packets average:54 octets 0-64:100% -256:0% -1024:0% -4096:0% -16384:0% -32768:0% -66000:0% RX states:410 probes:213 naks:0 defs:0 dups:0 TX states:410 probes:197 naks:0 acks:0 dups:0 Congestion bearer:0 link:0 Send queue max:1 avg:0 Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-04-17 00:18:28 -06:00
if (res < 0)
goto err;
res = tipc_ib_media_start();
if (res < 0)
goto err;
return res;
err:
tipc_core_stop_net();
return res;
}
/**
* tipc_core_stop - switch TIPC from SINGLE NODE to NOT RUNNING mode
*/
static void tipc_core_stop(void)
{
tipc_netlink_stop();
tipc_handler_stop();
tipc_cfg_stop();
tipc_subscr_stop();
tipc_nametbl_stop();
tipc_ref_table_stop();
tipc_socket_stop();
tipc_unregister_sysctl();
}
/**
* tipc_core_start - switch TIPC from NOT RUNNING to SINGLE NODE mode
*/
static int tipc_core_start(void)
{
int res;
get_random_bytes(&tipc_random, sizeof(tipc_random));
res = tipc_handler_start();
if (!res)
res = tipc_ref_table_init(tipc_max_ports, tipc_random);
if (!res)
res = tipc_nametbl_init();
if (!res)
res = tipc_netlink_start();
if (!res)
res = tipc_socket_init();
if (!res)
res = tipc_register_sysctl();
tipc: convert topology server to use new server facility As the new TIPC server infrastructure has been introduced, we can now convert the TIPC topology server to it. We get two benefits from doing this: 1) It simplifies the topology server locking policy. In the original locking policy, we placed one spin lock pointer in the tipc_subscriber structure to reuse the lock of the subscriber's server port, controlling access to members of tipc_subscriber instance. That is, we only used one lock to ensure both tipc_port and tipc_subscriber members were safely accessed. Now we introduce another spin lock for tipc_subscriber structure only protecting themselves, to get a finer granularity locking policy. Moreover, the change will allow us to make the topology server code more readable and maintainable. 2) It fixes a bug where sent subscription events may be lost when the topology port is congested. Using the new service, the topology server now queues sent events into an outgoing buffer, and then wakes up a sender process which has been blocked in workqueue context. The process will keep picking events from the buffer and send them to their respective subscribers, using the kernel socket interface, until the buffer is empty. Even if the socket is congested during transmission there is no risk that events may be dropped, since the sender process may block when needed. Some minor reordering of initialization is done, since we now have a scenario where the topology server must be started after socket initialization has taken place, as the former depends on the latter. And overall, we see a simplification of the TIPC subscriber code in making this changeover. Signed-off-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-17 08:54:40 -06:00
if (!res)
res = tipc_subscr_start();
if (!res)
res = tipc_cfg_init();
if (res)
tipc_core_stop();
return res;
}
static int __init tipc_init(void)
{
int res;
pr_info("Activated (version " TIPC_MOD_VER ")\n");
tipc_own_addr = 0;
tipc_remote_management = 1;
tipc_max_ports = CONFIG_TIPC_PORTS;
tipc_net_id = 4711;
sysctl_tipc_rmem[0] = CONN_OVERLOAD_LIMIT >> 4 << TIPC_LOW_IMPORTANCE;
sysctl_tipc_rmem[1] = CONN_OVERLOAD_LIMIT >> 4 <<
TIPC_CRITICAL_IMPORTANCE;
sysctl_tipc_rmem[2] = CONN_OVERLOAD_LIMIT;
res = tipc_core_start();
if (res)
pr_err("Unable to start in single node mode\n");
else
pr_info("Started in single node mode\n");
return res;
}
static void __exit tipc_exit(void)
{
tipc_core_stop_net();
tipc_core_stop();
pr_info("Deactivated\n");
}
module_init(tipc_init);
module_exit(tipc_exit);
MODULE_DESCRIPTION("TIPC: Transparent Inter Process Communication");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_VERSION(TIPC_MOD_VER);