linux/net/tipc/bearer.c

1285 lines
30 KiB
C
Raw Normal View History

/*
* net/tipc/bearer.c: TIPC bearer code
*
tipc: add neighbor monitoring framework TIPC based clusters are by default set up with full-mesh link connectivity between all nodes. Those links are expected to provide a short failure detection time, by default set to 1500 ms. Because of this, the background load for neighbor monitoring in an N-node cluster increases with a factor N on each node, while the overall monitoring traffic through the network infrastructure increases at a ~(N * (N - 1)) rate. Experience has shown that such clusters don't scale well beyond ~100 nodes unless we significantly increase failure discovery tolerance. This commit introduces a framework and an algorithm that drastically reduces this background load, while basically maintaining the original failure detection times across the whole cluster. Using this algorithm, background load will now grow at a rate of ~(2 * sqrt(N)) per node, and at ~(2 * N * sqrt(N)) in traffic overhead. As an example, each node will now have to actively monitor 38 neighbors in a 400-node cluster, instead of as before 399. This "Overlapping Ring Supervision Algorithm" is completely distributed and employs no centralized or coordinated state. It goes as follows: - Each node makes up a linearly ascending, circular list of all its N known neighbors, based on their TIPC node identity. This algorithm must be the same on all nodes. - The node then selects the next M = sqrt(N) - 1 nodes downstream from itself in the list, and chooses to actively monitor those. This is called its "local monitoring domain". - It creates a domain record describing the monitoring domain, and piggy-backs this in the data area of all neighbor monitoring messages (LINK_PROTOCOL/STATE) leaving that node. This means that all nodes in the cluster eventually (default within 400 ms) will learn about its monitoring domain. - Whenever a node discovers a change in its local domain, e.g., a node has been added or has gone down, it creates and sends out a new version of its node record to inform all neighbors about the change. - A node receiving a domain record from anybody outside its local domain matches this against its own list (which may not look the same), and chooses to not actively monitor those members of the received domain record that are also present in its own list. Instead, it relies on indications from the direct monitoring nodes if an indirectly monitored node has gone up or down. If a node is indicated lost, the receiving node temporarily activates its own direct monitoring towards that node in order to confirm, or not, that it is actually gone. - Since each node is actively monitoring sqrt(N) downstream neighbors, each node is also actively monitored by the same number of upstream neighbors. This means that all non-direct monitoring nodes normally will receive sqrt(N) indications that a node is gone. - A major drawback with ring monitoring is how it handles failures that cause massive network partitionings. If both a lost node and all its direct monitoring neighbors are inside the lost partition, the nodes in the remaining partition will never receive indications about the loss. To overcome this, each node also chooses to actively monitor some nodes outside its local domain. Those nodes are called remote domain "heads", and are selected in such a way that no node in the cluster will be more than two direct monitoring hops away. Because of this, each node, apart from monitoring the member of its local domain, will also typically monitor sqrt(N) remote head nodes. - As an optimization, local list status, domain status and domain records are marked with a generation number. This saves senders from unnecessarily conveying unaltered domain records, and receivers from performing unneeded re-adaptations of their node monitoring list, such as re-assigning domain heads. - As a measure of caution we have added the possibility to disable the new algorithm through configuration. We do this by keeping a threshold value for the cluster size; a cluster that grows beyond this value will switch from full-mesh to ring monitoring, and vice versa when it shrinks below the value. This means that if the threshold is set to a value larger than any anticipated cluster size (default size is 32) the new algorithm is effectively disabled. A patch set for altering the threshold value and for listing the table contents will follow shortly. - This change is fully backwards compatible. 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>
2016-06-14 00:46:22 +00:00
* Copyright (c) 1996-2006, 2013-2016, Ericsson AB
* Copyright (c) 2004-2006, 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 <net/sock.h>
#include "core.h"
#include "bearer.h"
#include "link.h"
#include "discover.h"
tipc: add neighbor monitoring framework TIPC based clusters are by default set up with full-mesh link connectivity between all nodes. Those links are expected to provide a short failure detection time, by default set to 1500 ms. Because of this, the background load for neighbor monitoring in an N-node cluster increases with a factor N on each node, while the overall monitoring traffic through the network infrastructure increases at a ~(N * (N - 1)) rate. Experience has shown that such clusters don't scale well beyond ~100 nodes unless we significantly increase failure discovery tolerance. This commit introduces a framework and an algorithm that drastically reduces this background load, while basically maintaining the original failure detection times across the whole cluster. Using this algorithm, background load will now grow at a rate of ~(2 * sqrt(N)) per node, and at ~(2 * N * sqrt(N)) in traffic overhead. As an example, each node will now have to actively monitor 38 neighbors in a 400-node cluster, instead of as before 399. This "Overlapping Ring Supervision Algorithm" is completely distributed and employs no centralized or coordinated state. It goes as follows: - Each node makes up a linearly ascending, circular list of all its N known neighbors, based on their TIPC node identity. This algorithm must be the same on all nodes. - The node then selects the next M = sqrt(N) - 1 nodes downstream from itself in the list, and chooses to actively monitor those. This is called its "local monitoring domain". - It creates a domain record describing the monitoring domain, and piggy-backs this in the data area of all neighbor monitoring messages (LINK_PROTOCOL/STATE) leaving that node. This means that all nodes in the cluster eventually (default within 400 ms) will learn about its monitoring domain. - Whenever a node discovers a change in its local domain, e.g., a node has been added or has gone down, it creates and sends out a new version of its node record to inform all neighbors about the change. - A node receiving a domain record from anybody outside its local domain matches this against its own list (which may not look the same), and chooses to not actively monitor those members of the received domain record that are also present in its own list. Instead, it relies on indications from the direct monitoring nodes if an indirectly monitored node has gone up or down. If a node is indicated lost, the receiving node temporarily activates its own direct monitoring towards that node in order to confirm, or not, that it is actually gone. - Since each node is actively monitoring sqrt(N) downstream neighbors, each node is also actively monitored by the same number of upstream neighbors. This means that all non-direct monitoring nodes normally will receive sqrt(N) indications that a node is gone. - A major drawback with ring monitoring is how it handles failures that cause massive network partitionings. If both a lost node and all its direct monitoring neighbors are inside the lost partition, the nodes in the remaining partition will never receive indications about the loss. To overcome this, each node also chooses to actively monitor some nodes outside its local domain. Those nodes are called remote domain "heads", and are selected in such a way that no node in the cluster will be more than two direct monitoring hops away. Because of this, each node, apart from monitoring the member of its local domain, will also typically monitor sqrt(N) remote head nodes. - As an optimization, local list status, domain status and domain records are marked with a generation number. This saves senders from unnecessarily conveying unaltered domain records, and receivers from performing unneeded re-adaptations of their node monitoring list, such as re-assigning domain heads. - As a measure of caution we have added the possibility to disable the new algorithm through configuration. We do this by keeping a threshold value for the cluster size; a cluster that grows beyond this value will switch from full-mesh to ring monitoring, and vice versa when it shrinks below the value. This means that if the threshold is set to a value larger than any anticipated cluster size (default size is 32) the new algorithm is effectively disabled. A patch set for altering the threshold value and for listing the table contents will follow shortly. - This change is fully backwards compatible. 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>
2016-06-14 00:46:22 +00:00
#include "monitor.h"
#include "bcast.h"
#include "netlink.h"
#include "udp_media.h"
#include "trace.h"
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 06:18:28 +00:00
#define MAX_ADDR_STR 60
static struct tipc_media * const media_info_array[] = {
&eth_media_info,
#ifdef CONFIG_TIPC_MEDIA_IB
&ib_media_info,
#endif
#ifdef CONFIG_TIPC_MEDIA_UDP
&udp_media_info,
#endif
NULL
};
static struct tipc_bearer *bearer_get(struct net *net, int bearer_id)
{
struct tipc_net *tn = tipc_net(net);
return rcu_dereference(tn->bearer_list[bearer_id]);
}
static void bearer_disable(struct net *net, struct tipc_bearer *b);
static int tipc_l2_rcv_msg(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev);
/**
* tipc_media_find - locates specified media object by name
*/
struct tipc_media *tipc_media_find(const char *name)
{
u32 i;
for (i = 0; media_info_array[i] != NULL; i++) {
if (!strcmp(media_info_array[i]->name, name))
break;
}
return media_info_array[i];
}
/**
* media_find_id - locates specified media object by type identifier
*/
static struct tipc_media *media_find_id(u8 type)
{
u32 i;
for (i = 0; media_info_array[i] != NULL; i++) {
if (media_info_array[i]->type_id == type)
break;
}
return media_info_array[i];
}
/**
* tipc_media_addr_printf - record media address in print buffer
*/
tipc: enable tracepoints in tipc As for the sake of debugging/tracing, the commit enables tracepoints in TIPC along with some general trace_events as shown below. It also defines some 'tipc_*_dump()' functions that allow to dump TIPC object data whenever needed, that is, for general debug purposes, ie. not just for the trace_events. The following trace_events are now available: - trace_tipc_skb_dump(): allows to trace and dump TIPC msg & skb data, e.g. message type, user, droppable, skb truesize, cloned skb, etc. - trace_tipc_list_dump(): allows to trace and dump any TIPC buffers or queues, e.g. TIPC link transmq, socket receive queue, etc. - trace_tipc_sk_dump(): allows to trace and dump TIPC socket data, e.g. sk state, sk type, connection type, rmem_alloc, socket queues, etc. - trace_tipc_link_dump(): allows to trace and dump TIPC link data, e.g. link state, silent_intv_cnt, gap, bc_gap, link queues, etc. - trace_tipc_node_dump(): allows to trace and dump TIPC node data, e.g. node state, active links, capabilities, link entries, etc. How to use: Put the trace functions at any places where we want to dump TIPC data or events. Note: a) The dump functions will generate raw data only, that is, to offload the trace event's processing, it can require a tool or script to parse the data but this should be simple. b) The trace_tipc_*_dump() should be reserved for a failure cases only (e.g. the retransmission failure case) or where we do not expect to happen too often, then we can consider enabling these events by default since they will almost not take any effects under normal conditions, but once the rare condition or failure occurs, we get the dumped data fully for post-analysis. For other trace purposes, we can reuse these trace classes as template but different events. c) A trace_event is only effective when we enable it. To enable the TIPC trace_events, echo 1 to 'enable' files in the events/tipc/ directory in the 'debugfs' file system. Normally, they are located at: /sys/kernel/debug/tracing/events/tipc/ For example: To enable the tipc_link_dump event: echo 1 > /sys/kernel/debug/tracing/events/tipc/tipc_link_dump/enable To enable all the TIPC trace_events: echo 1 > /sys/kernel/debug/tracing/events/tipc/enable To collect the trace data: cat trace or cat trace_pipe > /trace.out & To disable all the TIPC trace_events: echo 0 > /sys/kernel/debug/tracing/events/tipc/enable To clear the trace buffer: echo > trace d) Like the other trace_events, the feature like 'filter' or 'trigger' is also usable for the tipc trace_events. For more details, have a look at: Documentation/trace/ftrace.txt MAINTAINERS | add two new files 'trace.h' & 'trace.c' in tipc Acked-by: Ying Xue <ying.xue@windriver.com> Tested-by: Ying Xue <ying.xue@windriver.com> 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>
2018-12-19 02:17:56 +00:00
int tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a)
{
char addr_str[MAX_ADDR_STR];
struct tipc_media *m;
tipc: phase out most of the struct print_buf usage The tipc_printf is renamed to tipc_snprintf, as the new name describes more what the function actually does. It is also changed to take a buffer and length parameter and return number of characters written to the buffer. All callers of this function that used to pass a print_buf are updated. Final removal of the struct print_buf itself will be done synchronously with the pending removal of the deprecated logging code that also was using it. Functions that build up a response message with a list of ports, nametable contents etc. are changed to return the number of characters written to the output buffer. This information was previously hidden in a field of the print_buf struct, and the number of chars written was fetched with a call to tipc_printbuf_validate. This function is removed since it is no longer referenced nor needed. A generic max size ULTRA_STRING_MAX_LEN is defined, named in keeping with the existing TIPC_TLV_ULTRA_STRING, and the various definitions in port, link and nametable code that largely duplicated this information are removed. This means that amount of link statistics that can be returned is now increased from 2k to 32k. The buffer overflow check is now done just before the reply message is passed over netlink or TIPC to a remote node and the message indicating a truncated buffer is changed to a less dramatic one (less CAPS), placed at the end of the message. Signed-off-by: Erik Hugne <erik.hugne@ericsson.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2012-06-29 04:50:23 +00:00
int ret;
m = media_find_id(a->media_id);
if (m && !m->addr2str(a, addr_str, sizeof(addr_str)))
ret = scnprintf(buf, len, "%s(%s)", m->name, addr_str);
else {
u32 i;
ret = scnprintf(buf, len, "UNKNOWN(%u)", a->media_id);
for (i = 0; i < sizeof(a->value); i++)
tipc: enable tracepoints in tipc As for the sake of debugging/tracing, the commit enables tracepoints in TIPC along with some general trace_events as shown below. It also defines some 'tipc_*_dump()' functions that allow to dump TIPC object data whenever needed, that is, for general debug purposes, ie. not just for the trace_events. The following trace_events are now available: - trace_tipc_skb_dump(): allows to trace and dump TIPC msg & skb data, e.g. message type, user, droppable, skb truesize, cloned skb, etc. - trace_tipc_list_dump(): allows to trace and dump any TIPC buffers or queues, e.g. TIPC link transmq, socket receive queue, etc. - trace_tipc_sk_dump(): allows to trace and dump TIPC socket data, e.g. sk state, sk type, connection type, rmem_alloc, socket queues, etc. - trace_tipc_link_dump(): allows to trace and dump TIPC link data, e.g. link state, silent_intv_cnt, gap, bc_gap, link queues, etc. - trace_tipc_node_dump(): allows to trace and dump TIPC node data, e.g. node state, active links, capabilities, link entries, etc. How to use: Put the trace functions at any places where we want to dump TIPC data or events. Note: a) The dump functions will generate raw data only, that is, to offload the trace event's processing, it can require a tool or script to parse the data but this should be simple. b) The trace_tipc_*_dump() should be reserved for a failure cases only (e.g. the retransmission failure case) or where we do not expect to happen too often, then we can consider enabling these events by default since they will almost not take any effects under normal conditions, but once the rare condition or failure occurs, we get the dumped data fully for post-analysis. For other trace purposes, we can reuse these trace classes as template but different events. c) A trace_event is only effective when we enable it. To enable the TIPC trace_events, echo 1 to 'enable' files in the events/tipc/ directory in the 'debugfs' file system. Normally, they are located at: /sys/kernel/debug/tracing/events/tipc/ For example: To enable the tipc_link_dump event: echo 1 > /sys/kernel/debug/tracing/events/tipc/tipc_link_dump/enable To enable all the TIPC trace_events: echo 1 > /sys/kernel/debug/tracing/events/tipc/enable To collect the trace data: cat trace or cat trace_pipe > /trace.out & To disable all the TIPC trace_events: echo 0 > /sys/kernel/debug/tracing/events/tipc/enable To clear the trace buffer: echo > trace d) Like the other trace_events, the feature like 'filter' or 'trigger' is also usable for the tipc trace_events. For more details, have a look at: Documentation/trace/ftrace.txt MAINTAINERS | add two new files 'trace.h' & 'trace.c' in tipc Acked-by: Ying Xue <ying.xue@windriver.com> Tested-by: Ying Xue <ying.xue@windriver.com> 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>
2018-12-19 02:17:56 +00:00
ret += scnprintf(buf + ret, len - ret,
"-%x", a->value[i]);
}
tipc: enable tracepoints in tipc As for the sake of debugging/tracing, the commit enables tracepoints in TIPC along with some general trace_events as shown below. It also defines some 'tipc_*_dump()' functions that allow to dump TIPC object data whenever needed, that is, for general debug purposes, ie. not just for the trace_events. The following trace_events are now available: - trace_tipc_skb_dump(): allows to trace and dump TIPC msg & skb data, e.g. message type, user, droppable, skb truesize, cloned skb, etc. - trace_tipc_list_dump(): allows to trace and dump any TIPC buffers or queues, e.g. TIPC link transmq, socket receive queue, etc. - trace_tipc_sk_dump(): allows to trace and dump TIPC socket data, e.g. sk state, sk type, connection type, rmem_alloc, socket queues, etc. - trace_tipc_link_dump(): allows to trace and dump TIPC link data, e.g. link state, silent_intv_cnt, gap, bc_gap, link queues, etc. - trace_tipc_node_dump(): allows to trace and dump TIPC node data, e.g. node state, active links, capabilities, link entries, etc. How to use: Put the trace functions at any places where we want to dump TIPC data or events. Note: a) The dump functions will generate raw data only, that is, to offload the trace event's processing, it can require a tool or script to parse the data but this should be simple. b) The trace_tipc_*_dump() should be reserved for a failure cases only (e.g. the retransmission failure case) or where we do not expect to happen too often, then we can consider enabling these events by default since they will almost not take any effects under normal conditions, but once the rare condition or failure occurs, we get the dumped data fully for post-analysis. For other trace purposes, we can reuse these trace classes as template but different events. c) A trace_event is only effective when we enable it. To enable the TIPC trace_events, echo 1 to 'enable' files in the events/tipc/ directory in the 'debugfs' file system. Normally, they are located at: /sys/kernel/debug/tracing/events/tipc/ For example: To enable the tipc_link_dump event: echo 1 > /sys/kernel/debug/tracing/events/tipc/tipc_link_dump/enable To enable all the TIPC trace_events: echo 1 > /sys/kernel/debug/tracing/events/tipc/enable To collect the trace data: cat trace or cat trace_pipe > /trace.out & To disable all the TIPC trace_events: echo 0 > /sys/kernel/debug/tracing/events/tipc/enable To clear the trace buffer: echo > trace d) Like the other trace_events, the feature like 'filter' or 'trigger' is also usable for the tipc trace_events. For more details, have a look at: Documentation/trace/ftrace.txt MAINTAINERS | add two new files 'trace.h' & 'trace.c' in tipc Acked-by: Ying Xue <ying.xue@windriver.com> Tested-by: Ying Xue <ying.xue@windriver.com> 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>
2018-12-19 02:17:56 +00:00
return ret;
}
/**
* bearer_name_validate - validate & (optionally) deconstruct bearer name
* @name: ptr to bearer name string
* @name_parts: ptr to area for bearer name components (or NULL if not needed)
*
* Returns 1 if bearer name is valid, otherwise 0.
*/
static int bearer_name_validate(const char *name,
struct tipc_bearer_names *name_parts)
{
char name_copy[TIPC_MAX_BEARER_NAME];
char *media_name;
char *if_name;
u32 media_len;
u32 if_len;
/* copy bearer name & ensure length is OK */
name_copy[TIPC_MAX_BEARER_NAME - 1] = 0;
/* need above in case non-Posix strncpy() doesn't pad with nulls */
strncpy(name_copy, name, TIPC_MAX_BEARER_NAME);
if (name_copy[TIPC_MAX_BEARER_NAME - 1] != 0)
return 0;
/* ensure all component parts of bearer name are present */
media_name = name_copy;
if_name = strchr(media_name, ':');
if (if_name == NULL)
return 0;
*(if_name++) = 0;
media_len = if_name - media_name;
if_len = strlen(if_name) + 1;
/* validate component parts of bearer name */
if ((media_len <= 1) || (media_len > TIPC_MAX_MEDIA_NAME) ||
(if_len <= 1) || (if_len > TIPC_MAX_IF_NAME))
return 0;
/* return bearer name components, if necessary */
if (name_parts) {
strcpy(name_parts->media_name, media_name);
strcpy(name_parts->if_name, if_name);
}
return 1;
}
/**
* tipc_bearer_find - locates bearer object with matching bearer name
*/
struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name)
{
struct tipc_net *tn = net_generic(net, tipc_net_id);
struct tipc_bearer *b;
u32 i;
for (i = 0; i < MAX_BEARERS; i++) {
b = rtnl_dereference(tn->bearer_list[i]);
if (b && (!strcmp(b->name, name)))
return b;
}
return NULL;
}
/* tipc_bearer_get_name - get the bearer name from its id.
* @net: network namespace
* @name: a pointer to the buffer where the name will be stored.
* @bearer_id: the id to get the name from.
*/
int tipc_bearer_get_name(struct net *net, char *name, u32 bearer_id)
{
struct tipc_net *tn = tipc_net(net);
struct tipc_bearer *b;
if (bearer_id >= MAX_BEARERS)
return -EINVAL;
b = rtnl_dereference(tn->bearer_list[bearer_id]);
if (!b)
return -EINVAL;
strcpy(name, b->name);
return 0;
}
void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest)
{
struct tipc_net *tn = net_generic(net, tipc_net_id);
struct tipc_bearer *b;
rcu_read_lock();
b = rcu_dereference(tn->bearer_list[bearer_id]);
if (b)
tipc_disc_add_dest(b->disc);
rcu_read_unlock();
}
void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest)
{
struct tipc_net *tn = net_generic(net, tipc_net_id);
struct tipc_bearer *b;
rcu_read_lock();
b = rcu_dereference(tn->bearer_list[bearer_id]);
if (b)
tipc_disc_remove_dest(b->disc);
rcu_read_unlock();
}
/**
* tipc_enable_bearer - enable bearer with the given name
*/
static int tipc_enable_bearer(struct net *net, const char *name,
u32 disc_domain, u32 prio,
struct nlattr *attr[])
{
struct tipc_net *tn = tipc_net(net);
struct tipc_bearer_names b_names;
int with_this_prio = 1;
struct tipc_bearer *b;
struct tipc_media *m;
struct sk_buff *skb;
int bearer_id = 0;
int res = -EINVAL;
char *errstr = "";
if (!bearer_name_validate(name, &b_names)) {
errstr = "illegal name";
goto rejected;
}
if (prio > TIPC_MAX_LINK_PRI && prio != TIPC_MEDIA_LINK_PRI) {
errstr = "illegal priority";
goto rejected;
}
m = tipc_media_find(b_names.media_name);
if (!m) {
errstr = "media not registered";
goto rejected;
}
if (prio == TIPC_MEDIA_LINK_PRI)
prio = m->priority;
/* Check new bearer vs existing ones and find free bearer id if any */
while (bearer_id < MAX_BEARERS) {
b = rtnl_dereference(tn->bearer_list[bearer_id]);
if (!b)
break;
if (!strcmp(name, b->name)) {
errstr = "already enabled";
goto rejected;
}
bearer_id++;
if (b->priority != prio)
continue;
if (++with_this_prio <= 2)
continue;
pr_warn("Bearer <%s>: already 2 bearers with priority %u\n",
name, prio);
if (prio == TIPC_MIN_LINK_PRI) {
errstr = "cannot adjust to lower";
goto rejected;
}
pr_warn("Bearer <%s>: trying with adjusted priority\n", name);
prio--;
bearer_id = 0;
with_this_prio = 1;
}
if (bearer_id >= MAX_BEARERS) {
errstr = "max 3 bearers permitted";
goto rejected;
}
b = kzalloc(sizeof(*b), GFP_ATOMIC);
if (!b)
tipc: purge tipc_net_lock lock Now tipc routing hierarchy comprises the structures 'node', 'link'and 'bearer'. The whole hierarchy is protected by a big read/write lock, tipc_net_lock, to ensure that nothing is added or removed while code is accessing any of these structures. Obviously the locking policy makes node, link and bearer components closely bound together so that their relationship becomes unnecessarily complex. In the worst case, such locking policy not only has a negative influence on performance, but also it's prone to lead to deadlock occasionally. In order o decouple the complex relationship between bearer and node as well as link, the locking policy is adjusted as follows: - Bearer level RTNL lock is used on update side, and RCU is used on read side. Meanwhile, all bearer instances including broadcast bearer are saved into bearer_list array. - Node and link level All node instances are saved into two tipc_node_list and node_htable lists. The two lists are protected by node_list_lock on write side, and they are guarded with RCU lock on read side. All members in node structure including link instances are protected by node spin lock. - The relationship between bearer and node When link accesses bearer, it first needs to find the bearer with its bearer identity from the bearer_list array. When bearer accesses node, it can iterate the node_htable hash list with the node address to find the corresponding node. In the new locking policy, every component has its private locking solution and the relationship between bearer and node is very simple, that is, they can find each other with node address or bearer identity from node_htable hash list or bearer_list array. Until now above all changes have been done, so tipc_net_lock can be removed safely. Signed-off-by: Ying Xue <ying.xue@windriver.com> Reviewed-by: Jon Maloy <jon.maloy@ericsson.com> Reviewed-by: Erik Hugne <erik.hugne@ericsson.com> Tested-by: Erik Hugne <erik.hugne@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-04-21 02:55:48 +00:00
return -ENOMEM;
strcpy(b->name, name);
b->media = m;
res = m->enable_media(net, b, attr);
if (res) {
kfree(b);
errstr = "failed to enable media";
goto rejected;
}
b->identity = bearer_id;
b->tolerance = m->tolerance;
b->window = m->window;
b->domain = disc_domain;
b->net_plane = bearer_id + 'A';
b->priority = prio;
test_and_set_bit_lock(0, &b->up);
refcount_set(&b->refcnt, 1);
res = tipc_disc_create(net, b, &b->bcast_addr, &skb);
if (res) {
bearer_disable(net, b);
errstr = "failed to create discoverer";
goto rejected;
}
rcu_assign_pointer(tn->bearer_list[bearer_id], b);
if (skb)
tipc_bearer_xmit_skb(net, bearer_id, skb, &b->bcast_addr);
tipc: add neighbor monitoring framework TIPC based clusters are by default set up with full-mesh link connectivity between all nodes. Those links are expected to provide a short failure detection time, by default set to 1500 ms. Because of this, the background load for neighbor monitoring in an N-node cluster increases with a factor N on each node, while the overall monitoring traffic through the network infrastructure increases at a ~(N * (N - 1)) rate. Experience has shown that such clusters don't scale well beyond ~100 nodes unless we significantly increase failure discovery tolerance. This commit introduces a framework and an algorithm that drastically reduces this background load, while basically maintaining the original failure detection times across the whole cluster. Using this algorithm, background load will now grow at a rate of ~(2 * sqrt(N)) per node, and at ~(2 * N * sqrt(N)) in traffic overhead. As an example, each node will now have to actively monitor 38 neighbors in a 400-node cluster, instead of as before 399. This "Overlapping Ring Supervision Algorithm" is completely distributed and employs no centralized or coordinated state. It goes as follows: - Each node makes up a linearly ascending, circular list of all its N known neighbors, based on their TIPC node identity. This algorithm must be the same on all nodes. - The node then selects the next M = sqrt(N) - 1 nodes downstream from itself in the list, and chooses to actively monitor those. This is called its "local monitoring domain". - It creates a domain record describing the monitoring domain, and piggy-backs this in the data area of all neighbor monitoring messages (LINK_PROTOCOL/STATE) leaving that node. This means that all nodes in the cluster eventually (default within 400 ms) will learn about its monitoring domain. - Whenever a node discovers a change in its local domain, e.g., a node has been added or has gone down, it creates and sends out a new version of its node record to inform all neighbors about the change. - A node receiving a domain record from anybody outside its local domain matches this against its own list (which may not look the same), and chooses to not actively monitor those members of the received domain record that are also present in its own list. Instead, it relies on indications from the direct monitoring nodes if an indirectly monitored node has gone up or down. If a node is indicated lost, the receiving node temporarily activates its own direct monitoring towards that node in order to confirm, or not, that it is actually gone. - Since each node is actively monitoring sqrt(N) downstream neighbors, each node is also actively monitored by the same number of upstream neighbors. This means that all non-direct monitoring nodes normally will receive sqrt(N) indications that a node is gone. - A major drawback with ring monitoring is how it handles failures that cause massive network partitionings. If both a lost node and all its direct monitoring neighbors are inside the lost partition, the nodes in the remaining partition will never receive indications about the loss. To overcome this, each node also chooses to actively monitor some nodes outside its local domain. Those nodes are called remote domain "heads", and are selected in such a way that no node in the cluster will be more than two direct monitoring hops away. Because of this, each node, apart from monitoring the member of its local domain, will also typically monitor sqrt(N) remote head nodes. - As an optimization, local list status, domain status and domain records are marked with a generation number. This saves senders from unnecessarily conveying unaltered domain records, and receivers from performing unneeded re-adaptations of their node monitoring list, such as re-assigning domain heads. - As a measure of caution we have added the possibility to disable the new algorithm through configuration. We do this by keeping a threshold value for the cluster size; a cluster that grows beyond this value will switch from full-mesh to ring monitoring, and vice versa when it shrinks below the value. This means that if the threshold is set to a value larger than any anticipated cluster size (default size is 32) the new algorithm is effectively disabled. A patch set for altering the threshold value and for listing the table contents will follow shortly. - This change is fully backwards compatible. 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>
2016-06-14 00:46:22 +00:00
if (tipc_mon_create(net, bearer_id)) {
bearer_disable(net, b);
tipc: add neighbor monitoring framework TIPC based clusters are by default set up with full-mesh link connectivity between all nodes. Those links are expected to provide a short failure detection time, by default set to 1500 ms. Because of this, the background load for neighbor monitoring in an N-node cluster increases with a factor N on each node, while the overall monitoring traffic through the network infrastructure increases at a ~(N * (N - 1)) rate. Experience has shown that such clusters don't scale well beyond ~100 nodes unless we significantly increase failure discovery tolerance. This commit introduces a framework and an algorithm that drastically reduces this background load, while basically maintaining the original failure detection times across the whole cluster. Using this algorithm, background load will now grow at a rate of ~(2 * sqrt(N)) per node, and at ~(2 * N * sqrt(N)) in traffic overhead. As an example, each node will now have to actively monitor 38 neighbors in a 400-node cluster, instead of as before 399. This "Overlapping Ring Supervision Algorithm" is completely distributed and employs no centralized or coordinated state. It goes as follows: - Each node makes up a linearly ascending, circular list of all its N known neighbors, based on their TIPC node identity. This algorithm must be the same on all nodes. - The node then selects the next M = sqrt(N) - 1 nodes downstream from itself in the list, and chooses to actively monitor those. This is called its "local monitoring domain". - It creates a domain record describing the monitoring domain, and piggy-backs this in the data area of all neighbor monitoring messages (LINK_PROTOCOL/STATE) leaving that node. This means that all nodes in the cluster eventually (default within 400 ms) will learn about its monitoring domain. - Whenever a node discovers a change in its local domain, e.g., a node has been added or has gone down, it creates and sends out a new version of its node record to inform all neighbors about the change. - A node receiving a domain record from anybody outside its local domain matches this against its own list (which may not look the same), and chooses to not actively monitor those members of the received domain record that are also present in its own list. Instead, it relies on indications from the direct monitoring nodes if an indirectly monitored node has gone up or down. If a node is indicated lost, the receiving node temporarily activates its own direct monitoring towards that node in order to confirm, or not, that it is actually gone. - Since each node is actively monitoring sqrt(N) downstream neighbors, each node is also actively monitored by the same number of upstream neighbors. This means that all non-direct monitoring nodes normally will receive sqrt(N) indications that a node is gone. - A major drawback with ring monitoring is how it handles failures that cause massive network partitionings. If both a lost node and all its direct monitoring neighbors are inside the lost partition, the nodes in the remaining partition will never receive indications about the loss. To overcome this, each node also chooses to actively monitor some nodes outside its local domain. Those nodes are called remote domain "heads", and are selected in such a way that no node in the cluster will be more than two direct monitoring hops away. Because of this, each node, apart from monitoring the member of its local domain, will also typically monitor sqrt(N) remote head nodes. - As an optimization, local list status, domain status and domain records are marked with a generation number. This saves senders from unnecessarily conveying unaltered domain records, and receivers from performing unneeded re-adaptations of their node monitoring list, such as re-assigning domain heads. - As a measure of caution we have added the possibility to disable the new algorithm through configuration. We do this by keeping a threshold value for the cluster size; a cluster that grows beyond this value will switch from full-mesh to ring monitoring, and vice versa when it shrinks below the value. This means that if the threshold is set to a value larger than any anticipated cluster size (default size is 32) the new algorithm is effectively disabled. A patch set for altering the threshold value and for listing the table contents will follow shortly. - This change is fully backwards compatible. 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>
2016-06-14 00:46:22 +00:00
return -ENOMEM;
}
tipc: add neighbor monitoring framework TIPC based clusters are by default set up with full-mesh link connectivity between all nodes. Those links are expected to provide a short failure detection time, by default set to 1500 ms. Because of this, the background load for neighbor monitoring in an N-node cluster increases with a factor N on each node, while the overall monitoring traffic through the network infrastructure increases at a ~(N * (N - 1)) rate. Experience has shown that such clusters don't scale well beyond ~100 nodes unless we significantly increase failure discovery tolerance. This commit introduces a framework and an algorithm that drastically reduces this background load, while basically maintaining the original failure detection times across the whole cluster. Using this algorithm, background load will now grow at a rate of ~(2 * sqrt(N)) per node, and at ~(2 * N * sqrt(N)) in traffic overhead. As an example, each node will now have to actively monitor 38 neighbors in a 400-node cluster, instead of as before 399. This "Overlapping Ring Supervision Algorithm" is completely distributed and employs no centralized or coordinated state. It goes as follows: - Each node makes up a linearly ascending, circular list of all its N known neighbors, based on their TIPC node identity. This algorithm must be the same on all nodes. - The node then selects the next M = sqrt(N) - 1 nodes downstream from itself in the list, and chooses to actively monitor those. This is called its "local monitoring domain". - It creates a domain record describing the monitoring domain, and piggy-backs this in the data area of all neighbor monitoring messages (LINK_PROTOCOL/STATE) leaving that node. This means that all nodes in the cluster eventually (default within 400 ms) will learn about its monitoring domain. - Whenever a node discovers a change in its local domain, e.g., a node has been added or has gone down, it creates and sends out a new version of its node record to inform all neighbors about the change. - A node receiving a domain record from anybody outside its local domain matches this against its own list (which may not look the same), and chooses to not actively monitor those members of the received domain record that are also present in its own list. Instead, it relies on indications from the direct monitoring nodes if an indirectly monitored node has gone up or down. If a node is indicated lost, the receiving node temporarily activates its own direct monitoring towards that node in order to confirm, or not, that it is actually gone. - Since each node is actively monitoring sqrt(N) downstream neighbors, each node is also actively monitored by the same number of upstream neighbors. This means that all non-direct monitoring nodes normally will receive sqrt(N) indications that a node is gone. - A major drawback with ring monitoring is how it handles failures that cause massive network partitionings. If both a lost node and all its direct monitoring neighbors are inside the lost partition, the nodes in the remaining partition will never receive indications about the loss. To overcome this, each node also chooses to actively monitor some nodes outside its local domain. Those nodes are called remote domain "heads", and are selected in such a way that no node in the cluster will be more than two direct monitoring hops away. Because of this, each node, apart from monitoring the member of its local domain, will also typically monitor sqrt(N) remote head nodes. - As an optimization, local list status, domain status and domain records are marked with a generation number. This saves senders from unnecessarily conveying unaltered domain records, and receivers from performing unneeded re-adaptations of their node monitoring list, such as re-assigning domain heads. - As a measure of caution we have added the possibility to disable the new algorithm through configuration. We do this by keeping a threshold value for the cluster size; a cluster that grows beyond this value will switch from full-mesh to ring monitoring, and vice versa when it shrinks below the value. This means that if the threshold is set to a value larger than any anticipated cluster size (default size is 32) the new algorithm is effectively disabled. A patch set for altering the threshold value and for listing the table contents will follow shortly. - This change is fully backwards compatible. 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>
2016-06-14 00:46:22 +00:00
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>
2018-03-22 19:42:47 +00:00
pr_info("Enabled bearer <%s>, priority %u\n", name, prio);
return res;
rejected:
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>
2018-03-22 19:42:47 +00:00
pr_warn("Enabling of bearer <%s> rejected, %s\n", name, errstr);
return res;
}
/**
tipc: remove interface state mirroring in bearer struct 'tipc_bearer' is a generic representation of the underlying media type, and exists in a one-to-one relationship to each interface TIPC is using. The struct contains a 'blocked' flag that mirrors the operational and execution state of the represented interface, and is updated through notification calls from the latter. The users of tipc_bearer are checking this flag before each attempt to send a packet via the interface. This state mirroring serves no purpose in the current code base. TIPC links will not discover a media failure any faster through this mechanism, and in reality the flag only adds overhead at packet sending and reception. Furthermore, the fact that the flag needs to be protected by a spinlock aggregated into tipc_bearer has turned out to cause a serious and completely unnecessary deadlock problem. CPU0 CPU1 ---- ---- Time 0: bearer_disable() link_timeout() Time 1: spin_lock_bh(&b_ptr->lock) tipc_link_push_queue() Time 2: tipc_link_delete() tipc_bearer_blocked(b_ptr) Time 3: k_cancel_timer(&req->timer) spin_lock_bh(&b_ptr->lock) Time 4: del_timer_sync(&req->timer) I.e., del_timer_sync() on CPU0 never returns, because the timer handler on CPU1 is waiting for the bearer lock. We eliminate the 'blocked' flag from struct tipc_bearer, along with all tests on this flag. This not only resolves the deadlock, but also simplifies and speeds up the data path execution of TIPC. It also fits well into our ongoing effort to make the locking policy simpler and more manageable. An effect of this change is that we can get rid of functions such as tipc_bearer_blocked(), tipc_continue() and tipc_block_bearer(). We replace the latter with a new function, tipc_reset_bearer(), which resets all links associated to the bearer immediately after an interface goes down. A user might notice one slight change in link behaviour after this change. When an interface goes down, (e.g. through a NETDEV_DOWN event) all attached links will be reset immediately, instead of leaving it to each link to detect the failure through a timer-driven mechanism. We consider this an improvement, and see no obvious risks with the new behavior. Signed-off-by: Erik Hugne <erik.hugne@ericsson.com> Reviewed-by: Ying Xue <ying.xue@windriver.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>
2013-12-06 15:08:00 +00:00
* tipc_reset_bearer - Reset all links established over this bearer
*/
static int tipc_reset_bearer(struct net *net, struct tipc_bearer *b)
{
pr_info("Resetting bearer <%s>\n", b->name);
tipc_node_delete_links(net, b->identity);
tipc_disc_reset(net, b);
return 0;
}
bool tipc_bearer_hold(struct tipc_bearer *b)
{
return (b && refcount_inc_not_zero(&b->refcnt));
}
void tipc_bearer_put(struct tipc_bearer *b)
{
if (b && refcount_dec_and_test(&b->refcnt))
kfree_rcu(b, rcu);
}
/**
* bearer_disable
*
tipc: purge tipc_net_lock lock Now tipc routing hierarchy comprises the structures 'node', 'link'and 'bearer'. The whole hierarchy is protected by a big read/write lock, tipc_net_lock, to ensure that nothing is added or removed while code is accessing any of these structures. Obviously the locking policy makes node, link and bearer components closely bound together so that their relationship becomes unnecessarily complex. In the worst case, such locking policy not only has a negative influence on performance, but also it's prone to lead to deadlock occasionally. In order o decouple the complex relationship between bearer and node as well as link, the locking policy is adjusted as follows: - Bearer level RTNL lock is used on update side, and RCU is used on read side. Meanwhile, all bearer instances including broadcast bearer are saved into bearer_list array. - Node and link level All node instances are saved into two tipc_node_list and node_htable lists. The two lists are protected by node_list_lock on write side, and they are guarded with RCU lock on read side. All members in node structure including link instances are protected by node spin lock. - The relationship between bearer and node When link accesses bearer, it first needs to find the bearer with its bearer identity from the bearer_list array. When bearer accesses node, it can iterate the node_htable hash list with the node address to find the corresponding node. In the new locking policy, every component has its private locking solution and the relationship between bearer and node is very simple, that is, they can find each other with node address or bearer identity from node_htable hash list or bearer_list array. Until now above all changes have been done, so tipc_net_lock can be removed safely. Signed-off-by: Ying Xue <ying.xue@windriver.com> Reviewed-by: Jon Maloy <jon.maloy@ericsson.com> Reviewed-by: Erik Hugne <erik.hugne@ericsson.com> Tested-by: Erik Hugne <erik.hugne@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-04-21 02:55:48 +00:00
* Note: This routine assumes caller holds RTNL lock.
*/
static void bearer_disable(struct net *net, struct tipc_bearer *b)
{
struct tipc_net *tn = tipc_net(net);
int bearer_id = b->identity;
pr_info("Disabling bearer <%s>\n", b->name);
clear_bit_unlock(0, &b->up);
tipc_node_delete_links(net, bearer_id);
b->media->disable_media(b);
RCU_INIT_POINTER(b->media_ptr, NULL);
if (b->disc)
tipc_disc_delete(b->disc);
RCU_INIT_POINTER(tn->bearer_list[bearer_id], NULL);
tipc_bearer_put(b);
tipc: add neighbor monitoring framework TIPC based clusters are by default set up with full-mesh link connectivity between all nodes. Those links are expected to provide a short failure detection time, by default set to 1500 ms. Because of this, the background load for neighbor monitoring in an N-node cluster increases with a factor N on each node, while the overall monitoring traffic through the network infrastructure increases at a ~(N * (N - 1)) rate. Experience has shown that such clusters don't scale well beyond ~100 nodes unless we significantly increase failure discovery tolerance. This commit introduces a framework and an algorithm that drastically reduces this background load, while basically maintaining the original failure detection times across the whole cluster. Using this algorithm, background load will now grow at a rate of ~(2 * sqrt(N)) per node, and at ~(2 * N * sqrt(N)) in traffic overhead. As an example, each node will now have to actively monitor 38 neighbors in a 400-node cluster, instead of as before 399. This "Overlapping Ring Supervision Algorithm" is completely distributed and employs no centralized or coordinated state. It goes as follows: - Each node makes up a linearly ascending, circular list of all its N known neighbors, based on their TIPC node identity. This algorithm must be the same on all nodes. - The node then selects the next M = sqrt(N) - 1 nodes downstream from itself in the list, and chooses to actively monitor those. This is called its "local monitoring domain". - It creates a domain record describing the monitoring domain, and piggy-backs this in the data area of all neighbor monitoring messages (LINK_PROTOCOL/STATE) leaving that node. This means that all nodes in the cluster eventually (default within 400 ms) will learn about its monitoring domain. - Whenever a node discovers a change in its local domain, e.g., a node has been added or has gone down, it creates and sends out a new version of its node record to inform all neighbors about the change. - A node receiving a domain record from anybody outside its local domain matches this against its own list (which may not look the same), and chooses to not actively monitor those members of the received domain record that are also present in its own list. Instead, it relies on indications from the direct monitoring nodes if an indirectly monitored node has gone up or down. If a node is indicated lost, the receiving node temporarily activates its own direct monitoring towards that node in order to confirm, or not, that it is actually gone. - Since each node is actively monitoring sqrt(N) downstream neighbors, each node is also actively monitored by the same number of upstream neighbors. This means that all non-direct monitoring nodes normally will receive sqrt(N) indications that a node is gone. - A major drawback with ring monitoring is how it handles failures that cause massive network partitionings. If both a lost node and all its direct monitoring neighbors are inside the lost partition, the nodes in the remaining partition will never receive indications about the loss. To overcome this, each node also chooses to actively monitor some nodes outside its local domain. Those nodes are called remote domain "heads", and are selected in such a way that no node in the cluster will be more than two direct monitoring hops away. Because of this, each node, apart from monitoring the member of its local domain, will also typically monitor sqrt(N) remote head nodes. - As an optimization, local list status, domain status and domain records are marked with a generation number. This saves senders from unnecessarily conveying unaltered domain records, and receivers from performing unneeded re-adaptations of their node monitoring list, such as re-assigning domain heads. - As a measure of caution we have added the possibility to disable the new algorithm through configuration. We do this by keeping a threshold value for the cluster size; a cluster that grows beyond this value will switch from full-mesh to ring monitoring, and vice versa when it shrinks below the value. This means that if the threshold is set to a value larger than any anticipated cluster size (default size is 32) the new algorithm is effectively disabled. A patch set for altering the threshold value and for listing the table contents will follow shortly. - This change is fully backwards compatible. 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>
2016-06-14 00:46:22 +00:00
tipc_mon_delete(net, bearer_id);
}
int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b,
struct nlattr *attr[])
{
char *dev_name = strchr((const char *)b->name, ':') + 1;
int hwaddr_len = b->media->hwaddr_len;
u8 node_id[NODE_ID_LEN] = {0,};
struct net_device *dev;
/* Find device with specified name */
dev = dev_get_by_name(net, dev_name);
if (!dev)
return -ENODEV;
if (tipc_mtu_bad(dev, 0)) {
dev_put(dev);
return -EINVAL;
}
if (dev == net->loopback_dev) {
dev_put(dev);
pr_info("Enabling <%s> not permitted\n", b->name);
return -EINVAL;
}
/* Autoconfigure own node identity if needed */
if (!tipc_own_id(net) && hwaddr_len <= NODE_ID_LEN) {
memcpy(node_id, dev->dev_addr, hwaddr_len);
tipc_net_init(net, node_id, 0);
}
if (!tipc_own_id(net)) {
dev_put(dev);
pr_warn("Failed to obtain node identity\n");
return -EINVAL;
}
tipc: improve and extend media address conversion functions TIPC currently handles two media specific addresses: Ethernet MAC addresses and InfiniBand addresses. Those are kept in three different formats: 1) A "raw" format as obtained from the device. This format is known only by the media specific adapter code in eth_media.c and ib_media.c. 2) A "generic" internal format, in the form of struct tipc_media_addr, which can be referenced and passed around by the generic media- unaware code. 3) A serialized version of the latter, to be conveyed in neighbor discovery messages. Conversion between the three formats can only be done by the media specific code, so we have function pointers for this purpose in struct tipc_media. Here, the media adapters can install their own conversion functions at startup. We now introduce a new such function, 'raw2addr()', whose purpose is to convert from format 1 to format 2 above. We also try to as far as possible uniform commenting, variable names and usage of these functions, with the purpose of making them more comprehensible. We can now also remove the function tipc_l2_media_addr_set(), whose job is done better by the new function. Finally, we expand the field for serialized addresses (format 3) in discovery messages from 20 to 32 bytes. This is permitted according to the spec, and reduces the risk of problems when we add new media in the future. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Reviewed-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-14 09:39:13 +00:00
/* Associate TIPC bearer with L2 bearer */
rcu_assign_pointer(b->media_ptr, dev);
b->pt.dev = dev;
b->pt.type = htons(ETH_P_TIPC);
b->pt.func = tipc_l2_rcv_msg;
dev_add_pack(&b->pt);
tipc: improve and extend media address conversion functions TIPC currently handles two media specific addresses: Ethernet MAC addresses and InfiniBand addresses. Those are kept in three different formats: 1) A "raw" format as obtained from the device. This format is known only by the media specific adapter code in eth_media.c and ib_media.c. 2) A "generic" internal format, in the form of struct tipc_media_addr, which can be referenced and passed around by the generic media- unaware code. 3) A serialized version of the latter, to be conveyed in neighbor discovery messages. Conversion between the three formats can only be done by the media specific code, so we have function pointers for this purpose in struct tipc_media. Here, the media adapters can install their own conversion functions at startup. We now introduce a new such function, 'raw2addr()', whose purpose is to convert from format 1 to format 2 above. We also try to as far as possible uniform commenting, variable names and usage of these functions, with the purpose of making them more comprehensible. We can now also remove the function tipc_l2_media_addr_set(), whose job is done better by the new function. Finally, we expand the field for serialized addresses (format 3) in discovery messages from 20 to 32 bytes. This is permitted according to the spec, and reduces the risk of problems when we add new media in the future. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Reviewed-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-14 09:39:13 +00:00
memset(&b->bcast_addr, 0, sizeof(b->bcast_addr));
memcpy(b->bcast_addr.value, dev->broadcast, hwaddr_len);
b->bcast_addr.media_id = b->media->type_id;
b->bcast_addr.broadcast = TIPC_BROADCAST_SUPPORT;
b->mtu = dev->mtu;
tipc: improve and extend media address conversion functions TIPC currently handles two media specific addresses: Ethernet MAC addresses and InfiniBand addresses. Those are kept in three different formats: 1) A "raw" format as obtained from the device. This format is known only by the media specific adapter code in eth_media.c and ib_media.c. 2) A "generic" internal format, in the form of struct tipc_media_addr, which can be referenced and passed around by the generic media- unaware code. 3) A serialized version of the latter, to be conveyed in neighbor discovery messages. Conversion between the three formats can only be done by the media specific code, so we have function pointers for this purpose in struct tipc_media. Here, the media adapters can install their own conversion functions at startup. We now introduce a new such function, 'raw2addr()', whose purpose is to convert from format 1 to format 2 above. We also try to as far as possible uniform commenting, variable names and usage of these functions, with the purpose of making them more comprehensible. We can now also remove the function tipc_l2_media_addr_set(), whose job is done better by the new function. Finally, we expand the field for serialized addresses (format 3) in discovery messages from 20 to 32 bytes. This is permitted according to the spec, and reduces the risk of problems when we add new media in the future. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Reviewed-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-14 09:39:13 +00:00
b->media->raw2addr(b, &b->addr, (char *)dev->dev_addr);
rcu_assign_pointer(dev->tipc_ptr, b);
return 0;
}
tipc: improve and extend media address conversion functions TIPC currently handles two media specific addresses: Ethernet MAC addresses and InfiniBand addresses. Those are kept in three different formats: 1) A "raw" format as obtained from the device. This format is known only by the media specific adapter code in eth_media.c and ib_media.c. 2) A "generic" internal format, in the form of struct tipc_media_addr, which can be referenced and passed around by the generic media- unaware code. 3) A serialized version of the latter, to be conveyed in neighbor discovery messages. Conversion between the three formats can only be done by the media specific code, so we have function pointers for this purpose in struct tipc_media. Here, the media adapters can install their own conversion functions at startup. We now introduce a new such function, 'raw2addr()', whose purpose is to convert from format 1 to format 2 above. We also try to as far as possible uniform commenting, variable names and usage of these functions, with the purpose of making them more comprehensible. We can now also remove the function tipc_l2_media_addr_set(), whose job is done better by the new function. Finally, we expand the field for serialized addresses (format 3) in discovery messages from 20 to 32 bytes. This is permitted according to the spec, and reduces the risk of problems when we add new media in the future. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Reviewed-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-14 09:39:13 +00:00
/* tipc_disable_l2_media - detach TIPC bearer from an L2 interface
*
* Mark L2 bearer as inactive so that incoming buffers are thrown away
*/
void tipc_disable_l2_media(struct tipc_bearer *b)
{
struct net_device *dev;
dev = (struct net_device *)rtnl_dereference(b->media_ptr);
dev_remove_pack(&b->pt);
RCU_INIT_POINTER(dev->tipc_ptr, NULL);
synchronize_net();
dev_put(dev);
}
/**
tipc: improve and extend media address conversion functions TIPC currently handles two media specific addresses: Ethernet MAC addresses and InfiniBand addresses. Those are kept in three different formats: 1) A "raw" format as obtained from the device. This format is known only by the media specific adapter code in eth_media.c and ib_media.c. 2) A "generic" internal format, in the form of struct tipc_media_addr, which can be referenced and passed around by the generic media- unaware code. 3) A serialized version of the latter, to be conveyed in neighbor discovery messages. Conversion between the three formats can only be done by the media specific code, so we have function pointers for this purpose in struct tipc_media. Here, the media adapters can install their own conversion functions at startup. We now introduce a new such function, 'raw2addr()', whose purpose is to convert from format 1 to format 2 above. We also try to as far as possible uniform commenting, variable names and usage of these functions, with the purpose of making them more comprehensible. We can now also remove the function tipc_l2_media_addr_set(), whose job is done better by the new function. Finally, we expand the field for serialized addresses (format 3) in discovery messages from 20 to 32 bytes. This is permitted according to the spec, and reduces the risk of problems when we add new media in the future. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Reviewed-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-14 09:39:13 +00:00
* tipc_l2_send_msg - send a TIPC packet out over an L2 interface
* @skb: the packet to be sent
* @b: the bearer through which the packet is to be sent
* @dest: peer destination address
*/
int tipc_l2_send_msg(struct net *net, struct sk_buff *skb,
struct tipc_bearer *b, struct tipc_media_addr *dest)
{
struct net_device *dev;
int delta;
dev = (struct net_device *)rcu_dereference(b->media_ptr);
if (!dev)
return 0;
delta = SKB_DATA_ALIGN(dev->hard_header_len - skb_headroom(skb));
if ((delta > 0) && pskb_expand_head(skb, delta, 0, GFP_ATOMIC)) {
kfree_skb(skb);
return 0;
}
skb_reset_network_header(skb);
skb->dev = dev;
skb->protocol = htons(ETH_P_TIPC);
dev_hard_header(skb, dev, ETH_P_TIPC, dest->value,
dev->dev_addr, skb->len);
dev_queue_xmit(skb);
return 0;
}
bool tipc_bearer_bcast_support(struct net *net, u32 bearer_id)
{
bool supp = false;
struct tipc_bearer *b;
rcu_read_lock();
b = bearer_get(net, bearer_id);
if (b)
supp = (b->bcast_addr.broadcast == TIPC_BROADCAST_SUPPORT);
rcu_read_unlock();
return supp;
}
int tipc_bearer_mtu(struct net *net, u32 bearer_id)
{
int mtu = 0;
struct tipc_bearer *b;
rcu_read_lock();
b = rcu_dereference(tipc_net(net)->bearer_list[bearer_id]);
if (b)
mtu = b->mtu;
rcu_read_unlock();
return mtu;
}
/* tipc_bearer_xmit_skb - sends buffer to destination over bearer
*/
void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id,
struct sk_buff *skb,
struct tipc_media_addr *dest)
{
struct tipc_msg *hdr = buf_msg(skb);
struct tipc_bearer *b;
rcu_read_lock();
b = bearer_get(net, bearer_id);
if (likely(b && (test_bit(0, &b->up) || msg_is_reset(hdr))))
b->media->send_msg(net, skb, b, dest);
else
kfree_skb(skb);
rcu_read_unlock();
}
/* tipc_bearer_xmit() -send buffer to destination over bearer
*/
void tipc_bearer_xmit(struct net *net, u32 bearer_id,
struct sk_buff_head *xmitq,
struct tipc_media_addr *dst)
{
struct tipc_bearer *b;
struct sk_buff *skb, *tmp;
if (skb_queue_empty(xmitq))
return;
rcu_read_lock();
b = bearer_get(net, bearer_id);
if (unlikely(!b))
__skb_queue_purge(xmitq);
skb_queue_walk_safe(xmitq, skb, tmp) {
__skb_dequeue(xmitq);
if (likely(test_bit(0, &b->up) || msg_is_reset(buf_msg(skb))))
b->media->send_msg(net, skb, b, dst);
else
kfree_skb(skb);
}
rcu_read_unlock();
}
/* tipc_bearer_bc_xmit() - broadcast buffers to all destinations
*/
void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id,
struct sk_buff_head *xmitq)
{
struct tipc_net *tn = tipc_net(net);
int net_id = tn->net_id;
struct tipc_bearer *b;
struct sk_buff *skb, *tmp;
struct tipc_msg *hdr;
rcu_read_lock();
b = bearer_get(net, bearer_id);
if (unlikely(!b || !test_bit(0, &b->up)))
__skb_queue_purge(xmitq);
skb_queue_walk_safe(xmitq, skb, tmp) {
hdr = buf_msg(skb);
msg_set_non_seq(hdr, 1);
msg_set_mc_netid(hdr, net_id);
__skb_dequeue(xmitq);
b->media->send_msg(net, skb, b, &b->bcast_addr);
}
rcu_read_unlock();
}
/**
* tipc_l2_rcv_msg - handle incoming TIPC message from an interface
* @buf: the received packet
* @dev: the net device that the packet was received on
* @pt: the packet_type structure which was used to register this handler
* @orig_dev: the original receive net device in case the device is a bond
*
* Accept only packets explicitly sent to this node, or broadcast packets;
* ignores packets sent using interface multicast, and traffic sent to other
* nodes (which can happen if interface is running in promiscuous mode).
*/
static int tipc_l2_rcv_msg(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev)
{
struct tipc_bearer *b;
rcu_read_lock();
b = rcu_dereference(dev->tipc_ptr) ?:
rcu_dereference(orig_dev->tipc_ptr);
if (likely(b && test_bit(0, &b->up) &&
(skb->pkt_type <= PACKET_MULTICAST))) {
skb_mark_not_on_list(skb);
tipc_rcv(dev_net(b->pt.dev), skb, b);
rcu_read_unlock();
return NET_RX_SUCCESS;
}
rcu_read_unlock();
kfree_skb(skb);
return NET_RX_DROP;
}
/**
* tipc_l2_device_event - handle device events from network device
* @nb: the context of the notification
* @evt: the type of event
* @ptr: the net device that the event was on
*
* This function is called by the Ethernet driver in case of link
* change event.
*/
static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt,
void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net *net = dev_net(dev);
struct tipc_bearer *b;
b = rtnl_dereference(dev->tipc_ptr);
if (!b)
return NOTIFY_DONE;
trace_tipc_l2_device_event(dev, b, evt);
switch (evt) {
case NETDEV_CHANGE:
if (netif_carrier_ok(dev) && netif_oper_up(dev)) {
test_and_set_bit_lock(0, &b->up);
break;
}
/* fall through */
case NETDEV_GOING_DOWN:
clear_bit_unlock(0, &b->up);
tipc_reset_bearer(net, b);
break;
case NETDEV_UP:
test_and_set_bit_lock(0, &b->up);
break;
case NETDEV_CHANGEMTU:
if (tipc_mtu_bad(dev, 0)) {
bearer_disable(net, b);
break;
}
b->mtu = dev->mtu;
tipc_reset_bearer(net, b);
break;
case NETDEV_CHANGEADDR:
b->media->raw2addr(b, &b->addr,
(char *)dev->dev_addr);
tipc_reset_bearer(net, b);
break;
case NETDEV_UNREGISTER:
case NETDEV_CHANGENAME:
bearer_disable(net, b);
break;
}
return NOTIFY_OK;
}
static struct notifier_block notifier = {
.notifier_call = tipc_l2_device_event,
.priority = 0,
};
int tipc_bearer_setup(void)
{
return register_netdevice_notifier(&notifier);
}
void tipc_bearer_cleanup(void)
{
unregister_netdevice_notifier(&notifier);
}
void tipc_bearer_stop(struct net *net)
{
struct tipc_net *tn = net_generic(net, tipc_net_id);
struct tipc_bearer *b;
u32 i;
for (i = 0; i < MAX_BEARERS; i++) {
b = rtnl_dereference(tn->bearer_list[i]);
if (b) {
bearer_disable(net, b);
tn->bearer_list[i] = NULL;
}
}
}
void tipc_clone_to_loopback(struct net *net, struct sk_buff_head *pkts)
{
struct net_device *dev = net->loopback_dev;
struct sk_buff *skb, *_skb;
int exp;
skb_queue_walk(pkts, _skb) {
skb = pskb_copy(_skb, GFP_ATOMIC);
if (!skb)
continue;
exp = SKB_DATA_ALIGN(dev->hard_header_len - skb_headroom(skb));
if (exp > 0 && pskb_expand_head(skb, exp, 0, GFP_ATOMIC)) {
kfree_skb(skb);
continue;
}
skb_reset_network_header(skb);
dev_hard_header(skb, dev, ETH_P_TIPC, dev->dev_addr,
dev->dev_addr, skb->len);
skb->dev = dev;
skb->pkt_type = PACKET_HOST;
skb->ip_summed = CHECKSUM_UNNECESSARY;
skb->protocol = eth_type_trans(skb, dev);
netif_rx_ni(skb);
}
}
static int tipc_loopback_rcv_pkt(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *od)
{
consume_skb(skb);
return NET_RX_SUCCESS;
}
int tipc_attach_loopback(struct net *net)
{
struct net_device *dev = net->loopback_dev;
struct tipc_net *tn = tipc_net(net);
if (!dev)
return -ENODEV;
dev_hold(dev);
tn->loopback_pt.dev = dev;
tn->loopback_pt.type = htons(ETH_P_TIPC);
tn->loopback_pt.func = tipc_loopback_rcv_pkt;
dev_add_pack(&tn->loopback_pt);
return 0;
}
void tipc_detach_loopback(struct net *net)
{
struct tipc_net *tn = tipc_net(net);
dev_remove_pack(&tn->loopback_pt);
dev_put(net->loopback_dev);
}
/* Caller should hold rtnl_lock to protect the bearer */
static int __tipc_nl_add_bearer(struct tipc_nl_msg *msg,
struct tipc_bearer *bearer, int nlflags)
{
void *hdr;
struct nlattr *attrs;
struct nlattr *prop;
hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
nlflags, TIPC_NL_BEARER_GET);
if (!hdr)
return -EMSGSIZE;
attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_BEARER);
if (!attrs)
goto msg_full;
if (nla_put_string(msg->skb, TIPC_NLA_BEARER_NAME, bearer->name))
goto attr_msg_full;
prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_BEARER_PROP);
if (!prop)
goto prop_msg_full;
if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, bearer->priority))
goto prop_msg_full;
if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, bearer->tolerance))
goto prop_msg_full;
if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bearer->window))
goto prop_msg_full;
if (bearer->media->type_id == TIPC_MEDIA_TYPE_UDP)
if (nla_put_u32(msg->skb, TIPC_NLA_PROP_MTU, bearer->mtu))
goto prop_msg_full;
nla_nest_end(msg->skb, prop);
#ifdef CONFIG_TIPC_MEDIA_UDP
if (bearer->media->type_id == TIPC_MEDIA_TYPE_UDP) {
if (tipc_udp_nl_add_bearer_data(msg, bearer))
goto attr_msg_full;
}
#endif
nla_nest_end(msg->skb, attrs);
genlmsg_end(msg->skb, hdr);
return 0;
prop_msg_full:
nla_nest_cancel(msg->skb, prop);
attr_msg_full:
nla_nest_cancel(msg->skb, attrs);
msg_full:
genlmsg_cancel(msg->skb, hdr);
return -EMSGSIZE;
}
int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
int err;
int i = cb->args[0];
struct tipc_bearer *bearer;
struct tipc_nl_msg msg;
struct net *net = sock_net(skb->sk);
struct tipc_net *tn = net_generic(net, tipc_net_id);
if (i == MAX_BEARERS)
return 0;
msg.skb = skb;
msg.portid = NETLINK_CB(cb->skb).portid;
msg.seq = cb->nlh->nlmsg_seq;
rtnl_lock();
for (i = 0; i < MAX_BEARERS; i++) {
bearer = rtnl_dereference(tn->bearer_list[i]);
if (!bearer)
continue;
err = __tipc_nl_add_bearer(&msg, bearer, NLM_F_MULTI);
if (err)
break;
}
rtnl_unlock();
cb->args[0] = i;
return skb->len;
}
int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info)
{
int err;
char *name;
struct sk_buff *rep;
struct tipc_bearer *bearer;
struct tipc_nl_msg msg;
struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1];
struct net *net = genl_info_net(info);
if (!info->attrs[TIPC_NLA_BEARER])
return -EINVAL;
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 12:07:28 +00:00
err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX,
info->attrs[TIPC_NLA_BEARER],
tipc_nl_bearer_policy, info->extack);
if (err)
return err;
if (!attrs[TIPC_NLA_BEARER_NAME])
return -EINVAL;
name = nla_data(attrs[TIPC_NLA_BEARER_NAME]);
rep = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
if (!rep)
return -ENOMEM;
msg.skb = rep;
msg.portid = info->snd_portid;
msg.seq = info->snd_seq;
rtnl_lock();
bearer = tipc_bearer_find(net, name);
if (!bearer) {
err = -EINVAL;
goto err_out;
}
err = __tipc_nl_add_bearer(&msg, bearer, 0);
if (err)
goto err_out;
rtnl_unlock();
return genlmsg_reply(rep, info);
err_out:
rtnl_unlock();
nlmsg_free(rep);
return err;
}
int __tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info)
{
int err;
char *name;
struct tipc_bearer *bearer;
struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1];
struct net *net = sock_net(skb->sk);
if (!info->attrs[TIPC_NLA_BEARER])
return -EINVAL;
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 12:07:28 +00:00
err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX,
info->attrs[TIPC_NLA_BEARER],
tipc_nl_bearer_policy, info->extack);
if (err)
return err;
if (!attrs[TIPC_NLA_BEARER_NAME])
return -EINVAL;
name = nla_data(attrs[TIPC_NLA_BEARER_NAME]);
bearer = tipc_bearer_find(net, name);
if (!bearer)
return -EINVAL;
bearer_disable(net, bearer);
return 0;
}
int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info)
{
int err;
rtnl_lock();
err = __tipc_nl_bearer_disable(skb, info);
rtnl_unlock();
return err;
}
int __tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info)
{
int err;
char *bearer;
struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1];
struct net *net = sock_net(skb->sk);
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>
2018-03-22 19:42:47 +00:00
u32 domain = 0;
u32 prio;
prio = TIPC_MEDIA_LINK_PRI;
if (!info->attrs[TIPC_NLA_BEARER])
return -EINVAL;
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 12:07:28 +00:00
err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX,
info->attrs[TIPC_NLA_BEARER],
tipc_nl_bearer_policy, info->extack);
if (err)
return err;
if (!attrs[TIPC_NLA_BEARER_NAME])
return -EINVAL;
bearer = nla_data(attrs[TIPC_NLA_BEARER_NAME]);
if (attrs[TIPC_NLA_BEARER_DOMAIN])
domain = nla_get_u32(attrs[TIPC_NLA_BEARER_DOMAIN]);
if (attrs[TIPC_NLA_BEARER_PROP]) {
struct nlattr *props[TIPC_NLA_PROP_MAX + 1];
err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_BEARER_PROP],
props);
if (err)
return err;
if (props[TIPC_NLA_PROP_PRIO])
prio = nla_get_u32(props[TIPC_NLA_PROP_PRIO]);
}
return tipc_enable_bearer(net, bearer, domain, prio, attrs);
}
int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info)
{
int err;
rtnl_lock();
err = __tipc_nl_bearer_enable(skb, info);
rtnl_unlock();
return err;
}
int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info)
{
int err;
char *name;
struct tipc_bearer *b;
struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1];
struct net *net = sock_net(skb->sk);
if (!info->attrs[TIPC_NLA_BEARER])
return -EINVAL;
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 12:07:28 +00:00
err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX,
info->attrs[TIPC_NLA_BEARER],
tipc_nl_bearer_policy, info->extack);
if (err)
return err;
if (!attrs[TIPC_NLA_BEARER_NAME])
return -EINVAL;
name = nla_data(attrs[TIPC_NLA_BEARER_NAME]);
rtnl_lock();
b = tipc_bearer_find(net, name);
if (!b) {
rtnl_unlock();
return -EINVAL;
}
#ifdef CONFIG_TIPC_MEDIA_UDP
if (attrs[TIPC_NLA_BEARER_UDP_OPTS]) {
err = tipc_udp_nl_bearer_add(b,
attrs[TIPC_NLA_BEARER_UDP_OPTS]);
if (err) {
rtnl_unlock();
return err;
}
}
#endif
rtnl_unlock();
return 0;
}
int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info)
{
struct tipc_bearer *b;
struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1];
struct net *net = sock_net(skb->sk);
char *name;
int err;
if (!info->attrs[TIPC_NLA_BEARER])
return -EINVAL;
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 12:07:28 +00:00
err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX,
info->attrs[TIPC_NLA_BEARER],
tipc_nl_bearer_policy, info->extack);
if (err)
return err;
if (!attrs[TIPC_NLA_BEARER_NAME])
return -EINVAL;
name = nla_data(attrs[TIPC_NLA_BEARER_NAME]);
b = tipc_bearer_find(net, name);
if (!b)
return -EINVAL;
if (attrs[TIPC_NLA_BEARER_PROP]) {
struct nlattr *props[TIPC_NLA_PROP_MAX + 1];
err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_BEARER_PROP],
props);
if (err)
return err;
if (props[TIPC_NLA_PROP_TOL]) {
b->tolerance = nla_get_u32(props[TIPC_NLA_PROP_TOL]);
tipc_node_apply_property(net, b, TIPC_NLA_PROP_TOL);
}
if (props[TIPC_NLA_PROP_PRIO])
b->priority = nla_get_u32(props[TIPC_NLA_PROP_PRIO]);
if (props[TIPC_NLA_PROP_WIN])
b->window = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
if (props[TIPC_NLA_PROP_MTU]) {
if (b->media->type_id != TIPC_MEDIA_TYPE_UDP)
return -EINVAL;
#ifdef CONFIG_TIPC_MEDIA_UDP
if (tipc_udp_mtu_bad(nla_get_u32
(props[TIPC_NLA_PROP_MTU])))
return -EINVAL;
b->mtu = nla_get_u32(props[TIPC_NLA_PROP_MTU]);
tipc_node_apply_property(net, b, TIPC_NLA_PROP_MTU);
#endif
}
}
return 0;
}
int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info)
{
int err;
rtnl_lock();
err = __tipc_nl_bearer_set(skb, info);
rtnl_unlock();
return err;
}
static int __tipc_nl_add_media(struct tipc_nl_msg *msg,
struct tipc_media *media, int nlflags)
{
void *hdr;
struct nlattr *attrs;
struct nlattr *prop;
hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
nlflags, TIPC_NL_MEDIA_GET);
if (!hdr)
return -EMSGSIZE;
attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MEDIA);
if (!attrs)
goto msg_full;
if (nla_put_string(msg->skb, TIPC_NLA_MEDIA_NAME, media->name))
goto attr_msg_full;
prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_MEDIA_PROP);
if (!prop)
goto prop_msg_full;
if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, media->priority))
goto prop_msg_full;
if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, media->tolerance))
goto prop_msg_full;
if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, media->window))
goto prop_msg_full;
if (media->type_id == TIPC_MEDIA_TYPE_UDP)
if (nla_put_u32(msg->skb, TIPC_NLA_PROP_MTU, media->mtu))
goto prop_msg_full;
nla_nest_end(msg->skb, prop);
nla_nest_end(msg->skb, attrs);
genlmsg_end(msg->skb, hdr);
return 0;
prop_msg_full:
nla_nest_cancel(msg->skb, prop);
attr_msg_full:
nla_nest_cancel(msg->skb, attrs);
msg_full:
genlmsg_cancel(msg->skb, hdr);
return -EMSGSIZE;
}
int tipc_nl_media_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
int err;
int i = cb->args[0];
struct tipc_nl_msg msg;
if (i == MAX_MEDIA)
return 0;
msg.skb = skb;
msg.portid = NETLINK_CB(cb->skb).portid;
msg.seq = cb->nlh->nlmsg_seq;
rtnl_lock();
for (; media_info_array[i] != NULL; i++) {
err = __tipc_nl_add_media(&msg, media_info_array[i],
NLM_F_MULTI);
if (err)
break;
}
rtnl_unlock();
cb->args[0] = i;
return skb->len;
}
int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info)
{
int err;
char *name;
struct tipc_nl_msg msg;
struct tipc_media *media;
struct sk_buff *rep;
struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1];
if (!info->attrs[TIPC_NLA_MEDIA])
return -EINVAL;
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 12:07:28 +00:00
err = nla_parse_nested_deprecated(attrs, TIPC_NLA_MEDIA_MAX,
info->attrs[TIPC_NLA_MEDIA],
tipc_nl_media_policy, info->extack);
if (err)
return err;
if (!attrs[TIPC_NLA_MEDIA_NAME])
return -EINVAL;
name = nla_data(attrs[TIPC_NLA_MEDIA_NAME]);
rep = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
if (!rep)
return -ENOMEM;
msg.skb = rep;
msg.portid = info->snd_portid;
msg.seq = info->snd_seq;
rtnl_lock();
media = tipc_media_find(name);
if (!media) {
err = -EINVAL;
goto err_out;
}
err = __tipc_nl_add_media(&msg, media, 0);
if (err)
goto err_out;
rtnl_unlock();
return genlmsg_reply(rep, info);
err_out:
rtnl_unlock();
nlmsg_free(rep);
return err;
}
int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info)
{
int err;
char *name;
struct tipc_media *m;
struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1];
if (!info->attrs[TIPC_NLA_MEDIA])
return -EINVAL;
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 12:07:28 +00:00
err = nla_parse_nested_deprecated(attrs, TIPC_NLA_MEDIA_MAX,
info->attrs[TIPC_NLA_MEDIA],
tipc_nl_media_policy, info->extack);
if (!attrs[TIPC_NLA_MEDIA_NAME])
return -EINVAL;
name = nla_data(attrs[TIPC_NLA_MEDIA_NAME]);
m = tipc_media_find(name);
if (!m)
return -EINVAL;
if (attrs[TIPC_NLA_MEDIA_PROP]) {
struct nlattr *props[TIPC_NLA_PROP_MAX + 1];
err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_MEDIA_PROP],
props);
if (err)
return err;
if (props[TIPC_NLA_PROP_TOL])
m->tolerance = nla_get_u32(props[TIPC_NLA_PROP_TOL]);
if (props[TIPC_NLA_PROP_PRIO])
m->priority = nla_get_u32(props[TIPC_NLA_PROP_PRIO]);
if (props[TIPC_NLA_PROP_WIN])
m->window = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
if (props[TIPC_NLA_PROP_MTU]) {
if (m->type_id != TIPC_MEDIA_TYPE_UDP)
return -EINVAL;
#ifdef CONFIG_TIPC_MEDIA_UDP
if (tipc_udp_mtu_bad(nla_get_u32
(props[TIPC_NLA_PROP_MTU])))
return -EINVAL;
m->mtu = nla_get_u32(props[TIPC_NLA_PROP_MTU]);
#endif
}
}
return 0;
}
int tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info)
{
int err;
rtnl_lock();
err = __tipc_nl_media_set(skb, info);
rtnl_unlock();
return err;
}