2
0
mirror of https://github.com/openvswitch/ovs synced 2025-08-22 09:58:01 +00:00
ovs/lib/netlink-protocol.h

219 lines
5.7 KiB
C
Raw Normal View History

/*
* Copyright (c) 2008, 2010, 2011, 2014 Nicira, Inc.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at:
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
#ifndef NETLINK_PROTOCOL_H
#define NETLINK_PROTOCOL_H 1
/* Netlink protocol definitions.
*
* Netlink is a message framing format described in RFC 3549 and used heavily
* in Linux to access the network stack. Open vSwitch uses AF_NETLINK sockets
* for this purpose on Linux. But on all platforms, Open vSwitch uses Netlink
* message framing internally for certain purposes.
*
* This header provides access to the Netlink message framing definitions
* regardless of platform. On Linux, it includes the proper headers directly;
* on other platforms it directly defines the structures and macros itself.
*/
#include <stdint.h>
#include <sys/socket.h>
#include "util.h"
#ifdef HAVE_NETLINK
#include <linux/netlink.h>
#include <linux/genetlink.h>
#else
#define NETLINK_NETFILTER 12
#define NETLINK_GENERIC 16
/* nlmsg_flags bits. */
#define NLM_F_REQUEST 0x001
#define NLM_F_MULTI 0x002
#define NLM_F_ACK 0x004
#define NLM_F_ECHO 0x008
/* GET request flag.*/
#define NLM_F_ROOT 0x100
#define NLM_F_MATCH 0x200
#define NLM_F_ATOMIC 0x400
#define NLM_F_DUMP (NLM_F_ROOT | NLM_F_MATCH)
/* NEW request flags. */
#define NLM_F_REPLACE 0x100
#define NLM_F_EXCL 0x200
#define NLM_F_CREATE 0x400
/* nlmsg_type values. */
#define NLMSG_NOOP 1
#define NLMSG_ERROR 2
#define NLMSG_DONE 3
#define NLMSG_OVERRUN 4
#define NLMSG_MIN_TYPE 0x10
#define MAX_LINKS 32
struct nlmsghdr {
uint32_t nlmsg_len;
uint16_t nlmsg_type;
uint16_t nlmsg_flags;
uint32_t nlmsg_seq;
uint32_t nlmsg_pid;
};
BUILD_ASSERT_DECL(sizeof(struct nlmsghdr) == 16);
#define NLMSG_ALIGNTO 4
#define NLMSG_ALIGN(SIZE) ROUND_UP(SIZE, NLMSG_ALIGNTO)
#define NLMSG_HDRLEN ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr)))
struct nlmsgerr
{
int error;
struct nlmsghdr msg;
};
BUILD_ASSERT_DECL(sizeof(struct nlmsgerr) == 20);
struct genlmsghdr {
uint8_t cmd;
uint8_t version;
uint16_t reserved;
};
BUILD_ASSERT_DECL(sizeof(struct genlmsghdr) == 4);
#define GENL_HDRLEN NLMSG_ALIGN(sizeof(struct genlmsghdr))
struct nlattr {
uint16_t nla_len;
uint16_t nla_type;
};
BUILD_ASSERT_DECL(sizeof(struct nlattr) == 4);
#define NLA_ALIGNTO 4
#define NLA_ALIGN(SIZE) ROUND_UP(SIZE, NLA_ALIGNTO)
#define NLA_HDRLEN ((int) NLA_ALIGN(sizeof(struct nlattr)))
#define GENL_MIN_ID NLMSG_MIN_TYPE
#define GENL_MAX_ID 1023
#define GENL_ID_CTRL NLMSG_MIN_TYPE
enum {
CTRL_CMD_UNSPEC,
CTRL_CMD_NEWFAMILY,
CTRL_CMD_DELFAMILY,
CTRL_CMD_GETFAMILY,
CTRL_CMD_NEWOPS,
CTRL_CMD_DELOPS,
CTRL_CMD_GETOPS,
__CTRL_CMD_MAX,
};
#define CTRL_CMD_MAX (__CTRL_CMD_MAX - 1)
enum {
CTRL_ATTR_UNSPEC,
CTRL_ATTR_FAMILY_ID,
CTRL_ATTR_FAMILY_NAME,
CTRL_ATTR_VERSION,
CTRL_ATTR_HDRSIZE,
CTRL_ATTR_MAXATTR,
CTRL_ATTR_OPS,
__CTRL_ATTR_MAX,
};
#define CTRL_ATTR_MAX (__CTRL_ATTR_MAX - 1)
enum {
CTRL_ATTR_OP_UNSPEC,
CTRL_ATTR_OP_ID,
CTRL_ATTR_OP_FLAGS,
__CTRL_ATTR_OP_MAX,
};
#define CTRL_ATTR_OP_MAX (__CTRL_ATTR_OP_MAX - 1)
#endif /* !HAVE_NETLINK */
/* These were introduced all together in 2.6.24. */
#ifndef NLA_TYPE_MASK
#define NLA_F_NESTED (1 << 15)
#define NLA_F_NET_BYTEORDER (1 << 14)
#define NLA_TYPE_MASK ~(NLA_F_NESTED | NLA_F_NET_BYTEORDER)
#endif
route-table: Avoid routes from non-standard routing tables. Currently, ovs-vswitchd is subscribed to all the routing changes in the kernel. On each change, it marks the internal routing table cache as invalid, then resets it and dumps all the routes from the kernel from scratch. The reason for that is kernel routing updates not being reliable in a sense that it's hard to tell which route is getting removed or modified. Userspace application has to track the order in which route entries are dumped from the kernel. Updates can get lost or even duplicated and the kernel doesn't provide a good mechanism to distinguish one route from another. To my knowledge, dumping all the routes from a kernel after each change is the only way to keep the cache consistent. Some more info can be found in the following never addressed issues: https://bugzilla.redhat.com/1337860 https://bugzilla.redhat.com/1337855 It seems to be believed that NetworkManager "mostly" does incremental updates right. But it is still not completely correct, will re-dump the whole table in certain cases, and it takes a huge amount of very complicated code to do the accounting and route comparisons. Going back to ovs-vswitchd, it currently dumps routes from all the routing tables. If it will get conflicting routes from multiple tables, the cache will not be useful. The routing cache in userspace is primarily used for checking the egress port for tunneled traffic and this way also detecting link state changes for a tunnel port. For userspace datapath it is used for actual routing of the packet after sending to a native tunnel. With kernel datapath we don't really have a mechanism to know which routing table will actually be used by the kernel after encapsulation, so our lookups on a cache may be incorrect because of this as well. So, unless all the relevant routes are in the standard tables, the lookup in userspace route cache is unreliable. Luckily, most setups are not using any complicated routing in non-standard tables that OVS has to be aware of. It is possible, but unlikely, that standard routing tables are completely empty while some other custom table is not, and all the OVS tunnel traffic is directed to that table. That would be the only scenario where dumping non-standard tables would make sense. But it seems like this kind of setup will likely need a way to tell OVS from which table the routes should be taken, or we'll need to dump routing rules and keep a separate cache for each table, so we can first match on rules and then lookup correct routes in a specific table. I'm not sure if trying to implement all that is justified. For now, stop considering routes from non-standard tables to avoid mixing different tables together and also wasting CPU resources. This fixes a high CPU usage in ovs-vswitchd in case a BGP daemon is running on a same host and in a same network namespace with OVS using its own custom routing table. Unfortunately, there seems to be no way to tell the kernel to send updates only for particular tables. So, we'll still receive and parse all of them. But they will not result in a full cache invalidation in most cases. Linux kernel v4.20 introduced filtering support for RTM_GETROUTE dumps. So, we can make use of it and dump only standard tables when we get a relevant route update. NETLINK_GET_STRICT_CHK has to be enabled on the socket for filtering to work. There is no reason to not enable it by default, if supported. It is not used outside of NETLINK_ROUTE. Fixes: f0e167f0dbad ("route-table: Handle route updates more robustly.") Fixes: ea83a2fcd0d3 ("lib: Show tunnel egress interface in ovsdb") Reported-at: https://github.com/openvswitch/ovs-issues/issues/185 Reported-at: https://mail.openvswitch.org/pipermail/ovs-discuss/2022-October/052091.html Acked-by: Aaron Conole <aconole@redhat.com> Signed-off-by: Ilya Maximets <i.maximets@ovn.org>
2024-03-20 19:47:21 +01:00
/* Introduced in v4.4. */
#ifndef NLM_F_DUMP_FILTERED
#define NLM_F_DUMP_FILTERED 0x20
#endif
/* These were introduced all together in 2.6.14. (We want our programs to
* support the newer kernel features even if compiled with older headers.) */
#ifndef NETLINK_ADD_MEMBERSHIP
#define NETLINK_ADD_MEMBERSHIP 1
#define NETLINK_DROP_MEMBERSHIP 2
#endif
/* This was introduced in v4.2. (We want our programs to support the newer
* kernel features even if compiled with older headers.) */
#ifndef NETLINK_LISTEN_ALL_NSID
#define NETLINK_LISTEN_ALL_NSID 8
#endif
route-table: Avoid routes from non-standard routing tables. Currently, ovs-vswitchd is subscribed to all the routing changes in the kernel. On each change, it marks the internal routing table cache as invalid, then resets it and dumps all the routes from the kernel from scratch. The reason for that is kernel routing updates not being reliable in a sense that it's hard to tell which route is getting removed or modified. Userspace application has to track the order in which route entries are dumped from the kernel. Updates can get lost or even duplicated and the kernel doesn't provide a good mechanism to distinguish one route from another. To my knowledge, dumping all the routes from a kernel after each change is the only way to keep the cache consistent. Some more info can be found in the following never addressed issues: https://bugzilla.redhat.com/1337860 https://bugzilla.redhat.com/1337855 It seems to be believed that NetworkManager "mostly" does incremental updates right. But it is still not completely correct, will re-dump the whole table in certain cases, and it takes a huge amount of very complicated code to do the accounting and route comparisons. Going back to ovs-vswitchd, it currently dumps routes from all the routing tables. If it will get conflicting routes from multiple tables, the cache will not be useful. The routing cache in userspace is primarily used for checking the egress port for tunneled traffic and this way also detecting link state changes for a tunnel port. For userspace datapath it is used for actual routing of the packet after sending to a native tunnel. With kernel datapath we don't really have a mechanism to know which routing table will actually be used by the kernel after encapsulation, so our lookups on a cache may be incorrect because of this as well. So, unless all the relevant routes are in the standard tables, the lookup in userspace route cache is unreliable. Luckily, most setups are not using any complicated routing in non-standard tables that OVS has to be aware of. It is possible, but unlikely, that standard routing tables are completely empty while some other custom table is not, and all the OVS tunnel traffic is directed to that table. That would be the only scenario where dumping non-standard tables would make sense. But it seems like this kind of setup will likely need a way to tell OVS from which table the routes should be taken, or we'll need to dump routing rules and keep a separate cache for each table, so we can first match on rules and then lookup correct routes in a specific table. I'm not sure if trying to implement all that is justified. For now, stop considering routes from non-standard tables to avoid mixing different tables together and also wasting CPU resources. This fixes a high CPU usage in ovs-vswitchd in case a BGP daemon is running on a same host and in a same network namespace with OVS using its own custom routing table. Unfortunately, there seems to be no way to tell the kernel to send updates only for particular tables. So, we'll still receive and parse all of them. But they will not result in a full cache invalidation in most cases. Linux kernel v4.20 introduced filtering support for RTM_GETROUTE dumps. So, we can make use of it and dump only standard tables when we get a relevant route update. NETLINK_GET_STRICT_CHK has to be enabled on the socket for filtering to work. There is no reason to not enable it by default, if supported. It is not used outside of NETLINK_ROUTE. Fixes: f0e167f0dbad ("route-table: Handle route updates more robustly.") Fixes: ea83a2fcd0d3 ("lib: Show tunnel egress interface in ovsdb") Reported-at: https://github.com/openvswitch/ovs-issues/issues/185 Reported-at: https://mail.openvswitch.org/pipermail/ovs-discuss/2022-October/052091.html Acked-by: Aaron Conole <aconole@redhat.com> Signed-off-by: Ilya Maximets <i.maximets@ovn.org>
2024-03-20 19:47:21 +01:00
/* Strict checking of netlink arguments introduced in Linux kernel v4.20. */
#ifndef NETLINK_GET_STRICT_CHK
#define NETLINK_GET_STRICT_CHK 12
#endif
/* These were introduced all together in 2.6.23. (We want our programs to
* support the newer kernel features even if compiled with older headers.) */
#ifndef CTRL_ATTR_MCAST_GRP_MAX
#undef CTRL_ATTR_MAX
#define CTRL_ATTR_MAX 7
#define CTRL_ATTR_MCAST_GROUPS 7
enum {
CTRL_ATTR_MCAST_GRP_UNSPEC,
CTRL_ATTR_MCAST_GRP_NAME,
CTRL_ATTR_MCAST_GRP_ID,
__CTRL_ATTR_MCAST_GRP_MAX,
};
#define CTRL_ATTR_MCAST_GRP_MAX (__CTRL_ATTR_MCAST_GRP_MAX - 1)
#endif /* CTRL_ATTR_MCAST_GRP_MAX */
#ifndef NETLINK_EXT_ACK
#define NETLINK_CAP_ACK 10
#define NETLINK_EXT_ACK 11
/* ACK message flags. */
#define NLM_F_CAPPED 0x100
#define NLM_F_ACK_TLVS 0x200
enum {
NLMSGERR_ATTR_UNUSED,
NLMSGERR_ATTR_MSG,
NLMSGERR_ATTR_OFFS,
__NLMSGERR_ATTR_MAX,
NLMSGERR_ATTR_MAX = __NLMSGERR_ATTR_MAX - 1
};
#endif /* NLM_F_ACK_TLVS */
#endif /* netlink-protocol.h */