2019-05-29 22:18:09 +08:00
|
|
|
/* SPDX-License-Identifier: GPL-2.0-only */
|
2015-08-27 02:31:48 +08:00
|
|
|
/*
|
|
|
|
|
* Copyright (c) 2015 Nicira, Inc.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#ifndef OVS_CONNTRACK_H
|
|
|
|
|
#define OVS_CONNTRACK_H 1
|
|
|
|
|
|
|
|
|
|
#include "flow.h"
|
|
|
|
|
|
|
|
|
|
struct ovs_conntrack_info;
|
openvswitch: Support conntrack zone limit
Currently, nf_conntrack_max is used to limit the maximum number of
conntrack entries in the conntrack table for every network namespace.
For the VMs and containers that reside in the same namespace,
they share the same conntrack table, and the total # of conntrack entries
for all the VMs and containers are limited by nf_conntrack_max. In this
case, if one of the VM/container abuses the usage the conntrack entries,
it blocks the others from committing valid conntrack entries into the
conntrack table. Even if we can possibly put the VM in different network
namespace, the current nf_conntrack_max configuration is kind of rigid
that we cannot limit different VM/container to have different # conntrack
entries.
To address the aforementioned issue, this patch proposes to have a
fine-grained mechanism that could further limit the # of conntrack entries
per-zone. For example, we can designate different zone to different VM,
and set conntrack limit to each zone. By providing this isolation, a
mis-behaved VM only consumes the conntrack entries in its own zone, and
it will not influence other well-behaved VMs. Moreover, the users can
set various conntrack limit to different zone based on their preference.
The proposed implementation utilizes Netfilter's nf_conncount backend
to count the number of connections in a particular zone. If the number of
connection is above a configured limitation, ovs will return ENOMEM to the
userspace. If userspace does not configure the zone limit, the limit
defaults to zero that is no limitation, which is backward compatible to
the behavior without this patch.
The following high leve APIs are provided to the userspace:
- OVS_CT_LIMIT_CMD_SET:
* set default connection limit for all zones
* set the connection limit for a particular zone
- OVS_CT_LIMIT_CMD_DEL:
* remove the connection limit for a particular zone
- OVS_CT_LIMIT_CMD_GET:
* get the default connection limit for all zones
* get the connection limit for a particular zone
Signed-off-by: Yi-Hung Wei <yihung.wei@gmail.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-25 08:56:43 +08:00
|
|
|
struct ovs_ct_limit_info;
|
2015-08-27 02:31:48 +08:00
|
|
|
enum ovs_key_attr;
|
|
|
|
|
|
2015-09-05 04:07:40 +08:00
|
|
|
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
|
openvswitch: Support conntrack zone limit
Currently, nf_conntrack_max is used to limit the maximum number of
conntrack entries in the conntrack table for every network namespace.
For the VMs and containers that reside in the same namespace,
they share the same conntrack table, and the total # of conntrack entries
for all the VMs and containers are limited by nf_conntrack_max. In this
case, if one of the VM/container abuses the usage the conntrack entries,
it blocks the others from committing valid conntrack entries into the
conntrack table. Even if we can possibly put the VM in different network
namespace, the current nf_conntrack_max configuration is kind of rigid
that we cannot limit different VM/container to have different # conntrack
entries.
To address the aforementioned issue, this patch proposes to have a
fine-grained mechanism that could further limit the # of conntrack entries
per-zone. For example, we can designate different zone to different VM,
and set conntrack limit to each zone. By providing this isolation, a
mis-behaved VM only consumes the conntrack entries in its own zone, and
it will not influence other well-behaved VMs. Moreover, the users can
set various conntrack limit to different zone based on their preference.
The proposed implementation utilizes Netfilter's nf_conncount backend
to count the number of connections in a particular zone. If the number of
connection is above a configured limitation, ovs will return ENOMEM to the
userspace. If userspace does not configure the zone limit, the limit
defaults to zero that is no limitation, which is backward compatible to
the behavior without this patch.
The following high leve APIs are provided to the userspace:
- OVS_CT_LIMIT_CMD_SET:
* set default connection limit for all zones
* set the connection limit for a particular zone
- OVS_CT_LIMIT_CMD_DEL:
* remove the connection limit for a particular zone
- OVS_CT_LIMIT_CMD_GET:
* get the default connection limit for all zones
* get the connection limit for a particular zone
Signed-off-by: Yi-Hung Wei <yihung.wei@gmail.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-25 08:56:43 +08:00
|
|
|
int ovs_ct_init(struct net *);
|
2015-08-27 02:31:52 +08:00
|
|
|
void ovs_ct_exit(struct net *);
|
|
|
|
|
bool ovs_ct_verify(struct net *, enum ovs_key_attr attr);
|
2015-08-27 02:31:48 +08:00
|
|
|
int ovs_ct_copy_action(struct net *, const struct nlattr *,
|
|
|
|
|
const struct sw_flow_key *, struct sw_flow_actions **,
|
|
|
|
|
bool log);
|
|
|
|
|
int ovs_ct_action_to_attr(const struct ovs_conntrack_info *, struct sk_buff *);
|
|
|
|
|
|
|
|
|
|
int ovs_ct_execute(struct net *, struct sk_buff *, struct sw_flow_key *,
|
|
|
|
|
const struct ovs_conntrack_info *);
|
2017-10-11 04:54:44 +08:00
|
|
|
int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key);
|
2015-08-27 02:31:48 +08:00
|
|
|
|
|
|
|
|
void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key);
|
openvswitch: Add original direction conntrack tuple to sw_flow_key.
Add the fields of the conntrack original direction 5-tuple to struct
sw_flow_key. The new fields are initially marked as non-existent, and
are populated whenever a conntrack action is executed and either finds
or generates a conntrack entry. This means that these fields exist
for all packets that were not rejected by conntrack as untrackable.
The original tuple fields in the sw_flow_key are filled from the
original direction tuple of the conntrack entry relating to the
current packet, or from the original direction tuple of the master
conntrack entry, if the current conntrack entry has a master.
Generally, expected connections of connections having an assigned
helper (e.g., FTP), have a master conntrack entry.
The main purpose of the new conntrack original tuple fields is to
allow matching on them for policy decision purposes, with the premise
that the admissibility of tracked connections reply packets (as well
as original direction packets), and both direction packets of any
related connections may be based on ACL rules applying to the master
connection's original direction 5-tuple. This also makes it easier to
make policy decisions when the actual packet headers might have been
transformed by NAT, as the original direction 5-tuple represents the
packet headers before any such transformation.
When using the original direction 5-tuple the admissibility of return
and/or related packets need not be based on the mere existence of a
conntrack entry, allowing separation of admission policy from the
established conntrack state. While existence of a conntrack entry is
required for admission of the return or related packets, policy
changes can render connections that were initially admitted to be
rejected or dropped afterwards. If the admission of the return and
related packets was based on mere conntrack state (e.g., connection
being in an established state), a policy change that would make the
connection rejected or dropped would need to find and delete all
conntrack entries affected by such a change. When using the original
direction 5-tuple matching the affected conntrack entries can be
allowed to time out instead, as the established state of the
connection would not need to be the basis for packet admission any
more.
It should be noted that the directionality of related connections may
be the same or different than that of the master connection, and
neither the original direction 5-tuple nor the conntrack state bits
carry this information. If needed, the directionality of the master
connection can be stored in master's conntrack mark or labels, which
are automatically inherited by the expected related connections.
The fact that neither ARP nor ND packets are trackable by conntrack
allows mutual exclusion between ARP/ND and the new conntrack original
tuple fields. Hence, the IP addresses are overlaid in union with ARP
and ND fields. This allows the sw_flow_key to not grow much due to
this patch, but it also means that we must be careful to never use the
new key fields with ARP or ND packets. ARP is easy to distinguish and
keep mutually exclusive based on the ethernet type, but ND being an
ICMPv6 protocol requires a bit more attention.
Signed-off-by: Jarno Rajahalme <jarno@ovn.org>
Acked-by: Joe Stringer <joe@ovn.org>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-10 03:21:59 +08:00
|
|
|
int ovs_ct_put_key(const struct sw_flow_key *swkey,
|
|
|
|
|
const struct sw_flow_key *output, struct sk_buff *skb);
|
2015-08-27 02:31:48 +08:00
|
|
|
void ovs_ct_free_action(const struct nlattr *a);
|
2015-10-07 01:59:59 +08:00
|
|
|
|
2015-10-20 10:18:57 +08:00
|
|
|
#define CT_SUPPORTED_MASK (OVS_CS_F_NEW | OVS_CS_F_ESTABLISHED | \
|
|
|
|
|
OVS_CS_F_RELATED | OVS_CS_F_REPLY_DIR | \
|
2016-03-11 02:54:23 +08:00
|
|
|
OVS_CS_F_INVALID | OVS_CS_F_TRACKED | \
|
|
|
|
|
OVS_CS_F_SRC_NAT | OVS_CS_F_DST_NAT)
|
2015-08-27 02:31:48 +08:00
|
|
|
#else
|
|
|
|
|
#include <linux/errno.h>
|
|
|
|
|
|
openvswitch: Support conntrack zone limit
Currently, nf_conntrack_max is used to limit the maximum number of
conntrack entries in the conntrack table for every network namespace.
For the VMs and containers that reside in the same namespace,
they share the same conntrack table, and the total # of conntrack entries
for all the VMs and containers are limited by nf_conntrack_max. In this
case, if one of the VM/container abuses the usage the conntrack entries,
it blocks the others from committing valid conntrack entries into the
conntrack table. Even if we can possibly put the VM in different network
namespace, the current nf_conntrack_max configuration is kind of rigid
that we cannot limit different VM/container to have different # conntrack
entries.
To address the aforementioned issue, this patch proposes to have a
fine-grained mechanism that could further limit the # of conntrack entries
per-zone. For example, we can designate different zone to different VM,
and set conntrack limit to each zone. By providing this isolation, a
mis-behaved VM only consumes the conntrack entries in its own zone, and
it will not influence other well-behaved VMs. Moreover, the users can
set various conntrack limit to different zone based on their preference.
The proposed implementation utilizes Netfilter's nf_conncount backend
to count the number of connections in a particular zone. If the number of
connection is above a configured limitation, ovs will return ENOMEM to the
userspace. If userspace does not configure the zone limit, the limit
defaults to zero that is no limitation, which is backward compatible to
the behavior without this patch.
The following high leve APIs are provided to the userspace:
- OVS_CT_LIMIT_CMD_SET:
* set default connection limit for all zones
* set the connection limit for a particular zone
- OVS_CT_LIMIT_CMD_DEL:
* remove the connection limit for a particular zone
- OVS_CT_LIMIT_CMD_GET:
* get the default connection limit for all zones
* get the connection limit for a particular zone
Signed-off-by: Yi-Hung Wei <yihung.wei@gmail.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-25 08:56:43 +08:00
|
|
|
static inline int ovs_ct_init(struct net *net) { return 0; }
|
2015-08-27 02:31:52 +08:00
|
|
|
|
|
|
|
|
static inline void ovs_ct_exit(struct net *net) { }
|
|
|
|
|
|
|
|
|
|
static inline bool ovs_ct_verify(struct net *net, int attr)
|
2015-08-27 02:31:48 +08:00
|
|
|
{
|
|
|
|
|
return false;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline int ovs_ct_copy_action(struct net *net, const struct nlattr *nla,
|
|
|
|
|
const struct sw_flow_key *key,
|
|
|
|
|
struct sw_flow_actions **acts, bool log)
|
|
|
|
|
{
|
|
|
|
|
return -ENOTSUPP;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline int ovs_ct_action_to_attr(const struct ovs_conntrack_info *info,
|
|
|
|
|
struct sk_buff *skb)
|
|
|
|
|
{
|
|
|
|
|
return -ENOTSUPP;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline int ovs_ct_execute(struct net *net, struct sk_buff *skb,
|
|
|
|
|
struct sw_flow_key *key,
|
|
|
|
|
const struct ovs_conntrack_info *info)
|
|
|
|
|
{
|
2015-10-26 11:21:48 +08:00
|
|
|
kfree_skb(skb);
|
2015-08-27 02:31:48 +08:00
|
|
|
return -ENOTSUPP;
|
|
|
|
|
}
|
|
|
|
|
|
2017-10-11 04:54:44 +08:00
|
|
|
static inline int ovs_ct_clear(struct sk_buff *skb,
|
|
|
|
|
struct sw_flow_key *key)
|
|
|
|
|
{
|
|
|
|
|
return -ENOTSUPP;
|
|
|
|
|
}
|
|
|
|
|
|
2015-08-27 02:31:48 +08:00
|
|
|
static inline void ovs_ct_fill_key(const struct sk_buff *skb,
|
|
|
|
|
struct sw_flow_key *key)
|
|
|
|
|
{
|
2017-02-10 03:22:01 +08:00
|
|
|
key->ct_state = 0;
|
|
|
|
|
key->ct_zone = 0;
|
2015-08-27 02:31:49 +08:00
|
|
|
key->ct.mark = 0;
|
2015-10-02 06:00:37 +08:00
|
|
|
memset(&key->ct.labels, 0, sizeof(key->ct.labels));
|
2017-02-10 03:22:01 +08:00
|
|
|
/* Clear 'ct_orig_proto' to mark the non-existence of original
|
openvswitch: Add original direction conntrack tuple to sw_flow_key.
Add the fields of the conntrack original direction 5-tuple to struct
sw_flow_key. The new fields are initially marked as non-existent, and
are populated whenever a conntrack action is executed and either finds
or generates a conntrack entry. This means that these fields exist
for all packets that were not rejected by conntrack as untrackable.
The original tuple fields in the sw_flow_key are filled from the
original direction tuple of the conntrack entry relating to the
current packet, or from the original direction tuple of the master
conntrack entry, if the current conntrack entry has a master.
Generally, expected connections of connections having an assigned
helper (e.g., FTP), have a master conntrack entry.
The main purpose of the new conntrack original tuple fields is to
allow matching on them for policy decision purposes, with the premise
that the admissibility of tracked connections reply packets (as well
as original direction packets), and both direction packets of any
related connections may be based on ACL rules applying to the master
connection's original direction 5-tuple. This also makes it easier to
make policy decisions when the actual packet headers might have been
transformed by NAT, as the original direction 5-tuple represents the
packet headers before any such transformation.
When using the original direction 5-tuple the admissibility of return
and/or related packets need not be based on the mere existence of a
conntrack entry, allowing separation of admission policy from the
established conntrack state. While existence of a conntrack entry is
required for admission of the return or related packets, policy
changes can render connections that were initially admitted to be
rejected or dropped afterwards. If the admission of the return and
related packets was based on mere conntrack state (e.g., connection
being in an established state), a policy change that would make the
connection rejected or dropped would need to find and delete all
conntrack entries affected by such a change. When using the original
direction 5-tuple matching the affected conntrack entries can be
allowed to time out instead, as the established state of the
connection would not need to be the basis for packet admission any
more.
It should be noted that the directionality of related connections may
be the same or different than that of the master connection, and
neither the original direction 5-tuple nor the conntrack state bits
carry this information. If needed, the directionality of the master
connection can be stored in master's conntrack mark or labels, which
are automatically inherited by the expected related connections.
The fact that neither ARP nor ND packets are trackable by conntrack
allows mutual exclusion between ARP/ND and the new conntrack original
tuple fields. Hence, the IP addresses are overlaid in union with ARP
and ND fields. This allows the sw_flow_key to not grow much due to
this patch, but it also means that we must be careful to never use the
new key fields with ARP or ND packets. ARP is easy to distinguish and
keep mutually exclusive based on the ethernet type, but ND being an
ICMPv6 protocol requires a bit more attention.
Signed-off-by: Jarno Rajahalme <jarno@ovn.org>
Acked-by: Joe Stringer <joe@ovn.org>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-10 03:21:59 +08:00
|
|
|
* direction key fields.
|
|
|
|
|
*/
|
2017-02-10 03:22:01 +08:00
|
|
|
key->ct_orig_proto = 0;
|
2015-08-27 02:31:48 +08:00
|
|
|
}
|
|
|
|
|
|
openvswitch: Add original direction conntrack tuple to sw_flow_key.
Add the fields of the conntrack original direction 5-tuple to struct
sw_flow_key. The new fields are initially marked as non-existent, and
are populated whenever a conntrack action is executed and either finds
or generates a conntrack entry. This means that these fields exist
for all packets that were not rejected by conntrack as untrackable.
The original tuple fields in the sw_flow_key are filled from the
original direction tuple of the conntrack entry relating to the
current packet, or from the original direction tuple of the master
conntrack entry, if the current conntrack entry has a master.
Generally, expected connections of connections having an assigned
helper (e.g., FTP), have a master conntrack entry.
The main purpose of the new conntrack original tuple fields is to
allow matching on them for policy decision purposes, with the premise
that the admissibility of tracked connections reply packets (as well
as original direction packets), and both direction packets of any
related connections may be based on ACL rules applying to the master
connection's original direction 5-tuple. This also makes it easier to
make policy decisions when the actual packet headers might have been
transformed by NAT, as the original direction 5-tuple represents the
packet headers before any such transformation.
When using the original direction 5-tuple the admissibility of return
and/or related packets need not be based on the mere existence of a
conntrack entry, allowing separation of admission policy from the
established conntrack state. While existence of a conntrack entry is
required for admission of the return or related packets, policy
changes can render connections that were initially admitted to be
rejected or dropped afterwards. If the admission of the return and
related packets was based on mere conntrack state (e.g., connection
being in an established state), a policy change that would make the
connection rejected or dropped would need to find and delete all
conntrack entries affected by such a change. When using the original
direction 5-tuple matching the affected conntrack entries can be
allowed to time out instead, as the established state of the
connection would not need to be the basis for packet admission any
more.
It should be noted that the directionality of related connections may
be the same or different than that of the master connection, and
neither the original direction 5-tuple nor the conntrack state bits
carry this information. If needed, the directionality of the master
connection can be stored in master's conntrack mark or labels, which
are automatically inherited by the expected related connections.
The fact that neither ARP nor ND packets are trackable by conntrack
allows mutual exclusion between ARP/ND and the new conntrack original
tuple fields. Hence, the IP addresses are overlaid in union with ARP
and ND fields. This allows the sw_flow_key to not grow much due to
this patch, but it also means that we must be careful to never use the
new key fields with ARP or ND packets. ARP is easy to distinguish and
keep mutually exclusive based on the ethernet type, but ND being an
ICMPv6 protocol requires a bit more attention.
Signed-off-by: Jarno Rajahalme <jarno@ovn.org>
Acked-by: Joe Stringer <joe@ovn.org>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-10 03:21:59 +08:00
|
|
|
static inline int ovs_ct_put_key(const struct sw_flow_key *swkey,
|
|
|
|
|
const struct sw_flow_key *output,
|
2015-08-27 02:31:48 +08:00
|
|
|
struct sk_buff *skb)
|
|
|
|
|
{
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void ovs_ct_free_action(const struct nlattr *a) { }
|
2015-10-20 10:18:57 +08:00
|
|
|
|
|
|
|
|
#define CT_SUPPORTED_MASK 0
|
2015-09-05 04:07:40 +08:00
|
|
|
#endif /* CONFIG_NF_CONNTRACK */
|
openvswitch: Support conntrack zone limit
Currently, nf_conntrack_max is used to limit the maximum number of
conntrack entries in the conntrack table for every network namespace.
For the VMs and containers that reside in the same namespace,
they share the same conntrack table, and the total # of conntrack entries
for all the VMs and containers are limited by nf_conntrack_max. In this
case, if one of the VM/container abuses the usage the conntrack entries,
it blocks the others from committing valid conntrack entries into the
conntrack table. Even if we can possibly put the VM in different network
namespace, the current nf_conntrack_max configuration is kind of rigid
that we cannot limit different VM/container to have different # conntrack
entries.
To address the aforementioned issue, this patch proposes to have a
fine-grained mechanism that could further limit the # of conntrack entries
per-zone. For example, we can designate different zone to different VM,
and set conntrack limit to each zone. By providing this isolation, a
mis-behaved VM only consumes the conntrack entries in its own zone, and
it will not influence other well-behaved VMs. Moreover, the users can
set various conntrack limit to different zone based on their preference.
The proposed implementation utilizes Netfilter's nf_conncount backend
to count the number of connections in a particular zone. If the number of
connection is above a configured limitation, ovs will return ENOMEM to the
userspace. If userspace does not configure the zone limit, the limit
defaults to zero that is no limitation, which is backward compatible to
the behavior without this patch.
The following high leve APIs are provided to the userspace:
- OVS_CT_LIMIT_CMD_SET:
* set default connection limit for all zones
* set the connection limit for a particular zone
- OVS_CT_LIMIT_CMD_DEL:
* remove the connection limit for a particular zone
- OVS_CT_LIMIT_CMD_GET:
* get the default connection limit for all zones
* get the connection limit for a particular zone
Signed-off-by: Yi-Hung Wei <yihung.wei@gmail.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-25 08:56:43 +08:00
|
|
|
|
|
|
|
|
#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
|
|
|
|
|
extern struct genl_family dp_ct_limit_genl_family;
|
|
|
|
|
#endif
|
2015-08-27 02:31:48 +08:00
|
|
|
#endif /* ovs_conntrack.h */
|