![Daniel Borkmann](/assets/img/avatar_default.png)
This work adds a direction parameter to netfilter zones, so identity separation can be performed only in original/reply or both directions (default). This basically opens up the possibility of doing NAT with conflicting IP address/port tuples from multiple, isolated tenants on a host (e.g. from a netns) without requiring each tenant to NAT twice resp. to use its own dedicated IP address to SNAT to, meaning overlapping tuples can be made unique with the zone identifier in original direction, where the NAT engine will then allocate a unique tuple in the commonly shared default zone for the reply direction. In some restricted, local DNAT cases, also port redirection could be used for making the reply traffic unique w/o requiring SNAT. The consensus we've reached and discussed at NFWS and since the initial implementation [1] was to directly integrate the direction meta data into the existing zones infrastructure, as opposed to the ct->mark approach we proposed initially. As we pass the nf_conntrack_zone object directly around, we don't have to touch all call-sites, but only those, that contain equality checks of zones. Thus, based on the current direction (original or reply), we either return the actual id, or the default NF_CT_DEFAULT_ZONE_ID. CT expectations are direction-agnostic entities when expectations are being compared among themselves, so we can only use the identifier in this case. Note that zone identifiers can not be included into the hash mix anymore as they don't contain a "stable" value that would be equal for both directions at all times, f.e. if only zone->id would unconditionally be xor'ed into the table slot hash, then replies won't find the corresponding conntracking entry anymore. If no particular direction is specified when configuring zones, the behaviour is exactly as we expect currently (both directions). Support has been added for the CT netlink interface as well as the x_tables raw CT target, which both already offer existing interfaces to user space for the configuration of zones. Below a minimal, simplified collision example (script in [2]) with netperf sessions: +--- tenant-1 ---+ mark := 1 | netperf |--+ +----------------+ | CT zone := mark [ORIGINAL] [ip,sport] := X +--------------+ +--- gateway ---+ | mark routing |--| SNAT |-- ... + +--------------+ +---------------+ | +--- tenant-2 ---+ | ~~~|~~~ | netperf |--+ +-----------+ | +----------------+ mark := 2 | netserver |------ ... + [ip,sport] := X +-----------+ [ip,port] := Y On the gateway netns, example: iptables -t raw -A PREROUTING -j CT --zone mark --zone-dir ORIGINAL iptables -t nat -A POSTROUTING -o <dev> -j SNAT --to-source <ip> --random-fully iptables -t mangle -A PREROUTING -m conntrack --ctdir ORIGINAL -j CONNMARK --save-mark iptables -t mangle -A POSTROUTING -m conntrack --ctdir REPLY -j CONNMARK --restore-mark conntrack dump from gateway netns: netperf -H 10.1.1.2 -t TCP_STREAM -l60 -p12865,5555 from each tenant netns tcp 6 431995 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=5555 dport=12865 zone-orig=1 src=10.1.1.2 dst=10.1.1.1 sport=12865 dport=1024 [ASSURED] mark=1 secctx=system_u:object_r:unlabeled_t:s0 use=1 tcp 6 431994 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=5555 dport=12865 zone-orig=2 src=10.1.1.2 dst=10.1.1.1 sport=12865 dport=5555 [ASSURED] mark=2 secctx=system_u:object_r:unlabeled_t:s0 use=1 tcp 6 299 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=39438 dport=33768 zone-orig=1 src=10.1.1.2 dst=10.1.1.1 sport=33768 dport=39438 [ASSURED] mark=1 secctx=system_u:object_r:unlabeled_t:s0 use=1 tcp 6 300 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=32889 dport=40206 zone-orig=2 src=10.1.1.2 dst=10.1.1.1 sport=40206 dport=32889 [ASSURED] mark=2 secctx=system_u:object_r:unlabeled_t:s0 use=2 Taking this further, test script in [2] creates 200 tenants and runs original-tuple colliding netperf sessions each. A conntrack -L dump in the gateway netns also confirms 200 overlapping entries, all in ESTABLISHED state as expected. I also did run various other tests with some permutations of the script, to mention some: SNAT in random/random-fully/persistent mode, no zones (no overlaps), static zones (original, reply, both directions), etc. [1] http://thread.gmane.org/gmane.comp.security.firewalls.netfilter.devel/57412/ [2] https://paste.fedoraproject.org/242835/65657871/ Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
196 lines
4.7 KiB
C
196 lines
4.7 KiB
C
/*
|
|
* net/sched/act_connmark.c netfilter connmark retriever action
|
|
* skb mark is over-written
|
|
*
|
|
* Copyright (c) 2011 Felix Fietkau <nbd@openwrt.org>
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License as published by
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
* (at your option) any later version.
|
|
*/
|
|
|
|
#include <linux/module.h>
|
|
#include <linux/init.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/skbuff.h>
|
|
#include <linux/rtnetlink.h>
|
|
#include <linux/pkt_cls.h>
|
|
#include <linux/ip.h>
|
|
#include <linux/ipv6.h>
|
|
#include <net/netlink.h>
|
|
#include <net/pkt_sched.h>
|
|
#include <net/act_api.h>
|
|
#include <uapi/linux/tc_act/tc_connmark.h>
|
|
#include <net/tc_act/tc_connmark.h>
|
|
|
|
#include <net/netfilter/nf_conntrack.h>
|
|
#include <net/netfilter/nf_conntrack_core.h>
|
|
#include <net/netfilter/nf_conntrack_zones.h>
|
|
|
|
#define CONNMARK_TAB_MASK 3
|
|
|
|
static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a,
|
|
struct tcf_result *res)
|
|
{
|
|
const struct nf_conntrack_tuple_hash *thash;
|
|
struct nf_conntrack_tuple tuple;
|
|
enum ip_conntrack_info ctinfo;
|
|
struct tcf_connmark_info *ca = a->priv;
|
|
struct nf_conntrack_zone zone;
|
|
struct nf_conn *c;
|
|
int proto;
|
|
|
|
spin_lock(&ca->tcf_lock);
|
|
ca->tcf_tm.lastuse = jiffies;
|
|
bstats_update(&ca->tcf_bstats, skb);
|
|
|
|
if (skb->protocol == htons(ETH_P_IP)) {
|
|
if (skb->len < sizeof(struct iphdr))
|
|
goto out;
|
|
|
|
proto = NFPROTO_IPV4;
|
|
} else if (skb->protocol == htons(ETH_P_IPV6)) {
|
|
if (skb->len < sizeof(struct ipv6hdr))
|
|
goto out;
|
|
|
|
proto = NFPROTO_IPV6;
|
|
} else {
|
|
goto out;
|
|
}
|
|
|
|
c = nf_ct_get(skb, &ctinfo);
|
|
if (c) {
|
|
skb->mark = c->mark;
|
|
/* using overlimits stats to count how many packets marked */
|
|
ca->tcf_qstats.overlimits++;
|
|
goto out;
|
|
}
|
|
|
|
if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb),
|
|
proto, &tuple))
|
|
goto out;
|
|
|
|
zone.id = ca->zone;
|
|
zone.dir = NF_CT_DEFAULT_ZONE_DIR;
|
|
|
|
thash = nf_conntrack_find_get(dev_net(skb->dev), &zone, &tuple);
|
|
if (!thash)
|
|
goto out;
|
|
|
|
c = nf_ct_tuplehash_to_ctrack(thash);
|
|
/* using overlimits stats to count how many packets marked */
|
|
ca->tcf_qstats.overlimits++;
|
|
skb->mark = c->mark;
|
|
nf_ct_put(c);
|
|
|
|
out:
|
|
spin_unlock(&ca->tcf_lock);
|
|
return ca->tcf_action;
|
|
}
|
|
|
|
static const struct nla_policy connmark_policy[TCA_CONNMARK_MAX + 1] = {
|
|
[TCA_CONNMARK_PARMS] = { .len = sizeof(struct tc_connmark) },
|
|
};
|
|
|
|
static int tcf_connmark_init(struct net *net, struct nlattr *nla,
|
|
struct nlattr *est, struct tc_action *a,
|
|
int ovr, int bind)
|
|
{
|
|
struct nlattr *tb[TCA_CONNMARK_MAX + 1];
|
|
struct tcf_connmark_info *ci;
|
|
struct tc_connmark *parm;
|
|
int ret = 0;
|
|
|
|
if (!nla)
|
|
return -EINVAL;
|
|
|
|
ret = nla_parse_nested(tb, TCA_CONNMARK_MAX, nla, connmark_policy);
|
|
if (ret < 0)
|
|
return ret;
|
|
|
|
parm = nla_data(tb[TCA_CONNMARK_PARMS]);
|
|
|
|
if (!tcf_hash_check(parm->index, a, bind)) {
|
|
ret = tcf_hash_create(parm->index, est, a, sizeof(*ci),
|
|
bind, false);
|
|
if (ret)
|
|
return ret;
|
|
|
|
ci = to_connmark(a);
|
|
ci->tcf_action = parm->action;
|
|
ci->zone = parm->zone;
|
|
|
|
tcf_hash_insert(a);
|
|
ret = ACT_P_CREATED;
|
|
} else {
|
|
ci = to_connmark(a);
|
|
if (bind)
|
|
return 0;
|
|
tcf_hash_release(a, bind);
|
|
if (!ovr)
|
|
return -EEXIST;
|
|
/* replacing action and zone */
|
|
ci->tcf_action = parm->action;
|
|
ci->zone = parm->zone;
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a,
|
|
int bind, int ref)
|
|
{
|
|
unsigned char *b = skb_tail_pointer(skb);
|
|
struct tcf_connmark_info *ci = a->priv;
|
|
|
|
struct tc_connmark opt = {
|
|
.index = ci->tcf_index,
|
|
.refcnt = ci->tcf_refcnt - ref,
|
|
.bindcnt = ci->tcf_bindcnt - bind,
|
|
.action = ci->tcf_action,
|
|
.zone = ci->zone,
|
|
};
|
|
struct tcf_t t;
|
|
|
|
if (nla_put(skb, TCA_CONNMARK_PARMS, sizeof(opt), &opt))
|
|
goto nla_put_failure;
|
|
|
|
t.install = jiffies_to_clock_t(jiffies - ci->tcf_tm.install);
|
|
t.lastuse = jiffies_to_clock_t(jiffies - ci->tcf_tm.lastuse);
|
|
t.expires = jiffies_to_clock_t(ci->tcf_tm.expires);
|
|
if (nla_put(skb, TCA_CONNMARK_TM, sizeof(t), &t))
|
|
goto nla_put_failure;
|
|
|
|
return skb->len;
|
|
nla_put_failure:
|
|
nlmsg_trim(skb, b);
|
|
return -1;
|
|
}
|
|
|
|
static struct tc_action_ops act_connmark_ops = {
|
|
.kind = "connmark",
|
|
.type = TCA_ACT_CONNMARK,
|
|
.owner = THIS_MODULE,
|
|
.act = tcf_connmark,
|
|
.dump = tcf_connmark_dump,
|
|
.init = tcf_connmark_init,
|
|
};
|
|
|
|
static int __init connmark_init_module(void)
|
|
{
|
|
return tcf_register_action(&act_connmark_ops, CONNMARK_TAB_MASK);
|
|
}
|
|
|
|
static void __exit connmark_cleanup_module(void)
|
|
{
|
|
tcf_unregister_action(&act_connmark_ops);
|
|
}
|
|
|
|
module_init(connmark_init_module);
|
|
module_exit(connmark_cleanup_module);
|
|
MODULE_AUTHOR("Felix Fietkau <nbd@openwrt.org>");
|
|
MODULE_DESCRIPTION("Connection tracking mark restoring");
|
|
MODULE_LICENSE("GPL");
|
|
|