Revision a82c25c366b0963d33ddf699196e6cf57f6d89b1 authored by Florian Westphal on 08 March 2022, 12:52:11 UTC, committed by Florian Westphal on 08 March 2022, 12:52:11 UTC
This reverts commit 878aed8db324bec64f3c3f956e64d5ae7375a5de.

This change breaks existing setups where conntrack is used with
asymmetric paths.

In these cases, the NAT transformation occurs on the syn-ack instead of
the syn:

1. SYN    x:12345 -> y -> 443 // sent by initiator, receiverd by responder
2. SYNACK y:443 -> x:12345 // First packet seen by conntrack, as sent by responder
3. tuple_force_port_remap() gets called, sees:
  'tcp from 443 to port 12345 NAT' -> pick a new source port, inititor receives
4. SYNACK y:$RANDOM -> x:12345   // connection is never established

While its possible to avoid the breakage with NOTRACK rules, a kernel
update should not break working setups.

An alternative to the revert is to augment conntrack to tag
mid-stream connections plus more code in the nat core to skip NAT
for such connections, however, this leads to more interaction/integration
between conntrack and NAT.

Therefore, revert, users will need to add explicit nat rules to avoid
port shadowing.

Link: https://lore.kernel.org/netfilter-devel/20220302105908.GA5852@breakpoint.cc/#R
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2051413
Signed-off-by: Florian Westphal <fw@strlen.de>
1 parent f8e9bd3
Raw File
xt_dscp.c
// SPDX-License-Identifier: GPL-2.0-only
/* IP tables module for matching the value of the IPv4/IPv6 DSCP field
 *
 * (C) 2002 by Harald Welte <laforge@netfilter.org>
 */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <net/dsfield.h>

#include <linux/netfilter/x_tables.h>
#include <linux/netfilter/xt_dscp.h>

MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>");
MODULE_DESCRIPTION("Xtables: DSCP/TOS field match");
MODULE_LICENSE("GPL");
MODULE_ALIAS("ipt_dscp");
MODULE_ALIAS("ip6t_dscp");
MODULE_ALIAS("ipt_tos");
MODULE_ALIAS("ip6t_tos");

static bool
dscp_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
	const struct xt_dscp_info *info = par->matchinfo;
	u_int8_t dscp = ipv4_get_dsfield(ip_hdr(skb)) >> XT_DSCP_SHIFT;

	return (dscp == info->dscp) ^ !!info->invert;
}

static bool
dscp_mt6(const struct sk_buff *skb, struct xt_action_param *par)
{
	const struct xt_dscp_info *info = par->matchinfo;
	u_int8_t dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> XT_DSCP_SHIFT;

	return (dscp == info->dscp) ^ !!info->invert;
}

static int dscp_mt_check(const struct xt_mtchk_param *par)
{
	const struct xt_dscp_info *info = par->matchinfo;

	if (info->dscp > XT_DSCP_MAX)
		return -EDOM;

	return 0;
}

static bool tos_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
	const struct xt_tos_match_info *info = par->matchinfo;

	if (xt_family(par) == NFPROTO_IPV4)
		return ((ip_hdr(skb)->tos & info->tos_mask) ==
		       info->tos_value) ^ !!info->invert;
	else
		return ((ipv6_get_dsfield(ipv6_hdr(skb)) & info->tos_mask) ==
		       info->tos_value) ^ !!info->invert;
}

static struct xt_match dscp_mt_reg[] __read_mostly = {
	{
		.name		= "dscp",
		.family		= NFPROTO_IPV4,
		.checkentry	= dscp_mt_check,
		.match		= dscp_mt,
		.matchsize	= sizeof(struct xt_dscp_info),
		.me		= THIS_MODULE,
	},
	{
		.name		= "dscp",
		.family		= NFPROTO_IPV6,
		.checkentry	= dscp_mt_check,
		.match		= dscp_mt6,
		.matchsize	= sizeof(struct xt_dscp_info),
		.me		= THIS_MODULE,
	},
	{
		.name		= "tos",
		.revision	= 1,
		.family		= NFPROTO_IPV4,
		.match		= tos_mt,
		.matchsize	= sizeof(struct xt_tos_match_info),
		.me		= THIS_MODULE,
	},
	{
		.name		= "tos",
		.revision	= 1,
		.family		= NFPROTO_IPV6,
		.match		= tos_mt,
		.matchsize	= sizeof(struct xt_tos_match_info),
		.me		= THIS_MODULE,
	},
};

static int __init dscp_mt_init(void)
{
	return xt_register_matches(dscp_mt_reg, ARRAY_SIZE(dscp_mt_reg));
}

static void __exit dscp_mt_exit(void)
{
	xt_unregister_matches(dscp_mt_reg, ARRAY_SIZE(dscp_mt_reg));
}

module_init(dscp_mt_init);
module_exit(dscp_mt_exit);
back to top