From 0b41713b606694257b90d61ba7e2712d8457648b Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Tue, 11 Feb 2020 20:47:05 +0100
Subject: [PATCH 1/5] icmp: introduce helper for nat'd source address in
network device context
This introduces a helper function to be called only by network drivers
that wraps calls to icmp[v6]_send in a conntrack transformation, in case
NAT has been used. We don't want to pollute the non-driver path, though,
so we introduce this as a helper to be called by places that actually
make use of this, as suggested by Florian.
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/linux/icmpv6.h | 6 ++++++
include/net/icmp.h | 6 ++++++
net/ipv4/icmp.c | 33 +++++++++++++++++++++++++++++++++
net/ipv6/ip6_icmp.c | 34 ++++++++++++++++++++++++++++++++++
4 files changed, 79 insertions(+)
diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h
index ef1cbb5f454f..93338fd54af8 100644
--- a/include/linux/icmpv6.h
+++ b/include/linux/icmpv6.h
@@ -31,6 +31,12 @@ static inline void icmpv6_send(struct sk_buff *skb,
}
#endif
+#if IS_ENABLED(CONFIG_NF_NAT)
+void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info);
+#else
+#define icmpv6_ndo_send icmpv6_send
+#endif
+
extern int icmpv6_init(void);
extern int icmpv6_err_convert(u8 type, u8 code,
int *err);
diff --git a/include/net/icmp.h b/include/net/icmp.h
index 5d4bfdba9adf..9ac2d2672a93 100644
--- a/include/net/icmp.h
+++ b/include/net/icmp.h
@@ -43,6 +43,12 @@ static inline void icmp_send(struct sk_buff *skb_in, int type, int code, __be32
__icmp_send(skb_in, type, code, info, &IPCB(skb_in)->opt);
}
+#if IS_ENABLED(CONFIG_NF_NAT)
+void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info);
+#else
+#define icmp_ndo_send icmp_send
+#endif
+
int icmp_rcv(struct sk_buff *skb);
int icmp_err(struct sk_buff *skb, u32 info);
int icmp_init(void);
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 18068ed42f25..f369e7ce685b 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -748,6 +748,39 @@ out:;
}
EXPORT_SYMBOL(__icmp_send);
+#if IS_ENABLED(CONFIG_NF_NAT)
+#include <net/netfilter/nf_conntrack.h>
+void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info)
+{
+ struct sk_buff *cloned_skb = NULL;
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct;
+ __be32 orig_ip;
+
+ ct = nf_ct_get(skb_in, &ctinfo);
+ if (!ct || !(ct->status & IPS_SRC_NAT)) {
+ icmp_send(skb_in, type, code, info);
+ return;
+ }
+
+ if (skb_shared(skb_in))
+ skb_in = cloned_skb = skb_clone(skb_in, GFP_ATOMIC);
+
+ if (unlikely(!skb_in || skb_network_header(skb_in) < skb_in->head ||
+ (skb_network_header(skb_in) + sizeof(struct iphdr)) >
+ skb_tail_pointer(skb_in) || skb_ensure_writable(skb_in,
+ skb_network_offset(skb_in) + sizeof(struct iphdr))))
+ goto out;
+
+ orig_ip = ip_hdr(skb_in)->saddr;
+ ip_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.ip;
+ icmp_send(skb_in, type, code, info);
+ ip_hdr(skb_in)->saddr = orig_ip;
+out:
+ consume_skb(cloned_skb);
+}
+EXPORT_SYMBOL(icmp_ndo_send);
+#endif
static void icmp_socket_deliver(struct sk_buff *skb, u32 info)
{
diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c
index 02045494c24c..e0086758b6ee 100644
--- a/net/ipv6/ip6_icmp.c
+++ b/net/ipv6/ip6_icmp.c
@@ -45,4 +45,38 @@ out:
rcu_read_unlock();
}
EXPORT_SYMBOL(icmpv6_send);
+
+#if IS_ENABLED(CONFIG_NF_NAT)
+#include <net/netfilter/nf_conntrack.h>
+void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info)
+{
+ struct sk_buff *cloned_skb = NULL;
+ enum ip_conntrack_info ctinfo;
+ struct in6_addr orig_ip;
+ struct nf_conn *ct;
+
+ ct = nf_ct_get(skb_in, &ctinfo);
+ if (!ct || !(ct->status & IPS_SRC_NAT)) {
+ icmpv6_send(skb_in, type, code, info);
+ return;
+ }
+
+ if (skb_shared(skb_in))
+ skb_in = cloned_skb = skb_clone(skb_in, GFP_ATOMIC);
+
+ if (unlikely(!skb_in || skb_network_header(skb_in) < skb_in->head ||
+ (skb_network_header(skb_in) + sizeof(struct ipv6hdr)) >
+ skb_tail_pointer(skb_in) || skb_ensure_writable(skb_in,
+ skb_network_offset(skb_in) + sizeof(struct ipv6hdr))))
+ goto out;
+
+ orig_ip = ipv6_hdr(skb_in)->saddr;
+ ipv6_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.in6;
+ icmpv6_send(skb_in, type, code, info);
+ ipv6_hdr(skb_in)->saddr = orig_ip;
+out:
+ consume_skb(cloned_skb);
+}
+EXPORT_SYMBOL(icmpv6_ndo_send);
+#endif
#endif
From e0fce6f945a26d4e953a147fe7ca11410322c9fe Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Tue, 11 Feb 2020 20:47:06 +0100
Subject: [PATCH 2/5] gtp: use icmp_ndo_send helper
Because gtp is calling icmp from network device context, it should use
the ndo helper so that the rate limiting applies correctly.
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Harald Welte <laforge@gnumonks.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/gtp.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index af07ea760b35..672cd2caf2fb 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -546,8 +546,8 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
mtu < ntohs(iph->tot_len)) {
netdev_dbg(dev, "packet too big, fragmentation needed\n");
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
- htonl(mtu));
+ icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+ htonl(mtu));
goto err_rt;
}
From 67c9a7e1e3ac491b5df018803639addc36f154ba Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Tue, 11 Feb 2020 20:47:07 +0100
Subject: [PATCH 3/5] sunvnet: use icmp_ndo_send helper
Because sunvnet is calling icmp from network device context, it should use
the ndo helper so that the rate limiting applies correctly. While we're
at it, doing the additional route lookup before calling icmp_ndo_send is
superfluous, since this is the job of the icmp code in the first place.
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/sun/sunvnet_common.c | 23 ++++-------------------
1 file changed, 4 insertions(+), 19 deletions(-)
diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c
index c23ce838ff63..8dc6c9ff22e1 100644
--- a/drivers/net/ethernet/sun/sunvnet_common.c
+++ b/drivers/net/ethernet/sun/sunvnet_common.c
@@ -1350,27 +1350,12 @@ sunvnet_start_xmit_common(struct sk_buff *skb, struct net_device *dev,
if (vio_version_after_eq(&port->vio, 1, 3))
localmtu -= VLAN_HLEN;
- if (skb->protocol == htons(ETH_P_IP)) {
- struct flowi4 fl4;
- struct rtable *rt = NULL;
-
- memset(&fl4, 0, sizeof(fl4));
- fl4.flowi4_oif = dev->ifindex;
- fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
- fl4.daddr = ip_hdr(skb)->daddr;
- fl4.saddr = ip_hdr(skb)->saddr;
-
- rt = ip_route_output_key(dev_net(dev), &fl4);
- if (!IS_ERR(rt)) {
- skb_dst_set(skb, &rt->dst);
- icmp_send(skb, ICMP_DEST_UNREACH,
- ICMP_FRAG_NEEDED,
- htonl(localmtu));
- }
- }
+ if (skb->protocol == htons(ETH_P_IP))
+ icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+ htonl(localmtu));
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6))
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, localmtu);
+ icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, localmtu);
#endif
goto out_dropped;
}
From a12d7f3cbdc72c7625881c8dc2660fc2c979fdf2 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Tue, 11 Feb 2020 20:47:08 +0100
Subject: [PATCH 4/5] wireguard: device: use icmp_ndo_send helper
Because wireguard is calling icmp from network device context, it should
use the ndo helper so that the rate limiting applies correctly. This
commit adds a small test to the wireguard test suite to ensure that the
new functions continue doing the right thing in the context of
wireguard. It does this by setting up a condition that will definately
evoke an icmp error message from the driver, but along a nat'd path.
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/wireguard/device.c | 4 ++--
tools/testing/selftests/wireguard/netns.sh | 11 +++++++++++
2 files changed, 13 insertions(+), 2 deletions(-)
diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c
index 16b19824b9ad..43db442b1373 100644
--- a/drivers/net/wireguard/device.c
+++ b/drivers/net/wireguard/device.c
@@ -203,9 +203,9 @@ err_peer:
err:
++dev->stats.tx_errors;
if (skb->protocol == htons(ETH_P_IP))
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
+ icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
else if (skb->protocol == htons(ETH_P_IPV6))
- icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
+ icmpv6_ndo_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
kfree_skb(skb);
return ret;
}
diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh
index f5ab1cda8bb5..138d46b3f330 100755
--- a/tools/testing/selftests/wireguard/netns.sh
+++ b/tools/testing/selftests/wireguard/netns.sh
@@ -24,6 +24,7 @@
set -e
exec 3>&1
+export LANG=C
export WG_HIDE_KEYS=never
netns0="wg-test-$$-0"
netns1="wg-test-$$-1"
@@ -297,7 +298,17 @@ ip1 -4 rule add table main suppress_prefixlength 0
n1 ping -W 1 -c 100 -f 192.168.99.7
n1 ping -W 1 -c 100 -f abab::1111
+# Have ns2 NAT into wg0 packets from ns0, but return an icmp error along the right route.
+n2 iptables -t nat -A POSTROUTING -s 10.0.0.0/24 -d 192.168.241.0/24 -j SNAT --to 192.168.241.2
+n0 iptables -t filter -A INPUT \! -s 10.0.0.0/24 -i vethrs -j DROP # Manual rpfilter just to be explicit.
+n2 bash -c 'printf 1 > /proc/sys/net/ipv4/ip_forward'
+ip0 -4 route add 192.168.241.1 via 10.0.0.100
+n2 wg set wg0 peer "$pub1" remove
+[[ $(! n0 ping -W 1 -c 1 192.168.241.1 || false) == *"From 10.0.0.100 icmp_seq=1 Destination Host Unreachable"* ]]
+
n0 iptables -t nat -F
+n0 iptables -t filter -F
+n2 iptables -t nat -F
ip0 link del vethrc
ip0 link del vethrs
ip1 link del wg0
From 45942ba890e6f35232727a5fa33d732681f4eb9f Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Tue, 11 Feb 2020 20:47:09 +0100
Subject: [PATCH 5/5] xfrm: interface: use icmp_ndo_send helper
Because xfrmi is calling icmp from network device context, it should use
the ndo helper so that the rate limiting applies correctly.
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/xfrm/xfrm_interface.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index dc651a628dcf..3361e3ac5714 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -300,10 +300,10 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
} else {
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
- htonl(mtu));
+ icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+ htonl(mtu));
}
dst_release(dst);