Merge branch 'icmp-account-for-NAT-when-sending-icmps-from-ndo-layer'

Jason A. Donenfeld says:

====================
icmp: account for NAT when sending icmps from ndo layer

The ICMP routines use the source address for two reasons:

1. Rate-limiting ICMP transmissions based on source address, so
   that one source address cannot provoke a flood of replies. If
   the source address is wrong, the rate limiting will be
   incorrectly applied.

2. Choosing the interface and hence new source address of the
   generated ICMP packet. If the original packet source address
   is wrong, ICMP replies will be sent from the wrong source
   address, resulting in either a misdelivery, infoleak, or just
   general network admin confusion.

Most of the time, the icmp_send and icmpv6_send routines can just reach
down into the skb's IP header to determine the saddr. However, if
icmp_send or icmpv6_send is being called from a network device driver --
there are a few in the tree -- then it's possible that by the time
icmp_send or icmpv6_send looks at the packet, the packet's source
address has already been transformed by SNAT or MASQUERADE or some other
transformation that CONNTRACK knows about. In this case, the packet's
source address is most certainly the *wrong* source address to be used
for the purpose of ICMP replies.

Rather, the source address we want to use for ICMP replies is the
original one, from before the transformation occurred.

Fortunately, it's very easy to just ask CONNTRACK if it knows about this
packet, and if so, how to fix it up. The saddr is the only field in the
header we need to fix up, for the purposes of the subsequent processing
in the icmp_send and icmpv6_send functions, so we do the lookup very
early on, so that the rest of the ICMP machinery can progress as usual.

Changes v3->v4:
- Add back the skb_shared checking, since the previous assumption isn't
  actually true [Eric]. This implies dropping the additional patches v3 had
  for removing skb_share_check from various drivers. We can revisit that
  general set of ideas later, but that's probably better suited as a net-next
  patchset rather than this stable one which is geared at fixing bugs. So,
  this implements things in the safe conservative way.

Changes v2->v3:
- Add selftest to ensure this actually does what we want and never regresses.
- Check the size of the skb header before operating on it.
- Use skb_ensure_writable to ensure we can modify the cloned skb [Florian].
- Conditionalize this on IPS_SRC_NAT so we don't do anything unnecessarily
  [Florian].
- It turns out that since we're calling these from the xmit path,
  skb_share_check isn't required, so remove that [Florian]. This simplifes the
  code a bit too. **The supposition here is that skbs passed to ndo_start_xmit
  are _never_ shared. If this is not correct NOW IS THE TIME TO PIPE UP, for
  doom awaits us later.**
- While investigating the shared skb business, several drivers appeared to be
  calling it incorrectly in the xmit path, so this series also removes those
  unnecessary calls, based on the supposition mentioned in the previous point.

Changes v1->v2:
- icmpv6 takes subtly different types than icmpv4, like u32 instead of be32,
  u8 instead of int.
- Since we're technically writing to the skb, we need to make sure it's not
  a shared one [Dave, 2017].
- Restore the original skb data after icmp_send returns. All current users
  are freeing the packet right after, so it doesn't matter, but future users
  might not.
- Remove superfluous route lookup in sunvnet [Dave].
- Use NF_NAT instead of NF_CONNTRACK for condition [Florian].
- Include this cover letter [Dave].
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

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,
+		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;
 	}

drivers/net/gtp.c

@@ -546,7 +546,7 @@ 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,
+		icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
 			      htonl(mtu));
 		goto err_rt;
 	}

drivers/net/wireguard/device.c

@@ -203,9 +203,9 @@ static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev)
 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;
 }

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);

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);

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)
 {

net/ipv6/ip6_icmp.c

@@ -45,4 +45,38 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	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

net/xfrm/xfrm_interface.c

@@ -300,9 +300,9 @@ 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,
+			icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
 				      htonl(mtu));
 		}
 

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