Merge branch 'ipv4-icmp-fix-source-ip-derivation-in-presence-of-vrfs'

Ido Schimmel says:

====================
ipv4: icmp: Fix source IP derivation in presence of VRFs

Align IPv4 with IPv6 and in the presence of VRFs generate ICMP error
messages with a source IP that is derived from the receiving interface
and not from its VRF master. This is especially important when the error
messages are "Time Exceeded" messages as it means that utilities like
traceroute will show an incorrect packet path.

Patches #1-#2 are preparations.

Patch #3 is the actual change.

Patches #4-#7 make small improvements in the existing traceroute test.

Patch #8 extends the traceroute test with VRF test cases for both IPv4
and IPv6.

Changes since v1 [1]:
* Rebase.

[1] https://lore.kernel.org/netdev/20250901083027.183468-1-idosch@nvidia.com/
====================

Link: https://patch.msgid.link/20250908073238.119240-1-idosch@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

5 files changed, 229 insertions, 69 deletions

diff --git a/include/net/icmp.h b/include/net/icmp.h
index caddf4a59ad1..935ee13d9ae9 100644
--- a/include/net/icmp.h
+++ b/include/net/icmp.h
@@ -37,10 +37,10 @@ struct sk_buff;
 struct net;
 
 void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
-		 const struct ip_options *opt);
+		 const struct inet_skb_parm *parm);
 static inline void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 {
-	__icmp_send(skb_in, type, code, info, &IPCB(skb_in)->opt);
+	__icmp_send(skb_in, type, code, info, IPCB(skb_in));
 }
 
 #if IS_ENABLED(CONFIG_NF_NAT)
@@ -48,8 +48,10 @@ void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info);
 #else
 static inline void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 {
-	struct ip_options opts = { 0 };
-	__icmp_send(skb_in, type, code, info, &opts);
+	struct inet_skb_parm parm;
+
+	memset(&parm, 0, sizeof(parm));
+	__icmp_send(skb_in, type, code, info, &parm);
 }
 #endif
 
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 740af8541d2f..709021197e1c 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1715,8 +1715,7 @@ validate_return:
  */
 void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway)
 {
-	unsigned char optbuf[sizeof(struct ip_options) + 40];
-	struct ip_options *opt = (struct ip_options *)optbuf;
+	struct inet_skb_parm parm;
 	int res;
 
 	if (ip_hdr(skb)->protocol == IPPROTO_ICMP || error != -EACCES)
@@ -1727,19 +1726,19 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway)
 	 * so we can not use icmp_send and IPCB here.
 	 */
 
-	memset(opt, 0, sizeof(struct ip_options));
-	opt->optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr);
+	memset(&parm, 0, sizeof(parm));
+	parm.opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr);
 	rcu_read_lock();
-	res = __ip_options_compile(dev_net(skb->dev), opt, skb, NULL);
+	res = __ip_options_compile(dev_net(skb->dev), &parm.opt, skb, NULL);
 	rcu_read_unlock();
 
 	if (res)
 		return;
 
 	if (gateway)
-		__icmp_send(skb, ICMP_DEST_UNREACH, ICMP_NET_ANO, 0, opt);
+		__icmp_send(skb, ICMP_DEST_UNREACH, ICMP_NET_ANO, 0, &parm);
 	else
-		__icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_ANO, 0, opt);
+		__icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_ANO, 0, &parm);
 }
 
 /**
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 863bf5023f2a..1b7fb5d935ed 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -594,7 +594,7 @@ relookup_failed:
  */
 
 void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
-		 const struct ip_options *opt)
+		 const struct inet_skb_parm *parm)
 {
 	struct iphdr *iph;
 	int room;
@@ -710,7 +710,8 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 		rcu_read_lock();
 		if (rt_is_input_route(rt) &&
 		    READ_ONCE(net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr))
-			dev = dev_get_by_index_rcu(net, inet_iif(skb_in));
+			dev = dev_get_by_index_rcu(net, parm->iif ? parm->iif :
+						   inet_iif(skb_in));
 
 		if (dev)
 			saddr = inet_select_addr(dev, iph->saddr,
@@ -725,7 +726,8 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 					   iph->tos;
 	mark = IP4_REPLY_MARK(net, skb_in->mark);
 
-	if (__ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in, opt))
+	if (__ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in,
+			      &parm->opt))
 		goto out_unlock;
 
 
@@ -799,15 +801,16 @@ EXPORT_SYMBOL(__icmp_send);
 void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 {
 	struct sk_buff *cloned_skb = NULL;
-	struct ip_options opts = { 0 };
 	enum ip_conntrack_info ctinfo;
 	enum ip_conntrack_dir dir;
+	struct inet_skb_parm parm;
 	struct nf_conn *ct;
 	__be32 orig_ip;
 
+	memset(&parm, 0, sizeof(parm));
 	ct = nf_ct_get(skb_in, &ctinfo);
 	if (!ct || !(READ_ONCE(ct->status) & IPS_NAT_MASK)) {
-		__icmp_send(skb_in, type, code, info, &opts);
+		__icmp_send(skb_in, type, code, info, &parm);
 		return;
 	}
 
@@ -823,7 +826,7 @@ void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 	orig_ip = ip_hdr(skb_in)->saddr;
 	dir = CTINFO2DIR(ctinfo);
 	ip_hdr(skb_in)->saddr = ct->tuplehash[dir].tuple.src.u3.ip;
-	__icmp_send(skb_in, type, code, info, &opts);
+	__icmp_send(skb_in, type, code, info, &parm);
 	ip_hdr(skb_in)->saddr = orig_ip;
 out:
 	consume_skb(cloned_skb);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 50309f2ab132..6d27d3610c1c 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1222,8 +1222,8 @@ EXPORT_INDIRECT_CALLABLE(ipv4_dst_check);
 
 static void ipv4_send_dest_unreach(struct sk_buff *skb)
 {
+	struct inet_skb_parm parm;
 	struct net_device *dev;
-	struct ip_options opt;
 	int res;
 
 	/* Recompile ip options since IPCB may not be valid anymore.
@@ -1233,21 +1233,21 @@ static void ipv4_send_dest_unreach(struct sk_buff *skb)
 	    ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5)
 		return;
 
-	memset(&opt, 0, sizeof(opt));
+	memset(&parm, 0, sizeof(parm));
 	if (ip_hdr(skb)->ihl > 5) {
 		if (!pskb_network_may_pull(skb, ip_hdr(skb)->ihl * 4))
 			return;
-		opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr);
+		parm.opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr);
 
 		rcu_read_lock();
 		dev = skb->dev ? skb->dev : skb_rtable(skb)->dst.dev;
-		res = __ip_options_compile(dev_net(dev), &opt, skb, NULL);
+		res = __ip_options_compile(dev_net(dev), &parm.opt, skb, NULL);
 		rcu_read_unlock();
 
 		if (res)
 			return;
 	}
-	__icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt);
+	__icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &parm);
 }
 
 static void ipv4_link_failure(struct sk_buff *skb)
diff --git a/tools/testing/selftests/net/traceroute.sh b/tools/testing/selftests/net/traceroute.sh
index 282f14760940..dbb34c7e09ce 100755
--- a/tools/testing/selftests/net/traceroute.sh
+++ b/tools/testing/selftests/net/traceroute.sh
@@ -10,28 +10,6 @@ PAUSE_ON_FAIL=no
 
 ################################################################################
 #
-log_test()
-{
-	local rc=$1
-	local expected=$2
-	local msg="$3"
-
-	if [ ${rc} -eq ${expected} ]; then
-		printf "TEST: %-60s  [ OK ]\n" "${msg}"
-		nsuccess=$((nsuccess+1))
-	else
-		ret=1
-		nfail=$((nfail+1))
-		printf "TEST: %-60s  [FAIL]\n" "${msg}"
-		if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
-			echo
-			echo "hit enter to continue, 'q' to quit"
-			read a
-			[ "$a" = "q" ] && exit 1
-		fi
-	fi
-}
-
 run_cmd()
 {
 	local ns
@@ -203,34 +181,137 @@ setup_traceroute6()
 
 run_traceroute6()
 {
-	if [ ! -x "$(command -v traceroute6)" ]; then
-		echo "SKIP: Could not run IPV6 test without traceroute6"
-		return
-	fi
-
 	setup_traceroute6
 
+	RET=0
+
 	# traceroute6 host-2 from host-1 (expects 2000:102::2)
 	run_cmd $h1 "traceroute6 2000:103::4 | grep -q 2000:102::2"
-	log_test $? 0 "IPV6 traceroute"
+	check_err $? "traceroute6 did not return 2000:102::2"
+	log_test "IPv6 traceroute"
 
 	cleanup_traceroute6
 }
 
 ################################################################################
+# traceroute6 with VRF test
+#
+# Verify that in this scenario
+#
+#        ------------------------ N2
+#         |                    |
+#       ------              ------  N3  ----
+#       | R1 |              | R2 |------|H2|
+#       ------              ------      ----
+#         |                    |
+#        ------------------------ N1
+#                  |
+#                 ----
+#                 |H1|
+#                 ----
+#
+# Where H1's default route goes through R1 and R1's default route goes through
+# R2 over N2, traceroute6 from H1 to H2 reports R2's address on N2 and not N1.
+# The interfaces connecting R2 to the different subnets are membmer in a VRF
+# and the intention is to check that traceroute6 does not report the VRF's
+# address.
+#
+# Addresses are assigned as follows:
+#
+# N1: 2000:101::/64
+# N2: 2000:102::/64
+# N3: 2000:103::/64
+#
+# R1's host part of address: 1
+# R2's host part of address: 2
+# H1's host part of address: 3
+# H2's host part of address: 4
+#
+# For example:
+# the IPv6 address of R1's interface on N2 is 2000:102::1/64
+
+cleanup_traceroute6_vrf()
+{
+	cleanup_all_ns
+}
+
+setup_traceroute6_vrf()
+{
+	# Start clean
+	cleanup_traceroute6_vrf
+
+	setup_ns h1 h2 r1 r2
+	create_ns "$h1"
+	create_ns "$h2"
+	create_ns "$r1"
+	create_ns "$r2"
+
+	ip -n "$r2" link add name vrf100 up type vrf table 100
+	ip -n "$r2" addr add 2001:db8:100::1/64 dev vrf100
+
+	# Setup N3
+	connect_ns "$r2" eth3 - 2000:103::2/64 "$h2" eth3 - 2000:103::4/64
+
+	ip -n "$r2" link set dev eth3 master vrf100
+
+	ip -n "$h2" route add default via 2000:103::2
+
+	# Setup N2
+	connect_ns "$r1" eth2 - 2000:102::1/64 "$r2" eth2 - 2000:102::2/64
+
+	ip -n "$r1" route add default via 2000:102::2
+
+	ip -n "$r2" link set dev eth2 master vrf100
+
+	# Setup N1. host-1 and router-2 connect to a bridge in router-1.
+	ip -n "$r1" link add name br100 up type bridge
+	ip -n "$r1" addr add 2000:101::1/64 dev br100
+
+	connect_ns "$h1" eth0 - 2000:101::3/64 "$r1" eth0 - -
+
+	ip -n "$h1" route add default via 2000:101::1
+
+	ip -n "$r1" link set dev eth0 master br100
+
+	connect_ns "$r2" eth1 - 2000:101::2/64 "$r1" eth1 - -
+
+	ip -n "$r2" link set dev eth1 master vrf100
+
+	ip -n "$r1" link set dev eth1 master br100
+
+	# Prime the network
+	ip netns exec "$h1" ping6 -c5 2000:103::4 >/dev/null 2>&1
+}
+
+run_traceroute6_vrf()
+{
+	setup_traceroute6_vrf
+
+	RET=0
+
+	# traceroute6 host-2 from host-1 (expects 2000:102::2)
+	run_cmd "$h1" "traceroute6 2000:103::4 | grep 2000:102::2"
+	check_err $? "traceroute6 did not return 2000:102::2"
+	log_test "IPv6 traceroute with VRF"
+
+	cleanup_traceroute6_vrf
+}
+
+################################################################################
 # traceroute test
 #
-# Verify that traceroute from H1 to H2 shows 1.0.1.1 in this scenario
+# Verify that traceroute from H1 to H2 shows 1.0.3.1 and 1.0.1.1 when
+# traceroute uses 1.0.3.3 and 1.0.1.3 as the source IP, respectively.
 #
-#                    1.0.3.1/24
+#      1.0.3.3/24    1.0.3.1/24
 # ---- 1.0.1.3/24    1.0.1.1/24 ---- 1.0.2.1/24    1.0.2.4/24 ----
 # |H1|--------------------------|R1|--------------------------|H2|
 # ----            N1            ----            N2            ----
 #
-# where net.ipv4.icmp_errors_use_inbound_ifaddr is set on R1 and
-# 1.0.3.1/24 and 1.0.1.1/24 are respectively R1's primary and secondary
-# address on N1.
-#
+# where net.ipv4.icmp_errors_use_inbound_ifaddr is set on R1 and 1.0.3.1/24 and
+# 1.0.1.1/24 are R1's primary addresses on N1. The kernel is expected to prefer
+# a source address that is on the same subnet as the destination IP of the ICMP
+# error message.
 
 cleanup_traceroute()
 {
@@ -250,6 +331,7 @@ setup_traceroute()
 
 	connect_ns $h1 eth0 1.0.1.3/24 - \
 	           $router eth1 1.0.3.1/24 -
+	ip -n "$h1" addr add 1.0.3.3/24 dev eth0
 	ip netns exec $h1 ip route add default via 1.0.1.1
 
 	ip netns exec $router ip addr add 1.0.1.1/24 dev eth1
@@ -268,35 +350,107 @@ setup_traceroute()
 
 run_traceroute()
 {
-	if [ ! -x "$(command -v traceroute)" ]; then
-		echo "SKIP: Could not run IPV4 test without traceroute"
-		return
-	fi
-
 	setup_traceroute
 
-	# traceroute host-2 from host-1 (expects 1.0.1.1). Takes a while.
-	run_cmd $h1 "traceroute 1.0.2.4 | grep -q 1.0.1.1"
-	log_test $? 0 "IPV4 traceroute"
+	RET=0
+
+	# traceroute host-2 from host-1. Expect a source IP that is on the same
+	# subnet as destination IP of the ICMP error message.
+	run_cmd "$h1" "traceroute -s 1.0.1.3 1.0.2.4 | grep -q 1.0.1.1"
+	check_err $? "traceroute did not return 1.0.1.1"
+	run_cmd "$h1" "traceroute -s 1.0.3.3 1.0.2.4 | grep -q 1.0.3.1"
+	check_err $? "traceroute did not return 1.0.3.1"
+	log_test "IPv4 traceroute"
 
 	cleanup_traceroute
 }
 
 ################################################################################
+# traceroute with VRF test
+#
+# Verify that traceroute from H1 to H2 shows 1.0.3.1 and 1.0.1.1 when
+# traceroute uses 1.0.3.3 and 1.0.1.3 as the source IP, respectively. The
+# intention is to check that the kernel does not choose an IP assigned to the
+# VRF device, but rather an address from the VRF port (eth1) that received the
+# packet that generates the ICMP error message.
+#
+#                          1.0.4.1/24 (vrf100)
+#      1.0.3.3/24    1.0.3.1/24
+# ---- 1.0.1.3/24    1.0.1.1/24 ---- 1.0.2.1/24    1.0.2.4/24 ----
+# |H1|--------------------------|R1|--------------------------|H2|
+# ----            N1            ----            N2            ----
+
+cleanup_traceroute_vrf()
+{
+	cleanup_all_ns
+}
+
+setup_traceroute_vrf()
+{
+	# Start clean
+	cleanup_traceroute_vrf
+
+	setup_ns h1 h2 router
+	create_ns "$h1"
+	create_ns "$h2"
+	create_ns "$router"
+
+	ip -n "$router" link add name vrf100 up type vrf table 100
+	ip -n "$router" addr add 1.0.4.1/24 dev vrf100
+
+	connect_ns "$h1" eth0 1.0.1.3/24 - \
+	           "$router" eth1 1.0.1.1/24 -
+
+	ip -n "$h1" addr add 1.0.3.3/24 dev eth0
+	ip -n "$h1" route add default via 1.0.1.1
+
+	ip -n "$router" link set dev eth1 master vrf100
+	ip -n "$router" addr add 1.0.3.1/24 dev eth1
+	ip netns exec "$router" sysctl -qw \
+		net.ipv4.icmp_errors_use_inbound_ifaddr=1
+
+	connect_ns "$h2" eth0 1.0.2.4/24 - \
+	           "$router" eth2 1.0.2.1/24 -
+
+	ip -n "$h2" route add default via 1.0.2.1
+
+	ip -n "$router" link set dev eth2 master vrf100
+
+	# Prime the network
+	ip netns exec "$h1" ping -c5 1.0.2.4 >/dev/null 2>&1
+}
+
+run_traceroute_vrf()
+{
+	setup_traceroute_vrf
+
+	RET=0
+
+	# traceroute host-2 from host-1. Expect a source IP that is on the same
+	# subnet as destination IP of the ICMP error message.
+	run_cmd "$h1" "traceroute -s 1.0.1.3 1.0.2.4 | grep 1.0.1.1"
+	check_err $? "traceroute did not return 1.0.1.1"
+	run_cmd "$h1" "traceroute -s 1.0.3.3 1.0.2.4 | grep 1.0.3.1"
+	check_err $? "traceroute did not return 1.0.3.1"
+	log_test "IPv4 traceroute with VRF"
+
+	cleanup_traceroute_vrf
+}
+
+################################################################################
 # Run tests
 
 run_tests()
 {
 	run_traceroute6
+	run_traceroute6_vrf
 	run_traceroute
+	run_traceroute_vrf
 }
 
 ################################################################################
 # main
 
-declare -i nfail=0
-declare -i nsuccess=0
-
 while getopts :pv o
 do
 	case $o in
@@ -306,7 +460,9 @@ do
 	esac
 done
 
+require_command traceroute6
+require_command traceroute
+
 run_tests
 
-printf "\nTests passed: %3d\n" ${nsuccess}
-printf "Tests failed: %3d\n"   ${nfail}
+exit "${EXIT_STATUS}"