16 files changed, 712 insertions, 54 deletions

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index b31a71f2b372..c7e03e1d6f63 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -99,6 +99,7 @@ TEST_GEN_PROGS += bind_wildcard
 TEST_GEN_PROGS += bind_timewait
 TEST_PROGS += test_vxlan_mdb.sh
 TEST_PROGS += test_bridge_neigh_suppress.sh
+TEST_PROGS += test_vxlan_nh.sh
 TEST_PROGS += test_vxlan_nolocalbypass.sh
 TEST_PROGS += test_bridge_backup_port.sh
 TEST_PROGS += test_neigh.sh
diff --git a/tools/testing/selftests/net/bind_bhash.c b/tools/testing/selftests/net/bind_bhash.c
index 57ff67a3751e..da04b0b19b73 100644
--- a/tools/testing/selftests/net/bind_bhash.c
+++ b/tools/testing/selftests/net/bind_bhash.c
@@ -75,7 +75,7 @@ static void *setup(void *arg)
 	int *array = (int *)arg;
 
 	for (i = 0; i < MAX_CONNECTIONS; i++) {
-		sock_fd = bind_socket(SO_REUSEADDR | SO_REUSEPORT, setup_addr);
+		sock_fd = bind_socket(SO_REUSEPORT, setup_addr);
 		if (sock_fd < 0) {
 			ret = sock_fd;
 			pthread_exit(&ret);
@@ -103,7 +103,7 @@ int main(int argc, const char *argv[])
 
 	setup_addr = use_v6 ? setup_addr_v6 : setup_addr_v4;
 
-	listener_fd = bind_socket(SO_REUSEADDR | SO_REUSEPORT, setup_addr);
+	listener_fd = bind_socket(SO_REUSEPORT, setup_addr);
 	if (listen(listener_fd, 100) < 0) {
 		perror("listen failed");
 		return -1;
diff --git a/tools/testing/selftests/net/forwarding/router.sh b/tools/testing/selftests/net/forwarding/router.sh
index b98ea9449b8b..dfb6646cb97b 100755
--- a/tools/testing/selftests/net/forwarding/router.sh
+++ b/tools/testing/selftests/net/forwarding/router.sh
@@ -18,6 +18,8 @@
 # | 2001:db8:1::1/64                             2001:db8:2::1/64   |
 # |                                                                 |
 # +-----------------------------------------------------------------+
+#
+#shellcheck disable=SC2034 # SC doesn't see our uses of global variables
 
 ALL_TESTS="
 	ping_ipv4
@@ -27,6 +29,7 @@ ALL_TESTS="
 	ipv4_sip_equal_dip
 	ipv6_sip_equal_dip
 	ipv4_dip_link_local
+	ipv4_sip_link_local
 "
 
 NUM_NETIFS=4
@@ -330,6 +333,32 @@ ipv4_dip_link_local()
 	tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower
 }
 
+ipv4_sip_link_local()
+{
+	local sip=169.254.1.1
+
+	RET=0
+
+	# Disable rpfilter to prevent packets to be dropped because of it.
+	sysctl_set net.ipv4.conf.all.rp_filter 0
+	sysctl_set net.ipv4.conf."$rp1".rp_filter 0
+
+	tc filter add dev "$rp2" egress protocol ip pref 1 handle 101 \
+		flower src_ip "$sip" action pass
+
+	$MZ "$h1" -t udp "sp=54321,dp=12345" -c 5 -d 1msec -b "$rp1mac" \
+		-A "$sip" -B 198.51.100.2 -q
+
+	tc_check_packets "dev $rp2 egress" 101 5
+	check_err $? "Packets were dropped"
+
+	log_test "IPv4 source IP is link-local"
+
+	tc filter del dev "$rp2" egress protocol ip pref 1 handle 101 flower
+	sysctl_restore net.ipv4.conf."$rp1".rp_filter
+	sysctl_restore net.ipv4.conf.all.rp_filter
+}
+
 trap cleanup EXIT
 
 setup_prepare
diff --git a/tools/testing/selftests/net/forwarding/sch_ets.sh b/tools/testing/selftests/net/forwarding/sch_ets.sh
index 1f6f53e284b5..6269d5e23487 100755
--- a/tools/testing/selftests/net/forwarding/sch_ets.sh
+++ b/tools/testing/selftests/net/forwarding/sch_ets.sh
@@ -11,6 +11,7 @@ ALL_TESTS="
 	ets_test_strict
 	ets_test_mixed
 	ets_test_dwrr
+	ets_test_plug
 	classifier_mode
 	ets_test_strict
 	ets_test_mixed
diff --git a/tools/testing/selftests/net/forwarding/sch_ets_tests.sh b/tools/testing/selftests/net/forwarding/sch_ets_tests.sh
index 08240d3e3c87..79d837a2868a 100644
--- a/tools/testing/selftests/net/forwarding/sch_ets_tests.sh
+++ b/tools/testing/selftests/net/forwarding/sch_ets_tests.sh
@@ -224,3 +224,11 @@ ets_test_dwrr()
 	ets_set_dwrr_two_bands
 	xfail_on_slow ets_dwrr_test_01
 }
+
+ets_test_plug()
+{
+	ets_change_qdisc $put 2 "3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3" "1514 1514"
+	tc qdisc add dev $put handle 20: parent 10:4 plug
+	start_traffic_pktsize 100 $h1.10 192.0.2.1 192.0.2.2 00:c1:a0:c1:a0:00 "-c 1"
+	ets_qdisc_setup $put 2
+}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index ac1349c4b9e5..4f07ac9fa207 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -183,9 +183,10 @@ static void xgetaddrinfo(const char *node, const char *service,
 			 struct addrinfo *hints,
 			 struct addrinfo **res)
 {
-again:
-	int err = getaddrinfo(node, service, hints, res);
+	int err;
 
+again:
+	err = getaddrinfo(node, service, hints, res);
 	if (err) {
 		const char *errstr;
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c
index 3cf1e2a612ce..f3bcaa48df8f 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_inq.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c
@@ -75,9 +75,10 @@ static void xgetaddrinfo(const char *node, const char *service,
 			 struct addrinfo *hints,
 			 struct addrinfo **res)
 {
-again:
-	int err = getaddrinfo(node, service, hints, res);
+	int err;
 
+again:
+	err = getaddrinfo(node, service, hints, res);
 	if (err) {
 		const char *errstr;
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index b8af65373b3a..82cae37d9c20 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -3842,6 +3842,7 @@ endpoint_tests()
 	# remove and re-add
 	if reset_with_events "delete re-add signal" &&
 	   mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
+		ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=0
 		pm_nl_set_limits $ns1 0 3
 		pm_nl_set_limits $ns2 3 3
 		pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
index 9934a68df237..e934dd26a59d 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
@@ -162,9 +162,10 @@ static void xgetaddrinfo(const char *node, const char *service,
 			 struct addrinfo *hints,
 			 struct addrinfo **res)
 {
-again:
-	int err = getaddrinfo(node, service, hints, res);
+	int err;
 
+again:
+	err = getaddrinfo(node, service, hints, res);
 	if (err) {
 		const char *errstr;
 
diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
index 2e6648a2b2c0..ac7ec6f94023 100755
--- a/tools/testing/selftests/net/mptcp/pm_netlink.sh
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -198,6 +198,7 @@ set_limits 1 9 2>/dev/null
 check "get_limits" "${default_limits}" "subflows above hard limit"
 
 set_limits 8 8
+flush_endpoint  ## to make sure it doesn't affect the limits
 check "get_limits" "$(format_limits 8 8)" "set limits"
 
 flush_endpoint
diff --git a/tools/testing/selftests/net/netfilter/conntrack_clash.sh b/tools/testing/selftests/net/netfilter/conntrack_clash.sh
index 606a43a60f73..7fc6c5dbd551 100755
--- a/tools/testing/selftests/net/netfilter/conntrack_clash.sh
+++ b/tools/testing/selftests/net/netfilter/conntrack_clash.sh
@@ -99,7 +99,7 @@ run_one_clash_test()
 	local entries
 	local cre
 
-	if ! ip netns exec "$ns" ./udpclash $daddr $dport;then
+	if ! ip netns exec "$ns" timeout 30 ./udpclash $daddr $dport;then
 		echo "INFO: did not receive expected number of replies for $daddr:$dport"
 		ip netns exec "$ctns" conntrack -S
 		# don't fail: check if clash resolution triggered after all.
diff --git a/tools/testing/selftests/net/netfilter/conntrack_resize.sh b/tools/testing/selftests/net/netfilter/conntrack_resize.sh
index 788cd56ea4a0..615fe3c6f405 100755
--- a/tools/testing/selftests/net/netfilter/conntrack_resize.sh
+++ b/tools/testing/selftests/net/netfilter/conntrack_resize.sh
@@ -187,7 +187,7 @@ ct_udpclash()
 	[ -x udpclash ] || return
 
         while [ $now -lt $end ]; do
-		ip netns exec "$ns" ./udpclash 127.0.0.1 $((RANDOM%65536)) > /dev/null 2>&1
+		ip netns exec "$ns" timeout 30 ./udpclash 127.0.0.1 $((RANDOM%65536)) > /dev/null 2>&1
 
 		now=$(date +%s)
 	done
@@ -277,6 +277,7 @@ check_taint()
 insert_flood()
 {
 	local n="$1"
+	local timeout="$2"
 	local r=0
 
 	r=$((RANDOM%$insert_count))
@@ -302,7 +303,7 @@ test_floodresize_all()
 	read tainted_then < /proc/sys/kernel/tainted
 
 	for n in "$nsclient1" "$nsclient2";do
-		insert_flood "$n" &
+		insert_flood "$n" "$timeout" &
 	done
 
 	# resize table constantly while flood/insert/dump/flushs
diff --git a/tools/testing/selftests/net/netfilter/nft_flowtable.sh b/tools/testing/selftests/net/netfilter/nft_flowtable.sh
index a4ee5496f2a1..45832df98295 100755
--- a/tools/testing/selftests/net/netfilter/nft_flowtable.sh
+++ b/tools/testing/selftests/net/netfilter/nft_flowtable.sh
@@ -20,6 +20,7 @@ ret=0
 SOCAT_TIMEOUT=60
 
 nsin=""
+nsin_small=""
 ns1out=""
 ns2out=""
 
@@ -36,7 +37,7 @@ cleanup() {
 
 	cleanup_all_ns
 
-	rm -f "$nsin" "$ns1out" "$ns2out"
+	rm -f "$nsin" "$nsin_small" "$ns1out" "$ns2out"
 
 	[ "$log_netns" -eq 0 ] && sysctl -q net.netfilter.nf_log_all_netns="$log_netns"
 }
@@ -72,6 +73,7 @@ lmtu=1500
 rmtu=2000
 
 filesize=$((2 * 1024 * 1024))
+filesize_small=$((filesize / 16))
 
 usage(){
 	echo "nft_flowtable.sh [OPTIONS]"
@@ -89,7 +91,10 @@ do
 		o) omtu=$OPTARG;;
 		l) lmtu=$OPTARG;;
 		r) rmtu=$OPTARG;;
-		s) filesize=$OPTARG;;
+		s)
+			filesize=$OPTARG
+			filesize_small=$((OPTARG / 16))
+		;;
 		*) usage;;
 	esac
 done
@@ -215,6 +220,7 @@ if ! ip netns exec "$ns2" ping -c 1 -q 10.0.1.99 > /dev/null; then
 fi
 
 nsin=$(mktemp)
+nsin_small=$(mktemp)
 ns1out=$(mktemp)
 ns2out=$(mktemp)
 
@@ -265,6 +271,7 @@ check_counters()
 check_dscp()
 {
 	local what=$1
+	local pmtud="$2"
 	local ok=1
 
 	local counter
@@ -277,37 +284,39 @@ check_dscp()
 	local pc4z=${counter%*bytes*}
 	local pc4z=${pc4z#*packets}
 
+	local failmsg="FAIL: pmtu $pmtu: $what counters do not match, expected"
+
 	case "$what" in
 	"dscp_none")
 		if [ "$pc4" -gt 0 ] || [ "$pc4z" -eq 0 ]; then
-			echo "FAIL: dscp counters do not match, expected dscp3 == 0, dscp0 > 0, but got $pc4,$pc4z" 1>&2
+			echo "$failmsg dscp3 == 0, dscp0 > 0, but got $pc4,$pc4z" 1>&2
 			ret=1
 			ok=0
 		fi
 		;;
 	"dscp_fwd")
 		if [ "$pc4" -eq 0 ] || [ "$pc4z" -eq 0 ]; then
-			echo "FAIL: dscp counters do not match, expected dscp3 and dscp0 > 0 but got $pc4,$pc4z" 1>&2
+			echo "$failmsg dscp3 and dscp0 > 0 but got $pc4,$pc4z" 1>&2
 			ret=1
 			ok=0
 		fi
 		;;
 	"dscp_ingress")
 		if [ "$pc4" -eq 0 ] || [ "$pc4z" -gt 0 ]; then
-			echo "FAIL: dscp counters do not match, expected dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2
+			echo "$failmsg dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2
 			ret=1
 			ok=0
 		fi
 		;;
 	"dscp_egress")
 		if [ "$pc4" -eq 0 ] || [ "$pc4z" -gt 0 ]; then
-			echo "FAIL: dscp counters do not match, expected dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2
+			echo "$failmsg dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2
 			ret=1
 			ok=0
 		fi
 		;;
 	*)
-		echo "FAIL: Unknown DSCP check" 1>&2
+		echo "$failmsg: Unknown DSCP check" 1>&2
 		ret=1
 		ok=0
 	esac
@@ -319,9 +328,9 @@ check_dscp()
 
 check_transfer()
 {
-	in=$1
-	out=$2
-	what=$3
+	local in=$1
+	local out=$2
+	local what=$3
 
 	if ! cmp "$in" "$out" > /dev/null 2>&1; then
 		echo "FAIL: file mismatch for $what" 1>&2
@@ -342,25 +351,39 @@ test_tcp_forwarding_ip()
 {
 	local nsa=$1
 	local nsb=$2
-	local dstip=$3
-	local dstport=$4
+	local pmtu=$3
+	local dstip=$4
+	local dstport=$5
 	local lret=0
+	local socatc
+	local socatl
+	local infile="$nsin"
+
+	if [ $pmtu -eq 0 ]; then
+		infile="$nsin_small"
+	fi
 
-	timeout "$SOCAT_TIMEOUT" ip netns exec "$nsb" socat -4 TCP-LISTEN:12345,reuseaddr STDIO < "$nsin" > "$ns2out" &
+	timeout "$SOCAT_TIMEOUT" ip netns exec "$nsb" socat -4 TCP-LISTEN:12345,reuseaddr STDIO < "$infile" > "$ns2out" &
 	lpid=$!
 
 	busywait 1000 listener_ready
 
-	timeout "$SOCAT_TIMEOUT" ip netns exec "$nsa" socat -4 TCP:"$dstip":"$dstport" STDIO < "$nsin" > "$ns1out"
+	timeout "$SOCAT_TIMEOUT" ip netns exec "$nsa" socat -4 TCP:"$dstip":"$dstport" STDIO < "$infile" > "$ns1out"
+	socatc=$?
 
 	wait $lpid
+	socatl=$?
 
-	if ! check_transfer "$nsin" "$ns2out" "ns1 -> ns2"; then
+	if [ $socatl -ne 0 ] || [ $socatc -ne 0 ];then
+		rc=1
+	fi
+
+	if ! check_transfer "$infile" "$ns2out" "ns1 -> ns2"; then
 		lret=1
 		ret=1
 	fi
 
-	if ! check_transfer "$nsin" "$ns1out" "ns1 <- ns2"; then
+	if ! check_transfer "$infile" "$ns1out" "ns1 <- ns2"; then
 		lret=1
 		ret=1
 	fi
@@ -370,14 +393,16 @@ test_tcp_forwarding_ip()
 
 test_tcp_forwarding()
 {
-	test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345
+	local pmtu="$3"
+
+	test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.0.2.99 12345
 
 	return $?
 }
 
 test_tcp_forwarding_set_dscp()
 {
-	check_dscp "dscp_none"
+	local pmtu="$3"
 
 ip netns exec "$nsr1" nft -f - <<EOF
 table netdev dscpmangle {
@@ -388,8 +413,8 @@ table netdev dscpmangle {
 }
 EOF
 if [ $? -eq 0 ]; then
-	test_tcp_forwarding_ip "$1" "$2"  10.0.2.99 12345
-	check_dscp "dscp_ingress"
+	test_tcp_forwarding_ip "$1" "$2" "$3" 10.0.2.99 12345
+	check_dscp "dscp_ingress" "$pmtu"
 
 	ip netns exec "$nsr1" nft delete table netdev dscpmangle
 else
@@ -405,10 +430,10 @@ table netdev dscpmangle {
 }
 EOF
 if [ $? -eq 0 ]; then
-	test_tcp_forwarding_ip "$1" "$2"  10.0.2.99 12345
-	check_dscp "dscp_egress"
+	test_tcp_forwarding_ip "$1" "$2" "$pmtu"  10.0.2.99 12345
+	check_dscp "dscp_egress" "$pmtu"
 
-	ip netns exec "$nsr1" nft flush table netdev dscpmangle
+	ip netns exec "$nsr1" nft delete table netdev dscpmangle
 else
 	echo "SKIP: Could not load netdev:egress for veth1"
 fi
@@ -416,48 +441,53 @@ fi
 	# partial.  If flowtable really works, then both dscp-is-0 and dscp-is-cs3
 	# counters should have seen packets (before and after ft offload kicks in).
 	ip netns exec "$nsr1" nft -a insert rule inet filter forward ip dscp set cs3
-	test_tcp_forwarding_ip "$1" "$2"  10.0.2.99 12345
-	check_dscp "dscp_fwd"
+	test_tcp_forwarding_ip "$1" "$2" "$pmtu"  10.0.2.99 12345
+	check_dscp "dscp_fwd" "$pmtu"
 }
 
 test_tcp_forwarding_nat()
 {
+	local nsa="$1"
+	local nsb="$2"
+	local pmtu="$3"
+	local what="$4"
 	local lret
-	local pmtu
 
-	test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345
-	lret=$?
+	[ "$pmtu" -eq 0 ] && what="$what (pmtu disabled)"
 
-	pmtu=$3
-	what=$4
+	test_tcp_forwarding_ip "$nsa" "$nsb" "$pmtu" 10.0.2.99 12345
+	lret=$?
 
 	if [ "$lret" -eq 0 ] ; then
 		if [ "$pmtu" -eq 1 ] ;then
-			check_counters "flow offload for ns1/ns2 with masquerade and pmtu discovery $what"
+			check_counters "flow offload for ns1/ns2 with masquerade $what"
 		else
 			echo "PASS: flow offload for ns1/ns2 with masquerade $what"
 		fi
 
-		test_tcp_forwarding_ip "$1" "$2" 10.6.6.6 1666
+		test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.6.6.6 1666
 		lret=$?
 		if [ "$pmtu" -eq 1 ] ;then
-			check_counters "flow offload for ns1/ns2 with dnat and pmtu discovery $what"
+			check_counters "flow offload for ns1/ns2 with dnat $what"
 		elif [ "$lret" -eq 0 ] ; then
 			echo "PASS: flow offload for ns1/ns2 with dnat $what"
 		fi
+	else
+		echo "FAIL: flow offload for ns1/ns2 with dnat $what"
 	fi
 
 	return $lret
 }
 
 make_file "$nsin" "$filesize"
+make_file "$nsin_small" "$filesize_small"
 
 # First test:
 # No PMTU discovery, nsr1 is expected to fragment packets from ns1 to ns2 as needed.
 # Due to MTU mismatch in both directions, all packets (except small packets like pure
 # acks) have to be handled by normal forwarding path.  Therefore, packet counters
 # are not checked.
-if test_tcp_forwarding "$ns1" "$ns2"; then
+if test_tcp_forwarding "$ns1" "$ns2" 0; then
 	echo "PASS: flow offloaded for ns1/ns2"
 else
 	echo "FAIL: flow offload for ns1/ns2:" 1>&2
@@ -489,8 +519,9 @@ table ip nat {
 }
 EOF
 
+check_dscp "dscp_none" "0"
 if ! test_tcp_forwarding_set_dscp "$ns1" "$ns2" 0 ""; then
-	echo "FAIL: flow offload for ns1/ns2 with dscp update" 1>&2
+	echo "FAIL: flow offload for ns1/ns2 with dscp update and no pmtu discovery" 1>&2
 	exit 0
 fi
 
@@ -513,6 +544,14 @@ ip netns exec "$ns2" sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null
 # For earlier tests (large mtus), packets cannot be handled via flowtable
 # (except pure acks and other small packets).
 ip netns exec "$nsr1" nft reset counters table inet filter >/dev/null
+ip netns exec "$ns2"  nft reset counters table inet filter >/dev/null
+
+if ! test_tcp_forwarding_set_dscp "$ns1" "$ns2" 1 ""; then
+	echo "FAIL: flow offload for ns1/ns2 with dscp update and pmtu discovery" 1>&2
+	exit 0
+fi
+
+ip netns exec "$nsr1" nft reset counters table inet filter >/dev/null
 
 if ! test_tcp_forwarding_nat "$ns1" "$ns2" 1 ""; then
 	echo "FAIL: flow offload for ns1/ns2 with NAT and pmtu discovery" 1>&2
@@ -644,7 +683,7 @@ ip -net "$ns2" route del 192.168.10.1 via 10.0.2.1
 ip -net "$ns2" route add default via 10.0.2.1
 ip -net "$ns2" route add default via dead:2::1
 
-if test_tcp_forwarding "$ns1" "$ns2"; then
+if test_tcp_forwarding "$ns1" "$ns2" 1; then
 	check_counters "ipsec tunnel mode for ns1/ns2"
 else
 	echo "FAIL: ipsec tunnel mode for ns1/ns2"
@@ -668,7 +707,7 @@ if [ "$1" = "" ]; then
 	fi
 
 	echo "re-run with random mtus and file size: -o $o -l $l -r $r -s $filesize"
-	$0 -o "$o" -l "$l" -r "$r" -s "$filesize"
+	$0 -o "$o" -l "$l" -r "$r" -s "$filesize" || ret=1
 fi
 
 exit $ret
diff --git a/tools/testing/selftests/net/netfilter/udpclash.c b/tools/testing/selftests/net/netfilter/udpclash.c
index 85c7b906ad08..79de163d61ab 100644
--- a/tools/testing/selftests/net/netfilter/udpclash.c
+++ b/tools/testing/selftests/net/netfilter/udpclash.c
@@ -29,7 +29,7 @@ struct thread_args {
 	int sockfd;
 };
 
-static int wait = 1;
+static volatile int wait = 1;
 
 static void *thread_main(void *varg)
 {
diff --git a/tools/testing/selftests/net/test_vxlan_nh.sh b/tools/testing/selftests/net/test_vxlan_nh.sh
new file mode 100755
index 000000000000..20f3369f776b
--- /dev/null
+++ b/tools/testing/selftests/net/test_vxlan_nh.sh
@@ -0,0 +1,223 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source lib.sh
+TESTS="
+	basic_tx_ipv4
+	basic_tx_ipv6
+	learning
+	proxy_ipv4
+	proxy_ipv6
+"
+VERBOSE=0
+
+################################################################################
+# Utilities
+
+run_cmd()
+{
+	local cmd="$1"
+	local out
+	local stderr="2>/dev/null"
+
+	if [ "$VERBOSE" = "1" ]; then
+		echo "COMMAND: $cmd"
+		stderr=
+	fi
+
+	out=$(eval "$cmd" "$stderr")
+	rc=$?
+	if [ "$VERBOSE" -eq 1 ] && [ -n "$out" ]; then
+		echo "    $out"
+	fi
+
+	return $rc
+}
+
+################################################################################
+# Cleanup
+
+exit_cleanup_all()
+{
+	cleanup_all_ns
+	exit "${EXIT_STATUS}"
+}
+
+################################################################################
+# Tests
+
+nh_stats_get()
+{
+	ip -n "$ns1" -s -j nexthop show id 10 | jq ".[][\"group_stats\"][][\"packets\"]"
+}
+
+tc_stats_get()
+{
+	tc_rule_handle_stats_get "dev dummy1 egress" 101 ".packets" "-n $ns1"
+}
+
+basic_tx_common()
+{
+	local af_str=$1; shift
+	local proto=$1; shift
+	local local_addr=$1; shift
+	local plen=$1; shift
+	local remote_addr=$1; shift
+
+	RET=0
+
+	# Test basic Tx functionality. Check that stats are incremented on
+	# both the FDB nexthop group and the egress device.
+
+	run_cmd "ip -n $ns1 link add name dummy1 up type dummy"
+	run_cmd "ip -n $ns1 route add $remote_addr/$plen dev dummy1"
+	run_cmd "tc -n $ns1 qdisc add dev dummy1 clsact"
+	run_cmd "tc -n $ns1 filter add dev dummy1 egress proto $proto pref 1 handle 101 flower ip_proto udp dst_ip $remote_addr dst_port 4789 action pass"
+
+	run_cmd "ip -n $ns1 address add $local_addr/$plen dev lo"
+
+	run_cmd "ip -n $ns1 nexthop add id 1 via $remote_addr fdb"
+	run_cmd "ip -n $ns1 nexthop add id 10 group 1 fdb"
+
+	run_cmd "ip -n $ns1 link add name vx0 up type vxlan id 10010 local $local_addr dstport 4789"
+	run_cmd "bridge -n $ns1 fdb add 00:11:22:33:44:55 dev vx0 self static nhid 10"
+
+	run_cmd "ip netns exec $ns1 mausezahn vx0 -a own -b 00:11:22:33:44:55 -c 1 -q"
+
+	busywait "$BUSYWAIT_TIMEOUT" until_counter_is "== 1" nh_stats_get > /dev/null
+	check_err $? "FDB nexthop group stats did not increase"
+
+	busywait "$BUSYWAIT_TIMEOUT" until_counter_is "== 1" tc_stats_get > /dev/null
+	check_err $? "tc filter stats did not increase"
+
+	log_test "VXLAN FDB nexthop: $af_str basic Tx"
+}
+
+basic_tx_ipv4()
+{
+	basic_tx_common "IPv4" ipv4 192.0.2.1 32 192.0.2.2
+}
+
+basic_tx_ipv6()
+{
+	basic_tx_common "IPv6" ipv6 2001:db8:1::1 128 2001:db8:1::2
+}
+
+learning()
+{
+	RET=0
+
+	# When learning is enabled on the VXLAN device, an incoming packet
+	# might try to refresh an FDB entry that points to an FDB nexthop group
+	# instead of an ordinary remote destination. Check that the kernel does
+	# not crash in this situation.
+
+	run_cmd "ip -n $ns1 address add 192.0.2.1/32 dev lo"
+	run_cmd "ip -n $ns1 address add 192.0.2.2/32 dev lo"
+
+	run_cmd "ip -n $ns1 nexthop add id 1 via 192.0.2.3 fdb"
+	run_cmd "ip -n $ns1 nexthop add id 10 group 1 fdb"
+
+	run_cmd "ip -n $ns1 link add name vx0 up type vxlan id 10010 local 192.0.2.1 dstport 12345 localbypass"
+	run_cmd "ip -n $ns1 link add name vx1 up type vxlan id 10020 local 192.0.2.2 dstport 54321 learning"
+
+	run_cmd "bridge -n $ns1 fdb add 00:11:22:33:44:55 dev vx0 self static dst 192.0.2.2 port 54321 vni 10020"
+	run_cmd "bridge -n $ns1 fdb add 00:aa:bb:cc:dd:ee dev vx1 self static nhid 10"
+
+	run_cmd "ip netns exec $ns1 mausezahn vx0 -a 00:aa:bb:cc:dd:ee -b 00:11:22:33:44:55 -c 1 -q"
+
+	log_test "VXLAN FDB nexthop: learning"
+}
+
+proxy_common()
+{
+	local af_str=$1; shift
+	local local_addr=$1; shift
+	local plen=$1; shift
+	local remote_addr=$1; shift
+	local neigh_addr=$1; shift
+	local ping_cmd=$1; shift
+
+	RET=0
+
+	# When the "proxy" option is enabled on the VXLAN device, the device
+	# will suppress ARP requests and IPv6 Neighbor Solicitation messages if
+	# it is able to reply on behalf of the remote host. That is, if a
+	# matching and valid neighbor entry is configured on the VXLAN device
+	# whose MAC address is not behind the "any" remote (0.0.0.0 / ::). The
+	# FDB entry for the neighbor's MAC address might point to an FDB
+	# nexthop group instead of an ordinary remote destination. Check that
+	# the kernel does not crash in this situation.
+
+	run_cmd "ip -n $ns1 address add $local_addr/$plen dev lo"
+
+	run_cmd "ip -n $ns1 nexthop add id 1 via $remote_addr fdb"
+	run_cmd "ip -n $ns1 nexthop add id 10 group 1 fdb"
+
+	run_cmd "ip -n $ns1 link add name vx0 up type vxlan id 10010 local $local_addr dstport 4789 proxy"
+
+	run_cmd "ip -n $ns1 neigh add $neigh_addr lladdr 00:11:22:33:44:55 nud perm dev vx0"
+
+	run_cmd "bridge -n $ns1 fdb add 00:11:22:33:44:55 dev vx0 self static nhid 10"
+
+	run_cmd "ip netns exec $ns1 $ping_cmd"
+
+	log_test "VXLAN FDB nexthop: $af_str proxy"
+}
+
+proxy_ipv4()
+{
+	proxy_common "IPv4" 192.0.2.1 32 192.0.2.2 192.0.2.3 \
+		"arping -b -c 1 -s 192.0.2.1 -I vx0 192.0.2.3"
+}
+
+proxy_ipv6()
+{
+	proxy_common "IPv6" 2001:db8:1::1 128 2001:db8:1::2 2001:db8:1::3 \
+		"ndisc6 -r 1 -s 2001:db8:1::1 -w 1 2001:db8:1::3 vx0"
+}
+
+################################################################################
+# Usage
+
+usage()
+{
+	cat <<EOF
+usage: ${0##*/} OPTS
+
+        -t <test>   Test(s) to run (default: all)
+                    (options: $TESTS)
+        -p          Pause on fail
+        -v          Verbose mode (show commands and output)
+EOF
+}
+
+################################################################################
+# Main
+
+while getopts ":t:pvh" opt; do
+	case $opt in
+		t) TESTS=$OPTARG;;
+		p) PAUSE_ON_FAIL=yes;;
+		v) VERBOSE=$((VERBOSE + 1));;
+		h) usage; exit 0;;
+		*) usage; exit 1;;
+	esac
+done
+
+require_command mausezahn
+require_command arping
+require_command ndisc6
+require_command jq
+
+if ! ip nexthop help 2>&1 | grep -q "stats"; then
+	echo "SKIP: iproute2 ip too old, missing nexthop stats support"
+	exit "$ksft_skip"
+fi
+
+trap exit_cleanup_all EXIT
+
+for t in $TESTS
+do
+	setup_ns ns1; $t; cleanup_all_ns;
+done
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 5ded3b3a7538..0f5640d8dc7f 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -181,13 +181,12 @@ static int tls_send_cmsg(int fd, unsigned char record_type,
 	return sendmsg(fd, &msg, flags);
 }
 
-static int tls_recv_cmsg(struct __test_metadata *_metadata,
-			 int fd, unsigned char record_type,
-			 void *data, size_t len, int flags)
+static int __tls_recv_cmsg(struct __test_metadata *_metadata,
+			   int fd, unsigned char *ctype,
+			   void *data, size_t len, int flags)
 {
 	char cbuf[CMSG_SPACE(sizeof(char))];
 	struct cmsghdr *cmsg;
-	unsigned char ctype;
 	struct msghdr msg;
 	struct iovec vec;
 	int n;
@@ -206,7 +205,20 @@ static int tls_recv_cmsg(struct __test_metadata *_metadata,
 	EXPECT_NE(cmsg, NULL);
 	EXPECT_EQ(cmsg->cmsg_level, SOL_TLS);
 	EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE);
-	ctype = *((unsigned char *)CMSG_DATA(cmsg));
+	if (ctype)
+		*ctype = *((unsigned char *)CMSG_DATA(cmsg));
+
+	return n;
+}
+
+static int tls_recv_cmsg(struct __test_metadata *_metadata,
+			 int fd, unsigned char record_type,
+			 void *data, size_t len, int flags)
+{
+	unsigned char ctype;
+	int n;
+
+	n = __tls_recv_cmsg(_metadata, fd, &ctype, data, len, flags);
 	EXPECT_EQ(ctype, record_type);
 
 	return n;
@@ -2164,6 +2176,284 @@ TEST_F(tls, rekey_poll_delay)
 	}
 }
 
+struct raw_rec {
+	unsigned int plain_len;
+	unsigned char plain_data[100];
+	unsigned int cipher_len;
+	unsigned char cipher_data[128];
+};
+
+/* TLS 1.2, AES_CCM, data, seqno:0, plaintext: 'Hello world' */
+static const struct raw_rec id0_data_l11 = {
+	.plain_len = 11,
+	.plain_data = {
+		0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f,
+		0x72, 0x6c, 0x64,
+	},
+	.cipher_len = 40,
+	.cipher_data = {
+		0x17, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x00, 0x26, 0xa2, 0x33,
+		0xde, 0x8d, 0x94, 0xf0, 0x29, 0x6c, 0xb1, 0xaf,
+		0x6a, 0x75, 0xb2, 0x93, 0xad, 0x45, 0xd5, 0xfd,
+		0x03, 0x51, 0x57, 0x8f, 0xf9, 0xcc, 0x3b, 0x42,
+	},
+};
+
+/* TLS 1.2, AES_CCM, ctrl, seqno:0, plaintext: '' */
+static const struct raw_rec id0_ctrl_l0 = {
+	.plain_len = 0,
+	.plain_data = {
+	},
+	.cipher_len = 29,
+	.cipher_data = {
+		0x16, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x00, 0x13, 0x38, 0x7b,
+		0xa6, 0x1c, 0xdd, 0xa7, 0x19, 0x33, 0xab, 0xae,
+		0x88, 0xe1, 0xd2, 0x08, 0x4f,
+	},
+};
+
+/* TLS 1.2, AES_CCM, data, seqno:0, plaintext: '' */
+static const struct raw_rec id0_data_l0 = {
+	.plain_len = 0,
+	.plain_data = {
+	},
+	.cipher_len = 29,
+	.cipher_data = {
+		0x17, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x00, 0xc5, 0x37, 0x90,
+		0x70, 0x45, 0x89, 0xfb, 0x5c, 0xc7, 0x89, 0x03,
+		0x68, 0x80, 0xd3, 0xd8, 0xcc,
+	},
+};
+
+/* TLS 1.2, AES_CCM, data, seqno:1, plaintext: 'Hello world' */
+static const struct raw_rec id1_data_l11 = {
+	.plain_len = 11,
+	.plain_data = {
+		0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f,
+		0x72, 0x6c, 0x64,
+	},
+	.cipher_len = 40,
+	.cipher_data = {
+		0x17, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x01, 0x3a, 0x1a, 0x9c,
+		0xd0, 0xa8, 0x9a, 0xd6, 0x69, 0xd6, 0x1a, 0xe3,
+		0xb5, 0x1f, 0x0d, 0x2c, 0xe2, 0x97, 0x46, 0xff,
+		0x2b, 0xcc, 0x5a, 0xc4, 0xa3, 0xb9, 0xef, 0xba,
+	},
+};
+
+/* TLS 1.2, AES_CCM, ctrl, seqno:1, plaintext: '' */
+static const struct raw_rec id1_ctrl_l0 = {
+	.plain_len = 0,
+	.plain_data = {
+	},
+	.cipher_len = 29,
+	.cipher_data = {
+		0x16, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x01, 0x3e, 0xf0, 0xfe,
+		0xee, 0xd9, 0xe2, 0x5d, 0xc7, 0x11, 0x4c, 0xe6,
+		0xb4, 0x7e, 0xef, 0x40, 0x2b,
+	},
+};
+
+/* TLS 1.2, AES_CCM, data, seqno:1, plaintext: '' */
+static const struct raw_rec id1_data_l0 = {
+	.plain_len = 0,
+	.plain_data = {
+	},
+	.cipher_len = 29,
+	.cipher_data = {
+		0x17, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x01, 0xce, 0xfc, 0x86,
+		0xc8, 0xf0, 0x55, 0xf9, 0x47, 0x3f, 0x74, 0xdc,
+		0xc9, 0xbf, 0xfe, 0x5b, 0xb1,
+	},
+};
+
+/* TLS 1.2, AES_CCM, ctrl, seqno:2, plaintext: 'Hello world' */
+static const struct raw_rec id2_ctrl_l11 = {
+	.plain_len = 11,
+	.plain_data = {
+		0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f,
+		0x72, 0x6c, 0x64,
+	},
+	.cipher_len = 40,
+	.cipher_data = {
+		0x16, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x02, 0xe5, 0x3d, 0x19,
+		0x3d, 0xca, 0xb8, 0x16, 0xb6, 0xff, 0x79, 0x87,
+		0x2a, 0x04, 0x11, 0x3d, 0xf8, 0x64, 0x5f, 0x36,
+		0x8b, 0xa8, 0xee, 0x4c, 0x6d, 0x62, 0xa5, 0x00,
+	},
+};
+
+/* TLS 1.2, AES_CCM, data, seqno:2, plaintext: 'Hello world' */
+static const struct raw_rec id2_data_l11 = {
+	.plain_len = 11,
+	.plain_data = {
+		0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f,
+		0x72, 0x6c, 0x64,
+	},
+	.cipher_len = 40,
+	.cipher_data = {
+		0x17, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x02, 0xe5, 0x3d, 0x19,
+		0x3d, 0xca, 0xb8, 0x16, 0xb6, 0xff, 0x79, 0x87,
+		0x8e, 0xa1, 0xd0, 0xcd, 0x33, 0xb5, 0x86, 0x2b,
+		0x17, 0xf1, 0x52, 0x2a, 0x55, 0x62, 0x65, 0x11,
+	},
+};
+
+/* TLS 1.2, AES_CCM, ctrl, seqno:2, plaintext: '' */
+static const struct raw_rec id2_ctrl_l0 = {
+	.plain_len = 0,
+	.plain_data = {
+	},
+	.cipher_len = 29,
+	.cipher_data = {
+		0x16, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x02, 0xdc, 0x5c, 0x0e,
+		0x41, 0xdd, 0xba, 0xd3, 0xcc, 0xcf, 0x6d, 0xd9,
+		0x06, 0xdb, 0x79, 0xe5, 0x5d,
+	},
+};
+
+/* TLS 1.2, AES_CCM, data, seqno:2, plaintext: '' */
+static const struct raw_rec id2_data_l0 = {
+	.plain_len = 0,
+	.plain_data = {
+	},
+	.cipher_len = 29,
+	.cipher_data = {
+		0x17, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x02, 0xc3, 0xca, 0x26,
+		0x22, 0xe4, 0x25, 0xfb, 0x5f, 0x6d, 0xbf, 0x83,
+		0x30, 0x48, 0x69, 0x1a, 0x47,
+	},
+};
+
+FIXTURE(zero_len)
+{
+	int fd, cfd;
+	bool notls;
+};
+
+FIXTURE_VARIANT(zero_len)
+{
+	const struct raw_rec *recs[4];
+	ssize_t recv_ret[4];
+};
+
+FIXTURE_VARIANT_ADD(zero_len, data_data_data)
+{
+	.recs = { &id0_data_l11, &id1_data_l11, &id2_data_l11, },
+	.recv_ret = { 33, -EAGAIN, },
+};
+
+FIXTURE_VARIANT_ADD(zero_len, data_0ctrl_data)
+{
+	.recs = { &id0_data_l11, &id1_ctrl_l0, &id2_data_l11, },
+	.recv_ret = { 11, 0, 11, -EAGAIN, },
+};
+
+FIXTURE_VARIANT_ADD(zero_len, 0data_0data_0data)
+{
+	.recs = { &id0_data_l0, &id1_data_l0, &id2_data_l0, },
+	.recv_ret = { -EAGAIN, },
+};
+
+FIXTURE_VARIANT_ADD(zero_len, 0data_0data_ctrl)
+{
+	.recs = { &id0_data_l0, &id1_data_l0, &id2_ctrl_l11, },
+	.recv_ret = { 0, 11, -EAGAIN, },
+};
+
+FIXTURE_VARIANT_ADD(zero_len, 0data_0data_0ctrl)
+{
+	.recs = { &id0_data_l0, &id1_data_l0, &id2_ctrl_l0, },
+	.recv_ret = { 0, 0, -EAGAIN, },
+};
+
+FIXTURE_VARIANT_ADD(zero_len, 0ctrl_0ctrl_0ctrl)
+{
+	.recs = { &id0_ctrl_l0, &id1_ctrl_l0, &id2_ctrl_l0, },
+	.recv_ret = { 0, 0, 0, -EAGAIN, },
+};
+
+FIXTURE_VARIANT_ADD(zero_len, 0data_0data_data)
+{
+	.recs = { &id0_data_l0, &id1_data_l0, &id2_data_l11, },
+	.recv_ret = { 11, -EAGAIN, },
+};
+
+FIXTURE_VARIANT_ADD(zero_len, data_0data_0data)
+{
+	.recs = { &id0_data_l11, &id1_data_l0, &id2_data_l0, },
+	.recv_ret = { 11, -EAGAIN, },
+};
+
+FIXTURE_SETUP(zero_len)
+{
+	struct tls_crypto_info_keys tls12;
+	int ret;
+
+	tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_CCM_128,
+			     &tls12, 0);
+
+	ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls);
+	if (self->notls)
+		return;
+
+	/* Don't install keys on fd, we'll send raw records */
+	ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len);
+	ASSERT_EQ(ret, 0);
+}
+
+FIXTURE_TEARDOWN(zero_len)
+{
+	close(self->fd);
+	close(self->cfd);
+}
+
+TEST_F(zero_len, test)
+{
+	const struct raw_rec *const *rec;
+	unsigned char buf[128];
+	int rec_off;
+	int i;
+
+	for (i = 0; i < 4 && variant->recs[i]; i++)
+		EXPECT_EQ(send(self->fd, variant->recs[i]->cipher_data,
+			       variant->recs[i]->cipher_len, 0),
+			  variant->recs[i]->cipher_len);
+
+	rec = &variant->recs[0];
+	rec_off = 0;
+	for (i = 0; i < 4; i++) {
+		int j, ret;
+
+		ret = variant->recv_ret[i] >= 0 ? variant->recv_ret[i] : -1;
+		EXPECT_EQ(__tls_recv_cmsg(_metadata, self->cfd, NULL,
+					  buf, sizeof(buf), MSG_DONTWAIT), ret);
+		if (ret == -1)
+			EXPECT_EQ(errno, -variant->recv_ret[i]);
+		if (variant->recv_ret[i] == -EAGAIN)
+			break;
+
+		for (j = 0; j < ret; j++) {
+			while (rec_off == (*rec)->plain_len) {
+				rec++;
+				rec_off = 0;
+			}
+			EXPECT_EQ(buf[j], (*rec)->plain_data[rec_off]);
+			rec_off++;
+		}
+	}
+};
+
 FIXTURE(tls_err)
 {
 	int fd, cfd;
@@ -2708,6 +2998,67 @@ TEST(prequeue) {
 	close(cfd);
 }
 
+TEST(data_steal) {
+	struct tls_crypto_info_keys tls;
+	char buf[20000], buf2[20000];
+	struct sockaddr_in addr;
+	int sfd, cfd, ret, fd;
+	int pid, status;
+	socklen_t len;
+
+	len = sizeof(addr);
+	memrnd(buf, sizeof(buf));
+
+	tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_256, &tls, 0);
+
+	addr.sin_family = AF_INET;
+	addr.sin_addr.s_addr = htonl(INADDR_ANY);
+	addr.sin_port = 0;
+
+	fd = socket(AF_INET, SOCK_STREAM, 0);
+	sfd = socket(AF_INET, SOCK_STREAM, 0);
+
+	ASSERT_EQ(bind(sfd, &addr, sizeof(addr)), 0);
+	ASSERT_EQ(listen(sfd, 10), 0);
+	ASSERT_EQ(getsockname(sfd, &addr, &len), 0);
+	ASSERT_EQ(connect(fd, &addr, sizeof(addr)), 0);
+	ASSERT_GE(cfd = accept(sfd, &addr, &len), 0);
+	close(sfd);
+
+	ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+	if (ret) {
+		ASSERT_EQ(errno, ENOENT);
+		SKIP(return, "no TLS support");
+	}
+	ASSERT_EQ(setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")), 0);
+
+	/* Spawn a child and get it into the read wait path of the underlying
+	 * TCP socket.
+	 */
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (!pid) {
+		EXPECT_EQ(recv(cfd, buf, sizeof(buf) / 2, MSG_WAITALL),
+			  sizeof(buf) / 2);
+		exit(!__test_passed(_metadata));
+	}
+
+	usleep(10000);
+	ASSERT_EQ(setsockopt(fd, SOL_TLS, TLS_TX, &tls, tls.len), 0);
+	ASSERT_EQ(setsockopt(cfd, SOL_TLS, TLS_RX, &tls, tls.len), 0);
+
+	EXPECT_EQ(send(fd, buf, sizeof(buf), 0), sizeof(buf));
+	EXPECT_EQ(wait(&status), pid);
+	EXPECT_EQ(status, 0);
+	EXPECT_EQ(recv(cfd, buf2, sizeof(buf2), MSG_DONTWAIT), -1);
+	/* Don't check errno, the error will be different depending
+	 * on what random bytes TLS interpreted as the record length.
+	 */
+
+	close(fd);
+	close(cfd);
+}
+
 static void __attribute__((constructor)) fips_check(void) {
 	int res;
 	FILE *f;