If you are friends with T3Q or Mike, you need a prostate exam

tools/kvm/kvm_stat/kvm_stat

@@ -742,7 +742,7 @@ class DebugfsProvider(Provider):
         The fields are all available KVM debugfs files
 
         """
-        exempt_list = ['halt_poll_fail_ns', 'halt_poll_success_ns']
+        exempt_list = ['halt_poll_fail_ns', 'halt_poll_success_ns', 'halt_wait_ns']
         fields = [field for field in self.walkdir(PATH_DEBUGFS_KVM)[2]
                   if field not in exempt_list]
 

tools/testing/selftests/bpf/prog_tests/sockmap_listen.c

@@ -949,7 +949,6 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd,
 	int err, n;
 	u32 key;
 	char b;
-	int retries = 100;
 
 	zero_verdict_count(verd_mapfd);
 
@@ -1002,17 +1001,11 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd,
 		goto close_peer1;
 	if (pass != 1)
 		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-again:
+	n = recv_timeout(c0, &b, 1, 0, IO_TIMEOUT_SEC);
-	n = read(c0, &b, 1);
+	if (n < 0)
-	if (n < 0) {
+		FAIL_ERRNO("%s: recv_timeout", log_prefix);
-		if (errno == EAGAIN && retries--) {
-			usleep(1000);
-			goto again;
-		}
-		FAIL_ERRNO("%s: read", log_prefix);
-	}
 	if (n == 0)
-		FAIL("%s: incomplete read", log_prefix);
+		FAIL("%s: incomplete recv", log_prefix);
 
 close_peer1:
 	xclose(p1);
@@ -1571,7 +1564,6 @@ static void unix_redir_to_connected(int sotype, int sock_mapfd,
 	const char *log_prefix = redir_mode_str(mode);
 	int c0, c1, p0, p1;
 	unsigned int pass;
-	int retries = 100;
 	int err, n;
 	int sfd[2];
 	u32 key;
@@ -1606,17 +1598,11 @@ static void unix_redir_to_connected(int sotype, int sock_mapfd,
 	if (pass != 1)
 		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
 
-again:
+	n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
-	n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
+	if (n < 0)
-	if (n < 0) {
+		FAIL_ERRNO("%s: recv_timeout", log_prefix);
-		if (errno == EAGAIN && retries--) {
-			usleep(1000);
-			goto again;
-		}
-		FAIL_ERRNO("%s: read", log_prefix);
-	}
 	if (n == 0)
-		FAIL("%s: incomplete read", log_prefix);
+		FAIL("%s: incomplete recv", log_prefix);
 
 close:
 	xclose(c1);
@@ -1748,7 +1734,6 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd,
 	const char *log_prefix = redir_mode_str(mode);
 	int c0, c1, p0, p1;
 	unsigned int pass;
-	int retries = 100;
 	int err, n;
 	u32 key;
 	char b;
@@ -1781,17 +1766,11 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd,
 	if (pass != 1)
 		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
 
-again:
+	n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
-	n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
+	if (n < 0)
-	if (n < 0) {
+		FAIL_ERRNO("%s: recv_timeout", log_prefix);
-		if (errno == EAGAIN && retries--) {
-			usleep(1000);
-			goto again;
-		}
-		FAIL_ERRNO("%s: read", log_prefix);
-	}
 	if (n == 0)
-		FAIL("%s: incomplete read", log_prefix);
+		FAIL("%s: incomplete recv", log_prefix);
 
 close_cli1:
 	xclose(c1);
@@ -1841,7 +1820,6 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd,
 	const char *log_prefix = redir_mode_str(mode);
 	int c0, c1, p0, p1;
 	unsigned int pass;
-	int retries = 100;
 	int err, n;
 	int sfd[2];
 	u32 key;
@@ -1876,17 +1854,11 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd,
 	if (pass != 1)
 		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
 
-again:
+	n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
-	n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
+	if (n < 0)
-	if (n < 0) {
+		FAIL_ERRNO("%s: recv_timeout", log_prefix);
-		if (errno == EAGAIN && retries--) {
-			usleep(1000);
-			goto again;
-		}
-		FAIL_ERRNO("%s: read", log_prefix);
-	}
 	if (n == 0)
-		FAIL("%s: incomplete read", log_prefix);
+		FAIL("%s: incomplete recv", log_prefix);
 
 close_cli1:
 	xclose(c1);
@@ -1932,7 +1904,6 @@ static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd,
 	int sfd[2];
 	u32 key;
 	char b;
-	int retries = 100;
 
 	zero_verdict_count(verd_mapfd);
 
@@ -1963,17 +1934,11 @@ static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd,
 	if (pass != 1)
 		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
 
-again:
+	n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
-	n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
+	if (n < 0)
-	if (n < 0) {
+		FAIL_ERRNO("%s: recv_timeout", log_prefix);
-		if (errno == EAGAIN && retries--) {
-			usleep(1000);
-			goto again;
-		}
-		FAIL_ERRNO("%s: read", log_prefix);
-	}
 	if (n == 0)
-		FAIL("%s: incomplete read", log_prefix);
+		FAIL("%s: incomplete recv", log_prefix);
 
 close:
 	xclose(c1);

tools/testing/selftests/net/config

@@ -43,3 +43,4 @@ CONFIG_NET_ACT_TUNNEL_KEY=m
 CONFIG_NET_ACT_MIRRED=m
 CONFIG_BAREUDP=m
 CONFIG_IPV6_IOAM6_LWTUNNEL=y
+CONFIG_CRYPTO_SM4=y

tools/testing/selftests/net/fcnal-test.sh

@@ -289,6 +289,12 @@ set_sysctl()
 	run_cmd sysctl -q -w $*
 }
 
+# get sysctl values in NS-A
+get_sysctl()
+{
+	${NSA_CMD} sysctl -n $*
+}
+
 ################################################################################
 # Setup for tests
 
@@ -439,10 +445,13 @@ cleanup()
 		ip -netns ${NSA} link set dev ${NSA_DEV} down
 		ip -netns ${NSA} link del dev ${NSA_DEV}
 
+		ip netns pids ${NSA} | xargs kill 2>/dev/null
 		ip netns del ${NSA}
 	fi
 
+	ip netns pids ${NSB} | xargs kill 2>/dev/null
 	ip netns del ${NSB}
+	ip netns pids ${NSC} | xargs kill 2>/dev/null
 	ip netns del ${NSC} >/dev/null 2>&1
 }
 
@@ -1003,6 +1012,60 @@ ipv4_tcp_md5()
 	run_cmd nettest -s -I ${NSA_DEV} -M ${MD5_PW} -m ${NS_NET}
 	log_test $? 1 "MD5: VRF: Device must be a VRF - prefix"
 
+	test_ipv4_md5_vrf__vrf_server__no_bind_ifindex
+	test_ipv4_md5_vrf__global_server__bind_ifindex0
+}
+
+test_ipv4_md5_vrf__vrf_server__no_bind_ifindex()
+{
+	log_start
+	show_hint "Simulates applications using VRF without TCP_MD5SIG_FLAG_IFINDEX"
+	run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET} --no-bind-key-ifindex &
+	sleep 1
+	run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW}
+	log_test $? 0 "MD5: VRF: VRF-bound server, unbound key accepts connection"
+
+	log_start
+	show_hint "Binding both the socket and the key is not required but it works"
+	run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET} --force-bind-key-ifindex &
+	sleep 1
+	run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW}
+	log_test $? 0 "MD5: VRF: VRF-bound server, bound key accepts connection"
+}
+
+test_ipv4_md5_vrf__global_server__bind_ifindex0()
+{
+	# This particular test needs tcp_l3mdev_accept=1 for Global server to accept VRF connections
+	local old_tcp_l3mdev_accept
+	old_tcp_l3mdev_accept=$(get_sysctl net.ipv4.tcp_l3mdev_accept)
+	set_sysctl net.ipv4.tcp_l3mdev_accept=1
+
+	log_start
+	run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --force-bind-key-ifindex &
+	sleep 1
+	run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW}
+	log_test $? 2 "MD5: VRF: Global server, Key bound to ifindex=0 rejects VRF connection"
+
+	log_start
+	run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --force-bind-key-ifindex &
+	sleep 1
+	run_cmd_nsc nettest -r ${NSA_IP} -X ${MD5_PW}
+	log_test $? 0 "MD5: VRF: Global server, key bound to ifindex=0 accepts non-VRF connection"
+	log_start
+
+	run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --no-bind-key-ifindex &
+	sleep 1
+	run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW}
+	log_test $? 0 "MD5: VRF: Global server, key not bound to ifindex accepts VRF connection"
+
+	log_start
+	run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --no-bind-key-ifindex &
+	sleep 1
+	run_cmd_nsc nettest -r ${NSA_IP} -X ${MD5_PW}
+	log_test $? 0 "MD5: VRF: Global server, key not bound to ifindex accepts non-VRF connection"
+
+	# restore value
+	set_sysctl net.ipv4.tcp_l3mdev_accept="$old_tcp_l3mdev_accept"
 }
 
 ipv4_tcp_novrf()

tools/testing/selftests/net/forwarding/Makefile

@@ -9,6 +9,7 @@ TEST_PROGS = bridge_igmp.sh \
 	gre_inner_v4_multipath.sh \
 	gre_inner_v6_multipath.sh \
 	gre_multipath.sh \
+	ip6_forward_instats_vrf.sh \
 	ip6gre_inner_v4_multipath.sh \
 	ip6gre_inner_v6_multipath.sh \
 	ipip_flat_gre_key.sh \

tools/testing/selftests/net/forwarding/forwarding.config.sample

@@ -39,3 +39,5 @@ NETIF_CREATE=yes
 # Timeout (in seconds) before ping exits regardless of how many packets have
 # been sent or received
 PING_TIMEOUT=5
+# IPv6 traceroute utility name.
+TROUTE6=traceroute6

tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh

@@ -0,0 +1,172 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test ipv6 stats on the incoming if when forwarding with VRF
+
+ALL_TESTS="
+	ipv6_ping
+	ipv6_in_too_big_err
+	ipv6_in_hdr_err
+	ipv6_in_addr_err
+	ipv6_in_discard
+"
+
+NUM_NETIFS=4
+source lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 2001:1:1::2/64
+	ip -6 route add vrf v$h1 2001:1:2::/64 via 2001:1:1::1
+}
+
+h1_destroy()
+{
+	ip -6 route del vrf v$h1 2001:1:2::/64 via 2001:1:1::1
+	simple_if_fini $h1 2001:1:1::2/64
+}
+
+router_create()
+{
+	vrf_create router
+	__simple_if_init $rtr1 router 2001:1:1::1/64
+	__simple_if_init $rtr2 router 2001:1:2::1/64
+	mtu_set $rtr2 1280
+}
+
+router_destroy()
+{
+	mtu_restore $rtr2
+	__simple_if_fini $rtr2 2001:1:2::1/64
+	__simple_if_fini $rtr1 2001:1:1::1/64
+	vrf_destroy router
+}
+
+h2_create()
+{
+	simple_if_init $h2 2001:1:2::2/64
+	ip -6 route add vrf v$h2 2001:1:1::/64 via 2001:1:2::1
+	mtu_set $h2 1280
+}
+
+h2_destroy()
+{
+	mtu_restore $h2
+	ip -6 route del vrf v$h2 2001:1:1::/64 via 2001:1:2::1
+	simple_if_fini $h2 2001:1:2::2/64
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	rtr1=${NETIFS[p2]}
+
+	rtr2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	vrf_prepare
+	h1_create
+	router_create
+	h2_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	h2_destroy
+	router_destroy
+	h1_destroy
+	vrf_cleanup
+}
+
+ipv6_in_too_big_err()
+{
+	RET=0
+
+	local t0=$(ipv6_stats_get $rtr1 Ip6InTooBigErrors)
+	local vrf_name=$(master_name_get $h1)
+
+	# Send too big packets
+	ip vrf exec $vrf_name \
+		$PING6 -s 1300 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null
+
+	local t1=$(ipv6_stats_get $rtr1 Ip6InTooBigErrors)
+	test "$((t1 - t0))" -ne 0
+	check_err $?
+	log_test "Ip6InTooBigErrors"
+}
+
+ipv6_in_hdr_err()
+{
+	RET=0
+
+	local t0=$(ipv6_stats_get $rtr1 Ip6InHdrErrors)
+	local vrf_name=$(master_name_get $h1)
+
+	# Send packets with hop limit 1, easiest with traceroute6 as some ping6
+	# doesn't allow hop limit to be specified
+	ip vrf exec $vrf_name \
+		$TROUTE6 2001:1:2::2 &> /dev/null
+
+	local t1=$(ipv6_stats_get $rtr1 Ip6InHdrErrors)
+	test "$((t1 - t0))" -ne 0
+	check_err $?
+	log_test "Ip6InHdrErrors"
+}
+
+ipv6_in_addr_err()
+{
+	RET=0
+
+	local t0=$(ipv6_stats_get $rtr1 Ip6InAddrErrors)
+	local vrf_name=$(master_name_get $h1)
+
+	# Disable forwarding temporary while sending the packet
+	sysctl -qw net.ipv6.conf.all.forwarding=0
+	ip vrf exec $vrf_name \
+		$PING6 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null
+	sysctl -qw net.ipv6.conf.all.forwarding=1
+
+	local t1=$(ipv6_stats_get $rtr1 Ip6InAddrErrors)
+	test "$((t1 - t0))" -ne 0
+	check_err $?
+	log_test "Ip6InAddrErrors"
+}
+
+ipv6_in_discard()
+{
+	RET=0
+
+	local t0=$(ipv6_stats_get $rtr1 Ip6InDiscards)
+	local vrf_name=$(master_name_get $h1)
+
+	# Add a policy to discard
+	ip xfrm policy add dst 2001:1:2::2/128 dir fwd action block
+	ip vrf exec $vrf_name \
+		$PING6 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null
+	ip xfrm policy del dst 2001:1:2::2/128 dir fwd
+
+	local t1=$(ipv6_stats_get $rtr1 Ip6InDiscards)
+	test "$((t1 - t0))" -ne 0
+	check_err $?
+	log_test "Ip6InDiscards"
+}
+ipv6_ping()
+{
+	RET=0
+
+	ping6_test $h1 2001:1:2::2
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS

tools/testing/selftests/net/forwarding/lib.sh

@@ -751,6 +751,14 @@ qdisc_parent_stats_get()
 	    | jq '.[] | select(.parent == "'"$parent"'") | '"$selector"
 }
 
+ipv6_stats_get()
+{
+	local dev=$1; shift
+	local stat=$1; shift
+
+	cat /proc/net/dev_snmp6/$dev | grep "^$stat" | cut -f2
+}
+
 humanize()
 {
 	local speed=$1; shift

tools/testing/selftests/net/nettest.c

@@ -28,6 +28,7 @@
 #include <unistd.h>
 #include <time.h>
 #include <errno.h>
+#include <getopt.h>
 
 #include <linux/xfrm.h>
 #include <linux/ipsec.h>
@@ -101,6 +102,8 @@ struct sock_args {
 		struct sockaddr_in6 v6;
 	} md5_prefix;
 	unsigned int prefix_len;
+	/* 0: default, -1: force off, +1: force on */
+	int bind_key_ifindex;
 
 	/* expected addresses and device index for connection */
 	const char *expected_dev;
@@ -271,11 +274,14 @@ static int tcp_md5sig(int sd, void *addr, socklen_t alen, struct sock_args *args
 	}
 	memcpy(&md5sig.tcpm_addr, addr, alen);
 
-	if (args->ifindex) {
+	if ((args->ifindex && args->bind_key_ifindex >= 0) || args->bind_key_ifindex >= 1) {
 		opt = TCP_MD5SIG_EXT;
 		md5sig.tcpm_flags |= TCP_MD5SIG_FLAG_IFINDEX;
 
 		md5sig.tcpm_ifindex = args->ifindex;
+		log_msg("TCP_MD5SIG_FLAG_IFINDEX set tcpm_ifindex=%d\n", md5sig.tcpm_ifindex);
+	} else {
+		log_msg("TCP_MD5SIG_FLAG_IFINDEX off\n", md5sig.tcpm_ifindex);
 	}
 
 	rc = setsockopt(sd, IPPROTO_TCP, opt, &md5sig, sizeof(md5sig));
@@ -1822,6 +1828,14 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args)
 }
 
 #define GETOPT_STR  "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6xL:0:1:2:3:Fbq"
+#define OPT_FORCE_BIND_KEY_IFINDEX 1001
+#define OPT_NO_BIND_KEY_IFINDEX 1002
+
+static struct option long_opts[] = {
+	{"force-bind-key-ifindex", 0, 0, OPT_FORCE_BIND_KEY_IFINDEX},
+	{"no-bind-key-ifindex", 0, 0, OPT_NO_BIND_KEY_IFINDEX},
+	{0, 0, 0, 0}
+};
 
 static void print_usage(char *prog)
 {
@@ -1858,6 +1872,10 @@ static void print_usage(char *prog)
 	"    -M password   use MD5 sum protection\n"
 	"    -X password   MD5 password for client mode\n"
 	"    -m prefix/len prefix and length to use for MD5 key\n"
+	"    --no-bind-key-ifindex: Force TCP_MD5SIG_FLAG_IFINDEX off\n"
+	"    --force-bind-key-ifindex: Force TCP_MD5SIG_FLAG_IFINDEX on\n"
+	"        (default: only if -I is passed)\n"
+	"\n"
 	"    -g grp        multicast group (e.g., 239.1.1.1)\n"
 	"    -i            interactive mode (default is echo and terminate)\n"
 	"\n"
@@ -1893,7 +1911,7 @@ int main(int argc, char *argv[])
 	 * process input args
 	 */
 
-	while ((rc = getopt(argc, argv, GETOPT_STR)) != -1) {
+	while ((rc = getopt_long(argc, argv, GETOPT_STR, long_opts, NULL)) != -1) {
 		switch (rc) {
 		case 'B':
 			both_mode = 1;
@@ -1966,6 +1984,12 @@ int main(int argc, char *argv[])
 		case 'M':
 			args.password = optarg;
 			break;
+		case OPT_FORCE_BIND_KEY_IFINDEX:
+			args.bind_key_ifindex = 1;
+			break;
+		case OPT_NO_BIND_KEY_IFINDEX:
+			args.bind_key_ifindex = -1;
+			break;
 		case 'X':
 			args.client_pw = optarg;
 			break;

tools/testing/selftests/netfilter/nft_flowtable.sh

@@ -199,7 +199,6 @@ fi
 # test basic connectivity
 if ! ip netns exec ns1 ping -c 1 -q 10.0.2.99 > /dev/null; then
   echo "ERROR: ns1 cannot reach ns2" 1>&2
-  bash
   exit 1
 fi
 

tools/testing/selftests/netfilter/nft_nat.sh

@@ -741,6 +741,149 @@ EOF
 	return $lret
 }
 
+# test port shadowing.
+# create two listening services, one on router (ns0), one
+# on client (ns2), which is masqueraded from ns1 point of view.
+# ns2 sends udp packet coming from service port to ns1, on a highport.
+# Later, if n1 uses same highport to connect to ns0:service, packet
+# might be port-forwarded to ns2 instead.
+
+# second argument tells if we expect the 'fake-entry' to take effect
+# (CLIENT) or not (ROUTER).
+test_port_shadow()
+{
+	local test=$1
+	local expect=$2
+	local daddrc="10.0.1.99"
+	local daddrs="10.0.1.1"
+	local result=""
+	local logmsg=""
+
+	echo ROUTER | ip netns exec "$ns0" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 &
+	nc_r=$!
+
+	echo CLIENT | ip netns exec "$ns2" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 &
+	nc_c=$!
+
+	# make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405.
+	echo "fake-entry" | ip netns exec "$ns2" nc -w 1 -p 1405 -u "$daddrc" 41404 > /dev/null
+
+	# ns1 tries to connect to ns0:1405.  With default settings this should connect
+	# to client, it matches the conntrack entry created above.
+
+	result=$(echo "" | ip netns exec "$ns1" nc -w 1 -p 41404 -u "$daddrs" 1405)
+
+	if [ "$result" = "$expect" ] ;then
+		echo "PASS: portshadow test $test: got reply from ${expect}${logmsg}"
+	else
+		echo "ERROR: portshadow test $test: got reply from \"$result\", not $expect as intended"
+		ret=1
+	fi
+
+	kill $nc_r $nc_c 2>/dev/null
+
+	# flush udp entries for next test round, if any
+	ip netns exec "$ns0" conntrack -F >/dev/null 2>&1
+}
+
+# This prevents port shadow of router service via packet filter,
+# packets claiming to originate from service port from internal
+# network are dropped.
+test_port_shadow_filter()
+{
+	local family=$1
+
+ip netns exec "$ns0" nft -f /dev/stdin <<EOF
+table $family filter {
+	chain forward {
+		type filter hook forward priority 0; policy accept;
+		meta iif veth1 udp sport 1405 drop
+	}
+}
+EOF
+	test_port_shadow "port-filter" "ROUTER"
+
+	ip netns exec "$ns0" nft delete table $family filter
+}
+
+# This prevents port shadow of router service via notrack.
+test_port_shadow_notrack()
+{
+	local family=$1
+
+ip netns exec "$ns0" nft -f /dev/stdin <<EOF
+table $family raw {
+	chain prerouting {
+		type filter hook prerouting priority -300; policy accept;
+		meta iif veth0 udp dport 1405 notrack
+		udp dport 1405 notrack
+	}
+	chain output {
+		type filter hook output priority -300; policy accept;
+		udp sport 1405 notrack
+	}
+}
+EOF
+	test_port_shadow "port-notrack" "ROUTER"
+
+	ip netns exec "$ns0" nft delete table $family raw
+}
+
+# This prevents port shadow of router service via sport remap.
+test_port_shadow_pat()
+{
+	local family=$1
+
+ip netns exec "$ns0" nft -f /dev/stdin <<EOF
+table $family pat {
+	chain postrouting {
+		type nat hook postrouting priority -1; policy accept;
+		meta iif veth1 udp sport <= 1405 masquerade to : 1406-65535 random
+	}
+}
+EOF
+	test_port_shadow "pat" "ROUTER"
+
+	ip netns exec "$ns0" nft delete table $family pat
+}
+
+test_port_shadowing()
+{
+	local family="ip"
+
+	ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
+	ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+
+	ip netns exec "$ns0" nft -f /dev/stdin <<EOF
+table $family nat {
+	chain postrouting {
+		type nat hook postrouting priority 0; policy accept;
+		meta oif veth0 masquerade
+	}
+}
+EOF
+	if [ $? -ne 0 ]; then
+		echo "SKIP: Could not add add $family masquerade hook"
+		return $ksft_skip
+	fi
+
+	# test default behaviour. Packet from ns1 to ns0 is redirected to ns2.
+	test_port_shadow "default" "CLIENT"
+
+	# test packet filter based mitigation: prevent forwarding of
+	# packets claiming to come from the service port.
+	test_port_shadow_filter "$family"
+
+	# test conntrack based mitigation: connections going or coming
+	# from router:service bypass connection tracking.
+	test_port_shadow_notrack "$family"
+
+	# test nat based mitigation: fowarded packets coming from service port
+	# are masqueraded with random highport.
+	test_port_shadow_pat "$family"
+
+	ip netns exec "$ns0" nft delete table $family nat
+}
 
 # ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99
 for i in 0 1 2; do
@@ -861,6 +1004,8 @@ reset_counters
 $test_inet_nat && test_redirect inet
 $test_inet_nat && test_redirect6 inet
 
+test_port_shadowing
+
 if [ $ret -ne 0 ];then
 	echo -n "FAIL: "
 	nft --version

tools/testing/selftests/vm/split_huge_page_test.c

@@ -341,7 +341,7 @@ void split_file_backed_thp(void)
 	}
 
 	/* write something to the file, so a file-backed THP can be allocated */
-	num_written = write(fd, tmpfs_loc, sizeof(tmpfs_loc));
+	num_written = write(fd, tmpfs_loc, strlen(tmpfs_loc) + 1);
 	close(fd);
 
 	if (num_written < 1) {

tools/testing/selftests/vm/userfaultfd.c

@@ -414,9 +414,6 @@ static void uffd_test_ctx_init_ext(uint64_t *features)
 	uffd_test_ops->allocate_area((void **)&area_src);
 	uffd_test_ops->allocate_area((void **)&area_dst);
 
-	uffd_test_ops->release_pages(area_src);
-	uffd_test_ops->release_pages(area_dst);
-
 	userfaultfd_open(features);
 
 	count_verify = malloc(nr_pages * sizeof(unsigned long long));
@@ -437,6 +434,26 @@ static void uffd_test_ctx_init_ext(uint64_t *features)
 		*(area_count(area_src, nr) + 1) = 1;
 	}
 
+	/*
+	 * After initialization of area_src, we must explicitly release pages
+	 * for area_dst to make sure it's fully empty.  Otherwise we could have
+	 * some area_dst pages be errornously initialized with zero pages,
+	 * hence we could hit memory corruption later in the test.
+	 *
+	 * One example is when THP is globally enabled, above allocate_area()
+	 * calls could have the two areas merged into a single VMA (as they
+	 * will have the same VMA flags so they're mergeable).  When we
+	 * initialize the area_src above, it's possible that some part of
+	 * area_dst could have been faulted in via one huge THP that will be
+	 * shared between area_src and area_dst.  It could cause some of the
+	 * area_dst won't be trapped by missing userfaults.
+	 *
+	 * This release_pages() will guarantee even if that happened, we'll
+	 * proactively split the thp and drop any accidentally initialized
+	 * pages within area_dst.
+	 */
+	uffd_test_ops->release_pages(area_dst);
+
 	pipefd = malloc(sizeof(int) * nr_cpus * 2);
 	if (!pipefd)
 		err("pipefd");

tools/testing/vsock/vsock_diag_test.c

@@ -332,8 +332,6 @@ static void test_no_sockets(const struct test_opts *opts)
 	read_vsock_stat(&sockets);
 
 	check_no_sockets(&sockets);
-
-	free_sock_stat(&sockets);
 }
 
 static void test_listen_socket_server(const struct test_opts *opts)