Merge tag 'net-6.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from netfilter.

  It looks like that most people are still traveling: both the ML volume
  and the processing capacity are low.

  Previous releases - regressions:

    - netfilter:
        - nf_reject_ipv6: fix nf_reject_ip6_tcphdr_put()
        - nf_tables: keep deleted flowtable hooks until after RCU

    - tcp: check skb is non-NULL in tcp_rto_delta_us()

    - phy: aquantia: fix -ETIMEDOUT PHY probe failure when firmware not
      present

    - eth: virtio_net: fix mismatched buf address when unmapping for
      small packets

    - eth: stmmac: fix zero-division error when disabling tc cbs

    - eth: bonding: fix unnecessary warnings and logs from
      bond_xdp_get_xmit_slave()

  Previous releases - always broken:

    - netfilter:
        - fix clash resolution for bidirectional flows
        - fix allocation with no memcg accounting

    - eth: r8169: add tally counter fields added with RTL8125

    - eth: ravb: fix rx and tx frame size limit"

* tag 'net-6.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (35 commits)
  selftests: netfilter: Avoid hanging ipvs.sh
  kselftest: add test for nfqueue induced conntrack race
  netfilter: nfnetlink_queue: remove old clash resolution logic
  netfilter: nf_tables: missing objects with no memcg accounting
  netfilter: nf_tables: use rcu chain hook list iterator from netlink dump path
  netfilter: ctnetlink: compile ctnetlink_label_size with CONFIG_NF_CONNTRACK_EVENTS
  netfilter: nf_reject: Fix build warning when CONFIG_BRIDGE_NETFILTER=n
  netfilter: nf_tables: Keep deleted flowtable hooks until after RCU
  docs: tproxy: ignore non-transparent sockets in iptables
  netfilter: ctnetlink: Guard possible unused functions
  selftests: netfilter: nft_tproxy.sh: add tcp tests
  selftests: netfilter: add reverse-clash resolution test case
  netfilter: conntrack: add clash resolution for reverse collisions
  netfilter: nf_nat: don't try nat source port reallocation for reverse dir clash
  selftests/net: packetdrill: increase timing tolerance in debug mode
  usbnet: fix cyclical race on disconnect with work queue
  net: stmmac: set PP_FLAG_DMA_SYNC_DEV only if XDP is enabled
  virtio_net: Fix mismatched buf address when unmapping for small packets
  bonding: Fix unnecessary warnings and logs from bond_xdp_get_xmit_slave()
  r8169: add missing MODULE_FIRMWARE entry for RTL8126A rev.b
  ...

9 files changed, 900 insertions, 4 deletions

diff --git a/tools/testing/selftests/net/netfilter/Makefile b/tools/testing/selftests/net/netfilter/Makefile
index d13fb5ea3e89..e6c9e777fead 100644
--- a/tools/testing/selftests/net/netfilter/Makefile
+++ b/tools/testing/selftests/net/netfilter/Makefile
@@ -13,6 +13,7 @@ TEST_PROGS += conntrack_ipip_mtu.sh
 TEST_PROGS += conntrack_tcp_unreplied.sh
 TEST_PROGS += conntrack_sctp_collision.sh
 TEST_PROGS += conntrack_vrf.sh
+TEST_PROGS += conntrack_reverse_clash.sh
 TEST_PROGS += ipvs.sh
 TEST_PROGS += nf_conntrack_packetdrill.sh
 TEST_PROGS += nf_nat_edemux.sh
@@ -26,6 +27,8 @@ TEST_PROGS += nft_nat.sh
 TEST_PROGS += nft_nat_zones.sh
 TEST_PROGS += nft_queue.sh
 TEST_PROGS += nft_synproxy.sh
+TEST_PROGS += nft_tproxy_tcp.sh
+TEST_PROGS += nft_tproxy_udp.sh
 TEST_PROGS += nft_zones_many.sh
 TEST_PROGS += rpath.sh
 TEST_PROGS += xt_string.sh
@@ -36,6 +39,7 @@ TEST_GEN_PROGS = conntrack_dump_flush
 
 TEST_GEN_FILES = audit_logread
 TEST_GEN_FILES += connect_close nf_queue
+TEST_GEN_FILES += conntrack_reverse_clash
 TEST_GEN_FILES += sctp_collision
 
 include ../../lib.mk
diff --git a/tools/testing/selftests/net/netfilter/config b/tools/testing/selftests/net/netfilter/config
index b2dd4db45215..c5fe7b34eaf1 100644
--- a/tools/testing/selftests/net/netfilter/config
+++ b/tools/testing/selftests/net/netfilter/config
@@ -81,6 +81,7 @@ CONFIG_NFT_QUEUE=m
 CONFIG_NFT_QUOTA=m
 CONFIG_NFT_REDIR=m
 CONFIG_NFT_SYNPROXY=m
+CONFIG_NFT_TPROXY=m
 CONFIG_VETH=m
 CONFIG_VLAN_8021Q=m
 CONFIG_XFRM_USER=m
diff --git a/tools/testing/selftests/net/netfilter/conntrack_reverse_clash.c b/tools/testing/selftests/net/netfilter/conntrack_reverse_clash.c
new file mode 100644
index 000000000000..507930cee8cb
--- /dev/null
+++ b/tools/testing/selftests/net/netfilter/conntrack_reverse_clash.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Needs something like:
+ *
+ * iptables -t nat -A POSTROUTING -o nomatch -j MASQUERADE
+ *
+ * so NAT engine attaches a NAT null-binding to each connection.
+ *
+ * With unmodified kernels, child or parent will exit with
+ * "Port number changed" error, even though no port translation
+ * was requested.
+ */
+
+#include <errno.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+#include <time.h>
+#include <unistd.h>
+#include <arpa/inet.h>
+#include <sys/socket.h>
+#include <sys/wait.h>
+
+#define LEN 512
+#define PORT 56789
+#define TEST_TIME 5
+
+static void die(const char *e)
+{
+	perror(e);
+	exit(111);
+}
+
+static void die_port(uint16_t got, uint16_t want)
+{
+	fprintf(stderr, "Port number changed, wanted %d got %d\n", want, ntohs(got));
+	exit(1);
+}
+
+static int udp_socket(void)
+{
+	static const struct timeval tv = {
+		.tv_sec = 1,
+	};
+	int fd = socket(AF_INET, SOCK_DGRAM, IPPROTO_UDP);
+
+	if (fd < 0)
+		die("socket");
+
+	setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv));
+	return fd;
+}
+
+int main(int argc, char *argv[])
+{
+	struct sockaddr_in sa1 = {
+		.sin_family = AF_INET,
+	};
+	struct sockaddr_in sa2 = {
+		.sin_family = AF_INET,
+	};
+	int s1, s2, status;
+	time_t end, now;
+	socklen_t plen;
+	char buf[LEN];
+	bool child;
+
+	sa1.sin_port = htons(PORT);
+	sa2.sin_port = htons(PORT + 1);
+
+	s1 = udp_socket();
+	s2 = udp_socket();
+
+	inet_pton(AF_INET, "127.0.0.11", &sa1.sin_addr);
+	inet_pton(AF_INET, "127.0.0.12", &sa2.sin_addr);
+
+	if (bind(s1, (struct sockaddr *)&sa1, sizeof(sa1)) < 0)
+		die("bind 1");
+	if (bind(s2, (struct sockaddr *)&sa2, sizeof(sa2)) < 0)
+		die("bind 2");
+
+	child = fork() == 0;
+
+	now = time(NULL);
+	end = now + TEST_TIME;
+
+	while (now < end) {
+		struct sockaddr_in peer;
+		socklen_t plen = sizeof(peer);
+
+		now = time(NULL);
+
+		if (child) {
+			if (sendto(s1, buf, LEN, 0, (struct sockaddr *)&sa2, sizeof(sa2)) != LEN)
+				continue;
+
+			if (recvfrom(s2, buf, LEN, 0, (struct sockaddr *)&peer, &plen) < 0)
+				die("child recvfrom");
+
+			if (peer.sin_port != htons(PORT))
+				die_port(peer.sin_port, PORT);
+		} else {
+			if (sendto(s2, buf, LEN, 0, (struct sockaddr *)&sa1, sizeof(sa1)) != LEN)
+				continue;
+
+			if (recvfrom(s1, buf, LEN, 0, (struct sockaddr *)&peer, &plen) < 0)
+				die("parent recvfrom");
+
+			if (peer.sin_port != htons((PORT + 1)))
+				die_port(peer.sin_port, PORT + 1);
+		}
+	}
+
+	if (child)
+		return 0;
+
+	wait(&status);
+
+	if (WIFEXITED(status))
+		return WEXITSTATUS(status);
+
+	return 1;
+}
diff --git a/tools/testing/selftests/net/netfilter/conntrack_reverse_clash.sh b/tools/testing/selftests/net/netfilter/conntrack_reverse_clash.sh
new file mode 100755
index 000000000000..a24c896347a8
--- /dev/null
+++ b/tools/testing/selftests/net/netfilter/conntrack_reverse_clash.sh
@@ -0,0 +1,51 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source lib.sh
+
+cleanup()
+{
+	cleanup_all_ns
+}
+
+checktool "nft --version" "run test without nft"
+checktool "conntrack --version" "run test without conntrack"
+
+trap cleanup EXIT
+
+setup_ns ns0
+
+# make loopback connections get nat null bindings assigned
+ip netns exec "$ns0" nft -f - <<EOF
+table ip nat {
+        chain POSTROUTING {
+                type nat hook postrouting priority srcnat; policy accept;
+                oifname "nomatch" counter packets 0 bytes 0 masquerade
+        }
+}
+EOF
+
+do_flush()
+{
+	local end
+	local now
+
+	now=$(date +%s)
+	end=$((now + 5))
+
+	while [ $now -lt $end ];do
+		ip netns exec "$ns0" conntrack -F 2>/dev/null
+		now=$(date +%s)
+	done
+}
+
+do_flush &
+
+if ip netns exec "$ns0" ./conntrack_reverse_clash; then
+	echo "PASS: No SNAT performed for null bindings"
+else
+	echo "ERROR: SNAT performed without any matching snat rule"
+	exit 1
+fi
+
+exit 0
diff --git a/tools/testing/selftests/net/netfilter/ipvs.sh b/tools/testing/selftests/net/netfilter/ipvs.sh
index 4ceee9fb3949..d3edb16cd4b3 100755
--- a/tools/testing/selftests/net/netfilter/ipvs.sh
+++ b/tools/testing/selftests/net/netfilter/ipvs.sh
@@ -97,7 +97,7 @@ cleanup() {
 }
 
 server_listen() {
-	ip netns exec "$ns2" socat -u -4 TCP-LISTEN:8080,reuseaddr STDOUT > "${outfile}" &
+	ip netns exec "$ns2" timeout 5 socat -u -4 TCP-LISTEN:8080,reuseaddr STDOUT > "${outfile}" &
 	server_pid=$!
 	sleep 0.2
 }
diff --git a/tools/testing/selftests/net/netfilter/nft_queue.sh b/tools/testing/selftests/net/netfilter/nft_queue.sh
index d66e3c4dfec6..a9d109fcc15c 100755
--- a/tools/testing/selftests/net/netfilter/nft_queue.sh
+++ b/tools/testing/selftests/net/netfilter/nft_queue.sh
@@ -31,7 +31,7 @@ modprobe -q sctp
 
 trap cleanup EXIT
 
-setup_ns ns1 ns2 nsrouter
+setup_ns ns1 ns2 ns3 nsrouter
 
 TMPFILE0=$(mktemp)
 TMPFILE1=$(mktemp)
@@ -48,6 +48,7 @@ if ! ip link add veth0 netns "$nsrouter" type veth peer name eth0 netns "$ns1" >
     exit $ksft_skip
 fi
 ip link add veth1 netns "$nsrouter" type veth peer name eth0 netns "$ns2"
+ip link add veth2 netns "$nsrouter" type veth peer name eth0 netns "$ns3"
 
 ip -net "$nsrouter" link set veth0 up
 ip -net "$nsrouter" addr add 10.0.1.1/24 dev veth0
@@ -57,8 +58,13 @@ ip -net "$nsrouter" link set veth1 up
 ip -net "$nsrouter" addr add 10.0.2.1/24 dev veth1
 ip -net "$nsrouter" addr add dead:2::1/64 dev veth1 nodad
 
+ip -net "$nsrouter" link set veth2 up
+ip -net "$nsrouter" addr add 10.0.3.1/24 dev veth2
+ip -net "$nsrouter" addr add dead:3::1/64 dev veth2 nodad
+
 ip -net "$ns1" link set eth0 up
 ip -net "$ns2" link set eth0 up
+ip -net "$ns3" link set eth0 up
 
 ip -net "$ns1" addr add 10.0.1.99/24 dev eth0
 ip -net "$ns1" addr add dead:1::99/64 dev eth0 nodad
@@ -70,6 +76,11 @@ ip -net "$ns2" addr add dead:2::99/64 dev eth0 nodad
 ip -net "$ns2" route add default via 10.0.2.1
 ip -net "$ns2" route add default via dead:2::1
 
+ip -net "$ns3" addr add 10.0.3.99/24 dev eth0
+ip -net "$ns3" addr add dead:3::99/64 dev eth0 nodad
+ip -net "$ns3" route add default via 10.0.3.1
+ip -net "$ns3" route add default via dead:3::1
+
 load_ruleset() {
 	local name=$1
 	local prio=$2
@@ -473,6 +484,83 @@ EOF
 	check_output_files "$TMPINPUT" "$TMPFILE1" "sctp output"
 }
 
+udp_listener_ready()
+{
+	ss -S -N "$1" -uln -o "sport = :12345" | grep -q 12345
+}
+
+output_files_written()
+{
+	test -s "$1" && test -s "$2"
+}
+
+test_udp_ct_race()
+{
+        ip netns exec "$nsrouter" nft -f /dev/stdin <<EOF
+flush ruleset
+table inet udpq {
+	chain prerouting {
+		type nat hook prerouting priority dstnat - 5; policy accept;
+		ip daddr 10.6.6.6 udp dport 12345 counter dnat to numgen inc mod 2 map { 0 : 10.0.2.99, 1 : 10.0.3.99 }
+	}
+        chain postrouting {
+		type filter hook postrouting priority srcnat - 5; policy accept;
+		udp dport 12345 counter queue num 12
+        }
+}
+EOF
+	:> "$TMPFILE1"
+	:> "$TMPFILE2"
+
+	timeout 10 ip netns exec "$ns2" socat UDP-LISTEN:12345,fork OPEN:"$TMPFILE1",trunc &
+	local rpid1=$!
+
+	timeout 10 ip netns exec "$ns3" socat UDP-LISTEN:12345,fork OPEN:"$TMPFILE2",trunc &
+	local rpid2=$!
+
+	ip netns exec "$nsrouter" ./nf_queue -q 12 -d 1000 &
+	local nfqpid=$!
+
+	busywait "$BUSYWAIT_TIMEOUT" udp_listener_ready "$ns2"
+	busywait "$BUSYWAIT_TIMEOUT" udp_listener_ready "$ns3"
+	busywait "$BUSYWAIT_TIMEOUT" nf_queue_wait "$nsrouter" 12
+
+	# Send two packets, one should end up in ns1, other in ns2.
+	# This is because nfqueue will delay packet for long enough so that
+	# second packet will not find existing conntrack entry.
+	echo "Packet 1" | ip netns exec "$ns1" socat STDIN UDP-DATAGRAM:10.6.6.6:12345,bind=0.0.0.0:55221
+	echo "Packet 2" | ip netns exec "$ns1" socat STDIN UDP-DATAGRAM:10.6.6.6:12345,bind=0.0.0.0:55221
+
+	busywait 10000 output_files_written "$TMPFILE1" "$TMPFILE2"
+
+	kill "$nfqpid"
+
+	if ! ip netns exec "$nsrouter" bash -c 'conntrack -L -p udp --dport 12345 2>/dev/null | wc -l | grep -q "^1"'; then
+		echo "FAIL: Expected One udp conntrack entry"
+		ip netns exec "$nsrouter" conntrack -L -p udp --dport 12345
+		ret=1
+	fi
+
+	if ! ip netns exec "$nsrouter" nft delete table inet udpq; then
+		echo "FAIL: Could not delete udpq table"
+		ret=1
+		return
+	fi
+
+	NUMLINES1=$(wc -l < "$TMPFILE1")
+	NUMLINES2=$(wc -l < "$TMPFILE2")
+
+	if [ "$NUMLINES1" -ne 1 ] || [ "$NUMLINES2" -ne 1 ]; then
+		ret=1
+		echo "FAIL: uneven udp packet distribution: $NUMLINES1 $NUMLINES2"
+		echo -n "$TMPFILE1: ";cat "$TMPFILE1"
+		echo -n "$TMPFILE2: ";cat "$TMPFILE2"
+		return
+	fi
+
+	echo "PASS: both udp receivers got one packet each"
+}
+
 test_queue_removal()
 {
 	read tainted_then < /proc/sys/kernel/tainted
@@ -512,6 +600,7 @@ EOF
 ip netns exec "$nsrouter" sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
 ip netns exec "$nsrouter" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
 ip netns exec "$nsrouter" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+ip netns exec "$nsrouter" sysctl net.ipv4.conf.veth2.forwarding=1 > /dev/null
 
 load_ruleset "filter" 0
 
@@ -549,6 +638,7 @@ test_tcp_localhost_connectclose
 test_tcp_localhost_requeue
 test_sctp_forward
 test_sctp_output
+test_udp_ct_race
 
 # should be last, adds vrf device in ns1 and changes routes
 test_icmp_vrf
diff --git a/tools/testing/selftests/net/netfilter/nft_tproxy_tcp.sh b/tools/testing/selftests/net/netfilter/nft_tproxy_tcp.sh
new file mode 100755
index 000000000000..e208fb03eeb7
--- /dev/null
+++ b/tools/testing/selftests/net/netfilter/nft_tproxy_tcp.sh
@@ -0,0 +1,358 @@
+#!/bin/bash
+#
+# This tests tproxy on the following scenario:
+#
+#                         +------------+
+# +-------+               |  nsrouter  |                  +-------+
+# |ns1    |.99          .1|            |.1             .99|    ns2|
+# |   eth0|---------------|veth0  veth1|------------------|eth0   |
+# |       |  10.0.1.0/24  |            |   10.0.2.0/24    |       |
+# +-------+  dead:1::/64  |    veth2   |   dead:2::/64    +-------+
+#                         +------------+
+#                                |.1
+#                                |
+#                                |
+#                                |                        +-------+
+#                                |                     .99|    ns3|
+#                                +------------------------|eth0   |
+#                                       10.0.3.0/24       |       |
+#                                       dead:3::/64       +-------+
+#
+# The tproxy implementation acts as an echo server so the client
+# must receive the same message it sent if it has been proxied.
+# If is not proxied the servers return PONG_NS# with the number
+# of the namespace the server is running.
+#
+# shellcheck disable=SC2162,SC2317
+
+source lib.sh
+ret=0
+timeout=5
+
+cleanup()
+{
+	ip netns pids "$ns1" | xargs kill 2>/dev/null
+	ip netns pids "$ns2" | xargs kill 2>/dev/null
+	ip netns pids "$ns3" | xargs kill 2>/dev/null
+	ip netns pids "$nsrouter" | xargs kill 2>/dev/null
+
+	cleanup_all_ns
+}
+
+checktool "nft --version" "test without nft tool"
+checktool "socat -h" "run test without socat"
+
+trap cleanup EXIT
+setup_ns ns1 ns2 ns3 nsrouter
+
+if ! ip link add veth0 netns "$nsrouter" type veth peer name eth0 netns "$ns1" > /dev/null 2>&1; then
+    echo "SKIP: No virtual ethernet pair device support in kernel"
+    exit $ksft_skip
+fi
+ip link add veth1 netns "$nsrouter" type veth peer name eth0 netns "$ns2"
+ip link add veth2 netns "$nsrouter" type veth peer name eth0 netns "$ns3"
+
+ip -net "$nsrouter" link set veth0 up
+ip -net "$nsrouter" addr add 10.0.1.1/24 dev veth0
+ip -net "$nsrouter" addr add dead:1::1/64 dev veth0 nodad
+
+ip -net "$nsrouter" link set veth1 up
+ip -net "$nsrouter" addr add 10.0.2.1/24 dev veth1
+ip -net "$nsrouter" addr add dead:2::1/64 dev veth1 nodad
+
+ip -net "$nsrouter" link set veth2 up
+ip -net "$nsrouter" addr add 10.0.3.1/24 dev veth2
+ip -net "$nsrouter" addr add dead:3::1/64 dev veth2 nodad
+
+ip -net "$ns1" link set eth0 up
+ip -net "$ns2" link set eth0 up
+ip -net "$ns3" link set eth0 up
+
+ip -net "$ns1" addr add 10.0.1.99/24 dev eth0
+ip -net "$ns1" addr add dead:1::99/64 dev eth0 nodad
+ip -net "$ns1" route add default via 10.0.1.1
+ip -net "$ns1" route add default via dead:1::1
+
+ip -net "$ns2" addr add 10.0.2.99/24 dev eth0
+ip -net "$ns2" addr add dead:2::99/64 dev eth0 nodad
+ip -net "$ns2" route add default via 10.0.2.1
+ip -net "$ns2" route add default via dead:2::1
+
+ip -net "$ns3" addr add 10.0.3.99/24 dev eth0
+ip -net "$ns3" addr add dead:3::99/64 dev eth0 nodad
+ip -net "$ns3" route add default via 10.0.3.1
+ip -net "$ns3" route add default via dead:3::1
+
+ip netns exec "$nsrouter" sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
+ip netns exec "$nsrouter" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
+ip netns exec "$nsrouter" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+ip netns exec "$nsrouter" sysctl net.ipv4.conf.veth2.forwarding=1 > /dev/null
+
+test_ping() {
+  if ! ip netns exec "$ns1" ping -c 1 -q 10.0.2.99 > /dev/null; then
+	return 1
+  fi
+
+  if ! ip netns exec "$ns1" ping -c 1 -q dead:2::99 > /dev/null; then
+	return 2
+  fi
+
+  if ! ip netns exec "$ns1" ping -c 1 -q 10.0.3.99 > /dev/null; then
+	return 1
+  fi
+
+  if ! ip netns exec "$ns1" ping -c 1 -q dead:3::99 > /dev/null; then
+	return 2
+  fi
+
+  return 0
+}
+
+test_ping_router() {
+  if ! ip netns exec "$ns1" ping -c 1 -q 10.0.2.1 > /dev/null; then
+	return 3
+  fi
+
+  if ! ip netns exec "$ns1" ping -c 1 -q dead:2::1 > /dev/null; then
+	return 4
+  fi
+
+  return 0
+}
+
+
+listener_ready()
+{
+	local ns="$1"
+	local port="$2"
+	local proto="$3"
+	ss -N "$ns" -ln "$proto" -o "sport = :$port" | grep -q "$port"
+}
+
+test_tproxy()
+{
+	local traffic_origin="$1"
+	local ip_proto="$2"
+	local expect_ns1_ns2="$3"
+	local expect_ns1_ns3="$4"
+	local expect_nsrouter_ns2="$5"
+	local expect_nsrouter_ns3="$6"
+
+	# derived variables
+	local testname="test_${ip_proto}_tcp_${traffic_origin}"
+	local socat_ipproto
+	local ns1_ip
+	local ns2_ip
+	local ns3_ip
+	local ns2_target
+	local ns3_target
+	local nftables_subject
+	local ip_command
+
+	# socat 1.8.0 has a bug that requires to specify the IP family to bind (fixed in 1.8.0.1)
+	case $ip_proto in
+	"ip")
+		socat_ipproto="-4"
+		ns1_ip=10.0.1.99
+		ns2_ip=10.0.2.99
+		ns3_ip=10.0.3.99
+		ns2_target="tcp:$ns2_ip:8080"
+		ns3_target="tcp:$ns3_ip:8080"
+		nftables_subject="ip daddr $ns2_ip tcp dport 8080"
+		ip_command="ip"
+	;;
+	"ip6")
+		socat_ipproto="-6"
+		ns1_ip=dead:1::99
+		ns2_ip=dead:2::99
+		ns3_ip=dead:3::99
+		ns2_target="tcp:[$ns2_ip]:8080"
+		ns3_target="tcp:[$ns3_ip]:8080"
+		nftables_subject="ip6 daddr $ns2_ip tcp dport 8080"
+		ip_command="ip -6"
+	;;
+	*)
+	echo "FAIL: unsupported protocol"
+	exit 255
+	;;
+	esac
+
+	case $traffic_origin in
+	# to capture the local originated traffic we need to mark the outgoing
+	# traffic so the policy based routing rule redirects it and can be processed
+	# in the prerouting chain.
+	"local")
+		nftables_rules="
+flush ruleset
+table inet filter {
+	chain divert {
+		type filter hook prerouting priority 0; policy accept;
+		$nftables_subject tproxy $ip_proto to :12345 meta mark set 1 accept
+	}
+	chain output {
+		type route hook output priority 0; policy accept;
+		$nftables_subject meta mark set 1 accept
+	}
+}"
+	;;
+	"forward")
+		nftables_rules="
+flush ruleset
+table inet filter {
+	chain divert {
+		type filter hook prerouting priority 0; policy accept;
+		$nftables_subject tproxy $ip_proto to :12345 meta mark set 1 accept
+	}
+}"
+	;;
+	*)
+	echo "FAIL: unsupported parameter for traffic origin"
+	exit 255
+	;;
+	esac
+
+	# shellcheck disable=SC2046 # Intended splitting of ip_command
+	ip netns exec "$nsrouter" $ip_command rule add fwmark 1 table 100
+	ip netns exec "$nsrouter" $ip_command route add local "${ns2_ip}" dev lo table 100
+	echo "$nftables_rules" | ip netns exec "$nsrouter" nft -f /dev/stdin
+
+	timeout "$timeout" ip netns exec "$nsrouter" socat "$socat_ipproto" tcp-listen:12345,fork,ip-transparent SYSTEM:"cat" 2>/dev/null &
+	local tproxy_pid=$!
+
+	timeout "$timeout" ip netns exec "$ns2" socat "$socat_ipproto" tcp-listen:8080,fork SYSTEM:"echo PONG_NS2" 2>/dev/null &
+	local server2_pid=$!
+
+	timeout "$timeout" ip netns exec "$ns3" socat "$socat_ipproto" tcp-listen:8080,fork SYSTEM:"echo PONG_NS3" 2>/dev/null &
+	local server3_pid=$!
+
+	busywait "$BUSYWAIT_TIMEOUT" listener_ready "$nsrouter" 12345 "-t"
+	busywait "$BUSYWAIT_TIMEOUT" listener_ready "$ns2" 8080 "-t"
+	busywait "$BUSYWAIT_TIMEOUT" listener_ready "$ns3" 8080 "-t"
+
+	local result
+	# request from ns1 to ns2 (forwarded traffic)
+	result=$(echo I_M_PROXIED | ip netns exec "$ns1" socat -t 2 -T 2 STDIO "$ns2_target")
+	if [ "$result" == "$expect_ns1_ns2" ] ;then
+		echo "PASS: tproxy test $testname: ns1 got reply \"$result\" connecting to ns2"
+	else
+		echo "ERROR: tproxy test $testname: ns1 got reply \"$result\" connecting to ns2, not \"${expect_ns1_ns2}\" as intended"
+		ret=1
+	fi
+
+	# request from ns1 to ns3(forwarded traffic)
+	result=$(echo I_M_PROXIED | ip netns exec "$ns1" socat -t 2 -T 2 STDIO "$ns3_target")
+	if [ "$result" = "$expect_ns1_ns3" ] ;then
+		echo "PASS: tproxy test $testname: ns1 got reply \"$result\" connecting to ns3"
+	else
+		echo "ERROR: tproxy test $testname: ns1 got reply \"$result\" connecting to ns3, not \"$expect_ns1_ns3\" as intended"
+		ret=1
+	fi
+
+	# request from nsrouter to ns2 (localy originated traffic)
+	result=$(echo I_M_PROXIED | ip netns exec "$nsrouter" socat -t 2 -T 2 STDIO "$ns2_target")
+	if [ "$result" == "$expect_nsrouter_ns2" ] ;then
+		echo "PASS: tproxy test $testname: nsrouter got reply \"$result\" connecting to ns2"
+	else
+		echo "ERROR: tproxy test $testname: nsrouter got reply \"$result\" connecting to ns2, not \"$expect_nsrouter_ns2\" as intended"
+		ret=1
+	fi
+
+	# request from nsrouter to ns3 (localy originated traffic)
+	result=$(echo I_M_PROXIED | ip netns exec "$nsrouter" socat -t 2 -T 2 STDIO "$ns3_target")
+	if [ "$result" = "$expect_nsrouter_ns3" ] ;then
+		echo "PASS: tproxy test $testname: nsrouter got reply \"$result\" connecting to ns3"
+	else
+		echo "ERROR: tproxy test $testname: nsrouter got reply \"$result\" connecting to ns3, not \"$expect_nsrouter_ns3\"  as intended"
+		ret=1
+	fi
+
+	# cleanup
+	kill "$tproxy_pid" "$server2_pid" "$server3_pid" 2>/dev/null
+	# shellcheck disable=SC2046 # Intended splitting of ip_command
+	ip netns exec "$nsrouter" $ip_command rule del fwmark 1 table 100
+	ip netns exec "$nsrouter" $ip_command route flush table 100
+}
+
+
+test_ipv4_tcp_forward()
+{
+	local traffic_origin="forward"
+	local ip_proto="ip"
+	local expect_ns1_ns2="I_M_PROXIED"
+	local expect_ns1_ns3="PONG_NS3"
+	local expect_nsrouter_ns2="PONG_NS2"
+	local expect_nsrouter_ns3="PONG_NS3"
+
+	test_tproxy     "$traffic_origin" \
+			"$ip_proto" \
+			"$expect_ns1_ns2" \
+			"$expect_ns1_ns3" \
+			"$expect_nsrouter_ns2" \
+			"$expect_nsrouter_ns3"
+}
+
+test_ipv4_tcp_local()
+{
+	local traffic_origin="local"
+	local ip_proto="ip"
+	local expect_ns1_ns2="I_M_PROXIED"
+	local expect_ns1_ns3="PONG_NS3"
+	local expect_nsrouter_ns2="I_M_PROXIED"
+	local expect_nsrouter_ns3="PONG_NS3"
+
+	test_tproxy     "$traffic_origin" \
+			"$ip_proto" \
+			"$expect_ns1_ns2" \
+			"$expect_ns1_ns3" \
+			"$expect_nsrouter_ns2" \
+			"$expect_nsrouter_ns3"
+}
+
+test_ipv6_tcp_forward()
+{
+	local traffic_origin="forward"
+	local ip_proto="ip6"
+	local expect_ns1_ns2="I_M_PROXIED"
+	local expect_ns1_ns3="PONG_NS3"
+	local expect_nsrouter_ns2="PONG_NS2"
+	local expect_nsrouter_ns3="PONG_NS3"
+
+	test_tproxy     "$traffic_origin" \
+			"$ip_proto" \
+			"$expect_ns1_ns2" \
+			"$expect_ns1_ns3" \
+			"$expect_nsrouter_ns2" \
+			"$expect_nsrouter_ns3"
+}
+
+test_ipv6_tcp_local()
+{
+	local traffic_origin="local"
+	local ip_proto="ip6"
+	local expect_ns1_ns2="I_M_PROXIED"
+	local expect_ns1_ns3="PONG_NS3"
+	local expect_nsrouter_ns2="I_M_PROXIED"
+	local expect_nsrouter_ns3="PONG_NS3"
+
+	test_tproxy     "$traffic_origin" \
+			"$ip_proto" \
+			"$expect_ns1_ns2" \
+			"$expect_ns1_ns3" \
+			"$expect_nsrouter_ns2" \
+			"$expect_nsrouter_ns3"
+}
+
+if test_ping; then
+	# queue bypass works (rules were skipped, no listener)
+	echo "PASS: ${ns1} can reach ${ns2}"
+else
+	echo "FAIL: ${ns1} cannot reach ${ns2}: $ret" 1>&2
+	exit $ret
+fi
+
+test_ipv4_tcp_forward
+test_ipv4_tcp_local
+test_ipv6_tcp_forward
+test_ipv6_tcp_local
+
+exit $ret
diff --git a/tools/testing/selftests/net/netfilter/nft_tproxy_udp.sh b/tools/testing/selftests/net/netfilter/nft_tproxy_udp.sh
new file mode 100755
index 000000000000..d16de13fe5a7
--- /dev/null
+++ b/tools/testing/selftests/net/netfilter/nft_tproxy_udp.sh
@@ -0,0 +1,262 @@
+#!/bin/bash
+#
+# This tests tproxy on the following scenario:
+#
+#                         +------------+
+# +-------+               |  nsrouter  |                  +-------+
+# |ns1    |.99          .1|            |.1             .99|    ns2|
+# |   eth0|---------------|veth0  veth1|------------------|eth0   |
+# |       |  10.0.1.0/24  |            |   10.0.2.0/24    |       |
+# +-------+  dead:1::/64  |    veth2   |   dead:2::/64    +-------+
+#                         +------------+
+#                                |.1
+#                                |
+#                                |
+#                                |                        +-------+
+#                                |                     .99|    ns3|
+#                                +------------------------|eth0   |
+#                                       10.0.3.0/24       |       |
+#                                       dead:3::/64       +-------+
+#
+# The tproxy implementation acts as an echo server so the client
+# must receive the same message it sent if it has been proxied.
+# If is not proxied the servers return PONG_NS# with the number
+# of the namespace the server is running.
+# shellcheck disable=SC2162,SC2317
+
+source lib.sh
+ret=0
+# UDP is slow
+timeout=15
+
+cleanup()
+{
+	ip netns pids "$ns1" | xargs kill 2>/dev/null
+	ip netns pids "$ns2" | xargs kill 2>/dev/null
+	ip netns pids "$ns3" | xargs kill 2>/dev/null
+	ip netns pids "$nsrouter" | xargs kill 2>/dev/null
+
+	cleanup_all_ns
+}
+
+checktool "nft --version" "test without nft tool"
+checktool "socat -h" "run test without socat"
+
+trap cleanup EXIT
+setup_ns ns1 ns2 ns3 nsrouter
+
+if ! ip link add veth0 netns "$nsrouter" type veth peer name eth0 netns "$ns1" > /dev/null 2>&1; then
+    echo "SKIP: No virtual ethernet pair device support in kernel"
+    exit $ksft_skip
+fi
+ip link add veth1 netns "$nsrouter" type veth peer name eth0 netns "$ns2"
+ip link add veth2 netns "$nsrouter" type veth peer name eth0 netns "$ns3"
+
+ip -net "$nsrouter" link set veth0 up
+ip -net "$nsrouter" addr add 10.0.1.1/24 dev veth0
+ip -net "$nsrouter" addr add dead:1::1/64 dev veth0 nodad
+
+ip -net "$nsrouter" link set veth1 up
+ip -net "$nsrouter" addr add 10.0.2.1/24 dev veth1
+ip -net "$nsrouter" addr add dead:2::1/64 dev veth1 nodad
+
+ip -net "$nsrouter" link set veth2 up
+ip -net "$nsrouter" addr add 10.0.3.1/24 dev veth2
+ip -net "$nsrouter" addr add dead:3::1/64 dev veth2 nodad
+
+ip -net "$ns1" link set eth0 up
+ip -net "$ns2" link set eth0 up
+ip -net "$ns3" link set eth0 up
+
+ip -net "$ns1" addr add 10.0.1.99/24 dev eth0
+ip -net "$ns1" addr add dead:1::99/64 dev eth0 nodad
+ip -net "$ns1" route add default via 10.0.1.1
+ip -net "$ns1" route add default via dead:1::1
+
+ip -net "$ns2" addr add 10.0.2.99/24 dev eth0
+ip -net "$ns2" addr add dead:2::99/64 dev eth0 nodad
+ip -net "$ns2" route add default via 10.0.2.1
+ip -net "$ns2" route add default via dead:2::1
+
+ip -net "$ns3" addr add 10.0.3.99/24 dev eth0
+ip -net "$ns3" addr add dead:3::99/64 dev eth0 nodad
+ip -net "$ns3" route add default via 10.0.3.1
+ip -net "$ns3" route add default via dead:3::1
+
+ip netns exec "$nsrouter" sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
+ip netns exec "$nsrouter" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
+ip netns exec "$nsrouter" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+ip netns exec "$nsrouter" sysctl net.ipv4.conf.veth2.forwarding=1 > /dev/null
+
+test_ping() {
+  if ! ip netns exec "$ns1" ping -c 1 -q 10.0.2.99 > /dev/null; then
+	return 1
+  fi
+
+  if ! ip netns exec "$ns1" ping -c 1 -q dead:2::99 > /dev/null; then
+	return 2
+  fi
+
+  if ! ip netns exec "$ns1" ping -c 1 -q 10.0.3.99 > /dev/null; then
+	return 1
+  fi
+
+  if ! ip netns exec "$ns1" ping -c 1 -q dead:3::99 > /dev/null; then
+	return 2
+  fi
+
+  return 0
+}
+
+test_ping_router() {
+  if ! ip netns exec "$ns1" ping -c 1 -q 10.0.2.1 > /dev/null; then
+	return 3
+  fi
+
+  if ! ip netns exec "$ns1" ping -c 1 -q dead:2::1 > /dev/null; then
+	return 4
+  fi
+
+  return 0
+}
+
+
+listener_ready()
+{
+	local ns="$1"
+	local port="$2"
+	local proto="$3"
+	ss -N "$ns" -ln "$proto" -o "sport = :$port" | grep -q "$port"
+}
+
+test_tproxy_udp_forward()
+{
+	local ip_proto="$1"
+
+	local expect_ns1_ns2="I_M_PROXIED"
+	local expect_ns1_ns3="PONG_NS3"
+	local expect_nsrouter_ns2="PONG_NS2"
+	local expect_nsrouter_ns3="PONG_NS3"
+
+	# derived variables
+	local testname="test_${ip_proto}_udp_forward"
+	local socat_ipproto
+	local ns1_ip
+	local ns2_ip
+	local ns3_ip
+	local ns1_ip_port
+	local ns2_ip_port
+	local ns3_ip_port
+	local ip_command
+
+	# socat 1.8.0 has a bug that requires to specify the IP family to bind (fixed in 1.8.0.1)
+	case $ip_proto in
+	"ip")
+		socat_ipproto="-4"
+		ns1_ip=10.0.1.99
+		ns2_ip=10.0.2.99
+		ns3_ip=10.0.3.99
+		ns1_ip_port="$ns1_ip:18888"
+		ns2_ip_port="$ns2_ip:8080"
+		ns3_ip_port="$ns3_ip:8080"
+		ip_command="ip"
+	;;
+	"ip6")
+		socat_ipproto="-6"
+		ns1_ip=dead:1::99
+		ns2_ip=dead:2::99
+		ns3_ip=dead:3::99
+		ns1_ip_port="[$ns1_ip]:18888"
+		ns2_ip_port="[$ns2_ip]:8080"
+		ns3_ip_port="[$ns3_ip]:8080"
+		ip_command="ip -6"
+	;;
+	*)
+	echo "FAIL: unsupported protocol"
+	exit 255
+	;;
+	esac
+
+	# shellcheck disable=SC2046 # Intended splitting of ip_command
+	ip netns exec "$nsrouter" $ip_command rule add fwmark 1 table 100
+	ip netns exec "$nsrouter" $ip_command route add local "$ns2_ip" dev lo table 100
+	ip netns exec "$nsrouter" nft -f /dev/stdin <<EOF
+flush ruleset
+table inet filter {
+	chain divert {
+		type filter hook prerouting priority 0; policy accept;
+		$ip_proto daddr $ns2_ip udp dport 8080 tproxy $ip_proto to :12345 meta mark set 1 accept
+	}
+}
+EOF
+
+	timeout "$timeout" ip netns exec "$nsrouter" socat -u "$socat_ipproto" udp-listen:12345,fork,ip-transparent,reuseport udp:"$ns1_ip_port",ip-transparent,reuseport,bind="$ns2_ip_port" 2>/dev/null &
+	local tproxy_pid=$!
+
+	timeout "$timeout" ip netns exec "$ns2" socat "$socat_ipproto" udp-listen:8080,fork SYSTEM:"echo PONG_NS2" 2>/dev/null &
+	local server2_pid=$!
+
+	timeout "$timeout" ip netns exec "$ns3" socat "$socat_ipproto" udp-listen:8080,fork SYSTEM:"echo PONG_NS3" 2>/dev/null &
+	local server3_pid=$!
+
+	busywait "$BUSYWAIT_TIMEOUT" listener_ready "$nsrouter" 12345 "-u"
+	busywait "$BUSYWAIT_TIMEOUT" listener_ready "$ns2" 8080 "-u"
+	busywait "$BUSYWAIT_TIMEOUT" listener_ready "$ns3" 8080 "-u"
+
+	local result
+	# request from ns1 to ns2 (forwarded traffic)
+	result=$(echo I_M_PROXIED | ip netns exec "$ns1" socat -t 2 -T 2 STDIO udp:"$ns2_ip_port",sourceport=18888)
+	if [ "$result" == "$expect_ns1_ns2" ] ;then
+		echo "PASS: tproxy test $testname: ns1 got reply \"$result\" connecting to ns2"
+	else
+		echo "ERROR: tproxy test $testname: ns1 got reply \"$result\" connecting to ns2, not \"${expect_ns1_ns2}\" as intended"
+		ret=1
+	fi
+
+	# request from ns1 to ns3 (forwarded traffic)
+	result=$(echo I_M_PROXIED | ip netns exec "$ns1" socat -t 2 -T 2 STDIO udp:"$ns3_ip_port")
+	if [ "$result" = "$expect_ns1_ns3" ] ;then
+		echo "PASS: tproxy test $testname: ns1 got reply \"$result\" connecting to ns3"
+	else
+		echo "ERROR: tproxy test $testname: ns1 got reply \"$result\" connecting to ns3, not \"$expect_ns1_ns3\" as intended"
+		ret=1
+	fi
+
+	# request from nsrouter to ns2 (localy originated traffic)
+	result=$(echo I_M_PROXIED | ip netns exec "$nsrouter" socat -t 2 -T 2 STDIO udp:"$ns2_ip_port")
+	if [ "$result" == "$expect_nsrouter_ns2" ] ;then
+		echo "PASS: tproxy test $testname: nsrouter got reply \"$result\" connecting to ns2"
+	else
+		echo "ERROR: tproxy test $testname: nsrouter got reply \"$result\" connecting to ns2, not \"$expect_nsrouter_ns2\" as intended"
+		ret=1
+	fi
+
+	# request from nsrouter to ns3 (localy originated traffic)
+	result=$(echo I_M_PROXIED | ip netns exec "$nsrouter" socat -t 2 -T 2 STDIO udp:"$ns3_ip_port")
+	if [ "$result" = "$expect_nsrouter_ns3" ] ;then
+		echo "PASS: tproxy test $testname: nsrouter got reply \"$result\" connecting to ns3"
+	else
+		echo "ERROR: tproxy test $testname: nsrouter got reply \"$result\" connecting to ns3, not \"$expect_nsrouter_ns3\"  as intended"
+		ret=1
+	fi
+
+	# cleanup
+	kill "$tproxy_pid" "$server2_pid" "$server3_pid" 2>/dev/null
+	# shellcheck disable=SC2046 # Intended splitting of ip_command
+	ip netns exec "$nsrouter" $ip_command rule del fwmark 1 table 100
+	ip netns exec "$nsrouter" $ip_command route flush table 100
+}
+
+
+if test_ping; then
+	# queue bypass works (rules were skipped, no listener)
+	echo "PASS: ${ns1} can reach ${ns2}"
+else
+	echo "FAIL: ${ns1} cannot reach ${ns2}: $ret" 1>&2
+	exit $ret
+fi
+
+test_tproxy_udp_forward "ip"
+test_tproxy_udp_forward "ip6"
+
+exit $ret
diff --git a/tools/testing/selftests/net/packetdrill/ksft_runner.sh b/tools/testing/selftests/net/packetdrill/ksft_runner.sh
index 7478c0c0c9aa..4071c133f29e 100755
--- a/tools/testing/selftests/net/packetdrill/ksft_runner.sh
+++ b/tools/testing/selftests/net/packetdrill/ksft_runner.sh
@@ -30,12 +30,17 @@ if [ -z "$(which packetdrill)" ]; then
 	exit "$KSFT_SKIP"
 fi
 
+declare -a optargs
+if [[ -n "${KSFT_MACHINE_SLOW}" ]]; then
+	optargs+=('--tolerance_usecs=14000')
+fi
+
 ktap_print_header
 ktap_set_plan 2
 
-unshare -n packetdrill ${ipv4_args[@]} $(basename $script) > /dev/null \
+unshare -n packetdrill ${ipv4_args[@]} ${optargs[@]} $(basename $script) > /dev/null \
 	&& ktap_test_pass "ipv4" || ktap_test_fail "ipv4"
-unshare -n packetdrill ${ipv6_args[@]} $(basename $script) > /dev/null \
+unshare -n packetdrill ${ipv6_args[@]} ${optargs[@]} $(basename $script) > /dev/null \
 	&& ktap_test_pass "ipv6" || ktap_test_fail "ipv6"
 
 ktap_finished