Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Add VF IPSEC offload support in ixgbe, from Shannon Nelson.

 2) Add zero-copy AF_XDP support to i40e, from Björn Töpel.

 3) All in-tree drivers are converted to {g,s}et_link_ksettings() so we
    can get rid of the {g,s}et_settings ethtool callbacks, from Michal
    Kubecek.

 4) Add software timestamping to veth driver, from Michael Walle.

 5) More work to make packet classifiers and actions lockless, from Vlad
    Buslov.

 6) Support sticky FDB entries in bridge, from Nikolay Aleksandrov.

 7) Add ipv6 version of IP_MULTICAST_ALL sockopt, from Andre Naujoks.

 8) Support batching of XDP buffers in vhost_net, from Jason Wang.

 9) Add flow dissector BPF hook, from Petar Penkov.

10) i40e vf --> generic iavf conversion, from Jesse Brandeburg.

11) Add NLA_REJECT netlink attribute policy type, to signal when users
    provide attributes in situations which don't make sense. From
    Johannes Berg.

12) Switch TCP and fair-queue scheduler over to earliest departure time
    model. From Eric Dumazet.

13) Improve guest receive performance by doing rx busy polling in tx
    path of vhost networking driver, from Tonghao Zhang.

14) Add per-cgroup local storage to bpf

15) Add reference tracking to BPF, from Joe Stringer. The verifier can
    now make sure that references taken to objects are properly released
    by the program.

16) Support in-place encryption in TLS, from Vakul Garg.

17) Add new taprio packet scheduler, from Vinicius Costa Gomes.

18) Lots of selftests additions, too numerous to mention one by one here
    but all of which are very much appreciated.

19) Support offloading of eBPF programs containing BPF to BPF calls in
    nfp driver, frm Quentin Monnet.

20) Move dpaa2_ptp driver out of staging, from Yangbo Lu.

21) Lots of u32 classifier cleanups and simplifications, from Al Viro.

22) Add new strict versions of netlink message parsers, and enable them
    for some situations. From David Ahern.

23) Evict neighbour entries on carrier down, also from David Ahern.

24) Support BPF sk_msg verdict programs with kTLS, from Daniel Borkmann
    and John Fastabend.

25) Add support for filtering route dumps, from David Ahern.

26) New igc Intel driver for 2.5G parts, from Sasha Neftin et al.

27) Allow vxlan enslavement to bridges in mlxsw driver, from Ido
    Schimmel.

28) Add queue and stack map types to eBPF, from Mauricio Vasquez B.

29) Add back byte-queue-limit support to r8169, with all the bug fixes
    in other areas of the driver it works now! From Florian Westphal and
    Heiner Kallweit.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2147 commits)
  tcp: add tcp_reset_xmit_timer() helper
  qed: Fix static checker warning
  Revert "be2net: remove desc field from be_eq_obj"
  Revert "net: simplify sock_poll_wait"
  net: socionext: Reset tx queue in ndo_stop
  net: socionext: Add dummy PHY register read in phy_write()
  net: socionext: Stop PHY before resetting netsec
  net: stmmac: Set OWN bit for jumbo frames
  arm64: dts: stratix10: Support Ethernet Jumbo frame
  tls: Add maintainers
  net: ethernet: ti: cpsw: unsync mcast entries while switch promisc mode
  octeontx2-af: Support for NIXLF's UCAST/PROMISC/ALLMULTI modes
  octeontx2-af: Support for setting MAC address
  octeontx2-af: Support for changing RSS algorithm
  octeontx2-af: NIX Rx flowkey configuration for RSS
  octeontx2-af: Install ucast and bcast pkt forwarding rules
  octeontx2-af: Add LMAC channel info to NIXLF_ALLOC response
  octeontx2-af: NPC MCAM and LDATA extract minimal configuration
  octeontx2-af: Enable packet length and csum validation
  octeontx2-af: Support for VTAG strip and capture
  ...

9 files changed, 1011 insertions, 73 deletions

diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 78b24cf76f40..8cf22b3c2563 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -14,3 +14,4 @@ udpgso_bench_rx
 udpgso_bench_tx
 tcp_inq
 tls
+ip_defrag
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 919aa2ac00af..256d82d5fa87 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -5,13 +5,13 @@ CFLAGS =  -Wall -Wl,--no-as-needed -O2 -g
 CFLAGS += -I../../../../usr/include/
 
 TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
-TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh
+TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh
 TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
 TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd
-TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx
+TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx ip_defrag
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
 TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
 
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 0f45633bd634..802b4af18729 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -9,11 +9,11 @@ ret=0
 ksft_skip=4
 
 # all tests in this script. Can be overridden with -t option
-TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric"
+TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics"
 VERBOSE=0
 PAUSE_ON_FAIL=no
 PAUSE=no
-IP="ip -netns testns"
+IP="ip -netns ns1"
 
 log_test()
 {
@@ -47,8 +47,10 @@ log_test()
 setup()
 {
 	set -e
-	ip netns add testns
+	ip netns add ns1
 	$IP link set dev lo up
+	ip netns exec ns1 sysctl -qw net.ipv4.ip_forward=1
+	ip netns exec ns1 sysctl -qw net.ipv6.conf.all.forwarding=1
 
 	$IP link add dummy0 type dummy
 	$IP link set dev dummy0 up
@@ -61,7 +63,8 @@ setup()
 cleanup()
 {
 	$IP link del dev dummy0 &> /dev/null
-	ip netns del testns
+	ip netns del ns1
+	ip netns del ns2 &> /dev/null
 }
 
 get_linklocal()
@@ -639,11 +642,14 @@ add_initial_route6()
 
 check_route6()
 {
-	local pfx="2001:db8:104::/64"
+	local pfx
 	local expected="$1"
 	local out
 	local rc=0
 
+	set -- $expected
+	pfx=$1
+
 	out=$($IP -6 ro ls match ${pfx} | sed -e 's/ pref medium//')
 	[ "${out}" = "${expected}" ] && return 0
 
@@ -690,28 +696,33 @@ route_setup()
 	[ "${VERBOSE}" = "1" ] && set -x
 	set -e
 
-	$IP li add red up type vrf table 101
+	ip netns add ns2
+	ip -netns ns2 link set dev lo up
+	ip netns exec ns2 sysctl -qw net.ipv4.ip_forward=1
+	ip netns exec ns2 sysctl -qw net.ipv6.conf.all.forwarding=1
+
 	$IP li add veth1 type veth peer name veth2
 	$IP li add veth3 type veth peer name veth4
 
 	$IP li set veth1 up
 	$IP li set veth3 up
-	$IP li set veth2 vrf red up
-	$IP li set veth4 vrf red up
-	$IP li add dummy1 type dummy
-	$IP li set dummy1 vrf red up
-
-	$IP -6 addr add 2001:db8:101::1/64 dev veth1
-	$IP -6 addr add 2001:db8:101::2/64 dev veth2
-	$IP -6 addr add 2001:db8:103::1/64 dev veth3
-	$IP -6 addr add 2001:db8:103::2/64 dev veth4
-	$IP -6 addr add 2001:db8:104::1/64 dev dummy1
+	$IP li set veth2 netns ns2 up
+	$IP li set veth4 netns ns2 up
+	ip -netns ns2 li add dummy1 type dummy
+	ip -netns ns2 li set dummy1 up
 
+	$IP -6 addr add 2001:db8:101::1/64 dev veth1 nodad
+	$IP -6 addr add 2001:db8:103::1/64 dev veth3 nodad
 	$IP addr add 172.16.101.1/24 dev veth1
-	$IP addr add 172.16.101.2/24 dev veth2
 	$IP addr add 172.16.103.1/24 dev veth3
-	$IP addr add 172.16.103.2/24 dev veth4
-	$IP addr add 172.16.104.1/24 dev dummy1
+
+	ip -netns ns2 -6 addr add 2001:db8:101::2/64 dev veth2 nodad
+	ip -netns ns2 -6 addr add 2001:db8:103::2/64 dev veth4 nodad
+	ip -netns ns2 -6 addr add 2001:db8:104::1/64 dev dummy1 nodad
+
+	ip -netns ns2 addr add 172.16.101.2/24 dev veth2
+	ip -netns ns2 addr add 172.16.103.2/24 dev veth4
+	ip -netns ns2 addr add 172.16.104.1/24 dev dummy1
 
 	set +ex
 }
@@ -944,7 +955,7 @@ ipv6_addr_metric_test()
 	log_test $rc 0 "Modify metric of address"
 
 	# verify prefix route removed on down
-	run_cmd "ip netns exec testns sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1"
+	run_cmd "ip netns exec ns1 sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1"
 	run_cmd "$IP li set dev dummy2 down"
 	rc=$?
 	if [ $rc -eq 0 ]; then
@@ -967,6 +978,77 @@ ipv6_addr_metric_test()
 	cleanup
 }
 
+ipv6_route_metrics_test()
+{
+	local rc
+
+	echo
+	echo "IPv6 routes with metrics"
+
+	route_setup
+
+	#
+	# single path with metrics
+	#
+	run_cmd "$IP -6 ro add 2001:db8:111::/64 via 2001:db8:101::2 mtu 1400"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route6  "2001:db8:111::/64 via 2001:db8:101::2 dev veth1 metric 1024 mtu 1400"
+		rc=$?
+	fi
+	log_test $rc 0 "Single path route with mtu metric"
+
+
+	#
+	# multipath via separate routes with metrics
+	#
+	run_cmd "$IP -6 ro add 2001:db8:112::/64 via 2001:db8:101::2 mtu 1400"
+	run_cmd "$IP -6 ro append 2001:db8:112::/64 via 2001:db8:103::2"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route6 "2001:db8:112::/64 metric 1024 mtu 1400 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
+		rc=$?
+	fi
+	log_test $rc 0 "Multipath route via 2 single routes with mtu metric on first"
+
+	# second route is coalesced to first to make a multipath route.
+	# MTU of the second path is hidden from display!
+	run_cmd "$IP -6 ro add 2001:db8:113::/64 via 2001:db8:101::2"
+	run_cmd "$IP -6 ro append 2001:db8:113::/64 via 2001:db8:103::2 mtu 1400"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route6 "2001:db8:113::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
+		rc=$?
+	fi
+	log_test $rc 0 "Multipath route via 2 single routes with mtu metric on 2nd"
+
+	run_cmd "$IP -6 ro del 2001:db8:113::/64 via 2001:db8:101::2"
+	if [ $? -eq 0 ]; then
+		check_route6 "2001:db8:113::/64 via 2001:db8:103::2 dev veth3 metric 1024 mtu 1400"
+		log_test $? 0 "    MTU of second leg"
+	fi
+
+	#
+	# multipath with metrics
+	#
+	run_cmd "$IP -6 ro add 2001:db8:115::/64 mtu 1400 nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route6  "2001:db8:115::/64 metric 1024 mtu 1400 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
+		rc=$?
+	fi
+	log_test $rc 0 "Multipath route with mtu metric"
+
+	$IP -6 ro add 2001:db8:104::/64 via 2001:db8:101::2 mtu 1300
+	run_cmd "ip netns exec ns1 ping6 -w1 -c1 -s 1500 2001:db8:104::1"
+	log_test $? 0 "Using route with mtu metric"
+
+	run_cmd "$IP -6 ro add 2001:db8:114::/64 via  2001:db8:101::2  congctl lock foo"
+	log_test $? 2 "Invalid metric (fails metric_convert)"
+
+	route_cleanup
+}
+
 # add route for a prefix, flushing any existing routes first
 # expected to be the first step of a test
 add_route()
@@ -1005,11 +1087,15 @@ add_initial_route()
 
 check_route()
 {
-	local pfx="172.16.104.0/24"
+	local pfx
 	local expected="$1"
 	local out
 	local rc=0
 
+	set -- $expected
+	pfx=$1
+	[ "${pfx}" = "unreachable" ] && pfx=$2
+
 	out=$($IP ro ls match ${pfx})
 	[ "${out}" = "${expected}" ] && return 0
 
@@ -1319,6 +1405,43 @@ ipv4_addr_metric_test()
 	cleanup
 }
 
+ipv4_route_metrics_test()
+{
+	local rc
+
+	echo
+	echo "IPv4 route add / append tests"
+
+	route_setup
+
+	run_cmd "$IP ro add 172.16.111.0/24 via 172.16.101.2 mtu 1400"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route "172.16.111.0/24 via 172.16.101.2 dev veth1 mtu 1400"
+		rc=$?
+	fi
+	log_test $rc 0 "Single path route with mtu metric"
+
+
+	run_cmd "$IP ro add 172.16.112.0/24 mtu 1400 nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route "172.16.112.0/24 mtu 1400 nexthop via 172.16.101.2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1"
+		rc=$?
+	fi
+	log_test $rc 0 "Multipath route with mtu metric"
+
+	$IP ro add 172.16.104.0/24 via 172.16.101.2 mtu 1300
+	run_cmd "ip netns exec ns1 ping -w1 -c1 -s 1500 172.16.104.1"
+	log_test $? 0 "Using route with mtu metric"
+
+	run_cmd "$IP ro add 172.16.111.0/24 via 172.16.101.2 congctl lock foo"
+	log_test $? 2 "Invalid metric (fails metric_convert)"
+
+	route_cleanup
+}
+
+
 ################################################################################
 # usage
 
@@ -1385,6 +1508,8 @@ do
 	ipv4_route_test|ipv4_rt)	ipv4_route_test;;
 	ipv6_addr_metric)		ipv6_addr_metric_test;;
 	ipv4_addr_metric)		ipv4_addr_metric_test;;
+	ipv6_route_metrics)		ipv6_route_metrics_test;;
+	ipv4_route_metrics)		ipv4_route_metrics_test;;
 
 	help) echo "Test names: $TESTS"; exit 0;;
 	esac
diff --git a/tools/testing/selftests/net/forwarding/bridge_sticky_fdb.sh b/tools/testing/selftests/net/forwarding/bridge_sticky_fdb.sh
new file mode 100755
index 000000000000..1f8ef0eff862
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/bridge_sticky_fdb.sh
@@ -0,0 +1,69 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="sticky"
+NUM_NETIFS=4
+TEST_MAC=de:ad:be:ef:13:37
+source lib.sh
+
+switch_create()
+{
+	ip link add dev br0 type bridge
+
+	ip link set dev $swp1 master br0
+	ip link set dev $swp2 master br0
+
+	ip link set dev br0 up
+	ip link set dev $h1 up
+	ip link set dev $swp1 up
+	ip link set dev $h2 up
+	ip link set dev $swp2 up
+}
+
+switch_destroy()
+{
+	ip link set dev $swp2 down
+	ip link set dev $h2 down
+	ip link set dev $swp1 down
+	ip link set dev $h1 down
+
+	ip link del dev br0
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+	h2=${NETIFS[p3]}
+	swp2=${NETIFS[p4]}
+
+	switch_create
+}
+
+cleanup()
+{
+	pre_cleanup
+	switch_destroy
+}
+
+sticky()
+{
+	bridge fdb add $TEST_MAC dev $swp1 master static sticky
+	check_err $? "Could not add fdb entry"
+	bridge fdb del $TEST_MAC dev $swp1 vlan 1 master static sticky
+	$MZ $h2 -c 1 -a $TEST_MAC -t arp "request" -q
+	bridge -j fdb show br br0 brport $swp1\
+		| jq -e ".[] | select(.mac == \"$TEST_MAC\")" &> /dev/null
+	check_err $? "Did not find FDB record when should"
+
+	log_test "Sticky fdb entry"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index ca53b539aa2d..85d253546684 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -251,7 +251,7 @@ lldpad_app_wait_set()
 {
 	local dev=$1; shift
 
-	while lldptool -t -i $dev -V APP -c app | grep -q pending; do
+	while lldptool -t -i $dev -V APP -c app | grep -Eq "pending|unknown"; do
 		echo "$dev: waiting for lldpad to push pending APP updates"
 		sleep 5
 	done
@@ -494,6 +494,14 @@ tc_rule_stats_get()
 	    | jq '.[1].options.actions[].stats.packets'
 }
 
+ethtool_stats_get()
+{
+	local dev=$1; shift
+	local stat=$1; shift
+
+	ethtool -S $dev | grep "^ *$stat:" | head -n 1 | cut -d: -f2
+}
+
 mac_get()
 {
 	local if_name=$1
@@ -541,6 +549,23 @@ forwarding_restore()
 	sysctl_restore net.ipv4.conf.all.forwarding
 }
 
+declare -A MTU_ORIG
+mtu_set()
+{
+	local dev=$1; shift
+	local mtu=$1; shift
+
+	MTU_ORIG["$dev"]=$(ip -j link show dev $dev | jq -e '.[].mtu')
+	ip link set dev $dev mtu $mtu
+}
+
+mtu_restore()
+{
+	local dev=$1; shift
+
+	ip link set dev $dev mtu ${MTU_ORIG["$dev"]}
+}
+
 tc_offload_check()
 {
 	local num_netifs=${1:-$NUM_NETIFS}
diff --git a/tools/testing/selftests/net/ip_defrag.c b/tools/testing/selftests/net/ip_defrag.c
new file mode 100644
index 000000000000..61ae2782388e
--- /dev/null
+++ b/tools/testing/selftests/net/ip_defrag.c
@@ -0,0 +1,393 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <linux/in.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/udp.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+#include <unistd.h>
+
+static bool		cfg_do_ipv4;
+static bool		cfg_do_ipv6;
+static bool		cfg_verbose;
+static bool		cfg_overlap;
+static unsigned short	cfg_port = 9000;
+
+const struct in_addr addr4 = { .s_addr = __constant_htonl(INADDR_LOOPBACK + 2) };
+const struct in6_addr addr6 = IN6ADDR_LOOPBACK_INIT;
+
+#define IP4_HLEN	(sizeof(struct iphdr))
+#define IP6_HLEN	(sizeof(struct ip6_hdr))
+#define UDP_HLEN	(sizeof(struct udphdr))
+
+/* IPv6 fragment header lenth. */
+#define FRAG_HLEN	8
+
+static int payload_len;
+static int max_frag_len;
+
+#define MSG_LEN_MAX	60000	/* Max UDP payload length. */
+
+#define IP4_MF		(1u << 13)  /* IPv4 MF flag. */
+#define IP6_MF		(1)  /* IPv6 MF flag. */
+
+#define CSUM_MANGLED_0 (0xffff)
+
+static uint8_t udp_payload[MSG_LEN_MAX];
+static uint8_t ip_frame[IP_MAXPACKET];
+static uint32_t ip_id = 0xabcd;
+static int msg_counter;
+static int frag_counter;
+static unsigned int seed;
+
+/* Receive a UDP packet. Validate it matches udp_payload. */
+static void recv_validate_udp(int fd_udp)
+{
+	ssize_t ret;
+	static uint8_t recv_buff[MSG_LEN_MAX];
+
+	ret = recv(fd_udp, recv_buff, payload_len, 0);
+	msg_counter++;
+
+	if (cfg_overlap) {
+		if (ret != -1)
+			error(1, 0, "recv: expected timeout; got %d",
+				(int)ret);
+		if (errno != ETIMEDOUT && errno != EAGAIN)
+			error(1, errno, "recv: expected timeout: %d",
+				 errno);
+		return;  /* OK */
+	}
+
+	if (ret == -1)
+		error(1, errno, "recv: payload_len = %d max_frag_len = %d",
+			payload_len, max_frag_len);
+	if (ret != payload_len)
+		error(1, 0, "recv: wrong size: %d vs %d", (int)ret, payload_len);
+	if (memcmp(udp_payload, recv_buff, payload_len))
+		error(1, 0, "recv: wrong data");
+}
+
+static uint32_t raw_checksum(uint8_t *buf, int len, uint32_t sum)
+{
+	int i;
+
+	for (i = 0; i < (len & ~1U); i += 2) {
+		sum += (u_int16_t)ntohs(*((u_int16_t *)(buf + i)));
+		if (sum > 0xffff)
+			sum -= 0xffff;
+	}
+
+	if (i < len) {
+		sum += buf[i] << 8;
+		if (sum > 0xffff)
+			sum -= 0xffff;
+	}
+
+	return sum;
+}
+
+static uint16_t udp_checksum(struct ip *iphdr, struct udphdr *udphdr)
+{
+	uint32_t sum = 0;
+	uint16_t res;
+
+	sum = raw_checksum((uint8_t *)&iphdr->ip_src, 2 * sizeof(iphdr->ip_src),
+				IPPROTO_UDP + (uint32_t)(UDP_HLEN + payload_len));
+	sum = raw_checksum((uint8_t *)udphdr, UDP_HLEN, sum);
+	sum = raw_checksum((uint8_t *)udp_payload, payload_len, sum);
+	res = 0xffff & ~sum;
+	if (res)
+		return htons(res);
+	else
+		return CSUM_MANGLED_0;
+}
+
+static uint16_t udp6_checksum(struct ip6_hdr *iphdr, struct udphdr *udphdr)
+{
+	uint32_t sum = 0;
+	uint16_t res;
+
+	sum = raw_checksum((uint8_t *)&iphdr->ip6_src, 2 * sizeof(iphdr->ip6_src),
+				IPPROTO_UDP);
+	sum = raw_checksum((uint8_t *)&udphdr->len, sizeof(udphdr->len), sum);
+	sum = raw_checksum((uint8_t *)udphdr, UDP_HLEN, sum);
+	sum = raw_checksum((uint8_t *)udp_payload, payload_len, sum);
+	res = 0xffff & ~sum;
+	if (res)
+		return htons(res);
+	else
+		return CSUM_MANGLED_0;
+}
+
+static void send_fragment(int fd_raw, struct sockaddr *addr, socklen_t alen,
+				int offset, bool ipv6)
+{
+	int frag_len;
+	int res;
+	int payload_offset = offset > 0 ? offset - UDP_HLEN : 0;
+	uint8_t *frag_start = ipv6 ? ip_frame + IP6_HLEN + FRAG_HLEN :
+					ip_frame + IP4_HLEN;
+
+	if (offset == 0) {
+		struct udphdr udphdr;
+		udphdr.source = htons(cfg_port + 1);
+		udphdr.dest = htons(cfg_port);
+		udphdr.len = htons(UDP_HLEN + payload_len);
+		udphdr.check = 0;
+		if (ipv6)
+			udphdr.check = udp6_checksum((struct ip6_hdr *)ip_frame, &udphdr);
+		else
+			udphdr.check = udp_checksum((struct ip *)ip_frame, &udphdr);
+		memcpy(frag_start, &udphdr, UDP_HLEN);
+	}
+
+	if (ipv6) {
+		struct ip6_hdr *ip6hdr = (struct ip6_hdr *)ip_frame;
+		struct ip6_frag *fraghdr = (struct ip6_frag *)(ip_frame + IP6_HLEN);
+		if (payload_len - payload_offset <= max_frag_len && offset > 0) {
+			/* This is the last fragment. */
+			frag_len = FRAG_HLEN + payload_len - payload_offset;
+			fraghdr->ip6f_offlg = htons(offset);
+		} else {
+			frag_len = FRAG_HLEN + max_frag_len;
+			fraghdr->ip6f_offlg = htons(offset | IP6_MF);
+		}
+		ip6hdr->ip6_plen = htons(frag_len);
+		if (offset == 0)
+			memcpy(frag_start + UDP_HLEN, udp_payload,
+				frag_len - FRAG_HLEN - UDP_HLEN);
+		else
+			memcpy(frag_start, udp_payload + payload_offset,
+				frag_len - FRAG_HLEN);
+		frag_len += IP6_HLEN;
+	} else {
+		struct ip *iphdr = (struct ip *)ip_frame;
+		if (payload_len - payload_offset <= max_frag_len && offset > 0) {
+			/* This is the last fragment. */
+			frag_len = IP4_HLEN + payload_len - payload_offset;
+			iphdr->ip_off = htons(offset / 8);
+		} else {
+			frag_len = IP4_HLEN + max_frag_len;
+			iphdr->ip_off = htons(offset / 8 | IP4_MF);
+		}
+		iphdr->ip_len = htons(frag_len);
+		if (offset == 0)
+			memcpy(frag_start + UDP_HLEN, udp_payload,
+				frag_len - IP4_HLEN - UDP_HLEN);
+		else
+			memcpy(frag_start, udp_payload + payload_offset,
+				frag_len - IP4_HLEN);
+	}
+
+	res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen);
+	if (res < 0)
+		error(1, errno, "send_fragment");
+	if (res != frag_len)
+		error(1, 0, "send_fragment: %d vs %d", res, frag_len);
+
+	frag_counter++;
+}
+
+static void send_udp_frags(int fd_raw, struct sockaddr *addr,
+				socklen_t alen, bool ipv6)
+{
+	struct ip *iphdr = (struct ip *)ip_frame;
+	struct ip6_hdr *ip6hdr = (struct ip6_hdr *)ip_frame;
+	int res;
+	int offset;
+	int frag_len;
+
+	/* Send the UDP datagram using raw IP fragments: the 0th fragment
+	 * has the UDP header; other fragments are pieces of udp_payload
+	 * split in chunks of frag_len size.
+	 *
+	 * Odd fragments (1st, 3rd, 5th, etc.) are sent out first, then
+	 * even fragments (0th, 2nd, etc.) are sent out.
+	 */
+	if (ipv6) {
+		struct ip6_frag *fraghdr = (struct ip6_frag *)(ip_frame + IP6_HLEN);
+		((struct sockaddr_in6 *)addr)->sin6_port = 0;
+		memset(ip6hdr, 0, sizeof(*ip6hdr));
+		ip6hdr->ip6_flow = htonl(6<<28);  /* Version. */
+		ip6hdr->ip6_nxt = IPPROTO_FRAGMENT;
+		ip6hdr->ip6_hops = 255;
+		ip6hdr->ip6_src = addr6;
+		ip6hdr->ip6_dst = addr6;
+		fraghdr->ip6f_nxt = IPPROTO_UDP;
+		fraghdr->ip6f_reserved = 0;
+		fraghdr->ip6f_ident = htonl(ip_id++);
+	} else {
+		memset(iphdr, 0, sizeof(*iphdr));
+		iphdr->ip_hl = 5;
+		iphdr->ip_v = 4;
+		iphdr->ip_tos = 0;
+		iphdr->ip_id = htons(ip_id++);
+		iphdr->ip_ttl = 0x40;
+		iphdr->ip_p = IPPROTO_UDP;
+		iphdr->ip_src.s_addr = htonl(INADDR_LOOPBACK);
+		iphdr->ip_dst = addr4;
+		iphdr->ip_sum = 0;
+	}
+
+	/* Odd fragments. */
+	offset = max_frag_len;
+	while (offset < (UDP_HLEN + payload_len)) {
+		send_fragment(fd_raw, addr, alen, offset, ipv6);
+		offset += 2 * max_frag_len;
+	}
+
+	if (cfg_overlap) {
+		/* Send an extra random fragment. */
+		offset = rand() % (UDP_HLEN + payload_len - 1);
+		/* sendto() returns EINVAL if offset + frag_len is too small. */
+		if (ipv6) {
+			struct ip6_frag *fraghdr = (struct ip6_frag *)(ip_frame + IP6_HLEN);
+			frag_len = max_frag_len + rand() % 256;
+			/* In IPv6 if !!(frag_len % 8), the fragment is dropped. */
+			frag_len &= ~0x7;
+			fraghdr->ip6f_offlg = htons(offset / 8 | IP6_MF);
+			ip6hdr->ip6_plen = htons(frag_len);
+			frag_len += IP6_HLEN;
+		} else {
+			frag_len = IP4_HLEN + UDP_HLEN + rand() % 256;
+			iphdr->ip_off = htons(offset / 8 | IP4_MF);
+			iphdr->ip_len = htons(frag_len);
+		}
+		res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen);
+		if (res < 0)
+			error(1, errno, "sendto overlap");
+		if (res != frag_len)
+			error(1, 0, "sendto overlap: %d vs %d", (int)res, frag_len);
+		frag_counter++;
+	}
+
+	/* Event fragments. */
+	offset = 0;
+	while (offset < (UDP_HLEN + payload_len)) {
+		send_fragment(fd_raw, addr, alen, offset, ipv6);
+		offset += 2 * max_frag_len;
+	}
+}
+
+static void run_test(struct sockaddr *addr, socklen_t alen, bool ipv6)
+{
+	int fd_tx_raw, fd_rx_udp;
+	struct timeval tv = { .tv_sec = 0, .tv_usec = 10 * 1000 };
+	int idx;
+	int min_frag_len = ipv6 ? 1280 : 8;
+
+	/* Initialize the payload. */
+	for (idx = 0; idx < MSG_LEN_MAX; ++idx)
+		udp_payload[idx] = idx % 256;
+
+	/* Open sockets. */
+	fd_tx_raw = socket(addr->sa_family, SOCK_RAW, IPPROTO_RAW);
+	if (fd_tx_raw == -1)
+		error(1, errno, "socket tx_raw");
+
+	fd_rx_udp = socket(addr->sa_family, SOCK_DGRAM, 0);
+	if (fd_rx_udp == -1)
+		error(1, errno, "socket rx_udp");
+	if (bind(fd_rx_udp, addr, alen))
+		error(1, errno, "bind");
+	/* Fail fast. */
+	if (setsockopt(fd_rx_udp, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)))
+		error(1, errno, "setsockopt rcv timeout");
+
+	for (payload_len = min_frag_len; payload_len < MSG_LEN_MAX;
+			payload_len += (rand() % 4096)) {
+		if (cfg_verbose)
+			printf("payload_len: %d\n", payload_len);
+		max_frag_len = min_frag_len;
+		do {
+			send_udp_frags(fd_tx_raw, addr, alen, ipv6);
+			recv_validate_udp(fd_rx_udp);
+			max_frag_len += 8 * (rand() % 8);
+		} while (max_frag_len < (1500 - FRAG_HLEN) && max_frag_len <= payload_len);
+	}
+
+	/* Cleanup. */
+	if (close(fd_tx_raw))
+		error(1, errno, "close tx_raw");
+	if (close(fd_rx_udp))
+		error(1, errno, "close rx_udp");
+
+	if (cfg_verbose)
+		printf("processed %d messages, %d fragments\n",
+			msg_counter, frag_counter);
+
+	fprintf(stderr, "PASS\n");
+}
+
+
+static void run_test_v4(void)
+{
+	struct sockaddr_in addr = {0};
+
+	addr.sin_family = AF_INET;
+	addr.sin_port = htons(cfg_port);
+	addr.sin_addr = addr4;
+
+	run_test((void *)&addr, sizeof(addr), false /* !ipv6 */);
+}
+
+static void run_test_v6(void)
+{
+	struct sockaddr_in6 addr = {0};
+
+	addr.sin6_family = AF_INET6;
+	addr.sin6_port = htons(cfg_port);
+	addr.sin6_addr = addr6;
+
+	run_test((void *)&addr, sizeof(addr), true /* ipv6 */);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	int c;
+
+	while ((c = getopt(argc, argv, "46ov")) != -1) {
+		switch (c) {
+		case '4':
+			cfg_do_ipv4 = true;
+			break;
+		case '6':
+			cfg_do_ipv6 = true;
+			break;
+		case 'o':
+			cfg_overlap = true;
+			break;
+		case 'v':
+			cfg_verbose = true;
+			break;
+		default:
+			error(1, 0, "%s: parse error", argv[0]);
+		}
+	}
+}
+
+int main(int argc, char **argv)
+{
+	parse_opts(argc, argv);
+	seed = time(NULL);
+	srand(seed);
+	/* Print the seed to track/reproduce potential failures. */
+	printf("seed = %d\n", seed);
+
+	if (cfg_do_ipv4)
+		run_test_v4();
+	if (cfg_do_ipv6)
+		run_test_v6();
+
+	return 0;
+}
diff --git a/tools/testing/selftests/net/ip_defrag.sh b/tools/testing/selftests/net/ip_defrag.sh
new file mode 100755
index 000000000000..f34672796044
--- /dev/null
+++ b/tools/testing/selftests/net/ip_defrag.sh
@@ -0,0 +1,39 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a couple of IP defragmentation tests.
+
+set +x
+set -e
+
+readonly NETNS="ns-$(mktemp -u XXXXXX)"
+
+setup() {
+	ip netns add "${NETNS}"
+	ip -netns "${NETNS}" link set lo up
+	ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_high_thresh=9000000 >/dev/null 2>&1
+	ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_low_thresh=7000000 >/dev/null 2>&1
+	ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_high_thresh=9000000 >/dev/null 2>&1
+	ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_low_thresh=7000000 >/dev/null 2>&1
+}
+
+cleanup() {
+	ip netns del "${NETNS}"
+}
+
+trap cleanup EXIT
+setup
+
+echo "ipv4 defrag"
+ip netns exec "${NETNS}" ./ip_defrag -4
+
+
+echo "ipv4 defrag with overlaps"
+ip netns exec "${NETNS}" ./ip_defrag -4o
+
+echo "ipv6 defrag"
+ip netns exec "${NETNS}" ./ip_defrag -6
+
+echo "ipv6 defrag with overlaps"
+ip netns exec "${NETNS}" ./ip_defrag -6o
+
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 0ab9423d009f..a369d616b390 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -6,6 +6,26 @@
 #
 # Tests currently implemented:
 #
+# - pmtu_ipv4
+#	Set up two namespaces, A and B, with two paths between them over routers
+#	R1 and R2 (also implemented with namespaces), with different MTUs:
+#
+#	  segment a_r1    segment b_r1		a_r1: 2000
+#	.--------------R1--------------.	a_r2: 1500
+#	A                               B	a_r3: 2000
+#	'--------------R2--------------'	a_r4: 1400
+#	  segment a_r2    segment b_r2
+#
+#	Check that PMTU exceptions with the correct PMTU are created. Then
+#	decrease and increase the MTU of the local link for one of the paths,
+#	A to R1, checking that route exception PMTU changes accordingly over
+#	this path. Also check that locked exceptions are created when an ICMP
+#	message advertising a PMTU smaller than net.ipv4.route.min_pmtu is
+#	received
+#
+# - pmtu_ipv6
+#	Same as pmtu_ipv4, except for locked PMTU tests, using IPv6
+#
 # - pmtu_vti4_exception
 #	Set up vti tunnel on top of veth, with xfrm states and policies, in two
 #	namespaces with matching endpoints. Check that route exception is not
@@ -50,6 +70,8 @@ ksft_skip=4
 which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
 
 tests="
+	pmtu_ipv4_exception		ipv4: PMTU exceptions
+	pmtu_ipv6_exception		ipv6: PMTU exceptions
 	pmtu_vti6_exception		vti6: PMTU exceptions
 	pmtu_vti4_exception		vti4: PMTU exceptions
 	pmtu_vti4_default_mtu		vti4: default MTU assignment
@@ -60,8 +82,45 @@ tests="
 
 NS_A="ns-$(mktemp -u XXXXXX)"
 NS_B="ns-$(mktemp -u XXXXXX)"
+NS_R1="ns-$(mktemp -u XXXXXX)"
+NS_R2="ns-$(mktemp -u XXXXXX)"
 ns_a="ip netns exec ${NS_A}"
 ns_b="ip netns exec ${NS_B}"
+ns_r1="ip netns exec ${NS_R1}"
+ns_r2="ip netns exec ${NS_R2}"
+
+# Addressing and routing for tests with routers: four network segments, with
+# index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an
+# identifier ID, which is 1 for hosts (A and B), 2 for routers (R1 and R2).
+# Addresses are:
+# - IPv4: PREFIX4.SEGMENT.ID (/24)
+# - IPv6: PREFIX6:SEGMENT::ID (/64)
+prefix4="192.168"
+prefix6="fd00"
+a_r1=1
+a_r2=2
+b_r1=3
+b_r2=4
+#	ns	peer	segment
+routing_addrs="
+	A	R1	${a_r1}
+	A	R2	${a_r2}
+	B	R1	${b_r1}
+	B	R2	${b_r2}
+"
+# Traffic from A to B goes through R1 by default, and through R2, if destined to
+# B's address on the b_r2 segment.
+# Traffic from B to A goes through R1.
+#	ns	destination		gateway
+routes="
+	A	default			${prefix4}.${a_r1}.2
+	A	${prefix4}.${b_r2}.1	${prefix4}.${a_r2}.2
+	B	default			${prefix4}.${b_r1}.2
+
+	A	default			${prefix6}:${a_r1}::2
+	A	${prefix6}:${b_r2}::1	${prefix6}:${a_r2}::2
+	B	default			${prefix6}:${b_r1}::2
+"
 
 veth4_a_addr="192.168.1.1"
 veth4_b_addr="192.168.1.2"
@@ -83,6 +142,7 @@ dummy6_mask="64"
 
 cleanup_done=1
 err_buf=
+tcpdump_pids=
 
 err() {
 	err_buf="${err_buf}${1}
@@ -94,9 +154,15 @@ err_flush() {
 	err_buf=
 }
 
+# Find the auto-generated name for this namespace
+nsname() {
+	eval echo \$NS_$1
+}
+
 setup_namespaces() {
-	ip netns add ${NS_A} || return 1
-	ip netns add ${NS_B}
+	for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
+		ip netns add ${n} || return 1
+	done
 }
 
 setup_veth() {
@@ -167,6 +233,49 @@ setup_xfrm6() {
 	setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr}
 }
 
+setup_routing() {
+	for i in ${NS_R1} ${NS_R2}; do
+		ip netns exec ${i} sysctl -q net/ipv4/ip_forward=1
+		ip netns exec ${i} sysctl -q net/ipv6/conf/all/forwarding=1
+	done
+
+	for i in ${routing_addrs}; do
+		[ "${ns}" = "" ]	&& ns="${i}"		&& continue
+		[ "${peer}" = "" ]	&& peer="${i}"		&& continue
+		[ "${segment}" = "" ]	&& segment="${i}"
+
+		ns_name="$(nsname ${ns})"
+		peer_name="$(nsname ${peer})"
+		if="veth_${ns}-${peer}"
+		ifpeer="veth_${peer}-${ns}"
+
+		# Create veth links
+		ip link add ${if} up netns ${ns_name} type veth peer name ${ifpeer} netns ${peer_name} || return 1
+		ip -n ${peer_name} link set dev ${ifpeer} up
+
+		# Add addresses
+		ip -n ${ns_name}   addr add ${prefix4}.${segment}.1/24  dev ${if}
+		ip -n ${ns_name}   addr add ${prefix6}:${segment}::1/64 dev ${if}
+
+		ip -n ${peer_name} addr add ${prefix4}.${segment}.2/24  dev ${ifpeer}
+		ip -n ${peer_name} addr add ${prefix6}:${segment}::2/64 dev ${ifpeer}
+
+		ns=""; peer=""; segment=""
+	done
+
+	for i in ${routes}; do
+		[ "${ns}" = "" ]	&& ns="${i}"		&& continue
+		[ "${addr}" = "" ]	&& addr="${i}"		&& continue
+		[ "${gw}" = "" ]	&& gw="${i}"
+
+		ns_name="$(nsname ${ns})"
+
+		ip -n ${ns_name} route add ${addr} via ${gw}
+
+		ns=""; addr=""; gw=""
+	done
+}
+
 setup() {
 	[ "$(id -u)" -ne 0 ] && echo "  need to run as root" && return $ksft_skip
 
@@ -176,10 +285,28 @@ setup() {
 	done
 }
 
+trace() {
+	[ $tracing -eq 0 ] && return
+
+	for arg do
+		[ "${ns_cmd}" = "" ] && ns_cmd="${arg}" && continue
+		${ns_cmd} tcpdump -s 0 -i "${arg}" -w "${name}_${arg}.pcap" 2> /dev/null &
+		tcpdump_pids="${tcpdump_pids} $!"
+		ns_cmd=
+	done
+	sleep 1
+}
+
 cleanup() {
+	for pid in ${tcpdump_pids}; do
+		kill ${pid}
+	done
+	tcpdump_pids=
+
 	[ ${cleanup_done} -eq 1 ] && return
-	ip netns del ${NS_A} 2> /dev/null
-	ip netns del ${NS_B} 2> /dev/null
+	for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
+		ip netns del ${n} 2> /dev/null
+	done
 	cleanup_done=1
 }
 
@@ -196,7 +323,9 @@ mtu_parse() {
 
 	next=0
 	for i in ${input}; do
+		[ ${next} -eq 1 -a "${i}" = "lock" ] && next=2 && continue
 		[ ${next} -eq 1 ] && echo "${i}" && return
+		[ ${next} -eq 2 ] && echo "lock ${i}" && return
 		[ "${i}" = "mtu" ] && next=1
 	done
 }
@@ -229,8 +358,117 @@ route_get_dst_pmtu_from_exception() {
 	mtu_parse "$(route_get_dst_exception "${ns_cmd}" ${dst})"
 }
 
+check_pmtu_value() {
+	expected="${1}"
+	value="${2}"
+	event="${3}"
+
+	[ "${expected}" = "any" ] && [ -n "${value}" ] && return 0
+	[ "${value}" = "${expected}" ] && return 0
+	[ -z "${value}" ] &&    err "  PMTU exception wasn't created after ${event}" && return 1
+	[ -z "${expected}" ] && err "  PMTU exception shouldn't exist after ${event}" && return 1
+	err "  found PMTU exception with incorrect MTU ${value}, expected ${expected}, after ${event}"
+	return 1
+}
+
+test_pmtu_ipvX() {
+	family=${1}
+
+	setup namespaces routing || return 2
+	trace "${ns_a}"  veth_A-R1    "${ns_r1}" veth_R1-A \
+	      "${ns_r1}" veth_R1-B    "${ns_b}"  veth_B-R1 \
+	      "${ns_a}"  veth_A-R2    "${ns_r2}" veth_R2-A \
+	      "${ns_r2}" veth_R2-B    "${ns_b}"  veth_B-R2
+
+	if [ ${family} -eq 4 ]; then
+		ping=ping
+		dst1="${prefix4}.${b_r1}.1"
+		dst2="${prefix4}.${b_r2}.1"
+	else
+		ping=${ping6}
+		dst1="${prefix6}:${b_r1}::1"
+		dst2="${prefix6}:${b_r2}::1"
+	fi
+
+	# Set up initial MTU values
+	mtu "${ns_a}"  veth_A-R1 2000
+	mtu "${ns_r1}" veth_R1-A 2000
+	mtu "${ns_r1}" veth_R1-B 1400
+	mtu "${ns_b}"  veth_B-R1 1400
+
+	mtu "${ns_a}"  veth_A-R2 2000
+	mtu "${ns_r2}" veth_R2-A 2000
+	mtu "${ns_r2}" veth_R2-B 1500
+	mtu "${ns_b}"  veth_B-R2 1500
+
+	# Create route exceptions
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1800 ${dst1} > /dev/null
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1800 ${dst2} > /dev/null
+
+	# Check that exceptions have been created with the correct PMTU
+	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})"
+	check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1
+
+	# Decrease local MTU below PMTU, check for PMTU decrease in route exception
+	mtu "${ns_a}"  veth_A-R1 1300
+	mtu "${ns_r1}" veth_R1-A 1300
+	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})"
+	check_pmtu_value "1300" "${pmtu_1}" "decreasing local MTU" || return 1
+	# Second exception shouldn't be modified
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "1500" "${pmtu_2}" "changing local MTU on a link not on this path" || return 1
+
+	# Increase MTU, check for PMTU increase in route exception
+	mtu "${ns_a}"  veth_A-R1 1700
+	mtu "${ns_r1}" veth_R1-A 1700
+	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})"
+	check_pmtu_value "1700" "${pmtu_1}" "increasing local MTU" || return 1
+	# Second exception shouldn't be modified
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "1500" "${pmtu_2}" "changing local MTU on a link not on this path" || return 1
+
+	# Skip PMTU locking tests for IPv6
+	[ $family -eq 6 ] && return 0
+
+	# Decrease remote MTU on path via R2, get new exception
+	mtu "${ns_r2}" veth_R2-B 400
+	mtu "${ns_b}"  veth_B-R2 400
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1400 ${dst2} > /dev/null
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "lock 552" "${pmtu_2}" "exceeding MTU, with MTU < min_pmtu" || return 1
+
+	# Decrease local MTU below PMTU
+	mtu "${ns_a}"  veth_A-R2 500
+	mtu "${ns_r2}" veth_R2-A 500
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "500" "${pmtu_2}" "decreasing local MTU" || return 1
+
+	# Increase local MTU
+	mtu "${ns_a}"  veth_A-R2 1500
+	mtu "${ns_r2}" veth_R2-A 1500
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "1500" "${pmtu_2}" "increasing local MTU" || return 1
+
+	# Get new exception
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1400 ${dst2} > /dev/null
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "lock 552" "${pmtu_2}" "exceeding MTU, with MTU < min_pmtu" || return 1
+}
+
+test_pmtu_ipv4_exception() {
+	test_pmtu_ipvX 4
+}
+
+test_pmtu_ipv6_exception() {
+	test_pmtu_ipvX 6
+}
+
 test_pmtu_vti4_exception() {
 	setup namespaces veth vti4 xfrm4 || return 2
+	trace "${ns_a}" veth_a    "${ns_b}" veth_b \
+	      "${ns_a}" vti4_a    "${ns_b}" vti4_b
 
 	veth_mtu=1500
 	vti_mtu=$((veth_mtu - 20))
@@ -248,28 +486,19 @@ test_pmtu_vti4_exception() {
 	# exception is created
 	${ns_a} ping -q -M want -i 0.1 -w 2 -s ${ping_payload} ${vti4_b_addr} > /dev/null
 	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti4_b_addr})"
-	if [ "${pmtu}" != "" ]; then
-		err "  unexpected exception created with PMTU ${pmtu} for IP payload length ${esp_payload_rfc4106}"
-		return 1
-	fi
+	check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
 
 	# Now exceed link layer MTU by one byte, check that exception is created
+	# with the right PMTU value
 	${ns_a} ping -q -M want -i 0.1 -w 2 -s $((ping_payload + 1)) ${vti4_b_addr} > /dev/null
 	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti4_b_addr})"
-	if [ "${pmtu}" = "" ]; then
-		err "  exception not created for IP payload length $((esp_payload_rfc4106 + 1))"
-		return 1
-	fi
-
-	# ...with the right PMTU value
-	if [ ${pmtu} -ne ${esp_payload_rfc4106} ]; then
-		err "  wrong PMTU ${pmtu} in exception, expected: ${esp_payload_rfc4106}"
-		return 1
-	fi
+	check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))"
 }
 
 test_pmtu_vti6_exception() {
 	setup namespaces veth vti6 xfrm6 || return 2
+	trace "${ns_a}" veth_a    "${ns_b}" veth_b \
+	      "${ns_a}" vti6_a    "${ns_b}" vti6_b
 	fail=0
 
 	# Create route exception by exceeding link layer MTU
@@ -280,25 +509,18 @@ test_pmtu_vti6_exception() {
 	${ns_a} ${ping6} -q -i 0.1 -w 2 -s 60000 ${vti6_b_addr} > /dev/null
 
 	# Check that exception was created
-	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" = "" ]; then
-		err "  tunnel exceeding link layer MTU didn't create route exception"
-		return 1
-	fi
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+	check_pmtu_value any "${pmtu}" "creating tunnel exceeding link layer MTU" || return 1
 
 	# Decrease tunnel MTU, check for PMTU decrease in route exception
 	mtu "${ns_a}" vti6_a 3000
-
-	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" -ne 3000 ]; then
-		err "  decreasing tunnel MTU didn't decrease route exception PMTU"
-		fail=1
-	fi
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+	check_pmtu_value "3000" "${pmtu}" "decreasing tunnel MTU" || fail=1
 
 	# Increase tunnel MTU, check for PMTU increase in route exception
 	mtu "${ns_a}" vti6_a 9000
-	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" -ne 9000 ]; then
-		err "  increasing tunnel MTU didn't increase route exception PMTU"
-		fail=1
-	fi
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+	check_pmtu_value "9000" "${pmtu}" "increasing tunnel MTU" || fail=1
 
 	return ${fail}
 }
@@ -445,15 +667,56 @@ test_pmtu_vti6_link_change_mtu() {
 	return ${fail}
 }
 
-trap cleanup EXIT
+usage() {
+	echo
+	echo "$0 [OPTIONS] [TEST]..."
+	echo "If no TEST argument is given, all tests will be run."
+	echo
+	echo "Options"
+	echo "  --trace: capture traffic to TEST_INTERFACE.pcap"
+	echo
+	echo "Available tests${tests}"
+	exit 1
+}
 
 exitcode=0
 desc=0
 IFS="	
 "
+
+tracing=0
+for arg do
+	if [ "${arg}" != "${arg#--*}" ]; then
+		opt="${arg#--}"
+		if [ "${opt}" = "trace" ]; then
+			if which tcpdump > /dev/null 2>&1; then
+				tracing=1
+			else
+				echo "=== tcpdump not available, tracing disabled"
+			fi
+		else
+			usage
+		fi
+	else
+		# Check first that all requested tests are available before
+		# running any
+		command -v > /dev/null "test_${arg}" || { echo "=== Test ${arg} not found"; usage; }
+	fi
+done
+
+trap cleanup EXIT
+
 for t in ${tests}; do
 	[ $desc -eq 0 ] && name="${t}" && desc=1 && continue || desc=0
 
+	run_this=1
+	for arg do
+		[ "${arg}" != "${arg#--*}" ] && continue
+		[ "${arg}" = "${name}" ] && run_this=1 && break
+		run_this=0
+	done
+	[ $run_this -eq 0 ] && continue
+
 	(
 		unset IFS
 		eval test_${name}
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 8fdfeafaf8c0..fac68d710f35 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -121,11 +121,11 @@ TEST_F(tls, send_then_sendfile)
 	buf = (char *)malloc(st.st_size);
 
 	EXPECT_EQ(send(self->fd, test_str, to_send, 0), to_send);
-	EXPECT_EQ(recv(self->cfd, recv_buf, to_send, 0), to_send);
+	EXPECT_EQ(recv(self->cfd, recv_buf, to_send, MSG_WAITALL), to_send);
 	EXPECT_EQ(memcmp(test_str, recv_buf, to_send), 0);
 
 	EXPECT_GE(sendfile(self->fd, filefd, 0, st.st_size), 0);
-	EXPECT_EQ(recv(self->cfd, buf, st.st_size, 0), st.st_size);
+	EXPECT_EQ(recv(self->cfd, buf, st.st_size, MSG_WAITALL), st.st_size);
 }
 
 TEST_F(tls, recv_max)
@@ -160,7 +160,7 @@ TEST_F(tls, msg_more)
 	EXPECT_EQ(send(self->fd, test_str, send_len, MSG_MORE), send_len);
 	EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_DONTWAIT), -1);
 	EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
-	EXPECT_EQ(recv(self->cfd, buf, send_len * 2, MSG_DONTWAIT),
+	EXPECT_EQ(recv(self->cfd, buf, send_len * 2, MSG_WAITALL),
 		  send_len * 2);
 	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
 }
@@ -180,7 +180,7 @@ TEST_F(tls, sendmsg_single)
 	msg.msg_iov = &vec;
 	msg.msg_iovlen = 1;
 	EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len);
-	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+	EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_WAITALL), send_len);
 	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
 }
 
@@ -288,7 +288,7 @@ TEST_F(tls, splice_from_pipe)
 	ASSERT_GE(pipe(p), 0);
 	EXPECT_GE(write(p[1], mem_send, send_len), 0);
 	EXPECT_GE(splice(p[0], NULL, self->fd, NULL, send_len, 0), 0);
-	EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0);
+	EXPECT_EQ(recv(self->cfd, mem_recv, send_len, MSG_WAITALL), send_len);
 	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
 }
 
@@ -306,7 +306,7 @@ TEST_F(tls, splice_from_pipe2)
 	EXPECT_GE(splice(p[0], NULL, self->fd, NULL, 8000, 0), 0);
 	EXPECT_GE(write(p2[1], mem_send + 8000, 8000), 0);
 	EXPECT_GE(splice(p2[0], NULL, self->fd, NULL, 8000, 0), 0);
-	EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0);
+	EXPECT_EQ(recv(self->cfd, mem_recv, send_len, MSG_WAITALL), send_len);
 	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
 }
 
@@ -322,13 +322,13 @@ TEST_F(tls, send_and_splice)
 
 	ASSERT_GE(pipe(p), 0);
 	EXPECT_EQ(send(self->fd, test_str, send_len2, 0), send_len2);
-	EXPECT_NE(recv(self->cfd, buf, send_len2, 0), -1);
+	EXPECT_EQ(recv(self->cfd, buf, send_len2, MSG_WAITALL), send_len2);
 	EXPECT_EQ(memcmp(test_str, buf, send_len2), 0);
 
 	EXPECT_GE(write(p[1], mem_send, send_len), send_len);
 	EXPECT_GE(splice(p[0], NULL, self->fd, NULL, send_len, 0), send_len);
 
-	EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0);
+	EXPECT_EQ(recv(self->cfd, mem_recv, send_len, MSG_WAITALL), send_len);
 	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
 }
 
@@ -436,7 +436,7 @@ TEST_F(tls, multiple_send_single_recv)
 	EXPECT_GE(send(self->fd, send_mem, send_len, 0), 0);
 	EXPECT_GE(send(self->fd, send_mem, send_len, 0), 0);
 	memset(recv_mem, 0, total_len);
-	EXPECT_EQ(recv(self->cfd, recv_mem, total_len, 0), total_len);
+	EXPECT_EQ(recv(self->cfd, recv_mem, total_len, MSG_WAITALL), total_len);
 
 	EXPECT_EQ(memcmp(send_mem, recv_mem, send_len), 0);
 	EXPECT_EQ(memcmp(send_mem, recv_mem + send_len, send_len), 0);
@@ -516,17 +516,17 @@ TEST_F(tls, recv_peek_multiple_records)
 	len = strlen(test_str_second) + 1;
 	EXPECT_EQ(send(self->fd, test_str_second, len, 0), len);
 
-	len = sizeof(buf);
+	len = strlen(test_str_first);
 	memset(buf, 0, len);
-	EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1);
+	EXPECT_EQ(recv(self->cfd, buf, len, MSG_PEEK | MSG_WAITALL), len);
 
 	/* MSG_PEEK can only peek into the current record. */
-	len = strlen(test_str_first) + 1;
+	len = strlen(test_str_first);
 	EXPECT_EQ(memcmp(test_str_first, buf, len), 0);
 
-	len = sizeof(buf);
+	len = strlen(test_str) + 1;
 	memset(buf, 0, len);
-	EXPECT_NE(recv(self->cfd, buf, len, 0), -1);
+	EXPECT_EQ(recv(self->cfd, buf, len, MSG_WAITALL), len);
 
 	/* Non-MSG_PEEK will advance strparser (and therefore record)
 	 * however.
@@ -543,6 +543,28 @@ TEST_F(tls, recv_peek_multiple_records)
 	len = strlen(test_str_second) + 1;
 	EXPECT_EQ(send(self->fd, test_str_second, len, 0), len);
 
+	len = strlen(test_str) + 1;
+	memset(buf, 0, len);
+	EXPECT_EQ(recv(self->cfd, buf, len, MSG_PEEK | MSG_WAITALL), len);
+
+	len = strlen(test_str) + 1;
+	EXPECT_EQ(memcmp(test_str, buf, len), 0);
+}
+
+TEST_F(tls, recv_peek_large_buf_mult_recs)
+{
+	char const *test_str = "test_read_peek_mult_recs";
+	char const *test_str_first = "test_read_peek";
+	char const *test_str_second = "_mult_recs";
+	int len;
+	char buf[64];
+
+	len = strlen(test_str_first);
+	EXPECT_EQ(send(self->fd, test_str_first, len, 0), len);
+
+	len = strlen(test_str_second) + 1;
+	EXPECT_EQ(send(self->fd, test_str_second, len, 0), len);
+
 	len = sizeof(buf);
 	memset(buf, 0, len);
 	EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1);
@@ -551,6 +573,7 @@ TEST_F(tls, recv_peek_multiple_records)
 	EXPECT_EQ(memcmp(test_str, buf, len), 0);
 }
 
+
 TEST_F(tls, pollin)
 {
 	char const *test_str = "test_poll";
@@ -564,7 +587,7 @@ TEST_F(tls, pollin)
 
 	EXPECT_EQ(poll(&fd, 1, 20), 1);
 	EXPECT_EQ(fd.revents & POLLIN, 1);
-	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+	EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_WAITALL), send_len);
 	/* Test timing out */
 	EXPECT_EQ(poll(&fd, 1, 20), 0);
 }
@@ -582,7 +605,7 @@ TEST_F(tls, poll_wait)
 	/* Set timeout to inf. secs */
 	EXPECT_EQ(poll(&fd, 1, -1), 1);
 	EXPECT_EQ(fd.revents & POLLIN, 1);
-	EXPECT_EQ(recv(self->cfd, recv_mem, send_len, 0), send_len);
+	EXPECT_EQ(recv(self->cfd, recv_mem, send_len, MSG_WAITALL), send_len);
 }
 
 TEST_F(tls, blocking)
@@ -728,7 +751,7 @@ TEST_F(tls, control_msg)
 	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1);
 
 	vec.iov_base = buf;
-	EXPECT_EQ(recvmsg(self->cfd, &msg, 0), send_len);
+	EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL), send_len);
 	cmsg = CMSG_FIRSTHDR(&msg);
 	EXPECT_NE(cmsg, NULL);
 	EXPECT_EQ(cmsg->cmsg_level, SOL_TLS);