[PATCH net-next 0/9] selftests: pmtu: Add further vti/vti6 MTU and PMTU tests

[PATCH net-next 0/9] selftests: pmtu: Add further vti/vti6 MTU and PMTU tests

[Stefano Brivio]

Patches 4/9 to 9/9 add tests to verify default MTU assignment for
vti4 and vti6 interfaces, to check that MTU values set on new
link and link changes are properly taken and validated, and to
verify PMTU exceptions on vti4 interfaces.

Patch 1/9 fixes the helper to fetch exceptions MTU to run in the
passed namespace.

Patches 2/9 and 3/9 are preparation work to make it easier to
introduce those tests.

Stefano Brivio (9):
  selftests: pmtu: Use namespace command prefix to fetch route mtu
  selftests: pmtu: Factor out MTU parsing helper
  selftests: pmtu: Introduce support for multiple tests
  selftests: pmtu: Add pmtu_vti4_default_mtu test
  selftests: pmtu: Add pmtu_vti6_default_mtu test
  selftests: pmtu: Add pmtu_vti4_exception test
  selftests: pmtu: Add pmtu_vti4_link_add_mtu test
  selftests: pmtu: Add pmtu_vti6_link_add_mtu test
  selftests: pmtu: Add pmtu_vti6_link_change_mtu test

 tools/testing/selftests/net/pmtu.sh | 413 +++++++++++++++++++++++++++++++-----
 1 file changed, 357 insertions(+), 56 deletions(-)

-- 
2.15.1

[PATCH net-next 1/9] selftests: pmtu: Use namespace command prefix to fetch route mtu

[Stefano Brivio]

In commit 7af137b72131 ("selftests: net: Introduce first PMTU
test") I accidentally assumed route_get_* helpers would run from
a single namespace. Make them a bit more generic, by passing the
namespace command prefix as a parameter instead.

Fixes: 7af137b72131 ("selftests: net: Introduce first PMTU test")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
---
 tools/testing/selftests/net/pmtu.sh | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 6c19c148cef8..7a7845e415e4 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -106,15 +106,17 @@ mtu() {
 }
 
 route_get_dst_exception() {
-	dst="${1}"
+	ns_cmd="${1}"
+	dst="${2}"
 
-	${ns_a} ip route get "${dst}"
+	${ns_cmd} ip route get "${dst}"
 }
 
 route_get_dst_pmtu_from_exception() {
-	dst="${1}"
+	ns_cmd="${1}"
+	dst="${2}"
 
-	exception="$(route_get_dst_exception ${dst})"
+	exception="$(route_get_dst_exception "${ns_cmd}" ${dst})"
 	next=0
 	for i in ${exception}; do
 		[ ${next} -eq 1 ] && echo "${i}" && return
@@ -133,7 +135,7 @@ 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 ${vti6_b_addr})" = "" ]; then
+	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" = "" ]; then
 		echo "FAIL: Tunnel exceeding link layer MTU didn't create route exception"
 		exit 1
 	fi
@@ -141,14 +143,14 @@ test_pmtu_vti6_exception() {
 	# Decrease tunnel MTU, check for PMTU decrease in route exception
 	mtu "${ns_a}" vti_a 3000
 
-	if [ "$(route_get_dst_pmtu_from_exception ${vti6_b_addr})" -ne 3000 ]; then
+	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" -ne 3000 ]; then
 		echo "FAIL: Decreasing tunnel MTU didn't decrease route exception PMTU"
 		exit 1
 	fi
 
 	# Increase tunnel MTU, check for PMTU increase in route exception
 	mtu "${ns_a}" vti_a 9000
-	if [ "$(route_get_dst_pmtu_from_exception ${vti6_b_addr})" -ne 9000 ]; then
+	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" -ne 9000 ]; then
 		echo "FAIL: Increasing tunnel MTU didn't increase route exception PMTU"
 		exit 1
 	fi
-- 
2.15.1

[PATCH net-next 2/9] selftests: pmtu: Factor out MTU parsing helper

[Stefano Brivio]

...so that it can be used for any iproute command output.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
---
 tools/testing/selftests/net/pmtu.sh | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 7a7845e415e4..fc79cc6f49a6 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -105,6 +105,16 @@ mtu() {
 	${ns_cmd} ip link set dev ${dev} mtu ${mtu}
 }
 
+mtu_parse() {
+	input="${1}"
+
+	next=0
+	for i in ${input}; do
+		[ ${next} -eq 1 ] && echo "${i}" && return
+		[ "${i}" = "mtu" ] && next=1
+	done
+}
+
 route_get_dst_exception() {
 	ns_cmd="${1}"
 	dst="${2}"
@@ -116,12 +126,7 @@ route_get_dst_pmtu_from_exception() {
 	ns_cmd="${1}"
 	dst="${2}"
 
-	exception="$(route_get_dst_exception "${ns_cmd}" ${dst})"
-	next=0
-	for i in ${exception}; do
-		[ ${next} -eq 1 ] && echo "${i}" && return
-		[ "${i}" = "mtu" ] && next=1
-	done
+	mtu_parse "$(route_get_dst_exception "${ns_cmd}" ${dst})"
 }
 
 test_pmtu_vti6_exception() {
-- 
2.15.1

[PATCH net-next 3/9] selftests: pmtu: Introduce support for multiple tests

[Stefano Brivio]

Introduce list of tests and loop on it in main body.

Tests will now just take care of calling setup with a list of
"units" they need, and return 0 for failure, 1 for success, 2 if
the test had to be skipped.

Main script body will take care of displaying results and
cleaning up after every test. Introduce guard variable so that
we don't clean up twice in case of interrupts or unexpected
failures.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
---
 tools/testing/selftests/net/pmtu.sh | 58 ++++++++++++++++++++++---------------
 1 file changed, 34 insertions(+), 24 deletions(-)

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index fc79cc6f49a6..feebb6fcff21 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -5,13 +5,15 @@
 #
 # Tests currently implemented:
 #
-# - test_pmtu_vti6_exception
+# - pmtu_vti6_exception
 #	Set up vti6 tunnel on top of veth, with xfrm states and policies, in two
 #	namespaces with matching endpoints. Check that route exception is
 #	created by exceeding link layer MTU with ping to other endpoint. Then
 #	decrease and increase MTU of tunnel, checking that route exception PMTU
 #	changes accordingly
 
+tests="pmtu_vti6_exception"
+
 NS_A="ns-$(mktemp -u XXXXXX)"
 NS_B="ns-$(mktemp -u XXXXXX)"
 ns_a="ip netns exec ${NS_A}"
@@ -25,6 +27,8 @@ vti6_a_addr="fd00:2::a"
 vti6_b_addr="fd00:2::b"
 vti6_mask="64"
 
+cleanup_done=1
+
 setup_namespaces() {
 	ip netns add ${NS_A} || return 0
 	ip netns add ${NS_B}
@@ -75,26 +79,21 @@ setup_xfrm() {
 }
 
 setup() {
-	tunnel_type="$1"
+	[ "$(id -u)" -ne 0 ] && echo "  need to run as root" && return 0
 
-	[ "$(id -u)" -ne 0 ] && echo "SKIP: need to run as root" && exit 0
-
-	setup_namespaces && echo "SKIP: namespaces not supported" && exit 0
-	setup_veth && echo "SKIP: veth not supported" && exit 0
+	cleanup_done=0
+	for arg do
+		eval setup_${arg} && echo "  ${arg} not supported" && return 0
+	done
 
-	case ${tunnel_type} in
-	"vti6")
-		setup_vti6 && echo "SKIP: vti6 not supported" && exit 0
-		setup_xfrm && echo "SKIP: xfrm not supported" && exit 0
-		;;
-	*)
-		;;
-	esac
+	return 1
 }
 
 cleanup() {
+	[ ${cleanup_done} -eq 1 ] && return
 	ip netns del ${NS_A} 2 > /dev/null
 	ip netns del ${NS_B} 2 > /dev/null
+	cleanup_done=1
 }
 
 mtu() {
@@ -130,7 +129,7 @@ route_get_dst_pmtu_from_exception() {
 }
 
 test_pmtu_vti6_exception() {
-	setup vti6
+	setup namespaces veth vti6 xfrm && return 2
 
 	# Create route exception by exceeding link layer MTU
 	mtu "${ns_a}" veth_a 4000
@@ -141,30 +140,41 @@ test_pmtu_vti6_exception() {
 
 	# Check that exception was created
 	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" = "" ]; then
-		echo "FAIL: Tunnel exceeding link layer MTU didn't create route exception"
-		exit 1
+		echo "  tunnel exceeding link layer MTU didn't create route exception"
+		return 0
 	fi
 
 	# Decrease tunnel MTU, check for PMTU decrease in route exception
 	mtu "${ns_a}" vti_a 3000
 
 	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" -ne 3000 ]; then
-		echo "FAIL: Decreasing tunnel MTU didn't decrease route exception PMTU"
-		exit 1
+		echo "  decreasing tunnel MTU didn't decrease route exception PMTU"
+		return 0
 	fi
 
 	# Increase tunnel MTU, check for PMTU increase in route exception
 	mtu "${ns_a}" vti_a 9000
 	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" -ne 9000 ]; then
-		echo "FAIL: Increasing tunnel MTU didn't increase route exception PMTU"
-		exit 1
+		echo "  increasing tunnel MTU didn't increase route exception PMTU"
+		return 0
 	fi
 
-	echo "PASS"
+	return 1
 }
 
 trap cleanup EXIT
 
-test_pmtu_vti6_exception
+exitcode=0
+for name in ${tests}; do
+	echo "${name}: START"
+	eval test_${name}
+	ret=$?
+	cleanup
+
+	if [ $ret -eq 0 ]; then echo "${name}: FAIL"; exitcode=1
+	elif [ $ret -eq 1 ]; then echo "${name}: PASS"
+	elif [ $ret -eq 2 ]; then echo "${name}: SKIP"
+	fi
+done
 
-exit 0
+exit ${exitcode}
-- 
2.15.1

Re: [PATCH net-next 3/9] selftests: pmtu: Introduce support for multiple tests

[David Ahern]

On 3/15/18 9:18 AM, Stefano Brivio wrote:
>  trap cleanup EXIT
>  
> -test_pmtu_vti6_exception
> +exitcode=0
> +for name in ${tests}; do
> +	echo "${name}: START"
> +	eval test_${name}
> +	ret=$?
> +	cleanup
> +
> +	if [ $ret -eq 0 ]; then echo "${name}: FAIL"; exitcode=1

ret = 0 == failure is counterintuitive for Linux.

> +	elif [ $ret -eq 1 ]; then echo "${name}: PASS"
> +	elif [ $ret -eq 2 ]; then echo "${name}: SKIP"

I use printf in other scripts so that the pass/fail verdict lineup. e.g.,
printf "        %-60s  [PASS]\n" "${name}"


> +	fi
> +done
>  
> -exit 0
> +exit ${exitcode}
> 

Re: [PATCH net-next 3/9] selftests: pmtu: Introduce support for multiple tests

[Stefano Brivio]

On Fri, 16 Mar 2018 11:06:07 -0700
David Ahern <dsahern@gmail.com> wrote:

> On 3/15/18 9:18 AM, Stefano Brivio wrote:
> >  trap cleanup EXIT
> >  
> > -test_pmtu_vti6_exception
> > +exitcode=0
> > +for name in ${tests}; do
> > +	echo "${name}: START"
> > +	eval test_${name}
> > +	ret=$?
> > +	cleanup
> > +
> > +	if [ $ret -eq 0 ]; then echo "${name}: FAIL"; exitcode=1  
> 
> ret = 0 == failure is counterintuitive for Linux.

However, in POSIX shell's AND and OR lists with function calls, a
function returning zero behaves in a similar fashion to a C function
evaluating to true, and a function returning non-zero behaves like a C
function evaluating to false [1]:

	a() {
		return 0
	}

	b() {
		return 1
	}

	a && echo this gets printed
	b && echo and this does not

This might be equally counter-intuitive for somebody. If one does a lot
of explicit error checking with early returns, my return convention is
also rather practical. E.g. in the setup() function I can do:

	eval setup_${arg} && echo "  ${arg} not supported" && return 0

instead of:

	eval setup_${arg} || { echo "  ${arg} not supported" && return 0; }

Still, I went ahead and reversed return codes in the whole script, and
it doesn't look *too* bad with the setup() function from patch 3/9. It
would have been quite ugly earlier.

So I don't have a strong preference. If you still prefer that I reverse
my return codes, I will re-spin the series (and probably I'll need a
first patch that reverses the existing logic, too).

> > +	elif [ $ret -eq 1 ]; then echo "${name}: PASS"
> > +	elif [ $ret -eq 2 ]; then echo "${name}: SKIP"  
> 
> I use printf in other scripts so that the pass/fail verdict lineup. e.g.,
> printf "        %-60s  [PASS]\n" "${name}"

I avoided 'printf' so far because it's not a built-in utility on some
shells (e.g. csh), being a "recent" addition to the POSIX Base
Specifications (issue 4, while 'echo' is from issue 2), and it might be
unavailable on some (embedded?) systems.

I don't have a strong preference about this either. It's a very minor
portability concern vs. a very minor readability improvement, what do
you think? 


[1] http://pubs.opengroup.org/onlinepubs/9699919799/utilities/V3_chap02.html#tag_18_09_03_06

-- 
Stefano

Re: [PATCH net-next 3/9] selftests: pmtu: Introduce support for multiple tests

[David Ahern]

On 3/16/18 12:29 PM, Stefano Brivio wrote:
> On Fri, 16 Mar 2018 11:06:07 -0700
> David Ahern <dsahern@gmail.com> wrote:
> 
>> On 3/15/18 9:18 AM, Stefano Brivio wrote:
>>>  trap cleanup EXIT
>>>  
>>> -test_pmtu_vti6_exception
>>> +exitcode=0
>>> +for name in ${tests}; do
>>> +	echo "${name}: START"
>>> +	eval test_${name}
>>> +	ret=$?
>>> +	cleanup
>>> +
>>> +	if [ $ret -eq 0 ]; then echo "${name}: FAIL"; exitcode=1  
>>
>> ret = 0 == failure is counterintuitive for Linux.
> 
> However, in POSIX shell's AND and OR lists with function calls, a
> function returning zero behaves in a similar fashion to a C function
> evaluating to true, and a function returning non-zero behaves like a C
> function evaluating to false [1]:
> 
> 	a() {
> 		return 0
> 	}
> 
> 	b() {
> 		return 1
> 	}
> 
> 	a && echo this gets printed
> 	b && echo and this does not
> 
> This might be equally counter-intuitive for somebody. If one does a lot
> of explicit error checking with early returns, my return convention is
> also rather practical. E.g. in the setup() function I can do:
> 
> 	eval setup_${arg} && echo "  ${arg} not supported" && return 0
> 
> instead of:
> 
> 	eval setup_${arg} || { echo "  ${arg} not supported" && return 0; }

I think it is weird to have 'a && b' where b is done when a fails as
opposed to succeeds hence the comment. I think a common convention
across scripts is important but having the tests is more so. Just a
suggestion.


> 
> Still, I went ahead and reversed return codes in the whole script, and
> it doesn't look *too* bad with the setup() function from patch 3/9. It
> would have been quite ugly earlier.
> 
> So I don't have a strong preference. If you still prefer that I reverse
> my return codes, I will re-spin the series (and probably I'll need a
> first patch that reverses the existing logic, too).
> 
>>> +	elif [ $ret -eq 1 ]; then echo "${name}: PASS"
>>> +	elif [ $ret -eq 2 ]; then echo "${name}: SKIP"  
>>
>> I use printf in other scripts so that the pass/fail verdict lineup. e.g.,
>> printf "        %-60s  [PASS]\n" "${name}"
> 
> I avoided 'printf' so far because it's not a built-in utility on some
> shells (e.g. csh), being a "recent" addition to the POSIX Base
> Specifications (issue 4, while 'echo' is from issue 2), and it might be
> unavailable on some (embedded?) systems.
> 
> I don't have a strong preference about this either. It's a very minor
> portability concern vs. a very minor readability improvement, what do
> you think? 

Look at fib_tests and fib-onlink-tests. As the number of tests grows,
output consistency makes your life easier. With printf:

...
TEST: IPv4 linkdown flag set                                  [ OK ]
TEST: IPv6 linkdown flag set                                  [ OK ]
TEST: Directly connected nexthop, unicast address             [ OK ]
TEST: Directly connected nexthop, unicast address with device [ OK ]
TEST: Gateway is linklocal address                            [ OK ]
TEST: Gateway is linklocal address, no device                 [ OK ]
TEST: Gateway can not be local unicast address                [ OK ]
TEST: Gateway can not be local unicast address, with device   [ OK ]
TEST: Gateway can not be a local linklocal address            [ OK ]
TEST: Gateway can be local address in a VRF                   [FAIL]
TEST: Gateway can be local address in a VRF, with device      [FAIL]
TEST: Gateway can be local linklocal address in a VRF         [ OK ]
TEST: Redirect to VRF lookup                                  [ OK ]
...

the FAIL cases jump out versus echo

...
TEST: IPv4 linkdown flag set [ OK ]
TEST: IPv6 linkdown flag set [ OK ]
TEST: Directly connected nexthop, unicast address [ OK ]
TEST: Directly connected nexthop, unicast address with device [ OK ]
TEST: Gateway is linklocal address [ OK ]
TEST: Gateway is linklocal address, no device [ OK ]
TEST: Gateway can not be local unicast address [ OK ]
TEST: Gateway can not be local unicast address, with device [ OK ]
TEST: Gateway can not be a local linklocal address [ OK ]
TEST: Gateway can be local address in a VRF [FAIL]
TEST: Gateway can be local address in a VRF, with device [FAIL]
TEST: Gateway can be local linklocal address in a VRF [ OK ]
TEST: Redirect to VRF lookup [ OK ]
...

where your mind has a lot more work to do to find the tests broken by a
change.

That is also why I chose OK versus PASS -- ok at 2 letters, fail at 4
the failures really stand out.

Re: [PATCH net-next 3/9] selftests: pmtu: Introduce support for multiple tests

[Stefano Brivio]

On Fri, 16 Mar 2018 12:53:23 -0700
David Ahern <dsahern@gmail.com> wrote:

> On 3/16/18 12:29 PM, Stefano Brivio wrote:
> > This might be equally counter-intuitive for somebody. If one does a lot
> > of explicit error checking with early returns, my return convention is
> > also rather practical. E.g. in the setup() function I can do:
> > 
> > 	eval setup_${arg} && echo "  ${arg} not supported" && return 0
> > 
> > instead of:
> > 
> > 	eval setup_${arg} || { echo "  ${arg} not supported" && return 0; }  
> 
> I think it is weird to have 'a && b' where b is done when a fails as
> opposed to succeeds hence the comment. I think a common convention
> across scripts is important but having the tests is more so. Just a
> suggestion.

Yeah, also true. I'll change this.

> Look at fib_tests and fib-onlink-tests. As the number of tests grows,
> output consistency makes your life easier. With printf:
> 
> ...
> TEST: IPv4 linkdown flag set                                  [ OK ]
> TEST: IPv6 linkdown flag set                                  [ OK ]
> TEST: Directly connected nexthop, unicast address             [ OK ]
> TEST: Directly connected nexthop, unicast address with device [ OK ]
> TEST: Gateway is linklocal address                            [ OK ]
> TEST: Gateway is linklocal address, no device                 [ OK ]
> TEST: Gateway can not be local unicast address                [ OK ]
> TEST: Gateway can not be local unicast address, with device   [ OK ]
> TEST: Gateway can not be a local linklocal address            [ OK ]
> TEST: Gateway can be local address in a VRF                   [FAIL]
> TEST: Gateway can be local address in a VRF, with device      [FAIL]
> TEST: Gateway can be local linklocal address in a VRF         [ OK ]
> TEST: Redirect to VRF lookup                                  [ OK ]
> ...
> 
> the FAIL cases jump out versus echo
> 
> ...
> TEST: IPv4 linkdown flag set [ OK ]
> TEST: IPv6 linkdown flag set [ OK ]
> TEST: Directly connected nexthop, unicast address [ OK ]
> TEST: Directly connected nexthop, unicast address with device [ OK ]
> TEST: Gateway is linklocal address [ OK ]
> TEST: Gateway is linklocal address, no device [ OK ]
> TEST: Gateway can not be local unicast address [ OK ]
> TEST: Gateway can not be local unicast address, with device [ OK ]
> TEST: Gateway can not be a local linklocal address [ OK ]
> TEST: Gateway can be local address in a VRF [FAIL]
> TEST: Gateway can be local address in a VRF, with device [FAIL]
> TEST: Gateway can be local linklocal address in a VRF [ OK ]
> TEST: Redirect to VRF lookup [ OK ]
> ...
> 
> where your mind has a lot more work to do to find the tests broken by a
> change.
> 
> That is also why I chose OK versus PASS -- ok at 2 letters, fail at 4
> the failures really stand out.

I see your point. I'll use printf and make it a bit prettier in v2.

-- 
Stefano

[PATCH net-next 4/9] selftests: pmtu: Add pmtu_vti4_default_mtu test

[Stefano Brivio]

This test checks that the MTU assigned by default to a vti
(IPv4) interface created on top of veth is simply veth's MTU
minus the length of the encapsulated IPv4 header.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
---
 tools/testing/selftests/net/pmtu.sh | 89 +++++++++++++++++++++++++++++++------
 1 file changed, 76 insertions(+), 13 deletions(-)

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index feebb6fcff21..440d2defe592 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -1,7 +1,8 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 #
-# Check that route PMTU values match expectations
+# Check that route PMTU values match expectations, and that initial device MTU
+# values are assigned correctly
 #
 # Tests currently implemented:
 #
@@ -11,18 +12,30 @@
 #	created by exceeding link layer MTU with ping to other endpoint. Then
 #	decrease and increase MTU of tunnel, checking that route exception PMTU
 #	changes accordingly
+#
+# - pmtu_vti4_default_mtu
+#	Set up vti4 tunnel on top of veth, in two namespaces with matching
+#	endpoints. Check that MTU assigned to vti interface is the MTU of the
+#	lower layer (veth) minus additional lower layer headers (zero, for veth)
+#	minus IPv4 header length
 
-tests="pmtu_vti6_exception"
+tests="pmtu_vti6_exception pmtu_vti4_default_mtu"
 
 NS_A="ns-$(mktemp -u XXXXXX)"
 NS_B="ns-$(mktemp -u XXXXXX)"
 ns_a="ip netns exec ${NS_A}"
 ns_b="ip netns exec ${NS_B}"
 
+veth4_a_addr="192.168.1.1"
+veth4_b_addr="192.168.1.2"
+veth4_mask="24"
 veth6_a_addr="fd00:1::a"
 veth6_b_addr="fd00:1::b"
 veth6_mask="64"
 
+vti4_a_addr="192.168.2.1"
+vti4_b_addr="192.168.2.2"
+vti4_mask="24"
 vti6_a_addr="fd00:2::a"
 vti6_b_addr="fd00:2::b"
 vti6_mask="64"
@@ -40,6 +53,9 @@ setup_veth() {
 	${ns_a} ip link add veth_a type veth peer name veth_b || return 0
 	${ns_a} ip link set veth_b netns ${NS_B}
 
+	${ns_a} ip addr add ${veth4_a_addr}/${veth4_mask} dev veth_a
+	${ns_b} ip addr add ${veth4_b_addr}/${veth4_mask} dev veth_b
+
 	${ns_a} ip addr add ${veth6_a_addr}/${veth6_mask} dev veth_a
 	${ns_b} ip addr add ${veth6_b_addr}/${veth6_mask} dev veth_b
 
@@ -49,21 +65,40 @@ setup_veth() {
 	return 1
 }
 
-setup_vti6() {
-	${ns_a} ip link add vti_a type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10 || return 0
-	${ns_b} ip link add vti_b type vti6 local ${veth6_b_addr} remote ${veth6_a_addr} key 10
+setup_vti() {
+	proto=${1}
+	veth_a_addr="${2}"
+	veth_b_addr="${3}"
+	vti_a_addr="${4}"
+	vti_b_addr="${5}"
+	vti_mask=${6}
+
+	[ ${proto} -eq 6 ] && vti_type="vti6" || vti_type="vti"
 
-	${ns_a} ip addr add ${vti6_a_addr}/${vti6_mask} dev vti_a
-	${ns_b} ip addr add ${vti6_b_addr}/${vti6_mask} dev vti_b
+	${ns_a} ip link add vti${proto}_a type ${vti_type} local ${veth_a_addr} remote ${veth_b_addr} key 10 || return 0
+	${ns_b} ip link add vti${proto}_b type ${vti_type} local ${veth_b_addr} remote ${veth_a_addr} key 10
 
-	${ns_a} ip link set vti_a up
-	${ns_b} ip link set vti_b up
+	${ns_a} ip addr add ${vti_a_addr}/${vti_mask} dev vti${proto}_a
+	${ns_b} ip addr add ${vti_b_addr}/${vti_mask} dev vti${proto}_b
+
+	${ns_a} ip link set vti${proto}_a up
+	${ns_b} ip link set vti${proto}_b up
 
 	sleep 1
 
 	return 1
 }
 
+setup_vti4() {
+	setup_vti 4 ${veth4_a_addr} ${veth4_b_addr} ${vti4_a_addr} ${vti4_b_addr} ${vti4_mask}
+	return $?
+}
+
+setup_vti6() {
+	setup_vti 6 ${veth6_a_addr} ${veth6_b_addr} ${vti6_a_addr} ${vti6_b_addr} ${vti6_mask}
+	return $?
+}
+
 setup_xfrm() {
 	${ns_a} ip -6 xfrm state add src ${veth6_a_addr} dst ${veth6_b_addr} spi 0x1000 proto esp aead "rfc4106(gcm(aes))" 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel || return 0
 	${ns_a} ip -6 xfrm state add src ${veth6_b_addr} dst ${veth6_a_addr} spi 0x1001 proto esp aead "rfc4106(gcm(aes))" 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
@@ -114,6 +149,20 @@ mtu_parse() {
 	done
 }
 
+link_get() {
+	ns_cmd="${1}"
+	name="${2}"
+
+	${ns_cmd} ip link show dev "${name}"
+}
+
+link_get_mtu() {
+	ns_cmd="${1}"
+	name="${2}"
+
+	mtu_parse "$(link_get "${ns_cmd}" ${name})"
+}
+
 route_get_dst_exception() {
 	ns_cmd="${1}"
 	dst="${2}"
@@ -134,8 +183,8 @@ test_pmtu_vti6_exception() {
 	# Create route exception by exceeding link layer MTU
 	mtu "${ns_a}" veth_a 4000
 	mtu "${ns_b}" veth_b 4000
-	mtu "${ns_a}" vti_a 5000
-	mtu "${ns_b}" vti_b 5000
+	mtu "${ns_a}" vti6_a 5000
+	mtu "${ns_b}" vti6_b 5000
 	${ns_a} ping6 -q -i 0.1 -w 2 -s 60000 ${vti6_b_addr} > /dev/null
 
 	# Check that exception was created
@@ -145,7 +194,7 @@ test_pmtu_vti6_exception() {
 	fi
 
 	# Decrease tunnel MTU, check for PMTU decrease in route exception
-	mtu "${ns_a}" vti_a 3000
+	mtu "${ns_a}" vti6_a 3000
 
 	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" -ne 3000 ]; then
 		echo "  decreasing tunnel MTU didn't decrease route exception PMTU"
@@ -153,7 +202,7 @@ test_pmtu_vti6_exception() {
 	fi
 
 	# Increase tunnel MTU, check for PMTU increase in route exception
-	mtu "${ns_a}" vti_a 9000
+	mtu "${ns_a}" vti6_a 9000
 	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" -ne 9000 ]; then
 		echo "  increasing tunnel MTU didn't increase route exception PMTU"
 		return 0
@@ -162,6 +211,20 @@ test_pmtu_vti6_exception() {
 	return 1
 }
 
+test_pmtu_vti4_default_mtu() {
+	setup namespaces veth vti4 && return 2
+
+	# Check that MTU of vti device is MTU of veth minus IPv4 header length
+	veth_mtu="$(link_get_mtu "${ns_a}" veth_a)"
+	vti4_mtu="$(link_get_mtu "${ns_a}" vti4_a)"
+	if [ $((veth_mtu - vti4_mtu)) -ne 20 ]; then
+		echo "  vti MTU ${vti4_mtu} is not veth MTU ${veth_mtu} minus IPv4 header length"
+		return 0
+	fi
+
+	return 1
+}
+
 trap cleanup EXIT
 
 exitcode=0
-- 
2.15.1

[PATCH net-next 5/9] selftests: pmtu: Add pmtu_vti6_default_mtu test

[Stefano Brivio]

Same as pmtu_vti4_default_mtu, but on IPv6 with vti6.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
---
 tools/testing/selftests/net/pmtu.sh | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 440d2defe592..67b77f9108ee 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -18,8 +18,11 @@
 #	endpoints. Check that MTU assigned to vti interface is the MTU of the
 #	lower layer (veth) minus additional lower layer headers (zero, for veth)
 #	minus IPv4 header length
+#
+# - pmtu_vti6_default_mtu
+#	Same as above, for IPv6
 
-tests="pmtu_vti6_exception pmtu_vti4_default_mtu"
+tests="pmtu_vti6_exception pmtu_vti4_default_mtu pmtu_vti6_default_mtu"
 
 NS_A="ns-$(mktemp -u XXXXXX)"
 NS_B="ns-$(mktemp -u XXXXXX)"
@@ -225,6 +228,20 @@ test_pmtu_vti4_default_mtu() {
 	return 1
 }
 
+test_pmtu_vti6_default_mtu() {
+	setup namespaces veth vti6 && return 2
+
+	# Check that MTU of vti device is MTU of veth minus IPv6 header length
+	veth_mtu="$(link_get_mtu "${ns_a}" veth_a)"
+	vti6_mtu="$(link_get_mtu "${ns_a}" vti6_a)"
+	if [ $((veth_mtu - vti6_mtu)) -ne 40 ]; then
+		echo "  vti MTU ${vti6_mtu} is not veth MTU ${veth_mtu} minus IPv6 header length"
+		return 0
+	fi
+
+	return 1
+}
+
 trap cleanup EXIT
 
 exitcode=0
-- 
2.15.1

[PATCH net-next 6/9] selftests: pmtu: Add pmtu_vti4_exception test

[Stefano Brivio]

This test checks that PMTU exceptions are created only when
needed on IPv4 routes with vti and xfrm, and their PMTU value is
checked as well.

We can't adopt the same approach as test_pmtu_vti6_exception()
here, because on IPv4 administrative MTU changes won't be
reflected directly on PMTU.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
---
 tools/testing/selftests/net/pmtu.sh | 84 ++++++++++++++++++++++++++++++++-----
 1 file changed, 74 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 67b77f9108ee..336b8545c4bd 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -6,6 +6,14 @@
 #
 # Tests currently implemented:
 #
+# - 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
+#	created if link layer MTU is not exceeded, then exceed it and check that
+#	exception is created with the expected PMTU. The approach described
+#	below for IPv6 doesn't apply here, because, on IPv4, administrative MTU
+#	changes alone won't affect PMTU
+#
 # - pmtu_vti6_exception
 #	Set up vti6 tunnel on top of veth, with xfrm states and policies, in two
 #	namespaces with matching endpoints. Check that route exception is
@@ -22,7 +30,8 @@
 # - pmtu_vti6_default_mtu
 #	Same as above, for IPv6
 
-tests="pmtu_vti6_exception pmtu_vti4_default_mtu pmtu_vti6_default_mtu"
+tests="pmtu_vti4_exception pmtu_vti6_exception
+       pmtu_vti4_default_mtu pmtu_vti6_default_mtu"
 
 NS_A="ns-$(mktemp -u XXXXXX)"
 NS_B="ns-$(mktemp -u XXXXXX)"
@@ -103,19 +112,33 @@ setup_vti6() {
 }
 
 setup_xfrm() {
-	${ns_a} ip -6 xfrm state add src ${veth6_a_addr} dst ${veth6_b_addr} spi 0x1000 proto esp aead "rfc4106(gcm(aes))" 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel || return 0
-	${ns_a} ip -6 xfrm state add src ${veth6_b_addr} dst ${veth6_a_addr} spi 0x1001 proto esp aead "rfc4106(gcm(aes))" 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
-	${ns_a} ip -6 xfrm policy add dir out mark 10 tmpl src ${veth6_a_addr} dst ${veth6_b_addr} proto esp mode tunnel
-	${ns_a} ip -6 xfrm policy add dir in mark 10 tmpl src ${veth6_b_addr} dst ${veth6_a_addr} proto esp mode tunnel
+	proto=${1}
+	veth_a_addr="${2}"
+	veth_b_addr="${3}"
 
-	${ns_b} ip -6 xfrm state add src ${veth6_a_addr} dst ${veth6_b_addr} spi 0x1000 proto esp aead "rfc4106(gcm(aes))" 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
-	${ns_b} ip -6 xfrm state add src ${veth6_b_addr} dst ${veth6_a_addr} spi 0x1001 proto esp aead "rfc4106(gcm(aes))" 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
-	${ns_b} ip -6 xfrm policy add dir out mark 10 tmpl src ${veth6_b_addr} dst ${veth6_a_addr} proto esp mode tunnel
-	${ns_b} ip -6 xfrm policy add dir in mark 10 tmpl src ${veth6_a_addr} dst ${veth6_b_addr} proto esp mode tunnel
+	${ns_a} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead "rfc4106(gcm(aes))" 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel || return 0
+	${ns_a} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead "rfc4106(gcm(aes))" 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
+	${ns_a} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel
+	${ns_a} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel
+
+	${ns_b} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead "rfc4106(gcm(aes))" 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
+	${ns_b} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead "rfc4106(gcm(aes))" 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
+	${ns_b} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel
+	${ns_b} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel
 
 	return 1
 }
 
+setup_xfrm4() {
+	setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr}
+	return $?
+}
+
+setup_xfrm6() {
+	setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr}
+	return $?
+}
+
 setup() {
 	[ "$(id -u)" -ne 0 ] && echo "  need to run as root" && return 0
 
@@ -180,8 +203,49 @@ route_get_dst_pmtu_from_exception() {
 	mtu_parse "$(route_get_dst_exception "${ns_cmd}" ${dst})"
 }
 
+test_pmtu_vti4_exception() {
+	setup namespaces veth vti4 xfrm4 && return 2
+
+	veth_mtu=1500
+	vti_mtu=$((veth_mtu - 20))
+
+	#                                SPI   SN   IV  ICV   pad length   next header
+	esp_payload_rfc4106=$((vti_mtu - 4   - 4  - 8 - 16  - 1          - 1))
+	ping_payload=$((esp_payload_rfc4106 - 28))
+
+	mtu "${ns_a}" veth_a ${veth_mtu}
+	mtu "${ns_b}" veth_b ${veth_mtu}
+	mtu "${ns_a}" vti4_a ${vti_mtu}
+	mtu "${ns_b}" vti4_b ${vti_mtu}
+
+	# Send DF packet without exceeding link layer MTU, check that no
+	# 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
+		echo "  unexpected exception created with PMTU ${pmtu} for IP payload length ${esp_payload_rfc4106}"
+		return 0
+	fi
+
+	# Now exceed link layer MTU by one byte, check that exception is created
+	${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
+		echo "  exception not created for IP payload length $((esp_payload_rfc4106 + 1))"
+		return 0
+	fi
+
+	# ...with the right PMTU value
+	if [ ${pmtu} -ne ${esp_payload_rfc4106} ]; then
+		echo "  wrong PMTU ${pmtu} in exception, expected: ${esp_payload_rfc4106}"
+		return 0
+	fi
+
+	return 1
+}
+
 test_pmtu_vti6_exception() {
-	setup namespaces veth vti6 xfrm && return 2
+	setup namespaces veth vti6 xfrm6 && return 2
 
 	# Create route exception by exceeding link layer MTU
 	mtu "${ns_a}" veth_a 4000
-- 
2.15.1

[PATCH net-next 7/9] selftests: pmtu: Add pmtu_vti4_link_add_mtu test

[Stefano Brivio]

This test checks that MTU given on vti link creation is actually
configured, and that tunnel is not created with an invalid MTU.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
---
 tools/testing/selftests/net/pmtu.sh | 45 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 44 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 336b8545c4bd..2a7ada49d0c0 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -29,9 +29,14 @@
 #
 # - pmtu_vti6_default_mtu
 #	Same as above, for IPv6
+#
+# - pmtu_vti4_link_add_mtu
+#	Set up vti4 interface passing MTU value at link creation, check MTU is
+#	configured, and that link is not created with invalid MTU values
 
 tests="pmtu_vti4_exception pmtu_vti6_exception
-       pmtu_vti4_default_mtu pmtu_vti6_default_mtu"
+       pmtu_vti4_default_mtu pmtu_vti6_default_mtu
+       pmtu_vti4_link_add_mtu"
 
 NS_A="ns-$(mktemp -u XXXXXX)"
 NS_B="ns-$(mktemp -u XXXXXX)"
@@ -306,6 +311,44 @@ test_pmtu_vti6_default_mtu() {
 	return 1
 }
 
+test_pmtu_vti4_link_add_mtu() {
+	setup namespaces && return 2
+
+	${ns_a} ip link add vti4_a type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10
+	[ $? -ne 0 ] && echo "  vti not supported" && return 2
+	${ns_a} ip link del vti4_a
+
+	pass=1
+
+	min=68
+	max=$((65528 - 20))
+	# Check invalid values first
+	for v in $((min - 1)) $((max + 1)); do
+		${ns_a} ip link add vti4_a mtu ${v} type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10 2>/dev/null
+		# This can fail, or MTU can be adjusted to a proper value
+		[ $? -ne 0 ] && continue
+		mtu="$(link_get_mtu "${ns_a}" vti4_a)"
+		if [ ${mtu} -lt ${min} -o ${mtu} -gt ${max} ]; then
+			echo "  vti tunnel created with invalid MTU ${mtu}"
+			pass=0
+		fi
+		${ns_a} ip link del vti4_a
+	done
+
+	# Now check valid values
+	for v in ${min} 1300 ${max}; do
+		${ns_a} ip link add vti4_a mtu ${v} type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10
+		mtu="$(link_get_mtu "${ns_a}" vti4_a)"
+		${ns_a} ip link del vti4_a
+		if [ "${mtu}" != "${v}" ]; then
+			echo "  vti MTU ${mtu} doesn't match configured value ${v}"
+			pass=0
+		fi
+	done
+
+	return ${pass}
+}
+
 trap cleanup EXIT
 
 exitcode=0
-- 
2.15.1

[PATCH net-next 8/9] selftests: pmtu: Add pmtu_vti6_link_add_mtu test

[Stefano Brivio]

Same as pmtu_vti4_link_add_mtu test, but for IPv6.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
---
 tools/testing/selftests/net/pmtu.sh | 43 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 42 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 2a7ada49d0c0..aad9f880c8ee 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -33,10 +33,13 @@
 # - pmtu_vti4_link_add_mtu
 #	Set up vti4 interface passing MTU value at link creation, check MTU is
 #	configured, and that link is not created with invalid MTU values
+#
+# - pmtu_vti6_link_add_mtu
+#	Same as above, for IPv6
 
 tests="pmtu_vti4_exception pmtu_vti6_exception
        pmtu_vti4_default_mtu pmtu_vti6_default_mtu
-       pmtu_vti4_link_add_mtu"
+       pmtu_vti4_link_add_mtu pmtu_vti6_link_add_mtu"
 
 NS_A="ns-$(mktemp -u XXXXXX)"
 NS_B="ns-$(mktemp -u XXXXXX)"
@@ -349,6 +352,44 @@ test_pmtu_vti4_link_add_mtu() {
 	return ${pass}
 }
 
+test_pmtu_vti6_link_add_mtu() {
+	setup namespaces && return 2
+
+	${ns_a} ip link add vti6_a type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10
+	[ $? -ne 0 ] && echo "  vti6 not supported" && return 2
+	${ns_a} ip link del vti6_a
+
+	pass=1
+
+	min=1280
+	max=$((65535 - 40))
+	# Check invalid values first
+	for v in $((min - 1)) $((max + 1)); do
+		${ns_a} ip link add vti6_a mtu ${v} type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10 2>/dev/null
+		# This can fail, or MTU can be adjusted to a proper value
+		[ $? -ne 0 ] && continue
+		mtu="$(link_get_mtu "${ns_a}" vti6_a)"
+		if [ ${mtu} -lt ${min} -o ${mtu} -gt ${max} ]; then
+			echo "  vti6 tunnel created with invalid MTU ${v}"
+			pass=0
+		fi
+		${ns_a} ip link del vti6_a
+	done
+
+	# Now check valid values
+	for v in 1280 1300 $((65535 - 40)); do
+		${ns_a} ip link add vti6_a mtu ${v} type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10
+		mtu="$(link_get_mtu "${ns_a}" vti6_a)"
+		${ns_a} ip link del vti6_a
+		if [ "${mtu}" != "${v}" ]; then
+			echo "  vti6 MTU ${mtu} doesn't match configured value ${v}"
+			pass=0
+		fi
+	done
+
+	return ${pass}
+}
+
 trap cleanup EXIT
 
 exitcode=0
-- 
2.15.1

[PATCH net-next 9/9] selftests: pmtu: Add pmtu_vti6_link_change_mtu test

[Stefano Brivio]

This test checks that MTU configured from userspace is used on
link creation and changes, and that when it's not passed from
userspace, it's calculated properly from the MTU of the lower
layer.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
---
 tools/testing/selftests/net/pmtu.sh | 58 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 57 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index aad9f880c8ee..937cabe5b969 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -36,10 +36,17 @@
 #
 # - pmtu_vti6_link_add_mtu
 #	Same as above, for IPv6
+#
+# - pmtu_vti6_link_change_mtu
+#	Set up two dummy interfaces with different MTUs, create a vti6 tunnel
+#	and check that configured MTU is used on link creation and changes, and
+#	that MTU is properly calculated instead when MTU is not configured from
+#	userspace
 
 tests="pmtu_vti4_exception pmtu_vti6_exception
        pmtu_vti4_default_mtu pmtu_vti6_default_mtu
-       pmtu_vti4_link_add_mtu pmtu_vti6_link_add_mtu"
+       pmtu_vti4_link_add_mtu pmtu_vti6_link_add_mtu
+       pmtu_vti6_link_change_mtu"
 
 NS_A="ns-$(mktemp -u XXXXXX)"
 NS_B="ns-$(mktemp -u XXXXXX)"
@@ -60,6 +67,10 @@ vti6_a_addr="fd00:2::a"
 vti6_b_addr="fd00:2::b"
 vti6_mask="64"
 
+dummy6_0_addr="fc00:1000::0"
+dummy6_1_addr="fc00:1001::0"
+dummy6_mask="64"
+
 cleanup_done=1
 
 setup_namespaces() {
@@ -390,6 +401,51 @@ test_pmtu_vti6_link_add_mtu() {
 	return ${pass}
 }
 
+test_pmtu_vti6_link_change_mtu() {
+	setup namespaces && return 2
+
+	${ns_a} ip link add dummy0 mtu 1500 type dummy
+	[ $? -ne 0 ] && echo "  dummy not supported" && return 2
+	${ns_a} ip link add dummy1 mtu 3000 type dummy
+	${ns_a} ip link set dummy0 up
+	${ns_a} ip link set dummy1 up
+
+	${ns_a} ip addr add ${dummy6_0_addr}/${dummy6_mask} dev dummy0
+	${ns_a} ip addr add ${dummy6_1_addr}/${dummy6_mask} dev dummy1
+
+	pass=1
+
+	# Create vti6 interface bound to device, passing MTU, check it
+	echo "${ns_a} ip link add vti6_a mtu 1300 type vti6 remote ${dummy6_0_addr} local ${dummy6_0_addr}" > /dev/kmsg
+	${ns_a} ip link add vti6_a mtu 1300 type vti6 remote ${dummy6_0_addr} local ${dummy6_0_addr}
+	mtu="$(link_get_mtu "${ns_a}" vti6_a)"
+	if [ ${mtu} -ne 1300 ]; then
+		echo "  vti6 MTU ${mtu} doesn't match configured value 1300"
+		pass=0
+	fi
+
+	# Move to another device with different MTU, without passing MTU, check
+	# MTU is adjusted
+	echo "${ns_a} ip link set vti6_a type vti6 remote ${dummy6_1_addr} local ${dummy6_1_addr}" > /dev/kmsg
+	${ns_a} ip link set vti6_a type vti6 remote ${dummy6_1_addr} local ${dummy6_1_addr}
+	mtu="$(link_get_mtu "${ns_a}" vti6_a)"
+	if [ ${mtu} -ne $((3000 - 40)) ]; then
+		echo "  vti MTU ${mtu} is not dummy MTU 3000 minus IPv6 header length"
+		pass=0
+	fi
+
+	# Move it back, passing MTU, check MTU is not overridden
+	echo "${ns_a} ip link set vti6_a mtu 1280 type vti6 remote ${dummy6_0_addr} local ${dummy6_0_addr}" > /dev/kmsg
+	${ns_a} ip link set vti6_a mtu 1280 type vti6 remote ${dummy6_0_addr} local ${dummy6_0_addr}
+	mtu="$(link_get_mtu "${ns_a}" vti6_a)"
+	if [ ${mtu} -ne 1280 ]; then
+		echo "  vti6 MTU ${mtu} doesn't match configured value 1280"
+		pass=0
+	fi
+
+	return ${pass}
+}
+
 trap cleanup EXIT
 
 exitcode=0
-- 
2.15.1