From 6f9a50691055618b1042ead4d84f80755d1b9315 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:07 +0000
Subject: [PATCH 01/18] net: skb_scrub_packet(): Scrub offload_fwd_mark

When a packet is trapped and the corresponding SKB marked as
already-forwarded, it retains this marking even after it is forwarded
across veth links into another bridge. There, since it ingresses the
bridge over veth, which doesn't have offload_fwd_mark, it triggers a
warning in nbp_switchdev_frame_mark().

Then nbp_switchdev_allowed_egress() decides not to allow egress from
this bridge through another veth, because the SKB is already marked, and
the mark (of 0) of course matches. Thus the packet is incorrectly
blocked.

Solve by resetting offload_fwd_mark() in skb_scrub_packet(). That
function is called from tunnels and also from veth, and thus catches the
cases where traffic is forwarded between bridges and transformed in a
way that invalidates the marking.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Suggested-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a1be7f19d998..9a8a72cefe9b 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4882,6 +4882,11 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 	nf_reset(skb);
 	nf_reset_trace(skb);
 
+#ifdef CONFIG_NET_SWITCHDEV
+	skb->offload_fwd_mark = 0;
+	skb->offload_mr_fwd_mark = 0;
+#endif
+
 	if (!xnet)
 		return;
 

From 601bc1c13916899a14e682ada3dfa3ec21b13318 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:08 +0000
Subject: [PATCH 02/18] selftests: forwarding: lib: Support NUM_NETIFS of 0

So far the case of NUM_NETIFS of 0 has not been interesting. However if
one wishes to reuse the lib.sh routines in a setup of a separate
namespace, being able to import like this is handy.

Therefore replace the {1..$NUM_NETIFS} references, which cause iteration
over 1 and 0, with an explicit for loop like we do in setup_wait() and
tc_offload_check(), so that for NUM_NETIFS of 0 no iteration is done.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 85d253546684..bb0e9fdf893e 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -104,7 +104,7 @@ create_netif_veth()
 {
 	local i
 
-	for i in $(eval echo {1..$NUM_NETIFS}); do
+	for ((i = 1; i <= NUM_NETIFS; ++i)); do
 		local j=$((i+1))
 
 		ip link show dev ${NETIFS[p$i]} &> /dev/null
@@ -135,7 +135,7 @@ if [[ "$NETIF_CREATE" = "yes" ]]; then
 	create_netif
 fi
 
-for i in $(eval echo {1..$NUM_NETIFS}); do
+for ((i = 1; i <= NUM_NETIFS; ++i)); do
 	ip link show dev ${NETIFS[p$i]} &> /dev/null
 	if [[ $? -ne 0 ]]; then
 		echo "SKIP: could not find all required interfaces"

From d0540d1706c3cfbb51769de02858f846d3836389 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:10 +0000
Subject: [PATCH 03/18] selftests: forwarding: lib: Add in_ns()

In order to run a certain command inside another network namespace, it's
possible to use "ip netns exec ns command". However then one can't use
functions defined in lib.sh or a test suite.

One option is to do "ip netns exec ns bash -c command", provided that
all functions that one wishes to use (and their dependencies) are
published using "export -f". That may not be practical.

Therefore, introduce a helper in_ns(), which wraps a given command in a
boilerplate of "ip netns exec" and "source lib.sh", thus making all
library functions available. (Custom functions that a script wishes to
run within a namespace still need to be exported.)

Because quotes in "$@" aren't recognized in heredoc, hand-expand the
array in an explicit for loop, leveraging printf %q to handle proper
quoting.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index bb0e9fdf893e..93d6e9df483e 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -783,6 +783,17 @@ multipath_eval()
 	log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio"
 }
 
+in_ns()
+{
+	local name=$1; shift
+
+	ip netns exec $name bash <<-EOF
+		NUM_NETIFS=0
+		source lib.sh
+		$(for a in "$@"; do printf "%q${IFS:0:1}" "$a"; done)
+	EOF
+}
+
 ##############################################################################
 # Tests
 

From 58c7a2d19e90a6ec3fbe6cd0c6b1025b731bc000 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:11 +0000
Subject: [PATCH 04/18] selftests: forwarding: ping{6, }_test(): Add
 description argument

Have ping_test() recognize an optional argument with a description of
the test. This is handy if there are several ping test, to make it clear
which is which.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 93d6e9df483e..fa734ddce2e9 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -813,7 +813,7 @@ ping_test()
 
 	ping_do $1 $2
 	check_err $?
-	log_test "ping"
+	log_test "ping$3"
 }
 
 ping6_do()
@@ -832,7 +832,7 @@ ping6_test()
 
 	ping6_do $1 $2
 	check_err $?
-	log_test "ping6"
+	log_test "ping6$3"
 }
 
 learning_test()

From d20b0f214aa74a3f6b28b8d522f273e1fd2abea3 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:12 +0000
Subject: [PATCH 05/18] selftests: forwarding: ping{6, }_do(): Allow passing
 ping arguments

Make the ping routine more generic by allowing passing arbitrary ping
command-line arguments.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index fa734ddce2e9..e916663a1019 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -801,10 +801,11 @@ ping_do()
 {
 	local if_name=$1
 	local dip=$2
+	local args=$3
 	local vrf_name
 
 	vrf_name=$(master_name_get $if_name)
-	ip vrf exec $vrf_name $PING $dip -c 10 -i 0.1 -w 2 &> /dev/null
+	ip vrf exec $vrf_name $PING $args $dip -c 10 -i 0.1 -w 2 &> /dev/null
 }
 
 ping_test()
@@ -820,10 +821,11 @@ ping6_do()
 {
 	local if_name=$1
 	local dip=$2
+	local args=$3
 	local vrf_name
 
 	vrf_name=$(master_name_get $if_name)
-	ip vrf exec $vrf_name $PING6 $dip -c 10 -i 0.1 -w 2 &> /dev/null
+	ip vrf exec $vrf_name $PING6 $args $dip -c 10 -i 0.1 -w 2 &> /dev/null
 }
 
 ping6_test()

From d1038cd0f67e542f2744782f958b95c4909fb63a Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:13 +0000
Subject: [PATCH 06/18] selftests: forwarding: lib: Add
 link_stats_rx_errors_get()

Such a function will be useful for counting malformed packets in the ECN
decap test.

To that end, introduce a common handler for handling stat-fetching, and
reuse it in link_stats_tx_packets_get() and link_stats_rx_errors_get().

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index e916663a1019..7af5a03bcb32 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -477,11 +477,24 @@ master_name_get()
 	ip -j link show dev $if_name | jq -r '.[]["master"]'
 }
 
+link_stats_get()
+{
+	local if_name=$1; shift
+	local dir=$1; shift
+	local stat=$1; shift
+
+	ip -j -s link show dev $if_name \
+		| jq '.[]["stats64"]["'$dir'"]["'$stat'"]'
+}
+
 link_stats_tx_packets_get()
 {
-       local if_name=$1
+	link_stats_get $1 tx packets
+}
 
-       ip -j -s link show dev $if_name | jq '.[]["stats64"]["tx"]["packets"]'
+link_stats_rx_errors_get()
+{
+	link_stats_get $1 rx errors
 }
 
 tc_rule_stats_get()

From fd64d5a2e383568bb0d6b7b8c619358e68b6718c Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:14 +0000
Subject: [PATCH 07/18] selftests: forwarding: Add a skeleton of
 vxlan_bridge_1d

This skeleton sets up a topology with three VXLAN endpoints: one
"local", possibly offloaded, and two "remote", formed using veth pairs
and likely purely software bridges. The "local" endpoint is connected to
host systems by a VLAN-unaware bridge.

Since VXLAN tunnels must be unique per namespace, each of the "remote"
endpoints is in its own namespace. H3 forms the bridge between the three
domains.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/vxlan_bridge_1d.sh         | 296 ++++++++++++++++++
 1 file changed, 296 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
new file mode 100755
index 000000000000..af88e1c146a7
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -0,0 +1,296 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +--------------------+                               +----------------------+
+# | H1 (vrf)           |                               |             H2 (vrf) |
+# |    + $h1           |                               |  + $h2               |
+# |    | 192.0.2.1/28  |                               |  | 192.0.2.2/28      |
+# +----|---------------+                               +--|-------------------+
+#      |                                                  |
+# +----|--------------------------------------------------|-------------------+
+# | SW |                                                  |                   |
+# | +--|--------------------------------------------------|-----------------+ |
+# | |  + $swp1                   BR1 (802.1d)             + $swp2           | |
+# | |                                                                       | |
+# | |  + vx1 (vxlan)                                                        | |
+# | |    local 192.0.2.17                                                   | |
+# | |    remote 192.0.2.34 192.0.2.50                                       | |
+# | |    id 1000 dstport $VXPORT                                            | |
+# | +-----------------------------------------------------------------------+ |
+# |                                                                           |
+# |  192.0.2.32/28 via 192.0.2.18                                             |
+# |  192.0.2.48/28 via 192.0.2.18                                             |
+# |                                                                           |
+# |    + $rp1                                                                 |
+# |    | 192.0.2.17/28                                                        |
+# +----|----------------------------------------------------------------------+
+#      |
+# +----|--------------------------------------------------------+
+# |    |                                             VRP2 (vrf) |
+# |    + $rp2                                                   |
+# |      192.0.2.18/28                                          |
+# |                                                             |   (maybe) HW
+# =============================================================================
+# |                                                             |  (likely) SW
+# |    + v1 (veth)                             + v3 (veth)      |
+# |    | 192.0.2.33/28                         | 192.0.2.49/28  |
+# +----|---------------------------------------|----------------+
+#      |                                       |
+# +----|------------------------------+   +----|------------------------------+
+# |    + v2 (veth)        NS1 (netns) |   |    + v4 (veth)        NS2 (netns) |
+# |      192.0.2.34/28                |   |      192.0.2.50/28                |
+# |                                   |   |                                   |
+# |   192.0.2.16/28 via 192.0.2.33    |   |   192.0.2.16/28 via 192.0.2.49    |
+# |   192.0.2.50/32 via 192.0.2.33    |   |   192.0.2.34/32 via 192.0.2.49    |
+# |                                   |   |                                   |
+# | +-------------------------------+ |   | +-------------------------------+ |
+# | |                  BR2 (802.1d) | |   | |                  BR2 (802.1d) | |
+# | |  + vx2 (vxlan)                | |   | |  + vx2 (vxlan)                | |
+# | |    local 192.0.2.34           | |   | |    local 192.0.2.50           | |
+# | |    remote 192.0.2.17          | |   | |    remote 192.0.2.17          | |
+# | |    remote 192.0.2.50          | |   | |    remote 192.0.2.34          | |
+# | |    id 1000 dstport $VXPORT    | |   | |    id 1000 dstport $VXPORT    | |
+# | |                               | |   | |                               | |
+# | |  + w1 (veth)                  | |   | |  + w1 (veth)                  | |
+# | +--|----------------------------+ |   | +--|----------------------------+ |
+# |    |                              |   |    |                              |
+# | +--|----------------------------+ |   | +--|----------------------------+ |
+# | |  |                  VW2 (vrf) | |   | |  |                  VW2 (vrf) | |
+# | |  + w2 (veth)                  | |   | |  + w2 (veth)                  | |
+# | |    192.0.2.3/28               | |   | |    192.0.2.4/28               | |
+# | +-------------------------------+ |   | +-------------------------------+ |
+# +-----------------------------------+   +-----------------------------------+
+
+: ${VXPORT:=4789}
+export VXPORT
+
+: ${ALL_TESTS:="
+    "}
+
+NUM_NETIFS=6
+source lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/28
+	tc qdisc add dev $h1 clsact
+}
+
+h1_destroy()
+{
+	tc qdisc del dev $h1 clsact
+	simple_if_fini $h1 192.0.2.1/28
+}
+
+h2_create()
+{
+	simple_if_init $h2 192.0.2.2/28
+	tc qdisc add dev $h2 clsact
+}
+
+h2_destroy()
+{
+	tc qdisc del dev $h2 clsact
+	simple_if_fini $h2 192.0.2.2/28
+}
+
+rp1_set_addr()
+{
+	ip address add dev $rp1 192.0.2.17/28
+
+	ip route add 192.0.2.32/28 nexthop via 192.0.2.18
+	ip route add 192.0.2.48/28 nexthop via 192.0.2.18
+}
+
+rp1_unset_addr()
+{
+	ip route del 192.0.2.48/28 nexthop via 192.0.2.18
+	ip route del 192.0.2.32/28 nexthop via 192.0.2.18
+
+	ip address del dev $rp1 192.0.2.17/28
+}
+
+switch_create()
+{
+	ip link add name br1 type bridge vlan_filtering 0 mcast_snooping 0
+	# Make sure the bridge uses the MAC address of the local port and not
+	# that of the VxLAN's device.
+	ip link set dev br1 address $(mac_get $swp1)
+	ip link set dev br1 up
+
+	ip link set dev $rp1 up
+	rp1_set_addr
+
+	ip link add name vx1 type vxlan id 1000		\
+		local 192.0.2.17 dstport "$VXPORT"	\
+		nolearning noudpcsum tos inherit ttl 100
+	ip link set dev vx1 up
+
+	ip link set dev vx1 master br1
+	ip link set dev $swp1 master br1
+	ip link set dev $swp1 up
+
+	ip link set dev $swp2 master br1
+	ip link set dev $swp2 up
+
+	bridge fdb append dev vx1 00:00:00:00:00:00 dst 192.0.2.34 self
+	bridge fdb append dev vx1 00:00:00:00:00:00 dst 192.0.2.50 self
+}
+
+switch_destroy()
+{
+	rp1_unset_addr
+	ip link set dev $rp1 down
+
+	bridge fdb del dev vx1 00:00:00:00:00:00 dst 192.0.2.50 self
+	bridge fdb del dev vx1 00:00:00:00:00:00 dst 192.0.2.34 self
+
+	ip link set dev vx1 nomaster
+	ip link set dev vx1 down
+	ip link del dev vx1
+
+	ip link set dev $swp2 down
+	ip link set dev $swp2 nomaster
+
+	ip link set dev $swp1 down
+	ip link set dev $swp1 nomaster
+
+	ip link set dev br1 down
+	ip link del dev br1
+}
+
+vrp2_create()
+{
+	simple_if_init $rp2 192.0.2.18/28
+	__simple_if_init v1 v$rp2 192.0.2.33/28
+	__simple_if_init v3 v$rp2 192.0.2.49/28
+	tc qdisc add dev v1 clsact
+}
+
+vrp2_destroy()
+{
+	tc qdisc del dev v1 clsact
+	__simple_if_fini v3 192.0.2.49/28
+	__simple_if_fini v1 192.0.2.33/28
+	simple_if_fini $rp2 192.0.2.18/28
+}
+
+ns_init_common()
+{
+	local in_if=$1; shift
+	local in_addr=$1; shift
+	local other_in_addr=$1; shift
+	local nh_addr=$1; shift
+	local host_addr=$1; shift
+
+	ip link set dev $in_if up
+	ip address add dev $in_if $in_addr/28
+	tc qdisc add dev $in_if clsact
+
+	ip link add name br2 type bridge vlan_filtering 0
+	ip link set dev br2 up
+
+	ip link add name w1 type veth peer name w2
+
+	ip link set dev w1 master br2
+	ip link set dev w1 up
+
+	ip link add name vx2 type vxlan id 1000 local $in_addr dstport "$VXPORT"
+	ip link set dev vx2 up
+	bridge fdb append dev vx2 00:00:00:00:00:00 dst 192.0.2.17 self
+	bridge fdb append dev vx2 00:00:00:00:00:00 dst $other_in_addr self
+
+	ip link set dev vx2 master br2
+	tc qdisc add dev vx2 clsact
+
+	simple_if_init w2 $host_addr/28
+
+	ip route add 192.0.2.16/28 nexthop via $nh_addr
+	ip route add $other_in_addr/32 nexthop via $nh_addr
+}
+export -f ns_init_common
+
+ns1_create()
+{
+	ip netns add ns1
+	ip link set dev v2 netns ns1
+	in_ns ns1 \
+	      ns_init_common v2 192.0.2.34 192.0.2.50 192.0.2.33 192.0.2.3
+}
+
+ns1_destroy()
+{
+	ip netns exec ns1 ip link set dev v2 netns 1
+	ip netns del ns1
+}
+
+ns2_create()
+{
+	ip netns add ns2
+	ip link set dev v4 netns ns2
+	in_ns ns2 \
+	      ns_init_common v4 192.0.2.50 192.0.2.34 192.0.2.49 192.0.2.4
+}
+
+ns2_destroy()
+{
+	ip netns exec ns2 ip link set dev v4 netns 1
+	ip netns del ns2
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	rp1=${NETIFS[p5]}
+	rp2=${NETIFS[p6]}
+
+	vrf_prepare
+	forwarding_enable
+
+	h1_create
+	h2_create
+	switch_create
+
+	ip link add name v1 type veth peer name v2
+	ip link add name v3 type veth peer name v4
+	vrp2_create
+	ns1_create
+	ns2_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ns2_destroy
+	ns1_destroy
+	vrp2_destroy
+	ip link del dev v3
+	ip link del dev v1
+
+	switch_destroy
+	h2_destroy
+	h1_destroy
+
+	forwarding_restore
+	vrf_cleanup
+}
+
+test_all()
+{
+	echo "Running tests with UDP port $VXPORT"
+	tests_run
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+test_all
+
+exit $EXIT_STATUS

From 5852fd07c441bc7c2e720440d8df2e2b80aea58b Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:15 +0000
Subject: [PATCH 08/18] selftests: forwarding: vxlan_bridge_1d: Add ping test

Test end-to-end reachability between local and remote endpoints.

Note that because learning is disabled on the VXLAN device, the ICMP
requests will end up being flooded to all remotes.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index af88e1c146a7..0e3d7abc70d3 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -65,6 +65,7 @@
 export VXPORT
 
 : ${ALL_TESTS:="
+	ping_ipv4
     "}
 
 NUM_NETIFS=6
@@ -281,6 +282,13 @@ cleanup()
 	vrf_cleanup
 }
 
+ping_ipv4()
+{
+	ping_test $h1 192.0.2.2 ": local->local"
+	ping_test $h1 192.0.2.3 ": local->remote 1"
+	ping_test $h1 192.0.2.4 ": local->remote 2"
+}
+
 test_all()
 {
 	echo "Running tests with UDP port $VXPORT"

From edaa117efe46845e17275c51f61591df15d9e9a9 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:17 +0000
Subject: [PATCH 09/18] selftests: forwarding: vxlan_bridge_1d: Add flood test

Test that when sending traffic to an unlearned MAC address, the traffic
is flooded to both remote VXLAN endpoints.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/vxlan_bridge_1d.sh         | 105 ++++++++++++++++++
 1 file changed, 105 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index 0e3d7abc70d3..1edd5189c41c 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -66,6 +66,7 @@ export VXPORT
 
 : ${ALL_TESTS:="
 	ping_ipv4
+	test_flood
     "}
 
 NUM_NETIFS=6
@@ -289,6 +290,110 @@ ping_ipv4()
 	ping_test $h1 192.0.2.4 ": local->remote 2"
 }
 
+maybe_in_ns()
+{
+	echo ${1:+in_ns} $1
+}
+
+__flood_counter_add_del()
+{
+	local add_del=$1; shift
+	local dev=$1; shift
+	local ns=$1; shift
+
+	# Putting the ICMP capture both to HW and to SW will end up
+	# double-counting the packets that are trapped to slow path, such as for
+	# the unicast test. Adding either skip_hw or skip_sw fixes this problem,
+	# but with skip_hw, the flooded packets are not counted at all, because
+	# those are dropped due to MAC address mismatch; and skip_sw is a no-go
+	# for veth-based topologies.
+	#
+	# So try to install with skip_sw and fall back to skip_sw if that fails.
+
+	$(maybe_in_ns $ns) __icmp_capture_add_del          \
+			   $add_del 100 "" $dev skip_sw 2>/dev/null || \
+	$(maybe_in_ns $ns) __icmp_capture_add_del          \
+			   $add_del 100 "" $dev skip_hw
+}
+
+flood_counter_install()
+{
+	__flood_counter_add_del add "$@"
+}
+
+flood_counter_uninstall()
+{
+	__flood_counter_add_del del "$@"
+}
+
+flood_fetch_stat()
+{
+	local dev=$1; shift
+	local ns=$1; shift
+
+	$(maybe_in_ns $ns) tc_rule_stats_get $dev 100 ingress
+}
+
+flood_fetch_stats()
+{
+	local counters=("${@}")
+	local counter
+
+	for counter in "${counters[@]}"; do
+		flood_fetch_stat $counter
+	done
+}
+
+vxlan_flood_test()
+{
+	local mac=$1; shift
+	local dst=$1; shift
+	local -a expects=("${@}")
+
+	local -a counters=($h2 "vx2 ns1" "vx2 ns2")
+	local counter
+	local key
+
+	for counter in "${counters[@]}"; do
+		flood_counter_install $counter
+	done
+
+	local -a t0s=($(flood_fetch_stats "${counters[@]}"))
+	$MZ $h1 -c 10 -d 100msec -p 64 -b $mac -B $dst -t icmp -q
+	sleep 1
+	local -a t1s=($(flood_fetch_stats "${counters[@]}"))
+
+	for key in ${!t0s[@]}; do
+		local delta=$((t1s[$key] - t0s[$key]))
+		local expect=${expects[$key]}
+
+		((expect == delta))
+		check_err $? "${counters[$key]}: Expected to capture $expect packets, got $delta."
+	done
+
+	for counter in "${counters[@]}"; do
+		flood_counter_uninstall $counter
+	done
+}
+
+__test_flood()
+{
+	local mac=$1; shift
+	local dst=$1; shift
+	local what=$1; shift
+
+	RET=0
+
+	vxlan_flood_test $mac $dst 10 10 10
+
+	log_test "VXLAN: $what"
+}
+
+test_flood()
+{
+	__test_flood de:ad:be:ef:13:37 192.0.2.100 "flood"
+}
+
 test_all()
 {
 	echo "Running tests with UDP port $VXPORT"

From bfd1e27038ab7e9ee3f730667cd0ae0e0eb23f88 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:18 +0000
Subject: [PATCH 10/18] selftests: forwarding: vxlan_bridge_1d: Add unicast
 test

Test that when sending traffic to a learned MAC address, the traffic is
forwarded accurately only to the right endpoint.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/vxlan_bridge_1d.sh         | 54 +++++++++++++++++++
 1 file changed, 54 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index 1edd5189c41c..1a3486ec1d21 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -67,6 +67,7 @@ export VXPORT
 : ${ALL_TESTS:="
 	ping_ipv4
 	test_flood
+	test_unicast
     "}
 
 NUM_NETIFS=6
@@ -263,6 +264,10 @@ setup_prepare()
 	vrp2_create
 	ns1_create
 	ns2_create
+
+	r1_mac=$(in_ns ns1 mac_get w2)
+	r2_mac=$(in_ns ns2 mac_get w2)
+	h2_mac=$(mac_get $h2)
 }
 
 cleanup()
@@ -394,6 +399,55 @@ test_flood()
 	__test_flood de:ad:be:ef:13:37 192.0.2.100 "flood"
 }
 
+vxlan_fdb_add_del()
+{
+	local add_del=$1; shift
+	local mac=$1; shift
+	local dev=$1; shift
+	local dst=$1; shift
+
+	bridge fdb $add_del dev $dev $mac self static permanent \
+		${dst:+dst} $dst 2>/dev/null
+	bridge fdb $add_del dev $dev $mac master static 2>/dev/null
+}
+
+__test_unicast()
+{
+	local mac=$1; shift
+	local dst=$1; shift
+	local hit_idx=$1; shift
+	local what=$1; shift
+
+	RET=0
+
+	local -a expects=(0 0 0)
+	expects[$hit_idx]=10
+
+	vxlan_flood_test $mac $dst "${expects[@]}"
+
+	log_test "VXLAN: $what"
+}
+
+test_unicast()
+{
+	local -a targets=("$h2_mac $h2"
+			  "$r1_mac vx1 192.0.2.34"
+			  "$r2_mac vx1 192.0.2.50")
+	local target
+
+	for target in "${targets[@]}"; do
+		vxlan_fdb_add_del add $target
+	done
+
+	__test_unicast $h2_mac 192.0.2.2 0 "local MAC unicast"
+	__test_unicast $r1_mac 192.0.2.3 1 "remote MAC 1 unicast"
+	__test_unicast $r2_mac 192.0.2.4 2 "remote MAC 2 unicast"
+
+	for target in "${targets[@]}"; do
+		vxlan_fdb_add_del del $target
+	done
+}
+
 test_all()
 {
 	echo "Running tests with UDP port $VXPORT"

From 50a02b0825668fe96884d47914fa082c91bda504 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:19 +0000
Subject: [PATCH 11/18] selftests: forwarding: vxlan_bridge_1d: Reconfigure &
 rerun tests

The ordering of the topology creation can have impact on whether a
driver is successful in offloading VXLAN. Therefore add a pseudo-test
that reshuffles bits of the topology, and then reruns the same suite of
tests again to make sure that the new setup is supported as well.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/vxlan_bridge_1d.sh         | 26 +++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index 1a3486ec1d21..a943d8da14b9 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -68,6 +68,10 @@ export VXPORT
 	ping_ipv4
 	test_flood
 	test_unicast
+	reapply_config
+	ping_ipv4
+	test_flood
+	test_unicast
     "}
 
 NUM_NETIFS=6
@@ -288,6 +292,28 @@ cleanup()
 	vrf_cleanup
 }
 
+# For the first round of tests, vx1 is the first device to get attached to the
+# bridge, and that at the point that the local IP is already configured. Try the
+# other scenario of attaching the device to an already-offloaded bridge, and
+# only then attach the local IP.
+reapply_config()
+{
+	echo "Reapplying configuration"
+
+	bridge fdb del dev vx1 00:00:00:00:00:00 dst 192.0.2.50 self
+	bridge fdb del dev vx1 00:00:00:00:00:00 dst 192.0.2.34 self
+	rp1_unset_addr
+	ip link set dev vx1 nomaster
+	sleep 5
+
+	ip link set dev vx1 master br1
+	bridge fdb append dev vx1 00:00:00:00:00:00 dst 192.0.2.34 self
+	bridge fdb append dev vx1 00:00:00:00:00:00 dst 192.0.2.50 self
+	sleep 1
+	rp1_set_addr
+	sleep 5
+}
+
 ping_ipv4()
 {
 	ping_test $h1 192.0.2.2 ": local->local"

From b3a7ee74ee659c789b6e6254d0839789477f5c3e Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:20 +0000
Subject: [PATCH 12/18] selftests: forwarding: vxlan_bridge_1d: Add a TTL test

This tests whether TTL of VXLAN envelope packets is properly set based
on the device configuration.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/vxlan_bridge_1d.sh         | 33 +++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index a943d8da14b9..0c17b0d427ba 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -68,6 +68,7 @@ export VXPORT
 	ping_ipv4
 	test_flood
 	test_unicast
+	test_ttl
 	reapply_config
 	ping_ipv4
 	test_flood
@@ -474,6 +475,38 @@ test_unicast()
 	done
 }
 
+vxlan_ping_test()
+{
+	local ping_dev=$1; shift
+	local ping_dip=$1; shift
+	local ping_args=$1; shift
+	local capture_dev=$1; shift
+	local capture_dir=$1; shift
+	local capture_pref=$1; shift
+	local expect=$1; shift
+
+	local t0=$(tc_rule_stats_get $capture_dev $capture_pref $capture_dir)
+	ping_do $ping_dev $ping_dip "$ping_args"
+	local t1=$(tc_rule_stats_get $capture_dev $capture_pref $capture_dir)
+	local delta=$((t1 - t0))
+
+	# Tolerate a couple stray extra packets.
+	((expect <= delta && delta <= expect + 2))
+	check_err $? "$capture_dev: Expected to capture $expect packets, got $delta."
+}
+
+test_ttl()
+{
+	RET=0
+
+	tc filter add dev v1 egress pref 77 prot ip \
+		flower ip_ttl 99 action pass
+	vxlan_ping_test $h1 192.0.2.3 "" v1 egress 77 10
+	tc filter del dev v1 egress pref 77 prot ip
+
+	log_test "VXLAN: envelope TTL"
+}
+
 test_all()
 {
 	echo "Running tests with UDP port $VXPORT"

From d417ecf533fe014de667705f58ae5c579f7740b9 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:21 +0000
Subject: [PATCH 13/18] selftests: forwarding: vxlan_bridge_1d: Add a TOS test

Test that TOS is inherited from the tunneled packet into the envelope as
configured at the VXLAN device.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/vxlan_bridge_1d.sh    | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index 0c17b0d427ba..ac1070937ae7 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -69,6 +69,7 @@ export VXPORT
 	test_flood
 	test_unicast
 	test_ttl
+	test_tos
 	reapply_config
 	ping_ipv4
 	test_flood
@@ -507,6 +508,19 @@ test_ttl()
 	log_test "VXLAN: envelope TTL"
 }
 
+test_tos()
+{
+	RET=0
+
+	tc filter add dev v1 egress pref 77 prot ip \
+		flower ip_tos 0x40 action pass
+	vxlan_ping_test $h1 192.0.2.3 "-Q 0x40" v1 egress 77 10
+	vxlan_ping_test $h1 192.0.2.3 "-Q 0x30" v1 egress 77 0
+	tc filter del dev v1 egress pref 77 prot ip
+
+	log_test "VXLAN: envelope TOS inheritance"
+}
+
 test_all()
 {
 	echo "Running tests with UDP port $VXPORT"

From 1e5abfb3ff41a532f687875ada9ea2af7a1069b3 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:22 +0000
Subject: [PATCH 14/18] selftests: forwarding: vxlan_bridge_1d: Add an ECN
 encap test

Test that ECN bits in the VXLAN envelope are correctly deduced from the
overlay packet.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/vxlan_bridge_1d.sh         | 26 +++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index ac1070937ae7..82a124cbd523 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -70,6 +70,7 @@ export VXPORT
 	test_unicast
 	test_ttl
 	test_tos
+	test_ecn_encap
 	reapply_config
 	ping_ipv4
 	test_flood
@@ -521,6 +522,31 @@ test_tos()
 	log_test "VXLAN: envelope TOS inheritance"
 }
 
+__test_ecn_encap()
+{
+	local q=$1; shift
+	local tos=$1; shift
+
+	RET=0
+
+	tc filter add dev v1 egress pref 77 prot ip \
+		flower ip_tos $tos action pass
+	sleep 1
+	vxlan_ping_test $h1 192.0.2.3 "-Q $q" v1 egress 77 10
+	tc filter del dev v1 egress pref 77 prot ip
+
+	log_test "VXLAN: ECN encap: $q->$tos"
+}
+
+test_ecn_encap()
+{
+	# In accordance with INET_ECN_encapsulate()
+	__test_ecn_encap 0x00 0x00
+	__test_ecn_encap 0x01 0x01
+	__test_ecn_encap 0x02 0x02
+	__test_ecn_encap 0x03 0x02
+}
+
 test_all()
 {
 	echo "Running tests with UDP port $VXPORT"

From a0b61f3d8ebfe927d596c1aaca9b6e23bd185f55 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:24 +0000
Subject: [PATCH 15/18] selftests: forwarding: vxlan_bridge_1d: Add an ECN
 decap test

Test that when decapsulating from VXLAN, the values of inner and outer
TOS are handled appropriately. Because VXLAN driver on its own won't
produce the arbitrary TOS combinations necessary to test this feature,
simply open-code a single ICMP packet and have mausezahn assemble it.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/vxlan_bridge_1d.sh         | 116 ++++++++++++++++++
 1 file changed, 116 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index 82a124cbd523..5cc6ac74eb74 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -71,6 +71,7 @@ export VXPORT
 	test_ttl
 	test_tos
 	test_ecn_encap
+	test_ecn_decap
 	reapply_config
 	ping_ipv4
 	test_flood
@@ -547,6 +548,121 @@ test_ecn_encap()
 	__test_ecn_encap 0x03 0x02
 }
 
+vxlan_encapped_ping_do()
+{
+	local count=$1; shift
+	local dev=$1; shift
+	local next_hop_mac=$1; shift
+	local dest_ip=$1; shift
+	local dest_mac=$1; shift
+	local inner_tos=$1; shift
+	local outer_tos=$1; shift
+
+	$MZ $dev -c $count -d 100msec -q \
+		-b $next_hop_mac -B $dest_ip \
+		-t udp tos=$outer_tos,sp=23456,dp=$VXPORT,p=$(:
+		    )"08:"$(                      : VXLAN flags
+		    )"00:00:00:"$(                : VXLAN reserved
+		    )"00:03:e8:"$(                : VXLAN VNI
+		    )"00:"$(                      : VXLAN reserved
+		    )"$dest_mac:"$(               : ETH daddr
+		    )"$(mac_get w2):"$(           : ETH saddr
+		    )"08:00:"$(                   : ETH type
+		    )"45:"$(                      : IP version + IHL
+		    )"$inner_tos:"$(              : IP TOS
+		    )"00:54:"$(                   : IP total length
+		    )"99:83:"$(                   : IP identification
+		    )"40:00:"$(                   : IP flags + frag off
+		    )"40:"$(                      : IP TTL
+		    )"01:"$(                      : IP proto
+		    )"00:00:"$(                   : IP header csum
+		    )"c0:00:02:03:"$(             : IP saddr: 192.0.2.3
+		    )"c0:00:02:01:"$(             : IP daddr: 192.0.2.1
+		    )"08:"$(                      : ICMP type
+		    )"00:"$(                      : ICMP code
+		    )"8b:f2:"$(                   : ICMP csum
+		    )"1f:6a:"$(                   : ICMP request identifier
+		    )"00:01:"$(                   : ICMP request sequence number
+		    )"4f:ff:c5:5b:00:00:00:00:"$( : ICMP payload
+		    )"6d:74:0b:00:00:00:00:00:"$( :
+		    )"10:11:12:13:14:15:16:17:"$( :
+		    )"18:19:1a:1b:1c:1d:1e:1f:"$( :
+		    )"20:21:22:23:24:25:26:27:"$( :
+		    )"28:29:2a:2b:2c:2d:2e:2f:"$( :
+		    )"30:31:32:33:34:35:36:37"
+}
+export -f vxlan_encapped_ping_do
+
+vxlan_encapped_ping_test()
+{
+	local ping_dev=$1; shift
+	local nh_dev=$1; shift
+	local ping_dip=$1; shift
+	local inner_tos=$1; shift
+	local outer_tos=$1; shift
+	local stat_get=$1; shift
+	local expect=$1; shift
+
+	local t0=$($stat_get)
+
+	in_ns ns1 \
+		vxlan_encapped_ping_do 10 $ping_dev $(mac_get $nh_dev) \
+			$ping_dip $(mac_get $h1) \
+			$inner_tos $outer_tos
+
+	local t1=$($stat_get)
+	local delta=$((t1 - t0))
+
+	# Tolerate a couple stray extra packets.
+	((expect <= delta && delta <= expect + 2))
+	check_err $? "Expected to capture $expect packets, got $delta."
+}
+export -f vxlan_encapped_ping_test
+
+__test_ecn_decap()
+{
+	local orig_inner_tos=$1; shift
+	local orig_outer_tos=$1; shift
+	local decapped_tos=$1; shift
+
+	RET=0
+
+	tc filter add dev $h1 ingress pref 77 prot ip \
+		flower ip_tos $decapped_tos action pass
+	sleep 1
+	vxlan_encapped_ping_test v2 v1 192.0.2.17 \
+				 $orig_inner_tos $orig_outer_tos \
+				 "tc_rule_stats_get $h1 77 ingress" 10
+	tc filter del dev $h1 ingress pref 77
+
+	log_test "VXLAN: ECN decap: $orig_outer_tos/$orig_inner_tos->$decapped_tos"
+}
+
+test_ecn_decap_error()
+{
+	local orig_inner_tos=00
+	local orig_outer_tos=03
+
+	RET=0
+
+	vxlan_encapped_ping_test v2 v1 192.0.2.17 \
+				 $orig_inner_tos $orig_outer_tos \
+				 "link_stats_rx_errors_get vx1" 10
+
+	log_test "VXLAN: ECN decap: $orig_outer_tos/$orig_inner_tos->error"
+}
+
+test_ecn_decap()
+{
+	# In accordance with INET_ECN_decapsulate()
+	__test_ecn_decap 00 00 0x00
+	__test_ecn_decap 01 01 0x01
+	__test_ecn_decap 02 01 0x02
+	__test_ecn_decap 01 03 0x03
+	__test_ecn_decap 02 03 0x03
+	test_ecn_decap_error
+}
+
 test_all()
 {
 	echo "Running tests with UDP port $VXPORT"

From 3485f87cb7f82434cb6526a2ab5088012378dcb6 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:25 +0000
Subject: [PATCH 16/18] selftests: forwarding: vxlan_bridge_1d_port_8472: New
 test

This simple wrapper reruns the VXLAN ping test with a port number of
8472.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/vxlan_bridge_1d_port_8472.sh        | 10 ++++++++++
 1 file changed, 10 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/vxlan_bridge_1d_port_8472.sh

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_port_8472.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_port_8472.sh
new file mode 100755
index 000000000000..3bf3da69195f
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_port_8472.sh
@@ -0,0 +1,10 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# A wrapper to run VXLAN tests with an unusual port number.
+
+VXPORT=8472
+ALL_TESTS="
+	ping_ipv4
+"
+source vxlan_bridge_1d.sh

From 99c9b084f0bec000ef394d1bb58f33c4910752d9 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:26 +0000
Subject: [PATCH 17/18] selftests: mlxsw: Add a test for VxLAN configuration

Test various aspects of VxLAN offloading which are specific to mlxsw,
such as sanitization of invalid configurations and offload indication.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/vxlan.sh      | 664 ++++++++++++++++++
 1 file changed, 664 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/vxlan.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
new file mode 100755
index 000000000000..52e78adfe081
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
@@ -0,0 +1,664 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test various aspects of VxLAN offloading which are specific to mlxsw, such
+# as sanitization of invalid configurations and offload indication.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="sanitization_test offload_indication_test"
+NUM_NETIFS=2
+source $lib_dir/lib.sh
+
+setup_prepare()
+{
+	swp1=${NETIFS[p1]}
+	swp2=${NETIFS[p2]}
+
+	ip link set dev $swp1 up
+	ip link set dev $swp2 up
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ip link set dev $swp2 down
+	ip link set dev $swp1 down
+}
+
+sanitization_single_dev_test_pass()
+{
+	ip link set dev $swp1 master br0
+	check_err $?
+	ip link set dev vxlan0 master br0
+	check_err $?
+
+	ip link set dev $swp1 nomaster
+
+	ip link set dev $swp1 master br0
+	check_err $?
+}
+
+sanitization_single_dev_test_fail()
+{
+	ip link set dev $swp1 master br0
+	check_err $?
+	ip link set dev vxlan0 master br0 &> /dev/null
+	check_fail $?
+
+	ip link set dev $swp1 nomaster
+
+	ip link set dev vxlan0 master br0
+	check_err $?
+	ip link set dev $swp1 master br0 &> /dev/null
+	check_fail $?
+}
+
+sanitization_single_dev_valid_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+	sanitization_single_dev_test_pass
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device - valid configuration"
+}
+
+sanitization_single_dev_vlan_aware_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0 vlan_filtering 1
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+	sanitization_single_dev_test_fail
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device with a vlan-aware bridge"
+}
+
+sanitization_single_dev_mcast_enabled_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+	sanitization_single_dev_test_fail
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device with a multicast enabled bridge"
+}
+
+sanitization_single_dev_mcast_group_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789 \
+		dev $swp2 group 239.0.0.1
+
+	sanitization_single_dev_test_fail
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device with a multicast group"
+}
+
+sanitization_single_dev_no_local_ip_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit dstport 4789
+
+	sanitization_single_dev_test_fail
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device with no local ip"
+}
+
+sanitization_single_dev_local_ipv6_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 2001:db8::1 dstport 4789
+
+	sanitization_single_dev_test_fail
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device with local ipv6 address"
+}
+
+sanitization_single_dev_learning_enabled_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 learning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+	sanitization_single_dev_test_fail
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device with learning enabled"
+}
+
+sanitization_single_dev_local_interface_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789 dev $swp2
+
+	sanitization_single_dev_test_fail
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device with local interface"
+}
+
+sanitization_single_dev_port_range_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789 \
+		srcport 4000 5000
+
+	sanitization_single_dev_test_fail
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device with udp source port range"
+}
+
+sanitization_single_dev_tos_static_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos 20 local 198.51.100.1 dstport 4789
+
+	sanitization_single_dev_test_fail
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device with static tos"
+}
+
+sanitization_single_dev_ttl_inherit_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl inherit tos inherit local 198.51.100.1 dstport 4789
+
+	sanitization_single_dev_test_fail
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device with inherit ttl"
+}
+
+sanitization_single_dev_udp_checksum_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning udpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+	sanitization_single_dev_test_fail
+
+	ip link del dev vxlan0
+	ip link del dev br0
+
+	log_test "vxlan device with udp checksum"
+}
+
+sanitization_single_dev_test()
+{
+	# These tests make sure that we correctly sanitize VxLAN device
+	# configurations we do not support
+	sanitization_single_dev_valid_test
+	sanitization_single_dev_vlan_aware_test
+	sanitization_single_dev_mcast_enabled_test
+	sanitization_single_dev_mcast_group_test
+	sanitization_single_dev_no_local_ip_test
+	sanitization_single_dev_local_ipv6_test
+	sanitization_single_dev_learning_enabled_test
+	sanitization_single_dev_local_interface_test
+	sanitization_single_dev_port_range_test
+	sanitization_single_dev_tos_static_test
+	sanitization_single_dev_ttl_inherit_test
+	sanitization_single_dev_udp_checksum_test
+}
+
+sanitization_multi_devs_test_pass()
+{
+	ip link set dev $swp1 master br0
+	check_err $?
+	ip link set dev vxlan0 master br0
+	check_err $?
+	ip link set dev $swp2 master br1
+	check_err $?
+	ip link set dev vxlan1 master br1
+	check_err $?
+
+	ip link set dev $swp2 nomaster
+	ip link set dev $swp1 nomaster
+
+	ip link set dev $swp1 master br0
+	check_err $?
+	ip link set dev $swp2 master br1
+	check_err $?
+}
+
+sanitization_multi_devs_test_fail()
+{
+	ip link set dev $swp1 master br0
+	check_err $?
+	ip link set dev vxlan0 master br0
+	check_err $?
+	ip link set dev $swp2 master br1
+	check_err $?
+	ip link set dev vxlan1 master br1 &> /dev/null
+	check_fail $?
+
+	ip link set dev $swp2 nomaster
+	ip link set dev $swp1 nomaster
+
+	ip link set dev vxlan1 master br1
+	check_err $?
+	ip link set dev $swp1 master br0
+	check_err $?
+	ip link set dev $swp2 master br1 &> /dev/null
+	check_fail $?
+}
+
+sanitization_multi_devs_valid_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+	ip link add dev br1 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+	ip link add name vxlan1 up type vxlan id 20 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+	sanitization_multi_devs_test_pass
+
+	ip link del dev vxlan1
+	ip link del dev vxlan0
+	ip link del dev br1
+	ip link del dev br0
+
+	log_test "multiple vxlan devices - valid configuration"
+}
+
+sanitization_multi_devs_ttl_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+	ip link add dev br1 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+	ip link add name vxlan1 up type vxlan id 20 nolearning noudpcsum \
+		ttl 40 tos inherit local 198.51.100.1 dstport 4789
+
+	sanitization_multi_devs_test_fail
+
+	ip link del dev vxlan1
+	ip link del dev vxlan0
+	ip link del dev br1
+	ip link del dev br0
+
+	log_test "multiple vxlan devices with different ttl"
+}
+
+sanitization_multi_devs_udp_dstport_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+	ip link add dev br1 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+	ip link add name vxlan1 up type vxlan id 20 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 5789
+
+	sanitization_multi_devs_test_fail
+
+	ip link del dev vxlan1
+	ip link del dev vxlan0
+	ip link del dev br1
+	ip link del dev br0
+
+	log_test "multiple vxlan devices with different udp destination port"
+}
+
+sanitization_multi_devs_local_ip_test()
+{
+	RET=0
+
+	ip link add dev br0 type bridge mcast_snooping 0
+	ip link add dev br1 type bridge mcast_snooping 0
+
+	ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+	ip link add name vxlan1 up type vxlan id 20 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.2 dstport 4789
+
+	sanitization_multi_devs_test_fail
+
+	ip link del dev vxlan1
+	ip link del dev vxlan0
+	ip link del dev br1
+	ip link del dev br0
+
+	log_test "multiple vxlan devices with different local ip"
+}
+
+sanitization_multi_devs_test()
+{
+	# The device has a single VTEP, which means all the VxLAN devices
+	# we offload must share certain properties such as source IP and
+	# UDP destination port. These tests make sure that we forbid
+	# configurations that violate this limitation
+	sanitization_multi_devs_valid_test
+	sanitization_multi_devs_ttl_test
+	sanitization_multi_devs_udp_dstport_test
+	sanitization_multi_devs_local_ip_test
+}
+
+sanitization_test()
+{
+	sanitization_single_dev_test
+	sanitization_multi_devs_test
+}
+
+offload_indication_setup_create()
+{
+	# Create a simple setup with two bridges, each with a VxLAN device
+	# and one local port
+	ip link add name br0 up type bridge mcast_snooping 0
+	ip link add name br1 up type bridge mcast_snooping 0
+
+	ip link set dev $swp1 master br0
+	ip link set dev $swp2 master br1
+
+	ip address add 198.51.100.1/32 dev lo
+
+	ip link add name vxlan0 up master br0 type vxlan id 10 nolearning \
+		noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789
+	ip link add name vxlan1 up master br1 type vxlan id 20 nolearning \
+		noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789
+}
+
+offload_indication_setup_destroy()
+{
+	ip link del dev vxlan1
+	ip link del dev vxlan0
+
+	ip address del 198.51.100.1/32 dev lo
+
+	ip link set dev $swp2 nomaster
+	ip link set dev $swp1 nomaster
+
+	ip link del dev br1
+	ip link del dev br0
+}
+
+offload_indication_fdb_flood_test()
+{
+	RET=0
+
+	bridge fdb append 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.2
+
+	bridge fdb show brport vxlan0 | grep 00:00:00:00:00:00 \
+		| grep -q offload
+	check_err $?
+
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self
+
+	log_test "vxlan flood entry offload indication"
+}
+
+offload_indication_fdb_bridge_test()
+{
+	RET=0
+
+	bridge fdb add de:ad:be:ef:13:37 dev vxlan0 self master static \
+		dst 198.51.100.2
+
+	bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \
+		| grep -q offload
+	check_err $?
+	bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \
+		| grep -q offload
+	check_err $?
+
+	log_test "vxlan entry offload indication - initial state"
+
+	# Remove FDB entry from the bridge driver and check that corresponding
+	# entry in the VxLAN driver is not marked as offloaded
+	RET=0
+
+	bridge fdb del de:ad:be:ef:13:37 dev vxlan0 master
+	bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \
+		| grep -q offload
+	check_fail $?
+
+	log_test "vxlan entry offload indication - after removal from bridge"
+
+	# Add the FDB entry back to the bridge driver and make sure it is
+	# marked as offloaded in both drivers
+	RET=0
+
+	bridge fdb add de:ad:be:ef:13:37 dev vxlan0 master static
+	bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \
+		| grep -q offload
+	check_err $?
+	bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \
+		| grep -q offload
+	check_err $?
+
+	log_test "vxlan entry offload indication - after re-add to bridge"
+
+	# Remove FDB entry from the VxLAN driver and check that corresponding
+	# entry in the bridge driver is not marked as offloaded
+	RET=0
+
+	bridge fdb del de:ad:be:ef:13:37 dev vxlan0 self
+	bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \
+		| grep -q offload
+	check_fail $?
+
+	log_test "vxlan entry offload indication - after removal from vxlan"
+
+	# Add the FDB entry back to the VxLAN driver and make sure it is
+	# marked as offloaded in both drivers
+	RET=0
+
+	bridge fdb add de:ad:be:ef:13:37 dev vxlan0 self dst 198.51.100.2
+	bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \
+		| grep -q offload
+	check_err $?
+	bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \
+		| grep -q offload
+	check_err $?
+
+	log_test "vxlan entry offload indication - after re-add to vxlan"
+
+	bridge fdb del de:ad:be:ef:13:37 dev vxlan0 self master
+}
+
+offload_indication_fdb_test()
+{
+	offload_indication_fdb_flood_test
+	offload_indication_fdb_bridge_test
+}
+
+offload_indication_decap_route_test()
+{
+	RET=0
+
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	ip link set dev vxlan0 down
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	ip link set dev vxlan1 down
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_fail $?
+
+	log_test "vxlan decap route - vxlan device down"
+
+	RET=0
+
+	ip link set dev vxlan1 up
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	ip link set dev vxlan0 up
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	log_test "vxlan decap route - vxlan device up"
+
+	RET=0
+
+	ip address delete 198.51.100.1/32 dev lo
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_fail $?
+
+	ip address add 198.51.100.1/32 dev lo
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	log_test "vxlan decap route - add local route"
+
+	RET=0
+
+	ip link set dev $swp1 nomaster
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	ip link set dev $swp2 nomaster
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_fail $?
+
+	ip link set dev $swp1 master br0
+	ip link set dev $swp2 master br1
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	log_test "vxlan decap route - local ports enslavement"
+
+	RET=0
+
+	ip link del dev br0
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	ip link del dev br1
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_fail $?
+
+	log_test "vxlan decap route - bridge device deletion"
+
+	RET=0
+
+	ip link add name br0 up type bridge mcast_snooping 0
+	ip link add name br1 up type bridge mcast_snooping 0
+	ip link set dev $swp1 master br0
+	ip link set dev $swp2 master br1
+	ip link set dev vxlan0 master br0
+	ip link set dev vxlan1 master br1
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	ip link del dev vxlan0
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_err $?
+
+	ip link del dev vxlan1
+	ip route show table local | grep 198.51.100.1 | grep -q offload
+	check_fail $?
+
+	log_test "vxlan decap route - vxlan device deletion"
+
+	ip link add name vxlan0 up master br0 type vxlan id 10 nolearning \
+		noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789
+	ip link add name vxlan1 up master br1 type vxlan id 20 nolearning \
+		noudpcsum ttl 20 tos inherit local 198.51.100.1 dstport 4789
+}
+
+offload_indication_test()
+{
+	offload_indication_setup_create
+	offload_indication_fdb_test
+	offload_indication_decap_route_test
+	offload_indication_setup_destroy
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS

From 94d302deae25a0925dc736e444005918522be730 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 19 Nov 2018 16:11:27 +0000
Subject: [PATCH 18/18] selftests: mlxsw: Add a test for VxLAN flooding

The device stores flood records in a singly linked list where each
record stores up to three IPv4 addresses of remote VTEPs. The test
verifies that packets are correctly flooded in various cases such as
deletion of a record in the middle of the list.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/mlxsw/vxlan_flooding.sh       | 309 ++++++++++++++++++
 1 file changed, 309 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh
new file mode 100755
index 000000000000..fedcb7b35af9
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh
@@ -0,0 +1,309 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test VxLAN flooding. The device stores flood records in a singly linked list
+# where each record stores up to three IPv4 addresses of remote VTEPs. The test
+# verifies that packets are correctly flooded in various cases such as deletion
+# of a record in the middle of the list.
+#
+# +--------------------+
+# | H1 (vrf)           |
+# |    + $h1           |
+# |    | 203.0.113.1/24|
+# +----|---------------+
+#      |
+# +----|----------------------------------------------------------------------+
+# | SW |                                                                      |
+# | +--|--------------------------------------------------------------------+ |
+# | |  + $swp1                   BR0 (802.1d)                               | |
+# | |                                                                       | |
+# | |  + vxlan0 (vxlan)                                                     | |
+# | |    local 198.51.100.1                                                 | |
+# | |    remote 198.51.100.{2..13}                                          | |
+# | |    id 10 dstport 4789                                                 | |
+# | +-----------------------------------------------------------------------+ |
+# |                                                                           |
+# |  198.51.100.0/24 via 192.0.2.2                                            |
+# |                                                                           |
+# |    + $rp1                                                                 |
+# |    | 192.0.2.1/24                                                         |
+# +----|----------------------------------------------------------------------+
+#      |
+# +----|--------------------------------------------------------+
+# |    |                                               R2 (vrf) |
+# |    + $rp2                                                   |
+# |      192.0.2.2/24                                           |
+# |                                                             |
+# +-------------------------------------------------------------+
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="flooding_test"
+NUM_NETIFS=4
+source $lib_dir/tc_common.sh
+source $lib_dir/lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 203.0.113.1/24
+}
+
+h1_destroy()
+{
+	simple_if_fini $h1 203.0.113.1/24
+}
+
+switch_create()
+{
+	# Make sure the bridge uses the MAC address of the local port and
+	# not that of the VxLAN's device
+	ip link add dev br0 type bridge mcast_snooping 0
+	ip link set dev br0 address $(mac_get $swp1)
+
+	ip link add name vxlan0 type vxlan id 10 nolearning noudpcsum \
+		ttl 20 tos inherit local 198.51.100.1 dstport 4789
+
+	ip address add 198.51.100.1/32 dev lo
+
+	ip link set dev $swp1 master br0
+	ip link set dev vxlan0 master br0
+
+	ip link set dev br0 up
+	ip link set dev $swp1 up
+	ip link set dev vxlan0 up
+}
+
+switch_destroy()
+{
+	ip link set dev vxlan0 down
+	ip link set dev $swp1 down
+	ip link set dev br0 down
+
+	ip link set dev vxlan0 nomaster
+	ip link set dev $swp1 nomaster
+
+	ip address del 198.51.100.1/32 dev lo
+
+	ip link del dev vxlan0
+
+	ip link del dev br0
+}
+
+router1_create()
+{
+	# This router is in the default VRF, where the VxLAN device is
+	# performing the L3 lookup
+	ip link set dev $rp1 up
+	ip address add 192.0.2.1/24 dev $rp1
+	ip route add 198.51.100.0/24 via 192.0.2.2
+}
+
+router1_destroy()
+{
+	ip route del 198.51.100.0/24 via 192.0.2.2
+	ip address del 192.0.2.1/24 dev $rp1
+	ip link set dev $rp1 down
+}
+
+router2_create()
+{
+	# This router is not in the default VRF, so use simple_if_init()
+	simple_if_init $rp2 192.0.2.2/24
+}
+
+router2_destroy()
+{
+	simple_if_fini $rp2 192.0.2.2/24
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	rp1=${NETIFS[p3]}
+	rp2=${NETIFS[p4]}
+
+	vrf_prepare
+
+	h1_create
+
+	switch_create
+
+	router1_create
+	router2_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	router2_destroy
+	router1_destroy
+
+	switch_destroy
+
+	h1_destroy
+
+	vrf_cleanup
+}
+
+flooding_remotes_add()
+{
+	local num_remotes=$1
+	local lsb
+	local i
+
+	for i in $(eval echo {1..$num_remotes}); do
+		lsb=$((i + 1))
+
+		bridge fdb append 00:00:00:00:00:00 dev vxlan0 self \
+			dst 198.51.100.$lsb
+	done
+}
+
+flooding_filters_add()
+{
+	local num_remotes=$1
+	local lsb
+	local i
+
+	tc qdisc add dev $rp2 clsact
+
+	for i in $(eval echo {1..$num_remotes}); do
+		lsb=$((i + 1))
+
+		tc filter add dev $rp2 ingress protocol ip pref $i handle $i \
+			flower ip_proto udp dst_ip 198.51.100.$lsb \
+			dst_port 4789 skip_sw action drop
+	done
+}
+
+flooding_filters_del()
+{
+	local num_remotes=$1
+	local i
+
+	for i in $(eval echo {1..$num_remotes}); do
+		tc filter del dev $rp2 ingress protocol ip pref $i \
+			handle $i flower
+	done
+
+	tc qdisc del dev $rp2 clsact
+}
+
+flooding_check_packets()
+{
+	local packets=("$@")
+	local num_remotes=${#packets[@]}
+	local i
+
+	for i in $(eval echo {1..$num_remotes}); do
+		tc_check_packets "dev $rp2 ingress" $i ${packets[i - 1]}
+		check_err $? "remote $i - did not get expected number of packets"
+	done
+}
+
+flooding_test()
+{
+	# Use 12 remote VTEPs that will be stored in 4 records. The array
+	# 'packets' will store how many packets are expected to be received
+	# by each remote VTEP at each stage of the test
+	declare -a packets=(1 1 1 1 1 1 1 1 1 1 1 1)
+	local num_remotes=12
+
+	RET=0
+
+	# Add FDB entries for remote VTEPs and corresponding tc filters on the
+	# ingress of the nexthop router. These filters will count how many
+	# packets were flooded to each remote VTEP
+	flooding_remotes_add $num_remotes
+	flooding_filters_add $num_remotes
+
+	# Send one packet and make sure it is flooded to all the remote VTEPs
+	$MZ $h1 -q -p 64 -b de:ad:be:ef:13:37 -t ip -c 1
+	flooding_check_packets "${packets[@]}"
+	log_test "flood after 1 packet"
+
+	# Delete the third record which corresponds to VTEPs with LSB 8..10
+	# and check that packet is flooded correctly when we remove a record
+	# from the middle of the list
+	RET=0
+
+	packets=(2 2 2 2 2 2 1 1 1 2 2 2)
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.8
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.9
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.10
+
+	$MZ $h1 -q -p 64 -b de:ad:be:ef:13:37 -t ip -c 1
+	flooding_check_packets "${packets[@]}"
+	log_test "flood after 2 packets"
+
+	# Delete the first record and make sure the packet is flooded correctly
+	RET=0
+
+	packets=(2 2 2 3 3 3 1 1 1 3 3 3)
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.2
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.3
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.4
+
+	$MZ $h1 -q -p 64 -b de:ad:be:ef:13:37 -t ip -c 1
+	flooding_check_packets "${packets[@]}"
+	log_test "flood after 3 packets"
+
+	# Delete the last record and make sure the packet is flooded correctly
+	RET=0
+
+	packets=(2 2 2 4 4 4 1 1 1 3 3 3)
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.11
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.12
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.13
+
+	$MZ $h1 -q -p 64 -b de:ad:be:ef:13:37 -t ip -c 1
+	flooding_check_packets "${packets[@]}"
+	log_test "flood after 4 packets"
+
+	# Delete the last record, one entry at a time and make sure single
+	# entries are correctly removed
+	RET=0
+
+	packets=(2 2 2 4 5 5 1 1 1 3 3 3)
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.5
+
+	$MZ $h1 -q -p 64 -b de:ad:be:ef:13:37 -t ip -c 1
+	flooding_check_packets "${packets[@]}"
+	log_test "flood after 5 packets"
+
+	RET=0
+
+	packets=(2 2 2 4 5 6 1 1 1 3 3 3)
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.6
+
+	$MZ $h1 -q -p 64 -b de:ad:be:ef:13:37 -t ip -c 1
+	flooding_check_packets "${packets[@]}"
+	log_test "flood after 6 packets"
+
+	RET=0
+
+	packets=(2 2 2 4 5 6 1 1 1 3 3 3)
+	bridge fdb del 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.7
+
+	$MZ $h1 -q -p 64 -b de:ad:be:ef:13:37 -t ip -c 1
+	flooding_check_packets "${packets[@]}"
+	log_test "flood after 7 packets"
+
+	flooding_filters_del $num_remotes
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS