Merge branch 'selftests-Add-tests-for-VXLAN-at-an-802-1d-bridge'

Ido Schimmel says:

====================
selftests: Add tests for VXLAN at an 802.1d bridge

Petr says:

This patchset adds several tests for VXLAN attached to an 802.1d bridge
and fixes a related bug.

First patch #1 fixes a bug in propagating SKB already-forwarded marks
over veth to bridges, where they are irrelevant. This bug causes the
vxlan_bridge_1d test suite from this patchset to fail as the packets
aren't forwarded by br2.

In patches #2 and #3, lib.sh is extended to support network namespaces.
The use of namespaces is necessitated by VXLAN, which allows only one
VXLAN device with a given VNI per namespace. Thus to host full topology
on a single box for selftests, the "remote" endpoints need to be in
namespaces.

In patches #4-#6, lib.sh is extended in other ways to facilitate the
following patches.

In patches #7-#15, first the skeleton, and later the generic tests
themselves are added.

Patch #16 then adds another test that serves as a wrapper around the
previous one, and runs it with a non-default port number.

Patches #17 and #18 add mlxsw-specific tests. About those, Ido writes:

The first test creates various configurations with regards to the VxLAN
and bridge devices and makes sure the driver correctly forbids
unsupported configuration and permits supported ones. It also verifies
that the driver correctly sets the offload indication on FDB entries and
the local route used for VxLAN decapsulation.

The second test verifies that the driver correctly configures the singly
linked list used to flood BUM traffic and that traffic is flooded as
expected.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

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;
 

tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh

+#!/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

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"
@@ -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()
@@ -783,6 +796,17 @@ 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
 
@@ -790,10 +814,11 @@ 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()
@@ -802,17 +827,18 @@ ping_test()
 
 	ping_do $1 $2
 	check_err $?
-	log_test "ping"
+	log_test "ping$3"
 }
 
 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()
@@ -821,7 +847,7 @@ ping6_test()
 
 	ping6_do $1 $2
 	check_err $?
-	log_test "ping6"
+	log_test "ping6$3"
 }
 
 learning_test()

tools/testing/selftests/net/forwarding/vxlan_bridge_1d_port_8472.sh

+#!/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