Merge branch 'mlxsw-Disable-checks-in-hardware-pipeline'

Ido Schimmel says:

====================
mlxsw: Disable checks in hardware pipeline

Amit says:

The hardware pipeline contains some checks that, by default, are
configured to drop packets. Since the software data path does not drop
packets due to these reasons and since we are interested in offloading
the software data path to hardware, then these checks should be disabled
in the hardware pipeline as well.

This patch set changes mlxsw to disable four of these checks and adds
corresponding selftests. The tests pass both when the software data path
is exercised (using veth pair) and when the hardware data path is
exercised (using mlxsw ports in loopback).
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 200 insertions, 1 deletions

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index fe02ffb1e3a8..431c3765b545 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4545,6 +4545,14 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	MLXSW_SP_RXL_MARK(DECAP_ECN0, TRAP_TO_CPU, ROUTER_EXP, false),
 	MLXSW_SP_RXL_MARK(IPV4_VRRP, TRAP_TO_CPU, VRRP, false),
 	MLXSW_SP_RXL_MARK(IPV6_VRRP, TRAP_TO_CPU, VRRP, false),
+	MLXSW_SP_RXL_NO_MARK(DISCARD_ING_ROUTER_SIP_CLASS_E, FORWARD,
+			     ROUTER_EXP, false),
+	MLXSW_SP_RXL_NO_MARK(DISCARD_ING_ROUTER_MC_DMAC, FORWARD,
+			     ROUTER_EXP, false),
+	MLXSW_SP_RXL_NO_MARK(DISCARD_ING_ROUTER_SIP_DIP, FORWARD,
+			     ROUTER_EXP, false),
+	MLXSW_SP_RXL_NO_MARK(DISCARD_ING_ROUTER_DIP_LINK_LOCAL, FORWARD,
+			     ROUTER_EXP, false),
 	/* PKT Sample trap */
 	MLXSW_RXL(mlxsw_sp_rx_listener_sample_func, PKT_SAMPLE, MIRROR_TO_CPU,
 		  false, SP_IP2ME, DISCARD),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h
index 0c1c142bb6b0..3d2331be05d8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h
@@ -80,10 +80,14 @@ enum {
 	MLXSW_TRAP_ID_DISCARD_ING_ROUTER_UC_DIP_MC_DMAC = 0x161,
 	MLXSW_TRAP_ID_DISCARD_ING_ROUTER_DIP_LB = 0x162,
 	MLXSW_TRAP_ID_DISCARD_ING_ROUTER_SIP_MC = 0x163,
+	MLXSW_TRAP_ID_DISCARD_ING_ROUTER_SIP_CLASS_E = 0x164,
 	MLXSW_TRAP_ID_DISCARD_ING_ROUTER_SIP_LB = 0x165,
 	MLXSW_TRAP_ID_DISCARD_ING_ROUTER_CORRUPTED_IP_HDR = 0x167,
+	MLXSW_TRAP_ID_DISCARD_ING_ROUTER_MC_DMAC = 0x168,
+	MLXSW_TRAP_ID_DISCARD_ING_ROUTER_SIP_DIP = 0x169,
 	MLXSW_TRAP_ID_DISCARD_ING_ROUTER_IPV4_SIP_BC = 0x16A,
 	MLXSW_TRAP_ID_DISCARD_ING_ROUTER_IPV4_DIP_LOCAL_NET = 0x16B,
+	MLXSW_TRAP_ID_DISCARD_ING_ROUTER_DIP_LINK_LOCAL = 0x16C,
 	MLXSW_TRAP_ID_DISCARD_ROUTER_LPM4 = 0x17B,
 	MLXSW_TRAP_ID_DISCARD_ROUTER_LPM6 = 0x17C,
 	MLXSW_TRAP_ID_DISCARD_IPV6_MC_DIP_RESERVED_SCOPE = 0x1B0,
diff --git a/tools/testing/selftests/net/forwarding/router.sh b/tools/testing/selftests/net/forwarding/router.sh
index a75cb51cc5bd..057f91b05098 100755
--- a/tools/testing/selftests/net/forwarding/router.sh
+++ b/tools/testing/selftests/net/forwarding/router.sh
@@ -1,9 +1,23 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-ALL_TESTS="ping_ipv4 ping_ipv6"
+ALL_TESTS="
+	ping_ipv4
+	ping_ipv6
+	sip_in_class_e
+	mc_mac_mismatch
+	ipv4_sip_equal_dip
+	ipv6_sip_equal_dip
+	ipv4_dip_link_local
+"
+
 NUM_NETIFS=4
 source lib.sh
+source tc_common.sh
+
+require_command $MCD
+require_command $MC_CLI
+table_name=selftests
 
 h1_create()
 {
@@ -64,6 +78,8 @@ router_create()
 	ip link set dev $rp1 up
 	ip link set dev $rp2 up
 
+	tc qdisc add dev $rp2 clsact
+
 	ip address add 192.0.2.1/24 dev $rp1
 	ip address add 2001:db8:1::1/64 dev $rp1
 
@@ -79,10 +95,31 @@ router_destroy()
 	ip address del 2001:db8:1::1/64 dev $rp1
 	ip address del 192.0.2.1/24 dev $rp1
 
+	tc qdisc del dev $rp2 clsact
+
 	ip link set dev $rp2 down
 	ip link set dev $rp1 down
 }
 
+start_mcd()
+{
+	SMCROUTEDIR="$(mktemp -d)"
+
+	for ((i = 1; i <= $NUM_NETIFS; ++i)); do
+		echo "phyint ${NETIFS[p$i]} enable" >> \
+			$SMCROUTEDIR/$table_name.conf
+	done
+
+	$MCD -N -I $table_name -f $SMCROUTEDIR/$table_name.conf \
+		-P $SMCROUTEDIR/$table_name.pid
+}
+
+kill_mcd()
+{
+	pkill $MCD
+	rm -rf $SMCROUTEDIR
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}
@@ -91,6 +128,10 @@ setup_prepare()
 	rp2=${NETIFS[p3]}
 	h2=${NETIFS[p4]}
 
+	rp1mac=$(mac_get $rp1)
+
+	start_mcd
+
 	vrf_prepare
 
 	h1_create
@@ -113,6 +154,8 @@ cleanup()
 	h1_destroy
 
 	vrf_cleanup
+
+	kill_mcd
 }
 
 ping_ipv4()
@@ -125,6 +168,150 @@ ping_ipv6()
 	ping6_test $h1 2001:db8:2::2
 }
 
+sip_in_class_e()
+{
+	RET=0
+
+	# Disable rpfilter to prevent packets to be dropped because of it.
+	sysctl_set net.ipv4.conf.all.rp_filter 0
+	sysctl_set net.ipv4.conf.$rp1.rp_filter 0
+
+	tc filter add dev $rp2 egress protocol ip pref 1 handle 101 \
+		flower src_ip 240.0.0.1 ip_proto udp action pass
+
+	$MZ $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec \
+		-A 240.0.0.1 -b $rp1mac -B 198.51.100.2 -q
+
+	tc_check_packets "dev $rp2 egress" 101 5
+	check_err $? "Packets were dropped"
+
+	log_test "Source IP in class E"
+
+	tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower
+	sysctl_restore net.ipv4.conf.$rp1.rp_filter
+	sysctl_restore net.ipv4.conf.all.rp_filter
+}
+
+create_mcast_sg()
+{
+	local if_name=$1; shift
+	local s_addr=$1; shift
+	local mcast=$1; shift
+	local dest_ifs=${@}
+
+	$MC_CLI -I $table_name add $if_name $s_addr $mcast $dest_ifs
+}
+
+delete_mcast_sg()
+{
+	local if_name=$1; shift
+	local s_addr=$1; shift
+	local mcast=$1; shift
+	local dest_ifs=${@}
+
+	$MC_CLI -I $table_name remove $if_name $s_addr $mcast $dest_ifs
+}
+
+__mc_mac_mismatch()
+{
+	local desc=$1; shift
+	local proto=$1; shift
+	local sip=$1; shift
+	local dip=$1; shift
+	local flags=${1:-""}; shift
+	local dmac=01:02:03:04:05:06
+
+	RET=0
+
+	tc filter add dev $rp2 egress protocol $proto pref 1 handle 101 \
+		flower dst_ip $dip action pass
+
+	create_mcast_sg $rp1 $sip $dip $rp2
+
+	$MZ $flags $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec -b $dmac \
+		-B $dip -q
+
+	tc_check_packets "dev $rp2 egress" 101 5
+	check_err $? "Packets were dropped"
+
+	log_test "Multicast MAC mismatch: $desc"
+
+	delete_mcast_sg $rp1 $sip $dip $rp2
+	tc filter del dev $rp2 egress protocol $proto pref 1 handle 101 flower
+}
+
+mc_mac_mismatch()
+{
+	__mc_mac_mismatch "IPv4" "ip" 192.0.2.2 225.1.2.3
+	__mc_mac_mismatch "IPv6" "ipv6" 2001:db8:1::2 ff0e::3 "-6"
+}
+
+ipv4_sip_equal_dip()
+{
+	RET=0
+
+	# Disable rpfilter to prevent packets to be dropped because of it.
+	sysctl_set net.ipv4.conf.all.rp_filter 0
+	sysctl_set net.ipv4.conf.$rp1.rp_filter 0
+
+	tc filter add dev $rp2 egress protocol ip pref 1 handle 101 \
+		flower src_ip 198.51.100.2  action pass
+
+	$MZ $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec \
+		-A 198.51.100.2 -b $rp1mac -B 198.51.100.2 -q
+
+	tc_check_packets "dev $rp2 egress" 101 5
+	check_err $? "Packets were dropped"
+
+	log_test "Source IP is equal to destination IP: IPv4"
+
+	tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower
+	sysctl_restore net.ipv4.conf.$rp1.rp_filter
+	sysctl_restore net.ipv4.conf.all.rp_filter
+}
+
+ipv6_sip_equal_dip()
+{
+	RET=0
+
+	tc filter add dev $rp2 egress protocol ipv6 pref 1 handle 101 \
+		flower src_ip 2001:db8:2::2 action pass
+
+	$MZ -6 $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec \
+		-A 2001:db8:2::2 -b $rp1mac -B 2001:db8:2::2 -q
+
+	tc_check_packets "dev $rp2 egress" 101 5
+	check_err $? "Packets were dropped"
+
+	log_test "Source IP is equal to destination IP: IPv6"
+
+	tc filter del dev $rp2 egress protocol ipv6 pref 1 handle 101 flower
+}
+
+ipv4_dip_link_local()
+{
+	local dip=169.254.1.1
+
+	RET=0
+
+	tc filter add dev $rp2 egress protocol ip pref 1 handle 101 \
+		flower dst_ip $dip action pass
+
+	ip neigh add 169.254.1.1 lladdr 00:11:22:33:44:55 dev $rp2
+	ip route add 169.254.1.0/24 dev $rp2
+
+	$MZ $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec -b $rp1mac -B $dip -q
+
+	tc_check_packets "dev $rp2 egress" 101 5
+	check_err $? "Packets were dropped"
+
+	log_test "IPv4 destination IP is link-local"
+
+	ip route del 169.254.1.0/24 dev $rp2
+	ip neigh del 169.254.1.1 lladdr 00:11:22:33:44:55 dev $rp2
+	tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower
+}
+
 trap cleanup EXIT
 
 setup_prepare