This will be used in other subtests as well; make new macvlan_create() and macvlan_destroy() functions.

Signed-off-by: Vladimir Oltean vladimir.oltean@nxp.com --- .../net/forwarding/local_termination.sh | 30 +++++++++++-------- 1 file changed, 18 insertions(+), 12 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index 4b364cdf3ef0..36f3d577d0be 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -247,19 +247,29 @@ bridge_destroy() ip link del br0 }

-standalone() +macvlan_create() { - h1_create - h2_create + local lower=$1

- ip link add link $h2 name macvlan0 type macvlan mode private + ip link add link $lower name macvlan0 type macvlan mode private ip link set macvlan0 address $MACVLAN_ADDR ip link set macvlan0 up +}

- run_test $h2 - +macvlan_destroy() +{ ip link del macvlan0 +} + +standalone() +{ + h1_create + h2_create + macvlan_create $h2 + + run_test $h2

+ macvlan_destroy h2_destroy h1_destroy } @@ -268,15 +278,11 @@ bridge() { h1_create bridge_create - - ip link add link br0 name macvlan0 type macvlan mode private - ip link set macvlan0 address $MACVLAN_ADDR - ip link set macvlan0 up + macvlan_create br0

run_test br0

- ip link del macvlan0 - + macvlan_destroy bridge_destroy h1_destroy }

There are upcoming tests which verify the RX filtering of a bridge (or bridge port), but under differing vlan_filtering conditions. Since we currently print $h2 (the DUT) in the log_test() output, it becomes necessary to make a further distinction between tests, to not give the user the impression that the exact same thing is run twice.

Signed-off-by: Vladimir Oltean vladimir.oltean@nxp.com --- .../net/forwarding/local_termination.sh | 38 ++++++++++--------- 1 file changed, 20 insertions(+), 18 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index 92f0e242d119..af284edaf401 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -68,10 +68,11 @@ send_uc_ipv4()

check_rcv() { - local if_name=$1 - local type=$2 - local pattern=$3 - local should_receive=$4 + local if_name=$1; shift + local type=$1; shift + local pattern=$1; shift + local should_receive=$1; shift + local test_name="$1"; shift local should_fail=

[ $should_receive = true ] && should_fail=0 || should_fail=1 @@ -81,7 +82,7 @@ check_rcv()

check_err_fail "$should_fail" "$?" "reception"

- log_test "$if_name: $type" + log_test "$test_name: $type" }

mc_route_prepare() @@ -106,6 +107,7 @@ run_test() { local send_if_name=$1; shift local rcv_if_name=$1; shift + local test_name="$1"; shift local smac=$(mac_get $send_if_name) local rcv_dmac=$(mac_get $rcv_if_name)

@@ -150,61 +152,61 @@ run_test()

check_rcv $rcv_if_name "Unicast IPv4 to primary MAC address" \ "$smac > $rcv_dmac, ethertype IPv4 (0x0800)" \ - true + true "$test_name"

check_rcv $rcv_if_name "Unicast IPv4 to macvlan MAC address" \ "$smac > $MACVLAN_ADDR, ethertype IPv4 (0x0800)" \ - true + true "$test_name"

xfail_on_veth $h1 \ check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address" \ "$smac > $UNKNOWN_UC_ADDR1, ethertype IPv4 (0x0800)" \ - false + false "$test_name"

check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address, promisc" \ "$smac > $UNKNOWN_UC_ADDR2, ethertype IPv4 (0x0800)" \ - true + true "$test_name"

xfail_on_veth $h1 \ check_rcv $rcv_if_name \ "Unicast IPv4 to unknown MAC address, allmulti" \ "$smac > $UNKNOWN_UC_ADDR3, ethertype IPv4 (0x0800)" \ - false + false "$test_name"

check_rcv $rcv_if_name "Multicast IPv4 to joined group" \ "$smac > $JOINED_MACV4_MC_ADDR, ethertype IPv4 (0x0800)" \ - true + true "$test_name"

xfail_on_veth $h1 \ check_rcv $rcv_if_name \ "Multicast IPv4 to unknown group" \ "$smac > $UNKNOWN_MACV4_MC_ADDR1, ethertype IPv4 (0x0800)" \ - false + false "$test_name"

check_rcv $rcv_if_name "Multicast IPv4 to unknown group, promisc" \ "$smac > $UNKNOWN_MACV4_MC_ADDR2, ethertype IPv4 (0x0800)" \ - true + true "$test_name"

check_rcv $rcv_if_name "Multicast IPv4 to unknown group, allmulti" \ "$smac > $UNKNOWN_MACV4_MC_ADDR3, ethertype IPv4 (0x0800)" \ - true + true "$test_name"

check_rcv $rcv_if_name "Multicast IPv6 to joined group" \ "$smac > $JOINED_MACV6_MC_ADDR, ethertype IPv6 (0x86dd)" \ - true + true "$test_name"

xfail_on_veth $h1 \ check_rcv $rcv_if_name "Multicast IPv6 to unknown group" \ "$smac > $UNKNOWN_MACV6_MC_ADDR1, ethertype IPv6 (0x86dd)" \ - false + false "$test_name"

check_rcv $rcv_if_name "Multicast IPv6 to unknown group, promisc" \ "$smac > $UNKNOWN_MACV6_MC_ADDR2, ethertype IPv6 (0x86dd)" \ - true + true "$test_name"

check_rcv $rcv_if_name "Multicast IPv6 to unknown group, allmulti" \ "$smac > $UNKNOWN_MACV6_MC_ADDR3, ethertype IPv6 (0x86dd)" \ - true + true "$test_name"

tcpdump_cleanup $rcv_if_name }

Add more coverage to the local termination selftest as follows: - 8021q upper of $h2 - 8021q upper of $h2, where $h2 is a port of a VLAN-unaware bridge - 8021q upper of $h2, where $h2 is a port of a VLAN-aware bridge - 8021q upper of VLAN-unaware br0, which is the upper of $h2 - 8021q upper of VLAN-aware br0, which is the upper of $h2

Especially the cases with traffic sent through the VLAN upper of a VLAN-aware bridge port will be immediately relevant when we will start transmitting PTP packets as an additional kind of traffic.

Signed-off-by: Vladimir Oltean vladimir.oltean@nxp.com --- .../net/forwarding/local_termination.sh | 117 ++++++++++++++++-- 1 file changed, 110 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index 5aa364b40e33..e22c6a693bef 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -1,7 +1,9 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0

-ALL_TESTS="standalone vlan_unaware_bridge vlan_aware_bridge" +ALL_TESTS="standalone vlan_unaware_bridge vlan_aware_bridge test_vlan \ + vlan_over_vlan_unaware_bridged_port vlan_over_vlan_aware_bridged_port \ + vlan_over_vlan_unaware_bridge vlan_over_vlan_aware_bridge" NUM_NETIFS=2 PING_COUNT=1 REQUIRE_MTOOLS=yes @@ -231,6 +233,30 @@ h2_destroy() simple_if_fini $h2 $H2_IPV4/24 $H2_IPV6/64 }

+h1_vlan_create() +{ + simple_if_init $h1 + vlan_create $h1 100 v$h1 $H1_IPV4/24 $H1_IPV6/64 +} + +h1_vlan_destroy() +{ + vlan_destroy $h1 100 + simple_if_fini $h1 +} + +h2_vlan_create() +{ + simple_if_init $h2 + vlan_create $h2 100 v$h2 $H2_IPV4/24 $H2_IPV6/64 +} + +h2_vlan_destroy() +{ + vlan_destroy $h2 100 + simple_if_fini $h2 +} + bridge_create() { local vlan_filtering=$1 @@ -241,14 +267,10 @@ bridge_create()

ip link set $h2 master br0 ip link set $h2 up - - simple_if_init br0 $H2_IPV4/24 $H2_IPV6/64 }

bridge_destroy() { - simple_if_fini br0 $H2_IPV4/24 $H2_IPV6/64 - ip link del br0 }

@@ -272,7 +294,7 @@ standalone() h2_create macvlan_create $h2

- run_test $h1 $h2 + run_test $h1 $h2 "$h2"

macvlan_destroy h2_destroy @@ -285,11 +307,13 @@ test_bridge()

h1_create bridge_create $vlan_filtering + simple_if_init br0 $H2_IPV4/24 $H2_IPV6/64 macvlan_create br0

- run_test $h1 br0 + run_test $h1 br0 "vlan_filtering=$vlan_filtering bridge"

macvlan_destroy + simple_if_fini br0 $H2_IPV4/24 $H2_IPV6/64 bridge_destroy h1_destroy } @@ -304,6 +328,85 @@ vlan_aware_bridge() test_bridge 1 }

+test_vlan() +{ + h1_vlan_create + h2_vlan_create + macvlan_create $h2.100 + + run_test $h1.100 $h2.100 "VLAN upper" + + macvlan_destroy + h2_vlan_destroy + h1_vlan_destroy +} + +vlan_over_bridged_port() +{ + local vlan_filtering=$1 + + h1_vlan_create + h2_vlan_create + bridge_create $vlan_filtering + macvlan_create $h2.100 + + run_test $h1.100 $h2.100 "VLAN over vlan_filtering=$vlan_filtering bridged port" + + macvlan_destroy + bridge_destroy + h2_vlan_destroy + h1_vlan_destroy +} + +vlan_over_vlan_unaware_bridged_port() +{ + vlan_over_bridged_port 0 +} + +vlan_over_vlan_aware_bridged_port() +{ + vlan_over_bridged_port 1 +} + +vlan_over_bridge() +{ + local vlan_filtering=$1 + + h1_vlan_create + bridge_create $vlan_filtering + simple_if_init br0 + vlan_create br0 100 vbr0 $H2_IPV4/24 $H2_IPV6/64 + macvlan_create br0.100 + + if [ $vlan_filtering = 1 ]; then + bridge vlan add dev $h2 vid 100 master + bridge vlan add dev br0 vid 100 self + fi + + run_test $h1.100 br0.100 "VLAN over vlan_filtering=$vlan_filtering bridge" + + if [ $vlan_filtering = 1 ]; then + bridge vlan del dev br0 vid 100 self + bridge vlan del dev $h2 vid 100 master + fi + + macvlan_destroy + vlan_destroy br0 100 + simple_if_fini br0 + bridge_destroy + h1_vlan_destroy +} + +vlan_over_vlan_unaware_bridge() +{ + vlan_over_bridge 0 +} + +vlan_over_vlan_aware_bridge() +{ + vlan_over_bridge 1 +} + cleanup() { pre_cleanup

A breakage in the felix DSA driver shows we do not have enough test coverage. More generally, it is sufficiently special that it is likely drivers will treat it differently.

This is not meant to be a full PTP test, it just makes sure that PTP packets sent to the different addresses corresponding to their profiles are received correctly. The local_termination selftest seemed like the most appropriate place for this addition.

PTP RX/TX in some cases makes no sense (over a bridge) and this is why $skip_ptp exists. And in others - PTP over a bridge port - the IP stack needs convincing through the available bridge netfilter hooks to leave the PTP packets alone and not stolen by the bridge rx_handler. It is safe to assume that users have that figured out already. This is a driver level test, and by using tcpdump, all that extra setup is out of scope here.

send_non_ip() was an unfinished idea; written but never used. Replace it with a more generic send_raw(), and send 3 PTP packet types times 3 transports.

Signed-off-by: Vladimir Oltean vladimir.oltean@nxp.com --- .../net/forwarding/local_termination.sh | 161 ++++++++++++++++-- 1 file changed, 148 insertions(+), 13 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index 80ea4c10d764..648868f74604 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -39,9 +39,68 @@ UNKNOWN_MACV6_MC_ADDR1="33:33:01:02:03:05" UNKNOWN_MACV6_MC_ADDR2="33:33:01:02:03:06" UNKNOWN_MACV6_MC_ADDR3="33:33:01:02:03:07"

-NON_IP_MC="01:02:03:04:05:06" -NON_IP_PKT="00:04 48:45:4c:4f" -BC="ff:ff:ff:ff:ff:ff" +PTP_1588_L2_SYNC=" \ +01:1b:19:00:00:00 00:00:de:ad:be:ef 88:f7 00 02 \ +00 2c 00 00 02 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 3e 37 63 ff fe cf 17 0e 00 01 00 00 00 00 \ +00 00 00 00 00 00 00 00 00 00" +PTP_1588_L2_FOLLOW_UP=" \ +01:1b:19:00:00:00 00:00:de:ad:be:ef 88:f7 08 02 \ +00 2c 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 3e 37 63 ff fe cf 17 0e 00 01 00 00 02 00 \ +00 00 66 83 c5 f1 17 97 ed f0" +PTP_1588_L2_PDELAY_REQ=" \ +01:80:c2:00:00:0e 00:00:de:ad:be:ef 88:f7 02 02 \ +00 36 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 3e 37 63 ff fe cf 17 0e 00 01 00 06 05 7f \ +00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 00 00" +PTP_1588_IPV4_SYNC=" \ +01:00:5e:00:01:81 00:00:de:ad:be:ef 08:00 45 00 \ +00 48 0a 9a 40 00 01 11 cb 88 c0 00 02 01 e0 00 \ +01 81 01 3f 01 3f 00 34 a3 c8 00 02 00 2c 00 00 \ +02 00 00 00 00 00 00 00 00 00 00 00 00 00 3e 37 \ +63 ff fe cf 17 0e 00 01 00 00 00 00 00 00 00 00 \ +00 00 00 00 00 00" +PTP_1588_IPV4_FOLLOW_UP=" +01:00:5e:00:01:81 00:00:de:ad:be:ef 08:00 45 00 \ +00 48 0a 9b 40 00 01 11 cb 87 c0 00 02 01 e0 00 \ +01 81 01 40 01 40 00 34 a3 c8 08 02 00 2c 00 00 \ +00 00 00 00 00 00 00 00 00 00 00 00 00 00 3e 37 \ +63 ff fe cf 17 0e 00 01 00 00 02 00 00 00 66 83 \ +c6 0f 1d 9a 61 87" +PTP_1588_IPV4_PDELAY_REQ=" \ +01:00:5e:00:00:6b 00:00:de:ad:be:ef 08:00 45 00 \ +00 52 35 a9 40 00 01 11 a1 85 c0 00 02 01 e0 00 \ +00 6b 01 3f 01 3f 00 3e a2 bc 02 02 00 36 00 00 \ +00 00 00 00 00 00 00 00 00 00 00 00 00 00 3e 37 \ +63 ff fe cf 17 0e 00 01 00 01 05 7f 00 00 00 00 \ +00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00" +PTP_1588_IPV6_SYNC=" \ +33:33:00:00:01:81 00:00:de:ad:be:ef 86:dd 60 06 \ +7c 2f 00 36 11 01 20 01 0d b8 00 01 00 00 00 00 \ +00 00 00 00 00 01 ff 0e 00 00 00 00 00 00 00 00 \ +00 00 00 00 01 81 01 3f 01 3f 00 36 2e 92 00 02 \ +00 2c 00 00 02 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 3e 37 63 ff fe cf 17 0e 00 01 00 00 00 00 \ +00 00 00 00 00 00 00 00 00 00 00 00" +PTP_1588_IPV6_FOLLOW_UP=" \ +33:33:00:00:01:81 00:00:de:ad:be:ef 86:dd 60 0a \ +00 bc 00 36 11 01 20 01 0d b8 00 01 00 00 00 00 \ +00 00 00 00 00 01 ff 0e 00 00 00 00 00 00 00 00 \ +00 00 00 00 01 81 01 40 01 40 00 36 2e 92 08 02 \ +00 2c 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 3e 37 63 ff fe cf 17 0e 00 01 00 00 02 00 \ +00 00 66 83 c6 2a 32 09 bd 74 00 00" +PTP_1588_IPV6_PDELAY_REQ=" \ +33:33:00:00:00:6b 00:00:de:ad:be:ef 86:dd 60 0c \ +5c fd 00 40 11 01 fe 80 00 00 00 00 00 00 3c 37 \ +63 ff fe cf 17 0e ff 02 00 00 00 00 00 00 00 00 \ +00 00 00 00 00 6b 01 3f 01 3f 00 40 b4 54 02 02 \ +00 36 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 3e 37 63 ff fe cf 17 0e 00 01 00 01 05 7f \ +00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 00 00 00 00"

# Disable promisc to ensure we don't receive unknown MAC DA packets export TCPDUMP_EXTRA_FLAGS="-pl" @@ -49,13 +108,15 @@ export TCPDUMP_EXTRA_FLAGS="-pl" h1=${NETIFS[p1]} h2=${NETIFS[p2]}

-send_non_ip() +send_raw() { - local if_name=$1 - local smac=$2 - local dmac=$3 + local if_name=$1; shift + local pkt="$1"; shift + local smac=$(mac_get $if_name)

- $MZ -q $if_name "$dmac $smac $NON_IP_PKT" + pkt="${pkt/00:00:de:ad:be:ef/$smac}" + + $MZ -q $if_name "$pkt" }

send_uc_ipv4() @@ -109,6 +170,7 @@ run_test() { local send_if_name=$1; shift local rcv_if_name=$1; shift + local skip_ptp=$1; shift local no_unicast_flt=$1; shift local test_name="$1"; shift local smac=$(mac_get $send_if_name) @@ -150,6 +212,35 @@ run_test() mc_route_destroy $rcv_if_name mc_route_destroy $send_if_name

+ if [ $skip_ptp = false ]; then + ip maddress add 01:1b:19:00:00:00 dev $rcv_if_name + send_raw $send_if_name "$PTP_1588_L2_SYNC" + send_raw $send_if_name "$PTP_1588_L2_FOLLOW_UP" + ip maddress del 01:1b:19:00:00:00 dev $rcv_if_name + + ip maddress add 01:80:c2:00:00:0e dev $rcv_if_name + send_raw $send_if_name "$PTP_1588_L2_PDELAY_REQ" + ip maddress del 01:80:c2:00:00:0e dev $rcv_if_name + + mc_join $rcv_if_name 224.0.1.129 + send_raw $send_if_name "$PTP_1588_IPV4_SYNC" + send_raw $send_if_name "$PTP_1588_IPV4_FOLLOW_UP" + mc_leave + + mc_join $rcv_if_name 224.0.0.107 + send_raw $send_if_name "$PTP_1588_IPV4_PDELAY_REQ" + mc_leave + + mc_join $rcv_if_name ff0e::181 + send_raw $send_if_name "$PTP_1588_IPV6_SYNC" + send_raw $send_if_name "$PTP_1588_IPV6_FOLLOW_UP" + mc_leave + + mc_join $rcv_if_name ff02::6b + send_raw $send_if_name "$PTP_1588_IPV6_PDELAY_REQ" + mc_leave + fi + sleep 1

tcpdump_stop $rcv_if_name @@ -212,6 +303,44 @@ run_test() "$smac > $UNKNOWN_MACV6_MC_ADDR3, ethertype IPv6 (0x86dd)" \ true "$test_name"

+ if [ $skip_ptp = false ]; then + check_rcv $rcv_if_name "1588v2 over L2 transport, Sync" \ + "ethertype PTP (0x88f7).* PTPv2.* msg type : sync msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over L2 transport, Follow-Up" \ + "ethertype PTP (0x88f7).* PTPv2.* msg type : follow up msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over L2 transport, Peer Delay Request" \ + "ethertype PTP (0x88f7).* PTPv2.* msg type : peer delay req msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over IPv4, Sync" \ + "ethertype IPv4 (0x0800).* PTPv2.* msg type : sync msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over IPv4, Follow-Up" \ + "ethertype IPv4 (0x0800).* PTPv2.* msg type : follow up msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over IPv4, Peer Delay Request" \ + "ethertype IPv4 (0x0800).* PTPv2.* msg type : peer delay req msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over IPv6, Sync" \ + "ethertype IPv6 (0x86dd).* PTPv2.* msg type : sync msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over IPv6, Follow-Up" \ + "ethertype IPv6 (0x86dd).* PTPv2.* msg type : follow up msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over IPv6, Peer Delay Request" \ + "ethertype IPv6 (0x86dd).* PTPv2.* msg type : peer delay req msg" \ + true "$test_name" + fi + tcpdump_cleanup $rcv_if_name }

@@ -293,6 +422,7 @@ macvlan_destroy() standalone() { local no_unicast_flt=true + local skip_ptp=false

if [ $(has_unicast_flt $h2) = yes ]; then no_unicast_flt=false @@ -302,7 +432,7 @@ standalone() h2_create macvlan_create $h2

- run_test $h1 $h2 $no_unicast_flt "$h2" + run_test $h1 $h2 $skip_ptp $no_unicast_flt "$h2"

macvlan_destroy h2_destroy @@ -313,13 +443,15 @@ test_bridge() { local no_unicast_flt=true local vlan_filtering=$1 + local skip_ptp=true

h1_create bridge_create $vlan_filtering simple_if_init br0 $H2_IPV4/24 $H2_IPV6/64 macvlan_create br0

- run_test $h1 br0 $no_unicast_flt "vlan_filtering=$vlan_filtering bridge" + run_test $h1 br0 $skip_ptp $no_unicast_flt \ + "vlan_filtering=$vlan_filtering bridge"

macvlan_destroy simple_if_fini br0 $H2_IPV4/24 $H2_IPV6/64 @@ -340,6 +472,7 @@ vlan_aware_bridge() test_vlan() { local no_unicast_flt=true + local skip_ptp=false

if [ $(has_unicast_flt $h2) = yes ]; then no_unicast_flt=false @@ -349,7 +482,7 @@ test_vlan() h2_vlan_create macvlan_create $h2.100

- run_test $h1.100 $h2.100 $no_unicast_flt "VLAN upper" + run_test $h1.100 $h2.100 $skip_ptp $no_unicast_flt "VLAN upper"

macvlan_destroy h2_vlan_destroy @@ -360,6 +493,7 @@ vlan_over_bridged_port() { local no_unicast_flt=true local vlan_filtering=$1 + local skip_ptp=false

# br_manage_promisc() will not force a single vlan_filtering port to # promiscuous mode, so we should still expect unicast filtering to take @@ -373,7 +507,7 @@ vlan_over_bridged_port() bridge_create $vlan_filtering macvlan_create $h2.100

- run_test $h1.100 $h2.100 $no_unicast_flt \ + run_test $h1.100 $h2.100 $skip_ptp $no_unicast_flt \ "VLAN over vlan_filtering=$vlan_filtering bridged port"

macvlan_destroy @@ -396,6 +530,7 @@ vlan_over_bridge() { local no_unicast_flt=true local vlan_filtering=$1 + local skip_ptp=true

h1_vlan_create bridge_create $vlan_filtering @@ -408,7 +543,7 @@ vlan_over_bridge() bridge vlan add dev br0 vid 100 self fi

- run_test $h1.100 br0.100 $no_unicast_flt \ + run_test $h1.100 br0.100 $skip_ptp $no_unicast_flt \ "VLAN over vlan_filtering=$vlan_filtering bridge"

if [ $vlan_filtering = 1 ]; then

Problem description -------------------

On an NXP LS1028A (felix DSA driver) with the following configuration:

- ocelot-8021q tagging protocol - VLAN-aware bridge (with STP) spanning at least swp0 and swp1 - 8021q VLAN upper interfaces on swp0 and swp1: swp0.700, swp1.700 - ptp4l on swp0.700 and swp1.700

we see that the ptp4l instances do not see each other's traffic, and they all go to the grand master state due to the ANNOUNCE_RECEIPT_TIMEOUT_EXPIRES condition.

Jumping to the conclusion for the impatient -------------------------------------------

There is a zero-day bug in the ocelot switchdev driver in the way it handles VLAN-tagged packet injection. The correct logic already exists in the source code, in function ocelot_xmit_get_vlan_info() added by commit 5ca721c54d86 ("net: dsa: tag_ocelot: set the classified VLAN during xmit"). But it is used only for normal NPI-based injection with the DSA "ocelot" tagging protocol. The other injection code paths (register-based and FDMA-based) roll their own wrong logic. This affects and was noticed on the DSA "ocelot-8021q" protocol because it uses register-based injection.

By moving ocelot_xmit_get_vlan_info() to a place that's common for both the DSA tagger and the ocelot switch library, it can also be called from ocelot_port_inject_frame() in ocelot.c.

We need to touch the lines with ocelot_ifh_port_set()'s prototype anyway, so let's rename it to something clearer regarding what it does, and add a kernel-doc. ocelot_ifh_set_basic() should do.

Investigation notes -------------------

Debugging reveals that PTP event (aka those carrying timestamps, like Sync) frames injected into swp0.700 (but also swp1.700) hit the wire with two VLAN tags:

00000000: 01 1b 19 00 00 00 00 01 02 03 04 05 81 00 02 bc ~~~~~~~~~~~ 00000010: 81 00 02 bc 88 f7 00 12 00 2c 00 00 02 00 00 00 ~~~~~~~~~~~ 00000020: 00 00 00 00 00 00 00 00 00 00 00 01 02 ff fe 03 00000030: 04 05 00 01 00 04 00 00 00 00 00 00 00 00 00 00 00000040: 00 00

The second (unexpected) VLAN tag makes felix_check_xtr_pkt() -> ptp_classify_raw() fail to see these as PTP packets at the link partner's receiving end, and return PTP_CLASS_NONE (because the BPF classifier is not written to expect 2 VLAN tags).

The reason why packets have 2 VLAN tags is because the transmission code treats VLAN incorrectly.

Neither ocelot switchdev, nor felix DSA, declare the NETIF_F_HW_VLAN_CTAG_TX feature. Therefore, at xmit time, all VLANs should be in the skb head, and none should be in the hwaccel area. This is done by:

static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb, netdev_features_t features) { if (skb_vlan_tag_present(skb) && !vlan_hw_offload_capable(features, skb->vlan_proto)) skb = __vlan_hwaccel_push_inside(skb); return skb; }

But ocelot_port_inject_frame() handles things incorrectly:

ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb));

void ocelot_ifh_port_set(struct sk_buff *skb, void *ifh, int port, u32 rew_op) { (...) if (vlan_tag) ocelot_ifh_set_vlan_tci(ifh, vlan_tag); (...) }

The way __vlan_hwaccel_push_inside() pushes the tag inside the skb head is by calling:

static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb) { skb->vlan_present = 0; }

which does _not_ zero out skb->vlan_tci as seen by skb_vlan_tag_get(). This means that ocelot, when it calls skb_vlan_tag_get(), sees (and uses) a residual skb->vlan_tci, while the same VLAN tag is _already_ in the skb head.

The trivial fix for double VLAN headers is to replace the content of ocelot_ifh_port_set() with:

if (skb_vlan_tag_present(skb)) ocelot_ifh_set_vlan_tci(ifh, skb_vlan_tag_get(skb));

but this would not be correct either, because, as mentioned, vlan_hw_offload_capable() is false for us, so we'd be inserting dead code and we'd always transmit packets with VID=0 in the injection frame header.

I can't actually test the ocelot switchdev driver and rely exclusively on code inspection, but I don't think traffic from 8021q uppers has ever been injected properly, and not double-tagged. Thus I'm blaming the introduction of VLAN fields in the injection header - early driver code.

As hinted at in the early conclusion, what we _want_ to happen for VLAN transmission was already described once in commit 5ca721c54d86 ("net: dsa: tag_ocelot: set the classified VLAN during xmit").

ocelot_xmit_get_vlan_info() intends to ensure that if the port through which we're transmitting is under a VLAN-aware bridge, the outer VLAN tag from the skb head is stripped from there and inserted into the injection frame header (so that the packet is processed in hardware through that actual VLAN). And in all other cases, the packet is sent with VID=0 in the injection frame header, since the port is VLAN-unaware and has logic to strip this VID on egress (making it invisible to the wire).

Fixes: 08d02364b12f ("net: mscc: fix the injection header") Signed-off-by: Vladimir Oltean vladimir.oltean@nxp.com --- drivers/net/ethernet/mscc/ocelot.c | 29 +++++++++++---- drivers/net/ethernet/mscc/ocelot_fdma.c | 2 +- include/linux/dsa/ocelot.h | 47 +++++++++++++++++++++++++ include/soc/mscc/ocelot.h | 3 +- net/dsa/tag_ocelot.c | 37 ++----------------- 5 files changed, 75 insertions(+), 43 deletions(-)

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index ed2fb44500b0..69a4e5a90475 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1193,17 +1193,34 @@ bool ocelot_can_inject(struct ocelot *ocelot, int grp) } EXPORT_SYMBOL(ocelot_can_inject);

-void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag) +/** + * ocelot_ifh_set_basic - Set basic information in Injection Frame Header + * @ifh: Pointer to Injection Frame Header memory + * @ocelot: Switch private data structure + * @port: Egress port number + * @rew_op: Egress rewriter operation for PTP + * @skb: Pointer to socket buffer (packet) + * + * Populate the Injection Frame Header with basic information for this skb: the + * analyzer bypass bit, destination port, VLAN info, egress rewriter info. + */ +void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port, + u32 rew_op, struct sk_buff *skb) { + struct ocelot_port *ocelot_port = ocelot->ports[port]; + u64 vlan_tci, tag_type; + + ocelot_xmit_get_vlan_info(skb, ocelot_port->bridge, &vlan_tci, + &tag_type); + ocelot_ifh_set_bypass(ifh, 1); ocelot_ifh_set_dest(ifh, BIT_ULL(port)); - ocelot_ifh_set_tag_type(ifh, IFH_TAG_TYPE_C); - if (vlan_tag) - ocelot_ifh_set_vlan_tci(ifh, vlan_tag); + ocelot_ifh_set_tag_type(ifh, tag_type); + ocelot_ifh_set_vlan_tci(ifh, vlan_tci); if (rew_op) ocelot_ifh_set_rew_op(ifh, rew_op); } -EXPORT_SYMBOL(ocelot_ifh_port_set); +EXPORT_SYMBOL(ocelot_ifh_set_basic);

void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb) @@ -1214,7 +1231,7 @@ void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, ocelot_write_rix(ocelot, QS_INJ_CTRL_GAP_SIZE(1) | QS_INJ_CTRL_SOF, QS_INJ_CTRL, grp);

- ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb)); + ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb);

for (i = 0; i < OCELOT_TAG_LEN / 4; i++) ocelot_write_rix(ocelot, ifh[i], QS_INJ_WR, grp); diff --git a/drivers/net/ethernet/mscc/ocelot_fdma.c b/drivers/net/ethernet/mscc/ocelot_fdma.c index 312a46832154..87b59cc5e441 100644 --- a/drivers/net/ethernet/mscc/ocelot_fdma.c +++ b/drivers/net/ethernet/mscc/ocelot_fdma.c @@ -666,7 +666,7 @@ static int ocelot_fdma_prepare_skb(struct ocelot *ocelot, int port, u32 rew_op, ifh = skb_push(skb, OCELOT_TAG_LEN); skb_put(skb, ETH_FCS_LEN); memset(ifh, 0, OCELOT_TAG_LEN); - ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb)); + ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb);

return 0; } diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index dca2969015d8..6fbfbde68a37 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -5,6 +5,8 @@ #ifndef _NET_DSA_TAG_OCELOT_H #define _NET_DSA_TAG_OCELOT_H

+#include <linux/if_bridge.h> +#include <linux/if_vlan.h> #include <linux/kthread.h> #include <linux/packing.h> #include <linux/skbuff.h> @@ -273,4 +275,49 @@ static inline u32 ocelot_ptp_rew_op(struct sk_buff *skb) return rew_op; }

+/** + * ocelot_xmit_get_vlan_info: Determine VLAN_TCI and TAG_TYPE for injected frame + * @skb: Pointer to socket buffer + * @br: Pointer to bridge device that the port is under, if any + * @vlan_tci: + * @tag_type: + * + * If the port is under a VLAN-aware bridge, remove the VLAN header from the + * payload and move it into the DSA tag, which will make the switch classify + * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero, + * which is the pvid of standalone ports (OCELOT_STANDALONE_PVID), although not + * of VLAN-unaware bridge ports (that would be ocelot_vlan_unaware_pvid()). + * Anyway, VID 0 is fine because it is stripped on egress for these port modes, + * and source address learning is not performed for packets injected from the + * CPU anyway, so it doesn't matter that the VID is "wrong". + */ +static inline void ocelot_xmit_get_vlan_info(struct sk_buff *skb, + struct net_device *br, + u64 *vlan_tci, u64 *tag_type) +{ + struct vlan_ethhdr *hdr; + u16 proto, tci; + + if (!br || !br_vlan_enabled(br)) { + *vlan_tci = 0; + *tag_type = IFH_TAG_TYPE_C; + return; + } + + hdr = (struct vlan_ethhdr *)skb_mac_header(skb); + br_vlan_get_proto(br, &proto); + + if (ntohs(hdr->h_vlan_proto) == proto) { + vlan_remove_tag(skb, &tci); + *vlan_tci = tci; + } else { + rcu_read_lock(); + br_vlan_get_pvid_rcu(br, &tci); + rcu_read_unlock(); + *vlan_tci = tci; + } + + *tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C; +} + #endif diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 6a37b29f4b4c..ed18e6bafc8d 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -969,7 +969,8 @@ void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target, bool ocelot_can_inject(struct ocelot *ocelot, int grp); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb); -void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag); +void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port, + u32 rew_op, struct sk_buff *skb); int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **skb); void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp); void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb, diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index e0e4300bfbd3..bf6608fc6be7 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -8,40 +8,6 @@ #define OCELOT_NAME "ocelot" #define SEVILLE_NAME "seville"

-/* If the port is under a VLAN-aware bridge, remove the VLAN header from the - * payload and move it into the DSA tag, which will make the switch classify - * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero, - * which is the pvid of standalone and VLAN-unaware bridge ports. - */ -static void ocelot_xmit_get_vlan_info(struct sk_buff *skb, struct dsa_port *dp, - u64 *vlan_tci, u64 *tag_type) -{ - struct net_device *br = dsa_port_bridge_dev_get(dp); - struct vlan_ethhdr *hdr; - u16 proto, tci; - - if (!br || !br_vlan_enabled(br)) { - *vlan_tci = 0; - *tag_type = IFH_TAG_TYPE_C; - return; - } - - hdr = skb_vlan_eth_hdr(skb); - br_vlan_get_proto(br, &proto); - - if (ntohs(hdr->h_vlan_proto) == proto) { - vlan_remove_tag(skb, &tci); - *vlan_tci = tci; - } else { - rcu_read_lock(); - br_vlan_get_pvid_rcu(br, &tci); - rcu_read_unlock(); - *vlan_tci = tci; - } - - *tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C; -} - static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, __be32 ifh_prefix, void **ifh) { @@ -53,7 +19,8 @@ static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, u32 rew_op = 0; u64 qos_class;

- ocelot_xmit_get_vlan_info(skb, dp, &vlan_tci, &tag_type); + ocelot_xmit_get_vlan_info(skb, dsa_port_bridge_dev_get(dp), &vlan_tci, + &tag_type);

qos_class = netdev_get_num_tc(netdev) ? netdev_get_prio_tc_map(netdev, skb->priority) : skb->priority;

As explained by Horatiu Vultur in commit 603ead96582d ("net: sparx5: Add spinlock for frame transmission from CPU") which is for a similar hardware design, multiple CPUs can simultaneously perform injection or extraction. There are only 2 register groups for injection and 2 for extraction, and the driver only uses one of each. So we'd better serialize access using spin locks, otherwise frame corruption is possible.

Note that unlike in sparx5, FDMA in ocelot does not have this issue because struct ocelot_fdma_tx_ring already contains an xmit_lock.

I guess this is mostly a problem for NXP LS1028A, as that is dual core. I don't think VSC7514 is. So I'm blaming the commit where LS1028A (aka the felix DSA driver) started using register-based packet injection and extraction.

Fixes: 0a6f17c6ae21 ("net: dsa: tag_ocelot_8021q: add support for PTP timestamping") Signed-off-by: Vladimir Oltean vladimir.oltean@nxp.com --- drivers/net/dsa/ocelot/felix.c | 11 +++++ drivers/net/ethernet/mscc/ocelot.c | 52 ++++++++++++++++++++++ drivers/net/ethernet/mscc/ocelot_vsc7514.c | 4 ++ include/soc/mscc/ocelot.h | 9 ++++ 4 files changed, 76 insertions(+)

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index e554699f06d4..8d31ff18c5c7 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -528,7 +528,9 @@ static int felix_tag_8021q_setup(struct dsa_switch *ds) * so we need to be careful that there are no extra frames to be * dequeued over MMIO, since we would never know to discard them. */ + ocelot_lock_xtr_grp_bh(ocelot, 0); ocelot_drain_cpu_queue(ocelot, 0); + ocelot_unlock_xtr_grp_bh(ocelot, 0);

return 0; } @@ -1518,6 +1520,8 @@ static void felix_port_deferred_xmit(struct kthread_work *work) int port = xmit_work->dp->index; int retries = 10;

+ ocelot_lock_inj_grp(ocelot, 0); + do { if (ocelot_can_inject(ocelot, 0)) break; @@ -1526,6 +1530,7 @@ static void felix_port_deferred_xmit(struct kthread_work *work) } while (--retries);

if (!retries) { + ocelot_unlock_inj_grp(ocelot, 0); dev_err(ocelot->dev, "port %d failed to inject skb\n", port); ocelot_port_purge_txtstamp_skb(ocelot, port, skb); @@ -1535,6 +1540,8 @@ static void felix_port_deferred_xmit(struct kthread_work *work)

ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb);

+ ocelot_unlock_inj_grp(ocelot, 0); + consume_skb(skb); kfree(xmit_work); } @@ -1694,6 +1701,8 @@ static bool felix_check_xtr_pkt(struct ocelot *ocelot) if (!felix->info->quirk_no_xtr_irq) return false;

+ ocelot_lock_xtr_grp(ocelot, grp); + while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) { struct sk_buff *skb; unsigned int type; @@ -1730,6 +1739,8 @@ static bool felix_check_xtr_pkt(struct ocelot *ocelot) ocelot_drain_cpu_queue(ocelot, 0); }

+ ocelot_unlock_xtr_grp(ocelot, grp); + return true; }

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 9301716e21d5..f4e027a6fe95 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1099,6 +1099,48 @@ void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb, } EXPORT_SYMBOL(ocelot_ptp_rx_timestamp);

+void ocelot_lock_inj_grp(struct ocelot *ocelot, int grp) + __acquires(&ocelot->inj_lock) +{ + spin_lock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_lock_inj_grp); + +void ocelot_unlock_inj_grp(struct ocelot *ocelot, int grp) + __releases(&ocelot->inj_lock) +{ + spin_unlock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_unlock_inj_grp); + +void ocelot_lock_xtr_grp(struct ocelot *ocelot, int grp) + __acquires(&ocelot->inj_lock) +{ + spin_lock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_lock_xtr_grp); + +void ocelot_unlock_xtr_grp(struct ocelot *ocelot, int grp) + __releases(&ocelot->inj_lock) +{ + spin_unlock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_unlock_xtr_grp); + +void ocelot_lock_xtr_grp_bh(struct ocelot *ocelot, int grp) + __acquires(&ocelot->xtr_lock) +{ + spin_lock_bh(&ocelot->xtr_lock); +} +EXPORT_SYMBOL_GPL(ocelot_lock_xtr_grp_bh); + +void ocelot_unlock_xtr_grp_bh(struct ocelot *ocelot, int grp) + __releases(&ocelot->xtr_lock) +{ + spin_unlock_bh(&ocelot->xtr_lock); +} +EXPORT_SYMBOL_GPL(ocelot_unlock_xtr_grp_bh); + int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **nskb) { u64 timestamp, src_port, len; @@ -1109,6 +1151,8 @@ int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **nskb) u32 val, *buf; int err;

+ lockdep_assert_held(&ocelot->xtr_lock); + err = ocelot_xtr_poll_xfh(ocelot, grp, xfh); if (err) return err; @@ -1184,6 +1228,8 @@ bool ocelot_can_inject(struct ocelot *ocelot, int grp) { u32 val = ocelot_read(ocelot, QS_INJ_STATUS);

+ lockdep_assert_held(&ocelot->inj_lock); + if (!(val & QS_INJ_STATUS_FIFO_RDY(BIT(grp)))) return false; if (val & QS_INJ_STATUS_WMARK_REACHED(BIT(grp))) @@ -1236,6 +1282,8 @@ void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 ifh[OCELOT_TAG_LEN / 4]; unsigned int i, count, last;

+ lockdep_assert_held(&ocelot->inj_lock); + ocelot_write_rix(ocelot, QS_INJ_CTRL_GAP_SIZE(1) | QS_INJ_CTRL_SOF, QS_INJ_CTRL, grp);

@@ -1272,6 +1320,8 @@ EXPORT_SYMBOL(ocelot_port_inject_frame);

void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp) { + lockdep_assert_held(&ocelot->xtr_lock); + while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) ocelot_read_rix(ocelot, QS_XTR_RD, grp); } @@ -2954,6 +3004,8 @@ int ocelot_init(struct ocelot *ocelot) mutex_init(&ocelot->fwd_domain_lock); spin_lock_init(&ocelot->ptp_clock_lock); spin_lock_init(&ocelot->ts_id_lock); + spin_lock_init(&ocelot->inj_lock); + spin_lock_init(&ocelot->xtr_lock);

ocelot->owq = alloc_ordered_workqueue("ocelot-owq", 0); if (!ocelot->owq) diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c index 993212c3a7da..c09dd2e3343c 100644 --- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c +++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c @@ -51,6 +51,8 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg) struct ocelot *ocelot = arg; int grp = 0, err;

+ ocelot_lock_xtr_grp(ocelot, grp); + while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) { struct sk_buff *skb;

@@ -69,6 +71,8 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg) if (err < 0) ocelot_drain_cpu_queue(ocelot, 0);

+ ocelot_unlock_xtr_grp(ocelot, grp); + return IRQ_HANDLED; }

diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index ed18e6bafc8d..462c653e1017 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -813,6 +813,9 @@ struct ocelot { const u32 *const *map; struct list_head stats_regions;

+ spinlock_t inj_lock; + spinlock_t xtr_lock; + u32 pool_size[OCELOT_SB_NUM][OCELOT_SB_POOL_NUM]; int packet_buffer_size; int num_frame_refs; @@ -966,6 +969,12 @@ void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target, u32 val, u32 reg, u32 offset);

/* Packet I/O */ +void ocelot_lock_inj_grp(struct ocelot *ocelot, int grp); +void ocelot_unlock_inj_grp(struct ocelot *ocelot, int grp); +void ocelot_lock_xtr_grp(struct ocelot *ocelot, int grp); +void ocelot_unlock_xtr_grp(struct ocelot *ocelot, int grp); +void ocelot_lock_xtr_grp_bh(struct ocelot *ocelot, int grp); +void ocelot_unlock_xtr_grp_bh(struct ocelot *ocelot, int grp); bool ocelot_can_inject(struct ocelot *ocelot, int grp); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb);

There is a major design bug with ocelot-8021q, which is that it expects more of the hardware than the hardware can actually do. The short summary of the issue is that when a port is under a VLAN-aware bridge and we use this tagging protocol, VLAN upper interfaces of this port do not see RX traffic.

We use VCAP ES0 (egress rewriter) rules towards the tag_8021q CPU port to encapsulate packets with an outer tag, later stripped by software, that depends on the source user port. We do this so that packets can be identified in ocelot_rcv(). To be precise, we create rules with push_outer_tag = OCELOT_ES0_TAG and push_inner_tag = 0.

With this configuration, we expect the switch to keep the inner tag configuration as found in the packet (if it was untagged on user port ingress, keep it untagged, otherwise preserve the VLAN tag unmodified as the inner tag towards the tag_8021q CPU port). But this is not what happens.

Instead, table "Tagging Combinations" from the user manual suggests that when the ES0 action is "PUSH_OUTER_TAG=1 and PUSH_INNER_TAG=0", there will be "no inner tag". Experimentation further clarifies what this means.

It appears that this "inner tag" which is not pushed into the packet on its egress towards the CPU is none other than the classified VLAN.

When the ingress user port is standalone or under a VLAN-unaware bridge, the classified VLAN is a discardable quantity: it is a fixed value - the result of ocelot_vlan_unaware_pvid()'s configuration, and actually independent of the VID from any 802.1Q header that may be in the frame. It is actually preferable to discard the "inner tag" in this case.

The problem is when the ingress port is under a VLAN-aware bridge. Then, the classified VLAN is taken from the frame's 802.1Q header, with a fallback on the bridge port's PVID. It would be very good to not discard the "inner tag" here, because if we do, we break communication with any 8021q VLAN uppers that the port might have. These have a processing path outside the bridge.

There seems to be nothing else we can do except to change the configuration for VCAP ES0 rules, to actually push the inner VLAN into the frame. There are 2 options for that, first is to push a fixed value specified in the rule, and second is to push a fixed value, plus (aka arithmetic +) the classified VLAN. We choose the second option, and we select that fixed value as 0. Thus, what is pushed in the inner tag is just the classified VLAN.

From there, we need to perform software untagging, in the receive path, of stuff that was untagged on the wire.

Fixes: 7c83a7c539ab ("net: dsa: add a second tagger for Ocelot switches based on tag_8021q") Signed-off-by: Vladimir Oltean vladimir.oltean@nxp.com --- drivers/net/dsa/ocelot/felix.c | 115 +++++++++++++++++++++++++++++++-- 1 file changed, 109 insertions(+), 6 deletions(-)

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 8d31ff18c5c7..4a705f7333f4 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -61,11 +61,46 @@ static int felix_cpu_port_for_conduit(struct dsa_switch *ds, return cpu_dp->index; }

+/** + * felix_update_tag_8021q_rx_rule - Update VCAP ES0 tag_8021q rule after + * vlan_filtering change + * @outer_tagging_rule: Pointer to VCAP filter on which the update is performed + * @vlan_filtering: Current bridge VLAN filtering setting + * + * Source port identification for tag_8021q is done using VCAP ES0 rules on the + * CPU port(s). The ES0 tag B (inner tag from the packet) can be configured as + * either: + * - push_inner_tag=0: the inner tag is never pushed into the frame + * (and we lose info about the classified VLAN). This is + * good when the classified VLAN is a discardable quantity + * for the software RX path: it is either set to + * OCELOT_STANDALONE_PVID, or to + * ocelot_vlan_unaware_pvid(bridge). + * - push_inner_tag=1: the inner tag is always pushed. This is good when the + * classified VLAN is not a discardable quantity (the port + * is under a VLAN-aware bridge, and software needs to + * continue processing the packet in the same VLAN as the + * hardware). + * The point is that what is good for a VLAN-unaware port is not good for a + * VLAN-aware port, and vice versa. Thus, the RX tagging rules must be kept in + * sync with the VLAN filtering state of the port. + */ +static void +felix_update_tag_8021q_rx_rule(struct ocelot_vcap_filter *outer_tagging_rule, + bool vlan_filtering) +{ + if (vlan_filtering) + outer_tagging_rule->action.push_inner_tag = OCELOT_ES0_TAG; + else + outer_tagging_rule->action.push_inner_tag = OCELOT_NO_ES0_TAG; +} + /* Set up VCAP ES0 rules for pushing a tag_8021q VLAN towards the CPU such that * the tagger can perform RX source port identification. */ static int felix_tag_8021q_vlan_add_rx(struct dsa_switch *ds, int port, - int upstream, u16 vid) + int upstream, u16 vid, + bool vlan_filtering) { struct ocelot_vcap_filter *outer_tagging_rule; struct ocelot *ocelot = ds->priv; @@ -96,6 +131,14 @@ static int felix_tag_8021q_vlan_add_rx(struct dsa_switch *ds, int port, outer_tagging_rule->action.tag_a_tpid_sel = OCELOT_TAG_TPID_SEL_8021AD; outer_tagging_rule->action.tag_a_vid_sel = 1; outer_tagging_rule->action.vid_a_val = vid; + felix_update_tag_8021q_rx_rule(outer_tagging_rule, vlan_filtering); + outer_tagging_rule->action.tag_b_tpid_sel = OCELOT_TAG_TPID_SEL_8021Q; + /* Leave TAG_B_VID_SEL at 0 (Classified VID + VID_B_VAL). Since we also + * leave VID_B_VAL at 0, this makes ES0 tag B (the inner tag) equal to + * the classified VID, which we need to see in the DSA tagger's receive + * path. Note: the inner tag is only visible in the packet when pushed + * (push_inner_tag == OCELOT_ES0_TAG). + */

err = ocelot_vcap_filter_add(ocelot, outer_tagging_rule, NULL); if (err) @@ -227,6 +270,7 @@ static int felix_tag_8021q_vlan_del_tx(struct dsa_switch *ds, int port, u16 vid) static int felix_tag_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid, u16 flags) { + struct dsa_port *dp = dsa_to_port(ds, port); struct dsa_port *cpu_dp; int err;

@@ -234,11 +278,12 @@ static int felix_tag_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid, * membership, which we aren't. So we don't need to add any VCAP filter * for the CPU port. */ - if (!dsa_is_user_port(ds, port)) + if (!dsa_port_is_user(dp)) return 0;

dsa_switch_for_each_cpu_port(cpu_dp, ds) { - err = felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid); + err = felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid, + dsa_port_is_vlan_filtering(dp)); if (err) return err; } @@ -258,10 +303,11 @@ static int felix_tag_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid,

static int felix_tag_8021q_vlan_del(struct dsa_switch *ds, int port, u16 vid) { + struct dsa_port *dp = dsa_to_port(ds, port); struct dsa_port *cpu_dp; int err;

- if (!dsa_is_user_port(ds, port)) + if (!dsa_port_is_user(dp)) return 0;

dsa_switch_for_each_cpu_port(cpu_dp, ds) { @@ -278,11 +324,41 @@ static int felix_tag_8021q_vlan_del(struct dsa_switch *ds, int port, u16 vid)

del_tx_failed: dsa_switch_for_each_cpu_port(cpu_dp, ds) - felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid); + felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid, + dsa_port_is_vlan_filtering(dp));

return err; }

+static int felix_update_tag_8021q_rx_rules(struct dsa_switch *ds, int port, + bool vlan_filtering) +{ + struct ocelot_vcap_filter *outer_tagging_rule; + struct ocelot_vcap_block *block_vcap_es0; + struct ocelot *ocelot = ds->priv; + struct dsa_port *cpu_dp; + unsigned long cookie; + int err; + + block_vcap_es0 = &ocelot->block[VCAP_ES0]; + + dsa_switch_for_each_cpu_port(cpu_dp, ds) { + cookie = OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN(ocelot, port, + cpu_dp->index); + + outer_tagging_rule = ocelot_vcap_block_find_filter_by_id(block_vcap_es0, + cookie, false); + + felix_update_tag_8021q_rx_rule(outer_tagging_rule, vlan_filtering); + + err = ocelot_vcap_filter_replace(ocelot, outer_tagging_rule); + if (err) + return err; + } + + return 0; +} + static int felix_trap_get_cpu_port(struct dsa_switch *ds, const struct ocelot_vcap_filter *trap) { @@ -532,6 +608,16 @@ static int felix_tag_8021q_setup(struct dsa_switch *ds) ocelot_drain_cpu_queue(ocelot, 0); ocelot_unlock_xtr_grp_bh(ocelot, 0);

+ /* Problem: when using push_inner_tag=1 for ES0 tag B, we lose info + * about whether the received packets were VLAN-tagged on the wire, + * since they are always tagged on egress towards the CPU port. + * + * Since using push_inner_tag=1 is unavoidable for VLAN-aware bridges, + * we must work around the fallout by untagging in software to make + * untagged reception work more or less as expected. + */ + ds->untag_vlan_aware_bridge_pvid = true; + return 0; }

@@ -556,6 +642,8 @@ static void felix_tag_8021q_teardown(struct dsa_switch *ds) ocelot_port_teardown_dsa_8021q_cpu(ocelot, dp->index);

dsa_tag_8021q_unregister(ds); + + ds->untag_vlan_aware_bridge_pvid = false; }

static unsigned long felix_tag_8021q_get_host_fwd_mask(struct dsa_switch *ds) @@ -1010,8 +1098,23 @@ static int felix_vlan_filtering(struct dsa_switch *ds, int port, bool enabled, struct netlink_ext_ack *extack) { struct ocelot *ocelot = ds->priv; + bool using_tag_8021q; + struct felix *felix; + int err;

- return ocelot_port_vlan_filtering(ocelot, port, enabled, extack); + err = ocelot_port_vlan_filtering(ocelot, port, enabled, extack); + if (err) + return err; + + felix = ocelot_to_felix(ocelot); + using_tag_8021q = felix->tag_proto == DSA_TAG_PROTO_OCELOT_8021Q; + if (using_tag_8021q) { + err = felix_update_tag_8021q_rx_rules(ds, port, enabled); + if (err) + return err; + } + + return 0; }

static int felix_vlan_add(struct dsa_switch *ds, int port,