Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 804 insertions, 0 deletions

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh
new file mode 100755
index 000000000..ac97f07e5
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh
@@ -0,0 +1,804 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +-----------------------+                          +------------------------+
+# | H1 (vrf)              |                          | H2 (vrf)               |
+# |    + $h1              |                          |    + $h2               |
+# |    | 192.0.2.1/28     |                          |    | 192.0.2.2/28      |
+# |    | 2001:db8:1::1/64 |                          |    | 2001:db8:1::2/64  |
+# +----|------------------+                          +----|-------------------+
+#      |                                                  |
+# +----|--------------------------------------------------|-------------------+
+# | SW |                                                  |                   |
+# | +--|--------------------------------------------------|-----------------+ |
+# | |  + $swp1                   BR1 (802.1d)             + $swp2           | |
+# | |                                                                       | |
+# | |  + vx1 (vxlan)                                                        | |
+# | |    local 2001:db8:3::1                                                | |
+# | |    remote 2001:db8:4::1 2001:db8:5::1                                 | |
+# | |    id 1000 dstport $VXPORT                                            | |
+# | +-----------------------------------------------------------------------+ |
+# |                                                                           |
+# |  2001:db8:4::0/64 via 2001:db8:3::2                                       |
+# |  2001:db8:5::0/64 via 2001:db8:3::2                                       |
+# |                                                                           |
+# |    + $rp1                                                                 |
+# |    | 2001:db8:3::1/64                                                     |
+# +----|----------------------------------------------------------------------+
+#      |
+# +----|----------------------------------------------------------+
+# |    |                                             VRP2 (vrf)   |
+# |    + $rp2                                                     |
+# |      2001:db8:3::2/64                                         |
+# |                                                               |  (maybe) HW
+# =============================================================================
+# |                                                               |  (likely) SW
+# |    + v1 (veth)                             + v3 (veth)        |
+# |    | 2001:db8:4::2/64                      | 2001:db8:5::2/64 |
+# +----|---------------------------------------|------------------+
+#      |                                       |
+# +----|--------------------------------+ +----|-------------------------------+
+# |    + v2 (veth)        NS1 (netns)   | |    + v4 (veth)        NS2 (netns)  |
+# |      2001:db8:4::1/64               | |      2001:db8:5::1/64              |
+# |                                     | |                                    |
+# | 2001:db8:3::0/64 via 2001:db8:4::2  | | 2001:db8:3::0/64 via 2001:db8:5::2 |
+# | 2001:db8:5::1/128 via 2001:db8:4::2 | | 2001:db8:4::1/128 via              |
+# |                                     | |         2001:db8:5::2              |
+# |                                     | |                                    |
+# | +-------------------------------+   | | +-------------------------------+  |
+# | |                  BR2 (802.1d) |   | | |                  BR2 (802.1d) |  |
+# | |  + vx2 (vxlan)                |   | | |  + vx2 (vxlan)                |  |
+# | |    local 2001:db8:4::1        |   | | |    local 2001:db8:5::1        |  |
+# | |    remote 2001:db8:3::1       |   | | |    remote 2001:db8:3::1       |  |
+# | |    remote 2001:db8:5::1       |   | | |    remote 2001:db8:4::1       |  |
+# | |    id 1000 dstport $VXPORT    |   | | |    id 1000 dstport $VXPORT    |  |
+# | |                               |   | | |                               |  |
+# | |  + w1 (veth)                  |   | | |  + w1 (veth)                  |  |
+# | +--|----------------------------+   | | +--|----------------------------+  |
+# |    |                                | |    |                               |
+# | +--|----------------------------+   | | +--|----------------------------+  |
+# | |  + w2 (veth)        VW2 (vrf) |   | | |  + w2 (veth)        VW2 (vrf) |  |
+# | |    192.0.2.3/28               |   | | |    192.0.2.4/28               |  |
+# | |    2001:db8:1::3/64           |   | | |    2001:db8:1::4/64           |  |
+# | +-------------------------------+   | | +-------------------------------+  |
+# +-------------------------------------+ +------------------------------------+
+
+: ${VXPORT:=4789}
+export VXPORT
+
+: ${ALL_TESTS:="
+	ping_ipv4
+	ping_ipv6
+	test_flood
+	test_unicast
+	test_ttl
+	test_tos
+	test_ecn_encap
+	test_ecn_decap
+	reapply_config
+	ping_ipv4
+	ping_ipv6
+	test_flood
+	test_unicast
+"}
+
+NUM_NETIFS=6
+source lib.sh
+source tc_common.sh
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64
+	tc qdisc add dev $h1 clsact
+}
+
+h1_destroy()
+{
+	tc qdisc del dev $h1 clsact
+	simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64
+}
+
+h2_create()
+{
+	simple_if_init $h2 192.0.2.2/28 2001:db8:1::2/64
+	tc qdisc add dev $h2 clsact
+}
+
+h2_destroy()
+{
+	tc qdisc del dev $h2 clsact
+	simple_if_fini $h2 192.0.2.2/28 2001:db8:1::2/64
+}
+
+rp1_set_addr()
+{
+	ip address add dev $rp1 2001:db8:3::1/64
+
+	ip route add 2001:db8:4::0/64 nexthop via 2001:db8:3::2
+	ip route add 2001:db8:5::0/64 nexthop via 2001:db8:3::2
+}
+
+rp1_unset_addr()
+{
+	ip route del 2001:db8:5::0/64 nexthop via 2001:db8:3::2
+	ip route del 2001:db8:4::0/64 nexthop via 2001:db8:3::2
+
+	ip address del dev $rp1 2001:db8:3::1/64
+}
+
+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
+	tc qdisc add dev $rp1 clsact
+
+	ip link add name vx1 type vxlan id 1000	local 2001:db8:3::1 \
+		dstport "$VXPORT" nolearning udp6zerocsumrx udp6zerocsumtx \
+		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
+	tc qdisc add dev $swp1 clsact
+
+	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 2001:db8:4::1 self
+	bridge fdb append dev vx1 00:00:00:00:00:00 dst 2001:db8:5::1 self
+}
+
+switch_destroy()
+{
+	bridge fdb del dev vx1 00:00:00:00:00:00 dst 2001:db8:5::1 self
+	bridge fdb del dev vx1 00:00:00:00:00:00 dst 2001:db8:4::1 self
+
+	ip link set dev $swp2 down
+	ip link set dev $swp2 nomaster
+
+	tc qdisc del dev $swp1 clsact
+	ip link set dev $swp1 down
+	ip link set dev $swp1 nomaster
+
+	ip link set dev vx1 nomaster
+	ip link set dev vx1 down
+	ip link del dev vx1
+
+	tc qdisc del dev $rp1 clsact
+	rp1_unset_addr
+	ip link set dev $rp1 down
+
+	ip link set dev br1 down
+	ip link del dev br1
+}
+
+vrp2_create()
+{
+	simple_if_init $rp2 2001:db8:3::2/64
+	__simple_if_init v1 v$rp2 2001:db8:4::2/64
+	__simple_if_init v3 v$rp2 2001:db8:5::2/64
+	tc qdisc add dev v1 clsact
+}
+
+vrp2_destroy()
+{
+	tc qdisc del dev v1 clsact
+	__simple_if_fini v3 2001:db8:5::2/64
+	__simple_if_fini v1 2001:db8:4::2/64
+	simple_if_fini $rp2 2001:db8:3::2/64
+}
+
+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_ipv4=$1; shift
+	local host_addr_ipv6=$1; shift
+
+	ip link set dev $in_if up
+	ip address add dev $in_if $in_addr/64
+	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" udp6zerocsumrx
+	ip link set dev vx2 up
+	bridge fdb append dev vx2 00:00:00:00:00:00 dst 2001:db8:3::1 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_ipv4/28 $host_addr_ipv6/64
+
+	ip route add 2001:db8:3::0/64 nexthop via $nh_addr
+	ip route add $other_in_addr/128 nexthop via $nh_addr
+}
+export -f ns_init_common
+
+ns1_create()
+{
+	ip netns add ns1
+	ip link set dev v2 netns ns1
+	in_ns ns1 \
+	      ns_init_common v2 2001:db8:4::1 2001:db8:5::1 2001:db8:4::2 \
+	      192.0.2.3 2001:db8:1::3
+}
+
+ns1_destroy()
+{
+	ip netns exec ns1 ip link set dev v2 netns 1
+	ip netns del ns1
+}
+
+ns2_create()
+{
+	ip netns add ns2
+	ip link set dev v4 netns ns2
+	in_ns ns2 \
+	      ns_init_common v4 2001:db8:5::1 2001:db8:4::1 2001:db8:5::2 \
+	      192.0.2.4 2001:db8:1::4
+}
+
+ns2_destroy()
+{
+	ip netns exec ns2 ip link set dev v4 netns 1
+	ip netns del ns2
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	rp1=${NETIFS[p5]}
+	rp2=${NETIFS[p6]}
+
+	vrf_prepare
+	forwarding_enable
+
+	h1_create
+	h2_create
+	switch_create
+
+	ip link add name v1 type veth peer name v2
+	ip link add name v3 type veth peer name v4
+	vrp2_create
+	ns1_create
+	ns2_create
+
+	r1_mac=$(in_ns ns1 mac_get w2)
+	r2_mac=$(in_ns ns2 mac_get w2)
+	h2_mac=$(mac_get $h2)
+}
+
+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
+}
+
+# For the first round of tests, vx1 is the first device to get
+# attached to the bridge, and at that point the local IP is already
+# configured. Try the other scenario of attaching the devices to a an
+# already-offloaded bridge, and only then assign the local IP.
+reapply_config()
+{
+	log_info "Reapplying configuration"
+
+	bridge fdb del dev vx1 00:00:00:00:00:00 dst 2001:db8:5::1 self
+	bridge fdb del dev vx1 00:00:00:00:00:00 dst 2001:db8:4::1 self
+	ip link set dev vx1 nomaster
+	rp1_unset_addr
+	sleep 5
+
+	ip link set dev vx1 master br1
+	bridge fdb append dev vx1 00:00:00:00:00:00 dst 2001:db8:4::1 self
+	bridge fdb append dev vx1 00:00:00:00:00:00 dst 2001:db8:5::1 self
+	sleep 1
+	rp1_set_addr
+	sleep 5
+}
+
+__ping_ipv4()
+{
+	local vxlan_local_ip=$1; shift
+	local vxlan_remote_ip=$1; shift
+	local src_ip=$1; shift
+	local dst_ip=$1; shift
+	local dev=$1; shift
+	local info=$1; shift
+
+	RET=0
+
+	tc filter add dev $rp1 egress protocol ipv6 pref 1 handle 101 \
+		flower ip_proto udp src_ip $vxlan_local_ip \
+		dst_ip $vxlan_remote_ip dst_port $VXPORT $TC_FLAG action pass
+	# Match ICMP-reply packets after decapsulation, so source IP is
+	# destination IP of the ping and destination IP is source IP of the
+	# ping.
+	tc filter add dev $swp1 egress protocol ip pref 1 handle 101 \
+		flower src_ip $dst_ip dst_ip $src_ip \
+		$TC_FLAG action pass
+
+	# Send 100 packets and verify that at least 100 packets hit the rule,
+	# to overcome ARP noise.
+	PING_COUNT=100 PING_TIMEOUT=11 ping_do $dev $dst_ip
+	check_err $? "Ping failed"
+
+	tc_check_at_least_x_packets "dev $rp1 egress" 101 10 100
+	check_err $? "Encapsulated packets did not go through router"
+
+	tc_check_at_least_x_packets "dev $swp1 egress" 101 10 100
+	check_err $? "Decapsulated packets did not go through switch"
+
+	log_test "ping: $info"
+
+	tc filter del dev $swp1 egress
+	tc filter del dev $rp1 egress
+}
+
+ping_ipv4()
+{
+	RET=0
+
+	local local_sw_ip=2001:db8:3::1
+	local remote_ns1_ip=2001:db8:4::1
+	local remote_ns2_ip=2001:db8:5::1
+	local h1_ip=192.0.2.1
+	local w2_ns1_ip=192.0.2.3
+	local w2_ns2_ip=192.0.2.4
+
+	ping_test $h1 192.0.2.2 ": local->local"
+
+	__ping_ipv4 $local_sw_ip $remote_ns1_ip $h1_ip $w2_ns1_ip $h1 \
+		"local->remote 1"
+	__ping_ipv4 $local_sw_ip $remote_ns2_ip $h1_ip $w2_ns2_ip $h1 \
+		"local->remote 2"
+}
+
+__ping_ipv6()
+{
+	local vxlan_local_ip=$1; shift
+	local vxlan_remote_ip=$1; shift
+	local src_ip=$1; shift
+	local dst_ip=$1; shift
+	local dev=$1; shift
+	local info=$1; shift
+
+	RET=0
+
+	tc filter add dev $rp1 egress protocol ipv6 pref 1 handle 101 \
+		flower ip_proto udp src_ip $vxlan_local_ip \
+		dst_ip $vxlan_remote_ip dst_port $VXPORT $TC_FLAG action pass
+	# Match ICMP-reply packets after decapsulation, so source IP is
+	# destination IP of the ping and destination IP is source IP of the
+	# ping.
+	tc filter add dev $swp1 egress protocol ipv6 pref 1 handle 101 \
+		flower src_ip $dst_ip dst_ip $src_ip $TC_FLAG action pass
+
+	# Send 100 packets and verify that at least 100 packets hit the rule,
+	# to overcome neighbor discovery noise.
+	PING_COUNT=100 PING_TIMEOUT=11 ping6_do $dev $dst_ip
+	check_err $? "Ping failed"
+
+	tc_check_at_least_x_packets "dev $rp1 egress" 101 100
+	check_err $? "Encapsulated packets did not go through router"
+
+	tc_check_at_least_x_packets "dev $swp1 egress" 101 100
+	check_err $? "Decapsulated packets did not go through switch"
+
+	log_test "ping6: $info"
+
+	tc filter del dev $swp1 egress
+	tc filter del dev $rp1 egress
+}
+
+ping_ipv6()
+{
+	RET=0
+
+	local local_sw_ip=2001:db8:3::1
+	local remote_ns1_ip=2001:db8:4::1
+	local remote_ns2_ip=2001:db8:5::1
+	local h1_ip=2001:db8:1::1
+	local w2_ns1_ip=2001:db8:1::3
+	local w2_ns2_ip=2001:db8:1::4
+
+	ping6_test $h1 2001:db8:1::2 ": local->local"
+
+	__ping_ipv6 $local_sw_ip $remote_ns1_ip $h1_ip $w2_ns1_ip $h1 \
+		"local->remote 1"
+	__ping_ipv6 $local_sw_ip $remote_ns2_ip $h1_ip $w2_ns2_ip $h1 \
+		"local->remote 2"
+}
+
+maybe_in_ns()
+{
+	echo ${1:+in_ns} $1
+}
+
+__flood_counter_add_del()
+{
+	local add_del=$1; shift
+	local dst_ip=$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) tc filter $add_del dev "$dev" ingress \
+	   proto ipv6 pref 100 flower dst_ip $dst_ip ip_proto \
+	   icmpv6 skip_sw action pass 2>/dev/null || \
+	$(maybe_in_ns $ns) tc filter $add_del dev "$dev" ingress \
+	   proto ipv6 pref 100 flower dst_ip $dst_ip ip_proto \
+	   icmpv6 skip_hw action pass
+}
+
+flood_counter_install()
+{
+	__flood_counter_add_del add "$@"
+}
+
+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 $dst $counter
+	done
+
+	local -a t0s=($(flood_fetch_stats "${counters[@]}"))
+	$MZ -6 $h1 -c 10 -d 100msec -p 64 -b $mac -B $dst -t icmp6 type=128 -q
+	sleep 1
+	local -a t1s=($(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 $dst $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 2001:db8:1::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 2001:db8:4::1"
+			  "$r2_mac vx1 2001:db8:5::1")
+	local target
+
+	for target in "${targets[@]}"; do
+		vxlan_fdb_add_del add $target
+	done
+
+	__test_unicast $h2_mac 2001:db8:1::2 0 "local MAC unicast"
+	__test_unicast $r1_mac 2001:db8:1::3 1 "remote MAC 1 unicast"
+	__test_unicast $r2_mac 2001:db8:1::4 2 "remote MAC 2 unicast"
+
+	for target in "${targets[@]}"; do
+		vxlan_fdb_add_del del $target
+	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)
+	ping6_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 protocol ipv6 \
+		flower ip_ttl 99 action pass
+	vxlan_ping_test $h1 2001:db8:1::3 "" v1 egress 77 10
+	tc filter del dev v1 egress pref 77 protocol ipv6
+
+	log_test "VXLAN: envelope TTL"
+}
+
+test_tos()
+{
+	RET=0
+
+	tc filter add dev v1 egress pref 77 protocol ipv6 \
+		flower ip_tos 0x14 action pass
+	vxlan_ping_test $h1 2001:db8:1::3 "-Q 0x14" v1 egress 77 10
+	vxlan_ping_test $h1 2001:db8:1::3 "-Q 0x18" v1 egress 77 0
+	tc filter del dev v1 egress pref 77 protocol ipv6
+
+	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 protocol ipv6 \
+		flower ip_tos $tos action pass
+	sleep 1
+	vxlan_ping_test $h1 2001:db8:1::3 "-Q $q" v1 egress 77 10
+	tc filter del dev v1 egress pref 77 protocol ipv6
+
+	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
+}
+
+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
+	local saddr="20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:03"
+	local daddr="20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:01"
+
+	$MZ -6 $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
+		    )"86:dd:"$(                   : ETH type
+		    )"6"$(			  : IP version
+		    )"$inner_tos"$(               : Traffic class
+		    )"0:00:00:"$(                 : Flow label
+		    )"00:08:"$(                   : Payload length
+		    )"3a:"$(                      : Next header
+		    )"04:"$(                      : Hop limit
+		    )"$saddr:"$(		  : IP saddr
+		    )"$daddr:"$(		  : IP daddr
+		    )"80:"$(			  : ICMPv6.type
+		    )"00:"$(			  : ICMPv6.code
+		    )"00:"$(			  : ICMPv6.checksum
+		    )
+}
+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 $outer_tos
+	sleep 1
+	local t1=$($stat_get)
+	local delta=$((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 protocol ipv6 \
+		flower src_ip 2001:db8:1::3 dst_ip 2001:db8:1::1 \
+		ip_tos $decapped_tos action drop
+	sleep 1
+	vxlan_encapped_ping_test v2 v1 2001:db8:3::1 \
+				 $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="0:0"
+	local orig_outer_tos=03
+
+	RET=0
+
+	vxlan_encapped_ping_test v2 v1 2001:db8:3::1 \
+				 $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 "0:0" 00 0x00
+	__test_ecn_decap "0:0" 01 0x00
+	__test_ecn_decap "0:0" 02 0x00
+	# 00 03 is tested in test_ecn_decap_error()
+	__test_ecn_decap "0:1" 00 0x01
+	__test_ecn_decap "0:1" 01 0x01
+	__test_ecn_decap "0:1" 02 0x01
+	__test_ecn_decap "0:1" 03 0x03
+	__test_ecn_decap "0:2" 00 0x02
+	__test_ecn_decap "0:2" 01 0x01
+	__test_ecn_decap "0:2" 02 0x02
+	__test_ecn_decap "0:2" 03 0x03
+	__test_ecn_decap "0:3" 00 0x03
+	__test_ecn_decap "0:3" 01 0x03
+	__test_ecn_decap "0:3" 02 0x03
+	__test_ecn_decap "0:3" 03 0x03
+	test_ecn_decap_error
+}
+
+test_all()
+{
+	log_info "Running tests with UDP port $VXPORT"
+	tests_run
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+test_all
+
+exit $EXIT_STATUS