From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next 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(). ... --- .../testing/selftests/drivers/net/bonding/Makefile | 17 ++ .../net/bonding/bond-arp-interval-causes-panic.sh | 49 +++++ .../drivers/net/bonding/bond-break-lacpdu-tx.sh | 81 +++++++ .../drivers/net/bonding/bond-lladdr-target.sh | 65 ++++++ tools/testing/selftests/drivers/net/bonding/config | 2 + .../drivers/net/bonding/dev_addr_lists.sh | 109 +++++++++ .../selftests/drivers/net/bonding/lag_lib.sh | 167 ++++++++++++++ .../drivers/net/bonding/mode-1-recovery-updelay.sh | 45 ++++ .../drivers/net/bonding/mode-2-recovery-updelay.sh | 45 ++++ .../drivers/net/bonding/net_forwarding_lib.sh | 1 + .../selftests/drivers/net/bonding/option_prio.sh | 245 +++++++++++++++++++++ .../testing/selftests/drivers/net/bonding/settings | 1 + 12 files changed, 827 insertions(+) create mode 100644 tools/testing/selftests/drivers/net/bonding/Makefile create mode 100755 tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh create mode 100755 tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh create mode 100755 tools/testing/selftests/drivers/net/bonding/bond-lladdr-target.sh create mode 100644 tools/testing/selftests/drivers/net/bonding/config create mode 100755 tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh create mode 100644 tools/testing/selftests/drivers/net/bonding/lag_lib.sh create mode 100755 tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh create mode 100755 tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh create mode 120000 tools/testing/selftests/drivers/net/bonding/net_forwarding_lib.sh create mode 100755 tools/testing/selftests/drivers/net/bonding/option_prio.sh create mode 100644 tools/testing/selftests/drivers/net/bonding/settings (limited to 'tools/testing/selftests/drivers/net/bonding') diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile new file mode 100644 index 000000000..8e3b786a7 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/Makefile @@ -0,0 +1,17 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for net selftests + +TEST_PROGS := \ + bond-arp-interval-causes-panic.sh \ + bond-break-lacpdu-tx.sh \ + bond-lladdr-target.sh \ + dev_addr_lists.sh \ + mode-1-recovery-updelay.sh \ + mode-2-recovery-updelay.sh \ + option_prio.sh + +TEST_FILES := \ + lag_lib.sh \ + net_forwarding_lib.sh + +include ../../../lib.mk diff --git a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh new file mode 100755 index 000000000..71c00bfaf --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh @@ -0,0 +1,49 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# cause kernel oops in bond_rr_gen_slave_id +DEBUG=${DEBUG:-0} + +set -e +test ${DEBUG} -ne 0 && set -x + +finish() +{ + ip netns delete server || true + ip netns delete client || true + ip link del link1_1 || true +} + +trap finish EXIT + +client_ip4=192.168.1.198 +server_ip4=192.168.1.254 + +# setup kernel so it reboots after causing the panic +echo 180 >/proc/sys/kernel/panic + +# build namespaces +ip link add dev link1_1 type veth peer name link1_2 + +ip netns add "server" +ip link set dev link1_2 netns server up name eth0 +ip netns exec server ip addr add ${server_ip4}/24 dev eth0 + +ip netns add "client" +ip link set dev link1_1 netns client down name eth0 +ip netns exec client ip link add dev bond0 down type bond mode 1 \ + miimon 100 all_slaves_active 1 +ip netns exec client ip link set dev eth0 down master bond0 +ip netns exec client ip link set dev bond0 up +ip netns exec client ip addr add ${client_ip4}/24 dev bond0 +ip netns exec client ping -c 5 $server_ip4 >/dev/null + +ip netns exec client ip link set dev eth0 down nomaster +ip netns exec client ip link set dev bond0 down +ip netns exec client ip link set dev bond0 type bond mode 0 \ + arp_interval 1000 arp_ip_target "+${server_ip4}" +ip netns exec client ip link set dev eth0 down master bond0 +ip netns exec client ip link set dev bond0 up +ip netns exec client ping -c 5 $server_ip4 >/dev/null + +exit 0 diff --git a/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh b/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh new file mode 100755 index 000000000..47ab90596 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh @@ -0,0 +1,81 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +# Regression Test: +# Verify LACPDUs get transmitted after setting the MAC address of +# the bond. +# +# https://bugzilla.redhat.com/show_bug.cgi?id=2020773 +# +# +---------+ +# | fab-br0 | +# +---------+ +# | +# +---------+ +# | fbond | +# +---------+ +# | | +# +------+ +------+ +# |veth1 | |veth2 | +# +------+ +------+ +# +# We use veths instead of physical interfaces + +set -e +tmp=$(mktemp -q dump.XXXXXX) +cleanup() { + ip link del fab-br0 >/dev/null 2>&1 || : + ip link del fbond >/dev/null 2>&1 || : + ip link del veth1-bond >/dev/null 2>&1 || : + ip link del veth2-bond >/dev/null 2>&1 || : + modprobe -r bonding >/dev/null 2>&1 || : + rm -f -- ${tmp} +} + +trap cleanup 0 1 2 +cleanup +sleep 1 + +# create the bridge +ip link add fab-br0 address 52:54:00:3B:7C:A6 mtu 1500 type bridge \ + forward_delay 15 + +# create the bond +ip link add fbond type bond mode 4 miimon 200 xmit_hash_policy 1 \ + ad_actor_sys_prio 65535 lacp_rate fast + +# set bond address +ip link set fbond address 52:54:00:3B:7C:A6 +ip link set fbond up + +# set again bond sysfs parameters +ip link set fbond type bond ad_actor_sys_prio 65535 + +# create veths +ip link add name veth1-bond type veth peer name veth1-end +ip link add name veth2-bond type veth peer name veth2-end + +# add ports +ip link set fbond master fab-br0 +ip link set veth1-bond down master fbond +ip link set veth2-bond down master fbond + +# bring up +ip link set veth1-end up +ip link set veth2-end up +ip link set fab-br0 up +ip link set fbond up +ip addr add dev fab-br0 10.0.0.3 + +tcpdump -n -i veth1-end -e ether proto 0x8809 >${tmp} 2>&1 & +sleep 15 +pkill tcpdump >/dev/null 2>&1 +rc=0 +num=$(grep "packets captured" ${tmp} | awk '{print $1}') +if test "$num" -gt 0; then + echo "PASS, captured ${num}" +else + echo "FAIL" + rc=1 +fi +exit $rc diff --git a/tools/testing/selftests/drivers/net/bonding/bond-lladdr-target.sh b/tools/testing/selftests/drivers/net/bonding/bond-lladdr-target.sh new file mode 100755 index 000000000..89af402fa --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/bond-lladdr-target.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Regression Test: +# Verify bond interface could up when set IPv6 link local address target. +# +# +----------------+ +# | br0 | +# | | | sw +# | veth0 veth1 | +# +---+-------+----+ +# | | +# +---+-------+----+ +# | veth0 veth1 | +# | | | host +# | bond0 | +# +----------------+ +# +# We use veths instead of physical interfaces +sw="sw-$(mktemp -u XXXXXX)" +host="ns-$(mktemp -u XXXXXX)" + +cleanup() +{ + ip netns del $sw + ip netns del $host +} + +trap cleanup 0 1 2 + +ip netns add $sw +ip netns add $host + +ip -n $host link add veth0 type veth peer name veth0 netns $sw +ip -n $host link add veth1 type veth peer name veth1 netns $sw + +ip -n $sw link add br0 type bridge +ip -n $sw link set br0 up +sw_lladdr=$(ip -n $sw addr show br0 | awk '/fe80/{print $2}' | cut -d'/' -f1) +# sleep some time to make sure bridge lladdr pass DAD +sleep 2 + +ip -n $host link add bond0 type bond mode 1 ns_ip6_target ${sw_lladdr} \ + arp_validate 3 arp_interval 1000 +# add a lladdr for bond to make sure there is a route to target +ip -n $host addr add fe80::beef/64 dev bond0 +ip -n $host link set bond0 up +ip -n $host link set veth0 master bond0 +ip -n $host link set veth1 master bond0 + +ip -n $sw link set veth0 master br0 +ip -n $sw link set veth1 master br0 +ip -n $sw link set veth0 up +ip -n $sw link set veth1 up + +sleep 5 + +rc=0 +if ip -n $host link show bond0 | grep -q LOWER_UP; then + echo "PASS" +else + echo "FAIL" + rc=1 +fi +exit $rc diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config new file mode 100644 index 000000000..70638fa50 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/config @@ -0,0 +1,2 @@ +CONFIG_BONDING=y +CONFIG_MACVLAN=y diff --git a/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh b/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh new file mode 100755 index 000000000..5cfe7d8eb --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh @@ -0,0 +1,109 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test bond device handling of addr lists (dev->uc, mc) +# + +ALL_TESTS=" + bond_cleanup_mode1 + bond_cleanup_mode4 + bond_listen_lacpdu_multicast_case_down + bond_listen_lacpdu_multicast_case_up +" + +REQUIRE_MZ=no +NUM_NETIFS=0 +lib_dir=$(dirname "$0") +source "$lib_dir"/net_forwarding_lib.sh + +source "$lib_dir"/lag_lib.sh + + +destroy() +{ + local ifnames=(dummy1 dummy2 bond1 mv0) + local ifname + + for ifname in "${ifnames[@]}"; do + ip link del "$ifname" &>/dev/null + done +} + +cleanup() +{ + pre_cleanup + + destroy +} + + +# bond driver control paths vary between modes that have a primary slave +# (bond_uses_primary()) and others. Test both kinds of modes. + +bond_cleanup_mode1() +{ + RET=0 + + test_LAG_cleanup "bonding" "active-backup" +} + +bond_cleanup_mode4() { + RET=0 + + test_LAG_cleanup "bonding" "802.3ad" +} + +bond_listen_lacpdu_multicast() +{ + # Initial state of bond device, up | down + local init_state=$1 + local lacpdu_mc="01:80:c2:00:00:02" + + ip link add dummy1 type dummy + ip link add bond1 "$init_state" type bond mode 802.3ad + ip link set dev dummy1 master bond1 + if [ "$init_state" = "down" ]; then + ip link set dev bond1 up + fi + + grep_bridge_fdb "$lacpdu_mc" bridge fdb show brport dummy1 >/dev/null + check_err $? "LACPDU multicast address not present on slave (1)" + + ip link set dev bond1 down + + not grep_bridge_fdb "$lacpdu_mc" bridge fdb show brport dummy1 >/dev/null + check_err $? "LACPDU multicast address still present on slave" + + ip link set dev bond1 up + + grep_bridge_fdb "$lacpdu_mc" bridge fdb show brport dummy1 >/dev/null + check_err $? "LACPDU multicast address not present on slave (2)" + + cleanup + + log_test "bonding LACPDU multicast address to slave (from bond $init_state)" +} + +# The LACPDU mc addr is added by different paths depending on the initial state +# of the bond when enslaving a device. Test both cases. + +bond_listen_lacpdu_multicast_case_down() +{ + RET=0 + + bond_listen_lacpdu_multicast "down" +} + +bond_listen_lacpdu_multicast_case_up() +{ + RET=0 + + bond_listen_lacpdu_multicast "up" +} + + +trap cleanup EXIT + +tests_run + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/drivers/net/bonding/lag_lib.sh b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh new file mode 100644 index 000000000..2a268b17b --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh @@ -0,0 +1,167 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +NAMESPACES="" + +# Test that a link aggregation device (bonding, team) removes the hardware +# addresses that it adds on its underlying devices. +test_LAG_cleanup() +{ + local driver=$1 + local mode=$2 + local ucaddr="02:00:00:12:34:56" + local addr6="fe80::78:9abc/64" + local mcaddr="33:33:ff:78:9a:bc" + local name + + ip link add dummy1 type dummy + ip link add dummy2 type dummy + if [ "$driver" = "bonding" ]; then + name="bond1" + ip link add "$name" up type bond mode "$mode" + ip link set dev dummy1 master "$name" + ip link set dev dummy2 master "$name" + elif [ "$driver" = "team" ]; then + name="team0" + teamd -d -c ' + { + "device": "'"$name"'", + "runner": { + "name": "'"$mode"'" + }, + "ports": { + "dummy1": + {}, + "dummy2": + {} + } + } + ' + ip link set dev "$name" up + else + check_err 1 + log_test test_LAG_cleanup ": unknown driver \"$driver\"" + return + fi + + # Used to test dev->uc handling + ip link add mv0 link "$name" up address "$ucaddr" type macvlan + # Used to test dev->mc handling + ip address add "$addr6" dev "$name" + ip link set dev "$name" down + ip link del "$name" + + not grep_bridge_fdb "$ucaddr" bridge fdb show >/dev/null + check_err $? "macvlan unicast address still present on a slave" + + not grep_bridge_fdb "$mcaddr" bridge fdb show >/dev/null + check_err $? "IPv6 solicited-node multicast mac address still present on a slave" + + cleanup + + log_test "$driver cleanup mode $mode" +} + +# Build a generic 2 node net namespace with 2 connections +# between the namespaces +# +# +-----------+ +-----------+ +# | node1 | | node2 | +# | | | | +# | | | | +# | eth0 +-------+ eth0 | +# | | | | +# | eth1 +-------+ eth1 | +# | | | | +# +-----------+ +-----------+ +lag_setup2x2() +{ + local state=${1:-down} + local namespaces="lag_node1 lag_node2" + + # create namespaces + for n in ${namespaces}; do + ip netns add ${n} + done + + # wire up namespaces + ip link add name lag1 type veth peer name lag1-end + ip link set dev lag1 netns lag_node1 $state name eth0 + ip link set dev lag1-end netns lag_node2 $state name eth0 + + ip link add name lag1 type veth peer name lag1-end + ip link set dev lag1 netns lag_node1 $state name eth1 + ip link set dev lag1-end netns lag_node2 $state name eth1 + + NAMESPACES="${namespaces}" +} + +# cleanup all lag related namespaces and remove the bonding module +lag_cleanup() +{ + for n in ${NAMESPACES}; do + ip netns delete ${n} >/dev/null 2>&1 || true + done + modprobe -r bonding +} + +SWITCH="lag_node1" +CLIENT="lag_node2" +CLIENTIP="172.20.2.1" +SWITCHIP="172.20.2.2" + +lag_setup_network() +{ + lag_setup2x2 "down" + + # create switch + ip netns exec ${SWITCH} ip link add br0 up type bridge + ip netns exec ${SWITCH} ip link set eth0 master br0 up + ip netns exec ${SWITCH} ip link set eth1 master br0 up + ip netns exec ${SWITCH} ip addr add ${SWITCHIP}/24 dev br0 +} + +lag_reset_network() +{ + ip netns exec ${CLIENT} ip link del bond0 + ip netns exec ${SWITCH} ip link set eth0 up + ip netns exec ${SWITCH} ip link set eth1 up +} + +create_bond() +{ + # create client + ip netns exec ${CLIENT} ip link set eth0 down + ip netns exec ${CLIENT} ip link set eth1 down + + ip netns exec ${CLIENT} ip link add bond0 type bond $@ + ip netns exec ${CLIENT} ip link set eth0 master bond0 + ip netns exec ${CLIENT} ip link set eth1 master bond0 + ip netns exec ${CLIENT} ip link set bond0 up + ip netns exec ${CLIENT} ip addr add ${CLIENTIP}/24 dev bond0 +} + +test_bond_recovery() +{ + RET=0 + + create_bond $@ + + # verify connectivity + ip netns exec ${CLIENT} ping ${SWITCHIP} -c 2 >/dev/null 2>&1 + check_err $? "No connectivity" + + # force the links of the bond down + ip netns exec ${SWITCH} ip link set eth0 down + sleep 2 + ip netns exec ${SWITCH} ip link set eth0 up + ip netns exec ${SWITCH} ip link set eth1 down + + # re-verify connectivity + ip netns exec ${CLIENT} ping ${SWITCHIP} -c 2 >/dev/null 2>&1 + + local rc=$? + check_err $rc "Bond failed to recover" + log_test "$1 ($2) bond recovery" + lag_reset_network +} diff --git a/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh b/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh new file mode 100755 index 000000000..ad4c845a4 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh @@ -0,0 +1,45 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +# Regression Test: +# When the bond is configured with down/updelay and the link state of +# slave members flaps if there are no remaining members up the bond +# should immediately select a member to bring up. (from bonding.txt +# section 13.1 paragraph 4) +# +# +-------------+ +-----------+ +# | client | | switch | +# | | | | +# | +--------| link1 |-----+ | +# | | +-------+ | | +# | | | | | | +# | | +-------+ | | +# | | bond | link2 | Br0 | | +# +-------------+ +-----------+ +# 172.20.2.1 172.20.2.2 + + +REQUIRE_MZ=no +REQUIRE_JQ=no +NUM_NETIFS=0 +lib_dir=$(dirname "$0") +source "$lib_dir"/net_forwarding_lib.sh +source "$lib_dir"/lag_lib.sh + +cleanup() +{ + lag_cleanup +} + +trap cleanup 0 1 2 + +lag_setup_network +test_bond_recovery mode 1 miimon 100 updelay 0 +test_bond_recovery mode 1 miimon 100 updelay 200 +test_bond_recovery mode 1 miimon 100 updelay 500 +test_bond_recovery mode 1 miimon 100 updelay 1000 +test_bond_recovery mode 1 miimon 100 updelay 2000 +test_bond_recovery mode 1 miimon 100 updelay 5000 +test_bond_recovery mode 1 miimon 100 updelay 10000 + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh b/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh new file mode 100755 index 000000000..2330d3745 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh @@ -0,0 +1,45 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +# Regression Test: +# When the bond is configured with down/updelay and the link state of +# slave members flaps if there are no remaining members up the bond +# should immediately select a member to bring up. (from bonding.txt +# section 13.1 paragraph 4) +# +# +-------------+ +-----------+ +# | client | | switch | +# | | | | +# | +--------| link1 |-----+ | +# | | +-------+ | | +# | | | | | | +# | | +-------+ | | +# | | bond | link2 | Br0 | | +# +-------------+ +-----------+ +# 172.20.2.1 172.20.2.2 + + +REQUIRE_MZ=no +REQUIRE_JQ=no +NUM_NETIFS=0 +lib_dir=$(dirname "$0") +source "$lib_dir"/net_forwarding_lib.sh +source "$lib_dir"/lag_lib.sh + +cleanup() +{ + lag_cleanup +} + +trap cleanup 0 1 2 + +lag_setup_network +test_bond_recovery mode 2 miimon 100 updelay 0 +test_bond_recovery mode 2 miimon 100 updelay 200 +test_bond_recovery mode 2 miimon 100 updelay 500 +test_bond_recovery mode 2 miimon 100 updelay 1000 +test_bond_recovery mode 2 miimon 100 updelay 2000 +test_bond_recovery mode 2 miimon 100 updelay 5000 +test_bond_recovery mode 2 miimon 100 updelay 10000 + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/drivers/net/bonding/net_forwarding_lib.sh b/tools/testing/selftests/drivers/net/bonding/net_forwarding_lib.sh new file mode 120000 index 000000000..39c96828c --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/net_forwarding_lib.sh @@ -0,0 +1 @@ +../../../net/forwarding/lib.sh \ No newline at end of file diff --git a/tools/testing/selftests/drivers/net/bonding/option_prio.sh b/tools/testing/selftests/drivers/net/bonding/option_prio.sh new file mode 100755 index 000000000..c32eebff5 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/option_prio.sh @@ -0,0 +1,245 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test bonding option prio +# + +ALL_TESTS=" + prio_arp_ip_target_test + prio_miimon_test +" + +REQUIRE_MZ=no +REQUIRE_JQ=no +NUM_NETIFS=0 +lib_dir=$(dirname "$0") +source "$lib_dir"/net_forwarding_lib.sh + +destroy() +{ + ip link del bond0 &>/dev/null + ip link del br0 &>/dev/null + ip link del veth0 &>/dev/null + ip link del veth1 &>/dev/null + ip link del veth2 &>/dev/null + ip netns del ns1 &>/dev/null + ip link del veth3 &>/dev/null +} + +cleanup() +{ + pre_cleanup + + destroy +} + +skip() +{ + local skip=1 + ip link add name bond0 type bond mode 1 miimon 100 &>/dev/null + ip link add name veth0 type veth peer name veth0_p + ip link set veth0 master bond0 + + # check if iproute support prio option + ip link set dev veth0 type bond_slave prio 10 + [[ $? -ne 0 ]] && skip=0 + + # check if bonding support prio option + ip -d link show veth0 | grep -q "prio 10" + [[ $? -ne 0 ]] && skip=0 + + ip link del bond0 &>/dev/null + ip link del veth0 + + return $skip +} + +active_slave="" +check_active_slave() +{ + local target_active_slave=$1 + active_slave="$(cat /sys/class/net/bond0/bonding/active_slave)" + test "$active_slave" = "$target_active_slave" + check_err $? "Current active slave is $active_slave but not $target_active_slave" +} + + +# Test bonding prio option with mode=$mode monitor=$monitor +# and primary_reselect=$primary_reselect +prio_test() +{ + RET=0 + + local monitor=$1 + local mode=$2 + local primary_reselect=$3 + + local bond_ip4="192.169.1.2" + local peer_ip4="192.169.1.1" + local bond_ip6="2009:0a:0b::02" + local peer_ip6="2009:0a:0b::01" + + + # create veths + ip link add name veth0 type veth peer name veth0_p + ip link add name veth1 type veth peer name veth1_p + ip link add name veth2 type veth peer name veth2_p + + # create bond + if [[ "$monitor" == "miimon" ]];then + ip link add name bond0 type bond mode $mode miimon 100 primary veth1 primary_reselect $primary_reselect + elif [[ "$monitor" == "arp_ip_target" ]];then + ip link add name bond0 type bond mode $mode arp_interval 1000 arp_ip_target $peer_ip4 primary veth1 primary_reselect $primary_reselect + elif [[ "$monitor" == "ns_ip6_target" ]];then + ip link add name bond0 type bond mode $mode arp_interval 1000 ns_ip6_target $peer_ip6 primary veth1 primary_reselect $primary_reselect + fi + ip link set bond0 up + ip link set veth0 master bond0 + ip link set veth1 master bond0 + ip link set veth2 master bond0 + # check bonding member prio value + ip link set dev veth0 type bond_slave prio 0 + ip link set dev veth1 type bond_slave prio 10 + ip link set dev veth2 type bond_slave prio 11 + ip -d link show veth0 | grep -q 'prio 0' + check_err $? "veth0 prio is not 0" + ip -d link show veth1 | grep -q 'prio 10' + check_err $? "veth0 prio is not 10" + ip -d link show veth2 | grep -q 'prio 11' + check_err $? "veth0 prio is not 11" + + ip link set veth0 up + ip link set veth1 up + ip link set veth2 up + ip link set veth0_p up + ip link set veth1_p up + ip link set veth2_p up + + # prepare ping target + ip link add name br0 type bridge + ip link set br0 up + ip link set veth0_p master br0 + ip link set veth1_p master br0 + ip link set veth2_p master br0 + ip link add name veth3 type veth peer name veth3_p + ip netns add ns1 + ip link set veth3_p master br0 up + ip link set veth3 netns ns1 up + ip netns exec ns1 ip addr add $peer_ip4/24 dev veth3 + ip netns exec ns1 ip addr add $peer_ip6/64 dev veth3 + ip addr add $bond_ip4/24 dev bond0 + ip addr add $bond_ip6/64 dev bond0 + sleep 5 + + ping $peer_ip4 -c5 -I bond0 &>/dev/null + check_err $? "ping failed 1." + ping6 $peer_ip6 -c5 -I bond0 &>/dev/null + check_err $? "ping6 failed 1." + + # active salve should be the primary slave + check_active_slave veth1 + + # active slave should be the higher prio slave + ip link set $active_slave down + ping $peer_ip4 -c5 -I bond0 &>/dev/null + check_err $? "ping failed 2." + check_active_slave veth2 + + # when only 1 slave is up + ip link set $active_slave down + ping $peer_ip4 -c5 -I bond0 &>/dev/null + check_err $? "ping failed 3." + check_active_slave veth0 + + # when a higher prio slave change to up + ip link set veth2 up + ping $peer_ip4 -c5 -I bond0 &>/dev/null + check_err $? "ping failed 4." + case $primary_reselect in + "0") + check_active_slave "veth2" + ;; + "1") + check_active_slave "veth0" + ;; + "2") + check_active_slave "veth0" + ;; + esac + local pre_active_slave=$active_slave + + # when the primary slave change to up + ip link set veth1 up + ping $peer_ip4 -c5 -I bond0 &>/dev/null + check_err $? "ping failed 5." + case $primary_reselect in + "0") + check_active_slave "veth1" + ;; + "1") + check_active_slave "$pre_active_slave" + ;; + "2") + check_active_slave "$pre_active_slave" + ip link set $active_slave down + ping $peer_ip4 -c5 -I bond0 &>/dev/null + check_err $? "ping failed 6." + check_active_slave "veth1" + ;; + esac + + # Test changing bond salve prio + if [[ "$primary_reselect" == "0" ]];then + ip link set dev veth0 type bond_slave prio 1000000 + ip link set dev veth1 type bond_slave prio 0 + ip link set dev veth2 type bond_slave prio -50 + ip -d link show veth0 | grep -q 'prio 1000000' + check_err $? "veth0 prio is not 1000000" + ip -d link show veth1 | grep -q 'prio 0' + check_err $? "veth1 prio is not 0" + ip -d link show veth2 | grep -q 'prio -50' + check_err $? "veth3 prio is not -50" + check_active_slave "veth1" + + ip link set $active_slave down + ping $peer_ip4 -c5 -I bond0 &>/dev/null + check_err $? "ping failed 7." + check_active_slave "veth0" + fi + + cleanup + + log_test "prio_test" "Test bonding option 'prio' with mode=$mode monitor=$monitor and primary_reselect=$primary_reselect" +} + +prio_miimon_test() +{ + local mode + local primary_reselect + + for mode in 1 5 6; do + for primary_reselect in 0 1 2; do + prio_test "miimon" $mode $primary_reselect + done + done +} + +prio_arp_ip_target_test() +{ + local primary_reselect + + for primary_reselect in 0 1 2; do + prio_test "arp_ip_target" 1 $primary_reselect + done +} + +if skip;then + log_test_skip "option_prio.sh" "Current iproute doesn't support 'prio'." + exit 0 +fi + +trap cleanup EXIT + +tests_run + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/drivers/net/bonding/settings b/tools/testing/selftests/drivers/net/bonding/settings new file mode 100644 index 000000000..6091b45d2 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/settings @@ -0,0 +1 @@ +timeout=120 -- cgit v1.2.3