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(). ... --- .../selftests/net/fib_nexthop_multiprefix.sh | 292 +++++++++++++++++++++ 1 file changed, 292 insertions(+) create mode 100755 tools/testing/selftests/net/fib_nexthop_multiprefix.sh (limited to 'tools/testing/selftests/net/fib_nexthop_multiprefix.sh') diff --git a/tools/testing/selftests/net/fib_nexthop_multiprefix.sh b/tools/testing/selftests/net/fib_nexthop_multiprefix.sh new file mode 100755 index 000000000..51df5e305 --- /dev/null +++ b/tools/testing/selftests/net/fib_nexthop_multiprefix.sh @@ -0,0 +1,292 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Validate cached routes in fib{6}_nh that is used by multiple prefixes. +# Validate a different # exception is generated in h0 for each remote host. +# +# h1 +# / +# h0 - r1 - h2 +# \ +# h3 +# +# routing in h0 to hN is done with nexthop objects. + +PAUSE_ON_FAIL=no +VERBOSE=0 + +which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) + +################################################################################ +# helpers + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + printf "TEST: %-60s [ OK ]\n" "${msg}" + nsuccess=$((nsuccess+1)) + else + ret=1 + nfail=$((nfail+1)) + printf "TEST: %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi + + [ "$VERBOSE" = "1" ] && echo +} + +run_cmd() +{ + local cmd="$*" + local out + local rc + + if [ "$VERBOSE" = "1" ]; then + echo "COMMAND: $cmd" + fi + + out=$(eval $cmd 2>&1) + rc=$? + if [ "$VERBOSE" = "1" -a -n "$out" ]; then + echo "$out" + fi + + [ "$VERBOSE" = "1" ] && echo + + return $rc +} + +################################################################################ +# config + +create_ns() +{ + local ns=${1} + + ip netns del ${ns} 2>/dev/null + + ip netns add ${ns} + ip -netns ${ns} addr add 127.0.0.1/8 dev lo + ip -netns ${ns} link set lo up + + ip netns exec ${ns} sysctl -q -w net.ipv6.conf.all.keep_addr_on_down=1 + case ${ns} in + h*) + ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=0 + ;; + r*) + ip netns exec $ns sysctl -q -w net.ipv4.ip_forward=1 + ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=1 + ;; + esac +} + +setup() +{ + local ns + local i + + #set -e + + for ns in h0 r1 h1 h2 h3 + do + create_ns ${ns} + done + + # + # create interconnects + # + + for i in 0 1 2 3 + do + ip -netns h${i} li add eth0 type veth peer name r1h${i} + ip -netns h${i} li set eth0 up + ip -netns h${i} li set r1h${i} netns r1 name eth${i} up + + ip -netns h${i} addr add dev eth0 172.16.10${i}.1/24 + ip -netns h${i} -6 addr add dev eth0 2001:db8:10${i}::1/64 + ip -netns r1 addr add dev eth${i} 172.16.10${i}.254/24 + ip -netns r1 -6 addr add dev eth${i} 2001:db8:10${i}::64/64 + done + + ip -netns h0 nexthop add id 4 via 172.16.100.254 dev eth0 + ip -netns h0 nexthop add id 6 via 2001:db8:100::64 dev eth0 + + # routing from h0 to h1-h3 and back + for i in 1 2 3 + do + ip -netns h0 ro add 172.16.10${i}.0/24 nhid 4 + ip -netns h${i} ro add 172.16.100.0/24 via 172.16.10${i}.254 + + ip -netns h0 -6 ro add 2001:db8:10${i}::/64 nhid 6 + ip -netns h${i} -6 ro add 2001:db8:100::/64 via 2001:db8:10${i}::64 + done + + if [ "$VERBOSE" = "1" ]; then + echo + echo "host 1 config" + ip -netns h0 li sh + ip -netns h0 ro sh + ip -netns h0 -6 ro sh + fi + + #set +e +} + +cleanup() +{ + for n in h0 r1 h1 h2 h3 + do + ip netns del ${n} 2>/dev/null + done +} + +change_mtu() +{ + local hostid=$1 + local mtu=$2 + + run_cmd ip -netns h${hostid} li set eth0 mtu ${mtu} + run_cmd ip -netns r1 li set eth${hostid} mtu ${mtu} +} + +################################################################################ +# validate exceptions + +validate_v4_exception() +{ + local i=$1 + local mtu=$2 + local ping_sz=$3 + local dst="172.16.10${i}.1" + local h0=172.16.100.1 + local r1=172.16.100.254 + local rc + + if [ ${ping_sz} != "0" ]; then + run_cmd ip netns exec h0 ping -s ${ping_sz} -c5 -w5 ${dst} + fi + + if [ "$VERBOSE" = "1" ]; then + echo "Route get" + ip -netns h0 ro get ${dst} + echo "Searching for:" + echo " cache .* mtu ${mtu}" + echo + fi + + ip -netns h0 ro get ${dst} | \ + grep -q "cache .* mtu ${mtu}" + rc=$? + + log_test $rc 0 "IPv4: host 0 to host ${i}, mtu ${mtu}" +} + +validate_v6_exception() +{ + local i=$1 + local mtu=$2 + local ping_sz=$3 + local dst="2001:db8:10${i}::1" + local h0=2001:db8:100::1 + local r1=2001:db8:100::64 + local rc + + if [ ${ping_sz} != "0" ]; then + run_cmd ip netns exec h0 ${ping6} -s ${ping_sz} -c5 -w5 ${dst} + fi + + if [ "$VERBOSE" = "1" ]; then + echo "Route get" + ip -netns h0 -6 ro get ${dst} + echo "Searching for:" + echo " ${dst} from :: via ${r1} dev eth0 src ${h0} .* mtu ${mtu}" + echo + fi + + ip -netns h0 -6 ro get ${dst} | \ + grep -q "${dst} from :: via ${r1} dev eth0 src ${h0} .* mtu ${mtu}" + rc=$? + + log_test $rc 0 "IPv6: host 0 to host ${i}, mtu ${mtu}" +} + +################################################################################ +# main + +while getopts :pv o +do + case $o in + p) PAUSE_ON_FAIL=yes;; + v) VERBOSE=1;; + esac +done + +cleanup +setup +sleep 2 + +cpus=$(cat /sys/devices/system/cpu/online) +cpus="$(seq ${cpus/-/ })" +ret=0 +for i in 1 2 3 +do + # generate a cached route per-cpu + for c in ${cpus}; do + run_cmd taskset -c ${c} ip netns exec h0 ping -c1 -w1 172.16.10${i}.1 + [ $? -ne 0 ] && printf "\nERROR: ping to h${i} failed\n" && ret=1 + + run_cmd taskset -c ${c} ip netns exec h0 ${ping6} -c1 -w1 2001:db8:10${i}::1 + [ $? -ne 0 ] && printf "\nERROR: ping6 to h${i} failed\n" && ret=1 + + [ $ret -ne 0 ] && break + done + [ $ret -ne 0 ] && break +done + +if [ $ret -eq 0 ]; then + # generate different exceptions in h0 for h1, h2 and h3 + change_mtu 1 1300 + validate_v4_exception 1 1300 1350 + validate_v6_exception 1 1300 1350 + echo + + change_mtu 2 1350 + validate_v4_exception 2 1350 1400 + validate_v6_exception 2 1350 1400 + echo + + change_mtu 3 1400 + validate_v4_exception 3 1400 1450 + validate_v6_exception 3 1400 1450 + echo + + validate_v4_exception 1 1300 0 + validate_v6_exception 1 1300 0 + echo + + validate_v4_exception 2 1350 0 + validate_v6_exception 2 1350 0 + echo + + validate_v4_exception 3 1400 0 + validate_v6_exception 3 1400 0 + + # targeted deletes to trigger cleanup paths in kernel + ip -netns h0 ro del 172.16.102.0/24 nhid 4 + ip -netns h0 -6 ro del 2001:db8:102::/64 nhid 6 + + ip -netns h0 nexthop del id 4 + ip -netns h0 nexthop del id 6 +fi + +cleanup -- cgit v1.2.3