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(). ... --- samples/pktgen/functions.sh | 339 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 339 insertions(+) create mode 100644 samples/pktgen/functions.sh (limited to 'samples/pktgen/functions.sh') diff --git a/samples/pktgen/functions.sh b/samples/pktgen/functions.sh new file mode 100644 index 000000000..dd4e53ae9 --- /dev/null +++ b/samples/pktgen/functions.sh @@ -0,0 +1,339 @@ +# +# Common functions used by pktgen scripts +# - Depending on bash 3 (or higher) syntax +# +# Author: Jesper Dangaaard Brouer +# License: GPL + +set -o errexit + +## -- General shell logging cmds -- +function err() { + local exitcode=$1 + shift + echo "ERROR: $@" >&2 + exit $exitcode +} + +function warn() { + echo "WARN : $@" >&2 +} + +function info() { + if [[ -n "$VERBOSE" ]]; then + echo "INFO : $@" >&2 + fi +} + +## -- Pktgen proc config commands -- ## +export PROC_DIR=/proc/net/pktgen +# +# Three different shell functions for configuring the different +# components of pktgen: +# pg_ctrl(), pg_thread() and pg_set(). +# +# These functions correspond to pktgens different components. +# * pg_ctrl() control "pgctrl" (/proc/net/pktgen/pgctrl) +# * pg_thread() control the kernel threads and binding to devices +# * pg_set() control setup of individual devices +function pg_ctrl() { + local proc_file="pgctrl" + proc_cmd ${proc_file} "$@" +} + +function pg_thread() { + local thread=$1 + local proc_file="kpktgend_${thread}" + shift + proc_cmd ${proc_file} "$@" +} + +function pg_set() { + local dev=$1 + local proc_file="$dev" + shift + proc_cmd ${proc_file} "$@" +} + +# More generic replacement for pgset(), that does not depend on global +# variable for proc file. +function proc_cmd() { + local result + local proc_file=$1 + local status=0 + # after shift, the remaining args are contained in $@ + shift + local proc_ctrl=${PROC_DIR}/$proc_file + if [[ ! -e "$proc_ctrl" ]]; then + err 3 "proc file:$proc_ctrl does not exists (dev added to thread?)" + else + if [[ ! -w "$proc_ctrl" ]]; then + err 4 "proc file:$proc_ctrl not writable, not root?!" + fi + fi + + if [[ "$DEBUG" == "yes" ]]; then + echo "cmd: $@ > $proc_ctrl" + fi + # Quoting of "$@" is important for space expansion + echo "$@" > "$proc_ctrl" || status=$? + + if [[ "$proc_file" != "pgctrl" ]]; then + result=$(grep "Result: OK:" $proc_ctrl) || true + if [[ "$result" == "" ]]; then + grep "Result:" $proc_ctrl >&2 + fi + fi + if (( $status != 0 )); then + err 5 "Write error($status) occurred cmd: \"$@ > $proc_ctrl\"" + fi +} + +# Old obsolete "pgset" function, with slightly improved err handling +function pgset() { + local result + + if [[ "$DEBUG" == "yes" ]]; then + echo "cmd: $1 > $PGDEV" + fi + echo $1 > $PGDEV + local status=$? + + result=`cat $PGDEV | fgrep "Result: OK:"` + if [[ "$result" == "" ]]; then + cat $PGDEV | fgrep Result: + fi + if (( $status != 0 )); then + err 5 "Write error($status) occurred cmd: \"$1 > $PGDEV\"" + fi +} + +if [[ -z "$APPEND" ]]; then + if [[ $EUID -eq 0 ]]; then + # Cleanup pktgen setup on exit if thats not "append mode" + trap 'pg_ctrl "reset"' EXIT + fi +fi + +## -- General shell tricks -- + +function root_check_run_with_sudo() { + # Trick so, program can be run as normal user, will just use "sudo" + # call as root_check_run_as_sudo "$@" + if [ "$EUID" -ne 0 ]; then + if [ -x $0 ]; then # Directly executable use sudo + info "Not root, running with sudo" + sudo -E "$0" "$@" + exit $? + fi + err 4 "cannot perform sudo run of $0" + fi +} + +# Exact input device's NUMA node info +function get_iface_node() +{ + local node=$( fe80:0:0:0:42:bcff:fe84:e10a +function extend_addr6() +{ + local addr=$1 + local sep=: sep2=:: + local sep_cnt=$(tr -cd $sep <<< $1 | wc -c) + local shrink + + # separator count should be (2 <= $sep_cnt <= 7) + if ! (in_between $sep_cnt 2 7); then + err 5 "Invalid IP6 address: $1" + fi + + # if shrink '::' occurs multiple, it's malformed. + shrink=( $(grep -E -o "$sep{2,}" <<< $addr) ) + if [[ ${#shrink[@]} -ne 0 ]]; then + if [[ ${#shrink[@]} -gt 1 || ( ${shrink[0]} != $sep2 ) ]]; then + err 5 "Invalid IP6 address: $1" + fi + fi + + # add 0 at begin & end, and extend addr by adding :0 + [[ ${addr:0:1} == $sep ]] && addr=0${addr} + [[ ${addr: -1} == $sep ]] && addr=${addr}0 + echo "${addr/$sep2/$(printf ':0%.s' $(seq $[8-sep_cnt])):}" +} + +# Given a single IP(v4/v6) address, whether it is valid. +function validate_addr() +{ + # check function is called with (funcname)6 + [[ ${FUNCNAME[1]: -1} == 6 ]] && local IP6=6 + local bitlen=$[ IP6 ? 128 : 32 ] + local len=$[ IP6 ? 8 : 4 ] + local max=$[ 2**(len*2)-1 ] + local net prefix + local addr sep + + IFS='/' read net prefix <<< $1 + [[ $IP6 ]] && net=$(extend_addr6 $net) + + # if prefix exists, check (0 <= $prefix <= $bitlen) + if [[ -n $prefix ]]; then + if ! (in_between $prefix 0 $bitlen); then + err 5 "Invalid prefix: /$prefix" + fi + fi + + # set separator for each IP(v4/v6) + [[ $IP6 ]] && sep=: || sep=. + IFS=$sep read -a addr <<< $net + + # array length + if [[ ${#addr[@]} != $len ]]; then + err 5 "Invalid IP$IP6 address: $1" + fi + + # check each digit (0 <= $digit <= $max) + for digit in "${addr[@]}"; do + [[ $IP6 ]] && digit=$[ 16#$digit ] + if ! (in_between $digit 0 $max); then + err 5 "Invalid IP$IP6 address: $1" + fi + done + + return 0 +} + +function validate_addr6() { validate_addr $@ ; } + +# Given a single IP(v4/v6) or CIDR, return minimum and maximum IP addr. +function parse_addr() +{ + # check function is called with (funcname)6 + [[ ${FUNCNAME[1]: -1} == 6 ]] && local IP6=6 + local net prefix + local min_ip max_ip + + IFS='/' read net prefix <<< $1 + [[ $IP6 ]] && net=$(extend_addr6 $net) + + if [[ -z $prefix ]]; then + min_ip=$net + max_ip=$net + else + # defining array for converting Decimal 2 Binary + # 00000000 00000001 00000010 00000011 00000100 ... + local d2b='{0..1}{0..1}{0..1}{0..1}{0..1}{0..1}{0..1}{0..1}' + [[ $IP6 ]] && d2b+=$d2b + eval local D2B=($d2b) + + local bitlen=$[ IP6 ? 128 : 32 ] + local remain=$[ bitlen-prefix ] + local octet=$[ IP6 ? 16 : 8 ] + local min_mask max_mask + local min max + local ip_bit + local ip sep + + # set separator for each IP(v4/v6) + [[ $IP6 ]] && sep=: || sep=. + IFS=$sep read -ra ip <<< $net + + min_mask="$(printf '1%.s' $(seq $prefix))$(printf '0%.s' $(seq $remain))" + max_mask="$(printf '0%.s' $(seq $prefix))$(printf '1%.s' $(seq $remain))" + + # calculate min/max ip with &,| operator + for i in "${!ip[@]}"; do + digit=$[ IP6 ? 16#${ip[$i]} : ${ip[$i]} ] + ip_bit=${D2B[$digit]} + + idx=$[ octet*i ] + min[$i]=$[ 2#$ip_bit & 2#${min_mask:$idx:$octet} ] + max[$i]=$[ 2#$ip_bit | 2#${max_mask:$idx:$octet} ] + [[ $IP6 ]] && { min[$i]=$(printf '%X' ${min[$i]}); + max[$i]=$(printf '%X' ${max[$i]}); } + done + + min_ip=$(IFS=$sep; echo "${min[*]}") + max_ip=$(IFS=$sep; echo "${max[*]}") + fi + + echo $min_ip $max_ip +} + +function parse_addr6() { parse_addr $@ ; } + +# Given a single or range of port(s), return minimum and maximum port number. +function parse_ports() +{ + local port_str=$1 + local port_list + local min_port + local max_port + + IFS="-" read -ra port_list <<< $port_str + + min_port=${port_list[0]} + max_port=${port_list[1]:-$min_port} + + echo $min_port $max_port +} + +# Given a minimum and maximum port, verify port number. +function validate_ports() +{ + local min_port=$1 + local max_port=$2 + + # 1 <= port <= 65535 + if (in_between $min_port 1 65535); then + if (in_between $max_port 1 65535); then + if [[ $min_port -le $max_port ]]; then + return 0 + fi + fi + fi + + err 5 "Invalid port(s): $min_port-$max_port" +} -- cgit v1.2.3