Merge branch 'GRO-Toeplitz-selftests'

Coco Li says:

====================
GRO and Toeplitz hash selftests

This patch contains two selftests in net, as well as respective
scripts to run the tests on a single machine in loopback mode.
GRO: tests the Linux kernel GRO behavior
Toeplitz: tests the toeplitz hash implementation
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

tools/testing/selftests/net/Makefile

@@ -38,8 +38,10 @@ TEST_GEN_FILES += reuseaddr_ports_exhausted
 TEST_GEN_FILES += hwtstamp_config rxtimestamp timestamping txtimestamp
 TEST_GEN_FILES += ipsec
 TEST_GEN_FILES += ioam6_parser
+TEST_GEN_FILES += gro
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
 TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
+TEST_GEN_FILES += toeplitz
 
 TEST_FILES := settings
 

tools/testing/selftests/net/gro.sh

+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source setup_loopback.sh
+readonly SERVER_MAC="aa:00:00:00:00:02"
+readonly CLIENT_MAC="aa:00:00:00:00:01"
+readonly TESTS=("data" "ack" "flags" "tcp" "ip" "large")
+readonly PROTOS=("ipv4" "ipv6")
+dev="eth0"
+test="all"
+proto="ipv4"
+
+setup_interrupt() {
+  # Use timer on  host to trigger the network stack
+  # Also disable device interrupt to not depend on NIC interrupt
+  # Reduce test flakiness caused by unexpected interrupts
+  echo 100000 >"${FLUSH_PATH}"
+  echo 50 >"${IRQ_PATH}"
+}
+
+setup_ns() {
+  # Set up server_ns namespace and client_ns namespace
+  setup_macvlan_ns "${dev}" server_ns server "${SERVER_MAC}"
+  setup_macvlan_ns "${dev}" client_ns client "${CLIENT_MAC}"
+}
+
+cleanup_ns() {
+  cleanup_macvlan_ns server_ns server client_ns client
+}
+
+setup() {
+  setup_loopback_environment "${dev}"
+  setup_interrupt
+}
+
+cleanup() {
+  cleanup_loopback "${dev}"
+
+  echo "${FLUSH_TIMEOUT}" >"${FLUSH_PATH}"
+  echo "${HARD_IRQS}" >"${IRQ_PATH}"
+}
+
+run_test() {
+  local server_pid=0
+  local exit_code=0
+  local protocol=$1
+  local test=$2
+  local ARGS=( "--${protocol}" "--dmac" "${SERVER_MAC}" \
+  "--smac" "${CLIENT_MAC}" "--test" "${test}" "--verbose" )
+
+  setup_ns
+  # Each test is run 3 times to deflake, because given the receive timing,
+  # not all packets that should coalesce will be considered in the same flow
+  # on every try.
+  for tries in {1..3}; do
+    # Actual test starts here
+    ip netns exec server_ns ./gro "${ARGS[@]}" "--rx" "--iface" "server" \
+      1>>log.txt &
+    server_pid=$!
+    sleep 0.5  # to allow for socket init
+    ip netns exec client_ns ./gro "${ARGS[@]}" "--iface" "client" \
+      1>>log.txt
+    wait "${server_pid}"
+    exit_code=$?
+    if [[ "${exit_code}" -eq 0 ]]; then
+        break;
+    fi
+  done
+  cleanup_ns
+  echo ${exit_code}
+}
+
+run_all_tests() {
+  local failed_tests=()
+  for proto in "${PROTOS[@]}"; do
+    for test in "${TESTS[@]}"; do
+      echo "running test ${proto} ${test}" >&2
+      exit_code=$(run_test $proto $test)
+      if [[ "${exit_code}" -ne 0 ]]; then
+        failed_tests+=("${proto}_${test}")
+      fi;
+    done;
+  done
+  if [[ ${#failed_tests[@]} -ne 0 ]]; then
+    echo "failed tests: ${failed_tests[*]}. \
+    Please see log.txt for more logs"
+    exit 1
+  else
+    echo "All Tests Succeeded!"
+  fi;
+}
+
+usage() {
+  echo "Usage: $0 \
+  [-i <DEV>] \
+  [-t data|ack|flags|tcp|ip|large] \
+  [-p <ipv4|ipv6>]" 1>&2;
+  exit 1;
+}
+
+while getopts "i:t:p:" opt; do
+  case "${opt}" in
+    i)
+      dev="${OPTARG}"
+      ;;
+    t)
+      test="${OPTARG}"
+      ;;
+    p)
+      proto="${OPTARG}"
+      ;;
+    *)
+      usage
+      ;;
+  esac
+done
+
+readonly FLUSH_PATH="/sys/class/net/${dev}/gro_flush_timeout"
+readonly IRQ_PATH="/sys/class/net/${dev}/napi_defer_hard_irqs"
+readonly FLUSH_TIMEOUT="$(< ${FLUSH_PATH})"
+readonly HARD_IRQS="$(< ${IRQ_PATH})"
+setup
+trap cleanup EXIT
+if [[ "${test}" == "all" ]]; then
+  run_all_tests
+else
+  run_test "${proto}" "${test}"
+fi;

tools/testing/selftests/net/setup_loopback.sh

+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+netdev_check_for_carrier() {
+	local -r dev="$1"
+
+	for i in {1..5}; do
+		carrier="$(cat /sys/class/net/${dev}/carrier)"
+		if [[ "${carrier}" -ne 1 ]] ; then
+			echo "carrier not ready yet..." >&2
+			sleep 1
+		else
+			echo "carrier ready" >&2
+			break
+		fi
+	done
+	echo "${carrier}"
+}
+
+# Assumes that there is no existing ipvlan device on the physical device
+setup_loopback_environment() {
+    local dev="$1"
+
+	# Fail hard if cannot turn on loopback mode for current NIC
+	ethtool -K "${dev}" loopback on || exit 1
+	sleep 1
+
+	# Check for the carrier
+	carrier=$(netdev_check_for_carrier ${dev})
+	if [[ "${carrier}" -ne 1 ]] ; then
+		echo "setup_loopback_environment failed"
+		exit 1
+	fi
+}
+
+setup_macvlan_ns(){
+	local -r link_dev="$1"
+	local -r ns_name="$2"
+	local -r ns_dev="$3"
+	local -r ns_mac="$4"
+	local -r addr="$5"
+
+	ip link add link "${link_dev}" dev "${ns_dev}" \
+		address "${ns_mac}" type macvlan
+	exit_code=$?
+	if [[ "${exit_code}" -ne 0 ]]; then
+		echo "setup_macvlan_ns failed"
+		exit $exit_code
+	fi
+
+	[[ -e /var/run/netns/"${ns_name}" ]] || ip netns add "${ns_name}"
+	ip link set dev "${ns_dev}" netns "${ns_name}"
+	ip -netns "${ns_name}" link set dev "${ns_dev}" up
+	if [[ -n "${addr}" ]]; then
+		ip -netns "${ns_name}" addr add dev "${ns_dev}" "${addr}"
+	fi
+
+	sleep 1
+}
+
+cleanup_macvlan_ns(){
+	while (( $# >= 2 )); do
+		ns_name="$1"
+		ns_dev="$2"
+		ip -netns "${ns_name}" link del dev "${ns_dev}"
+		ip netns del "${ns_name}"
+		shift 2
+	done
+}
+
+cleanup_loopback(){
+	local -r dev="$1"
+
+	ethtool -K "${dev}" loopback off
+	sleep 1
+
+	# Check for the carrier
+	carrier=$(netdev_check_for_carrier ${dev})
+	if [[ "${carrier}" -ne 1 ]] ; then
+		echo "setup_loopback_environment failed"
+		exit 1
+	fi
+}

tools/testing/selftests/net/toeplitz.sh

+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# extended toeplitz test: test rxhash plus, optionally, either (1) rss mapping
+# from rxhash to rx queue ('-rss') or (2) rps mapping from rxhash to cpu
+# ('-rps <rps_map>')
+#
+# irq-pattern-prefix can be derived from /sys/kernel/irq/*/action,
+# which is a driver-specific encoding.
+#
+# invoke as ./toeplitz.sh (-i <iface>) -u|-t -4|-6 \
+# [(-rss -irq_prefix <irq-pattern-prefix>)|(-rps <rps_map>)]
+
+source setup_loopback.sh
+readonly SERVER_IP4="192.168.1.200/24"
+readonly SERVER_IP6="fda8::1/64"
+readonly SERVER_MAC="aa:00:00:00:00:02"
+
+readonly CLIENT_IP4="192.168.1.100/24"
+readonly CLIENT_IP6="fda8::2/64"
+readonly CLIENT_MAC="aa:00:00:00:00:01"
+
+PORT=8000
+KEY="$(</proc/sys/net/core/netdev_rss_key)"
+TEST_RSS=false
+RPS_MAP=""
+PROTO_FLAG=""
+IP_FLAG=""
+DEV="eth0"
+
+# Return the number of rxqs among which RSS is configured to spread packets.
+# This is determined by reading the RSS indirection table using ethtool.
+get_rss_cfg_num_rxqs() {
+	echo $(ethtool -x "${DEV}" |
+		egrep [[:space:]]+[0-9]+:[[:space:]]+ |
+		cut -d: -f2- |
+		awk '{$1=$1};1' |
+		tr ' ' '\n' |
+		sort -u |
+		wc -l)
+}
+
+# Return a list of the receive irq handler cpus.
+# The list is ordered by the irqs, so first rxq-0 cpu, then rxq-1 cpu, etc.
+# Reads /sys/kernel/irq/ in order, so algorithm depends on
+# irq_{rxq-0} < irq_{rxq-1}, etc.
+get_rx_irq_cpus() {
+	CPUS=""
+	# sort so that irq 2 is read before irq 10
+	SORTED_IRQS=$(for i in /sys/kernel/irq/*; do echo $i; done | sort -V)
+	# Consider only as many queues as RSS actually uses. We assume that
+	# if RSS_CFG_NUM_RXQS=N, then RSS uses rxqs 0-(N-1).
+	RSS_CFG_NUM_RXQS=$(get_rss_cfg_num_rxqs)
+	RXQ_COUNT=0
+
+	for i in ${SORTED_IRQS}
+	do
+		[[ "${RXQ_COUNT}" -lt "${RSS_CFG_NUM_RXQS}" ]] || break
+		# lookup relevant IRQs by action name
+		[[ -e "$i/actions" ]] || continue
+		cat "$i/actions" | grep -q "${IRQ_PATTERN}" || continue
+		irqname=$(<"$i/actions")
+
+		# does the IRQ get called
+		irqcount=$(cat "$i/per_cpu_count" | tr -d '0,')
+		[[ -n "${irqcount}" ]] || continue
+
+		# lookup CPU
+		irq=$(basename "$i")
+		cpu=$(cat "/proc/irq/$irq/smp_affinity_list")
+
+		if [[ -z "${CPUS}" ]]; then
+			CPUS="${cpu}"
+		else
+			CPUS="${CPUS},${cpu}"
+		fi
+		RXQ_COUNT=$((RXQ_COUNT+1))
+	done
+
+	echo "${CPUS}"
+}
+
+get_disable_rfs_cmd() {
+	echo "echo 0 > /proc/sys/net/core/rps_sock_flow_entries;"
+}
+
+get_set_rps_bitmaps_cmd() {
+	CMD=""
+	for i in /sys/class/net/${DEV}/queues/rx-*/rps_cpus
+	do
+		CMD="${CMD} echo $1 > ${i};"
+	done
+
+	echo "${CMD}"
+}
+
+get_disable_rps_cmd() {
+	echo "$(get_set_rps_bitmaps_cmd 0)"
+}
+
+die() {
+	echo "$1"
+	exit 1
+}
+
+check_nic_rxhash_enabled() {
+	local -r pattern="receive-hashing:\ on"
+
+	ethtool -k "${DEV}" | grep -q "${pattern}" || die "rxhash must be enabled"
+}
+
+parse_opts() {
+	local prog=$0
+	shift 1
+
+	while [[ "$1" =~ "-" ]]; do
+		if [[ "$1" = "-irq_prefix" ]]; then
+			shift
+			IRQ_PATTERN="^$1-[0-9]*$"
+		elif [[ "$1" = "-u" || "$1" = "-t" ]]; then
+			PROTO_FLAG="$1"
+		elif [[ "$1" = "-4" ]]; then
+			IP_FLAG="$1"
+			SERVER_IP="${SERVER_IP4}"
+			CLIENT_IP="${CLIENT_IP4}"
+		elif [[ "$1" = "-6" ]]; then
+			IP_FLAG="$1"
+			SERVER_IP="${SERVER_IP6}"
+			CLIENT_IP="${CLIENT_IP6}"
+		elif [[ "$1" = "-rss" ]]; then
+			TEST_RSS=true
+		elif [[ "$1" = "-rps" ]]; then
+			shift
+			RPS_MAP="$1"
+		elif [[ "$1" = "-i" ]]; then
+			shift
+			DEV="$1"
+		else
+			die "Usage: ${prog} (-i <iface>) -u|-t -4|-6 \
+			     [(-rss -irq_prefix <irq-pattern-prefix>)|(-rps <rps_map>)]"
+		fi
+		shift
+	done
+}
+
+setup() {
+	setup_loopback_environment "${DEV}"
+
+	# Set up server_ns namespace and client_ns namespace
+	setup_macvlan_ns "${DEV}" server_ns server \
+	"${SERVER_MAC}" "${SERVER_IP}"
+	setup_macvlan_ns "${DEV}" client_ns client \
+	"${CLIENT_MAC}" "${CLIENT_IP}"
+}
+
+cleanup() {
+	cleanup_macvlan_ns server_ns server client_ns client
+	cleanup_loopback "${DEV}"
+}
+
+parse_opts $0 $@
+
+setup
+trap cleanup EXIT
+
+check_nic_rxhash_enabled
+
+# Actual test starts here
+if [[ "${TEST_RSS}" = true ]]; then
+	# RPS/RFS must be disabled because they move packets between cpus,
+	# which breaks the PACKET_FANOUT_CPU identification of RSS decisions.
+	eval "$(get_disable_rfs_cmd) $(get_disable_rps_cmd)" \
+	  ip netns exec server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \
+	  -d "${PORT}" -i "${DEV}" -k "${KEY}" -T 1000 \
+	  -C "$(get_rx_irq_cpus)" -s -v &
+elif [[ ! -z "${RPS_MAP}" ]]; then
+	eval "$(get_disable_rfs_cmd) $(get_set_rps_bitmaps_cmd ${RPS_MAP})" \
+	  ip netns exec server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \
+	  -d "${PORT}" -i "${DEV}" -k "${KEY}" -T 1000 \
+	  -r "0x${RPS_MAP}" -s -v &
+else
+	ip netns exec server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \
+	  -d "${PORT}" -i "${DEV}" -k "${KEY}" -T 1000 -s -v &
+fi
+
+server_pid=$!
+
+ip netns exec client_ns ./toeplitz_client.sh "${PROTO_FLAG}" \
+  "${IP_FLAG}" "${SERVER_IP%%/*}" "${PORT}" &
+
+client_pid=$!
+
+wait "${server_pid}"
+exit_code=$?
+kill -9 "${client_pid}"
+if [[ "${exit_code}" -eq 0 ]]; then
+	echo "Test Succeeded!"
+fi
+exit "${exit_code}"

tools/testing/selftests/net/toeplitz_client.sh

+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# A simple program for generating traffic for the toeplitz test.
+#
+# This program sends packets periodically for, conservatively, 20 seconds. The
+# intent is for the calling program to kill this program once it is no longer
+# needed, rather than waiting for the 20 second expiration.
+
+send_traffic() {
+	expiration=$((SECONDS+20))
+	while [[ "${SECONDS}" -lt "${expiration}" ]]
+	do
+		if [[ "${PROTO}" == "-u" ]]; then
+			echo "msg $i" | nc "${IPVER}" -u -w 0 "${ADDR}" "${PORT}"
+		else
+			echo "msg $i" | nc "${IPVER}" -w 0 "${ADDR}" "${PORT}"
+		fi
+		sleep 0.001
+	done
+}
+
+PROTO=$1
+IPVER=$2
+ADDR=$3
+PORT=$4
+
+send_traffic