@@ -18851,6 +18851,7 @@ S: Supported
W: https://oss.oracle.com/projects/rds/
F: Documentation/networking/rds.rst
F: net/rds/
+F: tools/testing/selftests/net/rds/
RDT - RESOURCE ALLOCATION
M: Fenghua Yu <fenghua.yu@intel.com>
@@ -66,6 +66,7 @@ TARGETS += net/mptcp
TARGETS += net/openvswitch
TARGETS += net/tcp_ao
TARGETS += net/netfilter
+TARGETS += net/rds
TARGETS += nsfs
TARGETS += perf_events
TARGETS += pidfd
new file mode 100644
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: GPL-2.0
+
+all:
+ @echo mk_build_dir="$(shell pwd)" > include.sh
+
+TEST_PROGS := run.sh \
+ include.sh \
+ test.py \
+ init.sh
+
+EXTRA_CLEAN := /tmp/rds_logs
+
+include ../../lib.mk
new file mode 100644
@@ -0,0 +1,15 @@
+RDS self-tests
+==============
+
+Usage:
+
+ # create a suitable .config
+ tools/testing/selftests/net/rds/config.sh
+
+ # build the kernel
+ make -j128
+
+ # launch the tests in a VM
+ tools/testing/selftests/net/rds/run.sh
+
+An HTML coverage report will be output in /tmp/rds_logs/coverage/.
new file mode 100755
@@ -0,0 +1,33 @@
+# SPDX-License-Identifier: GPL-2.0
+#! /bin/bash
+
+set -e
+set -u
+set -x
+
+unset KBUILD_OUTPUT
+
+# start with a default config
+make defconfig
+
+# no modules
+scripts/config --disable CONFIG_MODULES
+
+# enable RDS
+scripts/config --enable CONFIG_RDS
+scripts/config --enable CONFIG_RDS_TCP
+
+# instrument RDS and only RDS
+scripts/config --enable CONFIG_GCOV_KERNEL
+scripts/config --disable GCOV_PROFILE_ALL
+scripts/config --enable GCOV_PROFILE_RDS
+
+# need network namespaces to run tests with veth network interfaces
+scripts/config --enable CONFIG_NET_NS
+scripts/config --enable CONFIG_VETH
+
+# simulate packet loss
+scripts/config --enable CONFIG_NET_SCH_NETEM
+
+# generate real .config without asking any questions
+make olddefconfig
new file mode 100755
@@ -0,0 +1,49 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+set -u
+
+LOG_DIR=/tmp
+PY_CMD="/usr/bin/python3"
+while getopts "d:p:" opt; do
+ case ${opt} in
+ d)
+ LOG_DIR=${OPTARG}
+ ;;
+ p)
+ PY_CMD=${OPTARG}
+ ;;
+ :)
+ echo "USAGE: init.sh [-d logdir] [-p python_cmd]"
+ exit 1
+ ;;
+ ?)
+ echo "Invalid option: -${OPTARG}."
+ exit 1
+ ;;
+ esac
+done
+
+LOG_FILE=$LOG_DIR/rds-strace.txt
+
+mount -t proc none /proc
+mount -t sysfs none /sys
+mount -t tmpfs none /var/run
+mount -t debugfs none /sys/kernel/debug
+
+echo running RDS tests...
+echo Traces will be logged to $LOG_FILE
+rm -f $LOG_FILE
+strace -T -tt -o "$LOG_FILE" $PY_CMD $(dirname "$0")/test.py -d "$LOG_DIR" || true
+
+echo saving coverage data...
+(set +x; cd /sys/kernel/debug/gcov; find * -name '*.gcda' | \
+while read f
+do
+ cat < /sys/kernel/debug/gcov/$f > /$f
+done)
+
+dmesg > $LOG_DIR/dmesg.out
+
+/usr/sbin/poweroff --no-wtmp --force
new file mode 100755
@@ -0,0 +1,168 @@
+# SPDX-License-Identifier: GPL-2.0
+#! /bin/bash
+
+set -e
+set -u
+
+unset KBUILD_OUTPUT
+
+current_dir="$(realpath "$(dirname "$0")")"
+build_dir=$current_dir
+
+build_include="$current_dir/include.sh"
+if test -f "$build_include"; then
+ # this include will define "$mk_build_dir" as the location the test was
+ # built. We will need this if the tests are installed in a location
+ # other than the kernel source
+
+ source $build_include
+ build_dir=$mk_build_dir
+fi
+
+# This test requires kernel source and the *.gcda data therein
+# Locate the top level of the kernel source, and the net/rds
+# subfolder with the appropriate *.gcno object files
+ksrc_dir="$(realpath $build_dir/../../../../../)"
+kconfig="$ksrc_dir/.config"
+obj_dir="$ksrc_dir/net/rds"
+
+GCOV_CMD=gcov
+
+# This script currently only works for x86_64
+ARCH="$(uname -m)"
+case "${ARCH}" in
+x86_64)
+ QEMU_BINARY=qemu-system-x86_64
+ ;;
+*)
+ echo "selftests: [SKIP] Unsupported architecture"
+ exit 4
+ ;;
+esac
+
+# Kselftest framework requirement - SKIP code is 4.
+check_conf_enabled() {
+ if ! grep -x "$1=y" $kconfig > /dev/null 2>&1; then
+ echo selftests: [SKIP] This test requires $1 enabled
+ echo Please run tools/testing/selftests/net/rds/config.sh and rebuild the kernel
+ exit 4
+ fi
+}
+check_conf_disabled() {
+ if grep -x "$1=y" $kconfig > /dev/null 2>&1; then
+ echo selftests: [SKIP] This test requires $1 disabled
+ echo Please run tools/testing/selftests/net/rds/config.sh and rebuild the kernel
+ exit 4
+ fi
+}
+check_conf() {
+ check_conf_enabled CONFIG_NET_SCH_NETEM
+ check_conf_enabled CONFIG_VETH
+ check_conf_enabled CONFIG_NET_NS
+ check_conf_enabled CONFIG_GCOV_PROFILE_RDS
+ check_conf_enabled CONFIG_GCOV_KERNEL
+ check_conf_enabled CONFIG_RDS_TCP
+ check_conf_enabled CONFIG_RDS
+ check_conf_disabled CONFIG_MODULES
+ check_conf_disabled CONFIG_GCOV_PROFILE_ALL
+}
+
+check_env()
+{
+ if ! test -d $obj_dir; then
+ echo "selftests: [SKIP] This test requires a kernel source tree"
+ exit 4
+ fi
+ if ! test -e $kconfig; then
+ echo "selftests: [SKIP] This test requires a configured kernel source tree"
+ exit 4
+ fi
+ if ! which strace > /dev/null 2>&1; then
+ echo "selftests: [SKIP] Could not run test without strace"
+ exit 4
+ fi
+ if ! which tcpdump > /dev/null 2>&1; then
+ echo "selftests: [SKIP] Could not run test without tcpdump"
+ exit 4
+ fi
+ if ! which $GCOV_CMD > /dev/null 2>&1; then
+ echo "selftests: [SKIP] Could not run with out gcov. "
+ exit 4
+ fi
+
+ # the gcov version much match the gcc version
+ GCC_VER=`gcc -dumpfullversion`
+ GCOV_VER=`$GCOV_CMD -v | grep gcov | awk '{print $3}'| awk 'BEGIN {FS="-"}{print $1}'`
+ if [ "$GCOV_VER" != "$GCC_VER" ]; then
+ #attempt to find a matching gcov version
+ GCOV_CMD=gcov-`gcc -dumpversion`
+
+ if ! which $GCOV_CMD > /dev/null 2>&1; then
+ echo "selftests: [SKIP] gcov version must match gcc version"
+ exit 4
+ fi
+
+ #recheck version number of found gcov executable
+ GCOV_VER=`$GCOV_CMD -v | grep gcov | awk '{print $3}'| \
+ awk 'BEGIN {FS="-"}{print $1}'`
+ if [ "$GCOV_VER" != "$GCC_VER" ]; then
+ echo "selftests: [SKIP] gcov version must match gcc version"
+ exit 4
+ fi
+ fi
+
+ if ! which gcovr > /dev/null 2>&1; then
+ echo "selftests: [SKIP] Could not run test without gcovr"
+ exit 4
+ fi
+
+ if ! which $QEMU_BINARY > /dev/null 2>&1; then
+ echo "selftests: [SKIP] Could not run test without qemu"
+ exit 4
+ fi
+
+ if ! which python3 > /dev/null 2>&1; then
+ echo "selftests: [SKIP] Could not run test without python3"
+ exit 4
+ fi
+
+ python_major=`python3 -c "import sys; print(sys.version_info[0])"`
+ python_minor=`python3 -c "import sys; print(sys.version_info[1])"`
+ if [[ python_major -lt 3 || ( python_major -eq 3 && python_minor -lt 9 ) ]] ; then
+ echo "selftests: [SKIP] Could not run test without at least python3.9"
+ python3 -V
+ exit 4
+ fi
+}
+
+check_env
+check_conf
+
+#if we are running in a python environment, we need to capture that
+#python bin so we can use the same python environment in the vm
+PY_CMD=`which python3`
+
+LOG_DIR=/tmp/rds_logs
+mkdir -p $LOG_DIR
+
+# start a VM using a 9P root filesystem that maps to the host's /
+# we pass ./init.sh from the same directory as we are in as the
+# guest's init, which will run the tests and copy the coverage
+# data back to the host filesystem.
+$QEMU_BINARY \
+ -enable-kvm \
+ -cpu host \
+ -smp 4 \
+ -kernel ${ksrc_dir}/arch/x86/boot/bzImage \
+ -append "rootfstype=9p root=/dev/root rootflags=trans=virtio,version=9p2000.L rw \
+ console=ttyS0 init=${current_dir}/init.sh -d ${LOG_DIR} -p ${PY_CMD}" \
+ -display none \
+ -serial stdio \
+ -fsdev local,id=fsdev0,path=/,security_model=none,multidevs=remap \
+ -device virtio-9p-pci,fsdev=fsdev0,mount_tag=/dev/root \
+ -no-reboot
+
+# generate a nice HTML coverage report
+echo running gcovr...
+gcovr -v -s --html-details --gcov-executable $GCOV_CMD --gcov-ignore-parse-errors \
+ -o $LOG_DIR/coverage/ "${ksrc_dir}/net/rds/"
new file mode 100644
@@ -0,0 +1,244 @@
+# SPDX-License-Identifier: GPL-2.0
+#! /usr/bin/env python3
+
+import argparse
+import ctypes
+import errno
+import hashlib
+import os
+import select
+import signal
+import socket
+import subprocess
+import sys
+import atexit
+from pwd import getpwuid
+from os import stat
+
+libc = ctypes.cdll.LoadLibrary('libc.so.6')
+setns = libc.setns
+
+net0 = 'net0'
+net1 = 'net1'
+
+veth0 = 'veth0'
+veth1 = 'veth1'
+
+# Convenience wrapper function for calling the subsystem ip command.
+def ip(*args):
+ subprocess.check_call(['/usr/sbin/ip'] + list(args))
+
+# Helper function for creating a socket inside a network namespace.
+# We need this because otherwise RDS will detect that the two TCP
+# sockets are on the same interface and use the loop transport instead
+# of the TCP transport.
+def netns_socket(netns, *args):
+ u0, u1 = socket.socketpair(socket.AF_UNIX, socket.SOCK_SEQPACKET)
+
+ child = os.fork()
+ if child == 0:
+ # change network namespace
+ with open(f'/var/run/netns/{netns}') as f:
+ try:
+ ret = setns(f.fileno(), 0)
+ except IOError as e:
+ print(e.errno)
+ print(e)
+
+ # create socket in target namespace
+ s = socket.socket(*args)
+
+ # send resulting socket to parent
+ socket.send_fds(u0, [], [s.fileno()])
+
+ sys.exit(0)
+
+ # receive socket from child
+ _, s, _, _ = socket.recv_fds(u1, 0, 1)
+ os.waitpid(child, 0)
+ u0.close()
+ u1.close()
+ return socket.fromfd(s[0], *args)
+
+#Parse out command line arguments. We take an optional
+# timeout parameter and an optional log output folder
+parser = argparse.ArgumentParser(description="init script args",
+ formatter_class=argparse.ArgumentDefaultsHelpFormatter)
+parser.add_argument("-d", "--logdir", action="store", help="directory to store logs", default="/tmp")
+parser.add_argument('--timeout', type=int, default=0)
+args = parser.parse_args()
+logdir=args.logdir
+
+ip('netns', 'add', net0)
+ip('netns', 'add', net1)
+ip('link', 'add', 'type', 'veth')
+
+addrs = [
+ # we technically don't need different port numbers, but this will
+ # help identify traffic in the network analyzer
+ ('10.0.0.1', 10000),
+ ('10.0.0.2', 20000),
+]
+
+# move interfaces to separate namespaces so they can no longer be
+# bound directly; this prevents rds from switching over from the tcp
+# transport to the loop transport.
+ip('link', 'set', veth0, 'netns', net0, 'up')
+ip('link', 'set', veth1, 'netns', net1, 'up')
+
+# add addresses
+ip('-n', net0, 'addr', 'add', addrs[0][0] + '/32', 'dev', veth0)
+ip('-n', net1, 'addr', 'add', addrs[1][0] + '/32', 'dev', veth1)
+
+# add routes
+ip('-n', net0, 'route', 'add', addrs[1][0] + '/32', 'dev', veth0)
+ip('-n', net1, 'route', 'add', addrs[0][0] + '/32', 'dev', veth1)
+
+# sanity check that our two interfaces/addresses are correctly set up
+# and communicating by doing a single ping
+ip('netns', 'exec', net0, 'ping', '-c', '1', addrs[1][0])
+
+# Start a packet capture on each network
+for net in [net0, net1]:
+ tcpdump_pid = os.fork()
+ if tcpdump_pid == 0:
+ pcap = logdir+'/'+net+'.pcap'
+ subprocess.check_call(['touch', pcap])
+ user = getpwuid(stat(pcap).st_uid).pw_name
+ ip('netns', 'exec', net, '/usr/sbin/tcpdump', '-Z', user, '-i', 'any', '-w', pcap)
+ sys.exit(0)
+
+# simulate packet loss, duplication and corruption
+for net, iface in [(net0, veth0), (net1, veth1)]:
+ ip('netns', 'exec', net,
+ '/usr/sbin/tc', 'qdisc', 'add', 'dev', iface, 'root', 'netem',
+ 'corrupt', '5%',
+ 'loss', '5%',
+ 'duplicate', '5%',
+ )
+
+# add a timeout
+if args.timeout > 0:
+ signal.alarm(args.timeout)
+
+sockets = [
+ netns_socket(net0, socket.AF_RDS, socket.SOCK_SEQPACKET),
+ netns_socket(net1, socket.AF_RDS, socket.SOCK_SEQPACKET),
+]
+
+for s, addr in zip(sockets, addrs):
+ s.bind(addr)
+ s.setblocking(0)
+
+fileno_to_socket = {
+ s.fileno(): s for s in sockets
+}
+
+addr_to_socket = {
+ addr: s for addr, s in zip(addrs, sockets)
+}
+
+socket_to_addr = {
+ s: addr for addr, s in zip(addrs, sockets)
+}
+
+send_hashes = {}
+recv_hashes = {}
+
+ep = select.epoll()
+
+for s in sockets:
+ ep.register(s, select.EPOLLRDNORM)
+
+n = 50000
+nr_send = 0
+nr_recv = 0
+
+while nr_send < n:
+ # Send as much as we can without blocking
+ print("sending...", nr_send, nr_recv)
+ while nr_send < n:
+ send_data = hashlib.sha256(f'packet {nr_send}'.encode('utf-8')).hexdigest().encode('utf-8')
+
+ # pseudo-random send/receive pattern
+ sender = sockets[nr_send % 2]
+ receiver = sockets[1 - (nr_send % 3) % 2]
+
+ try:
+ sender.sendto(send_data, socket_to_addr[receiver])
+ send_hashes.setdefault((sender.fileno(), receiver.fileno()), hashlib.sha256()).update(f'<{send_data}>'.encode('utf-8'))
+ nr_send = nr_send + 1
+ except BlockingIOError as e:
+ break
+ except OSError as e:
+ if e.errno in [errno.ENOBUFS, errno.ECONNRESET, errno.EPIPE]:
+ break
+ raise
+
+ # Receive as much as we can without blocking
+ print("receiving...", nr_send, nr_recv)
+ while nr_recv < nr_send:
+ for fileno, eventmask in ep.poll():
+ receiver = fileno_to_socket[fileno]
+
+ if eventmask & select.EPOLLRDNORM:
+ while True:
+ try:
+ recv_data, address = receiver.recvfrom(1024)
+ sender = addr_to_socket[address]
+ recv_hashes.setdefault((sender.fileno(), receiver.fileno()), hashlib.sha256()).update(f'<{recv_data}>'.encode('utf-8'))
+ nr_recv = nr_recv + 1
+ except BlockingIOError as e:
+ break
+
+ # exercise net/rds/tcp.c:rds_tcp_sysctl_reset()
+ for net in [net0, net1]:
+ ip('netns', 'exec', net, '/usr/sbin/sysctl', 'net.rds.tcp.rds_tcp_rcvbuf=10000')
+ ip('netns', 'exec', net, '/usr/sbin/sysctl', 'net.rds.tcp.rds_tcp_sndbuf=10000')
+
+print("done", nr_send, nr_recv)
+
+# the Python socket module doesn't know these
+RDS_INFO_FIRST = 10000
+RDS_INFO_LAST = 10017
+
+nr_success = 0
+nr_error = 0
+
+for s in sockets:
+ for optname in range(RDS_INFO_FIRST, RDS_INFO_LAST + 1):
+ # Sigh, the Python socket module doesn't allow us to pass
+ # buffer lengths greater than 1024 for some reason. RDS
+ # wants multiple pages.
+ try:
+ s.getsockopt(socket.SOL_RDS, optname, 1024)
+ nr_success = nr_success + 1
+ except OSError as e:
+ nr_error = nr_error + 1
+ if e.errno == errno.ENOSPC:
+ # ignore
+ pass
+
+print(f"getsockopt(): {nr_success}/{nr_error}")
+
+print("Stopping network packet captures")
+subprocess.check_call(['killall', '-q', 'tcpdump'])
+
+# We're done sending and receiving stuff, now let's check if what
+# we received is what we sent.
+for (sender, receiver), send_hash in send_hashes.items():
+ recv_hash = recv_hashes.get((sender, receiver))
+
+ if recv_hash is None:
+ print("FAIL: No data received")
+ sys.exit(1)
+
+ if send_hash.hexdigest() != recv_hash.hexdigest():
+ print("FAIL: Send/recv mismatch")
+ print("hash expected:", send_hash.hexdigest())
+ print("hash received:", recv_hash.hexdigest())
+ sys.exit(1)
+
+ print(f"{sender}/{receiver}: ok")
+
+print("Success")