summaryrefslogtreecommitdiffstats
path: root/tools/testing/selftests/net/mptcp/simult_flows.sh
blob: 06ad0510469e39148bdb2ecd89d82ae7b2b9eb01 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0

. "$(dirname "${0}")/mptcp_lib.sh"

rndh=$(printf %x $sec)-$(mktemp -u XXXXXX)
ns1="ns1-$rndh"
ns2="ns2-$rndh"
ns3="ns3-$rndh"
capture=false
ksft_skip=4
timeout_poll=30
timeout_test=$((timeout_poll * 2 + 1))
test_cnt=1
ret=0
bail=0
slack=50

usage() {
	echo "Usage: $0 [ -b ] [ -c ] [ -d ]"
	echo -e "\t-b: bail out after first error, otherwise runs al testcases"
	echo -e "\t-c: capture packets for each test using tcpdump (default: no capture)"
	echo -e "\t-d: debug this script"
}

cleanup()
{
	rm -f "$cout" "$sout"
	rm -f "$large" "$small"
	rm -f "$capout"

	local netns
	for netns in "$ns1" "$ns2" "$ns3";do
		ip netns del $netns
	done
}

mptcp_lib_check_mptcp

ip -Version > /dev/null 2>&1
if [ $? -ne 0 ];then
	echo "SKIP: Could not run test without ip tool"
	exit $ksft_skip
fi

#  "$ns1"              ns2                    ns3
#     ns1eth1    ns2eth1   ns2eth3      ns3eth1
#            netem
#     ns1eth2    ns2eth2
#            netem

setup()
{
	large=$(mktemp)
	small=$(mktemp)
	sout=$(mktemp)
	cout=$(mktemp)
	capout=$(mktemp)
	size=$((2 * 2048 * 4096))

	dd if=/dev/zero of=$small bs=4096 count=20 >/dev/null 2>&1
	dd if=/dev/zero of=$large bs=4096 count=$((size / 4096)) >/dev/null 2>&1

	trap cleanup EXIT

	for i in "$ns1" "$ns2" "$ns3";do
		ip netns add $i || exit $ksft_skip
		ip -net $i link set lo up
		ip netns exec $i sysctl -q net.ipv4.conf.all.rp_filter=0
		ip netns exec $i sysctl -q net.ipv4.conf.default.rp_filter=0
	done

	ip link add ns1eth1 netns "$ns1" type veth peer name ns2eth1 netns "$ns2"
	ip link add ns1eth2 netns "$ns1" type veth peer name ns2eth2 netns "$ns2"
	ip link add ns2eth3 netns "$ns2" type veth peer name ns3eth1 netns "$ns3"

	ip -net "$ns1" addr add 10.0.1.1/24 dev ns1eth1
	ip -net "$ns1" addr add dead:beef:1::1/64 dev ns1eth1 nodad
	ip -net "$ns1" link set ns1eth1 up mtu 1500
	ip -net "$ns1" route add default via 10.0.1.2
	ip -net "$ns1" route add default via dead:beef:1::2

	ip -net "$ns1" addr add 10.0.2.1/24 dev ns1eth2
	ip -net "$ns1" addr add dead:beef:2::1/64 dev ns1eth2 nodad
	ip -net "$ns1" link set ns1eth2 up mtu 1500
	ip -net "$ns1" route add default via 10.0.2.2 metric 101
	ip -net "$ns1" route add default via dead:beef:2::2 metric 101

	ip netns exec "$ns1" ./pm_nl_ctl limits 1 1
	ip netns exec "$ns1" ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags subflow

	ip -net "$ns2" addr add 10.0.1.2/24 dev ns2eth1
	ip -net "$ns2" addr add dead:beef:1::2/64 dev ns2eth1 nodad
	ip -net "$ns2" link set ns2eth1 up mtu 1500

	ip -net "$ns2" addr add 10.0.2.2/24 dev ns2eth2
	ip -net "$ns2" addr add dead:beef:2::2/64 dev ns2eth2 nodad
	ip -net "$ns2" link set ns2eth2 up mtu 1500

	ip -net "$ns2" addr add 10.0.3.2/24 dev ns2eth3
	ip -net "$ns2" addr add dead:beef:3::2/64 dev ns2eth3 nodad
	ip -net "$ns2" link set ns2eth3 up mtu 1500
	ip netns exec "$ns2" sysctl -q net.ipv4.ip_forward=1
	ip netns exec "$ns2" sysctl -q net.ipv6.conf.all.forwarding=1

	ip -net "$ns3" addr add 10.0.3.3/24 dev ns3eth1
	ip -net "$ns3" addr add dead:beef:3::3/64 dev ns3eth1 nodad
	ip -net "$ns3" link set ns3eth1 up mtu 1500
	ip -net "$ns3" route add default via 10.0.3.2
	ip -net "$ns3" route add default via dead:beef:3::2

	ip netns exec "$ns3" ./pm_nl_ctl limits 1 1

	# debug build can slow down measurably the test program
	# we use quite tight time limit on the run-time, to ensure
	# maximum B/W usage.
	# Use kmemleak/lockdep/kasan/prove_locking presence as a rough
	# estimate for this being a debug kernel and increase the
	# maximum run-time accordingly. Observed run times for CI builds
	# running selftests, including kbuild, were used to determine the
	# amount of time to add.
	grep -q ' kmemleak_init$\| lockdep_init$\| kasan_init$\| prove_locking$' /proc/kallsyms && slack=$((slack+550))
}

# $1: ns, $2: port
wait_local_port_listen()
{
	local listener_ns="${1}"
	local port="${2}"

	local port_hex i

	port_hex="$(printf "%04X" "${port}")"
	for i in $(seq 10); do
		ip netns exec "${listener_ns}" cat /proc/net/tcp* | \
			awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" &&
			break
		sleep 0.1
	done
}

do_transfer()
{
	local cin=$1
	local sin=$2
	local max_time=$3
	local port
	port=$((10000+$test_cnt))
	test_cnt=$((test_cnt+1))

	:> "$cout"
	:> "$sout"
	:> "$capout"

	local addr_port
	addr_port=$(printf "%s:%d" ${connect_addr} ${port})

	if $capture; then
		local capuser
		if [ -z $SUDO_USER ] ; then
			capuser=""
		else
			capuser="-Z $SUDO_USER"
		fi

		local capfile="${rndh}-${port}"
		local capopt="-i any -s 65535 -B 32768 ${capuser}"

		ip netns exec ${ns3}  tcpdump ${capopt} -w "${capfile}-listener.pcap"  >> "${capout}" 2>&1 &
		local cappid_listener=$!

		ip netns exec ${ns1} tcpdump ${capopt} -w "${capfile}-connector.pcap" >> "${capout}" 2>&1 &
		local cappid_connector=$!

		sleep 1
	fi

	timeout ${timeout_test} \
		ip netns exec ${ns3} \
			./mptcp_connect -jt ${timeout_poll} -l -p $port -T $time \
				0.0.0.0 < "$sin" > "$sout" &
	local spid=$!

	wait_local_port_listen "${ns3}" "${port}"

	timeout ${timeout_test} \
		ip netns exec ${ns1} \
			./mptcp_connect -jt ${timeout_poll} -p $port -T $time \
				10.0.3.3 < "$cin" > "$cout" &
	local cpid=$!

	wait $cpid
	local retc=$?
	wait $spid
	local rets=$?

	if $capture; then
		sleep 1
		kill ${cappid_listener}
		kill ${cappid_connector}
	fi

	cmp $sin $cout > /dev/null 2>&1
	local cmps=$?
	cmp $cin $sout > /dev/null 2>&1
	local cmpc=$?

	printf "%-16s" " max $max_time "
	if [ $retc -eq 0 ] && [ $rets -eq 0 ] && \
	   [ $cmpc -eq 0 ] && [ $cmps -eq 0 ]; then
		echo "[ OK ]"
		cat "$capout"
		return 0
	fi

	echo " [ fail ]"
	echo "client exit code $retc, server $rets" 1>&2
	echo -e "\nnetns ${ns3} socket stat for $port:" 1>&2
	ip netns exec ${ns3} ss -nita 1>&2 -o "sport = :$port"
	echo -e "\nnetns ${ns1} socket stat for $port:" 1>&2
	ip netns exec ${ns1} ss -nita 1>&2 -o "dport = :$port"
	ls -l $sin $cout
	ls -l $cin $sout

	cat "$capout"
	return 1
}

run_test()
{
	local rate1=$1
	local rate2=$2
	local delay1=$3
	local delay2=$4
	local lret
	local dev
	shift 4
	local msg=$*

	[ $delay1 -gt 0 ] && delay1="delay $delay1" || delay1=""
	[ $delay2 -gt 0 ] && delay2="delay $delay2" || delay2=""

	for dev in ns1eth1 ns1eth2; do
		tc -n $ns1 qdisc del dev $dev root >/dev/null 2>&1
	done
	for dev in ns2eth1 ns2eth2; do
		tc -n $ns2 qdisc del dev $dev root >/dev/null 2>&1
	done
	tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1
	tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2
	tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1
	tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2

	# time is measured in ms, account for transfer size, aggregated link speed
	# and header overhead (10%)
	#              ms    byte -> bit   10%        mbit      -> kbit -> bit  10%
	local time=$((1000 * size  *  8  * 10 / ((rate1 + rate2) * 1000 * 1000 * 9) ))

	# mptcp_connect will do some sleeps to allow the mp_join handshake
	# completion (see mptcp_connect): 200ms on each side, add some slack
	time=$((time + 400 + slack))

	printf "%-60s" "$msg"
	do_transfer $small $large $time
	lret=$?
	if [ $lret -ne 0 ]; then
		ret=$lret
		[ $bail -eq 0 ] || exit $ret
	fi

	printf "%-60s" "$msg - reverse direction"
	do_transfer $large $small $time
	lret=$?
	if [ $lret -ne 0 ]; then
		ret=$lret
		[ $bail -eq 0 ] || exit $ret
	fi
}

while getopts "bcdh" option;do
	case "$option" in
	"h")
		usage $0
		exit 0
		;;
	"b")
		bail=1
		;;
	"c")
		capture=true
		;;
	"d")
		set -x
		;;
	"?")
		usage $0
		exit 1
		;;
	esac
done

setup
run_test 10 10 0 0 "balanced bwidth"
run_test 10 10 1 25 "balanced bwidth with unbalanced delay"

# we still need some additional infrastructure to pass the following test-cases
run_test 10 3 0 0 "unbalanced bwidth"
run_test 10 3 1 25 "unbalanced bwidth with unbalanced delay"
run_test 10 3 25 1 "unbalanced bwidth with opposed, unbalanced delay"
exit $ret