Linux kernel mirror (for testing)
git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel
os
linux
1#!/bin/bash
2# SPDX-License-Identifier: GPL-2.0
3
4source lib.sh
5
6# shellcheck disable=SC2155 # prefer RO variable over return value from cmd
7readonly CLI="$(dirname "$(readlink -f "$0")")/../../../net/ynl/pyynl/cli.py"
8
9readonly SRC=1
10readonly DST=2
11
12readonly NET_V4=192.168.1.
13readonly NET_V6=2001:db8::
14readonly OL1_NET_V4=172.16.1.
15readonly OL1_NET_V6=2001:db8:1::
16readonly OL2_NET_V4=172.16.2.
17readonly OL2_NET_V6=2001:db8:2::
18
19trap cleanup_all_ns EXIT
20
21# shellcheck disable=SC2329 # can't figure out usage trough a variable
22is_ipv6() {
23 if [[ $1 =~ .*:.* ]]; then
24 return 0
25 fi
26 return 1
27}
28
29# shellcheck disable=SC2329 # can't figure out usage trough a variable
30create_gnv_endpoint() {
31 local -r netns=$1
32 local -r bm_rem_addr=$2
33 local -r gnv_dev=$3
34 local -r gnv_id=$4
35 local opts=$5
36 local gnv_json
37 local rem
38
39 if is_ipv6 "$bm_rem_addr"; then
40 rem=remote6
41 else
42 rem=remote
43 fi
44
45 # add ynl opt separator, if needed
46 [ -n "$opts" ] && opts=", $opts"
47
48 gnv_json="{ \"id\": $gnv_id, \"$rem\": \"$bm_rem_addr\"$opts }"
49 ip netns exec "$netns" "$CLI" --family rt-link --create --excl \
50 --do newlink --json "{\"ifname\": \"$gnv_dev\",
51 \"linkinfo\": {\"kind\":\"geneve\",
52 \"data\": $gnv_json } }" > /dev/null
53 ip -n "$netns" link set dev "$gnv_dev" up
54}
55
56# shellcheck disable=SC2329 # can't figure out usage trough a variable
57create_vxlan_endpoint() {
58 local -r netns=$1
59 local -r bm_rem_addr=$2
60 local -r vxlan_dev=$3
61 local -r vxlan_id=$4
62 local -r opts_str=$5
63 local oldifs
64 local -a opts
65 local opt
66
67 # convert the arguments from yaml format
68 oldifs=$IFS
69 IFS=','
70 for opt in $opts_str; do
71 local pattern='"port":'
72
73 [ -n "$opt" ] || continue
74
75 opts+=("${opt/$pattern*/dstport}" "${opt/$pattern/}")
76 done
77 IFS=$oldifs
78 [ ${#opts[@]} -gt 0 ] || opts+=("dstport" "4789")
79
80 ip -n "$netns" link add "$vxlan_dev" type vxlan id "$vxlan_id" \
81 remote "$bm_rem_addr" "${opts[@]}"
82 ip -n "$netns" link set dev "$vxlan_dev" up
83}
84
85create_ns() {
86 local nested_opt='"port":6082'
87 local create_endpoint
88 local options="$1"
89 local feature
90 local dev
91 local id
92 local ns
93
94 RET=0
95
96 # +-------------+ +-------------+
97 # | NS_SRC | | NS_NST_DST |
98 # | | | |
99 # | gnv_nst1 | | gnv_nst2 |
100 # | + | | + |
101 # | | | | | |
102 # | + | | + |
103 # | gnv1 | | gnv2 |
104 # | + | | + |
105 # | | | | | |
106 # | + veth1 +--------+ veth2 + |
107 # | | | |
108 # +-------------+ +-------------+
109
110 setup_ns NS_SRC NS_DST
111
112 # concatenate caller provided options and default one
113 [ -n "$2" ] && nested_opt="$nested_opt,$2"
114
115 ip link add name "veth$SRC" netns "$NS_SRC" type veth \
116 peer name "veth$DST" netns "$NS_DST"
117 case "$ENCAP" in
118 vxlan)
119 create_endpoint=create_vxlan_endpoint
120 dev=vx
121 ;;
122 geneve)
123 create_endpoint=create_gnv_endpoint
124 dev=gnv
125 ;;
126 esac
127
128 id=1
129 for ns in "${NS_LIST[@]}"; do
130 ip -n "$ns" link set dev "veth$id" up
131
132 # ensure the sender can do large write just after 3whs
133 ip netns exec "$ns" \
134 sysctl -qw net.ipv4.tcp_wmem="4096 4194304 4194304"
135
136 # note that 3 - $SRC == $DST and 3 - $DST == $SRC
137 if [ $FAMILY = "4" ]; then
138 ip -n "$ns" addr add dev "veth$id" "$NET_V4$id/24"
139 $create_endpoint "$ns" "$NET_V4$((3 - id))" \
140 "$dev$id" 4 "$options"
141 ip -n "$ns" addr add dev "$dev$id" "$OL1_NET_V4$id/24"
142
143 # nested tunnel devices
144 # pmtu can't be propagated to upper layer devices;
145 # need manual adjust
146 $create_endpoint "$ns" "$OL1_NET_V4$((3 - id))" \
147 "$dev"_nst"$id" 40 "$nested_opt"
148 ip -n "$ns" addr add dev "$dev"_nst"$id" \
149 "$OL2_NET_V4$id/24"
150 ip -n "$ns" link set dev "$dev"_nst"$id" mtu 1392
151 else
152 ip -n "$ns" addr add dev "veth$id" "$NET_V6$id/64" \
153 nodad
154 $create_endpoint "$ns" "$NET_V6$((3 - id))" \
155 "$dev"6"$id" 6 "$options"
156 ip -n "$ns" addr add dev "$dev"6"$id" \
157 "$OL1_NET_V6$id/64" nodad
158
159 $create_endpoint "$ns" "$OL1_NET_V6$((3 - id))" \
160 "$dev"6_nst"$id" 60 "$nested_opt"
161 ip -n "$ns" addr add dev "$dev"6_nst"$id" \
162 "$OL2_NET_V6$id/64" nodad
163 ip -n "$ns" link set dev "$dev"6_nst"$id" mtu 1352
164 fi
165 id=$((id+1))
166 done
167
168 # enable GRO heuristic on the veth peer and ensure UDP L4 over tunnel is
169 # actually segmented
170 for feature in tso tx-udp_tnl-segmentation; do
171 ip netns exec "$NS_SRC" ethtool -K "veth$SRC" \
172 "$feature" off 2>/dev/null
173 done
174}
175
176create_ns_gso() {
177 local dev
178
179 create_ns "$@"
180 if [ "$ENCAP" = "geneve" ]; then
181 dev=gnv
182 else
183 dev=vx
184 fi
185 [ "$FAMILY" = "6" ] && dev="$dev"6
186 ip netns exec "$NS_SRC" ethtool -K "$dev$SRC" \
187 tx-gso-partial on \
188 tx-udp_tnl-segmentation on \
189 tx-udp_tnl-csum-segmentation on
190}
191
192create_ns_gso_gro() {
193 create_ns_gso "$@"
194 ip netns exec "$NS_DST" ethtool -K "veth$DST" gro on
195 ip netns exec "$NS_SRC" ethtool -K "veth$SRC" tx off >/dev/null 2>&1
196}
197
198run_test() {
199 local -r dst=$NET$DST
200 local -r msg=$1
201 local -r total_size=$2
202 local -r encappkts=$3
203 local inner_proto_offset=0
204 local inner_maclen=14
205 local rx_family="-4"
206 local ipt=iptables
207 local bpf_filter
208 local -a rx_args
209 local wire_pkts
210 local rcvpkts
211 local encl=8
212 local dport
213 local pkts
214 local snd
215
216 if [ $FAMILY = "6" ]; then
217 ipt=ip6tables
218 else
219 # rx program does not support '-6' and implies ipv6 usage by
220 # default
221 rx_args=("$rx_family")
222 fi
223
224 # The received can only check fixed size packet
225 pkts=$((total_size / GSO_SIZE))
226 if [ -n "$4" ]; then
227 wire_pkts=$4
228 elif [ $((total_size % GSO_SIZE)) -eq 0 ]; then
229 wire_pkts=1
230 rx_args+=("-l" "$GSO_SIZE")
231 else
232 wire_pkts=2
233 pkts=$((pkts + 1))
234 fi
235
236 if [ "$ENCAP" = "geneve" ]; then
237 dport=6081
238 else
239 dport=4789
240 fi
241
242 # Either:
243 # - IPv4, nested tunnel carries UDP over IPv4, with dport 6082,
244 # innermost is TCP over IPv4 on port 8000
245 # - IPv6, nested tunnel carries UDP over IPv6, with dport 6082,
246 # innermost is TCP over IPv6 on port 8000
247 # The nested tunnel port is 6082 and the nested encap len is 8
248 # regardless of the encap type (no geneve opts).
249 # In inherit protocol mode there is no nested mac hdr and the nested
250 # l3 protocol type field belongs to the geneve hdr.
251 [ "$USE_HINT" = true ] && encl=16
252 [ "$INHERIT" = true ] && inner_maclen=0
253 [ "$INHERIT" = true ] && inner_proto_offset=-4
254 local inner=$((inner_maclen+encl))
255 local proto=$((inner_maclen+encl+inner_proto_offset))
256 bpf_filter=$(nfbpf_compile "(ip &&
257 ip[$((40+encl))] == 0x08 && ip[$((41+encl))] == 0x00 &&
258 ip[$((51+encl))] == 0x11 &&
259 ip[$((64+encl))] == 0x17 && ip[$((65+encl))] == 0xc2 &&
260 ip[$((76+proto))] == 0x08 && ip[$((77+proto))] == 0x00 &&
261 ip[$((87+inner))] == 0x6 &&
262 ip[$((100+inner))] == 0x1f && ip[$((101+inner))] == 0x40) ||
263 (ip6 &&
264 ip6[$((60+encl))] == 0x86 && ip6[$((61+encl))] == 0xdd &&
265 ip6[$((68+encl))] == 0x11 &&
266 ip6[$((104+encl))] == 0x17 && ip6[$((105+encl))] == 0xc2 &&
267 ip6[$((116+proto))] == 0x86 && ip6[$((117+proto))] == 0xdd &&
268 ip6[$((124+inner))] == 0x6 &&
269 ip6[$((160+inner))] == 0x1f && ip6[$((161+inner))] == 0x40)")
270
271 # ignore shorts packet, to avoid arp/mld induced noise
272 ip netns exec "$NS_SRC" "$ipt" -A OUTPUT -p udp --dport "$dport" \
273 -m length --length 600:65535 -m bpf --bytecode "$bpf_filter"
274 ip netns exec "$NS_DST" "$ipt" -A INPUT -p udp --dport "$dport" \
275 -m length --length 600:65535 -m bpf --bytecode "$bpf_filter"
276 ip netns exec "$NS_DST" ./udpgso_bench_rx -C 2000 -t -R 100 \
277 -n "$pkts" "${rx_args[@]}" &
278 local pid=$!
279 wait_local_port_listen "$NS_DST" 8000 tcp
280 ip netns exec "$NS_SRC" ./udpgso_bench_tx -"$FAMILY" -t -M 1 \
281 -s "$total_size" -D "$dst"
282 local ret=$?
283 check_err "$ret" "client failure exit code $ret"
284 wait "$pid"
285 ret=$?
286 check_err "$ret" "sever failure exit code $ret"
287
288 snd=$(ip netns exec "$NS_SRC" "$ipt"-save -c |
289 grep "dport $dport" | sed -e 's/\[//' -e 's/:.*//')
290
291 [ "$snd" = "$wire_pkts" ]
292 # shellcheck disable=SC2319 # known false positive
293 check_err $? "send $snd packets on the lowest link, expected $wire_pkts"
294
295 rcvpkts=$(ip netns exec "$NS_DST" "$ipt"-save -c | \
296 grep "dport $dport" | sed -e 's/\[//' -e 's/:.*//')
297
298 [ "$rcvpkts" = "$encappkts" ]
299 check_err $? "received $rcvpkts $ENCAP packets, expected $encappkts"
300 log_test "$msg"
301}
302
303run_tests() {
304 for FAMILY in 4 6; do
305 NET=$OL2_NET_V4
306 GSO_SIZE=1340 # 1392 - 20 - 32
307
308 if [ $FAMILY = 6 ]; then
309 NET=$OL2_NET_V6
310 GSO_SIZE=1280 # 1352 - 40 - 32
311 fi
312
313 echo "IPv$FAMILY"
314
315 unset USE_HINT
316 unset INHERIT
317
318 # "geneve" must be last encap in list, so that later
319 # test cases will run on it
320 for ENCAP in "vxlan" "geneve"; do
321 create_ns
322 run_test "No GSO - $ENCAP" $((GSO_SIZE * 4)) 4 4
323 cleanup_all_ns
324
325 create_ns_gso
326 run_test "GSO without GRO - $ENCAP" $((GSO_SIZE * 4)) \
327 4 1
328 cleanup_all_ns
329
330 # IPv4 only test
331 [ $FAMILY = "4" ] || continue
332 create_ns_gso
333 ip netns exec "$NS_SRC" \
334 sysctl -qw net.ipv4.ip_no_pmtu_disc=1
335 run_test "GSO disable due to no fixedid - $ENCAP" \
336 $((GSO_SIZE * 4)) 4 4
337 cleanup_all_ns
338 done
339
340 # GRO tests imply/require geneve encap, the only one providing
341 # GRO hints
342 create_ns_gso_gro
343 run_test "double tunnel GRO, no hints" $((GSO_SIZE * 4)) 4
344 cleanup_all_ns
345
346 # hint option is expected for all the following tests in the RX
347 # path
348 USE_HINT=true
349 create_ns_gso_gro \
350 '"gro-hint":1,"udp-zero-csum6-tx":1,"udp-zero-csum6-rx":1' \
351 '"udp-zero-csum6-tx":1,"udp-zero-csum6-rx":1'
352 run_test "double tunnel GRO" $((GSO_SIZE * 4)) 1
353 cleanup_all_ns
354
355 create_ns_gso_gro '"gro-hint":1,"udp-csum":1' '"udp-csum":1'
356 run_test "double tunnel GRO - csum complete" $((GSO_SIZE * 4))\
357 1
358 cleanup_all_ns
359
360 create_ns_gso_gro '"gro-hint":1' \
361 '"udp-csum":0,"udp-zero-csum6-tx":1,"udp-zero-csum6-rx":1'
362 run_test "double tunnel GRO - no nested csum" \
363 $((GSO_SIZE * 4)) 1
364 cleanup_all_ns
365
366 create_ns_gso_gro \
367 '"gro-hint":1,"udp-zero-csum6-tx":1,"udp-zero-csum6-rx":1' \
368 '"udp-csum":1'
369 run_test "double tunnel GRO - nested csum, outer 0-csum, skip"\
370 $((GSO_SIZE * 4)) 4
371 cleanup_all_ns
372
373 INHERIT=true
374 create_ns_gso_gro '"gro-hint":1,"udp-csum":1' \
375 '"udp-csum":1,"inner-proto-inherit":1'
376 run_test "double tunnel GRO - nested inherit proto" \
377 $((GSO_SIZE * 4)) 1
378 cleanup_all_ns
379 unset INHERIT
380
381 create_ns_gso_gro '"gro-hint":1'
382 run_test "double tunnel GRO - short last pkt" \
383 $((GSO_SIZE * 4 + GSO_SIZE / 2)) 2
384 cleanup_all_ns
385 done
386}
387
388require_command nfbpf_compile
389require_command jq
390
391# tcp retransmisions will break the accounting
392xfail_on_slow run_tests
393exit "$EXIT_STATUS"