diff mbox series

[net-next,8/8] selftests: net: add UDP GRO forwarding self-tests

Message ID a9791dcc26e3f70858eee5d14506f8b36e747960.1616345643.git.pabeni@redhat.com (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series udp: GRO L4 improvements | expand

Checks

Context Check Description
netdev/cover_letter success Link
netdev/fixes_present success Link
netdev/patch_count success Link
netdev/tree_selection success Clearly marked for net-next
netdev/subject_prefix success Link
netdev/cc_maintainers warning 12 maintainers not CCed: linux-kselftest@vger.kernel.org yhs@fb.com hawk@kernel.org daniel@iogearbox.net andrii@kernel.org kpsingh@kernel.org bpf@vger.kernel.org kafai@fb.com ast@kernel.org john.fastabend@gmail.com songliubraving@fb.com shuah@kernel.org
netdev/source_inline success Was 0 now: 0
netdev/verify_signedoff success Link
netdev/module_param success Was 0 now: 0
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/verify_fixes success Link
netdev/checkpatch warning WARNING: added, moved or deleted file(s), does MAINTAINERS need updating? WARNING: line length of 81 exceeds 80 columns WARNING: line length of 83 exceeds 80 columns WARNING: line length of 84 exceeds 80 columns WARNING: line length of 85 exceeds 80 columns WARNING: line length of 86 exceeds 80 columns WARNING: line length of 87 exceeds 80 columns WARNING: line length of 88 exceeds 80 columns WARNING: line length of 89 exceeds 80 columns WARNING: line length of 93 exceeds 80 columns WARNING: line length of 99 exceeds 80 columns
netdev/build_allmodconfig_warn success Errors and warnings before: 0 this patch: 0
netdev/header_inline success Link

Commit Message

Paolo Abeni March 21, 2021, 5:01 p.m. UTC
create a bunch of virtual topology and verify that
GRO_FRAG_LIST and GRO_FWD aggregate the ingress
packets as expected, and the aggregate packets
are segmented correctly when landing on a socket

Also test L4 aggregation on top of UDP tunnel (vxlan)

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/Makefile      |   1 +
 tools/testing/selftests/net/udpgro_fwd.sh | 251 ++++++++++++++++++++++
 2 files changed, 252 insertions(+)
 create mode 100755 tools/testing/selftests/net/udpgro_fwd.sh

Comments

Willem de Bruijn March 22, 2021, 1:44 p.m. UTC | #1
On Sun, Mar 21, 2021 at 1:02 PM Paolo Abeni <pabeni@redhat.com> wrote:
>
> create a bunch of virtual topology and verify that
> GRO_FRAG_LIST and GRO_FWD aggregate the ingress

what are these constants? Aliases for SKB_GSO_FRAGLIST and ?

> packets as expected, and the aggregate packets
> are segmented correctly when landing on a socket
>
> Also test L4 aggregation on top of UDP tunnel (vxlan)
>
> Signed-off-by: Paolo Abeni <pabeni@redhat.com>

Nice comprehensive test, thanks!

> ---
>  tools/testing/selftests/net/Makefile      |   1 +
>  tools/testing/selftests/net/udpgro_fwd.sh | 251 ++++++++++++++++++++++
>  2 files changed, 252 insertions(+)
>  create mode 100755 tools/testing/selftests/net/udpgro_fwd.sh
>
> diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
> index 25f198bec0b25..2d71b283dde36 100644
> --- a/tools/testing/selftests/net/Makefile
> +++ b/tools/testing/selftests/net/Makefile
> @@ -23,6 +23,7 @@ TEST_PROGS += drop_monitor_tests.sh
>  TEST_PROGS += vrf_route_leaking.sh
>  TEST_PROGS += bareudp.sh
>  TEST_PROGS += unicast_extensions.sh
> +TEST_PROGS += udpgro_fwd.sh
>  TEST_PROGS_EXTENDED := in_netns.sh
>  TEST_GEN_FILES =  socket nettest
>  TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
> diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
> new file mode 100755
> index 0000000000000..ac7ac56a27524
> --- /dev/null
> +++ b/tools/testing/selftests/net/udpgro_fwd.sh
> @@ -0,0 +1,251 @@
> +#!/bin/sh
> +# SPDX-License-Identifier: GPL-2.0
> +
> +readonly BASE="ns-$(mktemp -u XXXXXX)"
> +readonly SRC=2
> +readonly DST=1
> +readonly DST_NAT=100
> +readonly NS_SRC=$BASE$SRC
> +readonly NS_DST=$BASE$DST
> +
> +# "baremetal" network used for raw UDP traffic
> +readonly BM_NET_V4=192.168.1.
> +readonly BM_NET_V6=2001:db8::
> +
> +# "overlay" network used for UDP over UDP tunnel traffic
> +readonly OL_NET_V4=172.16.1.
> +readonly OL_NET_V6=2002:db8::

is it okay to use a prod64 prefix for this? should this be another
subnet of 2001:db8:: instead? of fd..
Paolo Abeni March 22, 2021, 5:18 p.m. UTC | #2
On Mon, 2021-03-22 at 09:44 -0400, Willem de Bruijn wrote:
> On Sun, Mar 21, 2021 at 1:02 PM Paolo Abeni <pabeni@redhat.com> wrote:
> > create a bunch of virtual topology and verify that
> > GRO_FRAG_LIST and GRO_FWD aggregate the ingress
> 
> what are these constants? Aliases for SKB_GSO_FRAGLIST and ?

Well, I was inaccurate in many ways :(

I was speaking about device features, so it's really:

NETIF_F_GSO_FRAGLIST and NETIF_F_GRO_UDP_FWD

I really would love a commit message "compiler" to clarify this sort of
thing before submission;)

Thanks,

Paolo
Paolo Abeni March 23, 2021, 5:12 p.m. UTC | #3
Hello,

On Mon, 2021-03-22 at 09:44 -0400, Willem de Bruijn wrote:
> > diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
> > new file mode 100755
> > index 0000000000000..ac7ac56a27524
> > --- /dev/null
> > +++ b/tools/testing/selftests/net/udpgro_fwd.sh
> > @@ -0,0 +1,251 @@
> > +#!/bin/sh
> > +# SPDX-License-Identifier: GPL-2.0
> > +
> > +readonly BASE="ns-$(mktemp -u XXXXXX)"
> > +readonly SRC=2
> > +readonly DST=1
> > +readonly DST_NAT=100
> > +readonly NS_SRC=$BASE$SRC
> > +readonly NS_DST=$BASE$DST
> > +
> > +# "baremetal" network used for raw UDP traffic
> > +readonly BM_NET_V4=192.168.1.
> > +readonly BM_NET_V6=2001:db8::
> > +
> > +# "overlay" network used for UDP over UDP tunnel traffic
> > +readonly OL_NET_V4=172.16.1.
> > +readonly OL_NET_V6=2002:db8::
> 
> is it okay to use a prod64 prefix for this? should this be another
> subnet of 2001:db8:: instead? of fd..

It looks like this comment slipped out of my sight... yep, I'll use
2001:db8:1:: for the overlay network in the next iteration.

Thanks!

Paolo
diff mbox series

Patch

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 25f198bec0b25..2d71b283dde36 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -23,6 +23,7 @@  TEST_PROGS += drop_monitor_tests.sh
 TEST_PROGS += vrf_route_leaking.sh
 TEST_PROGS += bareudp.sh
 TEST_PROGS += unicast_extensions.sh
+TEST_PROGS += udpgro_fwd.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket nettest
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
new file mode 100755
index 0000000000000..ac7ac56a27524
--- /dev/null
+++ b/tools/testing/selftests/net/udpgro_fwd.sh
@@ -0,0 +1,251 @@ 
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+readonly BASE="ns-$(mktemp -u XXXXXX)"
+readonly SRC=2
+readonly DST=1
+readonly DST_NAT=100
+readonly NS_SRC=$BASE$SRC
+readonly NS_DST=$BASE$DST
+
+# "baremetal" network used for raw UDP traffic
+readonly BM_NET_V4=192.168.1.
+readonly BM_NET_V6=2001:db8::
+
+# "overlay" network used for UDP over UDP tunnel traffic
+readonly OL_NET_V4=172.16.1.
+readonly OL_NET_V6=2002:db8::
+readonly NPROCS=`nproc`
+
+cleanup() {
+	local ns
+	local -r jobs="$(jobs -p)"
+	[ -n "${jobs}" ] && kill -1 ${jobs} 2>/dev/null
+
+	for ns in $NS_SRC $NS_DST; do
+		ip netns del $ns 2>/dev/null
+	done
+}
+
+trap cleanup EXIT
+
+create_ns() {
+	local net
+	local ns
+
+	for ns in $NS_SRC $NS_DST; do
+		ip netns add $ns
+		ip -n $ns link set dev lo up
+	done
+
+	ip link add name veth$SRC type veth peer name veth$DST
+
+	for ns in $SRC $DST; do
+		ip link set dev veth$ns netns $BASE$ns
+		ip -n $BASE$ns link set dev veth$ns up
+		ip -n $BASE$ns addr add dev veth$ns $BM_NET_V4$ns/24
+		ip -n $BASE$ns addr add dev veth$ns $BM_NET_V6$ns/64 nodad
+	done
+	ip -n $NS_DST link set veth$DST xdp object ../bpf/xdp_dummy.o section xdp_dummy 2>/dev/null
+}
+
+create_vxlan_endpoint() {
+	local -r netns=$1
+	local -r bm_dev=$2
+	local -r bm_rem_addr=$3
+	local -r vxlan_dev=$4
+	local -r vxlan_id=$5
+	local -r vxlan_port=4789
+
+	ip -n $netns link set dev $bm_dev up
+	ip -n $netns link add dev $vxlan_dev type vxlan id $vxlan_id \
+				dstport $vxlan_port remote $bm_rem_addr
+	ip -n $netns link set dev $vxlan_dev up
+}
+
+create_vxlan_pair() {
+	local ns
+
+	create_ns
+
+	for ns in $SRC $DST; do
+		# note that 3 - $SRC == $DST and 3 - $DST == $SRC
+		create_vxlan_endpoint $BASE$ns veth$ns $BM_NET_V4$((3 - $ns)) vxlan$ns 4
+		ip -n $BASE$ns addr add dev vxlan$ns $OL_NET_V4$ns/24
+	done
+	for ns in $SRC $DST; do
+		create_vxlan_endpoint $BASE$ns veth$ns $BM_NET_V6$((3 - $ns)) vxlan6$ns 6
+		ip -n $BASE$ns addr add dev vxlan6$ns $OL_NET_V6$ns/24 nodad
+	done
+}
+
+is_ipv6() {
+	if [[ $1 =~ .*:.* ]]; then
+		return 0
+	fi
+	return 1
+}
+
+run_test() {
+	local -r msg=$1
+	local -r dst=$2
+	local -r pkts=$3
+	local -r vxpkts=$4
+	local bind=$5
+	local rx_args=""
+	local rx_family="-4"
+	local family=-4
+	local filter=IpInReceives
+	local ipt=iptables
+
+	printf "%-40s" "$msg"
+
+	if is_ipv6 $dst; then
+		# rx program does not support '-6' and implies ipv6 usage by default
+		rx_family=""
+		family=-6
+		filter=Ip6InReceives
+		ipt=ip6tables
+	fi
+
+	rx_args="$rx_family"
+	[ -n "$bind" ] && rx_args="$rx_args -b $bind"
+
+	# send a single GSO packet, segmented in 10 UDP frames.
+	# Always expect 10 UDP frames on RX side as rx socket does
+	# not enable GRO
+	ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 4789
+	ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 8000
+	ip netns exec $NS_DST ./udpgso_bench_rx -C 1000 -R 10 -n 10 -l 1300 $rx_args &
+	local spid=$!
+	sleep 0.1
+	ip netns exec $NS_SRC ./udpgso_bench_tx $family -M 1 -s 13000 -S 1300 -D $dst
+	local retc=$?
+	wait $spid
+	local rets=$?
+	if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then
+		echo " fail client exit code $retc, server $rets"
+		ret=1
+		return
+	fi
+
+	local rcv=`ip netns exec $NS_DST $ipt"-save" -c | grep 'dport 8000' | \
+							  sed -e 's/\[//' -e 's/:.*//'`
+	if [ $rcv != $pkts ]; then
+		echo " fail - received $rvs packets, expected $pkts"
+		ret=1
+		return
+	fi
+
+	local vxrcv=`ip netns exec $NS_DST $ipt"-save" -c | grep 'dport 4789' | \
+							    sed -e 's/\[//' -e 's/:.*//'`
+
+	# upper net can generate a little noise, allow some tolerance
+	if [ $vxrcv -lt $vxpkts -o $vxrcv -gt $((vxpkts + 3)) ]; then
+		echo " fail - received $vxrcv vxlan packets, expected $vxpkts"
+		ret=1
+		return
+	fi
+	echo " ok"
+}
+
+run_bench() {
+	local -r msg=$1
+	local -r dst=$2
+	local family=-4
+
+	printf "%-40s" "$msg"
+	if [ $NPROCS -lt 2 ]; then
+		echo " skip - needed 2 CPUs found $NPROCS"
+		return
+	fi
+
+	is_ipv6 $dst && family=-6
+
+	# bind the sender and the receiver to different CPUs to try
+	# get reproducible results
+	ip netns exec $NS_DST bash -c "echo 2 > /sys/class/net/veth$DST/queues/rx-0/rps_cpus"
+	ip netns exec $NS_DST taskset 0x2 ./udpgso_bench_rx -C 1000 -R 10  &
+	local spid=$!
+	sleep 0.1
+	ip netns exec $NS_SRC taskset 0x1 ./udpgso_bench_tx $family -l 3 -S 1300 -D $dst
+	local retc=$?
+	wait $spid
+	local rets=$?
+	if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then
+		echo " fail client exit code $retc, server $rets"
+		ret=1
+		return
+	fi
+}
+
+for family in 4 6; do
+	BM_NET=$BM_NET_V4
+	OL_NET=$OL_NET_V4
+	IPT=iptables
+	SUFFIX=24
+	VXDEV=vxlan
+
+	if [ $family = 6 ]; then
+		BM_NET=$BM_NET_V6
+		OL_NET=$OL_NET_V6
+		SUFFIX="64 nodad"
+		VXDEV=vxlan6
+		IPT=ip6tables
+	fi
+
+	echo "IPv$family"
+
+	create_ns
+	run_test "No GRO" $BM_NET$DST 10 0
+	cleanup
+
+	create_ns
+	ip netns exec $NS_DST ethtool -K veth$DST rx-gro-list on
+	run_test "GRO frag list" $BM_NET$DST 1 0
+	cleanup
+
+	# UDP GRO fwd skips aggregation when find an udp socket with the GRO option
+	# if there is an UDP tunnel in the running system, such lookup happen
+	# take place.
+	# use NAT to circumvent GRO FWD check
+	create_ns
+	ip -n $NS_DST addr add dev veth$DST $BM_NET$DST_NAT/$SUFFIX
+	ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on
+	ip netns exec $NS_DST $IPT -t nat -I PREROUTING -d $BM_NET$DST_NAT \
+					-j DNAT --to-destination $BM_NET$DST
+	run_test "GRO fwd" $BM_NET$DST_NAT 1 0 $BM_NET$DST
+	cleanup
+
+	create_ns
+	run_bench "UDP fwd perf" $BM_NET$DST
+	ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on
+	run_bench "UDP GRO fwd perf" $BM_NET$DST
+	cleanup
+
+	create_vxlan_pair
+	ip netns exec $NS_DST ethtool -K veth$DST rx-gro-list on
+	run_test "GRO frag list over UDP tunnel" $OL_NET$DST 1 1
+	cleanup
+
+	# use NAT to circumvent GRO FWD check
+	create_vxlan_pair
+	ip -n $NS_DST addr add dev $VXDEV$DST $OL_NET$DST_NAT/$SUFFIX
+	ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on
+	ip netns exec $NS_DST $IPT -t nat -I PREROUTING -d $OL_NET$DST_NAT \
+					-j DNAT --to-destination $OL_NET$DST
+
+	# load arp cache before running the test to reduce the amount of
+	# stray traffic on top of the UDP tunnel
+	ip netns exec $NS_SRC ping -q -c 1 $OL_NET$DST_NAT >/dev/null
+	run_test "GRO fwd over UDP tunnel" $OL_NET$DST_NAT 1 1 $OL_NET$DST
+	cleanup
+
+	create_vxlan_pair
+	run_bench "UDP tunnel fwd perf" $OL_NET$DST
+	ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on
+	run_bench "UDP tunnel GRO fwd perf" $OL_NET$DST
+	cleanup
+done
+
+exit $ret