selftests: add functionals test for UDP GRO

Extends the existing udp programs to allow checking for proper
GRO aggregation/GSO size, and run the tests via a shell script, using
a veth pair with XDP program attached to trigger the GRO code path.

rfc v3 -> v1:
 - use ip route to attach the xdp helper to the veth

rfc v2 -> rfc v3:
 - add missing test program options documentation
 - fix sporatic test failures (receiver faster than sender)

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 282 insertions, 23 deletions

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index b1bba2f60467..eec359895feb 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -7,7 +7,7 @@ CFLAGS += -I../../../../usr/include/
 TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
 TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh
 TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
-TEST_PROGS += udpgro_bench.sh
+TEST_PROGS += udpgro_bench.sh udpgro.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
new file mode 100755
index 000000000000..e94ef8067173
--- /dev/null
+++ b/tools/testing/selftests/net/udpgro.sh
@@ -0,0 +1,148 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a series of udpgro functional tests.
+
+readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
+
+cleanup() {
+	local -r jobs="$(jobs -p)"
+	local -r ns="$(ip netns list|grep $PEER_NS)"
+
+	[ -n "${jobs}" ] && kill -1 ${jobs} 2>/dev/null
+	[ -n "$ns" ] && ip netns del $ns 2>/dev/null
+}
+trap cleanup EXIT
+
+cfg_veth() {
+	ip netns add "${PEER_NS}"
+	ip -netns "${PEER_NS}" link set lo up
+	ip link add type veth
+	ip link set dev veth0 up
+	ip addr add dev veth0 192.168.1.2/24
+	ip addr add dev veth0 2001:db8::2/64 nodad
+
+	ip link set dev veth1 netns "${PEER_NS}"
+	ip -netns "${PEER_NS}" addr add dev veth1 192.168.1.1/24
+	ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad
+	ip -netns "${PEER_NS}" link set dev veth1 up
+	ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp_dummy
+}
+
+run_one() {
+	# use 'rx' as separator between sender args and receiver args
+	local -r all="$@"
+	local -r tx_args=${all%rx*}
+	local -r rx_args=${all#*rx}
+
+	cfg_veth
+
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} && \
+		echo "ok" || \
+		echo "failed" &
+
+	# Hack: let bg programs complete the startup
+	sleep 0.1
+	./udpgso_bench_tx ${tx_args}
+	wait $(jobs -p)
+}
+
+run_test() {
+	local -r args=$@
+
+	printf " %-40s" "$1"
+	./in_netns.sh $0 __subprocess $2 rx -G -r $3
+}
+
+run_one_nat() {
+	# use 'rx' as separator between sender args and receiver args
+	local addr1 addr2 pid family="" ipt_cmd=ip6tables
+	local -r all="$@"
+	local -r tx_args=${all%rx*}
+	local -r rx_args=${all#*rx}
+
+	if [[ ${tx_args} = *-4* ]]; then
+		ipt_cmd=iptables
+		family=-4
+		addr1=192.168.1.1
+		addr2=192.168.1.3/24
+	else
+		addr1=2001:db8::1
+		addr2="2001:db8::3/64 nodad"
+	fi
+
+	cfg_veth
+	ip -netns "${PEER_NS}" addr add dev veth1 ${addr2}
+
+	# fool the GRO engine changing the destination address ...
+	ip netns exec "${PEER_NS}" $ipt_cmd -t nat -I PREROUTING -d ${addr1} -j DNAT --to-destination ${addr2%/*}
+
+	# ... so that GRO will match the UDP_GRO enabled socket, but packets
+	# will land on the 'plain' one
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -G ${family} -b ${addr1} -n 0 &
+	pid=$!
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${family} -b ${addr2%/*} ${rx_args} && \
+		echo "ok" || \
+		echo "failed"&
+
+	sleep 0.1
+	./udpgso_bench_tx ${tx_args}
+	kill -INT $pid
+	wait $(jobs -p)
+}
+
+run_nat_test() {
+	local -r args=$@
+
+	printf " %-40s" "$1"
+	./in_netns.sh $0 __subprocess_nat $2 rx -r $3
+}
+
+run_all() {
+	local -r core_args="-l 4"
+	local -r ipv4_args="${core_args} -4 -D 192.168.1.1"
+	local -r ipv6_args="${core_args} -6 -D 2001:db8::1"
+
+	echo "ipv4"
+	run_test "no GRO" "${ipv4_args} -M 10 -s 1400" "-4 -n 10 -l 1400"
+
+	# explicitly check we are not receiving UDP_SEGMENT cmsg (-S -1)
+	# when GRO does not take place
+	run_test "no GRO chk cmsg" "${ipv4_args} -M 10 -s 1400" "-4 -n 10 -l 1400 -S -1"
+
+	# the GSO packets are aggregated because:
+	# * veth schedule napi after each xmit
+	# * segmentation happens in BH context, veth napi poll is delayed after
+	#   the transmission of the last segment
+	run_test "GRO" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720"
+	run_test "GRO chk cmsg" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720 -S 1472"
+	run_test "GRO with custom segment size" "${ipv4_args} -M 1 -s 14720 -S 500 " "-4 -n 1 -l 14720"
+	run_test "GRO with custom segment size cmsg" "${ipv4_args} -M 1 -s 14720 -S 500 " "-4 -n 1 -l 14720 -S 500"
+
+	run_nat_test "bad GRO lookup" "${ipv4_args} -M 1 -s 14720 -S 0" "-n 10 -l 1472"
+
+	echo "ipv6"
+	run_test "no GRO" "${ipv6_args} -M 10 -s 1400" "-n 10 -l 1400"
+	run_test "no GRO chk cmsg" "${ipv6_args} -M 10 -s 1400" "-n 10 -l 1400 -S -1"
+	run_test "GRO" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 1 -l 14520"
+	run_test "GRO chk cmsg" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 1 -l 14520 -S 1452"
+	run_test "GRO with custom segment size" "${ipv6_args} -M 1 -s 14520 -S 500" "-n 1 -l 14520"
+	run_test "GRO with custom segment size cmsg" "${ipv6_args} -M 1 -s 14520 -S 500" "-n 1 -l 14520 -S 500"
+
+	run_nat_test "bad GRO lookup" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 10 -l 1452"
+}
+
+if [ ! -f ../bpf/xdp_dummy.o ]; then
+	echo "Missing xdp_dummy helper. Build bpf selftest first"
+	exit -1
+fi
+
+if [[ $# -eq 0 ]]; then
+	run_all
+elif [[ $1 == "__subprocess" ]]; then
+	shift
+	run_one $@
+elif [[ $1 == "__subprocess_nat" ]]; then
+	shift
+	run_one_nat $@
+fi
diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh
index 9ef4b1ee0f76..820bc50f6b68 100755
--- a/tools/testing/selftests/net/udpgro_bench.sh
+++ b/tools/testing/selftests/net/udpgro_bench.sh
@@ -18,7 +18,9 @@ run_one() {
 	# use 'rx' as separator between sender args and receiver args
 	local -r all="$@"
 	local -r tx_args=${all%rx*}
-	local -r rx_args=${all#*rx}
+	local rx_args=${all#*rx}
+
+	[[ "${tx_args}" == *"-4"* ]] && rx_args="${rx_args} -4"
 
 	ip netns add "${PEER_NS}"
 	ip -netns "${PEER_NS}" link set lo up
@@ -51,10 +53,10 @@ run_udp() {
 	local -r args=$@
 
 	echo "udp gso - over veth touching data"
-	run_in_netns ${args} -S rx
+	run_in_netns ${args} -S 0 rx
 
 	echo "udp gso and gro - over veth touching data"
-	run_in_netns ${args} -S rx -G
+	run_in_netns ${args} -S 0 rx -G
 }
 
 run_tcp() {
diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh
index 99e537ab5ad9..0f0628613f81 100755
--- a/tools/testing/selftests/net/udpgso_bench.sh
+++ b/tools/testing/selftests/net/udpgso_bench.sh
@@ -34,7 +34,7 @@ run_udp() {
 	run_in_netns ${args}
 
 	echo "udp gso"
-	run_in_netns ${args} -S
+	run_in_netns ${args} -S 0
 }
 
 run_tcp() {
diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c
index 8f48d7fb32cf..0c960f673324 100644
--- a/tools/testing/selftests/net/udpgso_bench_rx.c
+++ b/tools/testing/selftests/net/udpgso_bench_rx.c
@@ -40,6 +40,12 @@ static bool cfg_tcp;
 static bool cfg_verify;
 static bool cfg_read_all;
 static bool cfg_gro_segment;
+static int  cfg_family		= PF_INET6;
+static int  cfg_alen 		= sizeof(struct sockaddr_in6);
+static int  cfg_expected_pkt_nr;
+static int  cfg_expected_pkt_len;
+static int  cfg_expected_gso_size;
+static struct sockaddr_storage cfg_bind_addr;
 
 static bool interrupted;
 static unsigned long packets, bytes;
@@ -50,6 +56,29 @@ static void sigint_handler(int signum)
 		interrupted = true;
 }
 
+static void setup_sockaddr(int domain, const char *str_addr, void *sockaddr)
+{
+	struct sockaddr_in6 *addr6 = (void *) sockaddr;
+	struct sockaddr_in *addr4 = (void *) sockaddr;
+
+	switch (domain) {
+	case PF_INET:
+		addr4->sin_family = AF_INET;
+		addr4->sin_port = htons(cfg_port);
+		if (inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1)
+			error(1, 0, "ipv4 parse error: %s", str_addr);
+		break;
+	case PF_INET6:
+		addr6->sin6_family = AF_INET6;
+		addr6->sin6_port = htons(cfg_port);
+		if (inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1)
+			error(1, 0, "ipv6 parse error: %s", str_addr);
+		break;
+	default:
+		error(1, 0, "illegal domain");
+	}
+}
+
 static unsigned long gettimeofday_ms(void)
 {
 	struct timeval tv;
@@ -83,10 +112,9 @@ static void do_poll(int fd)
 
 static int do_socket(bool do_tcp)
 {
-	struct sockaddr_in6 addr = {0};
 	int fd, val;
 
-	fd = socket(PF_INET6, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0);
+	fd = socket(cfg_family, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0);
 	if (fd == -1)
 		error(1, errno, "socket");
 
@@ -97,10 +125,7 @@ static int do_socket(bool do_tcp)
 	if (setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &val, sizeof(val)))
 		error(1, errno, "setsockopt reuseport");
 
-	addr.sin6_family =	PF_INET6;
-	addr.sin6_port =	htons(cfg_port);
-	addr.sin6_addr =	in6addr_any;
-	if (bind(fd, (void *) &addr, sizeof(addr)))
+	if (bind(fd, (void *)&cfg_bind_addr, cfg_alen))
 		error(1, errno, "bind");
 
 	if (do_tcp) {
@@ -174,52 +199,117 @@ static void do_verify_udp(const char *data, int len)
 	}
 }
 
+static int recv_msg(int fd, char *buf, int len, int *gso_size)
+{
+	char control[CMSG_SPACE(sizeof(uint16_t))] = {0};
+	struct msghdr msg = {0};
+	struct iovec iov = {0};
+	struct cmsghdr *cmsg;
+	uint16_t *gsosizeptr;
+	int ret;
+
+	iov.iov_base = buf;
+	iov.iov_len = len;
+
+	msg.msg_iov = &iov;
+	msg.msg_iovlen = 1;
+
+	msg.msg_control = control;
+	msg.msg_controllen = sizeof(control);
+
+	*gso_size = -1;
+	ret = recvmsg(fd, &msg, MSG_TRUNC | MSG_DONTWAIT);
+	if (ret != -1) {
+		for (cmsg = CMSG_FIRSTHDR(&msg); cmsg != NULL;
+		     cmsg = CMSG_NXTHDR(&msg, cmsg)) {
+			if (cmsg->cmsg_level == SOL_UDP
+			    && cmsg->cmsg_type == UDP_GRO) {
+				gsosizeptr = (uint16_t *) CMSG_DATA(cmsg);
+				*gso_size = *gsosizeptr;
+				break;
+			}
+		}
+	}
+	return ret;
+}
+
 /* Flush all outstanding datagrams. Verify first few bytes of each. */
 static void do_flush_udp(int fd)
 {
 	static char rbuf[ETH_MAX_MTU];
-	int ret, len, budget = 256;
+	int ret, len, gso_size, budget = 256;
 
 	len = cfg_read_all ? sizeof(rbuf) : 0;
 	while (budget--) {
 		/* MSG_TRUNC will make return value full datagram length */
-		ret = recv(fd, rbuf, len, MSG_TRUNC | MSG_DONTWAIT);
+		if (!cfg_expected_gso_size)
+			ret = recv(fd, rbuf, len, MSG_TRUNC | MSG_DONTWAIT);
+		else
+			ret = recv_msg(fd, rbuf, len, &gso_size);
 		if (ret == -1 && errno == EAGAIN)
-			return;
+			break;
 		if (ret == -1)
 			error(1, errno, "recv");
+		if (cfg_expected_pkt_len && ret != cfg_expected_pkt_len)
+			error(1, 0, "recv: bad packet len, got %d,"
+			      " expected %d\n", ret, cfg_expected_pkt_len);
 		if (len && cfg_verify) {
 			if (ret == 0)
 				error(1, errno, "recv: 0 byte datagram\n");
 
 			do_verify_udp(rbuf, ret);
 		}
+		if (cfg_expected_gso_size && cfg_expected_gso_size != gso_size)
+			error(1, 0, "recv: bad gso size, got %d, expected %d "
+			      "(-1 == no gso cmsg))\n", gso_size,
+			      cfg_expected_gso_size);
 
 		packets++;
 		bytes += ret;
+		if (cfg_expected_pkt_nr && packets >= cfg_expected_pkt_nr)
+			break;
 	}
 }
 
 static void usage(const char *filepath)
 {
-	error(1, 0, "Usage: %s [-Grtv] [-p port]", filepath);
+	error(1, 0, "Usage: %s [-Grtv] [-b addr] [-p port] [-l pktlen] [-n packetnr] [-S gsosize]", filepath);
 }
 
 static void parse_opts(int argc, char **argv)
 {
 	int c;
 
-	while ((c = getopt(argc, argv, "Gp:rtv")) != -1) {
+	/* bind to any by default */
+	setup_sockaddr(PF_INET6, "::", &cfg_bind_addr);
+	while ((c = getopt(argc, argv, "4b:Gl:n:p:rS:tv")) != -1) {
 		switch (c) {
+		case '4':
+			cfg_family = PF_INET;
+			cfg_alen = sizeof(struct sockaddr_in);
+			setup_sockaddr(PF_INET, "0.0.0.0", &cfg_bind_addr);
+			break;
+		case 'b':
+			setup_sockaddr(cfg_family, optarg, &cfg_bind_addr);
+			break;
 		case 'G':
 			cfg_gro_segment = true;
 			break;
+		case 'l':
+			cfg_expected_pkt_len = strtoul(optarg, NULL, 0);
+			break;
+		case 'n':
+			cfg_expected_pkt_nr = strtoul(optarg, NULL, 0);
+			break;
 		case 'p':
 			cfg_port = strtoul(optarg, NULL, 0);
 			break;
 		case 'r':
 			cfg_read_all = true;
 			break;
+		case 'S':
+			cfg_expected_gso_size = strtol(optarg, NULL, 0);
+			break;
 		case 't':
 			cfg_tcp = true;
 			break;
@@ -240,7 +330,7 @@ static void parse_opts(int argc, char **argv)
 static void do_recv(void)
 {
 	unsigned long tnow, treport;
-	int fd;
+	int fd, loop = 0;
 
 	fd = do_socket(cfg_tcp);
 
@@ -252,6 +342,11 @@ static void do_recv(void)
 
 	treport = gettimeofday_ms() + 1000;
 	do {
+		/* force termination after the second poll(); this cope both
+		 * with sender slower than receiver and missing packet errors
+		 */
+		if (cfg_expected_pkt_nr && loop++)
+			interrupted = true;
 		do_poll(fd);
 
 		if (cfg_tcp)
@@ -272,6 +367,10 @@ static void do_recv(void)
 
 	} while (!interrupted);
 
+	if (cfg_expected_pkt_nr && (packets != cfg_expected_pkt_nr))
+		error(1, 0, "wrong packet number! got %ld, expected %d\n",
+		      packets, cfg_expected_pkt_nr);
+
 	if (close(fd))
 		error(1, errno, "close");
 }
diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c
index e821564053cf..4074538b5df5 100644
--- a/tools/testing/selftests/net/udpgso_bench_tx.c
+++ b/tools/testing/selftests/net/udpgso_bench_tx.c
@@ -52,6 +52,8 @@ static bool	cfg_segment;
 static bool	cfg_sendmmsg;
 static bool	cfg_tcp;
 static bool	cfg_zerocopy;
+static int	cfg_msg_nr;
+static uint16_t	cfg_gso_size;
 
 static socklen_t cfg_alen;
 static struct sockaddr_storage cfg_dst_addr;
@@ -205,14 +207,14 @@ static void send_udp_segment_cmsg(struct cmsghdr *cm)
 
 	cm->cmsg_level = SOL_UDP;
 	cm->cmsg_type = UDP_SEGMENT;
-	cm->cmsg_len = CMSG_LEN(sizeof(cfg_mss));
+	cm->cmsg_len = CMSG_LEN(sizeof(cfg_gso_size));
 	valp = (void *)CMSG_DATA(cm);
-	*valp = cfg_mss;
+	*valp = cfg_gso_size;
 }
 
 static int send_udp_segment(int fd, char *data)
 {
-	char control[CMSG_SPACE(sizeof(cfg_mss))] = {0};
+	char control[CMSG_SPACE(sizeof(cfg_gso_size))] = {0};
 	struct msghdr msg = {0};
 	struct iovec iov = {0};
 	int ret;
@@ -241,7 +243,7 @@ static int send_udp_segment(int fd, char *data)
 
 static void usage(const char *filepath)
 {
-	error(1, 0, "Usage: %s [-46cmStuz] [-C cpu] [-D dst ip] [-l secs] [-p port] [-s sendsize]",
+	error(1, 0, "Usage: %s [-46cmtuz] [-C cpu] [-D dst ip] [-l secs] [-m messagenr] [-p port] [-s sendsize] [-S gsosize]",
 		    filepath);
 }
 
@@ -250,7 +252,7 @@ static void parse_opts(int argc, char **argv)
 	int max_len, hdrlen;
 	int c;
 
-	while ((c = getopt(argc, argv, "46cC:D:l:mp:s:Stuz")) != -1) {
+	while ((c = getopt(argc, argv, "46cC:D:l:mM:p:s:S:tuz")) != -1) {
 		switch (c) {
 		case '4':
 			if (cfg_family != PF_UNSPEC)
@@ -279,6 +281,9 @@ static void parse_opts(int argc, char **argv)
 		case 'm':
 			cfg_sendmmsg = true;
 			break;
+		case 'M':
+			cfg_msg_nr = strtoul(optarg, NULL, 10);
+			break;
 		case 'p':
 			cfg_port = strtoul(optarg, NULL, 0);
 			break;
@@ -286,6 +291,7 @@ static void parse_opts(int argc, char **argv)
 			cfg_payload_len = strtoul(optarg, NULL, 0);
 			break;
 		case 'S':
+			cfg_gso_size = strtoul(optarg, NULL, 0);
 			cfg_segment = true;
 			break;
 		case 't':
@@ -317,6 +323,8 @@ static void parse_opts(int argc, char **argv)
 
 	cfg_mss = ETH_DATA_LEN - hdrlen;
 	max_len = ETH_MAX_MTU - hdrlen;
+	if (!cfg_gso_size)
+		cfg_gso_size = cfg_mss;
 
 	if (cfg_payload_len > max_len)
 		error(1, 0, "payload length %u exceeds max %u",
@@ -392,10 +400,12 @@ int main(int argc, char **argv)
 		else
 			num_sends += send_udp(fd, buf[i]);
 		num_msgs++;
-
 		if (cfg_zerocopy && ((num_msgs & 0xF) == 0))
 			flush_zerocopy(fd);
 
+		if (cfg_msg_nr && num_msgs >= cfg_msg_nr)
+			break;
+
 		tnow = gettimeofday_ms();
 		if (tnow > treport) {
 			fprintf(stderr,