Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

3 files changed, 113 insertions, 33 deletions

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index e2c94e47707c..912b2dc50be3 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -103,6 +103,15 @@
 #	and check that configured MTU is used on link creation and changes, and
 #	that MTU is properly calculated instead when MTU is not configured from
 #	userspace
+#
+# - cleanup_ipv4_exception
+#	Similar to pmtu_ipv4_vxlan4_exception, but explicitly generate PMTU
+#	exceptions on multiple CPUs and check that the veth device tear-down
+# 	happens in a timely manner
+#
+# - cleanup_ipv6_exception
+#	Same as above, but use IPv6 transport from A to B
+
 
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
@@ -135,7 +144,9 @@ tests="
 	pmtu_vti6_default_mtu		vti6: default MTU assignment
 	pmtu_vti4_link_add_mtu		vti4: MTU setting on link creation
 	pmtu_vti6_link_add_mtu		vti6: MTU setting on link creation
-	pmtu_vti6_link_change_mtu	vti6: MTU changes on link changes"
+	pmtu_vti6_link_change_mtu	vti6: MTU changes on link changes
+	cleanup_ipv4_exception		ipv4: cleanup of cached exceptions
+	cleanup_ipv6_exception		ipv6: cleanup of cached exceptions"
 
 NS_A="ns-$(mktemp -u XXXXXX)"
 NS_B="ns-$(mktemp -u XXXXXX)"
@@ -263,8 +274,6 @@ setup_fou_or_gue() {
 
 	${ns_a} ip link set ${encap}_a up
 	${ns_b} ip link set ${encap}_b up
-
-	sleep 1
 }
 
 setup_fou44() {
@@ -302,6 +311,10 @@ setup_gue66() {
 setup_namespaces() {
 	for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
 		ip netns add ${n} || return 1
+
+		# Disable DAD, so that we don't have to wait to use the
+		# configured IPv6 addresses
+		ip netns exec ${n} sysctl -q net/ipv6/conf/default/accept_dad=0
 	done
 }
 
@@ -337,8 +350,6 @@ setup_vti() {
 
 	${ns_a} ip link set vti${proto}_a up
 	${ns_b} ip link set vti${proto}_b up
-
-	sleep 1
 }
 
 setup_vti4() {
@@ -375,8 +386,6 @@ setup_vxlan_or_geneve() {
 
 	${ns_a} ip link set ${type}_a up
 	${ns_b} ip link set ${type}_b up
-
-	sleep 1
 }
 
 setup_geneve4() {
@@ -588,8 +597,8 @@ test_pmtu_ipvX() {
 	mtu "${ns_b}"  veth_B-R2 1500
 
 	# Create route exceptions
-	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1800 ${dst1} > /dev/null
-	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1800 ${dst2} > /dev/null
+	${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst1} > /dev/null
+	${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst2} > /dev/null
 
 	# Check that exceptions have been created with the correct PMTU
 	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})"
@@ -621,7 +630,7 @@ test_pmtu_ipvX() {
 	# Decrease remote MTU on path via R2, get new exception
 	mtu "${ns_r2}" veth_R2-B 400
 	mtu "${ns_b}"  veth_B-R2 400
-	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1400 ${dst2} > /dev/null
+	${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1400 ${dst2} > /dev/null
 	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
 	check_pmtu_value "lock 552" "${pmtu_2}" "exceeding MTU, with MTU < min_pmtu" || return 1
 
@@ -638,7 +647,7 @@ test_pmtu_ipvX() {
 	check_pmtu_value "1500" "${pmtu_2}" "increasing local MTU" || return 1
 
 	# Get new exception
-	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1400 ${dst2} > /dev/null
+	${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1400 ${dst2} > /dev/null
 	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
 	check_pmtu_value "lock 552" "${pmtu_2}" "exceeding MTU, with MTU < min_pmtu" || return 1
 }
@@ -687,7 +696,7 @@ test_pmtu_ipvX_over_vxlanY_or_geneveY_exception() {
 
 	mtu "${ns_a}" ${type}_a $((${ll_mtu} + 1000))
 	mtu "${ns_b}" ${type}_b $((${ll_mtu} + 1000))
-	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s $((${ll_mtu} + 500)) ${dst} > /dev/null
+	${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst} > /dev/null
 
 	# Check that exception was created
 	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})"
@@ -767,7 +776,7 @@ test_pmtu_ipvX_over_fouY_or_gueY() {
 
 	mtu "${ns_a}" ${encap}_a $((${ll_mtu} + 1000))
 	mtu "${ns_b}" ${encap}_b $((${ll_mtu} + 1000))
-	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s $((${ll_mtu} + 500)) ${dst} > /dev/null
+	${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst} > /dev/null
 
 	# Check that exception was created
 	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})"
@@ -825,13 +834,13 @@ test_pmtu_vti4_exception() {
 
 	# Send DF packet without exceeding link layer MTU, check that no
 	# exception is created
-	${ns_a} ping -q -M want -i 0.1 -w 2 -s ${ping_payload} ${tunnel4_b_addr} > /dev/null
+	${ns_a} ping -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel4_b_addr} > /dev/null
 	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
 	check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
 
 	# Now exceed link layer MTU by one byte, check that exception is created
 	# with the right PMTU value
-	${ns_a} ping -q -M want -i 0.1 -w 2 -s $((ping_payload + 1)) ${tunnel4_b_addr} > /dev/null
+	${ns_a} ping -q -M want -i 0.1 -w 1 -s $((ping_payload + 1)) ${tunnel4_b_addr} > /dev/null
 	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
 	check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))"
 }
@@ -847,7 +856,7 @@ test_pmtu_vti6_exception() {
 	mtu "${ns_b}" veth_b 4000
 	mtu "${ns_a}" vti6_a 5000
 	mtu "${ns_b}" vti6_b 5000
-	${ns_a} ${ping6} -q -i 0.1 -w 2 -s 60000 ${tunnel6_b_addr} > /dev/null
+	${ns_a} ${ping6} -q -i 0.1 -w 1 -s 60000 ${tunnel6_b_addr} > /dev/null
 
 	# Check that exception was created
 	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
@@ -1008,6 +1017,61 @@ test_pmtu_vti6_link_change_mtu() {
 	return ${fail}
 }
 
+check_command() {
+	cmd=${1}
+
+	if ! which ${cmd} > /dev/null 2>&1; then
+		err "  missing required command: '${cmd}'"
+		return 1
+	fi
+	return 0
+}
+
+test_cleanup_vxlanX_exception() {
+	outer="${1}"
+	encap="vxlan"
+	ll_mtu=4000
+
+	check_command taskset || return 2
+	cpu_list=$(grep -m 2 processor /proc/cpuinfo | cut -d ' ' -f 2)
+
+	setup namespaces routing ${encap}${outer} || return 2
+	trace "${ns_a}" ${encap}_a   "${ns_b}"  ${encap}_b \
+	      "${ns_a}" veth_A-R1    "${ns_r1}" veth_R1-A \
+	      "${ns_b}" veth_B-R1    "${ns_r1}" veth_R1-B
+
+	# Create route exception by exceeding link layer MTU
+	mtu "${ns_a}"  veth_A-R1 $((${ll_mtu} + 1000))
+	mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000))
+	mtu "${ns_b}"  veth_B-R1 ${ll_mtu}
+	mtu "${ns_r1}" veth_R1-B ${ll_mtu}
+
+	mtu "${ns_a}" ${encap}_a $((${ll_mtu} + 1000))
+	mtu "${ns_b}" ${encap}_b $((${ll_mtu} + 1000))
+
+	# Fill exception cache for multiple CPUs (2)
+	# we can always use inner IPv4 for that
+	for cpu in ${cpu_list}; do
+		taskset --cpu-list ${cpu} ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${tunnel4_b_addr} > /dev/null
+	done
+
+	${ns_a} ip link del dev veth_A-R1 &
+	iplink_pid=$!
+	sleep 1
+	if [ "$(cat /proc/${iplink_pid}/cmdline 2>/dev/null | tr -d '\0')" = "iplinkdeldevveth_A-R1" ]; then
+		err "  can't delete veth device in a timely manner, PMTU dst likely leaked"
+		return 1
+	fi
+}
+
+test_cleanup_ipv6_exception() {
+	test_cleanup_vxlanX_exception 6
+}
+
+test_cleanup_ipv4_exception() {
+	test_cleanup_vxlanX_exception 4
+}
+
 usage() {
 	echo
 	echo "$0 [OPTIONS] [TEST]..."
diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
index aeac53a99aeb..ac2a30be9b32 100755
--- a/tools/testing/selftests/net/udpgro.sh
+++ b/tools/testing/selftests/net/udpgro.sh
@@ -37,7 +37,7 @@ run_one() {
 
 	cfg_veth
 
-	ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} && \
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} && \
 		echo "ok" || \
 		echo "failed" &
 
@@ -81,7 +81,7 @@ run_one_nat() {
 	# 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%/*} ${rx_args} && \
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${family} -b ${addr2%/*} ${rx_args} && \
 		echo "ok" || \
 		echo "failed"&
 
@@ -99,8 +99,8 @@ run_one_2sock() {
 
 	cfg_veth
 
-	ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -p 12345 &
-	ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} && \
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} -p 12345 &
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 10 ${rx_args} && \
 		echo "ok" || \
 		echo "failed" &
 
diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c
index 0c960f673324..db3d4a8b5a4c 100644
--- a/tools/testing/selftests/net/udpgso_bench_rx.c
+++ b/tools/testing/selftests/net/udpgso_bench_rx.c
@@ -45,6 +45,8 @@ 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 int  cfg_connect_timeout_ms;
+static int  cfg_rcv_timeout_ms;
 static struct sockaddr_storage cfg_bind_addr;
 
 static bool interrupted;
@@ -87,7 +89,7 @@ static unsigned long gettimeofday_ms(void)
 	return (tv.tv_sec * 1000) + (tv.tv_usec / 1000);
 }
 
-static void do_poll(int fd)
+static void do_poll(int fd, int timeout_ms)
 {
 	struct pollfd pfd;
 	int ret;
@@ -102,8 +104,16 @@ static void do_poll(int fd)
 			break;
 		if (ret == -1)
 			error(1, errno, "poll");
-		if (ret == 0)
-			continue;
+		if (ret == 0) {
+			if (!timeout_ms)
+				continue;
+
+			timeout_ms -= 10;
+			if (timeout_ms <= 0) {
+				interrupted = true;
+				break;
+			}
+		}
 		if (pfd.revents != POLLIN)
 			error(1, errno, "poll: 0x%x expected 0x%x\n",
 					pfd.revents, POLLIN);
@@ -134,7 +144,7 @@ static int do_socket(bool do_tcp)
 		if (listen(accept_fd, 1))
 			error(1, errno, "listen");
 
-		do_poll(accept_fd);
+		do_poll(accept_fd, cfg_connect_timeout_ms);
 		if (interrupted)
 			exit(0);
 
@@ -273,7 +283,9 @@ static void do_flush_udp(int fd)
 
 static void usage(const char *filepath)
 {
-	error(1, 0, "Usage: %s [-Grtv] [-b addr] [-p port] [-l pktlen] [-n packetnr] [-S gsosize]", filepath);
+	error(1, 0, "Usage: %s [-C connect_timeout] [-Grtv] [-b addr] [-p port]"
+	      " [-l pktlen] [-n packetnr] [-R rcv_timeout] [-S gsosize]",
+	      filepath);
 }
 
 static void parse_opts(int argc, char **argv)
@@ -282,7 +294,7 @@ static void parse_opts(int argc, char **argv)
 
 	/* bind to any by default */
 	setup_sockaddr(PF_INET6, "::", &cfg_bind_addr);
-	while ((c = getopt(argc, argv, "4b:Gl:n:p:rS:tv")) != -1) {
+	while ((c = getopt(argc, argv, "4b:C:Gl:n:p:rR:S:tv")) != -1) {
 		switch (c) {
 		case '4':
 			cfg_family = PF_INET;
@@ -292,6 +304,9 @@ static void parse_opts(int argc, char **argv)
 		case 'b':
 			setup_sockaddr(cfg_family, optarg, &cfg_bind_addr);
 			break;
+		case 'C':
+			cfg_connect_timeout_ms = strtoul(optarg, NULL, 0);
+			break;
 		case 'G':
 			cfg_gro_segment = true;
 			break;
@@ -307,6 +322,9 @@ static void parse_opts(int argc, char **argv)
 		case 'r':
 			cfg_read_all = true;
 			break;
+		case 'R':
+			cfg_rcv_timeout_ms = strtoul(optarg, NULL, 0);
+			break;
 		case 'S':
 			cfg_expected_gso_size = strtol(optarg, NULL, 0);
 			break;
@@ -329,8 +347,9 @@ static void parse_opts(int argc, char **argv)
 
 static void do_recv(void)
 {
+	int timeout_ms = cfg_tcp ? cfg_rcv_timeout_ms : cfg_connect_timeout_ms;
 	unsigned long tnow, treport;
-	int fd, loop = 0;
+	int fd;
 
 	fd = do_socket(cfg_tcp);
 
@@ -342,12 +361,7 @@ 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);
+		do_poll(fd, timeout_ms);
 
 		if (cfg_tcp)
 			do_flush_tcp(fd);
@@ -365,6 +379,8 @@ static void do_recv(void)
 			treport = tnow + 1000;
 		}
 
+		timeout_ms = cfg_rcv_timeout_ms;
+
 	} while (!interrupted);
 
 	if (cfg_expected_pkt_nr && (packets != cfg_expected_pkt_nr))