summaryrefslogtreecommitdiff
path: root/tools/testing/selftests/net
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing/selftests/net')
-rw-r--r--tools/testing/selftests/net/.gitignore3
-rw-r--r--tools/testing/selftests/net/Makefile14
-rw-r--r--tools/testing/selftests/net/af_unix/scm_rights.c80
-rwxr-xr-xtools/testing/selftests/net/amt.sh20
-rwxr-xr-xtools/testing/selftests/net/bareudp.sh49
-rwxr-xr-xtools/testing/selftests/net/bpf_offload.py5
-rwxr-xr-xtools/testing/selftests/net/busy_poll_test.sh2
-rw-r--r--tools/testing/selftests/net/can/.gitignore2
-rw-r--r--tools/testing/selftests/net/can/Makefile11
-rw-r--r--tools/testing/selftests/net/can/test_raw_filter.c405
-rwxr-xr-xtools/testing/selftests/net/can/test_raw_filter.sh45
-rwxr-xr-xtools/testing/selftests/net/cmsg_ip.sh187
-rwxr-xr-xtools/testing/selftests/net/cmsg_ipv6.sh154
-rw-r--r--tools/testing/selftests/net/cmsg_sender.c114
-rw-r--r--tools/testing/selftests/net/config9
-rwxr-xr-xtools/testing/selftests/net/fcnal-test.sh4
-rwxr-xr-xtools/testing/selftests/net/fdb_flush.sh2
-rwxr-xr-xtools/testing/selftests/net/fib_nexthops.sh9
-rwxr-xr-xtools/testing/selftests/net/fib_rule_tests.sh111
-rwxr-xr-xtools/testing/selftests/net/fib_tests.sh123
-rw-r--r--tools/testing/selftests/net/forwarding/README2
-rwxr-xr-xtools/testing/selftests/net/forwarding/bridge_igmp.sh80
-rwxr-xr-xtools/testing/selftests/net/forwarding/bridge_mdb.sh2
-rwxr-xr-xtools/testing/selftests/net/forwarding/bridge_mld.sh81
-rwxr-xr-xtools/testing/selftests/net/forwarding/bridge_vlan_aware.sh96
-rw-r--r--tools/testing/selftests/net/forwarding/config1
-rw-r--r--tools/testing/selftests/net/forwarding/lib.sh10
-rwxr-xr-xtools/testing/selftests/net/forwarding/tc_taprio.sh421
-rw-r--r--tools/testing/selftests/net/forwarding/tsn_lib.sh26
-rwxr-xr-xtools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh10
-rwxr-xr-xtools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh15
-rwxr-xr-xtools/testing/selftests/net/gre_ipv6_lladdr.sh177
-rw-r--r--tools/testing/selftests/net/gro.c8
-rwxr-xr-xtools/testing/selftests/net/gro.sh7
-rwxr-xr-xtools/testing/selftests/net/icmp_redirect.sh2
-rwxr-xr-xtools/testing/selftests/net/ip_local_port_range.sh4
-rwxr-xr-xtools/testing/selftests/net/ipv6_route_update_soft_lockup.sh1
-rw-r--r--tools/testing/selftests/net/lib.sh91
-rw-r--r--tools/testing/selftests/net/lib/.gitignore1
-rw-r--r--tools/testing/selftests/net/lib/Makefile1
-rw-r--r--tools/testing/selftests/net/lib/ksft.h56
-rw-r--r--tools/testing/selftests/net/lib/py/__init__.py4
-rw-r--r--tools/testing/selftests/net/lib/py/ksft.py31
-rw-r--r--tools/testing/selftests/net/lib/py/netns.py18
-rw-r--r--tools/testing/selftests/net/lib/py/utils.py89
-rw-r--r--tools/testing/selftests/net/lib/py/ynl.py6
-rw-r--r--tools/testing/selftests/net/lib/xdp_helper.c131
-rwxr-xr-xtools/testing/selftests/net/link_netns.py141
-rw-r--r--tools/testing/selftests/net/mptcp/.gitignore1
-rw-r--r--tools/testing/selftests/net/mptcp/Makefile4
-rwxr-xr-xtools/testing/selftests/net/mptcp/diag.sh58
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_connect.c32
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_diag.c435
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_inq.c16
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_join.sh44
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_lib.sh10
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_sockopt.c16
-rwxr-xr-xtools/testing/selftests/net/mptcp/simult_flows.sh2
-rwxr-xr-xtools/testing/selftests/net/mptcp/userspace_pm.sh30
-rw-r--r--tools/testing/selftests/net/net_helper.sh25
-rw-r--r--tools/testing/selftests/net/netfilter/Makefile2
-rwxr-xr-xtools/testing/selftests/net/netfilter/br_netfilter.sh3
-rwxr-xr-xtools/testing/selftests/net/netfilter/bridge_brouter.sh2
-rw-r--r--tools/testing/selftests/net/netfilter/config1
-rwxr-xr-xtools/testing/selftests/net/netfilter/conntrack_resize.sh427
-rwxr-xr-xtools/testing/selftests/net/netfilter/conntrack_vrf.sh37
-rwxr-xr-xtools/testing/selftests/net/netfilter/ipvs.sh6
-rwxr-xr-xtools/testing/selftests/net/netfilter/nft_concat_range.sh204
-rwxr-xr-xtools/testing/selftests/net/netfilter/nft_fib.sh635
-rwxr-xr-xtools/testing/selftests/net/netfilter/nft_interface_stress.sh154
-rwxr-xr-xtools/testing/selftests/net/netfilter/nft_nat_zones.sh2
-rwxr-xr-xtools/testing/selftests/net/netfilter/nft_queue.sh38
-rwxr-xr-xtools/testing/selftests/net/netfilter/rpath.sh18
-rwxr-xr-xtools/testing/selftests/net/netns-name.sh23
-rwxr-xr-xtools/testing/selftests/net/nl_netdev.py18
-rwxr-xr-xtools/testing/selftests/net/openvswitch/openvswitch.sh11
-rw-r--r--tools/testing/selftests/net/ovpn/.gitignore2
-rw-r--r--tools/testing/selftests/net/ovpn/Makefile32
-rw-r--r--tools/testing/selftests/net/ovpn/common.sh108
-rw-r--r--tools/testing/selftests/net/ovpn/config10
-rw-r--r--tools/testing/selftests/net/ovpn/data64.key5
-rw-r--r--tools/testing/selftests/net/ovpn/ovpn-cli.c2383
-rw-r--r--tools/testing/selftests/net/ovpn/tcp_peers.txt5
-rwxr-xr-xtools/testing/selftests/net/ovpn/test-chachapoly.sh9
-rwxr-xr-xtools/testing/selftests/net/ovpn/test-close-socket-tcp.sh9
-rwxr-xr-xtools/testing/selftests/net/ovpn/test-close-socket.sh45
-rwxr-xr-xtools/testing/selftests/net/ovpn/test-float.sh9
-rwxr-xr-xtools/testing/selftests/net/ovpn/test-tcp.sh9
-rwxr-xr-xtools/testing/selftests/net/ovpn/test.sh117
-rw-r--r--tools/testing/selftests/net/ovpn/udp_peers.txt6
-rwxr-xr-xtools/testing/selftests/net/pmtu.sh1
-rw-r--r--tools/testing/selftests/net/proc_net_pktgen.c690
-rw-r--r--tools/testing/selftests/net/psock_tpacket.c2
-rw-r--r--tools/testing/selftests/net/reuseaddr_ports_exhausted.c2
-rw-r--r--tools/testing/selftests/net/reuseport_addr_any.c36
-rwxr-xr-xtools/testing/selftests/net/rtnetlink.py30
-rw-r--r--tools/testing/selftests/net/setup_veth.sh3
-rw-r--r--tools/testing/selftests/net/skf_net_off.c244
-rwxr-xr-xtools/testing/selftests/net/skf_net_off.sh30
-rw-r--r--tools/testing/selftests/net/so_rcv_listener.c168
-rwxr-xr-xtools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh5
-rwxr-xr-xtools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh5
-rwxr-xr-xtools/testing/selftests/net/srv6_end_flavors_test.sh4
-rwxr-xr-xtools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh77
-rwxr-xr-xtools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh83
-rwxr-xr-xtools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh74
-rwxr-xr-xtools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh83
-rw-r--r--tools/testing/selftests/net/tcp_ao/connect-deny.c58
-rw-r--r--tools/testing/selftests/net/tcp_ao/connect.c22
-rw-r--r--tools/testing/selftests/net/tcp_ao/icmps-discard.c17
-rw-r--r--tools/testing/selftests/net/tcp_ao/key-management.c76
-rw-r--r--tools/testing/selftests/net/tcp_ao/lib/aolib.h114
-rw-r--r--tools/testing/selftests/net/tcp_ao/lib/ftrace-tcp.c7
-rw-r--r--tools/testing/selftests/net/tcp_ao/lib/sock.c315
-rw-r--r--tools/testing/selftests/net/tcp_ao/restore.c75
-rw-r--r--tools/testing/selftests/net/tcp_ao/rst.c47
-rw-r--r--tools/testing/selftests/net/tcp_ao/self-connect.c21
-rw-r--r--tools/testing/selftests/net/tcp_ao/seq-ext.c30
-rw-r--r--tools/testing/selftests/net/tcp_ao/unsigned-md5.c118
-rwxr-xr-xtools/testing/selftests/net/test_blackhole_dev.sh11
-rwxr-xr-xtools/testing/selftests/net/test_bridge_neigh_suppress.sh125
-rwxr-xr-xtools/testing/selftests/net/test_so_rcv.sh73
-rwxr-xr-xtools/testing/selftests/net/test_vxlan_fdb_changelink.sh111
-rw-r--r--tools/testing/selftests/net/tls.c36
-rwxr-xr-xtools/testing/selftests/net/udpgro.sh2
-rwxr-xr-xtools/testing/selftests/net/udpgro_bench.sh4
-rwxr-xr-xtools/testing/selftests/net/udpgro_frglist.sh4
-rwxr-xr-xtools/testing/selftests/net/udpgro_fwd.sh4
-rwxr-xr-xtools/testing/selftests/net/veth.sh2
-rw-r--r--tools/testing/selftests/net/xdp_dummy.bpf.c13
-rw-r--r--tools/testing/selftests/net/ynl.mk3
131 files changed, 9541 insertions, 1148 deletions
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 28a715a8ef2b..532bb732bc6d 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -21,6 +21,7 @@ msg_oob
msg_zerocopy
netlink-dumps
nettest
+proc_net_pktgen
psock_fanout
psock_snd
psock_tpacket
@@ -38,10 +39,12 @@ scm_rights
sk_bind_sendto_listen
sk_connect_zero_addr
sk_so_peek_off
+skf_net_off
socket
so_incoming_cpu
so_netns_cookie
so_txtime
+so_rcv_listener
stress_reuseport_listen
tap
tcp_fastopen_backup_key
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 8f32b4f01aee..ea84b88bcb30 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -7,7 +7,7 @@ CFLAGS += -I../../../../usr/include/ $(KHDR_INCLUDES)
CFLAGS += -I../
TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh \
- rtnetlink.sh xfrm_policy.sh test_blackhole_dev.sh
+ rtnetlink.sh xfrm_policy.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 udpgro.sh test_vxlan_under_vrf.sh reuseport_addr_any.sh
@@ -31,11 +31,15 @@ TEST_PROGS += veth.sh
TEST_PROGS += ioam6.sh
TEST_PROGS += gro.sh
TEST_PROGS += gre_gso.sh
+TEST_PROGS += gre_ipv6_lladdr.sh
TEST_PROGS += cmsg_so_mark.sh
TEST_PROGS += cmsg_so_priority.sh
-TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh
+TEST_PROGS += test_so_rcv.sh
+TEST_PROGS += cmsg_time.sh cmsg_ip.sh
TEST_PROGS += netns-name.sh
+TEST_PROGS += link_netns.py
TEST_PROGS += nl_netdev.py
+TEST_PROGS += rtnetlink.py
TEST_PROGS += srv6_end_dt46_l3vpn_test.sh
TEST_PROGS += srv6_end_dt4_l3vpn_test.sh
TEST_PROGS += srv6_end_dt6_l3vpn_test.sh
@@ -75,6 +79,7 @@ TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls tun tap epoll_busy_
TEST_GEN_FILES += toeplitz
TEST_GEN_FILES += cmsg_sender
TEST_GEN_FILES += stress_reuseport_listen
+TEST_GEN_FILES += so_rcv_listener
TEST_PROGS += test_vxlan_vnifiltering.sh
TEST_GEN_FILES += io_uring_zerocopy_tx
TEST_PROGS += io_uring_zerocopy_tx.sh
@@ -100,14 +105,17 @@ TEST_PROGS += vlan_bridge_binding.sh
TEST_PROGS += bpf_offload.py
TEST_PROGS += ipv6_route_update_soft_lockup.sh
TEST_PROGS += busy_poll_test.sh
+TEST_GEN_PROGS += proc_net_pktgen
TEST_PROGS += lwt_dst_cache_ref_loop.sh
+TEST_PROGS += skf_net_off.sh
+TEST_GEN_FILES += skf_net_off
# YNL files, must be before "include ..lib.mk"
YNL_GEN_FILES := busy_poller netlink-dumps
TEST_GEN_FILES += $(YNL_GEN_FILES)
TEST_FILES := settings
-TEST_FILES += in_netns.sh lib.sh net_helper.sh setup_loopback.sh setup_veth.sh
+TEST_FILES += in_netns.sh lib.sh setup_loopback.sh setup_veth.sh
TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c))
diff --git a/tools/testing/selftests/net/af_unix/scm_rights.c b/tools/testing/selftests/net/af_unix/scm_rights.c
index d66336256580..8b015f16c03d 100644
--- a/tools/testing/selftests/net/af_unix/scm_rights.c
+++ b/tools/testing/selftests/net/af_unix/scm_rights.c
@@ -23,6 +23,7 @@ FIXTURE_VARIANT(scm_rights)
int type;
int flags;
bool test_listener;
+ bool disabled;
};
FIXTURE_VARIANT_ADD(scm_rights, dgram)
@@ -31,6 +32,16 @@ FIXTURE_VARIANT_ADD(scm_rights, dgram)
.type = SOCK_DGRAM,
.flags = 0,
.test_listener = false,
+ .disabled = false,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, dgram_disabled)
+{
+ .name = "UNIX ",
+ .type = SOCK_DGRAM,
+ .flags = 0,
+ .test_listener = false,
+ .disabled = true,
};
FIXTURE_VARIANT_ADD(scm_rights, stream)
@@ -39,6 +50,16 @@ FIXTURE_VARIANT_ADD(scm_rights, stream)
.type = SOCK_STREAM,
.flags = 0,
.test_listener = false,
+ .disabled = false,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, stream_disabled)
+{
+ .name = "UNIX-STREAM ",
+ .type = SOCK_STREAM,
+ .flags = 0,
+ .test_listener = false,
+ .disabled = true,
};
FIXTURE_VARIANT_ADD(scm_rights, stream_oob)
@@ -47,6 +68,16 @@ FIXTURE_VARIANT_ADD(scm_rights, stream_oob)
.type = SOCK_STREAM,
.flags = MSG_OOB,
.test_listener = false,
+ .disabled = false,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, stream_oob_disabled)
+{
+ .name = "UNIX-STREAM ",
+ .type = SOCK_STREAM,
+ .flags = MSG_OOB,
+ .test_listener = false,
+ .disabled = true,
};
FIXTURE_VARIANT_ADD(scm_rights, stream_listener)
@@ -55,6 +86,16 @@ FIXTURE_VARIANT_ADD(scm_rights, stream_listener)
.type = SOCK_STREAM,
.flags = 0,
.test_listener = true,
+ .disabled = false,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, stream_listener_disabled)
+{
+ .name = "UNIX-STREAM ",
+ .type = SOCK_STREAM,
+ .flags = 0,
+ .test_listener = true,
+ .disabled = true,
};
FIXTURE_VARIANT_ADD(scm_rights, stream_listener_oob)
@@ -63,6 +104,16 @@ FIXTURE_VARIANT_ADD(scm_rights, stream_listener_oob)
.type = SOCK_STREAM,
.flags = MSG_OOB,
.test_listener = true,
+ .disabled = false,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, stream_listener_oob_disabled)
+{
+ .name = "UNIX-STREAM ",
+ .type = SOCK_STREAM,
+ .flags = MSG_OOB,
+ .test_listener = true,
+ .disabled = true,
};
static int count_sockets(struct __test_metadata *_metadata,
@@ -105,6 +156,9 @@ FIXTURE_SETUP(scm_rights)
ret = unshare(CLONE_NEWNET);
ASSERT_EQ(0, ret);
+ if (variant->disabled)
+ return;
+
ret = count_sockets(_metadata, variant);
ASSERT_EQ(0, ret);
}
@@ -113,6 +167,9 @@ FIXTURE_TEARDOWN(scm_rights)
{
int ret;
+ if (variant->disabled)
+ return;
+
sleep(1);
ret = count_sockets(_metadata, variant);
@@ -121,6 +178,7 @@ FIXTURE_TEARDOWN(scm_rights)
static void create_listeners(struct __test_metadata *_metadata,
FIXTURE_DATA(scm_rights) *self,
+ const FIXTURE_VARIANT(scm_rights) *variant,
int n)
{
struct sockaddr_un addr = {
@@ -140,6 +198,12 @@ static void create_listeners(struct __test_metadata *_metadata,
ret = listen(self->fd[i], -1);
ASSERT_EQ(0, ret);
+ if (variant->disabled) {
+ ret = setsockopt(self->fd[i], SOL_SOCKET, SO_PASSRIGHTS,
+ &(int){0}, sizeof(int));
+ ASSERT_EQ(0, ret);
+ }
+
addrlen = sizeof(addr);
ret = getsockname(self->fd[i], (struct sockaddr *)&addr, &addrlen);
ASSERT_EQ(0, ret);
@@ -164,6 +228,12 @@ static void create_socketpairs(struct __test_metadata *_metadata,
for (i = 0; i < n * 2; i += 2) {
ret = socketpair(AF_UNIX, variant->type, 0, self->fd + i);
ASSERT_EQ(0, ret);
+
+ if (variant->disabled) {
+ ret = setsockopt(self->fd[i], SOL_SOCKET, SO_PASSRIGHTS,
+ &(int){0}, sizeof(int));
+ ASSERT_EQ(0, ret);
+ }
}
}
@@ -175,7 +245,7 @@ static void __create_sockets(struct __test_metadata *_metadata,
ASSERT_LE(n * 2, sizeof(self->fd) / sizeof(self->fd[0]));
if (variant->test_listener)
- create_listeners(_metadata, self, n);
+ create_listeners(_metadata, self, variant, n);
else
create_socketpairs(_metadata, self, variant, n);
}
@@ -230,7 +300,13 @@ void __send_fd(struct __test_metadata *_metadata,
int ret;
ret = sendmsg(self->fd[receiver * 2 + 1], &msg, variant->flags);
- ASSERT_EQ(MSGLEN, ret);
+
+ if (variant->disabled) {
+ ASSERT_EQ(-1, ret);
+ ASSERT_EQ(-EPERM, -errno);
+ } else {
+ ASSERT_EQ(MSGLEN, ret);
+ }
}
#define create_sockets(n) \
diff --git a/tools/testing/selftests/net/amt.sh b/tools/testing/selftests/net/amt.sh
index d458b45c775b..3ef209cacb8e 100755
--- a/tools/testing/selftests/net/amt.sh
+++ b/tools/testing/selftests/net/amt.sh
@@ -194,15 +194,21 @@ test_remote_ip()
send_mcast_torture4()
{
- ip netns exec "${SOURCE}" bash -c \
- 'cat /dev/urandom | head -c 1G | nc -w 1 -u 239.0.0.1 4001'
+ for i in `seq 10`; do
+ ip netns exec "${SOURCE}" bash -c \
+ 'cat /dev/urandom | head -c 100M | nc -w 1 -u 239.0.0.1 4001'
+ echo -n "."
+ done
}
send_mcast_torture6()
{
- ip netns exec "${SOURCE}" bash -c \
- 'cat /dev/urandom | head -c 1G | nc -w 1 -u ff0e::5:6 6001'
+ for i in `seq 10`; do
+ ip netns exec "${SOURCE}" bash -c \
+ 'cat /dev/urandom | head -c 100M | nc -w 1 -u ff0e::5:6 6001'
+ echo -n "."
+ done
}
check_features()
@@ -278,10 +284,12 @@ wait $pid || err=$?
if [ $err -eq 1 ]; then
ERR=1
fi
+printf "TEST: %-50s" "IPv4 amt traffic forwarding torture"
send_mcast_torture4
-printf "TEST: %-60s [ OK ]\n" "IPv4 amt traffic forwarding torture"
+printf " [ OK ]\n"
+printf "TEST: %-50s" "IPv6 amt traffic forwarding torture"
send_mcast_torture6
-printf "TEST: %-60s [ OK ]\n" "IPv6 amt traffic forwarding torture"
+printf " [ OK ]\n"
sleep 5
if [ "${ERR}" -eq 1 ]; then
echo "Some tests failed." >&2
diff --git a/tools/testing/selftests/net/bareudp.sh b/tools/testing/selftests/net/bareudp.sh
index f366cadbc5e8..4046131e7888 100755
--- a/tools/testing/selftests/net/bareudp.sh
+++ b/tools/testing/selftests/net/bareudp.sh
@@ -106,26 +106,16 @@
# | |
# +-----------------------------------------------------------------------+
+. ./lib.sh
+
ERR=4 # Return 4 by default, which is the SKIP code for kselftest
PING6="ping"
PAUSE_ON_FAIL="no"
-readonly NS0=$(mktemp -u ns0-XXXXXXXX)
-readonly NS1=$(mktemp -u ns1-XXXXXXXX)
-readonly NS2=$(mktemp -u ns2-XXXXXXXX)
-readonly NS3=$(mktemp -u ns3-XXXXXXXX)
-
# Exit the script after having removed the network namespaces it created
-#
-# Parameters:
-#
-# * The list of network namespaces to delete before exiting.
-#
exit_cleanup()
{
- for ns in "$@"; do
- ip netns delete "${ns}" 2>/dev/null || true
- done
+ cleanup_all_ns
if [ "${ERR}" -eq 4 ]; then
echo "Error: Setting up the testing environment failed." >&2
@@ -140,17 +130,7 @@ exit_cleanup()
# namespaces created by this script are deleted.
create_namespaces()
{
- ip netns add "${NS0}" || exit_cleanup
- ip netns add "${NS1}" || exit_cleanup "${NS0}"
- ip netns add "${NS2}" || exit_cleanup "${NS0}" "${NS1}"
- ip netns add "${NS3}" || exit_cleanup "${NS0}" "${NS1}" "${NS2}"
-}
-
-# The trap function handler
-#
-exit_cleanup_all()
-{
- exit_cleanup "${NS0}" "${NS1}" "${NS2}" "${NS3}"
+ setup_ns NS0 NS1 NS2 NS3 || exit_cleanup
}
# Configure a network interface using a host route
@@ -188,10 +168,6 @@ iface_config()
#
setup_underlay()
{
- for ns in "${NS0}" "${NS1}" "${NS2}" "${NS3}"; do
- ip -netns "${ns}" link set dev lo up
- done;
-
ip link add name veth01 netns "${NS0}" type veth peer name veth10 netns "${NS1}"
ip link add name veth12 netns "${NS1}" type veth peer name veth21 netns "${NS2}"
ip link add name veth23 netns "${NS2}" type veth peer name veth32 netns "${NS3}"
@@ -234,14 +210,6 @@ setup_overlay_ipv4()
ip netns exec "${NS2}" sysctl -qw net.ipv4.ip_forward=1
ip -netns "${NS1}" route add 192.0.2.100/32 via 192.0.2.10
ip -netns "${NS2}" route add 192.0.2.103/32 via 192.0.2.33
-
- # The intermediate namespaces don't have routes for the reverse path,
- # as it will be handled by tc. So we need to ensure that rp_filter is
- # not going to block the traffic.
- ip netns exec "${NS1}" sysctl -qw net.ipv4.conf.all.rp_filter=0
- ip netns exec "${NS2}" sysctl -qw net.ipv4.conf.all.rp_filter=0
- ip netns exec "${NS1}" sysctl -qw net.ipv4.conf.default.rp_filter=0
- ip netns exec "${NS2}" sysctl -qw net.ipv4.conf.default.rp_filter=0
}
setup_overlay_ipv6()
@@ -521,13 +489,10 @@ done
check_features
-# Create namespaces before setting up the exit trap.
-# Otherwise, exit_cleanup_all() could delete namespaces that were not created
-# by this script.
-create_namespaces
-
set -e
-trap exit_cleanup_all EXIT
+trap exit_cleanup EXIT
+
+create_namespaces
setup_underlay
setup_overlay_ipv4
diff --git a/tools/testing/selftests/net/bpf_offload.py b/tools/testing/selftests/net/bpf_offload.py
index fd0d959914e4..b2c271b79240 100755
--- a/tools/testing/selftests/net/bpf_offload.py
+++ b/tools/testing/selftests/net/bpf_offload.py
@@ -207,9 +207,11 @@ def bpftool_prog_list_wait(expected=0, n_retry=20):
raise Exception("Time out waiting for program counts to stabilize want %d, have %d" % (expected, nprogs))
def bpftool_map_list_wait(expected=0, n_retry=20, ns=""):
+ nmaps = None
for i in range(n_retry):
maps = bpftool_map_list(ns=ns)
- if len(maps) == expected:
+ nmaps = len(maps)
+ if nmaps == expected:
return maps
time.sleep(0.05)
raise Exception("Time out waiting for map counts to stabilize want %d, have %d" % (expected, nmaps))
@@ -710,6 +712,7 @@ _, base_maps = bpftool("map")
base_map_names = [
'pid_iter.rodata', # created on each bpftool invocation
'libbpf_det_bind', # created on each bpftool invocation
+ 'libbpf_global',
]
# Check netdevsim
diff --git a/tools/testing/selftests/net/busy_poll_test.sh b/tools/testing/selftests/net/busy_poll_test.sh
index 7db292ec4884..7d2d40812074 100755
--- a/tools/testing/selftests/net/busy_poll_test.sh
+++ b/tools/testing/selftests/net/busy_poll_test.sh
@@ -1,6 +1,6 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
-source net_helper.sh
+source lib.sh
NSIM_SV_ID=$((256 + RANDOM % 256))
NSIM_SV_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_SV_ID
diff --git a/tools/testing/selftests/net/can/.gitignore b/tools/testing/selftests/net/can/.gitignore
new file mode 100644
index 000000000000..764a53fc837f
--- /dev/null
+++ b/tools/testing/selftests/net/can/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+test_raw_filter
diff --git a/tools/testing/selftests/net/can/Makefile b/tools/testing/selftests/net/can/Makefile
new file mode 100644
index 000000000000..5b82e60a03e7
--- /dev/null
+++ b/tools/testing/selftests/net/can/Makefile
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0
+
+top_srcdir = ../../../../..
+
+CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES)
+
+TEST_PROGS := test_raw_filter.sh
+
+TEST_GEN_FILES := test_raw_filter
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/net/can/test_raw_filter.c b/tools/testing/selftests/net/can/test_raw_filter.c
new file mode 100644
index 000000000000..4101c36390fd
--- /dev/null
+++ b/tools/testing/selftests/net/can/test_raw_filter.c
@@ -0,0 +1,405 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/*
+ * Copyright (c) 2011 Volkswagen Group Electronic Research
+ * All rights reserved.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <sys/time.h>
+#include <net/if.h>
+#include <linux/if.h>
+
+#include <linux/can.h>
+#include <linux/can/raw.h>
+
+#include "../../kselftest_harness.h"
+
+#define ID 0x123
+
+char CANIF[IFNAMSIZ];
+
+static int send_can_frames(int sock, int testcase)
+{
+ struct can_frame frame;
+
+ frame.can_dlc = 1;
+ frame.data[0] = testcase;
+
+ frame.can_id = ID;
+ if (write(sock, &frame, sizeof(frame)) < 0)
+ goto write_err;
+
+ frame.can_id = (ID | CAN_RTR_FLAG);
+ if (write(sock, &frame, sizeof(frame)) < 0)
+ goto write_err;
+
+ frame.can_id = (ID | CAN_EFF_FLAG);
+ if (write(sock, &frame, sizeof(frame)) < 0)
+ goto write_err;
+
+ frame.can_id = (ID | CAN_EFF_FLAG | CAN_RTR_FLAG);
+ if (write(sock, &frame, sizeof(frame)) < 0)
+ goto write_err;
+
+ return 0;
+
+write_err:
+ perror("write");
+ return 1;
+}
+
+FIXTURE(can_filters) {
+ int sock;
+};
+
+FIXTURE_SETUP(can_filters)
+{
+ struct sockaddr_can addr;
+ struct ifreq ifr;
+ int recv_own_msgs = 1;
+ int s, ret;
+
+ s = socket(PF_CAN, SOCK_RAW, CAN_RAW);
+ ASSERT_GE(s, 0)
+ TH_LOG("failed to create CAN_RAW socket: %d", errno);
+
+ strncpy(ifr.ifr_name, CANIF, sizeof(ifr.ifr_name));
+ ret = ioctl(s, SIOCGIFINDEX, &ifr);
+ ASSERT_GE(ret, 0)
+ TH_LOG("failed SIOCGIFINDEX: %d", errno);
+
+ addr.can_family = AF_CAN;
+ addr.can_ifindex = ifr.ifr_ifindex;
+
+ setsockopt(s, SOL_CAN_RAW, CAN_RAW_RECV_OWN_MSGS,
+ &recv_own_msgs, sizeof(recv_own_msgs));
+
+ ret = bind(s, (struct sockaddr *)&addr, sizeof(addr));
+ ASSERT_EQ(ret, 0)
+ TH_LOG("failed bind socket: %d", errno);
+
+ self->sock = s;
+}
+
+FIXTURE_TEARDOWN(can_filters)
+{
+ close(self->sock);
+}
+
+FIXTURE_VARIANT(can_filters) {
+ int testcase;
+ canid_t id;
+ canid_t mask;
+ int exp_num_rx;
+ canid_t exp_flags[];
+};
+
+/* Receive all frames when filtering for the ID in standard frame format */
+FIXTURE_VARIANT_ADD(can_filters, base) {
+ .testcase = 1,
+ .id = ID,
+ .mask = CAN_SFF_MASK,
+ .exp_num_rx = 4,
+ .exp_flags = {
+ 0,
+ CAN_RTR_FLAG,
+ CAN_EFF_FLAG,
+ CAN_EFF_FLAG | CAN_RTR_FLAG,
+ },
+};
+
+/* Ignore EFF flag in filter ID if not covered by filter mask */
+FIXTURE_VARIANT_ADD(can_filters, base_eff) {
+ .testcase = 2,
+ .id = ID | CAN_EFF_FLAG,
+ .mask = CAN_SFF_MASK,
+ .exp_num_rx = 4,
+ .exp_flags = {
+ 0,
+ CAN_RTR_FLAG,
+ CAN_EFF_FLAG,
+ CAN_EFF_FLAG | CAN_RTR_FLAG,
+ },
+};
+
+/* Ignore RTR flag in filter ID if not covered by filter mask */
+FIXTURE_VARIANT_ADD(can_filters, base_rtr) {
+ .testcase = 3,
+ .id = ID | CAN_RTR_FLAG,
+ .mask = CAN_SFF_MASK,
+ .exp_num_rx = 4,
+ .exp_flags = {
+ 0,
+ CAN_RTR_FLAG,
+ CAN_EFF_FLAG,
+ CAN_EFF_FLAG | CAN_RTR_FLAG,
+ },
+};
+
+/* Ignore EFF and RTR flags in filter ID if not covered by filter mask */
+FIXTURE_VARIANT_ADD(can_filters, base_effrtr) {
+ .testcase = 4,
+ .id = ID | CAN_EFF_FLAG | CAN_RTR_FLAG,
+ .mask = CAN_SFF_MASK,
+ .exp_num_rx = 4,
+ .exp_flags = {
+ 0,
+ CAN_RTR_FLAG,
+ CAN_EFF_FLAG,
+ CAN_EFF_FLAG | CAN_RTR_FLAG,
+ },
+};
+
+/* Receive only SFF frames when expecting no EFF flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_eff) {
+ .testcase = 5,
+ .id = ID,
+ .mask = CAN_SFF_MASK | CAN_EFF_FLAG,
+ .exp_num_rx = 2,
+ .exp_flags = {
+ 0,
+ CAN_RTR_FLAG,
+ },
+};
+
+/* Receive only EFF frames when filter id and filter mask include EFF flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_eff_eff) {
+ .testcase = 6,
+ .id = ID | CAN_EFF_FLAG,
+ .mask = CAN_SFF_MASK | CAN_EFF_FLAG,
+ .exp_num_rx = 2,
+ .exp_flags = {
+ CAN_EFF_FLAG,
+ CAN_EFF_FLAG | CAN_RTR_FLAG,
+ },
+};
+
+/* Receive only SFF frames when expecting no EFF flag, ignoring RTR flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_eff_rtr) {
+ .testcase = 7,
+ .id = ID | CAN_RTR_FLAG,
+ .mask = CAN_SFF_MASK | CAN_EFF_FLAG,
+ .exp_num_rx = 2,
+ .exp_flags = {
+ 0,
+ CAN_RTR_FLAG,
+ },
+};
+
+/* Receive only EFF frames when filter id and filter mask include EFF flag,
+ * ignoring RTR flag
+ */
+FIXTURE_VARIANT_ADD(can_filters, filter_eff_effrtr) {
+ .testcase = 8,
+ .id = ID | CAN_EFF_FLAG | CAN_RTR_FLAG,
+ .mask = CAN_SFF_MASK | CAN_EFF_FLAG,
+ .exp_num_rx = 2,
+ .exp_flags = {
+ CAN_EFF_FLAG,
+ CAN_EFF_FLAG | CAN_RTR_FLAG,
+ },
+};
+
+/* Receive no remote frames when filtering for no RTR flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_rtr) {
+ .testcase = 9,
+ .id = ID,
+ .mask = CAN_SFF_MASK | CAN_RTR_FLAG,
+ .exp_num_rx = 2,
+ .exp_flags = {
+ 0,
+ CAN_EFF_FLAG,
+ },
+};
+
+/* Receive no remote frames when filtering for no RTR flag, ignoring EFF flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_rtr_eff) {
+ .testcase = 10,
+ .id = ID | CAN_EFF_FLAG,
+ .mask = CAN_SFF_MASK | CAN_RTR_FLAG,
+ .exp_num_rx = 2,
+ .exp_flags = {
+ 0,
+ CAN_EFF_FLAG,
+ },
+};
+
+/* Receive only remote frames when filter includes RTR flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_rtr_rtr) {
+ .testcase = 11,
+ .id = ID | CAN_RTR_FLAG,
+ .mask = CAN_SFF_MASK | CAN_RTR_FLAG,
+ .exp_num_rx = 2,
+ .exp_flags = {
+ CAN_RTR_FLAG,
+ CAN_EFF_FLAG | CAN_RTR_FLAG,
+ },
+};
+
+/* Receive only remote frames when filter includes RTR flag, ignoring EFF
+ * flag
+ */
+FIXTURE_VARIANT_ADD(can_filters, filter_rtr_effrtr) {
+ .testcase = 12,
+ .id = ID | CAN_EFF_FLAG | CAN_RTR_FLAG,
+ .mask = CAN_SFF_MASK | CAN_RTR_FLAG,
+ .exp_num_rx = 2,
+ .exp_flags = {
+ CAN_RTR_FLAG,
+ CAN_EFF_FLAG | CAN_RTR_FLAG,
+ },
+};
+
+/* Receive only SFF data frame when filtering for no flags */
+FIXTURE_VARIANT_ADD(can_filters, filter_effrtr) {
+ .testcase = 13,
+ .id = ID,
+ .mask = CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG,
+ .exp_num_rx = 1,
+ .exp_flags = {
+ 0,
+ },
+};
+
+/* Receive only EFF data frame when filtering for EFF but no RTR flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_effrtr_eff) {
+ .testcase = 14,
+ .id = ID | CAN_EFF_FLAG,
+ .mask = CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG,
+ .exp_num_rx = 1,
+ .exp_flags = {
+ CAN_EFF_FLAG,
+ },
+};
+
+/* Receive only SFF remote frame when filtering for RTR but no EFF flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_effrtr_rtr) {
+ .testcase = 15,
+ .id = ID | CAN_RTR_FLAG,
+ .mask = CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG,
+ .exp_num_rx = 1,
+ .exp_flags = {
+ CAN_RTR_FLAG,
+ },
+};
+
+/* Receive only EFF remote frame when filtering for EFF and RTR flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_effrtr_effrtr) {
+ .testcase = 16,
+ .id = ID | CAN_EFF_FLAG | CAN_RTR_FLAG,
+ .mask = CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG,
+ .exp_num_rx = 1,
+ .exp_flags = {
+ CAN_EFF_FLAG | CAN_RTR_FLAG,
+ },
+};
+
+/* Receive only SFF data frame when filtering for no EFF flag and no RTR flag
+ * but based on EFF mask
+ */
+FIXTURE_VARIANT_ADD(can_filters, eff) {
+ .testcase = 17,
+ .id = ID,
+ .mask = CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG,
+ .exp_num_rx = 1,
+ .exp_flags = {
+ 0,
+ },
+};
+
+/* Receive only EFF data frame when filtering for EFF flag and no RTR flag but
+ * based on EFF mask
+ */
+FIXTURE_VARIANT_ADD(can_filters, eff_eff) {
+ .testcase = 18,
+ .id = ID | CAN_EFF_FLAG,
+ .mask = CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG,
+ .exp_num_rx = 1,
+ .exp_flags = {
+ CAN_EFF_FLAG,
+ },
+};
+
+/* This test verifies that the raw CAN filters work, by checking if only frames
+ * with the expected set of flags are received. For each test case, the given
+ * filter (id and mask) is added and four CAN frames are sent with every
+ * combination of set/unset EFF/RTR flags.
+ */
+TEST_F(can_filters, test_filter)
+{
+ struct can_filter rfilter;
+ int ret;
+
+ rfilter.can_id = variant->id;
+ rfilter.can_mask = variant->mask;
+ setsockopt(self->sock, SOL_CAN_RAW, CAN_RAW_FILTER,
+ &rfilter, sizeof(rfilter));
+
+ TH_LOG("filters: can_id = 0x%08X can_mask = 0x%08X",
+ rfilter.can_id, rfilter.can_mask);
+
+ ret = send_can_frames(self->sock, variant->testcase);
+ ASSERT_EQ(ret, 0)
+ TH_LOG("failed to send CAN frames");
+
+ for (int i = 0; i <= variant->exp_num_rx; i++) {
+ struct can_frame frame;
+ struct timeval tv = {
+ .tv_sec = 0,
+ .tv_usec = 50000, /* 50ms timeout */
+ };
+ fd_set rdfs;
+
+ FD_ZERO(&rdfs);
+ FD_SET(self->sock, &rdfs);
+
+ ret = select(self->sock + 1, &rdfs, NULL, NULL, &tv);
+ ASSERT_GE(ret, 0)
+ TH_LOG("failed select for frame %d, err: %d)", i, errno);
+
+ ret = FD_ISSET(self->sock, &rdfs);
+ if (i == variant->exp_num_rx) {
+ ASSERT_EQ(ret, 0)
+ TH_LOG("too many frames received");
+ } else {
+ ASSERT_NE(ret, 0)
+ TH_LOG("too few frames received");
+
+ ret = read(self->sock, &frame, sizeof(frame));
+ ASSERT_GE(ret, 0)
+ TH_LOG("failed to read frame %d, err: %d", i, errno);
+
+ TH_LOG("rx: can_id = 0x%08X rx = %d", frame.can_id, i);
+
+ ASSERT_EQ(ID, frame.can_id & CAN_SFF_MASK)
+ TH_LOG("received wrong can_id");
+ ASSERT_EQ(variant->testcase, frame.data[0])
+ TH_LOG("received wrong test case");
+
+ ASSERT_EQ(frame.can_id & ~CAN_ERR_MASK,
+ variant->exp_flags[i])
+ TH_LOG("received unexpected flags");
+ }
+ }
+}
+
+int main(int argc, char **argv)
+{
+ char *ifname = getenv("CANIF");
+
+ if (!ifname) {
+ printf("CANIF environment variable must contain the test interface\n");
+ return KSFT_FAIL;
+ }
+
+ strncpy(CANIF, ifname, sizeof(CANIF) - 1);
+
+ return test_harness_run(argc, argv);
+}
diff --git a/tools/testing/selftests/net/can/test_raw_filter.sh b/tools/testing/selftests/net/can/test_raw_filter.sh
new file mode 100755
index 000000000000..276d6c06ac95
--- /dev/null
+++ b/tools/testing/selftests/net/can/test_raw_filter.sh
@@ -0,0 +1,45 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+ test_raw_filter
+"
+
+net_dir=$(dirname $0)/..
+source $net_dir/lib.sh
+
+export CANIF=${CANIF:-"vcan0"}
+BITRATE=${BITRATE:-500000}
+
+setup()
+{
+ if [[ $CANIF == vcan* ]]; then
+ ip link add name $CANIF type vcan || exit $ksft_skip
+ else
+ ip link set dev $CANIF type can bitrate $BITRATE || exit $ksft_skip
+ fi
+ ip link set dev $CANIF up
+ pwd
+}
+
+cleanup()
+{
+ ip link set dev $CANIF down
+ if [[ $CANIF == vcan* ]]; then
+ ip link delete $CANIF
+ fi
+}
+
+test_raw_filter()
+{
+ ./test_raw_filter
+ check_err $?
+ log_test "test_raw_filter"
+}
+
+trap cleanup EXIT
+setup
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/cmsg_ip.sh b/tools/testing/selftests/net/cmsg_ip.sh
new file mode 100755
index 000000000000..b55680e081ad
--- /dev/null
+++ b/tools/testing/selftests/net/cmsg_ip.sh
@@ -0,0 +1,187 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source lib.sh
+
+IP4=172.16.0.1/24
+TGT4=172.16.0.2
+IP6=2001:db8:1::1/64
+TGT6=2001:db8:1::2
+TMPF=$(mktemp --suffix ".pcap")
+
+cleanup()
+{
+ rm -f $TMPF
+ cleanup_ns $NS
+}
+
+trap cleanup EXIT
+
+tcpdump -h | grep immediate-mode >> /dev/null
+if [ $? -ne 0 ]; then
+ echo "SKIP - tcpdump with --immediate-mode option required"
+ exit $ksft_skip
+fi
+
+# Namespaces
+setup_ns NS
+NSEXE="ip netns exec $NS"
+
+$NSEXE sysctl -w net.ipv4.ping_group_range='0 2147483647' > /dev/null
+
+# Connectivity
+ip -netns $NS link add type dummy
+ip -netns $NS link set dev dummy0 up
+ip -netns $NS addr add $IP4 dev dummy0
+ip -netns $NS addr add $IP6 dev dummy0
+
+# Test
+BAD=0
+TOTAL=0
+
+check_result() {
+ ((TOTAL++))
+ if [ $1 -ne $2 ]; then
+ echo " Case $3 returned $1, expected $2"
+ ((BAD++))
+ fi
+}
+
+# IPV6_DONTFRAG
+for ovr in setsock cmsg both diff; do
+ for df in 0 1; do
+ for p in u U i r; do
+ [ $p == "u" ] && prot=UDP
+ [ $p == "U" ] && prot=UDP
+ [ $p == "i" ] && prot=ICMP
+ [ $p == "r" ] && prot=RAW
+
+ [ $ovr == "setsock" ] && m="-F $df"
+ [ $ovr == "cmsg" ] && m="-f $df"
+ [ $ovr == "both" ] && m="-F $df -f $df"
+ [ $ovr == "diff" ] && m="-F $((1 - df)) -f $df"
+
+ $NSEXE ./cmsg_sender -s -S 2000 -6 -p $p $m $TGT6 1234
+ check_result $? $df "DONTFRAG $prot $ovr"
+ done
+ done
+done
+
+# IP_TOS + IPV6_TCLASS
+
+test_dscp() {
+ local -r IPVER=$1
+ local -r TGT=$2
+ local -r MATCH=$3
+
+ local -r TOS=0x10
+ local -r TOS2=0x20
+ local -r ECN=0x3
+
+ ip $IPVER -netns $NS rule add tos $TOS lookup 300
+ ip $IPVER -netns $NS route add table 300 prohibit any
+
+ for ovr in setsock cmsg both diff; do
+ for p in u U i r; do
+ [ $p == "u" ] && prot=UDP
+ [ $p == "U" ] && prot=UDP
+ [ $p == "i" ] && prot=ICMP
+ [ $p == "r" ] && prot=RAW
+
+ [ $ovr == "setsock" ] && m="-C"
+ [ $ovr == "cmsg" ] && m="-c"
+ [ $ovr == "both" ] && m="-C $((TOS2)) -c"
+ [ $ovr == "diff" ] && m="-C $((TOS )) -c"
+
+ $NSEXE nohup tcpdump --immediate-mode -p -ni dummy0 -w $TMPF -c 4 2> /dev/null &
+ BG=$!
+ sleep 0.05
+
+ $NSEXE ./cmsg_sender $IPVER -p $p $m $((TOS2)) $TGT 1234
+ check_result $? 0 "$MATCH $prot $ovr - pass"
+
+ while [ -d /proc/$BG ]; do
+ $NSEXE ./cmsg_sender $IPVER -p $p $m $((TOS2)) $TGT 1234
+ done
+
+ tcpdump -r $TMPF -v 2>&1 | grep "$MATCH $TOS2" >> /dev/null
+ check_result $? 0 "$MATCH $prot $ovr - packet data"
+ rm $TMPF
+
+ [ $ovr == "both" ] && m="-C $((TOS )) -c"
+ [ $ovr == "diff" ] && m="-C $((TOS2)) -c"
+
+ # Match prohibit rule: expect failure
+ $NSEXE ./cmsg_sender $IPVER -p $p $m $((TOS)) -s $TGT 1234
+ check_result $? 1 "$MATCH $prot $ovr - rejection"
+
+ # Match prohibit rule: IPv4 masks ECN: expect failure
+ if [[ "$IPVER" == "-4" ]]; then
+ $NSEXE ./cmsg_sender $IPVER -p $p $m "$((TOS | ECN))" -s $TGT 1234
+ check_result $? 1 "$MATCH $prot $ovr - rejection (ECN)"
+ fi
+ done
+ done
+}
+
+test_dscp -4 $TGT4 tos
+test_dscp -6 $TGT6 class
+
+# IP_TTL + IPV6_HOPLIMIT
+test_ttl_hoplimit() {
+ local -r IPVER=$1
+ local -r TGT=$2
+ local -r MATCH=$3
+
+ local -r LIM=4
+
+ for ovr in setsock cmsg both diff; do
+ for p in u U i r; do
+ [ $p == "u" ] && prot=UDP
+ [ $p == "U" ] && prot=UDP
+ [ $p == "i" ] && prot=ICMP
+ [ $p == "r" ] && prot=RAW
+
+ [ $ovr == "setsock" ] && m="-L"
+ [ $ovr == "cmsg" ] && m="-l"
+ [ $ovr == "both" ] && m="-L $LIM -l"
+ [ $ovr == "diff" ] && m="-L $((LIM + 1)) -l"
+
+ $NSEXE nohup tcpdump --immediate-mode -p -ni dummy0 -w $TMPF -c 4 2> /dev/null &
+ BG=$!
+ sleep 0.05
+
+ $NSEXE ./cmsg_sender $IPVER -p $p $m $LIM $TGT 1234
+ check_result $? 0 "$MATCH $prot $ovr - pass"
+
+ while [ -d /proc/$BG ]; do
+ $NSEXE ./cmsg_sender $IPVER -p $p $m $LIM $TGT 1234
+ done
+
+ tcpdump -r $TMPF -v 2>&1 | grep "$MATCH $LIM[^0-9]" >> /dev/null
+ check_result $? 0 "$MATCH $prot $ovr - packet data"
+ rm $TMPF
+ done
+ done
+}
+
+test_ttl_hoplimit -4 $TGT4 ttl
+test_ttl_hoplimit -6 $TGT6 hlim
+
+# IPV6 exthdr
+for p in u U i r; do
+ # Very basic "does it crash" test
+ for h in h d r; do
+ $NSEXE ./cmsg_sender -p $p -6 -H $h $TGT6 1234
+ check_result $? 0 "ExtHdr $prot $ovr - pass"
+ done
+done
+
+# Summary
+if [ $BAD -ne 0 ]; then
+ echo "FAIL - $BAD/$TOTAL cases failed"
+ exit 1
+else
+ echo "OK"
+ exit 0
+fi
diff --git a/tools/testing/selftests/net/cmsg_ipv6.sh b/tools/testing/selftests/net/cmsg_ipv6.sh
deleted file mode 100755
index 8bc23fb4c82b..000000000000
--- a/tools/testing/selftests/net/cmsg_ipv6.sh
+++ /dev/null
@@ -1,154 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-source lib.sh
-
-IP6=2001:db8:1::1/64
-TGT6=2001:db8:1::2
-TMPF=$(mktemp --suffix ".pcap")
-
-cleanup()
-{
- rm -f $TMPF
- cleanup_ns $NS
-}
-
-trap cleanup EXIT
-
-tcpdump -h | grep immediate-mode >> /dev/null
-if [ $? -ne 0 ]; then
- echo "SKIP - tcpdump with --immediate-mode option required"
- exit $ksft_skip
-fi
-
-# Namespaces
-setup_ns NS
-NSEXE="ip netns exec $NS"
-
-$NSEXE sysctl -w net.ipv4.ping_group_range='0 2147483647' > /dev/null
-
-# Connectivity
-ip -netns $NS link add type dummy
-ip -netns $NS link set dev dummy0 up
-ip -netns $NS addr add $IP6 dev dummy0
-
-# Test
-BAD=0
-TOTAL=0
-
-check_result() {
- ((TOTAL++))
- if [ $1 -ne $2 ]; then
- echo " Case $3 returned $1, expected $2"
- ((BAD++))
- fi
-}
-
-# IPV6_DONTFRAG
-for ovr in setsock cmsg both diff; do
- for df in 0 1; do
- for p in u i r; do
- [ $p == "u" ] && prot=UDP
- [ $p == "i" ] && prot=ICMP
- [ $p == "r" ] && prot=RAW
-
- [ $ovr == "setsock" ] && m="-F $df"
- [ $ovr == "cmsg" ] && m="-f $df"
- [ $ovr == "both" ] && m="-F $df -f $df"
- [ $ovr == "diff" ] && m="-F $((1 - df)) -f $df"
-
- $NSEXE ./cmsg_sender -s -S 2000 -6 -p $p $m $TGT6 1234
- check_result $? $df "DONTFRAG $prot $ovr"
- done
- done
-done
-
-# IPV6_TCLASS
-TOS=0x10
-TOS2=0x20
-
-ip -6 -netns $NS rule add tos $TOS lookup 300
-ip -6 -netns $NS route add table 300 prohibit any
-
-for ovr in setsock cmsg both diff; do
- for p in u i r; do
- [ $p == "u" ] && prot=UDP
- [ $p == "i" ] && prot=ICMP
- [ $p == "r" ] && prot=RAW
-
- [ $ovr == "setsock" ] && m="-C"
- [ $ovr == "cmsg" ] && m="-c"
- [ $ovr == "both" ] && m="-C $((TOS2)) -c"
- [ $ovr == "diff" ] && m="-C $((TOS )) -c"
-
- $NSEXE nohup tcpdump --immediate-mode -p -ni dummy0 -w $TMPF -c 4 2> /dev/null &
- BG=$!
- sleep 0.05
-
- $NSEXE ./cmsg_sender -6 -p $p $m $((TOS2)) $TGT6 1234
- check_result $? 0 "TCLASS $prot $ovr - pass"
-
- while [ -d /proc/$BG ]; do
- $NSEXE ./cmsg_sender -6 -p $p $m $((TOS2)) $TGT6 1234
- done
-
- tcpdump -r $TMPF -v 2>&1 | grep "class $TOS2" >> /dev/null
- check_result $? 0 "TCLASS $prot $ovr - packet data"
- rm $TMPF
-
- [ $ovr == "both" ] && m="-C $((TOS )) -c"
- [ $ovr == "diff" ] && m="-C $((TOS2)) -c"
-
- $NSEXE ./cmsg_sender -6 -p $p $m $((TOS)) -s $TGT6 1234
- check_result $? 1 "TCLASS $prot $ovr - rejection"
- done
-done
-
-# IPV6_HOPLIMIT
-LIM=4
-
-for ovr in setsock cmsg both diff; do
- for p in u i r; do
- [ $p == "u" ] && prot=UDP
- [ $p == "i" ] && prot=ICMP
- [ $p == "r" ] && prot=RAW
-
- [ $ovr == "setsock" ] && m="-L"
- [ $ovr == "cmsg" ] && m="-l"
- [ $ovr == "both" ] && m="-L $LIM -l"
- [ $ovr == "diff" ] && m="-L $((LIM + 1)) -l"
-
- $NSEXE nohup tcpdump --immediate-mode -p -ni dummy0 -w $TMPF -c 4 2> /dev/null &
- BG=$!
- sleep 0.05
-
- $NSEXE ./cmsg_sender -6 -p $p $m $LIM $TGT6 1234
- check_result $? 0 "HOPLIMIT $prot $ovr - pass"
-
- while [ -d /proc/$BG ]; do
- $NSEXE ./cmsg_sender -6 -p $p $m $LIM $TGT6 1234
- done
-
- tcpdump -r $TMPF -v 2>&1 | grep "hlim $LIM[^0-9]" >> /dev/null
- check_result $? 0 "HOPLIMIT $prot $ovr - packet data"
- rm $TMPF
- done
-done
-
-# IPV6 exthdr
-for p in u i r; do
- # Very basic "does it crash" test
- for h in h d r; do
- $NSEXE ./cmsg_sender -p $p -6 -H $h $TGT6 1234
- check_result $? 0 "ExtHdr $prot $ovr - pass"
- done
-done
-
-# Summary
-if [ $BAD -ne 0 ]; then
- echo "FAIL - $BAD/$TOTAL cases failed"
- exit 1
-else
- echo "OK"
- exit 0
-fi
diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c
index bc314382e4e1..a825e628aee7 100644
--- a/tools/testing/selftests/net/cmsg_sender.c
+++ b/tools/testing/selftests/net/cmsg_sender.c
@@ -33,6 +33,7 @@ enum {
ERN_RECVERR,
ERN_CMSG_RD,
ERN_CMSG_RCV,
+ ERN_SEND_MORE,
};
struct option_cmsg_u32 {
@@ -46,6 +47,7 @@ struct options {
const char *service;
unsigned int size;
unsigned int num_pkt;
+ bool msg_more;
struct {
unsigned int mark;
unsigned int dontfrag;
@@ -72,7 +74,7 @@ struct options {
struct option_cmsg_u32 tclass;
struct option_cmsg_u32 hlimit;
struct option_cmsg_u32 exthdr;
- } v6;
+ } cmsg;
} opt = {
.size = 13,
.num_pkt = 1,
@@ -94,7 +96,8 @@ static void __attribute__((noreturn)) cs_usage(const char *bin)
"\t\t-S send() size\n"
"\t\t-4/-6 Force IPv4 / IPv6 only\n"
"\t\t-p prot Socket protocol\n"
- "\t\t (u = UDP (default); i = ICMP; r = RAW)\n"
+ "\t\t (u = UDP (default); i = ICMP; r = RAW;\n"
+ "\t\t U = UDP with MSG_MORE)\n"
"\n"
"\t\t-m val Set SO_MARK with given value\n"
"\t\t-M val Set SO_MARK via setsockopt\n"
@@ -104,13 +107,13 @@ static void __attribute__((noreturn)) cs_usage(const char *bin)
"\t\t-t Enable time stamp reporting\n"
"\t\t-f val Set don't fragment via cmsg\n"
"\t\t-F val Set don't fragment via setsockopt\n"
- "\t\t-c val Set TCLASS via cmsg\n"
- "\t\t-C val Set TCLASS via setsockopt\n"
- "\t\t-l val Set HOPLIMIT via cmsg\n"
- "\t\t-L val Set HOPLIMIT via setsockopt\n"
+ "\t\t-c val Set TOS/TCLASS via cmsg\n"
+ "\t\t-C val Set TOS/TCLASS via setsockopt\n"
+ "\t\t-l val Set TTL/HOPLIMIT via cmsg\n"
+ "\t\t-L val Set TTL/HOPLIMIT via setsockopt\n"
"\t\t-H type Add an IPv6 header option\n"
- "\t\t (h = HOP; d = DST; r = RTDST)"
- "");
+ "\t\t (h = HOP; d = DST; r = RTDST)\n"
+ "\n");
exit(ERN_HELP);
}
@@ -133,8 +136,11 @@ static void cs_parse_args(int argc, char *argv[])
opt.sock.family = AF_INET6;
break;
case 'p':
- if (*optarg == 'u' || *optarg == 'U') {
+ if (*optarg == 'u') {
opt.sock.proto = IPPROTO_UDP;
+ } else if (*optarg == 'U') {
+ opt.sock.proto = IPPROTO_UDP;
+ opt.msg_more = true;
} else if (*optarg == 'i' || *optarg == 'I') {
opt.sock.proto = IPPROTO_ICMP;
} else if (*optarg == 'r') {
@@ -169,37 +175,37 @@ static void cs_parse_args(int argc, char *argv[])
opt.ts.ena = true;
break;
case 'f':
- opt.v6.dontfrag.ena = true;
- opt.v6.dontfrag.val = atoi(optarg);
+ opt.cmsg.dontfrag.ena = true;
+ opt.cmsg.dontfrag.val = atoi(optarg);
break;
case 'F':
opt.sockopt.dontfrag = atoi(optarg);
break;
case 'c':
- opt.v6.tclass.ena = true;
- opt.v6.tclass.val = atoi(optarg);
+ opt.cmsg.tclass.ena = true;
+ opt.cmsg.tclass.val = atoi(optarg);
break;
case 'C':
opt.sockopt.tclass = atoi(optarg);
break;
case 'l':
- opt.v6.hlimit.ena = true;
- opt.v6.hlimit.val = atoi(optarg);
+ opt.cmsg.hlimit.ena = true;
+ opt.cmsg.hlimit.val = atoi(optarg);
break;
case 'L':
opt.sockopt.hlimit = atoi(optarg);
break;
case 'H':
- opt.v6.exthdr.ena = true;
+ opt.cmsg.exthdr.ena = true;
switch (optarg[0]) {
case 'h':
- opt.v6.exthdr.val = IPV6_HOPOPTS;
+ opt.cmsg.exthdr.val = IPV6_HOPOPTS;
break;
case 'd':
- opt.v6.exthdr.val = IPV6_DSTOPTS;
+ opt.cmsg.exthdr.val = IPV6_DSTOPTS;
break;
case 'r':
- opt.v6.exthdr.val = IPV6_RTHDRDSTOPTS;
+ opt.cmsg.exthdr.val = IPV6_RTHDRDSTOPTS;
break;
default:
printf("Error: hdr type: %s\n", optarg);
@@ -261,12 +267,20 @@ cs_write_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz)
SOL_SOCKET, SO_MARK, &opt.mark);
ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
SOL_SOCKET, SO_PRIORITY, &opt.priority);
- ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
- SOL_IPV6, IPV6_DONTFRAG, &opt.v6.dontfrag);
- ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
- SOL_IPV6, IPV6_TCLASS, &opt.v6.tclass);
- ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
- SOL_IPV6, IPV6_HOPLIMIT, &opt.v6.hlimit);
+
+ if (opt.sock.family == AF_INET) {
+ ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
+ SOL_IP, IP_TOS, &opt.cmsg.tclass);
+ ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
+ SOL_IP, IP_TTL, &opt.cmsg.hlimit);
+ } else {
+ ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
+ SOL_IPV6, IPV6_DONTFRAG, &opt.cmsg.dontfrag);
+ ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
+ SOL_IPV6, IPV6_TCLASS, &opt.cmsg.tclass);
+ ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
+ SOL_IPV6, IPV6_HOPLIMIT, &opt.cmsg.hlimit);
+ }
if (opt.txtime.ena) {
__u64 txtime;
@@ -297,14 +311,14 @@ cs_write_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz)
*(__u32 *)CMSG_DATA(cmsg) = SOF_TIMESTAMPING_TX_SCHED |
SOF_TIMESTAMPING_TX_SOFTWARE;
}
- if (opt.v6.exthdr.ena) {
+ if (opt.cmsg.exthdr.ena) {
cmsg = (struct cmsghdr *)(cbuf + cmsg_len);
cmsg_len += CMSG_SPACE(8);
if (cbuf_sz < cmsg_len)
error(ERN_CMSG_WR, EFAULT, "cmsg buffer too small");
cmsg->cmsg_level = SOL_IPV6;
- cmsg->cmsg_type = opt.v6.exthdr.val;
+ cmsg->cmsg_type = opt.cmsg.exthdr.val;
cmsg->cmsg_len = CMSG_LEN(8);
*(__u64 *)CMSG_DATA(cmsg) = 0;
}
@@ -405,23 +419,35 @@ static void ca_set_sockopts(int fd)
setsockopt(fd, SOL_SOCKET, SO_MARK,
&opt.sockopt.mark, sizeof(opt.sockopt.mark)))
error(ERN_SOCKOPT, errno, "setsockopt SO_MARK");
- if (opt.sockopt.dontfrag &&
- setsockopt(fd, SOL_IPV6, IPV6_DONTFRAG,
- &opt.sockopt.dontfrag, sizeof(opt.sockopt.dontfrag)))
- error(ERN_SOCKOPT, errno, "setsockopt IPV6_DONTFRAG");
- if (opt.sockopt.tclass &&
- setsockopt(fd, SOL_IPV6, IPV6_TCLASS,
- &opt.sockopt.tclass, sizeof(opt.sockopt.tclass)))
- error(ERN_SOCKOPT, errno, "setsockopt IPV6_TCLASS");
- if (opt.sockopt.hlimit &&
- setsockopt(fd, SOL_IPV6, IPV6_UNICAST_HOPS,
- &opt.sockopt.hlimit, sizeof(opt.sockopt.hlimit)))
- error(ERN_SOCKOPT, errno, "setsockopt IPV6_HOPLIMIT");
if (opt.sockopt.priority &&
setsockopt(fd, SOL_SOCKET, SO_PRIORITY,
&opt.sockopt.priority, sizeof(opt.sockopt.priority)))
error(ERN_SOCKOPT, errno, "setsockopt SO_PRIORITY");
+ if (opt.sock.family == AF_INET) {
+ if (opt.sockopt.tclass &&
+ setsockopt(fd, SOL_IP, IP_TOS,
+ &opt.sockopt.tclass, sizeof(opt.sockopt.tclass)))
+ error(ERN_SOCKOPT, errno, "setsockopt IP_TOS");
+ if (opt.sockopt.hlimit &&
+ setsockopt(fd, SOL_IP, IP_TTL,
+ &opt.sockopt.hlimit, sizeof(opt.sockopt.hlimit)))
+ error(ERN_SOCKOPT, errno, "setsockopt IP_TTL");
+ } else {
+ if (opt.sockopt.dontfrag &&
+ setsockopt(fd, SOL_IPV6, IPV6_DONTFRAG,
+ &opt.sockopt.dontfrag, sizeof(opt.sockopt.dontfrag)))
+ error(ERN_SOCKOPT, errno, "setsockopt IPV6_DONTFRAG");
+ if (opt.sockopt.tclass &&
+ setsockopt(fd, SOL_IPV6, IPV6_TCLASS,
+ &opt.sockopt.tclass, sizeof(opt.sockopt.tclass)))
+ error(ERN_SOCKOPT, errno, "setsockopt IPV6_TCLASS");
+ if (opt.sockopt.hlimit &&
+ setsockopt(fd, SOL_IPV6, IPV6_UNICAST_HOPS,
+ &opt.sockopt.hlimit, sizeof(opt.sockopt.hlimit)))
+ error(ERN_SOCKOPT, errno, "setsockopt IPV6_HOPLIMIT");
+ }
+
if (opt.txtime.ena) {
struct sock_txtime so_txtime = {
.clockid = CLOCK_MONOTONIC,
@@ -511,7 +537,7 @@ int main(int argc, char *argv[])
cs_write_cmsg(fd, &msg, cbuf, sizeof(cbuf));
for (i = 0; i < opt.num_pkt; i++) {
- err = sendmsg(fd, &msg, 0);
+ err = sendmsg(fd, &msg, opt.msg_more ? MSG_MORE : 0);
if (err < 0) {
if (!opt.silent_send)
fprintf(stderr, "send failed: %s\n", strerror(errno));
@@ -522,6 +548,14 @@ int main(int argc, char *argv[])
err = ERN_SEND_SHORT;
goto err_out;
}
+ if (opt.msg_more) {
+ err = write(fd, NULL, 0);
+ if (err < 0) {
+ fprintf(stderr, "send more: %s\n", strerror(errno));
+ err = ERN_SEND_MORE;
+ goto err_out;
+ }
+ }
}
err = ERN_SUCCESS;
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 61e5116987f3..3cfef5153823 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -18,6 +18,8 @@ CONFIG_DUMMY=y
CONFIG_BRIDGE_VLAN_FILTERING=y
CONFIG_BRIDGE=y
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_DEBUG_INFO_BTF=y
+CONFIG_DEBUG_INFO_BTF_MODULES=n
CONFIG_VLAN_8021Q=y
CONFIG_GENEVE=m
CONFIG_IFB=y
@@ -31,7 +33,6 @@ CONFIG_NETFILTER_ADVANCED=y
CONFIG_NF_CONNTRACK=m
CONFIG_IPV6_MROUTE=y
CONFIG_IPV6_SIT=y
-CONFIG_IP_DCCP=m
CONFIG_NF_NAT=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP_NF_IPTABLES=m
@@ -107,5 +108,11 @@ CONFIG_XFRM_INTERFACE=m
CONFIG_XFRM_USER=m
CONFIG_IP_NF_MATCH_RPFILTER=m
CONFIG_IP6_NF_MATCH_RPFILTER=m
+CONFIG_IPVLAN=m
+CONFIG_CAN=m
+CONFIG_CAN_DEV=m
+CONFIG_CAN_VXCAN=m
+CONFIG_NETKIT=y
+CONFIG_NET_PKTGEN=m
CONFIG_IPV6_ILA=m
CONFIG_IPV6_RPL_LWTUNNEL=y
diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index 899dbad0104b..4fcc38907e48 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -3667,7 +3667,7 @@ ipv6_addr_bind_novrf()
# when it really should not
a=${NSA_LO_IP6}
log_start
- show_hint "Tecnically should fail since address is not on device but kernel allows"
+ show_hint "Technically should fail since address is not on device but kernel allows"
run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b
log_test_addr ${a} $? 0 "TCP socket bind to out of scope local address"
}
@@ -3724,7 +3724,7 @@ ipv6_addr_bind_vrf()
# passes when it really should not
a=${VRF_IP6}
log_start
- show_hint "Tecnically should fail since address is not on device but kernel allows"
+ show_hint "Technically should fail since address is not on device but kernel allows"
run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b
log_test_addr ${a} $? 0 "TCP socket bind to VRF address with device bind"
diff --git a/tools/testing/selftests/net/fdb_flush.sh b/tools/testing/selftests/net/fdb_flush.sh
index d5e3abb8658c..9931a1e36e3d 100755
--- a/tools/testing/selftests/net/fdb_flush.sh
+++ b/tools/testing/selftests/net/fdb_flush.sh
@@ -583,7 +583,7 @@ vxlan_test_flush_by_remote_attributes()
$IP link del dev vx10
$IP link add name vx10 type vxlan dstport "$VXPORT" external
- # For multicat FDB entries, the VXLAN driver stores a linked list of
+ # For multicast FDB entries, the VXLAN driver stores a linked list of
# remotes for a given key. Verify that only the expected remotes are
# flushed.
multicast_fdb_entries_add
diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index 77c83d9508d3..b39f748c2572 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -76,11 +76,13 @@ log_test()
printf "TEST: %-60s [ OK ]\n" "${msg}"
nsuccess=$((nsuccess+1))
else
- ret=1
- nfail=$((nfail+1))
if [[ $rc -eq $ksft_skip ]]; then
+ [[ $ret -eq 0 ]] && ret=$ksft_skip
+ nskip=$((nskip+1))
printf "TEST: %-60s [SKIP]\n" "${msg}"
else
+ ret=1
+ nfail=$((nfail+1))
printf "TEST: %-60s [FAIL]\n" "${msg}"
fi
@@ -741,7 +743,7 @@ ipv6_fcnal()
run_cmd "$IP nexthop add id 52 via 2001:db8:92::3"
log_test $? 2 "Create nexthop - gw only"
- # gw is not reachable throught given dev
+ # gw is not reachable through given dev
run_cmd "$IP nexthop add id 53 via 2001:db8:3::3 dev veth1"
log_test $? 2 "Create nexthop - invalid gw+dev combination"
@@ -2528,6 +2530,7 @@ done
if [ "$TESTS" != "none" ]; then
printf "\nTests passed: %3d\n" ${nsuccess}
printf "Tests failed: %3d\n" ${nfail}
+ printf "Tests skipped: %2d\n" ${nskip}
fi
exit $ret
diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index 847936363a12..5fbdd2a0b537 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -256,6 +256,24 @@ fib_rule6_test()
fib_rule6_test_match_n_redirect "$match" "$match" \
"$getnomatch" "sport and dport redirect to table" \
"sport and dport no redirect to table"
+
+ match="sport 100-200 dport 300-400"
+ getmatch="sport 100 dport 400"
+ getnomatch="sport 100 dport 401"
+ fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" \
+ "sport and dport range redirect to table" \
+ "sport and dport range no redirect to table"
+ fi
+
+ ip rule help 2>&1 | grep sport | grep -q MASK
+ if [ $? -eq 0 ]; then
+ match="sport 0x0f00/0xff00 dport 0x000f/0x00ff"
+ getmatch="sport 0x0f11 dport 0x220f"
+ getnomatch="sport 0x1f11 dport 0x221f"
+ fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "sport and dport masked redirect to table" \
+ "sport and dport masked no redirect to table"
fi
fib_check_iproute_support "ipproto" "ipproto"
@@ -292,6 +310,25 @@ fib_rule6_test()
"iif dscp no redirect to table"
fi
+ ip rule help 2>&1 | grep -q "DSCP\[/MASK\]"
+ if [ $? -eq 0 ]; then
+ match="dscp 0x0f/0x0f"
+ tosmatch=$(printf 0x"%x" $((0x1f << 2)))
+ tosnomatch=$(printf 0x"%x" $((0x1e << 2)))
+ getmatch="tos $tosmatch"
+ getnomatch="tos $tosnomatch"
+ fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "dscp masked redirect to table" \
+ "dscp masked no redirect to table"
+
+ match="dscp 0x0f/0x0f"
+ getmatch="from $SRC_IP6 iif $DEV tos $tosmatch"
+ getnomatch="from $SRC_IP6 iif $DEV tos $tosnomatch"
+ fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "iif dscp masked redirect to table" \
+ "iif dscp masked no redirect to table"
+ fi
+
fib_check_iproute_support "flowlabel" "flowlabel"
if [ $? -eq 0 ]; then
match="flowlabel 0xfffff"
@@ -322,6 +359,23 @@ fib_rule6_test()
"$getnomatch" "iif flowlabel masked redirect to table" \
"iif flowlabel masked no redirect to table"
fi
+
+ $IP link show dev $DEV | grep -q vrf0
+ if [ $? -eq 0 ]; then
+ match="oif vrf0"
+ getmatch="oif $DEV"
+ getnomatch="oif lo"
+ fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "VRF oif redirect to table" \
+ "VRF oif no redirect to table"
+
+ match="from $SRC_IP6 iif vrf0"
+ getmatch="from $SRC_IP6 iif $DEV"
+ getnomatch="from $SRC_IP6 iif lo"
+ fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "VRF iif redirect to table" \
+ "VRF iif no redirect to table"
+ fi
}
fib_rule6_vrf_test()
@@ -462,10 +516,7 @@ fib_rule4_test()
fib_rule4_test_match_n_redirect "$match" "$match" "$getnomatch" \
"oif redirect to table" "oif no redirect to table"
- # Enable forwarding and disable rp_filter as all the addresses are in
- # the same subnet and egress device == ingress device.
ip netns exec $testns sysctl -qw net.ipv4.ip_forward=1
- ip netns exec $testns sysctl -qw net.ipv4.conf.$DEV.rp_filter=0
match="from $SRC_IP iif $DEV"
getnomatch="from $SRC_IP iif lo"
fib_rule4_test_match_n_redirect "$match" "$match" "$getnomatch" \
@@ -525,6 +576,24 @@ fib_rule4_test()
fib_rule4_test_match_n_redirect "$match" "$match" \
"$getnomatch" "sport and dport redirect to table" \
"sport and dport no redirect to table"
+
+ match="sport 100-200 dport 300-400"
+ getmatch="sport 100 dport 400"
+ getnomatch="sport 100 dport 401"
+ fib_rule4_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" \
+ "sport and dport range redirect to table" \
+ "sport and dport range no redirect to table"
+ fi
+
+ ip rule help 2>&1 | grep sport | grep -q MASK
+ if [ $? -eq 0 ]; then
+ match="sport 0x0f00/0xff00 dport 0x000f/0x00ff"
+ getmatch="sport 0x0f11 dport 0x220f"
+ getnomatch="sport 0x1f11 dport 0x221f"
+ fib_rule4_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "sport and dport masked redirect to table" \
+ "sport and dport masked no redirect to table"
fi
fib_check_iproute_support "ipproto" "ipproto"
@@ -561,6 +630,42 @@ fib_rule4_test()
"$getnomatch" "iif dscp redirect to table" \
"iif dscp no redirect to table"
fi
+
+ ip rule help 2>&1 | grep -q "DSCP\[/MASK\]"
+ if [ $? -eq 0 ]; then
+ match="dscp 0x0f/0x0f"
+ tosmatch=$(printf 0x"%x" $((0x1f << 2)))
+ tosnomatch=$(printf 0x"%x" $((0x1e << 2)))
+ getmatch="tos $tosmatch"
+ getnomatch="tos $tosnomatch"
+ fib_rule4_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "dscp masked redirect to table" \
+ "dscp masked no redirect to table"
+
+ match="dscp 0x0f/0x0f"
+ getmatch="from $SRC_IP iif $DEV tos $tosmatch"
+ getnomatch="from $SRC_IP iif $DEV tos $tosnomatch"
+ fib_rule4_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "iif dscp masked redirect to table" \
+ "iif dscp masked no redirect to table"
+ fi
+
+ $IP link show dev $DEV | grep -q vrf0
+ if [ $? -eq 0 ]; then
+ match="oif vrf0"
+ getmatch="oif $DEV"
+ getnomatch="oif lo"
+ fib_rule4_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "VRF oif redirect to table" \
+ "VRF oif no redirect to table"
+
+ match="from $SRC_IP iif vrf0"
+ getmatch="from $SRC_IP iif $DEV"
+ getnomatch="from $SRC_IP iif lo"
+ fib_rule4_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "VRF iif redirect to table" \
+ "VRF iif no redirect to table"
+ fi
}
fib_rule4_vrf_test()
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 3ea6f886a210..a94b73a53f72 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -11,7 +11,7 @@ TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify \
ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics \
ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr \
ipv6_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh fib6_gc_test \
- ipv4_mpath_list ipv6_mpath_list"
+ ipv4_mpath_list ipv6_mpath_list ipv4_mpath_balance ipv6_mpath_balance"
VERBOSE=0
PAUSE_ON_FAIL=no
@@ -1085,6 +1085,35 @@ route_setup()
set +e
}
+forwarding_cleanup()
+{
+ cleanup_ns $ns3
+
+ route_cleanup
+}
+
+# extend route_setup with an ns3 reachable through ns2 over both devices
+forwarding_setup()
+{
+ forwarding_cleanup
+
+ route_setup
+
+ setup_ns ns3
+
+ ip link add veth5 netns $ns3 type veth peer name veth6 netns $ns2
+ ip -netns $ns3 link set veth5 up
+ ip -netns $ns2 link set veth6 up
+
+ ip -netns $ns3 -4 addr add dev veth5 172.16.105.1/24
+ ip -netns $ns2 -4 addr add dev veth6 172.16.105.2/24
+ ip -netns $ns3 -4 route add 172.16.100.0/22 via 172.16.105.2
+
+ ip -netns $ns3 -6 addr add dev veth5 2001:db8:105::1/64 nodad
+ ip -netns $ns2 -6 addr add dev veth6 2001:db8:105::2/64 nodad
+ ip -netns $ns3 -6 route add 2001:db8:101::/33 via 2001:db8:105::2
+}
+
# assumption is that basic add of a single path route works
# otherwise just adding an address on an interface is broken
ipv6_rt_add()
@@ -2531,9 +2560,6 @@ ipv4_mpath_list_test()
run_cmd "ip -n $ns2 route add 203.0.113.0/24
nexthop via 172.16.201.2 nexthop via 172.16.202.2"
run_cmd "ip netns exec $ns2 sysctl -qw net.ipv4.fib_multipath_hash_policy=1"
- run_cmd "ip netns exec $ns2 sysctl -qw net.ipv4.conf.veth2.rp_filter=0"
- run_cmd "ip netns exec $ns2 sysctl -qw net.ipv4.conf.all.rp_filter=0"
- run_cmd "ip netns exec $ns2 sysctl -qw net.ipv4.conf.default.rp_filter=0"
set +e
local dmac=$(ip -n $ns2 -j link show dev veth2 | jq -r '.[]["address"]')
@@ -2600,6 +2626,93 @@ ipv6_mpath_list_test()
route_cleanup
}
+tc_set_flower_counter__saddr_syn() {
+ tc_set_flower_counter $1 $2 $3 "src_ip $4 ip_proto tcp tcp_flags 0x2"
+}
+
+ip_mpath_balance_dep_check()
+{
+ if [ ! -x "$(command -v socat)" ]; then
+ echo "socat command not found. Skipping test"
+ return 1
+ fi
+
+ if [ ! -x "$(command -v jq)" ]; then
+ echo "jq command not found. Skipping test"
+ return 1
+ fi
+}
+
+ip_mpath_balance() {
+ local -r ipver=$1
+ local -r daddr=$2
+ local -r num_conn=20
+
+ for i in $(seq 1 $num_conn); do
+ ip netns exec $ns3 socat $ipver TCP-LISTEN:8000 STDIO >/dev/null &
+ sleep 0.02
+ echo -n a | ip netns exec $ns1 socat $ipver STDIO TCP:$daddr:8000
+ done
+
+ local -r syn0="$(tc_get_flower_counter $ns1 veth1)"
+ local -r syn1="$(tc_get_flower_counter $ns1 veth3)"
+ local -r syns=$((syn0+syn1))
+
+ [ "$VERBOSE" = "1" ] && echo "multipath: syns seen: ($syn0,$syn1)"
+
+ [[ $syns -ge $num_conn ]] && [[ $syn0 -gt 0 ]] && [[ $syn1 -gt 0 ]]
+}
+
+ipv4_mpath_balance_test()
+{
+ echo
+ echo "IPv4 multipath load balance test"
+
+ ip_mpath_balance_dep_check || return 1
+ forwarding_setup
+
+ $IP route add 172.16.105.1 \
+ nexthop via 172.16.101.2 \
+ nexthop via 172.16.103.2
+
+ ip netns exec $ns1 \
+ sysctl -q -w net.ipv4.fib_multipath_hash_policy=1
+
+ tc_set_flower_counter__saddr_syn $ns1 4 veth1 172.16.101.1
+ tc_set_flower_counter__saddr_syn $ns1 4 veth3 172.16.103.1
+
+ ip_mpath_balance -4 172.16.105.1
+
+ log_test $? 0 "IPv4 multipath loadbalance"
+
+ forwarding_cleanup
+}
+
+ipv6_mpath_balance_test()
+{
+ echo
+ echo "IPv6 multipath load balance test"
+
+ ip_mpath_balance_dep_check || return 1
+ forwarding_setup
+
+ $IP route add 2001:db8:105::1\
+ nexthop via 2001:db8:101::2 \
+ nexthop via 2001:db8:103::2
+
+ ip netns exec $ns1 \
+ sysctl -q -w net.ipv6.fib_multipath_hash_policy=1
+
+ tc_set_flower_counter__saddr_syn $ns1 6 veth1 2001:db8:101::1
+ tc_set_flower_counter__saddr_syn $ns1 6 veth3 2001:db8:103::1
+
+ ip_mpath_balance -6 "[2001:db8:105::1]"
+
+ log_test $? 0 "IPv6 multipath loadbalance"
+
+ forwarding_cleanup
+}
+
################################################################################
# usage
@@ -2683,6 +2796,8 @@ do
fib6_gc_test|ipv6_gc) fib6_gc_test;;
ipv4_mpath_list) ipv4_mpath_list_test;;
ipv6_mpath_list) ipv6_mpath_list_test;;
+ ipv4_mpath_balance) ipv4_mpath_balance_test;;
+ ipv6_mpath_balance) ipv6_mpath_balance_test;;
help) echo "Test names: $TESTS"; exit 0;;
esac
diff --git a/tools/testing/selftests/net/forwarding/README b/tools/testing/selftests/net/forwarding/README
index a652429bfd53..7b41cff993ad 100644
--- a/tools/testing/selftests/net/forwarding/README
+++ b/tools/testing/selftests/net/forwarding/README
@@ -6,7 +6,7 @@ to easily create and test complex environments.
Unfortunately, these namespaces can not be used with actual switching
ASICs, as their ports can not be migrated to other network namespaces
-(dev->netns_local) and most of them probably do not support the
+(dev->netns_immutable) and most of them probably do not support the
L1-separation provided by namespaces.
However, a similar kind of flexibility can be achieved by using VRFs and
diff --git a/tools/testing/selftests/net/forwarding/bridge_igmp.sh b/tools/testing/selftests/net/forwarding/bridge_igmp.sh
index e6a3e04fd83f..d4e7dd659354 100755
--- a/tools/testing/selftests/net/forwarding/bridge_igmp.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_igmp.sh
@@ -1,10 +1,24 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
-ALL_TESTS="v2reportleave_test v3include_test v3inc_allow_test v3inc_is_include_test \
- v3inc_is_exclude_test v3inc_to_exclude_test v3exc_allow_test v3exc_is_include_test \
- v3exc_is_exclude_test v3exc_to_exclude_test v3inc_block_test v3exc_block_test \
- v3exc_timeout_test v3star_ex_auto_add_test"
+ALL_TESTS="
+ v2reportleave_test
+ v3include_test
+ v3inc_allow_test
+ v3inc_is_include_test
+ v3inc_is_exclude_test
+ v3inc_to_exclude_test
+ v3exc_allow_test
+ v3exc_is_include_test
+ v3exc_is_exclude_test
+ v3exc_to_exclude_test
+ v3inc_block_test
+ v3exc_block_test
+ v3exc_timeout_test
+ v3star_ex_auto_add_test
+ v2per_vlan_snooping_port_stp_test
+ v2per_vlan_snooping_vlan_stp_test
+"
NUM_NETIFS=4
CHECK_TC="yes"
TEST_GROUP="239.10.10.10"
@@ -554,6 +568,64 @@ v3star_ex_auto_add_test()
v3cleanup $swp2 $TEST_GROUP
}
+v2per_vlan_snooping_stp_test()
+{
+ local is_port=$1
+
+ local msg="port"
+ [[ $is_port -ne 1 ]] && msg="vlan"
+
+ ip link set br0 up type bridge vlan_filtering 1 \
+ mcast_igmp_version 2 \
+ mcast_snooping 1 \
+ mcast_vlan_snooping 1 \
+ mcast_querier 1 \
+ mcast_stats_enabled 1
+ bridge vlan global set vid 1 dev br0 \
+ mcast_snooping 1 \
+ mcast_querier 1 \
+ mcast_query_interval 100 \
+ mcast_startup_query_count 0
+ [[ $is_port -eq 1 ]] && bridge link set dev $swp1 state 0
+ [[ $is_port -ne 1 ]] && bridge vlan set vid 1 dev $swp1 state 4
+ sleep 5
+ local tx_s=$(ip -j -p stats show dev $swp1 \
+ group xstats_slave subgroup bridge suite mcast \
+ | jq '.[]["multicast"]["igmp_queries"]["tx_v2"]')
+
+ [[ $is_port -eq 1 ]] && bridge link set dev $swp1 state 3
+ [[ $is_port -ne 1 ]] && bridge vlan set vid 1 dev $swp1 state 3
+ sleep 5
+ local tx_e=$(ip -j -p stats show dev $swp1 \
+ group xstats_slave subgroup bridge suite mcast \
+ | jq '.[]["multicast"]["igmp_queries"]["tx_v2"]')
+
+ RET=0
+ local tx=$(expr $tx_e - $tx_s)
+ test $tx -gt 0
+ check_err $? "No IGMP queries after STP state becomes forwarding"
+ log_test "per vlan snooping with $msg stp state change"
+
+ # restore settings
+ bridge vlan global set vid 1 dev br0 \
+ mcast_querier 0 \
+ mcast_query_interval 12500 \
+ mcast_startup_query_count 2
+ ip link set br0 up type bridge vlan_filtering 0 \
+ mcast_vlan_snooping 0 \
+ mcast_stats_enabled 0
+}
+
+v2per_vlan_snooping_port_stp_test()
+{
+ v2per_vlan_snooping_stp_test 1
+}
+
+v2per_vlan_snooping_vlan_stp_test()
+{
+ v2per_vlan_snooping_stp_test 0
+}
+
trap cleanup EXIT
setup_prepare
diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh
index d9d587454d20..8c1597ebc2d3 100755
--- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh
@@ -149,7 +149,7 @@ cfg_test_host_common()
check_err $? "Failed to add $name host entry"
bridge mdb replace dev br0 port br0 grp $grp $state vid 10 &> /dev/null
- check_fail $? "Managed to replace $name host entry"
+ check_err $? "Failed to replace $name host entry"
bridge mdb del dev br0 port br0 grp $grp $state vid 10
bridge mdb get dev br0 grp $grp vid 10 &> /dev/null
diff --git a/tools/testing/selftests/net/forwarding/bridge_mld.sh b/tools/testing/selftests/net/forwarding/bridge_mld.sh
index f84ab2e65754..4cacef5a813a 100755
--- a/tools/testing/selftests/net/forwarding/bridge_mld.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_mld.sh
@@ -1,10 +1,23 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
-ALL_TESTS="mldv2include_test mldv2inc_allow_test mldv2inc_is_include_test mldv2inc_is_exclude_test \
- mldv2inc_to_exclude_test mldv2exc_allow_test mldv2exc_is_include_test \
- mldv2exc_is_exclude_test mldv2exc_to_exclude_test mldv2inc_block_test \
- mldv2exc_block_test mldv2exc_timeout_test mldv2star_ex_auto_add_test"
+ALL_TESTS="
+ mldv2include_test
+ mldv2inc_allow_test
+ mldv2inc_is_include_test
+ mldv2inc_is_exclude_test
+ mldv2inc_to_exclude_test
+ mldv2exc_allow_test
+ mldv2exc_is_include_test
+ mldv2exc_is_exclude_test
+ mldv2exc_to_exclude_test
+ mldv2inc_block_test
+ mldv2exc_block_test
+ mldv2exc_timeout_test
+ mldv2star_ex_auto_add_test
+ mldv2per_vlan_snooping_port_stp_test
+ mldv2per_vlan_snooping_vlan_stp_test
+"
NUM_NETIFS=4
CHECK_TC="yes"
TEST_GROUP="ff02::cc"
@@ -554,6 +567,66 @@ mldv2star_ex_auto_add_test()
mldv2cleanup $swp2
}
+mldv2per_vlan_snooping_stp_test()
+{
+ local is_port=$1
+
+ local msg="port"
+ [[ $is_port -ne 1 ]] && msg="vlan"
+
+ ip link set br0 up type bridge vlan_filtering 1 \
+ mcast_mld_version 2 \
+ mcast_snooping 1 \
+ mcast_vlan_snooping 1 \
+ mcast_querier 1 \
+ mcast_stats_enabled 1
+ bridge vlan global set vid 1 dev br0 \
+ mcast_mld_version 2 \
+ mcast_snooping 1 \
+ mcast_querier 1 \
+ mcast_query_interval 100 \
+ mcast_startup_query_count 0
+
+ [[ $is_port -eq 1 ]] && bridge link set dev $swp1 state 0
+ [[ $is_port -ne 1 ]] && bridge vlan set vid 1 dev $swp1 state 4
+ sleep 5
+ local tx_s=$(ip -j -p stats show dev $swp1 \
+ group xstats_slave subgroup bridge suite mcast \
+ | jq '.[]["multicast"]["mld_queries"]["tx_v2"]')
+ [[ $is_port -eq 1 ]] && bridge link set dev $swp1 state 3
+ [[ $is_port -ne 1 ]] && bridge vlan set vid 1 dev $swp1 state 3
+ sleep 5
+ local tx_e=$(ip -j -p stats show dev $swp1 \
+ group xstats_slave subgroup bridge suite mcast \
+ | jq '.[]["multicast"]["mld_queries"]["tx_v2"]')
+
+ RET=0
+ local tx=$(expr $tx_e - $tx_s)
+ test $tx -gt 0
+ check_err $? "No MLD queries after STP state becomes forwarding"
+ log_test "per vlan snooping with $msg stp state change"
+
+ # restore settings
+ bridge vlan global set vid 1 dev br0 \
+ mcast_querier 0 \
+ mcast_query_interval 12500 \
+ mcast_startup_query_count 2 \
+ mcast_mld_version 1
+ ip link set br0 up type bridge vlan_filtering 0 \
+ mcast_vlan_snooping 0 \
+ mcast_stats_enabled 0
+}
+
+mldv2per_vlan_snooping_port_stp_test()
+{
+ mldv2per_vlan_snooping_stp_test 1
+}
+
+mldv2per_vlan_snooping_vlan_stp_test()
+{
+ mldv2per_vlan_snooping_stp_test 0
+}
+
trap cleanup EXIT
setup_prepare
diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
index 90f8a244ea90..e59fba366a0a 100755
--- a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
@@ -1,7 +1,7 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
-ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion extern_learn other_tpid"
+ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion extern_learn other_tpid 8021p drop_untagged"
NUM_NETIFS=4
CHECK_TC="yes"
source lib.sh
@@ -194,6 +194,100 @@ other_tpid()
tc qdisc del dev $h2 clsact
}
+8021p_do()
+{
+ local should_fail=$1; shift
+ local mac=de:ad:be:ef:13:37
+
+ tc filter add dev $h2 ingress protocol all pref 1 handle 101 \
+ flower dst_mac $mac action drop
+
+ $MZ -q $h1 -c 1 -b $mac -a own "81:00 00:00 08:00 aa-aa-aa-aa-aa-aa-aa-aa-aa"
+ sleep 1
+
+ tc -j -s filter show dev $h2 ingress \
+ | jq -e ".[] | select(.options.handle == 101) \
+ | select(.options.actions[0].stats.packets == 1)" &> /dev/null
+ check_err_fail $should_fail $? "802.1p-tagged reception"
+
+ tc filter del dev $h2 ingress pref 1
+}
+
+8021p()
+{
+ RET=0
+
+ tc qdisc add dev $h2 clsact
+ ip link set $h2 promisc on
+
+ # Test that with the default_pvid, 1, packets tagged with VID 0 are
+ # accepted.
+ 8021p_do 0
+
+ # Test that packets tagged with VID 0 are still accepted after changing
+ # the default_pvid.
+ ip link set br0 type bridge vlan_default_pvid 10
+ 8021p_do 0
+
+ log_test "Reception of 802.1p-tagged traffic"
+
+ ip link set $h2 promisc off
+ tc qdisc del dev $h2 clsact
+}
+
+send_untagged_and_8021p()
+{
+ ping_do $h1 192.0.2.2
+ check_fail $?
+
+ 8021p_do 1
+}
+
+drop_untagged()
+{
+ RET=0
+
+ tc qdisc add dev $h2 clsact
+ ip link set $h2 promisc on
+
+ # Test that with no PVID, untagged and 802.1p-tagged traffic is
+ # dropped.
+ ip link set br0 type bridge vlan_default_pvid 1
+
+ # First we reconfigure the default_pvid, 1, as a non-PVID VLAN.
+ bridge vlan add dev $swp1 vid 1 untagged
+ send_untagged_and_8021p
+ bridge vlan add dev $swp1 vid 1 pvid untagged
+
+ # Next we try to delete VID 1 altogether
+ bridge vlan del dev $swp1 vid 1
+ send_untagged_and_8021p
+ bridge vlan add dev $swp1 vid 1 pvid untagged
+
+ # Set up the bridge without a default_pvid, then check that the 8021q
+ # module, when the bridge port goes down and then up again, does not
+ # accidentally re-enable untagged packet reception.
+ ip link set br0 type bridge vlan_default_pvid 0
+ ip link set $swp1 down
+ ip link set $swp1 up
+ setup_wait
+ send_untagged_and_8021p
+
+ # Remove swp1 as a bridge port and let it rejoin the bridge while it
+ # has no default_pvid.
+ ip link set $swp1 nomaster
+ ip link set $swp1 master br0
+ send_untagged_and_8021p
+
+ # Restore settings
+ ip link set br0 type bridge vlan_default_pvid 1
+
+ log_test "Dropping of untagged and 802.1p-tagged traffic with no PVID"
+
+ ip link set $h2 promisc off
+ tc qdisc del dev $h2 clsact
+}
+
trap cleanup EXIT
setup_prepare
diff --git a/tools/testing/selftests/net/forwarding/config b/tools/testing/selftests/net/forwarding/config
index 8d7a1a004b7c..18fd69d8d937 100644
--- a/tools/testing/selftests/net/forwarding/config
+++ b/tools/testing/selftests/net/forwarding/config
@@ -1,6 +1,7 @@
CONFIG_BRIDGE=m
CONFIG_VLAN_8021Q=m
CONFIG_BRIDGE_VLAN_FILTERING=y
+CONFIG_BRIDGE_IGMP_SNOOPING=y
CONFIG_NET_L3_MASTER_DEV=y
CONFIG_IPV6_MULTIPLE_TABLES=y
CONFIG_NET_VRF=m
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 8de80acf249e..508f3c700d71 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -291,16 +291,6 @@ if [[ "$CHECK_TC" = "yes" ]]; then
check_tc_version
fi
-require_command()
-{
- local cmd=$1; shift
-
- if [[ ! -x "$(command -v "$cmd")" ]]; then
- echo "SKIP: $cmd not installed"
- exit $ksft_skip
- fi
-}
-
# IPv6 support was added in v3.0
check_mtools_version()
{
diff --git a/tools/testing/selftests/net/forwarding/tc_taprio.sh b/tools/testing/selftests/net/forwarding/tc_taprio.sh
new file mode 100755
index 000000000000..8992aeabfe0b
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/tc_taprio.sh
@@ -0,0 +1,421 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS=" \
+ test_clock_jump_backward \
+ test_taprio_after_ptp \
+ test_max_sdu \
+ test_clock_jump_backward_forward \
+"
+NUM_NETIFS=4
+source tc_common.sh
+source lib.sh
+source tsn_lib.sh
+
+require_command python3
+
+# The test assumes the usual topology from the README, where h1 is connected to
+# swp1, h2 to swp2, and swp1 and swp2 are together in a bridge.
+# Additional assumption: h1 and h2 use the same PHC, and so do swp1 and swp2.
+# By synchronizing h1 to swp1 via PTP, h2 is also implicitly synchronized to
+# swp1 (and both to CLOCK_REALTIME).
+h1=${NETIFS[p1]}
+swp1=${NETIFS[p2]}
+swp2=${NETIFS[p3]}
+h2=${NETIFS[p4]}
+
+UDS_ADDRESS_H1="/var/run/ptp4l_h1"
+UDS_ADDRESS_SWP1="/var/run/ptp4l_swp1"
+
+H1_IPV4="192.0.2.1"
+H2_IPV4="192.0.2.2"
+H1_IPV6="2001:db8:1::1"
+H2_IPV6="2001:db8:1::2"
+
+# Tunables
+NUM_PKTS=100
+STREAM_VID=10
+STREAM_PRIO_1=6
+STREAM_PRIO_2=5
+STREAM_PRIO_3=4
+# PTP uses TC 0
+ALL_GATES=$((1 << 0 | 1 << STREAM_PRIO_1 | 1 << STREAM_PRIO_2))
+# Use a conservative cycle of 10 ms to allow the test to still pass when the
+# kernel has some extra overhead like lockdep etc
+CYCLE_TIME_NS=10000000
+# Create two Gate Control List entries, one OPEN and one CLOSE, of equal
+# durations
+GATE_DURATION_NS=$((CYCLE_TIME_NS / 2))
+# Give 2/3 of the cycle time to user space and 1/3 to the kernel
+FUDGE_FACTOR=$((CYCLE_TIME_NS / 3))
+# Shift the isochron base time by half the gate time, so that packets are
+# always received by swp1 close to the middle of the time slot, to minimize
+# inaccuracies due to network sync
+SHIFT_TIME_NS=$((GATE_DURATION_NS / 2))
+
+path_delay=
+
+h1_create()
+{
+ simple_if_init $h1 $H1_IPV4/24 $H1_IPV6/64
+}
+
+h1_destroy()
+{
+ simple_if_fini $h1 $H1_IPV4/24 $H1_IPV6/64
+}
+
+h2_create()
+{
+ simple_if_init $h2 $H2_IPV4/24 $H2_IPV6/64
+}
+
+h2_destroy()
+{
+ simple_if_fini $h2 $H2_IPV4/24 $H2_IPV6/64
+}
+
+switch_create()
+{
+ local h2_mac_addr=$(mac_get $h2)
+
+ ip link set $swp1 up
+ ip link set $swp2 up
+
+ ip link add br0 type bridge vlan_filtering 1
+ ip link set $swp1 master br0
+ ip link set $swp2 master br0
+ ip link set br0 up
+
+ bridge vlan add dev $swp2 vid $STREAM_VID
+ bridge vlan add dev $swp1 vid $STREAM_VID
+ bridge fdb add dev $swp2 \
+ $h2_mac_addr vlan $STREAM_VID static master
+}
+
+switch_destroy()
+{
+ ip link del br0
+}
+
+ptp_setup()
+{
+ # Set up swp1 as a master PHC for h1, synchronized to the local
+ # CLOCK_REALTIME.
+ phc2sys_start $UDS_ADDRESS_SWP1
+ ptp4l_start $h1 true $UDS_ADDRESS_H1
+ ptp4l_start $swp1 false $UDS_ADDRESS_SWP1
+}
+
+ptp_cleanup()
+{
+ ptp4l_stop $swp1
+ ptp4l_stop $h1
+ phc2sys_stop
+}
+
+txtime_setup()
+{
+ local if_name=$1
+
+ tc qdisc add dev $if_name clsact
+ # Classify PTP on TC 7 and isochron on TC 6
+ tc filter add dev $if_name egress protocol 0x88f7 \
+ flower action skbedit priority 7
+ tc filter add dev $if_name egress protocol 802.1Q \
+ flower vlan_ethtype 0xdead action skbedit priority 6
+ tc qdisc add dev $if_name handle 100: parent root mqprio num_tc 8 \
+ queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 \
+ map 0 1 2 3 4 5 6 7 \
+ hw 1
+ # Set up TC 5, 6, 7 for SO_TXTIME. tc-mqprio queues count from 1.
+ tc qdisc replace dev $if_name parent 100:$((STREAM_PRIO_1 + 1)) etf \
+ clockid CLOCK_TAI offload delta $FUDGE_FACTOR
+ tc qdisc replace dev $if_name parent 100:$((STREAM_PRIO_2 + 1)) etf \
+ clockid CLOCK_TAI offload delta $FUDGE_FACTOR
+ tc qdisc replace dev $if_name parent 100:$((STREAM_PRIO_3 + 1)) etf \
+ clockid CLOCK_TAI offload delta $FUDGE_FACTOR
+}
+
+txtime_cleanup()
+{
+ local if_name=$1
+
+ tc qdisc del dev $if_name clsact
+ tc qdisc del dev $if_name root
+}
+
+taprio_replace()
+{
+ local if_name="$1"; shift
+ local extra_args="$1"; shift
+
+ # STREAM_PRIO_1 always has an open gate.
+ # STREAM_PRIO_2 has a gate open for GATE_DURATION_NS (half the cycle time)
+ # STREAM_PRIO_3 always has a closed gate.
+ tc qdisc replace dev $if_name root stab overhead 24 taprio num_tc 8 \
+ queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 \
+ map 0 1 2 3 4 5 6 7 \
+ sched-entry S $(printf "%x" $ALL_GATES) $GATE_DURATION_NS \
+ sched-entry S $(printf "%x" $((ALL_GATES & ~(1 << STREAM_PRIO_2)))) $GATE_DURATION_NS \
+ base-time 0 flags 0x2 $extra_args
+ taprio_wait_for_admin $if_name
+}
+
+taprio_cleanup()
+{
+ local if_name=$1
+
+ tc qdisc del dev $if_name root
+}
+
+probe_path_delay()
+{
+ local isochron_dat="$(mktemp)"
+ local received
+
+ log_info "Probing path delay"
+
+ isochron_do "$h1" "$h2" "$UDS_ADDRESS_H1" "" 0 \
+ "$CYCLE_TIME_NS" "" "" "$NUM_PKTS" \
+ "$STREAM_VID" "$STREAM_PRIO_1" "" "$isochron_dat"
+
+ received=$(isochron_report_num_received "$isochron_dat")
+ if [ "$received" != "$NUM_PKTS" ]; then
+ echo "Cannot establish basic data path between $h1 and $h2"
+ exit $ksft_fail
+ fi
+
+ printf "pdelay = {}\n" > isochron_data.py
+ isochron report --input-file "$isochron_dat" \
+ --printf-format "pdelay[%u] = %d - %d\n" \
+ --printf-args "qRT" \
+ >> isochron_data.py
+ cat <<-'EOF' > isochron_postprocess.py
+ #!/usr/bin/env python3
+
+ from isochron_data import pdelay
+ import numpy as np
+
+ w = np.array(list(pdelay.values()))
+ print("{}".format(np.max(w)))
+ EOF
+ path_delay=$(python3 ./isochron_postprocess.py)
+
+ log_info "Path delay from $h1 to $h2 estimated at $path_delay ns"
+
+ if [ "$path_delay" -gt "$GATE_DURATION_NS" ]; then
+ echo "Path delay larger than gate duration, aborting"
+ exit $ksft_fail
+ fi
+
+ rm -f ./isochron_data.py 2> /dev/null
+ rm -f ./isochron_postprocess.py 2> /dev/null
+ rm -f "$isochron_dat" 2> /dev/null
+}
+
+setup_prepare()
+{
+ vrf_prepare
+
+ h1_create
+ h2_create
+ switch_create
+
+ txtime_setup $h1
+
+ # Temporarily set up PTP just to probe the end-to-end path delay.
+ ptp_setup
+ probe_path_delay
+ ptp_cleanup
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ isochron_recv_stop
+ txtime_cleanup $h1
+
+ switch_destroy
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+run_test()
+{
+ local base_time=$1; shift
+ local stream_prio=$1; shift
+ local expected_delay=$1; shift
+ local should_fail=$1; shift
+ local test_name=$1; shift
+ local isochron_dat="$(mktemp)"
+ local received
+ local median_delay
+
+ RET=0
+
+ # Set the shift time equal to the cycle time, which effectively
+ # cancels the default advance time. Packets won't be sent early in
+ # software, which ensures that they won't prematurely enter through
+ # the open gate in __test_out_of_band(). Also, the gate is open for
+ # long enough that this won't cause a problem in __test_in_band().
+ isochron_do "$h1" "$h2" "$UDS_ADDRESS_H1" "" "$base_time" \
+ "$CYCLE_TIME_NS" "$SHIFT_TIME_NS" "$GATE_DURATION_NS" \
+ "$NUM_PKTS" "$STREAM_VID" "$stream_prio" "" "$isochron_dat"
+
+ received=$(isochron_report_num_received "$isochron_dat")
+ [ "$received" = "$NUM_PKTS" ]
+ check_err_fail $should_fail $? "Reception of $NUM_PKTS packets"
+
+ if [ $should_fail = 0 ] && [ "$received" = "$NUM_PKTS" ]; then
+ printf "pdelay = {}\n" > isochron_data.py
+ isochron report --input-file "$isochron_dat" \
+ --printf-format "pdelay[%u] = %d - %d\n" \
+ --printf-args "qRT" \
+ >> isochron_data.py
+ cat <<-'EOF' > isochron_postprocess.py
+ #!/usr/bin/env python3
+
+ from isochron_data import pdelay
+ import numpy as np
+
+ w = np.array(list(pdelay.values()))
+ print("{}".format(int(np.median(w))))
+ EOF
+ median_delay=$(python3 ./isochron_postprocess.py)
+
+ # If the condition below is true, packets were delayed by a closed gate
+ [ "$median_delay" -gt $((path_delay + expected_delay)) ]
+ check_fail $? "Median delay $median_delay is greater than expected delay $expected_delay plus path delay $path_delay"
+
+ # If the condition below is true, packets were sent expecting them to
+ # hit a closed gate in the switch, but were not delayed
+ [ "$expected_delay" -gt 0 ] && [ "$median_delay" -lt "$expected_delay" ]
+ check_fail $? "Median delay $median_delay is less than expected delay $expected_delay"
+ fi
+
+ log_test "$test_name"
+
+ rm -f ./isochron_data.py 2> /dev/null
+ rm -f ./isochron_postprocess.py 2> /dev/null
+ rm -f "$isochron_dat" 2> /dev/null
+}
+
+__test_always_open()
+{
+ run_test 0.000000000 $STREAM_PRIO_1 0 0 "Gate always open"
+}
+
+__test_always_closed()
+{
+ run_test 0.000000000 $STREAM_PRIO_3 0 1 "Gate always closed"
+}
+
+__test_in_band()
+{
+ # Send packets in-band with the OPEN gate entry
+ run_test 0.000000000 $STREAM_PRIO_2 0 0 "In band with gate"
+}
+
+__test_out_of_band()
+{
+ # Send packets in-band with the CLOSE gate entry
+ run_test 0.005000000 $STREAM_PRIO_2 \
+ $((GATE_DURATION_NS - SHIFT_TIME_NS)) 0 \
+ "Out of band with gate"
+}
+
+run_subtests()
+{
+ __test_always_open
+ __test_always_closed
+ __test_in_band
+ __test_out_of_band
+}
+
+test_taprio_after_ptp()
+{
+ log_info "Setting up taprio after PTP"
+ ptp_setup
+ taprio_replace $swp2
+ run_subtests
+ taprio_cleanup $swp2
+ ptp_cleanup
+}
+
+__test_under_max_sdu()
+{
+ # Limit max-sdu for STREAM_PRIO_1
+ taprio_replace "$swp2" "max-sdu 0 0 0 0 0 0 100 0"
+ run_test 0.000000000 $STREAM_PRIO_1 0 0 "Under maximum SDU"
+}
+
+__test_over_max_sdu()
+{
+ # Limit max-sdu for STREAM_PRIO_1
+ taprio_replace "$swp2" "max-sdu 0 0 0 0 0 0 20 0"
+ run_test 0.000000000 $STREAM_PRIO_1 0 1 "Over maximum SDU"
+}
+
+test_max_sdu()
+{
+ ptp_setup
+ __test_under_max_sdu
+ __test_over_max_sdu
+ taprio_cleanup $swp2
+ ptp_cleanup
+}
+
+# Perform a clock jump in the past without synchronization running, so that the
+# time base remains where it was set by phc_ctl.
+test_clock_jump_backward()
+{
+ # This is a more complex schedule specifically crafted in a way that
+ # has been problematic on NXP LS1028A. Not much to test with it other
+ # than the fact that it passes traffic.
+ tc qdisc replace dev $swp2 root stab overhead 24 taprio num_tc 8 \
+ queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 map 0 1 2 3 4 5 6 7 \
+ base-time 0 sched-entry S 20 300000 sched-entry S 10 200000 \
+ sched-entry S 20 300000 sched-entry S 48 200000 \
+ sched-entry S 20 300000 sched-entry S 83 200000 \
+ sched-entry S 40 300000 sched-entry S 00 200000 flags 2
+
+ log_info "Forcing a backward clock jump"
+ phc_ctl $swp1 set 0
+
+ ping_test $h1 192.0.2.2
+ taprio_cleanup $swp2
+}
+
+# Test that taprio tolerates clock jumps.
+# Since ptp4l and phc2sys are running, it is expected for the time to
+# eventually recover (through yet another clock jump). Isochron waits
+# until that is the case.
+test_clock_jump_backward_forward()
+{
+ log_info "Forcing a backward and a forward clock jump"
+ taprio_replace $swp2
+ phc_ctl $swp1 set 0
+ ptp_setup
+ ping_test $h1 192.0.2.2
+ run_subtests
+ ptp_cleanup
+ taprio_cleanup $swp2
+}
+
+tc_offload_check
+if [[ $? -ne 0 ]]; then
+ log_test_skip "Could not test offloaded functionality"
+ exit $EXIT_STATUS
+fi
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/tsn_lib.sh b/tools/testing/selftests/net/forwarding/tsn_lib.sh
index b91bcd8008a9..08c044ff6689 100644
--- a/tools/testing/selftests/net/forwarding/tsn_lib.sh
+++ b/tools/testing/selftests/net/forwarding/tsn_lib.sh
@@ -2,6 +2,8 @@
# SPDX-License-Identifier: GPL-2.0
# Copyright 2021-2022 NXP
+tc_testing_scripts_dir=$(dirname $0)/../../tc-testing/scripts
+
REQUIRE_ISOCHRON=${REQUIRE_ISOCHRON:=yes}
REQUIRE_LINUXPTP=${REQUIRE_LINUXPTP:=yes}
@@ -18,6 +20,7 @@ fi
if [[ "$REQUIRE_LINUXPTP" = "yes" ]]; then
require_command phc2sys
require_command ptp4l
+ require_command phc_ctl
fi
phc2sys_start()
@@ -182,6 +185,7 @@ isochron_do()
local base_time=$1; shift
local cycle_time=$1; shift
local shift_time=$1; shift
+ local window_size=$1; shift
local num_pkts=$1; shift
local vid=$1; shift
local priority=$1; shift
@@ -212,6 +216,10 @@ isochron_do()
extra_args="${extra_args} --shift-time=${shift_time}"
fi
+ if ! [ -z "${window_size}" ]; then
+ extra_args="${extra_args} --window-size=${window_size}"
+ fi
+
if [ "${use_l2}" = "true" ]; then
extra_args="${extra_args} --l2 --etype=0xdead ${vid}"
receiver_extra_args="--l2 --etype=0xdead"
@@ -247,3 +255,21 @@ isochron_do()
cpufreq_restore ${ISOCHRON_CPU}
}
+
+isochron_report_num_received()
+{
+ local isochron_dat=$1; shift
+
+ # Count all received packets by looking at the non-zero RX timestamps
+ isochron report \
+ --input-file "${isochron_dat}" \
+ --printf-format "%u\n" --printf-args "R" | \
+ grep -w -v '0' | wc -l
+}
+
+taprio_wait_for_admin()
+{
+ local if_name="$1"; shift
+
+ "$tc_testing_scripts_dir/taprio_wait_for_admin.sh" "$(which tc)" "$if_name"
+}
diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index 3f9d50f1ef9e..b43816dd998c 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -428,6 +428,14 @@ __test_flood()
test_flood()
{
__test_flood de:ad:be:ef:13:37 192.0.2.100 "flood"
+
+ # Add an entry with arbitrary destination IP. Verify that packets are
+ # not duplicated (this can happen if hardware floods the packets, and
+ # then traps them due to misconfiguration, so software data path repeats
+ # flooding and resends packets).
+ bridge fdb append dev vx1 00:00:00:00:00:00 dst 198.51.100.1 self
+ __test_flood de:ad:be:ef:13:37 192.0.2.100 "flood, unresolved FDB entry"
+ bridge fdb del dev vx1 00:00:00:00:00:00 dst 198.51.100.1 self
}
vxlan_fdb_add_del()
@@ -740,6 +748,8 @@ test_learning()
vxlan_flood_test $mac $dst 0 10 0
+ # The entry should age out when it only forwards traffic
+ $MZ $h1 -c 50 -d 1sec -p 64 -b $mac -B $dst -t icmp -q &
sleep 60
bridge fdb show brport vx1 | grep $mac | grep -q self
diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh
index fb9a34cb50c6..afc65647f673 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh
@@ -539,6 +539,21 @@ test_flood()
10 10 0 10 0
__test_flood ca:fe:be:ef:13:37 198.51.100.100 20 "flood vlan 20" \
10 0 10 0 10
+
+ # Add entries with arbitrary destination IP. Verify that packets are
+ # not duplicated (this can happen if hardware floods the packets, and
+ # then traps them due to misconfiguration, so software data path repeats
+ # flooding and resends packets).
+ bridge fdb append dev vx10 00:00:00:00:00:00 dst 203.0.113.1 self
+ bridge fdb append dev vx20 00:00:00:00:00:00 dst 203.0.113.2 self
+
+ __test_flood de:ad:be:ef:13:37 192.0.2.100 10 \
+ "flood vlan 10, unresolved FDB entry" 10 10 0 10 0
+ __test_flood ca:fe:be:ef:13:37 198.51.100.100 20 \
+ "flood vlan 20, unresolved FDB entry" 10 0 10 0 10
+
+ bridge fdb del dev vx20 00:00:00:00:00:00 dst 203.0.113.2 self
+ bridge fdb del dev vx10 00:00:00:00:00:00 dst 203.0.113.1 self
}
vxlan_fdb_add_del()
diff --git a/tools/testing/selftests/net/gre_ipv6_lladdr.sh b/tools/testing/selftests/net/gre_ipv6_lladdr.sh
new file mode 100755
index 000000000000..5b34f6e1f831
--- /dev/null
+++ b/tools/testing/selftests/net/gre_ipv6_lladdr.sh
@@ -0,0 +1,177 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source ./lib.sh
+
+PAUSE_ON_FAIL="no"
+
+# The trap function handler
+#
+exit_cleanup_all()
+{
+ cleanup_all_ns
+
+ exit "${EXIT_STATUS}"
+}
+
+# Add fake IPv4 and IPv6 networks on the loopback device, to be used as
+# underlay by future GRE devices.
+#
+setup_basenet()
+{
+ ip -netns "${NS0}" link set dev lo up
+ ip -netns "${NS0}" address add dev lo 192.0.2.10/24
+ ip -netns "${NS0}" address add dev lo 2001:db8::10/64 nodad
+}
+
+# Check if network device has an IPv6 link-local address assigned.
+#
+# Parameters:
+#
+# * $1: The network device to test
+# * $2: An extra regular expression that should be matched (to verify the
+# presence of extra attributes)
+# * $3: The expected return code from grep (to allow checking the absence of
+# a link-local address)
+# * $4: The user visible name for the scenario being tested
+#
+check_ipv6_ll_addr()
+{
+ local DEV="$1"
+ local EXTRA_MATCH="$2"
+ local XRET="$3"
+ local MSG="$4"
+
+ RET=0
+ set +e
+ ip -netns "${NS0}" -6 address show dev "${DEV}" scope link | grep "fe80::" | grep -q "${EXTRA_MATCH}"
+ check_err_fail "${XRET}" $? ""
+ log_test "${MSG}"
+ set -e
+}
+
+# Create a GRE device and verify that it gets an IPv6 link-local address as
+# expected.
+#
+# Parameters:
+#
+# * $1: The device type (gre, ip6gre, gretap or ip6gretap)
+# * $2: The local underlay IP address (can be an IPv4, an IPv6 or "any")
+# * $3: The remote underlay IP address (can be an IPv4, an IPv6 or "any")
+# * $4: The IPv6 interface identifier generation mode to use for the GRE
+# device (eui64, none, stable-privacy or random).
+#
+test_gre_device()
+{
+ local GRE_TYPE="$1"
+ local LOCAL_IP="$2"
+ local REMOTE_IP="$3"
+ local MODE="$4"
+ local ADDR_GEN_MODE
+ local MATCH_REGEXP
+ local MSG
+
+ ip link add netns "${NS0}" name gretest type "${GRE_TYPE}" local "${LOCAL_IP}" remote "${REMOTE_IP}"
+
+ case "${MODE}" in
+ "eui64")
+ ADDR_GEN_MODE=0
+ MATCH_REGEXP=""
+ MSG="${GRE_TYPE}, mode: 0 (EUI64), ${LOCAL_IP} -> ${REMOTE_IP}"
+ XRET=0
+ ;;
+ "none")
+ ADDR_GEN_MODE=1
+ MATCH_REGEXP=""
+ MSG="${GRE_TYPE}, mode: 1 (none), ${LOCAL_IP} -> ${REMOTE_IP}"
+ XRET=1 # No link-local address should be generated
+ ;;
+ "stable-privacy")
+ ADDR_GEN_MODE=2
+ MATCH_REGEXP="stable-privacy"
+ MSG="${GRE_TYPE}, mode: 2 (stable privacy), ${LOCAL_IP} -> ${REMOTE_IP}"
+ XRET=0
+ # Initialise stable_secret (required for stable-privacy mode)
+ ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.stable_secret="2001:db8::abcd"
+ ;;
+ "random")
+ ADDR_GEN_MODE=3
+ MATCH_REGEXP="stable-privacy"
+ MSG="${GRE_TYPE}, mode: 3 (random), ${LOCAL_IP} -> ${REMOTE_IP}"
+ XRET=0
+ ;;
+ esac
+
+ # Check that IPv6 link-local address is generated when device goes up
+ ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}"
+ ip -netns "${NS0}" link set dev gretest up
+ check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "config: ${MSG}"
+
+ # Now disable link-local address generation
+ ip -netns "${NS0}" link set dev gretest down
+ ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode=1
+ ip -netns "${NS0}" link set dev gretest up
+
+ # Check that link-local address generation works when re-enabled while
+ # the device is already up
+ ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}"
+ check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "update: ${MSG}"
+
+ ip -netns "${NS0}" link del dev gretest
+}
+
+test_gre4()
+{
+ local GRE_TYPE
+ local MODE
+
+ for GRE_TYPE in "gre" "gretap"; do
+ printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n"
+
+ for MODE in "eui64" "none" "stable-privacy" "random"; do
+ test_gre_device "${GRE_TYPE}" 192.0.2.10 192.0.2.11 "${MODE}"
+ test_gre_device "${GRE_TYPE}" any 192.0.2.11 "${MODE}"
+ test_gre_device "${GRE_TYPE}" 192.0.2.10 any "${MODE}"
+ done
+ done
+}
+
+test_gre6()
+{
+ local GRE_TYPE
+ local MODE
+
+ for GRE_TYPE in "ip6gre" "ip6gretap"; do
+ printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n"
+
+ for MODE in "eui64" "none" "stable-privacy" "random"; do
+ test_gre_device "${GRE_TYPE}" 2001:db8::10 2001:db8::11 "${MODE}"
+ test_gre_device "${GRE_TYPE}" any 2001:db8::11 "${MODE}"
+ test_gre_device "${GRE_TYPE}" 2001:db8::10 any "${MODE}"
+ done
+ done
+}
+
+usage()
+{
+ echo "Usage: $0 [-p]"
+ exit 1
+}
+
+while getopts :p o
+do
+ case $o in
+ p) PAUSE_ON_FAIL="yes";;
+ *) usage;;
+ esac
+done
+
+setup_ns NS0
+
+set -e
+trap exit_cleanup_all EXIT
+
+setup_basenet
+
+test_gre4
+test_gre6
diff --git a/tools/testing/selftests/net/gro.c b/tools/testing/selftests/net/gro.c
index b2184847e388..d5824eadea10 100644
--- a/tools/testing/selftests/net/gro.c
+++ b/tools/testing/selftests/net/gro.c
@@ -1318,11 +1318,13 @@ int main(int argc, char **argv)
read_MAC(src_mac, smac);
read_MAC(dst_mac, dmac);
- if (tx_socket)
+ if (tx_socket) {
gro_sender();
- else
+ } else {
+ /* Only the receiver exit status determines test success. */
gro_receiver();
+ fprintf(stderr, "Gro::%s test passed.\n", testname);
+ }
- fprintf(stderr, "Gro::%s test passed.\n", testname);
return 0;
}
diff --git a/tools/testing/selftests/net/gro.sh b/tools/testing/selftests/net/gro.sh
index 02c21ff4ca81..9e3f186bc2a1 100755
--- a/tools/testing/selftests/net/gro.sh
+++ b/tools/testing/selftests/net/gro.sh
@@ -18,10 +18,10 @@ run_test() {
"--smac" "${CLIENT_MAC}" "--test" "${test}" "--verbose" )
setup_ns
- # Each test is run 3 times to deflake, because given the receive timing,
+ # Each test is run 6 times to deflake, because given the receive timing,
# not all packets that should coalesce will be considered in the same flow
# on every try.
- for tries in {1..3}; do
+ for tries in {1..6}; do
# Actual test starts here
ip netns exec $server_ns ./gro "${ARGS[@]}" "--rx" "--iface" "server" \
1>>log.txt &
@@ -100,5 +100,6 @@ trap cleanup EXIT
if [[ "${test}" == "all" ]]; then
run_all_tests
else
- run_test "${proto}" "${test}"
+ exit_code=$(run_test "${proto}" "${test}")
+ exit $exit_code
fi;
diff --git a/tools/testing/selftests/net/icmp_redirect.sh b/tools/testing/selftests/net/icmp_redirect.sh
index d6f0e449c029..b13c89a99ecb 100755
--- a/tools/testing/selftests/net/icmp_redirect.sh
+++ b/tools/testing/selftests/net/icmp_redirect.sh
@@ -178,8 +178,6 @@ setup()
else
ip netns exec $ns sysctl -q -w net.ipv4.ip_forward=1
ip netns exec $ns sysctl -q -w net.ipv4.conf.all.send_redirects=1
- ip netns exec $ns sysctl -q -w net.ipv4.conf.default.rp_filter=0
- ip netns exec $ns sysctl -q -w net.ipv4.conf.all.rp_filter=0
ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=1
ip netns exec $ns sysctl -q -w net.ipv6.route.mtu_expires=10
diff --git a/tools/testing/selftests/net/ip_local_port_range.sh b/tools/testing/selftests/net/ip_local_port_range.sh
index 6c6ad346eaa0..4ff746db1256 100755
--- a/tools/testing/selftests/net/ip_local_port_range.sh
+++ b/tools/testing/selftests/net/ip_local_port_range.sh
@@ -2,4 +2,6 @@
# SPDX-License-Identifier: GPL-2.0
./in_netns.sh \
- sh -c 'sysctl -q -w net.ipv4.ip_local_port_range="40000 49999" && ./ip_local_port_range'
+ sh -c 'sysctl -q -w net.mptcp.enabled=1 && \
+ sysctl -q -w net.ipv4.ip_local_port_range="40000 49999" && \
+ ./ip_local_port_range'
diff --git a/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh b/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh
index a6b2b1f9c641..c6866e42f95c 100755
--- a/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh
+++ b/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh
@@ -69,7 +69,6 @@
# which can affect the conditions needed to trigger a soft lockup.
source lib.sh
-source net_helper.sh
TEST_DURATION=300
ROUTING_TABLE_REFRESH_PERIOD=0.01
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index 0bd9a038a1f0..006fdadcc4b9 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -217,11 +217,38 @@ setup_ns()
return $ksft_skip
fi
ip -n "${!ns_name}" link set lo up
+ ip netns exec "${!ns_name}" sysctl -wq net.ipv4.conf.all.rp_filter=0
+ ip netns exec "${!ns_name}" sysctl -wq net.ipv4.conf.default.rp_filter=0
ns_list+=("${!ns_name}")
done
NS_LIST+=("${ns_list[@]}")
}
+# Create netdevsim with given id and net namespace.
+create_netdevsim() {
+ local id="$1"
+ local ns="$2"
+
+ modprobe netdevsim &> /dev/null
+ udevadm settle
+
+ echo "$id 1" | ip netns exec $ns tee /sys/bus/netdevsim/new_device >/dev/null
+ local dev=$(ip netns exec $ns ls /sys/bus/netdevsim/devices/netdevsim$id/net)
+ ip -netns $ns link set dev $dev name nsim$id
+ ip -netns $ns link set dev nsim$id up
+
+ echo nsim$id
+}
+
+# Remove netdevsim with given id.
+cleanup_netdevsim() {
+ local id="$1"
+
+ if [ -d "/sys/bus/netdevsim/devices/netdevsim$id/net" ]; then
+ echo "$id" > /sys/bus/netdevsim/del_device
+ fi
+}
+
tc_rule_stats_get()
{
local dev=$1; shift
@@ -245,6 +272,30 @@ tc_rule_handle_stats_get()
.options.actions[0].stats$selector"
}
+# attach a qdisc with two children match/no-match and a flower filter to match
+tc_set_flower_counter() {
+ local -r ns=$1
+ local -r ipver=$2
+ local -r dev=$3
+ local -r flower_expr=$4
+
+ tc -n $ns qdisc add dev $dev root handle 1: prio bands 2 \
+ priomap 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
+
+ tc -n $ns qdisc add dev $dev parent 1:1 handle 11: pfifo
+ tc -n $ns qdisc add dev $dev parent 1:2 handle 12: pfifo
+
+ tc -n $ns filter add dev $dev parent 1: protocol ipv$ipver \
+ flower $flower_expr classid 1:2
+}
+
+tc_get_flower_counter() {
+ local -r ns=$1
+ local -r dev=$2
+
+ tc -n $ns -j -s qdisc show dev $dev handle 12: | jq .[0].packets
+}
+
ret_set_ksft_status()
{
local ksft_status=$1; shift
@@ -450,6 +501,25 @@ kill_process()
{ kill $pid && wait $pid; } 2>/dev/null
}
+check_command()
+{
+ local cmd=$1; shift
+
+ if [[ ! -x "$(command -v "$cmd")" ]]; then
+ log_test_skip "$cmd not installed"
+ return $EXIT_STATUS
+ fi
+}
+
+require_command()
+{
+ local cmd=$1; shift
+
+ if ! check_command "$cmd"; then
+ exit $EXIT_STATUS
+ fi
+}
+
ip_link_add()
{
local name=$1; shift
@@ -525,3 +595,24 @@ bridge_vlan_add()
bridge vlan add "$@"
defer bridge vlan del "$@"
}
+
+wait_local_port_listen()
+{
+ local listener_ns="${1}"
+ local port="${2}"
+ local protocol="${3}"
+ local pattern
+ local i
+
+ pattern=":$(printf "%04X" "${port}") "
+
+ # for tcp protocol additionally check the socket state
+ [ ${protocol} = "tcp" ] && pattern="${pattern}0A"
+ for i in $(seq 10); do
+ if ip netns exec "${listener_ns}" awk '{print $2" "$4}' \
+ /proc/net/"${protocol}"* | grep -q "${pattern}"; then
+ break
+ fi
+ sleep 0.1
+ done
+}
diff --git a/tools/testing/selftests/net/lib/.gitignore b/tools/testing/selftests/net/lib/.gitignore
index 1ebc6187f421..bbc97d6bf556 100644
--- a/tools/testing/selftests/net/lib/.gitignore
+++ b/tools/testing/selftests/net/lib/.gitignore
@@ -1,2 +1,3 @@
# SPDX-License-Identifier: GPL-2.0-only
csum
+xdp_helper
diff --git a/tools/testing/selftests/net/lib/Makefile b/tools/testing/selftests/net/lib/Makefile
index c22623b9a2a5..88c4bc461459 100644
--- a/tools/testing/selftests/net/lib/Makefile
+++ b/tools/testing/selftests/net/lib/Makefile
@@ -10,6 +10,7 @@ TEST_FILES += ../../../../net/ynl
TEST_GEN_FILES += csum
TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c))
+TEST_GEN_FILES += xdp_helper
TEST_INCLUDES := $(wildcard py/*.py sh/*.sh)
diff --git a/tools/testing/selftests/net/lib/ksft.h b/tools/testing/selftests/net/lib/ksft.h
new file mode 100644
index 000000000000..17dc34a612c6
--- /dev/null
+++ b/tools/testing/selftests/net/lib/ksft.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#if !defined(__NET_KSFT_H__)
+#define __NET_KSFT_H__
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+static inline void ksft_ready(void)
+{
+ const char msg[7] = "ready\n";
+ char *env_str;
+ int fd;
+
+ env_str = getenv("KSFT_READY_FD");
+ if (env_str) {
+ fd = atoi(env_str);
+ if (!fd) {
+ fprintf(stderr, "invalid KSFT_READY_FD = '%s'\n",
+ env_str);
+ return;
+ }
+ } else {
+ fd = STDOUT_FILENO;
+ }
+
+ write(fd, msg, sizeof(msg));
+ if (fd != STDOUT_FILENO)
+ close(fd);
+}
+
+static inline void ksft_wait(void)
+{
+ char *env_str;
+ char byte;
+ int fd;
+
+ env_str = getenv("KSFT_WAIT_FD");
+ if (env_str) {
+ fd = atoi(env_str);
+ if (!fd) {
+ fprintf(stderr, "invalid KSFT_WAIT_FD = '%s'\n",
+ env_str);
+ return;
+ }
+ } else {
+ /* Not running in KSFT env, wait for input from STDIN instead */
+ fd = STDIN_FILENO;
+ }
+
+ read(fd, &byte, sizeof(byte));
+ if (fd != STDIN_FILENO)
+ close(fd);
+}
+
+#endif
diff --git a/tools/testing/selftests/net/lib/py/__init__.py b/tools/testing/selftests/net/lib/py/__init__.py
index 54d8f5eba810..8697bd27dc30 100644
--- a/tools/testing/selftests/net/lib/py/__init__.py
+++ b/tools/testing/selftests/net/lib/py/__init__.py
@@ -2,8 +2,8 @@
from .consts import KSRC
from .ksft import *
-from .netns import NetNS
+from .netns import NetNS, NetNSEnter
from .nsim import *
from .utils import *
-from .ynl import NlError, YnlFamily, EthtoolFamily, NetdevFamily, RtnlFamily
+from .ynl import NlError, YnlFamily, EthtoolFamily, NetdevFamily, RtnlFamily, RtnlAddrFamily
from .ynl import NetshaperFamily
diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py
index 3efe005436cd..61287c203b6e 100644
--- a/tools/testing/selftests/net/lib/py/ksft.py
+++ b/tools/testing/selftests/net/lib/py/ksft.py
@@ -3,6 +3,7 @@
import builtins
import functools
import inspect
+import signal
import sys
import time
import traceback
@@ -26,6 +27,10 @@ class KsftXfailEx(Exception):
pass
+class KsftTerminate(KeyboardInterrupt):
+ pass
+
+
def ksft_pr(*objs, **kwargs):
print("#", *objs, **kwargs)
@@ -71,6 +76,11 @@ def ksft_in(a, b, comment=""):
_fail("Check failed", a, "not in", b, comment)
+def ksft_not_in(a, b, comment=""):
+ if a in b:
+ _fail("Check failed", a, "in", b, comment)
+
+
def ksft_is(a, b, comment=""):
if a is not b:
_fail("Check failed", a, "is not", b, comment)
@@ -188,6 +198,17 @@ def ksft_setup(env):
return env
+def _ksft_intr(signum, frame):
+ # ksft runner.sh sends 2 SIGTERMs in a row on a timeout
+ # if we don't ignore the second one it will stop us from handling cleanup
+ global term_cnt
+ term_cnt += 1
+ if term_cnt == 1:
+ raise KsftTerminate()
+ else:
+ ksft_pr(f"Ignoring SIGTERM (cnt: {term_cnt}), already exiting...")
+
+
def ksft_run(cases=None, globs=None, case_pfx=None, args=()):
cases = cases or []
@@ -200,9 +221,13 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()):
cases.append(value)
break
+ global term_cnt
+ term_cnt = 0
+ prev_sigterm = signal.signal(signal.SIGTERM, _ksft_intr)
+
totals = {"pass": 0, "fail": 0, "skip": 0, "xfail": 0}
- print("KTAP version 1")
+ print("TAP version 13")
print("1.." + str(len(cases)))
global KSFT_RESULT
@@ -228,7 +253,7 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()):
for line in tb.strip().split('\n'):
ksft_pr("Exception|", line)
if stop:
- ksft_pr("Stopping tests due to KeyboardInterrupt.")
+ ksft_pr(f"Stopping tests due to {type(e).__name__}.")
KSFT_RESULT = False
cnt_key = 'fail'
@@ -243,6 +268,8 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()):
if stop:
break
+ signal.signal(signal.SIGTERM, prev_sigterm)
+
print(
f"# Totals: pass:{totals['pass']} fail:{totals['fail']} xfail:{totals['xfail']} xpass:0 skip:{totals['skip']} error:0"
)
diff --git a/tools/testing/selftests/net/lib/py/netns.py b/tools/testing/selftests/net/lib/py/netns.py
index ecff85f9074f..8e9317044eef 100644
--- a/tools/testing/selftests/net/lib/py/netns.py
+++ b/tools/testing/selftests/net/lib/py/netns.py
@@ -1,9 +1,12 @@
# SPDX-License-Identifier: GPL-2.0
from .utils import ip
+import ctypes
import random
import string
+libc = ctypes.cdll.LoadLibrary('libc.so.6')
+
class NetNS:
def __init__(self, name=None):
@@ -29,3 +32,18 @@ class NetNS:
def __repr__(self):
return f"NetNS({self.name})"
+
+
+class NetNSEnter:
+ def __init__(self, ns_name):
+ self.ns_path = f"/run/netns/{ns_name}"
+
+ def __enter__(self):
+ self.saved = open("/proc/thread-self/ns/net")
+ with open(self.ns_path) as ns_file:
+ libc.setns(ns_file.fileno(), 0)
+ return self
+
+ def __exit__(self, exc_type, exc_value, traceback):
+ libc.setns(self.saved.fileno(), 0)
+ self.saved.close()
diff --git a/tools/testing/selftests/net/lib/py/utils.py b/tools/testing/selftests/net/lib/py/utils.py
index 9e3bcddcf3e8..34470d65d871 100644
--- a/tools/testing/selftests/net/lib/py/utils.py
+++ b/tools/testing/selftests/net/lib/py/utils.py
@@ -2,8 +2,10 @@
import errno
import json as _json
+import os
import random
import re
+import select
import socket
import subprocess
import time
@@ -15,21 +17,56 @@ class CmdExitFailure(Exception):
self.cmd = cmd_obj
+def fd_read_timeout(fd, timeout):
+ rlist, _, _ = select.select([fd], [], [], timeout)
+ if rlist:
+ return os.read(fd, 1024)
+ else:
+ raise TimeoutError("Timeout waiting for fd read")
+
+
class cmd:
- def __init__(self, comm, shell=True, fail=True, ns=None, background=False, host=None, timeout=5):
+ """
+ Execute a command on local or remote host.
+
+ Use bkg() instead to run a command in the background.
+ """
+ def __init__(self, comm, shell=True, fail=True, ns=None, background=False,
+ host=None, timeout=5, ksft_wait=None):
if ns:
comm = f'ip netns exec {ns} ' + comm
self.stdout = None
self.stderr = None
self.ret = None
+ self.ksft_term_fd = None
self.comm = comm
if host:
self.proc = host.cmd(comm)
else:
+ # ksft_wait lets us wait for the background process to fully start,
+ # we pass an FD to the child process, and wait for it to write back.
+ # Similarly term_fd tells child it's time to exit.
+ pass_fds = ()
+ env = os.environ.copy()
+ if ksft_wait is not None:
+ rfd, ready_fd = os.pipe()
+ wait_fd, self.ksft_term_fd = os.pipe()
+ pass_fds = (ready_fd, wait_fd, )
+ env["KSFT_READY_FD"] = str(ready_fd)
+ env["KSFT_WAIT_FD"] = str(wait_fd)
+
self.proc = subprocess.Popen(comm, shell=shell, stdout=subprocess.PIPE,
- stderr=subprocess.PIPE)
+ stderr=subprocess.PIPE, pass_fds=pass_fds,
+ env=env)
+ if ksft_wait is not None:
+ os.close(ready_fd)
+ os.close(wait_fd)
+ msg = fd_read_timeout(rfd, ksft_wait)
+ os.close(rfd)
+ if not msg:
+ raise Exception("Did not receive ready message")
if not background:
self.process(terminate=False, fail=fail, timeout=timeout)
@@ -37,6 +74,8 @@ class cmd:
if fail is None:
fail = not terminate
+ if self.ksft_term_fd:
+ os.write(self.ksft_term_fd, b"1")
if terminate:
self.proc.terminate()
stdout, stderr = self.proc.communicate(timeout)
@@ -54,13 +93,36 @@ class cmd:
class bkg(cmd):
+ """
+ Run a command in the background.
+
+ Examples usage:
+
+ Run a command on remote host, and wait for it to finish.
+ This is usually paired with wait_port_listen() to make sure
+ the command has initialized:
+
+ with bkg("socat ...", exit_wait=True, host=cfg.remote) as nc:
+ ...
+
+ Run a command and expect it to let us know that it's ready
+ by writing to a special file descriptor passed via KSFT_READY_FD.
+ Command will be terminated when we exit the context manager:
+
+ with bkg("my_binary", ksft_wait=5):
+ """
def __init__(self, comm, shell=True, fail=None, ns=None, host=None,
- exit_wait=False):
+ exit_wait=False, ksft_wait=None):
super().__init__(comm, background=True,
- shell=shell, fail=fail, ns=ns, host=host)
- self.terminate = not exit_wait
+ shell=shell, fail=fail, ns=ns, host=host,
+ ksft_wait=ksft_wait)
+ self.terminate = not exit_wait and not ksft_wait
self.check_fail = fail
+ if shell and self.terminate:
+ print("# Warning: combining shell and terminate is risky!")
+ print("# SIGTERM may not reach the child on zsh/ksh!")
+
def __enter__(self):
return self
@@ -123,20 +185,13 @@ def ethtool(args, json=None, ns=None, host=None):
return tool('ethtool', args, json=json, ns=ns, host=host)
-def rand_port():
+def rand_port(type=socket.SOCK_STREAM):
"""
- Get a random unprivileged port, try to make sure it's not already used.
+ Get a random unprivileged port.
"""
- for _ in range(1000):
- port = random.randint(10000, 65535)
- try:
- with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s:
- s.bind(("", port))
- return port
- except OSError as e:
- if e.errno != errno.EADDRINUSE:
- raise
- raise Exception("Can't find any free unprivileged port")
+ with socket.socket(socket.AF_INET6, type) as s:
+ s.bind(("", 0))
+ return s.getsockname()[1]
def wait_port_listen(port, proto="tcp", ns=None, host=None, sleep=0.005, deadline=5):
diff --git a/tools/testing/selftests/net/lib/py/ynl.py b/tools/testing/selftests/net/lib/py/ynl.py
index ad1e36baee2a..6329ae805abf 100644
--- a/tools/testing/selftests/net/lib/py/ynl.py
+++ b/tools/testing/selftests/net/lib/py/ynl.py
@@ -39,9 +39,13 @@ class EthtoolFamily(YnlFamily):
class RtnlFamily(YnlFamily):
def __init__(self, recv_size=0):
- super().__init__((SPEC_PATH / Path('rt_link.yaml')).as_posix(),
+ super().__init__((SPEC_PATH / Path('rt-link.yaml')).as_posix(),
schema='', recv_size=recv_size)
+class RtnlAddrFamily(YnlFamily):
+ def __init__(self, recv_size=0):
+ super().__init__((SPEC_PATH / Path('rt-addr.yaml')).as_posix(),
+ schema='', recv_size=recv_size)
class NetdevFamily(YnlFamily):
def __init__(self, recv_size=0):
diff --git a/tools/testing/selftests/net/lib/xdp_helper.c b/tools/testing/selftests/net/lib/xdp_helper.c
new file mode 100644
index 000000000000..eb025a9f35b1
--- /dev/null
+++ b/tools/testing/selftests/net/lib/xdp_helper.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <sys/socket.h>
+#include <linux/if_xdp.h>
+#include <linux/if_link.h>
+#include <net/if.h>
+#include <inttypes.h>
+
+#include "ksft.h"
+
+#define UMEM_SZ (1U << 16)
+#define NUM_DESC (UMEM_SZ / 2048)
+
+
+static void print_usage(const char *bin)
+{
+ fprintf(stderr, "Usage: %s ifindex queue_id [-z]\n\n"
+ "where:\n\t-z: force zerocopy mode", bin);
+}
+
+/* this is a simple helper program that creates an XDP socket and does the
+ * minimum necessary to get bind() to succeed.
+ *
+ * this test program is not intended to actually process packets, but could be
+ * extended in the future if that is actually needed.
+ *
+ * it is used by queues.py to ensure the xsk netlinux attribute is set
+ * correctly.
+ */
+int main(int argc, char **argv)
+{
+ struct xdp_umem_reg umem_reg = { 0 };
+ struct sockaddr_xdp sxdp = { 0 };
+ int num_desc = NUM_DESC;
+ void *umem_area;
+ int retry = 0;
+ int ifindex;
+ int sock_fd;
+ int queue;
+
+ if (argc != 3 && argc != 4) {
+ print_usage(argv[0]);
+ return 1;
+ }
+
+ sock_fd = socket(AF_XDP, SOCK_RAW, 0);
+ if (sock_fd < 0) {
+ perror("socket creation failed");
+ /* if the kernel doesn't support AF_XDP, let the test program
+ * know with -1. All other error paths return 1.
+ */
+ if (errno == EAFNOSUPPORT)
+ return -1;
+ return 1;
+ }
+
+ /* "Probing mode", just checking if AF_XDP sockets are supported */
+ if (!strcmp(argv[1], "-") && !strcmp(argv[2], "-")) {
+ printf("AF_XDP support detected\n");
+ close(sock_fd);
+ return 0;
+ }
+
+ ifindex = atoi(argv[1]);
+ queue = atoi(argv[2]);
+
+ umem_area = mmap(NULL, UMEM_SZ, PROT_READ | PROT_WRITE, MAP_PRIVATE |
+ MAP_ANONYMOUS, -1, 0);
+ if (umem_area == MAP_FAILED) {
+ perror("mmap failed");
+ return 1;
+ }
+
+ umem_reg.addr = (uintptr_t)umem_area;
+ umem_reg.len = UMEM_SZ;
+ umem_reg.chunk_size = 2048;
+ umem_reg.headroom = 0;
+
+ setsockopt(sock_fd, SOL_XDP, XDP_UMEM_REG, &umem_reg,
+ sizeof(umem_reg));
+ setsockopt(sock_fd, SOL_XDP, XDP_UMEM_FILL_RING, &num_desc,
+ sizeof(num_desc));
+ setsockopt(sock_fd, SOL_XDP, XDP_UMEM_COMPLETION_RING, &num_desc,
+ sizeof(num_desc));
+ setsockopt(sock_fd, SOL_XDP, XDP_RX_RING, &num_desc, sizeof(num_desc));
+
+ sxdp.sxdp_family = AF_XDP;
+ sxdp.sxdp_ifindex = ifindex;
+ sxdp.sxdp_queue_id = queue;
+ sxdp.sxdp_flags = 0;
+
+ if (argc > 3) {
+ if (!strcmp(argv[3], "-z")) {
+ sxdp.sxdp_flags = XDP_ZEROCOPY;
+ } else {
+ print_usage(argv[0]);
+ return 1;
+ }
+ }
+
+ while (1) {
+ if (bind(sock_fd, (struct sockaddr *)&sxdp, sizeof(sxdp)) == 0)
+ break;
+
+ if (errno == EBUSY && retry < 3) {
+ retry++;
+ sleep(1);
+ continue;
+ } else {
+ perror("bind failed");
+ munmap(umem_area, UMEM_SZ);
+ close(sock_fd);
+ return 1;
+ }
+ }
+
+ ksft_ready();
+ ksft_wait();
+
+ /* parent program will write a byte to stdin when its ready for this
+ * helper to exit
+ */
+
+ close(sock_fd);
+ return 0;
+}
diff --git a/tools/testing/selftests/net/link_netns.py b/tools/testing/selftests/net/link_netns.py
new file mode 100755
index 000000000000..aab043c59d69
--- /dev/null
+++ b/tools/testing/selftests/net/link_netns.py
@@ -0,0 +1,141 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import time
+
+from lib.py import ksft_run, ksft_exit, ksft_true
+from lib.py import ip
+from lib.py import NetNS, NetNSEnter
+from lib.py import RtnlFamily
+
+
+LINK_NETNSID = 100
+
+
+def test_event() -> None:
+ with NetNS() as ns1, NetNS() as ns2:
+ with NetNSEnter(str(ns2)):
+ rtnl = RtnlFamily()
+
+ rtnl.ntf_subscribe("rtnlgrp-link")
+
+ ip(f"netns set {ns2} {LINK_NETNSID}", ns=str(ns1))
+ ip(f"link add netns {ns1} link-netnsid {LINK_NETNSID} dummy1 type dummy")
+ ip(f"link add netns {ns1} dummy2 type dummy", ns=str(ns2))
+
+ ip("link del dummy1", ns=str(ns1))
+ ip("link del dummy2", ns=str(ns1))
+
+ time.sleep(1)
+ rtnl.check_ntf()
+ ksft_true(rtnl.async_msg_queue.empty(),
+ "Received unexpected link notification")
+
+
+def validate_link_netns(netns, ifname, link_netnsid) -> bool:
+ link_info = ip(f"-d link show dev {ifname}", ns=netns, json=True)
+ if not link_info:
+ return False
+ return link_info[0].get("link_netnsid") == link_netnsid
+
+
+def test_link_net() -> None:
+ configs = [
+ # type, common args, type args, fallback to dev_net
+ ("ipvlan", "link dummy1", "", False),
+ ("macsec", "link dummy1", "", False),
+ ("macvlan", "link dummy1", "", False),
+ ("macvtap", "link dummy1", "", False),
+ ("vlan", "link dummy1", "id 100", False),
+ ("gre", "", "local 192.0.2.1", True),
+ ("vti", "", "local 192.0.2.1", True),
+ ("ipip", "", "local 192.0.2.1", True),
+ ("ip6gre", "", "local 2001:db8::1", True),
+ ("ip6tnl", "", "local 2001:db8::1", True),
+ ("vti6", "", "local 2001:db8::1", True),
+ ("sit", "", "local 192.0.2.1", True),
+ ("xfrm", "", "if_id 1", True),
+ ]
+
+ with NetNS() as ns1, NetNS() as ns2, NetNS() as ns3:
+ net1, net2, net3 = str(ns1), str(ns2), str(ns3)
+
+ # prepare link netnsid and a dummy link needed by certain drivers
+ ip(f"netns set {net3} {LINK_NETNSID}", ns=str(net2))
+ ip("link add dummy1 type dummy", ns=net3)
+
+ cases = [
+ # source, "netns", "link-netns", expected link-netns
+ (net3, None, None, None, None),
+ (net3, net2, None, None, LINK_NETNSID),
+ (net2, None, net3, LINK_NETNSID, LINK_NETNSID),
+ (net1, net2, net3, LINK_NETNSID, LINK_NETNSID),
+ ]
+
+ for src_net, netns, link_netns, exp1, exp2 in cases:
+ tgt_net = netns or src_net
+ for typ, cargs, targs, fb_dev_net in configs:
+ cmd = "link add"
+ if netns:
+ cmd += f" netns {netns}"
+ if link_netns:
+ cmd += f" link-netns {link_netns}"
+ cmd += f" {cargs} foo type {typ} {targs}"
+ ip(cmd, ns=src_net)
+ if fb_dev_net:
+ ksft_true(validate_link_netns(tgt_net, "foo", exp1),
+ f"{typ} link_netns validation failed")
+ else:
+ ksft_true(validate_link_netns(tgt_net, "foo", exp2),
+ f"{typ} link_netns validation failed")
+ ip(f"link del foo", ns=tgt_net)
+
+
+def test_peer_net() -> None:
+ types = [
+ "vxcan",
+ "netkit",
+ "veth",
+ ]
+
+ with NetNS() as ns1, NetNS() as ns2, NetNS() as ns3, NetNS() as ns4:
+ net1, net2, net3, net4 = str(ns1), str(ns2), str(ns3), str(ns4)
+
+ ip(f"netns set {net3} {LINK_NETNSID}", ns=str(net2))
+
+ cases = [
+ # source, "netns", "link-netns", "peer netns", expected
+ (net1, None, None, None, None),
+ (net1, net2, None, None, None),
+ (net2, None, net3, None, LINK_NETNSID),
+ (net1, net2, net3, None, None),
+ (net2, None, None, net3, LINK_NETNSID),
+ (net1, net2, None, net3, LINK_NETNSID),
+ (net2, None, net2, net3, LINK_NETNSID),
+ (net1, net2, net4, net3, LINK_NETNSID),
+ ]
+
+ for src_net, netns, link_netns, peer_netns, exp in cases:
+ tgt_net = netns or src_net
+ for typ in types:
+ cmd = "link add"
+ if netns:
+ cmd += f" netns {netns}"
+ if link_netns:
+ cmd += f" link-netns {link_netns}"
+ cmd += f" foo type {typ}"
+ if peer_netns:
+ cmd += f" peer netns {peer_netns}"
+ ip(cmd, ns=src_net)
+ ksft_true(validate_link_netns(tgt_net, "foo", exp),
+ f"{typ} peer_netns validation failed")
+ ip(f"link del foo", ns=tgt_net)
+
+
+def main() -> None:
+ ksft_run([test_event, test_link_net, test_peer_net])
+ ksft_exit()
+
+
+if __name__ == "__main__":
+ main()
diff --git a/tools/testing/selftests/net/mptcp/.gitignore b/tools/testing/selftests/net/mptcp/.gitignore
index 49daae73c41e..833279fb34e2 100644
--- a/tools/testing/selftests/net/mptcp/.gitignore
+++ b/tools/testing/selftests/net/mptcp/.gitignore
@@ -1,5 +1,6 @@
# SPDX-License-Identifier: GPL-2.0-only
mptcp_connect
+mptcp_diag
mptcp_inq
mptcp_sockopt
pm_nl_ctl
diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile
index c76525fe2b84..e47788bfa671 100644
--- a/tools/testing/selftests/net/mptcp/Makefile
+++ b/tools/testing/selftests/net/mptcp/Makefile
@@ -7,11 +7,11 @@ CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INC
TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \
simult_flows.sh mptcp_sockopt.sh userspace_pm.sh
-TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq
+TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq mptcp_diag
TEST_FILES := mptcp_lib.sh settings
-TEST_INCLUDES := ../lib.sh $(wildcard ../lib/sh/*.sh) ../net_helper.sh
+TEST_INCLUDES := ../lib.sh $(wildcard ../lib/sh/*.sh)
EXTRA_CLEAN := *.pcap
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 2bd0c1eb70c5..7a3cb4c09e45 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -200,6 +200,62 @@ chk_msk_cestab()
"${expected}" "${msg}" ""
}
+chk_dump_one()
+{
+ local ss_token
+ local token
+ local msg
+
+ ss_token="$(ss -inmHMN $ns |
+ mptcp_lib_get_info_value "token" "token")"
+
+ token="$(ip netns exec $ns ./mptcp_diag -t $ss_token |\
+ awk -F':[ \t]+' '/^token/ {print $2}')"
+
+ msg="....chk dump_one"
+
+ mptcp_lib_print_title "$msg"
+ if [ -n "$ss_token" ] && [ "$ss_token" = "$token" ]; then
+ mptcp_lib_pr_ok
+ mptcp_lib_result_pass "${msg}"
+ else
+ mptcp_lib_pr_fail "expected $ss_token found $token"
+ mptcp_lib_result_fail "${msg}"
+ ret=${KSFT_FAIL}
+ fi
+}
+
+chk_dump_subflow()
+{
+ local inet_diag_token
+ local subflow_line
+ local ss_output
+ local ss_token
+ local msg
+
+ ss_output=$(ss -tniN $ns)
+
+ subflow_line=$(echo "$ss_output" | \
+ grep -m1 -Eo '[0-9.]+:[0-9].+ +[0-9.]+:[0-9.]+')
+
+ ss_token=$(echo "$ss_output" | grep -m1 -Eo 'token:[^ ]+')
+
+ inet_diag_token=$(ip netns exec $ns ./mptcp_diag -s "$subflow_line" | \
+ grep -Eo 'token:[^ ]+')
+
+ msg="....chk dump_subflow"
+
+ mptcp_lib_print_title "$msg"
+ if [ -n "$ss_token" ] && [ "$ss_token" = "$inet_diag_token" ]; then
+ mptcp_lib_pr_ok
+ mptcp_lib_result_pass "${msg}"
+ else
+ mptcp_lib_pr_fail "expected $ss_token found $inet_diag_token"
+ mptcp_lib_result_fail "${msg}"
+ ret=${KSFT_FAIL}
+ fi
+}
+
msk_info_get_value()
{
local port="${1}"
@@ -290,6 +346,8 @@ chk_msk_remote_key_nr 2 "....chk remote_key"
chk_msk_fallback_nr 0 "....chk no fallback"
chk_msk_inuse 2
chk_msk_cestab 2
+chk_dump_one
+chk_dump_subflow
flush_pids
chk_msk_inuse 0 "2->0"
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index d240d02fa443..ac1349c4b9e5 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -180,13 +180,26 @@ static void xgetnameinfo(const struct sockaddr *addr, socklen_t addrlen,
}
static void xgetaddrinfo(const char *node, const char *service,
- const struct addrinfo *hints,
+ struct addrinfo *hints,
struct addrinfo **res)
{
+again:
int err = getaddrinfo(node, service, hints, res);
if (err) {
- const char *errstr = getxinfo_strerr(err);
+ const char *errstr;
+
+ /* glibc starts to support MPTCP since v2.42.
+ * For older versions, use IPPROTO_TCP to resolve,
+ * and use TCP/MPTCP to create socket.
+ * Link: https://sourceware.org/git/?p=glibc.git;a=commit;h=a8e9022e0f82
+ */
+ if (err == EAI_SOCKTYPE) {
+ hints->ai_protocol = IPPROTO_TCP;
+ goto again;
+ }
+
+ errstr = getxinfo_strerr(err);
fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n",
node ? node : "", service ? service : "", errstr);
@@ -292,7 +305,7 @@ static int sock_listen_mptcp(const char * const listenaddr,
{
int sock = -1;
struct addrinfo hints = {
- .ai_protocol = IPPROTO_TCP,
+ .ai_protocol = IPPROTO_MPTCP,
.ai_socktype = SOCK_STREAM,
.ai_flags = AI_PASSIVE | AI_NUMERICHOST
};
@@ -356,7 +369,7 @@ static int sock_connect_mptcp(const char * const remoteaddr,
int infd, struct wstate *winfo)
{
struct addrinfo hints = {
- .ai_protocol = IPPROTO_TCP,
+ .ai_protocol = IPPROTO_MPTCP,
.ai_socktype = SOCK_STREAM,
};
struct addrinfo *a, *addr;
@@ -1270,7 +1283,7 @@ int main_loop(void)
if (cfg_input && cfg_sockopt_types.mptfo) {
fd_in = open(cfg_input, O_RDONLY);
- if (fd < 0)
+ if (fd_in < 0)
xerror("can't open %s:%d", cfg_input, errno);
}
@@ -1293,13 +1306,13 @@ again:
if (cfg_input && !cfg_sockopt_types.mptfo) {
fd_in = open(cfg_input, O_RDONLY);
- if (fd < 0)
+ if (fd_in < 0)
xerror("can't open %s:%d", cfg_input, errno);
}
ret = copyfd_io(fd_in, fd, 1, 0, &winfo);
if (ret)
- return ret;
+ goto out;
if (cfg_truncate > 0) {
shutdown(fd, SHUT_WR);
@@ -1320,7 +1333,10 @@ again:
close(fd);
}
- return 0;
+out:
+ if (cfg_input)
+ close(fd_in);
+ return ret;
}
int parse_proto(const char *proto)
diff --git a/tools/testing/selftests/net/mptcp/mptcp_diag.c b/tools/testing/selftests/net/mptcp/mptcp_diag.c
new file mode 100644
index 000000000000..e084796e804d
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/mptcp_diag.c
@@ -0,0 +1,435 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025, Kylin Software */
+
+#include <linux/sock_diag.h>
+#include <linux/rtnetlink.h>
+#include <linux/inet_diag.h>
+#include <linux/netlink.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <linux/tcp.h>
+#include <arpa/inet.h>
+
+#include <unistd.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <stdio.h>
+
+#ifndef IPPROTO_MPTCP
+#define IPPROTO_MPTCP 262
+#endif
+
+#define parse_rtattr_nested(tb, max, rta) \
+ (parse_rtattr_flags((tb), (max), RTA_DATA(rta), RTA_PAYLOAD(rta), \
+ NLA_F_NESTED))
+
+struct params {
+ __u32 target_token;
+ char subflow_addrs[1024];
+};
+
+struct mptcp_info {
+ __u8 mptcpi_subflows;
+ __u8 mptcpi_add_addr_signal;
+ __u8 mptcpi_add_addr_accepted;
+ __u8 mptcpi_subflows_max;
+ __u8 mptcpi_add_addr_signal_max;
+ __u8 mptcpi_add_addr_accepted_max;
+ __u32 mptcpi_flags;
+ __u32 mptcpi_token;
+ __u64 mptcpi_write_seq;
+ __u64 mptcpi_snd_una;
+ __u64 mptcpi_rcv_nxt;
+ __u8 mptcpi_local_addr_used;
+ __u8 mptcpi_local_addr_max;
+ __u8 mptcpi_csum_enabled;
+ __u32 mptcpi_retransmits;
+ __u64 mptcpi_bytes_retrans;
+ __u64 mptcpi_bytes_sent;
+ __u64 mptcpi_bytes_received;
+ __u64 mptcpi_bytes_acked;
+ __u8 mptcpi_subflows_total;
+ __u8 reserved[3];
+ __u32 mptcpi_last_data_sent;
+ __u32 mptcpi_last_data_recv;
+ __u32 mptcpi_last_ack_recv;
+};
+
+enum {
+ MPTCP_SUBFLOW_ATTR_UNSPEC,
+ MPTCP_SUBFLOW_ATTR_TOKEN_REM,
+ MPTCP_SUBFLOW_ATTR_TOKEN_LOC,
+ MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ,
+ MPTCP_SUBFLOW_ATTR_MAP_SEQ,
+ MPTCP_SUBFLOW_ATTR_MAP_SFSEQ,
+ MPTCP_SUBFLOW_ATTR_SSN_OFFSET,
+ MPTCP_SUBFLOW_ATTR_MAP_DATALEN,
+ MPTCP_SUBFLOW_ATTR_FLAGS,
+ MPTCP_SUBFLOW_ATTR_ID_REM,
+ MPTCP_SUBFLOW_ATTR_ID_LOC,
+ MPTCP_SUBFLOW_ATTR_PAD,
+
+ __MPTCP_SUBFLOW_ATTR_MAX
+};
+
+#define MPTCP_SUBFLOW_ATTR_MAX (__MPTCP_SUBFLOW_ATTR_MAX - 1)
+
+#define MPTCP_SUBFLOW_FLAG_MCAP_REM _BITUL(0)
+#define MPTCP_SUBFLOW_FLAG_MCAP_LOC _BITUL(1)
+#define MPTCP_SUBFLOW_FLAG_JOIN_REM _BITUL(2)
+#define MPTCP_SUBFLOW_FLAG_JOIN_LOC _BITUL(3)
+#define MPTCP_SUBFLOW_FLAG_BKUP_REM _BITUL(4)
+#define MPTCP_SUBFLOW_FLAG_BKUP_LOC _BITUL(5)
+#define MPTCP_SUBFLOW_FLAG_FULLY_ESTABLISHED _BITUL(6)
+#define MPTCP_SUBFLOW_FLAG_CONNECTED _BITUL(7)
+#define MPTCP_SUBFLOW_FLAG_MAPVALID _BITUL(8)
+
+#define rta_getattr(type, value) (*(type *)RTA_DATA(value))
+
+static void die_perror(const char *msg)
+{
+ perror(msg);
+ exit(1);
+}
+
+static void die_usage(int r)
+{
+ fprintf(stderr, "Usage:\n"
+ "mptcp_diag -t <token>\n"
+ "mptcp_diag -s \"<saddr>:<sport> <daddr>:<dport>\"\n");
+ exit(r);
+}
+
+static void send_query(int fd, struct inet_diag_req_v2 *r, __u32 proto)
+{
+ struct sockaddr_nl nladdr = {
+ .nl_family = AF_NETLINK
+ };
+ struct {
+ struct nlmsghdr nlh;
+ struct inet_diag_req_v2 r;
+ } req = {
+ .nlh = {
+ .nlmsg_len = sizeof(req),
+ .nlmsg_type = SOCK_DIAG_BY_FAMILY,
+ .nlmsg_flags = NLM_F_REQUEST
+ },
+ .r = *r
+ };
+ struct rtattr rta_proto;
+ struct iovec iov[6];
+ int iovlen = 0;
+
+ iov[iovlen++] = (struct iovec) {
+ .iov_base = &req,
+ .iov_len = sizeof(req)
+ };
+
+ if (proto == IPPROTO_MPTCP) {
+ rta_proto.rta_type = INET_DIAG_REQ_PROTOCOL;
+ rta_proto.rta_len = RTA_LENGTH(sizeof(proto));
+
+ iov[iovlen++] = (struct iovec){ &rta_proto, sizeof(rta_proto)};
+ iov[iovlen++] = (struct iovec){ &proto, sizeof(proto)};
+ req.nlh.nlmsg_len += RTA_LENGTH(sizeof(proto));
+ }
+
+ struct msghdr msg = {
+ .msg_name = &nladdr,
+ .msg_namelen = sizeof(nladdr),
+ .msg_iov = iov,
+ .msg_iovlen = iovlen
+ };
+
+ for (;;) {
+ if (sendmsg(fd, &msg, 0) < 0) {
+ if (errno == EINTR)
+ continue;
+ die_perror("sendmsg");
+ }
+ break;
+ }
+}
+
+static void parse_rtattr_flags(struct rtattr *tb[], int max, struct rtattr *rta,
+ int len, unsigned short flags)
+{
+ unsigned short type;
+
+ memset(tb, 0, sizeof(struct rtattr *) * (max + 1));
+ while (RTA_OK(rta, len)) {
+ type = rta->rta_type & ~flags;
+ if (type <= max && !tb[type])
+ tb[type] = rta;
+ rta = RTA_NEXT(rta, len);
+ }
+}
+
+static void print_info_msg(struct mptcp_info *info)
+{
+ printf("Token & Flags\n");
+ printf("token: %x\n", info->mptcpi_token);
+ printf("flags: %x\n", info->mptcpi_flags);
+ printf("csum_enabled: %u\n", info->mptcpi_csum_enabled);
+
+ printf("\nBasic Info\n");
+ printf("subflows: %u\n", info->mptcpi_subflows);
+ printf("subflows_max: %u\n", info->mptcpi_subflows_max);
+ printf("subflows_total: %u\n", info->mptcpi_subflows_total);
+ printf("local_addr_used: %u\n", info->mptcpi_local_addr_used);
+ printf("local_addr_max: %u\n", info->mptcpi_local_addr_max);
+ printf("add_addr_signal: %u\n", info->mptcpi_add_addr_signal);
+ printf("add_addr_accepted: %u\n", info->mptcpi_add_addr_accepted);
+ printf("add_addr_signal_max: %u\n", info->mptcpi_add_addr_signal_max);
+ printf("add_addr_accepted_max: %u\n", info->mptcpi_add_addr_accepted_max);
+
+ printf("\nTransmission Info\n");
+ printf("write_seq: %llu\n", info->mptcpi_write_seq);
+ printf("snd_una: %llu\n", info->mptcpi_snd_una);
+ printf("rcv_nxt: %llu\n", info->mptcpi_rcv_nxt);
+ printf("last_data_sent: %u\n", info->mptcpi_last_data_sent);
+ printf("last_data_recv: %u\n", info->mptcpi_last_data_recv);
+ printf("last_ack_recv: %u\n", info->mptcpi_last_ack_recv);
+ printf("retransmits: %u\n", info->mptcpi_retransmits);
+ printf("retransmit bytes: %llu\n", info->mptcpi_bytes_retrans);
+ printf("bytes_sent: %llu\n", info->mptcpi_bytes_sent);
+ printf("bytes_received: %llu\n", info->mptcpi_bytes_received);
+ printf("bytes_acked: %llu\n", info->mptcpi_bytes_acked);
+}
+
+/*
+ * 'print_subflow_info' is from 'mptcp_subflow_info'
+ * which is a function in 'misc/ss.c' of iproute2.
+ */
+static void print_subflow_info(struct rtattr *tb[])
+{
+ u_int32_t flags = 0;
+
+ printf("It's a mptcp subflow, the subflow info:\n");
+ if (tb[MPTCP_SUBFLOW_ATTR_FLAGS]) {
+ char caps[32 + 1] = { 0 }, *cap = &caps[0];
+
+ flags = rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_FLAGS]);
+
+ if (flags & MPTCP_SUBFLOW_FLAG_MCAP_REM)
+ *cap++ = 'M';
+ if (flags & MPTCP_SUBFLOW_FLAG_MCAP_LOC)
+ *cap++ = 'm';
+ if (flags & MPTCP_SUBFLOW_FLAG_JOIN_REM)
+ *cap++ = 'J';
+ if (flags & MPTCP_SUBFLOW_FLAG_JOIN_LOC)
+ *cap++ = 'j';
+ if (flags & MPTCP_SUBFLOW_FLAG_BKUP_REM)
+ *cap++ = 'B';
+ if (flags & MPTCP_SUBFLOW_FLAG_BKUP_LOC)
+ *cap++ = 'b';
+ if (flags & MPTCP_SUBFLOW_FLAG_FULLY_ESTABLISHED)
+ *cap++ = 'e';
+ if (flags & MPTCP_SUBFLOW_FLAG_CONNECTED)
+ *cap++ = 'c';
+ if (flags & MPTCP_SUBFLOW_FLAG_MAPVALID)
+ *cap++ = 'v';
+
+ if (flags)
+ printf(" flags:%s", caps);
+ }
+ if (tb[MPTCP_SUBFLOW_ATTR_TOKEN_REM] &&
+ tb[MPTCP_SUBFLOW_ATTR_TOKEN_LOC] &&
+ tb[MPTCP_SUBFLOW_ATTR_ID_REM] &&
+ tb[MPTCP_SUBFLOW_ATTR_ID_LOC])
+ printf(" token:%04x(id:%u)/%04x(id:%u)",
+ rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_TOKEN_REM]),
+ rta_getattr(__u8, tb[MPTCP_SUBFLOW_ATTR_ID_REM]),
+ rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_TOKEN_LOC]),
+ rta_getattr(__u8, tb[MPTCP_SUBFLOW_ATTR_ID_LOC]));
+ if (tb[MPTCP_SUBFLOW_ATTR_MAP_SEQ])
+ printf(" seq:%llu",
+ rta_getattr(__u64, tb[MPTCP_SUBFLOW_ATTR_MAP_SEQ]));
+ if (tb[MPTCP_SUBFLOW_ATTR_MAP_SFSEQ])
+ printf(" sfseq:%u",
+ rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_MAP_SFSEQ]));
+ if (tb[MPTCP_SUBFLOW_ATTR_SSN_OFFSET])
+ printf(" ssnoff:%u",
+ rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_SSN_OFFSET]));
+ if (tb[MPTCP_SUBFLOW_ATTR_MAP_DATALEN])
+ printf(" maplen:%u",
+ rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_MAP_DATALEN]));
+ printf("\n");
+}
+
+static void parse_nlmsg(struct nlmsghdr *nlh, __u32 proto)
+{
+ struct inet_diag_msg *r = NLMSG_DATA(nlh);
+ struct rtattr *tb[INET_DIAG_MAX + 1];
+
+ parse_rtattr_flags(tb, INET_DIAG_MAX, (struct rtattr *)(r + 1),
+ nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)),
+ NLA_F_NESTED);
+
+ if (proto == IPPROTO_MPTCP && tb[INET_DIAG_INFO]) {
+ int len = RTA_PAYLOAD(tb[INET_DIAG_INFO]);
+ struct mptcp_info *info;
+
+ /* workaround fort older kernels with less fields */
+ if (len < sizeof(*info)) {
+ info = alloca(sizeof(*info));
+ memcpy(info, RTA_DATA(tb[INET_DIAG_INFO]), len);
+ memset((char *)info + len, 0, sizeof(*info) - len);
+ } else {
+ info = RTA_DATA(tb[INET_DIAG_INFO]);
+ }
+ print_info_msg(info);
+ }
+ if (proto == IPPROTO_TCP && tb[INET_DIAG_ULP_INFO]) {
+ struct rtattr *ulpinfo[INET_ULP_INFO_MAX + 1] = { 0 };
+
+ parse_rtattr_nested(ulpinfo, INET_ULP_INFO_MAX,
+ tb[INET_DIAG_ULP_INFO]);
+
+ if (ulpinfo[INET_ULP_INFO_MPTCP]) {
+ struct rtattr *sfinfo[MPTCP_SUBFLOW_ATTR_MAX + 1] = { 0 };
+
+ parse_rtattr_nested(sfinfo, MPTCP_SUBFLOW_ATTR_MAX,
+ ulpinfo[INET_ULP_INFO_MPTCP]);
+ print_subflow_info(sfinfo);
+ } else {
+ printf("It's a normal TCP!\n");
+ }
+ }
+}
+
+static void recv_nlmsg(int fd, __u32 proto)
+{
+ char rcv_buff[8192];
+ struct nlmsghdr *nlh = (struct nlmsghdr *)rcv_buff;
+ struct sockaddr_nl rcv_nladdr = {
+ .nl_family = AF_NETLINK
+ };
+ struct iovec rcv_iov = {
+ .iov_base = rcv_buff,
+ .iov_len = sizeof(rcv_buff)
+ };
+ struct msghdr rcv_msg = {
+ .msg_name = &rcv_nladdr,
+ .msg_namelen = sizeof(rcv_nladdr),
+ .msg_iov = &rcv_iov,
+ .msg_iovlen = 1
+ };
+ int len;
+
+ len = recvmsg(fd, &rcv_msg, 0);
+
+ while (NLMSG_OK(nlh, len)) {
+ if (nlh->nlmsg_type == NLMSG_DONE) {
+ printf("NLMSG_DONE\n");
+ break;
+ } else if (nlh->nlmsg_type == NLMSG_ERROR) {
+ struct nlmsgerr *err;
+
+ err = (struct nlmsgerr *)NLMSG_DATA(nlh);
+ printf("Error %d:%s\n",
+ -(err->error), strerror(-(err->error)));
+ break;
+ }
+ parse_nlmsg(nlh, proto);
+ nlh = NLMSG_NEXT(nlh, len);
+ }
+}
+
+static void get_mptcpinfo(__u32 token)
+{
+ struct inet_diag_req_v2 r = {
+ .sdiag_family = AF_INET,
+ /* Real proto is set via INET_DIAG_REQ_PROTOCOL */
+ .sdiag_protocol = IPPROTO_TCP,
+ .idiag_ext = 1 << (INET_DIAG_INFO - 1),
+ .id.idiag_cookie[0] = token,
+ };
+ __u32 proto = IPPROTO_MPTCP;
+ int fd;
+
+ fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_SOCK_DIAG);
+ if (fd < 0)
+ die_perror("Netlink socket");
+
+ send_query(fd, &r, proto);
+ recv_nlmsg(fd, proto);
+
+ close(fd);
+}
+
+static void get_subflow_info(char *subflow_addrs)
+{
+ struct inet_diag_req_v2 r = {
+ .sdiag_family = AF_INET,
+ .sdiag_protocol = IPPROTO_TCP,
+ .idiag_ext = 1 << (INET_DIAG_INFO - 1),
+ .id.idiag_cookie[0] = INET_DIAG_NOCOOKIE,
+ .id.idiag_cookie[1] = INET_DIAG_NOCOOKIE,
+ };
+ char saddr[64], daddr[64];
+ int sport, dport;
+ int ret;
+ int fd;
+
+ ret = sscanf(subflow_addrs, "%[^:]:%d %[^:]:%d", saddr, &sport, daddr, &dport);
+ if (ret != 4)
+ die_perror("IP PORT Pairs has style problems!");
+
+ printf("%s:%d -> %s:%d\n", saddr, sport, daddr, dport);
+
+ fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_SOCK_DIAG);
+ if (fd < 0)
+ die_perror("Netlink socket");
+
+ r.id.idiag_sport = htons(sport);
+ r.id.idiag_dport = htons(dport);
+
+ inet_pton(AF_INET, saddr, &r.id.idiag_src);
+ inet_pton(AF_INET, daddr, &r.id.idiag_dst);
+ send_query(fd, &r, IPPROTO_TCP);
+ recv_nlmsg(fd, IPPROTO_TCP);
+}
+
+static void parse_opts(int argc, char **argv, struct params *p)
+{
+ int c;
+
+ if (argc < 2)
+ die_usage(1);
+
+ while ((c = getopt(argc, argv, "ht:s:")) != -1) {
+ switch (c) {
+ case 'h':
+ die_usage(0);
+ break;
+ case 't':
+ sscanf(optarg, "%x", &p->target_token);
+ break;
+ case 's':
+ strncpy(p->subflow_addrs, optarg,
+ sizeof(p->subflow_addrs) - 1);
+ break;
+ default:
+ die_usage(1);
+ break;
+ }
+ }
+}
+
+int main(int argc, char *argv[])
+{
+ struct params p = { 0 };
+
+ parse_opts(argc, argv, &p);
+
+ if (p.target_token)
+ get_mptcpinfo(p.target_token);
+
+ if (p.subflow_addrs[0] != '\0')
+ get_subflow_info(p.subflow_addrs);
+
+ return 0;
+}
+
diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c
index 218aac467321..3cf1e2a612ce 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_inq.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c
@@ -72,13 +72,21 @@ static const char *getxinfo_strerr(int err)
}
static void xgetaddrinfo(const char *node, const char *service,
- const struct addrinfo *hints,
+ struct addrinfo *hints,
struct addrinfo **res)
{
+again:
int err = getaddrinfo(node, service, hints, res);
if (err) {
- const char *errstr = getxinfo_strerr(err);
+ const char *errstr;
+
+ if (err == EAI_SOCKTYPE) {
+ hints->ai_protocol = IPPROTO_TCP;
+ goto again;
+ }
+
+ errstr = getxinfo_strerr(err);
fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n",
node ? node : "", service ? service : "", errstr);
@@ -91,7 +99,7 @@ static int sock_listen_mptcp(const char * const listenaddr,
{
int sock = -1;
struct addrinfo hints = {
- .ai_protocol = IPPROTO_TCP,
+ .ai_protocol = IPPROTO_MPTCP,
.ai_socktype = SOCK_STREAM,
.ai_flags = AI_PASSIVE | AI_NUMERICHOST
};
@@ -136,7 +144,7 @@ static int sock_connect_mptcp(const char * const remoteaddr,
const char * const port, int proto)
{
struct addrinfo hints = {
- .ai_protocol = IPPROTO_TCP,
+ .ai_protocol = IPPROTO_MPTCP,
.ai_socktype = SOCK_STREAM,
};
struct addrinfo *a, *addr;
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 13a3b68181ee..b8af65373b3a 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -62,6 +62,7 @@ unset sflags
unset fastclose
unset fullmesh
unset speed
+unset join_syn_rej
unset join_csum_ns1
unset join_csum_ns2
unset join_fail_nr
@@ -1403,6 +1404,7 @@ chk_join_nr()
local syn_nr=$1
local syn_ack_nr=$2
local ack_nr=$3
+ local syn_rej=${join_syn_rej:-0}
local csum_ns1=${join_csum_ns1:-0}
local csum_ns2=${join_csum_ns2:-0}
local fail_nr=${join_fail_nr:-0}
@@ -1441,6 +1443,15 @@ chk_join_nr()
fi
fi
+ count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinSynAckHMacFailure")
+ if [ -z "$count" ]; then
+ rc=${KSFT_SKIP}
+ elif [ "$count" != "0" ]; then
+ rc=${KSFT_FAIL}
+ print_check "synack HMAC"
+ fail_test "got $count JOIN[s] synack HMAC failure expected 0"
+ fi
+
count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinAckRx")
if [ -z "$count" ]; then
rc=${KSFT_SKIP}
@@ -1450,6 +1461,24 @@ chk_join_nr()
fail_test "got $count JOIN[s] ack rx expected $ack_nr"
fi
+ count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinAckHMacFailure")
+ if [ -z "$count" ]; then
+ rc=${KSFT_SKIP}
+ elif [ "$count" != "0" ]; then
+ rc=${KSFT_FAIL}
+ print_check "ack HMAC"
+ fail_test "got $count JOIN[s] ack HMAC failure expected 0"
+ fi
+
+ count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinRejected")
+ if [ -z "$count" ]; then
+ rc=${KSFT_SKIP}
+ elif [ "$count" != "$syn_rej" ]; then
+ rc=${KSFT_FAIL}
+ print_check "syn rejected"
+ fail_test "got $count JOIN[s] syn rejected expected $syn_rej"
+ fi
+
print_results "join Rx" ${rc}
join_syn_tx="${join_syn_tx:-${syn_nr}}" \
@@ -1945,7 +1974,8 @@ subflows_tests()
pm_nl_set_limits $ns2 0 1
pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
run_tests $ns1 $ns2 10.0.1.1
- chk_join_nr 1 1 0
+ join_syn_rej=1 \
+ chk_join_nr 1 1 0
fi
# subflow
@@ -1974,7 +2004,8 @@ subflows_tests()
pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow
run_tests $ns1 $ns2 10.0.1.1
- chk_join_nr 2 2 1
+ join_syn_rej=1 \
+ chk_join_nr 2 2 1
fi
# single subflow, dev
@@ -3043,7 +3074,8 @@ syncookies_tests()
pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow
run_tests $ns1 $ns2 10.0.1.1
- chk_join_nr 2 1 1
+ join_syn_rej=1 \
+ chk_join_nr 2 1 1
fi
# test signal address with cookies
@@ -3527,7 +3559,8 @@ userspace_tests()
pm_nl_set_limits $ns2 1 1
pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
run_tests $ns1 $ns2 10.0.1.1
- chk_join_nr 1 1 0
+ join_syn_rej=1 \
+ chk_join_nr 1 1 0
fi
# userspace pm type does not send join
@@ -3550,7 +3583,8 @@ userspace_tests()
pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
sflags=backup speed=slow \
run_tests $ns1 $ns2 10.0.1.1
- chk_join_nr 1 1 0
+ join_syn_rej=1 \
+ chk_join_nr 1 1 0
chk_prio_nr 0 0 0 0
fi
diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
index 051e289d7967..09cd24b2ae46 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -2,7 +2,6 @@
# SPDX-License-Identifier: GPL-2.0
. "$(dirname "${0}")/../lib.sh"
-. "$(dirname "${0}")/../net_helper.sh"
readonly KSFT_PASS=0
readonly KSFT_FAIL=1
@@ -331,12 +330,15 @@ mptcp_lib_result_print_all_tap() {
# get the value of keyword $1 in the line marked by keyword $2
mptcp_lib_get_info_value() {
- grep "${2}" | sed -n 's/.*\('"${1}"':\)\([0-9a-f:.]*\).*$/\2/p;q'
+ grep "${2}" 2>/dev/null |
+ sed -n 's/.*\('"${1}"':\)\([0-9a-f:.]*\).*$/\2/p;q'
+ # the ';q' at the end limits to the first matched entry.
}
# $1: info name ; $2: evts_ns ; [$3: event type; [$4: addr]]
mptcp_lib_evts_get_info() {
- grep "${4:-}" "${2}" | mptcp_lib_get_info_value "${1}" "^type:${3:-1},"
+ grep "${4:-}" "${2}" 2>/dev/null |
+ mptcp_lib_get_info_value "${1}" "^type:${3:-1},"
}
# $1: PID
@@ -476,8 +478,6 @@ mptcp_lib_ns_init() {
local netns
for netns in "${@}"; do
ip netns exec "${!netns}" sysctl -q net.mptcp.enabled=1
- ip netns exec "${!netns}" sysctl -q net.ipv4.conf.all.rp_filter=0
- ip netns exec "${!netns}" sysctl -q net.ipv4.conf.default.rp_filter=0
done
}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
index 926b0be87c99..9934a68df237 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
@@ -159,13 +159,21 @@ static const char *getxinfo_strerr(int err)
}
static void xgetaddrinfo(const char *node, const char *service,
- const struct addrinfo *hints,
+ struct addrinfo *hints,
struct addrinfo **res)
{
+again:
int err = getaddrinfo(node, service, hints, res);
if (err) {
- const char *errstr = getxinfo_strerr(err);
+ const char *errstr;
+
+ if (err == EAI_SOCKTYPE) {
+ hints->ai_protocol = IPPROTO_TCP;
+ goto again;
+ }
+
+ errstr = getxinfo_strerr(err);
fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n",
node ? node : "", service ? service : "", errstr);
@@ -178,7 +186,7 @@ static int sock_listen_mptcp(const char * const listenaddr,
{
int sock = -1;
struct addrinfo hints = {
- .ai_protocol = IPPROTO_TCP,
+ .ai_protocol = IPPROTO_MPTCP,
.ai_socktype = SOCK_STREAM,
.ai_flags = AI_PASSIVE | AI_NUMERICHOST
};
@@ -223,7 +231,7 @@ static int sock_connect_mptcp(const char * const remoteaddr,
const char * const port, int proto)
{
struct addrinfo hints = {
- .ai_protocol = IPPROTO_TCP,
+ .ai_protocol = IPPROTO_MPTCP,
.ai_socktype = SOCK_STREAM,
};
struct addrinfo *a, *addr;
diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index 9c2a415976cb..2329c2f8519b 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -28,7 +28,7 @@ size=0
usage() {
echo "Usage: $0 [ -b ] [ -c ] [ -d ] [ -i]"
- echo -e "\t-b: bail out after first error, otherwise runs al testcases"
+ echo -e "\t-b: bail out after first error, otherwise runs all testcases"
echo -e "\t-c: capture packets for each test using tcpdump (default: no capture)"
echo -e "\t-d: debug this script"
echo -e "\t-i: use 'ip mptcp' instead of 'pm_nl_ctl'"
diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh
index 3651f73451cf..333064b0b5ac 100755
--- a/tools/testing/selftests/net/mptcp/userspace_pm.sh
+++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh
@@ -117,7 +117,36 @@ cleanup()
trap cleanup EXIT
# Create and configure network namespaces for testing
+print_title "Init"
mptcp_lib_ns_init ns1 ns2
+
+# check path_manager and pm_type sysctl mapping
+if [ -f /proc/sys/net/mptcp/path_manager ]; then
+ ip netns exec "$ns1" sysctl -q net.mptcp.path_manager=userspace
+ pm_type="$(ip netns exec "$ns1" sysctl -n net.mptcp.pm_type)"
+ if [ "${pm_type}" != "1" ]; then
+ test_fail "unexpected pm_type: ${pm_type}"
+ mptcp_lib_result_print_all_tap
+ exit ${KSFT_FAIL}
+ fi
+
+ ip netns exec "$ns1" sysctl -q net.mptcp.path_manager=error 2>/dev/null
+ pm_type="$(ip netns exec "$ns1" sysctl -n net.mptcp.pm_type)"
+ if [ "${pm_type}" != "1" ]; then
+ test_fail "unexpected pm_type after error: ${pm_type}"
+ mptcp_lib_result_print_all_tap
+ exit ${KSFT_FAIL}
+ fi
+
+ ip netns exec "$ns1" sysctl -q net.mptcp.pm_type=0
+ pm_name="$(ip netns exec "$ns1" sysctl -n net.mptcp.path_manager)"
+ if [ "${pm_name}" != "kernel" ]; then
+ test_fail "unexpected path-manager: ${pm_name}"
+ mptcp_lib_result_print_all_tap
+ exit ${KSFT_FAIL}
+ fi
+fi
+
for i in "$ns1" "$ns2" ;do
ip netns exec "$i" sysctl -q net.mptcp.pm_type=1
done
@@ -152,7 +181,6 @@ mptcp_lib_events "${ns1}" "${server_evts}" server_evts_pid
sleep 0.5
mptcp_lib_subtests_last_ts_reset
-print_title "Init"
print_test "Created network namespaces ns1, ns2"
test_pass
diff --git a/tools/testing/selftests/net/net_helper.sh b/tools/testing/selftests/net/net_helper.sh
deleted file mode 100644
index 6596fe03c77f..000000000000
--- a/tools/testing/selftests/net/net_helper.sh
+++ /dev/null
@@ -1,25 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-#
-# Helper functions
-
-wait_local_port_listen()
-{
- local listener_ns="${1}"
- local port="${2}"
- local protocol="${3}"
- local pattern
- local i
-
- pattern=":$(printf "%04X" "${port}") "
-
- # for tcp protocol additionally check the socket state
- [ ${protocol} = "tcp" ] && pattern="${pattern}0A"
- for i in $(seq 10); do
- if ip netns exec "${listener_ns}" awk '{print $2" "$4}' \
- /proc/net/"${protocol}"* | grep -q "${pattern}"; then
- break
- fi
- sleep 0.1
- done
-}
diff --git a/tools/testing/selftests/net/netfilter/Makefile b/tools/testing/selftests/net/netfilter/Makefile
index ffe161fac8b5..e9b2f553588d 100644
--- a/tools/testing/selftests/net/netfilter/Makefile
+++ b/tools/testing/selftests/net/netfilter/Makefile
@@ -12,6 +12,7 @@ TEST_PROGS += conntrack_dump_flush.sh
TEST_PROGS += conntrack_icmp_related.sh
TEST_PROGS += conntrack_ipip_mtu.sh
TEST_PROGS += conntrack_tcp_unreplied.sh
+TEST_PROGS += conntrack_resize.sh
TEST_PROGS += conntrack_sctp_collision.sh
TEST_PROGS += conntrack_vrf.sh
TEST_PROGS += conntrack_reverse_clash.sh
@@ -23,6 +24,7 @@ TEST_PROGS += nft_concat_range.sh
TEST_PROGS += nft_conntrack_helper.sh
TEST_PROGS += nft_fib.sh
TEST_PROGS += nft_flowtable.sh
+TEST_PROGS += nft_interface_stress.sh
TEST_PROGS += nft_meta.sh
TEST_PROGS += nft_nat.sh
TEST_PROGS += nft_nat_zones.sh
diff --git a/tools/testing/selftests/net/netfilter/br_netfilter.sh b/tools/testing/selftests/net/netfilter/br_netfilter.sh
index 1559ba275105..011de8763094 100755
--- a/tools/testing/selftests/net/netfilter/br_netfilter.sh
+++ b/tools/testing/selftests/net/netfilter/br_netfilter.sh
@@ -60,9 +60,6 @@ bcast_ping()
done
}
-ip netns exec "$ns0" sysctl -q net.ipv4.conf.all.rp_filter=0
-ip netns exec "$ns0" sysctl -q net.ipv4.conf.default.rp_filter=0
-
if ! ip link add veth1 netns "$ns0" type veth peer name eth0 netns "$ns1"; then
echo "SKIP: Can't create veth device"
exit $ksft_skip
diff --git a/tools/testing/selftests/net/netfilter/bridge_brouter.sh b/tools/testing/selftests/net/netfilter/bridge_brouter.sh
index 2549b6590693..ea76f2bc2f59 100755
--- a/tools/testing/selftests/net/netfilter/bridge_brouter.sh
+++ b/tools/testing/selftests/net/netfilter/bridge_brouter.sh
@@ -22,8 +22,6 @@ trap cleanup EXIT
setup_ns nsbr ns1 ns2
-ip netns exec "$nsbr" sysctl -q net.ipv4.conf.default.rp_filter=0
-ip netns exec "$nsbr" sysctl -q net.ipv4.conf.all.rp_filter=0
if ! ip link add veth0 netns "$nsbr" type veth peer name eth0 netns "$ns1"; then
echo "SKIP: Can't create veth device"
exit $ksft_skip
diff --git a/tools/testing/selftests/net/netfilter/config b/tools/testing/selftests/net/netfilter/config
index 43d8b500d391..363646f4fefe 100644
--- a/tools/testing/selftests/net/netfilter/config
+++ b/tools/testing/selftests/net/netfilter/config
@@ -46,6 +46,7 @@ CONFIG_NETFILTER_XT_MATCH_STATE=m
CONFIG_NETFILTER_XT_MATCH_STRING=m
CONFIG_NETFILTER_XT_TARGET_REDIRECT=m
CONFIG_NF_CONNTRACK=m
+CONFIG_NF_CONNTRACK_PROCFS=y
CONFIG_NF_CONNTRACK_EVENTS=y
CONFIG_NF_CONNTRACK_FTP=m
CONFIG_NF_CONNTRACK_MARK=y
diff --git a/tools/testing/selftests/net/netfilter/conntrack_resize.sh b/tools/testing/selftests/net/netfilter/conntrack_resize.sh
new file mode 100755
index 000000000000..9e033e80219e
--- /dev/null
+++ b/tools/testing/selftests/net/netfilter/conntrack_resize.sh
@@ -0,0 +1,427 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source lib.sh
+
+checktool "conntrack --version" "run test without conntrack"
+checktool "nft --version" "run test without nft tool"
+
+init_net_max=0
+ct_buckets=0
+tmpfile=""
+tmpfile_proc=""
+tmpfile_uniq=""
+ret=0
+
+insert_count=2000
+[ "$KSFT_MACHINE_SLOW" = "yes" ] && insert_count=400
+
+modprobe -q nf_conntrack
+if ! sysctl -q net.netfilter.nf_conntrack_max >/dev/null;then
+ echo "SKIP: conntrack sysctls not available"
+ exit $KSFT_SKIP
+fi
+
+init_net_max=$(sysctl -n net.netfilter.nf_conntrack_max) || exit 1
+ct_buckets=$(sysctl -n net.netfilter.nf_conntrack_buckets) || exit 1
+
+cleanup() {
+ cleanup_all_ns
+
+ rm -f "$tmpfile" "$tmpfile_proc" "$tmpfile_uniq"
+
+ # restore original sysctl setting
+ sysctl -q net.netfilter.nf_conntrack_max=$init_net_max
+ sysctl -q net.netfilter.nf_conntrack_buckets=$ct_buckets
+}
+trap cleanup EXIT
+
+check_max_alias()
+{
+ local expected="$1"
+ # old name, expected to alias to the first, i.e. changing one
+ # changes the other as well.
+ local lv=$(sysctl -n net.nf_conntrack_max)
+
+ if [ $expected -ne "$lv" ];then
+ echo "nf_conntrack_max sysctls should have identical values"
+ exit 1
+ fi
+}
+
+insert_ctnetlink() {
+ local ns="$1"
+ local count="$2"
+ local i=0
+ local bulk=16
+
+ while [ $i -lt $count ] ;do
+ ip netns exec "$ns" bash -c "for i in \$(seq 1 $bulk); do \
+ if ! conntrack -I -s \$((\$RANDOM%256)).\$((\$RANDOM%256)).\$((\$RANDOM%256)).\$((\$RANDOM%255+1)) \
+ -d \$((\$RANDOM%256)).\$((\$RANDOM%256)).\$((\$RANDOM%256)).\$((\$RANDOM%255+1)) \
+ --protonum 17 --timeout 3600 --status ASSURED,SEEN_REPLY --sport \$RANDOM --dport 53; then \
+ return;\
+ fi & \
+ done ; wait" 2>/dev/null
+
+ i=$((i+bulk))
+ done
+}
+
+check_ctcount() {
+ local ns="$1"
+ local count="$2"
+ local msg="$3"
+
+ local now=$(ip netns exec "$ns" conntrack -C)
+
+ if [ $now -ne "$count" ] ;then
+ echo "expected $count entries in $ns, not $now: $msg"
+ exit 1
+ fi
+
+ echo "PASS: got $count connections: $msg"
+}
+
+ctresize() {
+ local duration="$1"
+ local now=$(date +%s)
+ local end=$((now + duration))
+
+ while [ $now -lt $end ]; do
+ sysctl -q net.netfilter.nf_conntrack_buckets=$RANDOM
+ now=$(date +%s)
+ done
+}
+
+do_rsleep() {
+ local limit="$1"
+ local r=$RANDOM
+
+ r=$((r%limit))
+ sleep "$r"
+}
+
+ct_flush_once() {
+ local ns="$1"
+
+ ip netns exec "$ns" conntrack -F 2>/dev/null
+}
+
+ctflush() {
+ local ns="$1"
+ local duration="$2"
+ local now=$(date +%s)
+ local end=$((now + duration))
+
+ do_rsleep "$duration"
+
+ while [ $now -lt $end ]; do
+ ct_flush_once "$ns"
+ do_rsleep "$duration"
+ now=$(date +%s)
+ done
+}
+
+ctflood()
+{
+ local ns="$1"
+ local duration="$2"
+ local msg="$3"
+ local now=$(date +%s)
+ local end=$((now + duration))
+ local j=0
+ local k=0
+
+ while [ $now -lt $end ]; do
+ j=$((j%256))
+ k=$((k%256))
+
+ ip netns exec "$ns" bash -c \
+ "j=$j k=$k; for i in \$(seq 1 254); do ping -q -c 1 127.\$k.\$j.\$i & done; wait" >/dev/null 2>&1
+
+ j=$((j+1))
+
+ if [ $j -eq 256 ];then
+ k=$((k+1))
+ fi
+
+ now=$(date +%s)
+ done
+
+ wait
+}
+
+# dump to /dev/null. We don't want dumps to cause infinite loops
+# or use-after-free even when conntrack table is altered while dumps
+# are in progress.
+ct_nulldump()
+{
+ local ns="$1"
+
+ ip netns exec "$ns" conntrack -L > /dev/null 2>&1 &
+
+ # Don't require /proc support in conntrack
+ if [ -r /proc/self/net/nf_conntrack ] ; then
+ ip netns exec "$ns" bash -c "wc -l < /proc/self/net/nf_conntrack" > /dev/null &
+ fi
+
+ wait
+}
+
+check_taint()
+{
+ local tainted_then="$1"
+ local msg="$2"
+
+ local tainted_now=0
+
+ if [ "$tainted_then" -ne 0 ];then
+ return
+ fi
+
+ read tainted_now < /proc/sys/kernel/tainted
+
+ if [ "$tainted_now" -eq 0 ];then
+ echo "PASS: $msg"
+ else
+ echo "TAINT: $msg"
+ dmesg
+ exit 1
+ fi
+}
+
+insert_flood()
+{
+ local n="$1"
+ local r=0
+
+ r=$((RANDOM%$insert_count))
+
+ ctflood "$n" "$timeout" "floodresize" &
+ insert_ctnetlink "$n" "$r" &
+ ctflush "$n" "$timeout" &
+ ct_nulldump "$n" &
+
+ wait
+}
+
+test_floodresize_all()
+{
+ local timeout=20
+ local n=""
+ local tainted_then=""
+
+ read tainted_then < /proc/sys/kernel/tainted
+
+ for n in "$nsclient1" "$nsclient2";do
+ insert_flood "$n" &
+ done
+
+ # resize table constantly while flood/insert/dump/flushs
+ # are happening in parallel.
+ ctresize "$timeout"
+
+ # wait for subshells to complete, everything is limited
+ # by $timeout.
+ wait
+
+ check_taint "$tainted_then" "resize+flood"
+}
+
+check_dump()
+{
+ local ns="$1"
+ local protoname="$2"
+ local c=0
+ local proto=0
+ local proc=0
+ local unique=""
+ local lret=0
+
+ # NOTE: assumes timeouts are large enough to not have
+ # expirations in all following tests.
+ l=$(ip netns exec "$ns" conntrack -L 2>/dev/null | sort | tee "$tmpfile" | wc -l)
+ c=$(ip netns exec "$ns" conntrack -C)
+
+ if [ "$c" -eq 0 ]; then
+ echo "FAIL: conntrack count for $ns is 0"
+ lret=1
+ fi
+
+ if [ "$c" -ne "$l" ]; then
+ echo "FAIL: conntrack count inconsistency for $ns -L: $c != $l"
+ lret=1
+ fi
+
+ # check the dump we retrieved is free of duplicated entries.
+ unique=$(uniq "$tmpfile" | tee "$tmpfile_uniq" | wc -l)
+ if [ "$l" -ne "$unique" ]; then
+ echo "FAIL: listing contained redundant entries for $ns: $l != $unique"
+ diff -u "$tmpfile" "$tmpfile_uniq"
+ lret=1
+ fi
+
+ # we either inserted icmp or only udp, hence, --proto should return same entry count as without filter.
+ proto=$(ip netns exec "$ns" conntrack -L --proto $protoname 2>/dev/null | sort | uniq | tee "$tmpfile_uniq" | wc -l)
+ if [ "$l" -ne "$proto" ]; then
+ echo "FAIL: dump inconsistency for $ns -L --proto $protoname: $l != $proto"
+ diff -u "$tmpfile" "$tmpfile_uniq"
+ lret=1
+ fi
+
+ if [ -r /proc/self/net/nf_conntrack ] ; then
+ proc=$(ip netns exec "$ns" bash -c "sort < /proc/self/net/nf_conntrack | tee \"$tmpfile_proc\" | wc -l")
+
+ if [ "$l" -ne "$proc" ]; then
+ echo "FAIL: proc inconsistency for $ns: $l != $proc"
+ lret=1
+ fi
+
+ proc=$(uniq "$tmpfile_proc" | tee "$tmpfile_uniq" | wc -l)
+ if [ "$l" -ne "$proc" ]; then
+ echo "FAIL: proc inconsistency after uniq filter for $ns: $l != $proc"
+ diff -u "$tmpfile_proc" "$tmpfile_uniq"
+ lret=1
+ fi
+ fi
+
+ if [ $lret -eq 0 ];then
+ echo "PASS: dump in netns $ns had same entry count (-C $c, -L $l, -p $proto, /proc $proc)"
+ else
+ echo "FAIL: dump in netns $ns had different entry count (-C $c, -L $l, -p $proto, /proc $proc)"
+ ret=1
+ fi
+}
+
+test_dump_all()
+{
+ local timeout=3
+ local tainted_then=""
+
+ read tainted_then < /proc/sys/kernel/tainted
+
+ ct_flush_once "$nsclient1"
+ ct_flush_once "$nsclient2"
+
+ ip netns exec "$nsclient1" sysctl -q net.netfilter.nf_conntrack_icmp_timeout=3600
+
+ ctflood "$nsclient1" $timeout "dumpall" &
+ insert_ctnetlink "$nsclient2" $insert_count
+
+ wait
+
+ check_dump "$nsclient1" "icmp"
+ check_dump "$nsclient2" "udp"
+
+ check_taint "$tainted_then" "test parallel conntrack dumps"
+}
+
+check_sysctl_immutable()
+{
+ local ns="$1"
+ local name="$2"
+ local failhard="$3"
+ local o=0
+ local n=0
+
+ o=$(ip netns exec "$ns" sysctl -n "$name" 2>/dev/null)
+ n=$((o+1))
+
+ # return value isn't reliable, need to read it back
+ ip netns exec "$ns" sysctl -q "$name"=$n 2>/dev/null >/dev/null
+
+ n=$(ip netns exec "$ns" sysctl -n "$name" 2>/dev/null)
+
+ [ -z "$n" ] && return 1
+
+ if [ $o -ne $n ]; then
+ if [ $failhard -gt 0 ] ;then
+ echo "FAIL: net.$name should not be changeable from namespace (now $n)"
+ ret=1
+ fi
+ return 0
+ fi
+
+ return 1
+}
+
+test_conntrack_max_limit()
+{
+ sysctl -q net.netfilter.nf_conntrack_max=100
+ insert_ctnetlink "$nsclient1" 101
+
+ # check netns is clamped by init_net, i.e., either netns follows
+ # init_net value, or a higher pernet limit (compared to init_net) is ignored.
+ check_ctcount "$nsclient1" 100 "netns conntrack_max is init_net bound"
+
+ sysctl -q net.netfilter.nf_conntrack_max=$init_net_max
+}
+
+test_conntrack_disable()
+{
+ local timeout=2
+
+ # disable conntrack pickups
+ ip netns exec "$nsclient1" nft flush table ip test_ct
+
+ ct_flush_once "$nsclient1"
+ ct_flush_once "$nsclient2"
+
+ ctflood "$nsclient1" "$timeout" "conntrack disable"
+ ip netns exec "$nsclient2" ping -q -c 1 127.0.0.1 >/dev/null 2>&1
+
+ # Disabled, should not have picked up any connection.
+ check_ctcount "$nsclient1" 0 "conntrack disabled"
+
+ # This one is still active, expect 1 connection.
+ check_ctcount "$nsclient2" 1 "conntrack enabled"
+}
+
+init_net_max=$(sysctl -n net.netfilter.nf_conntrack_max)
+
+check_max_alias $init_net_max
+
+sysctl -q net.netfilter.nf_conntrack_max="262000"
+check_max_alias 262000
+
+setup_ns nsclient1 nsclient2
+
+# check this only works from init_net
+for n in netfilter.nf_conntrack_buckets netfilter.nf_conntrack_expect_max net.nf_conntrack_max;do
+ check_sysctl_immutable "$nsclient1" "net.$n" 1
+done
+
+# won't work on older kernels. If it works, check that the netns obeys the limit
+if check_sysctl_immutable "$nsclient1" net.netfilter.nf_conntrack_max 0;then
+ # subtest: if pernet is changeable, check that reducing it in pernet
+ # limits the pernet entries. Inverse, pernet clamped by a lower init_net
+ # setting, is already checked by "test_conntrack_max_limit" test.
+
+ ip netns exec "$nsclient1" sysctl -q net.netfilter.nf_conntrack_max=1
+ insert_ctnetlink "$nsclient1" 2
+ check_ctcount "$nsclient1" 1 "netns conntrack_max is pernet bound"
+ ip netns exec "$nsclient1" sysctl -q net.netfilter.nf_conntrack_max=$init_net_max
+fi
+
+for n in "$nsclient1" "$nsclient2";do
+# enable conntrack in both namespaces
+ip netns exec "$n" nft -f - <<EOF
+table ip test_ct {
+ chain input {
+ type filter hook input priority 0
+ ct state new counter
+ }
+}
+EOF
+done
+
+tmpfile=$(mktemp)
+tmpfile_proc=$(mktemp)
+tmpfile_uniq=$(mktemp)
+test_conntrack_max_limit
+test_dump_all
+test_floodresize_all
+test_conntrack_disable
+
+exit $ret
diff --git a/tools/testing/selftests/net/netfilter/conntrack_vrf.sh b/tools/testing/selftests/net/netfilter/conntrack_vrf.sh
index e95ecb37c2b1..207b79932d91 100755
--- a/tools/testing/selftests/net/netfilter/conntrack_vrf.sh
+++ b/tools/testing/selftests/net/netfilter/conntrack_vrf.sh
@@ -32,7 +32,6 @@ source lib.sh
IP0=172.30.30.1
IP1=172.30.30.2
-DUMMYNET=10.9.9
PFXL=30
ret=0
@@ -52,11 +51,6 @@ trap cleanup EXIT
setup_ns ns0 ns1
-ip netns exec "$ns0" sysctl -q -w net.ipv4.conf.default.rp_filter=0
-ip netns exec "$ns0" sysctl -q -w net.ipv4.conf.all.rp_filter=0
-ip netns exec "$ns0" sysctl -q -w net.ipv4.conf.all.rp_filter=0
-ip netns exec "$ns0" sysctl -q -w net.ipv4.conf.all.forwarding=1
-
if ! ip link add veth0 netns "$ns0" type veth peer name veth0 netns "$ns1" > /dev/null 2>&1; then
echo "SKIP: Could not add veth device"
exit $ksft_skip
@@ -67,18 +61,13 @@ if ! ip -net "$ns0" li add tvrf type vrf table 9876; then
exit $ksft_skip
fi
-ip -net "$ns0" link add dummy0 type dummy
-
ip -net "$ns0" li set veth0 master tvrf
-ip -net "$ns0" li set dummy0 master tvrf
ip -net "$ns0" li set tvrf up
ip -net "$ns0" li set veth0 up
-ip -net "$ns0" li set dummy0 up
ip -net "$ns1" li set veth0 up
ip -net "$ns0" addr add $IP0/$PFXL dev veth0
ip -net "$ns1" addr add $IP1/$PFXL dev veth0
-ip -net "$ns0" addr add $DUMMYNET.1/$PFXL dev dummy0
listener_ready()
{
@@ -219,35 +208,9 @@ EOF
fi
}
-test_fib()
-{
-ip netns exec "$ns0" nft -f - <<EOF
-flush ruleset
-table ip t {
- counter fibcount { }
-
- chain prerouting {
- type filter hook prerouting priority 0;
- meta iifname veth0 ip daddr $DUMMYNET.2 fib daddr oif dummy0 counter name fibcount notrack
- }
-}
-EOF
- ip -net "$ns1" route add 10.9.9.0/24 via "$IP0" dev veth0
- ip netns exec "$ns1" ping -q -w 1 -c 1 "$DUMMYNET".2 > /dev/null
-
- if ip netns exec "$ns0" nft list counter t fibcount | grep -q "packets 1"; then
- echo "PASS: fib lookup returned exepected output interface"
- else
- echo "FAIL: fib lookup did not return exepected output interface"
- ret=1
- return
- fi
-}
-
test_ct_zone_in
test_masquerade_vrf "default"
test_masquerade_vrf "pfifo"
test_masquerade_veth
-test_fib
exit $ret
diff --git a/tools/testing/selftests/net/netfilter/ipvs.sh b/tools/testing/selftests/net/netfilter/ipvs.sh
index d3edb16cd4b3..6af2ea3ad6b8 100755
--- a/tools/testing/selftests/net/netfilter/ipvs.sh
+++ b/tools/testing/selftests/net/netfilter/ipvs.sh
@@ -129,9 +129,6 @@ test_dr() {
# avoid incorrect arp response
ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.arp_ignore=1
ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.arp_announce=2
- # avoid reverse route lookup
- ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.rp_filter=0
- ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.veth21.rp_filter=0
ip netns exec "${ns2}" ip addr add "${vip_v4}/32" dev lo:1
test_service
@@ -167,9 +164,6 @@ test_tun() {
ip netns exec "${ns2}" ip link set tunl0 up
ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.arp_ignore=1
ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.arp_announce=2
- ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.rp_filter=0
- ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.tunl0.rp_filter=0
- ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.veth21.rp_filter=0
ip netns exec "${ns2}" ip addr add "${vip_v4}/32" dev lo:1
test_service
diff --git a/tools/testing/selftests/net/netfilter/nft_concat_range.sh b/tools/testing/selftests/net/netfilter/nft_concat_range.sh
index 47088b005390..efea93cf23d4 100755
--- a/tools/testing/selftests/net/netfilter/nft_concat_range.sh
+++ b/tools/testing/selftests/net/netfilter/nft_concat_range.sh
@@ -15,10 +15,12 @@ source lib.sh
# Available test groups:
# - reported_issues: check for issues that were reported in the past
# - correctness: check that packets match given entries, and only those
+# - correctness_large: same but with additional non-matching entries
# - concurrency: attempt races between insertion, deletion and lookup
# - timeout: check that packets match entries until they expire
# - performance: estimate matching rate, compare with rbtree and hash baselines
-TESTS="reported_issues correctness concurrency timeout"
+TESTS="reported_issues correctness correctness_large concurrency timeout"
+
[ -n "$NFT_CONCAT_RANGE_TESTS" ] && TESTS="${NFT_CONCAT_RANGE_TESTS}"
# Set types, defined by TYPE_ variables below
@@ -27,7 +29,7 @@ TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto
net6_port_net6_port net_port_mac_proto_net"
# Reported bugs, also described by TYPE_ variables below
-BUGS="flush_remove_add reload net_port_proto_match"
+BUGS="flush_remove_add reload net_port_proto_match avx2_mismatch"
# List of possible paths to pktgen script from kernel tree for performance tests
PKTGEN_SCRIPT_PATHS="
@@ -387,6 +389,25 @@ race_repeat 0
perf_duration 0
"
+
+TYPE_avx2_mismatch="
+display avx2 false match
+type_spec inet_proto . ipv6_addr
+chain_spec meta l4proto . ip6 daddr
+dst proto addr6
+src
+start 1
+count 1
+src_delta 1
+tools ping
+proto icmp6
+
+race_repeat 0
+
+perf_duration 0
+"
+
+
# Set template for all tests, types and rules are filled in depending on test
set_template='
flush ruleset
@@ -1238,9 +1259,7 @@ send_nomatch() {
# - add ranged element, check that packets match it
# - check that packets outside range don't match it
# - remove some elements, check that packets don't match anymore
-test_correctness() {
- setup veth send_"${proto}" set || return ${ksft_skip}
-
+test_correctness_main() {
range_size=1
for i in $(seq "${start}" $((start + count))); do
end=$((start + range_size))
@@ -1274,6 +1293,163 @@ test_correctness() {
done
}
+test_correctness() {
+ setup veth send_"${proto}" set || return ${ksft_skip}
+
+ test_correctness_main
+}
+
+# Repeat the correctness tests, but add extra non-matching entries.
+# This exercises the more compact '4 bit group' representation that
+# gets picked when the default 8-bit representation exceed
+# NFT_PIPAPO_LT_SIZE_HIGH bytes of memory.
+# See usage of NFT_PIPAPO_LT_SIZE_HIGH in pipapo_lt_bits_adjust().
+#
+# The format() helper is way too slow when generating lots of
+# entries so its not used here.
+test_correctness_large() {
+ setup veth send_"${proto}" set || return ${ksft_skip}
+ # number of dummy (filler) entries to add.
+ local dcount=16385
+
+ (
+ echo -n "add element inet filter test { "
+
+ case "$type_spec" in
+ "ether_addr . ipv4_addr")
+ for i in $(seq 1 $dcount); do
+ [ $i -gt 1 ] && echo ", "
+ format_mac $((1000000 + i))
+ printf ". 172.%i.%i.%i " $((RANDOM%256)) $((RANDOM%256)) $((i%256))
+ done
+ ;;
+ "inet_proto . ipv6_addr")
+ for i in $(seq 1 $dcount); do
+ [ $i -gt 1 ] && echo ", "
+ printf "%i . " $((RANDOM%256))
+ format_addr6 $((1000000 + i))
+ done
+ ;;
+ "inet_service . inet_proto")
+ # smaller key sizes, need more entries to hit the
+ # 4-bit threshold.
+ dcount=65536
+ for i in $(seq 1 $dcount); do
+ local proto=$((RANDOM%256))
+
+ # Test uses UDP to match, as it also fails when matching
+ # an entry that doesn't exist, so skip 'udp' entries
+ # to not trigger a wrong failure.
+ [ $proto -eq 17 ] && proto=18
+ [ $i -gt 1 ] && echo ", "
+ printf "%i . %i " $(((i%65534) + 1)) $((proto))
+ done
+ ;;
+ "inet_service . ipv4_addr")
+ dcount=32768
+ for i in $(seq 1 $dcount); do
+ [ $i -gt 1 ] && echo ", "
+ printf "%i . 172.%i.%i.%i " $(((RANDOM%65534) + 1)) $((RANDOM%256)) $((RANDOM%256)) $((i%256))
+ done
+ ;;
+ "ipv4_addr . ether_addr")
+ for i in $(seq 1 $dcount); do
+ [ $i -gt 1 ] && echo ", "
+ printf "172.%i.%i.%i . " $((RANDOM%256)) $((RANDOM%256)) $((i%256))
+ format_mac $((1000000 + i))
+ done
+ ;;
+ "ipv4_addr . inet_service")
+ dcount=32768
+ for i in $(seq 1 $dcount); do
+ [ $i -gt 1 ] && echo ", "
+ printf "172.%i.%i.%i . %i" $((RANDOM%256)) $((RANDOM%256)) $((i%256)) $(((RANDOM%65534) + 1))
+ done
+ ;;
+ "ipv4_addr . inet_service . ether_addr . inet_proto . ipv4_addr")
+ dcount=65536
+ for i in $(seq 1 $dcount); do
+ [ $i -gt 1 ] && echo ", "
+ printf "172.%i.%i.%i . %i . " $((RANDOM%256)) $((RANDOM%256)) $((i%256)) $(((RANDOM%65534) + 1))
+ format_mac $((1000000 + i))
+ printf ". %i . 192.168.%i.%i" $((RANDOM%256)) $((RANDOM%256)) $((i%256))
+ done
+ ;;
+ "ipv4_addr . inet_service . inet_proto")
+ for i in $(seq 1 $dcount); do
+ [ $i -gt 1 ] && echo ", "
+ printf "172.%i.%i.%i . %i . %i " $((RANDOM%256)) $((RANDOM%256)) $((i%256)) $(((RANDOM%65534) + 1)) $((RANDOM%256))
+ done
+ ;;
+ "ipv4_addr . inet_service . inet_proto . ipv4_addr")
+ for i in $(seq 1 $dcount); do
+ [ $i -gt 1 ] && echo ", "
+ printf "172.%i.%i.%i . %i . %i . 192.168.%i.%i " $((RANDOM%256)) $((RANDOM%256)) $((i%256)) $(((RANDOM%65534) + 1)) $((RANDOM%256)) $((RANDOM%256)) $((RANDOM%256))
+ done
+ ;;
+ "ipv4_addr . inet_service . ipv4_addr")
+ dcount=32768
+ for i in $(seq 1 $dcount); do
+ [ $i -gt 1 ] && echo ", "
+ printf "172.%i.%i.%i . %i . 192.168.%i.%i " $((RANDOM%256)) $((RANDOM%256)) $((i%256)) $(((RANDOM%65534) + 1)) $((RANDOM%256)) $((RANDOM%256))
+ done
+ ;;
+ "ipv6_addr . ether_addr")
+ for i in $(seq 1 $dcount); do
+ [ $i -gt 1 ] && echo ", "
+ format_addr6 $((i + 1000000))
+ echo -n " . "
+ format_mac $((1000000 + i))
+ done
+ ;;
+ "ipv6_addr . inet_service")
+ dcount=32768
+ for i in $(seq 1 $dcount); do
+ [ $i -gt 1 ] && echo ", "
+ format_addr6 $((i + 1000000))
+ echo -n " . $(((RANDOM%65534) + 1))"
+ done
+ ;;
+ "ipv6_addr . inet_service . ether_addr")
+ dcount=32768
+ for i in $(seq 1 $dcount); do
+ [ $i -gt 1 ] && echo ", "
+ format_addr6 $((i + 1000000))
+ echo -n " . $(((RANDOM%65534) + 1)) . "
+ format_mac $((i + 1000000))
+ done
+ ;;
+ "ipv6_addr . inet_service . ether_addr . inet_proto")
+ dcount=65536
+ for i in $(seq 1 $dcount); do
+ [ $i -gt 1 ] && echo ", "
+ format_addr6 $((i + 1000000))
+ echo -n " . $(((RANDOM%65534) + 1)) . "
+ format_mac $((i + 1000000))
+ echo -n " . $((RANDOM%256))"
+ done
+ ;;
+ "ipv6_addr . inet_service . ipv6_addr . inet_service")
+ dcount=32768
+ for i in $(seq 1 $dcount); do
+ [ $i -gt 1 ] && echo ", "
+ format_addr6 $((i + 1000000))
+ echo -n " . $(((RANDOM%65534) + 1)) . "
+ format_addr6 $((i + 2123456))
+ echo -n " . $((RANDOM%256))"
+ done
+ ;;
+ *)
+ "Unhandled $type_spec"
+ return 1
+ esac
+ echo -n "}"
+
+ ) | nft -f - || return 1
+
+ test_correctness_main
+}
+
# Concurrency test template:
# - add all the elements
# - start a thread for each physical thread that:
@@ -1629,6 +1805,24 @@ test_bug_net_port_proto_match() {
nft flush ruleset
}
+test_bug_avx2_mismatch()
+{
+ setup veth send_"${proto}" set || return ${ksft_skip}
+
+ local a1="fe80:dead:01ff:0a02:0b03:6007:8009:a001"
+ local a2="fe80:dead:01fe:0a02:0b03:6007:8009:a001"
+
+ nft "add element inet filter test { icmpv6 . $a1 }"
+
+ dst_addr6="$a2"
+ send_icmp6
+
+ if [ "$(count_packets)" -gt "0" ]; then
+ err "False match for $a2"
+ return 1
+ fi
+}
+
test_reported_issues() {
eval test_bug_"${subtest}"
}
diff --git a/tools/testing/selftests/net/netfilter/nft_fib.sh b/tools/testing/selftests/net/netfilter/nft_fib.sh
index ce1451c275fd..9929a9ffef65 100755
--- a/tools/testing/selftests/net/netfilter/nft_fib.sh
+++ b/tools/testing/selftests/net/netfilter/nft_fib.sh
@@ -3,6 +3,10 @@
# This tests the fib expression.
#
# Kselftest framework requirement - SKIP code is 4.
+#
+# 10.0.1.99 10.0.1.1 10.0.2.1 10.0.2.99
+# dead:1::99 dead:1::1 dead:2::1 dead:2::99
+# ns1 <-------> [ veth0 ] nsrouter [veth1] <-------> ns2
source lib.sh
@@ -45,6 +49,19 @@ table inet filter {
EOF
}
+load_input_ruleset() {
+ local netns=$1
+
+ip netns exec "$netns" nft -f /dev/stdin <<EOF
+table inet filter {
+ chain input {
+ type filter hook input priority 0; policy accept;
+ fib saddr . iif oif missing counter log prefix "$netns nft_rpfilter: " drop
+ }
+}
+EOF
+}
+
load_pbr_ruleset() {
local netns=$1
@@ -59,6 +76,89 @@ table inet filter {
EOF
}
+load_type_ruleset() {
+ local netns=$1
+
+ for family in ip ip6;do
+ip netns exec "$netns" nft -f /dev/stdin <<EOF
+table $family filter {
+ chain type_match_in {
+ fib daddr type local counter comment "daddr configured on other iface"
+ fib daddr . iif type local counter comment "daddr configured on iif"
+ fib daddr type unicast counter comment "daddr not local"
+ fib daddr . iif type unicast counter comment "daddr not configured on iif"
+ }
+
+ chain type_match_out {
+ fib daddr type unicast counter
+ fib daddr . oif type unicast counter
+ fib daddr type local counter
+ fib daddr . oif type local counter
+ }
+
+ chain prerouting {
+ type filter hook prerouting priority 0;
+ icmp type echo-request counter jump type_match_in
+ icmpv6 type echo-request counter jump type_match_in
+ }
+
+ chain input {
+ type filter hook input priority 0;
+ icmp type echo-request counter jump type_match_in
+ icmpv6 type echo-request counter jump type_match_in
+ }
+
+ chain forward {
+ type filter hook forward priority 0;
+ icmp type echo-request counter jump type_match_in
+ icmpv6 type echo-request counter jump type_match_in
+ }
+
+ chain output {
+ type filter hook output priority 0;
+ icmp type echo-request counter jump type_match_out
+ icmpv6 type echo-request counter jump type_match_out
+ }
+
+ chain postrouting {
+ type filter hook postrouting priority 0;
+ icmp type echo-request counter jump type_match_out
+ icmpv6 type echo-request counter jump type_match_out
+ }
+}
+EOF
+done
+}
+
+reload_type_ruleset() {
+ ip netns exec "$1" nft flush table ip filter
+ ip netns exec "$1" nft flush table ip6 filter
+ load_type_ruleset "$1"
+}
+
+check_fib_type_counter_family() {
+ local family="$1"
+ local want="$2"
+ local ns="$3"
+ local chain="$4"
+ local what="$5"
+ local errmsg="$6"
+
+ if ! ip netns exec "$ns" nft list chain "$family" filter "$chain" | grep "$what" | grep -q "packets $want";then
+ echo "Netns $ns $family fib type counter doesn't match expected packet count of $want for $what $errmsg" 1>&2
+ ip netns exec "$ns" nft list chain "$family" filter "$chain"
+ ret=1
+ return 1
+ fi
+
+ return 0
+}
+
+check_fib_type_counter() {
+ check_fib_type_counter_family "ip" "$@" || return 1
+ check_fib_type_counter_family "ip6" "$@" || return 1
+}
+
load_ruleset_count() {
local netns=$1
@@ -77,6 +177,7 @@ check_drops() {
if dmesg | grep -q ' nft_rpfilter: ';then
dmesg | grep ' nft_rpfilter: '
echo "FAIL: rpfilter did drop packets"
+ ret=1
return 1
fi
@@ -151,19 +252,506 @@ test_ping() {
return 0
}
+test_ping_unreachable() {
+ local daddr4=$1
+ local daddr6=$2
+
+ if ip netns exec "$ns1" ping -c 1 -w 1 -q "$daddr4" > /dev/null; then
+ echo "FAIL: ${ns1} could reach $daddr4" 1>&2
+ return 1
+ fi
+
+ if ip netns exec "$ns1" ping -c 1 -w 1 -q "$daddr6" > /dev/null; then
+ echo "FAIL: ${ns1} could reach $daddr6" 1>&2
+ return 1
+ fi
+
+ return 0
+}
+
+test_fib_type() {
+ local notice="$1"
+ local errmsg="addr-on-if"
+ local lret=0
+
+ if ! load_type_ruleset "$nsrouter";then
+ echo "SKIP: Could not load fib type ruleset"
+ [ $ret -eq 0 ] && ret=$ksft_skip
+ return
+ fi
+
+ # makes router receive packet for addresses configured on incoming
+ # interface.
+ test_ping 10.0.1.1 dead:1::1 || return 1
+
+ # expectation: triggers all 'local' in prerouting/input.
+ check_fib_type_counter 2 "$nsrouter" "type_match_in" "fib daddr type local" "$errmsg" || lret=1
+ check_fib_type_counter 2 "$nsrouter" "type_match_in" "fib daddr . iif type local" "$errmsg" || lret=1
+
+ reload_type_ruleset "$nsrouter"
+ # makes router receive packet for address configured on a different (but local)
+ # interface.
+ test_ping 10.0.2.1 dead:2::1 || return 1
+
+ # expectation: triggers 'unicast' in prerouting/input for daddr . iif and local for 'daddr'.
+ errmsg="addr-on-host"
+ check_fib_type_counter 2 "$nsrouter" "type_match_in" "fib daddr type local" "$errmsg" || lret=1
+ check_fib_type_counter 2 "$nsrouter" "type_match_in" "fib daddr . iif type unicast" "$errmsg" || lret=1
+
+ reload_type_ruleset "$nsrouter"
+ test_ping 10.0.2.99 dead:2::99 || return 1
+ errmsg="addr-on-otherhost"
+ check_fib_type_counter 2 "$nsrouter" "type_match_in" "fib daddr type unicast" "$errmsg" || lret=1
+ check_fib_type_counter 2 "$nsrouter" "type_match_in" "fib daddr . iif type unicast" "$errmsg" || lret=1
+
+ if [ $lret -eq 0 ];then
+ echo "PASS: fib expression address types match ($notice)"
+ else
+ echo "FAIL: fib expression address types match ($notice)"
+ ret=1
+ fi
+}
+
+test_fib_vrf_dev_add_dummy()
+{
+ if ! ip -net "$nsrouter" link add dummy0 type dummy ;then
+ echo "SKIP: VRF tests: dummy device type not supported"
+ return 1
+ fi
+
+ if ! ip -net "$nsrouter" link add tvrf type vrf table 9876;then
+ echo "SKIP: VRF tests: vrf device type not supported"
+ return 1
+ fi
+
+ ip -net "$nsrouter" link set dummy0 master tvrf
+ ip -net "$nsrouter" link set dummy0 up
+ ip -net "$nsrouter" link set tvrf up
+}
+
+load_ruleset_vrf()
+{
+# Due to the many different possible combinations using named counters
+# or one-rule-per-expected-result is complex.
+#
+# Instead, add dynamic sets for the fib modes
+# (fib address type, fib output interface lookup .. ),
+# and then add the obtained fib results to them.
+#
+# The test is successful if the sets contain the expected results
+# and no unexpected extra entries existed.
+ip netns exec "$nsrouter" nft -f - <<EOF
+flush ruleset
+table inet t {
+ set fibif4 {
+ typeof meta iif . ip daddr . fib daddr oif
+ flags dynamic
+ counter
+ }
+
+ set fibif4iif {
+ typeof meta iif . ip daddr . fib daddr . iif oif
+ flags dynamic
+ counter
+ }
+
+ set fibif6 {
+ typeof meta iif . ip6 daddr . fib daddr oif
+ flags dynamic
+ counter
+ }
+
+ set fibif6iif {
+ typeof meta iif . ip6 daddr . fib daddr . iif oif
+ flags dynamic
+ counter
+ }
+
+ set fibtype4 {
+ typeof meta iif . ip daddr . fib daddr type
+ flags dynamic
+ counter
+ }
+
+ set fibtype4iif {
+ typeof meta iif . ip daddr . fib daddr . iif type
+ flags dynamic
+ counter
+ }
+
+ set fibtype6 {
+ typeof meta iif . ip6 daddr . fib daddr type
+ flags dynamic
+ counter
+ }
+
+ set fibtype6iif {
+ typeof meta iif . ip6 daddr . fib daddr . iif type
+ flags dynamic
+ counter
+ }
+
+ chain fib_test {
+ meta nfproto ipv4 jump {
+ add @fibif4 { meta iif . ip daddr . fib daddr oif }
+ add @fibif4iif { meta iif . ip daddr . fib daddr . iif oif }
+ add @fibtype4 { meta iif . ip daddr . fib daddr type }
+ add @fibtype4iif { meta iif . ip daddr . fib daddr . iif type }
+
+ add @fibif4 { meta iif . ip saddr . fib saddr oif }
+ add @fibif4iif { meta iif . ip saddr . fib saddr . iif oif }
+ }
+
+ meta nfproto ipv6 jump {
+ add @fibif6 { meta iif . ip6 daddr . fib daddr oif }
+ add @fibif6iif { meta iif . ip6 daddr . fib daddr . iif oif }
+ add @fibtype6 { meta iif . ip6 daddr . fib daddr type }
+ add @fibtype6iif { meta iif . ip6 daddr . fib daddr . iif type }
+
+ add @fibif6 { meta iif . ip6 saddr . fib saddr oif }
+ add @fibif6iif { meta iif . ip6 saddr . fib saddr . iif oif }
+ }
+ }
+
+ chain prerouting {
+ type filter hook prerouting priority 0;
+ icmp type echo-request counter jump fib_test
+
+ # neighbour discovery to be ignored.
+ icmpv6 type echo-request counter jump fib_test
+ }
+}
+EOF
+
+if [ $? -ne 0 ] ;then
+ echo "SKIP: Could not load ruleset for fib vrf test"
+ [ $ret -eq 0 ] && ret=$ksft_skip
+ return 1
+fi
+}
+
+check_type()
+{
+ local setname="$1"
+ local iifname="$2"
+ local addr="$3"
+ local type="$4"
+ local count="$5"
+
+ [ -z "$count" ] && count=1
+
+ if ! ip netns exec "$nsrouter" nft get element inet t "$setname" { "$iifname" . "$addr" . "$type" } |grep -q "counter packets $count";then
+ echo "FAIL: did not find $iifname . $addr . $type in $setname"
+ ip netns exec "$nsrouter" nft list set inet t "$setname"
+ ret=1
+ return 1
+ fi
+
+ # delete the entry, this allows to check if anything unexpected appeared
+ # at the end of the test run: all dynamic sets should be empty by then.
+ if ! ip netns exec "$nsrouter" nft delete element inet t "$setname" { "$iifname" . "$addr" . "$type" } ; then
+ echo "FAIL: can't delete $iifname . $addr . $type in $setname"
+ ip netns exec "$nsrouter" nft list set inet t "$setname"
+ ret=1
+ return 1
+ fi
+
+ return 0
+}
+
+check_local()
+{
+ check_type $@ "local" 1
+}
+
+check_unicast()
+{
+ check_type $@ "unicast" 1
+}
+
+check_rpf()
+{
+ check_type $@
+}
+
+check_fib_vrf_sets_empty()
+{
+ local setname=""
+ local lret=0
+
+ # A non-empty set means that we have seen unexpected packets OR
+ # that a fib lookup provided unexpected results.
+ for setname in "fibif4" "fibif4iif" "fibif6" "fibif6iif" \
+ "fibtype4" "fibtype4iif" "fibtype6" "fibtype6iif";do
+ if ip netns exec "$nsrouter" nft list set inet t "$setname" | grep -q elements;then
+ echo "FAIL: $setname not empty"
+ ip netns exec "$nsrouter" nft list set inet t "$setname"
+ ret=1
+ lret=1
+ fi
+ done
+
+ return $lret
+}
+
+check_fib_vrf_type()
+{
+ local msg="$1"
+
+ local addr
+ # the incoming interface is always veth0. As its not linked to a VRF,
+ # the 'tvrf' device should NOT show up anywhere.
+ local ifname="veth0"
+ local lret=0
+
+ # local_veth0, local_veth1
+ for addr in "10.0.1.1" "10.0.2.1"; do
+ check_local fibtype4 "$ifname" "$addr" || lret=1
+ check_type fibif4 "$ifname" "$addr" "0" || lret=1
+ done
+ for addr in "dead:1::1" "dead:2::1";do
+ check_local fibtype6 "$ifname" "$addr" || lret=1
+ check_type fibif6 "$ifname" "$addr" "0" || lret=1
+ done
+
+ # when restricted to the incoming interface, 10.0.1.1 should
+ # be 'local', but 10.0.2.1 unicast.
+ check_local fibtype4iif "$ifname" "10.0.1.1" || lret=1
+ check_unicast fibtype4iif "$ifname" "10.0.2.1" || lret=1
+
+ # same for the ipv6 addresses.
+ check_local fibtype6iif "$ifname" "dead:1::1" || lret=1
+ check_unicast fibtype6iif "$ifname" "dead:2::1" || lret=1
+
+ # None of these addresses should find a valid route when restricting
+ # to the incoming interface (we ask for daddr - 10.0.1.1/2.1 are
+ # reachable via 'lo'.
+ for addr in "10.0.1.1" "10.0.2.1" "10.9.9.1" "10.9.9.2";do
+ check_type fibif4iif "$ifname" "$addr" "0" || lret=1
+ done
+
+ # expect default route (veth1), dummy0 is part of VRF but iif isn't.
+ for addr in "10.9.9.1" "10.9.9.2";do
+ check_unicast fibtype4 "$ifname" "$addr" || lret=1
+ check_unicast fibtype4iif "$ifname" "$addr" || lret=1
+ check_type fibif4 "$ifname" "$addr" "veth1" || lret=1
+ done
+ for addr in "dead:9::1" "dead:9::2";do
+ check_unicast fibtype6 "$ifname" "$addr" || lret=1
+ check_unicast fibtype6iif "$ifname" "$addr" || lret=1
+ check_type fibif6 "$ifname" "$addr" "veth1" || lret=1
+ done
+
+ # same for the IPv6 equivalent addresses.
+ for addr in "dead:1::1" "dead:2::1" "dead:9::1" "dead:9::2";do
+ check_type fibif6iif "$ifname" "$addr" "0" || lret=1
+ done
+
+ check_unicast fibtype4 "$ifname" "10.0.2.99" || lret=1
+ check_unicast fibtype4iif "$ifname" "10.0.2.99" || lret=1
+ check_unicast fibtype6 "$ifname" "dead:2::99" || lret=1
+ check_unicast fibtype6iif "$ifname" "dead:2::99" || lret=1
+
+ check_type fibif4 "$ifname" "10.0.2.99" "veth1" || lret=1
+ check_type fibif4iif "$ifname" "10.0.2.99" 0 || lret=1
+ check_type fibif6 "$ifname" "dead:2::99" "veth1" || lret=1
+ check_type fibif6iif "$ifname" "dead:2::99" 0 || lret=1
+
+ check_rpf fibif4 "$ifname" "10.0.1.99" "veth0" 5 || lret=1
+ check_rpf fibif4iif "$ifname" "10.0.1.99" "veth0" 5 || lret=1
+ check_rpf fibif6 "$ifname" "dead:1::99" "veth0" 5 || lret=1
+ check_rpf fibif6iif "$ifname" "dead:1::99" "veth0" 5 || lret=1
+
+ check_fib_vrf_sets_empty || lret=1
+
+ if [ $lret -eq 0 ];then
+ echo "PASS: $msg"
+ else
+ echo "FAIL: $msg"
+ ret=1
+ fi
+}
+
+check_fib_veth_vrf_type()
+{
+ local msg="$1"
+
+ local addr
+ local ifname
+ local setname
+ local lret=0
+
+ # as veth0 is now part of tvrf interface, packets will be seen
+ # twice, once with iif veth0, then with iif tvrf.
+
+ for ifname in "veth0" "tvrf"; do
+ for addr in "10.0.1.1" "10.9.9.1"; do
+ check_local fibtype4 "$ifname" "$addr" || lret=1
+ # addr local, but nft_fib doesn't return routes with RTN_LOCAL.
+ check_type fibif4 "$ifname" "$addr" 0 || lret=1
+ check_type fibif4iif "$ifname" "$addr" 0 || lret=1
+ done
+
+ for addr in "dead:1::1" "dead:9::1"; do
+ check_local fibtype6 "$ifname" "$addr" || lret=1
+ # same, address is local but no route is returned for lo.
+ check_type fibif6 "$ifname" "$addr" 0 || lret=1
+ check_type fibif6iif "$ifname" "$addr" 0 || lret=1
+ done
+
+ for t in fibtype4 fibtype4iif; do
+ check_unicast "$t" "$ifname" 10.9.9.2 || lret=1
+ done
+ for t in fibtype6 fibtype6iif; do
+ check_unicast "$t" "$ifname" dead:9::2 || lret=1
+ done
+
+ check_unicast fibtype4iif "$ifname" "10.9.9.1" || lret=1
+ check_unicast fibtype6iif "$ifname" "dead:9::1" || lret=1
+
+ check_unicast fibtype4 "$ifname" "10.0.2.99" || lret=1
+ check_unicast fibtype4iif "$ifname" "10.0.2.99" || lret=1
+
+ check_unicast fibtype6 "$ifname" "dead:2::99" || lret=1
+ check_unicast fibtype6iif "$ifname" "dead:2::99" || lret=1
+
+ check_type fibif4 "$ifname" "10.0.2.99" "veth1" || lret=1
+ check_type fibif6 "$ifname" "dead:2::99" "veth1" || lret=1
+ check_type fibif4 "$ifname" "10.9.9.2" "dummy0" || lret=1
+ check_type fibif6 "$ifname" "dead:9::2" "dummy0" || lret=1
+
+ # restricted to iif -- MUST NOT provide result, its != $ifname.
+ check_type fibif4iif "$ifname" "10.0.2.99" 0 || lret=1
+ check_type fibif6iif "$ifname" "dead:2::99" 0 || lret=1
+
+ check_rpf fibif4 "$ifname" "10.0.1.99" "veth0" 4 || lret=1
+ check_rpf fibif6 "$ifname" "dead:1::99" "veth0" 4 || lret=1
+ check_rpf fibif4iif "$ifname" "10.0.1.99" "$ifname" 4 || lret=1
+ check_rpf fibif6iif "$ifname" "dead:1::99" "$ifname" 4 || lret=1
+ done
+
+ check_local fibtype4iif "veth0" "10.0.1.1" || lret=1
+ check_local fibtype6iif "veth0" "dead:1::1" || lret=1
+
+ check_unicast fibtype4iif "tvrf" "10.0.1.1" || lret=1
+ check_unicast fibtype6iif "tvrf" "dead:1::1" || lret=1
+
+ # 10.9.9.2 should not provide a result for iif veth, but
+ # should when iif is tvrf.
+ # This is because its reachable via dummy0 which is part of
+ # tvrf. iif veth0 MUST conceal the dummy0 result (i.e. return oif 0).
+ check_type fibif4iif "veth0" "10.9.9.2" 0 || lret=1
+ check_type fibif6iif "veth0" "dead:9::2" 0 || lret=1
+
+ check_type fibif4iif "tvrf" "10.9.9.2" "tvrf" || lret=1
+ check_type fibif6iif "tvrf" "dead:9::2" "tvrf" || lret=1
+
+ check_fib_vrf_sets_empty || lret=1
+
+ if [ $lret -eq 0 ];then
+ echo "PASS: $msg"
+ else
+ echo "FAIL: $msg"
+ ret=1
+ fi
+}
+
+# Extends nsrouter config by adding dummy0+vrf.
+#
+# 10.0.1.99 10.0.1.1 10.0.2.1 10.0.2.99
+# dead:1::99 dead:1::1 dead:2::1 dead:2::99
+# ns1 <-------> [ veth0 ] nsrouter [veth1] <-------> ns2
+# [dummy0]
+# 10.9.9.1
+# dead:9::1
+# [tvrf]
+test_fib_vrf()
+{
+ local cntname=""
+
+ if ! test_fib_vrf_dev_add_dummy; then
+ [ $ret -eq 0 ] && ret=$ksft_skip
+ return
+ fi
+
+ ip -net "$nsrouter" addr add "10.9.9.1"/24 dev dummy0
+ ip -net "$nsrouter" addr add "dead:9::1"/64 dev dummy0 nodad
+
+ ip -net "$nsrouter" route add default via 10.0.2.99
+ ip -net "$nsrouter" route add default via dead:2::99
+
+ load_ruleset_vrf || return
+
+ # no echo reply for these addresses: The dummy interface is part of tvrf,
+ # but veth0 (incoming interface) isn't linked to it.
+ test_ping_unreachable "10.9.9.1" "dead:9::1" &
+ test_ping_unreachable "10.9.9.2" "dead:9::2" &
+
+ # expect replies from these.
+ test_ping "10.0.1.1" "dead:1::1"
+ test_ping "10.0.2.1" "dead:2::1"
+ test_ping "10.0.2.99" "dead:2::99"
+
+ wait
+
+ check_fib_vrf_type "fib expression address types match (iif not in vrf)"
+
+ # second round: this time, make veth0 (rx interface) part of the vrf.
+ # 10.9.9.1 / dead:9::1 become reachable from ns1, while ns2
+ # becomes unreachable.
+ ip -net "$nsrouter" link set veth0 master tvrf
+ ip -net "$nsrouter" addr add dead:1::1/64 dev veth0 nodad
+
+ # this reload should not be needed, but in case
+ # there is some error (missing or unexpected entry) this will prevent them
+ # from leaking into round 2.
+ load_ruleset_vrf || return
+
+ test_ping "10.0.1.1" "dead:1::1"
+ test_ping "10.9.9.1" "dead:9::1"
+
+ # ns2 should no longer be reachable (veth1 not in vrf)
+ test_ping_unreachable "10.0.2.99" "dead:2::99" &
+
+ # vrf via dummy0, but host doesn't exist
+ test_ping_unreachable "10.9.9.2" "dead:9::2" &
+
+ wait
+
+ check_fib_veth_vrf_type "fib expression address types match (iif in vrf)"
+}
+
ip netns exec "$nsrouter" sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
ip netns exec "$nsrouter" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
ip netns exec "$nsrouter" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
-ip netns exec "$nsrouter" sysctl net.ipv4.conf.all.rp_filter=0 > /dev/null
-ip netns exec "$nsrouter" sysctl net.ipv4.conf.veth0.rp_filter=0 > /dev/null
test_ping 10.0.2.1 dead:2::1 || exit 1
-check_drops || exit 1
+check_drops
test_ping 10.0.2.99 dead:2::99 || exit 1
+check_drops
+
+[ $ret -eq 0 ] && echo "PASS: fib expression did not cause unwanted packet drops"
+
+load_input_ruleset "$ns1"
+
+test_ping 127.0.0.1 ::1
+check_drops
+
+test_ping 10.0.1.99 dead:1::99
+check_drops
+
+[ $ret -eq 0 ] && echo "PASS: fib expression did not discard loopback packets"
+
+load_input_ruleset "$ns1"
+
+test_ping 127.0.0.1 ::1 || exit 1
check_drops || exit 1
-echo "PASS: fib expression did not cause unwanted packet drops"
+test_ping 10.0.1.99 dead:1::99 || exit 1
+check_drops || exit 1
+
+echo "PASS: fib expression did not discard loopback packets"
ip netns exec "$nsrouter" nft flush table inet filter
@@ -213,7 +801,7 @@ ip -net "$nsrouter" addr del dead:2::1/64 dev veth0
# ... pbr ruleset for the router, check iif+oif.
if ! load_pbr_ruleset "$nsrouter";then
echo "SKIP: Could not load fib forward ruleset"
- exit $ksft_skip
+ [ "$ret" -eq 0 ] && ret=$ksft_skip
fi
ip -net "$nsrouter" rule add from all table 128
@@ -224,11 +812,36 @@ ip -net "$nsrouter" route add table 129 to 10.0.2.0/24 dev veth1
# drop main ipv4 table
ip -net "$nsrouter" -4 rule delete table main
-if ! test_ping 10.0.2.99 dead:2::99;then
- ip -net "$nsrouter" nft list ruleset
- echo "FAIL: fib mismatch in pbr setup"
- exit 1
+if test_ping 10.0.2.99 dead:2::99;then
+ echo "PASS: fib expression forward check with policy based routing"
+else
+ echo "FAIL: fib expression forward check with policy based routing"
+ ret=1
fi
-echo "PASS: fib expression forward check with policy based routing"
-exit 0
+test_fib_type "policy routing"
+ip netns exec "$nsrouter" nft delete table ip filter
+ip netns exec "$nsrouter" nft delete table ip6 filter
+
+# Un-do policy routing changes
+ip -net "$nsrouter" rule del from all table 128
+ip -net "$nsrouter" rule del from all iif veth0 table 129
+
+ip -net "$nsrouter" route del table 128 to 10.0.1.0/24 dev veth0
+ip -net "$nsrouter" route del table 129 to 10.0.2.0/24 dev veth1
+
+ip -net "$ns1" -4 route del default
+ip -net "$ns1" -6 route del default
+
+ip -net "$ns1" -4 route add default via 10.0.1.1
+ip -net "$ns1" -6 route add default via dead:1::1
+
+ip -net "$nsrouter" -4 rule add from all table main priority 32766
+
+test_fib_type "default table"
+ip netns exec "$nsrouter" nft delete table ip filter
+ip netns exec "$nsrouter" nft delete table ip6 filter
+
+test_fib_vrf
+
+exit $ret
diff --git a/tools/testing/selftests/net/netfilter/nft_interface_stress.sh b/tools/testing/selftests/net/netfilter/nft_interface_stress.sh
new file mode 100755
index 000000000000..5ff7be9daeee
--- /dev/null
+++ b/tools/testing/selftests/net/netfilter/nft_interface_stress.sh
@@ -0,0 +1,154 @@
+#!/bin/bash -e
+#
+# SPDX-License-Identifier: GPL-2.0
+#
+# Torture nftables' netdevice notifier callbacks and related code by frequent
+# renaming of interfaces which netdev-family chains and flowtables hook into.
+
+source lib.sh
+
+checktool "nft --version" "run test without nft tool"
+checktool "iperf3 --version" "run test without iperf3 tool"
+
+# how many seconds to torture the kernel?
+# default to 80% of max run time but don't exceed 48s
+TEST_RUNTIME=$((${kselftest_timeout:-60} * 8 / 10))
+[[ $TEST_RUNTIME -gt 48 ]] && TEST_RUNTIME=48
+
+trap "cleanup_all_ns" EXIT
+
+setup_ns nsc nsr nss
+
+ip -net $nsc link add cr0 type veth peer name rc0 netns $nsr
+ip -net $nsc addr add 10.0.0.1/24 dev cr0
+ip -net $nsc link set cr0 up
+ip -net $nsc route add default via 10.0.0.2
+
+ip -net $nss link add sr0 type veth peer name rs0 netns $nsr
+ip -net $nss addr add 10.1.0.1/24 dev sr0
+ip -net $nss link set sr0 up
+ip -net $nss route add default via 10.1.0.2
+
+ip -net $nsr addr add 10.0.0.2/24 dev rc0
+ip -net $nsr link set rc0 up
+ip -net $nsr addr add 10.1.0.2/24 dev rs0
+ip -net $nsr link set rs0 up
+ip netns exec $nsr sysctl -q net.ipv4.ip_forward=1
+ip netns exec $nsr sysctl -q net.ipv4.conf.all.forwarding=1
+
+{
+ echo "table netdev t {"
+ for ((i = 0; i < 10; i++)); do
+ cat <<-EOF
+ chain chain_rc$i {
+ type filter hook ingress device rc$i priority 0
+ counter
+ }
+ chain chain_rs$i {
+ type filter hook ingress device rs$i priority 0
+ counter
+ }
+ EOF
+ done
+ echo "}"
+ echo "table ip t {"
+ for ((i = 0; i < 10; i++)); do
+ cat <<-EOF
+ flowtable ft_${i} {
+ hook ingress priority 0
+ devices = { rc$i, rs$i }
+ }
+ EOF
+ done
+ echo "chain c {"
+ echo "type filter hook forward priority 0"
+ for ((i = 0; i < 10; i++)); do
+ echo -n "iifname rc$i oifname rs$i "
+ echo "ip protocol tcp counter flow add @ft_${i}"
+ done
+ echo "counter"
+ echo "}"
+ echo "}"
+} | ip netns exec $nsr nft -f - || {
+ echo "SKIP: Could not load nft ruleset"
+ exit $ksft_skip
+}
+
+for ((o=0, n=1; ; o=n, n++, n %= 10)); do
+ ip -net $nsr link set rc$o name rc$n
+ ip -net $nsr link set rs$o name rs$n
+done &
+rename_loop_pid=$!
+
+while true; do ip netns exec $nsr nft list ruleset >/dev/null 2>&1; done &
+nft_list_pid=$!
+
+ip netns exec $nsr nft monitor >/dev/null &
+nft_monitor_pid=$!
+
+ip netns exec $nss iperf3 --server --daemon -1
+summary_expr='s,^\[SUM\] .* \([0-9\.]\+\) Kbits/sec .* receiver,\1,p'
+rate=$(ip netns exec $nsc iperf3 \
+ --format k -c 10.1.0.1 --time $TEST_RUNTIME \
+ --length 56 --parallel 10 -i 0 | sed -n "$summary_expr")
+
+kill $nft_list_pid
+kill $nft_monitor_pid
+kill $rename_loop_pid
+wait
+
+wildcard_prep() {
+ ip netns exec $nsr nft -f - <<EOF
+table ip t {
+ flowtable ft_wild {
+ hook ingress priority 0
+ devices = { wild* }
+ }
+}
+EOF
+}
+
+if ! wildcard_prep; then
+ echo "SKIP wildcard tests: not supported by host's nft?"
+else
+ for ((i = 0; i < 100; i++)); do
+ ip -net $nsr link add wild$i type dummy &
+ done
+ wait
+ for ((i = 80; i < 100; i++)); do
+ ip -net $nsr link del wild$i &
+ done
+ for ((i = 0; i < 80; i++)); do
+ ip -net $nsr link del wild$i &
+ done
+ wait
+ for ((i = 0; i < 100; i += 10)); do
+ (
+ for ((j = 0; j < 10; j++)); do
+ ip -net $nsr link add wild$((i + j)) type dummy
+ done
+ for ((j = 0; j < 10; j++)); do
+ ip -net $nsr link del wild$((i + j))
+ done
+ ) &
+ done
+ wait
+fi
+
+[[ $(</proc/sys/kernel/tainted) -eq 0 ]] || {
+ echo "FAIL: Kernel is tainted!"
+ exit $ksft_fail
+}
+
+[[ $rate -gt 0 ]] || {
+ echo "FAIL: Zero throughput in iperf3"
+ exit $ksft_fail
+}
+
+[[ -f /sys/kernel/debug/kmemleak && \
+ -n $(</sys/kernel/debug/kmemleak) ]] && {
+ echo "FAIL: non-empty kmemleak report"
+ exit $ksft_fail
+}
+
+exit $ksft_pass
diff --git a/tools/testing/selftests/net/netfilter/nft_nat_zones.sh b/tools/testing/selftests/net/netfilter/nft_nat_zones.sh
index 3b81d88bdde3..9f200f80253a 100755
--- a/tools/testing/selftests/net/netfilter/nft_nat_zones.sh
+++ b/tools/testing/selftests/net/netfilter/nft_nat_zones.sh
@@ -88,7 +88,6 @@ for i in $(seq 1 "$maxclients");do
echo netns exec "$cl" sysctl -q net.ipv4.tcp_syn_retries=2
echo netns exec "$gw" ip link set "veth$i" up
echo netns exec "$gw" sysctl -q net.ipv4.conf.veth"$i".arp_ignore=2
- echo netns exec "$gw" sysctl -q net.ipv4.conf.veth"$i".rp_filter=0
# clients have same IP addresses.
echo netns exec "$cl" ip addr add 10.1.0.3/24 dev eth0
@@ -178,7 +177,6 @@ fi
ip netns exec "$gw" sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null
ip netns exec "$gw" sysctl -q net.ipv6.conf.all.forwarding=1 > /dev/null
-ip netns exec "$gw" sysctl -q net.ipv4.conf.all.rp_filter=0 >/dev/null
# useful for debugging: allows to use 'ping' from clients to gateway.
ip netns exec "$gw" sysctl -q net.ipv4.fwmark_reflect=1 > /dev/null
diff --git a/tools/testing/selftests/net/netfilter/nft_queue.sh b/tools/testing/selftests/net/netfilter/nft_queue.sh
index 784d1b46912b..6136ceec45e0 100755
--- a/tools/testing/selftests/net/netfilter/nft_queue.sh
+++ b/tools/testing/selftests/net/netfilter/nft_queue.sh
@@ -10,6 +10,8 @@ source lib.sh
ret=0
timeout=5
+SCTP_TEST_TIMEOUT=60
+
cleanup()
{
ip netns pids "$ns1" | xargs kill 2>/dev/null
@@ -40,7 +42,7 @@ TMPFILE3=$(mktemp)
TMPINPUT=$(mktemp)
COUNT=200
-[ "$KSFT_MACHINE_SLOW" = "yes" ] && COUNT=25
+[ "$KSFT_MACHINE_SLOW" = "yes" ] && COUNT=$((COUNT/8))
dd conv=sparse status=none if=/dev/zero bs=1M count=$COUNT of="$TMPINPUT"
if ! ip link add veth0 netns "$nsrouter" type veth peer name eth0 netns "$ns1" > /dev/null 2>&1; then
@@ -275,9 +277,11 @@ test_tcp_forward()
busywait "$BUSYWAIT_TIMEOUT" listener_ready "$ns2"
busywait "$BUSYWAIT_TIMEOUT" nf_queue_wait "$nsrouter" 2
+ local tthen=$(date +%s)
+
ip netns exec "$ns1" socat -u STDIN TCP:10.0.2.99:12345 <"$TMPINPUT" >/dev/null
- wait "$rpid" && echo "PASS: tcp and nfqueue in forward chain"
+ wait_and_check_retval "$rpid" "tcp and nfqueue in forward chain" "$tthen"
kill "$nfqpid"
}
@@ -288,13 +292,14 @@ test_tcp_localhost()
ip netns exec "$nsrouter" ./nf_queue -q 3 &
local nfqpid=$!
+ local tthen=$(date +%s)
busywait "$BUSYWAIT_TIMEOUT" listener_ready "$nsrouter"
busywait "$BUSYWAIT_TIMEOUT" nf_queue_wait "$nsrouter" 3
ip netns exec "$nsrouter" socat -u STDIN TCP:127.0.0.1:12345 <"$TMPINPUT" >/dev/null
- wait "$rpid" && echo "PASS: tcp via loopback"
+ wait_and_check_retval "$rpid" "tcp via loopback" "$tthen"
kill "$nfqpid"
}
@@ -417,6 +422,23 @@ check_output_files()
fi
}
+wait_and_check_retval()
+{
+ local rpid="$1"
+ local msg="$2"
+ local tthen="$3"
+ local tnow=$(date +%s)
+
+ if wait "$rpid";then
+ echo -n "PASS: "
+ else
+ echo -n "FAIL: "
+ ret=1
+ fi
+
+ printf "%s (duration: %ds)\n" "$msg" $((tnow-tthen))
+}
+
test_sctp_forward()
{
ip netns exec "$nsrouter" nft -f /dev/stdin <<EOF
@@ -428,13 +450,14 @@ table inet sctpq {
}
}
EOF
- timeout 60 ip netns exec "$ns2" socat -u SCTP-LISTEN:12345 STDOUT > "$TMPFILE1" &
+ timeout "$SCTP_TEST_TIMEOUT" ip netns exec "$ns2" socat -u SCTP-LISTEN:12345 STDOUT > "$TMPFILE1" &
local rpid=$!
busywait "$BUSYWAIT_TIMEOUT" sctp_listener_ready "$ns2"
ip netns exec "$nsrouter" ./nf_queue -q 10 -G &
local nfqpid=$!
+ local tthen=$(date +%s)
ip netns exec "$ns1" socat -u STDIN SCTP:10.0.2.99:12345 <"$TMPINPUT" >/dev/null
@@ -443,7 +466,7 @@ EOF
exit 1
fi
- wait "$rpid" && echo "PASS: sctp and nfqueue in forward chain"
+ wait_and_check_retval "$rpid" "sctp and nfqueue in forward chain" "$tthen"
kill "$nfqpid"
check_output_files "$TMPINPUT" "$TMPFILE1" "sctp forward"
@@ -462,13 +485,14 @@ EOF
# reduce test file size, software segmentation causes sk wmem increase.
dd conv=sparse status=none if=/dev/zero bs=1M count=$((COUNT/2)) of="$TMPINPUT"
- timeout 60 ip netns exec "$ns2" socat -u SCTP-LISTEN:12345 STDOUT > "$TMPFILE1" &
+ timeout "$SCTP_TEST_TIMEOUT" ip netns exec "$ns2" socat -u SCTP-LISTEN:12345 STDOUT > "$TMPFILE1" &
local rpid=$!
busywait "$BUSYWAIT_TIMEOUT" sctp_listener_ready "$ns2"
ip netns exec "$ns1" ./nf_queue -q 11 &
local nfqpid=$!
+ local tthen=$(date +%s)
ip netns exec "$ns1" socat -u STDIN SCTP:10.0.2.99:12345 <"$TMPINPUT" >/dev/null
@@ -478,7 +502,7 @@ EOF
fi
# must wait before checking completeness of output file.
- wait "$rpid" && echo "PASS: sctp and nfqueue in output chain with GSO"
+ wait_and_check_retval "$rpid" "sctp and nfqueue in output chain with GSO" "$tthen"
kill "$nfqpid"
check_output_files "$TMPINPUT" "$TMPFILE1" "sctp output"
diff --git a/tools/testing/selftests/net/netfilter/rpath.sh b/tools/testing/selftests/net/netfilter/rpath.sh
index 86ec4e68594d..24ad41d526d9 100755
--- a/tools/testing/selftests/net/netfilter/rpath.sh
+++ b/tools/testing/selftests/net/netfilter/rpath.sh
@@ -1,8 +1,7 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
-# return code to signal skipped test
-ksft_skip=4
+source lib.sh
# search for legacy iptables (it uses the xtables extensions
if iptables-legacy --version >/dev/null 2>&1; then
@@ -32,17 +31,10 @@ if [ -z "$iptables$ip6tables$nft" ]; then
exit $ksft_skip
fi
-sfx=$(mktemp -u "XXXXXXXX")
-ns1="ns1-$sfx"
-ns2="ns2-$sfx"
-trap "ip netns del $ns1; ip netns del $ns2" EXIT
-
-# create two netns, disable rp_filter in ns2 and
-# keep IPv6 address when moving into VRF
-ip netns add "$ns1"
-ip netns add "$ns2"
-ip netns exec "$ns2" sysctl -q net.ipv4.conf.all.rp_filter=0
-ip netns exec "$ns2" sysctl -q net.ipv4.conf.default.rp_filter=0
+trap cleanup_all_ns EXIT
+
+# create two netns, keep IPv6 address when moving into VRF
+setup_ns ns1 ns2
ip netns exec "$ns2" sysctl -q net.ipv6.conf.all.keep_addr_on_down=1
# a standard connection between the netns, should not trigger rp filter
diff --git a/tools/testing/selftests/net/netns-name.sh b/tools/testing/selftests/net/netns-name.sh
index 6974474c26f3..38871bdef67f 100755
--- a/tools/testing/selftests/net/netns-name.sh
+++ b/tools/testing/selftests/net/netns-name.sh
@@ -7,10 +7,12 @@ set -o pipefail
DEV=dummy-dev0
DEV2=dummy-dev1
ALT_NAME=some-alt-name
+NSIM_ADDR=2025
RET_CODE=0
cleanup() {
+ cleanup_netdevsim $NSIM_ADDR
cleanup_ns $NS $test_ns
}
@@ -25,12 +27,15 @@ setup_ns NS test_ns
#
# Test basic move without a rename
+# Use netdevsim because it has extra asserts for notifiers.
#
-ip -netns $NS link add name $DEV type dummy || fail
-ip -netns $NS link set dev $DEV netns $test_ns ||
+
+nsim=$(create_netdevsim $NSIM_ADDR $NS)
+ip -netns $NS link set dev $nsim netns $test_ns ||
fail "Can't perform a netns move"
-ip -netns $test_ns link show dev $DEV >> /dev/null || fail "Device not found after move"
-ip -netns $test_ns link del $DEV || fail
+ip -netns $test_ns link show dev $nsim >> /dev/null ||
+ fail "Device not found after move"
+cleanup_netdevsim $NSIM_ADDR
#
# Test move with a conflict
@@ -78,6 +83,16 @@ ip -netns $NS link show dev $ALT_NAME 2> /dev/null &&
fail "Can still find alt-name after move"
ip -netns $test_ns link del $DEV || fail
+#
+# Test no conflict of the same name/ifindex in different netns
+#
+ip -netns $NS link add name $DEV index 100 type dummy || fail
+ip -netns $NS link add netns $test_ns name $DEV index 100 type dummy ||
+ fail "Can create in netns without moving"
+ip -netns $test_ns link show dev $DEV >> /dev/null || fail "Device not found"
+ip -netns $NS link del $DEV || fail
+ip -netns $test_ns link del $DEV || fail
+
echo -ne "$(basename $0) \t\t\t\t"
if [ $RET_CODE -eq 0 ]; then
echo "[ OK ]"
diff --git a/tools/testing/selftests/net/nl_netdev.py b/tools/testing/selftests/net/nl_netdev.py
index 93e8cb671c3d..beaee5e4e2aa 100755
--- a/tools/testing/selftests/net/nl_netdev.py
+++ b/tools/testing/selftests/net/nl_netdev.py
@@ -35,6 +35,21 @@ def napi_list_check(nf) -> None:
comment=f"queue count after reset queue {q} mode {i}")
+def nsim_rxq_reset_down(nf) -> None:
+ """
+ Test that the queue API supports resetting a queue
+ while the interface is down. We should convert this
+ test to testing real HW once more devices support
+ queue API.
+ """
+ with NetdevSimDev(queue_count=4) as nsimdev:
+ nsim = nsimdev.nsims[0]
+
+ ip(f"link set dev {nsim.ifname} down")
+ for i in [0, 2, 3]:
+ nsim.dfs_write("queue_reset", f"1 {i}")
+
+
def page_pool_check(nf) -> None:
with NetdevSimDev() as nsimdev:
nsim = nsimdev.nsims[0]
@@ -106,7 +121,8 @@ def page_pool_check(nf) -> None:
def main() -> None:
nf = NetdevFamily()
- ksft_run([empty_check, lo_check, page_pool_check, napi_list_check],
+ ksft_run([empty_check, lo_check, page_pool_check, napi_list_check,
+ nsim_rxq_reset_down],
args=(nf, ))
ksft_exit()
diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh
index 960e1ab4dd04..3c8d3455d8e7 100755
--- a/tools/testing/selftests/net/openvswitch/openvswitch.sh
+++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh
@@ -330,6 +330,11 @@ test_psample() {
# - drop packets and verify the right drop reason is reported
test_drop_reason() {
which perf >/dev/null 2>&1 || return $ksft_skip
+ which pahole >/dev/null 2>&1 || return $ksft_skip
+
+ ovs_drop_subsys=$(pahole -C skb_drop_reason_subsys |
+ awk '/OPENVSWITCH/ { print $3; }' |
+ tr -d ,)
sbx_add "test_drop_reason" || return $?
@@ -373,7 +378,7 @@ test_drop_reason() {
"in_port(2),eth(),eth_type(0x0800),ipv4(src=172.31.110.20,proto=1),icmp()" 'drop'
ovs_drop_record_and_run "test_drop_reason" ip netns exec client ping -c 2 172.31.110.20
- ovs_drop_reason_count 0x30001 # OVS_DROP_FLOW_ACTION
+ ovs_drop_reason_count 0x${ovs_drop_subsys}0001 # OVS_DROP_FLOW_ACTION
if [[ "$?" -ne "2" ]]; then
info "Did not detect expected drops: $?"
return 1
@@ -390,7 +395,7 @@ test_drop_reason() {
ovs_drop_record_and_run \
"test_drop_reason" ip netns exec client nc -i 1 -zuv 172.31.110.20 6000
- ovs_drop_reason_count 0x30004 # OVS_DROP_EXPLICIT_ACTION_ERROR
+ ovs_drop_reason_count 0x${ovs_drop_subsys}0004 # OVS_DROP_EXPLICIT_ACTION_ERROR
if [[ "$?" -ne "1" ]]; then
info "Did not detect expected explicit error drops: $?"
return 1
@@ -398,7 +403,7 @@ test_drop_reason() {
ovs_drop_record_and_run \
"test_drop_reason" ip netns exec client nc -i 1 -zuv 172.31.110.20 7000
- ovs_drop_reason_count 0x30003 # OVS_DROP_EXPLICIT_ACTION
+ ovs_drop_reason_count 0x${ovs_drop_subsys}0003 # OVS_DROP_EXPLICIT_ACTION
if [[ "$?" -ne "1" ]]; then
info "Did not detect expected explicit drops: $?"
return 1
diff --git a/tools/testing/selftests/net/ovpn/.gitignore b/tools/testing/selftests/net/ovpn/.gitignore
new file mode 100644
index 000000000000..ee44c081ca7c
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0+
+ovpn-cli
diff --git a/tools/testing/selftests/net/ovpn/Makefile b/tools/testing/selftests/net/ovpn/Makefile
new file mode 100644
index 000000000000..e0926d76b4c8
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/Makefile
@@ -0,0 +1,32 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2020-2025 OpenVPN, Inc.
+#
+CFLAGS = -pedantic -Wextra -Wall -Wl,--no-as-needed -g -O0 -ggdb $(KHDR_INCLUDES)
+VAR_CFLAGS = $(shell pkg-config --cflags libnl-3.0 libnl-genl-3.0 2>/dev/null)
+ifeq ($(VAR_CFLAGS),)
+VAR_CFLAGS = -I/usr/include/libnl3
+endif
+CFLAGS += $(VAR_CFLAGS)
+
+
+LDLIBS = -lmbedtls -lmbedcrypto
+VAR_LDLIBS = $(shell pkg-config --libs libnl-3.0 libnl-genl-3.0 2>/dev/null)
+ifeq ($(VAR_LDLIBS),)
+VAR_LDLIBS = -lnl-genl-3 -lnl-3
+endif
+LDLIBS += $(VAR_LDLIBS)
+
+
+TEST_FILES = common.sh
+
+TEST_PROGS = test.sh \
+ test-large-mtu.sh \
+ test-chachapoly.sh \
+ test-tcp.sh \
+ test-float.sh \
+ test-close-socket.sh \
+ test-close-socket-tcp.sh
+
+TEST_GEN_FILES := ovpn-cli
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/net/ovpn/common.sh b/tools/testing/selftests/net/ovpn/common.sh
new file mode 100644
index 000000000000..88869c675d03
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/common.sh
@@ -0,0 +1,108 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2020-2025 OpenVPN, Inc.
+#
+# Author: Antonio Quartulli <antonio@openvpn.net>
+
+UDP_PEERS_FILE=${UDP_PEERS_FILE:-udp_peers.txt}
+TCP_PEERS_FILE=${TCP_PEERS_FILE:-tcp_peers.txt}
+OVPN_CLI=${OVPN_CLI:-./ovpn-cli}
+ALG=${ALG:-aes}
+PROTO=${PROTO:-UDP}
+FLOAT=${FLOAT:-0}
+
+LAN_IP="11.11.11.11"
+
+create_ns() {
+ ip netns add peer${1}
+}
+
+setup_ns() {
+ MODE="P2P"
+
+ if [ ${1} -eq 0 ]; then
+ MODE="MP"
+ for p in $(seq 1 ${NUM_PEERS}); do
+ ip link add veth${p} netns peer0 type veth peer name veth${p} netns peer${p}
+
+ ip -n peer0 addr add 10.10.${p}.1/24 dev veth${p}
+ ip -n peer0 addr add fd00:0:0:${p}::1/64 dev veth${p}
+ ip -n peer0 link set veth${p} up
+
+ ip -n peer${p} addr add 10.10.${p}.2/24 dev veth${p}
+ ip -n peer${p} addr add fd00:0:0:${p}::2/64 dev veth${p}
+ ip -n peer${p} link set veth${p} up
+ done
+ fi
+
+ ip netns exec peer${1} ${OVPN_CLI} new_iface tun${1} $MODE
+ ip -n peer${1} addr add ${2} dev tun${1}
+ # add a secondary IP to peer 1, to test a LAN behind a client
+ if [ ${1} -eq 1 -a -n "${LAN_IP}" ]; then
+ ip -n peer${1} addr add ${LAN_IP} dev tun${1}
+ ip -n peer0 route add ${LAN_IP} via $(echo ${2} |sed -e s'!/.*!!') dev tun0
+ fi
+ if [ -n "${3}" ]; then
+ ip -n peer${1} link set mtu ${3} dev tun${1}
+ fi
+ ip -n peer${1} link set tun${1} up
+}
+
+add_peer() {
+ if [ "${PROTO}" == "UDP" ]; then
+ if [ ${1} -eq 0 ]; then
+ ip netns exec peer0 ${OVPN_CLI} new_multi_peer tun0 1 ${UDP_PEERS_FILE}
+
+ for p in $(seq 1 ${NUM_PEERS}); do
+ ip netns exec peer0 ${OVPN_CLI} new_key tun0 ${p} 1 0 ${ALG} 0 \
+ data64.key
+ done
+ else
+ RADDR=$(awk "NR == ${1} {print \$2}" ${UDP_PEERS_FILE})
+ RPORT=$(awk "NR == ${1} {print \$3}" ${UDP_PEERS_FILE})
+ LPORT=$(awk "NR == ${1} {print \$5}" ${UDP_PEERS_FILE})
+ ip netns exec peer${1} ${OVPN_CLI} new_peer tun${1} ${1} ${LPORT} \
+ ${RADDR} ${RPORT}
+ ip netns exec peer${1} ${OVPN_CLI} new_key tun${1} ${1} 1 0 ${ALG} 1 \
+ data64.key
+ fi
+ else
+ if [ ${1} -eq 0 ]; then
+ (ip netns exec peer0 ${OVPN_CLI} listen tun0 1 ${TCP_PEERS_FILE} && {
+ for p in $(seq 1 ${NUM_PEERS}); do
+ ip netns exec peer0 ${OVPN_CLI} new_key tun0 ${p} 1 0 \
+ ${ALG} 0 data64.key
+ done
+ }) &
+ sleep 5
+ else
+ ip netns exec peer${1} ${OVPN_CLI} connect tun${1} ${1} 10.10.${1}.1 1 \
+ data64.key
+ fi
+ fi
+}
+
+cleanup() {
+ # some ovpn-cli processes sleep in background so they need manual poking
+ killall $(basename ${OVPN_CLI}) 2>/dev/null || true
+
+ # netns peer0 is deleted without erasing ifaces first
+ for p in $(seq 1 10); do
+ ip -n peer${p} link set tun${p} down 2>/dev/null || true
+ ip netns exec peer${p} ${OVPN_CLI} del_iface tun${p} 2>/dev/null || true
+ done
+ for p in $(seq 1 10); do
+ ip -n peer0 link del veth${p} 2>/dev/null || true
+ done
+ for p in $(seq 0 10); do
+ ip netns del peer${p} 2>/dev/null || true
+ done
+}
+
+if [ "${PROTO}" == "UDP" ]; then
+ NUM_PEERS=${NUM_PEERS:-$(wc -l ${UDP_PEERS_FILE} | awk '{print $1}')}
+else
+ NUM_PEERS=${NUM_PEERS:-$(wc -l ${TCP_PEERS_FILE} | awk '{print $1}')}
+fi
+
+
diff --git a/tools/testing/selftests/net/ovpn/config b/tools/testing/selftests/net/ovpn/config
new file mode 100644
index 000000000000..71946ba9fa17
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/config
@@ -0,0 +1,10 @@
+CONFIG_NET=y
+CONFIG_INET=y
+CONFIG_STREAM_PARSER=y
+CONFIG_NET_UDP_TUNNEL=y
+CONFIG_DST_CACHE=y
+CONFIG_CRYPTO=y
+CONFIG_CRYPTO_AES=y
+CONFIG_CRYPTO_GCM=y
+CONFIG_CRYPTO_CHACHA20POLY1305=y
+CONFIG_OVPN=m
diff --git a/tools/testing/selftests/net/ovpn/data64.key b/tools/testing/selftests/net/ovpn/data64.key
new file mode 100644
index 000000000000..a99e88c4e290
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/data64.key
@@ -0,0 +1,5 @@
+jRqMACN7d7/aFQNT8S7jkrBD8uwrgHbG5OQZP2eu4R1Y7tfpS2bf5RHv06Vi163CGoaIiTX99R3B
+ia9ycAH8Wz1+9PWv51dnBLur9jbShlgZ2QHLtUc4a/gfT7zZwULXuuxdLnvR21DDeMBaTbkgbai9
+uvAa7ne1liIgGFzbv+Bas4HDVrygxIxuAnP5Qgc3648IJkZ0QEXPF+O9f0n5+QIvGCxkAUVx+5K6
+KIs+SoeWXnAopELmoGSjUpFtJbagXK82HfdqpuUxT2Tnuef0/14SzVE/vNleBNu2ZbyrSAaah8tE
+BofkPJUBFY+YQcfZNM5Dgrw3i+Bpmpq/gpdg5w==
diff --git a/tools/testing/selftests/net/ovpn/ovpn-cli.c b/tools/testing/selftests/net/ovpn/ovpn-cli.c
new file mode 100644
index 000000000000..de9c26f98b2e
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/ovpn-cli.c
@@ -0,0 +1,2383 @@
+// SPDX-License-Identifier: GPL-2.0
+/* OpenVPN data channel accelerator
+ *
+ * Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ * Author: Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <stdio.h>
+#include <inttypes.h>
+#include <stdbool.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <arpa/inet.h>
+#include <net/if.h>
+#include <netinet/in.h>
+#include <time.h>
+
+#include <linux/ovpn.h>
+#include <linux/types.h>
+#include <linux/netlink.h>
+
+#include <netlink/socket.h>
+#include <netlink/netlink.h>
+#include <netlink/genl/genl.h>
+#include <netlink/genl/family.h>
+#include <netlink/genl/ctrl.h>
+
+#include <mbedtls/base64.h>
+#include <mbedtls/error.h>
+
+#include <sys/socket.h>
+
+/* defines to make checkpatch happy */
+#define strscpy strncpy
+#define __always_unused __attribute__((__unused__))
+
+/* libnl < 3.5.0 does not set the NLA_F_NESTED on its own, therefore we
+ * have to explicitly do it to prevent the kernel from failing upon
+ * parsing of the message
+ */
+#define nla_nest_start(_msg, _type) \
+ nla_nest_start(_msg, (_type) | NLA_F_NESTED)
+
+/* libnl < 3.11.0 does not implement nla_get_uint() */
+uint64_t ovpn_nla_get_uint(struct nlattr *attr)
+{
+ if (nla_len(attr) == sizeof(uint32_t))
+ return nla_get_u32(attr);
+ else
+ return nla_get_u64(attr);
+}
+
+typedef int (*ovpn_nl_cb)(struct nl_msg *msg, void *arg);
+
+enum ovpn_key_direction {
+ KEY_DIR_IN = 0,
+ KEY_DIR_OUT,
+};
+
+#define KEY_LEN (256 / 8)
+#define NONCE_LEN 8
+
+#define PEER_ID_UNDEF 0x00FFFFFF
+#define MAX_PEERS 10
+
+struct nl_ctx {
+ struct nl_sock *nl_sock;
+ struct nl_msg *nl_msg;
+ struct nl_cb *nl_cb;
+
+ int ovpn_dco_id;
+};
+
+enum ovpn_cmd {
+ CMD_INVALID,
+ CMD_NEW_IFACE,
+ CMD_DEL_IFACE,
+ CMD_LISTEN,
+ CMD_CONNECT,
+ CMD_NEW_PEER,
+ CMD_NEW_MULTI_PEER,
+ CMD_SET_PEER,
+ CMD_DEL_PEER,
+ CMD_GET_PEER,
+ CMD_NEW_KEY,
+ CMD_DEL_KEY,
+ CMD_GET_KEY,
+ CMD_SWAP_KEYS,
+ CMD_LISTEN_MCAST,
+};
+
+struct ovpn_ctx {
+ enum ovpn_cmd cmd;
+
+ __u8 key_enc[KEY_LEN];
+ __u8 key_dec[KEY_LEN];
+ __u8 nonce[NONCE_LEN];
+
+ enum ovpn_cipher_alg cipher;
+
+ sa_family_t sa_family;
+
+ unsigned long peer_id;
+ unsigned long lport;
+
+ union {
+ struct sockaddr_in in4;
+ struct sockaddr_in6 in6;
+ } remote;
+
+ union {
+ struct sockaddr_in in4;
+ struct sockaddr_in6 in6;
+ } peer_ip;
+
+ bool peer_ip_set;
+
+ unsigned int ifindex;
+ char ifname[IFNAMSIZ];
+ enum ovpn_mode mode;
+ bool mode_set;
+
+ int socket;
+ int cli_sockets[MAX_PEERS];
+
+ __u32 keepalive_interval;
+ __u32 keepalive_timeout;
+
+ enum ovpn_key_direction key_dir;
+ enum ovpn_key_slot key_slot;
+ int key_id;
+
+ const char *peers_file;
+};
+
+static int ovpn_nl_recvmsgs(struct nl_ctx *ctx)
+{
+ int ret;
+
+ ret = nl_recvmsgs(ctx->nl_sock, ctx->nl_cb);
+
+ switch (ret) {
+ case -NLE_INTR:
+ fprintf(stderr,
+ "netlink received interrupt due to signal - ignoring\n");
+ break;
+ case -NLE_NOMEM:
+ fprintf(stderr, "netlink out of memory error\n");
+ break;
+ case -NLE_AGAIN:
+ fprintf(stderr,
+ "netlink reports blocking read - aborting wait\n");
+ break;
+ default:
+ if (ret)
+ fprintf(stderr, "netlink reports error (%d): %s\n",
+ ret, nl_geterror(-ret));
+ break;
+ }
+
+ return ret;
+}
+
+static struct nl_ctx *nl_ctx_alloc_flags(struct ovpn_ctx *ovpn, int cmd,
+ int flags)
+{
+ struct nl_ctx *ctx;
+ int err, ret;
+
+ ctx = calloc(1, sizeof(*ctx));
+ if (!ctx)
+ return NULL;
+
+ ctx->nl_sock = nl_socket_alloc();
+ if (!ctx->nl_sock) {
+ fprintf(stderr, "cannot allocate netlink socket\n");
+ goto err_free;
+ }
+
+ nl_socket_set_buffer_size(ctx->nl_sock, 8192, 8192);
+
+ ret = genl_connect(ctx->nl_sock);
+ if (ret) {
+ fprintf(stderr, "cannot connect to generic netlink: %s\n",
+ nl_geterror(ret));
+ goto err_sock;
+ }
+
+ /* enable Extended ACK for detailed error reporting */
+ err = 1;
+ setsockopt(nl_socket_get_fd(ctx->nl_sock), SOL_NETLINK, NETLINK_EXT_ACK,
+ &err, sizeof(err));
+
+ ctx->ovpn_dco_id = genl_ctrl_resolve(ctx->nl_sock, OVPN_FAMILY_NAME);
+ if (ctx->ovpn_dco_id < 0) {
+ fprintf(stderr, "cannot find ovpn_dco netlink component: %d\n",
+ ctx->ovpn_dco_id);
+ goto err_free;
+ }
+
+ ctx->nl_msg = nlmsg_alloc();
+ if (!ctx->nl_msg) {
+ fprintf(stderr, "cannot allocate netlink message\n");
+ goto err_sock;
+ }
+
+ ctx->nl_cb = nl_cb_alloc(NL_CB_DEFAULT);
+ if (!ctx->nl_cb) {
+ fprintf(stderr, "failed to allocate netlink callback\n");
+ goto err_msg;
+ }
+
+ nl_socket_set_cb(ctx->nl_sock, ctx->nl_cb);
+
+ genlmsg_put(ctx->nl_msg, 0, 0, ctx->ovpn_dco_id, 0, flags, cmd, 0);
+
+ if (ovpn->ifindex > 0)
+ NLA_PUT_U32(ctx->nl_msg, OVPN_A_IFINDEX, ovpn->ifindex);
+
+ return ctx;
+nla_put_failure:
+err_msg:
+ nlmsg_free(ctx->nl_msg);
+err_sock:
+ nl_socket_free(ctx->nl_sock);
+err_free:
+ free(ctx);
+ return NULL;
+}
+
+static struct nl_ctx *nl_ctx_alloc(struct ovpn_ctx *ovpn, int cmd)
+{
+ return nl_ctx_alloc_flags(ovpn, cmd, 0);
+}
+
+static void nl_ctx_free(struct nl_ctx *ctx)
+{
+ if (!ctx)
+ return;
+
+ nl_socket_free(ctx->nl_sock);
+ nlmsg_free(ctx->nl_msg);
+ nl_cb_put(ctx->nl_cb);
+ free(ctx);
+}
+
+static int ovpn_nl_cb_error(struct sockaddr_nl (*nla)__always_unused,
+ struct nlmsgerr *err, void *arg)
+{
+ struct nlmsghdr *nlh = (struct nlmsghdr *)err - 1;
+ struct nlattr *tb_msg[NLMSGERR_ATTR_MAX + 1];
+ int len = nlh->nlmsg_len;
+ struct nlattr *attrs;
+ int *ret = arg;
+ int ack_len = sizeof(*nlh) + sizeof(int) + sizeof(*nlh);
+
+ *ret = err->error;
+
+ if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS))
+ return NL_STOP;
+
+ if (!(nlh->nlmsg_flags & NLM_F_CAPPED))
+ ack_len += err->msg.nlmsg_len - sizeof(*nlh);
+
+ if (len <= ack_len)
+ return NL_STOP;
+
+ attrs = (void *)((uint8_t *)nlh + ack_len);
+ len -= ack_len;
+
+ nla_parse(tb_msg, NLMSGERR_ATTR_MAX, attrs, len, NULL);
+ if (tb_msg[NLMSGERR_ATTR_MSG]) {
+ len = strnlen((char *)nla_data(tb_msg[NLMSGERR_ATTR_MSG]),
+ nla_len(tb_msg[NLMSGERR_ATTR_MSG]));
+ fprintf(stderr, "kernel error: %*s\n", len,
+ (char *)nla_data(tb_msg[NLMSGERR_ATTR_MSG]));
+ }
+
+ if (tb_msg[NLMSGERR_ATTR_MISS_NEST]) {
+ fprintf(stderr, "missing required nesting type %u\n",
+ nla_get_u32(tb_msg[NLMSGERR_ATTR_MISS_NEST]));
+ }
+
+ if (tb_msg[NLMSGERR_ATTR_MISS_TYPE]) {
+ fprintf(stderr, "missing required attribute type %u\n",
+ nla_get_u32(tb_msg[NLMSGERR_ATTR_MISS_TYPE]));
+ }
+
+ return NL_STOP;
+}
+
+static int ovpn_nl_cb_finish(struct nl_msg (*msg)__always_unused,
+ void *arg)
+{
+ int *status = arg;
+
+ *status = 0;
+ return NL_SKIP;
+}
+
+static int ovpn_nl_cb_ack(struct nl_msg (*msg)__always_unused,
+ void *arg)
+{
+ int *status = arg;
+
+ *status = 0;
+ return NL_STOP;
+}
+
+static int ovpn_nl_msg_send(struct nl_ctx *ctx, ovpn_nl_cb cb)
+{
+ int status = 1;
+
+ nl_cb_err(ctx->nl_cb, NL_CB_CUSTOM, ovpn_nl_cb_error, &status);
+ nl_cb_set(ctx->nl_cb, NL_CB_FINISH, NL_CB_CUSTOM, ovpn_nl_cb_finish,
+ &status);
+ nl_cb_set(ctx->nl_cb, NL_CB_ACK, NL_CB_CUSTOM, ovpn_nl_cb_ack, &status);
+
+ if (cb)
+ nl_cb_set(ctx->nl_cb, NL_CB_VALID, NL_CB_CUSTOM, cb, ctx);
+
+ nl_send_auto_complete(ctx->nl_sock, ctx->nl_msg);
+
+ while (status == 1)
+ ovpn_nl_recvmsgs(ctx);
+
+ if (status < 0)
+ fprintf(stderr, "failed to send netlink message: %s (%d)\n",
+ strerror(-status), status);
+
+ return status;
+}
+
+static int ovpn_parse_key(const char *file, struct ovpn_ctx *ctx)
+{
+ int idx_enc, idx_dec, ret = -1;
+ unsigned char *ckey = NULL;
+ __u8 *bkey = NULL;
+ size_t olen = 0;
+ long ckey_len;
+ FILE *fp;
+
+ fp = fopen(file, "r");
+ if (!fp) {
+ fprintf(stderr, "cannot open: %s\n", file);
+ return -1;
+ }
+
+ /* get file size */
+ fseek(fp, 0L, SEEK_END);
+ ckey_len = ftell(fp);
+ rewind(fp);
+
+ /* if the file is longer, let's just read a portion */
+ if (ckey_len > 256)
+ ckey_len = 256;
+
+ ckey = malloc(ckey_len);
+ if (!ckey)
+ goto err;
+
+ ret = fread(ckey, 1, ckey_len, fp);
+ if (ret != ckey_len) {
+ fprintf(stderr,
+ "couldn't read enough data from key file: %dbytes read\n",
+ ret);
+ goto err;
+ }
+
+ olen = 0;
+ ret = mbedtls_base64_decode(NULL, 0, &olen, ckey, ckey_len);
+ if (ret != MBEDTLS_ERR_BASE64_BUFFER_TOO_SMALL) {
+ char buf[256];
+
+ mbedtls_strerror(ret, buf, sizeof(buf));
+ fprintf(stderr, "unexpected base64 error1: %s (%d)\n", buf,
+ ret);
+
+ goto err;
+ }
+
+ bkey = malloc(olen);
+ if (!bkey) {
+ fprintf(stderr, "cannot allocate binary key buffer\n");
+ goto err;
+ }
+
+ ret = mbedtls_base64_decode(bkey, olen, &olen, ckey, ckey_len);
+ if (ret) {
+ char buf[256];
+
+ mbedtls_strerror(ret, buf, sizeof(buf));
+ fprintf(stderr, "unexpected base64 error2: %s (%d)\n", buf,
+ ret);
+
+ goto err;
+ }
+
+ if (olen < 2 * KEY_LEN + NONCE_LEN) {
+ fprintf(stderr,
+ "not enough data in key file, found %zdB but needs %dB\n",
+ olen, 2 * KEY_LEN + NONCE_LEN);
+ goto err;
+ }
+
+ switch (ctx->key_dir) {
+ case KEY_DIR_IN:
+ idx_enc = 0;
+ idx_dec = 1;
+ break;
+ case KEY_DIR_OUT:
+ idx_enc = 1;
+ idx_dec = 0;
+ break;
+ default:
+ goto err;
+ }
+
+ memcpy(ctx->key_enc, bkey + KEY_LEN * idx_enc, KEY_LEN);
+ memcpy(ctx->key_dec, bkey + KEY_LEN * idx_dec, KEY_LEN);
+ memcpy(ctx->nonce, bkey + 2 * KEY_LEN, NONCE_LEN);
+
+ ret = 0;
+
+err:
+ fclose(fp);
+ free(bkey);
+ free(ckey);
+
+ return ret;
+}
+
+static int ovpn_parse_cipher(const char *cipher, struct ovpn_ctx *ctx)
+{
+ if (strcmp(cipher, "aes") == 0)
+ ctx->cipher = OVPN_CIPHER_ALG_AES_GCM;
+ else if (strcmp(cipher, "chachapoly") == 0)
+ ctx->cipher = OVPN_CIPHER_ALG_CHACHA20_POLY1305;
+ else if (strcmp(cipher, "none") == 0)
+ ctx->cipher = OVPN_CIPHER_ALG_NONE;
+ else
+ return -ENOTSUP;
+
+ return 0;
+}
+
+static int ovpn_parse_key_direction(const char *dir, struct ovpn_ctx *ctx)
+{
+ int in_dir;
+
+ in_dir = strtoll(dir, NULL, 10);
+ switch (in_dir) {
+ case KEY_DIR_IN:
+ case KEY_DIR_OUT:
+ ctx->key_dir = in_dir;
+ break;
+ default:
+ fprintf(stderr,
+ "invalid key direction provided. Can be 0 or 1 only\n");
+ return -1;
+ }
+
+ return 0;
+}
+
+static int ovpn_socket(struct ovpn_ctx *ctx, sa_family_t family, int proto)
+{
+ struct sockaddr_storage local_sock = { 0 };
+ struct sockaddr_in6 *in6;
+ struct sockaddr_in *in;
+ int ret, s, sock_type;
+ size_t sock_len;
+
+ if (proto == IPPROTO_UDP)
+ sock_type = SOCK_DGRAM;
+ else if (proto == IPPROTO_TCP)
+ sock_type = SOCK_STREAM;
+ else
+ return -EINVAL;
+
+ s = socket(family, sock_type, 0);
+ if (s < 0) {
+ perror("cannot create socket");
+ return -1;
+ }
+
+ switch (family) {
+ case AF_INET:
+ in = (struct sockaddr_in *)&local_sock;
+ in->sin_family = family;
+ in->sin_port = htons(ctx->lport);
+ in->sin_addr.s_addr = htonl(INADDR_ANY);
+ sock_len = sizeof(*in);
+ break;
+ case AF_INET6:
+ in6 = (struct sockaddr_in6 *)&local_sock;
+ in6->sin6_family = family;
+ in6->sin6_port = htons(ctx->lport);
+ in6->sin6_addr = in6addr_any;
+ sock_len = sizeof(*in6);
+ break;
+ default:
+ return -1;
+ }
+
+ int opt = 1;
+
+ ret = setsockopt(s, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt));
+
+ if (ret < 0) {
+ perror("setsockopt for SO_REUSEADDR");
+ return ret;
+ }
+
+ ret = setsockopt(s, SOL_SOCKET, SO_REUSEPORT, &opt, sizeof(opt));
+ if (ret < 0) {
+ perror("setsockopt for SO_REUSEPORT");
+ return ret;
+ }
+
+ if (family == AF_INET6) {
+ opt = 0;
+ if (setsockopt(s, IPPROTO_IPV6, IPV6_V6ONLY, &opt,
+ sizeof(opt))) {
+ perror("failed to set IPV6_V6ONLY");
+ return -1;
+ }
+ }
+
+ ret = bind(s, (struct sockaddr *)&local_sock, sock_len);
+ if (ret < 0) {
+ perror("cannot bind socket");
+ goto err_socket;
+ }
+
+ ctx->socket = s;
+ ctx->sa_family = family;
+ return 0;
+
+err_socket:
+ close(s);
+ return -1;
+}
+
+static int ovpn_udp_socket(struct ovpn_ctx *ctx, sa_family_t family)
+{
+ return ovpn_socket(ctx, family, IPPROTO_UDP);
+}
+
+static int ovpn_listen(struct ovpn_ctx *ctx, sa_family_t family)
+{
+ int ret;
+
+ ret = ovpn_socket(ctx, family, IPPROTO_TCP);
+ if (ret < 0)
+ return ret;
+
+ ret = listen(ctx->socket, 10);
+ if (ret < 0) {
+ perror("listen");
+ close(ctx->socket);
+ return -1;
+ }
+
+ return 0;
+}
+
+static int ovpn_accept(struct ovpn_ctx *ctx)
+{
+ socklen_t socklen;
+ int ret;
+
+ socklen = sizeof(ctx->remote);
+ ret = accept(ctx->socket, (struct sockaddr *)&ctx->remote, &socklen);
+ if (ret < 0) {
+ perror("accept");
+ goto err;
+ }
+
+ fprintf(stderr, "Connection received!\n");
+
+ switch (socklen) {
+ case sizeof(struct sockaddr_in):
+ case sizeof(struct sockaddr_in6):
+ break;
+ default:
+ fprintf(stderr, "error: expecting IPv4 or IPv6 connection\n");
+ close(ret);
+ ret = -EINVAL;
+ goto err;
+ }
+
+ return ret;
+err:
+ close(ctx->socket);
+ return ret;
+}
+
+static int ovpn_connect(struct ovpn_ctx *ovpn)
+{
+ socklen_t socklen;
+ int s, ret;
+
+ s = socket(ovpn->remote.in4.sin_family, SOCK_STREAM, 0);
+ if (s < 0) {
+ perror("cannot create socket");
+ return -1;
+ }
+
+ switch (ovpn->remote.in4.sin_family) {
+ case AF_INET:
+ socklen = sizeof(struct sockaddr_in);
+ break;
+ case AF_INET6:
+ socklen = sizeof(struct sockaddr_in6);
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ ret = connect(s, (struct sockaddr *)&ovpn->remote, socklen);
+ if (ret < 0) {
+ perror("connect");
+ goto err;
+ }
+
+ fprintf(stderr, "connected\n");
+
+ ovpn->socket = s;
+
+ return 0;
+err:
+ close(s);
+ return ret;
+}
+
+static int ovpn_new_peer(struct ovpn_ctx *ovpn, bool is_tcp)
+{
+ struct nlattr *attr;
+ struct nl_ctx *ctx;
+ int ret = -1;
+
+ ctx = nl_ctx_alloc(ovpn, OVPN_CMD_PEER_NEW);
+ if (!ctx)
+ return -ENOMEM;
+
+ attr = nla_nest_start(ctx->nl_msg, OVPN_A_PEER);
+ NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_ID, ovpn->peer_id);
+ NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_SOCKET, ovpn->socket);
+
+ if (!is_tcp) {
+ switch (ovpn->remote.in4.sin_family) {
+ case AF_INET:
+ NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_REMOTE_IPV4,
+ ovpn->remote.in4.sin_addr.s_addr);
+ NLA_PUT_U16(ctx->nl_msg, OVPN_A_PEER_REMOTE_PORT,
+ ovpn->remote.in4.sin_port);
+ break;
+ case AF_INET6:
+ NLA_PUT(ctx->nl_msg, OVPN_A_PEER_REMOTE_IPV6,
+ sizeof(ovpn->remote.in6.sin6_addr),
+ &ovpn->remote.in6.sin6_addr);
+ NLA_PUT_U32(ctx->nl_msg,
+ OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID,
+ ovpn->remote.in6.sin6_scope_id);
+ NLA_PUT_U16(ctx->nl_msg, OVPN_A_PEER_REMOTE_PORT,
+ ovpn->remote.in6.sin6_port);
+ break;
+ default:
+ fprintf(stderr,
+ "Invalid family for remote socket address\n");
+ goto nla_put_failure;
+ }
+ }
+
+ if (ovpn->peer_ip_set) {
+ switch (ovpn->peer_ip.in4.sin_family) {
+ case AF_INET:
+ NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_VPN_IPV4,
+ ovpn->peer_ip.in4.sin_addr.s_addr);
+ break;
+ case AF_INET6:
+ NLA_PUT(ctx->nl_msg, OVPN_A_PEER_VPN_IPV6,
+ sizeof(struct in6_addr),
+ &ovpn->peer_ip.in6.sin6_addr);
+ break;
+ default:
+ fprintf(stderr, "Invalid family for peer address\n");
+ goto nla_put_failure;
+ }
+ }
+
+ nla_nest_end(ctx->nl_msg, attr);
+
+ ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+ nl_ctx_free(ctx);
+ return ret;
+}
+
+static int ovpn_set_peer(struct ovpn_ctx *ovpn)
+{
+ struct nlattr *attr;
+ struct nl_ctx *ctx;
+ int ret = -1;
+
+ ctx = nl_ctx_alloc(ovpn, OVPN_CMD_PEER_SET);
+ if (!ctx)
+ return -ENOMEM;
+
+ attr = nla_nest_start(ctx->nl_msg, OVPN_A_PEER);
+ NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_ID, ovpn->peer_id);
+ NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_KEEPALIVE_INTERVAL,
+ ovpn->keepalive_interval);
+ NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_KEEPALIVE_TIMEOUT,
+ ovpn->keepalive_timeout);
+ nla_nest_end(ctx->nl_msg, attr);
+
+ ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+ nl_ctx_free(ctx);
+ return ret;
+}
+
+static int ovpn_del_peer(struct ovpn_ctx *ovpn)
+{
+ struct nlattr *attr;
+ struct nl_ctx *ctx;
+ int ret = -1;
+
+ ctx = nl_ctx_alloc(ovpn, OVPN_CMD_PEER_DEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ attr = nla_nest_start(ctx->nl_msg, OVPN_A_PEER);
+ NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_ID, ovpn->peer_id);
+ nla_nest_end(ctx->nl_msg, attr);
+
+ ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+ nl_ctx_free(ctx);
+ return ret;
+}
+
+static int ovpn_handle_peer(struct nl_msg *msg, void (*arg)__always_unused)
+{
+ struct nlattr *pattrs[OVPN_A_PEER_MAX + 1];
+ struct genlmsghdr *gnlh = nlmsg_data(nlmsg_hdr(msg));
+ struct nlattr *attrs[OVPN_A_MAX + 1];
+ __u16 rport = 0, lport = 0;
+
+ nla_parse(attrs, OVPN_A_MAX, genlmsg_attrdata(gnlh, 0),
+ genlmsg_attrlen(gnlh, 0), NULL);
+
+ if (!attrs[OVPN_A_PEER]) {
+ fprintf(stderr, "no packet content in netlink message\n");
+ return NL_SKIP;
+ }
+
+ nla_parse(pattrs, OVPN_A_PEER_MAX, nla_data(attrs[OVPN_A_PEER]),
+ nla_len(attrs[OVPN_A_PEER]), NULL);
+
+ if (pattrs[OVPN_A_PEER_ID])
+ fprintf(stderr, "* Peer %u\n",
+ nla_get_u32(pattrs[OVPN_A_PEER_ID]));
+
+ if (pattrs[OVPN_A_PEER_SOCKET_NETNSID])
+ fprintf(stderr, "\tsocket NetNS ID: %d\n",
+ nla_get_s32(pattrs[OVPN_A_PEER_SOCKET_NETNSID]));
+
+ if (pattrs[OVPN_A_PEER_VPN_IPV4]) {
+ char buf[INET_ADDRSTRLEN];
+
+ inet_ntop(AF_INET, nla_data(pattrs[OVPN_A_PEER_VPN_IPV4]),
+ buf, sizeof(buf));
+ fprintf(stderr, "\tVPN IPv4: %s\n", buf);
+ }
+
+ if (pattrs[OVPN_A_PEER_VPN_IPV6]) {
+ char buf[INET6_ADDRSTRLEN];
+
+ inet_ntop(AF_INET6, nla_data(pattrs[OVPN_A_PEER_VPN_IPV6]),
+ buf, sizeof(buf));
+ fprintf(stderr, "\tVPN IPv6: %s\n", buf);
+ }
+
+ if (pattrs[OVPN_A_PEER_LOCAL_PORT])
+ lport = ntohs(nla_get_u16(pattrs[OVPN_A_PEER_LOCAL_PORT]));
+
+ if (pattrs[OVPN_A_PEER_REMOTE_PORT])
+ rport = ntohs(nla_get_u16(pattrs[OVPN_A_PEER_REMOTE_PORT]));
+
+ if (pattrs[OVPN_A_PEER_REMOTE_IPV6]) {
+ void *ip = pattrs[OVPN_A_PEER_REMOTE_IPV6];
+ char buf[INET6_ADDRSTRLEN];
+ int scope_id = -1;
+
+ if (pattrs[OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID]) {
+ void *p = pattrs[OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID];
+
+ scope_id = nla_get_u32(p);
+ }
+
+ inet_ntop(AF_INET6, nla_data(ip), buf, sizeof(buf));
+ fprintf(stderr, "\tRemote: %s:%hu (scope-id: %u)\n", buf, rport,
+ scope_id);
+
+ if (pattrs[OVPN_A_PEER_LOCAL_IPV6]) {
+ void *ip = pattrs[OVPN_A_PEER_LOCAL_IPV6];
+
+ inet_ntop(AF_INET6, nla_data(ip), buf, sizeof(buf));
+ fprintf(stderr, "\tLocal: %s:%hu\n", buf, lport);
+ }
+ }
+
+ if (pattrs[OVPN_A_PEER_REMOTE_IPV4]) {
+ void *ip = pattrs[OVPN_A_PEER_REMOTE_IPV4];
+ char buf[INET_ADDRSTRLEN];
+
+ inet_ntop(AF_INET, nla_data(ip), buf, sizeof(buf));
+ fprintf(stderr, "\tRemote: %s:%hu\n", buf, rport);
+
+ if (pattrs[OVPN_A_PEER_LOCAL_IPV4]) {
+ void *p = pattrs[OVPN_A_PEER_LOCAL_IPV4];
+
+ inet_ntop(AF_INET, nla_data(p), buf, sizeof(buf));
+ fprintf(stderr, "\tLocal: %s:%hu\n", buf, lport);
+ }
+ }
+
+ if (pattrs[OVPN_A_PEER_KEEPALIVE_INTERVAL]) {
+ void *p = pattrs[OVPN_A_PEER_KEEPALIVE_INTERVAL];
+
+ fprintf(stderr, "\tKeepalive interval: %u sec\n",
+ nla_get_u32(p));
+ }
+
+ if (pattrs[OVPN_A_PEER_KEEPALIVE_TIMEOUT])
+ fprintf(stderr, "\tKeepalive timeout: %u sec\n",
+ nla_get_u32(pattrs[OVPN_A_PEER_KEEPALIVE_TIMEOUT]));
+
+ if (pattrs[OVPN_A_PEER_VPN_RX_BYTES])
+ fprintf(stderr, "\tVPN RX bytes: %" PRIu64 "\n",
+ ovpn_nla_get_uint(pattrs[OVPN_A_PEER_VPN_RX_BYTES]));
+
+ if (pattrs[OVPN_A_PEER_VPN_TX_BYTES])
+ fprintf(stderr, "\tVPN TX bytes: %" PRIu64 "\n",
+ ovpn_nla_get_uint(pattrs[OVPN_A_PEER_VPN_TX_BYTES]));
+
+ if (pattrs[OVPN_A_PEER_VPN_RX_PACKETS])
+ fprintf(stderr, "\tVPN RX packets: %" PRIu64 "\n",
+ ovpn_nla_get_uint(pattrs[OVPN_A_PEER_VPN_RX_PACKETS]));
+
+ if (pattrs[OVPN_A_PEER_VPN_TX_PACKETS])
+ fprintf(stderr, "\tVPN TX packets: %" PRIu64 "\n",
+ ovpn_nla_get_uint(pattrs[OVPN_A_PEER_VPN_TX_PACKETS]));
+
+ if (pattrs[OVPN_A_PEER_LINK_RX_BYTES])
+ fprintf(stderr, "\tLINK RX bytes: %" PRIu64 "\n",
+ ovpn_nla_get_uint(pattrs[OVPN_A_PEER_LINK_RX_BYTES]));
+
+ if (pattrs[OVPN_A_PEER_LINK_TX_BYTES])
+ fprintf(stderr, "\tLINK TX bytes: %" PRIu64 "\n",
+ ovpn_nla_get_uint(pattrs[OVPN_A_PEER_LINK_TX_BYTES]));
+
+ if (pattrs[OVPN_A_PEER_LINK_RX_PACKETS])
+ fprintf(stderr, "\tLINK RX packets: %" PRIu64 "\n",
+ ovpn_nla_get_uint(pattrs[OVPN_A_PEER_LINK_RX_PACKETS]));
+
+ if (pattrs[OVPN_A_PEER_LINK_TX_PACKETS])
+ fprintf(stderr, "\tLINK TX packets: %" PRIu64 "\n",
+ ovpn_nla_get_uint(pattrs[OVPN_A_PEER_LINK_TX_PACKETS]));
+
+ return NL_SKIP;
+}
+
+static int ovpn_get_peer(struct ovpn_ctx *ovpn)
+{
+ int flags = 0, ret = -1;
+ struct nlattr *attr;
+ struct nl_ctx *ctx;
+
+ if (ovpn->peer_id == PEER_ID_UNDEF)
+ flags = NLM_F_DUMP;
+
+ ctx = nl_ctx_alloc_flags(ovpn, OVPN_CMD_PEER_GET, flags);
+ if (!ctx)
+ return -ENOMEM;
+
+ if (ovpn->peer_id != PEER_ID_UNDEF) {
+ attr = nla_nest_start(ctx->nl_msg, OVPN_A_PEER);
+ NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_ID, ovpn->peer_id);
+ nla_nest_end(ctx->nl_msg, attr);
+ }
+
+ ret = ovpn_nl_msg_send(ctx, ovpn_handle_peer);
+nla_put_failure:
+ nl_ctx_free(ctx);
+ return ret;
+}
+
+static int ovpn_new_key(struct ovpn_ctx *ovpn)
+{
+ struct nlattr *keyconf, *key_dir;
+ struct nl_ctx *ctx;
+ int ret = -1;
+
+ ctx = nl_ctx_alloc(ovpn, OVPN_CMD_KEY_NEW);
+ if (!ctx)
+ return -ENOMEM;
+
+ keyconf = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF);
+ NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_PEER_ID, ovpn->peer_id);
+ NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_SLOT, ovpn->key_slot);
+ NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_KEY_ID, ovpn->key_id);
+ NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_CIPHER_ALG, ovpn->cipher);
+
+ key_dir = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF_ENCRYPT_DIR);
+ NLA_PUT(ctx->nl_msg, OVPN_A_KEYDIR_CIPHER_KEY, KEY_LEN, ovpn->key_enc);
+ NLA_PUT(ctx->nl_msg, OVPN_A_KEYDIR_NONCE_TAIL, NONCE_LEN, ovpn->nonce);
+ nla_nest_end(ctx->nl_msg, key_dir);
+
+ key_dir = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF_DECRYPT_DIR);
+ NLA_PUT(ctx->nl_msg, OVPN_A_KEYDIR_CIPHER_KEY, KEY_LEN, ovpn->key_dec);
+ NLA_PUT(ctx->nl_msg, OVPN_A_KEYDIR_NONCE_TAIL, NONCE_LEN, ovpn->nonce);
+ nla_nest_end(ctx->nl_msg, key_dir);
+
+ nla_nest_end(ctx->nl_msg, keyconf);
+
+ ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+ nl_ctx_free(ctx);
+ return ret;
+}
+
+static int ovpn_del_key(struct ovpn_ctx *ovpn)
+{
+ struct nlattr *keyconf;
+ struct nl_ctx *ctx;
+ int ret = -1;
+
+ ctx = nl_ctx_alloc(ovpn, OVPN_CMD_KEY_DEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ keyconf = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF);
+ NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_PEER_ID, ovpn->peer_id);
+ NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_SLOT, ovpn->key_slot);
+ nla_nest_end(ctx->nl_msg, keyconf);
+
+ ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+ nl_ctx_free(ctx);
+ return ret;
+}
+
+static int ovpn_handle_key(struct nl_msg *msg, void (*arg)__always_unused)
+{
+ struct nlattr *kattrs[OVPN_A_KEYCONF_MAX + 1];
+ struct genlmsghdr *gnlh = nlmsg_data(nlmsg_hdr(msg));
+ struct nlattr *attrs[OVPN_A_MAX + 1];
+
+ nla_parse(attrs, OVPN_A_MAX, genlmsg_attrdata(gnlh, 0),
+ genlmsg_attrlen(gnlh, 0), NULL);
+
+ if (!attrs[OVPN_A_KEYCONF]) {
+ fprintf(stderr, "no packet content in netlink message\n");
+ return NL_SKIP;
+ }
+
+ nla_parse(kattrs, OVPN_A_KEYCONF_MAX, nla_data(attrs[OVPN_A_KEYCONF]),
+ nla_len(attrs[OVPN_A_KEYCONF]), NULL);
+
+ if (kattrs[OVPN_A_KEYCONF_PEER_ID])
+ fprintf(stderr, "* Peer %u\n",
+ nla_get_u32(kattrs[OVPN_A_KEYCONF_PEER_ID]));
+ if (kattrs[OVPN_A_KEYCONF_SLOT]) {
+ fprintf(stderr, "\t- Slot: ");
+ switch (nla_get_u32(kattrs[OVPN_A_KEYCONF_SLOT])) {
+ case OVPN_KEY_SLOT_PRIMARY:
+ fprintf(stderr, "primary\n");
+ break;
+ case OVPN_KEY_SLOT_SECONDARY:
+ fprintf(stderr, "secondary\n");
+ break;
+ default:
+ fprintf(stderr, "invalid (%u)\n",
+ nla_get_u32(kattrs[OVPN_A_KEYCONF_SLOT]));
+ break;
+ }
+ }
+ if (kattrs[OVPN_A_KEYCONF_KEY_ID])
+ fprintf(stderr, "\t- Key ID: %u\n",
+ nla_get_u32(kattrs[OVPN_A_KEYCONF_KEY_ID]));
+ if (kattrs[OVPN_A_KEYCONF_CIPHER_ALG]) {
+ fprintf(stderr, "\t- Cipher: ");
+ switch (nla_get_u32(kattrs[OVPN_A_KEYCONF_CIPHER_ALG])) {
+ case OVPN_CIPHER_ALG_NONE:
+ fprintf(stderr, "none\n");
+ break;
+ case OVPN_CIPHER_ALG_AES_GCM:
+ fprintf(stderr, "aes-gcm\n");
+ break;
+ case OVPN_CIPHER_ALG_CHACHA20_POLY1305:
+ fprintf(stderr, "chacha20poly1305\n");
+ break;
+ default:
+ fprintf(stderr, "invalid (%u)\n",
+ nla_get_u32(kattrs[OVPN_A_KEYCONF_CIPHER_ALG]));
+ break;
+ }
+ }
+
+ return NL_SKIP;
+}
+
+static int ovpn_get_key(struct ovpn_ctx *ovpn)
+{
+ struct nlattr *keyconf;
+ struct nl_ctx *ctx;
+ int ret = -1;
+
+ ctx = nl_ctx_alloc(ovpn, OVPN_CMD_KEY_GET);
+ if (!ctx)
+ return -ENOMEM;
+
+ keyconf = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF);
+ NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_PEER_ID, ovpn->peer_id);
+ NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_SLOT, ovpn->key_slot);
+ nla_nest_end(ctx->nl_msg, keyconf);
+
+ ret = ovpn_nl_msg_send(ctx, ovpn_handle_key);
+nla_put_failure:
+ nl_ctx_free(ctx);
+ return ret;
+}
+
+static int ovpn_swap_keys(struct ovpn_ctx *ovpn)
+{
+ struct nl_ctx *ctx;
+ struct nlattr *kc;
+ int ret = -1;
+
+ ctx = nl_ctx_alloc(ovpn, OVPN_CMD_KEY_SWAP);
+ if (!ctx)
+ return -ENOMEM;
+
+ kc = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF);
+ NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_PEER_ID, ovpn->peer_id);
+ nla_nest_end(ctx->nl_msg, kc);
+
+ ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+ nl_ctx_free(ctx);
+ return ret;
+}
+
+/* Helper function used to easily add attributes to a rtnl message */
+static int ovpn_addattr(struct nlmsghdr *n, int maxlen, int type,
+ const void *data, int alen)
+{
+ int len = RTA_LENGTH(alen);
+ struct rtattr *rta;
+
+ if ((int)(NLMSG_ALIGN(n->nlmsg_len) + RTA_ALIGN(len)) > maxlen) {
+ fprintf(stderr, "%s: rtnl: message exceeded bound of %d\n",
+ __func__, maxlen);
+ return -EMSGSIZE;
+ }
+
+ rta = nlmsg_tail(n);
+ rta->rta_type = type;
+ rta->rta_len = len;
+
+ if (!data)
+ memset(RTA_DATA(rta), 0, alen);
+ else
+ memcpy(RTA_DATA(rta), data, alen);
+
+ n->nlmsg_len = NLMSG_ALIGN(n->nlmsg_len) + RTA_ALIGN(len);
+
+ return 0;
+}
+
+static struct rtattr *ovpn_nest_start(struct nlmsghdr *msg, size_t max_size,
+ int attr)
+{
+ struct rtattr *nest = nlmsg_tail(msg);
+
+ if (ovpn_addattr(msg, max_size, attr, NULL, 0) < 0)
+ return NULL;
+
+ return nest;
+}
+
+static void ovpn_nest_end(struct nlmsghdr *msg, struct rtattr *nest)
+{
+ nest->rta_len = (uint8_t *)nlmsg_tail(msg) - (uint8_t *)nest;
+}
+
+#define RT_SNDBUF_SIZE (1024 * 2)
+#define RT_RCVBUF_SIZE (1024 * 4)
+
+/* Open RTNL socket */
+static int ovpn_rt_socket(void)
+{
+ int sndbuf = RT_SNDBUF_SIZE, rcvbuf = RT_RCVBUF_SIZE, fd;
+
+ fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+ if (fd < 0) {
+ fprintf(stderr, "%s: cannot open netlink socket\n", __func__);
+ return fd;
+ }
+
+ if (setsockopt(fd, SOL_SOCKET, SO_SNDBUF, &sndbuf,
+ sizeof(sndbuf)) < 0) {
+ fprintf(stderr, "%s: SO_SNDBUF\n", __func__);
+ close(fd);
+ return -1;
+ }
+
+ if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF, &rcvbuf,
+ sizeof(rcvbuf)) < 0) {
+ fprintf(stderr, "%s: SO_RCVBUF\n", __func__);
+ close(fd);
+ return -1;
+ }
+
+ return fd;
+}
+
+/* Bind socket to Netlink subsystem */
+static int ovpn_rt_bind(int fd, uint32_t groups)
+{
+ struct sockaddr_nl local = { 0 };
+ socklen_t addr_len;
+
+ local.nl_family = AF_NETLINK;
+ local.nl_groups = groups;
+
+ if (bind(fd, (struct sockaddr *)&local, sizeof(local)) < 0) {
+ fprintf(stderr, "%s: cannot bind netlink socket: %d\n",
+ __func__, errno);
+ return -errno;
+ }
+
+ addr_len = sizeof(local);
+ if (getsockname(fd, (struct sockaddr *)&local, &addr_len) < 0) {
+ fprintf(stderr, "%s: cannot getsockname: %d\n", __func__,
+ errno);
+ return -errno;
+ }
+
+ if (addr_len != sizeof(local)) {
+ fprintf(stderr, "%s: wrong address length %d\n", __func__,
+ addr_len);
+ return -EINVAL;
+ }
+
+ if (local.nl_family != AF_NETLINK) {
+ fprintf(stderr, "%s: wrong address family %d\n", __func__,
+ local.nl_family);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+typedef int (*ovpn_parse_reply_cb)(struct nlmsghdr *msg, void *arg);
+
+/* Send Netlink message and run callback on reply (if specified) */
+static int ovpn_rt_send(struct nlmsghdr *payload, pid_t peer,
+ unsigned int groups, ovpn_parse_reply_cb cb,
+ void *arg_cb)
+{
+ int len, rem_len, fd, ret, rcv_len;
+ struct sockaddr_nl nladdr = { 0 };
+ struct nlmsgerr *err;
+ struct nlmsghdr *h;
+ char buf[1024 * 16];
+ struct iovec iov = {
+ .iov_base = payload,
+ .iov_len = payload->nlmsg_len,
+ };
+ struct msghdr nlmsg = {
+ .msg_name = &nladdr,
+ .msg_namelen = sizeof(nladdr),
+ .msg_iov = &iov,
+ .msg_iovlen = 1,
+ };
+
+ nladdr.nl_family = AF_NETLINK;
+ nladdr.nl_pid = peer;
+ nladdr.nl_groups = groups;
+
+ payload->nlmsg_seq = time(NULL);
+
+ /* no need to send reply */
+ if (!cb)
+ payload->nlmsg_flags |= NLM_F_ACK;
+
+ fd = ovpn_rt_socket();
+ if (fd < 0) {
+ fprintf(stderr, "%s: can't open rtnl socket\n", __func__);
+ return -errno;
+ }
+
+ ret = ovpn_rt_bind(fd, 0);
+ if (ret < 0) {
+ fprintf(stderr, "%s: can't bind rtnl socket\n", __func__);
+ ret = -errno;
+ goto out;
+ }
+
+ ret = sendmsg(fd, &nlmsg, 0);
+ if (ret < 0) {
+ fprintf(stderr, "%s: rtnl: error on sendmsg()\n", __func__);
+ ret = -errno;
+ goto out;
+ }
+
+ /* prepare buffer to store RTNL replies */
+ memset(buf, 0, sizeof(buf));
+ iov.iov_base = buf;
+
+ while (1) {
+ /*
+ * iov_len is modified by recvmsg(), therefore has to be initialized before
+ * using it again
+ */
+ iov.iov_len = sizeof(buf);
+ rcv_len = recvmsg(fd, &nlmsg, 0);
+ if (rcv_len < 0) {
+ if (errno == EINTR || errno == EAGAIN) {
+ fprintf(stderr, "%s: interrupted call\n",
+ __func__);
+ continue;
+ }
+ fprintf(stderr, "%s: rtnl: error on recvmsg()\n",
+ __func__);
+ ret = -errno;
+ goto out;
+ }
+
+ if (rcv_len == 0) {
+ fprintf(stderr,
+ "%s: rtnl: socket reached unexpected EOF\n",
+ __func__);
+ ret = -EIO;
+ goto out;
+ }
+
+ if (nlmsg.msg_namelen != sizeof(nladdr)) {
+ fprintf(stderr,
+ "%s: sender address length: %u (expected %zu)\n",
+ __func__, nlmsg.msg_namelen, sizeof(nladdr));
+ ret = -EIO;
+ goto out;
+ }
+
+ h = (struct nlmsghdr *)buf;
+ while (rcv_len >= (int)sizeof(*h)) {
+ len = h->nlmsg_len;
+ rem_len = len - sizeof(*h);
+
+ if (rem_len < 0 || len > rcv_len) {
+ if (nlmsg.msg_flags & MSG_TRUNC) {
+ fprintf(stderr, "%s: truncated message\n",
+ __func__);
+ ret = -EIO;
+ goto out;
+ }
+ fprintf(stderr, "%s: malformed message: len=%d\n",
+ __func__, len);
+ ret = -EIO;
+ goto out;
+ }
+
+ if (h->nlmsg_type == NLMSG_DONE) {
+ ret = 0;
+ goto out;
+ }
+
+ if (h->nlmsg_type == NLMSG_ERROR) {
+ err = (struct nlmsgerr *)NLMSG_DATA(h);
+ if (rem_len < (int)sizeof(struct nlmsgerr)) {
+ fprintf(stderr, "%s: ERROR truncated\n",
+ __func__);
+ ret = -EIO;
+ goto out;
+ }
+
+ if (err->error) {
+ fprintf(stderr, "%s: (%d) %s\n",
+ __func__, err->error,
+ strerror(-err->error));
+ ret = err->error;
+ goto out;
+ }
+
+ ret = 0;
+ if (cb) {
+ int r = cb(h, arg_cb);
+
+ if (r <= 0)
+ ret = r;
+ }
+ goto out;
+ }
+
+ if (cb) {
+ int r = cb(h, arg_cb);
+
+ if (r <= 0) {
+ ret = r;
+ goto out;
+ }
+ } else {
+ fprintf(stderr, "%s: RTNL: unexpected reply\n",
+ __func__);
+ }
+
+ rcv_len -= NLMSG_ALIGN(len);
+ h = (struct nlmsghdr *)((uint8_t *)h +
+ NLMSG_ALIGN(len));
+ }
+
+ if (nlmsg.msg_flags & MSG_TRUNC) {
+ fprintf(stderr, "%s: message truncated\n", __func__);
+ continue;
+ }
+
+ if (rcv_len) {
+ fprintf(stderr, "%s: rtnl: %d not parsed bytes\n",
+ __func__, rcv_len);
+ ret = -1;
+ goto out;
+ }
+ }
+out:
+ close(fd);
+
+ return ret;
+}
+
+struct ovpn_link_req {
+ struct nlmsghdr n;
+ struct ifinfomsg i;
+ char buf[256];
+};
+
+static int ovpn_new_iface(struct ovpn_ctx *ovpn)
+{
+ struct rtattr *linkinfo, *data;
+ struct ovpn_link_req req = { 0 };
+ int ret = -1;
+
+ fprintf(stdout, "Creating interface %s with mode %u\n", ovpn->ifname,
+ ovpn->mode);
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(req.i));
+ req.n.nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE | NLM_F_EXCL;
+ req.n.nlmsg_type = RTM_NEWLINK;
+
+ if (ovpn_addattr(&req.n, sizeof(req), IFLA_IFNAME, ovpn->ifname,
+ strlen(ovpn->ifname) + 1) < 0)
+ goto err;
+
+ linkinfo = ovpn_nest_start(&req.n, sizeof(req), IFLA_LINKINFO);
+ if (!linkinfo)
+ goto err;
+
+ if (ovpn_addattr(&req.n, sizeof(req), IFLA_INFO_KIND, OVPN_FAMILY_NAME,
+ strlen(OVPN_FAMILY_NAME) + 1) < 0)
+ goto err;
+
+ if (ovpn->mode_set) {
+ data = ovpn_nest_start(&req.n, sizeof(req), IFLA_INFO_DATA);
+ if (!data)
+ goto err;
+
+ if (ovpn_addattr(&req.n, sizeof(req), IFLA_OVPN_MODE,
+ &ovpn->mode, sizeof(uint8_t)) < 0)
+ goto err;
+
+ ovpn_nest_end(&req.n, data);
+ }
+
+ ovpn_nest_end(&req.n, linkinfo);
+
+ req.i.ifi_family = AF_PACKET;
+
+ ret = ovpn_rt_send(&req.n, 0, 0, NULL, NULL);
+err:
+ return ret;
+}
+
+static int ovpn_del_iface(struct ovpn_ctx *ovpn)
+{
+ struct ovpn_link_req req = { 0 };
+
+ fprintf(stdout, "Deleting interface %s ifindex %u\n", ovpn->ifname,
+ ovpn->ifindex);
+
+ req.n.nlmsg_len = NLMSG_LENGTH(sizeof(req.i));
+ req.n.nlmsg_flags = NLM_F_REQUEST;
+ req.n.nlmsg_type = RTM_DELLINK;
+
+ req.i.ifi_family = AF_PACKET;
+ req.i.ifi_index = ovpn->ifindex;
+
+ return ovpn_rt_send(&req.n, 0, 0, NULL, NULL);
+}
+
+static int nl_seq_check(struct nl_msg (*msg)__always_unused,
+ void (*arg)__always_unused)
+{
+ return NL_OK;
+}
+
+struct mcast_handler_args {
+ const char *group;
+ int id;
+};
+
+static int mcast_family_handler(struct nl_msg *msg, void *arg)
+{
+ struct mcast_handler_args *grp = arg;
+ struct nlattr *tb[CTRL_ATTR_MAX + 1];
+ struct genlmsghdr *gnlh = nlmsg_data(nlmsg_hdr(msg));
+ struct nlattr *mcgrp;
+ int rem_mcgrp;
+
+ nla_parse(tb, CTRL_ATTR_MAX, genlmsg_attrdata(gnlh, 0),
+ genlmsg_attrlen(gnlh, 0), NULL);
+
+ if (!tb[CTRL_ATTR_MCAST_GROUPS])
+ return NL_SKIP;
+
+ nla_for_each_nested(mcgrp, tb[CTRL_ATTR_MCAST_GROUPS], rem_mcgrp) {
+ struct nlattr *tb_mcgrp[CTRL_ATTR_MCAST_GRP_MAX + 1];
+
+ nla_parse(tb_mcgrp, CTRL_ATTR_MCAST_GRP_MAX,
+ nla_data(mcgrp), nla_len(mcgrp), NULL);
+
+ if (!tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME] ||
+ !tb_mcgrp[CTRL_ATTR_MCAST_GRP_ID])
+ continue;
+ if (strncmp(nla_data(tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME]),
+ grp->group, nla_len(tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME])))
+ continue;
+ grp->id = nla_get_u32(tb_mcgrp[CTRL_ATTR_MCAST_GRP_ID]);
+ break;
+ }
+
+ return NL_SKIP;
+}
+
+static int mcast_error_handler(struct sockaddr_nl (*nla)__always_unused,
+ struct nlmsgerr *err, void *arg)
+{
+ int *ret = arg;
+
+ *ret = err->error;
+ return NL_STOP;
+}
+
+static int mcast_ack_handler(struct nl_msg (*msg)__always_unused, void *arg)
+{
+ int *ret = arg;
+
+ *ret = 0;
+ return NL_STOP;
+}
+
+static int ovpn_handle_msg(struct nl_msg *msg, void *arg)
+{
+ struct genlmsghdr *gnlh = nlmsg_data(nlmsg_hdr(msg));
+ struct nlattr *attrs[OVPN_A_MAX + 1];
+ struct nlmsghdr *nlh = nlmsg_hdr(msg);
+ char ifname[IF_NAMESIZE];
+ int *ret = arg;
+ __u32 ifindex;
+
+ fprintf(stderr, "received message from ovpn-dco\n");
+
+ *ret = -1;
+
+ if (!genlmsg_valid_hdr(nlh, 0)) {
+ fprintf(stderr, "invalid header\n");
+ return NL_STOP;
+ }
+
+ if (nla_parse(attrs, OVPN_A_MAX, genlmsg_attrdata(gnlh, 0),
+ genlmsg_attrlen(gnlh, 0), NULL)) {
+ fprintf(stderr, "received bogus data from ovpn-dco\n");
+ return NL_STOP;
+ }
+
+ if (!attrs[OVPN_A_IFINDEX]) {
+ fprintf(stderr, "no ifindex in this message\n");
+ return NL_STOP;
+ }
+
+ ifindex = nla_get_u32(attrs[OVPN_A_IFINDEX]);
+ if (!if_indextoname(ifindex, ifname)) {
+ fprintf(stderr, "cannot resolve ifname for ifindex: %u\n",
+ ifindex);
+ return NL_STOP;
+ }
+
+ switch (gnlh->cmd) {
+ case OVPN_CMD_PEER_DEL_NTF:
+ fprintf(stdout, "received CMD_PEER_DEL_NTF\n");
+ break;
+ case OVPN_CMD_KEY_SWAP_NTF:
+ fprintf(stdout, "received CMD_KEY_SWAP_NTF\n");
+ break;
+ default:
+ fprintf(stderr, "received unknown command: %d\n", gnlh->cmd);
+ return NL_STOP;
+ }
+
+ *ret = 0;
+ return NL_OK;
+}
+
+static int ovpn_get_mcast_id(struct nl_sock *sock, const char *family,
+ const char *group)
+{
+ struct nl_msg *msg;
+ struct nl_cb *cb;
+ int ret, ctrlid;
+ struct mcast_handler_args grp = {
+ .group = group,
+ .id = -ENOENT,
+ };
+
+ msg = nlmsg_alloc();
+ if (!msg)
+ return -ENOMEM;
+
+ cb = nl_cb_alloc(NL_CB_DEFAULT);
+ if (!cb) {
+ ret = -ENOMEM;
+ goto out_fail_cb;
+ }
+
+ ctrlid = genl_ctrl_resolve(sock, "nlctrl");
+
+ genlmsg_put(msg, 0, 0, ctrlid, 0, 0, CTRL_CMD_GETFAMILY, 0);
+
+ ret = -ENOBUFS;
+ NLA_PUT_STRING(msg, CTRL_ATTR_FAMILY_NAME, family);
+
+ ret = nl_send_auto_complete(sock, msg);
+ if (ret < 0)
+ goto nla_put_failure;
+
+ ret = 1;
+
+ nl_cb_err(cb, NL_CB_CUSTOM, mcast_error_handler, &ret);
+ nl_cb_set(cb, NL_CB_ACK, NL_CB_CUSTOM, mcast_ack_handler, &ret);
+ nl_cb_set(cb, NL_CB_VALID, NL_CB_CUSTOM, mcast_family_handler, &grp);
+
+ while (ret > 0)
+ nl_recvmsgs(sock, cb);
+
+ if (ret == 0)
+ ret = grp.id;
+ nla_put_failure:
+ nl_cb_put(cb);
+ out_fail_cb:
+ nlmsg_free(msg);
+ return ret;
+}
+
+static int ovpn_listen_mcast(void)
+{
+ struct nl_sock *sock;
+ struct nl_cb *cb;
+ int mcid, ret;
+
+ sock = nl_socket_alloc();
+ if (!sock) {
+ fprintf(stderr, "cannot allocate netlink socket\n");
+ goto err_free;
+ }
+
+ nl_socket_set_buffer_size(sock, 8192, 8192);
+
+ ret = genl_connect(sock);
+ if (ret < 0) {
+ fprintf(stderr, "cannot connect to generic netlink: %s\n",
+ nl_geterror(ret));
+ goto err_free;
+ }
+
+ mcid = ovpn_get_mcast_id(sock, OVPN_FAMILY_NAME, OVPN_MCGRP_PEERS);
+ if (mcid < 0) {
+ fprintf(stderr, "cannot get mcast group: %s\n",
+ nl_geterror(mcid));
+ goto err_free;
+ }
+
+ ret = nl_socket_add_membership(sock, mcid);
+ if (ret) {
+ fprintf(stderr, "failed to join mcast group: %d\n", ret);
+ goto err_free;
+ }
+
+ ret = 1;
+ cb = nl_cb_alloc(NL_CB_DEFAULT);
+ nl_cb_set(cb, NL_CB_SEQ_CHECK, NL_CB_CUSTOM, nl_seq_check, NULL);
+ nl_cb_set(cb, NL_CB_VALID, NL_CB_CUSTOM, ovpn_handle_msg, &ret);
+ nl_cb_err(cb, NL_CB_CUSTOM, ovpn_nl_cb_error, &ret);
+
+ while (ret == 1) {
+ int err = nl_recvmsgs(sock, cb);
+
+ if (err < 0) {
+ fprintf(stderr,
+ "cannot receive netlink message: (%d) %s\n",
+ err, nl_geterror(-err));
+ ret = -1;
+ break;
+ }
+ }
+
+ nl_cb_put(cb);
+err_free:
+ nl_socket_free(sock);
+ return ret;
+}
+
+static void usage(const char *cmd)
+{
+ fprintf(stderr,
+ "Usage %s <command> <iface> [arguments..]\n",
+ cmd);
+ fprintf(stderr, "where <command> can be one of the following\n\n");
+
+ fprintf(stderr, "* new_iface <iface> [mode]: create new ovpn interface\n");
+ fprintf(stderr, "\tiface: ovpn interface name\n");
+ fprintf(stderr, "\tmode:\n");
+ fprintf(stderr, "\t\t- P2P for peer-to-peer mode (i.e. client)\n");
+ fprintf(stderr, "\t\t- MP for multi-peer mode (i.e. server)\n");
+
+ fprintf(stderr, "* del_iface <iface>: delete ovpn interface\n");
+ fprintf(stderr, "\tiface: ovpn interface name\n");
+
+ fprintf(stderr,
+ "* listen <iface> <lport> <peers_file> [ipv6]: listen for incoming peer TCP connections\n");
+ fprintf(stderr, "\tiface: ovpn interface name\n");
+ fprintf(stderr, "\tlport: TCP port to listen to\n");
+ fprintf(stderr,
+ "\tpeers_file: file containing one peer per line: Line format:\n");
+ fprintf(stderr, "\t\t<peer_id> <vpnaddr>\n");
+ fprintf(stderr,
+ "\tipv6: whether the socket should listen to the IPv6 wildcard address\n");
+
+ fprintf(stderr,
+ "* connect <iface> <peer_id> <raddr> <rport> [key_file]: start connecting peer of TCP-based VPN session\n");
+ fprintf(stderr, "\tiface: ovpn interface name\n");
+ fprintf(stderr, "\tpeer_id: peer ID of the connecting peer\n");
+ fprintf(stderr, "\traddr: peer IP address to connect to\n");
+ fprintf(stderr, "\trport: peer TCP port to connect to\n");
+ fprintf(stderr,
+ "\tkey_file: file containing the symmetric key for encryption\n");
+
+ fprintf(stderr,
+ "* new_peer <iface> <peer_id> <lport> <raddr> <rport> [vpnaddr]: add new peer\n");
+ fprintf(stderr, "\tiface: ovpn interface name\n");
+ fprintf(stderr, "\tlport: local UDP port to bind to\n");
+ fprintf(stderr,
+ "\tpeer_id: peer ID to be used in data packets to/from this peer\n");
+ fprintf(stderr, "\traddr: peer IP address\n");
+ fprintf(stderr, "\trport: peer UDP port\n");
+ fprintf(stderr, "\tvpnaddr: peer VPN IP\n");
+
+ fprintf(stderr,
+ "* new_multi_peer <iface> <lport> <peers_file>: add multiple peers as listed in the file\n");
+ fprintf(stderr, "\tiface: ovpn interface name\n");
+ fprintf(stderr, "\tlport: local UDP port to bind to\n");
+ fprintf(stderr,
+ "\tpeers_file: text file containing one peer per line. Line format:\n");
+ fprintf(stderr, "\t\t<peer_id> <raddr> <rport> <vpnaddr>\n");
+
+ fprintf(stderr,
+ "* set_peer <iface> <peer_id> <keepalive_interval> <keepalive_timeout>: set peer attributes\n");
+ fprintf(stderr, "\tiface: ovpn interface name\n");
+ fprintf(stderr, "\tpeer_id: peer ID of the peer to modify\n");
+ fprintf(stderr,
+ "\tkeepalive_interval: interval for sending ping messages\n");
+ fprintf(stderr,
+ "\tkeepalive_timeout: time after which a peer is timed out\n");
+
+ fprintf(stderr, "* del_peer <iface> <peer_id>: delete peer\n");
+ fprintf(stderr, "\tiface: ovpn interface name\n");
+ fprintf(stderr, "\tpeer_id: peer ID of the peer to delete\n");
+
+ fprintf(stderr, "* get_peer <iface> [peer_id]: retrieve peer(s) status\n");
+ fprintf(stderr, "\tiface: ovpn interface name\n");
+ fprintf(stderr,
+ "\tpeer_id: peer ID of the peer to query. All peers are returned if omitted\n");
+
+ fprintf(stderr,
+ "* new_key <iface> <peer_id> <slot> <key_id> <cipher> <key_dir> <key_file>: set data channel key\n");
+ fprintf(stderr, "\tiface: ovpn interface name\n");
+ fprintf(stderr,
+ "\tpeer_id: peer ID of the peer to configure the key for\n");
+ fprintf(stderr, "\tslot: either 1 (primary) or 2 (secondary)\n");
+ fprintf(stderr, "\tkey_id: an ID from 0 to 7\n");
+ fprintf(stderr,
+ "\tcipher: cipher to use, supported: aes (AES-GCM), chachapoly (CHACHA20POLY1305)\n");
+ fprintf(stderr,
+ "\tkey_dir: key direction, must 0 on one host and 1 on the other\n");
+ fprintf(stderr, "\tkey_file: file containing the pre-shared key\n");
+
+ fprintf(stderr,
+ "* del_key <iface> <peer_id> [slot]: erase existing data channel key\n");
+ fprintf(stderr, "\tiface: ovpn interface name\n");
+ fprintf(stderr, "\tpeer_id: peer ID of the peer to modify\n");
+ fprintf(stderr, "\tslot: slot to erase. PRIMARY if omitted\n");
+
+ fprintf(stderr,
+ "* get_key <iface> <peer_id> <slot>: retrieve non sensible key data\n");
+ fprintf(stderr, "\tiface: ovpn interface name\n");
+ fprintf(stderr, "\tpeer_id: peer ID of the peer to query\n");
+ fprintf(stderr, "\tslot: either 1 (primary) or 2 (secondary)\n");
+
+ fprintf(stderr,
+ "* swap_keys <iface> <peer_id>: swap content of primary and secondary key slots\n");
+ fprintf(stderr, "\tiface: ovpn interface name\n");
+ fprintf(stderr, "\tpeer_id: peer ID of the peer to modify\n");
+
+ fprintf(stderr,
+ "* listen_mcast: listen to ovpn netlink multicast messages\n");
+}
+
+static int ovpn_parse_remote(struct ovpn_ctx *ovpn, const char *host,
+ const char *service, const char *vpnip)
+{
+ int ret;
+ struct addrinfo *result;
+ struct addrinfo hints = {
+ .ai_family = ovpn->sa_family,
+ .ai_socktype = SOCK_DGRAM,
+ .ai_protocol = IPPROTO_UDP
+ };
+
+ if (host) {
+ ret = getaddrinfo(host, service, &hints, &result);
+ if (ret) {
+ fprintf(stderr, "getaddrinfo on remote error: %s\n",
+ gai_strerror(ret));
+ return -1;
+ }
+
+ if (!(result->ai_family == AF_INET &&
+ result->ai_addrlen == sizeof(struct sockaddr_in)) &&
+ !(result->ai_family == AF_INET6 &&
+ result->ai_addrlen == sizeof(struct sockaddr_in6))) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ memcpy(&ovpn->remote, result->ai_addr, result->ai_addrlen);
+ }
+
+ if (vpnip) {
+ ret = getaddrinfo(vpnip, NULL, &hints, &result);
+ if (ret) {
+ fprintf(stderr, "getaddrinfo on vpnip error: %s\n",
+ gai_strerror(ret));
+ return -1;
+ }
+
+ if (!(result->ai_family == AF_INET &&
+ result->ai_addrlen == sizeof(struct sockaddr_in)) &&
+ !(result->ai_family == AF_INET6 &&
+ result->ai_addrlen == sizeof(struct sockaddr_in6))) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ memcpy(&ovpn->peer_ip, result->ai_addr, result->ai_addrlen);
+ ovpn->sa_family = result->ai_family;
+
+ ovpn->peer_ip_set = true;
+ }
+
+ ret = 0;
+out:
+ freeaddrinfo(result);
+ return ret;
+}
+
+static int ovpn_parse_new_peer(struct ovpn_ctx *ovpn, const char *peer_id,
+ const char *raddr, const char *rport,
+ const char *vpnip)
+{
+ ovpn->peer_id = strtoul(peer_id, NULL, 10);
+ if (errno == ERANGE || ovpn->peer_id > PEER_ID_UNDEF) {
+ fprintf(stderr, "peer ID value out of range\n");
+ return -1;
+ }
+
+ return ovpn_parse_remote(ovpn, raddr, rport, vpnip);
+}
+
+static int ovpn_parse_key_slot(const char *arg, struct ovpn_ctx *ovpn)
+{
+ int slot = strtoul(arg, NULL, 10);
+
+ if (errno == ERANGE || slot < 1 || slot > 2) {
+ fprintf(stderr, "key slot out of range\n");
+ return -1;
+ }
+
+ switch (slot) {
+ case 1:
+ ovpn->key_slot = OVPN_KEY_SLOT_PRIMARY;
+ break;
+ case 2:
+ ovpn->key_slot = OVPN_KEY_SLOT_SECONDARY;
+ break;
+ }
+
+ return 0;
+}
+
+static int ovpn_send_tcp_data(int socket)
+{
+ uint16_t len = htons(1000);
+ uint8_t buf[1002];
+ int ret;
+
+ memcpy(buf, &len, sizeof(len));
+ memset(buf + sizeof(len), 0x86, sizeof(buf) - sizeof(len));
+
+ ret = send(socket, buf, sizeof(buf), MSG_NOSIGNAL);
+
+ fprintf(stdout, "Sent %u bytes over TCP socket\n", ret);
+
+ return ret > 0 ? 0 : ret;
+}
+
+static int ovpn_recv_tcp_data(int socket)
+{
+ uint8_t buf[1002];
+ uint16_t len;
+ int ret;
+
+ ret = recv(socket, buf, sizeof(buf), MSG_NOSIGNAL);
+
+ if (ret < 2) {
+ fprintf(stderr, ">>>> Error while reading TCP data: %d\n", ret);
+ return ret;
+ }
+
+ memcpy(&len, buf, sizeof(len));
+ len = ntohs(len);
+
+ fprintf(stdout, ">>>> Received %u bytes over TCP socket, header: %u\n",
+ ret, len);
+
+ return 0;
+}
+
+static enum ovpn_cmd ovpn_parse_cmd(const char *cmd)
+{
+ if (!strcmp(cmd, "new_iface"))
+ return CMD_NEW_IFACE;
+
+ if (!strcmp(cmd, "del_iface"))
+ return CMD_DEL_IFACE;
+
+ if (!strcmp(cmd, "listen"))
+ return CMD_LISTEN;
+
+ if (!strcmp(cmd, "connect"))
+ return CMD_CONNECT;
+
+ if (!strcmp(cmd, "new_peer"))
+ return CMD_NEW_PEER;
+
+ if (!strcmp(cmd, "new_multi_peer"))
+ return CMD_NEW_MULTI_PEER;
+
+ if (!strcmp(cmd, "set_peer"))
+ return CMD_SET_PEER;
+
+ if (!strcmp(cmd, "del_peer"))
+ return CMD_DEL_PEER;
+
+ if (!strcmp(cmd, "get_peer"))
+ return CMD_GET_PEER;
+
+ if (!strcmp(cmd, "new_key"))
+ return CMD_NEW_KEY;
+
+ if (!strcmp(cmd, "del_key"))
+ return CMD_DEL_KEY;
+
+ if (!strcmp(cmd, "get_key"))
+ return CMD_GET_KEY;
+
+ if (!strcmp(cmd, "swap_keys"))
+ return CMD_SWAP_KEYS;
+
+ if (!strcmp(cmd, "listen_mcast"))
+ return CMD_LISTEN_MCAST;
+
+ return CMD_INVALID;
+}
+
+/* Send process to background and waits for signal.
+ *
+ * This helper is called at the end of commands
+ * creating sockets, so that the latter stay alive
+ * along with the process that created them.
+ *
+ * A signal is expected to be delivered in order to
+ * terminate the waiting processes
+ */
+static void ovpn_waitbg(void)
+{
+ daemon(1, 1);
+ pause();
+}
+
+static int ovpn_run_cmd(struct ovpn_ctx *ovpn)
+{
+ char peer_id[10], vpnip[INET6_ADDRSTRLEN], laddr[128], lport[10];
+ char raddr[128], rport[10];
+ int n, ret;
+ FILE *fp;
+
+ switch (ovpn->cmd) {
+ case CMD_NEW_IFACE:
+ ret = ovpn_new_iface(ovpn);
+ break;
+ case CMD_DEL_IFACE:
+ ret = ovpn_del_iface(ovpn);
+ break;
+ case CMD_LISTEN:
+ ret = ovpn_listen(ovpn, ovpn->sa_family);
+ if (ret < 0) {
+ fprintf(stderr, "cannot listen on TCP socket\n");
+ return ret;
+ }
+
+ fp = fopen(ovpn->peers_file, "r");
+ if (!fp) {
+ fprintf(stderr, "cannot open file: %s\n",
+ ovpn->peers_file);
+ return -1;
+ }
+
+ int num_peers = 0;
+
+ while ((n = fscanf(fp, "%s %s\n", peer_id, vpnip)) == 2) {
+ struct ovpn_ctx peer_ctx = { 0 };
+
+ if (num_peers == MAX_PEERS) {
+ fprintf(stderr, "max peers reached!\n");
+ return -E2BIG;
+ }
+
+ peer_ctx.ifindex = ovpn->ifindex;
+ peer_ctx.sa_family = ovpn->sa_family;
+
+ peer_ctx.socket = ovpn_accept(ovpn);
+ if (peer_ctx.socket < 0) {
+ fprintf(stderr, "cannot accept connection!\n");
+ return -1;
+ }
+
+ /* store peer sockets to test TCP I/O */
+ ovpn->cli_sockets[num_peers] = peer_ctx.socket;
+
+ ret = ovpn_parse_new_peer(&peer_ctx, peer_id, NULL,
+ NULL, vpnip);
+ if (ret < 0) {
+ fprintf(stderr, "error while parsing line\n");
+ return -1;
+ }
+
+ ret = ovpn_new_peer(&peer_ctx, true);
+ if (ret < 0) {
+ fprintf(stderr,
+ "cannot add peer to VPN: %s %s\n",
+ peer_id, vpnip);
+ return ret;
+ }
+ num_peers++;
+ }
+
+ for (int i = 0; i < num_peers; i++) {
+ ret = ovpn_recv_tcp_data(ovpn->cli_sockets[i]);
+ if (ret < 0)
+ break;
+ }
+ ovpn_waitbg();
+ break;
+ case CMD_CONNECT:
+ ret = ovpn_connect(ovpn);
+ if (ret < 0) {
+ fprintf(stderr, "cannot connect TCP socket\n");
+ return ret;
+ }
+
+ ret = ovpn_new_peer(ovpn, true);
+ if (ret < 0) {
+ fprintf(stderr, "cannot add peer to VPN\n");
+ close(ovpn->socket);
+ return ret;
+ }
+
+ if (ovpn->cipher != OVPN_CIPHER_ALG_NONE) {
+ ret = ovpn_new_key(ovpn);
+ if (ret < 0) {
+ fprintf(stderr, "cannot set key\n");
+ return ret;
+ }
+ }
+
+ ret = ovpn_send_tcp_data(ovpn->socket);
+ ovpn_waitbg();
+ break;
+ case CMD_NEW_PEER:
+ ret = ovpn_udp_socket(ovpn, AF_INET6);
+ if (ret < 0)
+ return ret;
+
+ ret = ovpn_new_peer(ovpn, false);
+ ovpn_waitbg();
+ break;
+ case CMD_NEW_MULTI_PEER:
+ ret = ovpn_udp_socket(ovpn, AF_INET6);
+ if (ret < 0)
+ return ret;
+
+ fp = fopen(ovpn->peers_file, "r");
+ if (!fp) {
+ fprintf(stderr, "cannot open file: %s\n",
+ ovpn->peers_file);
+ return -1;
+ }
+
+ while ((n = fscanf(fp, "%s %s %s %s %s %s\n", peer_id, laddr,
+ lport, raddr, rport, vpnip)) == 6) {
+ struct ovpn_ctx peer_ctx = { 0 };
+
+ peer_ctx.ifindex = ovpn->ifindex;
+ peer_ctx.socket = ovpn->socket;
+ peer_ctx.sa_family = AF_UNSPEC;
+
+ ret = ovpn_parse_new_peer(&peer_ctx, peer_id, raddr,
+ rport, vpnip);
+ if (ret < 0) {
+ fprintf(stderr, "error while parsing line\n");
+ return -1;
+ }
+
+ ret = ovpn_new_peer(&peer_ctx, false);
+ if (ret < 0) {
+ fprintf(stderr,
+ "cannot add peer to VPN: %s %s %s %s\n",
+ peer_id, raddr, rport, vpnip);
+ return ret;
+ }
+ }
+ ovpn_waitbg();
+ break;
+ case CMD_SET_PEER:
+ ret = ovpn_set_peer(ovpn);
+ break;
+ case CMD_DEL_PEER:
+ ret = ovpn_del_peer(ovpn);
+ break;
+ case CMD_GET_PEER:
+ if (ovpn->peer_id == PEER_ID_UNDEF)
+ fprintf(stderr, "List of peers connected to: %s\n",
+ ovpn->ifname);
+
+ ret = ovpn_get_peer(ovpn);
+ break;
+ case CMD_NEW_KEY:
+ ret = ovpn_new_key(ovpn);
+ break;
+ case CMD_DEL_KEY:
+ ret = ovpn_del_key(ovpn);
+ break;
+ case CMD_GET_KEY:
+ ret = ovpn_get_key(ovpn);
+ break;
+ case CMD_SWAP_KEYS:
+ ret = ovpn_swap_keys(ovpn);
+ break;
+ case CMD_LISTEN_MCAST:
+ ret = ovpn_listen_mcast();
+ break;
+ case CMD_INVALID:
+ break;
+ }
+
+ return ret;
+}
+
+static int ovpn_parse_cmd_args(struct ovpn_ctx *ovpn, int argc, char *argv[])
+{
+ int ret;
+
+ /* no args required for LISTEN_MCAST */
+ if (ovpn->cmd == CMD_LISTEN_MCAST)
+ return 0;
+
+ /* all commands need an ifname */
+ if (argc < 3)
+ return -EINVAL;
+
+ strscpy(ovpn->ifname, argv[2], IFNAMSIZ - 1);
+ ovpn->ifname[IFNAMSIZ - 1] = '\0';
+
+ /* all commands, except NEW_IFNAME, needs an ifindex */
+ if (ovpn->cmd != CMD_NEW_IFACE) {
+ ovpn->ifindex = if_nametoindex(ovpn->ifname);
+ if (!ovpn->ifindex) {
+ fprintf(stderr, "cannot find interface: %s\n",
+ strerror(errno));
+ return -1;
+ }
+ }
+
+ switch (ovpn->cmd) {
+ case CMD_NEW_IFACE:
+ if (argc < 4)
+ break;
+
+ if (!strcmp(argv[3], "P2P")) {
+ ovpn->mode = OVPN_MODE_P2P;
+ } else if (!strcmp(argv[3], "MP")) {
+ ovpn->mode = OVPN_MODE_MP;
+ } else {
+ fprintf(stderr, "Cannot parse iface mode: %s\n",
+ argv[3]);
+ return -1;
+ }
+ ovpn->mode_set = true;
+ break;
+ case CMD_DEL_IFACE:
+ break;
+ case CMD_LISTEN:
+ if (argc < 5)
+ return -EINVAL;
+
+ ovpn->lport = strtoul(argv[3], NULL, 10);
+ if (errno == ERANGE || ovpn->lport > 65535) {
+ fprintf(stderr, "lport value out of range\n");
+ return -1;
+ }
+
+ ovpn->peers_file = argv[4];
+
+ if (argc > 5 && !strcmp(argv[5], "ipv6"))
+ ovpn->sa_family = AF_INET6;
+ break;
+ case CMD_CONNECT:
+ if (argc < 6)
+ return -EINVAL;
+
+ ovpn->sa_family = AF_INET;
+
+ ret = ovpn_parse_new_peer(ovpn, argv[3], argv[4], argv[5],
+ NULL);
+ if (ret < 0) {
+ fprintf(stderr, "Cannot parse remote peer data\n");
+ return -1;
+ }
+
+ if (argc > 6) {
+ ovpn->key_slot = OVPN_KEY_SLOT_PRIMARY;
+ ovpn->key_id = 0;
+ ovpn->cipher = OVPN_CIPHER_ALG_AES_GCM;
+ ovpn->key_dir = KEY_DIR_OUT;
+
+ ret = ovpn_parse_key(argv[6], ovpn);
+ if (ret)
+ return -1;
+ }
+ break;
+ case CMD_NEW_PEER:
+ if (argc < 7)
+ return -EINVAL;
+
+ ovpn->lport = strtoul(argv[4], NULL, 10);
+ if (errno == ERANGE || ovpn->lport > 65535) {
+ fprintf(stderr, "lport value out of range\n");
+ return -1;
+ }
+
+ const char *vpnip = (argc > 7) ? argv[7] : NULL;
+
+ ret = ovpn_parse_new_peer(ovpn, argv[3], argv[5], argv[6],
+ vpnip);
+ if (ret < 0)
+ return -1;
+ break;
+ case CMD_NEW_MULTI_PEER:
+ if (argc < 5)
+ return -EINVAL;
+
+ ovpn->lport = strtoul(argv[3], NULL, 10);
+ if (errno == ERANGE || ovpn->lport > 65535) {
+ fprintf(stderr, "lport value out of range\n");
+ return -1;
+ }
+
+ ovpn->peers_file = argv[4];
+ break;
+ case CMD_SET_PEER:
+ if (argc < 6)
+ return -EINVAL;
+
+ ovpn->peer_id = strtoul(argv[3], NULL, 10);
+ if (errno == ERANGE || ovpn->peer_id > PEER_ID_UNDEF) {
+ fprintf(stderr, "peer ID value out of range\n");
+ return -1;
+ }
+
+ ovpn->keepalive_interval = strtoul(argv[4], NULL, 10);
+ if (errno == ERANGE) {
+ fprintf(stderr,
+ "keepalive interval value out of range\n");
+ return -1;
+ }
+
+ ovpn->keepalive_timeout = strtoul(argv[5], NULL, 10);
+ if (errno == ERANGE) {
+ fprintf(stderr,
+ "keepalive interval value out of range\n");
+ return -1;
+ }
+ break;
+ case CMD_DEL_PEER:
+ if (argc < 4)
+ return -EINVAL;
+
+ ovpn->peer_id = strtoul(argv[3], NULL, 10);
+ if (errno == ERANGE || ovpn->peer_id > PEER_ID_UNDEF) {
+ fprintf(stderr, "peer ID value out of range\n");
+ return -1;
+ }
+ break;
+ case CMD_GET_PEER:
+ ovpn->peer_id = PEER_ID_UNDEF;
+ if (argc > 3) {
+ ovpn->peer_id = strtoul(argv[3], NULL, 10);
+ if (errno == ERANGE || ovpn->peer_id > PEER_ID_UNDEF) {
+ fprintf(stderr, "peer ID value out of range\n");
+ return -1;
+ }
+ }
+ break;
+ case CMD_NEW_KEY:
+ if (argc < 9)
+ return -EINVAL;
+
+ ovpn->peer_id = strtoul(argv[3], NULL, 10);
+ if (errno == ERANGE) {
+ fprintf(stderr, "peer ID value out of range\n");
+ return -1;
+ }
+
+ ret = ovpn_parse_key_slot(argv[4], ovpn);
+ if (ret)
+ return -1;
+
+ ovpn->key_id = strtoul(argv[5], NULL, 10);
+ if (errno == ERANGE || ovpn->key_id > 2) {
+ fprintf(stderr, "key ID out of range\n");
+ return -1;
+ }
+
+ ret = ovpn_parse_cipher(argv[6], ovpn);
+ if (ret < 0)
+ return -1;
+
+ ret = ovpn_parse_key_direction(argv[7], ovpn);
+ if (ret < 0)
+ return -1;
+
+ ret = ovpn_parse_key(argv[8], ovpn);
+ if (ret)
+ return -1;
+ break;
+ case CMD_DEL_KEY:
+ if (argc < 4)
+ return -EINVAL;
+
+ ovpn->peer_id = strtoul(argv[3], NULL, 10);
+ if (errno == ERANGE) {
+ fprintf(stderr, "peer ID value out of range\n");
+ return -1;
+ }
+
+ ret = ovpn_parse_key_slot(argv[4], ovpn);
+ if (ret)
+ return ret;
+ break;
+ case CMD_GET_KEY:
+ if (argc < 5)
+ return -EINVAL;
+
+ ovpn->peer_id = strtoul(argv[3], NULL, 10);
+ if (errno == ERANGE) {
+ fprintf(stderr, "peer ID value out of range\n");
+ return -1;
+ }
+
+ ret = ovpn_parse_key_slot(argv[4], ovpn);
+ if (ret)
+ return ret;
+ break;
+ case CMD_SWAP_KEYS:
+ if (argc < 4)
+ return -EINVAL;
+
+ ovpn->peer_id = strtoul(argv[3], NULL, 10);
+ if (errno == ERANGE) {
+ fprintf(stderr, "peer ID value out of range\n");
+ return -1;
+ }
+ break;
+ case CMD_LISTEN_MCAST:
+ break;
+ case CMD_INVALID:
+ break;
+ }
+
+ return 0;
+}
+
+int main(int argc, char *argv[])
+{
+ struct ovpn_ctx ovpn;
+ int ret;
+
+ if (argc < 2) {
+ usage(argv[0]);
+ return -1;
+ }
+
+ memset(&ovpn, 0, sizeof(ovpn));
+ ovpn.sa_family = AF_UNSPEC;
+ ovpn.cipher = OVPN_CIPHER_ALG_NONE;
+
+ ovpn.cmd = ovpn_parse_cmd(argv[1]);
+ if (ovpn.cmd == CMD_INVALID) {
+ fprintf(stderr, "Error: unknown command.\n\n");
+ usage(argv[0]);
+ return -1;
+ }
+
+ ret = ovpn_parse_cmd_args(&ovpn, argc, argv);
+ if (ret < 0) {
+ fprintf(stderr, "Error: invalid arguments.\n\n");
+ if (ret == -EINVAL)
+ usage(argv[0]);
+ return ret;
+ }
+
+ ret = ovpn_run_cmd(&ovpn);
+ if (ret)
+ fprintf(stderr, "Cannot execute command: %s (%d)\n",
+ strerror(-ret), ret);
+
+ return ret;
+}
diff --git a/tools/testing/selftests/net/ovpn/tcp_peers.txt b/tools/testing/selftests/net/ovpn/tcp_peers.txt
new file mode 100644
index 000000000000..d753eebe8716
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/tcp_peers.txt
@@ -0,0 +1,5 @@
+1 5.5.5.2
+2 5.5.5.3
+3 5.5.5.4
+4 5.5.5.5
+5 5.5.5.6
diff --git a/tools/testing/selftests/net/ovpn/test-chachapoly.sh b/tools/testing/selftests/net/ovpn/test-chachapoly.sh
new file mode 100755
index 000000000000..32504079a2b8
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test-chachapoly.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2025 OpenVPN, Inc.
+#
+# Author: Antonio Quartulli <antonio@openvpn.net>
+
+ALG="chachapoly"
+
+source test.sh
diff --git a/tools/testing/selftests/net/ovpn/test-close-socket-tcp.sh b/tools/testing/selftests/net/ovpn/test-close-socket-tcp.sh
new file mode 100755
index 000000000000..093d44772ffd
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test-close-socket-tcp.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2025 OpenVPN, Inc.
+#
+# Author: Antonio Quartulli <antonio@openvpn.net>
+
+PROTO="TCP"
+
+source test-close-socket.sh
diff --git a/tools/testing/selftests/net/ovpn/test-close-socket.sh b/tools/testing/selftests/net/ovpn/test-close-socket.sh
new file mode 100755
index 000000000000..5e48a8b67928
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test-close-socket.sh
@@ -0,0 +1,45 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2020-2025 OpenVPN, Inc.
+#
+# Author: Antonio Quartulli <antonio@openvpn.net>
+
+#set -x
+set -e
+
+source ./common.sh
+
+cleanup
+
+modprobe -q ovpn || true
+
+for p in $(seq 0 ${NUM_PEERS}); do
+ create_ns ${p}
+done
+
+for p in $(seq 0 ${NUM_PEERS}); do
+ setup_ns ${p} 5.5.5.$((${p} + 1))/24
+done
+
+for p in $(seq 0 ${NUM_PEERS}); do
+ add_peer ${p}
+done
+
+for p in $(seq 1 ${NUM_PEERS}); do
+ ip netns exec peer0 ${OVPN_CLI} set_peer tun0 ${p} 60 120
+ ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} ${p} 60 120
+done
+
+sleep 1
+
+for p in $(seq 1 ${NUM_PEERS}); do
+ ip netns exec peer0 ping -qfc 500 -w 3 5.5.5.$((${p} + 1))
+done
+
+ip netns exec peer0 iperf3 -1 -s &
+sleep 1
+ip netns exec peer1 iperf3 -Z -t 3 -c 5.5.5.1
+
+cleanup
+
+modprobe -r ovpn || true
diff --git a/tools/testing/selftests/net/ovpn/test-float.sh b/tools/testing/selftests/net/ovpn/test-float.sh
new file mode 100755
index 000000000000..ba5d725e18b0
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test-float.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2025 OpenVPN, Inc.
+#
+# Author: Antonio Quartulli <antonio@openvpn.net>
+
+FLOAT="1"
+
+source test.sh
diff --git a/tools/testing/selftests/net/ovpn/test-tcp.sh b/tools/testing/selftests/net/ovpn/test-tcp.sh
new file mode 100755
index 000000000000..ba3f1f315a34
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test-tcp.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2025 OpenVPN, Inc.
+#
+# Author: Antonio Quartulli <antonio@openvpn.net>
+
+PROTO="TCP"
+
+source test.sh
diff --git a/tools/testing/selftests/net/ovpn/test.sh b/tools/testing/selftests/net/ovpn/test.sh
new file mode 100755
index 000000000000..e8acdc303307
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test.sh
@@ -0,0 +1,117 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2020-2025 OpenVPN, Inc.
+#
+# Author: Antonio Quartulli <antonio@openvpn.net>
+
+#set -x
+set -e
+
+source ./common.sh
+
+cleanup
+
+modprobe -q ovpn || true
+
+for p in $(seq 0 ${NUM_PEERS}); do
+ create_ns ${p}
+done
+
+for p in $(seq 0 ${NUM_PEERS}); do
+ setup_ns ${p} 5.5.5.$((${p} + 1))/24 ${MTU}
+done
+
+for p in $(seq 0 ${NUM_PEERS}); do
+ add_peer ${p}
+done
+
+for p in $(seq 1 ${NUM_PEERS}); do
+ ip netns exec peer0 ${OVPN_CLI} set_peer tun0 ${p} 60 120
+ ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} ${p} 60 120
+done
+
+sleep 1
+
+for p in $(seq 1 ${NUM_PEERS}); do
+ ip netns exec peer0 ping -qfc 500 -w 3 5.5.5.$((${p} + 1))
+ ip netns exec peer0 ping -qfc 500 -s 3000 -w 3 5.5.5.$((${p} + 1))
+done
+
+# ping LAN behind client 1
+ip netns exec peer0 ping -qfc 500 -w 3 ${LAN_IP}
+
+if [ "$FLOAT" == "1" ]; then
+ # make clients float..
+ for p in $(seq 1 ${NUM_PEERS}); do
+ ip -n peer${p} addr del 10.10.${p}.2/24 dev veth${p}
+ ip -n peer${p} addr add 10.10.${p}.3/24 dev veth${p}
+ done
+ for p in $(seq 1 ${NUM_PEERS}); do
+ ip netns exec peer${p} ping -qfc 500 -w 3 5.5.5.1
+ done
+fi
+
+ip netns exec peer0 iperf3 -1 -s &
+sleep 1
+ip netns exec peer1 iperf3 -Z -t 3 -c 5.5.5.1
+
+echo "Adding secondary key and then swap:"
+for p in $(seq 1 ${NUM_PEERS}); do
+ ip netns exec peer0 ${OVPN_CLI} new_key tun0 ${p} 2 1 ${ALG} 0 data64.key
+ ip netns exec peer${p} ${OVPN_CLI} new_key tun${p} ${p} 2 1 ${ALG} 1 data64.key
+ ip netns exec peer${p} ${OVPN_CLI} swap_keys tun${p} ${p}
+done
+
+sleep 1
+
+echo "Querying all peers:"
+ip netns exec peer0 ${OVPN_CLI} get_peer tun0
+ip netns exec peer1 ${OVPN_CLI} get_peer tun1
+
+echo "Querying peer 1:"
+ip netns exec peer0 ${OVPN_CLI} get_peer tun0 1
+
+echo "Querying non-existent peer 10:"
+ip netns exec peer0 ${OVPN_CLI} get_peer tun0 10 || true
+
+echo "Deleting peer 1:"
+ip netns exec peer0 ${OVPN_CLI} del_peer tun0 1
+ip netns exec peer1 ${OVPN_CLI} del_peer tun1 1
+
+echo "Querying keys:"
+for p in $(seq 2 ${NUM_PEERS}); do
+ ip netns exec peer${p} ${OVPN_CLI} get_key tun${p} ${p} 1
+ ip netns exec peer${p} ${OVPN_CLI} get_key tun${p} ${p} 2
+done
+
+echo "Deleting peer while sending traffic:"
+(ip netns exec peer2 ping -qf -w 4 5.5.5.1)&
+sleep 2
+ip netns exec peer0 ${OVPN_CLI} del_peer tun0 2
+# following command fails in TCP mode
+# (both ends get conn reset when one peer disconnects)
+ip netns exec peer2 ${OVPN_CLI} del_peer tun2 2 || true
+
+echo "Deleting keys:"
+for p in $(seq 3 ${NUM_PEERS}); do
+ ip netns exec peer${p} ${OVPN_CLI} del_key tun${p} ${p} 1
+ ip netns exec peer${p} ${OVPN_CLI} del_key tun${p} ${p} 2
+done
+
+echo "Setting timeout to 3s MP:"
+for p in $(seq 3 ${NUM_PEERS}); do
+ ip netns exec peer0 ${OVPN_CLI} set_peer tun0 ${p} 3 3 || true
+ ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} ${p} 0 0
+done
+# wait for peers to timeout
+sleep 5
+
+echo "Setting timeout to 3s P2P:"
+for p in $(seq 3 ${NUM_PEERS}); do
+ ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} ${p} 3 3
+done
+sleep 5
+
+cleanup
+
+modprobe -r ovpn || true
diff --git a/tools/testing/selftests/net/ovpn/udp_peers.txt b/tools/testing/selftests/net/ovpn/udp_peers.txt
new file mode 100644
index 000000000000..e9773ddf875c
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/udp_peers.txt
@@ -0,0 +1,6 @@
+1 10.10.1.1 1 10.10.1.2 1 5.5.5.2
+2 10.10.2.1 1 10.10.2.2 1 5.5.5.3
+3 10.10.3.1 1 10.10.3.2 1 5.5.5.4
+4 fd00:0:0:4::1 1 fd00:0:0:4::2 1 5.5.5.5
+5 fd00:0:0:5::1 1 fd00:0:0:5::2 1 5.5.5.6
+6 fd00:0:0:6::1 1 fd00:0:0:6::2 1 5.5.5.7
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 66be7699c72c..88e914c4eef9 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -205,7 +205,6 @@
# Check that PMTU exceptions are created for both paths.
source lib.sh
-source net_helper.sh
PAUSE_ON_FAIL=no
VERBOSE=0
diff --git a/tools/testing/selftests/net/proc_net_pktgen.c b/tools/testing/selftests/net/proc_net_pktgen.c
new file mode 100644
index 000000000000..69444fb29577
--- /dev/null
+++ b/tools/testing/selftests/net/proc_net_pktgen.c
@@ -0,0 +1,690 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * proc_net_pktgen: kselftest for /proc/net/pktgen interface
+ *
+ * Copyright (c) 2025 Peter Seiderer <ps.report@gmx.net>
+ *
+ */
+#include <errno.h>
+#include <fcntl.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include "../kselftest_harness.h"
+
+static const char ctrl_cmd_stop[] = "stop";
+static const char ctrl_cmd_start[] = "start";
+static const char ctrl_cmd_reset[] = "reset";
+
+static const char wrong_ctrl_cmd[] = "0123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789";
+
+static const char thr_cmd_add_loopback_0[] = "add_device lo@0";
+static const char thr_cmd_rm_loopback_0[] = "rem_device_all";
+
+static const char wrong_thr_cmd[] = "forsureawrongcommand";
+static const char legacy_thr_cmd[] = "max_before_softirq";
+
+static const char wrong_dev_cmd[] = "forsurewrongcommand";
+static const char dev_cmd_min_pkt_size_0[] = "min_pkt_size";
+static const char dev_cmd_min_pkt_size_1[] = "min_pkt_size ";
+static const char dev_cmd_min_pkt_size_2[] = "min_pkt_size 0";
+static const char dev_cmd_min_pkt_size_3[] = "min_pkt_size 1";
+static const char dev_cmd_min_pkt_size_4[] = "min_pkt_size 100";
+static const char dev_cmd_min_pkt_size_5[] = "min_pkt_size=1001";
+static const char dev_cmd_min_pkt_size_6[] = "min_pkt_size =2002";
+static const char dev_cmd_min_pkt_size_7[] = "min_pkt_size= 3003";
+static const char dev_cmd_min_pkt_size_8[] = "min_pkt_size = 4004";
+static const char dev_cmd_max_pkt_size_0[] = "max_pkt_size 200";
+static const char dev_cmd_pkt_size_0[] = "pkt_size 300";
+static const char dev_cmd_imix_weights_0[] = "imix_weights 0,7 576,4 1500,1";
+static const char dev_cmd_imix_weights_1[] = "imix_weights 101,1 102,2 103,3 104,4 105,5 106,6 107,7 108,8 109,9 110,10 111,11 112,12 113,13 114,14 115,15 116,16 117,17 118,18 119,19 120,20";
+static const char dev_cmd_imix_weights_2[] = "imix_weights 100,1 102,2 103,3 104,4 105,5 106,6 107,7 108,8 109,9 110,10 111,11 112,12 113,13 114,14 115,15 116,16 117,17 118,18 119,19 120,20 121,21";
+static const char dev_cmd_imix_weights_3[] = "imix_weights";
+static const char dev_cmd_imix_weights_4[] = "imix_weights ";
+static const char dev_cmd_imix_weights_5[] = "imix_weights 0";
+static const char dev_cmd_imix_weights_6[] = "imix_weights 0,";
+static const char dev_cmd_debug_0[] = "debug 1";
+static const char dev_cmd_debug_1[] = "debug 0";
+static const char dev_cmd_frags_0[] = "frags 100";
+static const char dev_cmd_delay_0[] = "delay 100";
+static const char dev_cmd_delay_1[] = "delay 2147483647";
+static const char dev_cmd_rate_0[] = "rate 0";
+static const char dev_cmd_rate_1[] = "rate 100";
+static const char dev_cmd_ratep_0[] = "ratep 0";
+static const char dev_cmd_ratep_1[] = "ratep 200";
+static const char dev_cmd_udp_src_min_0[] = "udp_src_min 1";
+static const char dev_cmd_udp_dst_min_0[] = "udp_dst_min 2";
+static const char dev_cmd_udp_src_max_0[] = "udp_src_max 3";
+static const char dev_cmd_udp_dst_max_0[] = "udp_dst_max 4";
+static const char dev_cmd_clone_skb_0[] = "clone_skb 1";
+static const char dev_cmd_clone_skb_1[] = "clone_skb 0";
+static const char dev_cmd_count_0[] = "count 100";
+static const char dev_cmd_src_mac_count_0[] = "src_mac_count 100";
+static const char dev_cmd_dst_mac_count_0[] = "dst_mac_count 100";
+static const char dev_cmd_burst_0[] = "burst 0";
+static const char dev_cmd_node_0[] = "node 100";
+static const char dev_cmd_xmit_mode_0[] = "xmit_mode start_xmit";
+static const char dev_cmd_xmit_mode_1[] = "xmit_mode netif_receive";
+static const char dev_cmd_xmit_mode_2[] = "xmit_mode queue_xmit";
+static const char dev_cmd_xmit_mode_3[] = "xmit_mode nonsense";
+static const char dev_cmd_flag_0[] = "flag UDPCSUM";
+static const char dev_cmd_flag_1[] = "flag !UDPCSUM";
+static const char dev_cmd_flag_2[] = "flag nonsense";
+static const char dev_cmd_dst_min_0[] = "dst_min 101.102.103.104";
+static const char dev_cmd_dst_0[] = "dst 101.102.103.104";
+static const char dev_cmd_dst_max_0[] = "dst_max 201.202.203.204";
+static const char dev_cmd_dst6_0[] = "dst6 2001:db38:1234:0000:0000:0000:0000:0000";
+static const char dev_cmd_dst6_min_0[] = "dst6_min 2001:db8:1234:0000:0000:0000:0000:0000";
+static const char dev_cmd_dst6_max_0[] = "dst6_max 2001:db8:1234:0000:0000:0000:0000:0000";
+static const char dev_cmd_src6_0[] = "src6 2001:db38:1234:0000:0000:0000:0000:0000";
+static const char dev_cmd_src_min_0[] = "src_min 101.102.103.104";
+static const char dev_cmd_src_max_0[] = "src_max 201.202.203.204";
+static const char dev_cmd_dst_mac_0[] = "dst_mac 01:02:03:04:05:06";
+static const char dev_cmd_src_mac_0[] = "src_mac 11:12:13:14:15:16";
+static const char dev_cmd_clear_counters_0[] = "clear_counters";
+static const char dev_cmd_flows_0[] = "flows 100";
+static const char dev_cmd_spi_0[] = "spi 100";
+static const char dev_cmd_flowlen_0[] = "flowlen 100";
+static const char dev_cmd_queue_map_min_0[] = "queue_map_min 1";
+static const char dev_cmd_queue_map_max_0[] = "queue_map_max 2";
+static const char dev_cmd_mpls_0[] = "mpls 00000001";
+static const char dev_cmd_mpls_1[] = "mpls 00000001,000000f2";
+static const char dev_cmd_mpls_2[] = "mpls 00000f00,00000f01,00000f02,00000f03,00000f04,00000f05,00000f06,00000f07,00000f08,00000f09,00000f0a,00000f0b,00000f0c,00000f0d,00000f0e,00000f0f";
+static const char dev_cmd_mpls_3[] = "mpls 00000f00,00000f01,00000f02,00000f03,00000f04,00000f05,00000f06,00000f07,00000f08,00000f09,00000f0a,00000f0b,00000f0c,00000f0d,00000f0e,00000f0f,00000f10";
+static const char dev_cmd_vlan_id_0[] = "vlan_id 1";
+static const char dev_cmd_vlan_p_0[] = "vlan_p 1";
+static const char dev_cmd_vlan_cfi_0[] = "vlan_cfi 1";
+static const char dev_cmd_vlan_id_1[] = "vlan_id 4096";
+static const char dev_cmd_svlan_id_0[] = "svlan_id 1";
+static const char dev_cmd_svlan_p_0[] = "svlan_p 1";
+static const char dev_cmd_svlan_cfi_0[] = "svlan_cfi 1";
+static const char dev_cmd_svlan_id_1[] = "svlan_id 4096";
+static const char dev_cmd_tos_0[] = "tos 0";
+static const char dev_cmd_tos_1[] = "tos 0f";
+static const char dev_cmd_tos_2[] = "tos 0ff";
+static const char dev_cmd_traffic_class_0[] = "traffic_class f0";
+static const char dev_cmd_skb_priority_0[] = "skb_priority 999";
+
+FIXTURE(proc_net_pktgen) {
+ int ctrl_fd;
+ int thr_fd;
+ int dev_fd;
+};
+
+FIXTURE_SETUP(proc_net_pktgen) {
+ int r;
+ ssize_t len;
+
+ r = system("modprobe pktgen");
+ ASSERT_EQ(r, 0) TH_LOG("CONFIG_NET_PKTGEN not enabled, module pktgen not loaded?");
+
+ self->ctrl_fd = open("/proc/net/pktgen/pgctrl", O_RDWR);
+ ASSERT_GE(self->ctrl_fd, 0) TH_LOG("CONFIG_NET_PKTGEN not enabled, module pktgen not loaded?");
+
+ self->thr_fd = open("/proc/net/pktgen/kpktgend_0", O_RDWR);
+ ASSERT_GE(self->thr_fd, 0) TH_LOG("CONFIG_NET_PKTGEN not enabled, module pktgen not loaded?");
+
+ len = write(self->thr_fd, thr_cmd_add_loopback_0, sizeof(thr_cmd_add_loopback_0));
+ ASSERT_EQ(len, sizeof(thr_cmd_add_loopback_0)) TH_LOG("device lo@0 already registered?");
+
+ self->dev_fd = open("/proc/net/pktgen/lo@0", O_RDWR);
+ ASSERT_GE(self->dev_fd, 0) TH_LOG("device entry for lo@0 missing?");
+}
+
+FIXTURE_TEARDOWN(proc_net_pktgen) {
+ int ret;
+ ssize_t len;
+
+ ret = close(self->dev_fd);
+ EXPECT_EQ(ret, 0);
+
+ len = write(self->thr_fd, thr_cmd_rm_loopback_0, sizeof(thr_cmd_rm_loopback_0));
+ EXPECT_EQ(len, sizeof(thr_cmd_rm_loopback_0));
+
+ ret = close(self->thr_fd);
+ EXPECT_EQ(ret, 0);
+
+ ret = close(self->ctrl_fd);
+ EXPECT_EQ(ret, 0);
+}
+
+TEST_F(proc_net_pktgen, wrong_ctrl_cmd) {
+ for (int i = 0; i <= sizeof(wrong_ctrl_cmd); i++) {
+ ssize_t len;
+
+ len = write(self->ctrl_fd, wrong_ctrl_cmd, i);
+ EXPECT_EQ(len, -1);
+ EXPECT_EQ(errno, EINVAL);
+ }
+}
+
+TEST_F(proc_net_pktgen, ctrl_cmd) {
+ ssize_t len;
+
+ len = write(self->ctrl_fd, ctrl_cmd_stop, sizeof(ctrl_cmd_stop));
+ EXPECT_EQ(len, sizeof(ctrl_cmd_stop));
+
+ len = write(self->ctrl_fd, ctrl_cmd_stop, sizeof(ctrl_cmd_stop) - 1);
+ EXPECT_EQ(len, sizeof(ctrl_cmd_stop) - 1);
+
+ len = write(self->ctrl_fd, ctrl_cmd_start, sizeof(ctrl_cmd_start));
+ EXPECT_EQ(len, sizeof(ctrl_cmd_start));
+
+ len = write(self->ctrl_fd, ctrl_cmd_start, sizeof(ctrl_cmd_start) - 1);
+ EXPECT_EQ(len, sizeof(ctrl_cmd_start) - 1);
+
+ len = write(self->ctrl_fd, ctrl_cmd_reset, sizeof(ctrl_cmd_reset));
+ EXPECT_EQ(len, sizeof(ctrl_cmd_reset));
+
+ len = write(self->ctrl_fd, ctrl_cmd_reset, sizeof(ctrl_cmd_reset) - 1);
+ EXPECT_EQ(len, sizeof(ctrl_cmd_reset) - 1);
+}
+
+TEST_F(proc_net_pktgen, wrong_thr_cmd) {
+ for (int i = 0; i <= sizeof(wrong_thr_cmd); i++) {
+ ssize_t len;
+
+ len = write(self->thr_fd, wrong_thr_cmd, i);
+ EXPECT_EQ(len, -1);
+ EXPECT_EQ(errno, EINVAL);
+ }
+}
+
+TEST_F(proc_net_pktgen, legacy_thr_cmd) {
+ for (int i = 0; i <= sizeof(legacy_thr_cmd); i++) {
+ ssize_t len;
+
+ len = write(self->thr_fd, legacy_thr_cmd, i);
+ if (i < (sizeof(legacy_thr_cmd) - 1)) {
+ /* incomplete command string */
+ EXPECT_EQ(len, -1);
+ EXPECT_EQ(errno, EINVAL);
+ } else {
+ /* complete command string without/with trailing '\0' */
+ EXPECT_EQ(len, i);
+ }
+ }
+}
+
+TEST_F(proc_net_pktgen, wrong_dev_cmd) {
+ for (int i = 0; i <= sizeof(wrong_dev_cmd); i++) {
+ ssize_t len;
+
+ len = write(self->dev_fd, wrong_dev_cmd, i);
+ EXPECT_EQ(len, -1);
+ EXPECT_EQ(errno, EINVAL);
+ }
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_min_pkt_size) {
+ ssize_t len;
+
+ /* with trailing '\0' */
+ len = write(self->dev_fd, dev_cmd_min_pkt_size_0, sizeof(dev_cmd_min_pkt_size_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_0));
+
+ /* without trailing '\0' */
+ len = write(self->dev_fd, dev_cmd_min_pkt_size_0, sizeof(dev_cmd_min_pkt_size_0) - 1);
+ EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_0) - 1);
+
+ /* with trailing '\0' */
+ len = write(self->dev_fd, dev_cmd_min_pkt_size_1, sizeof(dev_cmd_min_pkt_size_1));
+ EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_1));
+
+ /* without trailing '\0' */
+ len = write(self->dev_fd, dev_cmd_min_pkt_size_1, sizeof(dev_cmd_min_pkt_size_1) - 1);
+ EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_1) - 1);
+
+ /* with trailing '\0' */
+ len = write(self->dev_fd, dev_cmd_min_pkt_size_2, sizeof(dev_cmd_min_pkt_size_2));
+ EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_2));
+
+ /* without trailing '\0' */
+ len = write(self->dev_fd, dev_cmd_min_pkt_size_2, sizeof(dev_cmd_min_pkt_size_2) - 1);
+ EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_2) - 1);
+
+ len = write(self->dev_fd, dev_cmd_min_pkt_size_3, sizeof(dev_cmd_min_pkt_size_3));
+ EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_3));
+
+ len = write(self->dev_fd, dev_cmd_min_pkt_size_4, sizeof(dev_cmd_min_pkt_size_4));
+ EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_4));
+
+ len = write(self->dev_fd, dev_cmd_min_pkt_size_5, sizeof(dev_cmd_min_pkt_size_5));
+ EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_5));
+
+ len = write(self->dev_fd, dev_cmd_min_pkt_size_6, sizeof(dev_cmd_min_pkt_size_6));
+ EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_6));
+
+ len = write(self->dev_fd, dev_cmd_min_pkt_size_7, sizeof(dev_cmd_min_pkt_size_7));
+ EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_7));
+
+ len = write(self->dev_fd, dev_cmd_min_pkt_size_8, sizeof(dev_cmd_min_pkt_size_8));
+ EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_8));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_max_pkt_size) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_max_pkt_size_0, sizeof(dev_cmd_max_pkt_size_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_max_pkt_size_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_pkt_size) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_pkt_size_0, sizeof(dev_cmd_pkt_size_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_pkt_size_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_imix_weights) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_imix_weights_0, sizeof(dev_cmd_imix_weights_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_imix_weights_0));
+
+ len = write(self->dev_fd, dev_cmd_imix_weights_1, sizeof(dev_cmd_imix_weights_1));
+ EXPECT_EQ(len, sizeof(dev_cmd_imix_weights_1));
+
+ len = write(self->dev_fd, dev_cmd_imix_weights_2, sizeof(dev_cmd_imix_weights_2));
+ EXPECT_EQ(len, -1);
+ EXPECT_EQ(errno, E2BIG);
+
+ /* with trailing '\0' */
+ len = write(self->dev_fd, dev_cmd_imix_weights_3, sizeof(dev_cmd_imix_weights_3));
+ EXPECT_EQ(len, -1);
+ EXPECT_EQ(errno, EINVAL);
+
+ /* without trailing '\0' */
+ len = write(self->dev_fd, dev_cmd_imix_weights_3, sizeof(dev_cmd_imix_weights_3) - 1);
+ EXPECT_EQ(len, -1);
+ EXPECT_EQ(errno, EINVAL);
+
+ /* with trailing '\0' */
+ len = write(self->dev_fd, dev_cmd_imix_weights_4, sizeof(dev_cmd_imix_weights_4));
+ EXPECT_EQ(len, -1);
+ EXPECT_EQ(errno, EINVAL);
+
+ /* without trailing '\0' */
+ len = write(self->dev_fd, dev_cmd_imix_weights_4, sizeof(dev_cmd_imix_weights_4) - 1);
+ EXPECT_EQ(len, -1);
+ EXPECT_EQ(errno, EINVAL);
+
+ /* with trailing '\0' */
+ len = write(self->dev_fd, dev_cmd_imix_weights_5, sizeof(dev_cmd_imix_weights_5));
+ EXPECT_EQ(len, -1);
+ EXPECT_EQ(errno, EINVAL);
+
+ /* without trailing '\0' */
+ len = write(self->dev_fd, dev_cmd_imix_weights_5, sizeof(dev_cmd_imix_weights_5) - 1);
+ EXPECT_EQ(len, -1);
+ EXPECT_EQ(errno, EINVAL);
+
+ /* with trailing '\0' */
+ len = write(self->dev_fd, dev_cmd_imix_weights_6, sizeof(dev_cmd_imix_weights_6));
+ EXPECT_EQ(len, -1);
+ EXPECT_EQ(errno, EINVAL);
+
+ /* without trailing '\0' */
+ len = write(self->dev_fd, dev_cmd_imix_weights_6, sizeof(dev_cmd_imix_weights_6) - 1);
+ EXPECT_EQ(len, -1);
+ EXPECT_EQ(errno, EINVAL);
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_debug) {
+ ssize_t len;
+
+ /* debug on */
+ len = write(self->dev_fd, dev_cmd_debug_0, sizeof(dev_cmd_debug_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_debug_0));
+
+ /* debug off */
+ len = write(self->dev_fd, dev_cmd_debug_1, sizeof(dev_cmd_debug_1));
+ EXPECT_EQ(len, sizeof(dev_cmd_debug_1));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_frags) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_frags_0, sizeof(dev_cmd_frags_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_frags_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_delay) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_delay_0, sizeof(dev_cmd_delay_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_delay_0));
+
+ len = write(self->dev_fd, dev_cmd_delay_1, sizeof(dev_cmd_delay_1));
+ EXPECT_EQ(len, sizeof(dev_cmd_delay_1));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_rate) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_rate_0, sizeof(dev_cmd_rate_0));
+ EXPECT_EQ(len, -1);
+ EXPECT_EQ(errno, EINVAL);
+
+ len = write(self->dev_fd, dev_cmd_rate_1, sizeof(dev_cmd_rate_1));
+ EXPECT_EQ(len, sizeof(dev_cmd_rate_1));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_ratep) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_ratep_0, sizeof(dev_cmd_ratep_0));
+ EXPECT_EQ(len, -1);
+ EXPECT_EQ(errno, EINVAL);
+
+ len = write(self->dev_fd, dev_cmd_ratep_1, sizeof(dev_cmd_ratep_1));
+ EXPECT_EQ(len, sizeof(dev_cmd_ratep_1));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_udp_src_min) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_udp_src_min_0, sizeof(dev_cmd_udp_src_min_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_udp_src_min_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_udp_dst_min) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_udp_dst_min_0, sizeof(dev_cmd_udp_dst_min_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_udp_dst_min_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_udp_src_max) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_udp_src_max_0, sizeof(dev_cmd_udp_src_max_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_udp_src_max_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_udp_dst_max) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_udp_dst_max_0, sizeof(dev_cmd_udp_dst_max_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_udp_dst_max_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_clone_skb) {
+ ssize_t len;
+
+ /* clone_skb on (gives EOPNOTSUPP on lo device) */
+ len = write(self->dev_fd, dev_cmd_clone_skb_0, sizeof(dev_cmd_clone_skb_0));
+ EXPECT_EQ(len, -1);
+ EXPECT_EQ(errno, EOPNOTSUPP);
+
+ /* clone_skb off */
+ len = write(self->dev_fd, dev_cmd_clone_skb_1, sizeof(dev_cmd_clone_skb_1));
+ EXPECT_EQ(len, sizeof(dev_cmd_clone_skb_1));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_count) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_count_0, sizeof(dev_cmd_count_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_count_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_src_mac_count) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_src_mac_count_0, sizeof(dev_cmd_src_mac_count_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_src_mac_count_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_dst_mac_count) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_dst_mac_count_0, sizeof(dev_cmd_dst_mac_count_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_dst_mac_count_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_burst) {
+ ssize_t len;
+
+ /* burst off */
+ len = write(self->dev_fd, dev_cmd_burst_0, sizeof(dev_cmd_burst_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_burst_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_node) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_node_0, sizeof(dev_cmd_node_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_node_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_xmit_mode) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_xmit_mode_0, sizeof(dev_cmd_xmit_mode_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_xmit_mode_0));
+
+ len = write(self->dev_fd, dev_cmd_xmit_mode_1, sizeof(dev_cmd_xmit_mode_1));
+ EXPECT_EQ(len, sizeof(dev_cmd_xmit_mode_1));
+
+ len = write(self->dev_fd, dev_cmd_xmit_mode_2, sizeof(dev_cmd_xmit_mode_2));
+ EXPECT_EQ(len, sizeof(dev_cmd_xmit_mode_2));
+
+ len = write(self->dev_fd, dev_cmd_xmit_mode_3, sizeof(dev_cmd_xmit_mode_3));
+ EXPECT_EQ(len, sizeof(dev_cmd_xmit_mode_3));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_flag) {
+ ssize_t len;
+
+ /* flag UDPCSUM on */
+ len = write(self->dev_fd, dev_cmd_flag_0, sizeof(dev_cmd_flag_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_flag_0));
+
+ /* flag UDPCSUM off */
+ len = write(self->dev_fd, dev_cmd_flag_1, sizeof(dev_cmd_flag_1));
+ EXPECT_EQ(len, sizeof(dev_cmd_flag_1));
+
+ /* flag invalid */
+ len = write(self->dev_fd, dev_cmd_flag_2, sizeof(dev_cmd_flag_2));
+ EXPECT_EQ(len, sizeof(dev_cmd_flag_2));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_dst_min) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_dst_min_0, sizeof(dev_cmd_dst_min_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_dst_min_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_dst) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_dst_0, sizeof(dev_cmd_dst_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_dst_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_dst_max) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_dst_max_0, sizeof(dev_cmd_dst_max_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_dst_max_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_dst6) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_dst6_0, sizeof(dev_cmd_dst6_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_dst6_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_dst6_min) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_dst6_min_0, sizeof(dev_cmd_dst6_min_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_dst6_min_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_dst6_max) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_dst6_max_0, sizeof(dev_cmd_dst6_max_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_dst6_max_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_src6) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_src6_0, sizeof(dev_cmd_src6_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_src6_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_src_min) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_src_min_0, sizeof(dev_cmd_src_min_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_src_min_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_src_max) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_src_max_0, sizeof(dev_cmd_src_max_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_src_max_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_dst_mac) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_dst_mac_0, sizeof(dev_cmd_dst_mac_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_dst_mac_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_src_mac) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_src_mac_0, sizeof(dev_cmd_src_mac_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_src_mac_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_clear_counters) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_clear_counters_0, sizeof(dev_cmd_clear_counters_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_clear_counters_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_flows) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_flows_0, sizeof(dev_cmd_flows_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_flows_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_spi) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_spi_0, sizeof(dev_cmd_spi_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_spi_0)) TH_LOG("CONFIG_XFRM not enabled?");
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_flowlen) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_flowlen_0, sizeof(dev_cmd_flowlen_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_flowlen_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_queue_map_min) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_queue_map_min_0, sizeof(dev_cmd_queue_map_min_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_queue_map_min_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_queue_map_max) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_queue_map_max_0, sizeof(dev_cmd_queue_map_max_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_queue_map_max_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_mpls) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_mpls_0, sizeof(dev_cmd_mpls_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_mpls_0));
+
+ len = write(self->dev_fd, dev_cmd_mpls_1, sizeof(dev_cmd_mpls_1));
+ EXPECT_EQ(len, sizeof(dev_cmd_mpls_1));
+
+ len = write(self->dev_fd, dev_cmd_mpls_2, sizeof(dev_cmd_mpls_2));
+ EXPECT_EQ(len, sizeof(dev_cmd_mpls_2));
+
+ len = write(self->dev_fd, dev_cmd_mpls_3, sizeof(dev_cmd_mpls_3));
+ EXPECT_EQ(len, -1);
+ EXPECT_EQ(errno, E2BIG);
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_vlan_id) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_vlan_id_0, sizeof(dev_cmd_vlan_id_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_vlan_id_0));
+
+ len = write(self->dev_fd, dev_cmd_vlan_p_0, sizeof(dev_cmd_vlan_p_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_vlan_p_0));
+
+ len = write(self->dev_fd, dev_cmd_vlan_cfi_0, sizeof(dev_cmd_vlan_cfi_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_vlan_cfi_0));
+
+ len = write(self->dev_fd, dev_cmd_vlan_id_1, sizeof(dev_cmd_vlan_id_1));
+ EXPECT_EQ(len, sizeof(dev_cmd_vlan_id_1));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_svlan_id) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_svlan_id_0, sizeof(dev_cmd_svlan_id_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_svlan_id_0));
+
+ len = write(self->dev_fd, dev_cmd_svlan_p_0, sizeof(dev_cmd_svlan_p_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_svlan_p_0));
+
+ len = write(self->dev_fd, dev_cmd_svlan_cfi_0, sizeof(dev_cmd_svlan_cfi_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_svlan_cfi_0));
+
+ len = write(self->dev_fd, dev_cmd_svlan_id_1, sizeof(dev_cmd_svlan_id_1));
+ EXPECT_EQ(len, sizeof(dev_cmd_svlan_id_1));
+}
+
+
+TEST_F(proc_net_pktgen, dev_cmd_tos) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_tos_0, sizeof(dev_cmd_tos_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_tos_0));
+
+ len = write(self->dev_fd, dev_cmd_tos_1, sizeof(dev_cmd_tos_1));
+ EXPECT_EQ(len, sizeof(dev_cmd_tos_1));
+
+ len = write(self->dev_fd, dev_cmd_tos_2, sizeof(dev_cmd_tos_2));
+ EXPECT_EQ(len, sizeof(dev_cmd_tos_2));
+}
+
+
+TEST_F(proc_net_pktgen, dev_cmd_traffic_class) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_traffic_class_0, sizeof(dev_cmd_traffic_class_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_traffic_class_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_skb_priority) {
+ ssize_t len;
+
+ len = write(self->dev_fd, dev_cmd_skb_priority_0, sizeof(dev_cmd_skb_priority_0));
+ EXPECT_EQ(len, sizeof(dev_cmd_skb_priority_0));
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/net/psock_tpacket.c b/tools/testing/selftests/net/psock_tpacket.c
index 404a2ce759ab..221270cee3ea 100644
--- a/tools/testing/selftests/net/psock_tpacket.c
+++ b/tools/testing/selftests/net/psock_tpacket.c
@@ -12,7 +12,7 @@
*
* Datapath:
* Open a pair of packet sockets and send resp. receive an a priori known
- * packet pattern accross the sockets and check if it was received resp.
+ * packet pattern across the sockets and check if it was received resp.
* sent correctly. Fanout in combination with RX_RING is currently not
* tested here.
*
diff --git a/tools/testing/selftests/net/reuseaddr_ports_exhausted.c b/tools/testing/selftests/net/reuseaddr_ports_exhausted.c
index 066efd30e294..7b9bf8a7bbe1 100644
--- a/tools/testing/selftests/net/reuseaddr_ports_exhausted.c
+++ b/tools/testing/selftests/net/reuseaddr_ports_exhausted.c
@@ -112,7 +112,7 @@ TEST(reuseaddr_ports_exhausted_reusable_same_euid)
ASSERT_NE(-1, fd[0]) TH_LOG("failed to bind.");
if (opts->reuseport[0] && opts->reuseport[1]) {
- EXPECT_EQ(-1, fd[1]) TH_LOG("should fail to bind because both sockets succeed to be listened.");
+ EXPECT_EQ(-1, fd[1]) TH_LOG("should fail to bind because both sockets successfully listened.");
} else {
EXPECT_NE(-1, fd[1]) TH_LOG("should succeed to bind to connect to different destinations.");
}
diff --git a/tools/testing/selftests/net/reuseport_addr_any.c b/tools/testing/selftests/net/reuseport_addr_any.c
index b8475cb29be7..1c43401a1c80 100644
--- a/tools/testing/selftests/net/reuseport_addr_any.c
+++ b/tools/testing/selftests/net/reuseport_addr_any.c
@@ -9,7 +9,6 @@
#include <arpa/inet.h>
#include <errno.h>
#include <error.h>
-#include <linux/dccp.h>
#include <linux/in.h>
#include <linux/unistd.h>
#include <stdbool.h>
@@ -21,10 +20,6 @@
#include <sys/socket.h>
#include <unistd.h>
-#ifndef SOL_DCCP
-#define SOL_DCCP 269
-#endif
-
static const char *IP4_ADDR = "127.0.0.1";
static const char *IP6_ADDR = "::1";
static const char *IP4_MAPPED6 = "::ffff:127.0.0.1";
@@ -86,15 +81,6 @@ static void build_rcv_fd(int family, int proto, int *rcv_fds, int count,
if (proto == SOCK_STREAM && listen(rcv_fds[i], 10))
error(1, errno, "tcp: failed to listen on receive port");
- else if (proto == SOCK_DCCP) {
- if (setsockopt(rcv_fds[i], SOL_DCCP,
- DCCP_SOCKOPT_SERVICE,
- &(int) {htonl(42)}, sizeof(int)))
- error(1, errno, "failed to setsockopt");
-
- if (listen(rcv_fds[i], 10))
- error(1, errno, "dccp: failed to listen on receive port");
- }
}
}
@@ -148,11 +134,6 @@ static int connect_and_send(int family, int proto)
if (fd < 0)
error(1, errno, "failed to create send socket");
- if (proto == SOCK_DCCP &&
- setsockopt(fd, SOL_DCCP, DCCP_SOCKOPT_SERVICE,
- &(int){htonl(42)}, sizeof(int)))
- error(1, errno, "failed to setsockopt");
-
if (bind(fd, saddr, sz))
error(1, errno, "failed to bind send socket");
@@ -175,7 +156,7 @@ static int receive_once(int epfd, int proto)
if (i < 0)
error(1, errno, "epoll_wait failed");
- if (proto == SOCK_STREAM || proto == SOCK_DCCP) {
+ if (proto == SOCK_STREAM) {
fd = accept(ev.data.fd, NULL, NULL);
if (fd < 0)
error(1, errno, "failed to accept");
@@ -243,20 +224,6 @@ static void run_one_test(int fam_send, int fam_rcv, int proto,
static void test_proto(int proto, const char *proto_str)
{
- if (proto == SOCK_DCCP) {
- int test_fd;
-
- test_fd = socket(AF_INET, proto, 0);
- if (test_fd < 0) {
- if (errno == ESOCKTNOSUPPORT) {
- fprintf(stderr, "DCCP not supported: skipping DCCP tests\n");
- return;
- } else
- error(1, errno, "failed to create a DCCP socket");
- }
- close(test_fd);
- }
-
fprintf(stderr, "%s IPv4 ... ", proto_str);
run_one_test(AF_INET, AF_INET, proto, IP4_ADDR);
@@ -271,7 +238,6 @@ int main(void)
{
test_proto(SOCK_DGRAM, "UDP");
test_proto(SOCK_STREAM, "TCP");
- test_proto(SOCK_DCCP, "DCCP");
fprintf(stderr, "SUCCESS\n");
return 0;
diff --git a/tools/testing/selftests/net/rtnetlink.py b/tools/testing/selftests/net/rtnetlink.py
new file mode 100755
index 000000000000..e9ad5e88da97
--- /dev/null
+++ b/tools/testing/selftests/net/rtnetlink.py
@@ -0,0 +1,30 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+from lib.py import ksft_exit, ksft_run, ksft_ge, RtnlAddrFamily
+import socket
+
+IPV4_ALL_HOSTS_MULTICAST = b'\xe0\x00\x00\x01'
+
+def dump_mcaddr_check(rtnl: RtnlAddrFamily) -> None:
+ """
+ Verify that at least one interface has the IPv4 all-hosts multicast address.
+ At least the loopback interface should have this address.
+ """
+
+ addresses = rtnl.getmulticast({"ifa-family": socket.AF_INET}, dump=True)
+
+ all_host_multicasts = [
+ addr for addr in addresses if addr['multicast'] == IPV4_ALL_HOSTS_MULTICAST
+ ]
+
+ ksft_ge(len(all_host_multicasts), 1,
+ "No interface found with the IPv4 all-hosts multicast address")
+
+def main() -> None:
+ rtnl = RtnlAddrFamily()
+ ksft_run([dump_mcaddr_check], args=(rtnl, ))
+ ksft_exit()
+
+if __name__ == "__main__":
+ main()
diff --git a/tools/testing/selftests/net/setup_veth.sh b/tools/testing/selftests/net/setup_veth.sh
index 1f78a87f6f37..152bf4c65747 100644
--- a/tools/testing/selftests/net/setup_veth.sh
+++ b/tools/testing/selftests/net/setup_veth.sh
@@ -11,7 +11,8 @@ setup_veth_ns() {
local -r ns_mac="$4"
[[ -e /var/run/netns/"${ns_name}" ]] || ip netns add "${ns_name}"
- echo 1000000 > "/sys/class/net/${ns_dev}/gro_flush_timeout"
+ echo 200000 > "/sys/class/net/${ns_dev}/gro_flush_timeout"
+ echo 1 > "/sys/class/net/${ns_dev}/napi_defer_hard_irqs"
ip link set dev "${ns_dev}" netns "${ns_name}" mtu 65535
ip -netns "${ns_name}" link set dev "${ns_dev}" up
diff --git a/tools/testing/selftests/net/skf_net_off.c b/tools/testing/selftests/net/skf_net_off.c
new file mode 100644
index 000000000000..1fdf61d6cd7f
--- /dev/null
+++ b/tools/testing/selftests/net/skf_net_off.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Open a tun device.
+ *
+ * [modifications: use IFF_NAPI_FRAGS, add sk filter]
+ *
+ * Expects the device to have been configured previously, e.g.:
+ * sudo ip tuntap add name tap1 mode tap
+ * sudo ip link set tap1 up
+ * sudo ip link set dev tap1 addr 02:00:00:00:00:01
+ * sudo ip -6 addr add fdab::1 peer fdab::2 dev tap1 nodad
+ *
+ * And to avoid premature pskb_may_pull:
+ *
+ * sudo ethtool -K tap1 gro off
+ * sudo bash -c 'echo 0 > /proc/sys/net/ipv4/ip_early_demux'
+ */
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <fcntl.h>
+#include <getopt.h>
+#include <linux/filter.h>
+#include <linux/if.h>
+#include <linux/if_packet.h>
+#include <linux/if_tun.h>
+#include <linux/ipv6.h>
+#include <netinet/if_ether.h>
+#include <netinet/in.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/poll.h>
+#include <sys/types.h>
+#include <sys/uio.h>
+#include <unistd.h>
+
+static bool cfg_do_filter;
+static bool cfg_do_frags;
+static int cfg_dst_port = 8000;
+static char *cfg_ifname;
+
+static int tun_open(const char *tun_name)
+{
+ struct ifreq ifr = {0};
+ int fd, ret;
+
+ fd = open("/dev/net/tun", O_RDWR);
+ if (fd == -1)
+ error(1, errno, "open /dev/net/tun");
+
+ ifr.ifr_flags = IFF_TAP;
+ if (cfg_do_frags)
+ ifr.ifr_flags |= IFF_NAPI | IFF_NAPI_FRAGS;
+
+ strncpy(ifr.ifr_name, tun_name, IFNAMSIZ - 1);
+
+ ret = ioctl(fd, TUNSETIFF, &ifr);
+ if (ret)
+ error(1, ret, "ioctl TUNSETIFF");
+
+ return fd;
+}
+
+static void sk_set_filter(int fd)
+{
+ const int offset_proto = offsetof(struct ip6_hdr, ip6_nxt);
+ const int offset_dport = sizeof(struct ip6_hdr) + offsetof(struct udphdr, dest);
+
+ /* Filter UDP packets with destination port cfg_dst_port */
+ struct sock_filter filter_code[] = {
+ BPF_STMT(BPF_LD + BPF_B + BPF_ABS, SKF_AD_OFF + SKF_AD_PKTTYPE),
+ BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, PACKET_HOST, 0, 4),
+ BPF_STMT(BPF_LD + BPF_B + BPF_ABS, SKF_NET_OFF + offset_proto),
+ BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, IPPROTO_UDP, 0, 2),
+ BPF_STMT(BPF_LD + BPF_H + BPF_ABS, SKF_NET_OFF + offset_dport),
+ BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, cfg_dst_port, 1, 0),
+ BPF_STMT(BPF_RET + BPF_K, 0),
+ BPF_STMT(BPF_RET + BPF_K, 0xFFFF),
+ };
+
+ struct sock_fprog filter = {
+ sizeof(filter_code) / sizeof(filter_code[0]),
+ filter_code,
+ };
+
+ if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &filter, sizeof(filter)))
+ error(1, errno, "setsockopt attach filter");
+}
+
+static int raw_open(void)
+{
+ int fd;
+
+ fd = socket(PF_INET6, SOCK_RAW, IPPROTO_UDP);
+ if (fd == -1)
+ error(1, errno, "socket raw (udp)");
+
+ if (cfg_do_filter)
+ sk_set_filter(fd);
+
+ return fd;
+}
+
+static void tun_write(int fd)
+{
+ const char eth_src[] = { 0x02, 0x00, 0x00, 0x00, 0x00, 0x02 };
+ const char eth_dst[] = { 0x02, 0x00, 0x00, 0x00, 0x00, 0x01 };
+ struct tun_pi pi = {0};
+ struct ipv6hdr ip6h = {0};
+ struct udphdr uh = {0};
+ struct ethhdr eth = {0};
+ uint32_t payload;
+ struct iovec iov[5];
+ int ret;
+
+ pi.proto = htons(ETH_P_IPV6);
+
+ memcpy(eth.h_source, eth_src, sizeof(eth_src));
+ memcpy(eth.h_dest, eth_dst, sizeof(eth_dst));
+ eth.h_proto = htons(ETH_P_IPV6);
+
+ ip6h.version = 6;
+ ip6h.payload_len = htons(sizeof(uh) + sizeof(uint32_t));
+ ip6h.nexthdr = IPPROTO_UDP;
+ ip6h.hop_limit = 8;
+ if (inet_pton(AF_INET6, "fdab::2", &ip6h.saddr) != 1)
+ error(1, errno, "inet_pton src");
+ if (inet_pton(AF_INET6, "fdab::1", &ip6h.daddr) != 1)
+ error(1, errno, "inet_pton src");
+
+ uh.source = htons(8000);
+ uh.dest = htons(cfg_dst_port);
+ uh.len = ip6h.payload_len;
+ uh.check = 0;
+
+ payload = htonl(0xABABABAB); /* Covered in IPv6 length */
+
+ iov[0].iov_base = &pi;
+ iov[0].iov_len = sizeof(pi);
+ iov[1].iov_base = &eth;
+ iov[1].iov_len = sizeof(eth);
+ iov[2].iov_base = &ip6h;
+ iov[2].iov_len = sizeof(ip6h);
+ iov[3].iov_base = &uh;
+ iov[3].iov_len = sizeof(uh);
+ iov[4].iov_base = &payload;
+ iov[4].iov_len = sizeof(payload);
+
+ ret = writev(fd, iov, sizeof(iov) / sizeof(iov[0]));
+ if (ret <= 0)
+ error(1, errno, "writev");
+}
+
+static void raw_read(int fd)
+{
+ struct timeval tv = { .tv_usec = 100 * 1000 };
+ struct msghdr msg = {0};
+ struct iovec iov[2];
+ struct udphdr uh;
+ uint32_t payload[2];
+ int ret;
+
+ if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)))
+ error(1, errno, "setsockopt rcvtimeo udp");
+
+ iov[0].iov_base = &uh;
+ iov[0].iov_len = sizeof(uh);
+
+ iov[1].iov_base = payload;
+ iov[1].iov_len = sizeof(payload);
+
+ msg.msg_iov = iov;
+ msg.msg_iovlen = sizeof(iov) / sizeof(iov[0]);
+
+ ret = recvmsg(fd, &msg, 0);
+ if (ret <= 0)
+ error(1, errno, "read raw");
+ if (ret != sizeof(uh) + sizeof(payload[0]))
+ error(1, errno, "read raw: len=%d\n", ret);
+
+ fprintf(stderr, "raw recv: 0x%x\n", payload[0]);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ int c;
+
+ while ((c = getopt(argc, argv, "fFi:")) != -1) {
+ switch (c) {
+ case 'f':
+ cfg_do_filter = true;
+ printf("bpf filter enabled\n");
+ break;
+ case 'F':
+ cfg_do_frags = true;
+ printf("napi frags mode enabled\n");
+ break;
+ case 'i':
+ cfg_ifname = optarg;
+ break;
+ default:
+ error(1, 0, "unknown option %c", optopt);
+ break;
+ }
+ }
+
+ if (!cfg_ifname)
+ error(1, 0, "must specify tap interface name (-i)");
+}
+
+int main(int argc, char **argv)
+{
+ int fdt, fdr;
+
+ parse_opts(argc, argv);
+
+ fdr = raw_open();
+ fdt = tun_open(cfg_ifname);
+
+ tun_write(fdt);
+ raw_read(fdr);
+
+ if (close(fdt))
+ error(1, errno, "close tun");
+ if (close(fdr))
+ error(1, errno, "close udp");
+
+ fprintf(stderr, "OK\n");
+ return 0;
+}
+
diff --git a/tools/testing/selftests/net/skf_net_off.sh b/tools/testing/selftests/net/skf_net_off.sh
new file mode 100755
index 000000000000..5da5066fb465
--- /dev/null
+++ b/tools/testing/selftests/net/skf_net_off.sh
@@ -0,0 +1,30 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+readonly NS="ns-$(mktemp -u XXXXXX)"
+
+cleanup() {
+ ip netns del $NS
+}
+
+ip netns add $NS
+trap cleanup EXIT
+
+ip -netns $NS link set lo up
+ip -netns $NS tuntap add name tap1 mode tap
+ip -netns $NS link set tap1 up
+ip -netns $NS link set dev tap1 addr 02:00:00:00:00:01
+ip -netns $NS -6 addr add fdab::1 peer fdab::2 dev tap1 nodad
+ip netns exec $NS ethtool -K tap1 gro off
+
+# disable early demux, else udp_v6_early_demux pulls udp header into linear
+ip netns exec $NS sysctl -w net.ipv4.ip_early_demux=0
+
+echo "no filter"
+ip netns exec $NS ./skf_net_off -i tap1
+
+echo "filter, linear skb (-f)"
+ip netns exec $NS ./skf_net_off -i tap1 -f
+
+echo "filter, fragmented skb (-f) (-F)"
+ip netns exec $NS ./skf_net_off -i tap1 -f -F
diff --git a/tools/testing/selftests/net/so_rcv_listener.c b/tools/testing/selftests/net/so_rcv_listener.c
new file mode 100644
index 000000000000..bc5841192aa6
--- /dev/null
+++ b/tools/testing/selftests/net/so_rcv_listener.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <errno.h>
+#include <netdb.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/types.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+
+#ifndef SO_RCVPRIORITY
+#define SO_RCVPRIORITY 82
+#endif
+
+struct options {
+ __u32 val;
+ int name;
+ int rcvname;
+ const char *host;
+ const char *service;
+} opt;
+
+static void __attribute__((noreturn)) usage(const char *bin)
+{
+ printf("Usage: %s [opts] <dst host> <dst port / service>\n", bin);
+ printf("Options:\n"
+ "\t\t-M val Test SO_RCVMARK\n"
+ "\t\t-P val Test SO_RCVPRIORITY\n"
+ "");
+ exit(EXIT_FAILURE);
+}
+
+static void parse_args(int argc, char *argv[])
+{
+ int o;
+
+ while ((o = getopt(argc, argv, "M:P:")) != -1) {
+ switch (o) {
+ case 'M':
+ opt.val = atoi(optarg);
+ opt.name = SO_MARK;
+ opt.rcvname = SO_RCVMARK;
+ break;
+ case 'P':
+ opt.val = atoi(optarg);
+ opt.name = SO_PRIORITY;
+ opt.rcvname = SO_RCVPRIORITY;
+ break;
+ default:
+ usage(argv[0]);
+ break;
+ }
+ }
+
+ if (optind != argc - 2)
+ usage(argv[0]);
+
+ opt.host = argv[optind];
+ opt.service = argv[optind + 1];
+}
+
+int main(int argc, char *argv[])
+{
+ int err = 0;
+ int recv_fd = -1;
+ int ret_value = 0;
+ __u32 recv_val;
+ struct cmsghdr *cmsg;
+ char cbuf[CMSG_SPACE(sizeof(__u32))];
+ char recv_buf[CMSG_SPACE(sizeof(__u32))];
+ struct iovec iov[1];
+ struct msghdr msg;
+ struct sockaddr_in recv_addr4;
+ struct sockaddr_in6 recv_addr6;
+
+ parse_args(argc, argv);
+
+ int family = strchr(opt.host, ':') ? AF_INET6 : AF_INET;
+
+ recv_fd = socket(family, SOCK_DGRAM, IPPROTO_UDP);
+ if (recv_fd < 0) {
+ perror("Can't open recv socket");
+ ret_value = -errno;
+ goto cleanup;
+ }
+
+ err = setsockopt(recv_fd, SOL_SOCKET, opt.rcvname, &opt.val, sizeof(opt.val));
+ if (err < 0) {
+ perror("Recv setsockopt error");
+ ret_value = -errno;
+ goto cleanup;
+ }
+
+ if (family == AF_INET) {
+ memset(&recv_addr4, 0, sizeof(recv_addr4));
+ recv_addr4.sin_family = family;
+ recv_addr4.sin_port = htons(atoi(opt.service));
+
+ if (inet_pton(family, opt.host, &recv_addr4.sin_addr) <= 0) {
+ perror("Invalid IPV4 address");
+ ret_value = -errno;
+ goto cleanup;
+ }
+
+ err = bind(recv_fd, (struct sockaddr *)&recv_addr4, sizeof(recv_addr4));
+ } else {
+ memset(&recv_addr6, 0, sizeof(recv_addr6));
+ recv_addr6.sin6_family = family;
+ recv_addr6.sin6_port = htons(atoi(opt.service));
+
+ if (inet_pton(family, opt.host, &recv_addr6.sin6_addr) <= 0) {
+ perror("Invalid IPV6 address");
+ ret_value = -errno;
+ goto cleanup;
+ }
+
+ err = bind(recv_fd, (struct sockaddr *)&recv_addr6, sizeof(recv_addr6));
+ }
+
+ if (err < 0) {
+ perror("Recv bind error");
+ ret_value = -errno;
+ goto cleanup;
+ }
+
+ iov[0].iov_base = recv_buf;
+ iov[0].iov_len = sizeof(recv_buf);
+
+ memset(&msg, 0, sizeof(msg));
+ msg.msg_iov = iov;
+ msg.msg_iovlen = 1;
+ msg.msg_control = cbuf;
+ msg.msg_controllen = sizeof(cbuf);
+
+ err = recvmsg(recv_fd, &msg, 0);
+ if (err < 0) {
+ perror("Message receive error");
+ ret_value = -errno;
+ goto cleanup;
+ }
+
+ for (cmsg = CMSG_FIRSTHDR(&msg); cmsg != NULL; cmsg = CMSG_NXTHDR(&msg, cmsg)) {
+ if (cmsg->cmsg_level == SOL_SOCKET && cmsg->cmsg_type == opt.name) {
+ recv_val = *(__u32 *)CMSG_DATA(cmsg);
+ printf("Received value: %u\n", recv_val);
+
+ if (recv_val != opt.val) {
+ fprintf(stderr, "Error: expected value: %u, got: %u\n",
+ opt.val, recv_val);
+ ret_value = -EINVAL;
+ }
+ goto cleanup;
+ }
+ }
+
+ fprintf(stderr, "Error: No matching cmsg received\n");
+ ret_value = -ENOMSG;
+
+cleanup:
+ if (recv_fd >= 0)
+ close(recv_fd);
+
+ return ret_value;
+}
diff --git a/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh
index 02d617040793..a5e959a080bb 100755
--- a/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh
@@ -285,11 +285,6 @@ setup_hs()
ip netns exec ${hsname} sysctl -wq net.ipv6.conf.all.accept_dad=0
ip netns exec ${hsname} sysctl -wq net.ipv6.conf.default.accept_dad=0
- # disable the rp_filter otherwise the kernel gets confused about how
- # to route decap ipv4 packets.
- ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0
- ip netns exec ${rtname} sysctl -wq net.ipv4.conf.default.rp_filter=0
-
ip -netns ${hsname} link add veth0 type veth peer name ${rtveth}
ip -netns ${hsname} link set ${rtveth} netns ${rtname}
ip -netns ${hsname} addr add ${IPv6_HS_NETWORK}::${hid}/64 dev veth0 nodad
diff --git a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh
index 79fb81e63c59..a649dba3cb77 100755
--- a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh
@@ -250,11 +250,6 @@ setup_hs()
eval local rtname=\${rt_${rid}}
local rtveth=veth-t${tid}
- # disable the rp_filter otherwise the kernel gets confused about how
- # to route decap ipv4 packets.
- ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0
- ip netns exec ${rtname} sysctl -wq net.ipv4.conf.default.rp_filter=0
-
ip -netns ${hsname} link add veth0 type veth peer name ${rtveth}
ip -netns ${hsname} link set ${rtveth} netns ${rtname}
ip -netns ${hsname} addr add ${IPv4_HS_NETWORK}.${hid}/24 dev veth0
diff --git a/tools/testing/selftests/net/srv6_end_flavors_test.sh b/tools/testing/selftests/net/srv6_end_flavors_test.sh
index 50563443a4ad..318487eda671 100755
--- a/tools/testing/selftests/net/srv6_end_flavors_test.sh
+++ b/tools/testing/selftests/net/srv6_end_flavors_test.sh
@@ -399,7 +399,7 @@ __get_srv6_rtcfg_id()
# Given the description of a router <id:op> as an input, the function returns
# the <op> token which represents the operation (e.g. End behavior with or
-# withouth flavors) configured for the node.
+# without flavors) configured for the node.
# Note that when the operation represents an End behavior with a list of
# flavors, the output is the ordered version of that list.
@@ -480,7 +480,7 @@ setup_rt_local_sids()
# all SIDs start with a common locator. Routes and SRv6 Endpoint
- # behavior instaces are grouped together in the 'localsid' table.
+ # behavior instances are grouped together in the 'localsid' table.
ip -netns "${nsname}" -6 rule \
add to "${LOCATOR_SERVICE}::/16" \
lookup "${LOCALSID_TABLE_ID}" prio 999
diff --git a/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh
index 87e414cc417c..ba730655a7bf 100755
--- a/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh
@@ -245,10 +245,8 @@
# that adopted in the use cases already examined (of course, it is necessary to
# consider the different SIDs/C-SIDs).
-# Kselftest framework requirement - SKIP code is 4.
-readonly ksft_skip=4
+source lib.sh
-readonly RDMSUFF="$(mktemp -u XXXXXXXX)"
readonly DUMMY_DEVNAME="dum0"
readonly VRF_TID=100
readonly VRF_DEVNAME="vrf-${VRF_TID}"
@@ -376,32 +374,18 @@ test_command_or_ksft_skip()
fi
}
-get_nodename()
-{
- local name="$1"
-
- echo "${name}-${RDMSUFF}"
-}
-
get_rtname()
{
local rtid="$1"
- get_nodename "rt-${rtid}"
+ echo "rt_${rtid}"
}
get_hsname()
{
local hsid="$1"
- get_nodename "hs-${hsid}"
-}
-
-__create_namespace()
-{
- local name="$1"
-
- ip netns add "${name}"
+ echo "hs_${hsid}"
}
create_router()
@@ -410,8 +394,7 @@ create_router()
local nsname
nsname="$(get_rtname "${rtid}")"
-
- __create_namespace "${nsname}"
+ setup_ns "${nsname}"
}
create_host()
@@ -420,28 +403,12 @@ create_host()
local nsname
nsname="$(get_hsname "${hsid}")"
-
- __create_namespace "${nsname}"
+ setup_ns "${nsname}"
}
cleanup()
{
- local nsname
- local i
-
- # destroy routers
- for i in ${ROUTERS}; do
- nsname="$(get_rtname "${i}")"
-
- ip netns del "${nsname}" &>/dev/null || true
- done
-
- # destroy hosts
- for i in ${HOSTS}; do
- nsname="$(get_hsname "${i}")"
-
- ip netns del "${nsname}" &>/dev/null || true
- done
+ cleanup_all_ns
# check whether the setup phase was completed successfully or not. In
# case of an error during the setup phase of the testing environment,
@@ -462,10 +429,10 @@ add_link_rt_pairs()
local nsname
local neigh_nsname
- nsname="$(get_rtname "${rt}")"
+ eval nsname=\${$(get_rtname "${rt}")}
for neigh in ${rt_neighs}; do
- neigh_nsname="$(get_rtname "${neigh}")"
+ eval neigh_nsname=\${$(get_rtname "${neigh}")}
ip link add "veth-rt-${rt}-${neigh}" netns "${nsname}" \
type veth peer name "veth-rt-${neigh}-${rt}" \
@@ -497,7 +464,7 @@ setup_rt_networking()
local devname
local neigh
- nsname="$(get_rtname "${rt}")"
+ eval nsname=\${$(get_rtname "${rt}")}
for neigh in ${rt_neighs}; do
devname="veth-rt-${rt}-${neigh}"
@@ -518,9 +485,6 @@ setup_rt_networking()
ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.forwarding=1
-
- ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.all.rp_filter=0
- ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.default.rp_filter=0
ip netns exec "${nsname}" sysctl -wq net.ipv4.ip_forward=1
}
@@ -596,7 +560,7 @@ setup_rt_local_sids()
local lcnode_func_prefix
local lcblock_prefix
- nsname="$(get_rtname "${rt}")"
+ eval nsname=\${$(get_rtname "${rt}")}
for neigh in ${rt_neighs}; do
devname="veth-rt-${rt}-${neigh}"
@@ -668,8 +632,8 @@ __setup_l3vpn()
local rtsrc_nsname
local rtdst_nsname
- rtsrc_nsname="$(get_rtname "${src}")"
- rtdst_nsname="$(get_rtname "${dst}")"
+ eval rtsrc_nsname=\${$(get_rtname "${src}")}
+ eval rtdst_nsname=\${$(get_rtname "${dst}")}
container="${LCBLOCK_ADDR}"
@@ -744,8 +708,8 @@ setup_hs()
local hsname
local rtname
- hsname="$(get_hsname "${hs}")"
- rtname="$(get_rtname "${rt}")"
+ eval hsname=\${$(get_hsname "${hs}")}
+ eval rtname=\${$(get_rtname "${rt}")}
ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
@@ -791,11 +755,6 @@ setup_hs()
ip netns exec "${rtname}" \
sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".proxy_arp=1
- # disable the rp_filter otherwise the kernel gets confused about how
- # to route decap ipv4 packets.
- ip netns exec "${rtname}" \
- sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".rp_filter=0
-
ip netns exec "${rtname}" sh -c "echo 1 > /proc/sys/net/vrf/strict_mode"
}
@@ -880,7 +839,7 @@ check_rt_connectivity()
local prefix
local rtsrc_nsname
- rtsrc_nsname="$(get_rtname "${rtsrc}")"
+ eval rtsrc_nsname=\${$(get_rtname "${rtsrc}")}
prefix="$(get_network_prefix "${rtsrc}" "${rtdst}")"
@@ -903,7 +862,7 @@ check_hs_ipv6_connectivity()
local hsdst="$2"
local hssrc_nsname
- hssrc_nsname="$(get_hsname "${hssrc}")"
+ eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
"${IPv6_HS_NETWORK}::${hsdst}" >/dev/null 2>&1
@@ -915,7 +874,7 @@ check_hs_ipv4_connectivity()
local hsdst="$2"
local hssrc_nsname
- hssrc_nsname="$(get_hsname "${hssrc}")"
+ eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
"${IPv4_HS_NETWORK}.${hsdst}" >/dev/null 2>&1
@@ -1025,7 +984,7 @@ rt_x_nextcsid_end_behavior_test()
local nsname
local ret
- nsname="$(get_rtname "${rt}")"
+ eval nsname=\${$(get_rtname "${rt}")}
__nextcsid_end_behavior_test "${nsname}" "add" "${blen}" "${flen}"
ret="$?"
diff --git a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh
index c79cb8ede17f..4b86040c58c6 100755
--- a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh
@@ -287,10 +287,8 @@
# packet using the SRv6 End.DT46 behavior (associated with the SID fcff:1::d46)
# and sends it to the host hs-1.
-# Kselftest framework requirement - SKIP code is 4.
-readonly ksft_skip=4
+source lib.sh
-readonly RDMSUFF="$(mktemp -u XXXXXXXX)"
readonly DUMMY_DEVNAME="dum0"
readonly VRF_TID=100
readonly VRF_DEVNAME="vrf-${VRF_TID}"
@@ -418,32 +416,18 @@ test_command_or_ksft_skip()
fi
}
-get_nodename()
-{
- local name="$1"
-
- echo "${name}-${RDMSUFF}"
-}
-
get_rtname()
{
local rtid="$1"
- get_nodename "rt-${rtid}"
+ echo "rt_${rtid}"
}
get_hsname()
{
local hsid="$1"
- get_nodename "hs-${hsid}"
-}
-
-__create_namespace()
-{
- local name="$1"
-
- ip netns add "${name}"
+ echo "hs_${hsid}"
}
create_router()
@@ -452,15 +436,12 @@ create_router()
local nsname
nsname="$(get_rtname "${rtid}")"
+ setup_ns "${nsname}"
- __create_namespace "${nsname}"
-
+ eval nsname=\${$(get_rtname "${rtid}")}
ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.forwarding=1
-
- ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.all.rp_filter=0
- ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.default.rp_filter=0
ip netns exec "${nsname}" sysctl -wq net.ipv4.ip_forward=1
}
@@ -470,29 +451,12 @@ create_host()
local nsname
nsname="$(get_hsname "${hsid}")"
-
- __create_namespace "${nsname}"
+ setup_ns "${nsname}"
}
cleanup()
{
- local nsname
- local i
-
- # destroy routers
- for i in ${ROUTERS}; do
- nsname="$(get_rtname "${i}")"
-
- ip netns del "${nsname}" &>/dev/null || true
- done
-
- # destroy hosts
- for i in ${HOSTS}; do
- nsname="$(get_hsname "${i}")"
-
- ip netns del "${nsname}" &>/dev/null || true
- done
-
+ cleanup_all_ns
# check whether the setup phase was completed successfully or not. In
# case of an error during the setup phase of the testing environment,
# the selftest is considered as "skipped".
@@ -512,10 +476,10 @@ add_link_rt_pairs()
local nsname
local neigh_nsname
- nsname="$(get_rtname "${rt}")"
+ eval nsname=\${$(get_rtname "${rt}")}
for neigh in ${rt_neighs}; do
- neigh_nsname="$(get_rtname "${neigh}")"
+ eval neigh_nsname=\${$(get_rtname "${neigh}")}
ip link add "veth-rt-${rt}-${neigh}" netns "${nsname}" \
type veth peer name "veth-rt-${neigh}-${rt}" \
@@ -547,7 +511,7 @@ setup_rt_networking()
local devname
local neigh
- nsname="$(get_rtname "${rt}")"
+ eval nsname=\${$(get_rtname "${rt}")}
for neigh in ${rt_neighs}; do
devname="veth-rt-${rt}-${neigh}"
@@ -631,7 +595,7 @@ set_end_x_nextcsid()
local rt="$1"
local adj="$2"
- nsname="$(get_rtname "${rt}")"
+ eval nsname=\${$(get_rtname "${rt}")}
net_prefix="$(get_network_prefix "${rt}" "${adj}")"
lcnode_func_prefix="$(build_lcnode_func_prefix "${rt}")"
@@ -650,7 +614,7 @@ set_underlay_sids_reachability()
local rt="$1"
local rt_neighs="$2"
- nsname="$(get_rtname "${rt}")"
+ eval nsname=\${$(get_rtname "${rt}")}
for neigh in ${rt_neighs}; do
devname="veth-rt-${rt}-${neigh}"
@@ -685,7 +649,7 @@ setup_rt_local_sids()
local lcnode_func_prefix
local lcblock_prefix
- nsname="$(get_rtname "${rt}")"
+ eval nsname=\${$(get_rtname "${rt}")}
set_underlay_sids_reachability "${rt}" "${rt_neighs}"
@@ -728,8 +692,8 @@ __setup_l3vpn()
local rtsrc_nsname
local rtdst_nsname
- rtsrc_nsname="$(get_rtname "${src}")"
- rtdst_nsname="$(get_rtname "${dst}")"
+ eval rtsrc_nsname=\${$(get_rtname "${src}")}
+ eval rtdst_nsname=\${$(get_rtname "${dst}")}
container="${LCBLOCK_ADDR}"
@@ -804,8 +768,8 @@ setup_hs()
local hsname
local rtname
- hsname="$(get_hsname "${hs}")"
- rtname="$(get_rtname "${rt}")"
+ eval hsname=\${$(get_hsname "${hs}")}
+ eval rtname=\${$(get_rtname "${rt}")}
ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
@@ -851,11 +815,6 @@ setup_hs()
ip netns exec "${rtname}" \
sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".proxy_arp=1
- # disable the rp_filter otherwise the kernel gets confused about how
- # to route decap ipv4 packets.
- ip netns exec "${rtname}" \
- sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".rp_filter=0
-
ip netns exec "${rtname}" sh -c "echo 1 > /proc/sys/net/vrf/strict_mode"
}
@@ -947,7 +906,7 @@ check_rt_connectivity()
local prefix
local rtsrc_nsname
- rtsrc_nsname="$(get_rtname "${rtsrc}")"
+ eval rtsrc_nsname=\${$(get_rtname "${rtsrc}")}
prefix="$(get_network_prefix "${rtsrc}" "${rtdst}")"
@@ -970,7 +929,7 @@ check_hs_ipv6_connectivity()
local hsdst="$2"
local hssrc_nsname
- hssrc_nsname="$(get_hsname "${hssrc}")"
+ eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
"${IPv6_HS_NETWORK}::${hsdst}" >/dev/null 2>&1
@@ -982,7 +941,7 @@ check_hs_ipv4_connectivity()
local hsdst="$2"
local hssrc_nsname
- hssrc_nsname="$(get_hsname "${hssrc}")"
+ eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
"${IPv4_HS_NETWORK}.${hsdst}" >/dev/null 2>&1
@@ -1093,7 +1052,7 @@ rt_x_nextcsid_end_x_behavior_test()
local nsname
local ret
- nsname="$(get_rtname "${rt}")"
+ eval nsname=\${$(get_rtname "${rt}")}
__nextcsid_end_x_behavior_test "${nsname}" "add" "${blen}" "${flen}"
ret="$?"
diff --git a/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh b/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh
index 28a775654b92..3efce1718c5f 100755
--- a/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh
@@ -166,10 +166,8 @@
# hs-4->hs-3 |IPv6 DA=fcff:1::e|SRH SIDs=fcff:3::d46|IPv6|...| (i.d)
#
-# Kselftest framework requirement - SKIP code is 4.
-readonly ksft_skip=4
+source lib.sh
-readonly RDMSUFF="$(mktemp -u XXXXXXXX)"
readonly VRF_TID=100
readonly VRF_DEVNAME="vrf-${VRF_TID}"
readonly RT2HS_DEVNAME="veth-t${VRF_TID}"
@@ -248,32 +246,18 @@ test_command_or_ksft_skip()
fi
}
-get_nodename()
-{
- local name="$1"
-
- echo "${name}-${RDMSUFF}"
-}
-
get_rtname()
{
local rtid="$1"
- get_nodename "rt-${rtid}"
+ echo "rt_${rtid}"
}
get_hsname()
{
local hsid="$1"
- get_nodename "hs-${hsid}"
-}
-
-__create_namespace()
-{
- local name="$1"
-
- ip netns add "${name}"
+ echo "hs_${hsid}"
}
create_router()
@@ -282,8 +266,7 @@ create_router()
local nsname
nsname="$(get_rtname "${rtid}")"
-
- __create_namespace "${nsname}"
+ setup_ns "${nsname}"
}
create_host()
@@ -292,29 +275,12 @@ create_host()
local nsname
nsname="$(get_hsname "${hsid}")"
-
- __create_namespace "${nsname}"
+ setup_ns "${nsname}"
}
cleanup()
{
- local nsname
- local i
-
- # destroy routers
- for i in ${ROUTERS}; do
- nsname="$(get_rtname "${i}")"
-
- ip netns del "${nsname}" &>/dev/null || true
- done
-
- # destroy hosts
- for i in ${HOSTS}; do
- nsname="$(get_hsname "${i}")"
-
- ip netns del "${nsname}" &>/dev/null || true
- done
-
+ cleanup_all_ns
# check whether the setup phase was completed successfully or not. In
# case of an error during the setup phase of the testing environment,
# the selftest is considered as "skipped".
@@ -334,10 +300,10 @@ add_link_rt_pairs()
local nsname
local neigh_nsname
- nsname="$(get_rtname "${rt}")"
+ eval nsname=\${$(get_rtname "${rt}")}
for neigh in ${rt_neighs}; do
- neigh_nsname="$(get_rtname "${neigh}")"
+ eval neigh_nsname=\${$(get_rtname "${neigh}")}
ip link add "veth-rt-${rt}-${neigh}" netns "${nsname}" \
type veth peer name "veth-rt-${neigh}-${rt}" \
@@ -369,7 +335,7 @@ setup_rt_networking()
local devname
local neigh
- nsname="$(get_rtname "${rt}")"
+ eval nsname=\${$(get_rtname "${rt}")}
for neigh in ${rt_neighs}; do
devname="veth-rt-${rt}-${neigh}"
@@ -387,9 +353,6 @@ setup_rt_networking()
ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.forwarding=1
-
- ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.all.rp_filter=0
- ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.default.rp_filter=0
ip netns exec "${nsname}" sysctl -wq net.ipv4.ip_forward=1
}
@@ -403,7 +366,7 @@ setup_rt_local_sids()
local nsname
local neigh
- nsname="$(get_rtname "${rt}")"
+ eval nsname=\${$(get_rtname "${rt}")}
for neigh in ${rt_neighs}; do
devname="veth-rt-${rt}-${neigh}"
@@ -469,7 +432,7 @@ __setup_rt_policy()
local policy=''
local n
- nsname="$(get_rtname "${encap_rt}")"
+ eval nsname=\${$(get_rtname "${encap_rt}")}
for n in ${end_rts}; do
policy="${policy}${VPN_LOCATOR_SERVICE}:${n}::${END_FUNC},"
@@ -516,8 +479,8 @@ setup_hs()
local hsname
local rtname
- hsname="$(get_hsname "${hs}")"
- rtname="$(get_rtname "${rt}")"
+ eval hsname=\${$(get_hsname "${hs}")}
+ eval rtname=\${$(get_rtname "${rt}")}
ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
@@ -555,11 +518,6 @@ setup_hs()
ip netns exec "${rtname}" \
sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".proxy_arp=1
- # disable the rp_filter otherwise the kernel gets confused about how
- # to route decap ipv4 packets.
- ip netns exec "${rtname}" \
- sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".rp_filter=0
-
ip netns exec "${rtname}" sh -c "echo 1 > /proc/sys/net/vrf/strict_mode"
}
@@ -656,7 +614,7 @@ check_rt_connectivity()
local prefix
local rtsrc_nsname
- rtsrc_nsname="$(get_rtname "${rtsrc}")"
+ eval rtsrc_nsname=\${$(get_rtname "${rtsrc}")}
prefix="$(get_network_prefix "${rtsrc}" "${rtdst}")"
@@ -679,7 +637,7 @@ check_hs_ipv6_connectivity()
local hsdst="$2"
local hssrc_nsname
- hssrc_nsname="$(get_hsname "${hssrc}")"
+ eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
"${IPv6_HS_NETWORK}::${hsdst}" >/dev/null 2>&1
@@ -691,7 +649,7 @@ check_hs_ipv4_connectivity()
local hsdst="$2"
local hssrc_nsname
- hssrc_nsname="$(get_hsname "${hssrc}")"
+ eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
"${IPv4_HS_NETWORK}.${hsdst}" >/dev/null 2>&1
diff --git a/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh b/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh
index cb4177d41b21..cabc70538ffe 100755
--- a/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh
@@ -116,10 +116,8 @@
# hs-2->hs-1 |IPv6 DA=fcff:4::e|SRH SIDs=fcff:3::e,fcff:1::d2|eth|...| (i.b)
#
-# Kselftest framework requirement - SKIP code is 4.
-readonly ksft_skip=4
+source lib.sh
-readonly RDMSUFF="$(mktemp -u XXXXXXXX)"
readonly DUMMY_DEVNAME="dum0"
readonly RT2HS_DEVNAME="veth-hs"
readonly HS_VETH_NAME="veth0"
@@ -199,32 +197,18 @@ test_command_or_ksft_skip()
fi
}
-get_nodename()
-{
- local name="$1"
-
- echo "${name}-${RDMSUFF}"
-}
-
get_rtname()
{
local rtid="$1"
- get_nodename "rt-${rtid}"
+ echo "rt_${rtid}"
}
get_hsname()
{
local hsid="$1"
- get_nodename "hs-${hsid}"
-}
-
-__create_namespace()
-{
- local name="$1"
-
- ip netns add "${name}"
+ echo "hs_${hsid}"
}
create_router()
@@ -233,8 +217,7 @@ create_router()
local nsname
nsname="$(get_rtname "${rtid}")"
-
- __create_namespace "${nsname}"
+ setup_ns "${nsname}"
}
create_host()
@@ -243,28 +226,12 @@ create_host()
local nsname
nsname="$(get_hsname "${hsid}")"
-
- __create_namespace "${nsname}"
+ setup_ns "${nsname}"
}
cleanup()
{
- local nsname
- local i
-
- # destroy routers
- for i in ${ROUTERS}; do
- nsname="$(get_rtname "${i}")"
-
- ip netns del "${nsname}" &>/dev/null || true
- done
-
- # destroy hosts
- for i in ${HOSTS}; do
- nsname="$(get_hsname "${i}")"
-
- ip netns del "${nsname}" &>/dev/null || true
- done
+ cleanup_all_ns
# check whether the setup phase was completed successfully or not. In
# case of an error during the setup phase of the testing environment,
@@ -285,10 +252,10 @@ add_link_rt_pairs()
local nsname
local neigh_nsname
- nsname="$(get_rtname "${rt}")"
+ eval nsname=\${$(get_rtname "${rt}")}
for neigh in ${rt_neighs}; do
- neigh_nsname="$(get_rtname "${neigh}")"
+ eval neigh_nsname=\${$(get_rtname "${neigh}")}
ip link add "veth-rt-${rt}-${neigh}" netns "${nsname}" \
type veth peer name "veth-rt-${neigh}-${rt}" \
@@ -320,7 +287,7 @@ setup_rt_networking()
local devname
local neigh
- nsname="$(get_rtname "${rt}")"
+ eval nsname=\${$(get_rtname "${rt}")}
for neigh in ${rt_neighs}; do
devname="veth-rt-${rt}-${neigh}"
@@ -341,9 +308,6 @@ setup_rt_networking()
ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.forwarding=1
-
- ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.all.rp_filter=0
- ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.default.rp_filter=0
ip netns exec "${nsname}" sysctl -wq net.ipv4.ip_forward=1
}
@@ -357,7 +321,7 @@ setup_rt_local_sids()
local nsname
local neigh
- nsname="$(get_rtname "${rt}")"
+ eval nsname=\${$(get_rtname "${rt}")}
for neigh in ${rt_neighs}; do
devname="veth-rt-${rt}-${neigh}"
@@ -407,7 +371,7 @@ __setup_rt_policy()
local policy=''
local n
- nsname="$(get_rtname "${encap_rt}")"
+ eval nsname=\${$(get_rtname "${encap_rt}")}
for n in ${end_rts}; do
policy="${policy}${VPN_LOCATOR_SERVICE}:${n}::${END_FUNC},"
@@ -446,7 +410,7 @@ setup_decap()
local rt="$1"
local nsname
- nsname="$(get_rtname "${rt}")"
+ eval nsname=\${$(get_rtname "${rt}")}
# Local End.DX2 behavior
ip -netns "${nsname}" -6 route \
@@ -463,8 +427,8 @@ setup_hs()
local hsname
local rtname
- hsname="$(get_hsname "${hs}")"
- rtname="$(get_rtname "${rt}")"
+ eval hsname=\${$(get_hsname "${hs}")}
+ eval rtname=\${$(get_rtname "${rt}")}
ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
@@ -486,11 +450,6 @@ setup_hs()
add "${IPv4_HS_NETWORK}.254/24" dev "${RT2HS_DEVNAME}"
ip -netns "${rtname}" link set "${RT2HS_DEVNAME}" up
-
- # disable the rp_filter otherwise the kernel gets confused about how
- # to route decap ipv4 packets.
- ip netns exec "${rtname}" \
- sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".rp_filter=0
}
# set an auto-generated mac address
@@ -508,7 +467,7 @@ set_mac_address()
local ifname="$4"
local nsname
- nsname=$(get_nodename "${nodename}")
+ eval nsname=\${${nodename}}
ip -netns "${nsname}" link set dev "${ifname}" down
@@ -532,7 +491,7 @@ set_host_l2peer()
local hssrc_name
local ipaddr
- hssrc_name="$(get_hsname "${hssrc}")"
+ eval hssrc_name=\${$(get_hsname "${hssrc}")}
if [ "${proto}" -eq 6 ]; then
ipaddr="${ipprefix}::${hsdst}"
@@ -562,7 +521,7 @@ setup_l2vpn()
local rtdst="${hsdst}"
# set fixed mac for source node and the neigh MAC address
- set_mac_address "hs-${hssrc}" "${hssrc}" "${hssrc}" "${HS_VETH_NAME}"
+ set_mac_address "hs_${hssrc}" "${hssrc}" "${hssrc}" "${HS_VETH_NAME}"
set_host_l2peer "${hssrc}" "${hsdst}" "${IPv6_HS_NETWORK}" 6
set_host_l2peer "${hssrc}" "${hsdst}" "${IPv4_HS_NETWORK}" 4
@@ -570,7 +529,7 @@ setup_l2vpn()
# to the mac address of the remote peer (L2 VPN destination host).
# Otherwise, traffic coming from the source host is dropped at the
# ingress router.
- set_mac_address "rt-${rtsrc}" "${hsdst}" 254 "${RT2HS_DEVNAME}"
+ set_mac_address "rt_${rtsrc}" "${hsdst}" 254 "${RT2HS_DEVNAME}"
# set the SRv6 Policies at the ingress router
setup_rt_policy_ipv6 "${hsdst}" "${rtsrc}" "${end_rts}" "${rtdst}" \
@@ -647,7 +606,7 @@ check_rt_connectivity()
local prefix
local rtsrc_nsname
- rtsrc_nsname="$(get_rtname "${rtsrc}")"
+ eval rtsrc_nsname=\${$(get_rtname "${rtsrc}")}
prefix="$(get_network_prefix "${rtsrc}" "${rtdst}")"
@@ -670,7 +629,7 @@ check_hs_ipv6_connectivity()
local hsdst="$2"
local hssrc_nsname
- hssrc_nsname="$(get_hsname "${hssrc}")"
+ eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
"${IPv6_HS_NETWORK}::${hsdst}" >/dev/null 2>&1
@@ -682,7 +641,7 @@ check_hs_ipv4_connectivity()
local hsdst="$2"
local hssrc_nsname
- hssrc_nsname="$(get_hsname "${hssrc}")"
+ eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
"${IPv4_HS_NETWORK}.${hsdst}" >/dev/null 2>&1
diff --git a/tools/testing/selftests/net/tcp_ao/connect-deny.c b/tools/testing/selftests/net/tcp_ao/connect-deny.c
index d418162d335f..93b61e9a36f1 100644
--- a/tools/testing/selftests/net/tcp_ao/connect-deny.c
+++ b/tools/testing/selftests/net/tcp_ao/connect-deny.c
@@ -4,6 +4,7 @@
#include "aolib.h"
#define fault(type) (inj == FAULT_ ## type)
+static volatile int sk_pair;
static inline int test_add_key_maclen(int sk, const char *key, uint8_t maclen,
union tcp_addr in_addr, uint8_t prefix,
@@ -34,10 +35,10 @@ static void try_accept(const char *tst_name, unsigned int port, const char *pwd,
const char *cnt_name, test_cnt cnt_expected,
fault_t inj)
{
- struct tcp_ao_counters ao_cnt1, ao_cnt2;
+ struct tcp_counters cnt1, cnt2;
uint64_t before_cnt = 0, after_cnt = 0; /* silence GCC */
+ test_cnt poll_cnt = (cnt_expected == TEST_CNT_GOOD) ? 0 : cnt_expected;
int lsk, err, sk = 0;
- time_t timeout;
lsk = test_listen_socket(this_ip_addr, port, 1);
@@ -46,21 +47,24 @@ static void try_accept(const char *tst_name, unsigned int port, const char *pwd,
if (cnt_name)
before_cnt = netstat_get_one(cnt_name, NULL);
- if (pwd && test_get_tcp_ao_counters(lsk, &ao_cnt1))
- test_error("test_get_tcp_ao_counters()");
+ if (pwd && test_get_tcp_counters(lsk, &cnt1))
+ test_error("test_get_tcp_counters()");
synchronize_threads(); /* preparations done */
- timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
- err = test_wait_fd(lsk, timeout, 0);
+ err = test_skpair_wait_poll(lsk, 0, poll_cnt, &sk_pair);
if (err == -ETIMEDOUT) {
+ sk_pair = err;
if (!fault(TIMEOUT))
- test_fail("timed out for accept()");
+ test_fail("%s: timed out for accept()", tst_name);
+ } else if (err == -EKEYREJECTED) {
+ if (!fault(KEYREJECT))
+ test_fail("%s: key was rejected", tst_name);
} else if (err < 0) {
- test_error("test_wait_fd()");
+ test_error("test_skpair_wait_poll()");
} else {
if (fault(TIMEOUT))
- test_fail("ready to accept");
+ test_fail("%s: ready to accept", tst_name);
sk = accept(lsk, NULL, NULL);
if (sk < 0) {
@@ -72,13 +76,13 @@ static void try_accept(const char *tst_name, unsigned int port, const char *pwd,
}
synchronize_threads(); /* before counter checks */
- if (pwd && test_get_tcp_ao_counters(lsk, &ao_cnt2))
- test_error("test_get_tcp_ao_counters()");
+ if (pwd && test_get_tcp_counters(lsk, &cnt2))
+ test_error("test_get_tcp_counters()");
close(lsk);
if (pwd)
- test_tcp_ao_counters_cmp(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected);
+ test_assert_counters(tst_name, &cnt1, &cnt2, cnt_expected);
if (!cnt_name)
goto out;
@@ -109,7 +113,7 @@ static void *server_fn(void *arg)
try_accept("Non-AO server + AO client", port++, NULL,
this_ip_dest, -1, 100, 100, 0,
- "TCPAOKeyNotFound", 0, FAULT_TIMEOUT);
+ "TCPAOKeyNotFound", TEST_CNT_NS_KEY_NOT_FOUND, FAULT_TIMEOUT);
try_accept("AO server + Non-AO client", port++, DEFAULT_TEST_PASSWORD,
this_ip_dest, -1, 100, 100, 0,
@@ -135,8 +139,9 @@ static void *server_fn(void *arg)
wrong_addr, -1, 100, 100, 0,
"TCPAOKeyNotFound", TEST_CNT_AO_KEY_NOT_FOUND, FAULT_TIMEOUT);
+ /* Key rejected by the other side, failing short through skpair */
try_accept("Client: Wrong addr", port++, NULL,
- this_ip_dest, -1, 100, 100, 0, NULL, 0, FAULT_TIMEOUT);
+ this_ip_dest, -1, 100, 100, 0, NULL, 0, FAULT_KEYREJECT);
try_accept("rcv id != snd id", port++, DEFAULT_TEST_PASSWORD,
this_ip_dest, -1, 200, 100, 0,
@@ -163,8 +168,7 @@ static void try_connect(const char *tst_name, unsigned int port,
uint8_t sndid, uint8_t rcvid,
test_cnt cnt_expected, fault_t inj)
{
- struct tcp_ao_counters ao_cnt1, ao_cnt2;
- time_t timeout;
+ struct tcp_counters cnt1, cnt2;
int sk, ret;
sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
@@ -174,16 +178,15 @@ static void try_connect(const char *tst_name, unsigned int port,
if (pwd && test_add_key(sk, pwd, addr, prefix, sndid, rcvid))
test_error("setsockopt(TCP_AO_ADD_KEY)");
- if (pwd && test_get_tcp_ao_counters(sk, &ao_cnt1))
- test_error("test_get_tcp_ao_counters()");
+ if (pwd && test_get_tcp_counters(sk, &cnt1))
+ test_error("test_get_tcp_counters()");
synchronize_threads(); /* preparations done */
- timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
- ret = _test_connect_socket(sk, this_ip_dest, port, timeout);
-
+ ret = test_skpair_connect_poll(sk, this_ip_dest, port, cnt_expected, &sk_pair);
synchronize_threads(); /* before counter checks */
if (ret < 0) {
+ sk_pair = ret;
if (fault(KEYREJECT) && ret == -EKEYREJECTED) {
test_ok("%s: connect() was prevented", tst_name);
} else if (ret == -ETIMEDOUT && fault(TIMEOUT)) {
@@ -202,9 +205,11 @@ static void try_connect(const char *tst_name, unsigned int port,
else
test_ok("%s: connected", tst_name);
if (pwd && ret > 0) {
- if (test_get_tcp_ao_counters(sk, &ao_cnt2))
- test_error("test_get_tcp_ao_counters()");
- test_tcp_ao_counters_cmp(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected);
+ if (test_get_tcp_counters(sk, &cnt2))
+ test_error("test_get_tcp_counters()");
+ test_assert_counters(tst_name, &cnt1, &cnt2, cnt_expected);
+ } else if (pwd) {
+ test_tcp_counters_free(&cnt1);
}
out:
synchronize_threads(); /* close() */
@@ -241,6 +246,11 @@ static void *client_fn(void *arg)
try_connect("Wrong rcv id", port++, DEFAULT_TEST_PASSWORD,
this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT);
+ /*
+ * XXX: The test doesn't increase any counters, see tcp_make_synack().
+ * Potentially, it can be speed up by setting sk_pair = -ETIMEDOUT
+ * but the price would be increased complexity of the tracer thread.
+ */
trace_ao_event_sk_expect(TCP_AO_SYNACK_NO_KEY, this_ip_dest, addr_any,
port, 0, 100, 100);
try_connect("Wrong snd id", port++, DEFAULT_TEST_PASSWORD,
diff --git a/tools/testing/selftests/net/tcp_ao/connect.c b/tools/testing/selftests/net/tcp_ao/connect.c
index f1d8d29e393f..340f00e979ea 100644
--- a/tools/testing/selftests/net/tcp_ao/connect.c
+++ b/tools/testing/selftests/net/tcp_ao/connect.c
@@ -35,7 +35,7 @@ static void *client_fn(void *arg)
uint64_t before_aogood, after_aogood;
const size_t nr_packets = 20;
struct netstat *ns_before, *ns_after;
- struct tcp_ao_counters ao1, ao2;
+ struct tcp_counters ao1, ao2;
if (sk < 0)
test_error("socket()");
@@ -50,18 +50,18 @@ static void *client_fn(void *arg)
ns_before = netstat_read();
before_aogood = netstat_get(ns_before, "TCPAOGood", NULL);
- if (test_get_tcp_ao_counters(sk, &ao1))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(sk, &ao1))
+ test_error("test_get_tcp_counters()");
- if (test_client_verify(sk, 100, nr_packets, TEST_TIMEOUT_SEC)) {
+ if (test_client_verify(sk, 100, nr_packets)) {
test_fail("verify failed");
return NULL;
}
ns_after = netstat_read();
after_aogood = netstat_get(ns_after, "TCPAOGood", NULL);
- if (test_get_tcp_ao_counters(sk, &ao2))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(sk, &ao2))
+ test_error("test_get_tcp_counters()");
netstat_print_diff(ns_before, ns_after);
netstat_free(ns_before);
netstat_free(ns_after);
@@ -71,14 +71,14 @@ static void *client_fn(void *arg)
nr_packets, after_aogood, before_aogood);
return NULL;
}
- if (test_tcp_ao_counters_cmp("connect", &ao1, &ao2, TEST_CNT_GOOD))
+ if (test_assert_counters("connect", &ao1, &ao2, TEST_CNT_GOOD))
return NULL;
test_ok("connect TCPAOGood %" PRIu64 "/%" PRIu64 "/%" PRIu64 " => %" PRIu64 "/%" PRIu64 "/%" PRIu64 ", sent %zu",
- before_aogood, ao1.ao_info_pkt_good,
- ao1.key_cnts[0].pkt_good,
- after_aogood, ao2.ao_info_pkt_good,
- ao2.key_cnts[0].pkt_good,
+ before_aogood, ao1.ao.ao_info_pkt_good,
+ ao1.ao.key_cnts[0].pkt_good,
+ after_aogood, ao2.ao.ao_info_pkt_good,
+ ao2.ao.key_cnts[0].pkt_good,
nr_packets);
return NULL;
}
diff --git a/tools/testing/selftests/net/tcp_ao/icmps-discard.c b/tools/testing/selftests/net/tcp_ao/icmps-discard.c
index a1614f0d8c44..85c1a1e958c6 100644
--- a/tools/testing/selftests/net/tcp_ao/icmps-discard.c
+++ b/tools/testing/selftests/net/tcp_ao/icmps-discard.c
@@ -53,7 +53,7 @@ static void serve_interfered(int sk)
ssize_t test_quota = packet_size * packets_nr * 10;
uint64_t dest_unreach_a, dest_unreach_b;
uint64_t icmp_ignored_a, icmp_ignored_b;
- struct tcp_ao_counters ao_cnt1, ao_cnt2;
+ struct tcp_counters cnt1, cnt2;
bool counter_not_found;
struct netstat *ns_after, *ns_before;
ssize_t bytes;
@@ -61,16 +61,16 @@ static void serve_interfered(int sk)
ns_before = netstat_read();
dest_unreach_a = netstat_get(ns_before, dst_unreach, NULL);
icmp_ignored_a = netstat_get(ns_before, tcpao_icmps, NULL);
- if (test_get_tcp_ao_counters(sk, &ao_cnt1))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(sk, &cnt1))
+ test_error("test_get_tcp_counters()");
bytes = test_server_run(sk, test_quota, 0);
ns_after = netstat_read();
netstat_print_diff(ns_before, ns_after);
dest_unreach_b = netstat_get(ns_after, dst_unreach, NULL);
icmp_ignored_b = netstat_get(ns_after, tcpao_icmps,
&counter_not_found);
- if (test_get_tcp_ao_counters(sk, &ao_cnt2))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(sk, &cnt2))
+ test_error("test_get_tcp_counters()");
netstat_free(ns_before);
netstat_free(ns_after);
@@ -91,9 +91,9 @@ static void serve_interfered(int sk)
return;
}
#ifdef TEST_ICMPS_ACCEPT
- test_tcp_ao_counters_cmp(NULL, &ao_cnt1, &ao_cnt2, TEST_CNT_GOOD);
+ test_assert_counters(NULL, &cnt1, &cnt2, TEST_CNT_GOOD);
#else
- test_tcp_ao_counters_cmp(NULL, &ao_cnt1, &ao_cnt2, TEST_CNT_GOOD | TEST_CNT_AO_DROPPED_ICMP);
+ test_assert_counters(NULL, &cnt1, &cnt2, TEST_CNT_GOOD | TEST_CNT_AO_DROPPED_ICMP);
#endif
if (icmp_ignored_a >= icmp_ignored_b) {
test_icmps_fail("%s counter didn't change: %" PRIu64 " >= %" PRIu64,
@@ -395,7 +395,6 @@ static void icmp_interfere(const size_t nr, uint32_t rcv_nxt, void *src, void *d
static void send_interfered(int sk)
{
- const unsigned int timeout = TEST_TIMEOUT_SEC;
struct sockaddr_in6 src, dst;
socklen_t addr_sz;
@@ -409,7 +408,7 @@ static void send_interfered(int sk)
while (1) {
uint32_t rcv_nxt;
- if (test_client_verify(sk, packet_size, packets_nr, timeout)) {
+ if (test_client_verify(sk, packet_size, packets_nr)) {
test_fail("client: connection is broken");
return;
}
diff --git a/tools/testing/selftests/net/tcp_ao/key-management.c b/tools/testing/selftests/net/tcp_ao/key-management.c
index d4385b52c10b..69d9a7a05d5c 100644
--- a/tools/testing/selftests/net/tcp_ao/key-management.c
+++ b/tools/testing/selftests/net/tcp_ao/key-management.c
@@ -629,11 +629,11 @@ static int key_collection_socket(bool server, unsigned int port)
}
static void verify_counters(const char *tst_name, bool is_listen_sk, bool server,
- struct tcp_ao_counters *a, struct tcp_ao_counters *b)
+ struct tcp_counters *a, struct tcp_counters *b)
{
unsigned int i;
- __test_tcp_ao_counters_cmp(tst_name, a, b, TEST_CNT_GOOD);
+ test_assert_counters_sk(tst_name, a, b, TEST_CNT_GOOD);
for (i = 0; i < collection.nr_keys; i++) {
struct test_key *key = &collection.keys[i];
@@ -652,12 +652,12 @@ static void verify_counters(const char *tst_name, bool is_listen_sk, bool server
rx_cnt_expected = key->used_on_server_tx;
}
- test_tcp_ao_key_counters_cmp(tst_name, a, b,
- rx_cnt_expected ? TEST_CNT_KEY_GOOD : 0,
- sndid, rcvid);
+ test_assert_counters_key(tst_name, &a->ao, &b->ao,
+ rx_cnt_expected ? TEST_CNT_KEY_GOOD : 0,
+ sndid, rcvid);
}
- test_tcp_ao_counters_free(a);
- test_tcp_ao_counters_free(b);
+ test_tcp_counters_free(a);
+ test_tcp_counters_free(b);
test_ok("%s: passed counters checks", tst_name);
}
@@ -791,17 +791,17 @@ out:
}
static int start_server(const char *tst_name, unsigned int port, size_t quota,
- struct tcp_ao_counters *begin,
+ struct tcp_counters *begin,
unsigned int current_index, unsigned int rnext_index)
{
- struct tcp_ao_counters lsk_c1, lsk_c2;
+ struct tcp_counters lsk_c1, lsk_c2;
ssize_t bytes;
int sk, lsk;
synchronize_threads(); /* 1: key collection initialized */
lsk = key_collection_socket(true, port);
- if (test_get_tcp_ao_counters(lsk, &lsk_c1))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(lsk, &lsk_c1))
+ test_error("test_get_tcp_counters()");
synchronize_threads(); /* 2: MKTs added => connect() */
if (test_wait_fd(lsk, TEST_TIMEOUT_SEC, 0))
test_error("test_wait_fd()");
@@ -809,12 +809,12 @@ static int start_server(const char *tst_name, unsigned int port, size_t quota,
sk = accept(lsk, NULL, NULL);
if (sk < 0)
test_error("accept()");
- if (test_get_tcp_ao_counters(sk, begin))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(sk, begin))
+ test_error("test_get_tcp_counters()");
synchronize_threads(); /* 3: accepted => send data */
- if (test_get_tcp_ao_counters(lsk, &lsk_c2))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(lsk, &lsk_c2))
+ test_error("test_get_tcp_counters()");
verify_keys(tst_name, lsk, true, true);
close(lsk);
@@ -830,12 +830,12 @@ static int start_server(const char *tst_name, unsigned int port, size_t quota,
}
static void end_server(const char *tst_name, int sk,
- struct tcp_ao_counters *begin)
+ struct tcp_counters *begin)
{
- struct tcp_ao_counters end;
+ struct tcp_counters end;
- if (test_get_tcp_ao_counters(sk, &end))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(sk, &end))
+ test_error("test_get_tcp_counters()");
verify_keys(tst_name, sk, false, true);
synchronize_threads(); /* 4: verified => closed */
@@ -848,7 +848,7 @@ static void end_server(const char *tst_name, int sk,
static void try_server_run(const char *tst_name, unsigned int port, size_t quota,
unsigned int current_index, unsigned int rnext_index)
{
- struct tcp_ao_counters tmp;
+ struct tcp_counters tmp;
int sk;
sk = start_server(tst_name, port, quota, &tmp,
@@ -860,7 +860,7 @@ static void server_rotations(const char *tst_name, unsigned int port,
size_t quota, unsigned int rotations,
unsigned int current_index, unsigned int rnext_index)
{
- struct tcp_ao_counters tmp;
+ struct tcp_counters tmp;
unsigned int i;
int sk;
@@ -886,7 +886,7 @@ static void server_rotations(const char *tst_name, unsigned int port,
static int run_client(const char *tst_name, unsigned int port,
unsigned int nr_keys, int current_index, int rnext_index,
- struct tcp_ao_counters *before,
+ struct tcp_counters *before,
const size_t msg_sz, const size_t msg_nr)
{
int sk;
@@ -904,8 +904,8 @@ static int run_client(const char *tst_name, unsigned int port,
if (test_set_key(sk, sndid, rcvid))
test_error("failed to set current/rnext keys");
}
- if (before && test_get_tcp_ao_counters(sk, before))
- test_error("test_get_tcp_ao_counters()");
+ if (before && test_get_tcp_counters(sk, before))
+ test_error("test_get_tcp_counters()");
synchronize_threads(); /* 2: MKTs added => connect() */
if (test_connect_socket(sk, this_ip_dest, port++) <= 0)
@@ -918,11 +918,11 @@ static int run_client(const char *tst_name, unsigned int port,
collection.keys[rnext_index].used_on_server_tx = 1;
synchronize_threads(); /* 3: accepted => send data */
- if (test_client_verify(sk, msg_sz, msg_nr, TEST_TIMEOUT_SEC)) {
+ if (test_client_verify(sk, msg_sz, msg_nr)) {
test_fail("verify failed");
close(sk);
if (before)
- test_tcp_ao_counters_free(before);
+ test_tcp_counters_free(before);
return -1;
}
@@ -931,7 +931,7 @@ static int run_client(const char *tst_name, unsigned int port,
static int start_client(const char *tst_name, unsigned int port,
unsigned int nr_keys, int current_index, int rnext_index,
- struct tcp_ao_counters *before,
+ struct tcp_counters *before,
const size_t msg_sz, const size_t msg_nr)
{
if (init_default_key_collection(nr_keys, true))
@@ -943,9 +943,9 @@ static int start_client(const char *tst_name, unsigned int port,
static void end_client(const char *tst_name, int sk, unsigned int nr_keys,
int current_index, int rnext_index,
- struct tcp_ao_counters *start)
+ struct tcp_counters *start)
{
- struct tcp_ao_counters end;
+ struct tcp_counters end;
/* Some application may become dependent on this kernel choice */
if (current_index < 0)
@@ -955,8 +955,8 @@ static void end_client(const char *tst_name, int sk, unsigned int nr_keys,
verify_current_rnext(tst_name, sk,
collection.keys[current_index].client_keyid,
collection.keys[rnext_index].server_keyid);
- if (start && test_get_tcp_ao_counters(sk, &end))
- test_error("test_get_tcp_ao_counters()");
+ if (start && test_get_tcp_counters(sk, &end))
+ test_error("test_get_tcp_counters()");
verify_keys(tst_name, sk, false, false);
synchronize_threads(); /* 4: verify => closed */
close(sk);
@@ -1016,7 +1016,7 @@ static void try_unmatched_keys(int sk, int *rnext_index, unsigned int port)
trace_ao_event_expect(TCP_AO_RNEXT_REQUEST, this_ip_addr, this_ip_dest,
-1, port, 0, -1, -1, -1, -1, -1,
-1, key->server_keyid, -1);
- if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC))
+ if (test_client_verify(sk, msg_len, nr_packets))
test_fail("verify failed");
*rnext_index = i;
}
@@ -1048,7 +1048,7 @@ static void check_current_back(const char *tst_name, unsigned int port,
unsigned int current_index, unsigned int rnext_index,
unsigned int rotate_to_index)
{
- struct tcp_ao_counters tmp;
+ struct tcp_counters tmp;
int sk;
sk = start_client(tst_name, port, nr_keys, current_index, rnext_index,
@@ -1061,7 +1061,7 @@ static void check_current_back(const char *tst_name, unsigned int port,
port, -1, 0, -1, -1, -1, -1, -1,
collection.keys[rotate_to_index].client_keyid,
collection.keys[current_index].client_keyid, -1);
- if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC))
+ if (test_client_verify(sk, msg_len, nr_packets))
test_fail("verify failed");
/* There is a race here: between setting the current_key with
* setsockopt(TCP_AO_INFO) and starting to send some data - there
@@ -1081,7 +1081,7 @@ static void roll_over_keys(const char *tst_name, unsigned int port,
unsigned int nr_keys, unsigned int rotations,
unsigned int current_index, unsigned int rnext_index)
{
- struct tcp_ao_counters tmp;
+ struct tcp_counters tmp;
unsigned int i;
int sk;
@@ -1099,10 +1099,10 @@ static void roll_over_keys(const char *tst_name, unsigned int port,
collection.keys[i].server_keyid, -1);
if (test_set_key(sk, -1, collection.keys[i].server_keyid))
test_error("Can't change the Rnext key");
- if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC)) {
+ if (test_client_verify(sk, msg_len, nr_packets)) {
test_fail("verify failed");
close(sk);
- test_tcp_ao_counters_free(&tmp);
+ test_tcp_counters_free(&tmp);
return;
}
verify_current_rnext(tst_name, sk, -1,
@@ -1116,7 +1116,7 @@ static void roll_over_keys(const char *tst_name, unsigned int port,
static void try_client_run(const char *tst_name, unsigned int port,
unsigned int nr_keys, int current_index, int rnext_index)
{
- struct tcp_ao_counters tmp;
+ struct tcp_counters tmp;
int sk;
sk = start_client(tst_name, port, nr_keys, current_index, rnext_index,
diff --git a/tools/testing/selftests/net/tcp_ao/lib/aolib.h b/tools/testing/selftests/net/tcp_ao/lib/aolib.h
index 5db2f65cddc4..ebb2899c12fe 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/aolib.h
+++ b/tools/testing/selftests/net/tcp_ao/lib/aolib.h
@@ -289,7 +289,7 @@ extern int link_set_up(const char *intf);
extern const unsigned int test_server_port;
extern int test_wait_fd(int sk, time_t sec, bool write);
extern int __test_connect_socket(int sk, const char *device,
- void *addr, size_t addr_sz, time_t timeout);
+ void *addr, size_t addr_sz, bool async);
extern int __test_listen_socket(int backlog, void *addr, size_t addr_sz);
static inline int test_listen_socket(const union tcp_addr taddr,
@@ -331,25 +331,26 @@ static inline int test_listen_socket(const union tcp_addr taddr,
* If set to 0 - kernel will try to retransmit SYN number of times, set in
* /proc/sys/net/ipv4/tcp_syn_retries
* By default set to 1 to make tests pass faster on non-busy machine.
+ * [in process of removal, don't use in new tests]
*/
#ifndef TEST_RETRANSMIT_SEC
#define TEST_RETRANSMIT_SEC 1
#endif
static inline int _test_connect_socket(int sk, const union tcp_addr taddr,
- unsigned int port, time_t timeout)
+ unsigned int port, bool async)
{
sockaddr_af addr;
tcp_addr_to_sockaddr_in(&addr, &taddr, htons(port));
return __test_connect_socket(sk, veth_name,
- (void *)&addr, sizeof(addr), timeout);
+ (void *)&addr, sizeof(addr), async);
}
static inline int test_connect_socket(int sk, const union tcp_addr taddr,
unsigned int port)
{
- return _test_connect_socket(sk, taddr, port, TEST_TIMEOUT_SEC);
+ return _test_connect_socket(sk, taddr, port, false);
}
extern int __test_set_md5(int sk, void *addr, size_t addr_sz,
@@ -483,10 +484,7 @@ static inline int test_set_ao_flags(int sk, bool ao_required, bool accept_icmps)
}
extern ssize_t test_server_run(int sk, ssize_t quota, time_t timeout_sec);
-extern ssize_t test_client_loop(int sk, char *buf, size_t buf_sz,
- const size_t msg_len, time_t timeout_sec);
-extern int test_client_verify(int sk, const size_t msg_len, const size_t nr,
- time_t timeout_sec);
+extern int test_client_verify(int sk, const size_t msg_len, const size_t nr);
struct tcp_ao_key_counters {
uint8_t sndid;
@@ -512,7 +510,15 @@ struct tcp_ao_counters {
size_t nr_keys;
struct tcp_ao_key_counters *key_cnts;
};
-extern int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out);
+
+struct tcp_counters {
+ struct tcp_ao_counters ao;
+ uint64_t netns_md5_notfound;
+ uint64_t netns_md5_unexpected;
+ uint64_t netns_md5_failure;
+};
+
+extern int test_get_tcp_counters(int sk, struct tcp_counters *out);
#define TEST_CNT_KEY_GOOD BIT(0)
#define TEST_CNT_KEY_BAD BIT(1)
@@ -526,8 +532,31 @@ extern int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out);
#define TEST_CNT_NS_KEY_NOT_FOUND BIT(9)
#define TEST_CNT_NS_AO_REQUIRED BIT(10)
#define TEST_CNT_NS_DROPPED_ICMP BIT(11)
+#define TEST_CNT_NS_MD5_NOT_FOUND BIT(12)
+#define TEST_CNT_NS_MD5_UNEXPECTED BIT(13)
+#define TEST_CNT_NS_MD5_FAILURE BIT(14)
typedef uint16_t test_cnt;
+#define _for_each_counter(f) \
+do { \
+ /* per-netns */ \
+ f(ao.netns_ao_good, TEST_CNT_NS_GOOD); \
+ f(ao.netns_ao_bad, TEST_CNT_NS_BAD); \
+ f(ao.netns_ao_key_not_found, TEST_CNT_NS_KEY_NOT_FOUND); \
+ f(ao.netns_ao_required, TEST_CNT_NS_AO_REQUIRED); \
+ f(ao.netns_ao_dropped_icmp, TEST_CNT_NS_DROPPED_ICMP); \
+ /* per-socket */ \
+ f(ao.ao_info_pkt_good, TEST_CNT_SOCK_GOOD); \
+ f(ao.ao_info_pkt_bad, TEST_CNT_SOCK_BAD); \
+ f(ao.ao_info_pkt_key_not_found, TEST_CNT_SOCK_KEY_NOT_FOUND); \
+ f(ao.ao_info_pkt_ao_required, TEST_CNT_SOCK_AO_REQUIRED); \
+ f(ao.ao_info_pkt_dropped_icmp, TEST_CNT_SOCK_DROPPED_ICMP); \
+ /* non-AO */ \
+ f(netns_md5_notfound, TEST_CNT_NS_MD5_NOT_FOUND); \
+ f(netns_md5_unexpected, TEST_CNT_NS_MD5_UNEXPECTED); \
+ f(netns_md5_failure, TEST_CNT_NS_MD5_FAILURE); \
+} while (0)
+
#define TEST_CNT_AO_GOOD (TEST_CNT_SOCK_GOOD | TEST_CNT_NS_GOOD)
#define TEST_CNT_AO_BAD (TEST_CNT_SOCK_BAD | TEST_CNT_NS_BAD)
#define TEST_CNT_AO_KEY_NOT_FOUND (TEST_CNT_SOCK_KEY_NOT_FOUND | \
@@ -539,34 +568,71 @@ typedef uint16_t test_cnt;
#define TEST_CNT_GOOD (TEST_CNT_KEY_GOOD | TEST_CNT_AO_GOOD)
#define TEST_CNT_BAD (TEST_CNT_KEY_BAD | TEST_CNT_AO_BAD)
-extern int __test_tcp_ao_counters_cmp(const char *tst_name,
- struct tcp_ao_counters *before, struct tcp_ao_counters *after,
+extern test_cnt test_cmp_counters(struct tcp_counters *before,
+ struct tcp_counters *after);
+extern int test_assert_counters_sk(const char *tst_name,
+ struct tcp_counters *before, struct tcp_counters *after,
test_cnt expected);
-extern int test_tcp_ao_key_counters_cmp(const char *tst_name,
+extern int test_assert_counters_key(const char *tst_name,
struct tcp_ao_counters *before, struct tcp_ao_counters *after,
test_cnt expected, int sndid, int rcvid);
-extern void test_tcp_ao_counters_free(struct tcp_ao_counters *cnts);
+extern void test_tcp_counters_free(struct tcp_counters *cnts);
+
+/*
+ * Polling for netns and socket counters during select()/connect() and also
+ * client/server messaging. Instead of constant timeout on underlying select(),
+ * check the counters and return early. This allows to pass the tests where
+ * timeout is expected without waiting for that fixing timeout (tests speed-up).
+ * Previously shorter timeouts were used for tests expecting to time out,
+ * but that leaded to sporadic false positives on counter checks failures,
+ * as one second timeouts aren't enough for TCP retransmit.
+ *
+ * Two sides of the socketpair (client/server) should synchronize failures
+ * using a shared variable *err, so that they can detect the other side's
+ * failure.
+ */
+extern int test_skpair_wait_poll(int sk, bool write, test_cnt cond,
+ volatile int *err);
+extern int _test_skpair_connect_poll(int sk, const char *device,
+ void *addr, size_t addr_sz,
+ test_cnt cond, volatile int *err);
+static inline int test_skpair_connect_poll(int sk, const union tcp_addr taddr,
+ unsigned int port,
+ test_cnt cond, volatile int *err)
+{
+ sockaddr_af addr;
+
+ tcp_addr_to_sockaddr_in(&addr, &taddr, htons(port));
+ return _test_skpair_connect_poll(sk, veth_name,
+ (void *)&addr, sizeof(addr), cond, err);
+}
+
+extern int test_skpair_client(int sk, const size_t msg_len, const size_t nr,
+ test_cnt cond, volatile int *err);
+extern int test_skpair_server(int sk, ssize_t quota,
+ test_cnt cond, volatile int *err);
+
/*
- * Frees buffers allocated in test_get_tcp_ao_counters().
+ * Frees buffers allocated in test_get_tcp_counters().
* The function doesn't expect new keys or keys removed between calls
- * to test_get_tcp_ao_counters(). Check key counters manually if they
+ * to test_get_tcp_counters(). Check key counters manually if they
* may change.
*/
-static inline int test_tcp_ao_counters_cmp(const char *tst_name,
- struct tcp_ao_counters *before,
- struct tcp_ao_counters *after,
- test_cnt expected)
+static inline int test_assert_counters(const char *tst_name,
+ struct tcp_counters *before,
+ struct tcp_counters *after,
+ test_cnt expected)
{
int ret;
- ret = __test_tcp_ao_counters_cmp(tst_name, before, after, expected);
+ ret = test_assert_counters_sk(tst_name, before, after, expected);
if (ret)
goto out;
- ret = test_tcp_ao_key_counters_cmp(tst_name, before, after,
- expected, -1, -1);
+ ret = test_assert_counters_key(tst_name, &before->ao, &after->ao,
+ expected, -1, -1);
out:
- test_tcp_ao_counters_free(before);
- test_tcp_ao_counters_free(after);
+ test_tcp_counters_free(before);
+ test_tcp_counters_free(after);
return ret;
}
diff --git a/tools/testing/selftests/net/tcp_ao/lib/ftrace-tcp.c b/tools/testing/selftests/net/tcp_ao/lib/ftrace-tcp.c
index 24380c68fec6..27403f875054 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/ftrace-tcp.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/ftrace-tcp.c
@@ -427,11 +427,8 @@ static void dump_trace_event(struct expected_trace_point *e)
test_print("trace event filter %s [%s:%d => %s:%d, L3index %d, flags: %s%s%s%s%s, keyid: %d, rnext: %d, maclen: %d, sne: %d] = %zu",
trace_event_names[e->type],
src, e->src_port, dst, e->dst_port, e->L3index,
- (e->fin > 0) ? "F" : (e->fin == 0) ? "!F" : "",
- (e->syn > 0) ? "S" : (e->syn == 0) ? "!S" : "",
- (e->rst > 0) ? "R" : (e->rst == 0) ? "!R" : "",
- (e->psh > 0) ? "P" : (e->psh == 0) ? "!P" : "",
- (e->ack > 0) ? "." : (e->ack == 0) ? "!." : "",
+ e->fin ? "F" : "", e->syn ? "S" : "", e->rst ? "R" : "",
+ e->psh ? "P" : "", e->ack ? "." : "",
e->keyid, e->rnext, e->maclen, e->sne, e->matched);
}
diff --git a/tools/testing/selftests/net/tcp_ao/lib/sock.c b/tools/testing/selftests/net/tcp_ao/lib/sock.c
index 0ffda966c677..ef8e9031d47a 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/sock.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/sock.c
@@ -34,10 +34,8 @@ int __test_listen_socket(int backlog, void *addr, size_t addr_sz)
return sk;
}
-int test_wait_fd(int sk, time_t sec, bool write)
+static int __test_wait_fd(int sk, struct timeval *tv, bool write)
{
- struct timeval tv = { .tv_sec = sec };
- struct timeval *ptv = NULL;
fd_set fds, efds;
int ret;
socklen_t slen = sizeof(ret);
@@ -47,14 +45,11 @@ int test_wait_fd(int sk, time_t sec, bool write)
FD_ZERO(&efds);
FD_SET(sk, &efds);
- if (sec)
- ptv = &tv;
-
errno = 0;
if (write)
- ret = select(sk + 1, NULL, &fds, &efds, ptv);
+ ret = select(sk + 1, NULL, &fds, &efds, tv);
else
- ret = select(sk + 1, &fds, NULL, &efds, ptv);
+ ret = select(sk + 1, &fds, NULL, &efds, tv);
if (ret < 0)
return -errno;
if (ret == 0) {
@@ -69,8 +64,54 @@ int test_wait_fd(int sk, time_t sec, bool write)
return 0;
}
+int test_wait_fd(int sk, time_t sec, bool write)
+{
+ struct timeval tv = { .tv_sec = sec, };
+
+ return __test_wait_fd(sk, sec ? &tv : NULL, write);
+}
+
+static bool __skpair_poll_should_stop(int sk, struct tcp_counters *c,
+ test_cnt condition)
+{
+ struct tcp_counters c2;
+ test_cnt diff;
+
+ if (test_get_tcp_counters(sk, &c2))
+ test_error("test_get_tcp_counters()");
+
+ diff = test_cmp_counters(c, &c2);
+ test_tcp_counters_free(&c2);
+ return (diff & condition) == condition;
+}
+
+/* How often wake up and check netns counters & paired (*err) */
+#define POLL_USEC 150
+static int __test_skpair_poll(int sk, bool write, uint64_t timeout,
+ struct tcp_counters *c, test_cnt cond,
+ volatile int *err)
+{
+ uint64_t t;
+
+ for (t = 0; t <= timeout * 1000000; t += POLL_USEC) {
+ struct timeval tv = { .tv_usec = POLL_USEC, };
+ int ret;
+
+ ret = __test_wait_fd(sk, &tv, write);
+ if (ret != -ETIMEDOUT)
+ return ret;
+ if (c && cond && __skpair_poll_should_stop(sk, c, cond))
+ break;
+ if (err && *err)
+ return *err;
+ }
+ if (err)
+ *err = -ETIMEDOUT;
+ return -ETIMEDOUT;
+}
+
int __test_connect_socket(int sk, const char *device,
- void *addr, size_t addr_sz, time_t timeout)
+ void *addr, size_t addr_sz, bool async)
{
long flags;
int err;
@@ -82,15 +123,6 @@ int __test_connect_socket(int sk, const char *device,
test_error("setsockopt(SO_BINDTODEVICE, %s)", device);
}
- if (!timeout) {
- err = connect(sk, addr, addr_sz);
- if (err) {
- err = -errno;
- goto out;
- }
- return 0;
- }
-
flags = fcntl(sk, F_GETFL);
if ((flags < 0) || (fcntl(sk, F_SETFL, flags | O_NONBLOCK) < 0))
test_error("fcntl()");
@@ -100,9 +132,9 @@ int __test_connect_socket(int sk, const char *device,
err = -errno;
goto out;
}
- if (timeout < 0)
+ if (async)
return sk;
- err = test_wait_fd(sk, timeout, 1);
+ err = test_wait_fd(sk, TEST_TIMEOUT_SEC, 1);
if (err)
goto out;
}
@@ -113,6 +145,45 @@ out:
return err;
}
+int test_skpair_wait_poll(int sk, bool write,
+ test_cnt cond, volatile int *err)
+{
+ struct tcp_counters c;
+ int ret;
+
+ *err = 0;
+ if (test_get_tcp_counters(sk, &c))
+ test_error("test_get_tcp_counters()");
+ synchronize_threads(); /* 1: init skpair & read nscounters */
+
+ ret = __test_skpair_poll(sk, write, TEST_TIMEOUT_SEC, &c, cond, err);
+ test_tcp_counters_free(&c);
+ return ret;
+}
+
+int _test_skpair_connect_poll(int sk, const char *device,
+ void *addr, size_t addr_sz,
+ test_cnt condition, volatile int *err)
+{
+ struct tcp_counters c;
+ int ret;
+
+ *err = 0;
+ if (test_get_tcp_counters(sk, &c))
+ test_error("test_get_tcp_counters()");
+ synchronize_threads(); /* 1: init skpair & read nscounters */
+ ret = __test_connect_socket(sk, device, addr, addr_sz, true);
+ if (ret < 0) {
+ test_tcp_counters_free(&c);
+ return (*err = ret);
+ }
+ ret = __test_skpair_poll(sk, 1, TEST_TIMEOUT_SEC, &c, condition, err);
+ if (ret < 0)
+ close(sk);
+ test_tcp_counters_free(&c);
+ return ret;
+}
+
int __test_set_md5(int sk, void *addr, size_t addr_sz, uint8_t prefix,
int vrf, const char *password)
{
@@ -333,12 +404,12 @@ do { \
return 0;
}
-int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out)
+int test_get_tcp_counters(int sk, struct tcp_counters *out)
{
struct tcp_ao_getsockopt *key_dump;
socklen_t key_dump_sz = sizeof(*key_dump);
struct tcp_ao_info_opt info = {};
- bool c1, c2, c3, c4, c5;
+ bool c1, c2, c3, c4, c5, c6, c7, c8;
struct netstat *ns;
int err, nr_keys;
@@ -346,25 +417,30 @@ int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out)
/* per-netns */
ns = netstat_read();
- out->netns_ao_good = netstat_get(ns, "TCPAOGood", &c1);
- out->netns_ao_bad = netstat_get(ns, "TCPAOBad", &c2);
- out->netns_ao_key_not_found = netstat_get(ns, "TCPAOKeyNotFound", &c3);
- out->netns_ao_required = netstat_get(ns, "TCPAORequired", &c4);
- out->netns_ao_dropped_icmp = netstat_get(ns, "TCPAODroppedIcmps", &c5);
+ out->ao.netns_ao_good = netstat_get(ns, "TCPAOGood", &c1);
+ out->ao.netns_ao_bad = netstat_get(ns, "TCPAOBad", &c2);
+ out->ao.netns_ao_key_not_found = netstat_get(ns, "TCPAOKeyNotFound", &c3);
+ out->ao.netns_ao_required = netstat_get(ns, "TCPAORequired", &c4);
+ out->ao.netns_ao_dropped_icmp = netstat_get(ns, "TCPAODroppedIcmps", &c5);
+ out->netns_md5_notfound = netstat_get(ns, "TCPMD5NotFound", &c6);
+ out->netns_md5_unexpected = netstat_get(ns, "TCPMD5Unexpected", &c7);
+ out->netns_md5_failure = netstat_get(ns, "TCPMD5Failure", &c8);
netstat_free(ns);
- if (c1 || c2 || c3 || c4 || c5)
+ if (c1 || c2 || c3 || c4 || c5 || c6 || c7 || c8)
return -EOPNOTSUPP;
err = test_get_ao_info(sk, &info);
+ if (err == -ENOENT)
+ return 0;
if (err)
return err;
/* per-socket */
- out->ao_info_pkt_good = info.pkt_good;
- out->ao_info_pkt_bad = info.pkt_bad;
- out->ao_info_pkt_key_not_found = info.pkt_key_not_found;
- out->ao_info_pkt_ao_required = info.pkt_ao_required;
- out->ao_info_pkt_dropped_icmp = info.pkt_dropped_icmp;
+ out->ao.ao_info_pkt_good = info.pkt_good;
+ out->ao.ao_info_pkt_bad = info.pkt_bad;
+ out->ao.ao_info_pkt_key_not_found = info.pkt_key_not_found;
+ out->ao.ao_info_pkt_ao_required = info.pkt_ao_required;
+ out->ao.ao_info_pkt_dropped_icmp = info.pkt_dropped_icmp;
/* per-key */
nr_keys = test_get_ao_keys_nr(sk);
@@ -372,7 +448,7 @@ int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out)
return nr_keys;
if (nr_keys == 0)
test_error("test_get_ao_keys_nr() == 0");
- out->nr_keys = (size_t)nr_keys;
+ out->ao.nr_keys = (size_t)nr_keys;
key_dump = calloc(nr_keys, key_dump_sz);
if (!key_dump)
return -errno;
@@ -386,72 +462,84 @@ int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out)
return -errno;
}
- out->key_cnts = calloc(nr_keys, sizeof(out->key_cnts[0]));
- if (!out->key_cnts) {
+ out->ao.key_cnts = calloc(nr_keys, sizeof(out->ao.key_cnts[0]));
+ if (!out->ao.key_cnts) {
free(key_dump);
return -errno;
}
while (nr_keys--) {
- out->key_cnts[nr_keys].sndid = key_dump[nr_keys].sndid;
- out->key_cnts[nr_keys].rcvid = key_dump[nr_keys].rcvid;
- out->key_cnts[nr_keys].pkt_good = key_dump[nr_keys].pkt_good;
- out->key_cnts[nr_keys].pkt_bad = key_dump[nr_keys].pkt_bad;
+ out->ao.key_cnts[nr_keys].sndid = key_dump[nr_keys].sndid;
+ out->ao.key_cnts[nr_keys].rcvid = key_dump[nr_keys].rcvid;
+ out->ao.key_cnts[nr_keys].pkt_good = key_dump[nr_keys].pkt_good;
+ out->ao.key_cnts[nr_keys].pkt_bad = key_dump[nr_keys].pkt_bad;
}
free(key_dump);
return 0;
}
-int __test_tcp_ao_counters_cmp(const char *tst_name,
- struct tcp_ao_counters *before,
- struct tcp_ao_counters *after,
- test_cnt expected)
+test_cnt test_cmp_counters(struct tcp_counters *before,
+ struct tcp_counters *after)
+{
+#define __cmp(cnt, e_cnt) \
+do { \
+ if (before->cnt > after->cnt) \
+ test_error("counter " __stringify(cnt) " decreased"); \
+ if (before->cnt != after->cnt) \
+ ret |= e_cnt; \
+} while (0)
+
+ test_cnt ret = 0;
+ size_t i;
+
+ if (before->ao.nr_keys != after->ao.nr_keys)
+ test_error("the number of keys has changed");
+
+ _for_each_counter(__cmp);
+
+ i = before->ao.nr_keys;
+ while (i--) {
+ __cmp(ao.key_cnts[i].pkt_good, TEST_CNT_KEY_GOOD);
+ __cmp(ao.key_cnts[i].pkt_bad, TEST_CNT_KEY_BAD);
+ }
+#undef __cmp
+ return ret;
+}
+
+int test_assert_counters_sk(const char *tst_name,
+ struct tcp_counters *before,
+ struct tcp_counters *after,
+ test_cnt expected)
{
-#define __cmp_ao(cnt, expecting_inc) \
+#define __cmp_ao(cnt, e_cnt) \
do { \
if (before->cnt > after->cnt) { \
test_fail("%s: Decreased counter " __stringify(cnt) " %" PRIu64 " > %" PRIu64, \
- tst_name ?: "", before->cnt, after->cnt); \
+ tst_name ?: "", before->cnt, after->cnt); \
return -1; \
} \
- if ((before->cnt != after->cnt) != (expecting_inc)) { \
+ if ((before->cnt != after->cnt) != !!(expected & e_cnt)) { \
test_fail("%s: Counter " __stringify(cnt) " was %sexpected to increase %" PRIu64 " => %" PRIu64, \
- tst_name ?: "", (expecting_inc) ? "" : "not ", \
+ tst_name ?: "", (expected & e_cnt) ? "" : "not ", \
before->cnt, after->cnt); \
return -1; \
} \
-} while(0)
+} while (0)
errno = 0;
- /* per-netns */
- __cmp_ao(netns_ao_good, !!(expected & TEST_CNT_NS_GOOD));
- __cmp_ao(netns_ao_bad, !!(expected & TEST_CNT_NS_BAD));
- __cmp_ao(netns_ao_key_not_found,
- !!(expected & TEST_CNT_NS_KEY_NOT_FOUND));
- __cmp_ao(netns_ao_required, !!(expected & TEST_CNT_NS_AO_REQUIRED));
- __cmp_ao(netns_ao_dropped_icmp,
- !!(expected & TEST_CNT_NS_DROPPED_ICMP));
- /* per-socket */
- __cmp_ao(ao_info_pkt_good, !!(expected & TEST_CNT_SOCK_GOOD));
- __cmp_ao(ao_info_pkt_bad, !!(expected & TEST_CNT_SOCK_BAD));
- __cmp_ao(ao_info_pkt_key_not_found,
- !!(expected & TEST_CNT_SOCK_KEY_NOT_FOUND));
- __cmp_ao(ao_info_pkt_ao_required, !!(expected & TEST_CNT_SOCK_AO_REQUIRED));
- __cmp_ao(ao_info_pkt_dropped_icmp,
- !!(expected & TEST_CNT_SOCK_DROPPED_ICMP));
+ _for_each_counter(__cmp_ao);
return 0;
#undef __cmp_ao
}
-int test_tcp_ao_key_counters_cmp(const char *tst_name,
- struct tcp_ao_counters *before,
- struct tcp_ao_counters *after,
- test_cnt expected,
- int sndid, int rcvid)
+int test_assert_counters_key(const char *tst_name,
+ struct tcp_ao_counters *before,
+ struct tcp_ao_counters *after,
+ test_cnt expected, int sndid, int rcvid)
{
size_t i;
-#define __cmp_ao(i, cnt, expecting_inc) \
+#define __cmp_ao(i, cnt, e_cnt) \
do { \
if (before->key_cnts[i].cnt > after->key_cnts[i].cnt) { \
test_fail("%s: Decreased counter " __stringify(cnt) " %" PRIu64 " > %" PRIu64 " for key %u:%u", \
@@ -461,16 +549,16 @@ do { \
before->key_cnts[i].rcvid); \
return -1; \
} \
- if ((before->key_cnts[i].cnt != after->key_cnts[i].cnt) != (expecting_inc)) { \
+ if ((before->key_cnts[i].cnt != after->key_cnts[i].cnt) != !!(expected & e_cnt)) { \
test_fail("%s: Counter " __stringify(cnt) " was %sexpected to increase %" PRIu64 " => %" PRIu64 " for key %u:%u", \
- tst_name ?: "", (expecting_inc) ? "" : "not ",\
+ tst_name ?: "", (expected & e_cnt) ? "" : "not ",\
before->key_cnts[i].cnt, \
after->key_cnts[i].cnt, \
before->key_cnts[i].sndid, \
before->key_cnts[i].rcvid); \
return -1; \
} \
-} while(0)
+} while (0)
if (before->nr_keys != after->nr_keys) {
test_fail("%s: Keys changed on the socket %zu != %zu",
@@ -485,20 +573,22 @@ do { \
continue;
if (rcvid >= 0 && before->key_cnts[i].rcvid != rcvid)
continue;
- __cmp_ao(i, pkt_good, !!(expected & TEST_CNT_KEY_GOOD));
- __cmp_ao(i, pkt_bad, !!(expected & TEST_CNT_KEY_BAD));
+ __cmp_ao(i, pkt_good, TEST_CNT_KEY_GOOD);
+ __cmp_ao(i, pkt_bad, TEST_CNT_KEY_BAD);
}
return 0;
#undef __cmp_ao
}
-void test_tcp_ao_counters_free(struct tcp_ao_counters *cnts)
+void test_tcp_counters_free(struct tcp_counters *cnts)
{
- free(cnts->key_cnts);
+ free(cnts->ao.key_cnts);
}
#define TEST_BUF_SIZE 4096
-ssize_t test_server_run(int sk, ssize_t quota, time_t timeout_sec)
+static ssize_t _test_server_run(int sk, ssize_t quota, struct tcp_counters *c,
+ test_cnt cond, volatile int *err,
+ time_t timeout_sec)
{
ssize_t total = 0;
@@ -507,7 +597,7 @@ ssize_t test_server_run(int sk, ssize_t quota, time_t timeout_sec)
ssize_t bytes, sent;
int ret;
- ret = test_wait_fd(sk, timeout_sec, 0);
+ ret = __test_skpair_poll(sk, 0, timeout_sec, c, cond, err);
if (ret)
return ret;
@@ -518,7 +608,7 @@ ssize_t test_server_run(int sk, ssize_t quota, time_t timeout_sec)
if (bytes == 0)
break;
- ret = test_wait_fd(sk, timeout_sec, 1);
+ ret = __test_skpair_poll(sk, 1, timeout_sec, c, cond, err);
if (ret)
return ret;
@@ -533,13 +623,41 @@ ssize_t test_server_run(int sk, ssize_t quota, time_t timeout_sec)
return total;
}
-ssize_t test_client_loop(int sk, char *buf, size_t buf_sz,
- const size_t msg_len, time_t timeout_sec)
+ssize_t test_server_run(int sk, ssize_t quota, time_t timeout_sec)
+{
+ return _test_server_run(sk, quota, NULL, 0, NULL,
+ timeout_sec ?: TEST_TIMEOUT_SEC);
+}
+
+int test_skpair_server(int sk, ssize_t quota, test_cnt cond, volatile int *err)
+{
+ struct tcp_counters c;
+ ssize_t ret;
+
+ *err = 0;
+ if (test_get_tcp_counters(sk, &c))
+ test_error("test_get_tcp_counters()");
+ synchronize_threads(); /* 1: init skpair & read nscounters */
+
+ ret = _test_server_run(sk, quota, &c, cond, err, TEST_TIMEOUT_SEC);
+ test_tcp_counters_free(&c);
+ return ret;
+}
+
+static ssize_t test_client_loop(int sk, size_t buf_sz, const size_t msg_len,
+ struct tcp_counters *c, test_cnt cond,
+ volatile int *err)
{
char msg[msg_len];
int nodelay = 1;
+ char *buf;
size_t i;
+ buf = alloca(buf_sz);
+ if (!buf)
+ return -ENOMEM;
+ randomize_buffer(buf, buf_sz);
+
if (setsockopt(sk, IPPROTO_TCP, TCP_NODELAY, &nodelay, sizeof(nodelay)))
test_error("setsockopt(TCP_NODELAY)");
@@ -547,7 +665,7 @@ ssize_t test_client_loop(int sk, char *buf, size_t buf_sz,
size_t sent, bytes = min(msg_len, buf_sz - i);
int ret;
- ret = test_wait_fd(sk, timeout_sec, 1);
+ ret = __test_skpair_poll(sk, 1, TEST_TIMEOUT_SEC, c, cond, err);
if (ret)
return ret;
@@ -561,7 +679,8 @@ ssize_t test_client_loop(int sk, char *buf, size_t buf_sz,
do {
ssize_t got;
- ret = test_wait_fd(sk, timeout_sec, 0);
+ ret = __test_skpair_poll(sk, 0, TEST_TIMEOUT_SEC,
+ c, cond, err);
if (ret)
return ret;
@@ -580,15 +699,31 @@ ssize_t test_client_loop(int sk, char *buf, size_t buf_sz,
return i;
}
-int test_client_verify(int sk, const size_t msg_len, const size_t nr,
- time_t timeout_sec)
+int test_client_verify(int sk, const size_t msg_len, const size_t nr)
{
size_t buf_sz = msg_len * nr;
- char *buf = alloca(buf_sz);
ssize_t ret;
- randomize_buffer(buf, buf_sz);
- ret = test_client_loop(sk, buf, buf_sz, msg_len, timeout_sec);
+ ret = test_client_loop(sk, buf_sz, msg_len, NULL, 0, NULL);
+ if (ret < 0)
+ return (int)ret;
+ return ret != buf_sz ? -1 : 0;
+}
+
+int test_skpair_client(int sk, const size_t msg_len, const size_t nr,
+ test_cnt cond, volatile int *err)
+{
+ struct tcp_counters c;
+ size_t buf_sz = msg_len * nr;
+ ssize_t ret;
+
+ *err = 0;
+ if (test_get_tcp_counters(sk, &c))
+ test_error("test_get_tcp_counters()");
+ synchronize_threads(); /* 1: init skpair & read nscounters */
+
+ ret = test_client_loop(sk, buf_sz, msg_len, &c, cond, err);
+ test_tcp_counters_free(&c);
if (ret < 0)
return (int)ret;
return ret != buf_sz ? -1 : 0;
diff --git a/tools/testing/selftests/net/tcp_ao/restore.c b/tools/testing/selftests/net/tcp_ao/restore.c
index ecc6f1e3a414..9a059b6c4523 100644
--- a/tools/testing/selftests/net/tcp_ao/restore.c
+++ b/tools/testing/selftests/net/tcp_ao/restore.c
@@ -16,11 +16,11 @@ const size_t quota = nr_packets * msg_len;
static void try_server_run(const char *tst_name, unsigned int port,
fault_t inj, test_cnt cnt_expected)
{
+ test_cnt poll_cnt = (cnt_expected == TEST_CNT_GOOD) ? 0 : cnt_expected;
const char *cnt_name = "TCPAOGood";
- struct tcp_ao_counters ao1, ao2;
+ struct tcp_counters cnt1, cnt2;
uint64_t before_cnt, after_cnt;
- int sk, lsk;
- time_t timeout;
+ int sk, lsk, dummy;
ssize_t bytes;
if (fault(TIMEOUT))
@@ -48,11 +48,10 @@ static void try_server_run(const char *tst_name, unsigned int port,
}
before_cnt = netstat_get_one(cnt_name, NULL);
- if (test_get_tcp_ao_counters(sk, &ao1))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(sk, &cnt1))
+ test_error("test_get_tcp_counters()");
- timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
- bytes = test_server_run(sk, quota, timeout);
+ bytes = test_skpair_server(sk, quota, poll_cnt, &dummy);
if (fault(TIMEOUT)) {
if (bytes > 0)
test_fail("%s: server served: %zd", tst_name, bytes);
@@ -65,17 +64,17 @@ static void try_server_run(const char *tst_name, unsigned int port,
test_ok("%s: server alive", tst_name);
}
synchronize_threads(); /* 3: counters checks */
- if (test_get_tcp_ao_counters(sk, &ao2))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(sk, &cnt2))
+ test_error("test_get_tcp_counters()");
after_cnt = netstat_get_one(cnt_name, NULL);
- test_tcp_ao_counters_cmp(tst_name, &ao1, &ao2, cnt_expected);
+ test_assert_counters(tst_name, &cnt1, &cnt2, cnt_expected);
if (after_cnt <= before_cnt) {
- test_fail("%s: %s counter did not increase: %" PRIu64 " <= %" PRIu64,
- tst_name, cnt_name, after_cnt, before_cnt);
+ test_fail("%s(server): %s counter did not increase: %" PRIu64 " <= %" PRIu64,
+ tst_name, cnt_name, after_cnt, before_cnt);
} else {
- test_ok("%s: counter %s increased %" PRIu64 " => %" PRIu64,
+ test_ok("%s(server): counter %s increased %" PRIu64 " => %" PRIu64,
tst_name, cnt_name, before_cnt, after_cnt);
}
@@ -92,16 +91,16 @@ static void *server_fn(void *arg)
{
unsigned int port = test_server_port;
- try_server_run("TCP-AO migrate to another socket", port++,
+ try_server_run("TCP-AO migrate to another socket (server)", port++,
0, TEST_CNT_GOOD);
- try_server_run("TCP-AO with wrong send ISN", port++,
+ try_server_run("TCP-AO with wrong send ISN (server)", port++,
FAULT_TIMEOUT, TEST_CNT_BAD);
- try_server_run("TCP-AO with wrong receive ISN", port++,
+ try_server_run("TCP-AO with wrong receive ISN (server)", port++,
FAULT_TIMEOUT, TEST_CNT_BAD);
- try_server_run("TCP-AO with wrong send SEQ ext number", port++,
+ try_server_run("TCP-AO with wrong send SEQ ext number (server)", port++,
FAULT_TIMEOUT, TEST_CNT_BAD);
- try_server_run("TCP-AO with wrong receive SEQ ext number", port++,
- FAULT_TIMEOUT, TEST_CNT_NS_BAD | TEST_CNT_GOOD);
+ try_server_run("TCP-AO with wrong receive SEQ ext number (server)",
+ port++, FAULT_TIMEOUT, TEST_CNT_NS_BAD | TEST_CNT_GOOD);
synchronize_threads(); /* don't race to exit: client exits */
return NULL;
@@ -125,7 +124,7 @@ static void test_get_sk_checkpoint(unsigned int server_port, sockaddr_af *saddr,
test_error("failed to connect()");
synchronize_threads(); /* 2: accepted => send data */
- if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC))
+ if (test_client_verify(sk, msg_len, nr_packets))
test_fail("pre-migrate verify failed");
test_enable_repair(sk);
@@ -139,11 +138,11 @@ static void test_sk_restore(const char *tst_name, unsigned int server_port,
struct tcp_ao_repair *ao_img,
fault_t inj, test_cnt cnt_expected)
{
+ test_cnt poll_cnt = (cnt_expected == TEST_CNT_GOOD) ? 0 : cnt_expected;
const char *cnt_name = "TCPAOGood";
- struct tcp_ao_counters ao1, ao2;
+ struct tcp_counters cnt1, cnt2;
uint64_t before_cnt, after_cnt;
- time_t timeout;
- int sk;
+ int sk, dummy;
if (fault(TIMEOUT))
cnt_name = "TCPAOBad";
@@ -159,30 +158,30 @@ static void test_sk_restore(const char *tst_name, unsigned int server_port,
test_error("setsockopt(TCP_AO_ADD_KEY)");
test_ao_restore(sk, ao_img);
- if (test_get_tcp_ao_counters(sk, &ao1))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(sk, &cnt1))
+ test_error("test_get_tcp_counters()");
test_disable_repair(sk);
test_sock_state_free(img);
- timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
- if (test_client_verify(sk, msg_len, nr_packets, timeout)) {
+ if (test_skpair_client(sk, msg_len, nr_packets, poll_cnt, &dummy)) {
if (fault(TIMEOUT))
test_ok("%s: post-migrate connection is broken", tst_name);
else
test_fail("%s: post-migrate connection is working", tst_name);
} else {
if (fault(TIMEOUT))
- test_fail("%s: post-migrate connection still working", tst_name);
+ test_fail("%s: post-migrate connection is working", tst_name);
else
test_ok("%s: post-migrate connection is alive", tst_name);
}
+
synchronize_threads(); /* 3: counters checks */
- if (test_get_tcp_ao_counters(sk, &ao2))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(sk, &cnt2))
+ test_error("test_get_tcp_counters()");
after_cnt = netstat_get_one(cnt_name, NULL);
- test_tcp_ao_counters_cmp(tst_name, &ao1, &ao2, cnt_expected);
+ test_assert_counters(tst_name, &cnt1, &cnt2, cnt_expected);
if (after_cnt <= before_cnt) {
test_fail("%s: %s counter did not increase: %" PRIu64 " <= %" PRIu64,
@@ -203,7 +202,7 @@ static void *client_fn(void *arg)
sockaddr_af saddr;
test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img);
- test_sk_restore("TCP-AO migrate to another socket", port++,
+ test_sk_restore("TCP-AO migrate to another socket (client)", port++,
&saddr, &tcp_img, &ao_img, 0, TEST_CNT_GOOD);
test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img);
@@ -212,7 +211,7 @@ static void *client_fn(void *arg)
-1, port, 0, -1, -1, -1, -1, -1, 100, 100, -1);
trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_dest, this_ip_addr,
port, -1, 0, -1, -1, -1, -1, -1, 100, 100, -1);
- test_sk_restore("TCP-AO with wrong send ISN", port++,
+ test_sk_restore("TCP-AO with wrong send ISN (client)", port++,
&saddr, &tcp_img, &ao_img, FAULT_TIMEOUT, TEST_CNT_BAD);
test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img);
@@ -221,7 +220,7 @@ static void *client_fn(void *arg)
-1, port, 0, -1, -1, -1, -1, -1, 100, 100, -1);
trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_dest, this_ip_addr,
port, -1, 0, -1, -1, -1, -1, -1, 100, 100, -1);
- test_sk_restore("TCP-AO with wrong receive ISN", port++,
+ test_sk_restore("TCP-AO with wrong receive ISN (client)", port++,
&saddr, &tcp_img, &ao_img, FAULT_TIMEOUT, TEST_CNT_BAD);
test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img);
@@ -229,8 +228,8 @@ static void *client_fn(void *arg)
trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_addr, this_ip_dest,
-1, port, 0, -1, -1, -1, -1, -1, 100, 100, -1);
/* not expecting server => client mismatches as only snd sne is broken */
- test_sk_restore("TCP-AO with wrong send SEQ ext number", port++,
- &saddr, &tcp_img, &ao_img, FAULT_TIMEOUT,
+ test_sk_restore("TCP-AO with wrong send SEQ ext number (client)",
+ port++, &saddr, &tcp_img, &ao_img, FAULT_TIMEOUT,
TEST_CNT_NS_BAD | TEST_CNT_GOOD);
test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img);
@@ -238,8 +237,8 @@ static void *client_fn(void *arg)
/* not expecting client => server mismatches as only rcv sne is broken */
trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_dest, this_ip_addr,
port, -1, 0, -1, -1, -1, -1, -1, 100, 100, -1);
- test_sk_restore("TCP-AO with wrong receive SEQ ext number", port++,
- &saddr, &tcp_img, &ao_img, FAULT_TIMEOUT,
+ test_sk_restore("TCP-AO with wrong receive SEQ ext number (client)",
+ port++, &saddr, &tcp_img, &ao_img, FAULT_TIMEOUT,
TEST_CNT_NS_GOOD | TEST_CNT_BAD);
return NULL;
diff --git a/tools/testing/selftests/net/tcp_ao/rst.c b/tools/testing/selftests/net/tcp_ao/rst.c
index 6364facaa63e..883cddf377cf 100644
--- a/tools/testing/selftests/net/tcp_ao/rst.c
+++ b/tools/testing/selftests/net/tcp_ao/rst.c
@@ -84,15 +84,15 @@ static void close_forced(int sk)
static void test_server_active_rst(unsigned int port)
{
- struct tcp_ao_counters cnt1, cnt2;
+ struct tcp_counters cnt1, cnt2;
ssize_t bytes;
int sk, lsk;
lsk = test_listen_socket(this_ip_addr, port, backlog);
if (test_add_key(lsk, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 100, 100))
test_error("setsockopt(TCP_AO_ADD_KEY)");
- if (test_get_tcp_ao_counters(lsk, &cnt1))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(lsk, &cnt1))
+ test_error("test_get_tcp_counters()");
synchronize_threads(); /* 1: MKT added */
if (test_wait_fd(lsk, TEST_TIMEOUT_SEC, 0))
@@ -103,8 +103,8 @@ static void test_server_active_rst(unsigned int port)
test_error("accept()");
synchronize_threads(); /* 2: connection accept()ed, another queued */
- if (test_get_tcp_ao_counters(lsk, &cnt2))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(lsk, &cnt2))
+ test_error("test_get_tcp_counters()");
synchronize_threads(); /* 3: close listen socket */
close(lsk);
@@ -120,7 +120,7 @@ static void test_server_active_rst(unsigned int port)
synchronize_threads(); /* 5: closed active sk */
synchronize_threads(); /* 6: counters checks */
- if (test_tcp_ao_counters_cmp("active RST server", &cnt1, &cnt2, TEST_CNT_GOOD))
+ if (test_assert_counters("active RST server", &cnt1, &cnt2, TEST_CNT_GOOD))
test_fail("MKT counters (server) have not only good packets");
else
test_ok("MKT counters are good on server");
@@ -128,7 +128,7 @@ static void test_server_active_rst(unsigned int port)
static void test_server_passive_rst(unsigned int port)
{
- struct tcp_ao_counters ao1, ao2;
+ struct tcp_counters cnt1, cnt2;
int sk, lsk;
ssize_t bytes;
@@ -147,8 +147,8 @@ static void test_server_passive_rst(unsigned int port)
synchronize_threads(); /* 2: accepted => send data */
close(lsk);
- if (test_get_tcp_ao_counters(sk, &ao1))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(sk, &cnt1))
+ test_error("test_get_tcp_counters()");
bytes = test_server_run(sk, quota, TEST_TIMEOUT_SEC);
if (bytes != quota) {
@@ -160,12 +160,12 @@ static void test_server_passive_rst(unsigned int port)
synchronize_threads(); /* 3: checkpoint the client */
synchronize_threads(); /* 4: close the server, creating twsk */
- if (test_get_tcp_ao_counters(sk, &ao2))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(sk, &cnt2))
+ test_error("test_get_tcp_counters()");
close(sk);
synchronize_threads(); /* 5: restore the socket, send more data */
- test_tcp_ao_counters_cmp("passive RST server", &ao1, &ao2, TEST_CNT_GOOD);
+ test_assert_counters("passive RST server", &cnt1, &cnt2, TEST_CNT_GOOD);
synchronize_threads(); /* 6: server exits */
}
@@ -271,8 +271,7 @@ static void test_client_active_rst(unsigned int port)
synchronize_threads(); /* 1: MKT added */
for (i = 0; i < last; i++) {
- err = _test_connect_socket(sk[i], this_ip_dest, port,
- (i == 0) ? TEST_TIMEOUT_SEC : -1);
+ err = _test_connect_socket(sk[i], this_ip_dest, port, i != 0);
if (err < 0)
test_error("failed to connect()");
}
@@ -283,12 +282,12 @@ static void test_client_active_rst(unsigned int port)
test_error("test_wait_fds(): %d", err);
/* async connect() with third sk to get into request_sock_queue */
- err = _test_connect_socket(sk[last], this_ip_dest, port, -1);
+ err = _test_connect_socket(sk[last], this_ip_dest, port, 1);
if (err < 0)
test_error("failed to connect()");
synchronize_threads(); /* 3: close listen socket */
- if (test_client_verify(sk[0], packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC))
+ if (test_client_verify(sk[0], packet_sz, quota / packet_sz))
test_fail("Failed to send data on connected socket");
else
test_ok("Verified established tcp connection");
@@ -323,7 +322,7 @@ static void test_client_active_rst(unsigned int port)
static void test_client_passive_rst(unsigned int port)
{
- struct tcp_ao_counters ao1, ao2;
+ struct tcp_counters cnt1, cnt2;
struct tcp_ao_repair ao_img;
struct tcp_sock_state img;
sockaddr_af saddr;
@@ -341,7 +340,7 @@ static void test_client_passive_rst(unsigned int port)
test_error("failed to connect()");
synchronize_threads(); /* 2: accepted => send data */
- if (test_client_verify(sk, packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC))
+ if (test_client_verify(sk, packet_sz, quota / packet_sz))
test_fail("Failed to send data on connected socket");
else
test_ok("Verified established tcp connection");
@@ -397,8 +396,8 @@ static void test_client_passive_rst(unsigned int port)
test_error("setsockopt(TCP_AO_ADD_KEY)");
test_ao_restore(sk, &ao_img);
- if (test_get_tcp_ao_counters(sk, &ao1))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(sk, &cnt1))
+ test_error("test_get_tcp_counters()");
test_disable_repair(sk);
test_sock_state_free(&img);
@@ -417,7 +416,7 @@ static void test_client_passive_rst(unsigned int port)
* IP 10.0.254.1.7011 > 10.0.1.1.59772: Flags [R], seq 3215596252, win 0,
* options [tcp-ao keyid 100 rnextkeyid 100 mac 0x0bcfbbf497bce844312304b2], length 0
*/
- err = test_client_verify(sk, packet_sz, quota / packet_sz, 2 * TEST_TIMEOUT_SEC);
+ err = test_client_verify(sk, packet_sz, quota / packet_sz);
/* Make sure that the connection was reset, not timeouted */
if (err && err == -ECONNRESET)
test_ok("client sock was passively reset post-seq-adjust");
@@ -426,12 +425,12 @@ static void test_client_passive_rst(unsigned int port)
else
test_fail("client sock is yet connected post-seq-adjust");
- if (test_get_tcp_ao_counters(sk, &ao2))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(sk, &cnt2))
+ test_error("test_get_tcp_counters()");
synchronize_threads(); /* 6: server exits */
close(sk);
- test_tcp_ao_counters_cmp("client passive RST", &ao1, &ao2, TEST_CNT_GOOD);
+ test_assert_counters("client passive RST", &cnt1, &cnt2, TEST_CNT_GOOD);
}
static void *client_fn(void *arg)
diff --git a/tools/testing/selftests/net/tcp_ao/self-connect.c b/tools/testing/selftests/net/tcp_ao/self-connect.c
index 3ecd2b58de6a..2c73bea698a6 100644
--- a/tools/testing/selftests/net/tcp_ao/self-connect.c
+++ b/tools/testing/selftests/net/tcp_ao/self-connect.c
@@ -16,6 +16,9 @@ static void __setup_lo_intf(const char *lo_intf,
if (link_set_up(lo_intf))
test_error("Failed to bring %s up", lo_intf);
+
+ if (ip_route_add(lo_intf, TEST_FAMILY, local_addr, local_addr))
+ test_error("Failed to add a local route %s", lo_intf);
}
static void setup_lo_intf(const char *lo_intf)
@@ -30,7 +33,7 @@ static void setup_lo_intf(const char *lo_intf)
static void tcp_self_connect(const char *tst, unsigned int port,
bool different_keyids, bool check_restore)
{
- struct tcp_ao_counters before_ao, after_ao;
+ struct tcp_counters before, after;
uint64_t before_aogood, after_aogood;
struct netstat *ns_before, *ns_after;
const size_t nr_packets = 20;
@@ -60,17 +63,17 @@ static void tcp_self_connect(const char *tst, unsigned int port,
ns_before = netstat_read();
before_aogood = netstat_get(ns_before, "TCPAOGood", NULL);
- if (test_get_tcp_ao_counters(sk, &before_ao))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(sk, &before))
+ test_error("test_get_tcp_counters()");
if (__test_connect_socket(sk, "lo", (struct sockaddr *)&addr,
- sizeof(addr), TEST_TIMEOUT_SEC) < 0) {
+ sizeof(addr), 0) < 0) {
ns_after = netstat_read();
netstat_print_diff(ns_before, ns_after);
test_error("failed to connect()");
}
- if (test_client_verify(sk, 100, nr_packets, TEST_TIMEOUT_SEC)) {
+ if (test_client_verify(sk, 100, nr_packets)) {
test_fail("%s: tcp connection verify failed", tst);
close(sk);
return;
@@ -78,8 +81,8 @@ static void tcp_self_connect(const char *tst, unsigned int port,
ns_after = netstat_read();
after_aogood = netstat_get(ns_after, "TCPAOGood", NULL);
- if (test_get_tcp_ao_counters(sk, &after_ao))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(sk, &after))
+ test_error("test_get_tcp_counters()");
if (!check_restore) {
/* to debug: netstat_print_diff(ns_before, ns_after); */
netstat_free(ns_before);
@@ -93,7 +96,7 @@ static void tcp_self_connect(const char *tst, unsigned int port,
return;
}
- if (test_tcp_ao_counters_cmp(tst, &before_ao, &after_ao, TEST_CNT_GOOD)) {
+ if (test_assert_counters(tst, &before, &after, TEST_CNT_GOOD)) {
close(sk);
return;
}
@@ -136,7 +139,7 @@ static void tcp_self_connect(const char *tst, unsigned int port,
test_ao_restore(sk, &ao_img);
test_disable_repair(sk);
test_sock_state_free(&img);
- if (test_client_verify(sk, 100, nr_packets, TEST_TIMEOUT_SEC)) {
+ if (test_client_verify(sk, 100, nr_packets)) {
test_fail("%s: tcp connection verify failed", tst);
close(sk);
return;
diff --git a/tools/testing/selftests/net/tcp_ao/seq-ext.c b/tools/testing/selftests/net/tcp_ao/seq-ext.c
index 8901a6785dc8..f00245263b20 100644
--- a/tools/testing/selftests/net/tcp_ao/seq-ext.c
+++ b/tools/testing/selftests/net/tcp_ao/seq-ext.c
@@ -40,7 +40,7 @@ static void test_adjust_seqs(struct tcp_sock_state *img,
static int test_sk_restore(struct tcp_sock_state *img,
struct tcp_ao_repair *ao_img, sockaddr_af *saddr,
const union tcp_addr daddr, unsigned int dport,
- struct tcp_ao_counters *cnt)
+ struct tcp_counters *cnt)
{
int sk;
@@ -54,8 +54,8 @@ static int test_sk_restore(struct tcp_sock_state *img,
test_error("setsockopt(TCP_AO_ADD_KEY)");
test_ao_restore(sk, ao_img);
- if (test_get_tcp_ao_counters(sk, cnt))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(sk, cnt))
+ test_error("test_get_tcp_counters()");
test_disable_repair(sk);
test_sock_state_free(img);
@@ -65,7 +65,7 @@ static int test_sk_restore(struct tcp_sock_state *img,
static void *server_fn(void *arg)
{
uint64_t before_good, after_good, after_bad;
- struct tcp_ao_counters ao1, ao2;
+ struct tcp_counters cnt1, cnt2;
struct tcp_sock_state img;
struct tcp_ao_repair ao_img;
sockaddr_af saddr;
@@ -114,7 +114,7 @@ static void *server_fn(void *arg)
test_adjust_seqs(&img, &ao_img, true);
synchronize_threads(); /* 4: dump finished */
sk = test_sk_restore(&img, &ao_img, &saddr, this_ip_dest,
- client_new_port, &ao1);
+ client_new_port, &cnt1);
trace_ao_event_sne_expect(TCP_AO_SND_SNE_UPDATE, this_ip_addr,
this_ip_dest, test_server_port + 1, client_new_port, 1);
@@ -136,11 +136,11 @@ static void *server_fn(void *arg)
}
synchronize_threads(); /* 6: verify counters after SEQ-number rollover */
- if (test_get_tcp_ao_counters(sk, &ao2))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(sk, &cnt2))
+ test_error("test_get_tcp_counters()");
after_good = netstat_get_one("TCPAOGood", NULL);
- test_tcp_ao_counters_cmp(NULL, &ao1, &ao2, TEST_CNT_GOOD);
+ test_assert_counters(NULL, &cnt1, &cnt2, TEST_CNT_GOOD);
if (after_good <= before_good) {
test_fail("TCPAOGood counter did not increase: %" PRIu64 " <= %" PRIu64,
@@ -173,7 +173,7 @@ out:
static void *client_fn(void *arg)
{
uint64_t before_good, after_good, after_bad;
- struct tcp_ao_counters ao1, ao2;
+ struct tcp_counters cnt1, cnt2;
struct tcp_sock_state img;
struct tcp_ao_repair ao_img;
sockaddr_af saddr;
@@ -191,7 +191,7 @@ static void *client_fn(void *arg)
test_error("failed to connect()");
synchronize_threads(); /* 2: accepted => send data */
- if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC)) {
+ if (test_client_verify(sk, msg_len, nr_packets)) {
test_fail("pre-migrate verify failed");
return NULL;
}
@@ -213,20 +213,20 @@ static void *client_fn(void *arg)
test_adjust_seqs(&img, &ao_img, false);
synchronize_threads(); /* 4: dump finished */
sk = test_sk_restore(&img, &ao_img, &saddr, this_ip_dest,
- test_server_port + 1, &ao1);
+ test_server_port + 1, &cnt1);
synchronize_threads(); /* 5: verify the connection during SEQ-number rollover */
- if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC))
+ if (test_client_verify(sk, msg_len, nr_packets))
test_fail("post-migrate verify failed");
else
test_ok("post-migrate connection alive");
synchronize_threads(); /* 5: verify counters after SEQ-number rollover */
- if (test_get_tcp_ao_counters(sk, &ao2))
- test_error("test_get_tcp_ao_counters()");
+ if (test_get_tcp_counters(sk, &cnt2))
+ test_error("test_get_tcp_counters()");
after_good = netstat_get_one("TCPAOGood", NULL);
- test_tcp_ao_counters_cmp(NULL, &ao1, &ao2, TEST_CNT_GOOD);
+ test_assert_counters(NULL, &cnt1, &cnt2, TEST_CNT_GOOD);
if (after_good <= before_good) {
test_fail("TCPAOGood counter did not increase: %" PRIu64 " <= %" PRIu64,
diff --git a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
index f779e5892bc1..a1467b64390a 100644
--- a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
+++ b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
@@ -6,6 +6,7 @@
#define fault(type) (inj == FAULT_ ## type)
static const char *md5_password = "Some evil genius, enemy to mankind, must have been the first contriver.";
static const char *ao_password = DEFAULT_TEST_PASSWORD;
+static volatile int sk_pair;
static union tcp_addr client2;
static union tcp_addr client3;
@@ -41,10 +42,10 @@ static void try_accept(const char *tst_name, unsigned int port,
const char *cnt_name, test_cnt cnt_expected,
int needs_tcp_md5, fault_t inj)
{
- struct tcp_ao_counters ao_cnt1, ao_cnt2;
+ struct tcp_counters cnt1, cnt2;
uint64_t before_cnt = 0, after_cnt = 0; /* silence GCC */
- int lsk, err, sk = 0;
- time_t timeout;
+ test_cnt poll_cnt = (cnt_expected == TEST_CNT_GOOD) ? 0 : cnt_expected;
+ int lsk, err, sk = -1;
if (needs_tcp_md5 && should_skip_test(tst_name, KCONFIG_TCP_MD5))
return;
@@ -63,22 +64,25 @@ static void try_accept(const char *tst_name, unsigned int port,
if (cnt_name)
before_cnt = netstat_get_one(cnt_name, NULL);
- if (ao_addr && test_get_tcp_ao_counters(lsk, &ao_cnt1))
- test_error("test_get_tcp_ao_counters()");
+ if (ao_addr && test_get_tcp_counters(lsk, &cnt1))
+ test_error("test_get_tcp_counters()");
synchronize_threads(); /* preparations done */
- timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
- err = test_wait_fd(lsk, timeout, 0);
+ err = test_skpair_wait_poll(lsk, 0, poll_cnt, &sk_pair);
synchronize_threads(); /* connect()/accept() timeouts */
if (err == -ETIMEDOUT) {
+ sk_pair = err;
if (!fault(TIMEOUT))
- test_fail("timed out for accept()");
+ test_fail("%s: timed out for accept()", tst_name);
+ } else if (err == -EKEYREJECTED) {
+ if (!fault(KEYREJECT))
+ test_fail("%s: key was rejected", tst_name);
} else if (err < 0) {
- test_error("test_wait_fd()");
+ test_error("test_skpair_wait_poll()");
} else {
if (fault(TIMEOUT))
- test_fail("ready to accept");
+ test_fail("%s: ready to accept", tst_name);
sk = accept(lsk, NULL, NULL);
if (sk < 0) {
@@ -89,8 +93,8 @@ static void try_accept(const char *tst_name, unsigned int port,
}
}
- if (ao_addr && test_get_tcp_ao_counters(lsk, &ao_cnt2))
- test_error("test_get_tcp_ao_counters()");
+ if (ao_addr && test_get_tcp_counters(lsk, &cnt2))
+ test_error("test_get_tcp_counters()");
close(lsk);
if (!cnt_name) {
@@ -108,11 +112,11 @@ static void try_accept(const char *tst_name, unsigned int port,
tst_name, cnt_name, before_cnt, after_cnt);
}
if (ao_addr)
- test_tcp_ao_counters_cmp(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected);
+ test_assert_counters(tst_name, &cnt1, &cnt2, cnt_expected);
out:
synchronize_threads(); /* test_kill_sk() */
- if (sk > 0)
+ if (sk >= 0)
test_kill_sk(sk);
}
@@ -153,78 +157,82 @@ static void *server_fn(void *arg)
server_add_routes();
- try_accept("AO server (INADDR_ANY): AO client", port++, NULL, 0,
+ try_accept("[server] AO server (INADDR_ANY): AO client", port++, NULL, 0,
&addr_any, 0, 0, 100, 100, 0, "TCPAOGood",
TEST_CNT_GOOD, 0, 0);
- try_accept("AO server (INADDR_ANY): MD5 client", port++, NULL, 0,
+ try_accept("[server] AO server (INADDR_ANY): MD5 client", port++, NULL, 0,
&addr_any, 0, 0, 100, 100, 0, "TCPMD5Unexpected",
- 0, 1, FAULT_TIMEOUT);
- try_accept("AO server (INADDR_ANY): no sign client", port++, NULL, 0,
+ TEST_CNT_NS_MD5_UNEXPECTED, 1, FAULT_TIMEOUT);
+ try_accept("[server] AO server (INADDR_ANY): no sign client", port++, NULL, 0,
&addr_any, 0, 0, 100, 100, 0, "TCPAORequired",
TEST_CNT_AO_REQUIRED, 0, FAULT_TIMEOUT);
- try_accept("AO server (AO_REQUIRED): AO client", port++, NULL, 0,
+ try_accept("[server] AO server (AO_REQUIRED): AO client", port++, NULL, 0,
&this_ip_dest, TEST_PREFIX, true,
100, 100, 0, "TCPAOGood", TEST_CNT_GOOD, 0, 0);
- try_accept("AO server (AO_REQUIRED): unsigned client", port++, NULL, 0,
+ try_accept("[server] AO server (AO_REQUIRED): unsigned client", port++, NULL, 0,
&this_ip_dest, TEST_PREFIX, true,
100, 100, 0, "TCPAORequired",
TEST_CNT_AO_REQUIRED, 0, FAULT_TIMEOUT);
- try_accept("MD5 server (INADDR_ANY): AO client", port++, &addr_any, 0,
+ try_accept("[server] MD5 server (INADDR_ANY): AO client", port++, &addr_any, 0,
NULL, 0, 0, 0, 0, 0, "TCPAOKeyNotFound",
- 0, 1, FAULT_TIMEOUT);
- try_accept("MD5 server (INADDR_ANY): MD5 client", port++, &addr_any, 0,
+ TEST_CNT_NS_KEY_NOT_FOUND, 1, FAULT_TIMEOUT);
+ try_accept("[server] MD5 server (INADDR_ANY): MD5 client", port++, &addr_any, 0,
NULL, 0, 0, 0, 0, 0, NULL, 0, 1, 0);
- try_accept("MD5 server (INADDR_ANY): no sign client", port++, &addr_any,
+ try_accept("[server] MD5 server (INADDR_ANY): no sign client", port++, &addr_any,
0, NULL, 0, 0, 0, 0, 0, "TCPMD5NotFound",
- 0, 1, FAULT_TIMEOUT);
+ TEST_CNT_NS_MD5_NOT_FOUND, 1, FAULT_TIMEOUT);
- try_accept("no sign server: AO client", port++, NULL, 0,
+ try_accept("[server] no sign server: AO client", port++, NULL, 0,
NULL, 0, 0, 0, 0, 0, "TCPAOKeyNotFound",
- TEST_CNT_AO_KEY_NOT_FOUND, 0, FAULT_TIMEOUT);
- try_accept("no sign server: MD5 client", port++, NULL, 0,
+ TEST_CNT_NS_KEY_NOT_FOUND, 0, FAULT_TIMEOUT);
+ try_accept("[server] no sign server: MD5 client", port++, NULL, 0,
NULL, 0, 0, 0, 0, 0, "TCPMD5Unexpected",
- 0, 1, FAULT_TIMEOUT);
- try_accept("no sign server: no sign client", port++, NULL, 0,
+ TEST_CNT_NS_MD5_UNEXPECTED, 1, FAULT_TIMEOUT);
+ try_accept("[server] no sign server: no sign client", port++, NULL, 0,
NULL, 0, 0, 0, 0, 0, "CurrEstab", 0, 0, 0);
- try_accept("AO+MD5 server: AO client (matching)", port++,
+ try_accept("[server] AO+MD5 server: AO client (matching)", port++,
&this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
100, 100, 0, "TCPAOGood", TEST_CNT_GOOD, 1, 0);
- try_accept("AO+MD5 server: AO client (misconfig, matching MD5)", port++,
+ try_accept("[server] AO+MD5 server: AO client (misconfig, matching MD5)", port++,
&this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
100, 100, 0, "TCPAOKeyNotFound", TEST_CNT_AO_KEY_NOT_FOUND,
1, FAULT_TIMEOUT);
- try_accept("AO+MD5 server: AO client (misconfig, non-matching)", port++,
+ try_accept("[server] AO+MD5 server: AO client (misconfig, non-matching)", port++,
&this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
100, 100, 0, "TCPAOKeyNotFound", TEST_CNT_AO_KEY_NOT_FOUND,
1, FAULT_TIMEOUT);
- try_accept("AO+MD5 server: MD5 client (matching)", port++,
+ try_accept("[server] AO+MD5 server: MD5 client (matching)", port++,
&this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
100, 100, 0, NULL, 0, 1, 0);
- try_accept("AO+MD5 server: MD5 client (misconfig, matching AO)", port++,
+ try_accept("[server] AO+MD5 server: MD5 client (misconfig, matching AO)", port++,
&this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
- 100, 100, 0, "TCPMD5Unexpected", 0, 1, FAULT_TIMEOUT);
- try_accept("AO+MD5 server: MD5 client (misconfig, non-matching)", port++,
+ 100, 100, 0, "TCPMD5Unexpected",
+ TEST_CNT_NS_MD5_UNEXPECTED, 1, FAULT_TIMEOUT);
+ try_accept("[server] AO+MD5 server: MD5 client (misconfig, non-matching)", port++,
&this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
- 100, 100, 0, "TCPMD5Unexpected", 0, 1, FAULT_TIMEOUT);
- try_accept("AO+MD5 server: no sign client (unmatched)", port++,
+ 100, 100, 0, "TCPMD5Unexpected",
+ TEST_CNT_NS_MD5_UNEXPECTED, 1, FAULT_TIMEOUT);
+ try_accept("[server] AO+MD5 server: no sign client (unmatched)", port++,
&this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
100, 100, 0, "CurrEstab", 0, 1, 0);
- try_accept("AO+MD5 server: no sign client (misconfig, matching AO)",
+ try_accept("[server] AO+MD5 server: no sign client (misconfig, matching AO)",
port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
100, 100, 0, "TCPAORequired",
TEST_CNT_AO_REQUIRED, 1, FAULT_TIMEOUT);
- try_accept("AO+MD5 server: no sign client (misconfig, matching MD5)",
+ try_accept("[server] AO+MD5 server: no sign client (misconfig, matching MD5)",
port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
- 100, 100, 0, "TCPMD5NotFound", 0, 1, FAULT_TIMEOUT);
+ 100, 100, 0, "TCPMD5NotFound",
+ TEST_CNT_NS_MD5_NOT_FOUND, 1, FAULT_TIMEOUT);
- try_accept("AO+MD5 server: client with both [TCP-MD5] and TCP-AO keys",
+ /* Key rejected by the other side, failing short through skpair */
+ try_accept("[server] AO+MD5 server: client with both [TCP-MD5] and TCP-AO keys",
port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
- 100, 100, 0, NULL, 0, 1, FAULT_TIMEOUT);
- try_accept("AO+MD5 server: client with both TCP-MD5 and [TCP-AO] keys",
+ 100, 100, 0, NULL, 0, 1, FAULT_KEYREJECT);
+ try_accept("[server] AO+MD5 server: client with both TCP-MD5 and [TCP-AO] keys",
port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
- 100, 100, 0, NULL, 0, 1, FAULT_TIMEOUT);
+ 100, 100, 0, NULL, 0, 1, FAULT_KEYREJECT);
server_add_fail_tests(&port);
@@ -259,7 +267,6 @@ static void try_connect(const char *tst_name, unsigned int port,
uint8_t sndid, uint8_t rcvid, uint8_t vrf,
fault_t inj, int needs_tcp_md5, union tcp_addr *bind_addr)
{
- time_t timeout;
int sk, ret;
if (needs_tcp_md5 && should_skip_test(tst_name, KCONFIG_TCP_MD5))
@@ -281,11 +288,10 @@ static void try_connect(const char *tst_name, unsigned int port,
synchronize_threads(); /* preparations done */
- timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
- ret = _test_connect_socket(sk, this_ip_dest, port, timeout);
-
+ ret = test_skpair_connect_poll(sk, this_ip_dest, port, 0, &sk_pair);
synchronize_threads(); /* connect()/accept() timeouts */
if (ret < 0) {
+ sk_pair = ret;
if (fault(KEYREJECT) && ret == -EKEYREJECTED)
test_ok("%s: connect() was prevented", tst_name);
else if (ret == -ETIMEDOUT && fault(TIMEOUT))
@@ -305,8 +311,7 @@ static void try_connect(const char *tst_name, unsigned int port,
out:
synchronize_threads(); /* test_kill_sk() */
- /* _test_connect_socket() cleans up on failure */
- if (ret > 0)
+ if (ret > 0) /* test_skpair_connect_poll() cleans up on failure */
test_kill_sk(sk);
}
@@ -437,7 +442,6 @@ static void try_to_add(const char *tst_name, unsigned int port,
int ao_vrf, uint8_t sndid, uint8_t rcvid,
int needs_tcp_md5, fault_t inj)
{
- time_t timeout;
int sk, ret;
if (needs_tcp_md5 && should_skip_test(tst_name, KCONFIG_TCP_MD5))
@@ -450,11 +454,10 @@ static void try_to_add(const char *tst_name, unsigned int port,
synchronize_threads(); /* preparations done */
- timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
- ret = _test_connect_socket(sk, this_ip_dest, port, timeout);
+ ret = test_skpair_connect_poll(sk, this_ip_dest, port, 0, &sk_pair);
synchronize_threads(); /* connect()/accept() timeouts */
- if (ret <= 0) {
+ if (ret < 0) {
test_error("%s: connect() returned %d", tst_name, ret);
goto out;
}
@@ -490,8 +493,7 @@ static void try_to_add(const char *tst_name, unsigned int port,
out:
synchronize_threads(); /* test_kill_sk() */
- /* _test_connect_socket() cleans up on failure */
- if (ret > 0)
+ if (ret > 0) /* test_skpair_connect_poll() cleans up on failure */
test_kill_sk(sk);
}
diff --git a/tools/testing/selftests/net/test_blackhole_dev.sh b/tools/testing/selftests/net/test_blackhole_dev.sh
deleted file mode 100755
index 3119b80e711f..000000000000
--- a/tools/testing/selftests/net/test_blackhole_dev.sh
+++ /dev/null
@@ -1,11 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-# Runs blackhole-dev test using blackhole-dev kernel module
-
-if /sbin/modprobe -q test_blackhole_dev ; then
- /sbin/modprobe -q -r test_blackhole_dev;
- echo "test_blackhole_dev: ok";
-else
- echo "test_blackhole_dev: [FAIL]";
- exit 1;
-fi
diff --git a/tools/testing/selftests/net/test_bridge_neigh_suppress.sh b/tools/testing/selftests/net/test_bridge_neigh_suppress.sh
index 02b986c9c247..9067197c9055 100755
--- a/tools/testing/selftests/net/test_bridge_neigh_suppress.sh
+++ b/tools/testing/selftests/net/test_bridge_neigh_suppress.sh
@@ -51,7 +51,9 @@ ret=0
# All tests in this script. Can be overridden with -t option.
TESTS="
neigh_suppress_arp
+ neigh_suppress_uc_arp
neigh_suppress_ns
+ neigh_suppress_uc_ns
neigh_vlan_suppress_arp
neigh_vlan_suppress_ns
"
@@ -388,6 +390,52 @@ neigh_suppress_arp()
neigh_suppress_arp_common $vid $sip $tip
}
+neigh_suppress_uc_arp_common()
+{
+ local vid=$1; shift
+ local sip=$1; shift
+ local tip=$1; shift
+ local tmac
+
+ echo
+ echo "Unicast ARP, per-port ARP suppression - VLAN $vid"
+ echo "-----------------------------------------------"
+
+ run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress on"
+ run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
+ log_test $? 0 "\"neigh_suppress\" is on"
+
+ tmac=$(ip -n $h2 -j -p link show eth0.$vid | jq -r '.[]["address"]')
+ run_cmd "bridge -n $sw1 fdb replace $tmac dev vx0 master static vlan $vid"
+ run_cmd "ip -n $sw1 neigh replace $tip lladdr $tmac nud permanent dev br0.$vid"
+
+ run_cmd "tc -n $h1 qdisc replace dev eth0.$vid clsact"
+ run_cmd "tc -n $h1 filter replace dev eth0.$vid ingress pref 1 handle 101 proto arp flower arp_sip $tip arp_op reply action pass"
+
+ run_cmd "tc -n $h2 qdisc replace dev eth0.$vid clsact"
+ run_cmd "tc -n $h2 filter replace dev eth0.$vid egress pref 1 handle 101 proto arp flower arp_tip $sip arp_op reply action pass"
+
+ run_cmd "ip netns exec $h1 mausezahn eth0.$vid -c 1 -a own -b $tmac -t arp 'request sip=$sip, tip=$tip, tmac=$tmac' -q"
+ tc_check_packets $h1 "dev eth0.$vid ingress" 101 1
+ log_test $? 0 "Unicast ARP, suppression on, h1 filter"
+ tc_check_packets $h2 "dev eth0.$vid egress" 101 1
+ log_test $? 0 "Unicast ARP, suppression on, h2 filter"
+}
+
+neigh_suppress_uc_arp()
+{
+ local vid=10
+ local sip=192.0.2.1
+ local tip=192.0.2.2
+
+ neigh_suppress_uc_arp_common $vid $sip $tip
+
+ vid=20
+ sip=192.0.2.17
+ tip=192.0.2.18
+ neigh_suppress_uc_arp_common $vid $sip $tip
+}
+
neigh_suppress_ns_common()
{
local vid=$1; shift
@@ -494,6 +542,78 @@ neigh_suppress_ns()
neigh_suppress_ns_common $vid $saddr $daddr $maddr
}
+icmpv6_header_get()
+{
+ local csum=$1; shift
+ local tip=$1; shift
+ local type
+ local p
+
+ # Type 135 (Neighbor Solicitation), hex format
+ type="87"
+ p=$(:
+ )"$type:"$( : ICMPv6.type
+ )"00:"$( : ICMPv6.code
+ )"$csum:"$( : ICMPv6.checksum
+ )"00:00:00:00:"$( : Reserved
+ )"$tip:"$( : Target Address
+ )
+ echo $p
+}
+
+neigh_suppress_uc_ns_common()
+{
+ local vid=$1; shift
+ local sip=$1; shift
+ local dip=$1; shift
+ local full_dip=$1; shift
+ local csum=$1; shift
+ local tmac
+
+ echo
+ echo "Unicast NS, per-port NS suppression - VLAN $vid"
+ echo "---------------------------------------------"
+
+ run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress on"
+ run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
+ log_test $? 0 "\"neigh_suppress\" is on"
+
+ tmac=$(ip -n $h2 -j -p link show eth0.$vid | jq -r '.[]["address"]')
+ run_cmd "bridge -n $sw1 fdb replace $tmac dev vx0 master static vlan $vid"
+ run_cmd "ip -n $sw1 -6 neigh replace $dip lladdr $tmac nud permanent dev br0.$vid"
+
+ run_cmd "tc -n $h1 qdisc replace dev eth0.$vid clsact"
+ run_cmd "tc -n $h1 filter replace dev eth0.$vid ingress pref 1 handle 101 proto ipv6 flower ip_proto icmpv6 src_ip $dip type 136 code 0 action pass"
+
+ run_cmd "tc -n $h2 qdisc replace dev eth0.$vid clsact"
+ run_cmd "tc -n $h2 filter replace dev eth0.$vid egress pref 1 handle 101 proto ipv6 flower ip_proto icmpv6 dst_ip $sip type 136 code 0 action pass"
+
+ run_cmd "ip netns exec $h1 mausezahn -6 eth0.$vid -c 1 -a own -b $tmac -A $sip -B $dip -t ip hop=255,next=58,payload=$(icmpv6_header_get $csum $full_dip) -q"
+ tc_check_packets $h1 "dev eth0.$vid ingress" 101 1
+ log_test $? 0 "Unicast NS, suppression on, h1 filter"
+ tc_check_packets $h2 "dev eth0.$vid egress" 101 1
+ log_test $? 0 "Unicast NS, suppression on, h2 filter"
+}
+
+neigh_suppress_uc_ns()
+{
+ local vid=10
+ local saddr=2001:db8:1::1
+ local daddr=2001:db8:1::2
+ local full_daddr=20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:02
+ local csum="ef:79"
+
+ neigh_suppress_uc_ns_common $vid $saddr $daddr $full_daddr $csum
+
+ vid=20
+ saddr=2001:db8:2::1
+ daddr=2001:db8:2::2
+ full_daddr=20:01:0d:b8:00:02:00:00:00:00:00:00:00:00:00:02
+ csum="ef:76"
+
+ neigh_suppress_uc_ns_common $vid $saddr $daddr $full_daddr $csum
+}
+
neigh_vlan_suppress_arp()
{
local vid1=10
@@ -825,6 +945,11 @@ if [ ! -x "$(command -v jq)" ]; then
exit $ksft_skip
fi
+if [ ! -x "$(command -v mausezahn)" ]; then
+ echo "SKIP: Could not run test without mausezahn tool"
+ exit $ksft_skip
+fi
+
bridge link help 2>&1 | grep -q "neigh_vlan_suppress"
if [ $? -ne 0 ]; then
echo "SKIP: iproute2 bridge too old, missing per-VLAN neighbor suppression support"
diff --git a/tools/testing/selftests/net/test_so_rcv.sh b/tools/testing/selftests/net/test_so_rcv.sh
new file mode 100755
index 000000000000..d8aa4362879d
--- /dev/null
+++ b/tools/testing/selftests/net/test_so_rcv.sh
@@ -0,0 +1,73 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source lib.sh
+
+HOSTS=("127.0.0.1" "::1")
+PORT=1234
+TOTAL_TESTS=0
+FAILED_TESTS=0
+
+declare -A TESTS=(
+ ["SO_RCVPRIORITY"]="-P 2"
+ ["SO_RCVMARK"]="-M 3"
+)
+
+check_result() {
+ ((TOTAL_TESTS++))
+ if [ "$1" -ne 0 ]; then
+ ((FAILED_TESTS++))
+ fi
+}
+
+cleanup()
+{
+ cleanup_ns $NS
+}
+
+trap cleanup EXIT
+
+setup_ns NS
+
+for HOST in "${HOSTS[@]}"; do
+ PROTOCOL="IPv4"
+ if [[ "$HOST" == "::1" ]]; then
+ PROTOCOL="IPv6"
+ fi
+ for test_name in "${!TESTS[@]}"; do
+ echo "Running $test_name test, $PROTOCOL"
+ arg=${TESTS[$test_name]}
+
+ ip netns exec $NS ./so_rcv_listener $arg $HOST $PORT &
+ LISTENER_PID=$!
+
+ sleep 0.5
+
+ if ! ip netns exec $NS ./cmsg_sender $arg $HOST $PORT; then
+ echo "Sender failed for $test_name, $PROTOCOL"
+ kill "$LISTENER_PID" 2>/dev/null
+ wait "$LISTENER_PID"
+ check_result 1
+ continue
+ fi
+
+ wait "$LISTENER_PID"
+ LISTENER_EXIT_CODE=$?
+
+ if [ "$LISTENER_EXIT_CODE" -eq 0 ]; then
+ echo "Rcv test OK for $test_name, $PROTOCOL"
+ check_result 0
+ else
+ echo "Rcv test FAILED for $test_name, $PROTOCOL"
+ check_result 1
+ fi
+ done
+done
+
+if [ "$FAILED_TESTS" -ne 0 ]; then
+ echo "FAIL - $FAILED_TESTS/$TOTAL_TESTS tests failed"
+ exit ${KSFT_FAIL}
+else
+ echo "OK - All $TOTAL_TESTS tests passed"
+ exit ${KSFT_PASS}
+fi
diff --git a/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh b/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh
index 2d442cdab11e..062f957950af 100755
--- a/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh
+++ b/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh
@@ -1,29 +1,114 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
-# Check FDB default-remote handling across "ip link set".
+ALL_TESTS="
+ test_set_remote
+ test_change_mc_remote
+"
+source lib.sh
check_remotes()
{
local what=$1; shift
local N=$(bridge fdb sh dev vx | grep 00:00:00:00:00:00 | wc -l)
- echo -ne "expected two remotes after $what\t"
- if [[ $N != 2 ]]; then
- echo "[FAIL]"
- EXIT_STATUS=1
+ ((N == 2))
+ check_err $? "expected 2 remotes after $what, got $N"
+}
+
+# Check FDB default-remote handling across "ip link set".
+test_set_remote()
+{
+ RET=0
+
+ ip_link_add vx up type vxlan id 2000 dstport 4789
+ bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.20 self permanent
+ bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.30 self permanent
+ check_remotes "fdb append"
+
+ ip link set dev vx type vxlan remote 192.0.2.30
+ check_remotes "link set"
+
+ log_test 'FDB default-remote handling across "ip link set"'
+}
+
+fmt_remote()
+{
+ local addr=$1; shift
+
+ if [[ $addr == 224.* ]]; then
+ echo "group $addr"
else
- echo "[ OK ]"
+ echo "remote $addr"
fi
}
-ip link add name vx up type vxlan id 2000 dstport 4789
-bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.20 self permanent
-bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.30 self permanent
-check_remotes "fdb append"
+change_remote()
+{
+ local remote=$1; shift
+
+ ip link set dev vx type vxlan $(fmt_remote $remote) dev v1
+}
+
+check_membership()
+{
+ local check_vec=("$@")
+
+ local memberships
+ memberships=$(
+ netstat -n --groups |
+ sed -n '/^v1\b/p' |
+ grep -o '[^ ]*$'
+ )
+ check_err $? "Couldn't obtain group memberships"
+
+ local item
+ for item in "${check_vec[@]}"; do
+ eval "local $item"
+ echo "$memberships" | grep -q "\b$group\b"
+ check_err_fail $fail $? "$group is_ex reported in IGMP query response"
+ done
+}
+
+test_change_mc_remote()
+{
+ check_command netstat || return
+
+ ip_link_add v1 up type veth peer name v2
+ ip_link_set_up v2
+
+ RET=0
+
+ ip_link_add vx up type vxlan dstport 4789 \
+ local 192.0.2.1 $(fmt_remote 224.1.1.1) dev v1 vni 1000
+
+ check_membership "group=224.1.1.1 fail=0" \
+ "group=224.1.1.2 fail=1" \
+ "group=224.1.1.3 fail=1"
+
+ log_test "MC group report after VXLAN creation"
+
+ RET=0
+
+ change_remote 224.1.1.2
+ check_membership "group=224.1.1.1 fail=1" \
+ "group=224.1.1.2 fail=0" \
+ "group=224.1.1.3 fail=1"
+
+ log_test "MC group report after changing VXLAN remote MC->MC"
+
+ RET=0
+
+ change_remote 192.0.2.2
+ check_membership "group=224.1.1.1 fail=1" \
+ "group=224.1.1.2 fail=1" \
+ "group=224.1.1.3 fail=1"
+
+ log_test "MC group report after changing VXLAN remote MC->UC"
+}
+
+trap defer_scopes_cleanup EXIT
-ip link set dev vx type vxlan remote 192.0.2.30
-check_remotes "link set"
+tests_run
-ip link del dev vx
exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 9a85f93c33d8..5ded3b3a7538 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -1753,6 +1753,42 @@ TEST_F(tls_basic, rekey_tx)
EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
}
+TEST_F(tls_basic, disconnect)
+{
+ char const *test_str = "test_message";
+ int send_len = strlen(test_str) + 1;
+ struct tls_crypto_info_keys key;
+ struct sockaddr_in addr;
+ char buf[20];
+ int ret;
+
+ if (self->notls)
+ return;
+
+ tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128,
+ &key, 0);
+
+ ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &key, key.len);
+ ASSERT_EQ(ret, 0);
+
+ /* Pre-queue the data so that setsockopt parses it but doesn't
+ * dequeue it from the TCP socket. recvmsg would dequeue.
+ */
+ EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+
+ ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &key, key.len);
+ ASSERT_EQ(ret, 0);
+
+ addr.sin_family = AF_UNSPEC;
+ addr.sin_addr.s_addr = htonl(INADDR_ANY);
+ addr.sin_port = 0;
+ ret = connect(self->cfd, &addr, sizeof(addr));
+ EXPECT_EQ(ret, -1);
+ EXPECT_EQ(errno, EOPNOTSUPP);
+
+ EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+}
+
TEST_F(tls, rekey)
{
char const *test_str_1 = "test_message_before_rekey";
diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
index d5ffd8c9172e..1dc337c709f8 100755
--- a/tools/testing/selftests/net/udpgro.sh
+++ b/tools/testing/selftests/net/udpgro.sh
@@ -3,7 +3,7 @@
#
# Run a series of udpgro functional tests.
-source net_helper.sh
+source lib.sh
readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh
index c51ea90a1395..54fa4821bc5e 100755
--- a/tools/testing/selftests/net/udpgro_bench.sh
+++ b/tools/testing/selftests/net/udpgro_bench.sh
@@ -3,11 +3,11 @@
#
# Run a series of udpgro benchmarks
-source net_helper.sh
+source lib.sh
readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
-BPF_FILE="xdp_dummy.bpf.o"
+BPF_FILE="lib/xdp_dummy.bpf.o"
cleanup() {
local -r jobs="$(jobs -p)"
diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh
index 17404f49cdb6..9a2cfec1153e 100755
--- a/tools/testing/selftests/net/udpgro_frglist.sh
+++ b/tools/testing/selftests/net/udpgro_frglist.sh
@@ -3,11 +3,11 @@
#
# Run a series of udpgro benchmarks
-source net_helper.sh
+source lib.sh
readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
-BPF_FILE="xdp_dummy.bpf.o"
+BPF_FILE="lib/xdp_dummy.bpf.o"
cleanup() {
local -r jobs="$(jobs -p)"
diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
index 550d8eb3e224..a39fdc4aa2ff 100755
--- a/tools/testing/selftests/net/udpgro_fwd.sh
+++ b/tools/testing/selftests/net/udpgro_fwd.sh
@@ -1,9 +1,9 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
-source net_helper.sh
+source lib.sh
-BPF_FILE="xdp_dummy.bpf.o"
+BPF_FILE="lib/xdp_dummy.bpf.o"
readonly BASE="ns-$(mktemp -u XXXXXX)"
readonly SRC=2
readonly DST=1
diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh
index 6bb7dfaa30b6..9709dd067c72 100755
--- a/tools/testing/selftests/net/veth.sh
+++ b/tools/testing/selftests/net/veth.sh
@@ -1,7 +1,7 @@
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
-BPF_FILE="xdp_dummy.bpf.o"
+BPF_FILE="lib/xdp_dummy.bpf.o"
readonly STATS="$(mktemp -p /tmp ns-XXXXXX)"
readonly BASE=`basename $STATS`
readonly SRC=2
diff --git a/tools/testing/selftests/net/xdp_dummy.bpf.c b/tools/testing/selftests/net/xdp_dummy.bpf.c
deleted file mode 100644
index d988b2e0cee8..000000000000
--- a/tools/testing/selftests/net/xdp_dummy.bpf.c
+++ /dev/null
@@ -1,13 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-#define KBUILD_MODNAME "xdp_dummy"
-#include <linux/bpf.h>
-#include <bpf/bpf_helpers.h>
-
-SEC("xdp")
-int xdp_dummy_prog(struct xdp_md *ctx)
-{
- return XDP_PASS;
-}
-
-char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/net/ynl.mk b/tools/testing/selftests/net/ynl.mk
index 12e7cae251be..e907c2751956 100644
--- a/tools/testing/selftests/net/ynl.mk
+++ b/tools/testing/selftests/net/ynl.mk
@@ -27,7 +27,8 @@ $(OUTPUT)/.libynl-$(YNL_GENS_HASH).sig:
$(OUTPUT)/libynl.a: $(YNL_SPECS) $(OUTPUT)/.libynl-$(YNL_GENS_HASH).sig
$(Q)rm -f $(top_srcdir)/tools/net/ynl/libynl.a
- $(Q)$(MAKE) -C $(top_srcdir)/tools/net/ynl GENS="$(YNL_GENS)" libynl.a
+ $(Q)$(MAKE) -C $(top_srcdir)/tools/net/ynl \
+ GENS="$(YNL_GENS)" RSTS="" libynl.a
$(Q)cp $(top_srcdir)/tools/net/ynl/libynl.a $(OUTPUT)/libynl.a
EXTRA_CLEAN += \