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/Makefile13
-rw-r--r--tools/testing/selftests/net/af_unix/Makefile2
-rw-r--r--tools/testing/selftests/net/af_unix/msg_oob.c142
-rw-r--r--tools/testing/selftests/net/af_unix/scm_inq.c125
-rw-r--r--tools/testing/selftests/net/af_unix/scm_pidfd.c217
-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
-rw-r--r--tools/testing/selftests/net/bench/Makefile7
-rw-r--r--tools/testing/selftests/net/bench/page_pool/Makefile17
-rw-r--r--tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c267
-rw-r--r--tools/testing/selftests/net/bench/page_pool/time_bench.c394
-rw-r--r--tools/testing/selftests/net/bench/page_pool/time_bench.h238
-rwxr-xr-xtools/testing/selftests/net/bench/test_bench_page_pool.sh32
-rwxr-xr-xtools/testing/selftests/net/broadcast_pmtu.sh47
-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
-rw-r--r--tools/testing/selftests/net/config12
-rwxr-xr-xtools/testing/selftests/net/fib_rule_tests.sh37
-rwxr-xr-xtools/testing/selftests/net/fib_tests.sh123
-rw-r--r--tools/testing/selftests/net/forwarding/Makefile1
-rwxr-xr-xtools/testing/selftests/net/forwarding/bridge_igmp.sh80
-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.sh69
-rwxr-xr-xtools/testing/selftests/net/forwarding/router_multicast.sh35
-rwxr-xr-xtools/testing/selftests/net/forwarding/tc_flower.sh52
-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_1q_mc_ul.sh771
-rwxr-xr-xtools/testing/selftests/net/gre_ipv6_lladdr.sh184
-rwxr-xr-xtools/testing/selftests/net/icmp_redirect.sh2
-rwxr-xr-xtools/testing/selftests/net/ipv6_force_forwarding.sh105
-rwxr-xr-xtools/testing/selftests/net/ipv6_route_update_soft_lockup.sh1
-rw-r--r--tools/testing/selftests/net/lib.sh109
-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__.py2
-rw-r--r--tools/testing/selftests/net/lib/py/ksft.py31
-rw-r--r--tools/testing/selftests/net/lib/py/utils.py39
-rw-r--r--tools/testing/selftests/net/lib/py/ynl.py9
-rw-r--r--tools/testing/selftests/net/lib/xdp_helper.c131
-rw-r--r--tools/testing/selftests/net/lib/xdp_native.bpf.c621
-rw-r--r--tools/testing/selftests/net/mptcp/Makefile5
-rw-r--r--tools/testing/selftests/net/mptcp/config2
-rwxr-xr-xtools/testing/selftests/net/mptcp/diag.sh37
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_connect.c21
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_connect_checksum.sh5
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_connect_mmap.sh5
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_connect_sendfile.sh5
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_diag.c231
-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
-rw-r--r--tools/testing/selftests/net/msg_zerocopy.c24
-rwxr-xr-xtools/testing/selftests/net/msg_zerocopy.sh84
-rwxr-xr-xtools/testing/selftests/net/nat6to4.sh15
-rw-r--r--tools/testing/selftests/net/net_helper.sh25
-rwxr-xr-xtools/testing/selftests/net/netdev-l2addr.sh59
-rw-r--r--tools/testing/selftests/net/netfilter/.gitignore1
-rw-r--r--tools/testing/selftests/net/netfilter/Makefile5
-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/config8
-rwxr-xr-xtools/testing/selftests/net/netfilter/conntrack_clash.sh174
-rwxr-xr-xtools/testing/selftests/net/netfilter/conntrack_resize.sh514
-rwxr-xr-xtools/testing/selftests/net/netfilter/conntrack_vrf.sh37
-rwxr-xr-xtools/testing/selftests/net/netfilter/ipvs.sh8
-rwxr-xr-xtools/testing/selftests/net/netfilter/nft_concat_range.sh307
-rwxr-xr-xtools/testing/selftests/net/netfilter/nft_fib.sh635
-rwxr-xr-xtools/testing/selftests/net/netfilter/nft_interface_stress.sh157
-rwxr-xr-xtools/testing/selftests/net/netfilter/nft_nat.sh81
-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
-rw-r--r--tools/testing/selftests/net/netfilter/udpclash.c158
-rwxr-xr-xtools/testing/selftests/net/netns-name.sh13
-rw-r--r--tools/testing/selftests/net/nettest.c12
-rwxr-xr-xtools/testing/selftests/net/nl_netdev.py127
-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.c2384
-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-large-mtu.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/packetdrill/ksft_runner.sh4
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt2
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_dsack_mult.pkt45
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt3
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt3
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_ooo-before-and-after-accept.pkt53
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_ooo_rcv_mss.pkt27
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt44
-rw-r--r--tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt33
-rwxr-xr-xtools/testing/selftests/net/pmtu.sh1
-rw-r--r--tools/testing/selftests/net/reuseport_addr_any.c36
-rwxr-xr-xtools/testing/selftests/net/rtnetlink.py4
-rwxr-xr-xtools/testing/selftests/net/rtnetlink.sh92
-rwxr-xr-xtools/testing/selftests/net/rtnetlink_notification.sh112
-rw-r--r--tools/testing/selftests/net/skf_net_off.c244
-rwxr-xr-xtools/testing/selftests/net/skf_net_off.sh30
-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.sh79
-rwxr-xr-xtools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh133
-rwxr-xr-xtools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh76
-rwxr-xr-xtools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh85
-rw-r--r--tools/testing/selftests/net/tcp_ao/self-connect.c3
-rw-r--r--tools/testing/selftests/net/tcp_ao/seq-ext.c2
-rwxr-xr-xtools/testing/selftests/net/test_bridge_neigh_suppress.sh125
-rwxr-xr-xtools/testing/selftests/net/test_neigh.sh366
-rwxr-xr-xtools/testing/selftests/net/test_vxlan_vnifiltering.sh9
-rw-r--r--tools/testing/selftests/net/tfo.c171
-rwxr-xr-xtools/testing/selftests/net/tfo_passive.sh112
-rw-r--r--tools/testing/selftests/net/tls.c36
-rwxr-xr-xtools/testing/selftests/net/udpgro.sh10
-rwxr-xr-xtools/testing/selftests/net/udpgro_bench.sh2
-rwxr-xr-xtools/testing/selftests/net/udpgro_frglist.sh2
-rwxr-xr-xtools/testing/selftests/net/udpgro_fwd.sh2
-rwxr-xr-xtools/testing/selftests/net/vlan_hw_filter.sh98
-rwxr-xr-xtools/testing/selftests/net/vrf_route_leaking.sh4
138 files changed, 12215 insertions, 725 deletions
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 679542f565a4..47c293c2962f 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -34,11 +34,13 @@ reuseport_bpf_numa
reuseport_dualstack
rxtimestamp
sctp_hello
+scm_inq
scm_pidfd
scm_rights
sk_bind_sendto_listen
sk_connect_zero_addr
sk_so_peek_off
+skf_net_off
socket
so_incoming_cpu
so_netns_cookie
@@ -49,6 +51,7 @@ tap
tcp_fastopen_backup_key
tcp_inq
tcp_mmap
+tfo
timestamping
tls
toeplitz
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 6d718b478ed8..b31a71f2b372 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -27,10 +27,12 @@ TEST_PROGS += amt.sh
TEST_PROGS += unicast_extensions.sh
TEST_PROGS += udpgro_fwd.sh
TEST_PROGS += udpgro_frglist.sh
+TEST_PROGS += nat6to4.sh
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 += test_so_rcv.sh
@@ -39,6 +41,7 @@ TEST_PROGS += netns-name.sh
TEST_PROGS += link_netns.py
TEST_PROGS += nl_netdev.py
TEST_PROGS += rtnetlink.py
+TEST_PROGS += rtnetlink_notification.sh
TEST_PROGS += srv6_end_dt46_l3vpn_test.sh
TEST_PROGS += srv6_end_dt4_l3vpn_test.sh
TEST_PROGS += srv6_end_dt6_l3vpn_test.sh
@@ -60,6 +63,7 @@ TEST_PROGS += ip_local_port_range.sh
TEST_PROGS += rps_default_mask.sh
TEST_PROGS += big_tcp.sh
TEST_PROGS += netns-sysctl.sh
+TEST_PROGS += netdev-l2addr.sh
TEST_PROGS_EXTENDED := toeplitz_client.sh toeplitz.sh xfrm_policy_add_speed.sh
TEST_GEN_FILES = socket nettest
TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
@@ -97,6 +101,7 @@ TEST_PROGS += test_vxlan_mdb.sh
TEST_PROGS += test_bridge_neigh_suppress.sh
TEST_PROGS += test_vxlan_nolocalbypass.sh
TEST_PROGS += test_bridge_backup_port.sh
+TEST_PROGS += test_neigh.sh
TEST_PROGS += fdb_flush.sh fdb_notify.sh
TEST_PROGS += fq_band_pktlimit.sh
TEST_PROGS += vlan_hw_filter.sh
@@ -106,13 +111,19 @@ 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
+TEST_GEN_FILES += tfo
+TEST_PROGS += tfo_passive.sh
+TEST_PROGS += broadcast_pmtu.sh
+TEST_PROGS += ipv6_force_forwarding.sh
# 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/Makefile b/tools/testing/selftests/net/af_unix/Makefile
index 50584479540b..a4b61c6d0290 100644
--- a/tools/testing/selftests/net/af_unix/Makefile
+++ b/tools/testing/selftests/net/af_unix/Makefile
@@ -1,4 +1,4 @@
CFLAGS += $(KHDR_INCLUDES)
-TEST_GEN_PROGS := diag_uid msg_oob scm_pidfd scm_rights unix_connect
+TEST_GEN_PROGS := diag_uid msg_oob scm_inq scm_pidfd scm_rights unix_connect
include ../../lib.mk
diff --git a/tools/testing/selftests/net/af_unix/msg_oob.c b/tools/testing/selftests/net/af_unix/msg_oob.c
index 3ed3882a93b8..b5f474969917 100644
--- a/tools/testing/selftests/net/af_unix/msg_oob.c
+++ b/tools/testing/selftests/net/af_unix/msg_oob.c
@@ -210,7 +210,7 @@ static void __sendpair(struct __test_metadata *_metadata,
static void __recvpair(struct __test_metadata *_metadata,
FIXTURE_DATA(msg_oob) *self,
const char *expected_buf, int expected_len,
- int buf_len, int flags)
+ int buf_len, int flags, bool is_sender)
{
int i, ret[2], recv_errno[2], expected_errno = 0;
char recv_buf[2][BUF_SZ] = {};
@@ -221,7 +221,9 @@ static void __recvpair(struct __test_metadata *_metadata,
errno = 0;
for (i = 0; i < 2; i++) {
- ret[i] = recv(self->fd[i * 2 + 1], recv_buf[i], buf_len, flags);
+ int index = is_sender ? i * 2 : i * 2 + 1;
+
+ ret[i] = recv(self->fd[index], recv_buf[i], buf_len, flags);
recv_errno[i] = errno;
}
@@ -308,6 +310,20 @@ static void __siocatmarkpair(struct __test_metadata *_metadata,
ASSERT_EQ(answ[0], answ[1]);
}
+static void __resetpair(struct __test_metadata *_metadata,
+ FIXTURE_DATA(msg_oob) *self,
+ const FIXTURE_VARIANT(msg_oob) *variant,
+ bool reset)
+{
+ int i;
+
+ for (i = 0; i < 2; i++)
+ close(self->fd[i * 2 + 1]);
+
+ __recvpair(_metadata, self, "", reset ? -ECONNRESET : 0, 1,
+ variant->peek ? MSG_PEEK : 0, true);
+}
+
#define sendpair(buf, len, flags) \
__sendpair(_metadata, self, buf, len, flags)
@@ -316,9 +332,10 @@ static void __siocatmarkpair(struct __test_metadata *_metadata,
if (variant->peek) \
__recvpair(_metadata, self, \
expected_buf, expected_len, \
- buf_len, (flags) | MSG_PEEK); \
+ buf_len, (flags) | MSG_PEEK, false); \
__recvpair(_metadata, self, \
- expected_buf, expected_len, buf_len, flags); \
+ expected_buf, expected_len, \
+ buf_len, flags, false); \
} while (0)
#define epollpair(oob_remaining) \
@@ -330,6 +347,9 @@ static void __siocatmarkpair(struct __test_metadata *_metadata,
#define setinlinepair() \
__setinlinepair(_metadata, self)
+#define resetpair(reset) \
+ __resetpair(_metadata, self, variant, reset)
+
#define tcp_incompliant \
for (self->tcp_compliant = false; \
self->tcp_compliant == false; \
@@ -344,6 +364,21 @@ TEST_F(msg_oob, non_oob)
recvpair("", -EINVAL, 1, MSG_OOB);
epollpair(false);
siocatmarkpair(false);
+
+ resetpair(true);
+}
+
+TEST_F(msg_oob, non_oob_no_reset)
+{
+ sendpair("x", 1, 0);
+ epollpair(false);
+ siocatmarkpair(false);
+
+ recvpair("x", 1, 1, 0);
+ epollpair(false);
+ siocatmarkpair(false);
+
+ resetpair(false);
}
TEST_F(msg_oob, oob)
@@ -355,6 +390,19 @@ TEST_F(msg_oob, oob)
recvpair("x", 1, 1, MSG_OOB);
epollpair(false);
siocatmarkpair(true);
+
+ tcp_incompliant {
+ resetpair(false); /* TCP sets -ECONNRESET for ex-OOB. */
+ }
+}
+
+TEST_F(msg_oob, oob_reset)
+{
+ sendpair("x", 1, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(true);
+
+ resetpair(true);
}
TEST_F(msg_oob, oob_drop)
@@ -370,6 +418,8 @@ TEST_F(msg_oob, oob_drop)
recvpair("", -EINVAL, 1, MSG_OOB);
epollpair(false);
siocatmarkpair(false);
+
+ resetpair(false);
}
TEST_F(msg_oob, oob_ahead)
@@ -385,6 +435,10 @@ TEST_F(msg_oob, oob_ahead)
recvpair("hell", 4, 4, 0);
epollpair(false);
siocatmarkpair(true);
+
+ tcp_incompliant {
+ resetpair(false); /* TCP sets -ECONNRESET for ex-OOB. */
+ }
}
TEST_F(msg_oob, oob_break)
@@ -403,6 +457,8 @@ TEST_F(msg_oob, oob_break)
recvpair("", -EAGAIN, 1, 0);
siocatmarkpair(false);
+
+ resetpair(false);
}
TEST_F(msg_oob, oob_ahead_break)
@@ -426,6 +482,8 @@ TEST_F(msg_oob, oob_ahead_break)
recvpair("world", 5, 5, 0);
epollpair(false);
siocatmarkpair(false);
+
+ resetpair(false);
}
TEST_F(msg_oob, oob_break_drop)
@@ -449,6 +507,8 @@ TEST_F(msg_oob, oob_break_drop)
recvpair("", -EINVAL, 1, MSG_OOB);
epollpair(false);
siocatmarkpair(false);
+
+ resetpair(false);
}
TEST_F(msg_oob, ex_oob_break)
@@ -476,6 +536,8 @@ TEST_F(msg_oob, ex_oob_break)
recvpair("ld", 2, 2, 0);
epollpair(false);
siocatmarkpair(false);
+
+ resetpair(false);
}
TEST_F(msg_oob, ex_oob_drop)
@@ -498,6 +560,8 @@ TEST_F(msg_oob, ex_oob_drop)
epollpair(false);
siocatmarkpair(true);
}
+
+ resetpair(false);
}
TEST_F(msg_oob, ex_oob_drop_2)
@@ -523,6 +587,8 @@ TEST_F(msg_oob, ex_oob_drop_2)
epollpair(false);
siocatmarkpair(true);
}
+
+ resetpair(false);
}
TEST_F(msg_oob, ex_oob_oob)
@@ -546,6 +612,54 @@ TEST_F(msg_oob, ex_oob_oob)
recvpair("", -EINVAL, 1, MSG_OOB);
epollpair(false);
siocatmarkpair(false);
+
+ resetpair(false);
+}
+
+TEST_F(msg_oob, ex_oob_ex_oob)
+{
+ sendpair("x", 1, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(true);
+
+ recvpair("x", 1, 1, MSG_OOB);
+ epollpair(false);
+ siocatmarkpair(true);
+
+ sendpair("y", 1, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(true);
+
+ recvpair("y", 1, 1, MSG_OOB);
+ epollpair(false);
+ siocatmarkpair(true);
+
+ tcp_incompliant {
+ resetpair(false); /* TCP sets -ECONNRESET for ex-OOB. */
+ }
+}
+
+TEST_F(msg_oob, ex_oob_ex_oob_oob)
+{
+ sendpair("x", 1, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(true);
+
+ recvpair("x", 1, 1, MSG_OOB);
+ epollpair(false);
+ siocatmarkpair(true);
+
+ sendpair("y", 1, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(true);
+
+ recvpair("y", 1, 1, MSG_OOB);
+ epollpair(false);
+ siocatmarkpair(true);
+
+ sendpair("z", 1, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(true);
}
TEST_F(msg_oob, ex_oob_ahead_break)
@@ -576,6 +690,10 @@ TEST_F(msg_oob, ex_oob_ahead_break)
recvpair("d", 1, 1, MSG_OOB);
epollpair(false);
siocatmarkpair(true);
+
+ tcp_incompliant {
+ resetpair(false); /* TCP sets -ECONNRESET for ex-OOB. */
+ }
}
TEST_F(msg_oob, ex_oob_siocatmark)
@@ -595,6 +713,8 @@ TEST_F(msg_oob, ex_oob_siocatmark)
recvpair("hell", 4, 4, 0); /* Intentionally stop at ex-OOB. */
epollpair(true);
siocatmarkpair(false);
+
+ resetpair(true);
}
TEST_F(msg_oob, inline_oob)
@@ -612,6 +732,8 @@ TEST_F(msg_oob, inline_oob)
recvpair("x", 1, 1, 0);
epollpair(false);
siocatmarkpair(false);
+
+ resetpair(false);
}
TEST_F(msg_oob, inline_oob_break)
@@ -633,6 +755,8 @@ TEST_F(msg_oob, inline_oob_break)
recvpair("o", 1, 1, 0);
epollpair(false);
siocatmarkpair(false);
+
+ resetpair(false);
}
TEST_F(msg_oob, inline_oob_ahead_break)
@@ -661,6 +785,8 @@ TEST_F(msg_oob, inline_oob_ahead_break)
epollpair(false);
siocatmarkpair(false);
+
+ resetpair(false);
}
TEST_F(msg_oob, inline_ex_oob_break)
@@ -686,6 +812,8 @@ TEST_F(msg_oob, inline_ex_oob_break)
recvpair("rld", 3, 3, 0);
epollpair(false);
siocatmarkpair(false);
+
+ resetpair(false);
}
TEST_F(msg_oob, inline_ex_oob_no_drop)
@@ -707,6 +835,8 @@ TEST_F(msg_oob, inline_ex_oob_no_drop)
recvpair("y", 1, 1, 0);
epollpair(false);
siocatmarkpair(false);
+
+ resetpair(false);
}
TEST_F(msg_oob, inline_ex_oob_drop)
@@ -731,6 +861,8 @@ TEST_F(msg_oob, inline_ex_oob_drop)
epollpair(false);
siocatmarkpair(false);
}
+
+ resetpair(false);
}
TEST_F(msg_oob, inline_ex_oob_siocatmark)
@@ -752,6 +884,8 @@ TEST_F(msg_oob, inline_ex_oob_siocatmark)
recvpair("hell", 4, 4, 0); /* Intentionally stop at ex-OOB. */
epollpair(true);
siocatmarkpair(false);
+
+ resetpair(true);
}
TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/net/af_unix/scm_inq.c b/tools/testing/selftests/net/af_unix/scm_inq.c
new file mode 100644
index 000000000000..9d22561e7b8f
--- /dev/null
+++ b/tools/testing/selftests/net/af_unix/scm_inq.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright 2025 Google LLC */
+
+#include <linux/sockios.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+
+#include "../../kselftest_harness.h"
+
+#define NR_CHUNKS 100
+#define MSG_LEN 256
+
+struct scm_inq {
+ struct cmsghdr cmsghdr;
+ int inq;
+};
+
+FIXTURE(scm_inq)
+{
+ int fd[2];
+};
+
+FIXTURE_VARIANT(scm_inq)
+{
+ int type;
+};
+
+FIXTURE_VARIANT_ADD(scm_inq, stream)
+{
+ .type = SOCK_STREAM,
+};
+
+FIXTURE_VARIANT_ADD(scm_inq, dgram)
+{
+ .type = SOCK_DGRAM,
+};
+
+FIXTURE_VARIANT_ADD(scm_inq, seqpacket)
+{
+ .type = SOCK_SEQPACKET,
+};
+
+FIXTURE_SETUP(scm_inq)
+{
+ int err;
+
+ err = socketpair(AF_UNIX, variant->type | SOCK_NONBLOCK, 0, self->fd);
+ ASSERT_EQ(0, err);
+}
+
+FIXTURE_TEARDOWN(scm_inq)
+{
+ close(self->fd[0]);
+ close(self->fd[1]);
+}
+
+static void send_chunks(struct __test_metadata *_metadata,
+ FIXTURE_DATA(scm_inq) *self)
+{
+ char buf[MSG_LEN] = {};
+ int i, ret;
+
+ for (i = 0; i < NR_CHUNKS; i++) {
+ ret = send(self->fd[0], buf, sizeof(buf), 0);
+ ASSERT_EQ(sizeof(buf), ret);
+ }
+}
+
+static void recv_chunks(struct __test_metadata *_metadata,
+ FIXTURE_DATA(scm_inq) *self)
+{
+ struct msghdr msg = {};
+ struct iovec iov = {};
+ struct scm_inq cmsg;
+ char buf[MSG_LEN];
+ int i, ret;
+ int inq;
+
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+ msg.msg_control = &cmsg;
+ msg.msg_controllen = CMSG_SPACE(sizeof(cmsg.inq));
+
+ iov.iov_base = buf;
+ iov.iov_len = sizeof(buf);
+
+ for (i = 0; i < NR_CHUNKS; i++) {
+ memset(buf, 0, sizeof(buf));
+ memset(&cmsg, 0, sizeof(cmsg));
+
+ ret = recvmsg(self->fd[1], &msg, 0);
+ ASSERT_EQ(MSG_LEN, ret);
+ ASSERT_NE(NULL, CMSG_FIRSTHDR(&msg));
+ ASSERT_EQ(CMSG_LEN(sizeof(cmsg.inq)), cmsg.cmsghdr.cmsg_len);
+ ASSERT_EQ(SOL_SOCKET, cmsg.cmsghdr.cmsg_level);
+ ASSERT_EQ(SCM_INQ, cmsg.cmsghdr.cmsg_type);
+
+ ret = ioctl(self->fd[1], SIOCINQ, &inq);
+ ASSERT_EQ(0, ret);
+ ASSERT_EQ(cmsg.inq, inq);
+ }
+}
+
+TEST_F(scm_inq, basic)
+{
+ int err, inq;
+
+ err = setsockopt(self->fd[1], SOL_SOCKET, SO_INQ, &(int){1}, sizeof(int));
+ if (variant->type != SOCK_STREAM) {
+ ASSERT_EQ(-ENOPROTOOPT, -errno);
+ return;
+ }
+
+ ASSERT_EQ(0, err);
+
+ err = ioctl(self->fd[1], SIOCINQ, &inq);
+ ASSERT_EQ(0, err);
+ ASSERT_EQ(0, inq);
+
+ send_chunks(_metadata, self);
+ recv_chunks(_metadata, self);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/net/af_unix/scm_pidfd.c b/tools/testing/selftests/net/af_unix/scm_pidfd.c
index 7e534594167e..37e034874034 100644
--- a/tools/testing/selftests/net/af_unix/scm_pidfd.c
+++ b/tools/testing/selftests/net/af_unix/scm_pidfd.c
@@ -15,6 +15,7 @@
#include <sys/types.h>
#include <sys/wait.h>
+#include "../../pidfd/pidfd.h"
#include "../../kselftest_harness.h"
#define clean_errno() (errno == 0 ? "None" : strerror(errno))
@@ -26,6 +27,8 @@
#define SCM_PIDFD 0x04
#endif
+#define CHILD_EXIT_CODE_OK 123
+
static void child_die()
{
exit(1);
@@ -126,16 +129,65 @@ out:
return result;
}
+struct cmsg_data {
+ struct ucred *ucred;
+ int *pidfd;
+};
+
+static int parse_cmsg(struct msghdr *msg, struct cmsg_data *res)
+{
+ struct cmsghdr *cmsg;
+ int data = 0;
+
+ if (msg->msg_flags & (MSG_TRUNC | MSG_CTRUNC)) {
+ log_err("recvmsg: truncated");
+ return 1;
+ }
+
+ for (cmsg = CMSG_FIRSTHDR(msg); cmsg != NULL;
+ cmsg = CMSG_NXTHDR(msg, cmsg)) {
+ if (cmsg->cmsg_level == SOL_SOCKET &&
+ cmsg->cmsg_type == SCM_PIDFD) {
+ if (cmsg->cmsg_len < sizeof(*res->pidfd)) {
+ log_err("CMSG parse: SCM_PIDFD wrong len");
+ return 1;
+ }
+
+ res->pidfd = (void *)CMSG_DATA(cmsg);
+ }
+
+ if (cmsg->cmsg_level == SOL_SOCKET &&
+ cmsg->cmsg_type == SCM_CREDENTIALS) {
+ if (cmsg->cmsg_len < sizeof(*res->ucred)) {
+ log_err("CMSG parse: SCM_CREDENTIALS wrong len");
+ return 1;
+ }
+
+ res->ucred = (void *)CMSG_DATA(cmsg);
+ }
+ }
+
+ if (!res->pidfd) {
+ log_err("CMSG parse: SCM_PIDFD not found");
+ return 1;
+ }
+
+ if (!res->ucred) {
+ log_err("CMSG parse: SCM_CREDENTIALS not found");
+ return 1;
+ }
+
+ return 0;
+}
+
static int cmsg_check(int fd)
{
struct msghdr msg = { 0 };
- struct cmsghdr *cmsg;
+ struct cmsg_data res;
struct iovec iov;
- struct ucred *ucred = NULL;
int data = 0;
char control[CMSG_SPACE(sizeof(struct ucred)) +
CMSG_SPACE(sizeof(int))] = { 0 };
- int *pidfd = NULL;
pid_t parent_pid;
int err;
@@ -158,53 +210,99 @@ static int cmsg_check(int fd)
return 1;
}
- for (cmsg = CMSG_FIRSTHDR(&msg); cmsg != NULL;
- cmsg = CMSG_NXTHDR(&msg, cmsg)) {
- if (cmsg->cmsg_level == SOL_SOCKET &&
- cmsg->cmsg_type == SCM_PIDFD) {
- if (cmsg->cmsg_len < sizeof(*pidfd)) {
- log_err("CMSG parse: SCM_PIDFD wrong len");
- return 1;
- }
+ /* send(pfd, "x", sizeof(char), 0) */
+ if (data != 'x') {
+ log_err("recvmsg: data corruption");
+ return 1;
+ }
- pidfd = (void *)CMSG_DATA(cmsg);
- }
+ if (parse_cmsg(&msg, &res)) {
+ log_err("CMSG parse: parse_cmsg() failed");
+ return 1;
+ }
- if (cmsg->cmsg_level == SOL_SOCKET &&
- cmsg->cmsg_type == SCM_CREDENTIALS) {
- if (cmsg->cmsg_len < sizeof(*ucred)) {
- log_err("CMSG parse: SCM_CREDENTIALS wrong len");
- return 1;
- }
+ /* pidfd from SCM_PIDFD should point to the parent process PID */
+ parent_pid =
+ get_pid_from_fdinfo_file(*res.pidfd, "Pid:", sizeof("Pid:") - 1);
+ if (parent_pid != getppid()) {
+ log_err("wrong SCM_PIDFD %d != %d", parent_pid, getppid());
+ close(*res.pidfd);
+ return 1;
+ }
- ucred = (void *)CMSG_DATA(cmsg);
- }
+ close(*res.pidfd);
+ return 0;
+}
+
+static int cmsg_check_dead(int fd, int expected_pid)
+{
+ int err;
+ struct msghdr msg = { 0 };
+ struct cmsg_data res;
+ struct iovec iov;
+ int data = 0;
+ char control[CMSG_SPACE(sizeof(struct ucred)) +
+ CMSG_SPACE(sizeof(int))] = { 0 };
+ pid_t client_pid;
+ struct pidfd_info info = {
+ .mask = PIDFD_INFO_EXIT,
+ };
+
+ iov.iov_base = &data;
+ iov.iov_len = sizeof(data);
+
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+ msg.msg_control = control;
+ msg.msg_controllen = sizeof(control);
+
+ err = recvmsg(fd, &msg, 0);
+ if (err < 0) {
+ log_err("recvmsg");
+ return 1;
}
- /* send(pfd, "x", sizeof(char), 0) */
- if (data != 'x') {
+ if (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)) {
+ log_err("recvmsg: truncated");
+ return 1;
+ }
+
+ /* send(cfd, "y", sizeof(char), 0) */
+ if (data != 'y') {
log_err("recvmsg: data corruption");
return 1;
}
- if (!pidfd) {
- log_err("CMSG parse: SCM_PIDFD not found");
+ if (parse_cmsg(&msg, &res)) {
+ log_err("CMSG parse: parse_cmsg() failed");
return 1;
}
- if (!ucred) {
- log_err("CMSG parse: SCM_CREDENTIALS not found");
+ /*
+ * pidfd from SCM_PIDFD should point to the client_pid.
+ * Let's read exit information and check if it's what
+ * we expect to see.
+ */
+ if (ioctl(*res.pidfd, PIDFD_GET_INFO, &info)) {
+ log_err("%s: ioctl(PIDFD_GET_INFO) failed", __func__);
+ close(*res.pidfd);
return 1;
}
- /* pidfd from SCM_PIDFD should point to the parent process PID */
- parent_pid =
- get_pid_from_fdinfo_file(*pidfd, "Pid:", sizeof("Pid:") - 1);
- if (parent_pid != getppid()) {
- log_err("wrong SCM_PIDFD %d != %d", parent_pid, getppid());
+ if (!(info.mask & PIDFD_INFO_EXIT)) {
+ log_err("%s: No exit information from ioctl(PIDFD_GET_INFO)", __func__);
+ close(*res.pidfd);
return 1;
}
+ err = WIFEXITED(info.exit_code) ? WEXITSTATUS(info.exit_code) : 1;
+ if (err != CHILD_EXIT_CODE_OK) {
+ log_err("%s: wrong exit_code %d != %d", __func__, err, CHILD_EXIT_CODE_OK);
+ close(*res.pidfd);
+ return 1;
+ }
+
+ close(*res.pidfd);
return 0;
}
@@ -291,6 +389,24 @@ static void fill_sockaddr(struct sock_addr *addr, bool abstract)
memcpy(sun_path_buf, addr->sock_name, strlen(addr->sock_name));
}
+static int sk_enable_cred_pass(int sk)
+{
+ int on = 0;
+
+ on = 1;
+ if (setsockopt(sk, SOL_SOCKET, SO_PASSCRED, &on, sizeof(on))) {
+ log_err("Failed to set SO_PASSCRED");
+ return 1;
+ }
+
+ if (setsockopt(sk, SOL_SOCKET, SO_PASSPIDFD, &on, sizeof(on))) {
+ log_err("Failed to set SO_PASSPIDFD");
+ return 1;
+ }
+
+ return 0;
+}
+
static void client(FIXTURE_DATA(scm_pidfd) *self,
const FIXTURE_VARIANT(scm_pidfd) *variant)
{
@@ -299,7 +415,6 @@ static void client(FIXTURE_DATA(scm_pidfd) *self,
struct ucred peer_cred;
int peer_pidfd;
pid_t peer_pid;
- int on = 0;
cfd = socket(AF_UNIX, variant->type, 0);
if (cfd < 0) {
@@ -322,14 +437,8 @@ static void client(FIXTURE_DATA(scm_pidfd) *self,
child_die();
}
- on = 1;
- if (setsockopt(cfd, SOL_SOCKET, SO_PASSCRED, &on, sizeof(on))) {
- log_err("Failed to set SO_PASSCRED");
- child_die();
- }
-
- if (setsockopt(cfd, SOL_SOCKET, SO_PASSPIDFD, &on, sizeof(on))) {
- log_err("Failed to set SO_PASSPIDFD");
+ if (sk_enable_cred_pass(cfd)) {
+ log_err("sk_enable_cred_pass() failed");
child_die();
}
@@ -340,6 +449,12 @@ static void client(FIXTURE_DATA(scm_pidfd) *self,
child_die();
}
+ /* send something to the parent so it can receive SCM_PIDFD too and validate it */
+ if (send(cfd, "y", sizeof(char), 0) == -1) {
+ log_err("Failed to send(cfd, \"y\", sizeof(char), 0)");
+ child_die();
+ }
+
/* skip further for SOCK_DGRAM as it's not applicable */
if (variant->type == SOCK_DGRAM)
return;
@@ -398,7 +513,13 @@ TEST_F(scm_pidfd, test)
close(self->server);
close(self->startup_pipe[0]);
client(self, variant);
- exit(0);
+
+ /*
+ * It's a bit unusual, but in case of success we return non-zero
+ * exit code (CHILD_EXIT_CODE_OK) and then we expect to read it
+ * from ioctl(PIDFD_GET_INFO) in cmsg_check_dead().
+ */
+ exit(CHILD_EXIT_CODE_OK);
}
close(self->startup_pipe[1]);
@@ -421,9 +542,17 @@ TEST_F(scm_pidfd, test)
ASSERT_NE(-1, err);
}
- close(pfd);
waitpid(self->client_pid, &child_status, 0);
- ASSERT_EQ(0, WIFEXITED(child_status) ? WEXITSTATUS(child_status) : 1);
+ /* see comment before exit(CHILD_EXIT_CODE_OK) */
+ ASSERT_EQ(CHILD_EXIT_CODE_OK, WIFEXITED(child_status) ? WEXITSTATUS(child_status) : 1);
+
+ err = sk_enable_cred_pass(pfd);
+ ASSERT_EQ(0, err);
+
+ err = cmsg_check_dead(pfd, self->client_pid);
+ ASSERT_EQ(0, err);
+
+ close(pfd);
}
TEST_HARNESS_MAIN
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/bench/Makefile b/tools/testing/selftests/net/bench/Makefile
new file mode 100644
index 000000000000..2546c45e42f7
--- /dev/null
+++ b/tools/testing/selftests/net/bench/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+
+TEST_GEN_MODS_DIR := page_pool
+
+TEST_PROGS += test_bench_page_pool.sh
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/net/bench/page_pool/Makefile b/tools/testing/selftests/net/bench/page_pool/Makefile
new file mode 100644
index 000000000000..0549a16ba275
--- /dev/null
+++ b/tools/testing/selftests/net/bench/page_pool/Makefile
@@ -0,0 +1,17 @@
+BENCH_PAGE_POOL_SIMPLE_TEST_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST)))))
+KDIR ?= /lib/modules/$(shell uname -r)/build
+
+ifeq ($(V),1)
+Q =
+else
+Q = @
+endif
+
+obj-m += bench_page_pool.o
+bench_page_pool-y += bench_page_pool_simple.o time_bench.o
+
+all:
+ +$(Q)make -C $(KDIR) M=$(BENCH_PAGE_POOL_SIMPLE_TEST_DIR) modules
+
+clean:
+ +$(Q)make -C $(KDIR) M=$(BENCH_PAGE_POOL_SIMPLE_TEST_DIR) clean
diff --git a/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c b/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c
new file mode 100644
index 000000000000..cb6468adbda4
--- /dev/null
+++ b/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c
@@ -0,0 +1,267 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Benchmark module for page_pool.
+ *
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/interrupt.h>
+#include <linux/limits.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <net/page_pool/helpers.h>
+
+#include "time_bench.h"
+
+static int verbose = 1;
+#define MY_POOL_SIZE 1024
+
+/* Makes tests selectable. Useful for perf-record to analyze a single test.
+ * Hint: Bash shells support writing binary number like: $((2#101010)
+ *
+ * # modprobe bench_page_pool_simple run_flags=$((2#100))
+ */
+static unsigned long run_flags = 0xFFFFFFFF;
+module_param(run_flags, ulong, 0);
+MODULE_PARM_DESC(run_flags, "Limit which bench test that runs");
+
+/* Count the bit number from the enum */
+enum benchmark_bit {
+ bit_run_bench_baseline,
+ bit_run_bench_no_softirq01,
+ bit_run_bench_no_softirq02,
+ bit_run_bench_no_softirq03,
+};
+
+#define bit(b) (1 << (b))
+#define enabled(b) ((run_flags & (bit(b))))
+
+/* notice time_bench is limited to U32_MAX nr loops */
+static unsigned long loops = 10000000;
+module_param(loops, ulong, 0);
+MODULE_PARM_DESC(loops, "Specify loops bench will run");
+
+/* Timing at the nanosec level, we need to know the overhead
+ * introduced by the for loop itself
+ */
+static int time_bench_for_loop(struct time_bench_record *rec, void *data)
+{
+ uint64_t loops_cnt = 0;
+ int i;
+
+ time_bench_start(rec);
+ /** Loop to measure **/
+ for (i = 0; i < rec->loops; i++) {
+ loops_cnt++;
+ barrier(); /* avoid compiler to optimize this loop */
+ }
+ time_bench_stop(rec, loops_cnt);
+ return loops_cnt;
+}
+
+static int time_bench_atomic_inc(struct time_bench_record *rec, void *data)
+{
+ uint64_t loops_cnt = 0;
+ atomic_t cnt;
+ int i;
+
+ atomic_set(&cnt, 0);
+
+ time_bench_start(rec);
+ /** Loop to measure **/
+ for (i = 0; i < rec->loops; i++) {
+ atomic_inc(&cnt);
+ barrier(); /* avoid compiler to optimize this loop */
+ }
+ loops_cnt = atomic_read(&cnt);
+ time_bench_stop(rec, loops_cnt);
+ return loops_cnt;
+}
+
+/* The ptr_ping in page_pool uses a spinlock. We need to know the minimum
+ * overhead of taking+releasing a spinlock, to know the cycles that can be saved
+ * by e.g. amortizing this via bulking.
+ */
+static int time_bench_lock(struct time_bench_record *rec, void *data)
+{
+ uint64_t loops_cnt = 0;
+ spinlock_t lock;
+ int i;
+
+ spin_lock_init(&lock);
+
+ time_bench_start(rec);
+ /** Loop to measure **/
+ for (i = 0; i < rec->loops; i++) {
+ spin_lock(&lock);
+ loops_cnt++;
+ barrier(); /* avoid compiler to optimize this loop */
+ spin_unlock(&lock);
+ }
+ time_bench_stop(rec, loops_cnt);
+ return loops_cnt;
+}
+
+/* Helper for filling some page's into ptr_ring */
+static void pp_fill_ptr_ring(struct page_pool *pp, int elems)
+{
+ /* GFP_ATOMIC needed when under run softirq */
+ gfp_t gfp_mask = GFP_ATOMIC;
+ struct page **array;
+ int i;
+
+ array = kcalloc(elems, sizeof(struct page *), gfp_mask);
+
+ for (i = 0; i < elems; i++)
+ array[i] = page_pool_alloc_pages(pp, gfp_mask);
+ for (i = 0; i < elems; i++)
+ page_pool_put_page(pp, array[i], -1, false);
+
+ kfree(array);
+}
+
+enum test_type { type_fast_path, type_ptr_ring, type_page_allocator };
+
+/* Depends on compile optimizing this function */
+static int time_bench_page_pool(struct time_bench_record *rec, void *data,
+ enum test_type type, const char *func)
+{
+ uint64_t loops_cnt = 0;
+ gfp_t gfp_mask = GFP_ATOMIC; /* GFP_ATOMIC is not really needed */
+ int i, err;
+
+ struct page_pool *pp;
+ struct page *page;
+
+ struct page_pool_params pp_params = {
+ .order = 0,
+ .flags = 0,
+ .pool_size = MY_POOL_SIZE,
+ .nid = NUMA_NO_NODE,
+ .dev = NULL, /* Only use for DMA mapping */
+ .dma_dir = DMA_BIDIRECTIONAL,
+ };
+
+ pp = page_pool_create(&pp_params);
+ if (IS_ERR(pp)) {
+ err = PTR_ERR(pp);
+ pr_warn("%s: Error(%d) creating page_pool\n", func, err);
+ goto out;
+ }
+ pp_fill_ptr_ring(pp, 64);
+
+ if (in_serving_softirq())
+ pr_warn("%s(): in_serving_softirq fast-path\n", func);
+ else
+ pr_warn("%s(): Cannot use page_pool fast-path\n", func);
+
+ time_bench_start(rec);
+ /** Loop to measure **/
+ for (i = 0; i < rec->loops; i++) {
+ /* Common fast-path alloc that depend on in_serving_softirq() */
+ page = page_pool_alloc_pages(pp, gfp_mask);
+ if (!page)
+ break;
+ loops_cnt++;
+ barrier(); /* avoid compiler to optimize this loop */
+
+ /* The benchmarks purpose it to test different return paths.
+ * Compiler should inline optimize other function calls out
+ */
+ if (type == type_fast_path) {
+ /* Fast-path recycling e.g. XDP_DROP use-case */
+ page_pool_recycle_direct(pp, page);
+
+ } else if (type == type_ptr_ring) {
+ /* Normal return path */
+ page_pool_put_page(pp, page, -1, false);
+
+ } else if (type == type_page_allocator) {
+ /* Test if not pages are recycled, but instead
+ * returned back into systems page allocator
+ */
+ get_page(page); /* cause no-recycling */
+ page_pool_put_page(pp, page, -1, false);
+ put_page(page);
+ } else {
+ BUILD_BUG();
+ }
+ }
+ time_bench_stop(rec, loops_cnt);
+out:
+ page_pool_destroy(pp);
+ return loops_cnt;
+}
+
+static int time_bench_page_pool01_fast_path(struct time_bench_record *rec,
+ void *data)
+{
+ return time_bench_page_pool(rec, data, type_fast_path, __func__);
+}
+
+static int time_bench_page_pool02_ptr_ring(struct time_bench_record *rec,
+ void *data)
+{
+ return time_bench_page_pool(rec, data, type_ptr_ring, __func__);
+}
+
+static int time_bench_page_pool03_slow(struct time_bench_record *rec,
+ void *data)
+{
+ return time_bench_page_pool(rec, data, type_page_allocator, __func__);
+}
+
+static int run_benchmark_tests(void)
+{
+ uint32_t nr_loops = loops;
+
+ /* Baseline tests */
+ if (enabled(bit_run_bench_baseline)) {
+ time_bench_loop(nr_loops * 10, 0, "for_loop", NULL,
+ time_bench_for_loop);
+ time_bench_loop(nr_loops * 10, 0, "atomic_inc", NULL,
+ time_bench_atomic_inc);
+ time_bench_loop(nr_loops, 0, "lock", NULL, time_bench_lock);
+ }
+
+ /* This test cannot activate correct code path, due to no-softirq ctx */
+ if (enabled(bit_run_bench_no_softirq01))
+ time_bench_loop(nr_loops, 0, "no-softirq-page_pool01", NULL,
+ time_bench_page_pool01_fast_path);
+ if (enabled(bit_run_bench_no_softirq02))
+ time_bench_loop(nr_loops, 0, "no-softirq-page_pool02", NULL,
+ time_bench_page_pool02_ptr_ring);
+ if (enabled(bit_run_bench_no_softirq03))
+ time_bench_loop(nr_loops, 0, "no-softirq-page_pool03", NULL,
+ time_bench_page_pool03_slow);
+
+ return 0;
+}
+
+static int __init bench_page_pool_simple_module_init(void)
+{
+ if (verbose)
+ pr_info("Loaded\n");
+
+ if (loops > U32_MAX) {
+ pr_err("Module param loops(%lu) exceeded U32_MAX(%u)\n", loops,
+ U32_MAX);
+ return -ECHRNG;
+ }
+
+ run_benchmark_tests();
+
+ return 0;
+}
+module_init(bench_page_pool_simple_module_init);
+
+static void __exit bench_page_pool_simple_module_exit(void)
+{
+ if (verbose)
+ pr_info("Unloaded\n");
+}
+module_exit(bench_page_pool_simple_module_exit);
+
+MODULE_DESCRIPTION("Benchmark of page_pool simple cases");
+MODULE_AUTHOR("Jesper Dangaard Brouer <netoptimizer@brouer.com>");
+MODULE_LICENSE("GPL");
diff --git a/tools/testing/selftests/net/bench/page_pool/time_bench.c b/tools/testing/selftests/net/bench/page_pool/time_bench.c
new file mode 100644
index 000000000000..073bb36ec5f2
--- /dev/null
+++ b/tools/testing/selftests/net/bench/page_pool/time_bench.c
@@ -0,0 +1,394 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Benchmarking code execution time inside the kernel
+ *
+ * Copyright (C) 2014, Red Hat, Inc., Jesper Dangaard Brouer
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/time.h>
+
+#include <linux/perf_event.h> /* perf_event_create_kernel_counter() */
+
+/* For concurrency testing */
+#include <linux/completion.h>
+#include <linux/sched.h>
+#include <linux/workqueue.h>
+#include <linux/kthread.h>
+
+#include "time_bench.h"
+
+static int verbose = 1;
+
+/** TSC (Time-Stamp Counter) based **
+ * See: linux/time_bench.h
+ * tsc_start_clock() and tsc_stop_clock()
+ */
+
+/** Wall-clock based **
+ */
+
+/** PMU (Performance Monitor Unit) based **
+ */
+#define PERF_FORMAT \
+ (PERF_FORMAT_GROUP | PERF_FORMAT_ID | PERF_FORMAT_TOTAL_TIME_ENABLED | \
+ PERF_FORMAT_TOTAL_TIME_RUNNING)
+
+struct raw_perf_event {
+ uint64_t config; /* event */
+ uint64_t config1; /* umask */
+ struct perf_event *save;
+ char *desc;
+};
+
+/* if HT is enable a maximum of 4 events (5 if one is instructions
+ * retired can be specified, if HT is disabled a maximum of 8 (9 if
+ * one is instructions retired) can be specified.
+ *
+ * From Table 19-1. Architectural Performance Events
+ * Architectures Software Developer’s Manual Volume 3: System Programming
+ * Guide
+ */
+struct raw_perf_event perf_events[] = {
+ { 0x3c, 0x00, NULL, "Unhalted CPU Cycles" },
+ { 0xc0, 0x00, NULL, "Instruction Retired" }
+};
+
+#define NUM_EVTS (ARRAY_SIZE(perf_events))
+
+/* WARNING: PMU config is currently broken!
+ */
+bool time_bench_PMU_config(bool enable)
+{
+ int i;
+ struct perf_event_attr perf_conf;
+ struct perf_event *perf_event;
+ int cpu;
+
+ preempt_disable();
+ cpu = smp_processor_id();
+ pr_info("DEBUG: cpu:%d\n", cpu);
+ preempt_enable();
+
+ memset(&perf_conf, 0, sizeof(struct perf_event_attr));
+ perf_conf.type = PERF_TYPE_RAW;
+ perf_conf.size = sizeof(struct perf_event_attr);
+ perf_conf.read_format = PERF_FORMAT;
+ perf_conf.pinned = 1;
+ perf_conf.exclude_user = 1; /* No userspace events */
+ perf_conf.exclude_kernel = 0; /* Only kernel events */
+
+ for (i = 0; i < NUM_EVTS; i++) {
+ perf_conf.disabled = enable;
+ //perf_conf.disabled = (i == 0) ? 1 : 0;
+ perf_conf.config = perf_events[i].config;
+ perf_conf.config1 = perf_events[i].config1;
+ if (verbose)
+ pr_info("%s() enable PMU counter: %s\n",
+ __func__, perf_events[i].desc);
+ perf_event = perf_event_create_kernel_counter(&perf_conf, cpu,
+ NULL /* task */,
+ NULL /* overflow_handler*/,
+ NULL /* context */);
+ if (perf_event) {
+ perf_events[i].save = perf_event;
+ pr_info("%s():DEBUG perf_event success\n", __func__);
+
+ perf_event_enable(perf_event);
+ } else {
+ pr_info("%s():DEBUG perf_event is NULL\n", __func__);
+ }
+ }
+
+ return true;
+}
+
+/** Generic functions **
+ */
+
+/* Calculate stats, store results in record */
+bool time_bench_calc_stats(struct time_bench_record *rec)
+{
+#define NANOSEC_PER_SEC 1000000000 /* 10^9 */
+ uint64_t ns_per_call_tmp_rem = 0;
+ uint32_t ns_per_call_remainder = 0;
+ uint64_t pmc_ipc_tmp_rem = 0;
+ uint32_t pmc_ipc_remainder = 0;
+ uint32_t pmc_ipc_div = 0;
+ uint32_t invoked_cnt_precision = 0;
+ uint32_t invoked_cnt = 0; /* 32-bit due to div_u64_rem() */
+
+ if (rec->flags & TIME_BENCH_LOOP) {
+ if (rec->invoked_cnt < 1000) {
+ pr_err("ERR: need more(>1000) loops(%llu) for timing\n",
+ rec->invoked_cnt);
+ return false;
+ }
+ if (rec->invoked_cnt > ((1ULL << 32) - 1)) {
+ /* div_u64_rem() can only support div with 32bit*/
+ pr_err("ERR: Invoke cnt(%llu) too big overflow 32bit\n",
+ rec->invoked_cnt);
+ return false;
+ }
+ invoked_cnt = (uint32_t)rec->invoked_cnt;
+ }
+
+ /* TSC (Time-Stamp Counter) records */
+ if (rec->flags & TIME_BENCH_TSC) {
+ rec->tsc_interval = rec->tsc_stop - rec->tsc_start;
+ if (rec->tsc_interval == 0) {
+ pr_err("ABORT: timing took ZERO TSC time\n");
+ return false;
+ }
+ /* Calculate stats */
+ if (rec->flags & TIME_BENCH_LOOP)
+ rec->tsc_cycles = rec->tsc_interval / invoked_cnt;
+ else
+ rec->tsc_cycles = rec->tsc_interval;
+ }
+
+ /* Wall-clock time calc */
+ if (rec->flags & TIME_BENCH_WALLCLOCK) {
+ rec->time_start = rec->ts_start.tv_nsec +
+ (NANOSEC_PER_SEC * rec->ts_start.tv_sec);
+ rec->time_stop = rec->ts_stop.tv_nsec +
+ (NANOSEC_PER_SEC * rec->ts_stop.tv_sec);
+ rec->time_interval = rec->time_stop - rec->time_start;
+ if (rec->time_interval == 0) {
+ pr_err("ABORT: timing took ZERO wallclock time\n");
+ return false;
+ }
+ /* Calculate stats */
+ /*** Division in kernel it tricky ***/
+ /* Orig: time_sec = (time_interval / NANOSEC_PER_SEC); */
+ /* remainder only correct because NANOSEC_PER_SEC is 10^9 */
+ rec->time_sec = div_u64_rem(rec->time_interval, NANOSEC_PER_SEC,
+ &rec->time_sec_remainder);
+ //TODO: use existing struct timespec records instead of div?
+
+ if (rec->flags & TIME_BENCH_LOOP) {
+ /*** Division in kernel it tricky ***/
+ /* Orig: ns = ((double)time_interval / invoked_cnt); */
+ /* First get quotient */
+ rec->ns_per_call_quotient =
+ div_u64_rem(rec->time_interval, invoked_cnt,
+ &ns_per_call_remainder);
+ /* Now get decimals .xxx precision (incorrect roundup)*/
+ ns_per_call_tmp_rem = ns_per_call_remainder;
+ invoked_cnt_precision = invoked_cnt / 1000;
+ if (invoked_cnt_precision > 0) {
+ rec->ns_per_call_decimal =
+ div_u64_rem(ns_per_call_tmp_rem,
+ invoked_cnt_precision,
+ &ns_per_call_remainder);
+ }
+ }
+ }
+
+ /* Performance Monitor Unit (PMU) counters */
+ if (rec->flags & TIME_BENCH_PMU) {
+ //FIXME: Overflow handling???
+ rec->pmc_inst = rec->pmc_inst_stop - rec->pmc_inst_start;
+ rec->pmc_clk = rec->pmc_clk_stop - rec->pmc_clk_start;
+
+ /* Calc Instruction Per Cycle (IPC) */
+ /* First get quotient */
+ rec->pmc_ipc_quotient = div_u64_rem(rec->pmc_inst, rec->pmc_clk,
+ &pmc_ipc_remainder);
+ /* Now get decimals .xxx precision (incorrect roundup)*/
+ pmc_ipc_tmp_rem = pmc_ipc_remainder;
+ pmc_ipc_div = rec->pmc_clk / 1000;
+ if (pmc_ipc_div > 0) {
+ rec->pmc_ipc_decimal = div_u64_rem(pmc_ipc_tmp_rem,
+ pmc_ipc_div,
+ &pmc_ipc_remainder);
+ }
+ }
+
+ return true;
+}
+
+/* Generic function for invoking a loop function and calculating
+ * execution time stats. The function being called/timed is assumed
+ * to perform a tight loop, and update the timing record struct.
+ */
+bool time_bench_loop(uint32_t loops, int step, char *txt, void *data,
+ int (*func)(struct time_bench_record *record, void *data))
+{
+ struct time_bench_record rec;
+
+ /* Setup record */
+ memset(&rec, 0, sizeof(rec)); /* zero func might not update all */
+ rec.version_abi = 1;
+ rec.loops = loops;
+ rec.step = step;
+ rec.flags = (TIME_BENCH_LOOP | TIME_BENCH_TSC | TIME_BENCH_WALLCLOCK);
+
+ /*** Loop function being timed ***/
+ if (!func(&rec, data)) {
+ pr_err("ABORT: function being timed failed\n");
+ return false;
+ }
+
+ if (rec.invoked_cnt < loops)
+ pr_warn("WARNING: Invoke count(%llu) smaller than loops(%d)\n",
+ rec.invoked_cnt, loops);
+
+ /* Calculate stats */
+ time_bench_calc_stats(&rec);
+
+ pr_info("Type:%s Per elem: %llu cycles(tsc) %llu.%03llu ns (step:%d) - (measurement period time:%llu.%09u sec time_interval:%llu) - (invoke count:%llu tsc_interval:%llu)\n",
+ txt, rec.tsc_cycles, rec.ns_per_call_quotient,
+ rec.ns_per_call_decimal, rec.step, rec.time_sec,
+ rec.time_sec_remainder, rec.time_interval, rec.invoked_cnt,
+ rec.tsc_interval);
+ if (rec.flags & TIME_BENCH_PMU)
+ pr_info("Type:%s PMU inst/clock%llu/%llu = %llu.%03llu IPC (inst per cycle)\n",
+ txt, rec.pmc_inst, rec.pmc_clk, rec.pmc_ipc_quotient,
+ rec.pmc_ipc_decimal);
+ return true;
+}
+
+/* Function getting invoked by kthread */
+static int invoke_test_on_cpu_func(void *private)
+{
+ struct time_bench_cpu *cpu = private;
+ struct time_bench_sync *sync = cpu->sync;
+ cpumask_t newmask = CPU_MASK_NONE;
+ void *data = cpu->data;
+
+ /* Restrict CPU */
+ cpumask_set_cpu(cpu->rec.cpu, &newmask);
+ set_cpus_allowed_ptr(current, &newmask);
+
+ /* Synchronize start of concurrency test */
+ atomic_inc(&sync->nr_tests_running);
+ wait_for_completion(&sync->start_event);
+
+ /* Start benchmark function */
+ if (!cpu->bench_func(&cpu->rec, data)) {
+ pr_err("ERROR: function being timed failed on CPU:%d(%d)\n",
+ cpu->rec.cpu, smp_processor_id());
+ } else {
+ if (verbose)
+ pr_info("SUCCESS: ran on CPU:%d(%d)\n", cpu->rec.cpu,
+ smp_processor_id());
+ }
+ cpu->did_bench_run = true;
+
+ /* End test */
+ atomic_dec(&sync->nr_tests_running);
+ /* Wait for kthread_stop() telling us to stop */
+ while (!kthread_should_stop()) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule();
+ }
+ __set_current_state(TASK_RUNNING);
+ return 0;
+}
+
+void time_bench_print_stats_cpumask(const char *desc,
+ struct time_bench_cpu *cpu_tasks,
+ const struct cpumask *mask)
+{
+ uint64_t average = 0;
+ int cpu;
+ int step = 0;
+ struct sum {
+ uint64_t tsc_cycles;
+ int records;
+ } sum = { 0 };
+
+ /* Get stats */
+ for_each_cpu(cpu, mask) {
+ struct time_bench_cpu *c = &cpu_tasks[cpu];
+ struct time_bench_record *rec = &c->rec;
+
+ /* Calculate stats */
+ time_bench_calc_stats(rec);
+
+ pr_info("Type:%s CPU(%d) %llu cycles(tsc) %llu.%03llu ns (step:%d) - (measurement period time:%llu.%09u sec time_interval:%llu) - (invoke count:%llu tsc_interval:%llu)\n",
+ desc, cpu, rec->tsc_cycles, rec->ns_per_call_quotient,
+ rec->ns_per_call_decimal, rec->step, rec->time_sec,
+ rec->time_sec_remainder, rec->time_interval,
+ rec->invoked_cnt, rec->tsc_interval);
+
+ /* Collect average */
+ sum.records++;
+ sum.tsc_cycles += rec->tsc_cycles;
+ step = rec->step;
+ }
+
+ if (sum.records) /* avoid div-by-zero */
+ average = sum.tsc_cycles / sum.records;
+ pr_info("Sum Type:%s Average: %llu cycles(tsc) CPUs:%d step:%d\n", desc,
+ average, sum.records, step);
+}
+
+void time_bench_run_concurrent(uint32_t loops, int step, void *data,
+ const struct cpumask *mask, /* Support masking outsome CPUs*/
+ struct time_bench_sync *sync,
+ struct time_bench_cpu *cpu_tasks,
+ int (*func)(struct time_bench_record *record, void *data))
+{
+ int cpu, running = 0;
+
+ if (verbose) // DEBUG
+ pr_warn("%s() Started on CPU:%d\n", __func__,
+ smp_processor_id());
+
+ /* Reset sync conditions */
+ atomic_set(&sync->nr_tests_running, 0);
+ init_completion(&sync->start_event);
+
+ /* Spawn off jobs on all CPUs */
+ for_each_cpu(cpu, mask) {
+ struct time_bench_cpu *c = &cpu_tasks[cpu];
+
+ running++;
+ c->sync = sync; /* Send sync variable along */
+ c->data = data; /* Send opaque along */
+
+ /* Init benchmark record */
+ memset(&c->rec, 0, sizeof(struct time_bench_record));
+ c->rec.version_abi = 1;
+ c->rec.loops = loops;
+ c->rec.step = step;
+ c->rec.flags = (TIME_BENCH_LOOP | TIME_BENCH_TSC |
+ TIME_BENCH_WALLCLOCK);
+ c->rec.cpu = cpu;
+ c->bench_func = func;
+ c->task = kthread_run(invoke_test_on_cpu_func, c,
+ "time_bench%d", cpu);
+ if (IS_ERR(c->task)) {
+ pr_err("%s(): Failed to start test func\n", __func__);
+ return; /* Argh, what about cleanup?! */
+ }
+ }
+
+ /* Wait until all processes are running */
+ while (atomic_read(&sync->nr_tests_running) < running) {
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ schedule_timeout(10);
+ }
+ /* Kick off all CPU concurrently on completion event */
+ complete_all(&sync->start_event);
+
+ /* Wait for CPUs to finish */
+ while (atomic_read(&sync->nr_tests_running)) {
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ schedule_timeout(10);
+ }
+
+ /* Stop the kthreads */
+ for_each_cpu(cpu, mask) {
+ struct time_bench_cpu *c = &cpu_tasks[cpu];
+
+ kthread_stop(c->task);
+ }
+
+ if (verbose) // DEBUG - happens often, finish on another CPU
+ pr_warn("%s() Finished on CPU:%d\n", __func__,
+ smp_processor_id());
+}
diff --git a/tools/testing/selftests/net/bench/page_pool/time_bench.h b/tools/testing/selftests/net/bench/page_pool/time_bench.h
new file mode 100644
index 000000000000..e113fcf341dc
--- /dev/null
+++ b/tools/testing/selftests/net/bench/page_pool/time_bench.h
@@ -0,0 +1,238 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Benchmarking code execution time inside the kernel
+ *
+ * Copyright (C) 2014, Red Hat, Inc., Jesper Dangaard Brouer
+ * for licensing details see kernel-base/COPYING
+ */
+#ifndef _LINUX_TIME_BENCH_H
+#define _LINUX_TIME_BENCH_H
+
+/* Main structure used for recording a benchmark run */
+struct time_bench_record {
+ uint32_t version_abi;
+ uint32_t loops; /* Requested loop invocations */
+ uint32_t step; /* option for e.g. bulk invocations */
+
+ uint32_t flags; /* Measurements types enabled */
+#define TIME_BENCH_LOOP BIT(0)
+#define TIME_BENCH_TSC BIT(1)
+#define TIME_BENCH_WALLCLOCK BIT(2)
+#define TIME_BENCH_PMU BIT(3)
+
+ uint32_t cpu; /* Used when embedded in time_bench_cpu */
+
+ /* Records */
+ uint64_t invoked_cnt; /* Returned actual invocations */
+ uint64_t tsc_start;
+ uint64_t tsc_stop;
+ struct timespec64 ts_start;
+ struct timespec64 ts_stop;
+ /* PMU counters for instruction and cycles
+ * instructions counter including pipelined instructions
+ */
+ uint64_t pmc_inst_start;
+ uint64_t pmc_inst_stop;
+ /* CPU unhalted clock counter */
+ uint64_t pmc_clk_start;
+ uint64_t pmc_clk_stop;
+
+ /* Result records */
+ uint64_t tsc_interval;
+ uint64_t time_start, time_stop, time_interval; /* in nanosec */
+ uint64_t pmc_inst, pmc_clk;
+
+ /* Derived result records */
+ uint64_t tsc_cycles; // +decimal?
+ uint64_t ns_per_call_quotient, ns_per_call_decimal;
+ uint64_t time_sec;
+ uint32_t time_sec_remainder;
+ uint64_t pmc_ipc_quotient, pmc_ipc_decimal; /* inst per cycle */
+};
+
+/* For synchronizing parallel CPUs to run concurrently */
+struct time_bench_sync {
+ atomic_t nr_tests_running;
+ struct completion start_event;
+};
+
+/* Keep track of CPUs executing our bench function.
+ *
+ * Embed a time_bench_record for storing info per cpu
+ */
+struct time_bench_cpu {
+ struct time_bench_record rec;
+ struct time_bench_sync *sync; /* back ptr */
+ struct task_struct *task;
+ /* "data" opaque could have been placed in time_bench_sync,
+ * but to avoid any false sharing, place it per CPU
+ */
+ void *data;
+ /* Support masking outsome CPUs, mark if it ran */
+ bool did_bench_run;
+ /* int cpu; // note CPU stored in time_bench_record */
+ int (*bench_func)(struct time_bench_record *record, void *data);
+};
+
+/*
+ * Below TSC assembler code is not compatible with other archs, and
+ * can also fail on guests if cpu-flags are not correct.
+ *
+ * The way TSC reading is used, many iterations, does not require as
+ * high accuracy as described below (in Intel Doc #324264).
+ *
+ * Considering changing to use get_cycles() (#include <asm/timex.h>).
+ */
+
+/** TSC (Time-Stamp Counter) based **
+ * Recommend reading, to understand details of reading TSC accurately:
+ * Intel Doc #324264, "How to Benchmark Code Execution Times on Intel"
+ *
+ * Consider getting exclusive ownership of CPU by using:
+ * unsigned long flags;
+ * preempt_disable();
+ * raw_local_irq_save(flags);
+ * _your_code_
+ * raw_local_irq_restore(flags);
+ * preempt_enable();
+ *
+ * Clobbered registers: "%rax", "%rbx", "%rcx", "%rdx"
+ * RDTSC only change "%rax" and "%rdx" but
+ * CPUID clears the high 32-bits of all (rax/rbx/rcx/rdx)
+ */
+static __always_inline uint64_t tsc_start_clock(void)
+{
+ /* See: Intel Doc #324264 */
+ unsigned int hi, lo;
+
+ asm volatile("CPUID\n\t"
+ "RDTSC\n\t"
+ "mov %%edx, %0\n\t"
+ "mov %%eax, %1\n\t"
+ : "=r"(hi), "=r"(lo)::"%rax", "%rbx", "%rcx", "%rdx");
+ //FIXME: on 32bit use clobbered %eax + %edx
+ return ((uint64_t)lo) | (((uint64_t)hi) << 32);
+}
+
+static __always_inline uint64_t tsc_stop_clock(void)
+{
+ /* See: Intel Doc #324264 */
+ unsigned int hi, lo;
+
+ asm volatile("RDTSCP\n\t"
+ "mov %%edx, %0\n\t"
+ "mov %%eax, %1\n\t"
+ "CPUID\n\t"
+ : "=r"(hi), "=r"(lo)::"%rax", "%rbx", "%rcx", "%rdx");
+ return ((uint64_t)lo) | (((uint64_t)hi) << 32);
+}
+
+/** Wall-clock based **
+ *
+ * use: getnstimeofday()
+ * getnstimeofday(&rec->ts_start);
+ * getnstimeofday(&rec->ts_stop);
+ *
+ * API changed see: Documentation/core-api/timekeeping.rst
+ * https://www.kernel.org/doc/html/latest/core-api/timekeeping.html#c.getnstimeofday
+ *
+ * We should instead use: ktime_get_real_ts64() is a direct
+ * replacement, but consider using monotonic time (ktime_get_ts64())
+ * and/or a ktime_t based interface (ktime_get()/ktime_get_real()).
+ */
+
+/** PMU (Performance Monitor Unit) based **
+ *
+ * Needed for calculating: Instructions Per Cycle (IPC)
+ * - The IPC number tell how efficient the CPU pipelining were
+ */
+//lookup: perf_event_create_kernel_counter()
+
+bool time_bench_PMU_config(bool enable);
+
+/* Raw reading via rdpmc() using fixed counters
+ *
+ * From: https://github.com/andikleen/simple-pmu
+ */
+enum {
+ FIXED_SELECT = (1U << 30), /* == 0x40000000 */
+ FIXED_INST_RETIRED_ANY = 0,
+ FIXED_CPU_CLK_UNHALTED_CORE = 1,
+ FIXED_CPU_CLK_UNHALTED_REF = 2,
+};
+
+static __always_inline unsigned int long long p_rdpmc(unsigned int in)
+{
+ unsigned int d, a;
+
+ asm volatile("rdpmc" : "=d"(d), "=a"(a) : "c"(in) : "memory");
+ return ((unsigned long long)d << 32) | a;
+}
+
+/* These PMU counter needs to be enabled, but I don't have the
+ * configure code implemented. My current hack is running:
+ * sudo perf stat -e cycles:k -e instructions:k insmod lib/ring_queue_test.ko
+ */
+/* Reading all pipelined instruction */
+static __always_inline unsigned long long pmc_inst(void)
+{
+ return p_rdpmc(FIXED_SELECT | FIXED_INST_RETIRED_ANY);
+}
+
+/* Reading CPU clock cycles */
+static __always_inline unsigned long long pmc_clk(void)
+{
+ return p_rdpmc(FIXED_SELECT | FIXED_CPU_CLK_UNHALTED_CORE);
+}
+
+/* Raw reading via MSR rdmsr() is likely wrong
+ * FIXME: How can I know which raw MSR registers are conf for what?
+ */
+#define MSR_IA32_PCM0 0x400000C1 /* PERFCTR0 */
+#define MSR_IA32_PCM1 0x400000C2 /* PERFCTR1 */
+#define MSR_IA32_PCM2 0x400000C3
+static inline uint64_t msr_inst(unsigned long long *msr_result)
+{
+ return rdmsrq_safe(MSR_IA32_PCM0, msr_result);
+}
+
+/** Generic functions **
+ */
+bool time_bench_loop(uint32_t loops, int step, char *txt, void *data,
+ int (*func)(struct time_bench_record *rec, void *data));
+bool time_bench_calc_stats(struct time_bench_record *rec);
+
+void time_bench_run_concurrent(uint32_t loops, int step, void *data,
+ const struct cpumask *mask, /* Support masking outsome CPUs*/
+ struct time_bench_sync *sync, struct time_bench_cpu *cpu_tasks,
+ int (*func)(struct time_bench_record *record, void *data));
+void time_bench_print_stats_cpumask(const char *desc,
+ struct time_bench_cpu *cpu_tasks,
+ const struct cpumask *mask);
+
+//FIXME: use rec->flags to select measurement, should be MACRO
+static __always_inline void time_bench_start(struct time_bench_record *rec)
+{
+ //getnstimeofday(&rec->ts_start);
+ ktime_get_real_ts64(&rec->ts_start);
+ if (rec->flags & TIME_BENCH_PMU) {
+ rec->pmc_inst_start = pmc_inst();
+ rec->pmc_clk_start = pmc_clk();
+ }
+ rec->tsc_start = tsc_start_clock();
+}
+
+static __always_inline void time_bench_stop(struct time_bench_record *rec,
+ uint64_t invoked_cnt)
+{
+ rec->tsc_stop = tsc_stop_clock();
+ if (rec->flags & TIME_BENCH_PMU) {
+ rec->pmc_inst_stop = pmc_inst();
+ rec->pmc_clk_stop = pmc_clk();
+ }
+ //getnstimeofday(&rec->ts_stop);
+ ktime_get_real_ts64(&rec->ts_stop);
+ rec->invoked_cnt = invoked_cnt;
+}
+
+#endif /* _LINUX_TIME_BENCH_H */
diff --git a/tools/testing/selftests/net/bench/test_bench_page_pool.sh b/tools/testing/selftests/net/bench/test_bench_page_pool.sh
new file mode 100755
index 000000000000..7b8b18cfedce
--- /dev/null
+++ b/tools/testing/selftests/net/bench/test_bench_page_pool.sh
@@ -0,0 +1,32 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+
+set -e
+
+DRIVER="./page_pool/bench_page_pool.ko"
+result=""
+
+function run_test()
+{
+ rmmod "bench_page_pool.ko" || true
+ insmod $DRIVER > /dev/null 2>&1
+ result=$(dmesg | tail -10)
+ echo "$result"
+
+ echo
+ echo "Fast path results:"
+ echo "${result}" | grep -o -E "no-softirq-page_pool01 Per elem: ([0-9]+) cycles\(tsc\) ([0-9]+\.[0-9]+) ns"
+
+ echo
+ echo "ptr_ring results:"
+ echo "${result}" | grep -o -E "no-softirq-page_pool02 Per elem: ([0-9]+) cycles\(tsc\) ([0-9]+\.[0-9]+) ns"
+
+ echo
+ echo "slow path results:"
+ echo "${result}" | grep -o -E "no-softirq-page_pool03 Per elem: ([0-9]+) cycles\(tsc\) ([0-9]+\.[0-9]+) ns"
+}
+
+run_test
+
+exit 0
diff --git a/tools/testing/selftests/net/broadcast_pmtu.sh b/tools/testing/selftests/net/broadcast_pmtu.sh
new file mode 100755
index 000000000000..726eb5d25839
--- /dev/null
+++ b/tools/testing/selftests/net/broadcast_pmtu.sh
@@ -0,0 +1,47 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Ensures broadcast route MTU is respected
+
+CLIENT_NS=$(mktemp -u client-XXXXXXXX)
+CLIENT_IP4="192.168.0.1/24"
+CLIENT_BROADCAST_ADDRESS="192.168.0.255"
+
+SERVER_NS=$(mktemp -u server-XXXXXXXX)
+SERVER_IP4="192.168.0.2/24"
+
+setup() {
+ ip netns add "${CLIENT_NS}"
+ ip netns add "${SERVER_NS}"
+
+ ip -net "${SERVER_NS}" link add link1 type veth peer name link0 netns "${CLIENT_NS}"
+
+ ip -net "${CLIENT_NS}" link set link0 up
+ ip -net "${CLIENT_NS}" link set link0 mtu 9000
+ ip -net "${CLIENT_NS}" addr add "${CLIENT_IP4}" dev link0
+
+ ip -net "${SERVER_NS}" link set link1 up
+ ip -net "${SERVER_NS}" link set link1 mtu 1500
+ ip -net "${SERVER_NS}" addr add "${SERVER_IP4}" dev link1
+
+ read -r -a CLIENT_BROADCAST_ENTRY <<< "$(ip -net "${CLIENT_NS}" route show table local type broadcast)"
+ ip -net "${CLIENT_NS}" route del "${CLIENT_BROADCAST_ENTRY[@]}"
+ ip -net "${CLIENT_NS}" route add "${CLIENT_BROADCAST_ENTRY[@]}" mtu 1500
+
+ ip net exec "${SERVER_NS}" sysctl -wq net.ipv4.icmp_echo_ignore_broadcasts=0
+}
+
+cleanup() {
+ ip -net "${SERVER_NS}" link del link1
+ ip netns del "${CLIENT_NS}"
+ ip netns del "${SERVER_NS}"
+}
+
+trap cleanup EXIT
+
+setup &&
+ echo "Testing for broadcast route MTU" &&
+ ip net exec "${CLIENT_NS}" ping -f -M want -q -c 1 -s 8000 -w 1 -b "${CLIENT_BROADCAST_ADDRESS}" > /dev/null 2>&1
+
+exit $?
+
diff --git a/tools/testing/selftests/net/busy_poll_test.sh b/tools/testing/selftests/net/busy_poll_test.sh
index 7db292ec4884..7d2d40812074 100755
--- a/tools/testing/selftests/net/busy_poll_test.sh
+++ b/tools/testing/selftests/net/busy_poll_test.sh
@@ -1,6 +1,6 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
-source net_helper.sh
+source lib.sh
NSIM_SV_ID=$((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 $EXIT_STATUS
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 130d532b7e67..c24417d0047b 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -30,17 +30,25 @@ CONFIG_NET_FOU=y
CONFIG_NET_FOU_IP_TUNNELS=y
CONFIG_NETFILTER=y
CONFIG_NETFILTER_ADVANCED=y
+CONFIG_NETFILTER_XTABLES_LEGACY=y
CONFIG_NF_CONNTRACK=m
CONFIG_IPV6_MROUTE=y
CONFIG_IPV6_SIT=y
-CONFIG_IP_DCCP=m
CONFIG_NF_NAT=m
CONFIG_IP6_NF_IPTABLES=m
+CONFIG_IP6_NF_IPTABLES_LEGACY=m
CONFIG_IP_NF_IPTABLES=m
+CONFIG_IP_NF_IPTABLES_LEGACY=m
+CONFIG_IP6_NF_MANGLE=m
+CONFIG_IP6_NF_FILTER=m
CONFIG_IP6_NF_NAT=m
CONFIG_IP6_NF_RAW=m
+CONFIG_IP_NF_MANGLE=m
+CONFIG_IP_NF_FILTER=m
CONFIG_IP_NF_NAT=m
CONFIG_IP_NF_RAW=m
+CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP6_NF_TARGET_REJECT=m
CONFIG_IP_NF_TARGET_TTL=m
CONFIG_IPV6_GRE=m
CONFIG_IPV6_SEG6_LWTUNNEL=y
@@ -58,6 +66,8 @@ CONFIG_NF_TABLES_IPV6=y
CONFIG_NF_TABLES_IPV4=y
CONFIG_NFT_NAT=m
CONFIG_NETFILTER_XT_MATCH_LENGTH=m
+CONFIG_NETFILTER_XT_TARGET_HL=m
+CONFIG_NETFILTER_XT_NAT=m
CONFIG_NET_ACT_CSUM=m
CONFIG_NET_ACT_CT=m
CONFIG_NET_ACT_GACT=m
diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index b866bab1d92a..5fbdd2a0b537 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -359,6 +359,23 @@ fib_rule6_test()
"$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()
@@ -499,10 +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" \
@@ -635,6 +649,23 @@ fib_rule4_test()
"$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/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index 00bde7b6f39e..d7bb2e80e88c 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -102,6 +102,7 @@ TEST_PROGS = bridge_fdb_learning_limit.sh \
vxlan_bridge_1d_port_8472.sh \
vxlan_bridge_1d.sh \
vxlan_bridge_1q_ipv6.sh \
+ vxlan_bridge_1q_mc_ul.sh \
vxlan_bridge_1q_port_8472_ipv6.sh \
vxlan_bridge_1q_port_8472.sh \
vxlan_bridge_1q.sh \
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_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 $h2 clsact
+}
+
trap cleanup EXIT
setup_prepare
diff --git a/tools/testing/selftests/net/forwarding/config b/tools/testing/selftests/net/forwarding/config
index 8d7a1a004b7c..18fd69d8d937 100644
--- a/tools/testing/selftests/net/forwarding/config
+++ b/tools/testing/selftests/net/forwarding/config
@@ -1,6 +1,7 @@
CONFIG_BRIDGE=m
CONFIG_VLAN_8021Q=m
CONFIG_BRIDGE_VLAN_FILTERING=y
+CONFIG_BRIDGE_IGMP_SNOOPING=y
CONFIG_NET_L3_MASTER_DEV=y
CONFIG_IPV6_MULTIPLE_TABLES=y
CONFIG_NET_VRF=m
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 508f3c700d71..890b3374dacd 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -37,6 +37,7 @@ declare -A NETIFS=(
: "${TEAMD:=teamd}"
: "${MCD:=smcrouted}"
: "${MC_CLI:=smcroutectl}"
+: "${MCD_TABLE_NAME:=selftests}"
# Constants for netdevice bring-up:
# Default time in seconds to wait for an interface to come up before giving up
@@ -141,6 +142,20 @@ check_tc_version()
fi
}
+check_tc_erspan_support()
+{
+ local dev=$1; shift
+
+ tc filter add dev $dev ingress pref 1 handle 1 flower \
+ erspan_opts 1:0:0:0 &> /dev/null
+ if [[ $? -ne 0 ]]; then
+ echo "SKIP: iproute2 too old; tc is missing erspan support"
+ return $ksft_skip
+ fi
+ tc filter del dev $dev ingress pref 1 handle 1 flower \
+ erspan_opts 1:0:0:0 &> /dev/null
+}
+
# Old versions of tc don't understand "mpls_uc"
check_tc_mpls_support()
{
@@ -525,9 +540,9 @@ setup_wait_dev_with_timeout()
return 1
}
-setup_wait()
+setup_wait_n()
{
- local num_netifs=${1:-$NUM_NETIFS}
+ local num_netifs=$1; shift
local i
for ((i = 1; i <= num_netifs; ++i)); do
@@ -538,6 +553,11 @@ setup_wait()
sleep $WAIT_TIME
}
+setup_wait()
+{
+ setup_wait_n "$NUM_NETIFS"
+}
+
wait_for_dev()
{
local dev=$1; shift
@@ -1757,6 +1777,51 @@ mc_send()
msend -g $groups -I $if_name -c 1 > /dev/null 2>&1
}
+adf_mcd_start()
+{
+ local ifs=("$@")
+
+ local table_name="$MCD_TABLE_NAME"
+ local smcroutedir
+ local pid
+ local if
+ local i
+
+ check_command "$MCD" || return 1
+ check_command "$MC_CLI" || return 1
+
+ smcroutedir=$(mktemp -d)
+ defer rm -rf "$smcroutedir"
+
+ for ((i = 1; i <= NUM_NETIFS; ++i)); do
+ echo "phyint ${NETIFS[p$i]} enable" >> \
+ "$smcroutedir/$table_name.conf"
+ done
+
+ for if in "${ifs[@]}"; do
+ if ! ip_link_has_flag "$if" MULTICAST; then
+ ip link set dev "$if" multicast on
+ defer ip link set dev "$if" multicast off
+ fi
+
+ echo "phyint $if enable" >> \
+ "$smcroutedir/$table_name.conf"
+ done
+
+ "$MCD" -N -I "$table_name" -f "$smcroutedir/$table_name.conf" \
+ -P "$smcroutedir/$table_name.pid"
+ busywait "$BUSYWAIT_TIMEOUT" test -e "$smcroutedir/$table_name.pid"
+ pid=$(cat "$smcroutedir/$table_name.pid")
+ defer kill_process "$pid"
+}
+
+mc_cli()
+{
+ local table_name="$MCD_TABLE_NAME"
+
+ "$MC_CLI" -I "$table_name" "$@"
+}
+
start_ip_monitor()
{
local mtype=$1; shift
diff --git a/tools/testing/selftests/net/forwarding/router_multicast.sh b/tools/testing/selftests/net/forwarding/router_multicast.sh
index 5a58b1ec8aef..83e52abdbc2e 100755
--- a/tools/testing/selftests/net/forwarding/router_multicast.sh
+++ b/tools/testing/selftests/net/forwarding/router_multicast.sh
@@ -33,10 +33,6 @@ NUM_NETIFS=6
source lib.sh
source tc_common.sh
-require_command $MCD
-require_command $MC_CLI
-table_name=selftests
-
h1_create()
{
simple_if_init $h1 198.51.100.2/28 2001:db8:1::2/64
@@ -149,25 +145,6 @@ router_destroy()
ip link set dev $rp1 down
}
-start_mcd()
-{
- SMCROUTEDIR="$(mktemp -d)"
-
- for ((i = 1; i <= $NUM_NETIFS; ++i)); do
- echo "phyint ${NETIFS[p$i]} enable" >> \
- $SMCROUTEDIR/$table_name.conf
- done
-
- $MCD -N -I $table_name -f $SMCROUTEDIR/$table_name.conf \
- -P $SMCROUTEDIR/$table_name.pid
-}
-
-kill_mcd()
-{
- pkill $MCD
- rm -rf $SMCROUTEDIR
-}
-
setup_prepare()
{
h1=${NETIFS[p1]}
@@ -179,7 +156,7 @@ setup_prepare()
rp3=${NETIFS[p5]}
h3=${NETIFS[p6]}
- start_mcd
+ adf_mcd_start || exit "$EXIT_STATUS"
vrf_prepare
@@ -206,7 +183,7 @@ cleanup()
vrf_cleanup
- kill_mcd
+ defer_scopes_cleanup
}
create_mcast_sg()
@@ -214,9 +191,9 @@ create_mcast_sg()
local if_name=$1; shift
local s_addr=$1; shift
local mcast=$1; shift
- local dest_ifs=${@}
+ local dest_ifs=("${@}")
- $MC_CLI -I $table_name add $if_name $s_addr $mcast $dest_ifs
+ mc_cli add "$if_name" "$s_addr" "$mcast" "${dest_ifs[@]}"
}
delete_mcast_sg()
@@ -224,9 +201,9 @@ delete_mcast_sg()
local if_name=$1; shift
local s_addr=$1; shift
local mcast=$1; shift
- local dest_ifs=${@}
+ local dest_ifs=("${@}")
- $MC_CLI -I $table_name remove $if_name $s_addr $mcast $dest_ifs
+ mc_cli remove "$if_name" "$s_addr" "$mcast" "${dest_ifs[@]}"
}
mcast_v4()
diff --git a/tools/testing/selftests/net/forwarding/tc_flower.sh b/tools/testing/selftests/net/forwarding/tc_flower.sh
index b1daad19b01e..b58909a93112 100755
--- a/tools/testing/selftests/net/forwarding/tc_flower.sh
+++ b/tools/testing/selftests/net/forwarding/tc_flower.sh
@@ -6,7 +6,7 @@ ALL_TESTS="match_dst_mac_test match_src_mac_test match_dst_ip_test \
match_ip_tos_test match_indev_test match_ip_ttl_test
match_mpls_label_test \
match_mpls_tc_test match_mpls_bos_test match_mpls_ttl_test \
- match_mpls_lse_test"
+ match_mpls_lse_test match_erspan_opts_test"
NUM_NETIFS=2
source tc_common.sh
source lib.sh
@@ -676,6 +676,56 @@ match_mpls_lse_test()
log_test "mpls lse match ($tcflags)"
}
+match_erspan_opts_test()
+{
+ RET=0
+
+ check_tc_erspan_support $h2 || return 0
+
+ # h1 erspan setup
+ tunnel_create erspan1 erspan 192.0.2.1 192.0.2.2 dev $h1 seq key 1001 \
+ tos C ttl 64 erspan_ver 1 erspan 6789 # ERSPAN Type II
+ tunnel_create erspan2 erspan 192.0.2.1 192.0.2.2 dev $h1 seq key 1002 \
+ tos C ttl 64 erspan_ver 2 erspan_dir egress erspan_hwid 63 \
+ # ERSPAN Type III
+ ip link set dev erspan1 master v$h1
+ ip link set dev erspan2 master v$h1
+ # h2 erspan setup
+ ip link add ep-ex type erspan ttl 64 external # To collect tunnel info
+ ip link set ep-ex up
+ ip link set dev ep-ex master v$h2
+ tc qdisc add dev ep-ex clsact
+
+ # ERSPAN Type II [decap direction]
+ tc filter add dev ep-ex ingress protocol ip handle 101 flower \
+ $tcflags enc_src_ip 192.0.2.1 enc_dst_ip 192.0.2.2 \
+ enc_key_id 1001 erspan_opts 1:6789:0:0 \
+ action drop
+ # ERSPAN Type III [decap direction]
+ tc filter add dev ep-ex ingress protocol ip handle 102 flower \
+ $tcflags enc_src_ip 192.0.2.1 enc_dst_ip 192.0.2.2 \
+ enc_key_id 1002 erspan_opts 2:0:1:63 action drop
+
+ ep1mac=$(mac_get erspan1)
+ $MZ erspan1 -c 1 -p 64 -a $ep1mac -b $h2mac -t ip -q
+ tc_check_packets "dev ep-ex ingress" 101 1
+ check_err $? "ERSPAN Type II"
+
+ ep2mac=$(mac_get erspan2)
+ $MZ erspan2 -c 1 -p 64 -a $ep1mac -b $h2mac -t ip -q
+ tc_check_packets "dev ep-ex ingress" 102 1
+ check_err $? "ERSPAN Type III"
+
+ # h2 erspan cleanup
+ tc qdisc del dev ep-ex clsact
+ tunnel_destroy ep-ex
+ # h1 erspan cleanup
+ tunnel_destroy erspan2 # ERSPAN Type III
+ tunnel_destroy erspan1 # ERSPAN Type II
+
+ log_test "erspan_opts match ($tcflags)"
+}
+
setup_prepare()
{
h1=${NETIFS[p1]}
diff --git a/tools/testing/selftests/net/forwarding/tc_taprio.sh b/tools/testing/selftests/net/forwarding/tc_taprio.sh
new file mode 100755
index 000000000000..8992aeabfe0b
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/tc_taprio.sh
@@ -0,0 +1,421 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS=" \
+ test_clock_jump_backward \
+ test_taprio_after_ptp \
+ test_max_sdu \
+ test_clock_jump_backward_forward \
+"
+NUM_NETIFS=4
+source tc_common.sh
+source lib.sh
+source tsn_lib.sh
+
+require_command python3
+
+# The test assumes the usual topology from the README, where h1 is connected to
+# swp1, h2 to swp2, and swp1 and swp2 are together in a bridge.
+# Additional assumption: h1 and h2 use the same PHC, and so do swp1 and swp2.
+# By synchronizing h1 to swp1 via PTP, h2 is also implicitly synchronized to
+# swp1 (and both to CLOCK_REALTIME).
+h1=${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_1q_mc_ul.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh
new file mode 100755
index 000000000000..462db0b603e7
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh
@@ -0,0 +1,771 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +-----------------------------------------+
+# | + $h1.10 + $h1.20 |
+# | | 192.0.2.1/28 | 2001:db8:1::1/64 |
+# | \________ ________/ |
+# | \ / |
+# | + $h1 H1 (vrf) |
+# +-----------|-----------------------------+
+# |
+# +-----------|----------------------------------------------------------------+
+# | +---------|--------------------------------------+ SWITCH (main vrf) |
+# | | + $swp1 BR1 (802.1q) | |
+# | | vid 10 20 | |
+# | | | |
+# | | + vx10 (vxlan) + vx20 (vxlan) | + lo10 (dummy) |
+# | | local 192.0.2.100 local 2001:db8:4::1 | 192.0.2.100/28 |
+# | | group 233.252.0.1 group ff0e::1:2:3 | 2001:db8:4::1/64 |
+# | | id 1000 id 2000 | |
+# | | vid 10 pvid untagged vid 20 pvid untagged | |
+# | +------------------------------------------------+ |
+# | |
+# | + $swp2 $swp3 + |
+# | | 192.0.2.33/28 192.0.2.65/28 | |
+# | | 2001:db8:2::1/64 2001:db8:3::1/64 | |
+# | | | |
+# +---|--------------------------------------------------------------------|---+
+# | |
+# +---|--------------------------------+ +--------------------------------|---+
+# | | H2 (vrf) | | H3 (vrf) | |
+# | +-|----------------------------+ | | +-----------------------------|-+ |
+# | | + $h2 BR2 (802.1d) | | | | BR3 (802.1d) $h3 + | |
+# | | | | | | | |
+# | | + v1$h2 (veth) | | | | v1$h3 (veth) + | |
+# | +-|----------------------------+ | | +-----------------------------|-+ |
+# | | | | | |
+# +---|--------------------------------+ +--------------------------------|---+
+# | |
+# +---|--------------------------------+ +--------------------------------|---+
+# | + v2$h2 (veth) NS2 (netns) | | NS3 (netns) v2$h3 (veth) + |
+# | 192.0.2.34/28 | | 192.0.2.66/28 |
+# | 2001:db8:2::2/64 | | 2001:db8:3::2/64 |
+# | | | |
+# | +--------------------------------+ | | +--------------------------------+ |
+# | | BR1 (802.1q) | | | | BR1 (802.1q) | |
+# | | + vx10 (vxlan) | | | | + vx10 (vxlan) | |
+# | | local 192.0.2.34 | | | | local 192.0.2.50 | |
+# | | group 233.252.0.1 dev v2$h2 | | | | group 233.252.0.1 dev v2$h3 | |
+# | | id 1000 dstport $VXPORT | | | | id 1000 dstport $VXPORT | |
+# | | vid 10 pvid untagged | | | | vid 10 pvid untagged | |
+# | | | | | | | |
+# | | + vx20 (vxlan) | | | | + vx20 (vxlan) | |
+# | | local 2001:db8:2::2 | | | | local 2001:db8:3::2 | |
+# | | group ff0e::1:2:3 dev v2$h2 | | | | group ff0e::1:2:3 dev v2$h3 | |
+# | | id 2000 dstport $VXPORT | | | | id 2000 dstport $VXPORT | |
+# | | vid 20 pvid untagged | | | | vid 20 pvid untagged | |
+# | | | | | | | |
+# | | + w1 (veth) | | | | + w1 (veth) | |
+# | | | vid 10 20 | | | | | vid 10 20 | |
+# | +--|-----------------------------+ | | +--|-----------------------------+ |
+# | | | | | |
+# | +--|-----------------------------+ | | +--|-----------------------------+ |
+# | | + w2 (veth) VW2 (vrf) | | | | + w2 (veth) VW2 (vrf) | |
+# | | |\ | | | | |\ | |
+# | | | + w2.10 | | | | | + w2.10 | |
+# | | | 192.0.2.3/28 | | | | | 192.0.2.4/28 | |
+# | | | | | | | | | |
+# | | + w2.20 | | | | + w2.20 | |
+# | | 2001:db8:1::3/64 | | | | 2001:db8:1::4/64 | |
+# | +--------------------------------+ | | +--------------------------------+ |
+# +------------------------------------+ +------------------------------------+
+#
+#shellcheck disable=SC2317 # SC doesn't see our uses of functions.
+
+: "${VXPORT:=4789}"
+export VXPORT
+
+: "${GROUP4:=233.252.0.1}"
+export GROUP4
+
+: "${GROUP6:=ff0e::1:2:3}"
+export GROUP6
+
+: "${IPMR:=lo10}"
+
+ALL_TESTS="
+ ipv4_nomcroute
+ ipv4_mcroute
+ ipv4_mcroute_changelink
+ ipv4_mcroute_starg
+ ipv4_mcroute_noroute
+ ipv4_mcroute_fdb
+ ipv4_mcroute_fdb_oif0
+ ipv4_mcroute_fdb_oif0_sep
+
+ ipv6_nomcroute
+ ipv6_mcroute
+ ipv6_mcroute_changelink
+ ipv6_mcroute_starg
+ ipv6_mcroute_noroute
+ ipv6_mcroute_fdb
+ ipv6_mcroute_fdb_oif0
+
+ ipv4_nomcroute_rx
+ ipv4_mcroute_rx
+ ipv4_mcroute_starg_rx
+ ipv4_mcroute_fdb_oif0_sep_rx
+ ipv4_mcroute_fdb_sep_rx
+
+ ipv6_nomcroute_rx
+ ipv6_mcroute_rx
+ ipv6_mcroute_starg_rx
+ ipv6_mcroute_fdb_sep_rx
+"
+
+NUM_NETIFS=6
+source lib.sh
+
+h1_create()
+{
+ simple_if_init "$h1"
+ defer simple_if_fini "$h1"
+
+ ip_link_add "$h1.10" master "v$h1" link "$h1" type vlan id 10
+ ip_link_set_up "$h1.10"
+ ip_addr_add "$h1.10" 192.0.2.1/28
+
+ ip_link_add "$h1.20" master "v$h1" link "$h1" type vlan id 20
+ ip_link_set_up "$h1.20"
+ ip_addr_add "$h1.20" 2001:db8:1::1/64
+}
+
+install_capture()
+{
+ local dev=$1; shift
+
+ tc qdisc add dev "$dev" clsact
+ defer tc qdisc del dev "$dev" clsact
+
+ tc filter add dev "$dev" ingress proto ip pref 104 \
+ flower skip_hw ip_proto udp dst_port "$VXPORT" \
+ action pass
+ defer tc filter del dev "$dev" ingress proto ip pref 104
+
+ tc filter add dev "$dev" ingress proto ipv6 pref 106 \
+ flower skip_hw ip_proto udp dst_port "$VXPORT" \
+ action pass
+ defer tc filter del dev "$dev" ingress proto ipv6 pref 106
+}
+
+h2_create()
+{
+ # $h2
+ ip_link_set_up "$h2"
+
+ # H2
+ vrf_create "v$h2"
+ defer vrf_destroy "v$h2"
+
+ ip_link_set_up "v$h2"
+
+ # br2
+ ip_link_add br2 type bridge vlan_filtering 0 mcast_snooping 0
+ ip_link_set_master br2 "v$h2"
+ ip_link_set_up br2
+
+ # $h2
+ ip_link_set_master "$h2" br2
+ install_capture "$h2"
+
+ # v1$h2
+ ip_link_set_up "v1$h2"
+ ip_link_set_master "v1$h2" br2
+}
+
+h3_create()
+{
+ # $h3
+ ip_link_set_up "$h3"
+
+ # H3
+ vrf_create "v$h3"
+ defer vrf_destroy "v$h3"
+
+ ip_link_set_up "v$h3"
+
+ # br3
+ ip_link_add br3 type bridge vlan_filtering 0 mcast_snooping 0
+ ip_link_set_master br3 "v$h3"
+ ip_link_set_up br3
+
+ # $h3
+ ip_link_set_master "$h3" br3
+ install_capture "$h3"
+
+ # v1$h3
+ ip_link_set_up "v1$h3"
+ ip_link_set_master "v1$h3" br3
+}
+
+switch_create()
+{
+ local swp1_mac
+
+ # br1
+ swp1_mac=$(mac_get "$swp1")
+ ip_link_add br1 type bridge vlan_filtering 1 \
+ vlan_default_pvid 0 mcast_snooping 0
+ ip_link_set_addr br1 "$swp1_mac"
+ ip_link_set_up br1
+
+ # A dummy to force the IPv6 OIF=0 test to install a suitable MC route on
+ # $IPMR to be deterministic. Also used for the IPv6 RX!=TX ping test.
+ ip_link_add "X$IPMR" up type dummy
+
+ # IPMR
+ ip_link_add "$IPMR" up type dummy
+ ip_addr_add "$IPMR" 192.0.2.100/28
+ ip_addr_add "$IPMR" 2001:db8:4::1/64
+
+ # $swp1
+ ip_link_set_up "$swp1"
+ ip_link_set_master "$swp1" br1
+ bridge_vlan_add vid 10 dev "$swp1"
+ bridge_vlan_add vid 20 dev "$swp1"
+
+ # $swp2
+ ip_link_set_up "$swp2"
+ ip_addr_add "$swp2" 192.0.2.33/28
+ ip_addr_add "$swp2" 2001:db8:2::1/64
+
+ # $swp3
+ ip_link_set_up "$swp3"
+ ip_addr_add "$swp3" 192.0.2.65/28
+ ip_addr_add "$swp3" 2001:db8:3::1/64
+}
+
+vx_create()
+{
+ local name=$1; shift
+ local vid=$1; shift
+
+ ip_link_add "$name" up type vxlan dstport "$VXPORT" \
+ nolearning noudpcsum tos inherit ttl 16 \
+ "$@"
+ ip_link_set_master "$name" br1
+ bridge_vlan_add vid "$vid" dev "$name" pvid untagged
+}
+export -f vx_create
+
+vx_wait()
+{
+ # Wait for all the ARP, IGMP etc. noise to settle down so that the
+ # tunnel is clear for measurements.
+ sleep 10
+}
+
+vx10_create()
+{
+ vx_create vx10 10 id 1000 "$@"
+}
+export -f vx10_create
+
+vx20_create()
+{
+ vx_create vx20 20 id 2000 "$@"
+}
+export -f vx20_create
+
+vx10_create_wait()
+{
+ vx10_create "$@"
+ vx_wait
+}
+
+vx20_create_wait()
+{
+ vx20_create "$@"
+ vx_wait
+}
+
+ns_init_common()
+{
+ local ns=$1; shift
+ local if_in=$1; shift
+ local ipv4_in=$1; shift
+ local ipv6_in=$1; shift
+ local ipv4_host=$1; shift
+ local ipv6_host=$1; shift
+
+ # v2$h2 / v2$h3
+ ip_link_set_up "$if_in"
+ ip_addr_add "$if_in" "$ipv4_in"
+ ip_addr_add "$if_in" "$ipv6_in"
+
+ # br1
+ ip_link_add br1 type bridge vlan_filtering 1 \
+ vlan_default_pvid 0 mcast_snooping 0
+ ip_link_set_up br1
+
+ # vx10, vx20
+ vx10_create local "${ipv4_in%/*}" group "$GROUP4" dev "$if_in"
+ vx20_create local "${ipv6_in%/*}" group "$GROUP6" dev "$if_in"
+
+ # w1
+ ip_link_add w1 type veth peer name w2
+ ip_link_set_master w1 br1
+ ip_link_set_up w1
+ bridge_vlan_add vid 10 dev w1
+ bridge_vlan_add vid 20 dev w1
+
+ # w2
+ simple_if_init w2
+ defer simple_if_fini w2
+
+ # w2.10
+ ip_link_add w2.10 master vw2 link w2 type vlan id 10
+ ip_link_set_up w2.10
+ ip_addr_add w2.10 "$ipv4_host"
+
+ # w2.20
+ ip_link_add w2.20 master vw2 link w2 type vlan id 20
+ ip_link_set_up w2.20
+ ip_addr_add w2.20 "$ipv6_host"
+}
+export -f ns_init_common
+
+ns2_create()
+{
+ # NS2
+ ip netns add ns2
+ defer ip netns del ns2
+
+ # v2$h2
+ ip link set dev "v2$h2" netns ns2
+ defer ip -n ns2 link set dev "v2$h2" netns 1
+
+ in_ns ns2 \
+ ns_init_common ns2 "v2$h2" \
+ 192.0.2.34/28 2001:db8:2::2/64 \
+ 192.0.2.3/28 2001:db8:1::3/64
+}
+
+ns3_create()
+{
+ # NS3
+ ip netns add ns3
+ defer ip netns del ns3
+
+ # v2$h3
+ ip link set dev "v2$h3" netns ns3
+ defer ip -n ns3 link set dev "v2$h3" netns 1
+
+ ip -n ns3 link set dev "v2$h3" up
+
+ in_ns ns3 \
+ ns_init_common ns3 "v2$h3" \
+ 192.0.2.66/28 2001:db8:3::2/64 \
+ 192.0.2.4/28 2001:db8:1::4/64
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ vrf_prepare
+ defer vrf_cleanup
+
+ forwarding_enable
+ defer forwarding_restore
+
+ ip_link_add "v1$h2" type veth peer name "v2$h2"
+ ip_link_add "v1$h3" type veth peer name "v2$h3"
+
+ h1_create
+ h2_create
+ h3_create
+ switch_create
+ ns2_create
+ ns3_create
+}
+
+adf_install_broken_sg()
+{
+ adf_mcd_start "$IPMR" || exit "$EXIT_STATUS"
+
+ mc_cli add "$swp2" 192.0.2.100 "$GROUP4" "$swp1" "$swp3"
+ defer mc_cli remove "$swp2" 192.0.2.100 "$GROUP4" "$swp1" "$swp3"
+
+ mc_cli add "$swp2" 2001:db8:4::1 "$GROUP6" "$swp1" "$swp3"
+ defer mc_cli remove "$swp2" 2001:db8:4::1 "$GROUP6" "$swp1" "$swp3"
+}
+
+adf_install_rx()
+{
+ mc_cli add "$swp2" 0.0.0.0 "$GROUP4" "$IPMR"
+ defer mc_cli remove "$swp2" 0.0.0.0 "$GROUP4" lo10
+
+ mc_cli add "$swp3" 0.0.0.0 "$GROUP4" "$IPMR"
+ defer mc_cli remove "$swp3" 0.0.0.0 "$GROUP4" lo10
+
+ mc_cli add "$swp2" :: "$GROUP6" "$IPMR"
+ defer mc_cli remove "$swp2" :: "$GROUP6" lo10
+
+ mc_cli add "$swp3" :: "$GROUP6" "$IPMR"
+ defer mc_cli remove "$swp3" :: "$GROUP6" lo10
+}
+
+adf_install_sg()
+{
+ adf_mcd_start "$IPMR" || exit "$EXIT_STATUS"
+
+ mc_cli add "$IPMR" 192.0.2.100 "$GROUP4" "$swp2" "$swp3"
+ defer mc_cli remove "$IPMR" 192.0.2.33 "$GROUP4" "$swp2" "$swp3"
+
+ mc_cli add "$IPMR" 2001:db8:4::1 "$GROUP6" "$swp2" "$swp3"
+ defer mc_cli remove "$IPMR" 2001:db8:4::1 "$GROUP6" "$swp2" "$swp3"
+
+ adf_install_rx
+}
+
+adf_install_sg_sep()
+{
+ adf_mcd_start lo || exit "$EXIT_STATUS"
+
+ mc_cli add lo 192.0.2.120 "$GROUP4" "$swp2" "$swp3"
+ defer mc_cli remove lo 192.0.2.120 "$GROUP4" "$swp2" "$swp3"
+
+ mc_cli add lo 2001:db8:5::1 "$GROUP6" "$swp2" "$swp3"
+ defer mc_cli remove lo 2001:db8:5::1 "$GROUP6" "$swp2" "$swp3"
+}
+
+adf_install_sg_sep_rx()
+{
+ local lo=$1; shift
+
+ adf_mcd_start "$IPMR" "$lo" || exit "$EXIT_STATUS"
+
+ mc_cli add "$lo" 192.0.2.120 "$GROUP4" "$swp2" "$swp3"
+ defer mc_cli remove "$lo" 192.0.2.120 "$GROUP4" "$swp2" "$swp3"
+
+ mc_cli add "$lo" 2001:db8:5::1 "$GROUP6" "$swp2" "$swp3"
+ defer mc_cli remove "$lo" 2001:db8:5::1 "$GROUP6" "$swp2" "$swp3"
+
+ adf_install_rx
+}
+
+adf_install_starg()
+{
+ adf_mcd_start "$IPMR" || exit "$EXIT_STATUS"
+
+ mc_cli add "$IPMR" 0.0.0.0 "$GROUP4" "$swp2" "$swp3"
+ defer mc_cli remove "$IPMR" 0.0.0.0 "$GROUP4" "$swp2" "$swp3"
+
+ mc_cli add "$IPMR" :: "$GROUP6" "$swp2" "$swp3"
+ defer mc_cli remove "$IPMR" :: "$GROUP6" "$swp2" "$swp3"
+
+ adf_install_rx
+}
+
+do_packets_v4()
+{
+ local mac
+
+ mac=$(mac_get "$h2")
+ "$MZ" "$h1" -Q 10 -c 10 -d 100msec -p 64 -a own -b "$mac" \
+ -A 192.0.2.1 -B 192.0.2.2 -t udp sp=1234,dp=2345 -q
+}
+
+do_packets_v6()
+{
+ local mac
+
+ mac=$(mac_get "$h2")
+ "$MZ" -6 "$h1" -Q 20 -c 10 -d 100msec -p 64 -a own -b "$mac" \
+ -A 2001:db8:1::1 -B 2001:db8:1::2 -t udp sp=1234,dp=2345 -q
+}
+
+do_test()
+{
+ local ipv=$1; shift
+ local expect_h2=$1; shift
+ local expect_h3=$1; shift
+ local what=$1; shift
+
+ local pref=$((100 + ipv))
+ local t0_h2
+ local t0_h3
+ local t1_h2
+ local t1_h3
+ local d_h2
+ local d_h3
+
+ RET=0
+
+ t0_h2=$(tc_rule_stats_get "$h2" "$pref" ingress)
+ t0_h3=$(tc_rule_stats_get "$h3" "$pref" ingress)
+
+ "do_packets_v$ipv"
+ sleep 1
+
+ t1_h2=$(tc_rule_stats_get "$h2" "$pref" ingress)
+ t1_h3=$(tc_rule_stats_get "$h3" "$pref" ingress)
+
+ d_h2=$((t1_h2 - t0_h2))
+ d_h3=$((t1_h3 - t0_h3))
+
+ ((d_h2 == expect_h2))
+ check_err $? "Expected $expect_h2 packets on H2, got $d_h2"
+
+ ((d_h3 == expect_h3))
+ check_err $? "Expected $expect_h3 packets on H3, got $d_h3"
+
+ log_test "VXLAN MC flood $what"
+}
+
+ipv4_do_test_rx()
+{
+ local h3_should_fail=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ ping_do "$h1.10" 192.0.2.3
+ check_err $? "H2 should respond"
+
+ ping_do "$h1.10" 192.0.2.4
+ check_err_fail "$h3_should_fail" $? "H3 responds"
+
+ log_test "VXLAN MC flood $what"
+}
+
+ipv6_do_test_rx()
+{
+ local h3_should_fail=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ ping6_do "$h1.20" 2001:db8:1::3
+ check_err $? "H2 should respond"
+
+ ping6_do "$h1.20" 2001:db8:1::4
+ check_err_fail "$h3_should_fail" $? "H3 responds"
+
+ log_test "VXLAN MC flood $what"
+}
+
+ipv4_nomcroute()
+{
+ # Install a misleading (S,G) rule to attempt to trick the system into
+ # pushing the packets elsewhere.
+ adf_install_broken_sg
+ vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$swp2"
+ do_test 4 10 0 "IPv4 nomcroute"
+}
+
+ipv6_nomcroute()
+{
+ # Like for IPv4, install a misleading (S,G).
+ adf_install_broken_sg
+ vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$swp2"
+ do_test 6 10 0 "IPv6 nomcroute"
+}
+
+ipv4_nomcroute_rx()
+{
+ vx10_create local 192.0.2.100 group "$GROUP4" dev "$swp2"
+ ipv4_do_test_rx 1 "IPv4 nomcroute ping"
+}
+
+ipv6_nomcroute_rx()
+{
+ vx20_create local 2001:db8:4::1 group "$GROUP6" dev "$swp2"
+ ipv6_do_test_rx 1 "IPv6 nomcroute ping"
+}
+
+ipv4_mcroute()
+{
+ adf_install_sg
+ vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute
+ do_test 4 10 10 "IPv4 mcroute"
+}
+
+ipv6_mcroute()
+{
+ adf_install_sg
+ vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute
+ do_test 6 10 10 "IPv6 mcroute"
+}
+
+ipv4_mcroute_rx()
+{
+ adf_install_sg
+ vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute
+ ipv4_do_test_rx 0 "IPv4 mcroute ping"
+}
+
+ipv6_mcroute_rx()
+{
+ adf_install_sg
+ vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute
+ ipv6_do_test_rx 0 "IPv6 mcroute ping"
+}
+
+ipv4_mcroute_changelink()
+{
+ adf_install_sg
+ vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR"
+ ip link set dev vx10 type vxlan mcroute
+ sleep 1
+ do_test 4 10 10 "IPv4 mcroute changelink"
+}
+
+ipv6_mcroute_changelink()
+{
+ adf_install_sg
+ vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute
+ ip link set dev vx20 type vxlan mcroute
+ sleep 1
+ do_test 6 10 10 "IPv6 mcroute changelink"
+}
+
+ipv4_mcroute_starg()
+{
+ adf_install_starg
+ vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute
+ do_test 4 10 10 "IPv4 mcroute (*,G)"
+}
+
+ipv6_mcroute_starg()
+{
+ adf_install_starg
+ vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute
+ do_test 6 10 10 "IPv6 mcroute (*,G)"
+}
+
+ipv4_mcroute_starg_rx()
+{
+ adf_install_starg
+ vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute
+ ipv4_do_test_rx 0 "IPv4 mcroute (*,G) ping"
+}
+
+ipv6_mcroute_starg_rx()
+{
+ adf_install_starg
+ vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute
+ ipv6_do_test_rx 0 "IPv6 mcroute (*,G) ping"
+}
+
+ipv4_mcroute_noroute()
+{
+ vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute
+ do_test 4 0 0 "IPv4 mcroute, no route"
+}
+
+ipv6_mcroute_noroute()
+{
+ vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute
+ do_test 6 0 0 "IPv6 mcroute, no route"
+}
+
+ipv4_mcroute_fdb()
+{
+ adf_install_sg
+ vx10_create_wait local 192.0.2.100 dev "$IPMR" mcroute
+ bridge fdb add dev vx10 \
+ 00:00:00:00:00:00 self static dst "$GROUP4" via "$IPMR"
+ do_test 4 10 10 "IPv4 mcroute FDB"
+}
+
+ipv6_mcroute_fdb()
+{
+ adf_install_sg
+ vx20_create_wait local 2001:db8:4::1 dev "$IPMR" mcroute
+ bridge -6 fdb add dev vx20 \
+ 00:00:00:00:00:00 self static dst "$GROUP6" via "$IPMR"
+ do_test 6 10 10 "IPv6 mcroute FDB"
+}
+
+# Use FDB to configure VXLAN in a way where oif=0 for purposes of FIB lookup.
+ipv4_mcroute_fdb_oif0()
+{
+ adf_install_sg
+ vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute
+ bridge fdb del dev vx10 00:00:00:00:00:00
+ bridge fdb add dev vx10 00:00:00:00:00:00 self static dst "$GROUP4"
+ do_test 4 10 10 "IPv4 mcroute oif=0"
+}
+
+ipv6_mcroute_fdb_oif0()
+{
+ # The IPv6 tunnel lookup does not fall back to selection by source
+ # address. Instead it just does a FIB match, and that would find one of
+ # the several ff00::/8 multicast routes -- each device has one. In order
+ # to reliably force the $IPMR device, add a /128 route for the
+ # destination group address.
+ ip -6 route add table local multicast "$GROUP6/128" dev "$IPMR"
+ defer ip -6 route del table local multicast "$GROUP6/128" dev "$IPMR"
+
+ adf_install_sg
+ vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute
+ bridge -6 fdb del dev vx20 00:00:00:00:00:00
+ bridge -6 fdb add dev vx20 00:00:00:00:00:00 self static dst "$GROUP6"
+ do_test 6 10 10 "IPv6 mcroute oif=0"
+}
+
+# In oif=0 test as above, have FIB lookup resolve to loopback instead of IPMR.
+# This doesn't work with IPv6 -- a MC route on lo would be marked as RTF_REJECT.
+ipv4_mcroute_fdb_oif0_sep()
+{
+ adf_install_sg_sep
+
+ ip_addr_add lo 192.0.2.120/28
+ vx10_create_wait local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute
+ bridge fdb del dev vx10 00:00:00:00:00:00
+ bridge fdb add dev vx10 00:00:00:00:00:00 self static dst "$GROUP4"
+ do_test 4 10 10 "IPv4 mcroute TX!=RX oif=0"
+}
+
+ipv4_mcroute_fdb_oif0_sep_rx()
+{
+ adf_install_sg_sep_rx lo
+
+ ip_addr_add lo 192.0.2.120/28
+ vx10_create_wait local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute
+ bridge fdb del dev vx10 00:00:00:00:00:00
+ bridge fdb add dev vx10 00:00:00:00:00:00 self static dst "$GROUP4"
+ ipv4_do_test_rx 0 "IPv4 mcroute TX!=RX oif=0 ping"
+}
+
+ipv4_mcroute_fdb_sep_rx()
+{
+ adf_install_sg_sep_rx lo
+
+ ip_addr_add lo 192.0.2.120/28
+ vx10_create_wait local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute
+ bridge fdb del dev vx10 00:00:00:00:00:00
+ bridge fdb add \
+ dev vx10 00:00:00:00:00:00 self static dst "$GROUP4" via lo
+ ipv4_do_test_rx 0 "IPv4 mcroute TX!=RX ping"
+}
+
+ipv6_mcroute_fdb_sep_rx()
+{
+ adf_install_sg_sep_rx "X$IPMR"
+
+ ip_addr_add "X$IPMR" 2001:db8:5::1/64
+ vx20_create_wait local 2001:db8:5::1 group "$GROUP6" dev "$IPMR" mcroute
+ bridge -6 fdb del dev vx20 00:00:00:00:00:00
+ bridge -6 fdb add dev vx20 00:00:00:00:00:00 \
+ self static dst "$GROUP6" via "X$IPMR"
+ ipv6_do_test_rx 0 "IPv6 mcroute TX!=RX ping"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit "$EXIT_STATUS"
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..48eb999a3120
--- /dev/null
+++ b/tools/testing/selftests/net/gre_ipv6_lladdr.sh
@@ -0,0 +1,184 @@
+#!/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 the IPv6 configuration of a network device.
+#
+# We currently check the generation of the link-local IPv6 address and the
+# creation of the ff00::/8 multicast route.
+#
+# 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_device_config()
+{
+ 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}" $? "IPv6 link-local address generation"
+
+ ip -netns "${NS0}" -6 route show table local type multicast ff00::/8 proto kernel | grep -q "${DEV}"
+ check_err_fail 0 $? "IPv6 multicast route creation"
+
+ log_test "${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} -> ${REMOTE_IP}"
+ XRET=0
+ ;;
+ esac
+
+ # Check the IPv6 device configuration when it goes up
+ ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}"
+ ip -netns "${NS0}" link set dev gretest up
+ check_ipv6_device_config 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 the IPv6 device configuration when link-local address
+ # generation is 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_device_config 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 configuration of ${GRE_TYPE} devices\n####\n\n"
+
+ for MODE in "eui64" "none" "stable-privacy" "random"; do
+ test_gre_device "${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 configuration of ${GRE_TYPE} devices\n####\n\n"
+
+ for MODE in "eui64" "none" "stable-privacy" "random"; do
+ test_gre_device "${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/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/ipv6_force_forwarding.sh b/tools/testing/selftests/net/ipv6_force_forwarding.sh
new file mode 100755
index 000000000000..bf0243366caa
--- /dev/null
+++ b/tools/testing/selftests/net/ipv6_force_forwarding.sh
@@ -0,0 +1,105 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test IPv6 force_forwarding interface property
+#
+# This test verifies that the force_forwarding property works correctly:
+# - When global forwarding is disabled, packets are not forwarded normally
+# - When force_forwarding is enabled on an interface, packets are forwarded
+# regardless of the global forwarding setting
+
+source lib.sh
+
+cleanup() {
+ cleanup_ns $ns1 $ns2 $ns3
+}
+
+trap cleanup EXIT
+
+setup_test() {
+ # Create three namespaces: sender, router, receiver
+ setup_ns ns1 ns2 ns3
+
+ # Create veth pairs: ns1 <-> ns2 <-> ns3
+ ip link add name veth12 type veth peer name veth21
+ ip link add name veth23 type veth peer name veth32
+
+ # Move interfaces to namespaces
+ ip link set veth12 netns $ns1
+ ip link set veth21 netns $ns2
+ ip link set veth23 netns $ns2
+ ip link set veth32 netns $ns3
+
+ # Configure interfaces
+ ip -n $ns1 addr add 2001:db8:1::1/64 dev veth12 nodad
+ ip -n $ns2 addr add 2001:db8:1::2/64 dev veth21 nodad
+ ip -n $ns2 addr add 2001:db8:2::1/64 dev veth23 nodad
+ ip -n $ns3 addr add 2001:db8:2::2/64 dev veth32 nodad
+
+ # Bring up interfaces
+ ip -n $ns1 link set veth12 up
+ ip -n $ns2 link set veth21 up
+ ip -n $ns2 link set veth23 up
+ ip -n $ns3 link set veth32 up
+
+ # Add routes
+ ip -n $ns1 route add 2001:db8:2::/64 via 2001:db8:1::2
+ ip -n $ns3 route add 2001:db8:1::/64 via 2001:db8:2::1
+
+ # Disable global forwarding
+ ip netns exec $ns2 sysctl -qw net.ipv6.conf.all.forwarding=0
+}
+
+test_force_forwarding() {
+ local ret=0
+
+ echo "TEST: force_forwarding functionality"
+
+ # Check if force_forwarding sysctl exists
+ if ! ip netns exec $ns2 test -f /proc/sys/net/ipv6/conf/veth21/force_forwarding; then
+ echo "SKIP: force_forwarding not available"
+ return $ksft_skip
+ fi
+
+ # Test 1: Without force_forwarding, ping should fail
+ ip netns exec $ns2 sysctl -qw net.ipv6.conf.veth21.force_forwarding=0
+ ip netns exec $ns2 sysctl -qw net.ipv6.conf.veth23.force_forwarding=0
+
+ if ip netns exec $ns1 ping -6 -c 1 -W 2 2001:db8:2::2 &>/dev/null; then
+ echo "FAIL: ping succeeded when forwarding disabled"
+ ret=1
+ else
+ echo "PASS: forwarding disabled correctly"
+ fi
+
+ # Test 2: With force_forwarding enabled, ping should succeed
+ ip netns exec $ns2 sysctl -qw net.ipv6.conf.veth21.force_forwarding=1
+ ip netns exec $ns2 sysctl -qw net.ipv6.conf.veth23.force_forwarding=1
+
+ if ip netns exec $ns1 ping -6 -c 1 -W 2 2001:db8:2::2 &>/dev/null; then
+ echo "PASS: force_forwarding enabled forwarding"
+ else
+ echo "FAIL: ping failed with force_forwarding enabled"
+ ret=1
+ fi
+
+ return $ret
+}
+
+echo "IPv6 force_forwarding test"
+echo "=========================="
+
+setup_test
+test_force_forwarding
+ret=$?
+
+if [ $ret -eq 0 ]; then
+ echo "OK"
+ exit 0
+elif [ $ret -eq $ksft_skip ]; then
+ echo "SKIP"
+ exit $ksft_skip
+else
+ echo "FAIL"
+ exit 1
+fi
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 975be4fdbcdb..c7add0dc4c60 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -217,11 +217,61 @@ 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
+}
+
+create_netdevsim_port() {
+ local nsim_id="$1"
+ local ns="$2"
+ local port_id="$3"
+ local perm_addr="$4"
+ local orig_dev
+ local new_dev
+ local nsim_path
+
+ nsim_path="/sys/bus/netdevsim/devices/netdevsim$nsim_id"
+
+ echo "$port_id $perm_addr" | ip netns exec "$ns" tee "$nsim_path"/new_port > /dev/null || return 1
+
+ orig_dev=$(ip netns exec "$ns" find "$nsim_path"/net/ -maxdepth 1 -name 'e*' | tail -n 1)
+ orig_dev=$(basename "$orig_dev")
+ new_dev="nsim${nsim_id}p$port_id"
+
+ ip -netns "$ns" link set dev "$orig_dev" name "$new_dev"
+ ip -netns "$ns" link set dev "$new_dev" up
+
+ echo "$new_dev"
+}
+
+# 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=$1; shift
@@ -245,6 +295,30 @@ tc_rule_handle_stats_get()
.options.actions[0].stats$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
@@ -261,7 +335,7 @@ log_test_result()
local test_name=$1; shift
local opt_str=$1; shift
local result=$1; shift
- local retmsg=$1; shift
+ local retmsg=$1
printf "TEST: %-60s [%s]\n" "$test_name $opt_str" "$result"
if [[ $retmsg ]]; then
@@ -496,13 +570,19 @@ ip_link_set_addr()
defer ip link set dev "$name" address "$old_addr"
}
-ip_link_is_up()
+ip_link_has_flag()
{
local name=$1; shift
+ local flag=$1; shift
local state=$(ip -j link show "$name" |
- jq -r '(.[].flags[] | select(. == "UP")) // "DOWN"')
- [[ $state == "UP" ]]
+ jq --arg flag "$flag" 'any(.[].flags.[]; . == $flag)')
+ [[ $state == true ]]
+}
+
+ip_link_is_up()
+{
+ ip_link_has_flag "$1" UP
}
ip_link_set_up()
@@ -544,3 +624,24 @@ bridge_vlan_add()
bridge vlan add "$@"
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 8697bd27dc30..02be28dcc089 100644
--- a/tools/testing/selftests/net/lib/py/__init__.py
+++ b/tools/testing/selftests/net/lib/py/__init__.py
@@ -6,4 +6,4 @@ from .netns import NetNS, NetNSEnter
from .nsim import *
from .utils import *
from .ynl import NlError, YnlFamily, EthtoolFamily, NetdevFamily, RtnlFamily, RtnlAddrFamily
-from .ynl import NetshaperFamily
+from .ynl import NetshaperFamily, DevlinkFamily
diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py
index 3cfad0fd4570..8e35ed12ed9e 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
@@ -26,7 +27,12 @@ class KsftXfailEx(Exception):
pass
+class KsftTerminate(KeyboardInterrupt):
+ pass
+
+
def ksft_pr(*objs, **kwargs):
+ kwargs["flush"] = True
print("#", *objs, **kwargs)
@@ -134,7 +140,7 @@ def ktap_result(ok, cnt=1, case="", comment=""):
res += "." + str(case.__name__)
if comment:
res += " # " + comment
- print(res)
+ print(res, flush=True)
def ksft_flush_defer():
@@ -193,6 +199,17 @@ 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 []
@@ -205,10 +222,14 @@ 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("TAP version 13")
- print("1.." + str(len(cases)))
+ print("TAP version 13", flush=True)
+ print("1.." + str(len(cases)), flush=True)
global KSFT_RESULT
cnt = 0
@@ -233,7 +254,7 @@ 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'
@@ -248,6 +269,8 @@ 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/utils.py b/tools/testing/selftests/net/lib/py/utils.py
index 34470d65d871..f395c90fb0f1 100644
--- a/tools/testing/selftests/net/lib/py/utils.py
+++ b/tools/testing/selftests/net/lib/py/utils.py
@@ -175,6 +175,10 @@ def tool(name, args, json=None, ns=None, host=None):
return cmd_obj
+def bpftool(args, json=None, ns=None, host=None):
+ return tool('bpftool', args, json=json, ns=ns, host=host)
+
+
def ip(args, json=None, ns=None, host=None):
if ns:
args = f'-netns {ns} ' + args
@@ -185,6 +189,41 @@ def ethtool(args, json=None, ns=None, host=None):
return tool('ethtool', args, json=json, ns=ns, host=host)
+def bpftrace(expr, json=None, ns=None, host=None, timeout=None):
+ """
+ Run bpftrace and return map data (if json=True).
+ The output of bpftrace is inconvenient, so the helper converts
+ to a dict indexed by map name, e.g.:
+ {
+ "@": { ... },
+ "@map2": { ... },
+ }
+ """
+ cmd_arr = ['bpftrace']
+ # Throw in --quiet if json, otherwise the output has two objects
+ if json:
+ cmd_arr += ['-f', 'json', '-q']
+ if timeout:
+ expr += ' interval:s:' + str(timeout) + ' { exit(); }'
+ cmd_arr += ['-e', expr]
+ cmd_obj = cmd(cmd_arr, ns=ns, host=host, shell=False)
+ if json:
+ # bpftrace prints objects as lines
+ ret = {}
+ for l in cmd_obj.stdout.split('\n'):
+ if not l.strip():
+ continue
+ one = _json.loads(l)
+ if one.get('type') != 'map':
+ continue
+ for k, v in one["data"].items():
+ if k.startswith('@'):
+ k = k.lstrip('@')
+ ret[k] = v
+ return ret
+ return cmd_obj
+
+
def rand_port(type=socket.SOCK_STREAM):
"""
Get a random unprivileged port.
diff --git a/tools/testing/selftests/net/lib/py/ynl.py b/tools/testing/selftests/net/lib/py/ynl.py
index 8986c584cb37..2b3a61ea3bfa 100644
--- a/tools/testing/selftests/net/lib/py/ynl.py
+++ b/tools/testing/selftests/net/lib/py/ynl.py
@@ -39,12 +39,12 @@ 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(),
+ super().__init__((SPEC_PATH / Path('rt-addr.yaml')).as_posix(),
schema='', recv_size=recv_size)
class NetdevFamily(YnlFamily):
@@ -56,3 +56,8 @@ class NetshaperFamily(YnlFamily):
def __init__(self, recv_size=0):
super().__init__((SPEC_PATH / Path('net_shaper.yaml')).as_posix(),
schema='', recv_size=recv_size)
+
+class DevlinkFamily(YnlFamily):
+ def __init__(self, recv_size=0):
+ super().__init__((SPEC_PATH / Path('devlink.yaml')).as_posix(),
+ schema='', recv_size=recv_size)
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/lib/xdp_native.bpf.c b/tools/testing/selftests/net/lib/xdp_native.bpf.c
new file mode 100644
index 000000000000..521ba38f2ddd
--- /dev/null
+++ b/tools/testing/selftests/net/lib/xdp_native.bpf.c
@@ -0,0 +1,621 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/udp.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
+
+#define MAX_ADJST_OFFSET 256
+#define MAX_PAYLOAD_LEN 5000
+#define MAX_HDR_LEN 64
+
+enum {
+ XDP_MODE = 0,
+ XDP_PORT = 1,
+ XDP_ADJST_OFFSET = 2,
+ XDP_ADJST_TAG = 3,
+} xdp_map_setup_keys;
+
+enum {
+ XDP_MODE_PASS = 0,
+ XDP_MODE_DROP = 1,
+ XDP_MODE_TX = 2,
+ XDP_MODE_TAIL_ADJST = 3,
+ XDP_MODE_HEAD_ADJST = 4,
+} xdp_map_modes;
+
+enum {
+ STATS_RX = 0,
+ STATS_PASS = 1,
+ STATS_DROP = 2,
+ STATS_TX = 3,
+ STATS_ABORT = 4,
+} xdp_stats;
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 5);
+ __type(key, __u32);
+ __type(value, __s32);
+} map_xdp_setup SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 5);
+ __type(key, __u32);
+ __type(value, __u64);
+} map_xdp_stats SEC(".maps");
+
+static __u32 min(__u32 a, __u32 b)
+{
+ return a < b ? a : b;
+}
+
+static void record_stats(struct xdp_md *ctx, __u32 stat_type)
+{
+ __u64 *count;
+
+ count = bpf_map_lookup_elem(&map_xdp_stats, &stat_type);
+
+ if (count)
+ __sync_fetch_and_add(count, 1);
+}
+
+static struct udphdr *filter_udphdr(struct xdp_md *ctx, __u16 port)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct udphdr *udph = NULL;
+ struct ethhdr *eth = data;
+
+ if (data + sizeof(*eth) > data_end)
+ return NULL;
+
+ if (eth->h_proto == bpf_htons(ETH_P_IP)) {
+ struct iphdr *iph = data + sizeof(*eth);
+
+ if (iph + 1 > (struct iphdr *)data_end ||
+ iph->protocol != IPPROTO_UDP)
+ return NULL;
+
+ udph = (void *)eth + sizeof(*iph) + sizeof(*eth);
+ } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) {
+ struct ipv6hdr *ipv6h = data + sizeof(*eth);
+
+ if (ipv6h + 1 > (struct ipv6hdr *)data_end ||
+ ipv6h->nexthdr != IPPROTO_UDP)
+ return NULL;
+
+ udph = (void *)eth + sizeof(*ipv6h) + sizeof(*eth);
+ } else {
+ return NULL;
+ }
+
+ if (udph + 1 > (struct udphdr *)data_end)
+ return NULL;
+
+ if (udph->dest != bpf_htons(port))
+ return NULL;
+
+ record_stats(ctx, STATS_RX);
+
+ return udph;
+}
+
+static int xdp_mode_pass(struct xdp_md *ctx, __u16 port)
+{
+ struct udphdr *udph = NULL;
+
+ udph = filter_udphdr(ctx, port);
+ if (!udph)
+ return XDP_PASS;
+
+ record_stats(ctx, STATS_PASS);
+
+ return XDP_PASS;
+}
+
+static int xdp_mode_drop_handler(struct xdp_md *ctx, __u16 port)
+{
+ struct udphdr *udph = NULL;
+
+ udph = filter_udphdr(ctx, port);
+ if (!udph)
+ return XDP_PASS;
+
+ record_stats(ctx, STATS_DROP);
+
+ return XDP_DROP;
+}
+
+static void swap_machdr(void *data)
+{
+ struct ethhdr *eth = data;
+ __u8 tmp_mac[ETH_ALEN];
+
+ __builtin_memcpy(tmp_mac, eth->h_source, ETH_ALEN);
+ __builtin_memcpy(eth->h_source, eth->h_dest, ETH_ALEN);
+ __builtin_memcpy(eth->h_dest, tmp_mac, ETH_ALEN);
+}
+
+static int xdp_mode_tx_handler(struct xdp_md *ctx, __u16 port)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct udphdr *udph = NULL;
+ struct ethhdr *eth = data;
+
+ if (data + sizeof(*eth) > data_end)
+ return XDP_PASS;
+
+ if (eth->h_proto == bpf_htons(ETH_P_IP)) {
+ struct iphdr *iph = data + sizeof(*eth);
+ __be32 tmp_ip = iph->saddr;
+
+ if (iph + 1 > (struct iphdr *)data_end ||
+ iph->protocol != IPPROTO_UDP)
+ return XDP_PASS;
+
+ udph = data + sizeof(*iph) + sizeof(*eth);
+
+ if (udph + 1 > (struct udphdr *)data_end)
+ return XDP_PASS;
+ if (udph->dest != bpf_htons(port))
+ return XDP_PASS;
+
+ record_stats(ctx, STATS_RX);
+ swap_machdr((void *)eth);
+
+ iph->saddr = iph->daddr;
+ iph->daddr = tmp_ip;
+
+ record_stats(ctx, STATS_TX);
+
+ return XDP_TX;
+
+ } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) {
+ struct ipv6hdr *ipv6h = data + sizeof(*eth);
+ struct in6_addr tmp_ipv6;
+
+ if (ipv6h + 1 > (struct ipv6hdr *)data_end ||
+ ipv6h->nexthdr != IPPROTO_UDP)
+ return XDP_PASS;
+
+ udph = data + sizeof(*ipv6h) + sizeof(*eth);
+
+ if (udph + 1 > (struct udphdr *)data_end)
+ return XDP_PASS;
+ if (udph->dest != bpf_htons(port))
+ return XDP_PASS;
+
+ record_stats(ctx, STATS_RX);
+ swap_machdr((void *)eth);
+
+ __builtin_memcpy(&tmp_ipv6, &ipv6h->saddr, sizeof(tmp_ipv6));
+ __builtin_memcpy(&ipv6h->saddr, &ipv6h->daddr,
+ sizeof(tmp_ipv6));
+ __builtin_memcpy(&ipv6h->daddr, &tmp_ipv6, sizeof(tmp_ipv6));
+
+ record_stats(ctx, STATS_TX);
+
+ return XDP_TX;
+ }
+
+ return XDP_PASS;
+}
+
+static void *update_pkt(struct xdp_md *ctx, __s16 offset, __u32 *udp_csum)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct udphdr *udph = NULL;
+ struct ethhdr *eth = data;
+ __u32 len, len_new;
+
+ if (data + sizeof(*eth) > data_end)
+ return NULL;
+
+ if (eth->h_proto == bpf_htons(ETH_P_IP)) {
+ struct iphdr *iph = data + sizeof(*eth);
+ __u16 total_len;
+
+ if (iph + 1 > (struct iphdr *)data_end)
+ return NULL;
+
+ iph->tot_len = bpf_htons(bpf_ntohs(iph->tot_len) + offset);
+
+ udph = (void *)eth + sizeof(*iph) + sizeof(*eth);
+ if (!udph || udph + 1 > (struct udphdr *)data_end)
+ return NULL;
+
+ len_new = bpf_htons(bpf_ntohs(udph->len) + offset);
+ } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) {
+ struct ipv6hdr *ipv6h = data + sizeof(*eth);
+ __u16 payload_len;
+
+ if (ipv6h + 1 > (struct ipv6hdr *)data_end)
+ return NULL;
+
+ udph = (void *)eth + sizeof(*ipv6h) + sizeof(*eth);
+ if (!udph || udph + 1 > (struct udphdr *)data_end)
+ return NULL;
+
+ *udp_csum = ~((__u32)udph->check);
+
+ len = ipv6h->payload_len;
+ len_new = bpf_htons(bpf_ntohs(len) + offset);
+ ipv6h->payload_len = len_new;
+
+ *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new,
+ sizeof(len_new), *udp_csum);
+
+ len = udph->len;
+ len_new = bpf_htons(bpf_ntohs(udph->len) + offset);
+ *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new,
+ sizeof(len_new), *udp_csum);
+ } else {
+ return NULL;
+ }
+
+ udph->len = len_new;
+
+ return udph;
+}
+
+static __u16 csum_fold_helper(__u32 csum)
+{
+ return ~((csum & 0xffff) + (csum >> 16)) ? : 0xffff;
+}
+
+static int xdp_adjst_tail_shrnk_data(struct xdp_md *ctx, __u16 offset,
+ __u32 hdr_len)
+{
+ char tmp_buff[MAX_ADJST_OFFSET];
+ __u32 buff_pos, udp_csum = 0;
+ struct udphdr *udph = NULL;
+ __u32 buff_len;
+
+ udph = update_pkt(ctx, 0 - offset, &udp_csum);
+ if (!udph)
+ return -1;
+
+ buff_len = bpf_xdp_get_buff_len(ctx);
+
+ offset = (offset & 0x1ff) >= MAX_ADJST_OFFSET ? MAX_ADJST_OFFSET :
+ offset & 0xff;
+ if (offset == 0)
+ return -1;
+
+ /* Make sure we have enough data to avoid eating the header */
+ if (buff_len - offset < hdr_len)
+ return -1;
+
+ buff_pos = buff_len - offset;
+ if (bpf_xdp_load_bytes(ctx, buff_pos, tmp_buff, offset) < 0)
+ return -1;
+
+ udp_csum = bpf_csum_diff((__be32 *)tmp_buff, offset, 0, 0, udp_csum);
+ udph->check = (__u16)csum_fold_helper(udp_csum);
+
+ if (bpf_xdp_adjust_tail(ctx, 0 - offset) < 0)
+ return -1;
+
+ return 0;
+}
+
+static int xdp_adjst_tail_grow_data(struct xdp_md *ctx, __u16 offset)
+{
+ char tmp_buff[MAX_ADJST_OFFSET];
+ __u32 buff_pos, udp_csum = 0;
+ __u32 buff_len, hdr_len, key;
+ struct udphdr *udph;
+ __s32 *val;
+ __u8 tag;
+
+ /* Proceed to update the packet headers before attempting to adjuste
+ * the tail. Once the tail is adjusted we lose access to the offset
+ * amount of data at the end of the packet which is crucial to update
+ * the checksum.
+ * Since any failure beyond this would abort the packet, we should
+ * not worry about passing a packet up the stack with wrong headers
+ */
+ udph = update_pkt(ctx, offset, &udp_csum);
+ if (!udph)
+ return -1;
+
+ key = XDP_ADJST_TAG;
+ val = bpf_map_lookup_elem(&map_xdp_setup, &key);
+ if (!val)
+ return -1;
+
+ tag = (__u8)(*val);
+
+ for (int i = 0; i < MAX_ADJST_OFFSET; i++)
+ __builtin_memcpy(&tmp_buff[i], &tag, 1);
+
+ offset = (offset & 0x1ff) >= MAX_ADJST_OFFSET ? MAX_ADJST_OFFSET :
+ offset & 0xff;
+ if (offset == 0)
+ return -1;
+
+ udp_csum = bpf_csum_diff(0, 0, (__be32 *)tmp_buff, offset, udp_csum);
+ udph->check = (__u16)csum_fold_helper(udp_csum);
+
+ buff_len = bpf_xdp_get_buff_len(ctx);
+
+ if (bpf_xdp_adjust_tail(ctx, offset) < 0) {
+ bpf_printk("Failed to adjust tail\n");
+ return -1;
+ }
+
+ if (bpf_xdp_store_bytes(ctx, buff_len, tmp_buff, offset) < 0)
+ return -1;
+
+ return 0;
+}
+
+static int xdp_adjst_tail(struct xdp_md *ctx, __u16 port)
+{
+ void *data = (void *)(long)ctx->data;
+ struct udphdr *udph = NULL;
+ __s32 *adjust_offset, *val;
+ __u32 key, hdr_len;
+ void *offset_ptr;
+ __u8 tag;
+ int ret;
+
+ udph = filter_udphdr(ctx, port);
+ if (!udph)
+ return XDP_PASS;
+
+ hdr_len = (void *)udph - data + sizeof(struct udphdr);
+ key = XDP_ADJST_OFFSET;
+ adjust_offset = bpf_map_lookup_elem(&map_xdp_setup, &key);
+ if (!adjust_offset)
+ return XDP_PASS;
+
+ if (*adjust_offset < 0)
+ ret = xdp_adjst_tail_shrnk_data(ctx,
+ (__u16)(0 - *adjust_offset),
+ hdr_len);
+ else
+ ret = xdp_adjst_tail_grow_data(ctx, (__u16)(*adjust_offset));
+ if (ret)
+ goto abort_pkt;
+
+ record_stats(ctx, STATS_PASS);
+ return XDP_PASS;
+
+abort_pkt:
+ record_stats(ctx, STATS_ABORT);
+ return XDP_ABORTED;
+}
+
+static int xdp_adjst_head_shrnk_data(struct xdp_md *ctx, __u64 hdr_len,
+ __u32 offset)
+{
+ char tmp_buff[MAX_ADJST_OFFSET];
+ struct udphdr *udph;
+ void *offset_ptr;
+ __u32 udp_csum = 0;
+
+ /* Update the length information in the IP and UDP headers before
+ * adjusting the headroom. This simplifies accessing the relevant
+ * fields in the IP and UDP headers for fragmented packets. Any
+ * failure beyond this point will result in the packet being aborted,
+ * so we don't need to worry about incorrect length information for
+ * passed packets.
+ */
+ udph = update_pkt(ctx, (__s16)(0 - offset), &udp_csum);
+ if (!udph)
+ return -1;
+
+ offset = (offset & 0x1ff) >= MAX_ADJST_OFFSET ? MAX_ADJST_OFFSET :
+ offset & 0xff;
+ if (offset == 0)
+ return -1;
+
+ if (bpf_xdp_load_bytes(ctx, hdr_len, tmp_buff, offset) < 0)
+ return -1;
+
+ udp_csum = bpf_csum_diff((__be32 *)tmp_buff, offset, 0, 0, udp_csum);
+
+ udph->check = (__u16)csum_fold_helper(udp_csum);
+
+ if (bpf_xdp_load_bytes(ctx, 0, tmp_buff, MAX_ADJST_OFFSET) < 0)
+ return -1;
+
+ if (bpf_xdp_adjust_head(ctx, offset) < 0)
+ return -1;
+
+ if (offset > MAX_ADJST_OFFSET)
+ return -1;
+
+ if (hdr_len > MAX_ADJST_OFFSET || hdr_len == 0)
+ return -1;
+
+ /* Added here to handle clang complain about negative value */
+ hdr_len = hdr_len & 0xff;
+
+ if (hdr_len == 0)
+ return -1;
+
+ if (bpf_xdp_store_bytes(ctx, 0, tmp_buff, hdr_len) < 0)
+ return -1;
+
+ return 0;
+}
+
+static int xdp_adjst_head_grow_data(struct xdp_md *ctx, __u64 hdr_len,
+ __u32 offset)
+{
+ char hdr_buff[MAX_HDR_LEN];
+ char data_buff[MAX_ADJST_OFFSET];
+ void *offset_ptr;
+ __s32 *val;
+ __u32 key;
+ __u8 tag;
+ __u32 udp_csum = 0;
+ struct udphdr *udph;
+
+ udph = update_pkt(ctx, (__s16)(offset), &udp_csum);
+ if (!udph)
+ return -1;
+
+ key = XDP_ADJST_TAG;
+ val = bpf_map_lookup_elem(&map_xdp_setup, &key);
+ if (!val)
+ return -1;
+
+ tag = (__u8)(*val);
+ for (int i = 0; i < MAX_ADJST_OFFSET; i++)
+ __builtin_memcpy(&data_buff[i], &tag, 1);
+
+ offset = (offset & 0x1ff) >= MAX_ADJST_OFFSET ? MAX_ADJST_OFFSET :
+ offset & 0xff;
+ if (offset == 0)
+ return -1;
+
+ udp_csum = bpf_csum_diff(0, 0, (__be32 *)data_buff, offset, udp_csum);
+ udph->check = (__u16)csum_fold_helper(udp_csum);
+
+ if (hdr_len > MAX_ADJST_OFFSET || hdr_len == 0)
+ return -1;
+
+ /* Added here to handle clang complain about negative value */
+ hdr_len = hdr_len & 0xff;
+
+ if (hdr_len == 0)
+ return -1;
+
+ if (bpf_xdp_load_bytes(ctx, 0, hdr_buff, hdr_len) < 0)
+ return -1;
+
+ if (offset > MAX_ADJST_OFFSET)
+ return -1;
+
+ if (bpf_xdp_adjust_head(ctx, 0 - offset) < 0)
+ return -1;
+
+ if (bpf_xdp_store_bytes(ctx, 0, hdr_buff, hdr_len) < 0)
+ return -1;
+
+ if (bpf_xdp_store_bytes(ctx, hdr_len, data_buff, offset) < 0)
+ return -1;
+
+ return 0;
+}
+
+static int xdp_head_adjst(struct xdp_md *ctx, __u16 port)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct udphdr *udph_ptr = NULL;
+ __u32 key, size, hdr_len;
+ __s32 *val;
+ int res;
+
+ /* Filter packets based on UDP port */
+ udph_ptr = filter_udphdr(ctx, port);
+ if (!udph_ptr)
+ return XDP_PASS;
+
+ hdr_len = (void *)udph_ptr - data + sizeof(struct udphdr);
+
+ key = XDP_ADJST_OFFSET;
+ val = bpf_map_lookup_elem(&map_xdp_setup, &key);
+ if (!val)
+ return XDP_PASS;
+
+ switch (*val) {
+ case -16:
+ case 16:
+ size = 16;
+ break;
+ case -32:
+ case 32:
+ size = 32;
+ break;
+ case -64:
+ case 64:
+ size = 64;
+ break;
+ case -128:
+ case 128:
+ size = 128;
+ break;
+ case -256:
+ case 256:
+ size = 256;
+ break;
+ default:
+ bpf_printk("Invalid adjustment offset: %d\n", *val);
+ goto abort;
+ }
+
+ if (*val < 0)
+ res = xdp_adjst_head_grow_data(ctx, hdr_len, size);
+ else
+ res = xdp_adjst_head_shrnk_data(ctx, hdr_len, size);
+
+ if (res)
+ goto abort;
+
+ record_stats(ctx, STATS_PASS);
+ return XDP_PASS;
+
+abort:
+ record_stats(ctx, STATS_ABORT);
+ return XDP_ABORTED;
+}
+
+static int xdp_prog_common(struct xdp_md *ctx)
+{
+ __u32 key, *port;
+ __s32 *mode;
+
+ key = XDP_MODE;
+ mode = bpf_map_lookup_elem(&map_xdp_setup, &key);
+ if (!mode)
+ return XDP_PASS;
+
+ key = XDP_PORT;
+ port = bpf_map_lookup_elem(&map_xdp_setup, &key);
+ if (!port)
+ return XDP_PASS;
+
+ switch (*mode) {
+ case XDP_MODE_PASS:
+ return xdp_mode_pass(ctx, (__u16)(*port));
+ case XDP_MODE_DROP:
+ return xdp_mode_drop_handler(ctx, (__u16)(*port));
+ case XDP_MODE_TX:
+ return xdp_mode_tx_handler(ctx, (__u16)(*port));
+ case XDP_MODE_TAIL_ADJST:
+ return xdp_adjst_tail(ctx, (__u16)(*port));
+ case XDP_MODE_HEAD_ADJST:
+ return xdp_head_adjst(ctx, (__u16)(*port));
+ }
+
+ /* Default action is to simple pass */
+ return XDP_PASS;
+}
+
+SEC("xdp")
+int xdp_prog(struct xdp_md *ctx)
+{
+ return xdp_prog_common(ctx);
+}
+
+SEC("xdp.frags")
+int xdp_prog_frags(struct xdp_md *ctx)
+{
+ return xdp_prog_common(ctx);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile
index 340e1a777e16..4c7e51336ab2 100644
--- a/tools/testing/selftests/net/mptcp/Makefile
+++ b/tools/testing/selftests/net/mptcp/Makefile
@@ -4,14 +4,15 @@ top_srcdir = ../../../../..
CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES)
-TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \
+TEST_PROGS := mptcp_connect.sh mptcp_connect_mmap.sh mptcp_connect_sendfile.sh \
+ mptcp_connect_checksum.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 mptcp_diag
TEST_FILES := mptcp_lib.sh settings
-TEST_INCLUDES := ../lib.sh $(wildcard ../lib/sh/*.sh) ../net_helper.sh
+TEST_INCLUDES := ../lib.sh $(wildcard ../lib/sh/*.sh)
EXTRA_CLEAN := *.pcap
diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config
index 4f80014cae49..968d440c03fe 100644
--- a/tools/testing/selftests/net/mptcp/config
+++ b/tools/testing/selftests/net/mptcp/config
@@ -13,6 +13,7 @@ CONFIG_NETFILTER_NETLINK=m
CONFIG_NF_TABLES=m
CONFIG_NFT_COMPAT=m
CONFIG_NETFILTER_XTABLES=m
+CONFIG_NETFILTER_XTABLES_LEGACY=y
CONFIG_NETFILTER_XT_MATCH_BPF=m
CONFIG_NETFILTER_XT_MATCH_LENGTH=m
CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
@@ -25,6 +26,7 @@ CONFIG_IP_MULTIPLE_TABLES=y
CONFIG_IP_NF_FILTER=m
CONFIG_IP_NF_MANGLE=m
CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP6_NF_TARGET_REJECT=m
CONFIG_IPV6_MULTIPLE_TABLES=y
CONFIG_IP6_NF_FILTER=m
CONFIG_NET_ACT_CSUM=m
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 4f55477ffe08..7a3cb4c09e45 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -206,9 +206,8 @@ chk_dump_one()
local token
local msg
- ss_token="$(ss -inmHMN $ns | grep 'token:' |\
- head -n 1 |\
- sed 's/.*token:\([0-9a-f]*\).*/\1/')"
+ 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 $2}')"
@@ -226,6 +225,37 @@ chk_dump_one()
fi
}
+chk_dump_subflow()
+{
+ local inet_diag_token
+ local subflow_line
+ local ss_output
+ local ss_token
+ local msg
+
+ ss_output=$(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}"
@@ -317,6 +347,7 @@ 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 c83a8b47bbdf..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;
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect_checksum.sh b/tools/testing/selftests/net/mptcp/mptcp_connect_checksum.sh
new file mode 100755
index 000000000000..ce93ec2f107f
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect_checksum.sh
@@ -0,0 +1,5 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+MPTCP_LIB_KSFT_TEST="$(basename "${0}" .sh)" \
+ "$(dirname "${0}")/mptcp_connect.sh" -C "${@}"
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect_mmap.sh b/tools/testing/selftests/net/mptcp/mptcp_connect_mmap.sh
new file mode 100755
index 000000000000..5dd30f9394af
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect_mmap.sh
@@ -0,0 +1,5 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+MPTCP_LIB_KSFT_TEST="$(basename "${0}" .sh)" \
+ "$(dirname "${0}")/mptcp_connect.sh" -m mmap "${@}"
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect_sendfile.sh b/tools/testing/selftests/net/mptcp/mptcp_connect_sendfile.sh
new file mode 100755
index 000000000000..1d16fb1cc9bb
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect_sendfile.sh
@@ -0,0 +1,5 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+MPTCP_LIB_KSFT_TEST="$(basename "${0}" .sh)" \
+ "$(dirname "${0}")/mptcp_connect.sh" -m sendfile "${@}"
diff --git a/tools/testing/selftests/net/mptcp/mptcp_diag.c b/tools/testing/selftests/net/mptcp/mptcp_diag.c
index 284286c524cf..e084796e804d 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_diag.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_diag.c
@@ -8,6 +8,7 @@
#include <sys/socket.h>
#include <netinet/in.h>
#include <linux/tcp.h>
+#include <arpa/inet.h>
#include <unistd.h>
#include <stdlib.h>
@@ -19,6 +20,15 @@
#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;
@@ -46,6 +56,37 @@ struct mptcp_info {
__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);
@@ -54,11 +95,13 @@ static void die_perror(const char *msg)
static void die_usage(int r)
{
- fprintf(stderr, "Usage: mptcp_diag -t\n");
+ 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, __u32 token)
+static void send_query(int fd, struct inet_diag_req_v2 *r, __u32 proto)
{
struct sockaddr_nl nladdr = {
.nl_family = AF_NETLINK
@@ -72,31 +115,26 @@ static void send_query(int fd, __u32 token)
.nlmsg_type = SOCK_DIAG_BY_FAMILY,
.nlmsg_flags = NLM_F_REQUEST
},
- .r = {
- .sdiag_family = AF_INET,
- /* Real proto is set via INET_DIAG_REQ_PROTOCOL */
- .sdiag_protocol = IPPROTO_TCP,
- .id.idiag_cookie[0] = token,
- }
+ .r = *r
};
struct rtattr rta_proto;
struct iovec iov[6];
- int iovlen = 1;
- __u32 proto;
-
- req.r.idiag_ext |= (1 << (INET_DIAG_INFO - 1));
- proto = IPPROTO_MPTCP;
- rta_proto.rta_type = INET_DIAG_REQ_PROTOCOL;
- rta_proto.rta_len = RTA_LENGTH(sizeof(proto));
+ int iovlen = 0;
- iov[0] = (struct iovec) {
+ iov[iovlen++] = (struct iovec) {
.iov_base = &req,
.iov_len = sizeof(req)
};
- iov[iovlen] = (struct iovec){ &rta_proto, sizeof(rta_proto)};
- iov[iovlen + 1] = (struct iovec){ &proto, sizeof(proto)};
- req.nlh.nlmsg_len += RTA_LENGTH(sizeof(proto));
- iovlen += 2;
+
+ 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),
@@ -160,7 +198,67 @@ static void print_info_msg(struct mptcp_info *info)
printf("bytes_acked: %llu\n", info->mptcpi_bytes_acked);
}
-static void parse_nlmsg(struct nlmsghdr *nlh)
+/*
+ * '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];
@@ -169,7 +267,7 @@ static void parse_nlmsg(struct nlmsghdr *nlh)
nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)),
NLA_F_NESTED);
- if (tb[INET_DIAG_INFO]) {
+ if (proto == IPPROTO_MPTCP && tb[INET_DIAG_INFO]) {
int len = RTA_PAYLOAD(tb[INET_DIAG_INFO]);
struct mptcp_info *info;
@@ -183,11 +281,28 @@ static void parse_nlmsg(struct nlmsghdr *nlh)
}
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, struct nlmsghdr *nlh)
+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
};
@@ -204,7 +319,6 @@ static void recv_nlmsg(int fd, struct nlmsghdr *nlh)
int len;
len = recvmsg(fd, &rcv_msg, 0);
- nlh = (struct nlmsghdr *)rcv_buff;
while (NLMSG_OK(nlh, len)) {
if (nlh->nlmsg_type == NLMSG_DONE) {
@@ -218,40 +332,84 @@ static void recv_nlmsg(int fd, struct nlmsghdr *nlh)
-(err->error), strerror(-(err->error)));
break;
}
- parse_nlmsg(nlh);
+ parse_nlmsg(nlh, proto);
nlh = NLMSG_NEXT(nlh, len);
}
}
static void get_mptcpinfo(__u32 token)
{
- struct nlmsghdr *nlh = NULL;
+ 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, token);
- recv_nlmsg(fd, nlh);
+ send_query(fd, &r, proto);
+ recv_nlmsg(fd, proto);
close(fd);
}
-static void parse_opts(int argc, char **argv, __u32 *target_token)
+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:")) != -1) {
+ while ((c = getopt(argc, argv, "ht:s:")) != -1) {
switch (c) {
case 'h':
die_usage(0);
break;
case 't':
- sscanf(optarg, "%x", target_token);
+ sscanf(optarg, "%x", &p->target_token);
+ break;
+ case 's':
+ strncpy(p->subflow_addrs, optarg,
+ sizeof(p->subflow_addrs) - 1);
break;
default:
die_usage(1);
@@ -262,10 +420,15 @@ static void parse_opts(int argc, char **argv, __u32 *target_token)
int main(int argc, char *argv[])
{
- __u32 target_token;
+ struct params p = { 0 };
+
+ parse_opts(argc, argv, &p);
+
+ if (p.target_token)
+ get_mptcpinfo(p.target_token);
- parse_opts(argc, argv, &target_token);
- get_mptcpinfo(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/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c
index 7ea5fb28c93d..1d5d3c4e7e87 100644
--- a/tools/testing/selftests/net/msg_zerocopy.c
+++ b/tools/testing/selftests/net/msg_zerocopy.c
@@ -77,6 +77,7 @@
static int cfg_cork;
static bool cfg_cork_mixed;
static int cfg_cpu = -1; /* default: pin to last cpu */
+static int cfg_expect_zerocopy = -1;
static int cfg_family = PF_UNSPEC;
static int cfg_ifindex = 1;
static int cfg_payload_len;
@@ -92,9 +93,9 @@ static socklen_t cfg_alen;
static struct sockaddr_storage cfg_dst_addr;
static struct sockaddr_storage cfg_src_addr;
+static int exitcode;
static char payload[IP_MAXPACKET];
static long packets, bytes, completions, expected_completions;
-static int zerocopied = -1;
static uint32_t next_completion;
static uint32_t sends_since_notify;
@@ -444,11 +445,13 @@ static bool do_recv_completion(int fd, int domain)
next_completion = hi + 1;
zerocopy = !(serr->ee_code & SO_EE_CODE_ZEROCOPY_COPIED);
- if (zerocopied == -1)
- zerocopied = zerocopy;
- else if (zerocopied != zerocopy) {
- fprintf(stderr, "serr: inconsistent\n");
- zerocopied = zerocopy;
+ if (cfg_expect_zerocopy != -1 &&
+ cfg_expect_zerocopy != zerocopy) {
+ fprintf(stderr, "serr: ee_code: %u != expected %u\n",
+ zerocopy, cfg_expect_zerocopy);
+ exitcode = 1;
+ /* suppress repeated messages */
+ cfg_expect_zerocopy = zerocopy;
}
if (cfg_verbose >= 2)
@@ -571,7 +574,7 @@ static void do_tx(int domain, int type, int protocol)
fprintf(stderr, "tx=%lu (%lu MB) txc=%lu zc=%c\n",
packets, bytes >> 20, completions,
- zerocopied == 1 ? 'y' : 'n');
+ cfg_zerocopy && cfg_expect_zerocopy == 1 ? 'y' : 'n');
}
static int do_setup_rx(int domain, int type, int protocol)
@@ -715,7 +718,7 @@ static void parse_opts(int argc, char **argv)
cfg_payload_len = max_payload_len;
- while ((c = getopt(argc, argv, "46c:C:D:i:l:mp:rs:S:t:vz")) != -1) {
+ while ((c = getopt(argc, argv, "46c:C:D:i:l:mp:rs:S:t:vzZ:")) != -1) {
switch (c) {
case '4':
if (cfg_family != PF_UNSPEC)
@@ -770,6 +773,9 @@ static void parse_opts(int argc, char **argv)
case 'z':
cfg_zerocopy = true;
break;
+ case 'Z':
+ cfg_expect_zerocopy = !!atoi(optarg);
+ break;
}
}
@@ -817,5 +823,5 @@ int main(int argc, char **argv)
else
error(1, 0, "unknown cfg_test %s", cfg_test);
- return 0;
+ return exitcode;
}
diff --git a/tools/testing/selftests/net/msg_zerocopy.sh b/tools/testing/selftests/net/msg_zerocopy.sh
index 89c22f5320e0..28178a38a4e7 100755
--- a/tools/testing/selftests/net/msg_zerocopy.sh
+++ b/tools/testing/selftests/net/msg_zerocopy.sh
@@ -6,6 +6,7 @@
set -e
readonly DEV="veth0"
+readonly DUMMY_DEV="dummy0"
readonly DEV_MTU=65535
readonly BIN="./msg_zerocopy"
@@ -14,21 +15,25 @@ readonly NSPREFIX="ns-${RAND}"
readonly NS1="${NSPREFIX}1"
readonly NS2="${NSPREFIX}2"
-readonly SADDR4='192.168.1.1'
-readonly DADDR4='192.168.1.2'
-readonly SADDR6='fd::1'
-readonly DADDR6='fd::2'
+readonly LPREFIX4='192.168.1'
+readonly RPREFIX4='192.168.2'
+readonly LPREFIX6='fd'
+readonly RPREFIX6='fc'
+
readonly path_sysctl_mem="net.core.optmem_max"
# No arguments: automated test
if [[ "$#" -eq "0" ]]; then
- $0 4 tcp -t 1
- $0 6 tcp -t 1
- $0 4 udp -t 1
- $0 6 udp -t 1
- echo "OK. All tests passed"
- exit 0
+ ret=0
+
+ $0 4 tcp -t 1 || ret=1
+ $0 6 tcp -t 1 || ret=1
+ $0 4 udp -t 1 || ret=1
+ $0 6 udp -t 1 || ret=1
+
+ [[ "$ret" == "0" ]] && echo "OK. All tests passed"
+ exit $ret
fi
# Argument parsing
@@ -45,11 +50,18 @@ readonly EXTRA_ARGS="$@"
# Argument parsing: configure addresses
if [[ "${IP}" == "4" ]]; then
- readonly SADDR="${SADDR4}"
- readonly DADDR="${DADDR4}"
+ readonly SADDR="${LPREFIX4}.1"
+ readonly DADDR="${LPREFIX4}.2"
+ readonly DUMMY_ADDR="${RPREFIX4}.1"
+ readonly DADDR_TXONLY="${RPREFIX4}.2"
+ readonly MASK="24"
elif [[ "${IP}" == "6" ]]; then
- readonly SADDR="${SADDR6}"
- readonly DADDR="${DADDR6}"
+ readonly SADDR="${LPREFIX6}::1"
+ readonly DADDR="${LPREFIX6}::2"
+ readonly DUMMY_ADDR="${RPREFIX6}::1"
+ readonly DADDR_TXONLY="${RPREFIX6}::2"
+ readonly MASK="64"
+ readonly NODAD="nodad"
else
echo "Invalid IP version ${IP}"
exit 1
@@ -89,33 +101,61 @@ ip netns exec "${NS2}" sysctl -w -q "${path_sysctl_mem}=1000000"
ip link add "${DEV}" mtu "${DEV_MTU}" netns "${NS1}" type veth \
peer name "${DEV}" mtu "${DEV_MTU}" netns "${NS2}"
+ip link add "${DUMMY_DEV}" mtu "${DEV_MTU}" netns "${NS2}" type dummy
+
# Bring the devices up
ip -netns "${NS1}" link set "${DEV}" up
ip -netns "${NS2}" link set "${DEV}" up
+ip -netns "${NS2}" link set "${DUMMY_DEV}" up
# Set fixed MAC addresses on the devices
ip -netns "${NS1}" link set dev "${DEV}" address 02:02:02:02:02:02
ip -netns "${NS2}" link set dev "${DEV}" address 06:06:06:06:06:06
# Add fixed IP addresses to the devices
-ip -netns "${NS1}" addr add 192.168.1.1/24 dev "${DEV}"
-ip -netns "${NS2}" addr add 192.168.1.2/24 dev "${DEV}"
-ip -netns "${NS1}" addr add fd::1/64 dev "${DEV}" nodad
-ip -netns "${NS2}" addr add fd::2/64 dev "${DEV}" nodad
+ip -netns "${NS1}" addr add "${SADDR}/${MASK}" dev "${DEV}" ${NODAD}
+ip -netns "${NS2}" addr add "${DADDR}/${MASK}" dev "${DEV}" ${NODAD}
+ip -netns "${NS2}" addr add "${DUMMY_ADDR}/${MASK}" dev "${DUMMY_DEV}" ${NODAD}
+
+ip -netns "${NS1}" route add default via "${DADDR}" dev "${DEV}"
+ip -netns "${NS2}" route add default via "${DADDR_TXONLY}" dev "${DUMMY_DEV}"
+
+ip netns exec "${NS2}" sysctl -wq net.ipv4.ip_forward=1
+ip netns exec "${NS2}" sysctl -wq net.ipv6.conf.all.forwarding=1
# Optionally disable sg or csum offload to test edge cases
# ip netns exec "${NS1}" ethtool -K "${DEV}" sg off
+ret=0
+
do_test() {
local readonly ARGS="$1"
- echo "ipv${IP} ${TXMODE} ${ARGS}"
- ip netns exec "${NS2}" "${BIN}" "-${IP}" -i "${DEV}" -t 2 -C 2 -S "${SADDR}" -D "${DADDR}" ${ARGS} -r "${RXMODE}" &
+ # tx-rx test
+ # packets queued to a local socket are copied,
+ # sender notification has SO_EE_CODE_ZEROCOPY_COPIED.
+
+ echo -e "\nipv${IP} ${TXMODE} ${ARGS} tx-rx\n"
+ ip netns exec "${NS2}" "${BIN}" "-${IP}" -i "${DEV}" -t 2 -C 2 \
+ -S "${SADDR}" -D "${DADDR}" ${ARGS} -r "${RXMODE}" &
sleep 0.2
- ip netns exec "${NS1}" "${BIN}" "-${IP}" -i "${DEV}" -t 1 -C 3 -S "${SADDR}" -D "${DADDR}" ${ARGS} "${TXMODE}"
+ ip netns exec "${NS1}" "${BIN}" "-${IP}" -i "${DEV}" -t 1 -C 3 \
+ -S "${SADDR}" -D "${DADDR}" ${ARGS} "${TXMODE}" -Z 0 || ret=1
wait
+
+ # next test is unconnected tx to dummy0, cannot exercise with tcp
+ [[ "${TXMODE}" == "tcp" ]] && return
+
+ # tx-only test: send out dummy0
+ # packets leaving the host are not copied,
+ # sender notification does not have SO_EE_CODE_ZEROCOPY_COPIED.
+
+ echo -e "\nipv${IP} ${TXMODE} ${ARGS} tx-only\n"
+ ip netns exec "${NS1}" "${BIN}" "-${IP}" -i "${DEV}" -t 1 -C 3 \
+ -S "${SADDR}" -D "${DADDR_TXONLY}" ${ARGS} "${TXMODE}" -Z 1 || ret=1
}
do_test "${EXTRA_ARGS}"
do_test "-z ${EXTRA_ARGS}"
-echo ok
+
+[[ "$ret" == "0" ]] && echo "OK"
diff --git a/tools/testing/selftests/net/nat6to4.sh b/tools/testing/selftests/net/nat6to4.sh
new file mode 100755
index 000000000000..0ee859b622a4
--- /dev/null
+++ b/tools/testing/selftests/net/nat6to4.sh
@@ -0,0 +1,15 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+NS="ns-peer-$(mktemp -u XXXXXX)"
+
+ip netns add "${NS}"
+ip -netns "${NS}" link set lo up
+ip -netns "${NS}" route add default via 127.0.0.2 dev lo
+
+tc -n "${NS}" qdisc add dev lo ingress
+tc -n "${NS}" filter add dev lo ingress prio 4 protocol ip \
+ bpf object-file nat6to4.bpf.o section schedcls/egress4/snat4 direct-action
+
+ip netns exec "${NS}" \
+ bash -c 'echo 012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789abc | socat - UDP4-DATAGRAM:224.1.0.1:6666,ip-multicast-loop=1'
diff --git a/tools/testing/selftests/net/net_helper.sh b/tools/testing/selftests/net/net_helper.sh
deleted file mode 100644
index 6596fe03c77f..000000000000
--- a/tools/testing/selftests/net/net_helper.sh
+++ /dev/null
@@ -1,25 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-#
-# Helper functions
-
-wait_local_port_listen()
-{
- local listener_ns="${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 "${pattern}"; then
- break
- fi
- sleep 0.1
- done
-}
diff --git a/tools/testing/selftests/net/netdev-l2addr.sh b/tools/testing/selftests/net/netdev-l2addr.sh
new file mode 100755
index 000000000000..18509da293e5
--- /dev/null
+++ b/tools/testing/selftests/net/netdev-l2addr.sh
@@ -0,0 +1,59 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source lib.sh
+set -o pipefail
+
+NSIM_ADDR=2025
+TEST_ADDR="d0:be:d0:be:d0:00"
+
+RET_CODE=0
+
+cleanup() {
+ cleanup_netdevsim "$NSIM_ADDR"
+ cleanup_ns "$NS"
+}
+
+trap cleanup EXIT
+
+fail() {
+ echo "ERROR: ${1:-unexpected return code} (ret: $_)" >&2
+ RET_CODE=1
+}
+
+get_addr()
+{
+ local type="$1"
+ local dev="$2"
+ local ns="$3"
+
+ ip -j -n "$ns" link show dev "$dev" | jq -er ".[0].$type"
+}
+
+setup_ns NS
+
+nsim=$(create_netdevsim $NSIM_ADDR "$NS")
+
+get_addr address "$nsim" "$NS" >/dev/null || fail "Couldn't get ether addr"
+get_addr broadcast "$nsim" "$NS" >/dev/null || fail "Couldn't get brd addr"
+get_addr permaddr "$nsim" "$NS" >/dev/null && fail "Found perm_addr without setting it"
+
+ip -n "$NS" link set dev "$nsim" address "$TEST_ADDR"
+ip -n "$NS" link set dev "$nsim" brd "$TEST_ADDR"
+
+[[ "$(get_addr address "$nsim" "$NS")" == "$TEST_ADDR" ]] || fail "Couldn't set ether addr"
+[[ "$(get_addr broadcast "$nsim" "$NS")" == "$TEST_ADDR" ]] || fail "Couldn't set brd addr"
+
+if create_netdevsim_port "$NSIM_ADDR" "$NS" 2 "FF:FF:FF:FF:FF:FF" 2>/dev/null; then
+ fail "Created netdevsim with broadcast permaddr"
+fi
+
+nsim_port=$(create_netdevsim_port "$NSIM_ADDR" "$NS" 2 "$TEST_ADDR")
+
+get_addr address "$nsim_port" "$NS" >/dev/null || fail "Couldn't get ether addr"
+get_addr broadcast "$nsim_port" "$NS" >/dev/null || fail "Couldn't get brd addr"
+[[ "$(get_addr permaddr "$nsim_port" "$NS")" == "$TEST_ADDR" ]] || fail "Couldn't get permaddr"
+
+cleanup_netdevsim "$NSIM_ADDR" "$NS"
+
+exit $RET_CODE
diff --git a/tools/testing/selftests/net/netfilter/.gitignore b/tools/testing/selftests/net/netfilter/.gitignore
index 64c4f8d9aa6c..5d2be9a00627 100644
--- a/tools/testing/selftests/net/netfilter/.gitignore
+++ b/tools/testing/selftests/net/netfilter/.gitignore
@@ -5,3 +5,4 @@ conntrack_dump_flush
conntrack_reverse_clash
sctp_collision
nf_queue
+udpclash
diff --git a/tools/testing/selftests/net/netfilter/Makefile b/tools/testing/selftests/net/netfilter/Makefile
index ffe161fac8b5..a98ed892f55f 100644
--- a/tools/testing/selftests/net/netfilter/Makefile
+++ b/tools/testing/selftests/net/netfilter/Makefile
@@ -12,8 +12,10 @@ 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_clash.sh
TEST_PROGS += conntrack_reverse_clash.sh
TEST_PROGS += ipvs.sh
TEST_PROGS += nf_conntrack_packetdrill.sh
@@ -23,6 +25,7 @@ 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
@@ -42,6 +45,7 @@ TEST_GEN_FILES += connect_close nf_queue
TEST_GEN_FILES += conntrack_dump_flush
TEST_GEN_FILES += conntrack_reverse_clash
TEST_GEN_FILES += sctp_collision
+TEST_GEN_FILES += udpclash
include ../../lib.mk
@@ -50,6 +54,7 @@ $(OUTPUT)/nf_queue: LDLIBS += $(MNL_LDLIBS)
$(OUTPUT)/conntrack_dump_flush: CFLAGS += $(MNL_CFLAGS)
$(OUTPUT)/conntrack_dump_flush: LDLIBS += $(MNL_LDLIBS)
+$(OUTPUT)/udpclash: LDLIBS += -lpthread
TEST_FILES := lib.sh
TEST_FILES += packetdrill
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 $ksft_skip
diff --git a/tools/testing/selftests/net/netfilter/config b/tools/testing/selftests/net/netfilter/config
index 43d8b500d391..79d5b33966ba 100644
--- a/tools/testing/selftests/net/netfilter/config
+++ b/tools/testing/selftests/net/netfilter/config
@@ -1,6 +1,8 @@
CONFIG_AUDIT=y
CONFIG_BPF_SYSCALL=y
CONFIG_BRIDGE=m
+CONFIG_NETFILTER_XTABLES_LEGACY=y
+CONFIG_BRIDGE_NF_EBTABLES_LEGACY=m
CONFIG_BRIDGE_EBT_BROUTE=m
CONFIG_BRIDGE_EBT_IP=m
CONFIG_BRIDGE_EBT_REDIRECT=m
@@ -14,7 +16,10 @@ CONFIG_INET_ESP=m
CONFIG_IP_NF_MATCH_RPFILTER=m
CONFIG_IP6_NF_MATCH_RPFILTER=m
CONFIG_IP_NF_IPTABLES=m
+CONFIG_IP_NF_IPTABLES_LEGACY=m
CONFIG_IP6_NF_IPTABLES=m
+CONFIG_IP6_NF_IPTABLES_LEGACY=m
+CONFIG_IP_NF_NAT=m
CONFIG_IP_NF_FILTER=m
CONFIG_IP6_NF_FILTER=m
CONFIG_IP_NF_RAW=m
@@ -46,6 +51,7 @@ CONFIG_NETFILTER_XT_MATCH_STATE=m
CONFIG_NETFILTER_XT_MATCH_STRING=m
CONFIG_NETFILTER_XT_TARGET_REDIRECT=m
CONFIG_NF_CONNTRACK=m
+CONFIG_NF_CONNTRACK_PROCFS=y
CONFIG_NF_CONNTRACK_EVENTS=y
CONFIG_NF_CONNTRACK_FTP=m
CONFIG_NF_CONNTRACK_MARK=y
@@ -91,4 +97,4 @@ CONFIG_XFRM_STATISTICS=y
CONFIG_NET_PKTGEN=m
CONFIG_TUN=m
CONFIG_INET_DIAG=m
-CONFIG_SCTP_DIAG=m
+CONFIG_INET_SCTP_DIAG=m
diff --git a/tools/testing/selftests/net/netfilter/conntrack_clash.sh b/tools/testing/selftests/net/netfilter/conntrack_clash.sh
new file mode 100755
index 000000000000..606a43a60f73
--- /dev/null
+++ b/tools/testing/selftests/net/netfilter/conntrack_clash.sh
@@ -0,0 +1,174 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source lib.sh
+
+clash_resolution_active=0
+dport=22111
+ret=0
+
+cleanup()
+{
+ # netns cleanup also zaps any remaining socat echo server.
+ cleanup_all_ns
+}
+
+checktool "nft --version" "run test without nft"
+checktool "conntrack --version" "run test without conntrack"
+checktool "socat -h" "run test without socat"
+
+trap cleanup EXIT
+
+setup_ns nsclient1 nsclient2 nsrouter
+
+ip netns exec "$nsrouter" nft -f -<<EOF
+table ip t {
+ chain lb {
+ meta l4proto udp dnat to numgen random mod 3 map { 0 : 10.0.2.1 . 9000, 1 : 10.0.2.1 . 9001, 2 : 10.0.2.1 . 9002 }
+ }
+
+ chain prerouting {
+ type nat hook prerouting priority dstnat
+
+ udp dport $dport counter jump lb
+ }
+
+ chain output {
+ type nat hook output priority dstnat
+
+ udp dport $dport counter jump lb
+ }
+}
+EOF
+
+load_simple_ruleset()
+{
+ip netns exec "$1" nft -f -<<EOF
+table ip t {
+ chain forward {
+ type filter hook forward priority 0
+
+ ct state new counter
+ }
+}
+EOF
+}
+
+spawn_servers()
+{
+ local ns="$1"
+ local ports="9000 9001 9002"
+
+ for port in $ports; do
+ ip netns exec "$ns" socat UDP-RECVFROM:$port,fork PIPE 2>/dev/null &
+ done
+
+ for port in $ports; do
+ wait_local_port_listen "$ns" $port udp
+ done
+}
+
+add_addr()
+{
+ local ns="$1"
+ local dev="$2"
+ local i="$3"
+ local j="$4"
+
+ ip -net "$ns" link set "$dev" up
+ ip -net "$ns" addr add "10.0.$i.$j/24" dev "$dev"
+}
+
+ping_test()
+{
+ local ns="$1"
+ local daddr="$2"
+
+ if ! ip netns exec "$ns" ping -q -c 1 $daddr > /dev/null;then
+ echo "FAIL: ping from $ns to $daddr"
+ exit 1
+ fi
+}
+
+run_one_clash_test()
+{
+ local ns="$1"
+ local ctns="$2"
+ local daddr="$3"
+ local dport="$4"
+ local entries
+ local cre
+
+ if ! ip netns exec "$ns" ./udpclash $daddr $dport;then
+ echo "INFO: did not receive expected number of replies for $daddr:$dport"
+ ip netns exec "$ctns" conntrack -S
+ # don't fail: check if clash resolution triggered after all.
+ fi
+
+ entries=$(ip netns exec "$ctns" conntrack -S | wc -l)
+ cre=$(ip netns exec "$ctns" conntrack -S | grep "clash_resolve=0" | wc -l)
+
+ if [ "$cre" -ne "$entries" ];then
+ clash_resolution_active=1
+ return 0
+ fi
+
+ # not a failure: clash resolution logic did not trigger.
+ # With right timing, xmit completed sequentially and
+ # no parallel insertion occurs.
+ return $ksft_skip
+}
+
+run_clash_test()
+{
+ local ns="$1"
+ local ctns="$2"
+ local daddr="$3"
+ local dport="$4"
+ local softerr=0
+
+ for i in $(seq 1 10);do
+ run_one_clash_test "$ns" "$ctns" "$daddr" "$dport"
+ local rv=$?
+ if [ $rv -eq 0 ];then
+ echo "PASS: clash resolution test for $daddr:$dport on attempt $i"
+ return 0
+ elif [ $rv -eq $ksft_skip ]; then
+ softerr=1
+ fi
+ done
+
+ [ $softerr -eq 1 ] && echo "SKIP: clash resolution for $daddr:$dport did not trigger"
+}
+
+ip link add veth0 netns "$nsclient1" type veth peer name veth0 netns "$nsrouter"
+ip link add veth0 netns "$nsclient2" type veth peer name veth1 netns "$nsrouter"
+add_addr "$nsclient1" veth0 1 1
+add_addr "$nsclient2" veth0 2 1
+add_addr "$nsrouter" veth0 1 99
+add_addr "$nsrouter" veth1 2 99
+
+ip -net "$nsclient1" route add default via 10.0.1.99
+ip -net "$nsclient2" route add default via 10.0.2.99
+ip netns exec "$nsrouter" sysctl -q net.ipv4.ip_forward=1
+
+ping_test "$nsclient1" 10.0.1.99
+ping_test "$nsclient1" 10.0.2.1
+ping_test "$nsclient2" 10.0.1.1
+
+spawn_servers "$nsclient2"
+
+# exercise clash resolution with nat:
+# nsrouter is supposed to dnat to 10.0.2.1:900{0,1,2,3}.
+run_clash_test "$nsclient1" "$nsrouter" 10.0.1.99 "$dport"
+
+# exercise clash resolution without nat.
+load_simple_ruleset "$nsclient2"
+run_clash_test "$nsclient2" "$nsclient2" 127.0.0.1 9001
+
+if [ $clash_resolution_active -eq 0 ];then
+ [ "$ret" -eq 0 ] && ret=$ksft_skip
+ echo "SKIP: Clash resolution did not trigger"
+fi
+
+exit $ret
diff --git a/tools/testing/selftests/net/netfilter/conntrack_resize.sh b/tools/testing/selftests/net/netfilter/conntrack_resize.sh
new file mode 100755
index 000000000000..788cd56ea4a0
--- /dev/null
+++ b/tools/testing/selftests/net/netfilter/conntrack_resize.sh
@@ -0,0 +1,514 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source lib.sh
+
+checktool "conntrack --version" "run test without conntrack"
+checktool "nft --version" "run test without nft tool"
+
+init_net_max=0
+ct_buckets=0
+tmpfile=""
+tmpfile_proc=""
+tmpfile_uniq=""
+ret=0
+have_socat=0
+
+socat -h > /dev/null && have_socat=1
+
+insert_count=2000
+[ "$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
+}
+
+ct_pingflood()
+{
+ 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
+}
+
+ct_udpflood()
+{
+ local ns="$1"
+ local duration="$2"
+ local now=$(date +%s)
+ local end=$((now + duration))
+
+ [ $have_socat -ne "1" ] && return
+
+ while [ $now -lt $end ]; do
+ip netns exec "$ns" bash<<"EOF"
+ for i in $(seq 1 100);do
+ dport=$(((RANDOM%65536)+1))
+
+ echo bar | socat -u STDIN UDP:"127.0.0.1:$dport" &
+ done > /dev/null 2>&1
+ wait
+EOF
+ now=$(date +%s)
+ done
+}
+
+ct_udpclash()
+{
+ local ns="$1"
+ local duration="$2"
+ local now=$(date +%s)
+ local end=$((now + duration))
+
+ [ -x udpclash ] || return
+
+ while [ $now -lt $end ]; do
+ ip netns exec "$ns" ./udpclash 127.0.0.1 $((RANDOM%65536)) > /dev/null 2>&1
+
+ now=$(date +%s)
+ done
+}
+
+# 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
+}
+
+ct_nulldump_loop()
+{
+ local ns="$1"
+ local duration="$2"
+ local now=$(date +%s)
+ local end=$((now + duration))
+
+ while [ $now -lt $end ]; do
+ ct_nulldump "$ns"
+ sleep $((RANDOM%2))
+ now=$(date +%s)
+ done
+}
+
+change_timeouts()
+{
+ local ns="$1"
+ local r1=$((RANDOM%2))
+ local r2=$((RANDOM%2))
+
+ [ "$r1" -eq 1 ] && ip netns exec "$ns" sysctl -q net.netfilter.nf_conntrack_icmp_timeout=$((RANDOM%5))
+ [ "$r2" -eq 1 ] && ip netns exec "$ns" sysctl -q net.netfilter.nf_conntrack_udp_timeout=$((RANDOM%5))
+}
+
+ct_change_timeouts_loop()
+{
+ local ns="$1"
+ local duration="$2"
+ local now=$(date +%s)
+ local end=$((now + duration))
+
+ while [ $now -lt $end ]; do
+ change_timeouts "$ns"
+ sleep $((RANDOM%2))
+ now=$(date +%s)
+ done
+
+ # restore defaults
+ ip netns exec "$ns" sysctl -q net.netfilter.nf_conntrack_icmp_timeout=30
+ ip netns exec "$ns" sysctl -q net.netfilter.nf_conntrack_udp_timeout=30
+}
+
+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%$insert_count))
+
+ ct_pingflood "$n" "$timeout" "floodresize" &
+ ct_udpflood "$n" "$timeout" &
+ ct_udpclash "$n" "$timeout" &
+
+ insert_ctnetlink "$n" "$r" &
+ ctflush "$n" "$timeout" &
+ ct_nulldump_loop "$n" "$timeout" &
+ ct_change_timeouts_loop "$n" "$timeout" &
+
+ wait
+}
+
+test_floodresize_all()
+{
+ local timeout=20
+ local n=""
+ local tainted_then=""
+
+ read tainted_then < /proc/sys/kernel/tainted
+
+ for n in "$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
+
+ ct_pingflood "$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 "$nsclient2"
+
+ ct_pingflood "$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 $ret
diff --git a/tools/testing/selftests/net/netfilter/ipvs.sh b/tools/testing/selftests/net/netfilter/ipvs.sh
index d3edb16cd4b3..9c9d5b38ab71 100755
--- a/tools/testing/selftests/net/netfilter/ipvs.sh
+++ b/tools/testing/selftests/net/netfilter/ipvs.sh
@@ -129,9 +129,6 @@ test_dr() {
# avoid incorrect arp response
ip netns exec "${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 "${vip_v4}/32" dev lo:1
test_service
@@ -154,7 +151,7 @@ test_nat() {
test_tun() {
ip netns exec "${ns0}" ip route add "${vip_v4}" via "${gip_v4}" dev br0
- ip netns exec "${ns1}" modprobe -q ipip
+ modprobe -q ipip
ip netns exec "${ns1}" ip link set tunl0 up
ip netns exec "${ns1}" sysctl -qw net.ipv4.ip_forward=0
ip netns exec "${ns1}" sysctl -qw net.ipv4.conf.all.send_redirects=0
@@ -163,13 +160,10 @@ test_tun() {
ip netns exec "${ns1}" ipvsadm -a -i -t "${vip_v4}:${port}" -r ${rip_v4}:${port}
ip netns exec "${ns1}" ip addr add ${vip_v4}/32 dev lo:1
- ip netns exec "${ns2}" modprobe -q ipip
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..20e76b395c85 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="
@@ -376,7 +378,7 @@ display net,port,proto
type_spec ipv4_addr . inet_service . inet_proto
chain_spec ip daddr . udp dport . meta l4proto
dst addr4 port proto
-src
+src
start 1
count 9
src_delta 9
@@ -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
@@ -398,6 +419,7 @@ table inet filter {
set test {
type ${type_spec}
+ counter
flags interval,timeout
}
@@ -1137,9 +1159,18 @@ del() {
fi
}
-# Return packet count from 'test' counter in 'inet filter' table
+# Return packet count for elem $1 from 'test' counter in 'inet filter' table
count_packets() {
found=0
+ for token in $(nft reset element inet filter test "${1}" ); do
+ [ ${found} -eq 1 ] && echo "${token}" && return
+ [ "${token}" = "packets" ] && found=1
+ done
+}
+
+# Return packet count from 'test' counter in 'inet filter' table
+count_packets_nomatch() {
+ found=0
for token in $(nft list counter inet filter test); do
[ ${found} -eq 1 ] && echo "${token}" && return
[ "${token}" = "packets" ] && found=1
@@ -1185,6 +1216,10 @@ perf() {
# Set MAC addresses, send single packet, check that it matches, reset counter
send_match() {
+ local elem="$1"
+
+ shift
+
ip link set veth_a address "$(format_mac "${1}")"
ip -n B link set veth_b address "$(format_mac "${2}")"
@@ -1195,7 +1230,7 @@ send_match() {
eval src_"$f"=\$\(format_\$f "${2}"\)
done
eval send_\$proto
- if [ "$(count_packets)" != "1" ]; then
+ if [ "$(count_packets "$elem")" != "1" ]; then
err "${proto} packet to:"
err " $(for f in ${dst}; do
eval format_\$f "${1}"; printf ' '; done)"
@@ -1221,7 +1256,7 @@ send_nomatch() {
eval src_"$f"=\$\(format_\$f "${2}"\)
done
eval send_\$proto
- if [ "$(count_packets)" != "0" ]; then
+ if [ "$(count_packets_nomatch)" != "0" ]; then
err "${proto} packet to:"
err " $(for f in ${dst}; do
eval format_\$f "${1}"; printf ' '; done)"
@@ -1234,15 +1269,54 @@ send_nomatch() {
fi
}
+maybe_send_nomatch() {
+ local elem="$1"
+ local what="$4"
+
+ [ $((RANDOM%20)) -gt 0 ] && return
+
+ dst_addr4="$2"
+ dst_port="$3"
+ send_udp
+
+ if [ "$(count_packets_nomatch)" != "0" ]; then
+ err "Packet to $dst_addr4:$dst_port did match $what"
+ err "$(nft -a list ruleset)"
+ return 1
+ fi
+}
+
+maybe_send_match() {
+ local elem="$1"
+ local what="$4"
+
+ [ $((RANDOM%20)) -gt 0 ] && return
+
+ dst_addr4="$2"
+ dst_port="$3"
+ send_udp
+
+ if [ "$(count_packets "{ $elem }")" != "1" ]; then
+ err "Packet to $dst_addr4:$dst_port did not match $what"
+ err "$(nft -a list ruleset)"
+ return 1
+ fi
+ nft reset counter inet filter test >/dev/null
+ nft reset element inet filter test "{ $elem }" >/dev/null
+}
+
# Correctness test template:
# - add ranged element, check that packets match it
# - check that packets outside range don't match it
# - remove some elements, check that packets don't match anymore
-test_correctness() {
- setup veth send_"${proto}" set || return ${ksft_skip}
-
+test_correctness_main() {
range_size=1
+
+ send_nomatch $((end + 1)) $((end + 1 + src_delta)) || return 1
+
for i in $(seq "${start}" $((start + count))); do
+ local elem=""
+
end=$((start + range_size))
# Avoid negative or zero-sized port ranges
@@ -1253,15 +1327,16 @@ test_correctness() {
srcstart=$((start + src_delta))
srcend=$((end + src_delta))
- add "$(format)" || return 1
+ elem="$(format)"
+ add "$elem" || return 1
for j in $(seq "$start" $((range_size / 2 + 1)) ${end}); do
- send_match "${j}" $((j + src_delta)) || return 1
+ send_match "$elem" "${j}" $((j + src_delta)) || return 1
done
send_nomatch $((end + 1)) $((end + 1 + src_delta)) || return 1
# Delete elements now and then
if [ $((i % 3)) -eq 0 ]; then
- del "$(format)" || return 1
+ del "$elem" || return 1
for j in $(seq "$start" \
$((range_size / 2 + 1)) ${end}); do
send_nomatch "${j}" $((j + src_delta)) \
@@ -1274,6 +1349,163 @@ test_correctness() {
done
}
+test_correctness() {
+ setup veth send_"${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:
@@ -1396,14 +1628,17 @@ test_timeout() {
range_size=1
for i in $(seq "$start" $((start + count))); do
+ local elem=""
+
end=$((start + range_size))
srcstart=$((start + src_delta))
srcend=$((end + src_delta))
- add "$(format)" || return 1
+ elem="$(format)"
+ add "$elem" || return 1
for j in $(seq "$start" $((range_size / 2 + 1)) ${end}); do
- send_match "${j}" $((j + src_delta)) || return 1
+ send_match "$elem" "${j}" $((j + src_delta)) || return 1
done
range_size=$((range_size + 1))
@@ -1561,7 +1796,7 @@ test_bug_reload() {
srcend=$((end + src_delta))
for j in $(seq "$start" $((range_size / 2 + 1)) ${end}); do
- send_match "${j}" $((j + src_delta)) || return 1
+ send_match "$(format)" "${j}" $((j + src_delta)) || return 1
done
range_size=$((range_size + 1))
@@ -1580,22 +1815,34 @@ test_bug_net_port_proto_match() {
range_size=1
for i in $(seq 1 10); do
for j in $(seq 1 20) ; do
- elem=$(printf "10.%d.%d.0/24 . %d1-%d0 . 6-17 " ${i} ${j} ${i} "$((i+1))")
+ local dport=$j
+
+ elem=$(printf "10.%d.%d.0/24 . %d-%d0 . 6-17 " ${i} ${j} ${dport} "$((dport+1))")
+
+ # too slow, do not test all addresses
+ maybe_send_nomatch "$elem" $(printf "10.%d.%d.1" $i $j) $(printf "%d1" $((dport+1))) "before add" || return 1
nft "add element inet filter test { $elem }" || return 1
+
+ maybe_send_match "$elem" $(printf "10.%d.%d.1" $i $j) $(printf "%d" $dport) "after add" || return 1
+
nft "get element inet filter test { $elem }" | grep -q "$elem"
if [ $? -ne 0 ];then
local got=$(nft "get element inet filter test { $elem }")
err "post-add: should have returned $elem but got $got"
return 1
fi
+
+ maybe_send_nomatch "$elem" $(printf "10.%d.%d.1" $i $j) $(printf "%d1" $((dport+1))) "out-of-range" || return 1
done
done
# recheck after set was filled
for i in $(seq 1 10); do
for j in $(seq 1 20) ; do
- elem=$(printf "10.%d.%d.0/24 . %d1-%d0 . 6-17 " ${i} ${j} ${i} "$((i+1))")
+ local dport=$j
+
+ elem=$(printf "10.%d.%d.0/24 . %d-%d0 . 6-17 " ${i} ${j} ${dport} "$((dport+1))")
nft "get element inet filter test { $elem }" | grep -q "$elem"
if [ $? -ne 0 ];then
@@ -1603,6 +1850,9 @@ test_bug_net_port_proto_match() {
err "post-fill: should have returned $elem but got $got"
return 1
fi
+
+ maybe_send_match "$elem" $(printf "10.%d.%d.1" $i $j) $(printf "%d" $dport) "recheck" || return 1
+ maybe_send_nomatch "$elem" $(printf "10.%d.%d.1" $i $j) $(printf "%d1" $((dport+1))) "recheck out-of-range" || return 1
done
done
@@ -1610,9 +1860,10 @@ test_bug_net_port_proto_match() {
for i in $(seq 1 10); do
for j in $(seq 1 20) ; do
local rnd=$((RANDOM%10))
+ local dport=$j
local got=""
- elem=$(printf "10.%d.%d.0/24 . %d1-%d0 . 6-17 " ${i} ${j} ${i} "$((i+1))")
+ elem=$(printf "10.%d.%d.0/24 . %d-%d0 . 6-17 " ${i} ${j} ${dport} "$((dport+1))")
if [ $rnd -gt 0 ];then
continue
fi
@@ -1623,12 +1874,32 @@ test_bug_net_port_proto_match() {
err "post-delete: query for $elem returned $got instead of error."
return 1
fi
+
+ maybe_send_nomatch "$elem" $(printf "10.%d.%d.1" $i $j) $(printf "%d" $dport) "match after deletion" || return 1
done
done
nft flush ruleset
}
+test_bug_avx2_mismatch()
+{
+ setup veth send_"${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 "{ icmpv6 . $a1 }")" -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 $ret
diff --git a/tools/testing/selftests/net/netfilter/nft_interface_stress.sh b/tools/testing/selftests/net/netfilter/nft_interface_stress.sh
new file mode 100755
index 000000000000..c0fffaa6dbd9
--- /dev/null
+++ b/tools/testing/selftests/net/netfilter/nft_interface_stress.sh
@@ -0,0 +1,157 @@
+#!/bin/bash -e
+#
+# SPDX-License-Identifier: GPL-2.0
+#
+# Torture nftables' netdevice notifier callbacks and related code by frequent
+# renaming of interfaces which netdev-family chains and flowtables hook into.
+
+source lib.sh
+
+checktool "nft --version" "run test without nft tool"
+checktool "iperf3 --version" "run test without iperf3 tool"
+
+read kernel_tainted < /proc/sys/kernel/tainted
+
+# how many seconds to torture the kernel?
+# default to 80% of max run time but don't exceed 48s
+TEST_RUNTIME=$((${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
+
+
+[[ $kernel_tainted -eq 0 && $(</proc/sys/kernel/tainted) -ne 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 $ksft_pass
diff --git a/tools/testing/selftests/net/netfilter/nft_nat.sh b/tools/testing/selftests/net/netfilter/nft_nat.sh
index 9e39de26455f..a954754b99b3 100755
--- a/tools/testing/selftests/net/netfilter/nft_nat.sh
+++ b/tools/testing/selftests/net/netfilter/nft_nat.sh
@@ -866,6 +866,24 @@ EOF
ip netns exec "$ns0" nft delete table $family nat
}
+file_cmp()
+{
+ local infile="$1"
+ local outfile="$2"
+
+ if ! cmp "$infile" "$outfile";then
+ echo -n "Infile "
+ ls -l "$infile"
+ echo -n "Outfile "
+ ls -l "$outfile"
+ echo "ERROR: in and output file mismatch when checking $msg" 1>&1
+ ret=1
+ return 1
+ fi
+
+ return 0
+}
+
test_stateless_nat_ip()
{
local lret=0
@@ -966,11 +984,7 @@ EOF
wait
- if ! cmp "$INFILE" "$OUTFILE";then
- ls -l "$INFILE" "$OUTFILE"
- echo "ERROR: in and output file mismatch when checking udp with stateless nat" 1>&2
- lret=1
- fi
+ file_cmp "$INFILE" "$OUTFILE" "udp with stateless nat" || lret=1
:> "$OUTFILE"
@@ -991,6 +1005,62 @@ EOF
return $lret
}
+test_dnat_clash()
+{
+ local lret=0
+
+ if ! socat -h > /dev/null 2>&1;then
+ echo "SKIP: Could not run dnat clash test without socat tool"
+ [ $ret -eq 0 ] && ret=$ksft_skip
+ return $ksft_skip
+ fi
+
+ip netns exec "$ns0" nft -f /dev/stdin <<EOF
+flush ruleset
+table ip dnat-test {
+ chain prerouting {
+ type nat hook prerouting priority dstnat; policy accept;
+ ip daddr 10.0.2.1 udp dport 1234 counter dnat to 10.0.1.1:1234
+ }
+}
+EOF
+ if [ $? -ne 0 ]; then
+ echo "SKIP: Could not add dnat rules"
+ [ $ret -eq 0 ] && ret=$ksft_skip
+ return $ksft_skip
+ fi
+
+ local udpdaddr="10.0.2.1"
+ for i in 1 2;do
+ echo "PING $udpdaddr" > "$INFILE"
+ echo "PONG 10.0.1.1 step $i" | ip netns exec "$ns0" timeout 3 socat STDIO UDP4-LISTEN:1234,bind=10.0.1.1 > "$OUTFILE" 2>/dev/null &
+ local lpid=$!
+
+ busywait $BUSYWAIT_TIMEOUT listener_ready "$ns0" 1234 "-u"
+
+ result=$(ip netns exec "$ns1" timeout 3 socat STDIO UDP4-SENDTO:"$udpdaddr:1234,sourceport=4321" < "$INFILE")
+ udpdaddr="10.0.1.1"
+
+ if [ "$result" != "PONG 10.0.1.1 step $i" ] ; then
+ echo "ERROR: failed to test udp $ns1 to $ns2 with dnat rule step $i, result: \"$result\"" 1>&2
+ lret=1
+ ret=1
+ fi
+
+ wait
+
+ file_cmp "$INFILE" "$OUTFILE" "udp dnat step $i" || lret=1
+
+ :> "$OUTFILE"
+ done
+
+ test $lret -eq 0 && echo "PASS: IP dnat clash $ns1:$ns2"
+
+ ip netns exec "$ns0" nft flush ruleset
+
+ return $lret
+}
+
# ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99
for i in "$ns0" "$ns1" "$ns2" ;do
ip netns exec "$i" nft -f /dev/stdin <<EOF
@@ -1147,6 +1217,7 @@ $test_inet_nat && test_redirect6 inet
test_port_shadowing
test_stateless_nat_ip
+test_dnat_clash
if [ $ret -ne 0 ];then
echo -n "FAIL: "
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/netfilter/udpclash.c b/tools/testing/selftests/net/netfilter/udpclash.c
new file mode 100644
index 000000000000..85c7b906ad08
--- /dev/null
+++ b/tools/testing/selftests/net/netfilter/udpclash.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Usage: ./udpclash <IP> <PORT>
+ *
+ * Emit THREAD_COUNT UDP packets sharing the same saddr:daddr pair.
+ *
+ * This mimics DNS resolver libraries that emit A and AAAA requests
+ * in parallel.
+ *
+ * This exercises conntrack clash resolution logic added and later
+ * refined in
+ *
+ * 71d8c47fc653 ("netfilter: conntrack: introduce clash resolution on insertion race")
+ * ed07d9a021df ("netfilter: nf_conntrack: resolve clash for matching conntracks")
+ * 6a757c07e51f ("netfilter: conntrack: allow insertion of clashing entries")
+ */
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <arpa/inet.h>
+#include <sys/socket.h>
+#include <pthread.h>
+
+#define THREAD_COUNT 128
+
+struct thread_args {
+ const struct sockaddr_in *si_remote;
+ int sockfd;
+};
+
+static int wait = 1;
+
+static void *thread_main(void *varg)
+{
+ const struct sockaddr_in *si_remote;
+ const struct thread_args *args = varg;
+ static const char msg[] = "foo";
+
+ si_remote = args->si_remote;
+
+ while (wait == 1)
+ ;
+
+ if (sendto(args->sockfd, msg, strlen(msg), MSG_NOSIGNAL,
+ (struct sockaddr *)si_remote, sizeof(*si_remote)) < 0)
+ exit(111);
+
+ return varg;
+}
+
+static int run_test(int fd, const struct sockaddr_in *si_remote)
+{
+ struct thread_args thread_args = {
+ .si_remote = si_remote,
+ .sockfd = fd,
+ };
+ pthread_t *tid = calloc(THREAD_COUNT, sizeof(pthread_t));
+ unsigned int repl_count = 0, timeout = 0;
+ int i;
+
+ if (!tid) {
+ perror("calloc");
+ return 1;
+ }
+
+ for (i = 0; i < THREAD_COUNT; i++) {
+ int err = pthread_create(&tid[i], NULL, &thread_main, &thread_args);
+
+ if (err != 0) {
+ perror("pthread_create");
+ exit(1);
+ }
+ }
+
+ wait = 0;
+
+ for (i = 0; i < THREAD_COUNT; i++)
+ pthread_join(tid[i], NULL);
+
+ while (repl_count < THREAD_COUNT) {
+ struct sockaddr_in si_repl;
+ socklen_t si_repl_len = sizeof(si_repl);
+ char repl[512];
+ ssize_t ret;
+
+ ret = recvfrom(fd, repl, sizeof(repl), MSG_NOSIGNAL,
+ (struct sockaddr *) &si_repl, &si_repl_len);
+ if (ret < 0) {
+ if (timeout++ > 5000) {
+ fputs("timed out while waiting for reply from thread\n", stderr);
+ break;
+ }
+
+ /* give reply time to pass though the stack */
+ usleep(1000);
+ continue;
+ }
+
+ if (si_repl_len != sizeof(*si_remote)) {
+ fprintf(stderr, "warning: reply has unexpected repl_len %d vs %d\n",
+ (int)si_repl_len, (int)sizeof(si_repl));
+ } else if (si_remote->sin_addr.s_addr != si_repl.sin_addr.s_addr ||
+ si_remote->sin_port != si_repl.sin_port) {
+ char a[64], b[64];
+
+ inet_ntop(AF_INET, &si_remote->sin_addr, a, sizeof(a));
+ inet_ntop(AF_INET, &si_repl.sin_addr, b, sizeof(b));
+
+ fprintf(stderr, "reply from wrong source: want %s:%d got %s:%d\n",
+ a, ntohs(si_remote->sin_port), b, ntohs(si_repl.sin_port));
+ }
+
+ repl_count++;
+ }
+
+ printf("got %d of %d replies\n", repl_count, THREAD_COUNT);
+
+ free(tid);
+
+ return repl_count == THREAD_COUNT ? 0 : 1;
+}
+
+int main(int argc, char *argv[])
+{
+ struct sockaddr_in si_local = {
+ .sin_family = AF_INET,
+ };
+ struct sockaddr_in si_remote = {
+ .sin_family = AF_INET,
+ };
+ int fd, ret;
+
+ if (argc < 3) {
+ fputs("Usage: send_udp <daddr> <dport>\n", stderr);
+ return 1;
+ }
+
+ si_remote.sin_port = htons(atoi(argv[2]));
+ si_remote.sin_addr.s_addr = inet_addr(argv[1]);
+
+ fd = socket(AF_INET, SOCK_DGRAM|SOCK_CLOEXEC|SOCK_NONBLOCK, IPPROTO_UDP);
+ if (fd < 0) {
+ perror("socket");
+ return 1;
+ }
+
+ if (bind(fd, (struct sockaddr *)&si_local, sizeof(si_local)) < 0) {
+ perror("bind");
+ return 1;
+ }
+
+ ret = run_test(fd, &si_remote);
+
+ close(fd);
+
+ return ret;
+}
diff --git a/tools/testing/selftests/net/netns-name.sh b/tools/testing/selftests/net/netns-name.sh
index 0be1905d1f2f..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
diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c
index cd8a58097448..1f5227f3d64d 100644
--- a/tools/testing/selftests/net/nettest.c
+++ b/tools/testing/selftests/net/nettest.c
@@ -385,7 +385,7 @@ static int get_bind_to_device(int sd, char *name, size_t len)
name[0] = '\0';
rc = getsockopt(sd, SOL_SOCKET, SO_BINDTODEVICE, name, &optlen);
if (rc < 0)
- log_err_errno("setsockopt(SO_BINDTODEVICE)");
+ log_err_errno("getsockopt(SO_BINDTODEVICE)");
return rc;
}
@@ -535,7 +535,7 @@ static int set_freebind(int sd, int version)
break;
case AF_INET6:
if (setsockopt(sd, SOL_IPV6, IPV6_FREEBIND, &one, sizeof(one))) {
- log_err_errno("setsockopt(IPV6_FREEBIND");
+ log_err_errno("setsockopt(IPV6_FREEBIND)");
rc = -1;
}
break;
@@ -812,7 +812,7 @@ static int convert_addr(struct sock_args *args, const char *_str,
sep++;
if (str_to_uint(sep, 1, pfx_len_max,
&args->prefix_len) != 0) {
- fprintf(stderr, "Invalid port\n");
+ fprintf(stderr, "Invalid prefix length\n");
return 1;
}
} else {
@@ -1272,7 +1272,7 @@ static int msg_loop(int client, int sd, void *addr, socklen_t alen,
}
}
- nfds = interactive ? MAX(fileno(stdin), sd) + 1 : sd + 1;
+ nfds = interactive ? MAX(fileno(stdin), sd) + 1 : sd + 1;
while (1) {
FD_ZERO(&rfds);
FD_SET(sd, &rfds);
@@ -1492,7 +1492,7 @@ static int lsock_init(struct sock_args *args)
sd = socket(args->version, args->type, args->protocol);
if (sd < 0) {
log_err_errno("Error opening socket");
- return -1;
+ return -1;
}
if (set_reuseaddr(sd) != 0)
@@ -1912,7 +1912,7 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args)
* waiting to be told when to continue
*/
if (read(fd, &buf, sizeof(buf)) <= 0) {
- log_err_errno("Failed to read IPC status from status");
+ log_err_errno("Failed to read IPC status from pipe");
return 1;
}
if (!buf) {
diff --git a/tools/testing/selftests/net/nl_netdev.py b/tools/testing/selftests/net/nl_netdev.py
index beaee5e4e2aa..5c66421ab8aa 100755
--- a/tools/testing/selftests/net/nl_netdev.py
+++ b/tools/testing/selftests/net/nl_netdev.py
@@ -2,8 +2,9 @@
# SPDX-License-Identifier: GPL-2.0
import time
+from os import system
from lib.py import ksft_run, ksft_exit, ksft_pr
-from lib.py import ksft_eq, ksft_ge, ksft_busy_wait
+from lib.py import ksft_eq, ksft_ge, ksft_ne, ksft_busy_wait
from lib.py import NetdevFamily, NetdevSimDev, ip
@@ -34,6 +35,128 @@ def napi_list_check(nf) -> None:
ksft_eq(len(napis), 100,
comment=f"queue count after reset queue {q} mode {i}")
+def napi_set_threaded(nf) -> None:
+ """
+ Test that verifies various cases of napi threaded
+ set and unset at napi and device level.
+ """
+ with NetdevSimDev(queue_count=2) as nsimdev:
+ nsim = nsimdev.nsims[0]
+
+ ip(f"link set dev {nsim.ifname} up")
+
+ napis = nf.napi_get({'ifindex': nsim.ifindex}, dump=True)
+ ksft_eq(len(napis), 2)
+
+ napi0_id = napis[0]['id']
+ napi1_id = napis[1]['id']
+
+ # set napi threaded and verify
+ nf.napi_set({'id': napi0_id, 'threaded': "enabled"})
+ napi0 = nf.napi_get({'id': napi0_id})
+ ksft_eq(napi0['threaded'], "enabled")
+ ksft_ne(napi0.get('pid'), None)
+
+ # check it is not set for napi1
+ napi1 = nf.napi_get({'id': napi1_id})
+ ksft_eq(napi1['threaded'], "disabled")
+ ksft_eq(napi1.get('pid'), None)
+
+ ip(f"link set dev {nsim.ifname} down")
+ ip(f"link set dev {nsim.ifname} up")
+
+ # verify if napi threaded is still set
+ napi0 = nf.napi_get({'id': napi0_id})
+ ksft_eq(napi0['threaded'], "enabled")
+ ksft_ne(napi0.get('pid'), None)
+
+ # check it is still not set for napi1
+ napi1 = nf.napi_get({'id': napi1_id})
+ ksft_eq(napi1['threaded'], "disabled")
+ ksft_eq(napi1.get('pid'), None)
+
+ # unset napi threaded and verify
+ nf.napi_set({'id': napi0_id, 'threaded': "disabled"})
+ napi0 = nf.napi_get({'id': napi0_id})
+ ksft_eq(napi0['threaded'], "disabled")
+ ksft_eq(napi0.get('pid'), None)
+
+ # set threaded at device level
+ system(f"echo 1 > /sys/class/net/{nsim.ifname}/threaded")
+
+ # check napi threaded is set for both napis
+ napi0 = nf.napi_get({'id': napi0_id})
+ ksft_eq(napi0['threaded'], "enabled")
+ ksft_ne(napi0.get('pid'), None)
+ napi1 = nf.napi_get({'id': napi1_id})
+ ksft_eq(napi1['threaded'], "enabled")
+ ksft_ne(napi1.get('pid'), None)
+
+ # unset threaded at device level
+ system(f"echo 0 > /sys/class/net/{nsim.ifname}/threaded")
+
+ # check napi threaded is unset for both napis
+ napi0 = nf.napi_get({'id': napi0_id})
+ ksft_eq(napi0['threaded'], "disabled")
+ ksft_eq(napi0.get('pid'), None)
+ napi1 = nf.napi_get({'id': napi1_id})
+ ksft_eq(napi1['threaded'], "disabled")
+ ksft_eq(napi1.get('pid'), None)
+
+ # set napi threaded for napi0
+ nf.napi_set({'id': napi0_id, 'threaded': 1})
+ napi0 = nf.napi_get({'id': napi0_id})
+ ksft_eq(napi0['threaded'], "enabled")
+ ksft_ne(napi0.get('pid'), None)
+
+ # unset threaded at device level
+ system(f"echo 0 > /sys/class/net/{nsim.ifname}/threaded")
+
+ # check napi threaded is unset for both napis
+ napi0 = nf.napi_get({'id': napi0_id})
+ ksft_eq(napi0['threaded'], "disabled")
+ ksft_eq(napi0.get('pid'), None)
+ napi1 = nf.napi_get({'id': napi1_id})
+ ksft_eq(napi1['threaded'], "disabled")
+ ksft_eq(napi1.get('pid'), None)
+
+def dev_set_threaded(nf) -> None:
+ """
+ Test that verifies various cases of napi threaded
+ set and unset at device level using sysfs.
+ """
+ with NetdevSimDev(queue_count=2) as nsimdev:
+ nsim = nsimdev.nsims[0]
+
+ ip(f"link set dev {nsim.ifname} up")
+
+ napis = nf.napi_get({'ifindex': nsim.ifindex}, dump=True)
+ ksft_eq(len(napis), 2)
+
+ napi0_id = napis[0]['id']
+ napi1_id = napis[1]['id']
+
+ # set threaded
+ system(f"echo 1 > /sys/class/net/{nsim.ifname}/threaded")
+
+ # check napi threaded is set for both napis
+ napi0 = nf.napi_get({'id': napi0_id})
+ ksft_eq(napi0['threaded'], "enabled")
+ ksft_ne(napi0.get('pid'), None)
+ napi1 = nf.napi_get({'id': napi1_id})
+ ksft_eq(napi1['threaded'], "enabled")
+ ksft_ne(napi1.get('pid'), None)
+
+ # unset threaded
+ system(f"echo 0 > /sys/class/net/{nsim.ifname}/threaded")
+
+ # check napi threaded is unset for both napis
+ napi0 = nf.napi_get({'id': napi0_id})
+ ksft_eq(napi0['threaded'], "disabled")
+ ksft_eq(napi0.get('pid'), None)
+ napi1 = nf.napi_get({'id': napi1_id})
+ ksft_eq(napi1['threaded'], "disabled")
+ ksft_eq(napi1.get('pid'), None)
def nsim_rxq_reset_down(nf) -> None:
"""
@@ -122,7 +245,7 @@ def page_pool_check(nf) -> None:
def main() -> None:
nf = NetdevFamily()
ksft_run([empty_check, lo_check, page_pool_check, napi_list_check,
- nsim_rxq_reset_down],
+ dev_set_threaded, napi_set_threaded, nsim_rxq_reset_down],
args=(nf, ))
ksft_exit()
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..9201f2905f2c
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/ovpn-cli.c
@@ -0,0 +1,2384 @@
+// 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];
+
+ ovpn->sa_family = AF_INET;
+ 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-large-mtu.sh b/tools/testing/selftests/net/ovpn/test-large-mtu.sh
new file mode 100755
index 000000000000..ce2a2cb64f72
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test-large-mtu.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2025 OpenVPN, Inc.
+#
+# Author: Antonio Quartulli <antonio@openvpn.net>
+
+MTU="1500"
+
+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} ${p} 3 3
+done
+sleep 5
+
+cleanup
+
+modprobe -r ovpn || true
diff --git a/tools/testing/selftests/net/ovpn/udp_peers.txt b/tools/testing/selftests/net/ovpn/udp_peers.txt
new file mode 100644
index 000000000000..e9773ddf875c
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/udp_peers.txt
@@ -0,0 +1,6 @@
+1 10.10.1.1 1 10.10.1.2 1 5.5.5.2
+2 10.10.2.1 1 10.10.2.2 1 5.5.5.3
+3 10.10.3.1 1 10.10.3.2 1 5.5.5.4
+4 fd00:0:0:4::1 1 fd00:0:0:4::2 1 5.5.5.5
+5 fd00:0:0:5::1 1 fd00:0:0:5::2 1 5.5.5.6
+6 fd00:0:0:6::1 1 fd00:0:0:6::2 1 5.5.5.7
diff --git a/tools/testing/selftests/net/packetdrill/ksft_runner.sh b/tools/testing/selftests/net/packetdrill/ksft_runner.sh
index ef8b25a606d8..c5b01e1bd4c7 100755
--- a/tools/testing/selftests/net/packetdrill/ksft_runner.sh
+++ b/tools/testing/selftests/net/packetdrill/ksft_runner.sh
@@ -39,11 +39,15 @@ if [[ -n "${KSFT_MACHINE_SLOW}" ]]; then
# xfail tests that are known flaky with dbg config, not fixable.
# still run them for coverage (and expect 100% pass without dbg).
declare -ar xfail_list=(
+ "tcp_blocking_blocking-connect.pkt"
+ "tcp_blocking_blocking-read.pkt"
"tcp_eor_no-coalesce-retrans.pkt"
"tcp_fast_recovery_prr-ss.*.pkt"
+ "tcp_sack_sack-route-refresh-ip-tos.pkt"
"tcp_slow_start_slow-start-after-win-update.pkt"
"tcp_timestamping.*.pkt"
"tcp_user_timeout_user-timeout-probe.pkt"
+ "tcp_zerocopy_cl.*.pkt"
"tcp_zerocopy_epoll_.*.pkt"
"tcp_tcp_info_tcp-info-.*-limited.pkt"
)
diff --git a/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt
index 914eabab367a..657e42ca65b5 100644
--- a/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt
+++ b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt
@@ -1,6 +1,8 @@
// SPDX-License-Identifier: GPL-2.0
// Test for blocking read.
+
--tolerance_usecs=10000
+--mss=1000
`./defaults.sh`
diff --git a/tools/testing/selftests/net/packetdrill/tcp_dsack_mult.pkt b/tools/testing/selftests/net/packetdrill/tcp_dsack_mult.pkt
new file mode 100644
index 000000000000..c790d0af635e
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_dsack_mult.pkt
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test various DSACK (RFC 2883) behaviors.
+
+--mss=1000
+
+`./defaults.sh`
+
+
+ 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+ +.1 < . 1:1(0) ack 1 win 1024
+ +0 accept(3, ..., ...) = 4
+
+// First SACK range.
+ +0 < P. 1001:2001(1000) ack 1 win 1024
+ +0 > . 1:1(0) ack 1 <nop, nop, sack 1001:2001>
+
+// Check SACK coalescing (contiguous sequence).
+ +0 < P. 2001:3001(1000) ack 1 win 1024
+ +0 > . 1:1(0) ack 1 <nop,nop,sack 1001:3001>
+
+// Check we have two SACK ranges for non contiguous sequences.
+ +0 < P. 4001:5001(1000) ack 1 win 1024
+ +0 > . 1:1(0) ack 1 <nop,nop,sack 4001:5001 1001:3001>
+
+// Three ranges.
+ +0 < P. 7001:8001(1000) ack 1 win 1024
+ +0 > . 1:1(0) ack 1 <nop,nop,sack 7001:8001 4001:5001 1001:3001>
+
+// DSACK (1001:3001) + SACK (6001:7001)
+ +0 < P. 1:6001(6000) ack 1 win 1024
+ +0 > . 1:1(0) ack 6001 <nop,nop,sack 1001:3001 7001:8001>
+
+// DSACK (7001:8001)
+ +0 < P. 6001:8001(2000) ack 1 win 1024
+ +0 > . 1:1(0) ack 8001 <nop,nop,sack 7001:8001>
+
+// DSACK for an older segment.
+ +0 < P. 1:1001(1000) ack 1 win 1024
+ +0 > . 1:1(0) ack 8001 <nop,nop,sack 1:1001>
diff --git a/tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt b/tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt
index df49c67645ac..e13f0eee9795 100644
--- a/tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt
+++ b/tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt
@@ -1,5 +1,8 @@
// SPDX-License-Identifier: GPL-2.0
// Test TCP_INQ and TCP_CM_INQ on the client side.
+
+--mss=1000
+
`./defaults.sh
`
diff --git a/tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt b/tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt
index 04a5e2590c62..14dd5f813d50 100644
--- a/tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt
+++ b/tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt
@@ -1,5 +1,8 @@
// SPDX-License-Identifier: GPL-2.0
// Test TCP_INQ and TCP_CM_INQ on the server side.
+
+--mss=1000
+
`./defaults.sh
`
diff --git a/tools/testing/selftests/net/packetdrill/tcp_ooo-before-and-after-accept.pkt b/tools/testing/selftests/net/packetdrill/tcp_ooo-before-and-after-accept.pkt
new file mode 100644
index 000000000000..09aabc775e80
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_ooo-before-and-after-accept.pkt
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+
+--mss=1000
+
+`./defaults.sh
+sysctl -q net.ipv4.tcp_rmem="4096 131072 $((32*1024*1024))"`
+
+// Test that a not-yet-accepted socket does not change
+// its initial sk_rcvbuf (tcp_rmem[1]) when receiving ooo packets.
+
+ +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 65535 <mss 1000,nop,nop,sackOK,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 10>
+ +.1 < . 1:1(0) ack 1 win 257
+ +0 < . 2001:41001(39000) ack 1 win 257
+ +0 > . 1:1(0) ack 1 <nop,nop,sack 2001:41001>
+ +0 < . 41001:101001(60000) ack 1 win 257
+ +0 > . 1:1(0) ack 1 <nop,nop,sack 2001:101001>
+ +0 < . 1:1001(1000) ack 1 win 257
+ +0 > . 1:1(0) ack 1001 <nop,nop,sack 2001:101001>
+ +0 < . 1001:2001(1000) ack 1 win 257
+ +0 > . 1:1(0) ack 101001
+
+ +0 accept(3, ..., ...) = 4
+
+ +0 %{ assert SK_MEMINFO_RCVBUF == 131072, SK_MEMINFO_RCVBUF }%
+
+ +0 close(4) = 0
+ +0 close(3) = 0
+
+// Test that ooo packets for accepted sockets do increase sk_rcvbuf
+ +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 65535 <mss 1000,nop,nop,sackOK,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 10>
+ +.1 < . 1:1(0) ack 1 win 257
+
+ +0 accept(3, ..., ...) = 4
+
+ +0 < . 2001:41001(39000) ack 1 win 257
+ +0 > . 1:1(0) ack 1 <nop,nop,sack 2001:41001>
+ +0 < . 41001:101001(60000) ack 1 win 257
+ +0 > . 1:1(0) ack 1 <nop,nop,sack 2001:101001>
+
+ +0 %{ assert SK_MEMINFO_RCVBUF > 131072, SK_MEMINFO_RCVBUF }%
+
diff --git a/tools/testing/selftests/net/packetdrill/tcp_ooo_rcv_mss.pkt b/tools/testing/selftests/net/packetdrill/tcp_ooo_rcv_mss.pkt
new file mode 100644
index 000000000000..7e6bc5fb0c8d
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_ooo_rcv_mss.pkt
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+
+--mss=1000
+
+`./defaults.sh
+sysctl -q net.ipv4.tcp_rmem="4096 131072 $((32*1024*1024))"`
+
+ +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 65535 <mss 1000,nop,nop,sackOK,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 10>
+ +.1 < . 1:1(0) ack 1 win 257
+
+ +0 accept(3, ..., ...) = 4
+
+ +0 < . 2001:11001(9000) ack 1 win 257
+ +0 > . 1:1(0) ack 1 win 81 <nop,nop,sack 2001:11001>
+
+// check that ooo packet properly updates tcpi_rcv_mss
+ +0 %{ assert tcpi_rcv_mss == 1000, tcpi_rcv_mss }%
+
+ +0 < . 11001:21001(10000) ack 1 win 257
+ +0 > . 1:1(0) ack 1 win 81 <nop,nop,sack 2001:21001>
+
diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt
new file mode 100644
index 000000000000..3848b419e68c
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+
+--mss=1000
+
+`./defaults.sh`
+
+ 0 `nstat -n`
+
+// Establish a connection.
+ +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [10000], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 0>
+ +.1 < . 1:1(0) ack 1 win 257
+
+ +0 accept(3, ..., ...) = 4
+
+ +0 < P. 1:4001(4000) ack 1 win 257
+ +0 > . 1:1(0) ack 4001 win 5000
+
+// packet in sequence : SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE / LINUX_MIB_BEYOND_WINDOW
+ +0 < P. 4001:54001(50000) ack 1 win 257
+ +0 > . 1:1(0) ack 4001 win 5000
+
+// ooo packet. : SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE / LINUX_MIB_BEYOND_WINDOW
+ +1 < P. 5001:55001(50000) ack 1 win 257
+ +0 > . 1:1(0) ack 4001 win 5000
+
+// SKB_DROP_REASON_TCP_INVALID_SEQUENCE / LINUX_MIB_BEYOND_WINDOW
+ +0 < P. 70001:80001(10000) ack 1 win 257
+ +0 > . 1:1(0) ack 4001 win 5000
+
+ +0 read(4, ..., 100000) = 4000
+
+// If queue is empty, accept a packet even if its end_seq is above wup + rcv_wnd
+ +0 < P. 4001:54001(50000) ack 1 win 257
+ +0 > . 1:1(0) ack 54001 win 0
+
+// Check LINUX_MIB_BEYOND_WINDOW has been incremented 3 times.
++0 `nstat | grep TcpExtBeyondWindow | grep -q " 3 "`
diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt
new file mode 100644
index 000000000000..f575c0ff89da
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+
+--mss=1000
+
+`./defaults.sh`
+
+ 0 `nstat -n`
+
+// Establish a connection.
+ +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+ +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+ +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [20000], 4) = 0
+ +0 bind(3, ..., ...) = 0
+ +0 listen(3, 1) = 0
+
+ +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7>
+ +0 > S. 0:0(0) ack 1 win 18980 <mss 1460,nop,wscale 0>
+ +.1 < . 1:1(0) ack 1 win 257
+
+ +0 accept(3, ..., ...) = 4
+
+ +0 < P. 1:20001(20000) ack 1 win 257
+ +.04 > . 1:1(0) ack 20001 win 18000
+
+ +0 setsockopt(4, SOL_SOCKET, SO_RCVBUF, [12000], 4) = 0
+ +0 < P. 20001:80001(60000) ack 1 win 257
+ +0 > . 1:1(0) ack 20001 win 18000
+
+ +0 read(4, ..., 20000) = 20000
+// A too big packet is accepted if the receive queue is empty
+ +0 < P. 20001:80001(60000) ack 1 win 257
+ +0 > . 1:1(0) ack 80001 win 0
+
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/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
index 80950888800b..e9ad5e88da97 100755
--- a/tools/testing/selftests/net/rtnetlink.py
+++ b/tools/testing/selftests/net/rtnetlink.py
@@ -12,10 +12,10 @@ def dump_mcaddr_check(rtnl: RtnlAddrFamily) -> None:
At least the loopback interface should have this address.
"""
- addresses = rtnl.getmaddrs({"ifa-family": socket.AF_INET}, dump=True)
+ addresses = rtnl.getmulticast({"ifa-family": socket.AF_INET}, dump=True)
all_host_multicasts = [
- addr for addr in addresses if addr['ifa-multicast'] == IPV4_ALL_HOSTS_MULTICAST
+ addr for addr in addresses if addr['multicast'] == IPV4_ALL_HOSTS_MULTICAST
]
ksft_ge(len(all_host_multicasts), 1,
diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 2e8243a65b50..d6c00efeb664 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -21,6 +21,7 @@ ALL_TESTS="
kci_test_vrf
kci_test_encap
kci_test_macsec
+ kci_test_macsec_vlan
kci_test_ipsec
kci_test_ipsec_offload
kci_test_fdb_get
@@ -30,6 +31,7 @@ ALL_TESTS="
kci_test_address_proto
kci_test_enslave_bonding
kci_test_mngtmpaddr
+ kci_test_operstate
"
devdummy="test-dummy0"
@@ -291,6 +293,17 @@ kci_test_route_get()
end_test "PASS: route get"
}
+check_addr_not_exist()
+{
+ dev=$1
+ addr=$2
+ if ip addr show dev $dev | grep -q $addr; then
+ return 1
+ else
+ return 0
+ fi
+}
+
kci_test_addrlft()
{
for i in $(seq 10 100) ;do
@@ -298,9 +311,8 @@ kci_test_addrlft()
run_cmd ip addr add 10.23.11.$i/32 dev "$devdummy" preferred_lft $lft valid_lft $((lft+1))
done
- sleep 5
- run_cmd_grep_fail "10.23.11." ip addr show dev "$devdummy"
- if [ $? -eq 0 ]; then
+ slowwait 5 check_addr_not_exist "$devdummy" "10.23.11."
+ if [ $? -eq 1 ]; then
check_err 1
end_test "FAIL: preferred_lft addresses remaining"
return
@@ -561,6 +573,41 @@ kci_test_macsec()
end_test "PASS: macsec"
}
+# Test __dev_set_rx_mode call from dev_uc_add under addr_list_lock spinlock.
+# Make sure __dev_set_promiscuity is not grabbing (sleeping) netdev instance
+# lock.
+# https://lore.kernel.org/netdev/2aff4342b0f5b1539c02ffd8df4c7e58dd9746e7.camel@nvidia.com/
+kci_test_macsec_vlan()
+{
+ msname="test_macsec1"
+ vlanname="test_vlan1"
+ local ret=0
+ run_cmd_grep "^Usage: ip macsec" ip macsec help
+ if [ $? -ne 0 ]; then
+ end_test "SKIP: macsec: iproute2 too old"
+ return $ksft_skip
+ fi
+ run_cmd ip link add link "$devdummy" "$msname" type macsec port 42 encrypt on
+ if [ $ret -ne 0 ];then
+ end_test "FAIL: can't add macsec interface, skipping test"
+ return 1
+ fi
+
+ run_cmd ip link set dev "$msname" up
+ ip link add link "$msname" name "$vlanname" type vlan id 1
+ ip link set dev "$vlanname" address 00:11:22:33:44:88
+ ip link set dev "$vlanname" up
+ run_cmd ip link del dev "$vlanname"
+ run_cmd ip link del dev "$msname"
+
+ if [ $ret -ne 0 ];then
+ end_test "FAIL: macsec_vlan"
+ return 1
+ fi
+
+ end_test "PASS: macsec_vlan"
+}
+
#-------------------------------------------------------------------
# Example commands
# ip x s add proto esp src 14.0.0.52 dst 14.0.0.70 \
@@ -673,6 +720,11 @@ kci_test_ipsec_offload()
sysfsf=$sysfsd/ipsec
sysfsnet=/sys/bus/netdevsim/devices/netdevsim0/net/
probed=false
+ esp4_offload_probed_default=false
+
+ if lsmod | grep -q esp4_offload; then
+ esp4_offload_probed_default=true
+ fi
if ! mount | grep -q debugfs; then
mount -t debugfs none /sys/kernel/debug/ &> /dev/null
@@ -766,6 +818,7 @@ EOF
fi
# clean up any leftovers
+ ! "$esp4_offload_probed_default" && lsmod | grep -q esp4_offload && rmmod esp4_offload
echo 0 > /sys/bus/netdevsim/del_device
$probed && rmmod netdevsim
@@ -1334,6 +1387,39 @@ kci_test_mngtmpaddr()
return $ret
}
+kci_test_operstate()
+{
+ local ret=0
+
+ # Check that it is possible to set operational state during device
+ # creation and that it is preserved when the administrative state of
+ # the device is toggled.
+ run_cmd ip link add name vx0 up state up type vxlan id 10010 dstport 4789
+ run_cmd_grep "state UP" ip link show dev vx0
+ run_cmd ip link set dev vx0 down
+ run_cmd_grep "state DOWN" ip link show dev vx0
+ run_cmd ip link set dev vx0 up
+ run_cmd_grep "state UP" ip link show dev vx0
+
+ run_cmd ip link del dev vx0
+
+ # Check that it is possible to set the operational state of the device
+ # after creation.
+ run_cmd ip link add name vx0 up type vxlan id 10010 dstport 4789
+ run_cmd_grep "state UNKNOWN" ip link show dev vx0
+ run_cmd ip link set dev vx0 state up
+ run_cmd_grep "state UP" ip link show dev vx0
+
+ run_cmd ip link del dev vx0
+
+ if [ "$ret" -ne 0 ]; then
+ end_test "FAIL: operstate"
+ return 1
+ fi
+
+ end_test "PASS: operstate"
+}
+
kci_test_rtnl()
{
local current_test
diff --git a/tools/testing/selftests/net/rtnetlink_notification.sh b/tools/testing/selftests/net/rtnetlink_notification.sh
new file mode 100755
index 000000000000..3f9780232bd6
--- /dev/null
+++ b/tools/testing/selftests/net/rtnetlink_notification.sh
@@ -0,0 +1,112 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# This test is for checking rtnetlink notification callpaths, and get as much
+# coverage as possible.
+#
+# set -e
+
+ALL_TESTS="
+ kci_test_mcast_addr_notification
+ kci_test_anycast_addr_notification
+"
+
+source lib.sh
+test_dev="test-dummy1"
+
+kci_test_mcast_addr_notification()
+{
+ RET=0
+ local tmpfile
+ local monitor_pid
+ local match_result
+
+ tmpfile=$(mktemp)
+ defer rm "$tmpfile"
+
+ ip monitor maddr > $tmpfile &
+ monitor_pid=$!
+ defer kill_process "$monitor_pid"
+
+ sleep 1
+
+ if [ ! -e "/proc/$monitor_pid" ]; then
+ RET=$ksft_skip
+ log_test "mcast addr notification: iproute2 too old"
+ return $RET
+ fi
+
+ ip link add name "$test_dev" type dummy
+ check_err $? "failed to add dummy interface"
+ ip link set "$test_dev" up
+ check_err $? "failed to set dummy interface up"
+ ip link del dev "$test_dev"
+ check_err $? "Failed to delete dummy interface"
+ sleep 1
+
+ # There should be 4 line matches as follows.
+ # 13: test-dummy1    inet6 mcast ff02::1 scope global 
+ # 13: test-dummy1    inet mcast 224.0.0.1 scope global 
+ # Deleted 13: test-dummy1    inet mcast 224.0.0.1 scope global 
+ # Deleted 13: test-dummy1    inet6 mcast ff02::1 scope global 
+ match_result=$(grep -cE "$test_dev.*(224.0.0.1|ff02::1)" "$tmpfile")
+ if [ "$match_result" -ne 4 ]; then
+ RET=$ksft_fail
+ fi
+ log_test "mcast addr notification: Expected 4 matches, got $match_result"
+ return $RET
+}
+
+kci_test_anycast_addr_notification()
+{
+ RET=0
+ local tmpfile
+ local monitor_pid
+ local match_result
+
+ tmpfile=$(mktemp)
+ defer rm "$tmpfile"
+
+ ip monitor acaddress > "$tmpfile" &
+ monitor_pid=$!
+ defer kill_process "$monitor_pid"
+ sleep 1
+
+ if [ ! -e "/proc/$monitor_pid" ]; then
+ RET=$ksft_skip
+ log_test "anycast addr notification: iproute2 too old"
+ return "$RET"
+ fi
+
+ ip link add name "$test_dev" type dummy
+ check_err $? "failed to add dummy interface"
+ ip link set "$test_dev" up
+ check_err $? "failed to set dummy interface up"
+ sysctl -qw net.ipv6.conf."$test_dev".forwarding=1
+ ip link del dev "$test_dev"
+ check_err $? "Failed to delete dummy interface"
+ sleep 1
+
+ # There should be 2 line matches as follows.
+ # 9: dummy2 inet6 any fe80:: scope global
+ # Deleted 9: dummy2 inet6 any fe80:: scope global
+ match_result=$(grep -cE "$test_dev.*(fe80::)" "$tmpfile")
+ if [ "$match_result" -ne 2 ]; then
+ RET=$ksft_fail
+ fi
+ log_test "anycast addr notification: Expected 2 matches, got $match_result"
+ return "$RET"
+}
+
+#check for needed privileges
+if [ "$(id -u)" -ne 0 ];then
+ RET=$ksft_skip
+ log_test "need root privileges"
+ exit $RET
+fi
+
+require_command ip
+
+tests_run
+
+exit $EXIT_STATUS
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/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 "${LOCALSID_TABLE_ID}" prio 999
diff --git a/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh
index 87e414cc417c..4bc135e5c22c 100755
--- a/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh
@@ -245,10 +245,8 @@
# that adopted in the use cases already examined (of course, it is necessary to
# consider the different SIDs/C-SIDs).
-# Kselftest framework requirement - SKIP code is 4.
-readonly ksft_skip=4
+source lib.sh
-readonly RDMSUFF="$(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}-${neigh}"
@@ -630,7 +594,7 @@ setup_rt_local_sids()
dev "${DUMMY_DEVNAME}"
# all SIDs for VPNs start with a common locator. Routes and SRv6
- # Endpoint behavior instaces are grouped together in the 'localsid'
+ # Endpoint behavior instances are grouped together in the 'localsid'
# table.
ip -netns "${nsname}" -6 rule \
add to "${VPN_LOCATOR_SERVICE}::/16" \
@@ -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="$?"
diff --git a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh
index c79cb8ede17f..34b781a2ae74 100755
--- a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh
@@ -72,6 +72,9 @@
# Every fcf0:0:x:y::/64 network interconnects the SRv6 routers rt-x with rt-y in
# the selftest network.
#
+# In addition, every router interface connecting rt-x to rt-y is assigned an
+# IPv6 link-local address fe80::x:y/64.
+#
# Local SID/C-SID table
# =====================
#
@@ -287,10 +290,8 @@
# packet using the SRv6 End.DT46 behavior (associated with the SID fcff:1::d46)
# and sends it to the host hs-1.
-# Kselftest framework requirement - SKIP code is 4.
-readonly ksft_skip=4
+source lib.sh
-readonly RDMSUFF="$(mktemp -u XXXXXXXX)"
readonly DUMMY_DEVNAME="dum0"
readonly VRF_TID=100
readonly VRF_DEVNAME="vrf-${VRF_TID}"
@@ -418,32 +419,18 @@ 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_${hsid}"
}
create_router()
@@ -452,15 +439,12 @@ create_router()
local nsname
nsname="$(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 "${nsname}" sysctl -wq net.ipv4.ip_forward=1
}
@@ -470,29 +454,12 @@ create_host()
local nsname
nsname="$(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 +479,10 @@ 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 +514,7 @@ 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}-${neigh}"
@@ -557,6 +524,9 @@ setup_rt_networking()
ip -netns "${nsname}" addr \
add "${net_prefix}::${rt}/64" dev "${devname}" nodad
+ ip -netns "${nsname}" addr \
+ add "fe80::${rt}:${neigh}/64" dev "${devname}" nodad
+
ip -netns "${nsname}" link set "${devname}" up
done
@@ -631,7 +601,7 @@ 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}")"
@@ -645,12 +615,33 @@ set_end_x_nextcsid()
nflen "${LCNODEFUNC_BLEN}" dev "${DUMMY_DEVNAME}"
}
+set_end_x_ll_nextcsid()
+{
+ local rt="$1"
+ local adj="$2"
+
+ eval nsname=\${$(get_rtname "${rt}")}
+ lcnode_func_prefix="$(build_lcnode_func_prefix "${rt}")"
+ nh6_ll_addr="fe80::${adj}:${rt}"
+ oifname="veth-rt-${rt}-${adj}"
+
+ # enabled NEXT-C-SID SRv6 End.X behavior via an IPv6 link-local nexthop
+ # address (note that "dev" is the dummy dum0 device chosen for the sake
+ # of simplicity).
+ ip -netns "${nsname}" -6 route \
+ replace "${lcnode_func_prefix}" \
+ table "${LOCALSID_TABLE_ID}" \
+ encap seg6local action End.X nh6 "${nh6_ll_addr}" \
+ oif "${oifname}" flavors next-csid lblen "${LCBLOCK_BLEN}" \
+ nflen "${LCNODEFUNC_BLEN}" dev "${DUMMY_DEVNAME}"
+}
+
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}-${neigh}"
@@ -685,12 +676,12 @@ setup_rt_local_sids()
local lcnode_func_prefix
local lcblock_prefix
- nsname="$(get_rtname "${rt}")"
+ eval nsname=\${$(get_rtname "${rt}")}
set_underlay_sids_reachability "${rt}" "${rt_neighs}"
# all SIDs for VPNs start with a common locator. Routes and SRv6
- # Endpoint behavior instaces are grouped together in the 'localsid'
+ # Endpoint behavior instances are grouped together in the 'localsid'
# table.
ip -netns "${nsname}" -6 rule \
add to "${VPN_LOCATOR_SERVICE}::/16" \
@@ -728,8 +719,8 @@ __setup_l3vpn()
local rtsrc_nsname
local rtdst_nsname
- rtsrc_nsname="$(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 +795,8 @@ 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 +842,6 @@ 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 "${rtname}" sh -c "echo 1 > /proc/sys/net/vrf/strict_mode"
}
@@ -947,7 +933,7 @@ check_rt_connectivity()
local prefix
local rtsrc_nsname
- rtsrc_nsname="$(get_rtname "${rtsrc}")"
+ eval rtsrc_nsname=\${$(get_rtname "${rtsrc}")}
prefix="$(get_network_prefix "${rtsrc}" "${rtdst}")"
@@ -970,7 +956,7 @@ 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 +968,7 @@ 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}.${hsdst}" >/dev/null 2>&1
@@ -1057,6 +1043,27 @@ host_vpn_tests()
check_and_log_hs_ipv4_connectivity 1 2
check_and_log_hs_ipv4_connectivity 2 1
+
+ # Setup the adjacencies in the SRv6 aware routers using IPv6 link-local
+ # addresses.
+ # - rt-3 SRv6 End.X adjacency with rt-4
+ # - rt-4 SRv6 End.X adjacency with rt-1
+ set_end_x_ll_nextcsid 3 4
+ set_end_x_ll_nextcsid 4 1
+
+ log_section "SRv6 VPN connectivity test hosts (h1 <-> h2, IPv6), link-local"
+
+ check_and_log_hs_ipv6_connectivity 1 2
+ check_and_log_hs_ipv6_connectivity 2 1
+
+ log_section "SRv6 VPN connectivity test hosts (h1 <-> h2, IPv4), link-local"
+
+ check_and_log_hs_ipv4_connectivity 1 2
+ check_and_log_hs_ipv4_connectivity 2 1
+
+ # Restore the previous adjacencies.
+ set_end_x_nextcsid 3 4
+ set_end_x_nextcsid 4 1
}
__nextcsid_end_x_behavior_test()
@@ -1093,7 +1100,7 @@ rt_x_nextcsid_end_x_behavior_test()
local nsname
local ret
- nsname="$(get_rtname "${rt}")"
+ eval nsname=\${$(get_rtname "${rt}")}
__nextcsid_end_x_behavior_test "${nsname}" "add" "${blen}" "${flen}"
ret="$?"
diff --git a/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh b/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh
index 28a775654b92..6a68c7eff1dc 100755
--- a/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh
@@ -166,10 +166,8 @@
# hs-4->hs-3 |IPv6 DA=fcff:1::e|SRH SIDs=fcff:3::d46|IPv6|...| (i.d)
#
-# Kselftest framework requirement - SKIP code is 4.
-readonly ksft_skip=4
+source lib.sh
-readonly RDMSUFF="$(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}-${neigh}"
@@ -432,7 +395,7 @@ setup_rt_local_sids()
dev "${VRF_DEVNAME}"
# all SIDs for VPNs start with a common locator. Routes and SRv6
- # Endpoint behavior instaces are grouped together in the 'localsid'
+ # Endpoint behavior instances are grouped together in the 'localsid'
# table.
ip -netns "${nsname}" -6 rule \
add to "${VPN_LOCATOR_SERVICE}::/16" \
@@ -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}.${hsdst}" >/dev/null 2>&1
diff --git a/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh b/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh
index cb4177d41b21..0979b5316fdf 100755
--- a/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh
@@ -116,10 +116,8 @@
# hs-2->hs-1 |IPv6 DA=fcff:4::e|SRH SIDs=fcff:3::e,fcff:1::d2|eth|...| (i.b)
#
-# Kselftest framework requirement - SKIP code is 4.
-readonly ksft_skip=4
+source lib.sh
-readonly RDMSUFF="$(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}-${neigh}"
@@ -379,7 +343,7 @@ setup_rt_local_sids()
encap seg6local action End dev "${DUMMY_DEVNAME}"
# all SIDs for VPNs start with a common locator. Routes and SRv6
- # Endpoint behaviors instaces are grouped together in the 'localsid'
+ # Endpoint behaviors instances are grouped together in the 'localsid'
# table.
ip -netns "${nsname}" -6 rule add \
to "${VPN_LOCATOR_SERVICE}::/16" \
@@ -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/self-connect.c b/tools/testing/selftests/net/tcp_ao/self-connect.c
index 73b2f2276f3f..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)
diff --git a/tools/testing/selftests/net/tcp_ao/seq-ext.c b/tools/testing/selftests/net/tcp_ao/seq-ext.c
index f00245263b20..6478da6a71c3 100644
--- a/tools/testing/selftests/net/tcp_ao/seq-ext.c
+++ b/tools/testing/selftests/net/tcp_ao/seq-ext.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
/* Check that after SEQ number wrap-around:
* 1. SEQ-extension has upper bytes set
- * 2. TCP conneciton is alive and no TCPAOBad segments
+ * 2. TCP connection is alive and no TCPAOBad segments
* In order to test (2), the test doesn't just adjust seq number for a queue
* on a connected socket, but migrates it to another sk+port number, so
* that there won't be any delayed packets that will fail to verify
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_neigh.sh b/tools/testing/selftests/net/test_neigh.sh
new file mode 100755
index 000000000000..388056472b5b
--- /dev/null
+++ b/tools/testing/selftests/net/test_neigh.sh
@@ -0,0 +1,366 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source lib.sh
+TESTS="
+ extern_valid_ipv4
+ extern_valid_ipv6
+"
+VERBOSE=0
+
+################################################################################
+# Utilities
+
+run_cmd()
+{
+ local cmd="$1"
+ local out
+ local stderr="2>/dev/null"
+
+ if [ "$VERBOSE" = "1" ]; then
+ echo "COMMAND: $cmd"
+ stderr=
+ fi
+
+ out=$(eval "$cmd" "$stderr")
+ rc=$?
+ if [ "$VERBOSE" -eq 1 ] && [ -n "$out" ]; then
+ echo " $out"
+ fi
+
+ return $rc
+}
+
+################################################################################
+# Setup
+
+setup()
+{
+ set -e
+
+ setup_ns ns1 ns2
+
+ ip -n "$ns1" link add veth0 type veth peer name veth1 netns "$ns2"
+ ip -n "$ns1" link set dev veth0 up
+ ip -n "$ns2" link set dev veth1 up
+
+ ip -n "$ns1" address add 192.0.2.1/24 dev veth0
+ ip -n "$ns1" address add 2001:db8:1::1/64 dev veth0 nodad
+ ip -n "$ns2" address add 192.0.2.2/24 dev veth1
+ ip -n "$ns2" address add 2001:db8:1::2/64 dev veth1 nodad
+
+ ip netns exec "$ns1" sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1
+ ip netns exec "$ns2" sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1
+
+ sleep 5
+
+ set +e
+}
+
+exit_cleanup_all()
+{
+ cleanup_all_ns
+ exit "${EXIT_STATUS}"
+}
+
+################################################################################
+# Tests
+
+extern_valid_common()
+{
+ local af_str=$1; shift
+ local ip_addr=$1; shift
+ local tbl_name=$1; shift
+ local subnet=$1; shift
+ local mac
+
+ mac=$(ip -n "$ns2" -j link show dev veth1 | jq -r '.[]["address"]')
+
+ RET=0
+
+ # Check that simple addition works.
+ run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid"
+ run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\""
+ check_err $? "No \"extern_valid\" flag after addition"
+
+ log_test "$af_str \"extern_valid\" flag: Add entry"
+
+ RET=0
+
+ # Check that an entry cannot be added with "extern_valid" flag and an
+ # invalid state.
+ run_cmd "ip -n $ns1 neigh flush dev veth0"
+ run_cmd "ip -n $ns1 neigh add $ip_addr nud none dev veth0 extern_valid"
+ check_fail $? "Managed to add an entry with \"extern_valid\" flag and an invalid state"
+
+ log_test "$af_str \"extern_valid\" flag: Add with an invalid state"
+
+ RET=0
+
+ # Check that entry cannot be added with both "extern_valid" flag and
+ # "use" / "managed" flag.
+ run_cmd "ip -n $ns1 neigh flush dev veth0"
+ run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid use"
+ check_fail $? "Managed to add an entry with \"extern_valid\" flag and \"use\" flag"
+
+ log_test "$af_str \"extern_valid\" flag: Add with \"use\" flag"
+
+ RET=0
+
+ # Check that "extern_valid" flag can be toggled using replace.
+ run_cmd "ip -n $ns1 neigh flush dev veth0"
+ run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0"
+ run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0 extern_valid"
+ run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\""
+ check_err $? "Did not manage to set \"extern_valid\" flag with replace"
+ run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0"
+ run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\""
+ check_fail $? "Did not manage to clear \"extern_valid\" flag with replace"
+
+ log_test "$af_str \"extern_valid\" flag: Replace entry"
+
+ RET=0
+
+ # Check that an existing "extern_valid" entry can be marked as
+ # "managed".
+ run_cmd "ip -n $ns1 neigh flush dev veth0"
+ run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid"
+ run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0 extern_valid managed"
+ check_err $? "Did not manage to add \"managed\" flag to an existing \"extern_valid\" entry"
+
+ log_test "$af_str \"extern_valid\" flag: Replace entry with \"managed\" flag"
+
+ RET=0
+
+ # Check that entry cannot be replaced with "extern_valid" flag and an
+ # invalid state.
+ run_cmd "ip -n $ns1 neigh flush dev veth0"
+ run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid"
+ run_cmd "ip -n $ns1 neigh replace $ip_addr nud none dev veth0 extern_valid"
+ check_fail $? "Managed to replace an entry with \"extern_valid\" flag and an invalid state"
+
+ log_test "$af_str \"extern_valid\" flag: Replace with an invalid state"
+
+ RET=0
+
+ # Check that an "extern_valid" entry is flushed when the interface is
+ # put administratively down.
+ run_cmd "ip -n $ns1 neigh flush dev veth0"
+ run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid"
+ run_cmd "ip -n $ns1 link set dev veth0 down"
+ run_cmd "ip -n $ns1 link set dev veth0 up"
+ run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0"
+ check_fail $? "\"extern_valid\" entry not flushed upon interface down"
+
+ log_test "$af_str \"extern_valid\" flag: Interface down"
+
+ RET=0
+
+ # Check that an "extern_valid" entry is not flushed when the interface
+ # loses its carrier.
+ run_cmd "ip -n $ns1 neigh flush dev veth0"
+ run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid"
+ run_cmd "ip -n $ns2 link set dev veth1 down"
+ run_cmd "ip -n $ns2 link set dev veth1 up"
+ run_cmd "sleep 2"
+ run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0"
+ check_err $? "\"extern_valid\" entry flushed upon carrier down"
+
+ log_test "$af_str \"extern_valid\" flag: Carrier down"
+
+ RET=0
+
+ # Check that when entry transitions to "reachable" state it maintains
+ # the "extern_valid" flag. Wait "delay_probe" seconds for ARP request /
+ # NS to be sent.
+ local delay_probe
+
+ delay_probe=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["delay_probe"]')
+ run_cmd "ip -n $ns1 neigh flush dev veth0"
+ run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid"
+ run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0 extern_valid use"
+ run_cmd "sleep $((delay_probe / 1000 + 2))"
+ run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"REACHABLE\""
+ check_err $? "Entry did not transition to \"reachable\" state"
+ run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\""
+ check_err $? "Entry did not maintain \"extern_valid\" flag after transition to \"reachable\" state"
+
+ log_test "$af_str \"extern_valid\" flag: Transition to \"reachable\" state"
+
+ RET=0
+
+ # Drop all packets, trigger resolution and check that entry goes back
+ # to "stale" state instead of "failed".
+ local mcast_reprobes
+ local retrans_time
+ local ucast_probes
+ local app_probes
+ local probes
+ local delay
+
+ run_cmd "ip -n $ns1 neigh flush dev veth0"
+ run_cmd "tc -n $ns2 qdisc add dev veth1 clsact"
+ run_cmd "tc -n $ns2 filter add dev veth1 ingress proto all matchall action drop"
+ run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid"
+ run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0 extern_valid use"
+ retrans_time=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["retrans"]')
+ ucast_probes=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["ucast_probes"]')
+ app_probes=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["app_probes"]')
+ mcast_reprobes=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["mcast_reprobes"]')
+ delay=$((delay_probe + (ucast_probes + app_probes + mcast_reprobes) * retrans_time))
+ run_cmd "sleep $((delay / 1000 + 2))"
+ run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"STALE\""
+ check_err $? "Entry did not return to \"stale\" state"
+ run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\""
+ check_err $? "Entry did not maintain \"extern_valid\" flag after returning to \"stale\" state"
+ probes=$(ip -n "$ns1" -j -s neigh get "$ip_addr" dev veth0 | jq '.[]["probes"]')
+ if [[ $probes -eq 0 ]]; then
+ check_err 1 "No probes were sent"
+ fi
+
+ log_test "$af_str \"extern_valid\" flag: Transition back to \"stale\" state"
+
+ run_cmd "tc -n $ns2 qdisc del dev veth1 clsact"
+
+ RET=0
+
+ # Forced garbage collection runs whenever the number of entries is
+ # larger than "thresh3" and deletes stale entries that have not been
+ # updated in the last 5 seconds.
+ #
+ # Check that an "extern_valid" entry survives a forced garbage
+ # collection. Add an entry, wait 5 seconds and add more entries than
+ # "thresh3" so that forced garbage collection will run.
+ #
+ # Note that the garbage collection thresholds are global resources and
+ # that changes in the initial namespace affect all the namespaces.
+ local forced_gc_runs_t0
+ local forced_gc_runs_t1
+ local orig_thresh1
+ local orig_thresh2
+ local orig_thresh3
+
+ run_cmd "ip -n $ns1 neigh flush dev veth0"
+ orig_thresh1=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh1")) | .["thresh1"]')
+ orig_thresh2=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh2")) | .["thresh2"]')
+ orig_thresh3=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh3")) | .["thresh3"]')
+ run_cmd "ip ntable change name $tbl_name thresh3 10 thresh2 9 thresh1 8"
+ run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid"
+ run_cmd "ip -n $ns1 neigh add ${subnet}3 lladdr $mac nud stale dev veth0"
+ run_cmd "sleep 5"
+ forced_gc_runs_t0=$(ip -j -s ntable show name "$tbl_name" | jq '.[] | select(has("forced_gc_runs")) | .["forced_gc_runs"]')
+ for i in {1..20}; do
+ run_cmd "ip -n $ns1 neigh add ${subnet}$((i + 4)) nud none dev veth0"
+ done
+ forced_gc_runs_t1=$(ip -j -s ntable show name "$tbl_name" | jq '.[] | select(has("forced_gc_runs")) | .["forced_gc_runs"]')
+ if [[ $forced_gc_runs_t1 -eq $forced_gc_runs_t0 ]]; then
+ check_err 1 "Forced garbage collection did not run"
+ fi
+ run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\""
+ check_err $? "Entry with \"extern_valid\" flag did not survive forced garbage collection"
+ run_cmd "ip -n $ns1 neigh get ${subnet}3 dev veth0"
+ check_fail $? "Entry without \"extern_valid\" flag survived forced garbage collection"
+
+ log_test "$af_str \"extern_valid\" flag: Forced garbage collection"
+
+ run_cmd "ip ntable change name $tbl_name thresh3 $orig_thresh3 thresh2 $orig_thresh2 thresh1 $orig_thresh1"
+
+ RET=0
+
+ # Periodic garbage collection runs every "base_reachable"/2 seconds and
+ # if the number of entries is larger than "thresh1", then it deletes
+ # stale entries that have not been used in the last "gc_stale" seconds.
+ #
+ # Check that an "extern_valid" entry survives a periodic garbage
+ # collection. Add an "extern_valid" entry, add more than "thresh1"
+ # regular entries, wait "base_reachable" (longer than "gc_stale")
+ # seconds and check that the "extern_valid" entry was not deleted.
+ #
+ # Note that the garbage collection thresholds and "base_reachable" are
+ # global resources and that changes in the initial namespace affect all
+ # the namespaces.
+ local periodic_gc_runs_t0
+ local periodic_gc_runs_t1
+ local orig_base_reachable
+ local orig_gc_stale
+
+ run_cmd "ip -n $ns1 neigh flush dev veth0"
+ orig_thresh1=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh1")) | .["thresh1"]')
+ orig_base_reachable=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh1")) | .["base_reachable"]')
+ run_cmd "ip ntable change name $tbl_name thresh1 10 base_reachable 10000"
+ orig_gc_stale=$(ip -n "$ns1" -j ntable show name "$tbl_name" dev veth0 | jq '.[]["gc_stale"]')
+ run_cmd "ip -n $ns1 ntable change name $tbl_name dev veth0 gc_stale 5000"
+ # Wait orig_base_reachable/2 for the new interval to take effect.
+ run_cmd "sleep $(((orig_base_reachable / 1000) / 2 + 2))"
+ run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid"
+ run_cmd "ip -n $ns1 neigh add ${subnet}3 lladdr $mac nud stale dev veth0"
+ for i in {1..20}; do
+ run_cmd "ip -n $ns1 neigh add ${subnet}$((i + 4)) nud none dev veth0"
+ done
+ periodic_gc_runs_t0=$(ip -j -s ntable show name "$tbl_name" | jq '.[] | select(has("periodic_gc_runs")) | .["periodic_gc_runs"]')
+ run_cmd "sleep 10"
+ periodic_gc_runs_t1=$(ip -j -s ntable show name "$tbl_name" | jq '.[] | select(has("periodic_gc_runs")) | .["periodic_gc_runs"]')
+ [[ $periodic_gc_runs_t1 -ne $periodic_gc_runs_t0 ]]
+ check_err $? "Periodic garbage collection did not run"
+ run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\""
+ check_err $? "Entry with \"extern_valid\" flag did not survive periodic garbage collection"
+ run_cmd "ip -n $ns1 neigh get ${subnet}3 dev veth0"
+ check_fail $? "Entry without \"extern_valid\" flag survived periodic garbage collection"
+
+ log_test "$af_str \"extern_valid\" flag: Periodic garbage collection"
+
+ run_cmd "ip -n $ns1 ntable change name $tbl_name dev veth0 gc_stale $orig_gc_stale"
+ run_cmd "ip ntable change name $tbl_name thresh1 $orig_thresh1 base_reachable $orig_base_reachable"
+}
+
+extern_valid_ipv4()
+{
+ extern_valid_common "IPv4" 192.0.2.2 "arp_cache" 192.0.2.
+}
+
+extern_valid_ipv6()
+{
+ extern_valid_common "IPv6" 2001:db8:1::2 "ndisc_cache" 2001:db8:1::
+}
+
+################################################################################
+# Usage
+
+usage()
+{
+ cat <<EOF
+usage: ${0##*/} OPTS
+
+ -t <test> Test(s) to run (default: all)
+ (options: $TESTS)
+ -p Pause on fail
+ -v Verbose mode (show commands and output)
+EOF
+}
+
+################################################################################
+# Main
+
+while getopts ":t:pvh" opt; do
+ case $opt in
+ t) TESTS=$OPTARG;;
+ p) PAUSE_ON_FAIL=yes;;
+ v) VERBOSE=$((VERBOSE + 1));;
+ h) usage; exit 0;;
+ *) usage; exit 1;;
+ esac
+done
+
+require_command jq
+
+if ! ip neigh help 2>&1 | grep -q "extern_valid"; then
+ echo "SKIP: iproute2 ip too old, missing \"extern_valid\" support"
+ exit "$ksft_skip"
+fi
+
+trap exit_cleanup_all EXIT
+
+for t in $TESTS
+do
+ setup; $t; cleanup_all_ns;
+done
diff --git a/tools/testing/selftests/net/test_vxlan_vnifiltering.sh b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh
index 6127a78ee988..8deacc565afa 100755
--- a/tools/testing/selftests/net/test_vxlan_vnifiltering.sh
+++ b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh
@@ -146,18 +146,17 @@ run_cmd()
}
check_hv_connectivity() {
- ip netns exec $hv_1 ping -c 1 -W 1 $1 &>/dev/null
- sleep 1
- ip netns exec $hv_1 ping -c 1 -W 1 $2 &>/dev/null
+ slowwait 5 ip netns exec $hv_1 ping -c 1 -W 1 $1 &>/dev/null
+ slowwait 5 ip netns exec $hv_1 ping -c 1 -W 1 $2 &>/dev/null
return $?
}
check_vm_connectivity() {
- run_cmd "ip netns exec $vm_11 ping -c 1 -W 1 10.0.10.12"
+ slowwait 5 run_cmd "ip netns exec $vm_11 ping -c 1 -W 1 10.0.10.12"
log_test $? 0 "VM connectivity over $1 (ipv4 default rdst)"
- run_cmd "ip netns exec $vm_21 ping -c 1 -W 1 10.0.10.22"
+ slowwait 5 run_cmd "ip netns exec $vm_21 ping -c 1 -W 1 10.0.10.22"
log_test $? 0 "VM connectivity over $1 (ipv6 default rdst)"
}
diff --git a/tools/testing/selftests/net/tfo.c b/tools/testing/selftests/net/tfo.c
new file mode 100644
index 000000000000..eb3cac5e583c
--- /dev/null
+++ b/tools/testing/selftests/net/tfo.c
@@ -0,0 +1,171 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <error.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <arpa/inet.h>
+#include <sys/socket.h>
+#include <netinet/tcp.h>
+#include <errno.h>
+
+static int cfg_server;
+static int cfg_client;
+static int cfg_port = 8000;
+static struct sockaddr_in6 cfg_addr;
+static char *cfg_outfile;
+
+static int parse_address(const char *str, int port, struct sockaddr_in6 *sin6)
+{
+ int ret;
+
+ sin6->sin6_family = AF_INET6;
+ sin6->sin6_port = htons(port);
+
+ ret = inet_pton(sin6->sin6_family, str, &sin6->sin6_addr);
+ if (ret != 1) {
+ /* fallback to plain IPv4 */
+ ret = inet_pton(AF_INET, str, &sin6->sin6_addr.s6_addr32[3]);
+ if (ret != 1)
+ return -1;
+
+ /* add ::ffff prefix */
+ sin6->sin6_addr.s6_addr32[0] = 0;
+ sin6->sin6_addr.s6_addr32[1] = 0;
+ sin6->sin6_addr.s6_addr16[4] = 0;
+ sin6->sin6_addr.s6_addr16[5] = 0xffff;
+ }
+
+ return 0;
+}
+
+static void run_server(void)
+{
+ unsigned long qlen = 32;
+ int fd, opt, connfd;
+ socklen_t len;
+ char buf[64];
+ FILE *outfile;
+
+ outfile = fopen(cfg_outfile, "w");
+ if (!outfile)
+ error(1, errno, "fopen() outfile");
+
+ fd = socket(AF_INET6, SOCK_STREAM, 0);
+ if (fd == -1)
+ error(1, errno, "socket()");
+
+ opt = 1;
+ if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt)) < 0)
+ error(1, errno, "setsockopt(SO_REUSEADDR)");
+
+ if (setsockopt(fd, SOL_TCP, TCP_FASTOPEN, &qlen, sizeof(qlen)) < 0)
+ error(1, errno, "setsockopt(TCP_FASTOPEN)");
+
+ if (bind(fd, (struct sockaddr *)&cfg_addr, sizeof(cfg_addr)) < 0)
+ error(1, errno, "bind()");
+
+ if (listen(fd, 5) < 0)
+ error(1, errno, "listen()");
+
+ len = sizeof(cfg_addr);
+ connfd = accept(fd, (struct sockaddr *)&cfg_addr, &len);
+ if (connfd < 0)
+ error(1, errno, "accept()");
+
+ len = sizeof(opt);
+ if (getsockopt(connfd, SOL_SOCKET, SO_INCOMING_NAPI_ID, &opt, &len) < 0)
+ error(1, errno, "getsockopt(SO_INCOMING_NAPI_ID)");
+
+ read(connfd, buf, 64);
+ fprintf(outfile, "%d\n", opt);
+
+ fclose(outfile);
+ close(connfd);
+ close(fd);
+}
+
+static void run_client(void)
+{
+ int fd;
+ char *msg = "Hello, world!";
+
+ fd = socket(AF_INET6, SOCK_STREAM, 0);
+ if (fd == -1)
+ error(1, errno, "socket()");
+
+ sendto(fd, msg, strlen(msg), MSG_FASTOPEN, (struct sockaddr *)&cfg_addr, sizeof(cfg_addr));
+
+ close(fd);
+}
+
+static void usage(const char *filepath)
+{
+ error(1, 0, "Usage: %s (-s|-c) -h<server_ip> -p<port> -o<outfile> ", filepath);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ struct sockaddr_in6 *addr6 = (void *) &cfg_addr;
+ char *addr = NULL;
+ int ret;
+ int c;
+
+ if (argc <= 1)
+ usage(argv[0]);
+
+ while ((c = getopt(argc, argv, "sch:p:o:")) != -1) {
+ switch (c) {
+ case 's':
+ if (cfg_client)
+ error(1, 0, "Pass one of -s or -c");
+ cfg_server = 1;
+ break;
+ case 'c':
+ if (cfg_server)
+ error(1, 0, "Pass one of -s or -c");
+ cfg_client = 1;
+ break;
+ case 'h':
+ addr = optarg;
+ break;
+ case 'p':
+ cfg_port = strtoul(optarg, NULL, 0);
+ break;
+ case 'o':
+ cfg_outfile = strdup(optarg);
+ if (!cfg_outfile)
+ error(1, 0, "outfile invalid");
+ break;
+ }
+ }
+
+ if (cfg_server && addr)
+ error(1, 0, "Server cannot have -h specified");
+
+ memset(addr6, 0, sizeof(*addr6));
+ addr6->sin6_family = AF_INET6;
+ addr6->sin6_port = htons(cfg_port);
+ addr6->sin6_addr = in6addr_any;
+ if (addr) {
+ ret = parse_address(addr, cfg_port, addr6);
+ if (ret)
+ error(1, 0, "Client address parse error: %s", addr);
+ }
+}
+
+int main(int argc, char **argv)
+{
+ parse_opts(argc, argv);
+
+ if (cfg_server)
+ run_server();
+ else if (cfg_client)
+ run_client();
+
+ return 0;
+}
diff --git a/tools/testing/selftests/net/tfo_passive.sh b/tools/testing/selftests/net/tfo_passive.sh
new file mode 100755
index 000000000000..80bf11fdc046
--- /dev/null
+++ b/tools/testing/selftests/net/tfo_passive.sh
@@ -0,0 +1,112 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+source lib.sh
+
+NSIM_SV_ID=$((256 + RANDOM % 256))
+NSIM_SV_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_SV_ID
+NSIM_CL_ID=$((512 + RANDOM % 256))
+NSIM_CL_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_CL_ID
+
+NSIM_DEV_SYS_NEW=/sys/bus/netdevsim/new_device
+NSIM_DEV_SYS_DEL=/sys/bus/netdevsim/del_device
+NSIM_DEV_SYS_LINK=/sys/bus/netdevsim/link_device
+NSIM_DEV_SYS_UNLINK=/sys/bus/netdevsim/unlink_device
+
+SERVER_IP=192.168.1.1
+CLIENT_IP=192.168.1.2
+SERVER_PORT=48675
+
+setup_ns()
+{
+ set -e
+ ip netns add nssv
+ ip netns add nscl
+
+ NSIM_SV_NAME=$(find $NSIM_SV_SYS/net -maxdepth 1 -type d ! \
+ -path $NSIM_SV_SYS/net -exec basename {} \;)
+ NSIM_CL_NAME=$(find $NSIM_CL_SYS/net -maxdepth 1 -type d ! \
+ -path $NSIM_CL_SYS/net -exec basename {} \;)
+
+ ip link set $NSIM_SV_NAME netns nssv
+ ip link set $NSIM_CL_NAME netns nscl
+
+ ip netns exec nssv ip addr add "${SERVER_IP}/24" dev $NSIM_SV_NAME
+ ip netns exec nscl ip addr add "${CLIENT_IP}/24" dev $NSIM_CL_NAME
+
+ ip netns exec nssv ip link set dev $NSIM_SV_NAME up
+ ip netns exec nscl ip link set dev $NSIM_CL_NAME up
+
+ # Enable passive TFO
+ ip netns exec nssv sysctl -w net.ipv4.tcp_fastopen=519 > /dev/null
+
+ set +e
+}
+
+cleanup_ns()
+{
+ ip netns del nscl
+ ip netns del nssv
+}
+
+###
+### Code start
+###
+
+modprobe netdevsim
+
+# linking
+
+echo $NSIM_SV_ID > $NSIM_DEV_SYS_NEW
+echo $NSIM_CL_ID > $NSIM_DEV_SYS_NEW
+udevadm settle
+
+setup_ns
+
+NSIM_SV_FD=$((256 + RANDOM % 256))
+exec {NSIM_SV_FD}</var/run/netns/nssv
+NSIM_SV_IFIDX=$(ip netns exec nssv cat /sys/class/net/$NSIM_SV_NAME/ifindex)
+
+NSIM_CL_FD=$((256 + RANDOM % 256))
+exec {NSIM_CL_FD}</var/run/netns/nscl
+NSIM_CL_IFIDX=$(ip netns exec nscl cat /sys/class/net/$NSIM_CL_NAME/ifindex)
+
+echo "$NSIM_SV_FD:$NSIM_SV_IFIDX $NSIM_CL_FD:$NSIM_CL_IFIDX" > \
+ $NSIM_DEV_SYS_LINK
+
+if [ $? -ne 0 ]; then
+ echo "linking netdevsim1 with netdevsim2 should succeed"
+ cleanup_ns
+ exit 1
+fi
+
+out_file=$(mktemp)
+
+timeout -k 1s 30s ip netns exec nssv ./tfo \
+ -s \
+ -p ${SERVER_PORT} \
+ -o ${out_file}&
+
+wait_local_port_listen nssv ${SERVER_PORT} tcp
+
+ip netns exec nscl ./tfo -c -h ${SERVER_IP} -p ${SERVER_PORT}
+
+wait
+
+res=$(cat $out_file)
+rm $out_file
+
+if [ $res -eq 0 ]; then
+ echo "got invalid NAPI ID from passive TFO socket"
+ cleanup_ns
+ exit 1
+fi
+
+echo "$NSIM_SV_FD:$NSIM_SV_IFIDX" > $NSIM_DEV_SYS_UNLINK
+
+echo $NSIM_CL_ID > $NSIM_DEV_SYS_DEL
+
+cleanup_ns
+
+modprobe -r netdevsim
+
+exit 0
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 9a85f93c33d8..5ded3b3a7538 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -1753,6 +1753,42 @@ TEST_F(tls_basic, rekey_tx)
EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
}
+TEST_F(tls_basic, disconnect)
+{
+ char const *test_str = "test_message";
+ int send_len = strlen(test_str) + 1;
+ struct tls_crypto_info_keys key;
+ struct sockaddr_in addr;
+ char buf[20];
+ int ret;
+
+ if (self->notls)
+ return;
+
+ tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128,
+ &key, 0);
+
+ ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &key, key.len);
+ ASSERT_EQ(ret, 0);
+
+ /* Pre-queue the data so that setsockopt parses it but doesn't
+ * dequeue it from the TCP socket. recvmsg would dequeue.
+ */
+ EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+
+ ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &key, key.len);
+ ASSERT_EQ(ret, 0);
+
+ addr.sin_family = AF_UNSPEC;
+ addr.sin_addr.s_addr = htonl(INADDR_ANY);
+ addr.sin_port = 0;
+ ret = connect(self->cfd, &addr, sizeof(addr));
+ EXPECT_EQ(ret, -1);
+ EXPECT_EQ(errno, EOPNOTSUPP);
+
+ EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+}
+
TEST_F(tls, rekey)
{
char const *test_str_1 = "test_message_before_rekey";
diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
index d5ffd8c9172e..b17e032a6d75 100755
--- a/tools/testing/selftests/net/udpgro.sh
+++ b/tools/testing/selftests/net/udpgro.sh
@@ -3,7 +3,7 @@
#
# Run a series of udpgro functional tests.
-source net_helper.sh
+source lib.sh
readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
@@ -48,7 +48,7 @@ run_one() {
cfg_veth
- ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} &
+ ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 100 ${rx_args} &
local PID1=$!
wait_local_port_listen ${PEER_NS} 8000 udp
@@ -95,7 +95,7 @@ run_one_nat() {
# will land on the 'plain' one
ip netns exec "${PEER_NS}" ./udpgso_bench_rx -G ${family} -b ${addr1} -n 0 &
local PID1=$!
- ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${family} -b ${addr2%/*} ${rx_args} &
+ ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 100 ${family} -b ${addr2%/*} ${rx_args} &
local PID2=$!
wait_local_port_listen "${PEER_NS}" 8000 udp
@@ -117,9 +117,9 @@ run_one_2sock() {
cfg_veth
- ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} -p 12345 &
+ ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 100 ${rx_args} -p 12345 &
local PID1=$!
- ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 10 ${rx_args} &
+ ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 100 ${rx_args} &
local PID2=$!
wait_local_port_listen "${PEER_NS}" 12345 udp
diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh
index 815fad8c53a8..54fa4821bc5e 100755
--- a/tools/testing/selftests/net/udpgro_bench.sh
+++ b/tools/testing/selftests/net/udpgro_bench.sh
@@ -3,7 +3,7 @@
#
# Run a series of udpgro benchmarks
-source net_helper.sh
+source lib.sh
readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh
index 5f3d1a110d11..9a2cfec1153e 100755
--- a/tools/testing/selftests/net/udpgro_frglist.sh
+++ b/tools/testing/selftests/net/udpgro_frglist.sh
@@ -3,7 +3,7 @@
#
# Run a series of udpgro benchmarks
-source net_helper.sh
+source lib.sh
readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
index f22f6c66997e..a39fdc4aa2ff 100755
--- a/tools/testing/selftests/net/udpgro_fwd.sh
+++ b/tools/testing/selftests/net/udpgro_fwd.sh
@@ -1,7 +1,7 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
-source net_helper.sh
+source lib.sh
BPF_FILE="lib/xdp_dummy.bpf.o"
readonly BASE="ns-$(mktemp -u XXXXXX)"
diff --git a/tools/testing/selftests/net/vlan_hw_filter.sh b/tools/testing/selftests/net/vlan_hw_filter.sh
index 7bc804ffaf7c..0fb56baf28e4 100755
--- a/tools/testing/selftests/net/vlan_hw_filter.sh
+++ b/tools/testing/selftests/net/vlan_hw_filter.sh
@@ -3,27 +3,101 @@
readonly NETNS="ns-$(mktemp -u XXXXXX)"
+ALL_TESTS="
+ test_vlan_filter_check
+ test_vlan0_del_crash_01
+ test_vlan0_del_crash_02
+ test_vlan0_del_crash_03
+ test_vid0_memleak
+"
+
ret=0
+setup() {
+ ip netns add ${NETNS}
+}
+
cleanup() {
- ip netns del $NETNS
+ ip netns del $NETNS 2>/dev/null
}
trap cleanup EXIT
fail() {
- echo "ERROR: ${1:-unexpected return code} (ret: $_)" >&2
- ret=1
+ echo "ERROR: ${1:-unexpected return code} (ret: $_)" >&2
+ ret=1
+}
+
+tests_run()
+{
+ local current_test
+ for current_test in ${TESTS:-$ALL_TESTS}; do
+ $current_test
+ done
+}
+
+test_vlan_filter_check() {
+ setup
+ ip netns exec ${NETNS} ip link add bond0 type bond mode 0
+ ip netns exec ${NETNS} ip link add bond_slave_1 type veth peer veth2
+ ip netns exec ${NETNS} ip link set bond_slave_1 master bond0
+ ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter off
+ ip netns exec ${NETNS} ip link add link bond_slave_1 name bond_slave_1.0 type vlan id 0
+ ip netns exec ${NETNS} ip link add link bond0 name bond0.0 type vlan id 0
+ ip netns exec ${NETNS} ip link set bond_slave_1 nomaster
+ ip netns exec ${NETNS} ip link del veth2 || fail "Please check vlan HW filter function"
+ cleanup
}
-ip netns add ${NETNS}
-ip netns exec ${NETNS} ip link add bond0 type bond mode 0
-ip netns exec ${NETNS} ip link add bond_slave_1 type veth peer veth2
-ip netns exec ${NETNS} ip link set bond_slave_1 master bond0
-ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter off
-ip netns exec ${NETNS} ip link add link bond_slave_1 name bond_slave_1.0 type vlan id 0
-ip netns exec ${NETNS} ip link add link bond0 name bond0.0 type vlan id 0
-ip netns exec ${NETNS} ip link set bond_slave_1 nomaster
-ip netns exec ${NETNS} ip link del veth2 || fail "Please check vlan HW filter function"
+#enable vlan_filter feature of real_dev with vlan0 during running time
+test_vlan0_del_crash_01() {
+ setup
+ ip netns exec ${NETNS} ip link add bond0 type bond mode 0
+ ip netns exec ${NETNS} ip link add link bond0 name vlan0 type vlan id 0 protocol 802.1q
+ ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter off
+ ip netns exec ${NETNS} ifconfig bond0 up
+ ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter on
+ ip netns exec ${NETNS} ifconfig bond0 down
+ ip netns exec ${NETNS} ifconfig bond0 up
+ ip netns exec ${NETNS} ip link del vlan0 || fail "Please check vlan HW filter function"
+ cleanup
+}
+
+#enable vlan_filter feature and add vlan0 for real_dev during running time
+test_vlan0_del_crash_02() {
+ setup
+ ip netns exec ${NETNS} ip link add bond0 type bond mode 0
+ ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter off
+ ip netns exec ${NETNS} ifconfig bond0 up
+ ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter on
+ ip netns exec ${NETNS} ip link add link bond0 name vlan0 type vlan id 0 protocol 802.1q
+ ip netns exec ${NETNS} ifconfig bond0 down
+ ip netns exec ${NETNS} ifconfig bond0 up
+ ip netns exec ${NETNS} ip link del vlan0 || fail "Please check vlan HW filter function"
+ cleanup
+}
+
+#enable vlan_filter feature of real_dev during running time
+#test kernel_bug of vlan unregister
+test_vlan0_del_crash_03() {
+ setup
+ ip netns exec ${NETNS} ip link add bond0 type bond mode 0
+ ip netns exec ${NETNS} ip link add link bond0 name vlan0 type vlan id 0 protocol 802.1q
+ ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter off
+ ip netns exec ${NETNS} ifconfig bond0 up
+ ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter on
+ ip netns exec ${NETNS} ifconfig bond0 down
+ ip netns exec ${NETNS} ip link del vlan0 || fail "Please check vlan HW filter function"
+ cleanup
+}
+
+test_vid0_memleak() {
+ setup
+ ip netns exec ${NETNS} ip link add bond0 up type bond mode 0
+ ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter off
+ ip netns exec ${NETNS} ip link del dev bond0 || fail "Please check vlan HW filter function"
+ cleanup
+}
+tests_run
exit $ret
diff --git a/tools/testing/selftests/net/vrf_route_leaking.sh b/tools/testing/selftests/net/vrf_route_leaking.sh
index e9c2f71da207..ce34cb2e6e0b 100755
--- a/tools/testing/selftests/net/vrf_route_leaking.sh
+++ b/tools/testing/selftests/net/vrf_route_leaking.sh
@@ -275,7 +275,7 @@ setup_sym()
# Wait for ip config to settle
- sleep 2
+ slowwait 5 ip netns exec $h1 "${ping6}" -c1 -w1 ${H2_N2_IP6} >/dev/null 2>&1
}
setup_asym()
@@ -370,7 +370,7 @@ setup_asym()
ip -netns $r2 -6 addr add dev eth1 ${R2_N2_IP6}/64 nodad
# Wait for ip config to settle
- sleep 2
+ slowwait 5 ip netns exec $h1 "${ping6}" -c1 -w1 ${H2_N2_IP6} >/dev/null 2>&1
}
check_connectivity()