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/Makefile1
-rwxr-xr-xtools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh30
-rwxr-xr-xtools/testing/selftests/net/ioam6.sh2
-rw-r--r--tools/testing/selftests/net/lib/xdp_native.bpf.c55
-rwxr-xr-xtools/testing/selftests/net/link_netns.py61
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_connect.sh6
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_join.sh31
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_lib.sh26
-rwxr-xr-xtools/testing/selftests/net/mptcp/pm_netlink.sh20
-rw-r--r--tools/testing/selftests/net/netfilter/Makefile1
-rwxr-xr-xtools/testing/selftests/net/netfilter/nft_fib_nexthop.sh152
-rwxr-xr-xtools/testing/selftests/net/openvswitch/openvswitch.sh37
-rw-r--r--tools/testing/selftests/net/openvswitch/ovs-dpctl.py19
-rwxr-xr-xtools/testing/selftests/net/ovpn/test-close-socket.sh2
-rwxr-xr-xtools/testing/selftests/net/ovpn/test-mark.sh6
-rwxr-xr-xtools/testing/selftests/net/ovpn/test.sh8
-rw-r--r--tools/testing/selftests/net/rds/config1
-rwxr-xr-xtools/testing/selftests/net/rtnetlink.sh63
-rwxr-xr-xtools/testing/selftests/net/tcp_ecmp_failover.sh216
-rw-r--r--tools/testing/selftests/net/tls.c43
20 files changed, 716 insertions, 64 deletions
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index a275ed584026..f3da38c54d27 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -96,6 +96,7 @@ TEST_PROGS := \
srv6_hl2encap_red_l2vpn_test.sh \
srv6_iptunnel_cache.sh \
stress_reuseport_listen.sh \
+ tcp_ecmp_failover.sh \
tcp_fastopen_backup_key.sh \
test_bpf.sh \
test_bridge_backup_port.sh \
diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh
index e8031f68200a..ebdb4c790a5d 100755
--- a/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh
@@ -4,7 +4,7 @@
ALL_TESTS="vlmc_control_test vlmc_querier_test vlmc_igmp_mld_version_test \
vlmc_last_member_test vlmc_startup_query_test vlmc_membership_test \
vlmc_querier_intvl_test vlmc_query_intvl_test vlmc_query_response_intvl_test \
- vlmc_router_port_test vlmc_filtering_test"
+ vlmc_router_port_test vlmc_filtering_test vlmc_mcast_toggle_test"
NUM_NETIFS=4
CHECK_TC="yes"
TEST_GROUP="239.10.10.10"
@@ -537,6 +537,34 @@ vlmc_filtering_test()
log_test "Disable multicast vlan snooping when vlan filtering is disabled"
}
+vlmc_mcast_toggle_test()
+{
+ RET=0
+
+ ip link add name br1-mcast up type bridge mcast_snooping 1 mcast_querier 1 vlan_filtering 1
+ ip link add name dummy1-mcast up master br1-mcast type dummy
+
+ # Enabling per-VLAN multicast snooping should disable the per-port
+ # multicast context on "dummy1-mcast".
+ ip link set dev br1-mcast type bridge mcast_vlan_snooping 1
+
+ # Toggling multicast snooping on the bridge should not affect the
+ # per-port multicast context on "dummy1-mcast" given that per-VLAN
+ # multicast snooping is enabled.
+ ip link set dev br1-mcast type bridge mcast_snooping 0
+ ip link set dev br1-mcast type bridge mcast_snooping 1
+
+ # If both the per-port and per-{port, VLAN} multicast contexts are
+ # enabled on "dummy1-mcast", removing it from the bridge will result
+ # in a splat.
+ ip link set dev dummy1-mcast nomaster
+
+ log_test "Toggling mcast snooping with per-VLAN mcast snooping enabled"
+
+ ip link del dev dummy1-mcast
+ ip link del dev br1-mcast
+}
+
trap cleanup EXIT
setup_prepare
diff --git a/tools/testing/selftests/net/ioam6.sh b/tools/testing/selftests/net/ioam6.sh
index b2b99889942f..845c26dd01a9 100755
--- a/tools/testing/selftests/net/ioam6.sh
+++ b/tools/testing/selftests/net/ioam6.sh
@@ -273,8 +273,8 @@ setup()
ip -netns $ioam_node_beta link set ioam-veth-betaR name veth1 &>/dev/null
ip -netns $ioam_node_gamma link set ioam-veth-gamma name veth0 &>/dev/null
- ip -netns $ioam_node_alpha addr add 2001:db8:1::2/64 dev veth0 &>/dev/null
ip -netns $ioam_node_alpha addr add 2001:db8:1::50/64 dev veth0 &>/dev/null
+ ip -netns $ioam_node_alpha addr add 2001:db8:1::2/64 dev veth0 &>/dev/null
ip -netns $ioam_node_alpha link set veth0 up &>/dev/null
ip -netns $ioam_node_alpha link set lo up &>/dev/null
ip -netns $ioam_node_alpha route add 2001:db8:2::/64 \
diff --git a/tools/testing/selftests/net/lib/xdp_native.bpf.c b/tools/testing/selftests/net/lib/xdp_native.bpf.c
index 64f05229ab24..ded3f896e622 100644
--- a/tools/testing/selftests/net/lib/xdp_native.bpf.c
+++ b/tools/testing/selftests/net/lib/xdp_native.bpf.c
@@ -268,6 +268,17 @@ static int xdp_mode_tx_handler(struct xdp_md *ctx, __u16 port)
return XDP_PASS;
}
+static __always_inline __u16 csum_fold_helper(__u32 csum)
+{
+ csum = (csum & 0xffff) + (csum >> 16);
+ return ~((csum & 0xffff) + (csum >> 16));
+}
+
+static __always_inline __u16 csum_fold_udp_helper(__u32 csum)
+{
+ return csum_fold_helper(csum) ? : 0xffff;
+}
+
static void *update_pkt(struct xdp_md *ctx, __s16 offset, __u32 *udp_csum)
{
void *data_end = (void *)(long)ctx->data_end;
@@ -281,21 +292,22 @@ static void *update_pkt(struct xdp_md *ctx, __s16 offset, __u32 *udp_csum)
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);
+ len = iph->tot_len;
+ len_new = bpf_htons(bpf_ntohs(len) + offset);
+ iph->tot_len = len_new;
+ iph->check = csum_fold_helper(
+ bpf_csum_diff(&len, sizeof(len), &len_new,
+ sizeof(len_new), ~((__u32)iph->check)));
} 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;
@@ -304,33 +316,27 @@ static void *update_pkt(struct xdp_md *ctx, __s16 offset, __u32 *udp_csum)
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;
}
+ len = udph->len;
+ len_new = bpf_htons(bpf_ntohs(len) + offset);
+
+ *udp_csum = ~((__u32)udph->check);
+ *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new,
+ sizeof(len_new), *udp_csum);
+ *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new,
+ sizeof(len_new), *udp_csum);
+
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,
unsigned long hdr_len)
{
@@ -359,7 +365,7 @@ static int xdp_adjst_tail_shrnk_data(struct xdp_md *ctx, __u16 offset,
return -1;
udp_csum = bpf_csum_diff((__be32 *)tmp_buff, offset, 0, 0, udp_csum);
- udph->check = (__u16)csum_fold_helper(udp_csum);
+ udph->check = (__u16)csum_fold_udp_helper(udp_csum);
if (bpf_xdp_adjust_tail(ctx, 0 - offset) < 0)
return -1;
@@ -403,7 +409,7 @@ static int xdp_adjst_tail_grow_data(struct xdp_md *ctx, __u16 offset)
return -1;
udp_csum = bpf_csum_diff(0, 0, (__be32 *)tmp_buff, offset, udp_csum);
- udph->check = (__u16)csum_fold_helper(udp_csum);
+ udph->check = (__u16)csum_fold_udp_helper(udp_csum);
buff_len = bpf_xdp_get_buff_len(ctx);
@@ -484,8 +490,7 @@ static int xdp_adjst_head_shrnk_data(struct xdp_md *ctx, __u64 hdr_len,
return -1;
udp_csum = bpf_csum_diff((__be32 *)tmp_buff, offset, 0, 0, udp_csum);
-
- udph->check = (__u16)csum_fold_helper(udp_csum);
+ udph->check = (__u16)csum_fold_udp_helper(udp_csum);
if (bpf_xdp_load_bytes(ctx, 0, tmp_buff, MAX_ADJST_OFFSET) < 0)
return -1;
@@ -542,7 +547,7 @@ static int xdp_adjst_head_grow_data(struct xdp_md *ctx, __u64 hdr_len,
return -1;
udp_csum = bpf_csum_diff(0, 0, (__be32 *)data_buff, offset, udp_csum);
- udph->check = (__u16)csum_fold_helper(udp_csum);
+ udph->check = (__u16)csum_fold_udp_helper(udp_csum);
if (hdr_len > MAX_ADJST_OFFSET || hdr_len == 0)
return -1;
diff --git a/tools/testing/selftests/net/link_netns.py b/tools/testing/selftests/net/link_netns.py
index aab043c59d69..6d1f863b6262 100755
--- a/tools/testing/selftests/net/link_netns.py
+++ b/tools/testing/selftests/net/link_netns.py
@@ -3,13 +3,14 @@
import time
-from lib.py import ksft_run, ksft_exit, ksft_true
+from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_true
from lib.py import ip
from lib.py import NetNS, NetNSEnter
from lib.py import RtnlFamily
LINK_NETNSID = 100
+LINK_NETNSID2 = 200
def test_event() -> None:
@@ -32,6 +33,57 @@ def test_event() -> None:
"Received unexpected link notification")
+def test_event_all_nsid() -> None:
+ """NETLINK_LISTEN_ALL_NSID notifications: local events must not
+ carry nsid even with a self-referential mapping. Remote events
+ must carry the correct nsid."""
+
+ with NetNS() as ns1, NetNS() as ns2:
+ net1, net2 = str(ns1), str(ns2)
+
+ with NetNSEnter(net1):
+ rtnl = RtnlFamily()
+ rtnl.ntf_listen_all_nsid()
+ rtnl.ntf_subscribe("rtnlgrp-link")
+
+ # Case 1: no nsid assigned, local event, no nsid expected.
+ ip("link add dummy-lo type dummy", ns=net1)
+
+ # Case 2: self-referential nsid, local event, still no nsid.
+ ip(f"netns set {net1} {LINK_NETNSID}", ns=net1)
+ ip("link add dummy-sr type dummy", ns=net1)
+
+ # Case 3: remote event, nsid present.
+ ip(f"netns set {net2} {LINK_NETNSID2}", ns=net1)
+ ip("link add dummy-re type dummy", ns=net2)
+
+ # Collect the three newlink events, ignoring unrelated noise.
+ events = {}
+ for msg in rtnl.poll_ntf(duration=1):
+ if msg['name'] == 'getlink':
+ ifname = msg['msg'].get('ifname')
+ if ifname in ('dummy-lo', 'dummy-sr', 'dummy-re'):
+ events[ifname] = msg
+ if len(events) == 3:
+ break
+
+ ksft_true('dummy-lo' in events, "missing local event")
+ ksft_true(events['dummy-lo'].get('nsid') is None,
+ "local event without nsid should not carry nsid")
+
+ ksft_true('dummy-sr' in events, "missing self-ref event")
+ ksft_true(events['dummy-sr'].get('nsid') is None,
+ "local event with self-ref nsid should not carry nsid")
+
+ ksft_true('dummy-re' in events, "missing remote event")
+ ksft_eq(events['dummy-re'].get('nsid'), LINK_NETNSID2,
+ "remote event should carry nsid")
+
+ ip("link del dummy-lo", ns=net1)
+ ip("link del dummy-sr", ns=net1)
+ ip("link del dummy-re", ns=net2)
+
+
def validate_link_netns(netns, ifname, link_netnsid) -> bool:
link_info = ip(f"-d link show dev {ifname}", ns=netns, json=True)
if not link_info:
@@ -133,7 +185,12 @@ def test_peer_net() -> None:
def main() -> None:
- ksft_run([test_event, test_link_net, test_peer_net])
+ ksft_run([
+ test_event,
+ test_event_all_nsid,
+ test_link_net,
+ test_peer_net,
+ ])
ksft_exit()
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index a6447f7a31fe..d158678fa6ab 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -401,7 +401,7 @@ do_transfer()
mptcp_lib_wait_local_port_listen "${listener_ns}" "${port}"
local start
- start=$(date +%s%3N)
+ start=$(date +%s%N)
ip netns exec ${connector_ns} \
./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \
$extra_args $connect_addr < "$cin" > "$cout" &
@@ -423,7 +423,7 @@ do_transfer()
fi
local stop
- stop=$(date +%s%3N)
+ stop=$(date +%s%N)
if $capture; then
sleep 1
@@ -439,7 +439,7 @@ do_transfer()
fi
local duration
- duration=$((stop-start))
+ duration=$(((stop-start) / 1000000))
printf "(duration %05sms) " "${duration}"
if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ] || [ ${timeout_pid} -ne 0 ]; then
mptcp_lib_pr_fail "client exit code $retc, server $rets"
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index beec41f6662a..5acd12021e6e 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -1828,6 +1828,22 @@ chk_add_tx_nr()
fi
}
+chk_add_drop_tx_nr()
+{
+ local drop_tx_nr=$1
+ local count
+
+ print_check "add addr tx drop"
+ count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtAddAddrTxDrop")
+ if [ -z "$count" ]; then
+ print_skip
+ elif [ "$count" != "$drop_tx_nr" ]; then
+ fail_test "got $count ADD_ADDR drop[s] TX, expected $drop_tx_nr"
+ else
+ print_ok
+ fi
+}
+
chk_rm_nr()
{
local rm_addr_nr=$1
@@ -3278,6 +3294,21 @@ add_addr_ports_tests()
chk_mpc_endp_attempt ${retl} 1
fi
+
+ # first signal address drops, second one still progresses
+ if reset "signal addr list progresses after tx drop"; then
+ pm_nl_set_limits $ns1 0 2
+ pm_nl_set_limits $ns2 1 0
+ ip netns exec $ns1 sysctl -q net.ipv4.tcp_timestamps=1
+ ip netns exec $ns2 sysctl -q net.ipv4.tcp_timestamps=1
+
+ pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal port 10100
+ pm_nl_add_endpoint $ns1 dead:beef:3::1 flags signal
+ run_tests $ns1 $ns2 dead:beef:1::1
+ chk_add_drop_tx_nr 1
+ chk_add_tx_nr 1 1
+ chk_add_nr 1 1 0
+ fi
}
bind_tests()
diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
index 5fea7e7df628..5ef6033775c8 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -28,7 +28,7 @@ declare -rx MPTCP_LIB_AF_INET6=10
MPTCP_LIB_SUBTESTS=()
MPTCP_LIB_SUBTESTS_DUPLICATED=0
MPTCP_LIB_SUBTEST_FLAKY=0
-MPTCP_LIB_SUBTESTS_LAST_TS_MS=
+MPTCP_LIB_SUBTESTS_LAST_TS_NS=
MPTCP_LIB_TEST_COUNTER=0
MPTCP_LIB_TEST_FORMAT="%02u %-50s"
MPTCP_LIB_IP_MPTCP=0
@@ -236,7 +236,7 @@ mptcp_lib_kversion_ge() {
}
mptcp_lib_subtests_last_ts_reset() {
- MPTCP_LIB_SUBTESTS_LAST_TS_MS="$(date +%s%3N)"
+ MPTCP_LIB_SUBTESTS_LAST_TS_NS="$(date +%s%N)"
}
mptcp_lib_subtests_last_ts_reset
@@ -255,7 +255,7 @@ __mptcp_lib_result_check_duplicated() {
__mptcp_lib_result_add() {
local result="${1}"
local time="time="
- local ts_prev_ms
+ local ts_prev_ns
shift
local id=$((${#MPTCP_LIB_SUBTESTS[@]} + 1))
@@ -265,9 +265,9 @@ __mptcp_lib_result_add() {
# not to add two '#'
[[ "${*}" != *"#"* ]] && time="# ${time}"
- ts_prev_ms="${MPTCP_LIB_SUBTESTS_LAST_TS_MS}"
+ ts_prev_ns="${MPTCP_LIB_SUBTESTS_LAST_TS_NS}"
mptcp_lib_subtests_last_ts_reset
- time+="$((MPTCP_LIB_SUBTESTS_LAST_TS_MS - ts_prev_ms))ms"
+ time+="$(((MPTCP_LIB_SUBTESTS_LAST_TS_NS - ts_prev_ns) / 1000000))ms"
MPTCP_LIB_SUBTESTS+=("${result} ${id} - ${KSFT_TEST}: ${*} ${time}")
}
@@ -474,20 +474,24 @@ mptcp_lib_wait_local_port_listen() {
wait_local_port_listen "${@}" "tcp"
}
+# $1: error file, $2: cmd, $3: expected msg, [$4: expected error]
mptcp_lib_check_output() {
local err="${1}"
local cmd="${2}"
local expected="${3}"
+ local exp_error="${4:-0}"
local cmd_ret=0
local out
- if ! out=$(${cmd} 2>"${err}"); then
- cmd_ret=${?}
- fi
+ out=$(${cmd} 2>"${err}") || cmd_ret=1
- if [ ${cmd_ret} -ne 0 ]; then
- mptcp_lib_pr_fail "command execution '${cmd}' stderr"
- cat "${err}"
+ if [ "${cmd_ret}" != "${exp_error}" ]; then
+ mptcp_lib_pr_fail "unexpected returned code for '${cmd}', info:"
+ if [ "${exp_error}" = 0 ]; then
+ cat "${err}"
+ else
+ echo "${out}"
+ fi
return 2
elif [ "${out}" = "${expected}" ]; then
return 0
diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
index 123d9d7a0278..04594dfc22b1 100755
--- a/tools/testing/selftests/net/mptcp/pm_netlink.sh
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -122,10 +122,12 @@ check()
local cmd="$1"
local expected="$2"
local msg="$3"
+ local exp_error="$4"
local rc=0
mptcp_lib_print_title "$msg"
- mptcp_lib_check_output "${err}" "${cmd}" "${expected}" || rc=${?}
+ mptcp_lib_check_output "${err}" "${cmd}" "${expected}" "${exp_error}" ||
+ rc=${?}
if [ ${rc} -eq 2 ]; then
mptcp_lib_result_fail "${msg} # error ${rc}"
ret=${KSFT_FAIL}
@@ -158,13 +160,13 @@ check "show_endpoints" \
"3,10.0.1.3,signal backup")" "dump addrs"
del_endpoint 2
-check "get_endpoint 2" "" "simple del addr"
+check "get_endpoint 2" "" "simple del addr" 1
check "show_endpoints" \
"$(format_endpoints "1,10.0.1.1" \
"3,10.0.1.3,signal backup")" "dump addrs after del"
add_endpoint 10.0.1.3 2>/dev/null
-check "get_endpoint 4" "" "duplicate addr"
+check "get_endpoint 4" "" "duplicate addr" 1
add_endpoint 10.0.1.4 flags signal
check "get_endpoint 4" "$(format_endpoints "4,10.0.1.4,signal")" "id addr increment"
@@ -173,7 +175,7 @@ for i in $(seq 5 9); do
add_endpoint "10.0.1.${i}" flags signal >/dev/null 2>&1
done
check "get_endpoint 9" "$(format_endpoints "9,10.0.1.9,signal")" "hard addr limit"
-check "get_endpoint 10" "" "above hard addr limit"
+check "get_endpoint 10" "" "above hard addr limit" 1
del_endpoint 9
for i in $(seq 10 255); do
@@ -192,9 +194,13 @@ check "show_endpoints" \
flush_endpoint
check "show_endpoints" "" "flush addrs"
-add_endpoint 10.0.1.1 flags unknown
-check "show_endpoints" "$(format_endpoints "1,10.0.1.1")" "ignore unknown flags"
-flush_endpoint
+# "unknown" flag is only supported by pm_nl_ctl
+if ! mptcp_lib_is_ip_mptcp; then
+ add_endpoint 10.0.1.1 flags unknown
+ check "show_endpoints" "$(format_endpoints "1,10.0.1.1")" \
+ "ignore unknown flags"
+ flush_endpoint
+fi
set_limits 9 1 2>/dev/null
check "get_limits" "${default_limits}" "rcv addrs above hard limit"
diff --git a/tools/testing/selftests/net/netfilter/Makefile b/tools/testing/selftests/net/netfilter/Makefile
index ee2d1a5254f8..d953ee218c0f 100644
--- a/tools/testing/selftests/net/netfilter/Makefile
+++ b/tools/testing/selftests/net/netfilter/Makefile
@@ -26,6 +26,7 @@ TEST_PROGS := \
nft_concat_range.sh \
nft_conntrack_helper.sh \
nft_fib.sh \
+ nft_fib_nexthop.sh \
nft_flowtable.sh \
nft_interface_stress.sh \
nft_meta.sh \
diff --git a/tools/testing/selftests/net/netfilter/nft_fib_nexthop.sh b/tools/testing/selftests/net/netfilter/nft_fib_nexthop.sh
new file mode 100755
index 000000000000..c4f203057382
--- /dev/null
+++ b/tools/testing/selftests/net/netfilter/nft_fib_nexthop.sh
@@ -0,0 +1,152 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# shellcheck disable=SC2154
+#
+# Exercise nft_fib6_eval()'s sibling/nh enumeration on three route shapes:
+# 1) route via a single external nexthop (nhid)
+# 2) route via an external nexthop group (nhid -> group, two members)
+# 3) route via old-style multipath (nexthop ... nexthop ...)
+#
+# In each scenario the route's nexthop set contains veth0 (the iif of the
+# test packet). nft_fib6_info_nh_uses_dev() must walk the set and report
+# veth0 as a valid oif. For (2) and (3) the matching nexthop is the second
+# member, so the walk has to traverse beyond the primary nh.
+#
+# After sending $PKTS ICMPv6 echo requests from ns1, check two counters on
+# nsrouter:
+# nf_ok -- `fib daddr . iif oif eq "veth0"` must equal $PKTS
+# nf_bad -- `fib daddr . iif oif missing` must stay at 0
+# Both rules also match on iif veth0 and ip6 daddr dead:dead::/64 so that
+# kernel-generated ND/MLD/RA traffic cannot pollute the counters.
+#
+# Topology similar to nft_fib.sh, without ns2; two dummy interfaces on
+# nsrouter host extra nh devices:
+#
+# dead:1::99 dead:1::1
+# ns1 <----veth----> nsrouter --- dummy0 dead:2::1
+# \-- dummy1 dead:9::1
+
+source lib.sh
+
+ret=0
+PKTS=3
+
+checktool "nft --version" "run test without nft"
+checktool "ip -V" "run test without iproute2"
+
+setup_ns nsrouter ns1
+trap cleanup_all_ns EXIT
+
+if ! ip link add veth0 netns "$nsrouter" type veth peer name eth0 netns "$ns1" \
+ > /dev/null 2>&1; then
+ echo "SKIP: No virtual ethernet pair device support in kernel"
+ exit $ksft_skip
+fi
+
+ip -net "$ns1" link set lo up
+ip -net "$ns1" link set eth0 up
+ip -net "$ns1" -6 addr add dead:1::99/64 dev eth0 nodad
+ip -net "$ns1" -6 route add default via dead:1::1
+
+ip -net "$nsrouter" link set lo up
+ip -net "$nsrouter" link set veth0 up
+ip -net "$nsrouter" -6 addr add dead:1::1/64 dev veth0 nodad
+
+if ! ip -net "$nsrouter" link add dummy0 type dummy 2>/dev/null; then
+ echo "SKIP: dummy netdev not available"
+ exit $ksft_skip
+fi
+ip -net "$nsrouter" link set dummy0 up
+ip -net "$nsrouter" -6 addr add dead:2::1/64 dev dummy0 nodad
+
+ip -net "$nsrouter" link add dummy1 type dummy
+ip -net "$nsrouter" link set dummy1 up
+ip -net "$nsrouter" -6 addr add dead:9::1/64 dev dummy1 nodad
+
+ip netns exec "$nsrouter" sysctl -q net.ipv6.conf.all.forwarding=1
+
+load_fib_rule() {
+ # filter on iif + daddr so the counters only see our test packets
+ ip netns exec "$nsrouter" nft -f /dev/stdin <<EOF
+flush ruleset
+table ip6 t {
+ counter nf_ok { }
+ counter nf_bad { }
+ chain c {
+ type filter hook prerouting priority 0; policy accept;
+ iif "veth0" ip6 daddr dead:dead::/64 fib daddr . iif oif eq "veth0" counter name nf_ok
+ iif "veth0" ip6 daddr dead:dead::/64 fib daddr . iif oif missing counter name nf_bad
+ }
+}
+EOF
+}
+
+bad_counter() {
+ local counter=$1
+ local expect=$2
+ local tag=$3
+
+ echo "FAIL ($tag): counter $counter has unexpected value (expected \"$expect\")" 1>&2
+ ip netns exec "$nsrouter" nft list counter ip6 t "$counter" 1>&2
+}
+
+run_scenario() {
+ local what="$1"; shift
+ # counter output format is "packets PACKET_NUM bytes BYTES_NUM";
+ # we only care about the packet count
+ local expect_ok="packets $PKTS bytes"
+ local expect_bad="packets 0 bytes"
+ local lret=0
+
+ # reset route + nexthop state between scenarios
+ ip -net "$nsrouter" -6 route del dead:dead::/64 > /dev/null 2>&1 || true
+ ip -net "$nsrouter" nexthop flush > /dev/null 2>&1 || true
+
+ # run the scenario function passed by the caller
+ "$@" || echo "WARN ($what): scenario setup returned non-zero"
+
+ load_fib_rule || { echo "FAIL ($what): nft load"; ret=1; return; }
+
+ # ping a daddr inside dead:dead::/64 so fib has to walk the nh set
+ ip netns exec "$ns1" ping -6 -c "$PKTS" -i 0.1 -W 1 dead:dead::1 \
+ > /dev/null 2>&1 || true
+
+ # verify the packets went through the expected fib path
+ if ! ip netns exec "$nsrouter" nft list counter ip6 t nf_ok | grep -q "$expect_ok"; then
+ bad_counter nf_ok "$expect_ok" "$what"
+ lret=1
+ fi
+ if ! ip netns exec "$nsrouter" nft list counter ip6 t nf_bad | grep -q "$expect_bad"; then
+ bad_counter nf_bad "$expect_bad" "$what"
+ lret=1
+ fi
+
+ if [ $lret -eq 0 ]; then
+ echo "PASS: $what"
+ else
+ ret=1
+ fi
+}
+
+scenario_single_nh() {
+ ip -net "$nsrouter" nexthop add id 1 via dead:1::99 dev veth0
+ ip -net "$nsrouter" -6 route add dead:dead::/64 nhid 1
+}
+run_scenario "single external nexthop (nhid -> veth0)" scenario_single_nh
+
+scenario_nh_group() {
+ ip -net "$nsrouter" nexthop add id 1 via dead:2::2 dev dummy0
+ ip -net "$nsrouter" nexthop add id 2 via dead:1::99 dev veth0
+ ip -net "$nsrouter" nexthop add id 100 group 1/2
+ ip -net "$nsrouter" -6 route add dead:dead::/64 nhid 100
+}
+run_scenario "nexthop group (dummy0 + veth0)" scenario_nh_group
+
+scenario_old_multipath() {
+ ip -net "$nsrouter" -6 route add dead:dead::/64 \
+ nexthop via dead:2::2 dev dummy0 \
+ nexthop via dead:1::99 dev veth0
+}
+run_scenario "old-style multipath (sibling on veth0)" scenario_old_multipath
+
+exit $ret
diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh
index b327d3061ed5..3cdd953f6813 100755
--- a/tools/testing/selftests/net/openvswitch/openvswitch.sh
+++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh
@@ -26,6 +26,7 @@ tests="
netlink_checks ovsnl: validate netlink attrs and settings
upcall_interfaces ovs: test the upcall interfaces
tunnel_metadata ovs: test extraction of tunnel metadata
+ tunnel_refcount ovs: test tunnel vport reference cleanup
drop_reason drop: test drop reasons are emitted
psample psample: Sampling packets with psample"
@@ -830,6 +831,42 @@ test_tunnel_metadata() {
return 0
}
+test_tunnel_refcount() {
+ sbxname="test_tunnel_refcount"
+ sbx_add "${sbxname}" || return 1
+
+ ovs_sbx "${sbxname}" ip netns add trefns || return 1
+ on_exit "ovs_sbx ${sbxname} ip netns del trefns"
+
+ for tun_type in gre vxlan geneve; do
+ info "testing ${tun_type} tunnel vport refcount"
+
+ ovs_sbx "${sbxname}" ip netns exec trefns \
+ python3 $ovs_base/ovs-dpctl.py \
+ add-dp dp-${tun_type} || return 1
+
+ ovs_sbx "${sbxname}" ip netns exec trefns \
+ python3 $ovs_base/ovs-dpctl.py \
+ add-if --no-lwt -t ${tun_type} \
+ dp-${tun_type} ovs-${tun_type}0 || return 1
+
+ ovs_wait ip -netns trefns link show \
+ ovs-${tun_type}0 >/dev/null 2>&1 || return 1
+
+ info "deleting dp - may hang if reference counting is broken"
+ ovs_sbx "${sbxname}" ip netns exec trefns \
+ python3 $ovs_base/ovs-dpctl.py \
+ del-dp dp-${tun_type} &
+
+ dev_removed() {
+ ! ip -netns trefns link show "$1" >/dev/null 2>&1
+ }
+ ovs_wait dev_removed dp-${tun_type} || return 1
+ ovs_wait dev_removed ovs-${tun_type}0 || return 1
+ done
+ return 0
+}
+
run_test() {
(
tname="$1"
diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
index 848f61fdcee0..bbe35e2718d2 100644
--- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
+++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
@@ -11,7 +11,6 @@ import logging
import math
import multiprocessing
import re
-import socket
import struct
import sys
import time
@@ -2069,7 +2068,7 @@ class OvsVport(GenericNetlinkSocket):
elif vport_type == "internal":
return OvsVport.OVS_VPORT_TYPE_INTERNAL
elif vport_type == "gre":
- return OvsVport.OVS_VPORT_TYPE_INTERNAL
+ return OvsVport.OVS_VPORT_TYPE_GRE
elif vport_type == "vxlan":
return OvsVport.OVS_VPORT_TYPE_VXLAN
elif vport_type == "geneve":
@@ -2121,6 +2120,7 @@ class OvsVport(GenericNetlinkSocket):
)
TUNNEL_DEFAULTS = [("geneve", 6081),
+ ("gre", 0),
("vxlan", 4789)]
for tnl in TUNNEL_DEFAULTS:
@@ -2129,9 +2129,13 @@ class OvsVport(GenericNetlinkSocket):
dport = tnl[1]
if not lwt:
+ if tnl[0] == "gre":
+ # GRE tunnels have no options.
+ break
+
vportopt = OvsVport.ovs_vport_msg.vportopts()
vportopt["attrs"].append(
- ["OVS_TUNNEL_ATTR_DST_PORT", socket.htons(dport)]
+ ["OVS_TUNNEL_ATTR_DST_PORT", dport]
)
msg["attrs"].append(
["OVS_VPORT_ATTR_OPTIONS", vportopt]
@@ -2145,6 +2149,9 @@ class OvsVport(GenericNetlinkSocket):
geneve_port=dport,
geneve_collect_metadata=True,
geneve_udp_zero_csum6_rx=1)
+ elif tnl[0] == "gre":
+ ipr.link("add", ifname=vport_ifname, kind="gretap",
+ gre_collect_metadata=True)
elif tnl[0] == "vxlan":
ipr.link("add", ifname=vport_ifname, kind=tnl[0],
vxlan_learning=0, vxlan_collect_metadata=1,
@@ -2563,7 +2570,7 @@ def print_ovsdp_full(dp_lookup_rep, ifindex, ndb=NDB(), vpl=OvsVport()):
if vpo:
dpo = vpo.get_attr("OVS_TUNNEL_ATTR_DST_PORT")
if dpo:
- opts += " tnl-dport:%s" % socket.ntohs(dpo)
+ opts += " tnl-dport:%s" % dpo
print(
" port %d: %s (%s%s)"
% (
@@ -2632,7 +2639,7 @@ def main(argv):
"--ptype",
type=str,
default="netdev",
- choices=["netdev", "internal", "geneve", "vxlan"],
+ choices=["netdev", "internal", "gre", "geneve", "vxlan"],
help="Interface type (default netdev)",
)
addifcmd.add_argument(
@@ -2645,7 +2652,7 @@ def main(argv):
addifcmd.add_argument(
"-l",
"--lwt",
- type=bool,
+ action=argparse.BooleanOptionalAction,
default=True,
help="Use LWT infrastructure instead of vport (default true)."
)
diff --git a/tools/testing/selftests/net/ovpn/test-close-socket.sh b/tools/testing/selftests/net/ovpn/test-close-socket.sh
index af1532b4d2da..ec9a51bbf3c9 100755
--- a/tools/testing/selftests/net/ovpn/test-close-socket.sh
+++ b/tools/testing/selftests/net/ovpn/test-close-socket.sh
@@ -53,7 +53,7 @@ ovpn_run_ping_traffic() {
for p in $(seq 1 ${OVPN_NUM_PEERS}); do
ovpn_cmd_ok "send ping traffic to peer ${p}" \
- ip netns exec ovpn_peer0 ping -qfc 500 -w 3 \
+ ip netns exec ovpn_peer0 ping -qfc 100 -w 3 \
5.5.5.$((p + 1))
done
}
diff --git a/tools/testing/selftests/net/ovpn/test-mark.sh b/tools/testing/selftests/net/ovpn/test-mark.sh
index 5a8f47554286..7c1d56e9c525 100755
--- a/tools/testing/selftests/net/ovpn/test-mark.sh
+++ b/tools/testing/selftests/net/ovpn/test-mark.sh
@@ -66,7 +66,7 @@ ovpn_mark_run_baseline_traffic() {
for p in $(seq 1 3); do
ovpn_cmd_ok "send baseline traffic to peer ${p}" \
- ip netns exec ovpn_peer0 ping -qfc 500 -w 3 \
+ ip netns exec ovpn_peer0 ping -qfc 100 -w 3 \
5.5.5.$((p + 1))
done
}
@@ -101,7 +101,7 @@ ovpn_mark_verify_drop_traffic() {
local total_count
for p in $(seq 1 3); do
- if ping_output=$(ip netns exec ovpn_peer0 ping -qfc 500 -w 1 \
+ if ping_output=$(ip netns exec ovpn_peer0 ping -qfc 100 -w 1 \
5.5.5.$((p + 1)) 2>&1); then
printf '%s\n' "expected ping to peer ${p} to fail \
after nft drop rule"
@@ -144,7 +144,7 @@ ovpn_mark_verify_traffic_recovery() {
sleep 1
for p in $(seq 1 3); do
ovpn_cmd_ok "send recovery traffic to peer ${p}" \
- ip netns exec ovpn_peer0 ping -qfc 500 -w 3 \
+ ip netns exec ovpn_peer0 ping -qfc 100 -w 3 \
5.5.5.$((p + 1))
done
}
diff --git a/tools/testing/selftests/net/ovpn/test.sh b/tools/testing/selftests/net/ovpn/test.sh
index b50dbe45a4d0..9b5610837032 100755
--- a/tools/testing/selftests/net/ovpn/test.sh
+++ b/tools/testing/selftests/net/ovpn/test.sh
@@ -98,10 +98,10 @@ ovpn_run_basic_traffic() {
sleep 0.3
ovpn_cmd_ok "send baseline traffic to peer ${p}" \
ip netns exec ovpn_peer0 \
- ping -qfc 500 -w 3 5.5.5.$((p + 1))
+ ping -qfc 100 -w 3 5.5.5.$((p + 1))
ovpn_cmd_ok "send large-payload traffic to peer ${p}" \
ip netns exec ovpn_peer0 \
- ping -qfc 500 -s 3000 -w 3 5.5.5.$((p + 1))
+ ping -qfc 100 -s 3000 -w 3 5.5.5.$((p + 1))
wait "${tcpdump_pid1}" || return 1
wait "${tcpdump_pid2}" || return 1
@@ -110,7 +110,7 @@ ovpn_run_basic_traffic() {
ovpn_run_lan_traffic() {
ovpn_cmd_ok "ping LAN behind peer1" \
- ip netns exec ovpn_peer0 ping -qfc 500 -w 3 "${OVPN_LAN_IP}"
+ ip netns exec ovpn_peer0 ping -qfc 100 -w 3 "${OVPN_LAN_IP}"
}
ovpn_run_float_mode() {
@@ -127,7 +127,7 @@ ovpn_run_float_mode() {
for p in $(seq 1 ${OVPN_NUM_PEERS}); do
peer_ns="ovpn_peer${p}"
ovpn_cmd_ok "ping tunnel after float peer ${p}" \
- ip netns exec "${peer_ns}" ping -qfc 500 -w 3 5.5.5.1
+ ip netns exec "${peer_ns}" ping -qfc 100 -w 3 5.5.5.1
done
}
diff --git a/tools/testing/selftests/net/rds/config b/tools/testing/selftests/net/rds/config
index 97db7ecb892a..3d62d0c750a8 100644
--- a/tools/testing/selftests/net/rds/config
+++ b/tools/testing/selftests/net/rds/config
@@ -1,3 +1,4 @@
+CONFIG_MODULES=n
CONFIG_NET_NS=y
CONFIG_NET_SCH_NETEM=y
CONFIG_RDS=y
diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index c499953d4885..ace3a99023ed 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -24,6 +24,8 @@ ALL_TESTS="
kci_test_macsec
kci_test_macsec_vlan
kci_test_team_bridge_macvlan
+ kci_test_bridge_promisc_netlink
+ kci_test_bridge_promisc_sysfs
kci_test_ipsec
kci_test_ipsec_offload
kci_test_fdb_get
@@ -61,6 +63,14 @@ check_fail()
fi
}
+sysfs_write()
+{
+ local val="$1"
+ local path="$2"
+
+ echo "$val" > "$path"
+}
+
run_cmd_common()
{
local cmd="$*"
@@ -680,6 +690,59 @@ kci_test_team_bridge_macvlan()
end_test "PASS: team_bridge_macvlan"
}
+# Test that changing bridge port flags via the netlink path does not sleep with
+# the bridge spin lock held.
+kci_test_bridge_promisc_netlink()
+{
+ local dummy="test_dummy1"
+ local bridge="test_br1"
+ local team="test_team1"
+ local ret=0
+
+ run_cmd ip link add $team up type team
+ run_cmd ip link add $bridge up type bridge vlan_filtering 1
+ run_cmd ip link add $dummy up type dummy
+ run_cmd ip link set $dummy master $bridge
+ run_cmd ip link set $team master $bridge
+
+ # This causes the bridge driver to sync all the static FDB entries to
+ # the team device (which supports unicast filtering) and remove it from
+ # promiscuous mode. The call to dev_set_promiscuity() can sleep due to
+ # Rx mode inlining, which is a problem if the bridge spin lock is held.
+ run_cmd bridge link set dev $dummy flood off learning off
+
+ run_cmd ip link del $dummy
+ run_cmd ip link del $bridge
+ run_cmd ip link del $team
+
+ end_test "PASS: bridge_promisc_netlink"
+}
+
+# Same as kci_test_bridge_promisc_netlink(), but the flags are changed via the
+# sysfs path.
+kci_test_bridge_promisc_sysfs()
+{
+ local dummy="test_dummy1"
+ local bridge="test_br1"
+ local team="test_team1"
+ local ret=0
+
+ run_cmd ip link add $team up type team
+ run_cmd ip link add $bridge up type bridge vlan_filtering 1
+ run_cmd ip link add $dummy up type dummy
+ run_cmd ip link set $dummy master $bridge
+ run_cmd ip link set $team master $bridge
+
+ run_cmd sysfs_write 0 /sys/class/net/$dummy/brport/unicast_flood
+ run_cmd sysfs_write 0 /sys/class/net/$dummy/brport/learning
+
+ run_cmd ip link del $dummy
+ run_cmd ip link del $bridge
+ run_cmd ip link del $team
+
+ end_test "PASS: bridge_promisc_sysfs"
+}
+
#-------------------------------------------------------------------
# Example commands
# ip x s add proto esp src 14.0.0.52 dst 14.0.0.70 \
diff --git a/tools/testing/selftests/net/tcp_ecmp_failover.sh b/tools/testing/selftests/net/tcp_ecmp_failover.sh
new file mode 100755
index 000000000000..5768aa8bff6a
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ecmp_failover.sh
@@ -0,0 +1,216 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright 2026 Google LLC.
+#
+# This test verifies TCP flow failover between ECMP routes
+# upon carrier loss on the active device.
+#
+# socat -----------------------------> socat
+# |
+# .-- veth-c1 -|- veth-s1 --.
+# dummy0 -| | |-- dummy0
+# '-- veth-c2 -|- veth-s2 --'
+# |
+#
+
+REQUIRE_JQ=no
+REQUIRE_MZ=no
+NUM_NETIFS=0
+
+source forwarding/lib.sh
+
+CLIENT_IP="10.0.59.1"
+SERVER_IP="10.0.92.1"
+CLIENT_IP6="2001:db8:5a9a::1"
+SERVER_IP6="2001:db8:9292::1"
+
+setup_server()
+{
+ IP="ip -n $server"
+ NS_EXEC="ip netns exec $server"
+
+ $IP link add dummy0 type dummy
+ $IP link set dummy0 up
+
+ $IP -4 addr add $SERVER_IP/32 dev dummy0
+ $IP -6 addr add $SERVER_IP6/128 dev dummy0 nodad
+
+ $IP link set veth-s1 up
+ $IP link set veth-s2 up
+
+ $IP -4 addr add 192.168.1.2/24 dev veth-s1
+ $IP -4 addr add 192.168.2.2/24 dev veth-s2
+
+ $IP -4 route add $CLIENT_IP/32 \
+ nexthop via 192.168.1.1 dev veth-s1 weight 1 \
+ nexthop via 192.168.2.1 dev veth-s2 weight 1
+
+ $IP -6 addr add 2001:db8:1::2/64 dev veth-s1 nodad
+ $IP -6 addr add 2001:db8:2::2/64 dev veth-s2 nodad
+
+ $IP -6 route add $CLIENT_IP6/128 \
+ nexthop via 2001:db8:1::1 dev veth-s1 weight 1 \
+ nexthop via 2001:db8:2::1 dev veth-s2 weight 1
+}
+
+setup_client()
+{
+ IP="ip -n $client"
+ NS_EXEC="ip netns exec $client"
+
+ $IP link add dummy0 type dummy
+ $IP link set dummy0 up
+
+ $IP -4 addr add $CLIENT_IP/32 dev dummy0
+ $IP -6 addr add $CLIENT_IP6/128 dev dummy0 nodad
+
+ $IP link set veth-c1 up
+ $IP link set veth-c2 up
+
+ $IP -4 addr add 192.168.1.1/24 dev veth-c1
+ $IP -4 addr add 192.168.2.1/24 dev veth-c2
+
+ $IP -4 route add $SERVER_IP/32 \
+ nexthop via 192.168.1.2 dev veth-c1 weight 1 \
+ nexthop via 192.168.2.2 dev veth-c2 weight 1
+
+ $IP -6 addr add 2001:db8:1::1/64 dev veth-c1 nodad
+ $IP -6 addr add 2001:db8:2::1/64 dev veth-c2 nodad
+
+ $IP -6 route add $SERVER_IP6/128 \
+ nexthop via 2001:db8:1::2 dev veth-c1 weight 1 \
+ nexthop via 2001:db8:2::2 dev veth-c2 weight 1
+
+ # By default, tcp_retries1=3 triggers a route refresh
+ # after 3 retransmits (~5s). Ensure this never occurs
+ # for test stability.
+ $NS_EXEC sysctl -qw net.ipv4.tcp_retries1=100
+
+ # When NETDEV_CHANGE is issued for a dev tied to an ECMP
+ # route, RTNH_F_LINKDOWN is flagged and the sernum is
+ # bumped to invalidate the route via sk_dst_check().
+ #
+ # Without ignore_routes_with_linkdown=1, subsequent
+ # lookups may still select the same RTNH_F_LINKDOWN route.
+ $NS_EXEC sysctl -qw net.ipv4.conf.veth-c1.ignore_routes_with_linkdown=1
+ $NS_EXEC sysctl -qw net.ipv4.conf.veth-c2.ignore_routes_with_linkdown=1
+
+ $NS_EXEC sysctl -qw net.ipv6.conf.veth-c1.ignore_routes_with_linkdown=1
+ $NS_EXEC sysctl -qw net.ipv6.conf.veth-c2.ignore_routes_with_linkdown=1
+}
+
+setup()
+{
+ setup_ns client server
+
+ ip -n "$client" link add veth-c1 type veth peer veth-s1 netns "$server"
+ ip -n "$client" link add veth-c2 type veth peer veth-s2 netns "$server"
+
+ setup_server
+ setup_client
+}
+
+cleanup()
+{
+ cleanup_all_ns > /dev/null 2>&1
+}
+
+tcp_ecmp_failover()
+{
+ local pf=$1; shift
+ local server_ip=$1; shift
+ local client_ip=$1; shift
+
+ RET=0
+
+ tcpdump_start veth-s1 "$server"
+ tcpdump_start veth-s2 "$server"
+
+ ip netns exec "$server" \
+ socat -u TCP-LISTEN:8080,pf="$pf",bind="$server_ip",reuseaddr /dev/null &
+ server_pid=$!
+
+ # Wait for server to start listening.
+ # Sometimes client fails without this sleep.
+ sleep 1
+
+ ip netns exec "$client" \
+ socat -u /dev/zero TCP:"$server_ip":8080,pf="$pf",bind="$client_ip" &
+ client_pid=$!
+
+ # To capture enough packets.
+ sleep 3
+
+ tcpdump_stop veth-s1
+ tcpdump_stop veth-s2
+
+ pkts_s1=$(tcpdump_show veth-s1 | wc -l)
+ pkts_s2=$(tcpdump_show veth-s2 | wc -l)
+
+ tcpdump_cleanup veth-s1
+ tcpdump_cleanup veth-s2
+
+ # Detect the device chosen by the client
+ if [ "$pkts_s1" -gt "$pkts_s2" ]; then
+ veth_down=veth-s1
+ veth_up=veth-s2
+ else
+ veth_down=veth-s2
+ veth_up=veth-s1
+ fi
+
+ # Taking down $veth_down causes its peer to lose carrier,
+ # triggering NETDEV_CHANGE. This flags RTNH_F_LINKDOWN
+ # and bumps the sernum for the route associated with that
+ # peer, invalidating the cached dst in the TCP socket.
+ #
+ # Consequently, sk_dst_check() fails, forcing the subsequent
+ # lookup to select the remaining healthy route via $veth_up.
+ ip -n "$server" link set "$veth_down" down
+
+ tcpdump_start "$veth_up" "$server"
+
+ # To capture enough packets.
+ sleep 3
+
+ tcpdump_stop "$veth_up"
+
+ kill -9 "$client_pid" > /dev/null 2>&1
+ kill -9 "$server_pid" > /dev/null 2>&1
+ wait 2> /dev/null
+
+ pkts=$(tcpdump_show $veth_up | wc -l)
+
+ tcpdump_cleanup "$veth_up"
+
+ if [ "$pkts" -lt 1000 ]; then
+ RET=$ksft_fail
+ fi
+}
+
+test_ipv4()
+{
+ setup
+ tcp_ecmp_failover IPv4 $SERVER_IP $CLIENT_IP
+ log_test "TCP IPv4 failover"
+ cleanup
+}
+
+test_ipv6()
+{
+ setup
+ tcp_ecmp_failover IPv6 "[$SERVER_IP6]" "[$CLIENT_IP6]"
+ log_test "TCP IPv6 failover"
+ cleanup
+}
+
+require_command socat
+require_command tcpdump
+
+trap cleanup EXIT
+
+test_ipv4
+test_ipv6
+
+exit "$EXIT_STATUS"
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 9e2ccea13d70..30a236b8e9f7 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -946,6 +946,49 @@ TEST_F(tls, peek_and_splice)
EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
}
+TEST_F(tls, splice_to_pipe_small)
+{
+ int send_len = TLS_PAYLOAD_MAX_LEN;
+ char mem_send[TLS_PAYLOAD_MAX_LEN];
+ char mem_recv[TLS_PAYLOAD_MAX_LEN];
+ size_t total = 0;
+ int p[2];
+
+ memrnd(mem_send, sizeof(mem_send));
+
+ ASSERT_GE(pipe(p), 0);
+
+ /* Shrink pipe to 1 page (typically 4096 bytes) to force multiple
+ * splice iterations for a 16384-byte TLS record.
+ */
+ EXPECT_GE(fcntl(p[1], F_SETPIPE_SZ, 4096), 4096);
+
+ EXPECT_EQ(send(self->fd, mem_send, send_len, 0), send_len);
+
+ while (total < (size_t)send_len) {
+ ssize_t spliced, drained;
+
+ spliced = splice(self->cfd, NULL, p[1], NULL,
+ send_len - total, 0);
+ EXPECT_GT(spliced, 0);
+ if (spliced <= 0)
+ break;
+
+ drained = read(p[0], mem_recv + total, spliced);
+ EXPECT_EQ(drained, spliced);
+ if (drained <= 0)
+ break;
+
+ total += drained;
+ }
+
+ EXPECT_EQ(total, (size_t)send_len);
+ EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
+
+ close(p[0]);
+ close(p[1]);
+}
+
#define MAX_FRAGS 48
TEST_F(tls, splice_short)
{