* [PATCH mptcp-next v3 1/2] selftests: mptcp: convert iptables to nftables for mptcp_sockopt.sh
2026-09-04 7:31 [PATCH mptcp-next v3 0/2] selftests: mptcp: convert iptables to nftables Hangbin Liu
@ 2026-09-04 7:31 ` Hangbin Liu
2026-09-04 7:31 ` [PATCH mptcp-next v3 2/2] selftests: mptcp: convert iptables to nftables for mptcp_join.sh Hangbin Liu
2026-09-04 8:41 ` [PATCH mptcp-next v3 0/2] selftests: mptcp: convert iptables to nftables MPTCP CI
2 siblings, 0 replies; 6+ messages in thread
From: Hangbin Liu @ 2026-09-04 7:31 UTC (permalink / raw)
To: MPTCP Linux; +Cc: Hangbin Liu, Hangbin Liu
From: Hangbin Liu <liuhangbin@kylinos.cn>
During the conversion, we retain the same filter and chain names previously
used by iptables/ip6tables. Counters are not added to accept rules because
the test does not inspect them. After conversion, the generated output
matches the original iptables/ip6tables behavior.
Signed-off-by: Hangbin Liu <liuhangbin@kylinos.cn>
---
tools/testing/selftests/net/mptcp/mptcp_lib.sh | 2 +-
tools/testing/selftests/net/mptcp/mptcp_sockopt.sh | 64 ++++++++++++----------
2 files changed, 37 insertions(+), 29 deletions(-)
diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
index b9d14647f401..e65b4ebee06a 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -528,7 +528,7 @@ mptcp_lib_check_tools() {
exit ${KSFT_SKIP}
fi
;;
- "iptables"* | "ip6tables"*)
+ "iptables"* | "ip6tables"* | "nft" | "jq")
if ! "${tool}" -V &> /dev/null; then
mptcp_lib_pr_skip "Could not run all tests without ${tool}"
exit ${KSFT_SKIP}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
index e850a87429b6..b4e3eddc9cf2 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
@@ -15,8 +15,6 @@ cin=""
cout=""
timeout_poll=30
timeout_test=$((timeout_poll * 2 + 1))
-iptables="iptables"
-ip6tables="ip6tables"
ns1=""
ns2=""
@@ -49,16 +47,27 @@ add_mark_rules()
local ns=$1
local m=$2
- local t
- for t in ${iptables} ${ip6tables}; do
- # just to debug: check we have multiple subflows connection requests
- ip netns exec $ns $t -A OUTPUT -p tcp --syn -m mark --mark $m -j ACCEPT
-
- # RST packets might be handled by a internal dummy socket
- ip netns exec $ns $t -A OUTPUT -p tcp --tcp-flags RST RST -m mark --mark 0 -j ACCEPT
-
- ip netns exec $ns $t -A OUTPUT -p tcp -m mark --mark $m -j ACCEPT
- ip netns exec $ns $t -A OUTPUT -p tcp -m mark --mark 0 -j DROP
+ local table
+ for table in ip ip6; do
+ ip netns exec "$ns" nft -f - <<-EOF
+ add table $table filter
+ add chain $table filter OUTPUT \
+ { type filter hook output priority 0; policy accept; }
+
+ # just to debug: check we have multiple subflows connection requests
+ add rule $table filter OUTPUT \
+ tcp flags & (fin | syn | rst | ack) == syn \
+ meta mark $m accept
+
+ # RST packets might be handled by a internal dummy socket
+ add rule $table filter OUTPUT \
+ tcp flags & rst == rst meta mark 0x0 accept
+
+ add rule $table filter OUTPUT \
+ meta l4proto tcp meta mark $m accept
+ add rule $table filter OUTPUT \
+ meta l4proto tcp meta mark 0 counter drop
+ EOF
done
}
@@ -105,32 +114,31 @@ cleanup()
mptcp_lib_check_mptcp
mptcp_lib_check_kallsyms
-mptcp_lib_check_tools ip "${iptables}" "${ip6tables}"
+mptcp_lib_check_tools ip nft jq
check_mark()
{
local ns=$1
local af=$2
- local tables=${iptables}
+ local tables="ip"
if [ $af -eq 6 ];then
- tables=${ip6tables}
+ tables="ip6"
fi
- local counters values
- counters=$(ip netns exec $ns $tables -v -L OUTPUT | grep DROP)
- values=${counters%DROP*}
-
- local v
- for v in $values; do
- if [ $v -ne 0 ]; then
- mptcp_lib_pr_fail "got $tables $values in ns $ns," \
- "not 0 - not all expected packets marked"
- ret=${KSFT_FAIL}
- return 1
- fi
- done
+ local drops
+ drops=$(ip netns exec "$ns" nft -j list table "$tables" filter | \
+ jq '.nftables[] | select(has("rule")) | .rule |
+ select (.chain=="OUTPUT" and any(.expr[]; has("drop"))) |
+ .expr[] | select(has("counter")) | .counter.packets')
+
+ if [ -z "$drops" ] || [ "$drops" -ne 0 ]; then
+ mptcp_lib_pr_fail "got $tables $drops in ns $ns," \
+ "not 0 - not all expected packets marked"
+ ret=${KSFT_FAIL}
+ return 1
+ fi
return 0
}
--
2.55.0
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH mptcp-next v3 2/2] selftests: mptcp: convert iptables to nftables for mptcp_join.sh
2026-09-04 7:31 [PATCH mptcp-next v3 0/2] selftests: mptcp: convert iptables to nftables Hangbin Liu
2026-09-04 7:31 ` [PATCH mptcp-next v3 1/2] selftests: mptcp: convert iptables to nftables for mptcp_sockopt.sh Hangbin Liu
@ 2026-09-04 7:31 ` Hangbin Liu
2026-09-04 7:42 ` sashiko-bot
2026-09-04 8:41 ` [PATCH mptcp-next v3 0/2] selftests: mptcp: convert iptables to nftables MPTCP CI
2 siblings, 1 reply; 6+ messages in thread
From: Hangbin Liu @ 2026-09-04 7:31 UTC (permalink / raw)
To: MPTCP Linux; +Cc: Hangbin Liu, Hangbin Liu
From: Hangbin Liu <liuhangbin@kylinos.cn>
During conversion, we retain the same table and chain names used by the
original iptables/ip6tables setup, so rule output is identical to the
former iptables/ip6tables output. Add new function init_nftables so we
only do nft table setup when test need set nft rules.
Unlike iptables, nftables cannot match rules based on their full
specification. Some test need to delete the rules we add, so add
variable nft_handle and reset it before adding nf tables.
The BPF bytecode matching MPTCP add‑addr and remove‑addr suboptions
is replaced with native nft matching using "tcp option mptcp subtype".
The config file adds CONFIG_NFT_NUMGEN (replaces iptables statistic nth),
CONFIG_NFT_REJECT and CONFIG_NFT_REJECT_INET for reject‑related rules.
Remove CONFIG_NFT_COMPAT since we don't need it now.
Remove the iptables/ip6tables check in mptcp_lib.sh since no script use
it now.
Signed-off-by: Hangbin Liu <liuhangbin@kylinos.cn>
---
tools/testing/selftests/net/mptcp/config | 4 +-
tools/testing/selftests/net/mptcp/mptcp_join.sh | 158 ++++++++++--------------
tools/testing/selftests/net/mptcp/mptcp_lib.sh | 2 +-
3 files changed, 71 insertions(+), 93 deletions(-)
diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config
index 59051ee2a986..25dd134b9907 100644
--- a/tools/testing/selftests/net/mptcp/config
+++ b/tools/testing/selftests/net/mptcp/config
@@ -29,7 +29,9 @@ CONFIG_NET_SCH_INGRESS=m
CONFIG_NET_SCH_NETEM=m
CONFIG_NF_TABLES=m
CONFIG_NF_TABLES_INET=y
-CONFIG_NFT_COMPAT=m
+CONFIG_NFT_NUMGEN=m
+CONFIG_NFT_REJECT=m
+CONFIG_NFT_REJECT_INET=m
CONFIG_NFT_SOCKET=m
CONFIG_NFT_TPROXY=m
CONFIG_SYN_COOKIES=y
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 18ce7136a2b0..835cb92cab1a 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -26,8 +26,6 @@ capout=""
cappid=""
ns1=""
ns2=""
-iptables="iptables"
-ip6tables="ip6tables"
timeout_poll=30
timeout_test=$((timeout_poll * 2 + 1))
capture=false
@@ -50,6 +48,7 @@ declare -A failed_tests
MPTCP_LIB_TEST_FORMAT="%03u %s\n"
TEST_NAME=""
nr_blank=6
+nft_handle=""
# These var are used only in some tests, make sure they are not already set
unset FAILING_LINKS
@@ -99,42 +98,6 @@ unset add_addr_tx_nr
unset add_addr_echo_tx_nr
unset add_addr_drop_tx_nr
-# generated using "nfbpf_compile '(ip && (ip[54] & 0xf0) == 0x30) ||
-# (ip6 && (ip6[74] & 0xf0) == 0x30)'"
-CBPF_MPTCP_SUBOPTION_ADD_ADDR="14,
- 48 0 0 0,
- 84 0 0 240,
- 21 0 3 64,
- 48 0 0 54,
- 84 0 0 240,
- 21 6 7 48,
- 48 0 0 0,
- 84 0 0 240,
- 21 0 4 96,
- 48 0 0 74,
- 84 0 0 240,
- 21 0 1 48,
- 6 0 0 65535,
- 6 0 0 0"
-
-# IPv4: TCP hdr of 48B, a first suboption of 12B (DACK8), the RM_ADDR suboption
-# generated using "nfbpf_compile '(ip[32] & 0xf0) == 0xc0 && ip[53] == 0x0c &&
-# (ip[66] & 0xf0) == 0x40'"
-CBPF_MPTCP_SUBOPTION_RM_ADDR="13,
- 48 0 0 0,
- 84 0 0 240,
- 21 0 9 64,
- 48 0 0 32,
- 84 0 0 240,
- 21 0 6 192,
- 48 0 0 53,
- 21 0 4 12,
- 48 0 0 66,
- 84 0 0 240,
- 21 0 1 64,
- 6 0 0 65535,
- 6 0 0 0"
-
init_partial()
{
capout=$(mktemp)
@@ -184,6 +147,28 @@ init_shapers()
done
}
+init_nftables()
+{
+ nft_handle=""
+
+ local netns table
+ for netns in "$ns1" "$ns2"; do
+ for table in ip ip6; do
+ ip netns exec "$netns" nft -f - <<-EOF
+ add table $table filter
+ add chain $table filter INPUT \
+ { type filter hook input priority filter; policy accept; }
+ add chain $table filter OUTPUT \
+ { type filter hook output priority filter; policy accept; }
+
+ table $table mangle
+ chain $table mangle OUTPUT \
+ { type route hook output priority mangle; policy accept; }
+ EOF
+ done
+ done
+}
+
cleanup_partial()
{
rm -f "$capout"
@@ -196,7 +181,7 @@ init() {
mptcp_lib_check_mptcp
mptcp_lib_check_kallsyms
- mptcp_lib_check_tools ip tc ss "${iptables}" "${ip6tables}"
+ mptcp_lib_check_tools ip tc ss nft jq
sin=$(mktemp)
sout=$(mktemp)
@@ -380,24 +365,18 @@ reset_with_cookies()
# $1: test name
reset_with_add_addr_timeout()
{
- local ip="${2:-4}"
- local tables
+ local ip="${2:-}"
reset "${1}" || return 1
-
- tables="${iptables}"
- if [ $ip -eq 6 ]; then
- tables="${ip6tables}"
- fi
+ init_nftables
# set a maximum, to avoid too long timeout with exponential backoff
ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1
- if ! ip netns exec $ns2 $tables -A OUTPUT -p tcp \
- -m tcp --tcp-option 30 \
- -m bpf --bytecode \
- "$CBPF_MPTCP_SUBOPTION_ADD_ADDR" \
- -j DROP; then
+ if ! ip netns exec "$ns2" nft add rule \
+ ip"$ip" filter OUTPUT meta l4proto tcp \
+ tcp option mptcp subtype add-addr \
+ drop; then
mark_as_skipped "unable to set the 'add addr' rule"
return 1
fi
@@ -449,22 +428,14 @@ setup_fail_rules()
check_invert=1
validate_checksum=true
local i="$1"
- local ip="${2:-4}"
- local tables
+ local ip="${2:-}"
- tables="${iptables}"
- if [ $ip -eq 6 ]; then
- tables="${ip6tables}"
- fi
-
- ip netns exec $ns2 $tables \
- -t mangle \
- -A OUTPUT \
- -o ns2eth$i \
- -p tcp \
- -m length --length 150:9999 \
- -m statistic --mode nth --packet 1 --every 99999 \
- -j MARK --set-mark 42 || return ${KSFT_SKIP}
+ init_nftables
+ ip netns exec "$ns2" nft add rule \
+ ip"$ip" mangle OUTPUT oifname ns2eth$i \
+ meta l4proto tcp \
+ meta length 150-9999 numgen inc mod 99999 1 \
+ meta mark set 42 || return ${KSFT_SKIP}
tc -n $ns2 qdisc add dev ns2eth$i clsact || return ${KSFT_SKIP}
tc -n $ns2 filter add dev ns2eth$i egress \
@@ -510,16 +481,19 @@ reset_with_tcp_filter()
reset "${1}" || return 1
shift
+ init_nftables
+
local ns="${!1}"
local src="${2}"
local target="${3}"
local chain="${4:-INPUT}"
- if ! ip netns exec "${ns}" ${iptables} \
- -A "${chain}" \
- -s "${src}" \
- -p tcp \
- -j "${target}"; then
+ # Capture nft handle as endpoint_tests() need it
+ nft_handle=$(ip netns exec "$ns" nft -e --json add rule \
+ ip filter "${chain}" ip saddr "${src}" \
+ meta l4proto tcp "${target,,}" | \
+ jq '.nftables[] | select(has("add")) | .add.rule.handle')
+ if [ -z "$nft_handle" ]; then
mark_as_skipped "unable to set the filter rules"
return 1
fi
@@ -4313,12 +4287,15 @@ userspace_tests()
chk_mptcp_info subflows 1 subflows 1
chk_subflows_total 2 2
+ init_nftables
# force quick loss
ip netns exec $ns2 sysctl -q net.ipv4.tcp_syn_retries=1
- if ip netns exec "${ns1}" ${iptables} -A INPUT -s "10.0.1.2" \
- -p tcp --tcp-option 30 -j REJECT --reject-with tcp-reset &&
- ip netns exec "${ns2}" ${iptables} -A INPUT -d "10.0.1.2" \
- -p tcp --tcp-option 30 -j REJECT --reject-with tcp-reset; then
+ if ip netns exec "${ns1}" nft add rule ip filter INPUT \
+ ip saddr "10.0.1.2" meta l4proto tcp \
+ tcp option mptcp exists reject with tcp reset &&
+ ip netns exec "${ns2}" nft add rule ip filter INPUT \
+ ip daddr "10.0.1.2" meta l4proto tcp \
+ tcp option mptcp exists reject with tcp reset; then
wait_event ns2 MPTCP_LIB_EVENT_SUB_CLOSED 1
wait_event ns1 MPTCP_LIB_EVENT_SUB_CLOSED 1
chk_subflows_total 1 1
@@ -4393,7 +4370,7 @@ endpoint_tests()
chk_subflow_nr "after new reject" 2
chk_mptcp_info subflows 1 subflows 1
- ip netns exec "${ns2}" ${iptables} -D OUTPUT -s "10.0.3.2" -p tcp -j REJECT
+ ip netns exec "${ns2}" nft delete rule ip filter OUTPUT handle "$nft_handle"
pm_nl_del_endpoint $ns2 3 10.0.3.2
pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow
wait_mpj 3
@@ -4402,12 +4379,10 @@ endpoint_tests()
# To make sure RM_ADDR are sent over a different subflow, but
# allow the rest to quickly and cleanly close the subflow
- local ipt=1
- ip netns exec "${ns2}" ${iptables} -I OUTPUT -s "10.0.1.2" \
- -p tcp -m tcp --tcp-option 30 \
- -m bpf --bytecode \
- "$CBPF_MPTCP_SUBOPTION_RM_ADDR" \
- -j DROP || ipt=0
+ nft_handle=$(ip netns exec "${ns2}" nft -e --json insert rule \
+ ip filter OUTPUT ip saddr 10.0.1.2 meta l4proto tcp \
+ tcp option mptcp subtype remove-addr drop | \
+ jq '.nftables[] | select(has("insert")) | .insert.rule.handle')
local i
for i in $(seq 3); do
pm_nl_del_endpoint $ns2 1 10.0.1.2
@@ -4420,7 +4395,8 @@ endpoint_tests()
chk_subflow_nr "after re-add id 0 ($i)" 3
chk_mptcp_info subflows 3 subflows 3
done
- [ ${ipt} = 1 ] && ip netns exec "${ns2}" ${iptables} -D OUTPUT 1
+ [ -n "${nft_handle}" ] && ip netns exec "${ns2}" nft delete rule \
+ ip filter OUTPUT handle "${nft_handle}"
mptcp_lib_kill_group_wait $tests_pid
@@ -4480,20 +4456,20 @@ endpoint_tests()
chk_mptcp_info subflows 2 subflows 2
chk_mptcp_info add_addr_signal 2 add_addr_accepted 2
+ init_nftables
# To make sure RM_ADDR are sent over a different subflow, but
# allow the rest to quickly and cleanly close the subflow
- local ipt=1
- ip netns exec "${ns1}" ${iptables} -I OUTPUT -s "10.0.1.1" \
- -p tcp -m tcp --tcp-option 30 \
- -m bpf --bytecode \
- "$CBPF_MPTCP_SUBOPTION_RM_ADDR" \
- -j DROP || ipt=0
+ nft_handle=$(ip netns exec "${ns1}" nft -e --json insert rule \
+ ip filter OUTPUT ip saddr 10.0.1.1 meta l4proto tcp \
+ tcp option mptcp subtype remove-addr drop | \
+ jq '.nftables[] | select(has("insert")) | .insert.rule.handle')
pm_nl_del_endpoint $ns1 42 10.0.1.1
sleep 0.5
chk_subflow_nr "after delete ID 0" 2
chk_mptcp_info subflows 2 subflows 2
chk_mptcp_info add_addr_signal 2 add_addr_accepted 2
- [ ${ipt} = 1 ] && ip netns exec "${ns1}" ${iptables} -D OUTPUT 1
+ [ -n "${nft_handle}" ] && ip netns exec "${ns1}" nft delete rule \
+ ip filter OUTPUT handle "${nft_handle}"
pm_nl_add_endpoint $ns1 10.0.1.1 id 42 flags signal
wait_mpj 4
@@ -4555,7 +4531,7 @@ endpoint_tests()
pm_nl_flush_endpoint $ns2
pm_nl_flush_endpoint $ns1
wait_rm_addr $ns2 0
- ip netns exec "${ns2}" ${iptables} -D OUTPUT -s "10.0.3.2" -p tcp -j REJECT
+ ip netns exec "${ns2}" nft delete rule ip filter OUTPUT handle "$nft_handle"
pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow
wait_mpj 1
pm_nl_add_endpoint $ns1 10.0.3.1 id 2 flags signal
diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
index e65b4ebee06a..0559bb168203 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -528,7 +528,7 @@ mptcp_lib_check_tools() {
exit ${KSFT_SKIP}
fi
;;
- "iptables"* | "ip6tables"* | "nft" | "jq")
+ "nft" | "jq")
if ! "${tool}" -V &> /dev/null; then
mptcp_lib_pr_skip "Could not run all tests without ${tool}"
exit ${KSFT_SKIP}
--
2.55.0
^ permalink raw reply related [flat|nested] 6+ messages in thread