[PATCH bpf-next] selftests/bpf: Track test_xdp_features DUT processes

[PATCH bpf-next] selftests/bpf: Track test_xdp_features DUT processes

[Bochao Cao via B4 Relay]

From: Bochao Cao <bochaolucky@gmail.com>

test_xdp_features.sh waits for any xdp_features listener to appear and
uses pidof during cleanup. A concurrent test can therefore make another
test proceed before its own DUT is ready, and cleanup kills every
xdp_features process on the host. The readiness loop also has no timeout,
so a DUT that exits before listening leaves the test hung indefinitely.

Record each DUT PID when it is spawned, wait for ss to report that exact
PID with a bounded retry loop, and only terminate and reap recorded
children. Install an EXIT trap and signal handlers so failure paths also
remove child processes and network setup.

This also removes the runtime dependency on pidof.

Fixes: 4dba3e7852b7 ("selftests/bpf: introduce XDP compliance test tool")
Closes: https://bugs.debian.org/1136522
Signed-off-by: Bochao Cao <bochaolucky@gmail.com>
---
Tests:
- bash -n tools/testing/selftests/bpf/test_xdp_features.sh
- make -C tools/testing/selftests/bpf xdp_features
- sudo tools/testing/selftests/bpf/test_xdp_features.sh
- verified cleanup leaves an unrelated xdp_features process running
---
 tools/testing/selftests/bpf/test_xdp_features.sh | 60 ++++++++++++++++--------
 1 file changed, 40 insertions(+), 20 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_xdp_features.sh b/tools/testing/selftests/bpf/test_xdp_features.sh
index 0aa71c4..f3aa4d1 100755
--- a/tools/testing/selftests/bpf/test_xdp_features.sh
+++ b/tools/testing/selftests/bpf/test_xdp_features.sh
@@ -8,6 +8,7 @@ readonly V0_IP6=2001:db8::11
 readonly V1_IP6=2001:db8::1
 
 ret=1
+dut_pids=()
 
 setup() {
 	{
@@ -31,32 +32,53 @@ setup() {
 }
 
 cleanup() {
-	ip link del v1 2> /dev/null
-	ip netns del ${NS} 2> /dev/null
-	[ "$(pidof xdp_features)" = "" ] || kill $(pidof xdp_features) 2> /dev/null
+	for pid in "${dut_pids[@]}"; do
+		kill "$pid" 2> /dev/null || true
+		wait "$pid" 2> /dev/null || true
+	done
+	ip link del v1 2> /dev/null || true
+	ip netns del "${NS}" 2> /dev/null || true
 }
 
 wait_for_dut_server() {
-	while sleep 1; do
-		ss -tlp | grep -q xdp_features
-		[ $? -eq 0 ] && break
+	local pid=$1
+	local i
+
+	for ((i = 0; i < 10; i++)); do
+		if ! kill -0 "$pid" 2> /dev/null; then
+			echo "xdp_features server $pid exited before accepting connections" >&2
+			return 1
+		fi
+
+		if ss -tlp 2> /dev/null | grep -q "pid=$pid,"; then
+			return 0
+		fi
+
+		sleep 1
 	done
+
+	echo "Timed out waiting for xdp_features server $pid" >&2
+	return 1
+}
+
+start_dut_server() {
+	./xdp_features "$@" &
+	dut_pids+=("$!")
+	wait_for_dut_server "$!"
 }
 
 test_xdp_features() {
 	setup
 
 	## XDP_PASS
-	./xdp_features -f XDP_PASS -D $V1_IP6 -T $V0_IP6 v1 &
-	wait_for_dut_server
+	start_dut_server -f XDP_PASS -D $V1_IP6 -T $V0_IP6 v1
 	ip netns exec ${NS} ./xdp_features -t -f XDP_PASS \
 					   -D $V1_IP6 -C $V1_IP6 \
 					   -T $V0_IP6 v0
 	[ $? -ne 0 ] && exit
 
 	## XDP_DROP
-	./xdp_features -f XDP_DROP -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1 &
-	wait_for_dut_server
+	start_dut_server -f XDP_DROP -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1
 	ip netns exec ${NS} ./xdp_features -t -f XDP_DROP \
 					   -D ::ffff:$V1_IP4 \
 					   -C ::ffff:$V1_IP4 \
@@ -64,16 +86,14 @@ test_xdp_features() {
 	[ $? -ne 0 ] && exit
 
 	## XDP_ABORTED
-	./xdp_features -f XDP_ABORTED -D $V1_IP6 -T $V0_IP6 v1 &
-	wait_for_dut_server
+	start_dut_server -f XDP_ABORTED -D $V1_IP6 -T $V0_IP6 v1
 	ip netns exec ${NS} ./xdp_features -t -f XDP_ABORTED \
 					   -D $V1_IP6 -C $V1_IP6 \
 					   -T $V0_IP6 v0
 	[ $? -ne 0 ] && exit
 
 	## XDP_TX
-	./xdp_features -f XDP_TX -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1 &
-	wait_for_dut_server
+	start_dut_server -f XDP_TX -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1
 	ip netns exec ${NS} ./xdp_features -t -f XDP_TX \
 					   -D ::ffff:$V1_IP4 \
 					   -C ::ffff:$V1_IP4 \
@@ -81,26 +101,26 @@ test_xdp_features() {
 	[ $? -ne 0 ] && exit
 
 	## XDP_REDIRECT
-	./xdp_features -f XDP_REDIRECT -D $V1_IP6 -T $V0_IP6 v1 &
-	wait_for_dut_server
+	start_dut_server -f XDP_REDIRECT -D $V1_IP6 -T $V0_IP6 v1
 	ip netns exec ${NS} ./xdp_features -t -f XDP_REDIRECT \
 					   -D $V1_IP6 -C $V1_IP6 \
 					   -T $V0_IP6 v0
 	[ $? -ne 0 ] && exit
 
 	## XDP_NDO_XMIT
-	./xdp_features -f XDP_NDO_XMIT -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1 &
-	wait_for_dut_server
+	start_dut_server -f XDP_NDO_XMIT -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1
 	ip netns exec ${NS} ./xdp_features -t -f XDP_NDO_XMIT \
 					   -D ::ffff:$V1_IP4 \
 					   -C ::ffff:$V1_IP4 \
 					   -T ::ffff:$V0_IP4 v0
 	ret=$?
-	cleanup
 }
 
 set -e
-trap cleanup 2 3 6 9
+trap cleanup EXIT
+trap 'exit 129' HUP
+trap 'exit 130' INT
+trap 'exit 143' TERM
 
 test_xdp_features
 

---
base-commit: 6655c409707ec8ce9ce0850ffe4fe02331fd4d9c
change-id: 20260805-xdp-dut-process-lifecycle-gmail-6d60bf8dcdf1

Best regards,
--  
Bochao Cao <bochaolucky@gmail.com>

Re: [PATCH bpf-next] selftests/bpf: Track test_xdp_features DUT processes

[Jiayuan Chen]

On 8/5/26 3:29 PM, Bochao Cao via B4 Relay wrote:
> From: Bochao Cao <bochaolucky@gmail.com>
>
> test_xdp_features.sh waits for any xdp_features listener to appear and
> uses pidof during cleanup. A concurrent test can therefore make another
> test proceed before its own DUT is ready, and cleanup kills every
> xdp_features process on the host. The readiness loop also has no timeout,
> so a DUT that exits before listening leaves the test hung indefinitely.
>
> Record each DUT PID when it is spawned, wait for ss to report that exact
> PID with a bounded retry loop, and only terminate and reap recorded
> children. Install an EXIT trap and signal handlers so failure paths also
> remove child processes and network setup.
>
> This also removes the runtime dependency on pidof.
>
> Fixes: 4dba3e7852b7 ("selftests/bpf: introduce XDP compliance test tool")
> Closes: https://bugs.debian.org/1136522


It looks like part of the motivation here is dropping the pidof dependency?
I don't think that's worth optimizing. Selftests already require a bunch of
tools from non-essential packages (ip, ss and ethtool in this very script)