[PATCH bpf-next v2] selftests/bpf: Track test_xdp_features DUT processes

[PATCH bpf-next v2] 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.

Track one active DUT at a time, wait for ss to report that exact PID with
a bounded retry loop, and reap it after each test. Consult the shell job
table before signaling the DUT so a stale PID cannot target an unrelated
process. On failure, terminate the shell job with SIGKILL and reap it so
blocked I/O cannot hang cleanup. Install an EXIT trap and signal handlers
so failure paths also remove network setup.

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 terminates a blocked DUT without affecting an unrelated process
---
Changes in v2:
- Clarify that avoiding name-wide process matching, rather than dropping a dependency, is the motivation.
- Track and reap one active DUT at a time instead of retaining historical PIDs.
- Address PID reuse by signaling only the current Bash job during cleanup.
- Use SIGKILL on failure cleanup so blocked DUT I/O cannot hang wait indefinitely.
- Link to v1: https://patch.msgid.link/20260805-xdp-dut-process-lifecycle-gmail-v1-1-45984df8d295@gmail.com
---
 tools/testing/selftests/bpf/test_xdp_features.sh | 82 ++++++++++++++++++------
 1 file changed, 62 insertions(+), 20 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_xdp_features.sh b/tools/testing/selftests/bpf/test_xdp_features.sh
index 0aa71c4455c0..35ce0d4e2418 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_pid=""
 
 setup() {
 	{
@@ -30,77 +31,118 @@ setup() {
 	} > /dev/null 2>&1
 }
 
+terminate_dut_server() {
+	[ -z "$dut_pid" ] && return
+
+	# Use the shell job instead of a PID which may have been reused.
+	if [ "$(jobs -pr %% 2> /dev/null)" = "$dut_pid" ]; then
+		kill -KILL %% 2> /dev/null || true
+	fi
+
+	wait "$dut_pid" 2> /dev/null || true
+	dut_pid=""
+}
+
 cleanup() {
-	ip link del v1 2> /dev/null
-	ip netns del ${NS} 2> /dev/null
-	[ "$(pidof xdp_features)" = "" ] || kill $(pidof xdp_features) 2> /dev/null
+	terminate_dut_server
+	ip link del v1 2> /dev/null || true
+	ip netns del "${NS}" 2> /dev/null || true
 }
 
 wait_for_dut_server() {
-	while sleep 1; do
-		ss -tlp | grep -q xdp_features
-		[ $? -eq 0 ] && break
+	local i
+
+	for ((i = 0; i < 10; i++)); do
+		if [ "$(jobs -pr %% 2> /dev/null)" != "$dut_pid" ]; then
+			echo "xdp_features server $dut_pid exited before accepting connections" >&2
+			return 1
+		fi
+
+		if ss -tlp 2> /dev/null | grep -q "pid=$dut_pid,"; then
+			return 0
+		fi
+
+		sleep 1
 	done
+
+	echo "Timed out waiting for xdp_features server $dut_pid" >&2
+	return 1
+}
+
+start_dut_server() {
+	./xdp_features "$@" &
+	dut_pid=$!
+	wait_for_dut_server
+}
+
+reap_dut_server() {
+	local status=0
+
+	wait "$dut_pid" || status=$?
+	dut_pid=""
+	return "$status"
 }
 
 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
+	reap_dut_server
 
 	## 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:$V1_IP4 \
 					   -T ::ffff:$V0_IP4 v0
 	[ $? -ne 0 ] && exit
+	reap_dut_server
 
 	## 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
+	reap_dut_server
 
 	## 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:$V1_IP4 \
 					   -T ::ffff:$V0_IP4 v0
 	[ $? -ne 0 ] && exit
+	reap_dut_server
 
 	## 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
+	reap_dut_server
 
 	## 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
+	reap_dut_server
 }
 
 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: 07cb86aa50816b070b99c89bf948762ef035a1f2
change-id: 20260805-xdp-dut-process-lifecycle-gmail-6d60bf8dcdf1

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

Re: [PATCH bpf-next v2] selftests/bpf: Track test_xdp_features DUT processes

[bot+bpf-ci]

[-- Attachment #1: Type: text/plain, Size: 1691 bytes --]

> diff --git a/tools/testing/selftests/bpf/test_xdp_features.sh b/tools/testing/selftests/bpf/test_xdp_features.sh
> index 0aa71c4455c0..35ce0d4e2418 100755
> --- a/tools/testing/selftests/bpf/test_xdp_features.sh
> +++ b/tools/testing/selftests/bpf/test_xdp_features.sh

[ ... ]

> +terminate_dut_server() {
> +	[ -z "$dut_pid" ] && return
> +
> +	# Use the shell job instead of a PID which may have been reused.
> +	if [ "$(jobs -pr %% 2> /dev/null)" = "$dut_pid" ]; then
> +		kill -KILL %% 2> /dev/null || true
> +	fi
> +
> +	wait "$dut_pid" 2> /dev/null || true
> +	dut_pid=""
> +}
> +
>  cleanup() {
> -	ip link del v1 2> /dev/null
> -	ip netns del ${NS} 2> /dev/null
> -	[ "$(pidof xdp_features)" = "" ] || kill $(pidof xdp_features) 2> /dev/null
> +	terminate_dut_server
> +	ip link del v1 2> /dev/null || true
> +	ip netns del "${NS}" 2> /dev/null || true
>  }

Jiayuan Chen asked about removing the pidof dependency in v1: "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)". Does the
removal of pidof serve another purpose beyond reducing dependencies, such as
fixing the concurrent test interference described in the commit message? If
the primary goal is fixing the race condition rather than removing a
dependency, it might be worth clarifying the motivation.


---
AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md

CI run summary: https://github.com/kernel-patches/bpf/actions/runs/31579454720