BPF List
 help / color / mirror / Atom feed
* [PATCH v3] selftests/bpf: convert lirc_mode2 to prog_tests and extend coverage
@ 2026-08-20 21:43 Sean Young
  2026-08-20 21:54 ` sashiko-bot
  2026-08-20 22:34 ` bot+bpf-ci
  0 siblings, 2 replies; 3+ messages in thread
From: Sean Young @ 2026-08-20 21:43 UTC (permalink / raw)
  To: linux-kernel, Andrii Nakryiko, Eduard Zingerman, Ihor Solodrai,
	Alexei Starovoitov, Daniel Borkmann, Kumar Kartikeya Dwivedi,
	Martin KaFai Lau, Song Liu, Yonghong Song, Jiri Olsa,
	Emil Tsalapatis, Shuah Khan
  Cc: Sean Young, bpf, linux-kselftest

While porting, extend coverage of the BPF_LIRC_MODE2 attach/detach/
query API:

 - bpf_prog_attach() with invalid flags is rejected with -EINVAL
   and does not attach the program
 - bpf_prog_query() with invalid flags is rejected with -EINVAL
   without disturbing existing attachments
 - bpf_prog_query() reports the correct program id, not just count,
   at each step, via bpf_prog_get_info_by_fd()
 - a lirc chardev can hold more than one attached program: load a
   second, independent instance, attach it alongside the first,
   confirm both are reported by bpf_prog_query(), then detach it
   without disturbing the first program's attachment
 - detaching an already-detached program consistently fails with
   -ENOENT, for both the first and second program

Signed-off-by: Sean Young <sean@mess.org>
Assisted-by: Claude:claude-sonnet-5
---
Since v2:
 - Fix compilation bug - I sent the wrong version

Since v1:
 - Remove obsolete test_lirc_mode2_user.c file
 - Use SYS_NOFAIL() rather than system()
 - Fix comment formatting
 - Fix leaks in error paths

 tools/testing/selftests/bpf/.gitignore        |   1 -
 tools/testing/selftests/bpf/Makefile          |   3 -
 .../selftests/bpf/prog_tests/lirc_mode2.c     | 334 ++++++++++++++++++
 .../testing/selftests/bpf/progs/lirc_mode2.c  |  32 ++
 .../bpf/progs/test_lirc_mode2_kern.c          |  26 --
 .../testing/selftests/bpf/test_lirc_mode2.sh  |  41 ---
 .../selftests/bpf/test_lirc_mode2_user.c      | 177 ----------
 7 files changed, 366 insertions(+), 248 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/lirc_mode2.c
 create mode 100644 tools/testing/selftests/bpf/progs/lirc_mode2.c
 delete mode 100644 tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c
 delete mode 100755 tools/testing/selftests/bpf/test_lirc_mode2.sh
 delete mode 100644 tools/testing/selftests/bpf/test_lirc_mode2_user.c

diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 986a6389186b..b815bf0d8877 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -17,7 +17,6 @@ test_verifier_log
 feature
 urandom_read
 test_sockmap
-test_lirc_mode2_user
 flow_dissector_load
 test_tcpnotify_user
 test_libbpf
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 2b2f93dec474..f8ec0f574559 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -123,7 +123,6 @@ TEST_FILES = xsk_prereqs.sh $(wildcard progs/btf_dump_test_case_*.c)
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
-	test_lirc_mode2.sh \
 	test_bpftool_build.sh \
 	test_doc_build.sh \
 	test_xsk.sh \
@@ -141,7 +140,6 @@ TEST_GEN_PROGS_EXTENDED = \
 	bench \
 	flow_dissector_load \
 	test_cpp \
-	test_lirc_mode2_user \
 	veristat \
 	xdp_features \
 	xdp_hw_metadata \
@@ -338,7 +336,6 @@ $(OUTPUT)/test_sockmap: $(CGROUP_HELPERS) $(TESTING_HELPERS)
 $(OUTPUT)/test_tcpnotify_user: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(TRACE_HELPERS)
 $(OUTPUT)/test_sock_fields: $(CGROUP_HELPERS) $(TESTING_HELPERS)
 $(OUTPUT)/test_tag: $(TESTING_HELPERS)
-$(OUTPUT)/test_lirc_mode2_user: $(TESTING_HELPERS)
 $(OUTPUT)/flow_dissector_load: $(TESTING_HELPERS)
 $(OUTPUT)/test_maps: $(TESTING_HELPERS)
 $(OUTPUT)/test_verifier: $(TESTING_HELPERS) $(CAP_HELPERS) $(UNPRIV_HELPERS)
diff --git a/tools/testing/selftests/bpf/prog_tests/lirc_mode2.c b/tools/testing/selftests/bpf/prog_tests/lirc_mode2.c
new file mode 100644
index 000000000000..7b7352dbcd82
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/lirc_mode2.c
@@ -0,0 +1,334 @@
+// SPDX-License-Identifier: GPL-2.0
+// test ir decoder
+//
+// Copyright (C) 2018 Sean Young <sean@mess.org>
+
+// A lirc chardev is a device representing a consumer IR (cir) device which
+// can receive infrared signals from remote control and/or transmit IR.
+//
+// IR is sent as a series of pulses and space somewhat like morse code. The
+// BPF program can decode this into scancodes so that rc-core can translate
+// this into input key codes using the rc keymap.
+//
+// This test works by sending IR over rc-loopback, so the IR is processed by
+// BPF and then decoded into scancodes. The lirc chardev must be the one
+// associated with rc-loopback, see the output of ir-keytable(1).
+//
+// The following CONFIG options must be enabled for the test to succeed:
+// CONFIG_RC_CORE=y
+// CONFIG_BPF_LIRC_MODE2=y
+// CONFIG_RC_LOOPBACK=y
+// CONFIG_LIRC=y
+
+#include <linux/input.h>
+#include <linux/lirc.h>
+#include <glob.h>
+#include <limits.h>
+#include <poll.h>
+#include <test_progs.h>
+#include "lirc_mode2.skel.h"
+
+/*
+ * Read the DEVNAME= line out of the first uevent file that matches
+ * pattern, and turn it into a /dev/<name> path.
+ */
+static bool find_devname(const char *pattern, char *path, size_t path_sz)
+{
+	glob_t gl = {};
+	bool found = false;
+	FILE *f;
+
+	if (glob(pattern, 0, NULL, &gl) || gl.gl_pathc == 0)
+		goto out;
+
+	f = fopen(gl.gl_pathv[0], "r");
+	if (!f)
+		goto out;
+
+	char line[256];
+
+	while (fgets(line, sizeof(line), f)) {
+		char *val;
+
+		if (strncmp(line, "DEVNAME=", 8))
+			continue;
+
+		val = line + 8;
+		val[strcspn(val, "\n")] = '\0';
+		snprintf(path, path_sz, "/dev/%s", val);
+		found = true;
+		break;
+	}
+
+	fclose(f);
+out:
+	globfree(&gl);
+	return found;
+}
+
+/* Load rc-loopback and find the lirc and input chardevs it created. */
+static bool find_loopback_devices(char *lirc_path, char *input_path,
+				  size_t path_sz)
+{
+	glob_t gl = {};
+	bool found = false;
+
+	/* Ignore failure, we check for the resulting devices below. */
+	SYS_NOFAIL("modprobe rc-loopback > /dev/null 2>&1");
+
+	if (glob("/sys/class/rc/rc*", 0, NULL, &gl))
+		goto out;
+
+	for (size_t i = 0; i < gl.gl_pathc; i++) {
+		const char *rcdir = gl.gl_pathv[i];
+		char uevent_path[PATH_MAX];
+		char uevent[4096];
+		char pattern[PATH_MAX];
+		FILE *f;
+		size_t n;
+
+		snprintf(uevent_path, sizeof(uevent_path), "%s/uevent", rcdir);
+		f = fopen(uevent_path, "r");
+		if (!f)
+			continue;
+		n = fread(uevent, 1, sizeof(uevent) - 1, f);
+		fclose(f);
+		uevent[n] = '\0';
+
+		if (!strstr(uevent, "DRV_NAME=rc-loopback"))
+			continue;
+
+		snprintf(pattern, sizeof(pattern), "%s/lirc*/uevent", rcdir);
+		if (!find_devname(pattern, lirc_path, path_sz))
+			continue;
+
+		snprintf(pattern, sizeof(pattern), "%s/input*/event*/uevent", rcdir);
+		if (!find_devname(pattern, input_path, path_sz))
+			continue;
+
+		found = true;
+		break;
+	}
+
+out:
+	if (!found) {
+		fprintf(stderr, "No rc devices found\n");
+		fprintf(stderr, "Enable CONFIG_RC_LOOPBACK and CONFIG_BPF_LIRC_MODE2\n");
+	}
+
+	globfree(&gl);
+	return found;
+}
+
+void test_lirc_mode2(void)
+{
+	char lirc_path[PATH_MAX], input_path[PATH_MAX];
+	int lircfd = -1, inputfd = -1, progfd, progfd2 = -1;
+	struct lirc_mode2 *skel = NULL, *skel2 = NULL;
+	__u32 prog_ids[10], prog_flags[10], prog_cnt;
+	struct bpf_prog_info info;
+	__u32 info_len, prog_id, prog_id2;
+	int testir1 = 0x8ead;	/* keydown flag (0x8000) | scancode 0xead */
+	int testir2 = 0x4081;	/* pointer_rel flag (0x4000) | rel_x=1 | rel_y=1 */
+	struct input_event event;
+	struct pollfd pfd = {};
+	int ret;
+
+	if (getuid() != 0) {
+		test__skip();
+		return;
+	}
+
+	if (!find_loopback_devices(lirc_path, input_path, sizeof(lirc_path))) {
+		test__skip();
+		return;
+	}
+
+	skel = lirc_mode2__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "lirc_mode2__open_and_load"))
+		return;
+
+	progfd = bpf_program__fd(skel->progs.bpf_decoder);
+
+	memset(&info, 0, sizeof(info));
+	info_len = sizeof(info);
+	ret = bpf_prog_get_info_by_fd(progfd, &info, &info_len);
+	if (!ASSERT_OK(ret, "get first program's info"))
+		goto out;
+	prog_id = info.id;
+
+	lircfd = open(lirc_path, O_RDWR | O_NONBLOCK);
+	if (!ASSERT_GE(lircfd, 0, "open lirc device"))
+		goto out;
+
+	/* Try to detach it before it was ever attached, should fail. */
+	ret = bpf_prog_detach2(progfd, lircfd, BPF_LIRC_MODE2);
+	if (!ASSERT_EQ(ret, -ENOENT, "detach unattached program"))
+		goto out;
+
+	inputfd = open(input_path, O_RDONLY | O_NONBLOCK);
+	if (!ASSERT_GE(inputfd, 0, "open input device"))
+		goto out;
+
+	prog_cnt = ARRAY_SIZE(prog_ids);
+	ret = bpf_prog_query(lircfd, BPF_LIRC_MODE2, 0, prog_flags, prog_ids,
+			     &prog_cnt);
+	if (!ASSERT_OK(ret, "query programs before attach"))
+		goto out;
+	if (!ASSERT_EQ(prog_cnt, 0, "no programs should be attached yet"))
+		goto out;
+
+	/* Invalid attach flags must be rejected, and must not attach. */
+	ret = bpf_prog_attach(progfd, lircfd, BPF_LIRC_MODE2, 1);
+	if (!ASSERT_EQ(ret, -EINVAL, "attach with invalid flags"))
+		goto out;
+
+	prog_cnt = ARRAY_SIZE(prog_ids);
+	ret = bpf_prog_query(lircfd, BPF_LIRC_MODE2, 0, prog_flags, prog_ids,
+			     &prog_cnt);
+	if (!ASSERT_OK(ret, "query programs after rejected attach"))
+		goto out;
+	if (!ASSERT_EQ(prog_cnt, 0, "rejected attach should not attach"))
+		goto out;
+
+	ret = bpf_prog_attach(progfd, lircfd, BPF_LIRC_MODE2, 0);
+	if (!ASSERT_OK(ret, "attach program to lirc device"))
+		goto out;
+
+	/* Invalid query flags must be rejected too, without upsetting state. */
+	prog_cnt = ARRAY_SIZE(prog_ids);
+	ret = bpf_prog_query(lircfd, BPF_LIRC_MODE2, 1, prog_flags, prog_ids,
+			     &prog_cnt);
+	ASSERT_EQ(ret, -EINVAL, "query with invalid flags");
+
+	prog_cnt = ARRAY_SIZE(prog_ids);
+	ret = bpf_prog_query(lircfd, BPF_LIRC_MODE2, 0, prog_flags, prog_ids,
+			     &prog_cnt);
+	if (!ASSERT_OK(ret, "query programs after attach"))
+		goto out_detach;
+	if (!ASSERT_EQ(prog_cnt, 1, "one program should be attached"))
+		goto out_detach;
+	ASSERT_EQ(prog_ids[0], prog_id, "queried id should match attached program");
+
+	/* Write raw IR */
+	ret = write(lircfd, &testir1, sizeof(testir1));
+	if (!ASSERT_EQ(ret, sizeof(testir1), "send test IR message 1"))
+		goto out_detach;
+
+	pfd.fd = inputfd;
+	pfd.events = POLLIN;
+
+	for (;;) {
+		poll(&pfd, 1, 100);
+
+		/* Read decoded IR */
+		ret = read(inputfd, &event, sizeof(event));
+		if (!ASSERT_EQ(ret, sizeof(event), "read decoded IR 1"))
+			goto out_detach;
+
+		if (event.type == EV_MSC && event.code == MSC_SCAN &&
+		    event.value == 0xead)
+			break;
+	}
+
+	/* Write raw IR */
+	ret = write(lircfd, &testir2, sizeof(testir2));
+	if (!ASSERT_EQ(ret, sizeof(testir2), "send test IR message 2"))
+		goto out_detach;
+
+	for (;;) {
+		poll(&pfd, 1, 100);
+
+		/* Read decoded IR */
+		ret = read(inputfd, &event, sizeof(event));
+		if (!ASSERT_EQ(ret, sizeof(event), "read decoded IR 2"))
+			goto out_detach;
+
+		if (event.type == EV_REL && event.code == REL_Y &&
+		    event.value == 1)
+			break;
+	}
+
+	prog_cnt = ARRAY_SIZE(prog_ids);
+	ret = bpf_prog_query(lircfd, BPF_LIRC_MODE2, 0, prog_flags, prog_ids,
+			     &prog_cnt);
+	if (!ASSERT_OK(ret, "query programs after IR was decoded"))
+		goto out_detach;
+	if (!ASSERT_EQ(prog_cnt, 1, "one program should still be attached"))
+		goto out_detach;
+
+	/*
+	 * The lirc chardev can hold more than one attached program at once.
+	 * Load a second, independent instance and check it can be attached
+	 * alongside the first, queried, and then detached on its own
+	 * without disturbing the first program's attachment.
+	 */
+	skel2 = lirc_mode2__open_and_load();
+	if (!ASSERT_OK_PTR(skel2, "lirc_mode2__open_and_load (2nd)"))
+		goto out_detach;
+
+	progfd2 = bpf_program__fd(skel2->progs.bpf_decoder);
+
+	memset(&info, 0, sizeof(info));
+	info_len = sizeof(info);
+	ret = bpf_prog_get_info_by_fd(progfd2, &info, &info_len);
+	if (!ASSERT_OK(ret, "get second program's info"))
+		goto out_detach;
+	prog_id2 = info.id;
+
+	ret = bpf_prog_attach(progfd2, lircfd, BPF_LIRC_MODE2, 0);
+	if (!ASSERT_OK(ret, "attach second program to lirc device"))
+		goto out_detach;
+
+	prog_cnt = ARRAY_SIZE(prog_ids);
+	ret = bpf_prog_query(lircfd, BPF_LIRC_MODE2, 0, prog_flags, prog_ids,
+			     &prog_cnt);
+	if (!ASSERT_OK(ret, "query programs after second attach"))
+		goto out_detach2;
+	if (!ASSERT_EQ(prog_cnt, 2, "two programs should be attached"))
+		goto out_detach2;
+	ASSERT_TRUE((prog_ids[0] == prog_id && prog_ids[1] == prog_id2) ||
+		    (prog_ids[0] == prog_id2 && prog_ids[1] == prog_id),
+		    "queried ids should be the two attached programs");
+
+	/* Detach the second program; the first should remain attached. */
+	ret = bpf_prog_detach2(progfd2, lircfd, BPF_LIRC_MODE2);
+	if (!ASSERT_OK(ret, "detach second program"))
+		goto out_detach2;
+
+	/* Detaching an already-detached program should now fail. */
+	ret = bpf_prog_detach2(progfd2, lircfd, BPF_LIRC_MODE2);
+	ASSERT_EQ(ret, -ENOENT, "detach second program again");
+
+	prog_cnt = ARRAY_SIZE(prog_ids);
+	ret = bpf_prog_query(lircfd, BPF_LIRC_MODE2, 0, prog_flags, prog_ids,
+			     &prog_cnt);
+	if (!ASSERT_OK(ret, "query programs after second detach"))
+		goto out_detach;
+	if (!ASSERT_EQ(prog_cnt, 1, "one program should remain attached"))
+		goto out_detach;
+	ASSERT_EQ(prog_ids[0], prog_id, "remaining program should be the first one");
+
+out_detach:
+	/* Let's try detaching it now it is actually attached. */
+	ret = bpf_prog_detach2(progfd, lircfd, BPF_LIRC_MODE2);
+	ASSERT_OK(ret, "detach program from lirc device");
+
+	/* Detaching it again should now fail the same way. */
+	ret = bpf_prog_detach2(progfd, lircfd, BPF_LIRC_MODE2);
+	ASSERT_EQ(ret, -ENOENT, "detach program from lirc device again");
+	goto out;
+
+out_detach2:
+	/* Best-effort cleanup of the second program before bailing out. */
+	bpf_prog_detach2(progfd2, lircfd, BPF_LIRC_MODE2);
+	goto out_detach;
+
+out:
+	if (inputfd >= 0)
+		close(inputfd);
+	if (lircfd >= 0)
+		close(lircfd);
+	lirc_mode2__destroy(skel2);
+	lirc_mode2__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/lirc_mode2.c b/tools/testing/selftests/bpf/progs/lirc_mode2.c
new file mode 100644
index 000000000000..98137f3c5c03
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/lirc_mode2.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+// test ir decoder
+//
+// Copyright (C) 2018 Sean Young <sean@mess.org>
+
+#include <linux/bpf.h>
+#include <linux/lirc.h>
+#include <bpf/bpf_helpers.h>
+
+SEC("lirc_mode2")
+int bpf_decoder(unsigned int *sample)
+{
+	if (LIRC_IS_PULSE(*sample)) {
+		unsigned int duration = LIRC_VALUE(*sample);
+
+		/*
+		 * Flag bits picked deliberately low: rc-loopback simulates
+		 * a receiver overflow for any pulse over MS_TO_US(50) (see
+		 * loop_tx_ir() in rc-loopback.c), which would silently
+		 * swallow the sample before it ever reaches this decoder.
+		 */
+		if (duration & 0x8000)
+			bpf_rc_keydown(sample, 0x40, duration & 0x3fff, 0);
+		if (duration & 0x4000)
+			bpf_rc_pointer_rel(sample, (duration >> 7) & 0x7f,
+					   duration & 0x7f);
+	}
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c b/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c
deleted file mode 100644
index cbe4284c032f..000000000000
--- a/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c
+++ /dev/null
@@ -1,26 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// test ir decoder
-//
-// Copyright (C) 2018 Sean Young <sean@mess.org>
-
-#include <linux/bpf.h>
-#include <linux/lirc.h>
-#include <bpf/bpf_helpers.h>
-
-SEC("lirc_mode2")
-int bpf_decoder(unsigned int *sample)
-{
-	if (LIRC_IS_PULSE(*sample)) {
-		unsigned int duration = LIRC_VALUE(*sample);
-
-		if (duration & 0x1000)
-			bpf_rc_keydown(sample, 0x40, duration & 0xffff, 0);
-		if (duration & 0x2000)
-			bpf_rc_pointer_rel(sample, (duration >> 8) & 0xff,
-					   duration & 0xff);
-	}
-
-	return 0;
-}
-
-char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2.sh b/tools/testing/selftests/bpf/test_lirc_mode2.sh
deleted file mode 100755
index 5252b91f48a1..000000000000
--- a/tools/testing/selftests/bpf/test_lirc_mode2.sh
+++ /dev/null
@@ -1,41 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-ret=$ksft_skip
-
-msg="skip all tests:"
-if [ $UID != 0 ]; then
-	echo $msg please run this as root >&2
-	exit $ksft_skip
-fi
-
-GREEN='\033[0;92m'
-RED='\033[0;31m'
-NC='\033[0m' # No Color
-
-modprobe rc-loopback
-
-for i in /sys/class/rc/rc*
-do
-	if grep -q DRV_NAME=rc-loopback $i/uevent
-	then
-		LIRCDEV=$(grep DEVNAME= $i/lirc*/uevent | sed sQDEVNAME=Q/dev/Q)
-		INPUTDEV=$(grep DEVNAME= $i/input*/event*/uevent | sed sQDEVNAME=Q/dev/Q)
-	fi
-done
-
-if [ -n "$LIRCDEV" ];
-then
-	TYPE=lirc_mode2
-	./test_lirc_mode2_user $LIRCDEV $INPUTDEV
-	ret=$?
-	if [ $ret -ne 0 ]; then
-		echo -e ${RED}"FAIL: $TYPE"${NC}
-	else
-		echo -e ${GREEN}"PASS: $TYPE"${NC}
-	fi
-fi
-
-exit $ret
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_user.c b/tools/testing/selftests/bpf/test_lirc_mode2_user.c
deleted file mode 100644
index cd191da20d14..000000000000
--- a/tools/testing/selftests/bpf/test_lirc_mode2_user.c
+++ /dev/null
@@ -1,177 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// test ir decoder
-//
-// Copyright (C) 2018 Sean Young <sean@mess.org>
-
-// A lirc chardev is a device representing a consumer IR (cir) device which
-// can receive infrared signals from remote control and/or transmit IR.
-//
-// IR is sent as a series of pulses and space somewhat like morse code. The
-// BPF program can decode this into scancodes so that rc-core can translate
-// this into input key codes using the rc keymap.
-//
-// This test works by sending IR over rc-loopback, so the IR is processed by
-// BPF and then decoded into scancodes. The lirc chardev must be the one
-// associated with rc-loopback, see the output of ir-keytable(1).
-//
-// The following CONFIG options must be enabled for the test to succeed:
-// CONFIG_RC_CORE=y
-// CONFIG_BPF_RAWIR_EVENT=y
-// CONFIG_RC_LOOPBACK=y
-
-// Steps:
-// 1. Open the /dev/lircN device for rc-loopback (given on command line)
-// 2. Attach bpf_lirc_mode2 program which decodes some IR.
-// 3. Send some IR to the same IR device; since it is loopback, this will
-//    end up in the bpf program
-// 4. bpf program should decode IR and report keycode
-// 5. We can read keycode from same /dev/lirc device
-
-#include <linux/bpf.h>
-#include <linux/input.h>
-#include <errno.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <unistd.h>
-#include <poll.h>
-#include <sys/types.h>
-#include <sys/ioctl.h>
-#include <sys/stat.h>
-#include <fcntl.h>
-
-#include "bpf_util.h"
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-
-#include "testing_helpers.h"
-
-int main(int argc, char **argv)
-{
-	struct bpf_object *obj;
-	int ret, lircfd, progfd, inputfd;
-	int testir1 = 0x1ead;
-	int testir2 = 0x2101;
-	u32 prog_ids[10], prog_flags[10], prog_cnt;
-
-	if (argc != 3) {
-		printf("Usage: %s /dev/lircN /dev/input/eventM\n", argv[0]);
-		return 2;
-	}
-
-	ret = bpf_prog_test_load("test_lirc_mode2_kern.bpf.o",
-				 BPF_PROG_TYPE_LIRC_MODE2, &obj, &progfd);
-	if (ret) {
-		printf("Failed to load bpf program\n");
-		return 1;
-	}
-
-	lircfd = open(argv[1], O_RDWR | O_NONBLOCK);
-	if (lircfd == -1) {
-		printf("failed to open lirc device %s: %m\n", argv[1]);
-		return 1;
-	}
-
-	/* Let's try detach it before it was ever attached */
-	ret = bpf_prog_detach2(progfd, lircfd, BPF_LIRC_MODE2);
-	if (ret != -ENOENT) {
-		printf("bpf_prog_detach2 not attached should fail: %m\n");
-		return 1;
-	}
-
-	inputfd = open(argv[2], O_RDONLY | O_NONBLOCK);
-	if (inputfd == -1) {
-		printf("failed to open input device %s: %m\n", argv[1]);
-		return 1;
-	}
-
-	prog_cnt = 10;
-	ret = bpf_prog_query(lircfd, BPF_LIRC_MODE2, 0, prog_flags, prog_ids,
-			     &prog_cnt);
-	if (ret) {
-		printf("Failed to query bpf programs on lirc device: %m\n");
-		return 1;
-	}
-
-	if (prog_cnt != 0) {
-		printf("Expected nothing to be attached\n");
-		return 1;
-	}
-
-	ret = bpf_prog_attach(progfd, lircfd, BPF_LIRC_MODE2, 0);
-	if (ret) {
-		printf("Failed to attach bpf to lirc device: %m\n");
-		return 1;
-	}
-
-	/* Write raw IR */
-	ret = write(lircfd, &testir1, sizeof(testir1));
-	if (ret != sizeof(testir1)) {
-		printf("Failed to send test IR message: %m\n");
-		return 1;
-	}
-
-	struct pollfd pfd = { .fd = inputfd, .events = POLLIN };
-	struct input_event event;
-
-	for (;;) {
-		poll(&pfd, 1, 100);
-
-		/* Read decoded IR */
-		ret = read(inputfd, &event, sizeof(event));
-		if (ret != sizeof(event)) {
-			printf("Failed to read decoded IR: %m\n");
-			return 1;
-		}
-
-		if (event.type == EV_MSC && event.code == MSC_SCAN &&
-		    event.value == 0x1ead) {
-			break;
-		}
-	}
-
-	/* Write raw IR */
-	ret = write(lircfd, &testir2, sizeof(testir2));
-	if (ret != sizeof(testir2)) {
-		printf("Failed to send test IR message: %m\n");
-		return 1;
-	}
-
-	for (;;) {
-		poll(&pfd, 1, 100);
-
-		/* Read decoded IR */
-		ret = read(inputfd, &event, sizeof(event));
-		if (ret != sizeof(event)) {
-			printf("Failed to read decoded IR: %m\n");
-			return 1;
-		}
-
-		if (event.type == EV_REL && event.code == REL_Y &&
-		    event.value == 1 ) {
-			break;
-		}
-	}
-
-	prog_cnt = 10;
-	ret = bpf_prog_query(lircfd, BPF_LIRC_MODE2, 0, prog_flags, prog_ids,
-			     &prog_cnt);
-	if (ret) {
-		printf("Failed to query bpf programs on lirc device: %m\n");
-		return 1;
-	}
-
-	if (prog_cnt != 1) {
-		printf("Expected one program to be attached\n");
-		return 1;
-	}
-
-	/* Let's try detaching it now it is actually attached */
-	ret = bpf_prog_detach2(progfd, lircfd, BPF_LIRC_MODE2);
-	if (ret) {
-		printf("bpf_prog_detach2: returned %m\n");
-		return 1;
-	}
-
-	return 0;
-}
-- 
2.55.0


^ permalink raw reply related	[flat|nested] 3+ messages in thread

* Re: [PATCH v3] selftests/bpf: convert lirc_mode2 to prog_tests and extend coverage
  2026-08-20 21:43 [PATCH v3] selftests/bpf: convert lirc_mode2 to prog_tests and extend coverage Sean Young
@ 2026-08-20 21:54 ` sashiko-bot
  2026-08-20 22:34 ` bot+bpf-ci
  1 sibling, 0 replies; 3+ messages in thread
From: sashiko-bot @ 2026-08-20 21:54 UTC (permalink / raw)
  To: Sean Young; +Cc: bpf

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] Multi-line comments use C++ style `//` instead of the mandated kernel `/* ... */` format.
--

--- Patch [1]: [PATCH v3] selftests/bpf: convert lirc_mode2 to prog_tests and extend coverage ---
commit 5795d2e92debc935e217deb800d55dcb81234f7f
Author: Sean Young <sean@mess.org>

selftests/bpf: convert lirc_mode2 to prog_tests and extend coverage

This commit ports the lirc_mode2 test to the prog_tests framework and
extends coverage of the BPF_LIRC_MODE2 attach/detach/query APIs. It also
removes the obsolete user and kernel test files alongside the shell script.

> diff --git a/tools/testing/selftests/bpf/prog_tests/lirc_mode2.c b/tools/testing/selftests/bpf/prog_tests/lirc_mode2.c
> new file mode 100644
> index 0000000000000..7b7352dbcd826
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/prog_tests/lirc_mode2.c
> @@ -0,0 +1,334 @@
> +// SPDX-License-Identifier: GPL-2.0
> +// test ir decoder
> +//
> +// Copyright (C) 2018 Sean Young <sean@mess.org>
> +
> +// A lirc chardev is a device representing a consumer IR (cir) device which
> +// can receive infrared signals from remote control and/or transmit IR.
> +//
> +// IR is sent as a series of pulses and space somewhat like morse code. The
> +// BPF program can decode this into scancodes so that rc-core can translate
> +// this into input key codes using the rc keymap.

[Severity: Low]
This isn't a bug, but does this violate the BPF subsystem comment style?
Multi-line comments under the BPF subsystem generally require the standard
kernel C-style block comment format, with the opening /* on its own line.

Should these be converted to the /* ... */ format?

[ ... ]

> diff --git a/tools/testing/selftests/bpf/progs/lirc_mode2.c b/tools/testing/selftests/bpf/progs/lirc_mode2.c
> new file mode 100644
> index 0000000000000..98137f3c5c03d
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/progs/lirc_mode2.c
> @@ -0,0 +1,32 @@
> +// SPDX-License-Identifier: GPL-2.0
> +// test ir decoder
> +//
> +// Copyright (C) 2018 Sean Young <sean@mess.org>

[Severity: Low]
This isn't a bug, but this file header also uses the C++ style multi-line
comments instead of the preferred kernel block comment format.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260820214332.89030-1-sean@mess.org?part=1

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [PATCH v3] selftests/bpf: convert lirc_mode2 to prog_tests and extend coverage
  2026-08-20 21:43 [PATCH v3] selftests/bpf: convert lirc_mode2 to prog_tests and extend coverage Sean Young
  2026-08-20 21:54 ` sashiko-bot
@ 2026-08-20 22:34 ` bot+bpf-ci
  1 sibling, 0 replies; 3+ messages in thread
From: bot+bpf-ci @ 2026-08-20 22:34 UTC (permalink / raw)
  To: sean, linux-kernel, andrii, eddyz87, ihor.solodrai, ast, daniel,
	memxor, martin.lau, song, yonghong.song, jolsa, emil, shuah
  Cc: sean, bpf, linux-kselftest, ast, andrii, daniel, martin.lau,
	eddyz87, yonghong.song, clm, ihor.solodrai

[-- Attachment #1: Type: text/plain, Size: 4571 bytes --]

> diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
> index 986a6389186b..b815bf0d8877 100644
> --- a/tools/testing/selftests/bpf/.gitignore
> +++ b/tools/testing/selftests/bpf/.gitignore
> @@ -17,7 +17,6 @@ test_verifier_log
>  feature
>  urandom_read
>  test_sockmap
> -test_lirc_mode2_user
>  flow_dissector_load
>  test_tcpnotify_user
>  test_libbpf

[ ... ]

> diff --git a/tools/testing/selftests/bpf/prog_tests/lirc_mode2.c b/tools/testing/selftests/bpf/prog_tests/lirc_mode2.c
> new file mode 100644
> index 000000000000..7b7352dbcd82
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/prog_tests/lirc_mode2.c
> @@ -0,0 +1,334 @@

[ ... ]

> +// This test works by sending IR over rc-loopback, so the IR is processed by
> +// BPF and then decoded into scancodes. The lirc chardev must be the one
> +// associated with rc-loopback, see the output of ir-keytable(1).

This isn't a bug, but now that find_loopback_devices() discovers the
nodes itself, should the ir-keytable(1) sentence be reworded (or
dropped) so the header does not describe a manual step that no longer
exists?

> +//
> +// The following CONFIG options must be enabled for the test to succeed:
> +// CONFIG_RC_CORE=y
> +// CONFIG_BPF_LIRC_MODE2=y
> +// CONFIG_RC_LOOPBACK=y
> +// CONFIG_LIRC=y
> +
> +#include <linux/input.h>
> +#include <linux/lirc.h>

This isn't a bug, but is <linux/lirc.h> still needed in
prog_tests/lirc_mode2.c, or can it be dropped now that the raw-IR
values are written as plain ints?

> +#include <glob.h>
> +#include <limits.h>
> +#include <poll.h>
> +#include <test_progs.h>
> +#include "lirc_mode2.skel.h"
> +
> +/*
> + * Read the DEVNAME= line out of the first uevent file that matches
> + * pattern, and turn it into a /dev/<name> path.
> + */
> +static bool find_devname(const char *pattern, char *path, size_t path_sz)
> +{
> +	glob_t gl = {};
> +	bool found = false;
> +	FILE *f;
> +
> +	if (glob(pattern, 0, NULL, &gl) || gl.gl_pathc == 0)
> +		goto out;
> +
> +	f = fopen(gl.gl_pathv[0], "r");
> +	if (!f)
> +		goto out;
> +
> +	char line[256];

This isn't a bug, but could `char line[256]` move up with the other
locals at the top of find_devname(), to match the rest of the function?

> +
> +	while (fgets(line, sizeof(line), f)) {
> +		char *val;
> +
> +		if (strncmp(line, "DEVNAME=", 8))
> +			continue;
> +
> +		val = line + 8;
> +		val[strcspn(val, "\n")] = '\0';
> +		snprintf(path, path_sz, "/dev/%s", val);
> +		found = true;
> +		break;
> +	}
> +
> +	fclose(f);
> +out:
> +	globfree(&gl);
> +	return found;
> +}

[ ... ]

> commit 13acc020a68a79fa42ce134695e01654e17c1edf
> Author: Sean Young <sean@mess.org>
>
>     selftests/bpf: convert lirc_mode2 to prog_tests and extend coverage
>
>     While porting, extend coverage of the BPF_LIRC_MODE2 attach/detach/
>     query API:
>
>      - bpf_prog_attach() with invalid flags is rejected with -EINVAL
>        and does not attach the program
>      - bpf_prog_query() with invalid flags is rejected with -EINVAL
>        without disturbing existing attachments
>      - bpf_prog_query() reports the correct program id, not just count,
>        at each step, via bpf_prog_get_info_by_fd()
>      - a lirc chardev can hold more than one attached program: load a
>        second, independent instance, attach it alongside the first,
>        confirm both are reported by bpf_prog_query(), then detach it
>        without disturbing the first program's attachment
>      - detaching an already-detached program consistently fails with
>        -ENOENT, for both the first and second program

This isn't a bug, but could the changelog open with why the test is
being moved under test_progs, before listing the extra coverage that
was added while porting?

The changelog body starts at the secondary half of the change and
enumerates the new assertions, but never states the primary change or
its motivation. The conversion itself - deleting test_lirc_mode2.sh
plus test_lirc_mode2_user.c and the standalone TEST_PROGS/
TEST_GEN_PROGS_EXTENDED wiring, and re-adding the test as a prog_tests
entry with a skeleton - is what most of the diff does, and a reader
learns only what was added on top of it, not why running under
test_progs is preferable (single runner, DENYLIST/CI integration, no
separate binary to install).


---
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/32422213902

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2026-08-20 22:34 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-08-20 21:43 [PATCH v3] selftests/bpf: convert lirc_mode2 to prog_tests and extend coverage Sean Young
2026-08-20 21:54 ` sashiko-bot
2026-08-20 22:34 ` bot+bpf-ci

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox