When using GCC on x86-64 to compile an usdt prog with -O1 or higher
optimization, the compiler will generate SIB addressing mode for global
array and PC-relative addressing mode for global variable,
e.g. "1@-96(%rbp,%rax,8)" and "-1@4+t1(%rip)".

In this patch:
- add usdt_o2 test case to cover SIB addressing usdt argument spec
  handling logic

Signed-off-by: Jiawei Zhao <phoenix500526@163.com>
---
 tools/testing/selftests/bpf/Makefile          |  8 +++
 .../selftests/bpf/prog_tests/usdt_o2.c        | 71 +++++++++++++++++++
 .../selftests/bpf/progs/test_usdt_o2.c        | 37 ++++++++++
 3 files changed, 116 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/usdt_o2.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_usdt_o2.c

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 910d8d6402ef..68cf6a9cf05f 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -759,6 +759,14 @@ TRUNNER_BPF_BUILD_RULE := $$(error no BPF objects should be built)
 TRUNNER_BPF_CFLAGS :=
 $(eval $(call DEFINE_TEST_RUNNER,test_maps))
 
+# Use -O2 optimization to generate SIB addressing usdt argument spec
+# Only apply on x86 architecture where SIB addressing is relevant
+ifeq ($(ARCH), x86)
+$(OUTPUT)/usdt_o2.test.o: CFLAGS:=$(subst O0,O2,$(CFLAGS))
+$(OUTPUT)/cpuv4/usdt_o2.test.o: CFLAGS:=$(subst O0,O2,$(CFLAGS))
+$(OUTPUT)/no_alu32/usdt_o2.test.o: CFLAGS:=$(subst O0,O2,$(CFLAGS))
+endif
+
 # Define test_verifier test runner.
 # It is much simpler than test_maps/test_progs and sufficiently different from
 # them (e.g., test.h is using completely pattern), that it's worth just
diff --git a/tools/testing/selftests/bpf/prog_tests/usdt_o2.c b/tools/testing/selftests/bpf/prog_tests/usdt_o2.c
new file mode 100644
index 000000000000..f04b756b3640
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/usdt_o2.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Jiawei Zhao <phoenix500526@163.com>. */
+#include <test_progs.h>
+
+#define _SDT_HAS_SEMAPHORES 1
+#include "../sdt.h"
+#include "test_usdt_o2.skel.h"
+
+int lets_test_this(int);
+
+#define test_value 0xFEDCBA9876543210ULL
+#define SEC(name) __attribute__((section(name), used))
+
+
+static volatile __u64 array[1] = {test_value};
+unsigned short test_usdt1_semaphore SEC(".probes");
+
+static __always_inline void trigger_func(void)
+{
+	/* Base address + offset + (index * scale) */
+	if (test_usdt1_semaphore) {
+		for (volatile int i = 0; i <= 0; i++)
+			STAP_PROBE1(test, usdt1, array[i]);
+	}
+}
+
+static void basic_sib_usdt(void)
+{
+	LIBBPF_OPTS(bpf_usdt_opts, opts);
+	struct test_usdt_o2 *skel;
+	struct test_usdt_o2__bss *bss;
+	int err;
+
+	skel = test_usdt_o2__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	bss = skel->bss;
+	bss->my_pid = getpid();
+
+	err = test_usdt_o2__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	/* usdt1 won't be auto-attached */
+	opts.usdt_cookie = 0xcafedeadbeeffeed;
+	skel->links.usdt1 = bpf_program__attach_usdt(skel->progs.usdt1,
+						     0 /*self*/, "/proc/self/exe",
+						     "test", "usdt1", &opts);
+	if (!ASSERT_OK_PTR(skel->links.usdt1, "usdt1_link"))
+		goto cleanup;
+
+	trigger_func();
+
+	ASSERT_EQ(bss->usdt1_called, 1, "usdt1_called");
+	ASSERT_EQ(bss->usdt1_cookie, 0xcafedeadbeeffeed, "usdt1_cookie");
+	ASSERT_EQ(bss->usdt1_arg_cnt, 1, "usdt1_arg_cnt");
+	ASSERT_EQ(bss->usdt1_arg, test_value, "usdt1_arg");
+	ASSERT_EQ(bss->usdt1_arg_ret, 0, "usdt1_arg_ret");
+	ASSERT_EQ(bss->usdt1_arg_size, sizeof(array[0]), "usdt1_arg_size");
+
+cleanup:
+	test_usdt_o2__destroy(skel);
+}
+
+
+
+void test_usdt_o2(void)
+{
+	basic_sib_usdt();
+}
diff --git a/tools/testing/selftests/bpf/progs/test_usdt_o2.c b/tools/testing/selftests/bpf/progs/test_usdt_o2.c
new file mode 100644
index 000000000000..14602aa54578
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_usdt_o2.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/usdt.bpf.h>
+
+int my_pid;
+
+int usdt1_called;
+u64 usdt1_cookie;
+int usdt1_arg_cnt;
+int usdt1_arg_ret;
+u64 usdt1_arg;
+int usdt1_arg_size;
+
+SEC("usdt")
+int usdt1(struct pt_regs *ctx)
+{
+	long tmp;
+
+	if (my_pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	__sync_fetch_and_add(&usdt1_called, 1);
+
+	usdt1_cookie = bpf_usdt_cookie(ctx);
+	usdt1_arg_cnt = bpf_usdt_arg_cnt(ctx);
+
+	usdt1_arg_ret = bpf_usdt_arg(ctx, 0, &tmp);
+	usdt1_arg = (u64)tmp;
+	usdt1_arg_size = bpf_usdt_arg_size(ctx, 0);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
2.43.0

On Wed, Aug 6, 2025 at 7:35 PM Jiawei Zhao <phoenix500526@163.com> wrote:
>
> When using GCC on x86-64 to compile an usdt prog with -O1 or higher
> optimization, the compiler will generate SIB addressing mode for global
> array and PC-relative addressing mode for global variable,
> e.g. "1@-96(%rbp,%rax,8)" and "-1@4+t1(%rip)".
>
> In this patch:
> - add usdt_o2 test case to cover SIB addressing usdt argument spec
>   handling logic
>
> Signed-off-by: Jiawei Zhao <phoenix500526@163.com>
> ---
>  tools/testing/selftests/bpf/Makefile          |  8 +++
>  .../selftests/bpf/prog_tests/usdt_o2.c        | 71 +++++++++++++++++++
>  .../selftests/bpf/progs/test_usdt_o2.c        | 37 ++++++++++
>  3 files changed, 116 insertions(+)
>  create mode 100644 tools/testing/selftests/bpf/prog_tests/usdt_o2.c
>  create mode 100644 tools/testing/selftests/bpf/progs/test_usdt_o2.c
>
> diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
> index 910d8d6402ef..68cf6a9cf05f 100644
> --- a/tools/testing/selftests/bpf/Makefile
> +++ b/tools/testing/selftests/bpf/Makefile
> @@ -759,6 +759,14 @@ TRUNNER_BPF_BUILD_RULE := $$(error no BPF objects should be built)
>  TRUNNER_BPF_CFLAGS :=
>  $(eval $(call DEFINE_TEST_RUNNER,test_maps))
>
> +# Use -O2 optimization to generate SIB addressing usdt argument spec
> +# Only apply on x86 architecture where SIB addressing is relevant
> +ifeq ($(ARCH), x86)
> +$(OUTPUT)/usdt_o2.test.o: CFLAGS:=$(subst O0,O2,$(CFLAGS))
> +$(OUTPUT)/cpuv4/usdt_o2.test.o: CFLAGS:=$(subst O0,O2,$(CFLAGS))
> +$(OUTPUT)/no_alu32/usdt_o2.test.o: CFLAGS:=$(subst O0,O2,$(CFLAGS))
> +endif
> +

Have you considered using GCC's __attribute__((optimize("O2")))
attribute. It seems like Clang doesn't have support for something like
that, but we'll still have this covered in BPF CI for GCC-built
selftests. Then I'd just add this as another subtest to existing usdt
tests.

Can you please try that?

>  # Define test_verifier test runner.
>  # It is much simpler than test_maps/test_progs and sufficiently different from
>  # them (e.g., test.h is using completely pattern), that it's worth just
> diff --git a/tools/testing/selftests/bpf/prog_tests/usdt_o2.c b/tools/testing/selftests/bpf/prog_tests/usdt_o2.c
> new file mode 100644
> index 000000000000..f04b756b3640
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/prog_tests/usdt_o2.c
> @@ -0,0 +1,71 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/* Copyright (c) 2025 Jiawei Zhao <phoenix500526@163.com>. */
> +#include <test_progs.h>
> +
> +#define _SDT_HAS_SEMAPHORES 1
> +#include "../sdt.h"
> +#include "test_usdt_o2.skel.h"
> +
> +int lets_test_this(int);
> +
> +#define test_value 0xFEDCBA9876543210ULL
> +#define SEC(name) __attribute__((section(name), used))
> +
> +
> +static volatile __u64 array[1] = {test_value};
> +unsigned short test_usdt1_semaphore SEC(".probes");
> +

Is semaphore essential to this test?

> +static __always_inline void trigger_func(void)
> +{
> +       /* Base address + offset + (index * scale) */
> +       if (test_usdt1_semaphore) {
> +               for (volatile int i = 0; i <= 0; i++)
> +                       STAP_PROBE1(test, usdt1, array[i]);
> +       }
> +}
> +

[...]

>Have you considered using GCC's __attribute__((optimize("O2")))
>attribute. It seems like Clang doesn't have support for something like
>that, but we'll still have this covered in BPF CI for GCC-built
>selftests. Then I'd just add this as another subtest to existing usdt
>tests.
>
>Can you please try that?

Done


>Is semaphore essential to this test?


It's no essential. I've already removed it in the new patch. 



At 2025-08-14 08:04:35, "Andrii Nakryiko" <andrii.nakryiko@gmail.com> wrote:
>On Wed, Aug 6, 2025 at 7:35 PM Jiawei Zhao <phoenix500526@163.com> wrote:
>>
>> When using GCC on x86-64 to compile an usdt prog with -O1 or higher
>> optimization, the compiler will generate SIB addressing mode for global
>> array and PC-relative addressing mode for global variable,
>> e.g. "1@-96(%rbp,%rax,8)" and "-1@4+t1(%rip)".
>>
>> In this patch:
>> - add usdt_o2 test case to cover SIB addressing usdt argument spec
>>   handling logic
>>
>> Signed-off-by: Jiawei Zhao <phoenix500526@163.com>
>> ---
>>  tools/testing/selftests/bpf/Makefile          |  8 +++
>>  .../selftests/bpf/prog_tests/usdt_o2.c        | 71 +++++++++++++++++++
>>  .../selftests/bpf/progs/test_usdt_o2.c        | 37 ++++++++++
>>  3 files changed, 116 insertions(+)
>>  create mode 100644 tools/testing/selftests/bpf/prog_tests/usdt_o2.c
>>  create mode 100644 tools/testing/selftests/bpf/progs/test_usdt_o2.c
>>
>> diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
>> index 910d8d6402ef..68cf6a9cf05f 100644
>> --- a/tools/testing/selftests/bpf/Makefile
>> +++ b/tools/testing/selftests/bpf/Makefile
>> @@ -759,6 +759,14 @@ TRUNNER_BPF_BUILD_RULE := $$(error no BPF objects should be built)
>>  TRUNNER_BPF_CFLAGS :=
>>  $(eval $(call DEFINE_TEST_RUNNER,test_maps))
>>
>> +# Use -O2 optimization to generate SIB addressing usdt argument spec
>> +# Only apply on x86 architecture where SIB addressing is relevant
>> +ifeq ($(ARCH), x86)
>> +$(OUTPUT)/usdt_o2.test.o: CFLAGS:=$(subst O0,O2,$(CFLAGS))
>> +$(OUTPUT)/cpuv4/usdt_o2.test.o: CFLAGS:=$(subst O0,O2,$(CFLAGS))
>> +$(OUTPUT)/no_alu32/usdt_o2.test.o: CFLAGS:=$(subst O0,O2,$(CFLAGS))
>> +endif
>> +
>
>Have you considered using GCC's __attribute__((optimize("O2")))
>attribute. It seems like Clang doesn't have support for something like
>that, but we'll still have this covered in BPF CI for GCC-built
>selftests. Then I'd just add this as another subtest to existing usdt
>tests.
>
>Can you please try that?
>
>>  # Define test_verifier test runner.
>>  # It is much simpler than test_maps/test_progs and sufficiently different from
>>  # them (e.g., test.h is using completely pattern), that it's worth just
>> diff --git a/tools/testing/selftests/bpf/prog_tests/usdt_o2.c b/tools/testing/selftests/bpf/prog_tests/usdt_o2.c
>> new file mode 100644
>> index 000000000000..f04b756b3640
>> --- /dev/null
>> +++ b/tools/testing/selftests/bpf/prog_tests/usdt_o2.c
>> @@ -0,0 +1,71 @@
>> +// SPDX-License-Identifier: GPL-2.0
>> +/* Copyright (c) 2025 Jiawei Zhao <phoenix500526@163.com>. */
>> +#include <test_progs.h>
>> +
>> +#define _SDT_HAS_SEMAPHORES 1
>> +#include "../sdt.h"
>> +#include "test_usdt_o2.skel.h"
>> +
>> +int lets_test_this(int);
>> +
>> +#define test_value 0xFEDCBA9876543210ULL
>> +#define SEC(name) __attribute__((section(name), used))
>> +
>> +
>> +static volatile __u64 array[1] = {test_value};
>> +unsigned short test_usdt1_semaphore SEC(".probes");
>> +
>
>Is semaphore essential to this test?
>
>> +static __always_inline void trigger_func(void)
>> +{
>> +       /* Base address + offset + (index * scale) */
>> +       if (test_usdt1_semaphore) {
>> +               for (volatile int i = 0; i <= 0; i++)
>> +                       STAP_PROBE1(test, usdt1, array[i]);
>> +       }
>> +}
>> +
>
>[...]