Merge branch 'libbpf-fix-usdt-sib-argument-handling-causing-unrecognized-register-error'

Jiawei Zhao says:

====================
libbpf: fix USDT SIB argument handling causing unrecognized register error

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, e.g. "1@-96(%rbp,%rax,8)".

The current USDT implementation in libbpf cannot parse these two formats,
causing `bpf_program__attach_usdt()` to fail with -ENOENT
(unrecognized register).

This patch series adds support for SIB addressing mode in USDT probes.
The main changes include:
- add correct handling logic for SIB-addressed arguments in
  `parse_usdt_arg`.
- add an usdt_o2 test case to cover SIB addressing mode.

Testing shows that the SIB probe correctly generates 8@(%rcx,%rax,8)
argument spec and passes all validation checks.

The modification history of this patch series:
Change since v1:
- refactor the code to make it more readable
- modify the commit message to explain why and how

Change since v2:
- fix the `scale` uninitialized error

Change since v3:
- force -O2 optimization for usdt.test.o to generate SIB addressing usdt
  and pass all test cases.

Change since v4:
- split the patch into two parts, one for the fix and the other for the
  test

Change since v5:
- Only enable optimization for x86 architecture to generate SIB addressing
  usdt argument spec.

Change since v6:
- Add an usdt_o2 test case to cover SIB addressing mode.
- Reinstate the usdt.c test case.

Change since v7:
- Refactor modifications to __bpf_usdt_arg_spec to avoid increasing its size,
  achieving better compatibility
- Fix some minor code style issues
- Refactor the usdt_o2 test case, removing semaphore and adding GCC attribute
  to force -O2 optimization

Change since v8:
- Refactor the usdt_o2 test case, using assembly to force SIB addressing mode.

Change since v9:
- Only enable the usdt_o2 test case on x86_64 and i386 architectures since the
  SIB addressing mode is only supported on x86_64 and i386.

Change since v10:
- Replace `__attribute__((optimize("O2")))` with `#pragma GCC optimize("O1")`
  to fix the issue where the optimized compilation condition works improperly.
- Renamed test case usdt_o2 and relevant files name to usdt_o1 in that O1
  level optimization is enough to generate SIB addressing usdt argument spec.

Change since v11:
- Replace `STAP_PROBE1` with `STAP_PROBE_ASM`
- Use bit fields instead of bit shifting operations
- Merge the usdt_o1 test case into the usdt test case

Change since v12:
- This patch is same with the v12 but with a new version number.

Change since v13(resolve some review comments):
- https://lore.kernel.org/bpf/CAEf4BzZWd2zUC=U6uGJFF3EMZ7zWGLweQAG3CJWTeHy-5yFEPw@mail.gmail.com/
- https://lore.kernel.org/bpf/CAEf4Bzbs3hV_Q47+d93tTX13WkrpkpOb4=U04mZCjHyZg4aVdw@mail.gmail.com/

Change since v14:
- fix a typo in __bpf_usdt_arg_spec

Change since v15(resolve some review comments):
- https://lore.kernel.org/bpf/CAEf4BzaxuYijEfQMDFZ+CQdjxLuDZiesUXNA-SiopS+5+VxRaA@mail.gmail.com/
- https://lore.kernel.org/bpf/CAEf4BzaHi5kpuJ6OVvDU62LT5g0qHbWYMfb_FBQ3iuvvUF9fag@mail.gmail.com/
- https://lore.kernel.org/bpf/d438bf3a-a9c9-4d34-b814-63f2e9bb3a85@linux.dev/
====================

Link: https://patch.msgid.link/20250827053128.1301287-1-phoenix500526@163.com
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>

2 files changed, 112 insertions, 2 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/usdt.c b/tools/testing/selftests/bpf/prog_tests/usdt.c
index 9057e983cc54..615e9c3e93bf 100644
--- a/tools/testing/selftests/bpf/prog_tests/usdt.c
+++ b/tools/testing/selftests/bpf/prog_tests/usdt.c
@@ -40,12 +40,72 @@ static void __always_inline trigger_func(int x) {
 	}
 }
 
+#if defined(__x86_64__) || defined(__i386__)
+/*
+ * SIB (Scale-Index-Base) addressing format: "size@(base_reg, index_reg, scale)"
+ * - 'size' is the size in bytes of the array element, and its sign indicates
+ *   whether the type is signed (negative) or unsigned (positive).
+ * - 'base_reg' is the register holding the base address, normally rdx or edx
+ * - 'index_reg' is the register holding the index, normally rax or eax
+ * - 'scale' is the scaling factor (typically 1, 2, 4, or 8), which matches the
+ *    size of the element type.
+ *
+ * For example, for an array of 'short' (signed 2-byte elements), the SIB spec would be:
+ * - size: -2 (negative because 'short' is signed)
+ * - scale: 2 (since sizeof(short) == 2)
+ *
+ * The resulting SIB format: "-2@(%%rdx,%%rax,2)" for x86_64, "-2@(%%edx,%%eax,2)" for i386
+ */
+static volatile short array[] = {-1, -2, -3, -4};
+
+#if defined(__x86_64__)
+#define USDT_SIB_ARG_SPEC -2@(%%rdx,%%rax,2)
+#else
+#define USDT_SIB_ARG_SPEC -2@(%%edx,%%eax,2)
+#endif
+
+unsigned short test_usdt_sib_semaphore SEC(".probes");
+
+static void trigger_sib_spec(void)
+{
+	/*
+	 * Force SIB addressing with inline assembly.
+	 *
+	 * You must compile with -std=gnu99 or -std=c99 to use the
+	 * STAP_PROBE_ASM macro.
+	 *
+	 * The STAP_PROBE_ASM macro generates a quoted string that gets
+	 * inserted between the surrounding assembly instructions. In this
+	 * case, USDT_SIB_ARG_SPEC is embedded directly into the instruction
+	 * stream, creating a probe point between the asm statement boundaries.
+	 * It works fine with gcc/clang.
+	 *
+	 * Register constraints:
+	 * - "d"(array): Binds the 'array' variable to %rdx or %edx register
+	 * - "a"(0): Binds the constant 0 to %rax or %eax register
+	 * These ensure that when USDT_SIB_ARG_SPEC references %%rdx(%edx) and
+	 * %%rax(%eax), they contain the expected values for SIB addressing.
+	 *
+	 * The "memory" clobber prevents the compiler from reordering memory
+	 * accesses around the probe point, ensuring that the probe behavior
+	 * is predictable and consistent.
+	 */
+	asm volatile(
+		STAP_PROBE_ASM(test, usdt_sib, USDT_SIB_ARG_SPEC)
+		:
+		: "d"(array), "a"(0)
+		: "memory"
+	);
+}
+#endif
+
 static void subtest_basic_usdt(void)
 {
 	LIBBPF_OPTS(bpf_usdt_opts, opts);
 	struct test_usdt *skel;
 	struct test_usdt__bss *bss;
 	int err, i;
+	const __u64 expected_cookie = 0xcafedeadbeeffeed;
 
 	skel = test_usdt__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "skel_open"))
@@ -59,20 +119,29 @@ static void subtest_basic_usdt(void)
 		goto cleanup;
 
 	/* usdt0 won't be auto-attached */
-	opts.usdt_cookie = 0xcafedeadbeeffeed;
+	opts.usdt_cookie = expected_cookie;
 	skel->links.usdt0 = bpf_program__attach_usdt(skel->progs.usdt0,
 						     0 /*self*/, "/proc/self/exe",
 						     "test", "usdt0", &opts);
 	if (!ASSERT_OK_PTR(skel->links.usdt0, "usdt0_link"))
 		goto cleanup;
 
+#if defined(__x86_64__) || defined(__i386__)
+	opts.usdt_cookie = expected_cookie;
+	skel->links.usdt_sib = bpf_program__attach_usdt(skel->progs.usdt_sib,
+							 0 /*self*/, "/proc/self/exe",
+							 "test", "usdt_sib", &opts);
+	if (!ASSERT_OK_PTR(skel->links.usdt_sib, "usdt_sib_link"))
+		goto cleanup;
+#endif
+
 	trigger_func(1);
 
 	ASSERT_EQ(bss->usdt0_called, 1, "usdt0_called");
 	ASSERT_EQ(bss->usdt3_called, 1, "usdt3_called");
 	ASSERT_EQ(bss->usdt12_called, 1, "usdt12_called");
 
-	ASSERT_EQ(bss->usdt0_cookie, 0xcafedeadbeeffeed, "usdt0_cookie");
+	ASSERT_EQ(bss->usdt0_cookie, expected_cookie, "usdt0_cookie");
 	ASSERT_EQ(bss->usdt0_arg_cnt, 0, "usdt0_arg_cnt");
 	ASSERT_EQ(bss->usdt0_arg_ret, -ENOENT, "usdt0_arg_ret");
 	ASSERT_EQ(bss->usdt0_arg_size, -ENOENT, "usdt0_arg_size");
@@ -156,6 +225,16 @@ static void subtest_basic_usdt(void)
 	ASSERT_EQ(bss->usdt3_args[1], 42, "usdt3_arg2");
 	ASSERT_EQ(bss->usdt3_args[2], (uintptr_t)&bla, "usdt3_arg3");
 
+#if defined(__x86_64__) || defined(__i386__)
+	trigger_sib_spec();
+	ASSERT_EQ(bss->usdt_sib_called, 1, "usdt_sib_called");
+	ASSERT_EQ(bss->usdt_sib_cookie, expected_cookie, "usdt_sib_cookie");
+	ASSERT_EQ(bss->usdt_sib_arg_cnt, 1, "usdt_sib_arg_cnt");
+	ASSERT_EQ(bss->usdt_sib_arg, nums[0], "usdt_sib_arg");
+	ASSERT_EQ(bss->usdt_sib_arg_ret, 0, "usdt_sib_arg_ret");
+	ASSERT_EQ(bss->usdt_sib_arg_size, sizeof(nums[0]), "usdt_sib_arg_size");
+#endif
+
 cleanup:
 	test_usdt__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/progs/test_usdt.c b/tools/testing/selftests/bpf/progs/test_usdt.c
index 096488f47fbc..a78c87537b07 100644
--- a/tools/testing/selftests/bpf/progs/test_usdt.c
+++ b/tools/testing/selftests/bpf/progs/test_usdt.c
@@ -107,4 +107,35 @@ int BPF_USDT(usdt12, int a1, int a2, long a3, long a4, unsigned a5,
 	return 0;
 }
 
+int usdt_sib_called;
+u64 usdt_sib_cookie;
+int usdt_sib_arg_cnt;
+int usdt_sib_arg_ret;
+short usdt_sib_arg;
+int usdt_sib_arg_size;
+
+/*
+ * usdt_sib is only tested on x86-related architectures, so it requires
+ * manual attach since auto-attach will panic tests under other architectures
+ */
+SEC("usdt")
+int usdt_sib(struct pt_regs *ctx)
+{
+	long tmp;
+
+	if (my_pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	__sync_fetch_and_add(&usdt_sib_called, 1);
+
+	usdt_sib_cookie = bpf_usdt_cookie(ctx);
+	usdt_sib_arg_cnt = bpf_usdt_arg_cnt(ctx);
+
+	usdt_sib_arg_ret = bpf_usdt_arg(ctx, 0, &tmp);
+	usdt_sib_arg = (short)tmp;
+	usdt_sib_arg_size = bpf_usdt_arg_size(ctx, 0);
+
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";